diff options
Diffstat (limited to 'fs')
258 files changed, 2692 insertions, 2893 deletions
diff --git a/fs/9p/acl.c b/fs/9p/acl.c index 9da967f..eb3589e 100644 --- a/fs/9p/acl.c +++ b/fs/9p/acl.c @@ -93,7 +93,7 @@ static struct posix_acl *v9fs_get_cached_acl(struct inode *inode, int type) * instantiating the inode (v9fs_inode_from_fid) */ acl = get_cached_acl(inode, type); - BUG_ON(acl == ACL_NOT_CACHED); + BUG_ON(is_uncached_acl(acl)); return acl; } @@ -213,8 +213,8 @@ int v9fs_acl_mode(struct inode *dir, umode_t *modep, } static int v9fs_xattr_get_acl(const struct xattr_handler *handler, - struct dentry *dentry, const char *name, - void *buffer, size_t size) + struct dentry *dentry, struct inode *inode, + const char *name, void *buffer, size_t size) { struct v9fs_session_info *v9ses; struct posix_acl *acl; @@ -227,7 +227,7 @@ static int v9fs_xattr_get_acl(const struct xattr_handler *handler, if ((v9ses->flags & V9FS_ACCESS_MASK) != V9FS_ACCESS_CLIENT) return v9fs_xattr_get(dentry, handler->name, buffer, size); - acl = v9fs_get_cached_acl(d_inode(dentry), handler->flags); + acl = v9fs_get_cached_acl(inode, handler->flags); if (IS_ERR(acl)) return PTR_ERR(acl); if (acl == NULL) diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c index ac9225e..c37fb9c 100644 --- a/fs/9p/vfs_addr.c +++ b/fs/9p/vfs_addr.c @@ -245,9 +245,10 @@ static int v9fs_launder_page(struct page *page) * */ static ssize_t -v9fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t pos) +v9fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) { struct file *file = iocb->ki_filp; + loff_t pos = iocb->ki_pos; ssize_t n; int err = 0; if (iov_iter_rw(iter) == WRITE) { diff --git a/fs/9p/vfs_dir.c b/fs/9p/vfs_dir.c index 5cc00e5..b0405d6 100644 --- a/fs/9p/vfs_dir.c +++ b/fs/9p/vfs_dir.c @@ -246,7 +246,7 @@ int v9fs_dir_release(struct inode *inode, struct file *filp) const struct file_operations v9fs_dir_operations = { .read = generic_read_dir, .llseek = generic_file_llseek, - .iterate = v9fs_dir_readdir, + .iterate_shared = v9fs_dir_readdir, .open = v9fs_file_open, .release = v9fs_dir_release, }; @@ -254,7 +254,7 @@ const struct file_operations v9fs_dir_operations = { const struct file_operations v9fs_dir_operations_dotl = { .read = generic_read_dir, .llseek = generic_file_llseek, - .iterate = v9fs_dir_readdir_dotl, + .iterate_shared = v9fs_dir_readdir_dotl, .open = v9fs_file_open, .release = v9fs_dir_release, .fsync = v9fs_file_fsync_dotl, diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index 3a08b3e..f4645c5 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -1071,7 +1071,7 @@ v9fs_vfs_getattr(struct vfsmount *mnt, struct dentry *dentry, if (IS_ERR(st)) return PTR_ERR(st); - v9fs_stat2inode(st, d_inode(dentry), d_inode(dentry)->i_sb); + v9fs_stat2inode(st, d_inode(dentry), dentry->d_sb); generic_fillattr(d_inode(dentry), stat); p9stat_free(st); diff --git a/fs/9p/xattr.c b/fs/9p/xattr.c index 9dd9b47..18c62ba 100644 --- a/fs/9p/xattr.c +++ b/fs/9p/xattr.c @@ -138,8 +138,8 @@ ssize_t v9fs_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size) } static int v9fs_xattr_handler_get(const struct xattr_handler *handler, - struct dentry *dentry, const char *name, - void *buffer, size_t size) + struct dentry *dentry, struct inode *inode, + const char *name, void *buffer, size_t size) { const char *full_name = xattr_full_name(handler, name); diff --git a/fs/affs/dir.c b/fs/affs/dir.c index ac4f318..f1e7294 100644 --- a/fs/affs/dir.c +++ b/fs/affs/dir.c @@ -20,7 +20,7 @@ static int affs_readdir(struct file *, struct dir_context *); const struct file_operations affs_dir_operations = { .read = generic_read_dir, .llseek = generic_file_llseek, - .iterate = affs_readdir, + .iterate_shared = affs_readdir, .fsync = affs_file_fsync, }; diff --git a/fs/affs/file.c b/fs/affs/file.c index 0cde550..0deec9c 100644 --- a/fs/affs/file.c +++ b/fs/affs/file.c @@ -389,12 +389,13 @@ static void affs_write_failed(struct address_space *mapping, loff_t to) } static ssize_t -affs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset) +affs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; size_t count = iov_iter_count(iter); + loff_t offset = iocb->ki_pos; ssize_t ret; if (iov_iter_rw(iter) == WRITE) { @@ -404,7 +405,7 @@ affs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset) return 0; } - ret = blockdev_direct_IO(iocb, inode, iter, offset, affs_get_block); + ret = blockdev_direct_IO(iocb, inode, iter, affs_get_block); if (ret < 0 && iov_iter_rw(iter) == WRITE) affs_write_failed(mapping, offset + count); return ret; diff --git a/fs/afs/dir.c b/fs/afs/dir.c index 5fda2bc..eba5410 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -43,7 +43,7 @@ static int afs_rename(struct inode *old_dir, struct dentry *old_dentry, const struct file_operations afs_dir_file_operations = { .open = afs_dir_open, .release = afs_release, - .iterate = afs_readdir, + .iterate_shared = afs_readdir, .lock = afs_lock, .llseek = generic_file_llseek, }; @@ -128,7 +128,7 @@ struct afs_lookup_cookie { /* * check that a directory page is valid */ -static inline void afs_dir_check_page(struct inode *dir, struct page *page) +static inline bool afs_dir_check_page(struct inode *dir, struct page *page) { struct afs_dir_page *dbuf; loff_t latter; @@ -168,11 +168,11 @@ static inline void afs_dir_check_page(struct inode *dir, struct page *page) } SetPageChecked(page); - return; + return true; error: - SetPageChecked(page); SetPageError(page); + return false; } /* @@ -196,10 +196,10 @@ static struct page *afs_dir_get_page(struct inode *dir, unsigned long index, page = read_cache_page(dir->i_mapping, index, afs_page_filler, key); if (!IS_ERR(page)) { kmap(page); - if (!PageChecked(page)) - afs_dir_check_page(dir, page); - if (PageError(page)) - goto fail; + if (unlikely(!PageChecked(page))) { + if (PageError(page) || !afs_dir_check_page(dir, page)) + goto fail; + } } return page; diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c index b506428..63cd9f9 100644 --- a/fs/afs/rxrpc.c +++ b/fs/afs/rxrpc.c @@ -65,6 +65,12 @@ static void afs_async_workfn(struct work_struct *work) call->async_workfn(call); } +static int afs_wait_atomic_t(atomic_t *p) +{ + schedule(); + return 0; +} + /* * open an RxRPC socket and bind it to be a server for callback notifications * - the socket is left in blocking mode and non-blocking ops use MSG_DONTWAIT @@ -126,13 +132,16 @@ void afs_close_socket(void) { _enter(""); + wait_on_atomic_t(&afs_outstanding_calls, afs_wait_atomic_t, + TASK_UNINTERRUPTIBLE); + _debug("no outstanding calls"); + sock_release(afs_socket); _debug("dework"); destroy_workqueue(afs_async_calls); ASSERTCMP(atomic_read(&afs_outstanding_skbs), ==, 0); - ASSERTCMP(atomic_read(&afs_outstanding_calls), ==, 0); _leave(""); } @@ -178,8 +187,6 @@ static void afs_free_call(struct afs_call *call) { _debug("DONE %p{%s} [%d]", call, call->type->name, atomic_read(&afs_outstanding_calls)); - if (atomic_dec_return(&afs_outstanding_calls) == -1) - BUG(); ASSERTCMP(call->rxcall, ==, NULL); ASSERT(!work_pending(&call->async_work)); @@ -188,6 +195,9 @@ static void afs_free_call(struct afs_call *call) kfree(call->request); kfree(call); + + if (atomic_dec_and_test(&afs_outstanding_calls)) + wake_up_atomic_t(&afs_outstanding_calls); } /* @@ -420,9 +430,11 @@ error_kill_call: } /* - * handles intercepted messages that were arriving in the socket's Rx queue - * - called with the socket receive queue lock held to ensure message ordering - * - called with softirqs disabled + * Handles intercepted messages that were arriving in the socket's Rx queue. + * + * Called from the AF_RXRPC call processor in waitqueue process context. For + * each call, it is guaranteed this will be called in order of packet to be + * delivered. */ static void afs_rx_interceptor(struct sock *sk, unsigned long user_call_ID, struct sk_buff *skb) @@ -513,6 +525,12 @@ static void afs_deliver_to_call(struct afs_call *call) call->state = AFS_CALL_ABORTED; _debug("Rcv ABORT %u -> %d", abort_code, call->error); break; + case RXRPC_SKB_MARK_LOCAL_ABORT: + abort_code = rxrpc_kernel_get_abort_code(skb); + call->error = call->type->abort_to_error(abort_code); + call->state = AFS_CALL_ABORTED; + _debug("Loc ABORT %u -> %d", abort_code, call->error); + break; case RXRPC_SKB_MARK_NET_ERROR: call->error = -rxrpc_kernel_get_error_number(skb); call->state = AFS_CALL_ERROR; @@ -1447,8 +1447,6 @@ rw_common: return ret; } - len = ret; - if (rw == WRITE) file_start_write(file); diff --git a/fs/autofs4/root.c b/fs/autofs4/root.c index 7ab9239..78bd802 100644 --- a/fs/autofs4/root.c +++ b/fs/autofs4/root.c @@ -39,7 +39,7 @@ const struct file_operations autofs4_root_operations = { .open = dcache_dir_open, .release = dcache_dir_close, .read = generic_read_dir, - .iterate = dcache_readdir, + .iterate_shared = dcache_readdir, .llseek = dcache_dir_lseek, .unlocked_ioctl = autofs4_root_ioctl, #ifdef CONFIG_COMPAT @@ -51,7 +51,7 @@ const struct file_operations autofs4_dir_operations = { .open = autofs4_dir_open, .release = dcache_dir_close, .read = generic_read_dir, - .iterate = dcache_readdir, + .iterate_shared = dcache_readdir, .llseek = dcache_dir_lseek, }; diff --git a/fs/bad_inode.c b/fs/bad_inode.c index 103f5d7..72e35b7 100644 --- a/fs/bad_inode.c +++ b/fs/bad_inode.c @@ -106,8 +106,8 @@ static int bad_inode_setxattr(struct dentry *dentry, const char *name, return -EIO; } -static ssize_t bad_inode_getxattr(struct dentry *dentry, const char *name, - void *buffer, size_t size) +static ssize_t bad_inode_getxattr(struct dentry *dentry, struct inode *inode, + const char *name, void *buffer, size_t size) { return -EIO; } diff --git a/fs/befs/befs.h b/fs/befs/befs.h index 35d19e8..e0f59263a 100644 --- a/fs/befs/befs.h +++ b/fs/befs/befs.h @@ -116,7 +116,7 @@ BEFS_I(const struct inode *inode) } static inline befs_blocknr_t -iaddr2blockno(struct super_block *sb, befs_inode_addr * iaddr) +iaddr2blockno(struct super_block *sb, const befs_inode_addr *iaddr) { return ((iaddr->allocation_group << BEFS_SB(sb)->ag_shift) + iaddr->start); @@ -141,7 +141,7 @@ befs_iaddrs_per_block(struct super_block *sb) } static inline int -befs_iaddr_is_empty(befs_inode_addr * iaddr) +befs_iaddr_is_empty(const befs_inode_addr *iaddr) { return (!iaddr->allocation_group) && (!iaddr->start) && (!iaddr->len); } diff --git a/fs/befs/btree.c b/fs/befs/btree.c index 22c16628..307645f9 100644 --- a/fs/befs/btree.c +++ b/fs/befs/btree.c @@ -88,15 +88,15 @@ struct befs_btree_node { static const befs_off_t befs_bt_inval = 0xffffffffffffffffULL; /* local functions */ -static int befs_btree_seekleaf(struct super_block *sb, befs_data_stream * ds, +static int befs_btree_seekleaf(struct super_block *sb, const befs_data_stream *ds, befs_btree_super * bt_super, struct befs_btree_node *this_node, befs_off_t * node_off); -static int befs_bt_read_super(struct super_block *sb, befs_data_stream * ds, +static int befs_bt_read_super(struct super_block *sb, const befs_data_stream *ds, befs_btree_super * sup); -static int befs_bt_read_node(struct super_block *sb, befs_data_stream * ds, +static int befs_bt_read_node(struct super_block *sb, const befs_data_stream *ds, struct befs_btree_node *node, befs_off_t node_off); @@ -134,7 +134,7 @@ static int befs_compare_strings(const void *key1, int keylen1, * On failure, BEFS_ERR is returned. */ static int -befs_bt_read_super(struct super_block *sb, befs_data_stream * ds, +befs_bt_read_super(struct super_block *sb, const befs_data_stream *ds, befs_btree_super * sup) { struct buffer_head *bh; @@ -193,7 +193,7 @@ befs_bt_read_super(struct super_block *sb, befs_data_stream * ds, */ static int -befs_bt_read_node(struct super_block *sb, befs_data_stream * ds, +befs_bt_read_node(struct super_block *sb, const befs_data_stream *ds, struct befs_btree_node *node, befs_off_t node_off) { uint off = 0; @@ -247,7 +247,7 @@ befs_bt_read_node(struct super_block *sb, befs_data_stream * ds, * actuall value stored with the key. */ int -befs_btree_find(struct super_block *sb, befs_data_stream * ds, +befs_btree_find(struct super_block *sb, const befs_data_stream *ds, const char *key, befs_off_t * value) { struct befs_btree_node *this_node; @@ -416,7 +416,7 @@ befs_find_key(struct super_block *sb, struct befs_btree_node *node, * until the (key_no)th key is found or the tree is out of keys. */ int -befs_btree_read(struct super_block *sb, befs_data_stream * ds, +befs_btree_read(struct super_block *sb, const befs_data_stream *ds, loff_t key_no, size_t bufsize, char *keybuf, size_t * keysize, befs_off_t * value) { @@ -548,7 +548,7 @@ befs_btree_read(struct super_block *sb, befs_data_stream * ds, * Also checks for an empty tree. If there are no keys, returns BEFS_BT_EMPTY. */ static int -befs_btree_seekleaf(struct super_block *sb, befs_data_stream * ds, +befs_btree_seekleaf(struct super_block *sb, const befs_data_stream *ds, befs_btree_super *bt_super, struct befs_btree_node *this_node, befs_off_t * node_off) diff --git a/fs/befs/btree.h b/fs/befs/btree.h index 92e781e..f2a8f63 100644 --- a/fs/befs/btree.h +++ b/fs/befs/btree.h @@ -4,10 +4,10 @@ */ -int befs_btree_find(struct super_block *sb, befs_data_stream * ds, +int befs_btree_find(struct super_block *sb, const befs_data_stream *ds, const char *key, befs_off_t * value); -int befs_btree_read(struct super_block *sb, befs_data_stream * ds, +int befs_btree_read(struct super_block *sb, const befs_data_stream *ds, loff_t key_no, size_t bufsize, char *keybuf, size_t * keysize, befs_off_t * value); diff --git a/fs/befs/datastream.c b/fs/befs/datastream.c index ebd5071..dde0b79 100644 --- a/fs/befs/datastream.c +++ b/fs/befs/datastream.c @@ -21,16 +21,16 @@ const befs_inode_addr BAD_IADDR = { 0, 0, 0 }; static int befs_find_brun_direct(struct super_block *sb, - befs_data_stream * data, + const befs_data_stream *data, befs_blocknr_t blockno, befs_block_run * run); static int befs_find_brun_indirect(struct super_block *sb, - befs_data_stream * data, + const befs_data_stream *data, befs_blocknr_t blockno, befs_block_run * run); static int befs_find_brun_dblindirect(struct super_block *sb, - befs_data_stream * data, + const befs_data_stream *data, befs_blocknr_t blockno, befs_block_run * run); @@ -45,7 +45,7 @@ static int befs_find_brun_dblindirect(struct super_block *sb, * if you don't need to know offset just set @off = NULL. */ struct buffer_head * -befs_read_datastream(struct super_block *sb, befs_data_stream * ds, +befs_read_datastream(struct super_block *sb, const befs_data_stream *ds, befs_off_t pos, uint * off) { struct buffer_head *bh = NULL; @@ -87,7 +87,7 @@ befs_read_datastream(struct super_block *sb, befs_data_stream * ds, * 2001-11-15 Will Dyson */ int -befs_fblock2brun(struct super_block *sb, befs_data_stream * data, +befs_fblock2brun(struct super_block *sb, const befs_data_stream *data, befs_blocknr_t fblock, befs_block_run * run) { int err; @@ -122,8 +122,8 @@ befs_fblock2brun(struct super_block *sb, befs_data_stream * data, * Returns the number of bytes read */ size_t -befs_read_lsymlink(struct super_block * sb, befs_data_stream * ds, void *buff, - befs_off_t len) +befs_read_lsymlink(struct super_block *sb, const befs_data_stream *ds, + void *buff, befs_off_t len) { befs_off_t bytes_read = 0; /* bytes readed */ u16 plen; @@ -163,7 +163,7 @@ befs_read_lsymlink(struct super_block * sb, befs_data_stream * ds, void *buff, */ befs_blocknr_t -befs_count_blocks(struct super_block * sb, befs_data_stream * ds) +befs_count_blocks(struct super_block *sb, const befs_data_stream *ds) { befs_blocknr_t blocks; befs_blocknr_t datablocks; /* File data blocks */ @@ -243,11 +243,11 @@ befs_count_blocks(struct super_block * sb, befs_data_stream * ds) 2001-11-15 Will Dyson */ static int -befs_find_brun_direct(struct super_block *sb, befs_data_stream * data, +befs_find_brun_direct(struct super_block *sb, const befs_data_stream *data, befs_blocknr_t blockno, befs_block_run * run) { int i; - befs_block_run *array = data->direct; + const befs_block_run *array = data->direct; befs_blocknr_t sum; befs_blocknr_t max_block = data->max_direct_range >> BEFS_SB(sb)->block_shift; @@ -304,7 +304,8 @@ befs_find_brun_direct(struct super_block *sb, befs_data_stream * data, */ static int befs_find_brun_indirect(struct super_block *sb, - befs_data_stream * data, befs_blocknr_t blockno, + const befs_data_stream *data, + befs_blocknr_t blockno, befs_block_run * run) { int i, j; @@ -412,7 +413,8 @@ befs_find_brun_indirect(struct super_block *sb, */ static int befs_find_brun_dblindirect(struct super_block *sb, - befs_data_stream * data, befs_blocknr_t blockno, + const befs_data_stream *data, + befs_blocknr_t blockno, befs_block_run * run) { int dblindir_indx; diff --git a/fs/befs/datastream.h b/fs/befs/datastream.h index 45e8a3c..91ba820 100644 --- a/fs/befs/datastream.h +++ b/fs/befs/datastream.h @@ -4,16 +4,17 @@ */ struct buffer_head *befs_read_datastream(struct super_block *sb, - befs_data_stream * ds, befs_off_t pos, - uint * off); + const befs_data_stream *ds, + befs_off_t pos, uint * off); -int befs_fblock2brun(struct super_block *sb, befs_data_stream * data, +int befs_fblock2brun(struct super_block *sb, const befs_data_stream *data, befs_blocknr_t fblock, befs_block_run * run); -size_t befs_read_lsymlink(struct super_block *sb, befs_data_stream * data, +size_t befs_read_lsymlink(struct super_block *sb, const befs_data_stream *data, void *buff, befs_off_t len); -befs_blocknr_t befs_count_blocks(struct super_block *sb, befs_data_stream * ds); +befs_blocknr_t befs_count_blocks(struct super_block *sb, + const befs_data_stream *ds); extern const befs_inode_addr BAD_IADDR; diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c index cc0e082..71112aa 100644 --- a/fs/befs/linuxvfs.c +++ b/fs/befs/linuxvfs.c @@ -66,7 +66,7 @@ static struct kmem_cache *befs_inode_cachep; static const struct file_operations befs_dir_operations = { .read = generic_read_dir, - .iterate = befs_readdir, + .iterate_shared = befs_readdir, .llseek = generic_file_llseek, }; @@ -157,7 +157,7 @@ befs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { struct inode *inode = NULL; struct super_block *sb = dir->i_sb; - befs_data_stream *ds = &BEFS_I(dir)->i_data.ds; + const befs_data_stream *ds = &BEFS_I(dir)->i_data.ds; befs_off_t offset; int ret; int utfnamelen; @@ -207,7 +207,7 @@ befs_readdir(struct file *file, struct dir_context *ctx) { struct inode *inode = file_inode(file); struct super_block *sb = inode->i_sb; - befs_data_stream *ds = &BEFS_I(inode)->i_data.ds; + const befs_data_stream *ds = &BEFS_I(inode)->i_data.ds; befs_off_t value; int result; size_t keysize; diff --git a/fs/bfs/dir.c b/fs/bfs/dir.c index 3ec6113..34a5bc2 100644 --- a/fs/bfs/dir.c +++ b/fs/bfs/dir.c @@ -70,7 +70,7 @@ static int bfs_readdir(struct file *f, struct dir_context *ctx) const struct file_operations bfs_dir_operations = { .read = generic_read_dir, - .iterate = bfs_readdir, + .iterate_shared = bfs_readdir, .fsync = generic_file_fsync, .llseek = generic_file_llseek, }; diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 81381cc..56224ff 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -2273,7 +2273,7 @@ static int elf_core_dump(struct coredump_params *cprm) goto end_coredump; /* Align to page */ - if (!dump_skip(cprm, dataoff - cprm->written)) + if (!dump_skip(cprm, dataoff - cprm->file->f_pos)) goto end_coredump; for (i = 0, vma = first_vma(current, gate_vma); vma != NULL; diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c index 083ea2bc..71ade0e 100644 --- a/fs/binfmt_elf_fdpic.c +++ b/fs/binfmt_elf_fdpic.c @@ -1787,7 +1787,7 @@ static int elf_fdpic_core_dump(struct coredump_params *cprm) goto end_coredump; } - if (!dump_skip(cprm, dataoff - cprm->written)) + if (!dump_skip(cprm, dataoff - cprm->file->f_pos)) goto end_coredump; if (!elf_fdpic_dump_segments(cprm)) diff --git a/fs/block_dev.c b/fs/block_dev.c index 20a2c02..a063d4d 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -162,15 +162,15 @@ static struct inode *bdev_file_inode(struct file *file) } static ssize_t -blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset) +blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter) { struct file *file = iocb->ki_filp; struct inode *inode = bdev_file_inode(file); if (IS_DAX(inode)) - return dax_do_io(iocb, inode, iter, offset, blkdev_get_block, + return dax_do_io(iocb, inode, iter, blkdev_get_block, NULL, DIO_SKIP_DIO_COUNT); - return __blockdev_direct_IO(iocb, inode, I_BDEV(inode), iter, offset, + return __blockdev_direct_IO(iocb, inode, I_BDEV(inode), iter, blkdev_get_block, NULL, NULL, DIO_SKIP_DIO_COUNT); } @@ -1660,12 +1660,8 @@ ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from) blk_start_plug(&plug); ret = __generic_file_write_iter(iocb, from); - if (ret > 0) { - ssize_t err; - err = generic_write_sync(file, iocb->ki_pos - ret, ret); - if (err < 0) - ret = err; - } + if (ret > 0) + ret = generic_write_sync(iocb, ret); blk_finish_plug(&plug); return ret; } diff --git a/fs/btrfs/acl.c b/fs/btrfs/acl.c index 6d263bb..67a6077 100644 --- a/fs/btrfs/acl.c +++ b/fs/btrfs/acl.c @@ -63,9 +63,6 @@ struct posix_acl *btrfs_get_acl(struct inode *inode, int type) } kfree(value); - if (!IS_ERR(acl)) - set_cached_acl(inode, type, acl); - return acl; } diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 8d7b5a4..ea9f10b 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1703,18 +1703,17 @@ again: return num_written ? num_written : ret; } -static ssize_t __btrfs_direct_write(struct kiocb *iocb, - struct iov_iter *from, - loff_t pos) +static ssize_t __btrfs_direct_write(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct inode *inode = file_inode(file); + loff_t pos = iocb->ki_pos; ssize_t written; ssize_t written_buffered; loff_t endbyte; int err; - written = generic_file_direct_write(iocb, from, pos); + written = generic_file_direct_write(iocb, from); if (written < 0 || !iov_iter_count(from)) return written; @@ -1832,7 +1831,7 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb, atomic_inc(&BTRFS_I(inode)->sync_writers); if (iocb->ki_flags & IOCB_DIRECT) { - num_written = __btrfs_direct_write(iocb, from, pos); + num_written = __btrfs_direct_write(iocb, from); } else { num_written = __btrfs_buffered_write(file, from, pos); if (num_written > 0) @@ -1852,11 +1851,8 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb, spin_lock(&BTRFS_I(inode)->lock); BTRFS_I(inode)->last_sub_trans = root->log_transid; spin_unlock(&BTRFS_I(inode)->lock); - if (num_written > 0) { - err = generic_write_sync(file, pos, num_written); - if (err < 0) - num_written = err; - } + if (num_written > 0) + num_written = generic_write_sync(iocb, num_written); if (sync) atomic_dec(&BTRFS_I(inode)->sync_writers); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 2aaba58..6b7fe29 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -8541,13 +8541,13 @@ out: return retval; } -static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, - loff_t offset) +static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; struct btrfs_root *root = BTRFS_I(inode)->root; struct btrfs_dio_data dio_data = { 0 }; + loff_t offset = iocb->ki_pos; size_t count = 0; int flags = 0; bool wakeup = true; @@ -8607,7 +8607,7 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, ret = __blockdev_direct_IO(iocb, inode, BTRFS_I(inode)->root->fs_info->fs_devices->latest_bdev, - iter, offset, btrfs_get_blocks_direct, NULL, + iter, btrfs_get_blocks_direct, NULL, btrfs_submit_direct, flags); if (iov_iter_rw(iter) == WRITE) { current->journal_info = NULL; @@ -10160,10 +10160,10 @@ static const struct inode_operations btrfs_dir_inode_operations = { .symlink = btrfs_symlink, .setattr = btrfs_setattr, .mknod = btrfs_mknod, - .setxattr = btrfs_setxattr, + .setxattr = generic_setxattr, .getxattr = generic_getxattr, .listxattr = btrfs_listxattr, - .removexattr = btrfs_removexattr, + .removexattr = generic_removexattr, .permission = btrfs_permission, .get_acl = btrfs_get_acl, .set_acl = btrfs_set_acl, @@ -10237,10 +10237,10 @@ static const struct address_space_operations btrfs_symlink_aops = { static const struct inode_operations btrfs_file_inode_operations = { .getattr = btrfs_getattr, .setattr = btrfs_setattr, - .setxattr = btrfs_setxattr, + .setxattr = generic_setxattr, .getxattr = generic_getxattr, .listxattr = btrfs_listxattr, - .removexattr = btrfs_removexattr, + .removexattr = generic_removexattr, .permission = btrfs_permission, .fiemap = btrfs_fiemap, .get_acl = btrfs_get_acl, @@ -10251,10 +10251,10 @@ static const struct inode_operations btrfs_special_inode_operations = { .getattr = btrfs_getattr, .setattr = btrfs_setattr, .permission = btrfs_permission, - .setxattr = btrfs_setxattr, + .setxattr = generic_setxattr, .getxattr = generic_getxattr, .listxattr = btrfs_listxattr, - .removexattr = btrfs_removexattr, + .removexattr = generic_removexattr, .get_acl = btrfs_get_acl, .set_acl = btrfs_set_acl, .update_time = btrfs_update_time, @@ -10265,10 +10265,10 @@ static const struct inode_operations btrfs_symlink_inode_operations = { .getattr = btrfs_getattr, .setattr = btrfs_setattr, .permission = btrfs_permission, - .setxattr = btrfs_setxattr, + .setxattr = generic_setxattr, .getxattr = generic_getxattr, .listxattr = btrfs_listxattr, - .removexattr = btrfs_removexattr, + .removexattr = generic_removexattr, .update_time = btrfs_update_time, }; diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 5a23806..0b8ba71 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -837,9 +837,11 @@ static noinline int btrfs_mksubvol(struct path *parent, struct dentry *dentry; int error; - error = mutex_lock_killable_nested(&dir->i_mutex, I_MUTEX_PARENT); - if (error == -EINTR) - return error; + inode_lock_nested(dir, I_MUTEX_PARENT); + // XXX: should've been + // mutex_lock_killable_nested(&dir->i_mutex, I_MUTEX_PARENT); + // if (error == -EINTR) + // return error; dentry = lookup_one_len(name, parent->dentry, namelen); error = PTR_ERR(dentry); @@ -2366,9 +2368,11 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file, goto out; - err = mutex_lock_killable_nested(&dir->i_mutex, I_MUTEX_PARENT); - if (err == -EINTR) - goto out_drop_write; + inode_lock_nested(dir, I_MUTEX_PARENT); + // XXX: should've been + // err = mutex_lock_killable_nested(&dir->i_mutex, I_MUTEX_PARENT); + // if (err == -EINTR) + // goto out_drop_write; dentry = lookup_one_len(vol_args->name, parent, namelen); if (IS_ERR(dentry)) { err = PTR_ERR(dentry); @@ -2558,7 +2562,7 @@ out_dput: dput(dentry); out_unlock_dir: inode_unlock(dir); -out_drop_write: +//out_drop_write: mnt_drop_write_file(file); out: kfree(vol_args); diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 517d0cc..e692eea 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -4988,7 +4988,7 @@ static noinline int check_parent_dirs_for_sync(struct btrfs_trans_handle *trans, goto out; if (!S_ISDIR(inode->i_mode)) { - if (!parent || d_really_is_negative(parent) || sb != d_inode(parent)->i_sb) + if (!parent || d_really_is_negative(parent) || sb != parent->d_sb) goto out; inode = d_inode(parent); } @@ -5009,7 +5009,7 @@ static noinline int check_parent_dirs_for_sync(struct btrfs_trans_handle *trans, break; } - if (!parent || d_really_is_negative(parent) || sb != d_inode(parent)->i_sb) + if (!parent || d_really_is_negative(parent) || sb != parent->d_sb) break; if (IS_ROOT(parent)) @@ -5422,7 +5422,7 @@ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans, } while (1) { - if (!parent || d_really_is_negative(parent) || sb != d_inode(parent)->i_sb) + if (!parent || d_really_is_negative(parent) || sb != parent->d_sb) break; inode = d_inode(parent); diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c index 145d2b8..3bfb252 100644 --- a/fs/btrfs/xattr.c +++ b/fs/btrfs/xattr.c @@ -237,6 +237,9 @@ int __btrfs_setxattr(struct btrfs_trans_handle *trans, struct btrfs_root *root = BTRFS_I(inode)->root; int ret; + if (btrfs_root_readonly(root)) + return -EROFS; + if (trans) return do_setxattr(trans, inode, name, value, size, flags); @@ -369,11 +372,9 @@ err: } static int btrfs_xattr_handler_get(const struct xattr_handler *handler, - struct dentry *dentry, const char *name, - void *buffer, size_t size) + struct dentry *unused, struct inode *inode, + const char *name, void *buffer, size_t size) { - struct inode *inode = d_inode(dentry); - name = xattr_full_name(handler, name); return __btrfs_getxattr(inode, name, buffer, size); } @@ -434,25 +435,6 @@ const struct xattr_handler *btrfs_xattr_handlers[] = { NULL, }; -int btrfs_setxattr(struct dentry *dentry, const char *name, const void *value, - size_t size, int flags) -{ - struct btrfs_root *root = BTRFS_I(d_inode(dentry))->root; - - if (btrfs_root_readonly(root)) - return -EROFS; - return generic_setxattr(dentry, name, value, size, flags); -} - -int btrfs_removexattr(struct dentry *dentry, const char *name) -{ - struct btrfs_root *root = BTRFS_I(d_inode(dentry))->root; - - if (btrfs_root_readonly(root)) - return -EROFS; - return generic_removexattr(dentry, name); -} - static int btrfs_initxattrs(struct inode *inode, const struct xattr *xattr_array, void *fs_info) { diff --git a/fs/btrfs/xattr.h b/fs/btrfs/xattr.h index 96807b3..15fc474 100644 --- a/fs/btrfs/xattr.h +++ b/fs/btrfs/xattr.h @@ -28,9 +28,6 @@ extern ssize_t __btrfs_getxattr(struct inode *inode, const char *name, extern int __btrfs_setxattr(struct btrfs_trans_handle *trans, struct inode *inode, const char *name, const void *value, size_t size, int flags); -extern int btrfs_setxattr(struct dentry *dentry, const char *name, - const void *value, size_t size, int flags); -extern int btrfs_removexattr(struct dentry *dentry, const char *name); extern int btrfs_xattr_security_init(struct btrfs_trans_handle *trans, struct inode *inode, struct inode *dir, diff --git a/fs/ceph/acl.c b/fs/ceph/acl.c index f197084..4f67227 100644 --- a/fs/ceph/acl.c +++ b/fs/ceph/acl.c @@ -37,6 +37,8 @@ static inline void ceph_set_cached_acl(struct inode *inode, spin_lock(&ci->i_ceph_lock); if (__ceph_caps_issued_mask(ci, CEPH_CAP_XATTR_SHARED, 0)) set_cached_acl(inode, type, acl); + else + forget_cached_acl(inode, type); spin_unlock(&ci->i_ceph_lock); } @@ -88,7 +90,6 @@ int ceph_set_acl(struct inode *inode, struct posix_acl *acl, int type) char *value = NULL; struct iattr newattrs; umode_t new_mode = inode->i_mode, old_mode = inode->i_mode; - struct dentry *dentry; switch (type) { case ACL_TYPE_ACCESS: @@ -126,29 +127,26 @@ int ceph_set_acl(struct inode *inode, struct posix_acl *acl, int type) goto out_free; } - dentry = d_find_alias(inode); if (new_mode != old_mode) { newattrs.ia_mode = new_mode; newattrs.ia_valid = ATTR_MODE; - ret = ceph_setattr(dentry, &newattrs); + ret = __ceph_setattr(inode, &newattrs); if (ret) - goto out_dput; + goto out_free; } - ret = __ceph_setxattr(dentry, name, value, size, 0); + ret = __ceph_setxattr(inode, name, value, size, 0); if (ret) { if (new_mode != old_mode) { newattrs.ia_mode = old_mode; newattrs.ia_valid = ATTR_MODE; - ceph_setattr(dentry, &newattrs); + __ceph_setattr(inode, &newattrs); } - goto out_dput; + goto out_free; } ceph_set_cached_acl(inode, type, acl); -out_dput: - dput(dentry); out_free: kfree(value); out: diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 4801571..43098cd 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -1292,8 +1292,7 @@ static int ceph_write_end(struct file *file, struct address_space *mapping, * intercept O_DIRECT reads and writes early, this function should * never get called. */ -static ssize_t ceph_direct_io(struct kiocb *iocb, struct iov_iter *iter, - loff_t pos) +static ssize_t ceph_direct_io(struct kiocb *iocb, struct iov_iter *iter) { WARN_ON(1); return -EINVAL; diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index 4fb2bbc..3ab1192 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -5,6 +5,7 @@ #include <linux/namei.h> #include <linux/slab.h> #include <linux/sched.h> +#include <linux/xattr.h> #include "super.h" #include "mds_client.h" @@ -1342,10 +1343,10 @@ const struct inode_operations ceph_dir_iops = { .permission = ceph_permission, .getattr = ceph_getattr, .setattr = ceph_setattr, - .setxattr = ceph_setxattr, - .getxattr = ceph_getxattr, + .setxattr = generic_setxattr, + .getxattr = generic_getxattr, .listxattr = ceph_listxattr, - .removexattr = ceph_removexattr, + .removexattr = generic_removexattr, .get_acl = ceph_get_acl, .set_acl = ceph_set_acl, .mknod = ceph_mknod, diff --git a/fs/ceph/file.c b/fs/ceph/file.c index a79f926..4f1dc71 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -1382,12 +1382,11 @@ retry_snap: ceph_cap_string(got)); ceph_put_cap_refs(ci, got); - if (written >= 0 && - ((file->f_flags & O_SYNC) || IS_SYNC(file->f_mapping->host) || - ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_NEARFULL))) { - err = vfs_fsync_range(file, pos, pos + written - 1, 1); - if (err < 0) - written = err; + if (written >= 0) { + if (ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_NEARFULL)) + iocb->ki_flags |= IOCB_DSYNC; + + written = generic_write_sync(iocb, written); } goto out_unlocked; diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index edfade0..e669cfa 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -8,6 +8,7 @@ #include <linux/kernel.h> #include <linux/writeback.h> #include <linux/vmalloc.h> +#include <linux/xattr.h> #include <linux/posix_acl.h> #include <linux/random.h> @@ -92,10 +93,10 @@ const struct inode_operations ceph_file_iops = { .permission = ceph_permission, .setattr = ceph_setattr, .getattr = ceph_getattr, - .setxattr = ceph_setxattr, - .getxattr = ceph_getxattr, + .setxattr = generic_setxattr, + .getxattr = generic_getxattr, .listxattr = ceph_listxattr, - .removexattr = ceph_removexattr, + .removexattr = generic_removexattr, .get_acl = ceph_get_acl, .set_acl = ceph_set_acl, }; @@ -1770,22 +1771,18 @@ static const struct inode_operations ceph_symlink_iops = { .get_link = simple_get_link, .setattr = ceph_setattr, .getattr = ceph_getattr, - .setxattr = ceph_setxattr, - .getxattr = ceph_getxattr, + .setxattr = generic_setxattr, + .getxattr = generic_getxattr, .listxattr = ceph_listxattr, - .removexattr = ceph_removexattr, + .removexattr = generic_removexattr, }; -/* - * setattr - */ -int ceph_setattr(struct dentry *dentry, struct iattr *attr) +int __ceph_setattr(struct inode *inode, struct iattr *attr) { - struct inode *inode = d_inode(dentry); struct ceph_inode_info *ci = ceph_inode(inode); const unsigned int ia_valid = attr->ia_valid; struct ceph_mds_request *req; - struct ceph_mds_client *mdsc = ceph_sb_to_client(dentry->d_sb)->mdsc; + struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc; struct ceph_cap_flush *prealloc_cf; int issued; int release = 0, dirtied = 0; @@ -2010,6 +2007,14 @@ out_put: } /* + * setattr + */ +int ceph_setattr(struct dentry *dentry, struct iattr *attr) +{ + return __ceph_setattr(d_inode(dentry), attr); +} + +/* * Verify that we have a lease on the given mask. If not, * do a getattr against an mds. */ diff --git a/fs/ceph/super.h b/fs/ceph/super.h index e705c4d..7b99eb7 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -785,19 +785,15 @@ static inline int ceph_do_getattr(struct inode *inode, int mask, bool force) return __ceph_do_getattr(inode, NULL, mask, force); } extern int ceph_permission(struct inode *inode, int mask); +extern int __ceph_setattr(struct inode *inode, struct iattr *attr); extern int ceph_setattr(struct dentry *dentry, struct iattr *attr); extern int ceph_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat); /* xattr.c */ -extern int ceph_setxattr(struct dentry *, const char *, const void *, - size_t, int); -int __ceph_setxattr(struct dentry *, const char *, const void *, size_t, int); +int __ceph_setxattr(struct inode *, const char *, const void *, size_t, int); ssize_t __ceph_getxattr(struct inode *, const char *, void *, size_t); -int __ceph_removexattr(struct dentry *, const char *); -extern ssize_t ceph_getxattr(struct dentry *, const char *, void *, size_t); extern ssize_t ceph_listxattr(struct dentry *, char *, size_t); -extern int ceph_removexattr(struct dentry *, const char *); extern void __ceph_build_xattrs_blob(struct ceph_inode_info *ci); extern void __ceph_destroy_xattrs(struct ceph_inode_info *ci); extern void __init ceph_xattr_init(void); diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c index 9410abd..0d66722 100644 --- a/fs/ceph/xattr.c +++ b/fs/ceph/xattr.c @@ -16,6 +16,8 @@ static int __remove_xattr(struct ceph_inode_info *ci, struct ceph_inode_xattr *xattr); +const struct xattr_handler ceph_other_xattr_handler; + /* * List of handlers for synthetic system.* attributes. Other * attributes are handled directly. @@ -25,6 +27,7 @@ const struct xattr_handler *ceph_xattr_handlers[] = { &posix_acl_access_xattr_handler, &posix_acl_default_xattr_handler, #endif + &ceph_other_xattr_handler, NULL, }; @@ -33,7 +36,6 @@ static bool ceph_is_valid_xattr(const char *name) return !strncmp(name, XATTR_CEPH_PREFIX, XATTR_CEPH_PREFIX_LEN) || !strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN) || - !strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN) || !strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN) || !strncmp(name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN); } @@ -496,19 +498,6 @@ static int __remove_xattr(struct ceph_inode_info *ci, return 0; } -static int __remove_xattr_by_name(struct ceph_inode_info *ci, - const char *name) -{ - struct rb_node **p; - struct ceph_inode_xattr *xattr; - int err; - - p = &ci->i_xattrs.index.rb_node; - xattr = __get_xattr(ci, name); - err = __remove_xattr(ci, xattr); - return err; -} - static char *__copy_xattr_names(struct ceph_inode_info *ci, char *dest) { @@ -740,9 +729,6 @@ ssize_t __ceph_getxattr(struct inode *inode, const char *name, void *value, int req_mask; int err; - if (!ceph_is_valid_xattr(name)) - return -ENODATA; - /* let's see if a virtual xattr was requested */ vxattr = ceph_match_vxattr(inode, name); if (vxattr) { @@ -804,15 +790,6 @@ out: return err; } -ssize_t ceph_getxattr(struct dentry *dentry, const char *name, void *value, - size_t size) -{ - if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN)) - return generic_getxattr(dentry, name, value, size); - - return __ceph_getxattr(d_inode(dentry), name, value, size); -} - ssize_t ceph_listxattr(struct dentry *dentry, char *names, size_t size) { struct inode *inode = d_inode(dentry); @@ -877,11 +854,10 @@ out: return err; } -static int ceph_sync_setxattr(struct dentry *dentry, const char *name, +static int ceph_sync_setxattr(struct inode *inode, const char *name, const char *value, size_t size, int flags) { - struct ceph_fs_client *fsc = ceph_sb_to_client(dentry->d_sb); - struct inode *inode = d_inode(dentry); + struct ceph_fs_client *fsc = ceph_sb_to_client(inode->i_sb); struct ceph_inode_info *ci = ceph_inode(inode); struct ceph_mds_request *req; struct ceph_mds_client *mdsc = fsc->mdsc; @@ -939,13 +915,12 @@ out: return err; } -int __ceph_setxattr(struct dentry *dentry, const char *name, +int __ceph_setxattr(struct inode *inode, const char *name, const void *value, size_t size, int flags) { - struct inode *inode = d_inode(dentry); struct ceph_vxattr *vxattr; struct ceph_inode_info *ci = ceph_inode(inode); - struct ceph_mds_client *mdsc = ceph_sb_to_client(dentry->d_sb)->mdsc; + struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc; struct ceph_cap_flush *prealloc_cf = NULL; int issued; int err; @@ -958,8 +933,8 @@ int __ceph_setxattr(struct dentry *dentry, const char *name, int required_blob_size; bool lock_snap_rwsem = false; - if (!ceph_is_valid_xattr(name)) - return -EOPNOTSUPP; + if (ceph_snap(inode) != CEPH_NOSNAP) + return -EROFS; vxattr = ceph_match_vxattr(inode, name); if (vxattr && vxattr->readonly) @@ -1056,7 +1031,7 @@ do_sync_unlocked: "during filling trace\n", inode); err = -EBUSY; } else { - err = ceph_sync_setxattr(dentry, name, value, size, flags); + err = ceph_sync_setxattr(inode, name, value, size, flags); } out: ceph_free_cap_flush(prealloc_cf); @@ -1066,146 +1041,29 @@ out: return err; } -int ceph_setxattr(struct dentry *dentry, const char *name, - const void *value, size_t size, int flags) -{ - if (ceph_snap(d_inode(dentry)) != CEPH_NOSNAP) - return -EROFS; - - if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN)) - return generic_setxattr(dentry, name, value, size, flags); - - if (size == 0) - value = ""; /* empty EA, do not remove */ - - return __ceph_setxattr(dentry, name, value, size, flags); -} - -static int ceph_send_removexattr(struct dentry *dentry, const char *name) +static int ceph_get_xattr_handler(const struct xattr_handler *handler, + struct dentry *dentry, struct inode *inode, + const char *name, void *value, size_t size) { - struct ceph_fs_client *fsc = ceph_sb_to_client(dentry->d_sb); - struct ceph_mds_client *mdsc = fsc->mdsc; - struct inode *inode = d_inode(dentry); - struct ceph_mds_request *req; - int err; - - req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_RMXATTR, - USE_AUTH_MDS); - if (IS_ERR(req)) - return PTR_ERR(req); - req->r_path2 = kstrdup(name, GFP_NOFS); - if (!req->r_path2) - return -ENOMEM; - - req->r_inode = inode; - ihold(inode); - req->r_num_caps = 1; - req->r_inode_drop = CEPH_CAP_XATTR_SHARED; - err = ceph_mdsc_do_request(mdsc, NULL, req); - ceph_mdsc_put_request(req); - return err; + if (!ceph_is_valid_xattr(name)) + return -EOPNOTSUPP; + return __ceph_getxattr(inode, name, value, size); } -int __ceph_removexattr(struct dentry *dentry, const char *name) +static int ceph_set_xattr_handler(const struct xattr_handler *handler, + struct dentry *dentry, const char *name, + const void *value, size_t size, int flags) { - struct inode *inode = d_inode(dentry); - struct ceph_vxattr *vxattr; - struct ceph_inode_info *ci = ceph_inode(inode); - struct ceph_mds_client *mdsc = ceph_sb_to_client(dentry->d_sb)->mdsc; - struct ceph_cap_flush *prealloc_cf = NULL; - int issued; - int err; - int required_blob_size; - int dirty; - bool lock_snap_rwsem = false; - if (!ceph_is_valid_xattr(name)) return -EOPNOTSUPP; - - vxattr = ceph_match_vxattr(inode, name); - if (vxattr && vxattr->readonly) - return -EOPNOTSUPP; - - /* pass any unhandled ceph.* xattrs through to the MDS */ - if (!strncmp(name, XATTR_CEPH_PREFIX, XATTR_CEPH_PREFIX_LEN)) - goto do_sync_unlocked; - - prealloc_cf = ceph_alloc_cap_flush(); - if (!prealloc_cf) - return -ENOMEM; - - err = -ENOMEM; - spin_lock(&ci->i_ceph_lock); -retry: - issued = __ceph_caps_issued(ci, NULL); - if (ci->i_xattrs.version == 0 || !(issued & CEPH_CAP_XATTR_EXCL)) - goto do_sync; - - if (!lock_snap_rwsem && !ci->i_head_snapc) { - lock_snap_rwsem = true; - if (!down_read_trylock(&mdsc->snap_rwsem)) { - spin_unlock(&ci->i_ceph_lock); - down_read(&mdsc->snap_rwsem); - spin_lock(&ci->i_ceph_lock); - goto retry; - } - } - - dout("removexattr %p issued %s\n", inode, ceph_cap_string(issued)); - - __build_xattrs(inode); - - required_blob_size = __get_required_blob_size(ci, 0, 0); - - if (!ci->i_xattrs.prealloc_blob || - required_blob_size > ci->i_xattrs.prealloc_blob->alloc_len) { - struct ceph_buffer *blob; - - spin_unlock(&ci->i_ceph_lock); - dout(" preaallocating new blob size=%d\n", required_blob_size); - blob = ceph_buffer_new(required_blob_size, GFP_NOFS); - if (!blob) - goto do_sync_unlocked; - spin_lock(&ci->i_ceph_lock); - if (ci->i_xattrs.prealloc_blob) - ceph_buffer_put(ci->i_xattrs.prealloc_blob); - ci->i_xattrs.prealloc_blob = blob; - goto retry; - } - - err = __remove_xattr_by_name(ceph_inode(inode), name); - - dirty = __ceph_mark_dirty_caps(ci, CEPH_CAP_XATTR_EXCL, - &prealloc_cf); - ci->i_xattrs.dirty = true; - inode->i_ctime = current_fs_time(inode->i_sb); - spin_unlock(&ci->i_ceph_lock); - if (lock_snap_rwsem) - up_read(&mdsc->snap_rwsem); - if (dirty) - __mark_inode_dirty(inode, dirty); - ceph_free_cap_flush(prealloc_cf); - return err; -do_sync: - spin_unlock(&ci->i_ceph_lock); -do_sync_unlocked: - if (lock_snap_rwsem) - up_read(&mdsc->snap_rwsem); - ceph_free_cap_flush(prealloc_cf); - err = ceph_send_removexattr(dentry, name); - return err; + return __ceph_setxattr(d_inode(dentry), name, value, size, flags); } -int ceph_removexattr(struct dentry *dentry, const char *name) -{ - if (ceph_snap(d_inode(dentry)) != CEPH_NOSNAP) - return -EROFS; - - if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN)) - return generic_removexattr(dentry, name); - - return __ceph_removexattr(dentry, name); -} +const struct xattr_handler ceph_other_xattr_handler = { + .prefix = "", /* match any name => handlers called with full name */ + .get = ceph_get_xattr_handler, + .set = ceph_set_xattr_handler, +}; #ifdef CONFIG_SECURITY bool ceph_security_xattr_wanted(struct inode *in) diff --git a/fs/cifs/Makefile b/fs/cifs/Makefile index 1964d21..eed7eb0 100644 --- a/fs/cifs/Makefile +++ b/fs/cifs/Makefile @@ -5,9 +5,10 @@ obj-$(CONFIG_CIFS) += cifs.o cifs-y := cifsfs.o cifssmb.o cifs_debug.o connect.o dir.o file.o inode.o \ link.o misc.o netmisc.o smbencrypt.o transport.o asn1.o \ - cifs_unicode.o nterr.o xattr.o cifsencrypt.o \ + cifs_unicode.o nterr.o cifsencrypt.o \ readdir.o ioctl.o sess.o export.o smb1ops.o winucase.o +cifs-$(CONFIG_CIFS_XATTR) += xattr.o cifs-$(CONFIG_CIFS_ACL) += cifsacl.o cifs-$(CONFIG_CIFS_UPCALL) += cifs_spnego.o diff --git a/fs/cifs/cifs_dfs_ref.c b/fs/cifs/cifs_dfs_ref.c index e956cba..ec9dbbc 100644 --- a/fs/cifs/cifs_dfs_ref.c +++ b/fs/cifs/cifs_dfs_ref.c @@ -151,8 +151,12 @@ char *cifs_compose_mount_options(const char *sb_mountdata, if (sb_mountdata == NULL) return ERR_PTR(-EINVAL); - if (strlen(fullpath) - ref->path_consumed) + if (strlen(fullpath) - ref->path_consumed) { prepath = fullpath + ref->path_consumed; + /* skip initial delimiter */ + if (*prepath == '/' || *prepath == '\\') + prepath++; + } *devname = cifs_build_devname(ref->node_name, prepath); if (IS_ERR(*devname)) { @@ -302,7 +306,7 @@ static struct vfsmount *cifs_dfs_do_automount(struct dentry *mntpt) if (full_path == NULL) goto cdda_exit; - cifs_sb = CIFS_SB(d_inode(mntpt)->i_sb); + cifs_sb = CIFS_SB(mntpt->d_sb); tlink = cifs_sb_tlink(cifs_sb); if (IS_ERR(tlink)) { mnt = ERR_CAST(tlink); diff --git a/fs/cifs/cifsacl.c b/fs/cifs/cifsacl.c index 3f93125..71e8a56 100644 --- a/fs/cifs/cifsacl.c +++ b/fs/cifs/cifsacl.c @@ -360,7 +360,7 @@ init_cifs_idmap(void) GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, cred, (KEY_POS_ALL & ~KEY_POS_SETATTR) | KEY_USR_VIEW | KEY_USR_READ, - KEY_ALLOC_NOT_IN_QUOTA, NULL); + KEY_ALLOC_NOT_IN_QUOTA, NULL, NULL); if (IS_ERR(keyring)) { ret = PTR_ERR(keyring); goto failed_put_cred; diff --git a/fs/cifs/cifsencrypt.c b/fs/cifs/cifsencrypt.c index 4897dac..6aeb8d4 100644 --- a/fs/cifs/cifsencrypt.c +++ b/fs/cifs/cifsencrypt.c @@ -66,45 +66,15 @@ cifs_crypto_shash_md5_allocate(struct TCP_Server_Info *server) return 0; } -/* - * Calculate and return the CIFS signature based on the mac key and SMB PDU. - * The 16 byte signature must be allocated by the caller. Note we only use the - * 1st eight bytes and that the smb header signature field on input contains - * the sequence number before this function is called. Also, this function - * should be called with the server->srv_mutex held. - */ -static int cifs_calc_signature(struct smb_rqst *rqst, - struct TCP_Server_Info *server, char *signature) +int __cifs_calc_signature(struct smb_rqst *rqst, + struct TCP_Server_Info *server, char *signature, + struct shash_desc *shash) { int i; int rc; struct kvec *iov = rqst->rq_iov; int n_vec = rqst->rq_nvec; - if (iov == NULL || signature == NULL || server == NULL) - return -EINVAL; - - if (!server->secmech.sdescmd5) { - rc = cifs_crypto_shash_md5_allocate(server); - if (rc) { - cifs_dbg(VFS, "%s: Can't alloc md5 crypto\n", __func__); - return -1; - } - } - - rc = crypto_shash_init(&server->secmech.sdescmd5->shash); - if (rc) { - cifs_dbg(VFS, "%s: Could not init md5\n", __func__); - return rc; - } - - rc = crypto_shash_update(&server->secmech.sdescmd5->shash, - server->session_key.response, server->session_key.len); - if (rc) { - cifs_dbg(VFS, "%s: Could not update with response\n", __func__); - return rc; - } - for (i = 0; i < n_vec; i++) { if (iov[i].iov_len == 0) continue; @@ -117,12 +87,10 @@ static int cifs_calc_signature(struct smb_rqst *rqst, if (i == 0) { if (iov[0].iov_len <= 8) /* cmd field at offset 9 */ break; /* nothing to sign or corrupt header */ - rc = - crypto_shash_update(&server->secmech.sdescmd5->shash, + rc = crypto_shash_update(shash, iov[i].iov_base + 4, iov[i].iov_len - 4); } else { - rc = - crypto_shash_update(&server->secmech.sdescmd5->shash, + rc = crypto_shash_update(shash, iov[i].iov_base, iov[i].iov_len); } if (rc) { @@ -134,21 +102,64 @@ static int cifs_calc_signature(struct smb_rqst *rqst, /* now hash over the rq_pages array */ for (i = 0; i < rqst->rq_npages; i++) { - struct kvec p_iov; + void *kaddr = kmap(rqst->rq_pages[i]); + size_t len = rqst->rq_pagesz; + + if (i == rqst->rq_npages - 1) + len = rqst->rq_tailsz; + + crypto_shash_update(shash, kaddr, len); - cifs_rqst_page_to_kvec(rqst, i, &p_iov); - crypto_shash_update(&server->secmech.sdescmd5->shash, - p_iov.iov_base, p_iov.iov_len); kunmap(rqst->rq_pages[i]); } - rc = crypto_shash_final(&server->secmech.sdescmd5->shash, signature); + rc = crypto_shash_final(shash, signature); if (rc) - cifs_dbg(VFS, "%s: Could not generate md5 hash\n", __func__); + cifs_dbg(VFS, "%s: Could not generate hash\n", __func__); return rc; } +/* + * Calculate and return the CIFS signature based on the mac key and SMB PDU. + * The 16 byte signature must be allocated by the caller. Note we only use the + * 1st eight bytes and that the smb header signature field on input contains + * the sequence number before this function is called. Also, this function + * should be called with the server->srv_mutex held. + */ +static int cifs_calc_signature(struct smb_rqst *rqst, + struct TCP_Server_Info *server, char *signature) +{ + int rc; + + if (!rqst->rq_iov || !signature || !server) + return -EINVAL; + + if (!server->secmech.sdescmd5) { + rc = cifs_crypto_shash_md5_allocate(server); + if (rc) { + cifs_dbg(VFS, "%s: Can't alloc md5 crypto\n", __func__); + return -1; + } + } + + rc = crypto_shash_init(&server->secmech.sdescmd5->shash); + if (rc) { + cifs_dbg(VFS, "%s: Could not init md5\n", __func__); + return rc; + } + + rc = crypto_shash_update(&server->secmech.sdescmd5->shash, + server->session_key.response, server->session_key.len); + if (rc) { + cifs_dbg(VFS, "%s: Could not update with response\n", __func__); + return rc; + } + + return __cifs_calc_signature(rqst, server, signature, + &server->secmech.sdescmd5->shash); +} + /* must be called with server->srv_mutex held */ int cifs_sign_rqst(struct smb_rqst *rqst, struct TCP_Server_Info *server, __u32 *pexpected_response_sequence_number) diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index 8920156..08fa36e 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -37,6 +37,7 @@ #include <linux/freezer.h> #include <linux/namei.h> #include <linux/random.h> +#include <linux/xattr.h> #include <net/ipv6.h> #include "cifsfs.h" #include "cifspdu.h" @@ -135,6 +136,7 @@ cifs_read_super(struct super_block *sb) sb->s_magic = CIFS_MAGIC_NUMBER; sb->s_op = &cifs_super_ops; + sb->s_xattr = cifs_xattr_handlers; sb->s_bdi = &cifs_sb->bdi; sb->s_blocksize = CIFS_MAX_MSGSIZE; sb->s_blocksize_bits = 14; /* default 2**14 = CIFS_MAX_MSGSIZE */ @@ -892,12 +894,10 @@ const struct inode_operations cifs_dir_inode_ops = { .setattr = cifs_setattr, .symlink = cifs_symlink, .mknod = cifs_mknod, -#ifdef CONFIG_CIFS_XATTR - .setxattr = cifs_setxattr, - .getxattr = cifs_getxattr, + .setxattr = generic_setxattr, + .getxattr = generic_getxattr, .listxattr = cifs_listxattr, - .removexattr = cifs_removexattr, -#endif + .removexattr = generic_removexattr, }; const struct inode_operations cifs_file_inode_ops = { @@ -905,12 +905,10 @@ const struct inode_operations cifs_file_inode_ops = { .setattr = cifs_setattr, .getattr = cifs_getattr, /* do we need this anymore? */ .permission = cifs_permission, -#ifdef CONFIG_CIFS_XATTR - .setxattr = cifs_setxattr, - .getxattr = cifs_getxattr, + .setxattr = generic_setxattr, + .getxattr = generic_getxattr, .listxattr = cifs_listxattr, - .removexattr = cifs_removexattr, -#endif + .removexattr = generic_removexattr, }; const struct inode_operations cifs_symlink_inode_ops = { @@ -920,12 +918,10 @@ const struct inode_operations cifs_symlink_inode_ops = { /* BB add the following two eventually */ /* revalidate: cifs_revalidate, setattr: cifs_notify_change, *//* BB do we need notify change */ -#ifdef CONFIG_CIFS_XATTR - .setxattr = cifs_setxattr, - .getxattr = cifs_getxattr, + .setxattr = generic_setxattr, + .getxattr = generic_getxattr, .listxattr = cifs_listxattr, - .removexattr = cifs_removexattr, -#endif + .removexattr = generic_removexattr, }; static int cifs_clone_file_range(struct file *src_file, loff_t off, @@ -1083,7 +1079,7 @@ const struct file_operations cifs_file_direct_nobrl_ops = { }; const struct file_operations cifs_dir_ops = { - .iterate = cifs_readdir, + .iterate_shared = cifs_readdir, .release = cifs_closedir, .read = generic_read_dir, .unlocked_ioctl = cifs_ioctl, diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h index 83aac8b..9dcf974 100644 --- a/fs/cifs/cifsfs.h +++ b/fs/cifs/cifsfs.h @@ -120,15 +120,19 @@ extern const char *cifs_get_link(struct dentry *, struct inode *, struct delayed_call *); extern int cifs_symlink(struct inode *inode, struct dentry *direntry, const char *symname); -extern int cifs_removexattr(struct dentry *, const char *); -extern int cifs_setxattr(struct dentry *, const char *, const void *, - size_t, int); -extern ssize_t cifs_getxattr(struct dentry *, const char *, void *, size_t); + +#ifdef CONFIG_CIFS_XATTR +extern const struct xattr_handler *cifs_xattr_handlers[]; extern ssize_t cifs_listxattr(struct dentry *, char *, size_t); +#else +# define cifs_xattr_handlers NULL +# define cifs_listxattr NULL +#endif + extern long cifs_ioctl(struct file *filep, unsigned int cmd, unsigned long arg); #ifdef CONFIG_CIFS_NFSD_EXPORT extern const struct export_operations cifs_export_ops; #endif /* CONFIG_CIFS_NFSD_EXPORT */ -#define CIFS_VERSION "2.08" +#define CIFS_VERSION "2.09" #endif /* _CIFSFS_H */ diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index f2cc0b3..bba106c 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -615,8 +615,6 @@ struct TCP_Server_Info { bool sec_mskerberos; /* supports legacy MS Kerberos */ bool large_buf; /* is current buffer large? */ struct delayed_work echo; /* echo ping workqueue job */ - struct kvec *iov; /* reusable kvec array for receives */ - unsigned int nr_iov; /* number of kvecs in array */ char *smallbuf; /* pointer to current "small" buffer */ char *bigbuf; /* pointer to current "big" buffer */ unsigned int total_read; /* total amount of data read in this pass */ diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h index eed7ff5..0f9a6bc 100644 --- a/fs/cifs/cifsproto.h +++ b/fs/cifs/cifsproto.h @@ -37,8 +37,6 @@ extern void cifs_buf_release(void *); extern struct smb_hdr *cifs_small_buf_get(void); extern void cifs_small_buf_release(void *); extern void free_rsp_buf(int, void *); -extern void cifs_rqst_page_to_kvec(struct smb_rqst *rqst, unsigned int idx, - struct kvec *iov); extern int smb_send(struct TCP_Server_Info *, struct smb_hdr *, unsigned int /* length */); extern unsigned int _get_xid(void); @@ -181,10 +179,9 @@ extern int set_cifs_acl(struct cifs_ntsd *, __u32, struct inode *, extern void dequeue_mid(struct mid_q_entry *mid, bool malformed); extern int cifs_read_from_socket(struct TCP_Server_Info *server, char *buf, - unsigned int to_read); -extern int cifs_readv_from_socket(struct TCP_Server_Info *server, - struct kvec *iov_orig, unsigned int nr_segs, - unsigned int to_read); + unsigned int to_read); +extern int cifs_read_page_from_socket(struct TCP_Server_Info *server, + struct page *page, unsigned int to_read); extern void cifs_setup_cifs_sb(struct smb_vol *pvolume_info, struct cifs_sb_info *cifs_sb); extern int cifs_match_super(struct super_block *, void *); @@ -512,4 +509,7 @@ int cifs_create_mf_symlink(unsigned int xid, struct cifs_tcon *tcon, struct cifs_sb_info *cifs_sb, const unsigned char *path, char *pbuf, unsigned int *pbytes_written); +int __cifs_calc_signature(struct smb_rqst *rqst, + struct TCP_Server_Info *server, char *signature, + struct shash_desc *shash); #endif /* _CIFSPROTO_H */ diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index a894bf8..d47197e 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -1447,10 +1447,8 @@ cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid) len = min_t(unsigned int, buflen, server->vals->read_rsp_size) - HEADER_SIZE(server) + 1; - rdata->iov.iov_base = buf + HEADER_SIZE(server) - 1; - rdata->iov.iov_len = len; - - length = cifs_readv_from_socket(server, &rdata->iov, 1, len); + length = cifs_read_from_socket(server, + buf + HEADER_SIZE(server) - 1, len); if (length < 0) return length; server->total_read += length; @@ -1502,9 +1500,8 @@ cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid) len = data_offset - server->total_read; if (len > 0) { /* read any junk before data into the rest of smallbuf */ - rdata->iov.iov_base = buf + server->total_read; - rdata->iov.iov_len = len; - length = cifs_readv_from_socket(server, &rdata->iov, 1, len); + length = cifs_read_from_socket(server, + buf + server->total_read, len); if (length < 0) return length; server->total_read += length; @@ -3366,7 +3363,7 @@ static int cifs_copy_posix_acl(char *trgt, char *src, const int buflen, if (le16_to_cpu(cifs_acl->version) != CIFS_ACL_VERSION) return -EOPNOTSUPP; - if (acl_type & ACL_TYPE_ACCESS) { + if (acl_type == ACL_TYPE_ACCESS) { count = le16_to_cpu(cifs_acl->access_entry_count); pACE = &cifs_acl->ace_array[0]; size = sizeof(struct cifs_posix_acl); @@ -3377,7 +3374,7 @@ static int cifs_copy_posix_acl(char *trgt, char *src, const int buflen, size_of_data_area, size); return -EINVAL; } - } else if (acl_type & ACL_TYPE_DEFAULT) { + } else if (acl_type == ACL_TYPE_DEFAULT) { count = le16_to_cpu(cifs_acl->access_entry_count); size = sizeof(struct cifs_posix_acl); size += sizeof(struct cifs_posix_ace) * count; diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 6f62ac8..66736f5 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -501,99 +501,34 @@ server_unresponsive(struct TCP_Server_Info *server) return false; } -/* - * kvec_array_init - clone a kvec array, and advance into it - * @new: pointer to memory for cloned array - * @iov: pointer to original array - * @nr_segs: number of members in original array - * @bytes: number of bytes to advance into the cloned array - * - * This function will copy the array provided in iov to a section of memory - * and advance the specified number of bytes into the new array. It returns - * the number of segments in the new array. "new" must be at least as big as - * the original iov array. - */ -static unsigned int -kvec_array_init(struct kvec *new, struct kvec *iov, unsigned int nr_segs, - size_t bytes) -{ - size_t base = 0; - - while (bytes || !iov->iov_len) { - int copy = min(bytes, iov->iov_len); - - bytes -= copy; - base += copy; - if (iov->iov_len == base) { - iov++; - nr_segs--; - base = 0; - } - } - memcpy(new, iov, sizeof(*iov) * nr_segs); - new->iov_base += base; - new->iov_len -= base; - return nr_segs; -} - -static struct kvec * -get_server_iovec(struct TCP_Server_Info *server, unsigned int nr_segs) -{ - struct kvec *new_iov; - - if (server->iov && nr_segs <= server->nr_iov) - return server->iov; - - /* not big enough -- allocate a new one and release the old */ - new_iov = kmalloc(sizeof(*new_iov) * nr_segs, GFP_NOFS); - if (new_iov) { - kfree(server->iov); - server->iov = new_iov; - server->nr_iov = nr_segs; - } - return new_iov; -} - -int -cifs_readv_from_socket(struct TCP_Server_Info *server, struct kvec *iov_orig, - unsigned int nr_segs, unsigned int to_read) +static int +cifs_readv_from_socket(struct TCP_Server_Info *server, struct msghdr *smb_msg) { int length = 0; int total_read; - unsigned int segs; - struct msghdr smb_msg; - struct kvec *iov; - iov = get_server_iovec(server, nr_segs); - if (!iov) - return -ENOMEM; - - smb_msg.msg_control = NULL; - smb_msg.msg_controllen = 0; + smb_msg->msg_control = NULL; + smb_msg->msg_controllen = 0; - for (total_read = 0; to_read; total_read += length, to_read -= length) { + for (total_read = 0; msg_data_left(smb_msg); total_read += length) { try_to_freeze(); - if (server_unresponsive(server)) { - total_read = -ECONNABORTED; - break; - } + if (server_unresponsive(server)) + return -ECONNABORTED; - segs = kvec_array_init(iov, iov_orig, nr_segs, total_read); + length = sock_recvmsg(server->ssocket, smb_msg, 0); - length = kernel_recvmsg(server->ssocket, &smb_msg, - iov, segs, to_read, 0); + if (server->tcpStatus == CifsExiting) + return -ESHUTDOWN; - if (server->tcpStatus == CifsExiting) { - total_read = -ESHUTDOWN; - break; - } else if (server->tcpStatus == CifsNeedReconnect) { + if (server->tcpStatus == CifsNeedReconnect) { cifs_reconnect(server); - total_read = -ECONNABORTED; - break; - } else if (length == -ERESTARTSYS || - length == -EAGAIN || - length == -EINTR) { + return -ECONNABORTED; + } + + if (length == -ERESTARTSYS || + length == -EAGAIN || + length == -EINTR) { /* * Minimum sleep to prevent looping, allowing socket * to clear and app threads to set tcpStatus @@ -602,12 +537,12 @@ cifs_readv_from_socket(struct TCP_Server_Info *server, struct kvec *iov_orig, usleep_range(1000, 2000); length = 0; continue; - } else if (length <= 0) { - cifs_dbg(FYI, "Received no data or error: expecting %d\n" - "got %d", to_read, length); + } + + if (length <= 0) { + cifs_dbg(FYI, "Received no data or error: %d\n", length); cifs_reconnect(server); - total_read = -ECONNABORTED; - break; + return -ECONNABORTED; } } return total_read; @@ -617,12 +552,21 @@ int cifs_read_from_socket(struct TCP_Server_Info *server, char *buf, unsigned int to_read) { - struct kvec iov; + struct msghdr smb_msg; + struct kvec iov = {.iov_base = buf, .iov_len = to_read}; + iov_iter_kvec(&smb_msg.msg_iter, READ | ITER_KVEC, &iov, 1, to_read); - iov.iov_base = buf; - iov.iov_len = to_read; + return cifs_readv_from_socket(server, &smb_msg); +} - return cifs_readv_from_socket(server, &iov, 1, to_read); +int +cifs_read_page_from_socket(struct TCP_Server_Info *server, struct page *page, + unsigned int to_read) +{ + struct msghdr smb_msg; + struct bio_vec bv = {.bv_page = page, .bv_len = to_read}; + iov_iter_bvec(&smb_msg.msg_iter, READ | ITER_BVEC, &bv, 1, to_read); + return cifs_readv_from_socket(server, &smb_msg); } static bool @@ -783,7 +727,6 @@ static void clean_demultiplex_info(struct TCP_Server_Info *server) } kfree(server->hostname); - kfree(server->iov); kfree(server); length = atomic_dec_return(&tcpSesAllocCount); @@ -1196,8 +1139,12 @@ cifs_parse_devname(const char *devname, struct smb_vol *vol) convert_delimiter(vol->UNC, '\\'); - /* If pos is NULL, or is a bogus trailing delimiter then no prepath */ - if (!*pos++ || !*pos) + /* skip any delimiter */ + if (*pos == '/' || *pos == '\\') + pos++; + + /* If pos is NULL then no prepath */ + if (!*pos) return 0; vol->prepath = kstrdup(pos, GFP_KERNEL); @@ -2918,7 +2865,7 @@ static inline void cifs_reclassify_socket4(struct socket *sock) { struct sock *sk = sock->sk; - BUG_ON(sock_owned_by_user(sk)); + BUG_ON(!sock_allow_reclassification(sk)); sock_lock_init_class_and_name(sk, "slock-AF_INET-CIFS", &cifs_slock_key[0], "sk_lock-AF_INET-CIFS", &cifs_key[0]); } @@ -2927,7 +2874,7 @@ static inline void cifs_reclassify_socket6(struct socket *sock) { struct sock *sk = sock->sk; - BUG_ON(sock_owned_by_user(sk)); + BUG_ON(!sock_allow_reclassification(sk)); sock_lock_init_class_and_name(sk, "slock-AF_INET6-CIFS", &cifs_slock_key[1], "sk_lock-AF_INET6-CIFS", &cifs_key[1]); } diff --git a/fs/cifs/file.c b/fs/cifs/file.c index c03d074..9793ae0 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -271,7 +271,7 @@ struct cifsFileInfo * cifs_new_fileinfo(struct cifs_fid *fid, struct file *file, struct tcon_link *tlink, __u32 oplock) { - struct dentry *dentry = file->f_path.dentry; + struct dentry *dentry = file_dentry(file); struct inode *inode = d_inode(dentry); struct cifsInodeInfo *cinode = CIFS_I(inode); struct cifsFileInfo *cfile; @@ -461,7 +461,7 @@ int cifs_open(struct inode *inode, struct file *file) tcon = tlink_tcon(tlink); server = tcon->ses->server; - full_path = build_path_from_dentry(file->f_path.dentry); + full_path = build_path_from_dentry(file_dentry(file)); if (full_path == NULL) { rc = -ENOMEM; goto out; @@ -2687,11 +2687,8 @@ cifs_writev(struct kiocb *iocb, struct iov_iter *from) out: inode_unlock(inode); - if (rc > 0) { - ssize_t err = generic_write_sync(file, iocb->ki_pos - rc, rc); - if (err < 0) - rc = err; - } + if (rc > 0) + rc = generic_write_sync(iocb, rc); up_read(&cinode->lock_sem); return rc; } @@ -2855,39 +2852,31 @@ cifs_uncached_read_into_pages(struct TCP_Server_Info *server, int result = 0; unsigned int i; unsigned int nr_pages = rdata->nr_pages; - struct kvec iov; rdata->got_bytes = 0; rdata->tailsz = PAGE_SIZE; for (i = 0; i < nr_pages; i++) { struct page *page = rdata->pages[i]; + size_t n; - if (len >= PAGE_SIZE) { - /* enough data to fill the page */ - iov.iov_base = kmap(page); - iov.iov_len = PAGE_SIZE; - cifs_dbg(FYI, "%u: iov_base=%p iov_len=%zu\n", - i, iov.iov_base, iov.iov_len); - len -= PAGE_SIZE; - } else if (len > 0) { - /* enough for partial page, fill and zero the rest */ - iov.iov_base = kmap(page); - iov.iov_len = len; - cifs_dbg(FYI, "%u: iov_base=%p iov_len=%zu\n", - i, iov.iov_base, iov.iov_len); - memset(iov.iov_base + len, '\0', PAGE_SIZE - len); - rdata->tailsz = len; - len = 0; - } else { + if (len <= 0) { /* no need to hold page hostage */ rdata->pages[i] = NULL; rdata->nr_pages--; put_page(page); continue; } - - result = cifs_readv_from_socket(server, &iov, 1, iov.iov_len); - kunmap(page); + n = len; + if (len >= PAGE_SIZE) { + /* enough data to fill the page */ + n = PAGE_SIZE; + len -= n; + } else { + zero_user(page, len, PAGE_SIZE - len); + rdata->tailsz = len; + len = 0; + } + result = cifs_read_page_from_socket(server, page, n); if (result < 0) break; @@ -3303,7 +3292,6 @@ cifs_readpages_read_into_pages(struct TCP_Server_Info *server, u64 eof; pgoff_t eof_index; unsigned int nr_pages = rdata->nr_pages; - struct kvec iov; /* determine the eof that the server (probably) has */ eof = CIFS_I(rdata->mapping->host)->server_eof; @@ -3314,23 +3302,14 @@ cifs_readpages_read_into_pages(struct TCP_Server_Info *server, rdata->tailsz = PAGE_SIZE; for (i = 0; i < nr_pages; i++) { struct page *page = rdata->pages[i]; + size_t n = PAGE_SIZE; if (len >= PAGE_SIZE) { - /* enough data to fill the page */ - iov.iov_base = kmap(page); - iov.iov_len = PAGE_SIZE; - cifs_dbg(FYI, "%u: idx=%lu iov_base=%p iov_len=%zu\n", - i, page->index, iov.iov_base, iov.iov_len); len -= PAGE_SIZE; } else if (len > 0) { /* enough for partial page, fill and zero the rest */ - iov.iov_base = kmap(page); - iov.iov_len = len; - cifs_dbg(FYI, "%u: idx=%lu iov_base=%p iov_len=%zu\n", - i, page->index, iov.iov_base, iov.iov_len); - memset(iov.iov_base + len, - '\0', PAGE_SIZE - len); - rdata->tailsz = len; + zero_user(page, len, PAGE_SIZE - len); + n = rdata->tailsz = len; len = 0; } else if (page->index > eof_index) { /* @@ -3360,8 +3339,7 @@ cifs_readpages_read_into_pages(struct TCP_Server_Info *server, continue; } - result = cifs_readv_from_socket(server, &iov, 1, iov.iov_len); - kunmap(page); + result = cifs_read_page_from_socket(server, page, n); if (result < 0) break; @@ -3854,7 +3832,7 @@ void cifs_oplock_break(struct work_struct *work) * Direct IO is not yet supported in the cached mode. */ static ssize_t -cifs_direct_io(struct kiocb *iocb, struct iov_iter *iter, loff_t pos) +cifs_direct_io(struct kiocb *iocb, struct iov_iter *iter) { /* * FIXME diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 5f9ad5c..514dadb 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -2418,8 +2418,7 @@ cifs_setattr_exit: int cifs_setattr(struct dentry *direntry, struct iattr *attrs) { - struct inode *inode = d_inode(direntry); - struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); + struct cifs_sb_info *cifs_sb = CIFS_SB(direntry->d_sb); struct cifs_tcon *pTcon = cifs_sb_master_tcon(cifs_sb); if (pTcon->unix_ext) diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c index b30a4a6..65cf85d 100644 --- a/fs/cifs/readdir.c +++ b/fs/cifs/readdir.c @@ -78,20 +78,34 @@ cifs_prime_dcache(struct dentry *parent, struct qstr *name, { struct dentry *dentry, *alias; struct inode *inode; - struct super_block *sb = d_inode(parent)->i_sb; + struct super_block *sb = parent->d_sb; struct cifs_sb_info *cifs_sb = CIFS_SB(sb); + DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq); cifs_dbg(FYI, "%s: for %s\n", __func__, name->name); dentry = d_hash_and_lookup(parent, name); + if (!dentry) { + /* + * If we know that the inode will need to be revalidated + * immediately, then don't create a new dentry for it. + * We'll end up doing an on the wire call either way and + * this spares us an invalidation. + */ + if (fattr->cf_flags & CIFS_FATTR_NEED_REVAL) + return; +retry: + dentry = d_alloc_parallel(parent, name, &wq); + } if (IS_ERR(dentry)) return; - - if (dentry) { + if (!d_in_lookup(dentry)) { inode = d_inode(dentry); if (inode) { - if (d_mountpoint(dentry)) - goto out; + if (d_mountpoint(dentry)) { + dput(dentry); + return; + } /* * If we're generating inode numbers, then we don't * want to clobber the existing one with the one that @@ -106,33 +120,22 @@ cifs_prime_dcache(struct dentry *parent, struct qstr *name, (inode->i_mode & S_IFMT) == (fattr->cf_mode & S_IFMT)) { cifs_fattr_to_inode(inode, fattr); - goto out; + dput(dentry); + return; } } d_invalidate(dentry); dput(dentry); + goto retry; + } else { + inode = cifs_iget(sb, fattr); + if (!inode) + inode = ERR_PTR(-ENOMEM); + alias = d_splice_alias(inode, dentry); + d_lookup_done(dentry); + if (alias && !IS_ERR(alias)) + dput(alias); } - - /* - * If we know that the inode will need to be revalidated immediately, - * then don't create a new dentry for it. We'll end up doing an on - * the wire call either way and this spares us an invalidation. - */ - if (fattr->cf_flags & CIFS_FATTR_NEED_REVAL) - return; - - dentry = d_alloc(parent, name); - if (!dentry) - return; - - inode = cifs_iget(sb, fattr); - if (!inode) - goto out; - - alias = d_splice_alias(inode, dentry); - if (alias && !IS_ERR(alias)) - dput(alias); -out: dput(dentry); } @@ -300,7 +303,7 @@ initiate_cifs_search(const unsigned int xid, struct file *file) cifsFile->invalidHandle = true; cifsFile->srch_inf.endOfSearch = false; - full_path = build_path_from_dentry(file->f_path.dentry); + full_path = build_path_from_dentry(file_dentry(file)); if (full_path == NULL) { rc = -ENOMEM; goto error_exit; @@ -759,7 +762,7 @@ static int cifs_filldir(char *find_entry, struct file *file, */ fattr.cf_flags |= CIFS_FATTR_NEED_REVAL; - cifs_prime_dcache(file->f_path.dentry, &name, &fattr); + cifs_prime_dcache(file_dentry(file), &name, &fattr); ino = cifs_uniqueid_to_ino_t(fattr.cf_uniqueid); return !dir_emit(ctx, name.name, name.len, ino, fattr.cf_dtype); diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c index 59727e3..af0ec2d 100644 --- a/fs/cifs/sess.c +++ b/fs/cifs/sess.c @@ -400,19 +400,27 @@ int build_ntlmssp_auth_blob(unsigned char *pbuffer, sec_blob->LmChallengeResponse.MaximumLength = 0; sec_blob->NtChallengeResponse.BufferOffset = cpu_to_le32(tmp - pbuffer); - rc = setup_ntlmv2_rsp(ses, nls_cp); - if (rc) { - cifs_dbg(VFS, "Error %d during NTLMSSP authentication\n", rc); - goto setup_ntlmv2_ret; + if (ses->user_name != NULL) { + rc = setup_ntlmv2_rsp(ses, nls_cp); + if (rc) { + cifs_dbg(VFS, "Error %d during NTLMSSP authentication\n", rc); + goto setup_ntlmv2_ret; + } + memcpy(tmp, ses->auth_key.response + CIFS_SESS_KEY_SIZE, + ses->auth_key.len - CIFS_SESS_KEY_SIZE); + tmp += ses->auth_key.len - CIFS_SESS_KEY_SIZE; + + sec_blob->NtChallengeResponse.Length = + cpu_to_le16(ses->auth_key.len - CIFS_SESS_KEY_SIZE); + sec_blob->NtChallengeResponse.MaximumLength = + cpu_to_le16(ses->auth_key.len - CIFS_SESS_KEY_SIZE); + } else { + /* + * don't send an NT Response for anonymous access + */ + sec_blob->NtChallengeResponse.Length = 0; + sec_blob->NtChallengeResponse.MaximumLength = 0; } - memcpy(tmp, ses->auth_key.response + CIFS_SESS_KEY_SIZE, - ses->auth_key.len - CIFS_SESS_KEY_SIZE); - tmp += ses->auth_key.len - CIFS_SESS_KEY_SIZE; - - sec_blob->NtChallengeResponse.Length = - cpu_to_le16(ses->auth_key.len - CIFS_SESS_KEY_SIZE); - sec_blob->NtChallengeResponse.MaximumLength = - cpu_to_le16(ses->auth_key.len - CIFS_SESS_KEY_SIZE); if (ses->domainName == NULL) { sec_blob->DomainName.BufferOffset = cpu_to_le32(tmp - pbuffer); @@ -670,20 +678,24 @@ sess_auth_lanman(struct sess_data *sess_data) pSMB->req.hdr.Flags2 &= ~SMBFLG2_UNICODE; - /* no capabilities flags in old lanman negotiation */ - pSMB->old_req.PasswordLength = cpu_to_le16(CIFS_AUTH_RESP_SIZE); - - /* Calculate hash with password and copy into bcc_ptr. - * Encryption Key (stored as in cryptkey) gets used if the - * security mode bit in Negottiate Protocol response states - * to use challenge/response method (i.e. Password bit is 1). - */ - rc = calc_lanman_hash(ses->password, ses->server->cryptkey, - ses->server->sec_mode & SECMODE_PW_ENCRYPT ? - true : false, lnm_session_key); - - memcpy(bcc_ptr, (char *)lnm_session_key, CIFS_AUTH_RESP_SIZE); - bcc_ptr += CIFS_AUTH_RESP_SIZE; + if (ses->user_name != NULL) { + /* no capabilities flags in old lanman negotiation */ + pSMB->old_req.PasswordLength = cpu_to_le16(CIFS_AUTH_RESP_SIZE); + + /* Calculate hash with password and copy into bcc_ptr. + * Encryption Key (stored as in cryptkey) gets used if the + * security mode bit in Negottiate Protocol response states + * to use challenge/response method (i.e. Password bit is 1). + */ + rc = calc_lanman_hash(ses->password, ses->server->cryptkey, + ses->server->sec_mode & SECMODE_PW_ENCRYPT ? + true : false, lnm_session_key); + + memcpy(bcc_ptr, (char *)lnm_session_key, CIFS_AUTH_RESP_SIZE); + bcc_ptr += CIFS_AUTH_RESP_SIZE; + } else { + pSMB->old_req.PasswordLength = 0; + } /* * can not sign if LANMAN negotiated so no need @@ -769,26 +781,31 @@ sess_auth_ntlm(struct sess_data *sess_data) capabilities = cifs_ssetup_hdr(ses, pSMB); pSMB->req_no_secext.Capabilities = cpu_to_le32(capabilities); - pSMB->req_no_secext.CaseInsensitivePasswordLength = - cpu_to_le16(CIFS_AUTH_RESP_SIZE); - pSMB->req_no_secext.CaseSensitivePasswordLength = - cpu_to_le16(CIFS_AUTH_RESP_SIZE); - - /* calculate ntlm response and session key */ - rc = setup_ntlm_response(ses, sess_data->nls_cp); - if (rc) { - cifs_dbg(VFS, "Error %d during NTLM authentication\n", - rc); - goto out; - } + if (ses->user_name != NULL) { + pSMB->req_no_secext.CaseInsensitivePasswordLength = + cpu_to_le16(CIFS_AUTH_RESP_SIZE); + pSMB->req_no_secext.CaseSensitivePasswordLength = + cpu_to_le16(CIFS_AUTH_RESP_SIZE); + + /* calculate ntlm response and session key */ + rc = setup_ntlm_response(ses, sess_data->nls_cp); + if (rc) { + cifs_dbg(VFS, "Error %d during NTLM authentication\n", + rc); + goto out; + } - /* copy ntlm response */ - memcpy(bcc_ptr, ses->auth_key.response + CIFS_SESS_KEY_SIZE, - CIFS_AUTH_RESP_SIZE); - bcc_ptr += CIFS_AUTH_RESP_SIZE; - memcpy(bcc_ptr, ses->auth_key.response + CIFS_SESS_KEY_SIZE, - CIFS_AUTH_RESP_SIZE); - bcc_ptr += CIFS_AUTH_RESP_SIZE; + /* copy ntlm response */ + memcpy(bcc_ptr, ses->auth_key.response + CIFS_SESS_KEY_SIZE, + CIFS_AUTH_RESP_SIZE); + bcc_ptr += CIFS_AUTH_RESP_SIZE; + memcpy(bcc_ptr, ses->auth_key.response + CIFS_SESS_KEY_SIZE, + CIFS_AUTH_RESP_SIZE); + bcc_ptr += CIFS_AUTH_RESP_SIZE; + } else { + pSMB->req_no_secext.CaseInsensitivePasswordLength = 0; + pSMB->req_no_secext.CaseSensitivePasswordLength = 0; + } if (ses->capabilities & CAP_UNICODE) { /* unicode strings must be word aligned */ @@ -878,22 +895,26 @@ sess_auth_ntlmv2(struct sess_data *sess_data) /* LM2 password would be here if we supported it */ pSMB->req_no_secext.CaseInsensitivePasswordLength = 0; - /* calculate nlmv2 response and session key */ - rc = setup_ntlmv2_rsp(ses, sess_data->nls_cp); - if (rc) { - cifs_dbg(VFS, "Error %d during NTLMv2 authentication\n", rc); - goto out; - } + if (ses->user_name != NULL) { + /* calculate nlmv2 response and session key */ + rc = setup_ntlmv2_rsp(ses, sess_data->nls_cp); + if (rc) { + cifs_dbg(VFS, "Error %d during NTLMv2 authentication\n", rc); + goto out; + } - memcpy(bcc_ptr, ses->auth_key.response + CIFS_SESS_KEY_SIZE, - ses->auth_key.len - CIFS_SESS_KEY_SIZE); - bcc_ptr += ses->auth_key.len - CIFS_SESS_KEY_SIZE; + memcpy(bcc_ptr, ses->auth_key.response + CIFS_SESS_KEY_SIZE, + ses->auth_key.len - CIFS_SESS_KEY_SIZE); + bcc_ptr += ses->auth_key.len - CIFS_SESS_KEY_SIZE; - /* set case sensitive password length after tilen may get - * assigned, tilen is 0 otherwise. - */ - pSMB->req_no_secext.CaseSensitivePasswordLength = - cpu_to_le16(ses->auth_key.len - CIFS_SESS_KEY_SIZE); + /* set case sensitive password length after tilen may get + * assigned, tilen is 0 otherwise. + */ + pSMB->req_no_secext.CaseSensitivePasswordLength = + cpu_to_le16(ses->auth_key.len - CIFS_SESS_KEY_SIZE); + } else { + pSMB->req_no_secext.CaseSensitivePasswordLength = 0; + } if (ses->capabilities & CAP_UNICODE) { if (sess_data->iov[0].iov_len % 2) { diff --git a/fs/cifs/smb2glob.h b/fs/cifs/smb2glob.h index bc0bb9c..0ffa180 100644 --- a/fs/cifs/smb2glob.h +++ b/fs/cifs/smb2glob.h @@ -44,6 +44,7 @@ #define SMB2_OP_DELETE 7 #define SMB2_OP_HARDLINK 8 #define SMB2_OP_SET_EOF 9 +#define SMB2_OP_RMDIR 10 /* Used when constructing chained read requests. */ #define CHAINED_REQUEST 1 diff --git a/fs/cifs/smb2inode.c b/fs/cifs/smb2inode.c index 899bbc8..4f0231e 100644 --- a/fs/cifs/smb2inode.c +++ b/fs/cifs/smb2inode.c @@ -80,6 +80,10 @@ smb2_open_op_close(const unsigned int xid, struct cifs_tcon *tcon, * SMB2_open() call. */ break; + case SMB2_OP_RMDIR: + tmprc = SMB2_rmdir(xid, tcon, fid.persistent_fid, + fid.volatile_fid); + break; case SMB2_OP_RENAME: tmprc = SMB2_rename(xid, tcon, fid.persistent_fid, fid.volatile_fid, (__le16 *)data); @@ -191,8 +195,8 @@ smb2_rmdir(const unsigned int xid, struct cifs_tcon *tcon, const char *name, struct cifs_sb_info *cifs_sb) { return smb2_open_op_close(xid, tcon, cifs_sb, name, DELETE, FILE_OPEN, - CREATE_NOT_FILE | CREATE_DELETE_ON_CLOSE, - NULL, SMB2_OP_DELETE); + CREATE_NOT_FILE, + NULL, SMB2_OP_RMDIR); } int diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 42e1f44..8f38e33 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -2575,6 +2575,22 @@ SMB2_rename(const unsigned int xid, struct cifs_tcon *tcon, } int +SMB2_rmdir(const unsigned int xid, struct cifs_tcon *tcon, + u64 persistent_fid, u64 volatile_fid) +{ + __u8 delete_pending = 1; + void *data; + unsigned int size; + + data = &delete_pending; + size = 1; /* sizeof __u8 */ + + return send_set_info(xid, tcon, persistent_fid, volatile_fid, + current->tgid, FILE_DISPOSITION_INFORMATION, 1, &data, + &size); +} + +int SMB2_set_hardlink(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, u64 volatile_fid, __le16 *target_file) { diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h index 4f07dc9..eb2cde2 100644 --- a/fs/cifs/smb2proto.h +++ b/fs/cifs/smb2proto.h @@ -141,6 +141,8 @@ extern int SMB2_query_directory(const unsigned int xid, struct cifs_tcon *tcon, extern int SMB2_rename(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, u64 volatile_fid, __le16 *target_file); +extern int SMB2_rmdir(const unsigned int xid, struct cifs_tcon *tcon, + u64 persistent_fid, u64 volatile_fid); extern int SMB2_set_hardlink(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, u64 volatile_fid, __le16 *target_file); diff --git a/fs/cifs/smb2transport.c b/fs/cifs/smb2transport.c index 8732a43..bc9a7b6 100644 --- a/fs/cifs/smb2transport.c +++ b/fs/cifs/smb2transport.c @@ -135,11 +135,10 @@ smb2_find_smb_ses(struct smb2_hdr *smb2hdr, struct TCP_Server_Info *server) int smb2_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server) { - int i, rc; + int rc; unsigned char smb2_signature[SMB2_HMACSHA256_SIZE]; unsigned char *sigptr = smb2_signature; struct kvec *iov = rqst->rq_iov; - int n_vec = rqst->rq_nvec; struct smb2_hdr *smb2_pdu = (struct smb2_hdr *)iov[0].iov_base; struct cifs_ses *ses; @@ -171,53 +170,11 @@ smb2_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server) return rc; } - for (i = 0; i < n_vec; i++) { - if (iov[i].iov_len == 0) - continue; - if (iov[i].iov_base == NULL) { - cifs_dbg(VFS, "null iovec entry\n"); - return -EIO; - } - /* - * The first entry includes a length field (which does not get - * signed that occupies the first 4 bytes before the header). - */ - if (i == 0) { - if (iov[0].iov_len <= 8) /* cmd field at offset 9 */ - break; /* nothing to sign or corrupt header */ - rc = - crypto_shash_update( - &server->secmech.sdeschmacsha256->shash, - iov[i].iov_base + 4, iov[i].iov_len - 4); - } else { - rc = - crypto_shash_update( - &server->secmech.sdeschmacsha256->shash, - iov[i].iov_base, iov[i].iov_len); - } - if (rc) { - cifs_dbg(VFS, "%s: Could not update with payload\n", - __func__); - return rc; - } - } - - /* now hash over the rq_pages array */ - for (i = 0; i < rqst->rq_npages; i++) { - struct kvec p_iov; - - cifs_rqst_page_to_kvec(rqst, i, &p_iov); - crypto_shash_update(&server->secmech.sdeschmacsha256->shash, - p_iov.iov_base, p_iov.iov_len); - kunmap(rqst->rq_pages[i]); - } - - rc = crypto_shash_final(&server->secmech.sdeschmacsha256->shash, - sigptr); - if (rc) - cifs_dbg(VFS, "%s: Could not generate sha256 hash\n", __func__); + rc = __cifs_calc_signature(rqst, server, sigptr, + &server->secmech.sdeschmacsha256->shash); - memcpy(smb2_pdu->Signature, sigptr, SMB2_SIGNATURE_SIZE); + if (!rc) + memcpy(smb2_pdu->Signature, sigptr, SMB2_SIGNATURE_SIZE); return rc; } @@ -395,12 +352,10 @@ generate_smb311signingkey(struct cifs_ses *ses) int smb3_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server) { - int i; int rc = 0; unsigned char smb3_signature[SMB2_CMACAES_SIZE]; unsigned char *sigptr = smb3_signature; struct kvec *iov = rqst->rq_iov; - int n_vec = rqst->rq_nvec; struct smb2_hdr *smb2_pdu = (struct smb2_hdr *)iov[0].iov_base; struct cifs_ses *ses; @@ -431,54 +386,12 @@ smb3_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server) cifs_dbg(VFS, "%s: Could not init cmac aes\n", __func__); return rc; } + + rc = __cifs_calc_signature(rqst, server, sigptr, + &server->secmech.sdesccmacaes->shash); - for (i = 0; i < n_vec; i++) { - if (iov[i].iov_len == 0) - continue; - if (iov[i].iov_base == NULL) { - cifs_dbg(VFS, "null iovec entry"); - return -EIO; - } - /* - * The first entry includes a length field (which does not get - * signed that occupies the first 4 bytes before the header). - */ - if (i == 0) { - if (iov[0].iov_len <= 8) /* cmd field at offset 9 */ - break; /* nothing to sign or corrupt header */ - rc = - crypto_shash_update( - &server->secmech.sdesccmacaes->shash, - iov[i].iov_base + 4, iov[i].iov_len - 4); - } else { - rc = - crypto_shash_update( - &server->secmech.sdesccmacaes->shash, - iov[i].iov_base, iov[i].iov_len); - } - if (rc) { - cifs_dbg(VFS, "%s: Couldn't update cmac aes with payload\n", - __func__); - return rc; - } - } - - /* now hash over the rq_pages array */ - for (i = 0; i < rqst->rq_npages; i++) { - struct kvec p_iov; - - cifs_rqst_page_to_kvec(rqst, i, &p_iov); - crypto_shash_update(&server->secmech.sdesccmacaes->shash, - p_iov.iov_base, p_iov.iov_len); - kunmap(rqst->rq_pages[i]); - } - - rc = crypto_shash_final(&server->secmech.sdesccmacaes->shash, - sigptr); - if (rc) - cifs_dbg(VFS, "%s: Could not generate cmac aes\n", __func__); - - memcpy(smb2_pdu->Signature, sigptr, SMB2_SIGNATURE_SIZE); + if (!rc) + memcpy(smb2_pdu->Signature, sigptr, SMB2_SIGNATURE_SIZE); return rc; } diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c index 87abe8e..206a597 100644 --- a/fs/cifs/transport.c +++ b/fs/cifs/transport.c @@ -124,41 +124,32 @@ cifs_delete_mid(struct mid_q_entry *mid) /* * smb_send_kvec - send an array of kvecs to the server * @server: Server to send the data to - * @iov: Pointer to array of kvecs - * @n_vec: length of kvec array + * @smb_msg: Message to send * @sent: amount of data sent on socket is stored here * * Our basic "send data to server" function. Should be called with srv_mutex * held. The caller is responsible for handling the results. */ static int -smb_send_kvec(struct TCP_Server_Info *server, struct kvec *iov, size_t n_vec, - size_t *sent) +smb_send_kvec(struct TCP_Server_Info *server, struct msghdr *smb_msg, + size_t *sent) { int rc = 0; - int i = 0; - struct msghdr smb_msg; - unsigned int remaining; - size_t first_vec = 0; + int retries = 0; struct socket *ssocket = server->ssocket; *sent = 0; - smb_msg.msg_name = (struct sockaddr *) &server->dstaddr; - smb_msg.msg_namelen = sizeof(struct sockaddr); - smb_msg.msg_control = NULL; - smb_msg.msg_controllen = 0; + smb_msg->msg_name = (struct sockaddr *) &server->dstaddr; + smb_msg->msg_namelen = sizeof(struct sockaddr); + smb_msg->msg_control = NULL; + smb_msg->msg_controllen = 0; if (server->noblocksnd) - smb_msg.msg_flags = MSG_DONTWAIT + MSG_NOSIGNAL; + smb_msg->msg_flags = MSG_DONTWAIT + MSG_NOSIGNAL; else - smb_msg.msg_flags = MSG_NOSIGNAL; - - remaining = 0; - for (i = 0; i < n_vec; i++) - remaining += iov[i].iov_len; + smb_msg->msg_flags = MSG_NOSIGNAL; - i = 0; - while (remaining) { + while (msg_data_left(smb_msg)) { /* * If blocking send, we try 3 times, since each can block * for 5 seconds. For nonblocking we have to try more @@ -177,35 +168,21 @@ smb_send_kvec(struct TCP_Server_Info *server, struct kvec *iov, size_t n_vec, * after the retries we will kill the socket and * reconnect which may clear the network problem. */ - rc = kernel_sendmsg(ssocket, &smb_msg, &iov[first_vec], - n_vec - first_vec, remaining); + rc = sock_sendmsg(ssocket, smb_msg); if (rc == -EAGAIN) { - i++; - if (i >= 14 || (!server->noblocksnd && (i > 2))) { + retries++; + if (retries >= 14 || + (!server->noblocksnd && (retries > 2))) { cifs_dbg(VFS, "sends on sock %p stuck for 15 seconds\n", ssocket); - rc = -EAGAIN; - break; + return -EAGAIN; } - msleep(1 << i); + msleep(1 << retries); continue; } if (rc < 0) - break; - - /* send was at least partially successful */ - *sent += rc; - - if (rc == remaining) { - remaining = 0; - break; - } - - if (rc > remaining) { - cifs_dbg(VFS, "sent %d requested %d\n", rc, remaining); - break; - } + return rc; if (rc == 0) { /* should never happen, letting socket clear before @@ -215,59 +192,11 @@ smb_send_kvec(struct TCP_Server_Info *server, struct kvec *iov, size_t n_vec, continue; } - remaining -= rc; - - /* the line below resets i */ - for (i = first_vec; i < n_vec; i++) { - if (iov[i].iov_len) { - if (rc > iov[i].iov_len) { - rc -= iov[i].iov_len; - iov[i].iov_len = 0; - } else { - iov[i].iov_base += rc; - iov[i].iov_len -= rc; - first_vec = i; - break; - } - } - } - - i = 0; /* in case we get ENOSPC on the next send */ - rc = 0; + /* send was at least partially successful */ + *sent += rc; + retries = 0; /* in case we get ENOSPC on the next send */ } - return rc; -} - -/** - * rqst_page_to_kvec - Turn a slot in the smb_rqst page array into a kvec - * @rqst: pointer to smb_rqst - * @idx: index into the array of the page - * @iov: pointer to struct kvec that will hold the result - * - * Helper function to convert a slot in the rqst->rq_pages array into a kvec. - * The page will be kmapped and the address placed into iov_base. The length - * will then be adjusted according to the ptailoff. - */ -void -cifs_rqst_page_to_kvec(struct smb_rqst *rqst, unsigned int idx, - struct kvec *iov) -{ - /* - * FIXME: We could avoid this kmap altogether if we used - * kernel_sendpage instead of kernel_sendmsg. That will only - * work if signing is disabled though as sendpage inlines the - * page directly into the fraglist. If userspace modifies the - * page after we calculate the signature, then the server will - * reject it and may break the connection. kernel_sendmsg does - * an extra copy of the data and avoids that issue. - */ - iov->iov_base = kmap(rqst->rq_pages[idx]); - - /* if last page, don't send beyond this offset into page */ - if (idx == (rqst->rq_npages - 1)) - iov->iov_len = rqst->rq_tailsz; - else - iov->iov_len = rqst->rq_pagesz; + return 0; } static unsigned long @@ -299,8 +228,9 @@ smb_send_rqst(struct TCP_Server_Info *server, struct smb_rqst *rqst) unsigned int smb_buf_length = get_rfc1002_length(iov[0].iov_base); unsigned long send_length; unsigned int i; - size_t total_len = 0, sent; + size_t total_len = 0, sent, size; struct socket *ssocket = server->ssocket; + struct msghdr smb_msg; int val = 1; if (ssocket == NULL) @@ -321,7 +251,13 @@ smb_send_rqst(struct TCP_Server_Info *server, struct smb_rqst *rqst) kernel_setsockopt(ssocket, SOL_TCP, TCP_CORK, (char *)&val, sizeof(val)); - rc = smb_send_kvec(server, iov, n_vec, &sent); + size = 0; + for (i = 0; i < n_vec; i++) + size += iov[i].iov_len; + + iov_iter_kvec(&smb_msg.msg_iter, WRITE | ITER_KVEC, iov, n_vec, size); + + rc = smb_send_kvec(server, &smb_msg, &sent); if (rc < 0) goto uncork; @@ -329,11 +265,16 @@ smb_send_rqst(struct TCP_Server_Info *server, struct smb_rqst *rqst) /* now walk the page array and send each page in it */ for (i = 0; i < rqst->rq_npages; i++) { - struct kvec p_iov; - - cifs_rqst_page_to_kvec(rqst, i, &p_iov); - rc = smb_send_kvec(server, &p_iov, 1, &sent); - kunmap(rqst->rq_pages[i]); + size_t len = i == rqst->rq_npages - 1 + ? rqst->rq_tailsz + : rqst->rq_pagesz; + struct bio_vec bvec = { + .bv_page = rqst->rq_pages[i], + .bv_len = len + }; + iov_iter_bvec(&smb_msg.msg_iter, WRITE | ITER_BVEC, + &bvec, 1, len); + rc = smb_send_kvec(server, &smb_msg, &sent); if (rc < 0) break; diff --git a/fs/cifs/xattr.c b/fs/cifs/xattr.c index f5dc2f0..c8b77aa 100644 --- a/fs/cifs/xattr.c +++ b/fs/cifs/xattr.c @@ -32,92 +32,24 @@ #include "cifs_unicode.h" #define MAX_EA_VALUE_SIZE 65535 -#define CIFS_XATTR_DOS_ATTRIB "user.DosAttrib" #define CIFS_XATTR_CIFS_ACL "system.cifs_acl" /* BB need to add server (Samba e.g) support for security and trusted prefix */ -int cifs_removexattr(struct dentry *direntry, const char *ea_name) -{ - int rc = -EOPNOTSUPP; -#ifdef CONFIG_CIFS_XATTR - unsigned int xid; - struct cifs_sb_info *cifs_sb; - struct tcon_link *tlink; - struct cifs_tcon *pTcon; - struct super_block *sb; - char *full_path = NULL; - - if (direntry == NULL) - return -EIO; - if (d_really_is_negative(direntry)) - return -EIO; - sb = d_inode(direntry)->i_sb; - if (sb == NULL) - return -EIO; - - cifs_sb = CIFS_SB(sb); - tlink = cifs_sb_tlink(cifs_sb); - if (IS_ERR(tlink)) - return PTR_ERR(tlink); - pTcon = tlink_tcon(tlink); - - xid = get_xid(); - - full_path = build_path_from_dentry(direntry); - if (full_path == NULL) { - rc = -ENOMEM; - goto remove_ea_exit; - } - if (ea_name == NULL) { - cifs_dbg(FYI, "Null xattr names not supported\n"); - } else if (strncmp(ea_name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN) - && (strncmp(ea_name, XATTR_OS2_PREFIX, XATTR_OS2_PREFIX_LEN))) { - cifs_dbg(FYI, - "illegal xattr request %s (only user namespace supported)\n", - ea_name); - /* BB what if no namespace prefix? */ - /* Should we just pass them to server, except for - system and perhaps security prefixes? */ - } else { - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_XATTR) - goto remove_ea_exit; +enum { XATTR_USER, XATTR_CIFS_ACL, XATTR_ACL_ACCESS, XATTR_ACL_DEFAULT }; - ea_name += XATTR_USER_PREFIX_LEN; /* skip past user. prefix */ - if (pTcon->ses->server->ops->set_EA) - rc = pTcon->ses->server->ops->set_EA(xid, pTcon, - full_path, ea_name, NULL, (__u16)0, - cifs_sb->local_nls, cifs_remap(cifs_sb)); - } -remove_ea_exit: - kfree(full_path); - free_xid(xid); - cifs_put_tlink(tlink); -#endif - return rc; -} - -int cifs_setxattr(struct dentry *direntry, const char *ea_name, - const void *ea_value, size_t value_size, int flags) +static int cifs_xattr_set(const struct xattr_handler *handler, + struct dentry *dentry, const char *name, + const void *value, size_t size, int flags) { int rc = -EOPNOTSUPP; -#ifdef CONFIG_CIFS_XATTR unsigned int xid; - struct cifs_sb_info *cifs_sb; + struct super_block *sb = dentry->d_sb; + struct cifs_sb_info *cifs_sb = CIFS_SB(sb); struct tcon_link *tlink; struct cifs_tcon *pTcon; - struct super_block *sb; char *full_path; - if (direntry == NULL) - return -EIO; - if (d_really_is_negative(direntry)) - return -EIO; - sb = d_inode(direntry)->i_sb; - if (sb == NULL) - return -EIO; - - cifs_sb = CIFS_SB(sb); tlink = cifs_sb_tlink(cifs_sb); if (IS_ERR(tlink)) return PTR_ERR(tlink); @@ -125,10 +57,10 @@ int cifs_setxattr(struct dentry *direntry, const char *ea_name, xid = get_xid(); - full_path = build_path_from_dentry(direntry); + full_path = build_path_from_dentry(dentry); if (full_path == NULL) { rc = -ENOMEM; - goto set_ea_exit; + goto out; } /* return dos attributes as pseudo xattr */ /* return alt name if available as pseudo attr */ @@ -136,123 +68,93 @@ int cifs_setxattr(struct dentry *direntry, const char *ea_name, /* if proc/fs/cifs/streamstoxattr is set then search server for EAs or streams to returns as xattrs */ - if (value_size > MAX_EA_VALUE_SIZE) { + if (size > MAX_EA_VALUE_SIZE) { cifs_dbg(FYI, "size of EA value too large\n"); rc = -EOPNOTSUPP; - goto set_ea_exit; + goto out; } - if (ea_name == NULL) { - cifs_dbg(FYI, "Null xattr names not supported\n"); - } else if (strncmp(ea_name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN) - == 0) { + switch (handler->flags) { + case XATTR_USER: if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_XATTR) - goto set_ea_exit; - if (strncmp(ea_name, CIFS_XATTR_DOS_ATTRIB, 14) == 0) - cifs_dbg(FYI, "attempt to set cifs inode metadata\n"); + goto out; - ea_name += XATTR_USER_PREFIX_LEN; /* skip past user. prefix */ if (pTcon->ses->server->ops->set_EA) rc = pTcon->ses->server->ops->set_EA(xid, pTcon, - full_path, ea_name, ea_value, (__u16)value_size, + full_path, name, value, (__u16)size, cifs_sb->local_nls, cifs_remap(cifs_sb)); - } else if (strncmp(ea_name, XATTR_OS2_PREFIX, XATTR_OS2_PREFIX_LEN) - == 0) { - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_XATTR) - goto set_ea_exit; + break; - ea_name += XATTR_OS2_PREFIX_LEN; /* skip past os2. prefix */ - if (pTcon->ses->server->ops->set_EA) - rc = pTcon->ses->server->ops->set_EA(xid, pTcon, - full_path, ea_name, ea_value, (__u16)value_size, - cifs_sb->local_nls, cifs_remap(cifs_sb)); - } else if (strncmp(ea_name, CIFS_XATTR_CIFS_ACL, - strlen(CIFS_XATTR_CIFS_ACL)) == 0) { + case XATTR_CIFS_ACL: { #ifdef CONFIG_CIFS_ACL struct cifs_ntsd *pacl; - pacl = kmalloc(value_size, GFP_KERNEL); + + if (!value) + goto out; + pacl = kmalloc(size, GFP_KERNEL); if (!pacl) { rc = -ENOMEM; } else { - memcpy(pacl, ea_value, value_size); - if (pTcon->ses->server->ops->set_acl) + memcpy(pacl, value, size); + if (value && + pTcon->ses->server->ops->set_acl) rc = pTcon->ses->server->ops->set_acl(pacl, - value_size, d_inode(direntry), + size, d_inode(dentry), full_path, CIFS_ACL_DACL); else rc = -EOPNOTSUPP; if (rc == 0) /* force revalidate of the inode */ - CIFS_I(d_inode(direntry))->time = 0; + CIFS_I(d_inode(dentry))->time = 0; kfree(pacl); } -#else - cifs_dbg(FYI, "Set CIFS ACL not supported yet\n"); #endif /* CONFIG_CIFS_ACL */ - } else { - int temp; - temp = strncmp(ea_name, XATTR_NAME_POSIX_ACL_ACCESS, - strlen(XATTR_NAME_POSIX_ACL_ACCESS)); - if (temp == 0) { + break; + } + + case XATTR_ACL_ACCESS: #ifdef CONFIG_CIFS_POSIX - if (sb->s_flags & MS_POSIXACL) - rc = CIFSSMBSetPosixACL(xid, pTcon, full_path, - ea_value, (const int)value_size, - ACL_TYPE_ACCESS, cifs_sb->local_nls, - cifs_remap(cifs_sb)); - cifs_dbg(FYI, "set POSIX ACL rc %d\n", rc); -#else - cifs_dbg(FYI, "set POSIX ACL not supported\n"); -#endif - } else if (strncmp(ea_name, XATTR_NAME_POSIX_ACL_DEFAULT, - strlen(XATTR_NAME_POSIX_ACL_DEFAULT)) == 0) { + if (!value) + goto out; + if (sb->s_flags & MS_POSIXACL) + rc = CIFSSMBSetPosixACL(xid, pTcon, full_path, + value, (const int)size, + ACL_TYPE_ACCESS, cifs_sb->local_nls, + cifs_remap(cifs_sb)); +#endif /* CONFIG_CIFS_POSIX */ + break; + + case XATTR_ACL_DEFAULT: #ifdef CONFIG_CIFS_POSIX - if (sb->s_flags & MS_POSIXACL) - rc = CIFSSMBSetPosixACL(xid, pTcon, full_path, - ea_value, (const int)value_size, - ACL_TYPE_DEFAULT, cifs_sb->local_nls, - cifs_remap(cifs_sb)); - cifs_dbg(FYI, "set POSIX default ACL rc %d\n", rc); -#else - cifs_dbg(FYI, "set default POSIX ACL not supported\n"); -#endif - } else { - cifs_dbg(FYI, "illegal xattr request %s (only user namespace supported)\n", - ea_name); - /* BB what if no namespace prefix? */ - /* Should we just pass them to server, except for - system and perhaps security prefixes? */ - } + if (!value) + goto out; + if (sb->s_flags & MS_POSIXACL) + rc = CIFSSMBSetPosixACL(xid, pTcon, full_path, + value, (const int)size, + ACL_TYPE_DEFAULT, cifs_sb->local_nls, + cifs_remap(cifs_sb)); +#endif /* CONFIG_CIFS_POSIX */ + break; } -set_ea_exit: +out: kfree(full_path); free_xid(xid); cifs_put_tlink(tlink); -#endif return rc; } -ssize_t cifs_getxattr(struct dentry *direntry, const char *ea_name, - void *ea_value, size_t buf_size) +static int cifs_xattr_get(const struct xattr_handler *handler, + struct dentry *dentry, struct inode *inode, + const char *name, void *value, size_t size) { ssize_t rc = -EOPNOTSUPP; -#ifdef CONFIG_CIFS_XATTR unsigned int xid; - struct cifs_sb_info *cifs_sb; + struct super_block *sb = dentry->d_sb; + struct cifs_sb_info *cifs_sb = CIFS_SB(sb); struct tcon_link *tlink; struct cifs_tcon *pTcon; - struct super_block *sb; char *full_path; - if (direntry == NULL) - return -EIO; - if (d_really_is_negative(direntry)) - return -EIO; - sb = d_inode(direntry)->i_sb; - if (sb == NULL) - return -EIO; - - cifs_sb = CIFS_SB(sb); tlink = cifs_sb_tlink(cifs_sb); if (IS_ERR(tlink)) return PTR_ERR(tlink); @@ -260,98 +162,72 @@ ssize_t cifs_getxattr(struct dentry *direntry, const char *ea_name, xid = get_xid(); - full_path = build_path_from_dentry(direntry); + full_path = build_path_from_dentry(dentry); if (full_path == NULL) { rc = -ENOMEM; - goto get_ea_exit; + goto out; } /* return dos attributes as pseudo xattr */ /* return alt name if available as pseudo attr */ - if (ea_name == NULL) { - cifs_dbg(FYI, "Null xattr names not supported\n"); - } else if (strncmp(ea_name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN) - == 0) { + switch (handler->flags) { + case XATTR_USER: if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_XATTR) - goto get_ea_exit; + goto out; - if (strncmp(ea_name, CIFS_XATTR_DOS_ATTRIB, 14) == 0) { - cifs_dbg(FYI, "attempt to query cifs inode metadata\n"); - /* revalidate/getattr then populate from inode */ - } /* BB add else when above is implemented */ - ea_name += XATTR_USER_PREFIX_LEN; /* skip past user. prefix */ if (pTcon->ses->server->ops->query_all_EAs) rc = pTcon->ses->server->ops->query_all_EAs(xid, pTcon, - full_path, ea_name, ea_value, buf_size, + full_path, name, value, size, cifs_sb->local_nls, cifs_remap(cifs_sb)); - } else if (strncmp(ea_name, XATTR_OS2_PREFIX, XATTR_OS2_PREFIX_LEN) == 0) { - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_XATTR) - goto get_ea_exit; + break; - ea_name += XATTR_OS2_PREFIX_LEN; /* skip past os2. prefix */ - if (pTcon->ses->server->ops->query_all_EAs) - rc = pTcon->ses->server->ops->query_all_EAs(xid, pTcon, - full_path, ea_name, ea_value, buf_size, - cifs_sb->local_nls, cifs_remap(cifs_sb)); - } else if (strncmp(ea_name, XATTR_NAME_POSIX_ACL_ACCESS, - strlen(XATTR_NAME_POSIX_ACL_ACCESS)) == 0) { + case XATTR_CIFS_ACL: { +#ifdef CONFIG_CIFS_ACL + u32 acllen; + struct cifs_ntsd *pacl; + + if (pTcon->ses->server->ops->get_acl == NULL) + goto out; /* rc already EOPNOTSUPP */ + + pacl = pTcon->ses->server->ops->get_acl(cifs_sb, + inode, full_path, &acllen); + if (IS_ERR(pacl)) { + rc = PTR_ERR(pacl); + cifs_dbg(VFS, "%s: error %zd getting sec desc\n", + __func__, rc); + } else { + if (value) { + if (acllen > size) + acllen = -ERANGE; + else + memcpy(value, pacl, acllen); + } + rc = acllen; + kfree(pacl); + } +#endif /* CONFIG_CIFS_ACL */ + break; + } + + case XATTR_ACL_ACCESS: #ifdef CONFIG_CIFS_POSIX if (sb->s_flags & MS_POSIXACL) rc = CIFSSMBGetPosixACL(xid, pTcon, full_path, - ea_value, buf_size, ACL_TYPE_ACCESS, + value, size, ACL_TYPE_ACCESS, cifs_sb->local_nls, cifs_remap(cifs_sb)); -#else - cifs_dbg(FYI, "Query POSIX ACL not supported yet\n"); -#endif /* CONFIG_CIFS_POSIX */ - } else if (strncmp(ea_name, XATTR_NAME_POSIX_ACL_DEFAULT, - strlen(XATTR_NAME_POSIX_ACL_DEFAULT)) == 0) { +#endif /* CONFIG_CIFS_POSIX */ + break; + + case XATTR_ACL_DEFAULT: #ifdef CONFIG_CIFS_POSIX if (sb->s_flags & MS_POSIXACL) rc = CIFSSMBGetPosixACL(xid, pTcon, full_path, - ea_value, buf_size, ACL_TYPE_DEFAULT, + value, size, ACL_TYPE_DEFAULT, cifs_sb->local_nls, cifs_remap(cifs_sb)); -#else - cifs_dbg(FYI, "Query POSIX default ACL not supported yet\n"); -#endif /* CONFIG_CIFS_POSIX */ - } else if (strncmp(ea_name, CIFS_XATTR_CIFS_ACL, - strlen(CIFS_XATTR_CIFS_ACL)) == 0) { -#ifdef CONFIG_CIFS_ACL - u32 acllen; - struct cifs_ntsd *pacl; - - if (pTcon->ses->server->ops->get_acl == NULL) - goto get_ea_exit; /* rc already EOPNOTSUPP */ - - pacl = pTcon->ses->server->ops->get_acl(cifs_sb, - d_inode(direntry), full_path, &acllen); - if (IS_ERR(pacl)) { - rc = PTR_ERR(pacl); - cifs_dbg(VFS, "%s: error %zd getting sec desc\n", - __func__, rc); - } else { - if (ea_value) { - if (acllen > buf_size) - acllen = -ERANGE; - else - memcpy(ea_value, pacl, acllen); - } - rc = acllen; - kfree(pacl); - } -#else - cifs_dbg(FYI, "Query CIFS ACL not supported yet\n"); -#endif /* CONFIG_CIFS_ACL */ - } else if (strncmp(ea_name, - XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN) == 0) { - cifs_dbg(FYI, "Trusted xattr namespace not supported yet\n"); - } else if (strncmp(ea_name, - XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN) == 0) { - cifs_dbg(FYI, "Security xattr namespace not supported yet\n"); - } else - cifs_dbg(FYI, - "illegal xattr request %s (only user namespace supported)\n", - ea_name); +#endif /* CONFIG_CIFS_POSIX */ + break; + } /* We could add an additional check for streams ie if proc/fs/cifs/streamstoxattr is set then @@ -361,34 +237,22 @@ ssize_t cifs_getxattr(struct dentry *direntry, const char *ea_name, if (rc == -EINVAL) rc = -EOPNOTSUPP; -get_ea_exit: +out: kfree(full_path); free_xid(xid); cifs_put_tlink(tlink); -#endif return rc; } ssize_t cifs_listxattr(struct dentry *direntry, char *data, size_t buf_size) { ssize_t rc = -EOPNOTSUPP; -#ifdef CONFIG_CIFS_XATTR unsigned int xid; - struct cifs_sb_info *cifs_sb; + struct cifs_sb_info *cifs_sb = CIFS_SB(direntry->d_sb); struct tcon_link *tlink; struct cifs_tcon *pTcon; - struct super_block *sb; char *full_path; - if (direntry == NULL) - return -EIO; - if (d_really_is_negative(direntry)) - return -EIO; - sb = d_inode(direntry)->i_sb; - if (sb == NULL) - return -EIO; - - cifs_sb = CIFS_SB(sb); if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_XATTR) return -EOPNOTSUPP; @@ -419,6 +283,50 @@ list_ea_exit: kfree(full_path); free_xid(xid); cifs_put_tlink(tlink); -#endif return rc; } + +static const struct xattr_handler cifs_user_xattr_handler = { + .prefix = XATTR_USER_PREFIX, + .flags = XATTR_USER, + .get = cifs_xattr_get, + .set = cifs_xattr_set, +}; + +/* os2.* attributes are treated like user.* attributes */ +static const struct xattr_handler cifs_os2_xattr_handler = { + .prefix = XATTR_OS2_PREFIX, + .flags = XATTR_USER, + .get = cifs_xattr_get, + .set = cifs_xattr_set, +}; + +static const struct xattr_handler cifs_cifs_acl_xattr_handler = { + .name = CIFS_XATTR_CIFS_ACL, + .flags = XATTR_CIFS_ACL, + .get = cifs_xattr_get, + .set = cifs_xattr_set, +}; + +static const struct xattr_handler cifs_posix_acl_access_xattr_handler = { + .name = XATTR_NAME_POSIX_ACL_ACCESS, + .flags = XATTR_ACL_ACCESS, + .get = cifs_xattr_get, + .set = cifs_xattr_set, +}; + +static const struct xattr_handler cifs_posix_acl_default_xattr_handler = { + .name = XATTR_NAME_POSIX_ACL_DEFAULT, + .flags = XATTR_ACL_DEFAULT, + .get = cifs_xattr_get, + .set = cifs_xattr_set, +}; + +const struct xattr_handler *cifs_xattr_handlers[] = { + &cifs_user_xattr_handler, + &cifs_os2_xattr_handler, + &cifs_cifs_acl_xattr_handler, + &cifs_posix_acl_access_xattr_handler, + &cifs_posix_acl_default_xattr_handler, + NULL +}; diff --git a/fs/coda/dir.c b/fs/coda/dir.c index 42e731b..6fb8672 100644 --- a/fs/coda/dir.c +++ b/fs/coda/dir.c @@ -424,16 +424,22 @@ static int coda_readdir(struct file *coda_file, struct dir_context *ctx) BUG_ON(!cfi || cfi->cfi_magic != CODA_MAGIC); host_file = cfi->cfi_container; - if (host_file->f_op->iterate) { + if (host_file->f_op->iterate || host_file->f_op->iterate_shared) { struct inode *host_inode = file_inode(host_file); - - inode_lock(host_inode); ret = -ENOENT; if (!IS_DEADDIR(host_inode)) { - ret = host_file->f_op->iterate(host_file, ctx); - file_accessed(host_file); + if (host_file->f_op->iterate_shared) { + inode_lock_shared(host_inode); + ret = host_file->f_op->iterate_shared(host_file, ctx); + file_accessed(host_file); + inode_unlock_shared(host_inode); + } else { + inode_lock(host_inode); + ret = host_file->f_op->iterate(host_file, ctx); + file_accessed(host_file); + inode_unlock(host_inode); + } } - inode_unlock(host_inode); return ret; } /* Venus: we must read Venus dirents from a file */ diff --git a/fs/compat.c b/fs/compat.c index a71936a..8754e9a 100644 --- a/fs/compat.c +++ b/fs/compat.c @@ -884,7 +884,7 @@ COMPAT_SYSCALL_DEFINE3(old_readdir, unsigned int, fd, struct compat_old_linux_dirent __user *, dirent, unsigned int, count) { int error; - struct fd f = fdget(fd); + struct fd f = fdget_pos(fd); struct compat_readdir_callback buf = { .ctx.actor = compat_fillonedir, .dirent = dirent @@ -897,7 +897,7 @@ COMPAT_SYSCALL_DEFINE3(old_readdir, unsigned int, fd, if (buf.result) error = buf.result; - fdput(f); + fdput_pos(f); return error; } @@ -975,7 +975,7 @@ COMPAT_SYSCALL_DEFINE3(getdents, unsigned int, fd, if (!access_ok(VERIFY_WRITE, dirent, count)) return -EFAULT; - f = fdget(fd); + f = fdget_pos(fd); if (!f.file) return -EBADF; @@ -989,7 +989,7 @@ COMPAT_SYSCALL_DEFINE3(getdents, unsigned int, fd, else error = count - buf.count; } - fdput(f); + fdput_pos(f); return error; } @@ -1062,7 +1062,7 @@ COMPAT_SYSCALL_DEFINE3(getdents64, unsigned int, fd, if (!access_ok(VERIFY_WRITE, dirent, count)) return -EFAULT; - f = fdget(fd); + f = fdget_pos(fd); if (!f.file) return -EBADF; @@ -1077,7 +1077,7 @@ COMPAT_SYSCALL_DEFINE3(getdents64, unsigned int, fd, else error = count - buf.count; } - fdput(f); + fdput_pos(f); return error; } #endif /* __ARCH_WANT_COMPAT_SYS_GETDENTS64 */ diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c index ea59c89..56fb261 100644 --- a/fs/configfs/dir.c +++ b/fs/configfs/dir.c @@ -494,7 +494,7 @@ out: * If there is an error, the caller will reset the flags via * configfs_detach_rollback(). */ -static int configfs_detach_prep(struct dentry *dentry, struct mutex **wait_mutex) +static int configfs_detach_prep(struct dentry *dentry, struct dentry **wait) { struct configfs_dirent *parent_sd = dentry->d_fsdata; struct configfs_dirent *sd; @@ -515,8 +515,8 @@ static int configfs_detach_prep(struct dentry *dentry, struct mutex **wait_mutex if (sd->s_type & CONFIGFS_USET_DEFAULT) { /* Abort if racing with mkdir() */ if (sd->s_type & CONFIGFS_USET_IN_MKDIR) { - if (wait_mutex) - *wait_mutex = &d_inode(sd->s_dentry)->i_mutex; + if (wait) + *wait= dget(sd->s_dentry); return -EAGAIN; } @@ -524,7 +524,7 @@ static int configfs_detach_prep(struct dentry *dentry, struct mutex **wait_mutex * Yup, recursive. If there's a problem, blame * deep nesting of default_groups */ - ret = configfs_detach_prep(sd->s_dentry, wait_mutex); + ret = configfs_detach_prep(sd->s_dentry, wait); if (!ret) continue; } else @@ -1458,7 +1458,7 @@ static int configfs_rmdir(struct inode *dir, struct dentry *dentry) * the new link is temporarily attached */ do { - struct mutex *wait_mutex; + struct dentry *wait; mutex_lock(&configfs_symlink_mutex); spin_lock(&configfs_dirent_lock); @@ -1469,7 +1469,7 @@ static int configfs_rmdir(struct inode *dir, struct dentry *dentry) */ ret = sd->s_dependent_count ? -EBUSY : 0; if (!ret) { - ret = configfs_detach_prep(dentry, &wait_mutex); + ret = configfs_detach_prep(dentry, &wait); if (ret) configfs_detach_rollback(dentry); } @@ -1483,8 +1483,9 @@ static int configfs_rmdir(struct inode *dir, struct dentry *dentry) } /* Wait until the racing operation terminates */ - mutex_lock(wait_mutex); - mutex_unlock(wait_mutex); + inode_lock(d_inode(wait)); + inode_unlock(d_inode(wait)); + dput(wait); } } while (ret == -EAGAIN); @@ -1632,11 +1633,9 @@ static int configfs_readdir(struct file *file, struct dir_context *ctx) if (!dir_emit_dots(file, ctx)) return 0; - if (ctx->pos == 2) { - spin_lock(&configfs_dirent_lock); + spin_lock(&configfs_dirent_lock); + if (ctx->pos == 2) list_move(q, &parent_sd->s_children); - spin_unlock(&configfs_dirent_lock); - } for (p = q->next; p != &parent_sd->s_children; p = p->next) { struct configfs_dirent *next; const char *name; @@ -1647,9 +1646,6 @@ static int configfs_readdir(struct file *file, struct dir_context *ctx) if (!next->s_element) continue; - name = configfs_get_name(next); - len = strlen(name); - /* * We'll have a dentry and an inode for * PINNED items and for open attribute @@ -1663,7 +1659,6 @@ static int configfs_readdir(struct file *file, struct dir_context *ctx) * they close it. Beyond that, we don't * care. */ - spin_lock(&configfs_dirent_lock); dentry = next->s_dentry; if (dentry) inode = d_inode(dentry); @@ -1673,15 +1668,18 @@ static int configfs_readdir(struct file *file, struct dir_context *ctx) if (!inode) ino = iunique(sb, 2); + name = configfs_get_name(next); + len = strlen(name); + if (!dir_emit(ctx, name, len, ino, dt_type(next))) return 0; spin_lock(&configfs_dirent_lock); list_move(q, p); - spin_unlock(&configfs_dirent_lock); p = q; ctx->pos++; } + spin_unlock(&configfs_dirent_lock); return 0; } @@ -1689,7 +1687,6 @@ static loff_t configfs_dir_lseek(struct file *file, loff_t offset, int whence) { struct dentry * dentry = file->f_path.dentry; - inode_lock(d_inode(dentry)); switch (whence) { case 1: offset += file->f_pos; @@ -1697,7 +1694,6 @@ static loff_t configfs_dir_lseek(struct file *file, loff_t offset, int whence) if (offset >= 0) break; default: - inode_unlock(d_inode(dentry)); return -EINVAL; } if (offset != file->f_pos) { @@ -1723,7 +1719,6 @@ static loff_t configfs_dir_lseek(struct file *file, loff_t offset, int whence) spin_unlock(&configfs_dirent_lock); } } - inode_unlock(d_inode(dentry)); return offset; } @@ -1732,7 +1727,7 @@ const struct file_operations configfs_dir_operations = { .release = configfs_dir_close, .llseek = configfs_dir_lseek, .read = generic_read_dir, - .iterate = configfs_readdir, + .iterate_shared = configfs_readdir, }; /** diff --git a/fs/configfs/inode.c b/fs/configfs/inode.c index 03d124a..0387968 100644 --- a/fs/configfs/inode.c +++ b/fs/configfs/inode.c @@ -156,7 +156,7 @@ static void configfs_set_inode_lock_class(struct configfs_dirent *sd, if (depth > 0) { if (depth <= ARRAY_SIZE(default_group_class)) { - lockdep_set_class(&inode->i_mutex, + lockdep_set_class(&inode->i_rwsem, &default_group_class[depth - 1]); } else { /* diff --git a/fs/coredump.c b/fs/coredump.c index 47c32c3..492c2db 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -803,12 +803,9 @@ int dump_skip(struct coredump_params *cprm, size_t nr) static char zeroes[PAGE_SIZE]; struct file *file = cprm->file; if (file->f_op->llseek && file->f_op->llseek != no_llseek) { - if (cprm->written + nr > cprm->limit) - return 0; if (dump_interrupted() || file->f_op->llseek(file, nr, SEEK_CUR) < 0) return 0; - cprm->written += nr; return 1; } else { while (nr > PAGE_SIZE) { @@ -823,7 +820,7 @@ EXPORT_SYMBOL(dump_skip); int dump_align(struct coredump_params *cprm, int align) { - unsigned mod = cprm->written & (align - 1); + unsigned mod = cprm->file->f_pos & (align - 1); if (align & (align - 1)) return 0; return mod ? dump_skip(cprm, align - mod) : 1; diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c index 3a32ddf..7919967 100644 --- a/fs/cramfs/inode.c +++ b/fs/cramfs/inode.c @@ -561,7 +561,7 @@ static const struct address_space_operations cramfs_aops = { static const struct file_operations cramfs_directory_operations = { .llseek = generic_file_llseek, .read = generic_read_dir, - .iterate = cramfs_readdir, + .iterate_shared = cramfs_readdir, }; static const struct inode_operations cramfs_dir_inode_operations = { @@ -244,7 +244,6 @@ static ssize_t dax_io(struct inode *inode, struct iov_iter *iter, * @iocb: The control block for this I/O * @inode: The file which the I/O is directed at * @iter: The addresses to do I/O from or to - * @pos: The file offset where the I/O starts * @get_block: The filesystem method used to translate file offsets to blocks * @end_io: A filesystem callback for I/O completion * @flags: See below @@ -257,11 +256,12 @@ static ssize_t dax_io(struct inode *inode, struct iov_iter *iter, * is in progress. */ ssize_t dax_do_io(struct kiocb *iocb, struct inode *inode, - struct iov_iter *iter, loff_t pos, get_block_t get_block, + struct iov_iter *iter, get_block_t get_block, dio_iodone_t end_io, int flags) { struct buffer_head bh; ssize_t retval = -EINVAL; + loff_t pos = iocb->ki_pos; loff_t end = pos + iov_iter_count(iter); memset(&bh, 0, sizeof(bh)); diff --git a/fs/dcache.c b/fs/dcache.c index d5ecc6e..c622872 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -111,6 +111,17 @@ static inline struct hlist_bl_head *d_hash(const struct dentry *parent, return dentry_hashtable + hash_32(hash, d_hash_shift); } +#define IN_LOOKUP_SHIFT 10 +static struct hlist_bl_head in_lookup_hashtable[1 << IN_LOOKUP_SHIFT]; + +static inline struct hlist_bl_head *in_lookup_hash(const struct dentry *parent, + unsigned int hash) +{ + hash += (unsigned long) parent / L1_CACHE_BYTES; + return in_lookup_hashtable + hash_32(hash, IN_LOOKUP_SHIFT); +} + + /* Statistics gathering. */ struct dentry_stat_t dentry_stat = { .age_limit = 45, @@ -761,6 +772,8 @@ repeat: /* Slow case: now with the dentry lock held */ rcu_read_unlock(); + WARN_ON(d_in_lookup(dentry)); + /* Unreachable? Get rid of it */ if (unlikely(d_unhashed(dentry))) goto kill_it; @@ -1558,7 +1571,11 @@ struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name) * be overwriting an internal NUL character */ dentry->d_iname[DNAME_INLINE_LEN-1] = 0; - if (name->len > DNAME_INLINE_LEN-1) { + if (unlikely(!name)) { + static const struct qstr anon = QSTR_INIT("/", 1); + name = &anon; + dname = dentry->d_iname; + } else if (name->len > DNAME_INLINE_LEN-1) { size_t size = offsetof(struct external_name, name[1]); struct external_name *p = kmalloc(size + name->len, GFP_KERNEL_ACCOUNT); @@ -1746,6 +1763,7 @@ type_determined: static void __d_instantiate(struct dentry *dentry, struct inode *inode) { unsigned add_flags = d_flags_for_inode(inode); + WARN_ON(d_in_lookup(dentry)); spin_lock(&dentry->d_lock); hlist_add_head(&dentry->d_u.d_alias, &inode->i_dentry); @@ -1775,11 +1793,11 @@ void d_instantiate(struct dentry *entry, struct inode * inode) { BUG_ON(!hlist_unhashed(&entry->d_u.d_alias)); if (inode) { + security_d_instantiate(entry, inode); spin_lock(&inode->i_lock); __d_instantiate(entry, inode); spin_unlock(&inode->i_lock); } - security_d_instantiate(entry, inode); } EXPORT_SYMBOL(d_instantiate); @@ -1796,6 +1814,7 @@ int d_instantiate_no_diralias(struct dentry *entry, struct inode *inode) { BUG_ON(!hlist_unhashed(&entry->d_u.d_alias)); + security_d_instantiate(entry, inode); spin_lock(&inode->i_lock); if (S_ISDIR(inode->i_mode) && !hlist_empty(&inode->i_dentry)) { spin_unlock(&inode->i_lock); @@ -1804,7 +1823,6 @@ int d_instantiate_no_diralias(struct dentry *entry, struct inode *inode) } __d_instantiate(entry, inode); spin_unlock(&inode->i_lock); - security_d_instantiate(entry, inode); return 0; } @@ -1815,9 +1833,7 @@ struct dentry *d_make_root(struct inode *root_inode) struct dentry *res = NULL; if (root_inode) { - static const struct qstr name = QSTR_INIT("/", 1); - - res = __d_alloc(root_inode->i_sb, &name); + res = __d_alloc(root_inode->i_sb, NULL); if (res) d_instantiate(res, root_inode); else @@ -1858,7 +1874,6 @@ EXPORT_SYMBOL(d_find_any_alias); static struct dentry *__d_obtain_alias(struct inode *inode, int disconnected) { - static const struct qstr anonstring = QSTR_INIT("/", 1); struct dentry *tmp; struct dentry *res; unsigned add_flags; @@ -1872,12 +1887,13 @@ static struct dentry *__d_obtain_alias(struct inode *inode, int disconnected) if (res) goto out_iput; - tmp = __d_alloc(inode->i_sb, &anonstring); + tmp = __d_alloc(inode->i_sb, NULL); if (!tmp) { res = ERR_PTR(-ENOMEM); goto out_iput; } + security_d_instantiate(tmp, inode); spin_lock(&inode->i_lock); res = __d_find_any_alias(inode); if (res) { @@ -1900,13 +1916,10 @@ static struct dentry *__d_obtain_alias(struct inode *inode, int disconnected) hlist_bl_unlock(&tmp->d_sb->s_anon); spin_unlock(&tmp->d_lock); spin_unlock(&inode->i_lock); - security_d_instantiate(tmp, inode); return tmp; out_iput: - if (res && !IS_ERR(res)) - security_d_instantiate(res, inode); iput(inode); return res; } @@ -1975,28 +1988,36 @@ EXPORT_SYMBOL(d_obtain_root); struct dentry *d_add_ci(struct dentry *dentry, struct inode *inode, struct qstr *name) { - struct dentry *found; - struct dentry *new; + struct dentry *found, *res; /* * First check if a dentry matching the name already exists, * if not go ahead and create it now. */ found = d_hash_and_lookup(dentry->d_parent, name); - if (!found) { - new = d_alloc(dentry->d_parent, name); - if (!new) { - found = ERR_PTR(-ENOMEM); - } else { - found = d_splice_alias(inode, new); - if (found) { - dput(new); - return found; - } - return new; + if (found) { + iput(inode); + return found; + } + if (d_in_lookup(dentry)) { + found = d_alloc_parallel(dentry->d_parent, name, + dentry->d_wait); + if (IS_ERR(found) || !d_in_lookup(found)) { + iput(inode); + return found; } + } else { + found = d_alloc(dentry->d_parent, name); + if (!found) { + iput(inode); + return ERR_PTR(-ENOMEM); + } + } + res = d_splice_alias(inode, found); + if (res) { + dput(found); + return res; } - iput(inode); return found; } EXPORT_SYMBOL(d_add_ci); @@ -2363,17 +2384,194 @@ void d_rehash(struct dentry * entry) } EXPORT_SYMBOL(d_rehash); +static inline unsigned start_dir_add(struct inode *dir) +{ + + for (;;) { + unsigned n = dir->i_dir_seq; + if (!(n & 1) && cmpxchg(&dir->i_dir_seq, n, n + 1) == n) + return n; + cpu_relax(); + } +} + +static inline void end_dir_add(struct inode *dir, unsigned n) +{ + smp_store_release(&dir->i_dir_seq, n + 2); +} + +static void d_wait_lookup(struct dentry *dentry) +{ + if (d_in_lookup(dentry)) { + DECLARE_WAITQUEUE(wait, current); + add_wait_queue(dentry->d_wait, &wait); + do { + set_current_state(TASK_UNINTERRUPTIBLE); + spin_unlock(&dentry->d_lock); + schedule(); + spin_lock(&dentry->d_lock); + } while (d_in_lookup(dentry)); + } +} + +struct dentry *d_alloc_parallel(struct dentry *parent, + const struct qstr *name, + wait_queue_head_t *wq) +{ + unsigned int len = name->len; + unsigned int hash = name->hash; + const unsigned char *str = name->name; + struct hlist_bl_head *b = in_lookup_hash(parent, hash); + struct hlist_bl_node *node; + struct dentry *new = d_alloc(parent, name); + struct dentry *dentry; + unsigned seq, r_seq, d_seq; + + if (unlikely(!new)) + return ERR_PTR(-ENOMEM); + +retry: + rcu_read_lock(); + seq = smp_load_acquire(&parent->d_inode->i_dir_seq) & ~1; + r_seq = read_seqbegin(&rename_lock); + dentry = __d_lookup_rcu(parent, name, &d_seq); + if (unlikely(dentry)) { + if (!lockref_get_not_dead(&dentry->d_lockref)) { + rcu_read_unlock(); + goto retry; + } + if (read_seqcount_retry(&dentry->d_seq, d_seq)) { + rcu_read_unlock(); + dput(dentry); + goto retry; + } + rcu_read_unlock(); + dput(new); + return dentry; + } + if (unlikely(read_seqretry(&rename_lock, r_seq))) { + rcu_read_unlock(); + goto retry; + } + hlist_bl_lock(b); + if (unlikely(parent->d_inode->i_dir_seq != seq)) { + hlist_bl_unlock(b); + rcu_read_unlock(); + goto retry; + } + rcu_read_unlock(); + /* + * No changes for the parent since the beginning of d_lookup(). + * Since all removals from the chain happen with hlist_bl_lock(), + * any potential in-lookup matches are going to stay here until + * we unlock the chain. All fields are stable in everything + * we encounter. + */ + hlist_bl_for_each_entry(dentry, node, b, d_u.d_in_lookup_hash) { + if (dentry->d_name.hash != hash) + continue; + if (dentry->d_parent != parent) + continue; + if (d_unhashed(dentry)) + continue; + if (parent->d_flags & DCACHE_OP_COMPARE) { + int tlen = dentry->d_name.len; + const char *tname = dentry->d_name.name; + if (parent->d_op->d_compare(parent, dentry, tlen, tname, name)) + continue; + } else { + if (dentry->d_name.len != len) + continue; + if (dentry_cmp(dentry, str, len)) + continue; + } + dget(dentry); + hlist_bl_unlock(b); + /* somebody is doing lookup for it right now; wait for it */ + spin_lock(&dentry->d_lock); + d_wait_lookup(dentry); + /* + * it's not in-lookup anymore; in principle we should repeat + * everything from dcache lookup, but it's likely to be what + * d_lookup() would've found anyway. If it is, just return it; + * otherwise we really have to repeat the whole thing. + */ + if (unlikely(dentry->d_name.hash != hash)) + goto mismatch; + if (unlikely(dentry->d_parent != parent)) + goto mismatch; + if (unlikely(d_unhashed(dentry))) + goto mismatch; + if (parent->d_flags & DCACHE_OP_COMPARE) { + int tlen = dentry->d_name.len; + const char *tname = dentry->d_name.name; + if (parent->d_op->d_compare(parent, dentry, tlen, tname, name)) + goto mismatch; + } else { + if (unlikely(dentry->d_name.len != len)) + goto mismatch; + if (unlikely(dentry_cmp(dentry, str, len))) + goto mismatch; + } + /* OK, it *is* a hashed match; return it */ + spin_unlock(&dentry->d_lock); + dput(new); + return dentry; + } + /* we can't take ->d_lock here; it's OK, though. */ + new->d_flags |= DCACHE_PAR_LOOKUP; + new->d_wait = wq; + hlist_bl_add_head_rcu(&new->d_u.d_in_lookup_hash, b); + hlist_bl_unlock(b); + return new; +mismatch: + spin_unlock(&dentry->d_lock); + dput(dentry); + goto retry; +} +EXPORT_SYMBOL(d_alloc_parallel); + +void __d_lookup_done(struct dentry *dentry) +{ + struct hlist_bl_head *b = in_lookup_hash(dentry->d_parent, + dentry->d_name.hash); + hlist_bl_lock(b); + dentry->d_flags &= ~DCACHE_PAR_LOOKUP; + __hlist_bl_del(&dentry->d_u.d_in_lookup_hash); + wake_up_all(dentry->d_wait); + dentry->d_wait = NULL; + hlist_bl_unlock(b); + INIT_HLIST_NODE(&dentry->d_u.d_alias); + INIT_LIST_HEAD(&dentry->d_lru); +} +EXPORT_SYMBOL(__d_lookup_done); /* inode->i_lock held if inode is non-NULL */ static inline void __d_add(struct dentry *dentry, struct inode *inode) { + struct inode *dir = NULL; + unsigned n; + spin_lock(&dentry->d_lock); + if (unlikely(d_in_lookup(dentry))) { + dir = dentry->d_parent->d_inode; + n = start_dir_add(dir); + __d_lookup_done(dentry); + } if (inode) { - __d_instantiate(dentry, inode); + unsigned add_flags = d_flags_for_inode(inode); + hlist_add_head(&dentry->d_u.d_alias, &inode->i_dentry); + raw_write_seqcount_begin(&dentry->d_seq); + __d_set_inode_and_type(dentry, inode, add_flags); + raw_write_seqcount_end(&dentry->d_seq); + __fsnotify_d_instantiate(dentry); + } + _d_rehash(dentry); + if (dir) + end_dir_add(dir, n); + spin_unlock(&dentry->d_lock); + if (inode) spin_unlock(&inode->i_lock); - } - security_d_instantiate(dentry, inode); - d_rehash(dentry); } /** @@ -2387,8 +2585,10 @@ static inline void __d_add(struct dentry *dentry, struct inode *inode) void d_add(struct dentry *entry, struct inode *inode) { - if (inode) + if (inode) { + security_d_instantiate(entry, inode); spin_lock(&inode->i_lock); + } __d_add(entry, inode); } EXPORT_SYMBOL(d_add); @@ -2598,6 +2798,8 @@ static void dentry_unlock_for_move(struct dentry *dentry, struct dentry *target) static void __d_move(struct dentry *dentry, struct dentry *target, bool exchange) { + struct inode *dir = NULL; + unsigned n; if (!dentry->d_inode) printk(KERN_WARNING "VFS: moving negative dcache entry\n"); @@ -2605,6 +2807,11 @@ static void __d_move(struct dentry *dentry, struct dentry *target, BUG_ON(d_ancestor(target, dentry)); dentry_lock_for_move(dentry, target); + if (unlikely(d_in_lookup(target))) { + dir = target->d_parent->d_inode; + n = start_dir_add(dir); + __d_lookup_done(target); + } write_seqcount_begin(&dentry->d_seq); write_seqcount_begin_nested(&target->d_seq, DENTRY_D_LOCK_NESTED); @@ -2654,6 +2861,8 @@ static void __d_move(struct dentry *dentry, struct dentry *target, write_seqcount_end(&target->d_seq); write_seqcount_end(&dentry->d_seq); + if (dir) + end_dir_add(dir, n); dentry_unlock_for_move(dentry, target); } @@ -2724,7 +2933,8 @@ struct dentry *d_ancestor(struct dentry *p1, struct dentry *p2) static int __d_unalias(struct inode *inode, struct dentry *dentry, struct dentry *alias) { - struct mutex *m1 = NULL, *m2 = NULL; + struct mutex *m1 = NULL; + struct rw_semaphore *m2 = NULL; int ret = -ESTALE; /* If alias and dentry share a parent, then no extra locks required */ @@ -2735,15 +2945,15 @@ static int __d_unalias(struct inode *inode, if (!mutex_trylock(&dentry->d_sb->s_vfs_rename_mutex)) goto out_err; m1 = &dentry->d_sb->s_vfs_rename_mutex; - if (!inode_trylock(alias->d_parent->d_inode)) + if (!inode_trylock_shared(alias->d_parent->d_inode)) goto out_err; - m2 = &alias->d_parent->d_inode->i_mutex; + m2 = &alias->d_parent->d_inode->i_rwsem; out_unalias: __d_move(alias, dentry, false); ret = 0; out_err: if (m2) - mutex_unlock(m2); + up_read(m2); if (m1) mutex_unlock(m1); return ret; @@ -2782,6 +2992,7 @@ struct dentry *d_splice_alias(struct inode *inode, struct dentry *dentry) if (!inode) goto out; + security_d_instantiate(dentry, inode); spin_lock(&inode->i_lock); if (S_ISDIR(inode->i_mode)) { struct dentry *new = __d_find_any_alias(inode); @@ -2809,7 +3020,6 @@ struct dentry *d_splice_alias(struct inode *inode, struct dentry *dentry) } else { __d_move(new, dentry, false); write_sequnlock(&rename_lock); - security_d_instantiate(new, inode); } iput(inode); return new; diff --git a/fs/direct-io.c b/fs/direct-io.c index 4720377..3bf3f20 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -224,9 +224,9 @@ static inline struct page *dio_get_page(struct dio *dio, * filesystems can use it to hold additional state between get_block calls and * dio_complete. */ -static ssize_t dio_complete(struct dio *dio, loff_t offset, ssize_t ret, - bool is_async) +static ssize_t dio_complete(struct dio *dio, ssize_t ret, bool is_async) { + loff_t offset = dio->iocb->ki_pos; ssize_t transferred = 0; /* @@ -256,6 +256,7 @@ static ssize_t dio_complete(struct dio *dio, loff_t offset, ssize_t ret, if (dio->end_io) { int err; + // XXX: ki_pos?? err = dio->end_io(dio->iocb, offset, ret, dio->private); if (err) ret = err; @@ -265,15 +266,15 @@ static ssize_t dio_complete(struct dio *dio, loff_t offset, ssize_t ret, inode_dio_end(dio->inode); if (is_async) { - if (dio->rw & WRITE) { - int err; - - err = generic_write_sync(dio->iocb->ki_filp, offset, - transferred); - if (err < 0 && ret > 0) - ret = err; - } + /* + * generic_write_sync expects ki_pos to have been updated + * already, but the submission path only does this for + * synchronous I/O. + */ + dio->iocb->ki_pos += transferred; + if (dio->rw & WRITE) + ret = generic_write_sync(dio->iocb, transferred); dio->iocb->ki_complete(dio->iocb, ret, 0); } @@ -285,7 +286,7 @@ static void dio_aio_complete_work(struct work_struct *work) { struct dio *dio = container_of(work, struct dio, complete_work); - dio_complete(dio, dio->iocb->ki_pos, 0, true); + dio_complete(dio, 0, true); } static int dio_bio_complete(struct dio *dio, struct bio *bio); @@ -314,7 +315,7 @@ static void dio_bio_end_aio(struct bio *bio) queue_work(dio->inode->i_sb->s_dio_done_wq, &dio->complete_work); } else { - dio_complete(dio, dio->iocb->ki_pos, 0, true); + dio_complete(dio, 0, true); } } } @@ -1113,7 +1114,7 @@ static inline int drop_refcount(struct dio *dio) static inline ssize_t do_blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, struct block_device *bdev, struct iov_iter *iter, - loff_t offset, get_block_t get_block, dio_iodone_t end_io, + get_block_t get_block, dio_iodone_t end_io, dio_submit_t submit_io, int flags) { unsigned i_blkbits = ACCESS_ONCE(inode->i_blkbits); @@ -1121,6 +1122,7 @@ do_blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, unsigned blocksize_mask = (1 << blkbits) - 1; ssize_t retval = -EINVAL; size_t count = iov_iter_count(iter); + loff_t offset = iocb->ki_pos; loff_t end = offset + count; struct dio *dio; struct dio_submit sdio = { 0, }; @@ -1318,7 +1320,7 @@ do_blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, dio_await_completion(dio); if (drop_refcount(dio) == 0) { - retval = dio_complete(dio, offset, retval, false); + retval = dio_complete(dio, retval, false); } else BUG_ON(retval != -EIOCBQUEUED); @@ -1328,7 +1330,7 @@ out: ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, struct block_device *bdev, struct iov_iter *iter, - loff_t offset, get_block_t get_block, + get_block_t get_block, dio_iodone_t end_io, dio_submit_t submit_io, int flags) { @@ -1344,7 +1346,7 @@ ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, prefetch(bdev->bd_queue); prefetch((char *)bdev->bd_queue + SMP_CACHE_BYTES); - return do_blockdev_direct_IO(iocb, inode, bdev, iter, offset, get_block, + return do_blockdev_direct_IO(iocb, inode, bdev, iter, get_block, end_io, submit_io, flags); } diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c index d09cb4c..ebd40f4 100644 --- a/fs/ecryptfs/crypto.c +++ b/fs/ecryptfs/crypto.c @@ -105,19 +105,7 @@ static int ecryptfs_calculate_md5(char *dst, struct crypto_shash *tfm; int rc = 0; - mutex_lock(&crypt_stat->cs_hash_tfm_mutex); tfm = crypt_stat->hash_tfm; - if (!tfm) { - tfm = crypto_alloc_shash(ECRYPTFS_DEFAULT_HASH, 0, 0); - if (IS_ERR(tfm)) { - rc = PTR_ERR(tfm); - ecryptfs_printk(KERN_ERR, "Error attempting to " - "allocate crypto context; rc = [%d]\n", - rc); - goto out; - } - crypt_stat->hash_tfm = tfm; - } rc = ecryptfs_hash_digest(tfm, src, len, dst); if (rc) { printk(KERN_ERR @@ -126,7 +114,6 @@ static int ecryptfs_calculate_md5(char *dst, goto out; } out: - mutex_unlock(&crypt_stat->cs_hash_tfm_mutex); return rc; } @@ -207,16 +194,29 @@ out: * * Initialize the crypt_stat structure. */ -void -ecryptfs_init_crypt_stat(struct ecryptfs_crypt_stat *crypt_stat) +int ecryptfs_init_crypt_stat(struct ecryptfs_crypt_stat *crypt_stat) { + struct crypto_shash *tfm; + int rc; + + tfm = crypto_alloc_shash(ECRYPTFS_DEFAULT_HASH, 0, 0); + if (IS_ERR(tfm)) { + rc = PTR_ERR(tfm); + ecryptfs_printk(KERN_ERR, "Error attempting to " + "allocate crypto context; rc = [%d]\n", + rc); + return rc; + } + memset((void *)crypt_stat, 0, sizeof(struct ecryptfs_crypt_stat)); INIT_LIST_HEAD(&crypt_stat->keysig_list); mutex_init(&crypt_stat->keysig_list_mutex); mutex_init(&crypt_stat->cs_mutex); mutex_init(&crypt_stat->cs_tfm_mutex); - mutex_init(&crypt_stat->cs_hash_tfm_mutex); + crypt_stat->hash_tfm = tfm; crypt_stat->flags |= ECRYPTFS_STRUCT_INITIALIZED; + + return 0; } /** @@ -1369,7 +1369,9 @@ int ecryptfs_read_xattr_region(char *page_virt, struct inode *ecryptfs_inode) ssize_t size; int rc = 0; - size = ecryptfs_getxattr_lower(lower_dentry, ECRYPTFS_XATTR_NAME, + size = ecryptfs_getxattr_lower(lower_dentry, + ecryptfs_inode_to_lower(ecryptfs_inode), + ECRYPTFS_XATTR_NAME, page_virt, ECRYPTFS_DEFAULT_EXTENT_SIZE); if (size < 0) { if (unlikely(ecryptfs_verbosity > 0)) @@ -1391,6 +1393,7 @@ int ecryptfs_read_and_validate_xattr_region(struct dentry *dentry, int rc; rc = ecryptfs_getxattr_lower(ecryptfs_dentry_to_lower(dentry), + ecryptfs_inode_to_lower(inode), ECRYPTFS_XATTR_NAME, file_size, ECRYPTFS_SIZE_AND_MARKER_BYTES); if (rc < ECRYPTFS_SIZE_AND_MARKER_BYTES) diff --git a/fs/ecryptfs/ecryptfs_kernel.h b/fs/ecryptfs/ecryptfs_kernel.h index d123fba..3ec495d 100644 --- a/fs/ecryptfs/ecryptfs_kernel.h +++ b/fs/ecryptfs/ecryptfs_kernel.h @@ -242,7 +242,6 @@ struct ecryptfs_crypt_stat { struct list_head keysig_list; struct mutex keysig_list_mutex; struct mutex cs_tfm_mutex; - struct mutex cs_hash_tfm_mutex; struct mutex cs_mutex; }; @@ -577,7 +576,7 @@ int virt_to_scatterlist(const void *addr, int size, struct scatterlist *sg, int sg_size); int ecryptfs_compute_root_iv(struct ecryptfs_crypt_stat *crypt_stat); void ecryptfs_rotate_iv(unsigned char *iv); -void ecryptfs_init_crypt_stat(struct ecryptfs_crypt_stat *crypt_stat); +int ecryptfs_init_crypt_stat(struct ecryptfs_crypt_stat *crypt_stat); void ecryptfs_destroy_crypt_stat(struct ecryptfs_crypt_stat *crypt_stat); void ecryptfs_destroy_mount_crypt_stat( struct ecryptfs_mount_crypt_stat *mount_crypt_stat); @@ -607,8 +606,8 @@ ecryptfs_parse_packet_set(struct ecryptfs_crypt_stat *crypt_stat, unsigned char *src, struct dentry *ecryptfs_dentry); int ecryptfs_truncate(struct dentry *dentry, loff_t new_length); ssize_t -ecryptfs_getxattr_lower(struct dentry *lower_dentry, const char *name, - void *value, size_t size); +ecryptfs_getxattr_lower(struct dentry *lower_dentry, struct inode *lower_inode, + const char *name, void *value, size_t size); int ecryptfs_setxattr(struct dentry *dentry, const char *name, const void *value, size_t size, int flags); diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c index feef8a9..7000b96 100644 --- a/fs/ecryptfs/file.c +++ b/fs/ecryptfs/file.c @@ -112,7 +112,6 @@ static int ecryptfs_readdir(struct file *file, struct dir_context *ctx) .sb = inode->i_sb, }; lower_file = ecryptfs_file_to_lower(file); - lower_file->f_pos = ctx->pos; rc = iterate_dir(lower_file, &buf.ctx); ctx->pos = buf.ctx.pos; if (rc < 0) @@ -223,14 +222,6 @@ static int ecryptfs_open(struct inode *inode, struct file *file) } ecryptfs_set_file_lower( file, ecryptfs_inode_to_private(inode)->lower_file); - if (d_is_dir(ecryptfs_dentry)) { - ecryptfs_printk(KERN_DEBUG, "This is a directory\n"); - mutex_lock(&crypt_stat->cs_mutex); - crypt_stat->flags &= ~(ECRYPTFS_ENCRYPTED); - mutex_unlock(&crypt_stat->cs_mutex); - rc = 0; - goto out; - } rc = read_or_initialize_metadata(ecryptfs_dentry); if (rc) goto out_put; @@ -247,6 +238,45 @@ out: return rc; } +/** + * ecryptfs_dir_open + * @inode: inode speciying file to open + * @file: Structure to return filled in + * + * Opens the file specified by inode. + * + * Returns zero on success; non-zero otherwise + */ +static int ecryptfs_dir_open(struct inode *inode, struct file *file) +{ + struct dentry *ecryptfs_dentry = file->f_path.dentry; + /* Private value of ecryptfs_dentry allocated in + * ecryptfs_lookup() */ + struct ecryptfs_file_info *file_info; + struct file *lower_file; + + /* Released in ecryptfs_release or end of function if failure */ + file_info = kmem_cache_zalloc(ecryptfs_file_info_cache, GFP_KERNEL); + ecryptfs_set_file_private(file, file_info); + if (unlikely(!file_info)) { + ecryptfs_printk(KERN_ERR, + "Error attempting to allocate memory\n"); + return -ENOMEM; + } + lower_file = dentry_open(ecryptfs_dentry_to_lower_path(ecryptfs_dentry), + file->f_flags, current_cred()); + if (IS_ERR(lower_file)) { + printk(KERN_ERR "%s: Error attempting to initialize " + "the lower file for the dentry with name " + "[%pd]; rc = [%ld]\n", __func__, + ecryptfs_dentry, PTR_ERR(lower_file)); + kmem_cache_free(ecryptfs_file_info_cache, file_info); + return PTR_ERR(lower_file); + } + ecryptfs_set_file_lower(file, lower_file); + return 0; +} + static int ecryptfs_flush(struct file *file, fl_owner_t td) { struct file *lower_file = ecryptfs_file_to_lower(file); @@ -267,6 +297,19 @@ static int ecryptfs_release(struct inode *inode, struct file *file) return 0; } +static int ecryptfs_dir_release(struct inode *inode, struct file *file) +{ + fput(ecryptfs_file_to_lower(file)); + kmem_cache_free(ecryptfs_file_info_cache, + ecryptfs_file_to_private(file)); + return 0; +} + +static loff_t ecryptfs_dir_llseek(struct file *file, loff_t offset, int whence) +{ + return vfs_llseek(ecryptfs_file_to_lower(file), offset, whence); +} + static int ecryptfs_fsync(struct file *file, loff_t start, loff_t end, int datasync) { @@ -340,26 +383,22 @@ ecryptfs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) #endif const struct file_operations ecryptfs_dir_fops = { - .iterate = ecryptfs_readdir, + .iterate_shared = ecryptfs_readdir, .read = generic_read_dir, .unlocked_ioctl = ecryptfs_unlocked_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = ecryptfs_compat_ioctl, #endif - .open = ecryptfs_open, - .flush = ecryptfs_flush, - .release = ecryptfs_release, + .open = ecryptfs_dir_open, + .release = ecryptfs_dir_release, .fsync = ecryptfs_fsync, - .fasync = ecryptfs_fasync, - .splice_read = generic_file_splice_read, - .llseek = default_llseek, + .llseek = ecryptfs_dir_llseek, }; const struct file_operations ecryptfs_main_fops = { .llseek = generic_file_llseek, .read_iter = ecryptfs_read_update_atime, .write_iter = generic_file_write_iter, - .iterate = ecryptfs_readdir, .unlocked_ioctl = ecryptfs_unlocked_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = ecryptfs_compat_ioctl, diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c index 224b49e..318b046 100644 --- a/fs/ecryptfs/inode.c +++ b/fs/ecryptfs/inode.c @@ -324,9 +324,8 @@ static int ecryptfs_i_size_read(struct dentry *dentry, struct inode *inode) /** * ecryptfs_lookup_interpose - Dentry interposition for a lookup */ -static int ecryptfs_lookup_interpose(struct dentry *dentry, - struct dentry *lower_dentry, - struct inode *dir_inode) +static struct dentry *ecryptfs_lookup_interpose(struct dentry *dentry, + struct dentry *lower_dentry) { struct inode *inode, *lower_inode = d_inode(lower_dentry); struct ecryptfs_dentry_info *dentry_info; @@ -339,11 +338,12 @@ static int ecryptfs_lookup_interpose(struct dentry *dentry, "to allocate ecryptfs_dentry_info struct\n", __func__); dput(lower_dentry); - return -ENOMEM; + return ERR_PTR(-ENOMEM); } lower_mnt = mntget(ecryptfs_dentry_to_lower_mnt(dentry->d_parent)); - fsstack_copy_attr_atime(dir_inode, d_inode(lower_dentry->d_parent)); + fsstack_copy_attr_atime(d_inode(dentry->d_parent), + d_inode(lower_dentry->d_parent)); BUG_ON(!d_count(lower_dentry)); ecryptfs_set_dentry_private(dentry, dentry_info); @@ -353,27 +353,25 @@ static int ecryptfs_lookup_interpose(struct dentry *dentry, if (d_really_is_negative(lower_dentry)) { /* We want to add because we couldn't find in lower */ d_add(dentry, NULL); - return 0; + return NULL; } - inode = __ecryptfs_get_inode(lower_inode, dir_inode->i_sb); + inode = __ecryptfs_get_inode(lower_inode, dentry->d_sb); if (IS_ERR(inode)) { printk(KERN_ERR "%s: Error interposing; rc = [%ld]\n", __func__, PTR_ERR(inode)); - return PTR_ERR(inode); + return ERR_CAST(inode); } if (S_ISREG(inode->i_mode)) { rc = ecryptfs_i_size_read(dentry, inode); if (rc) { make_bad_inode(inode); - return rc; + return ERR_PTR(rc); } } if (inode->i_state & I_NEW) unlock_new_inode(inode); - d_add(dentry, inode); - - return rc; + return d_splice_alias(inode, dentry); } /** @@ -390,55 +388,42 @@ static struct dentry *ecryptfs_lookup(struct inode *ecryptfs_dir_inode, unsigned int flags) { char *encrypted_and_encoded_name = NULL; - size_t encrypted_and_encoded_name_size; - struct ecryptfs_mount_crypt_stat *mount_crypt_stat = NULL; + struct ecryptfs_mount_crypt_stat *mount_crypt_stat; struct dentry *lower_dir_dentry, *lower_dentry; + const char *name = ecryptfs_dentry->d_name.name; + size_t len = ecryptfs_dentry->d_name.len; + struct dentry *res; int rc = 0; lower_dir_dentry = ecryptfs_dentry_to_lower(ecryptfs_dentry->d_parent); - lower_dentry = lookup_one_len_unlocked(ecryptfs_dentry->d_name.name, - lower_dir_dentry, - ecryptfs_dentry->d_name.len); - if (IS_ERR(lower_dentry)) { - rc = PTR_ERR(lower_dentry); - ecryptfs_printk(KERN_DEBUG, "%s: lookup_one_len() returned " - "[%d] on lower_dentry = [%pd]\n", __func__, rc, - ecryptfs_dentry); - goto out; - } - if (d_really_is_positive(lower_dentry)) - goto interpose; + mount_crypt_stat = &ecryptfs_superblock_to_private( ecryptfs_dentry->d_sb)->mount_crypt_stat; - if (!(mount_crypt_stat - && (mount_crypt_stat->flags & ECRYPTFS_GLOBAL_ENCRYPT_FILENAMES))) - goto interpose; - dput(lower_dentry); - rc = ecryptfs_encrypt_and_encode_filename( - &encrypted_and_encoded_name, &encrypted_and_encoded_name_size, - mount_crypt_stat, ecryptfs_dentry->d_name.name, - ecryptfs_dentry->d_name.len); - if (rc) { - printk(KERN_ERR "%s: Error attempting to encrypt and encode " - "filename; rc = [%d]\n", __func__, rc); - goto out; + if (mount_crypt_stat + && (mount_crypt_stat->flags & ECRYPTFS_GLOBAL_ENCRYPT_FILENAMES)) { + rc = ecryptfs_encrypt_and_encode_filename( + &encrypted_and_encoded_name, &len, + mount_crypt_stat, name, len); + if (rc) { + printk(KERN_ERR "%s: Error attempting to encrypt and encode " + "filename; rc = [%d]\n", __func__, rc); + return ERR_PTR(rc); + } + name = encrypted_and_encoded_name; } - lower_dentry = lookup_one_len_unlocked(encrypted_and_encoded_name, - lower_dir_dentry, - encrypted_and_encoded_name_size); + + lower_dentry = lookup_one_len_unlocked(name, lower_dir_dentry, len); if (IS_ERR(lower_dentry)) { - rc = PTR_ERR(lower_dentry); ecryptfs_printk(KERN_DEBUG, "%s: lookup_one_len() returned " - "[%d] on lower_dentry = [%s]\n", __func__, rc, - encrypted_and_encoded_name); - goto out; + "[%ld] on lower_dentry = [%s]\n", __func__, + PTR_ERR(lower_dentry), + name); + res = ERR_CAST(lower_dentry); + } else { + res = ecryptfs_lookup_interpose(ecryptfs_dentry, lower_dentry); } -interpose: - rc = ecryptfs_lookup_interpose(ecryptfs_dentry, lower_dentry, - ecryptfs_dir_inode); -out: kfree(encrypted_and_encoded_name); - return ERR_PTR(rc); + return res; } static int ecryptfs_link(struct dentry *old_dentry, struct inode *dir, @@ -898,8 +883,11 @@ static int ecryptfs_setattr(struct dentry *dentry, struct iattr *ia) struct ecryptfs_crypt_stat *crypt_stat; crypt_stat = &ecryptfs_inode_to_private(d_inode(dentry))->crypt_stat; - if (!(crypt_stat->flags & ECRYPTFS_STRUCT_INITIALIZED)) - ecryptfs_init_crypt_stat(crypt_stat); + if (!(crypt_stat->flags & ECRYPTFS_STRUCT_INITIALIZED)) { + rc = ecryptfs_init_crypt_stat(crypt_stat); + if (rc) + return rc; + } inode = d_inode(dentry); lower_inode = ecryptfs_inode_to_lower(inode); lower_dentry = ecryptfs_dentry_to_lower(dentry); @@ -1033,29 +1021,30 @@ out: } ssize_t -ecryptfs_getxattr_lower(struct dentry *lower_dentry, const char *name, - void *value, size_t size) +ecryptfs_getxattr_lower(struct dentry *lower_dentry, struct inode *lower_inode, + const char *name, void *value, size_t size) { int rc = 0; - if (!d_inode(lower_dentry)->i_op->getxattr) { + if (!lower_inode->i_op->getxattr) { rc = -EOPNOTSUPP; goto out; } - inode_lock(d_inode(lower_dentry)); - rc = d_inode(lower_dentry)->i_op->getxattr(lower_dentry, name, value, - size); - inode_unlock(d_inode(lower_dentry)); + inode_lock(lower_inode); + rc = lower_inode->i_op->getxattr(lower_dentry, lower_inode, + name, value, size); + inode_unlock(lower_inode); out: return rc; } static ssize_t -ecryptfs_getxattr(struct dentry *dentry, const char *name, void *value, - size_t size) +ecryptfs_getxattr(struct dentry *dentry, struct inode *inode, + const char *name, void *value, size_t size) { - return ecryptfs_getxattr_lower(ecryptfs_dentry_to_lower(dentry), name, - value, size); + return ecryptfs_getxattr_lower(ecryptfs_dentry_to_lower(dentry), + ecryptfs_inode_to_lower(inode), + name, value, size); } static ssize_t diff --git a/fs/ecryptfs/mmap.c b/fs/ecryptfs/mmap.c index e6b1d80..148d11b 100644 --- a/fs/ecryptfs/mmap.c +++ b/fs/ecryptfs/mmap.c @@ -436,7 +436,8 @@ static int ecryptfs_write_inode_size_to_xattr(struct inode *ecryptfs_inode) goto out; } inode_lock(lower_inode); - size = lower_inode->i_op->getxattr(lower_dentry, ECRYPTFS_XATTR_NAME, + size = lower_inode->i_op->getxattr(lower_dentry, lower_inode, + ECRYPTFS_XATTR_NAME, xattr_virt, PAGE_SIZE); if (size < 0) size = 8; diff --git a/fs/ecryptfs/super.c b/fs/ecryptfs/super.c index 77a486d..85411ce 100644 --- a/fs/ecryptfs/super.c +++ b/fs/ecryptfs/super.c @@ -55,7 +55,10 @@ static struct inode *ecryptfs_alloc_inode(struct super_block *sb) inode_info = kmem_cache_alloc(ecryptfs_inode_info_cache, GFP_KERNEL); if (unlikely(!inode_info)) goto out; - ecryptfs_init_crypt_stat(&inode_info->crypt_stat); + if (ecryptfs_init_crypt_stat(&inode_info->crypt_stat)) { + kmem_cache_free(ecryptfs_inode_info_cache, inode_info); + goto out; + } mutex_init(&inode_info->lower_file_mutex); atomic_set(&inode_info->lower_file_count, 0); inode_info->lower_file = NULL; diff --git a/fs/efivarfs/file.c b/fs/efivarfs/file.c index d48e0d2..5f22e74 100644 --- a/fs/efivarfs/file.c +++ b/fs/efivarfs/file.c @@ -157,7 +157,7 @@ efivarfs_ioc_setxflags(struct file *file, void __user *arg) return 0; } -long +static long efivarfs_file_ioctl(struct file *file, unsigned int cmd, unsigned long p) { void __user *arg = (void __user *)p; diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c index 553c5d2..9cb54a3 100644 --- a/fs/efivarfs/super.c +++ b/fs/efivarfs/super.c @@ -216,8 +216,7 @@ static int efivarfs_fill_super(struct super_block *sb, void *data, int silent) INIT_LIST_HEAD(&efivarfs_list); - err = efivar_init(efivarfs_callback, (void *)sb, false, - true, &efivarfs_list); + err = efivar_init(efivarfs_callback, (void *)sb, true, &efivarfs_list); if (err) __efivar_entry_iter(efivarfs_destroy, &efivarfs_list, NULL, NULL); diff --git a/fs/efs/dir.c b/fs/efs/dir.c index ce63b24..a7be96e 100644 --- a/fs/efs/dir.c +++ b/fs/efs/dir.c @@ -12,7 +12,7 @@ static int efs_readdir(struct file *, struct dir_context *); const struct file_operations efs_dir_operations = { .llseek = generic_file_llseek, .read = generic_read_dir, - .iterate = efs_readdir, + .iterate_shared = efs_readdir, }; const struct inode_operations efs_dir_inode_operations = { @@ -100,4 +100,3 @@ static int efs_readdir(struct file *file, struct dir_context *ctx) ctx->pos = (block << EFS_DIRBSIZE_BITS) | slot; return 0; } - diff --git a/fs/efs/namei.c b/fs/efs/namei.c index 40ba9cc..d34a40e 100644 --- a/fs/efs/namei.c +++ b/fs/efs/namei.c @@ -113,7 +113,7 @@ struct dentry *efs_get_parent(struct dentry *child) ino = efs_find_entry(d_inode(child), "..", 2); if (ino) - parent = d_obtain_alias(efs_iget(d_inode(child)->i_sb, ino)); + parent = d_obtain_alias(efs_iget(child->d_sb, ino)); return parent; } @@ -850,15 +850,25 @@ int kernel_read_file(struct file *file, void **buf, loff_t *size, if (ret) return ret; + ret = deny_write_access(file); + if (ret) + return ret; + i_size = i_size_read(file_inode(file)); - if (max_size > 0 && i_size > max_size) - return -EFBIG; - if (i_size <= 0) - return -EINVAL; + if (max_size > 0 && i_size > max_size) { + ret = -EFBIG; + goto out; + } + if (i_size <= 0) { + ret = -EINVAL; + goto out; + } *buf = vmalloc(i_size); - if (!*buf) - return -ENOMEM; + if (!*buf) { + ret = -ENOMEM; + goto out; + } pos = 0; while (pos < i_size) { @@ -876,18 +886,21 @@ int kernel_read_file(struct file *file, void **buf, loff_t *size, if (pos != i_size) { ret = -EIO; - goto out; + goto out_free; } ret = security_kernel_post_read_file(file, *buf, i_size, id); if (!ret) *size = pos; -out: +out_free: if (ret < 0) { vfree(*buf); *buf = NULL; } + +out: + allow_write_access(file); return ret; } EXPORT_SYMBOL_GPL(kernel_read_file); @@ -1387,7 +1400,12 @@ static void bprm_fill_uid(struct linux_binprm *bprm) kuid_t uid; kgid_t gid; - /* clear any previous set[ug]id data from a previous binary */ + /* + * Since this can be called multiple times (via prepare_binprm), + * we must clear any previous work done when setting set[ug]id + * bits from any earlier bprm->file uses (for example when run + * first for a setuid script then again for its interpreter). + */ bprm->cred->euid = current_euid(); bprm->cred->egid = current_egid(); diff --git a/fs/exofs/dir.c b/fs/exofs/dir.c index 547b93c..f69a1b5 100644 --- a/fs/exofs/dir.c +++ b/fs/exofs/dir.c @@ -79,7 +79,7 @@ static int exofs_commit_chunk(struct page *page, loff_t pos, unsigned len) return err; } -static void exofs_check_page(struct page *page) +static bool exofs_check_page(struct page *page) { struct inode *dir = page->mapping->host; unsigned chunk_size = exofs_chunk_size(dir); @@ -114,7 +114,7 @@ static void exofs_check_page(struct page *page) goto Eend; out: SetPageChecked(page); - return; + return true; Ebadsize: EXOFS_ERR("ERROR [exofs_check_page]: " @@ -150,8 +150,8 @@ Eend: dir->i_ino, (page->index<<PAGE_SHIFT)+offs, _LLU(le64_to_cpu(p->inode_no))); fail: - SetPageChecked(page); SetPageError(page); + return false; } static struct page *exofs_get_page(struct inode *dir, unsigned long n) @@ -161,10 +161,10 @@ static struct page *exofs_get_page(struct inode *dir, unsigned long n) if (!IS_ERR(page)) { kmap(page); - if (!PageChecked(page)) - exofs_check_page(page); - if (PageError(page)) - goto fail; + if (unlikely(!PageChecked(page))) { + if (PageError(page) || !exofs_check_page(page)) + goto fail; + } } return page; @@ -657,5 +657,5 @@ not_empty: const struct file_operations exofs_dir_operations = { .llseek = generic_file_llseek, .read = generic_read_dir, - .iterate = exofs_readdir, + .iterate_shared = exofs_readdir, }; diff --git a/fs/exofs/inode.c b/fs/exofs/inode.c index 49e1bd0..9dc4c6d 100644 --- a/fs/exofs/inode.c +++ b/fs/exofs/inode.c @@ -960,8 +960,7 @@ static void exofs_invalidatepage(struct page *page, unsigned int offset, /* TODO: Should be easy enough to do proprly */ -static ssize_t exofs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, - loff_t offset) +static ssize_t exofs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) { return 0; } diff --git a/fs/exofs/super.c b/fs/exofs/super.c index 6658a50..1076a42 100644 --- a/fs/exofs/super.c +++ b/fs/exofs/super.c @@ -122,7 +122,7 @@ static int parse_options(char *options, struct exofs_mountopt *opts) if (match_int(&args[0], &option)) return -EINVAL; if (option <= 0) { - EXOFS_ERR("Timout must be > 0"); + EXOFS_ERR("Timeout must be > 0"); return -EINVAL; } opts->timeout = option * HZ; @@ -958,7 +958,7 @@ static struct dentry *exofs_get_parent(struct dentry *child) if (!ino) return ERR_PTR(-ESTALE); - return d_obtain_alias(exofs_iget(d_inode(child)->i_sb, ino)); + return d_obtain_alias(exofs_iget(child->d_sb, ino)); } static struct inode *exofs_nfs_get_inode(struct super_block *sb, diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c index c46f1a1..207ba8d 100644 --- a/fs/exportfs/expfs.c +++ b/fs/exportfs/expfs.c @@ -143,14 +143,18 @@ static struct dentry *reconnect_one(struct vfsmount *mnt, if (err) goto out_err; dprintk("%s: found name: %s\n", __func__, nbuf); - inode_lock(parent->d_inode); - tmp = lookup_one_len(nbuf, parent, strlen(nbuf)); - inode_unlock(parent->d_inode); + tmp = lookup_one_len_unlocked(nbuf, parent, strlen(nbuf)); if (IS_ERR(tmp)) { dprintk("%s: lookup failed: %d\n", __func__, PTR_ERR(tmp)); goto out_err; } if (tmp != dentry) { + /* + * Somebody has renamed it since exportfs_get_name(); + * great, since it could've only been renamed if it + * got looked up and thus connected, and it would + * remain connected afterwards. We are done. + */ dput(tmp); goto out_reconnected; } @@ -308,7 +312,7 @@ static int get_name(const struct path *path, char *name, struct dentry *child) goto out; error = -EINVAL; - if (!file->f_op->iterate) + if (!file->f_op->iterate && !file->f_op->iterate_shared) goto out_close; buffer.sequence = 0; diff --git a/fs/ext2/acl.c b/fs/ext2/acl.c index 27695e6..42f1d18 100644 --- a/fs/ext2/acl.c +++ b/fs/ext2/acl.c @@ -172,9 +172,6 @@ ext2_get_acl(struct inode *inode, int type) acl = ERR_PTR(retval); kfree(value); - if (!IS_ERR(acl)) - set_cached_acl(inode, type, acl); - return acl; } diff --git a/fs/ext2/dir.c b/fs/ext2/dir.c index 7ff6fcf..19efd11 100644 --- a/fs/ext2/dir.c +++ b/fs/ext2/dir.c @@ -110,7 +110,7 @@ static int ext2_commit_chunk(struct page *page, loff_t pos, unsigned len) return err; } -static void ext2_check_page(struct page *page, int quiet) +static bool ext2_check_page(struct page *page, int quiet) { struct inode *dir = page->mapping->host; struct super_block *sb = dir->i_sb; @@ -148,7 +148,7 @@ static void ext2_check_page(struct page *page, int quiet) goto Eend; out: SetPageChecked(page); - return; + return true; /* Too bad, we had an error */ @@ -190,8 +190,8 @@ Eend: (unsigned long) le32_to_cpu(p->inode)); } fail: - SetPageChecked(page); SetPageError(page); + return false; } static struct page * ext2_get_page(struct inode *dir, unsigned long n, @@ -201,10 +201,10 @@ static struct page * ext2_get_page(struct inode *dir, unsigned long n, struct page *page = read_mapping_page(mapping, n, NULL); if (!IS_ERR(page)) { kmap(page); - if (!PageChecked(page)) - ext2_check_page(page, quiet); - if (PageError(page)) - goto fail; + if (unlikely(!PageChecked(page))) { + if (PageError(page) || !ext2_check_page(page, quiet)) + goto fail; + } } return page; @@ -716,7 +716,7 @@ not_empty: const struct file_operations ext2_dir_operations = { .llseek = generic_file_llseek, .read = generic_read_dir, - .iterate = ext2_readdir, + .iterate_shared = ext2_readdir, .unlocked_ioctl = ext2_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = ext2_compat_ioctl, diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index 6bd58e6..b675610 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -854,20 +854,20 @@ static sector_t ext2_bmap(struct address_space *mapping, sector_t block) } static ssize_t -ext2_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset) +ext2_direct_IO(struct kiocb *iocb, struct iov_iter *iter) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; size_t count = iov_iter_count(iter); + loff_t offset = iocb->ki_pos; ssize_t ret; if (IS_DAX(inode)) - ret = dax_do_io(iocb, inode, iter, offset, ext2_get_block, NULL, + ret = dax_do_io(iocb, inode, iter, ext2_get_block, NULL, DIO_LOCKING); else - ret = blockdev_direct_IO(iocb, inode, iter, offset, - ext2_get_block); + ret = blockdev_direct_IO(iocb, inode, iter, ext2_get_block); if (ret < 0 && iov_iter_rw(iter) == WRITE) ext2_write_failed(mapping, offset + count); return ret; diff --git a/fs/ext2/namei.c b/fs/ext2/namei.c index d348439..d446203 100644 --- a/fs/ext2/namei.c +++ b/fs/ext2/namei.c @@ -82,7 +82,7 @@ struct dentry *ext2_get_parent(struct dentry *child) unsigned long ino = ext2_inode_by_name(d_inode(child), &dotdot); if (!ino) return ERR_PTR(-ENOENT); - return d_obtain_alias(ext2_iget(d_inode(child)->i_sb, ino)); + return d_obtain_alias(ext2_iget(child->d_sb, ino)); } /* diff --git a/fs/ext2/xattr_security.c b/fs/ext2/xattr_security.c index ba97f24..7fd3b86 100644 --- a/fs/ext2/xattr_security.c +++ b/fs/ext2/xattr_security.c @@ -9,10 +9,10 @@ static int ext2_xattr_security_get(const struct xattr_handler *handler, - struct dentry *dentry, const char *name, - void *buffer, size_t size) + struct dentry *unused, struct inode *inode, + const char *name, void *buffer, size_t size) { - return ext2_xattr_get(d_inode(dentry), EXT2_XATTR_INDEX_SECURITY, name, + return ext2_xattr_get(inode, EXT2_XATTR_INDEX_SECURITY, name, buffer, size); } diff --git a/fs/ext2/xattr_trusted.c b/fs/ext2/xattr_trusted.c index 2c94d19..0f85705 100644 --- a/fs/ext2/xattr_trusted.c +++ b/fs/ext2/xattr_trusted.c @@ -16,10 +16,10 @@ ext2_xattr_trusted_list(struct dentry *dentry) static int ext2_xattr_trusted_get(const struct xattr_handler *handler, - struct dentry *dentry, const char *name, - void *buffer, size_t size) + struct dentry *unused, struct inode *inode, + const char *name, void *buffer, size_t size) { - return ext2_xattr_get(d_inode(dentry), EXT2_XATTR_INDEX_TRUSTED, name, + return ext2_xattr_get(inode, EXT2_XATTR_INDEX_TRUSTED, name, buffer, size); } diff --git a/fs/ext2/xattr_user.c b/fs/ext2/xattr_user.c index 72a2a96..1fafd27 100644 --- a/fs/ext2/xattr_user.c +++ b/fs/ext2/xattr_user.c @@ -18,12 +18,12 @@ ext2_xattr_user_list(struct dentry *dentry) static int ext2_xattr_user_get(const struct xattr_handler *handler, - struct dentry *dentry, const char *name, - void *buffer, size_t size) + struct dentry *unused, struct inode *inode, + const char *name, void *buffer, size_t size) { - if (!test_opt(dentry->d_sb, XATTR_USER)) + if (!test_opt(inode->i_sb, XATTR_USER)) return -EOPNOTSUPP; - return ext2_xattr_get(d_inode(dentry), EXT2_XATTR_INDEX_USER, + return ext2_xattr_get(inode, EXT2_XATTR_INDEX_USER, name, buffer, size); } diff --git a/fs/ext4/acl.c b/fs/ext4/acl.c index 69b1e73..c6601a4 100644 --- a/fs/ext4/acl.c +++ b/fs/ext4/acl.c @@ -172,9 +172,6 @@ ext4_get_acl(struct inode *inode, int type) acl = ERR_PTR(retval); kfree(value); - if (!IS_ERR(acl)) - set_cached_acl(inode, type, acl); - return acl; } diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c index 561d730..5d00bf0 100644 --- a/fs/ext4/dir.c +++ b/fs/ext4/dir.c @@ -266,7 +266,7 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx) ctx->pos += ext4_rec_len_from_disk(de->rec_len, sb->s_blocksize); } - if ((ctx->pos < inode->i_size) && !dir_relax(inode)) + if ((ctx->pos < inode->i_size) && !dir_relax_shared(inode)) goto done; brelse(bh); bh = NULL; @@ -644,7 +644,7 @@ int ext4_check_all_de(struct inode *dir, struct buffer_head *bh, void *buf, const struct file_operations ext4_dir_operations = { .llseek = ext4_dir_llseek, .read = generic_read_dir, - .iterate = ext4_readdir, + .iterate_shared = ext4_readdir, .unlocked_ioctl = ext4_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = ext4_compat_ioctl, diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 349afeb..72f4c9e 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -2581,8 +2581,7 @@ extern int ext4_get_next_extent(struct inode *inode, ext4_lblk_t lblk, /* indirect.c */ extern int ext4_ind_map_blocks(handle_t *handle, struct inode *inode, struct ext4_map_blocks *map, int flags); -extern ssize_t ext4_ind_direct_IO(struct kiocb *iocb, struct iov_iter *iter, - loff_t offset); +extern ssize_t ext4_ind_direct_IO(struct kiocb *iocb, struct iov_iter *iter); extern int ext4_ind_calc_metadata_amount(struct inode *inode, sector_t lblock); extern int ext4_ind_trans_blocks(struct inode *inode, int nrblocks); extern void ext4_ind_truncate(handle_t *, struct inode *inode); diff --git a/fs/ext4/file.c b/fs/ext4/file.c index fa2208b..00ff691 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -169,13 +169,8 @@ ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from) ret = __generic_file_write_iter(iocb, from); inode_unlock(inode); - if (ret > 0) { - ssize_t err; - - err = generic_write_sync(file, iocb->ki_pos - ret, ret); - if (err < 0) - ret = err; - } + if (ret > 0) + ret = generic_write_sync(iocb, ret); if (o_direct) blk_finish_plug(&plug); diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c index 3027fa6..627b7e8 100644 --- a/fs/ext4/indirect.c +++ b/fs/ext4/indirect.c @@ -659,12 +659,12 @@ out: * crashes then stale disk data _may_ be exposed inside the file. But current * VFS code falls back into buffered path in that case so we are safe. */ -ssize_t ext4_ind_direct_IO(struct kiocb *iocb, struct iov_iter *iter, - loff_t offset) +ssize_t ext4_ind_direct_IO(struct kiocb *iocb, struct iov_iter *iter) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; struct ext4_inode_info *ei = EXT4_I(inode); + loff_t offset = iocb->ki_pos; handle_t *handle; ssize_t ret; int orphan = 0; @@ -707,21 +707,21 @@ retry: goto locked; } if (IS_DAX(inode)) - ret = dax_do_io(iocb, inode, iter, offset, + ret = dax_do_io(iocb, inode, iter, ext4_dio_get_block, NULL, 0); else ret = __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev, iter, - offset, ext4_dio_get_block, + ext4_dio_get_block, NULL, NULL, 0); inode_dio_end(inode); } else { locked: if (IS_DAX(inode)) - ret = dax_do_io(iocb, inode, iter, offset, + ret = dax_do_io(iocb, inode, iter, ext4_dio_get_block, NULL, DIO_LOCKING); else - ret = blockdev_direct_IO(iocb, inode, iter, offset, + ret = blockdev_direct_IO(iocb, inode, iter, ext4_dio_get_block); if (unlikely(iov_iter_rw(iter) == WRITE && ret < 0)) { diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 981a1fc..79b298d 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -3334,12 +3334,12 @@ static int ext4_end_io_dio(struct kiocb *iocb, loff_t offset, * if the machine crashes during the write. * */ -static ssize_t ext4_ext_direct_IO(struct kiocb *iocb, struct iov_iter *iter, - loff_t offset) +static ssize_t ext4_ext_direct_IO(struct kiocb *iocb, struct iov_iter *iter) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; ssize_t ret; + loff_t offset = iocb->ki_pos; size_t count = iov_iter_count(iter); int overwrite = 0; get_block_t *get_block_func = NULL; @@ -3348,7 +3348,7 @@ static ssize_t ext4_ext_direct_IO(struct kiocb *iocb, struct iov_iter *iter, /* Use the old path for reads and writes beyond i_size. */ if (iov_iter_rw(iter) != WRITE || final_size > inode->i_size) - return ext4_ind_direct_IO(iocb, iter, offset); + return ext4_ind_direct_IO(iocb, iter); BUG_ON(iocb->private == NULL); @@ -3400,11 +3400,11 @@ static ssize_t ext4_ext_direct_IO(struct kiocb *iocb, struct iov_iter *iter, BUG_ON(ext4_encrypted_inode(inode) && S_ISREG(inode->i_mode)); #endif if (IS_DAX(inode)) - ret = dax_do_io(iocb, inode, iter, offset, get_block_func, + ret = dax_do_io(iocb, inode, iter, get_block_func, ext4_end_io_dio, dio_flags); else ret = __blockdev_direct_IO(iocb, inode, - inode->i_sb->s_bdev, iter, offset, + inode->i_sb->s_bdev, iter, get_block_func, ext4_end_io_dio, NULL, dio_flags); @@ -3431,12 +3431,12 @@ static ssize_t ext4_ext_direct_IO(struct kiocb *iocb, struct iov_iter *iter, return ret; } -static ssize_t ext4_direct_IO(struct kiocb *iocb, struct iov_iter *iter, - loff_t offset) +static ssize_t ext4_direct_IO(struct kiocb *iocb, struct iov_iter *iter) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; size_t count = iov_iter_count(iter); + loff_t offset = iocb->ki_pos; ssize_t ret; #ifdef CONFIG_EXT4_FS_ENCRYPTION @@ -3456,9 +3456,9 @@ static ssize_t ext4_direct_IO(struct kiocb *iocb, struct iov_iter *iter, trace_ext4_direct_IO_enter(inode, offset, count, iov_iter_rw(iter)); if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) - ret = ext4_ext_direct_IO(iocb, iter, offset); + ret = ext4_ext_direct_IO(iocb, iter); else - ret = ext4_ind_direct_IO(iocb, iter, offset); + ret = ext4_ind_direct_IO(iocb, iter); trace_ext4_direct_IO_exit(inode, offset, count, iov_iter_rw(iter), ret); return ret; } diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 48e4b89..5611ec9 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -1638,13 +1638,13 @@ struct dentry *ext4_get_parent(struct dentry *child) ino = le32_to_cpu(de->inode); brelse(bh); - if (!ext4_valid_inum(d_inode(child)->i_sb, ino)) { + if (!ext4_valid_inum(child->d_sb, ino)) { EXT4_ERROR_INODE(d_inode(child), "bad parent inode number: %u", ino); return ERR_PTR(-EFSCORRUPTED); } - return d_obtain_alias(ext4_iget_normal(d_inode(child)->i_sb, ino)); + return d_obtain_alias(ext4_iget_normal(child->d_sb, ino)); } /* diff --git a/fs/ext4/xattr_security.c b/fs/ext4/xattr_security.c index 3e81bdc..123a7d0 100644 --- a/fs/ext4/xattr_security.c +++ b/fs/ext4/xattr_security.c @@ -13,10 +13,10 @@ static int ext4_xattr_security_get(const struct xattr_handler *handler, - struct dentry *dentry, const char *name, - void *buffer, size_t size) + struct dentry *unused, struct inode *inode, + const char *name, void *buffer, size_t size) { - return ext4_xattr_get(d_inode(dentry), EXT4_XATTR_INDEX_SECURITY, + return ext4_xattr_get(inode, EXT4_XATTR_INDEX_SECURITY, name, buffer, size); } diff --git a/fs/ext4/xattr_trusted.c b/fs/ext4/xattr_trusted.c index 2a3c6f9..60652fa 100644 --- a/fs/ext4/xattr_trusted.c +++ b/fs/ext4/xattr_trusted.c @@ -20,10 +20,10 @@ ext4_xattr_trusted_list(struct dentry *dentry) static int ext4_xattr_trusted_get(const struct xattr_handler *handler, - struct dentry *dentry, const char *name, void *buffer, - size_t size) + struct dentry *unused, struct inode *inode, + const char *name, void *buffer, size_t size) { - return ext4_xattr_get(d_inode(dentry), EXT4_XATTR_INDEX_TRUSTED, + return ext4_xattr_get(inode, EXT4_XATTR_INDEX_TRUSTED, name, buffer, size); } diff --git a/fs/ext4/xattr_user.c b/fs/ext4/xattr_user.c index d152f43..17a446f 100644 --- a/fs/ext4/xattr_user.c +++ b/fs/ext4/xattr_user.c @@ -19,12 +19,12 @@ ext4_xattr_user_list(struct dentry *dentry) static int ext4_xattr_user_get(const struct xattr_handler *handler, - struct dentry *dentry, const char *name, - void *buffer, size_t size) + struct dentry *unused, struct inode *inode, + const char *name, void *buffer, size_t size) { - if (!test_opt(dentry->d_sb, XATTR_USER)) + if (!test_opt(inode->i_sb, XATTR_USER)) return -EOPNOTSUPP; - return ext4_xattr_get(d_inode(dentry), EXT4_XATTR_INDEX_USER, + return ext4_xattr_get(inode, EXT4_XATTR_INDEX_USER, name, buffer, size); } diff --git a/fs/f2fs/acl.c b/fs/f2fs/acl.c index c8f25f7..6f1fdda 100644 --- a/fs/f2fs/acl.c +++ b/fs/f2fs/acl.c @@ -190,9 +190,6 @@ static struct posix_acl *__f2fs_get_acl(struct inode *inode, int type, acl = ERR_PTR(retval); kfree(value); - if (!IS_ERR(acl)) - set_cached_acl(inode, type, acl); - return acl; } diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 5dafb9c..bb376c3 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -1665,12 +1665,12 @@ static int check_direct_IO(struct inode *inode, struct iov_iter *iter, return 0; } -static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, - loff_t offset) +static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) { struct address_space *mapping = iocb->ki_filp->f_mapping; struct inode *inode = mapping->host; size_t count = iov_iter_count(iter); + loff_t offset = iocb->ki_pos; int err; err = check_direct_IO(inode, iter, offset); @@ -1682,7 +1682,7 @@ static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, trace_f2fs_direct_IO_enter(inode, offset, count, iov_iter_rw(iter)); - err = blockdev_direct_IO(iocb, inode, iter, offset, get_data_block_dio); + err = blockdev_direct_IO(iocb, inode, iter, get_data_block_dio); if (err < 0 && iov_iter_rw(iter) == WRITE) f2fs_write_failed(mapping, offset + count); diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c index af81957..9e46151 100644 --- a/fs/f2fs/dir.c +++ b/fs/f2fs/dir.c @@ -902,7 +902,7 @@ static int f2fs_dir_open(struct inode *inode, struct file *filp) const struct file_operations f2fs_dir_operations = { .llseek = generic_file_llseek, .read = generic_read_dir, - .iterate = f2fs_readdir, + .iterate_shared = f2fs_readdir, .fsync = f2fs_sync_file, .open = f2fs_dir_open, .unlocked_ioctl = f2fs_ioctl, diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 90d1157..eb9d027 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -1886,13 +1886,8 @@ static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from) } inode_unlock(inode); - if (ret > 0) { - ssize_t err; - - err = generic_write_sync(file, iocb->ki_pos - ret, ret); - if (err < 0) - ret = err; - } + if (ret > 0) + ret = generic_write_sync(iocb, ret); return ret; } diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c index 013e579..324ed38 100644 --- a/fs/f2fs/namei.c +++ b/fs/f2fs/namei.c @@ -202,7 +202,7 @@ struct dentry *f2fs_get_parent(struct dentry *child) unsigned long ino = f2fs_inode_by_name(d_inode(child), &dotdot); if (!ino) return ERR_PTR(-ENOENT); - return d_obtain_alias(f2fs_iget(d_inode(child)->i_sb, ino)); + return d_obtain_alias(f2fs_iget(child->d_sb, ino)); } static int __recover_dot_dentries(struct inode *dir, nid_t pino) diff --git a/fs/f2fs/xattr.c b/fs/f2fs/xattr.c index 06a72dc..17fd2b1 100644 --- a/fs/f2fs/xattr.c +++ b/fs/f2fs/xattr.c @@ -26,10 +26,10 @@ #include "xattr.h" static int f2fs_xattr_generic_get(const struct xattr_handler *handler, - struct dentry *dentry, const char *name, void *buffer, - size_t size) + struct dentry *unused, struct inode *inode, + const char *name, void *buffer, size_t size) { - struct f2fs_sb_info *sbi = F2FS_SB(dentry->d_sb); + struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb); switch (handler->flags) { case F2FS_XATTR_INDEX_USER: @@ -45,7 +45,7 @@ static int f2fs_xattr_generic_get(const struct xattr_handler *handler, default: return -EINVAL; } - return f2fs_getxattr(d_inode(dentry), handler->flags, name, + return f2fs_getxattr(inode, handler->flags, name, buffer, size, NULL); } @@ -86,11 +86,9 @@ static bool f2fs_xattr_trusted_list(struct dentry *dentry) } static int f2fs_xattr_advise_get(const struct xattr_handler *handler, - struct dentry *dentry, const char *name, void *buffer, - size_t size) + struct dentry *unused, struct inode *inode, + const char *name, void *buffer, size_t size) { - struct inode *inode = d_inode(dentry); - if (buffer) *((char *)buffer) = F2FS_I(inode)->i_advise; return sizeof(char); diff --git a/fs/fat/dir.c b/fs/fat/dir.c index d0b95c9..663e428 100644 --- a/fs/fat/dir.c +++ b/fs/fat/dir.c @@ -769,7 +769,7 @@ static int fat_ioctl_readdir(struct inode *inode, struct file *file, buf.dirent = dirent; buf.result = 0; - inode_lock(inode); + inode_lock_shared(inode); buf.ctx.pos = file->f_pos; ret = -ENOENT; if (!IS_DEADDIR(inode)) { @@ -777,7 +777,7 @@ static int fat_ioctl_readdir(struct inode *inode, struct file *file, short_only, both ? &buf : NULL); file->f_pos = buf.ctx.pos; } - inode_unlock(inode); + inode_unlock_shared(inode); if (ret >= 0) ret = buf.result; return ret; @@ -861,7 +861,7 @@ static long fat_compat_dir_ioctl(struct file *filp, unsigned cmd, const struct file_operations fat_dir_operations = { .llseek = generic_file_llseek, .read = generic_read_dir, - .iterate = fat_readdir, + .iterate_shared = fat_readdir, .unlocked_ioctl = fat_dir_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = fat_compat_dir_ioctl, diff --git a/fs/fat/inode.c b/fs/fat/inode.c index 2262810..3bcf579 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -244,13 +244,13 @@ static int fat_write_end(struct file *file, struct address_space *mapping, return err; } -static ssize_t fat_direct_IO(struct kiocb *iocb, struct iov_iter *iter, - loff_t offset) +static ssize_t fat_direct_IO(struct kiocb *iocb, struct iov_iter *iter) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; size_t count = iov_iter_count(iter); + loff_t offset = iocb->ki_pos; ssize_t ret; if (iov_iter_rw(iter) == WRITE) { @@ -272,7 +272,7 @@ static ssize_t fat_direct_IO(struct kiocb *iocb, struct iov_iter *iter, * FAT need to use the DIO_LOCKING for avoiding the race * condition of fat_get_block() and ->truncate(). */ - ret = blockdev_direct_IO(iocb, inode, iter, offset, fat_get_block); + ret = blockdev_direct_IO(iocb, inode, iter, fat_get_block); if (ret < 0 && iov_iter_rw(iter) == WRITE) fat_write_failed(mapping, offset + count); @@ -784,6 +784,11 @@ unsigned long __fdget_pos(unsigned int fd) return v; } +void __f_unlock_pos(struct file *f) +{ + mutex_unlock(&f->f_pos_lock); +} + /* * We only lock f_pos if we have threads or if the file might be * shared with another process. In both cases we'll have an elevated diff --git a/fs/freevxfs/vxfs_lookup.c b/fs/freevxfs/vxfs_lookup.c index a49e0cf..6d576b9 100644 --- a/fs/freevxfs/vxfs_lookup.c +++ b/fs/freevxfs/vxfs_lookup.c @@ -58,7 +58,7 @@ const struct inode_operations vxfs_dir_inode_ops = { const struct file_operations vxfs_dir_operations = { .llseek = generic_file_llseek, .read = generic_read_dir, - .iterate = vxfs_readdir, + .iterate_shared = vxfs_readdir, }; static inline u_long diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 4b855b6..b941905 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -1162,7 +1162,6 @@ static int fuse_direntplus_link(struct file *file, struct fuse_direntplus *direntplus, u64 attr_version) { - int err; struct fuse_entry_out *o = &direntplus->entry_out; struct fuse_dirent *dirent = &direntplus->dirent; struct dentry *parent = file->f_path.dentry; @@ -1172,6 +1171,7 @@ static int fuse_direntplus_link(struct file *file, struct inode *dir = d_inode(parent); struct fuse_conn *fc; struct inode *inode; + DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq); if (!o->nodeid) { /* @@ -1204,65 +1204,61 @@ static int fuse_direntplus_link(struct file *file, name.hash = full_name_hash(name.name, name.len); dentry = d_lookup(parent, &name); - if (dentry) { + if (!dentry) { +retry: + dentry = d_alloc_parallel(parent, &name, &wq); + if (IS_ERR(dentry)) + return PTR_ERR(dentry); + } + if (!d_in_lookup(dentry)) { + struct fuse_inode *fi; inode = d_inode(dentry); - if (!inode) { - d_drop(dentry); - } else if (get_node_id(inode) != o->nodeid || - ((o->attr.mode ^ inode->i_mode) & S_IFMT)) { + if (!inode || + get_node_id(inode) != o->nodeid || + ((o->attr.mode ^ inode->i_mode) & S_IFMT)) { d_invalidate(dentry); - } else if (is_bad_inode(inode)) { - err = -EIO; - goto out; - } else { - struct fuse_inode *fi; - fi = get_fuse_inode(inode); - spin_lock(&fc->lock); - fi->nlookup++; - spin_unlock(&fc->lock); - - fuse_change_attributes(inode, &o->attr, - entry_attr_timeout(o), - attr_version); - - /* - * The other branch to 'found' comes via fuse_iget() - * which bumps nlookup inside - */ - goto found; + dput(dentry); + goto retry; + } + if (is_bad_inode(inode)) { + dput(dentry); + return -EIO; } - dput(dentry); - } - - dentry = d_alloc(parent, &name); - err = -ENOMEM; - if (!dentry) - goto out; - inode = fuse_iget(dir->i_sb, o->nodeid, o->generation, - &o->attr, entry_attr_timeout(o), attr_version); - if (!inode) - goto out; + fi = get_fuse_inode(inode); + spin_lock(&fc->lock); + fi->nlookup++; + spin_unlock(&fc->lock); - alias = d_splice_alias(inode, dentry); - err = PTR_ERR(alias); - if (IS_ERR(alias)) - goto out; + fuse_change_attributes(inode, &o->attr, + entry_attr_timeout(o), + attr_version); + /* + * The other branch comes via fuse_iget() + * which bumps nlookup inside + */ + } else { + inode = fuse_iget(dir->i_sb, o->nodeid, o->generation, + &o->attr, entry_attr_timeout(o), + attr_version); + if (!inode) + inode = ERR_PTR(-ENOMEM); - if (alias) { - dput(dentry); - dentry = alias; + alias = d_splice_alias(inode, dentry); + d_lookup_done(dentry); + if (alias) { + dput(dentry); + dentry = alias; + } + if (IS_ERR(dentry)) + return PTR_ERR(dentry); } - -found: if (fc->readdirplus_auto) set_bit(FUSE_I_INIT_RDPLUS, &get_fuse_inode(inode)->state); fuse_change_entry_timeout(dentry, o); - err = 0; -out: dput(dentry); - return err; + return 0; } static int parse_dirplusfile(char *buf, size_t nbytes, struct file *file, @@ -1759,10 +1755,9 @@ static int fuse_setxattr(struct dentry *entry, const char *name, return err; } -static ssize_t fuse_getxattr(struct dentry *entry, const char *name, - void *value, size_t size) +static ssize_t fuse_getxattr(struct dentry *entry, struct inode *inode, + const char *name, void *value, size_t size) { - struct inode *inode = d_inode(entry); struct fuse_conn *fc = get_fuse_conn(inode); FUSE_ARGS(args); struct fuse_getxattr_in inarg; @@ -1893,7 +1888,7 @@ static const struct inode_operations fuse_dir_inode_operations = { static const struct file_operations fuse_dir_operations = { .llseek = generic_file_llseek, .read = generic_read_dir, - .iterate = fuse_readdir, + .iterate_shared = fuse_readdir, .open = fuse_dir_open, .release = fuse_dir_release, .fsync = fuse_dir_fsync, diff --git a/fs/fuse/file.c b/fs/fuse/file.c index dcad5e2..9154f86 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -1186,7 +1186,7 @@ static ssize_t fuse_file_write_iter(struct kiocb *iocb, struct iov_iter *from) if (iocb->ki_flags & IOCB_DIRECT) { loff_t pos = iocb->ki_pos; - written = generic_file_direct_write(iocb, from, pos); + written = generic_file_direct_write(iocb, from); if (written < 0 || !iov_iter_count(from)) goto out; @@ -2837,7 +2837,7 @@ static inline loff_t fuse_round_up(loff_t off) } static ssize_t -fuse_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset) +fuse_direct_IO(struct kiocb *iocb, struct iov_iter *iter) { DECLARE_COMPLETION_ONSTACK(wait); ssize_t ret = 0; @@ -2848,6 +2848,7 @@ fuse_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset) struct inode *inode; loff_t i_size; size_t count = iov_iter_count(iter); + loff_t offset = iocb->ki_pos; struct fuse_io_priv *io; bool is_sync = is_sync_kiocb(iocb); diff --git a/fs/gfs2/acl.c b/fs/gfs2/acl.c index 7919326..363ba9e 100644 --- a/fs/gfs2/acl.c +++ b/fs/gfs2/acl.c @@ -24,6 +24,7 @@ #include "glock.h" #include "inode.h" #include "meta_io.h" +#include "rgrp.h" #include "trans.h" #include "util.h" @@ -38,7 +39,7 @@ static const char *gfs2_acl_name(int type) return NULL; } -struct posix_acl *gfs2_get_acl(struct inode *inode, int type) +static struct posix_acl *__gfs2_get_acl(struct inode *inode, int type) { struct gfs2_inode *ip = GFS2_I(inode); struct posix_acl *acl; @@ -50,29 +51,41 @@ struct posix_acl *gfs2_get_acl(struct inode *inode, int type) return NULL; name = gfs2_acl_name(type); - if (name == NULL) - return ERR_PTR(-EINVAL); - len = gfs2_xattr_acl_get(ip, name, &data); - if (len < 0) + if (len <= 0) return ERR_PTR(len); - if (len == 0) - return NULL; - acl = posix_acl_from_xattr(&init_user_ns, data, len); kfree(data); return acl; } -int gfs2_set_acl(struct inode *inode, struct posix_acl *acl, int type) +struct posix_acl *gfs2_get_acl(struct inode *inode, int type) +{ + struct gfs2_inode *ip = GFS2_I(inode); + struct gfs2_holder gh; + bool need_unlock = false; + struct posix_acl *acl; + + if (!gfs2_glock_is_locked_by_me(ip->i_gl)) { + int ret = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, + LM_FLAG_ANY, &gh); + if (ret) + return ERR_PTR(ret); + need_unlock = true; + } + acl = __gfs2_get_acl(inode, type); + if (need_unlock) + gfs2_glock_dq_uninit(&gh); + return acl; +} + +int __gfs2_set_acl(struct inode *inode, struct posix_acl *acl, int type) { int error; int len; char *data; const char *name = gfs2_acl_name(type); - BUG_ON(name == NULL); - if (acl && acl->a_count > GFS2_ACL_MAX_ENTRIES(GFS2_SB(inode))) return -E2BIG; @@ -115,3 +128,26 @@ out: kfree(data); return error; } + +int gfs2_set_acl(struct inode *inode, struct posix_acl *acl, int type) +{ + struct gfs2_inode *ip = GFS2_I(inode); + struct gfs2_holder gh; + bool need_unlock = false; + int ret; + + ret = gfs2_rsqa_alloc(ip); + if (ret) + return ret; + + if (!gfs2_glock_is_locked_by_me(ip->i_gl)) { + ret = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh); + if (ret) + return ret; + need_unlock = true; + } + ret = __gfs2_set_acl(inode, acl, type); + if (need_unlock) + gfs2_glock_dq_uninit(&gh); + return ret; +} diff --git a/fs/gfs2/acl.h b/fs/gfs2/acl.h index 3af4f40..f674fdd 100644 --- a/fs/gfs2/acl.h +++ b/fs/gfs2/acl.h @@ -15,6 +15,7 @@ #define GFS2_ACL_MAX_ENTRIES(sdp) ((300 << (sdp)->sd_sb.sb_bsize_shift) >> 12) extern struct posix_acl *gfs2_get_acl(struct inode *inode, int type); +extern int __gfs2_set_acl(struct inode *inode, struct posix_acl *acl, int type); extern int gfs2_set_acl(struct inode *inode, struct posix_acl *acl, int type); #endif /* __ACL_DOT_H__ */ diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c index 1bbbee9..8524c0e 100644 --- a/fs/gfs2/aops.c +++ b/fs/gfs2/aops.c @@ -1042,13 +1042,13 @@ static int gfs2_ok_for_dio(struct gfs2_inode *ip, loff_t offset) -static ssize_t gfs2_direct_IO(struct kiocb *iocb, struct iov_iter *iter, - loff_t offset) +static ssize_t gfs2_direct_IO(struct kiocb *iocb, struct iov_iter *iter) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; struct address_space *mapping = inode->i_mapping; struct gfs2_inode *ip = GFS2_I(inode); + loff_t offset = iocb->ki_pos; struct gfs2_holder gh; int rv; @@ -1099,7 +1099,7 @@ static ssize_t gfs2_direct_IO(struct kiocb *iocb, struct iov_iter *iter, } rv = __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev, iter, - offset, gfs2_get_block_direct, NULL, NULL, 0); + gfs2_get_block_direct, NULL, NULL, 0); out: gfs2_glock_dq(&gh); gfs2_holder_uninit(&gh); diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index 208efc7..e53b723 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -895,7 +895,10 @@ static long __gfs2_fallocate(struct file *file, int mode, loff_t offset, loff_t mark_inode_dirty(inode); } - return generic_write_sync(file, pos, count); + if ((file->f_flags & O_DSYNC) || IS_SYNC(file->f_mapping->host)) + return vfs_fsync_range(file, pos, pos + count - 1, + (file->f_flags & __O_SYNC) ? 0 : 1); + return 0; out_trans_fail: gfs2_inplace_release(ip); @@ -1119,7 +1122,7 @@ const struct file_operations gfs2_file_fops = { }; const struct file_operations gfs2_dir_fops = { - .iterate = gfs2_readdir, + .iterate_shared = gfs2_readdir, .unlocked_ioctl = gfs2_ioctl, .open = gfs2_open, .release = gfs2_release, @@ -1147,7 +1150,7 @@ const struct file_operations gfs2_file_fops_nolock = { }; const struct file_operations gfs2_dir_fops_nolock = { - .iterate = gfs2_readdir, + .iterate_shared = gfs2_readdir, .unlocked_ioctl = gfs2_ioctl, .open = gfs2_open, .release = gfs2_release, diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index 6539131..4b73bd1 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -1913,7 +1913,7 @@ static int gfs2_glocks_open(struct inode *inode, struct file *file) if (seq->buf) seq->size = GFS2_SEQ_GOODSIZE; gi->gl = NULL; - ret = rhashtable_walk_init(&gl_hash_table, &gi->hti); + ret = rhashtable_walk_init(&gl_hash_table, &gi->hti, GFP_KERNEL); } return ret; } @@ -1941,7 +1941,7 @@ static int gfs2_glstats_open(struct inode *inode, struct file *file) if (seq->buf) seq->size = GFS2_SEQ_GOODSIZE; gi->gl = NULL; - ret = rhashtable_walk_init(&gl_hash_table, &gi->hti); + ret = rhashtable_walk_init(&gl_hash_table, &gi->hti, GFP_KERNEL); } return ret; } diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index bb30f9a..72e9c64 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -692,12 +692,12 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, considered free. Any failures need to undo the gfs2 structures. */ if (default_acl) { - error = gfs2_set_acl(inode, default_acl, ACL_TYPE_DEFAULT); + error = __gfs2_set_acl(inode, default_acl, ACL_TYPE_DEFAULT); posix_acl_release(default_acl); } if (acl) { if (!error) - error = gfs2_set_acl(inode, acl, ACL_TYPE_ACCESS); + error = __gfs2_set_acl(inode, acl, ACL_TYPE_ACCESS); posix_acl_release(acl); } @@ -1948,67 +1948,6 @@ static int gfs2_getattr(struct vfsmount *mnt, struct dentry *dentry, return 0; } -static int gfs2_setxattr(struct dentry *dentry, const char *name, - const void *data, size_t size, int flags) -{ - struct inode *inode = d_inode(dentry); - struct gfs2_inode *ip = GFS2_I(inode); - struct gfs2_holder gh; - int ret; - - gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh); - ret = gfs2_glock_nq(&gh); - if (ret == 0) { - ret = gfs2_rsqa_alloc(ip); - if (ret == 0) - ret = generic_setxattr(dentry, name, data, size, flags); - gfs2_glock_dq(&gh); - } - gfs2_holder_uninit(&gh); - return ret; -} - -static ssize_t gfs2_getxattr(struct dentry *dentry, const char *name, - void *data, size_t size) -{ - struct inode *inode = d_inode(dentry); - struct gfs2_inode *ip = GFS2_I(inode); - struct gfs2_holder gh; - int ret; - - /* For selinux during lookup */ - if (gfs2_glock_is_locked_by_me(ip->i_gl)) - return generic_getxattr(dentry, name, data, size); - - gfs2_holder_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY, &gh); - ret = gfs2_glock_nq(&gh); - if (ret == 0) { - ret = generic_getxattr(dentry, name, data, size); - gfs2_glock_dq(&gh); - } - gfs2_holder_uninit(&gh); - return ret; -} - -static int gfs2_removexattr(struct dentry *dentry, const char *name) -{ - struct inode *inode = d_inode(dentry); - struct gfs2_inode *ip = GFS2_I(inode); - struct gfs2_holder gh; - int ret; - - gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh); - ret = gfs2_glock_nq(&gh); - if (ret == 0) { - ret = gfs2_rsqa_alloc(ip); - if (ret == 0) - ret = generic_removexattr(dentry, name); - gfs2_glock_dq(&gh); - } - gfs2_holder_uninit(&gh); - return ret; -} - static int gfs2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, u64 start, u64 len) { @@ -2055,10 +1994,10 @@ const struct inode_operations gfs2_file_iops = { .permission = gfs2_permission, .setattr = gfs2_setattr, .getattr = gfs2_getattr, - .setxattr = gfs2_setxattr, - .getxattr = gfs2_getxattr, + .setxattr = generic_setxattr, + .getxattr = generic_getxattr, .listxattr = gfs2_listxattr, - .removexattr = gfs2_removexattr, + .removexattr = generic_removexattr, .fiemap = gfs2_fiemap, .get_acl = gfs2_get_acl, .set_acl = gfs2_set_acl, @@ -2077,10 +2016,10 @@ const struct inode_operations gfs2_dir_iops = { .permission = gfs2_permission, .setattr = gfs2_setattr, .getattr = gfs2_getattr, - .setxattr = gfs2_setxattr, - .getxattr = gfs2_getxattr, + .setxattr = generic_setxattr, + .getxattr = generic_getxattr, .listxattr = gfs2_listxattr, - .removexattr = gfs2_removexattr, + .removexattr = generic_removexattr, .fiemap = gfs2_fiemap, .get_acl = gfs2_get_acl, .set_acl = gfs2_set_acl, @@ -2093,10 +2032,10 @@ const struct inode_operations gfs2_symlink_iops = { .permission = gfs2_permission, .setattr = gfs2_setattr, .getattr = gfs2_getattr, - .setxattr = gfs2_setxattr, - .getxattr = gfs2_getxattr, + .setxattr = generic_setxattr, + .getxattr = generic_getxattr, .listxattr = gfs2_listxattr, - .removexattr = gfs2_removexattr, + .removexattr = generic_removexattr, .fiemap = gfs2_fiemap, }; diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index 49b0bff..4546360 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -824,7 +824,7 @@ static int init_inodes(struct gfs2_sbd *sdp, int undo) * i_mutex on quota files is special. Since this inode is hidden system * file, we are safe to define locking ourselves. */ - lockdep_set_class(&sdp->sd_quota_inode->i_mutex, + lockdep_set_class(&sdp->sd_quota_inode->i_rwsem, &gfs2_quota_imutex_key); error = gfs2_rindex_update(sdp); @@ -1360,7 +1360,7 @@ static struct dentry *gfs2_mount_meta(struct file_system_type *fs_type, return ERR_PTR(error); } s = sget(&gfs2_fs_type, test_gfs2_super, set_meta_super, flags, - d_inode(path.dentry)->i_sb->s_bdev); + path.dentry->d_sb->s_bdev); path_put(&path); if (IS_ERR(s)) { pr_warn("gfs2 mount does not exist\n"); diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index f8a0cd8..9b2ff353 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -1176,7 +1176,7 @@ static int gfs2_statfs_i(struct gfs2_sbd *sdp, struct gfs2_statfs_change_host *s static int gfs2_statfs(struct dentry *dentry, struct kstatfs *buf) { - struct super_block *sb = d_inode(dentry)->i_sb; + struct super_block *sb = dentry->d_sb; struct gfs2_sbd *sdp = sb->s_fs_info; struct gfs2_statfs_change_host sc; int error; diff --git a/fs/gfs2/xattr.c b/fs/gfs2/xattr.c index e8dfb47..f42ab53b 100644 --- a/fs/gfs2/xattr.c +++ b/fs/gfs2/xattr.c @@ -583,13 +583,11 @@ out: * * Returns: actual size of data on success, -errno on error */ -static int gfs2_xattr_get(const struct xattr_handler *handler, - struct dentry *dentry, const char *name, - void *buffer, size_t size) +static int __gfs2_xattr_get(struct inode *inode, const char *name, + void *buffer, size_t size, int type) { - struct gfs2_inode *ip = GFS2_I(d_inode(dentry)); + struct gfs2_inode *ip = GFS2_I(inode); struct gfs2_ea_location el; - int type = handler->flags; int error; if (!ip->i_eattr) @@ -611,6 +609,29 @@ static int gfs2_xattr_get(const struct xattr_handler *handler, return error; } +static int gfs2_xattr_get(const struct xattr_handler *handler, + struct dentry *unused, struct inode *inode, + const char *name, void *buffer, size_t size) +{ + struct gfs2_inode *ip = GFS2_I(inode); + struct gfs2_holder gh; + bool need_unlock = false; + int ret; + + /* During lookup, SELinux calls this function with the glock locked. */ + + if (!gfs2_glock_is_locked_by_me(ip->i_gl)) { + ret = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY, &gh); + if (ret) + return ret; + need_unlock = true; + } + ret = __gfs2_xattr_get(inode, name, buffer, size, handler->flags); + if (need_unlock) + gfs2_glock_dq_uninit(&gh); + return ret; +} + /** * ea_alloc_blk - allocates a new block for extended attributes. * @ip: A pointer to the inode that's getting extended attributes @@ -1233,8 +1254,21 @@ static int gfs2_xattr_set(const struct xattr_handler *handler, struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { - return __gfs2_xattr_set(d_inode(dentry), name, value, - size, flags, handler->flags); + struct inode *inode = d_inode(dentry); + struct gfs2_inode *ip = GFS2_I(inode); + struct gfs2_holder gh; + int ret; + + ret = gfs2_rsqa_alloc(ip); + if (ret) + return ret; + + ret = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh); + if (ret) + return ret; + ret = __gfs2_xattr_set(inode, name, value, size, flags, handler->flags); + gfs2_glock_dq_uninit(&gh); + return ret; } static int ea_dealloc_indirect(struct gfs2_inode *ip) diff --git a/fs/hfs/attr.c b/fs/hfs/attr.c index 8d931b1..064f92f 100644 --- a/fs/hfs/attr.c +++ b/fs/hfs/attr.c @@ -56,10 +56,9 @@ out: return res; } -ssize_t hfs_getxattr(struct dentry *dentry, const char *name, - void *value, size_t size) +ssize_t hfs_getxattr(struct dentry *unused, struct inode *inode, + const char *name, void *value, size_t size) { - struct inode *inode = d_inode(dentry); struct hfs_find_data fd; hfs_cat_rec rec; struct hfs_cat_file *file; diff --git a/fs/hfs/catalog.c b/fs/hfs/catalog.c index 1eb5d41..98cde8b 100644 --- a/fs/hfs/catalog.c +++ b/fs/hfs/catalog.c @@ -240,10 +240,13 @@ int hfs_cat_delete(u32 cnid, struct inode *dir, struct qstr *str) } } + /* we only need to take spinlock for exclusion with ->release() */ + spin_lock(&HFS_I(dir)->open_dir_lock); list_for_each_entry(rd, &HFS_I(dir)->open_dir_list, list) { if (fd.tree->keycmp(fd.search_key, (void *)&rd->key) < 0) rd->file->f_pos--; } + spin_unlock(&HFS_I(dir)->open_dir_lock); res = hfs_brec_remove(&fd); if (res) diff --git a/fs/hfs/dir.c b/fs/hfs/dir.c index e9f2b85..163190e 100644 --- a/fs/hfs/dir.c +++ b/fs/hfs/dir.c @@ -161,8 +161,14 @@ static int hfs_readdir(struct file *file, struct dir_context *ctx) } file->private_data = rd; rd->file = file; + spin_lock(&HFS_I(inode)->open_dir_lock); list_add(&rd->list, &HFS_I(inode)->open_dir_list); + spin_unlock(&HFS_I(inode)->open_dir_lock); } + /* + * Can be done after the list insertion; exclusion with + * hfs_delete_cat() is provided by directory lock. + */ memcpy(&rd->key, &fd.key, sizeof(struct hfs_cat_key)); out: hfs_find_exit(&fd); @@ -173,9 +179,9 @@ static int hfs_dir_release(struct inode *inode, struct file *file) { struct hfs_readdir_data *rd = file->private_data; if (rd) { - inode_lock(inode); + spin_lock(&HFS_I(inode)->open_dir_lock); list_del(&rd->list); - inode_unlock(inode); + spin_unlock(&HFS_I(inode)->open_dir_lock); kfree(rd); } return 0; @@ -303,7 +309,7 @@ static int hfs_rename(struct inode *old_dir, struct dentry *old_dentry, const struct file_operations hfs_dir_operations = { .read = generic_read_dir, - .iterate = hfs_readdir, + .iterate_shared = hfs_readdir, .llseek = generic_file_llseek, .release = hfs_dir_release, }; diff --git a/fs/hfs/hfs_fs.h b/fs/hfs/hfs_fs.h index 1f1c7dc..fa3eed8 100644 --- a/fs/hfs/hfs_fs.h +++ b/fs/hfs/hfs_fs.h @@ -69,6 +69,7 @@ struct hfs_inode_info { struct hfs_cat_key cat_key; struct list_head open_dir_list; + spinlock_t open_dir_lock; struct inode *rsrc_inode; struct mutex extents_lock; @@ -213,8 +214,8 @@ extern void hfs_delete_inode(struct inode *); /* attr.c */ extern int hfs_setxattr(struct dentry *dentry, const char *name, const void *value, size_t size, int flags); -extern ssize_t hfs_getxattr(struct dentry *dentry, const char *name, - void *value, size_t size); +extern ssize_t hfs_getxattr(struct dentry *dentry, struct inode *inode, + const char *name, void *value, size_t size); extern ssize_t hfs_listxattr(struct dentry *dentry, char *buffer, size_t size); /* mdb.c */ diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c index cb1e5fa..8eed66a 100644 --- a/fs/hfs/inode.c +++ b/fs/hfs/inode.c @@ -124,8 +124,7 @@ static int hfs_releasepage(struct page *page, gfp_t mask) return res ? try_to_free_buffers(page) : 0; } -static ssize_t hfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, - loff_t offset) +static ssize_t hfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; @@ -133,7 +132,7 @@ static ssize_t hfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, size_t count = iov_iter_count(iter); ssize_t ret; - ret = blockdev_direct_IO(iocb, inode, iter, offset, hfs_get_block); + ret = blockdev_direct_IO(iocb, inode, iter, hfs_get_block); /* * In case of error extending write may have instantiated a few @@ -141,7 +140,7 @@ static ssize_t hfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, */ if (unlikely(iov_iter_rw(iter) == WRITE && ret < 0)) { loff_t isize = i_size_read(inode); - loff_t end = offset + count; + loff_t end = iocb->ki_pos + count; if (end > isize) hfs_write_failed(mapping, end); @@ -187,6 +186,7 @@ struct inode *hfs_new_inode(struct inode *dir, struct qstr *name, umode_t mode) mutex_init(&HFS_I(inode)->extents_lock); INIT_LIST_HEAD(&HFS_I(inode)->open_dir_list); + spin_lock_init(&HFS_I(inode)->open_dir_lock); hfs_cat_build_key(sb, (btree_key *)&HFS_I(inode)->cat_key, dir->i_ino, name); inode->i_ino = HFS_SB(sb)->next_id++; inode->i_mode = mode; @@ -318,6 +318,7 @@ static int hfs_read_inode(struct inode *inode, void *data) HFS_I(inode)->rsrc_inode = NULL; mutex_init(&HFS_I(inode)->extents_lock); INIT_LIST_HEAD(&HFS_I(inode)->open_dir_list); + spin_lock_init(&HFS_I(inode)->open_dir_lock); /* Initialize the inode */ inode->i_uid = hsb->s_uid; diff --git a/fs/hfsplus/catalog.c b/fs/hfsplus/catalog.c index 022974a..fb707e8 100644 --- a/fs/hfsplus/catalog.c +++ b/fs/hfsplus/catalog.c @@ -374,12 +374,15 @@ int hfsplus_delete_cat(u32 cnid, struct inode *dir, struct qstr *str) hfsplus_free_fork(sb, cnid, &fork, HFSPLUS_TYPE_RSRC); } + /* we only need to take spinlock for exclusion with ->release() */ + spin_lock(&HFSPLUS_I(dir)->open_dir_lock); list_for_each(pos, &HFSPLUS_I(dir)->open_dir_list) { struct hfsplus_readdir_data *rd = list_entry(pos, struct hfsplus_readdir_data, list); if (fd.tree->keycmp(fd.search_key, (void *)&rd->key) < 0) rd->file->f_pos--; } + spin_unlock(&HFSPLUS_I(dir)->open_dir_lock); err = hfs_brec_remove(&fd); if (err) diff --git a/fs/hfsplus/dir.c b/fs/hfsplus/dir.c index a4e867e..42e1286 100644 --- a/fs/hfsplus/dir.c +++ b/fs/hfsplus/dir.c @@ -271,8 +271,14 @@ next: } file->private_data = rd; rd->file = file; + spin_lock(&HFSPLUS_I(inode)->open_dir_lock); list_add(&rd->list, &HFSPLUS_I(inode)->open_dir_list); + spin_unlock(&HFSPLUS_I(inode)->open_dir_lock); } + /* + * Can be done after the list insertion; exclusion with + * hfsplus_delete_cat() is provided by directory lock. + */ memcpy(&rd->key, fd.key, sizeof(struct hfsplus_cat_key)); out: kfree(strbuf); @@ -284,9 +290,9 @@ static int hfsplus_dir_release(struct inode *inode, struct file *file) { struct hfsplus_readdir_data *rd = file->private_data; if (rd) { - inode_lock(inode); + spin_lock(&HFSPLUS_I(inode)->open_dir_lock); list_del(&rd->list); - inode_unlock(inode); + spin_unlock(&HFSPLUS_I(inode)->open_dir_lock); kfree(rd); } return 0; @@ -569,7 +575,7 @@ const struct inode_operations hfsplus_dir_inode_operations = { const struct file_operations hfsplus_dir_operations = { .fsync = hfsplus_file_fsync, .read = generic_read_dir, - .iterate = hfsplus_readdir, + .iterate_shared = hfsplus_readdir, .unlocked_ioctl = hfsplus_ioctl, .llseek = generic_file_llseek, .release = hfsplus_dir_release, diff --git a/fs/hfsplus/hfsplus_fs.h b/fs/hfsplus/hfsplus_fs.h index f91a1fa..fdc3446 100644 --- a/fs/hfsplus/hfsplus_fs.h +++ b/fs/hfsplus/hfsplus_fs.h @@ -244,6 +244,7 @@ struct hfsplus_inode_info { u8 userflags; /* BSD user file flags */ u32 subfolders; /* Subfolder count (HFSX only) */ struct list_head open_dir_list; + spinlock_t open_dir_lock; loff_t phys_size; struct inode vfs_inode; diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c index b28f398..ef9fefe 100644 --- a/fs/hfsplus/inode.c +++ b/fs/hfsplus/inode.c @@ -122,8 +122,7 @@ static int hfsplus_releasepage(struct page *page, gfp_t mask) return res ? try_to_free_buffers(page) : 0; } -static ssize_t hfsplus_direct_IO(struct kiocb *iocb, struct iov_iter *iter, - loff_t offset) +static ssize_t hfsplus_direct_IO(struct kiocb *iocb, struct iov_iter *iter) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; @@ -131,7 +130,7 @@ static ssize_t hfsplus_direct_IO(struct kiocb *iocb, struct iov_iter *iter, size_t count = iov_iter_count(iter); ssize_t ret; - ret = blockdev_direct_IO(iocb, inode, iter, offset, hfsplus_get_block); + ret = blockdev_direct_IO(iocb, inode, iter, hfsplus_get_block); /* * In case of error extending write may have instantiated a few @@ -139,7 +138,7 @@ static ssize_t hfsplus_direct_IO(struct kiocb *iocb, struct iov_iter *iter, */ if (unlikely(iov_iter_rw(iter) == WRITE && ret < 0)) { loff_t isize = i_size_read(inode); - loff_t end = offset + count; + loff_t end = iocb->ki_pos + count; if (end > isize) hfsplus_write_failed(mapping, end); @@ -374,6 +373,7 @@ struct inode *hfsplus_new_inode(struct super_block *sb, umode_t mode) hip = HFSPLUS_I(inode); INIT_LIST_HEAD(&hip->open_dir_list); + spin_lock_init(&hip->open_dir_lock); mutex_init(&hip->extents_lock); atomic_set(&hip->opencnt, 0); hip->extent_state = 0; diff --git a/fs/hfsplus/posix_acl.c b/fs/hfsplus/posix_acl.c index afb33ed..ab7ea25 100644 --- a/fs/hfsplus/posix_acl.c +++ b/fs/hfsplus/posix_acl.c @@ -48,9 +48,6 @@ struct posix_acl *hfsplus_get_posix_acl(struct inode *inode, int type) hfsplus_destroy_attr_entry((hfsplus_attr_entry *)value); - if (!IS_ERR(acl)) - set_cached_acl(inode, type, acl); - return acl; } diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c index c359113..755bf30 100644 --- a/fs/hfsplus/super.c +++ b/fs/hfsplus/super.c @@ -67,6 +67,7 @@ struct inode *hfsplus_iget(struct super_block *sb, unsigned long ino) return inode; INIT_LIST_HEAD(&HFSPLUS_I(inode)->open_dir_list); + spin_lock_init(&HFSPLUS_I(inode)->open_dir_lock); mutex_init(&HFSPLUS_I(inode)->extents_lock); HFSPLUS_I(inode)->flags = 0; HFSPLUS_I(inode)->extent_state = 0; diff --git a/fs/hfsplus/xattr.c b/fs/hfsplus/xattr.c index 70e445f..4f118d2 100644 --- a/fs/hfsplus/xattr.c +++ b/fs/hfsplus/xattr.c @@ -579,7 +579,7 @@ failed_getxattr_init: return res; } -ssize_t hfsplus_getxattr(struct dentry *dentry, const char *name, +ssize_t hfsplus_getxattr(struct inode *inode, const char *name, void *value, size_t size, const char *prefix, size_t prefixlen) { @@ -594,7 +594,7 @@ ssize_t hfsplus_getxattr(struct dentry *dentry, const char *name, strcpy(xattr_name, prefix); strcpy(xattr_name + prefixlen, name); - res = __hfsplus_getxattr(d_inode(dentry), xattr_name, value, size); + res = __hfsplus_getxattr(inode, xattr_name, value, size); kfree(xattr_name); return res; @@ -844,8 +844,8 @@ end_removexattr: } static int hfsplus_osx_getxattr(const struct xattr_handler *handler, - struct dentry *dentry, const char *name, - void *buffer, size_t size) + struct dentry *unused, struct inode *inode, + const char *name, void *buffer, size_t size) { /* * Don't allow retrieving properly prefixed attributes @@ -860,7 +860,7 @@ static int hfsplus_osx_getxattr(const struct xattr_handler *handler, * creates), so we pass the name through unmodified (after * ensuring it doesn't conflict with another namespace). */ - return __hfsplus_getxattr(d_inode(dentry), name, buffer, size); + return __hfsplus_getxattr(inode, name, buffer, size); } static int hfsplus_osx_setxattr(const struct xattr_handler *handler, diff --git a/fs/hfsplus/xattr.h b/fs/hfsplus/xattr.h index f9b0955..d04ba6f 100644 --- a/fs/hfsplus/xattr.h +++ b/fs/hfsplus/xattr.h @@ -28,7 +28,7 @@ int hfsplus_setxattr(struct dentry *dentry, const char *name, ssize_t __hfsplus_getxattr(struct inode *inode, const char *name, void *value, size_t size); -ssize_t hfsplus_getxattr(struct dentry *dentry, const char *name, +ssize_t hfsplus_getxattr(struct inode *inode, const char *name, void *value, size_t size, const char *prefix, size_t prefixlen); diff --git a/fs/hfsplus/xattr_security.c b/fs/hfsplus/xattr_security.c index 72a68a3..ae2ca8c 100644 --- a/fs/hfsplus/xattr_security.c +++ b/fs/hfsplus/xattr_security.c @@ -14,10 +14,10 @@ #include "acl.h" static int hfsplus_security_getxattr(const struct xattr_handler *handler, - struct dentry *dentry, const char *name, - void *buffer, size_t size) + struct dentry *unused, struct inode *inode, + const char *name, void *buffer, size_t size) { - return hfsplus_getxattr(dentry, name, buffer, size, + return hfsplus_getxattr(inode, name, buffer, size, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN); } diff --git a/fs/hfsplus/xattr_trusted.c b/fs/hfsplus/xattr_trusted.c index 95a7704..eae2947 100644 --- a/fs/hfsplus/xattr_trusted.c +++ b/fs/hfsplus/xattr_trusted.c @@ -12,10 +12,10 @@ #include "xattr.h" static int hfsplus_trusted_getxattr(const struct xattr_handler *handler, - struct dentry *dentry, const char *name, - void *buffer, size_t size) + struct dentry *unused, struct inode *inode, + const char *name, void *buffer, size_t size) { - return hfsplus_getxattr(dentry, name, buffer, size, + return hfsplus_getxattr(inode, name, buffer, size, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN); } diff --git a/fs/hfsplus/xattr_user.c b/fs/hfsplus/xattr_user.c index 6fc269b..3c9eec3 100644 --- a/fs/hfsplus/xattr_user.c +++ b/fs/hfsplus/xattr_user.c @@ -12,11 +12,11 @@ #include "xattr.h" static int hfsplus_user_getxattr(const struct xattr_handler *handler, - struct dentry *dentry, const char *name, - void *buffer, size_t size) + struct dentry *unused, struct inode *inode, + const char *name, void *buffer, size_t size) { - return hfsplus_getxattr(dentry, name, buffer, size, + return hfsplus_getxattr(inode, name, buffer, size, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN); } diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c index 7016653..5c57654 100644 --- a/fs/hostfs/hostfs_kern.c +++ b/fs/hostfs/hostfs_kern.c @@ -398,7 +398,7 @@ static const struct file_operations hostfs_file_fops = { static const struct file_operations hostfs_dir_fops = { .llseek = generic_file_llseek, - .iterate = hostfs_readdir, + .iterate_shared = hostfs_readdir, .read = generic_read_dir, .open = hostfs_open, .fsync = hostfs_fsync, diff --git a/fs/hpfs/dir.c b/fs/hpfs/dir.c index e57a53c..7b9150c 100644 --- a/fs/hpfs/dir.c +++ b/fs/hpfs/dir.c @@ -44,7 +44,11 @@ static loff_t hpfs_dir_lseek(struct file *filp, loff_t off, int whence) else goto fail; if (pos == 12) goto fail; } - hpfs_add_pos(i, &filp->f_pos); + if (unlikely(hpfs_add_pos(i, &filp->f_pos) < 0)) { + hpfs_unlock(s); + inode_unlock(i); + return -ENOMEM; + } ok: filp->f_pos = new_off; hpfs_unlock(s); @@ -141,8 +145,10 @@ static int hpfs_readdir(struct file *file, struct dir_context *ctx) ctx->pos = 1; } if (ctx->pos == 1) { + ret = hpfs_add_pos(inode, &file->f_pos); + if (unlikely(ret < 0)) + goto out; ctx->pos = ((loff_t) hpfs_de_as_down_as_possible(inode->i_sb, hpfs_inode->i_dno) << 4) + 1; - hpfs_add_pos(inode, &file->f_pos); file->f_version = inode->i_version; } next_pos = ctx->pos; @@ -324,7 +330,7 @@ const struct file_operations hpfs_dir_ops = { .llseek = hpfs_dir_lseek, .read = generic_read_dir, - .iterate = hpfs_readdir, + .iterate_shared = hpfs_readdir, .release = hpfs_dir_release, .fsync = hpfs_file_fsync, .unlocked_ioctl = hpfs_ioctl, diff --git a/fs/hpfs/dnode.c b/fs/hpfs/dnode.c index 2923a7b..86ab7e7 100644 --- a/fs/hpfs/dnode.c +++ b/fs/hpfs/dnode.c @@ -21,7 +21,7 @@ static loff_t get_pos(struct dnode *d, struct hpfs_dirent *fde) return ((loff_t)le32_to_cpu(d->self) << 4) | (loff_t)1; } -void hpfs_add_pos(struct inode *inode, loff_t *pos) +int hpfs_add_pos(struct inode *inode, loff_t *pos) { struct hpfs_inode_info *hpfs_inode = hpfs_i(inode); int i = 0; @@ -29,11 +29,12 @@ void hpfs_add_pos(struct inode *inode, loff_t *pos) if (hpfs_inode->i_rddir_off) for (; hpfs_inode->i_rddir_off[i]; i++) - if (hpfs_inode->i_rddir_off[i] == pos) return; + if (hpfs_inode->i_rddir_off[i] == pos) + return 0; if (!(i&0x0f)) { if (!(ppos = kmalloc((i+0x11) * sizeof(loff_t*), GFP_NOFS))) { pr_err("out of memory for position list\n"); - return; + return -ENOMEM; } if (hpfs_inode->i_rddir_off) { memcpy(ppos, hpfs_inode->i_rddir_off, i * sizeof(loff_t)); @@ -43,6 +44,7 @@ void hpfs_add_pos(struct inode *inode, loff_t *pos) } hpfs_inode->i_rddir_off[i] = pos; hpfs_inode->i_rddir_off[i + 1] = NULL; + return 0; } void hpfs_del_pos(struct inode *inode, loff_t *pos) diff --git a/fs/hpfs/hpfs_fn.h b/fs/hpfs/hpfs_fn.h index 975654a..aebb78f 100644 --- a/fs/hpfs/hpfs_fn.h +++ b/fs/hpfs/hpfs_fn.h @@ -242,7 +242,7 @@ extern const struct file_operations hpfs_dir_ops; /* dnode.c */ -void hpfs_add_pos(struct inode *, loff_t *); +int hpfs_add_pos(struct inode *, loff_t *); void hpfs_del_pos(struct inode *, loff_t *); struct hpfs_dirent *hpfs_add_de(struct super_block *, struct dnode *, const unsigned char *, unsigned, secno); @@ -151,6 +151,7 @@ int inode_init_always(struct super_block *sb, struct inode *inode) inode->i_bdev = NULL; inode->i_cdev = NULL; inode->i_link = NULL; + inode->i_dir_seq = 0; inode->i_rdev = 0; inode->dirtied_when = 0; @@ -165,8 +166,8 @@ int inode_init_always(struct super_block *sb, struct inode *inode) spin_lock_init(&inode->i_lock); lockdep_set_class(&inode->i_lock, &sb->s_type->i_lock_key); - mutex_init(&inode->i_mutex); - lockdep_set_class(&inode->i_mutex, &sb->s_type->i_mutex_key); + init_rwsem(&inode->i_rwsem); + lockdep_set_class(&inode->i_rwsem, &sb->s_type->i_mutex_key); atomic_set(&inode->i_dio_count, 0); @@ -238,9 +239,9 @@ void __destroy_inode(struct inode *inode) } #ifdef CONFIG_FS_POSIX_ACL - if (inode->i_acl && inode->i_acl != ACL_NOT_CACHED) + if (inode->i_acl && !is_uncached_acl(inode->i_acl)) posix_acl_release(inode->i_acl); - if (inode->i_default_acl && inode->i_default_acl != ACL_NOT_CACHED) + if (inode->i_default_acl && !is_uncached_acl(inode->i_default_acl)) posix_acl_release(inode->i_default_acl); #endif this_cpu_dec(nr_inodes); @@ -924,13 +925,13 @@ void lockdep_annotate_inode_mutex_key(struct inode *inode) struct file_system_type *type = inode->i_sb->s_type; /* Set new key only if filesystem hasn't already changed it */ - if (lockdep_match_class(&inode->i_mutex, &type->i_mutex_key)) { + if (lockdep_match_class(&inode->i_rwsem, &type->i_mutex_key)) { /* * ensure nobody is actually holding i_mutex */ - mutex_destroy(&inode->i_mutex); - mutex_init(&inode->i_mutex); - lockdep_set_class(&inode->i_mutex, + // mutex_destroy(&inode->i_mutex); + init_rwsem(&inode->i_rwsem); + lockdep_set_class(&inode->i_rwsem, &type->i_mutex_dir_key); } } diff --git a/fs/isofs/dir.c b/fs/isofs/dir.c index b943cbd..e759961 100644 --- a/fs/isofs/dir.c +++ b/fs/isofs/dir.c @@ -58,7 +58,7 @@ int get_acorn_filename(struct iso_directory_record *de, std = sizeof(struct iso_directory_record) + de->name_len[0]; if (std & 1) std++; - if ((*((unsigned char *) de) - std) != 32) + if (de->length[0] - std != 32) return retnamlen; chr = ((unsigned char *) de) + std; if (strncmp(chr, "ARCHIMEDES", 10)) @@ -269,7 +269,7 @@ const struct file_operations isofs_dir_operations = { .llseek = generic_file_llseek, .read = generic_read_dir, - .iterate = isofs_readdir, + .iterate_shared = isofs_readdir, }; /* diff --git a/fs/isofs/rock.c b/fs/isofs/rock.c index 5384ceb..98b3eb7 100644 --- a/fs/isofs/rock.c +++ b/fs/isofs/rock.c @@ -203,6 +203,8 @@ int get_rock_ridge_filename(struct iso_directory_record *de, int retnamlen = 0; int truncate = 0; int ret = 0; + char *p; + int len; if (!ISOFS_SB(inode->i_sb)->s_rock) return 0; @@ -267,12 +269,17 @@ repeat: rr->u.NM.flags); break; } - if ((strlen(retname) + rr->len - 5) >= 254) { + len = rr->len - 5; + if (retnamlen + len >= 254) { truncate = 1; break; } - strncat(retname, rr->u.NM.name, rr->len - 5); - retnamlen += rr->len - 5; + p = memchr(rr->u.NM.name, '\0', len); + if (unlikely(p)) + len = p - rr->u.NM.name; + memcpy(retname + retnamlen, rr->u.NM.name, len); + retnamlen += len; + retname[retnamlen] = '\0'; break; case SIG('R', 'E'): kfree(rs.buffer); diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c index 08a456b..805bc6b 100644 --- a/fs/jbd2/recovery.c +++ b/fs/jbd2/recovery.c @@ -303,7 +303,7 @@ int jbd2_journal_recover(journal_t *journal) * Locate any valid recovery information from the journal and set up the * journal structures in memory to ignore it (presumably because the * caller has evidence that it is out of date). - * This function does'nt appear to be exorted.. + * This function doesn't appear to be exported.. * * We perform one pass over the journal to allow us to tell the user how * much recovery information is being erased, and to let us initialise diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index 67c1038..2c56c3e 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -543,7 +543,7 @@ EXPORT_SYMBOL(jbd2_journal_start_reserved); * * Some transactions, such as large extends and truncates, can be done * atomically all at once or in several stages. The operation requests - * a credit for a number of buffer modications in advance, but can + * a credit for a number of buffer modifications in advance, but can * extend its credit if it needs more. * * jbd2_journal_extend tries to give the running handle more buffer credits. @@ -627,7 +627,7 @@ error_out: * If the jbd2_journal_extend() call above fails to grant new buffer credits * to a running handle, a call to jbd2_journal_restart will commit the * handle's transaction so far and reattach the handle to a new - * transaction capabable of guaranteeing the requested number of + * transaction capable of guaranteeing the requested number of * credits. We preserve reserved handle if there's any attached to the * passed in handle. */ @@ -1586,7 +1586,7 @@ drop: /** * int jbd2_journal_stop() - complete a transaction - * @handle: tranaction to complete. + * @handle: transaction to complete. * * All done for a particular handle. * diff --git a/fs/jffs2/acl.c b/fs/jffs2/acl.c index 2f7a3c0..bc2693d 100644 --- a/fs/jffs2/acl.c +++ b/fs/jffs2/acl.c @@ -203,8 +203,6 @@ struct posix_acl *jffs2_get_acl(struct inode *inode, int type) acl = ERR_PTR(rc); } kfree(value); - if (!IS_ERR(acl)) - set_cached_acl(inode, type, acl); return acl; } diff --git a/fs/jffs2/dir.c b/fs/jffs2/dir.c index 30c4c9e..84c4bf3 100644 --- a/fs/jffs2/dir.c +++ b/fs/jffs2/dir.c @@ -40,7 +40,7 @@ static int jffs2_rename (struct inode *, struct dentry *, const struct file_operations jffs2_dir_operations = { .read = generic_read_dir, - .iterate = jffs2_readdir, + .iterate_shared=jffs2_readdir, .unlocked_ioctl=jffs2_ioctl, .fsync = jffs2_fsync, .llseek = generic_file_llseek, @@ -241,7 +241,7 @@ static int jffs2_unlink(struct inode *dir_i, struct dentry *dentry) static int jffs2_link (struct dentry *old_dentry, struct inode *dir_i, struct dentry *dentry) { - struct jffs2_sb_info *c = JFFS2_SB_INFO(d_inode(old_dentry)->i_sb); + struct jffs2_sb_info *c = JFFS2_SB_INFO(old_dentry->d_sb); struct jffs2_inode_info *f = JFFS2_INODE_INFO(d_inode(old_dentry)); struct jffs2_inode_info *dir_f = JFFS2_INODE_INFO(dir_i); int ret; diff --git a/fs/jffs2/security.c b/fs/jffs2/security.c index 7a28fac..3ed9a4b4 100644 --- a/fs/jffs2/security.c +++ b/fs/jffs2/security.c @@ -49,10 +49,10 @@ int jffs2_init_security(struct inode *inode, struct inode *dir, /* ---- XATTR Handler for "security.*" ----------------- */ static int jffs2_security_getxattr(const struct xattr_handler *handler, - struct dentry *dentry, const char *name, - void *buffer, size_t size) + struct dentry *unused, struct inode *inode, + const char *name, void *buffer, size_t size) { - return do_jffs2_getxattr(d_inode(dentry), JFFS2_XPREFIX_SECURITY, + return do_jffs2_getxattr(inode, JFFS2_XPREFIX_SECURITY, name, buffer, size); } diff --git a/fs/jffs2/super.c b/fs/jffs2/super.c index 0a9a114..5ef21f4 100644 --- a/fs/jffs2/super.c +++ b/fs/jffs2/super.c @@ -147,7 +147,7 @@ static struct dentry *jffs2_get_parent(struct dentry *child) JFFS2_DEBUG("Parent of directory ino #%u is #%u\n", f->inocache->ino, pino); - return d_obtain_alias(jffs2_iget(d_inode(child)->i_sb, pino)); + return d_obtain_alias(jffs2_iget(child->d_sb, pino)); } static const struct export_operations jffs2_export_ops = { diff --git a/fs/jffs2/xattr_trusted.c b/fs/jffs2/xattr_trusted.c index b2555ef..4ebecff 100644 --- a/fs/jffs2/xattr_trusted.c +++ b/fs/jffs2/xattr_trusted.c @@ -17,10 +17,10 @@ #include "nodelist.h" static int jffs2_trusted_getxattr(const struct xattr_handler *handler, - struct dentry *dentry, const char *name, - void *buffer, size_t size) + struct dentry *unused, struct inode *inode, + const char *name, void *buffer, size_t size) { - return do_jffs2_getxattr(d_inode(dentry), JFFS2_XPREFIX_TRUSTED, + return do_jffs2_getxattr(inode, JFFS2_XPREFIX_TRUSTED, name, buffer, size); } diff --git a/fs/jffs2/xattr_user.c b/fs/jffs2/xattr_user.c index 539bd63..bce249e 100644 --- a/fs/jffs2/xattr_user.c +++ b/fs/jffs2/xattr_user.c @@ -17,10 +17,10 @@ #include "nodelist.h" static int jffs2_user_getxattr(const struct xattr_handler *handler, - struct dentry *dentry, const char *name, - void *buffer, size_t size) + struct dentry *unused, struct inode *inode, + const char *name, void *buffer, size_t size) { - return do_jffs2_getxattr(d_inode(dentry), JFFS2_XPREFIX_USER, + return do_jffs2_getxattr(inode, JFFS2_XPREFIX_USER, name, buffer, size); } diff --git a/fs/jfs/acl.c b/fs/jfs/acl.c index 4945685..21fa92b 100644 --- a/fs/jfs/acl.c +++ b/fs/jfs/acl.c @@ -34,10 +34,6 @@ struct posix_acl *jfs_get_acl(struct inode *inode, int type) int size; char *value = NULL; - acl = get_cached_acl(inode, type); - if (acl != ACL_NOT_CACHED) - return acl; - switch(type) { case ACL_TYPE_ACCESS: ea_name = XATTR_NAME_POSIX_ACL_ACCESS; @@ -67,8 +63,6 @@ struct posix_acl *jfs_get_acl(struct inode *inode, int type) acl = posix_acl_from_xattr(&init_user_ns, value, size); } kfree(value); - if (!IS_ERR(acl)) - set_cached_acl(inode, type, acl); return acl; } diff --git a/fs/jfs/file.c b/fs/jfs/file.c index 4ce7735..7f1a585 100644 --- a/fs/jfs/file.c +++ b/fs/jfs/file.c @@ -140,10 +140,10 @@ int jfs_setattr(struct dentry *dentry, struct iattr *iattr) } const struct inode_operations jfs_file_inode_operations = { - .setxattr = jfs_setxattr, - .getxattr = jfs_getxattr, + .setxattr = generic_setxattr, + .getxattr = generic_getxattr, .listxattr = jfs_listxattr, - .removexattr = jfs_removexattr, + .removexattr = generic_removexattr, .setattr = jfs_setattr, #ifdef CONFIG_JFS_POSIX_ACL .get_acl = jfs_get_acl, diff --git a/fs/jfs/inode.c b/fs/jfs/inode.c index 9d9bae6..ad3e7b1 100644 --- a/fs/jfs/inode.c +++ b/fs/jfs/inode.c @@ -102,8 +102,8 @@ int jfs_commit_inode(struct inode *inode, int wait) * partitions and may think inode is dirty */ if (!special_file(inode->i_mode) && noisy) { - jfs_err("jfs_commit_inode(0x%p) called on " - "read-only volume", inode); + jfs_err("jfs_commit_inode(0x%p) called on read-only volume", + inode); jfs_err("Is remount racy?"); noisy--; } @@ -332,8 +332,7 @@ static sector_t jfs_bmap(struct address_space *mapping, sector_t block) return generic_block_bmap(mapping, block, jfs_get_block); } -static ssize_t jfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, - loff_t offset) +static ssize_t jfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; @@ -341,7 +340,7 @@ static ssize_t jfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, size_t count = iov_iter_count(iter); ssize_t ret; - ret = blockdev_direct_IO(iocb, inode, iter, offset, jfs_get_block); + ret = blockdev_direct_IO(iocb, inode, iter, jfs_get_block); /* * In case of error extending write may have instantiated a few @@ -349,7 +348,7 @@ static ssize_t jfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, */ if (unlikely(iov_iter_rw(iter) == WRITE && ret < 0)) { loff_t isize = i_size_read(inode); - loff_t end = offset + count; + loff_t end = iocb->ki_pos + count; if (end > isize) jfs_write_failed(mapping, end); diff --git a/fs/jfs/jfs_discard.c b/fs/jfs/jfs_discard.c index dfcd503..f76ff0a 100644 --- a/fs/jfs/jfs_discard.c +++ b/fs/jfs/jfs_discard.c @@ -49,14 +49,12 @@ void jfs_issue_discard(struct inode *ip, u64 blkno, u64 nblocks) r = sb_issue_discard(sb, blkno, nblocks, GFP_NOFS, 0); if (unlikely(r != 0)) { - jfs_err("JFS: sb_issue_discard" \ - "(%p, %llu, %llu, GFP_NOFS, 0) = %d => failed!\n", + jfs_err("JFS: sb_issue_discard(%p, %llu, %llu, GFP_NOFS, 0) = %d => failed!", sb, (unsigned long long)blkno, (unsigned long long)nblocks, r); } - jfs_info("JFS: sb_issue_discard" \ - "(%p, %llu, %llu, GFP_NOFS, 0) = %d\n", + jfs_info("JFS: sb_issue_discard(%p, %llu, %llu, GFP_NOFS, 0) = %d", sb, (unsigned long long)blkno, (unsigned long long)nblocks, r); diff --git a/fs/jfs/jfs_dtree.c b/fs/jfs/jfs_dtree.c index d88576e..de2bcb3 100644 --- a/fs/jfs/jfs_dtree.c +++ b/fs/jfs/jfs_dtree.c @@ -3072,8 +3072,7 @@ int jfs_readdir(struct file *file, struct dir_context *ctx) } if (dirtab_slot.flag == DIR_INDEX_FREE) { if (loop_count++ > JFS_IP(ip)->next_index) { - jfs_err("jfs_readdir detected " - "infinite loop!"); + jfs_err("jfs_readdir detected infinite loop!"); ctx->pos = DIREND; return 0; } @@ -3151,8 +3150,7 @@ int jfs_readdir(struct file *file, struct dir_context *ctx) if (!dir_emit(ctx, "..", 2, PARENT(ip), DT_DIR)) return 0; } else { - jfs_err("jfs_readdir called with " - "invalid offset!"); + jfs_err("jfs_readdir called with invalid offset!"); } dtoffset->pn = 1; dtoffset->index = 0; @@ -3165,8 +3163,8 @@ int jfs_readdir(struct file *file, struct dir_context *ctx) } if ((rc = dtReadNext(ip, &ctx->pos, &btstack))) { - jfs_err("jfs_readdir: unexpected rc = %d " - "from dtReadNext", rc); + jfs_err("jfs_readdir: unexpected rc = %d from dtReadNext", + rc); ctx->pos = DIREND; return 0; } diff --git a/fs/jfs/jfs_imap.c b/fs/jfs/jfs_imap.c index f321986..6aca224 100644 --- a/fs/jfs/jfs_imap.c +++ b/fs/jfs/jfs_imap.c @@ -534,8 +534,7 @@ void diWriteSpecial(struct inode *ip, int secondary) /* read the page of fixed disk inode (AIT) in raw mode */ mp = read_metapage(ip, address << sbi->l2nbperpage, PSIZE, 1); if (mp == NULL) { - jfs_err("diWriteSpecial: failed to read aggregate inode " - "extent!"); + jfs_err("diWriteSpecial: failed to read aggregate inode extent!"); return; } diff --git a/fs/jfs/jfs_inode.c b/fs/jfs/jfs_inode.c index cf7936f..5e33cb9 100644 --- a/fs/jfs/jfs_inode.c +++ b/fs/jfs/jfs_inode.c @@ -151,7 +151,7 @@ struct inode *ialloc(struct inode *parent, umode_t mode) jfs_inode->xtlid = 0; jfs_set_inode_flags(inode); - jfs_info("ialloc returns inode = 0x%p\n", inode); + jfs_info("ialloc returns inode = 0x%p", inode); return inode; diff --git a/fs/jfs/jfs_logmgr.c b/fs/jfs/jfs_logmgr.c index a270cb7..63759d7 100644 --- a/fs/jfs/jfs_logmgr.c +++ b/fs/jfs/jfs_logmgr.c @@ -1094,7 +1094,7 @@ int lmLogOpen(struct super_block *sb) if (log->bdev->bd_dev == sbi->logdev) { if (memcmp(log->uuid, sbi->loguuid, sizeof(log->uuid))) { - jfs_warn("wrong uuid on JFS journal\n"); + jfs_warn("wrong uuid on JFS journal"); mutex_unlock(&jfs_log_mutex); return -EINVAL; } @@ -1333,9 +1333,8 @@ int lmLogInit(struct jfs_log * log) rc = -EINVAL; goto errout20; } - jfs_info("lmLogInit: inline log:0x%p base:0x%Lx " - "size:0x%x", log, - (unsigned long long) log->base, log->size); + jfs_info("lmLogInit: inline log:0x%p base:0x%Lx size:0x%x", + log, (unsigned long long)log->base, log->size); } else { if (memcmp(logsuper->uuid, log->uuid, 16)) { jfs_warn("wrong uuid on JFS log device"); @@ -1343,9 +1342,8 @@ int lmLogInit(struct jfs_log * log) } log->size = le32_to_cpu(logsuper->size); log->l2bsize = le32_to_cpu(logsuper->l2bsize); - jfs_info("lmLogInit: external log:0x%p base:0x%Lx " - "size:0x%x", log, - (unsigned long long) log->base, log->size); + jfs_info("lmLogInit: external log:0x%p base:0x%Lx size:0x%x", + log, (unsigned long long)log->base, log->size); } log->page = le32_to_cpu(logsuper->end) / LOGPSIZE; @@ -2136,7 +2134,7 @@ static void lbmStartIO(struct lbuf * bp) struct bio *bio; struct jfs_log *log = bp->l_log; - jfs_info("lbmStartIO\n"); + jfs_info("lbmStartIO"); bio = bio_alloc(GFP_NOFS, 1); bio->bi_iter.bi_sector = bp->l_blkno << (log->l2bsize - 9); diff --git a/fs/jfs/jfs_txnmgr.c b/fs/jfs/jfs_txnmgr.c index d595856..eddf2b6 100644 --- a/fs/jfs/jfs_txnmgr.c +++ b/fs/jfs/jfs_txnmgr.c @@ -1764,7 +1764,7 @@ static void xtLog(struct jfs_log * log, struct tblock * tblk, struct lrd * lrd, if (lwm == next) goto out; if (lwm > next) { - jfs_err("xtLog: lwm > next\n"); + jfs_err("xtLog: lwm > next"); goto out; } tlck->flag |= tlckUPDATEMAP; @@ -1798,8 +1798,8 @@ static void xtLog(struct jfs_log * log, struct tblock * tblk, struct lrd * lrd, xadlock->xdlist = &p->xad[lwm]; tblk->xflag &= ~COMMIT_LAZY; } - jfs_info("xtLog: alloc ip:0x%p mp:0x%p tlck:0x%p lwm:%d " - "count:%d", tlck->ip, mp, tlck, lwm, xadlock->count); + jfs_info("xtLog: alloc ip:0x%p mp:0x%p tlck:0x%p lwm:%d count:%d", + tlck->ip, mp, tlck, lwm, xadlock->count); maplock->index = 1; @@ -2025,8 +2025,7 @@ static void xtLog(struct jfs_log * log, struct tblock * tblk, struct lrd * lrd, xadlock->count = next - lwm; xadlock->xdlist = &p->xad[lwm]; - jfs_info("xtLog: alloc ip:0x%p mp:0x%p count:%d " - "lwm:%d next:%d", + jfs_info("xtLog: alloc ip:0x%p mp:0x%p count:%d lwm:%d next:%d", tlck->ip, mp, xadlock->count, lwm, next); maplock->index++; xadlock++; @@ -2047,8 +2046,8 @@ static void xtLog(struct jfs_log * log, struct tblock * tblk, struct lrd * lrd, pxdlock->count = 1; pxdlock->pxd = pxd; - jfs_info("xtLog: truncate ip:0x%p mp:0x%p count:%d " - "hwm:%d", ip, mp, pxdlock->count, hwm); + jfs_info("xtLog: truncate ip:0x%p mp:0x%p count:%d hwm:%d", + ip, mp, pxdlock->count, hwm); maplock->index++; xadlock++; } @@ -2066,8 +2065,7 @@ static void xtLog(struct jfs_log * log, struct tblock * tblk, struct lrd * lrd, xadlock->count = hwm - next + 1; xadlock->xdlist = &p->xad[next]; - jfs_info("xtLog: free ip:0x%p mp:0x%p count:%d " - "next:%d hwm:%d", + jfs_info("xtLog: free ip:0x%p mp:0x%p count:%d next:%d hwm:%d", tlck->ip, mp, xadlock->count, next, hwm); maplock->index++; } @@ -2523,8 +2521,7 @@ void txFreeMap(struct inode *ip, xlen = lengthXAD(xad); dbUpdatePMap(ipbmap, true, xaddr, (s64) xlen, tblk); - jfs_info("freePMap: xaddr:0x%lx " - "xlen:%d", + jfs_info("freePMap: xaddr:0x%lx xlen:%d", (ulong) xaddr, xlen); } } @@ -2814,7 +2811,7 @@ int jfs_lazycommit(void *arg) if (!list_empty(&TxAnchor.unlock_queue)) jfs_err("jfs_lazycommit being killed w/pending transactions!"); else - jfs_info("jfs_lazycommit being killed\n"); + jfs_info("jfs_lazycommit being killed"); return 0; } diff --git a/fs/jfs/jfs_xattr.h b/fs/jfs/jfs_xattr.h index e8d717d..561f6af4 100644 --- a/fs/jfs/jfs_xattr.h +++ b/fs/jfs/jfs_xattr.h @@ -19,6 +19,8 @@ #ifndef H_JFS_XATTR #define H_JFS_XATTR +#include <linux/xattr.h> + /* * jfs_ea_list describe the on-disk format of the extended attributes. * I know the null-terminator is redundant since namelen is stored, but @@ -54,12 +56,8 @@ struct jfs_ea_list { extern int __jfs_setxattr(tid_t, struct inode *, const char *, const void *, size_t, int); -extern int jfs_setxattr(struct dentry *, const char *, const void *, size_t, - int); extern ssize_t __jfs_getxattr(struct inode *, const char *, void *, size_t); -extern ssize_t jfs_getxattr(struct dentry *, const char *, void *, size_t); extern ssize_t jfs_listxattr(struct dentry *, char *, size_t); -extern int jfs_removexattr(struct dentry *, const char *); extern const struct xattr_handler *jfs_xattr_handlers[]; diff --git a/fs/jfs/namei.c b/fs/jfs/namei.c index 701f893..539dedd 100644 --- a/fs/jfs/namei.c +++ b/fs/jfs/namei.c @@ -1225,8 +1225,8 @@ static int jfs_rename(struct inode *old_dir, struct dentry *old_dentry, rc = dtSearch(new_dir, &new_dname, &ino, &btstack, JFS_CREATE); if (rc) { - jfs_err("jfs_rename didn't expect dtSearch to fail " - "w/rc = %d", rc); + jfs_err("jfs_rename didn't expect dtSearch to fail w/rc = %d", + rc); goto out_tx; } @@ -1524,7 +1524,7 @@ struct dentry *jfs_get_parent(struct dentry *dentry) parent_ino = le32_to_cpu(JFS_IP(d_inode(dentry))->i_dtroot.header.idotdot); - return d_obtain_alias(jfs_iget(d_inode(dentry)->i_sb, parent_ino)); + return d_obtain_alias(jfs_iget(dentry->d_sb, parent_ino)); } const struct inode_operations jfs_dir_inode_operations = { @@ -1537,10 +1537,10 @@ const struct inode_operations jfs_dir_inode_operations = { .rmdir = jfs_rmdir, .mknod = jfs_mknod, .rename = jfs_rename, - .setxattr = jfs_setxattr, - .getxattr = jfs_getxattr, + .setxattr = generic_setxattr, + .getxattr = generic_getxattr, .listxattr = jfs_listxattr, - .removexattr = jfs_removexattr, + .removexattr = generic_removexattr, .setattr = jfs_setattr, #ifdef CONFIG_JFS_POSIX_ACL .get_acl = jfs_get_acl, diff --git a/fs/jfs/super.c b/fs/jfs/super.c index 78d5991..cec8814 100644 --- a/fs/jfs/super.c +++ b/fs/jfs/super.c @@ -84,7 +84,7 @@ static void jfs_handle_error(struct super_block *sb) panic("JFS (device %s): panic forced after error\n", sb->s_id); else if (sbi->flag & JFS_ERR_REMOUNT_RO) { - jfs_err("ERROR: (device %s): remounting filesystem as read-only\n", + jfs_err("ERROR: (device %s): remounting filesystem as read-only", sb->s_id); sb->s_flags |= MS_RDONLY; } @@ -641,7 +641,7 @@ static int jfs_freeze(struct super_block *sb) } rc = updateSuper(sb, FM_CLEAN); if (rc) { - jfs_err("jfs_freeze: updateSuper failed\n"); + jfs_err("jfs_freeze: updateSuper failed"); /* * Don't fail here. Everything succeeded except * marking the superblock clean, so there's really diff --git a/fs/jfs/symlink.c b/fs/jfs/symlink.c index f8db4fd..c94c7e4 100644 --- a/fs/jfs/symlink.c +++ b/fs/jfs/symlink.c @@ -25,19 +25,19 @@ const struct inode_operations jfs_fast_symlink_inode_operations = { .readlink = generic_readlink, .get_link = simple_get_link, .setattr = jfs_setattr, - .setxattr = jfs_setxattr, - .getxattr = jfs_getxattr, + .setxattr = generic_setxattr, + .getxattr = generic_getxattr, .listxattr = jfs_listxattr, - .removexattr = jfs_removexattr, + .removexattr = generic_removexattr, }; const struct inode_operations jfs_symlink_inode_operations = { .readlink = generic_readlink, .get_link = page_get_link, .setattr = jfs_setattr, - .setxattr = jfs_setxattr, - .getxattr = jfs_getxattr, + .setxattr = generic_setxattr, + .getxattr = generic_getxattr, .listxattr = jfs_listxattr, - .removexattr = jfs_removexattr, + .removexattr = generic_removexattr, }; diff --git a/fs/jfs/xattr.c b/fs/jfs/xattr.c index 48b15a6..beb182b 100644 --- a/fs/jfs/xattr.c +++ b/fs/jfs/xattr.c @@ -86,6 +86,14 @@ struct ea_buffer { #define EA_MALLOC 0x0008 +/* + * Mapping of on-disk attribute names: for on-disk attribute names with an + * unknown prefix (not "system.", "user.", "security.", or "trusted."), the + * prefix "os2." is prepended. On the way back to disk, "os2." prefixes are + * stripped and we make sure that the remaining name does not start with one + * of the know prefixes. + */ + static int is_known_namespace(const char *name) { if (strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN) && @@ -97,29 +105,19 @@ static int is_known_namespace(const char *name) return true; } -/* - * These three routines are used to recognize on-disk extended attributes - * that are in a recognized namespace. If the attribute is not recognized, - * "os2." is prepended to the name - */ -static int is_os2_xattr(struct jfs_ea *ea) -{ - return !is_known_namespace(ea->name); -} - static inline int name_size(struct jfs_ea *ea) { - if (is_os2_xattr(ea)) - return ea->namelen + XATTR_OS2_PREFIX_LEN; - else + if (is_known_namespace(ea->name)) return ea->namelen; + else + return ea->namelen + XATTR_OS2_PREFIX_LEN; } static inline int copy_name(char *buffer, struct jfs_ea *ea) { int len = ea->namelen; - if (is_os2_xattr(ea)) { + if (!is_known_namespace(ea->name)) { memcpy(buffer, XATTR_OS2_PREFIX, XATTR_OS2_PREFIX_LEN); buffer += XATTR_OS2_PREFIX_LEN; len += XATTR_OS2_PREFIX_LEN; @@ -665,35 +663,6 @@ static int ea_put(tid_t tid, struct inode *inode, struct ea_buffer *ea_buf, return 0; } -/* - * Most of the permission checking is done by xattr_permission in the vfs. - * We also need to verify that this is a namespace that we recognize. - */ -static int can_set_xattr(struct inode *inode, const char *name, - const void *value, size_t value_len) -{ - if (!strncmp(name, XATTR_OS2_PREFIX, XATTR_OS2_PREFIX_LEN)) { - /* - * This makes sure that we aren't trying to set an - * attribute in a different namespace by prefixing it - * with "os2." - */ - if (is_known_namespace(name + XATTR_OS2_PREFIX_LEN)) - return -EOPNOTSUPP; - return 0; - } - - /* - * Don't allow setting an attribute in an unknown namespace. - */ - if (strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN) && - strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN) && - strncmp(name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN)) - return -EOPNOTSUPP; - - return 0; -} - int __jfs_setxattr(tid_t tid, struct inode *inode, const char *name, const void *value, size_t value_len, int flags) { @@ -704,21 +673,10 @@ int __jfs_setxattr(tid_t tid, struct inode *inode, const char *name, int xattr_size; int new_size; int namelen = strlen(name); - char *os2name = NULL; int found = 0; int rc; int length; - if (strncmp(name, XATTR_OS2_PREFIX, XATTR_OS2_PREFIX_LEN) == 0) { - os2name = kmalloc(namelen - XATTR_OS2_PREFIX_LEN + 1, - GFP_KERNEL); - if (!os2name) - return -ENOMEM; - strcpy(os2name, name + XATTR_OS2_PREFIX_LEN); - name = os2name; - namelen -= XATTR_OS2_PREFIX_LEN; - } - down_write(&JFS_IP(inode)->xattr_sem); xattr_size = ea_get(inode, &ea_buf, 0); @@ -841,44 +799,6 @@ int __jfs_setxattr(tid_t tid, struct inode *inode, const char *name, out: up_write(&JFS_IP(inode)->xattr_sem); - kfree(os2name); - - return rc; -} - -int jfs_setxattr(struct dentry *dentry, const char *name, const void *value, - size_t value_len, int flags) -{ - struct inode *inode = d_inode(dentry); - struct jfs_inode_info *ji = JFS_IP(inode); - int rc; - tid_t tid; - - /* - * If this is a request for a synthetic attribute in the system.* - * namespace use the generic infrastructure to resolve a handler - * for it via sb->s_xattr. - */ - if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN)) - return generic_setxattr(dentry, name, value, value_len, flags); - - if ((rc = can_set_xattr(inode, name, value, value_len))) - return rc; - - if (value == NULL) { /* empty EA, do not remove */ - value = ""; - value_len = 0; - } - - tid = txBegin(inode->i_sb, 0); - mutex_lock(&ji->commit_mutex); - rc = __jfs_setxattr(tid, d_inode(dentry), name, value, value_len, - flags); - if (!rc) - rc = txCommit(tid, 1, &inode, 0); - txEnd(tid); - mutex_unlock(&ji->commit_mutex); - return rc; } @@ -933,37 +853,6 @@ ssize_t __jfs_getxattr(struct inode *inode, const char *name, void *data, return size; } -ssize_t jfs_getxattr(struct dentry *dentry, const char *name, void *data, - size_t buf_size) -{ - int err; - - /* - * If this is a request for a synthetic attribute in the system.* - * namespace use the generic infrastructure to resolve a handler - * for it via sb->s_xattr. - */ - if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN)) - return generic_getxattr(dentry, name, data, buf_size); - - if (strncmp(name, XATTR_OS2_PREFIX, XATTR_OS2_PREFIX_LEN) == 0) { - /* - * skip past "os2." prefix - */ - name += XATTR_OS2_PREFIX_LEN; - /* - * Don't allow retrieving properly prefixed attributes - * by prepending them with "os2." - */ - if (is_known_namespace(name)) - return -EOPNOTSUPP; - } - - err = __jfs_getxattr(d_inode(dentry), name, data, buf_size); - - return err; -} - /* * No special permissions are needed to list attributes except for trusted.* */ @@ -1027,27 +916,16 @@ ssize_t jfs_listxattr(struct dentry * dentry, char *data, size_t buf_size) return size; } -int jfs_removexattr(struct dentry *dentry, const char *name) +static int __jfs_xattr_set(struct inode *inode, const char *name, + const void *value, size_t size, int flags) { - struct inode *inode = d_inode(dentry); struct jfs_inode_info *ji = JFS_IP(inode); - int rc; tid_t tid; - - /* - * If this is a request for a synthetic attribute in the system.* - * namespace use the generic infrastructure to resolve a handler - * for it via sb->s_xattr. - */ - if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN)) - return generic_removexattr(dentry, name); - - if ((rc = can_set_xattr(inode, name, NULL, 0))) - return rc; + int rc; tid = txBegin(inode->i_sb, 0); mutex_lock(&ji->commit_mutex); - rc = __jfs_setxattr(tid, d_inode(dentry), name, NULL, 0, XATTR_REPLACE); + rc = __jfs_setxattr(tid, inode, name, value, size, flags); if (!rc) rc = txCommit(tid, 1, &inode, 0); txEnd(tid); @@ -1056,15 +934,77 @@ int jfs_removexattr(struct dentry *dentry, const char *name) return rc; } -/* - * List of handlers for synthetic system.* attributes. All real ondisk - * attributes are handled directly. - */ +static int jfs_xattr_get(const struct xattr_handler *handler, + struct dentry *unused, struct inode *inode, + const char *name, void *value, size_t size) +{ + name = xattr_full_name(handler, name); + return __jfs_getxattr(inode, name, value, size); +} + +static int jfs_xattr_set(const struct xattr_handler *handler, + struct dentry *dentry, const char *name, + const void *value, size_t size, int flags) +{ + struct inode *inode = d_inode(dentry); + + name = xattr_full_name(handler, name); + return __jfs_xattr_set(inode, name, value, size, flags); +} + +static int jfs_xattr_get_os2(const struct xattr_handler *handler, + struct dentry *unused, struct inode *inode, + const char *name, void *value, size_t size) +{ + if (is_known_namespace(name)) + return -EOPNOTSUPP; + return __jfs_getxattr(inode, name, value, size); +} + +static int jfs_xattr_set_os2(const struct xattr_handler *handler, + struct dentry *dentry, const char *name, + const void *value, size_t size, int flags) +{ + struct inode *inode = d_inode(dentry); + + if (is_known_namespace(name)) + return -EOPNOTSUPP; + return __jfs_xattr_set(inode, name, value, size, flags); +} + +static const struct xattr_handler jfs_user_xattr_handler = { + .prefix = XATTR_USER_PREFIX, + .get = jfs_xattr_get, + .set = jfs_xattr_set, +}; + +static const struct xattr_handler jfs_os2_xattr_handler = { + .prefix = XATTR_OS2_PREFIX, + .get = jfs_xattr_get_os2, + .set = jfs_xattr_set_os2, +}; + +static const struct xattr_handler jfs_security_xattr_handler = { + .prefix = XATTR_SECURITY_PREFIX, + .get = jfs_xattr_get, + .set = jfs_xattr_set, +}; + +static const struct xattr_handler jfs_trusted_xattr_handler = { + .prefix = XATTR_TRUSTED_PREFIX, + .get = jfs_xattr_get, + .set = jfs_xattr_set, +}; + const struct xattr_handler *jfs_xattr_handlers[] = { #ifdef CONFIG_JFS_POSIX_ACL &posix_acl_access_xattr_handler, &posix_acl_default_xattr_handler, #endif + &jfs_os2_xattr_handler, + &jfs_user_xattr_handler, + &jfs_security_xattr_handler, + &jfs_trusted_xattr_handler, NULL, }; diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c index 03b688d..68a4431 100644 --- a/fs/kernfs/dir.c +++ b/fs/kernfs/dir.c @@ -153,9 +153,9 @@ static int kernfs_path_from_node_locked(struct kernfs_node *kn_to, p = buf + len + nlen; *p = '\0'; for (kn = kn_to; kn != common; kn = kn->parent) { - nlen = strlen(kn->name); - p -= nlen; - memcpy(p, kn->name, nlen); + size_t tmp = strlen(kn->name); + p -= tmp; + memcpy(p, kn->name, tmp); *(--p) = '/'; } @@ -1643,22 +1643,9 @@ static int kernfs_fop_readdir(struct file *file, struct dir_context *ctx) return 0; } -static loff_t kernfs_dir_fop_llseek(struct file *file, loff_t offset, - int whence) -{ - struct inode *inode = file_inode(file); - loff_t ret; - - inode_lock(inode); - ret = generic_file_llseek(file, offset, whence); - inode_unlock(inode); - - return ret; -} - const struct file_operations kernfs_dir_fops = { .read = generic_read_dir, - .iterate = kernfs_fop_readdir, + .iterate_shared = kernfs_fop_readdir, .release = kernfs_dir_fop_release, - .llseek = kernfs_dir_fop_llseek, + .llseek = generic_file_llseek, }; diff --git a/fs/kernfs/inode.c b/fs/kernfs/inode.c index 16405ae..b524722 100644 --- a/fs/kernfs/inode.c +++ b/fs/kernfs/inode.c @@ -208,10 +208,10 @@ int kernfs_iop_removexattr(struct dentry *dentry, const char *name) return simple_xattr_set(&attrs->xattrs, name, NULL, 0, XATTR_REPLACE); } -ssize_t kernfs_iop_getxattr(struct dentry *dentry, const char *name, void *buf, - size_t size) +ssize_t kernfs_iop_getxattr(struct dentry *unused, struct inode *inode, + const char *name, void *buf, size_t size) { - struct kernfs_node *kn = dentry->d_fsdata; + struct kernfs_node *kn = inode->i_private; struct kernfs_iattrs *attrs; attrs = kernfs_iattrs(kn); diff --git a/fs/kernfs/kernfs-internal.h b/fs/kernfs/kernfs-internal.h index 6762bfb..45c9192 100644 --- a/fs/kernfs/kernfs-internal.h +++ b/fs/kernfs/kernfs-internal.h @@ -84,8 +84,8 @@ int kernfs_iop_getattr(struct vfsmount *mnt, struct dentry *dentry, int kernfs_iop_setxattr(struct dentry *dentry, const char *name, const void *value, size_t size, int flags); int kernfs_iop_removexattr(struct dentry *dentry, const char *name); -ssize_t kernfs_iop_getxattr(struct dentry *dentry, const char *name, void *buf, - size_t size); +ssize_t kernfs_iop_getxattr(struct dentry *dentry, struct inode *inode, + const char *name, void *buf, size_t size); ssize_t kernfs_iop_listxattr(struct dentry *dentry, char *buf, size_t size); /* diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c index f73541f..63534f5 100644 --- a/fs/kernfs/mount.c +++ b/fs/kernfs/mount.c @@ -15,6 +15,7 @@ #include <linux/slab.h> #include <linux/pagemap.h> #include <linux/namei.h> +#include <linux/seq_file.h> #include "kernfs-internal.h" @@ -40,6 +41,19 @@ static int kernfs_sop_show_options(struct seq_file *sf, struct dentry *dentry) return 0; } +static int kernfs_sop_show_path(struct seq_file *sf, struct dentry *dentry) +{ + struct kernfs_node *node = dentry->d_fsdata; + struct kernfs_root *root = kernfs_root(node); + struct kernfs_syscall_ops *scops = root->syscall_ops; + + if (scops && scops->show_path) + return scops->show_path(sf, node, root); + + seq_dentry(sf, dentry, " \t\n\\"); + return 0; +} + const struct super_operations kernfs_sops = { .statfs = simple_statfs, .drop_inode = generic_delete_inode, @@ -47,6 +61,7 @@ const struct super_operations kernfs_sops = { .remount_fs = kernfs_sop_remount_fs, .show_options = kernfs_sop_show_options, + .show_path = kernfs_sop_show_path, }; /** @@ -120,9 +135,8 @@ struct dentry *kernfs_node_dentry(struct kernfs_node *kn, kntmp = find_next_ancestor(kn, knparent); if (WARN_ON(!kntmp)) return ERR_PTR(-EINVAL); - mutex_lock(&d_inode(dentry)->i_mutex); - dtmp = lookup_one_len(kntmp->name, dentry, strlen(kntmp->name)); - mutex_unlock(&d_inode(dentry)->i_mutex); + dtmp = lookup_one_len_unlocked(kntmp->name, dentry, + strlen(kntmp->name)); dput(dentry); if (IS_ERR(dtmp)) return dtmp; @@ -89,7 +89,6 @@ EXPORT_SYMBOL(dcache_dir_close); loff_t dcache_dir_lseek(struct file *file, loff_t offset, int whence) { struct dentry *dentry = file->f_path.dentry; - inode_lock(d_inode(dentry)); switch (whence) { case 1: offset += file->f_pos; @@ -97,7 +96,6 @@ loff_t dcache_dir_lseek(struct file *file, loff_t offset, int whence) if (offset >= 0) break; default: - inode_unlock(d_inode(dentry)); return -EINVAL; } if (offset != file->f_pos) { @@ -124,7 +122,6 @@ loff_t dcache_dir_lseek(struct file *file, loff_t offset, int whence) spin_unlock(&dentry->d_lock); } } - inode_unlock(d_inode(dentry)); return offset; } EXPORT_SYMBOL(dcache_dir_lseek); @@ -190,7 +187,7 @@ const struct file_operations simple_dir_operations = { .release = dcache_dir_close, .llseek = dcache_dir_lseek, .read = generic_read_dir, - .iterate = dcache_readdir, + .iterate_shared = dcache_readdir, .fsync = noop_fsync, }; EXPORT_SYMBOL(simple_dir_operations); @@ -1127,8 +1124,8 @@ static int empty_dir_setxattr(struct dentry *dentry, const char *name, return -EOPNOTSUPP; } -static ssize_t empty_dir_getxattr(struct dentry *dentry, const char *name, - void *value, size_t size) +static ssize_t empty_dir_getxattr(struct dentry *dentry, struct inode *inode, + const char *name, void *value, size_t size) { return -EOPNOTSUPP; } @@ -1169,7 +1166,7 @@ static int empty_dir_readdir(struct file *file, struct dir_context *ctx) static const struct file_operations empty_dir_operations = { .llseek = empty_dir_llseek, .read = generic_read_dir, - .iterate = empty_dir_readdir, + .iterate_shared = empty_dir_readdir, .fsync = noop_fsync, }; diff --git a/fs/logfs/dir.c b/fs/logfs/dir.c index ddbed2b..2d5336b 100644 --- a/fs/logfs/dir.c +++ b/fs/logfs/dir.c @@ -791,7 +791,7 @@ const struct inode_operations logfs_dir_iops = { const struct file_operations logfs_dir_fops = { .fsync = logfs_fsync, .unlocked_ioctl = logfs_ioctl, - .iterate = logfs_readdir, + .iterate_shared = logfs_readdir, .read = generic_read_dir, - .llseek = default_llseek, + .llseek = generic_file_llseek, }; diff --git a/fs/minix/dir.c b/fs/minix/dir.c index 33957c0..31dcd51 100644 --- a/fs/minix/dir.c +++ b/fs/minix/dir.c @@ -21,7 +21,7 @@ static int minix_readdir(struct file *, struct dir_context *); const struct file_operations minix_dir_operations = { .llseek = generic_file_llseek, .read = generic_read_dir, - .iterate = minix_readdir, + .iterate_shared = minix_readdir, .fsync = generic_file_fsync, }; @@ -265,7 +265,7 @@ static int check_acl(struct inode *inode, int mask) if (!acl) return -EAGAIN; /* no ->get_acl() calls in RCU mode... */ - if (acl == ACL_NOT_CACHED) + if (is_uncached_acl(acl)) return -ECHILD; return posix_acl_permission(inode, acl, mask & ~MAY_NOT_BLOCK); } @@ -1603,32 +1603,42 @@ static struct dentry *lookup_slow(const struct qstr *name, struct dentry *dir, unsigned int flags) { - struct dentry *dentry; - inode_lock(dir->d_inode); - dentry = d_lookup(dir, name); - if (unlikely(dentry)) { + struct dentry *dentry = ERR_PTR(-ENOENT), *old; + struct inode *inode = dir->d_inode; + DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq); + + inode_lock_shared(inode); + /* Don't go there if it's already dead */ + if (unlikely(IS_DEADDIR(inode))) + goto out; +again: + dentry = d_alloc_parallel(dir, name, &wq); + if (IS_ERR(dentry)) + goto out; + if (unlikely(!d_in_lookup(dentry))) { if ((dentry->d_flags & DCACHE_OP_REVALIDATE) && !(flags & LOOKUP_NO_REVAL)) { int error = d_revalidate(dentry, flags); if (unlikely(error <= 0)) { - if (!error) + if (!error) { d_invalidate(dentry); + dput(dentry); + goto again; + } dput(dentry); dentry = ERR_PTR(error); } } - if (dentry) { - inode_unlock(dir->d_inode); - return dentry; + } else { + old = inode->i_op->lookup(inode, dentry, flags); + d_lookup_done(dentry); + if (unlikely(old)) { + dput(dentry); + dentry = old; } } - dentry = d_alloc(dir, name); - if (unlikely(!dentry)) { - inode_unlock(dir->d_inode); - return ERR_PTR(-ENOMEM); - } - dentry = lookup_real(dir->d_inode, dentry, flags); - inode_unlock(dir->d_inode); +out: + inode_unlock_shared(inode); return dentry; } @@ -1794,30 +1804,49 @@ static inline unsigned int fold_hash(unsigned long hash) return hash_64(hash, 32); } +/* + * This is George Marsaglia's XORSHIFT generator. + * It implements a maximum-period LFSR in only a few + * instructions. It also has the property (required + * by hash_name()) that mix_hash(0) = 0. + */ +static inline unsigned long mix_hash(unsigned long hash) +{ + hash ^= hash << 13; + hash ^= hash >> 7; + hash ^= hash << 17; + return hash; +} + #else /* 32-bit case */ #define fold_hash(x) (x) +static inline unsigned long mix_hash(unsigned long hash) +{ + hash ^= hash << 13; + hash ^= hash >> 17; + hash ^= hash << 5; + return hash; +} + #endif unsigned int full_name_hash(const unsigned char *name, unsigned int len) { - unsigned long a, mask; - unsigned long hash = 0; + unsigned long a, hash = 0; for (;;) { a = load_unaligned_zeropad(name); if (len < sizeof(unsigned long)) break; - hash += a; - hash *= 9; + hash = mix_hash(hash + a); name += sizeof(unsigned long); len -= sizeof(unsigned long); if (!len) goto done; } - mask = bytemask_from_count(len); - hash += mask & a; + hash += a & bytemask_from_count(len); done: return fold_hash(hash); } @@ -1835,7 +1864,7 @@ static inline u64 hash_name(const char *name) hash = a = 0; len = -sizeof(unsigned long); do { - hash = (hash + a) * 9; + hash = mix_hash(hash + a); len += sizeof(unsigned long); a = load_unaligned_zeropad(name+len); b = a ^ REPEAT_BYTE('/'); @@ -2267,6 +2296,33 @@ int vfs_path_lookup(struct dentry *dentry, struct vfsmount *mnt, EXPORT_SYMBOL(vfs_path_lookup); /** + * lookup_hash - lookup single pathname component on already hashed name + * @name: name and hash to lookup + * @base: base directory to lookup from + * + * The name must have been verified and hashed (see lookup_one_len()). Using + * this after just full_name_hash() is unsafe. + * + * This function also doesn't check for search permission on base directory. + * + * Use lookup_one_len_unlocked() instead, unless you really know what you are + * doing. + * + * Do not hold i_mutex; this helper takes i_mutex if necessary. + */ +struct dentry *lookup_hash(const struct qstr *name, struct dentry *base) +{ + struct dentry *ret; + + ret = lookup_dcache(name, base, 0); + if (!ret) + ret = lookup_slow(name, base, 0); + + return ret; +} +EXPORT_SYMBOL(lookup_hash); + +/** * lookup_one_len - filesystem helper to lookup single pathname component * @name: pathname component to lookup * @base: base directory to lookup from @@ -2337,7 +2393,6 @@ struct dentry *lookup_one_len_unlocked(const char *name, struct qstr this; unsigned int c; int err; - struct dentry *ret; this.name = name; this.len = len; @@ -2369,10 +2424,7 @@ struct dentry *lookup_one_len_unlocked(const char *name, if (err) return ERR_PTR(err); - ret = lookup_dcache(&this, base, 0); - if (!ret) - ret = lookup_slow(&this, base, 0); - return ret; + return lookup_hash(&this, base); } EXPORT_SYMBOL(lookup_one_len_unlocked); @@ -2655,7 +2707,7 @@ struct dentry *lock_rename(struct dentry *p1, struct dentry *p2) return NULL; } - mutex_lock(&p1->d_inode->i_sb->s_vfs_rename_mutex); + mutex_lock(&p1->d_sb->s_vfs_rename_mutex); p = d_ancestor(p2, p1); if (p) { @@ -2682,7 +2734,7 @@ void unlock_rename(struct dentry *p1, struct dentry *p2) inode_unlock(p1->d_inode); if (p1 != p2) { inode_unlock(p2->d_inode); - mutex_unlock(&p1->d_inode->i_sb->s_vfs_rename_mutex); + mutex_unlock(&p1->d_sb->s_vfs_rename_mutex); } } EXPORT_SYMBOL(unlock_rename); @@ -2785,7 +2837,7 @@ static inline int open_to_namei_flags(int flag) return flag; } -static int may_o_create(struct path *dir, struct dentry *dentry, umode_t mode) +static int may_o_create(const struct path *dir, struct dentry *dentry, umode_t mode) { int error = security_path_mknod(dir, dentry, mode, 0); if (error) @@ -2814,155 +2866,56 @@ static int may_o_create(struct path *dir, struct dentry *dentry, umode_t mode) static int atomic_open(struct nameidata *nd, struct dentry *dentry, struct path *path, struct file *file, const struct open_flags *op, - bool got_write, bool need_lookup, + int open_flag, umode_t mode, int *opened) { + struct dentry *const DENTRY_NOT_SET = (void *) -1UL; struct inode *dir = nd->path.dentry->d_inode; - unsigned open_flag = open_to_namei_flags(op->open_flag); - umode_t mode; int error; - int acc_mode; - int create_error = 0; - struct dentry *const DENTRY_NOT_SET = (void *) -1UL; - bool excl; - - BUG_ON(dentry->d_inode); - /* Don't create child dentry for a dead directory. */ - if (unlikely(IS_DEADDIR(dir))) { - error = -ENOENT; - goto out; - } - - mode = op->mode; - if ((open_flag & O_CREAT) && !IS_POSIXACL(dir)) - mode &= ~current_umask(); - - excl = (open_flag & (O_EXCL | O_CREAT)) == (O_EXCL | O_CREAT); - if (excl) + if (!(~open_flag & (O_EXCL | O_CREAT))) /* both O_EXCL and O_CREAT */ open_flag &= ~O_TRUNC; - /* - * Checking write permission is tricky, bacuse we don't know if we are - * going to actually need it: O_CREAT opens should work as long as the - * file exists. But checking existence breaks atomicity. The trick is - * to check access and if not granted clear O_CREAT from the flags. - * - * Another problem is returing the "right" error value (e.g. for an - * O_EXCL open we want to return EEXIST not EROFS). - */ - if (((open_flag & (O_CREAT | O_TRUNC)) || - (open_flag & O_ACCMODE) != O_RDONLY) && unlikely(!got_write)) { - if (!(open_flag & O_CREAT)) { - /* - * No O_CREATE -> atomicity not a requirement -> fall - * back to lookup + open - */ - goto no_open; - } else if (open_flag & (O_EXCL | O_TRUNC)) { - /* Fall back and fail with the right error */ - create_error = -EROFS; - goto no_open; - } else { - /* No side effects, safe to clear O_CREAT */ - create_error = -EROFS; - open_flag &= ~O_CREAT; - } - } - - if (open_flag & O_CREAT) { - error = may_o_create(&nd->path, dentry, mode); - if (error) { - create_error = error; - if (open_flag & O_EXCL) - goto no_open; - open_flag &= ~O_CREAT; - } - } - if (nd->flags & LOOKUP_DIRECTORY) open_flag |= O_DIRECTORY; file->f_path.dentry = DENTRY_NOT_SET; file->f_path.mnt = nd->path.mnt; - error = dir->i_op->atomic_open(dir, dentry, file, open_flag, mode, - opened); - if (error < 0) { - if (create_error && error == -ENOENT) - error = create_error; - goto out; - } - - if (error) { /* returned 1, that is */ + error = dir->i_op->atomic_open(dir, dentry, file, + open_to_namei_flags(open_flag), + mode, opened); + d_lookup_done(dentry); + if (!error) { + /* + * We didn't have the inode before the open, so check open + * permission here. + */ + int acc_mode = op->acc_mode; + if (*opened & FILE_CREATED) { + WARN_ON(!(open_flag & O_CREAT)); + fsnotify_create(dir, dentry); + acc_mode = 0; + } + error = may_open(&file->f_path, acc_mode, open_flag); + if (WARN_ON(error > 0)) + error = -EINVAL; + } else if (error > 0) { if (WARN_ON(file->f_path.dentry == DENTRY_NOT_SET)) { error = -EIO; - goto out; - } - if (file->f_path.dentry) { - dput(dentry); - dentry = file->f_path.dentry; - } - if (*opened & FILE_CREATED) - fsnotify_create(dir, dentry); - if (!dentry->d_inode) { - WARN_ON(*opened & FILE_CREATED); - if (create_error) { - error = create_error; - goto out; - } } else { - if (excl && !(*opened & FILE_CREATED)) { - error = -EEXIST; - goto out; + if (file->f_path.dentry) { + dput(dentry); + dentry = file->f_path.dentry; } + if (*opened & FILE_CREATED) + fsnotify_create(dir, dentry); + path->dentry = dentry; + path->mnt = nd->path.mnt; + return 1; } - goto looked_up; } - - /* - * We didn't have the inode before the open, so check open permission - * here. - */ - acc_mode = op->acc_mode; - if (*opened & FILE_CREATED) { - WARN_ON(!(open_flag & O_CREAT)); - fsnotify_create(dir, dentry); - acc_mode = 0; - } - error = may_open(&file->f_path, acc_mode, open_flag); - if (error) - fput(file); - -out: dput(dentry); return error; - -no_open: - if (need_lookup) { - dentry = lookup_real(dir, dentry, nd->flags); - if (IS_ERR(dentry)) - return PTR_ERR(dentry); - - if (create_error) { - int open_flag = op->open_flag; - - error = create_error; - if ((open_flag & O_EXCL)) { - if (!dentry->d_inode) - goto out; - } else if (!dentry->d_inode) { - goto out; - } else if ((open_flag & O_TRUNC) && - d_is_reg(dentry)) { - goto out; - } - /* will fail later, go on to get the right error */ - } - } -looked_up: - path->dentry = dentry; - path->mnt = nd->path.mnt; - return 1; } /* @@ -2990,62 +2943,118 @@ static int lookup_open(struct nameidata *nd, struct path *path, { struct dentry *dir = nd->path.dentry; struct inode *dir_inode = dir->d_inode; + int open_flag = op->open_flag; struct dentry *dentry; - int error; - bool need_lookup = false; + int error, create_error = 0; + umode_t mode = op->mode; + DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq); + + if (unlikely(IS_DEADDIR(dir_inode))) + return -ENOENT; *opened &= ~FILE_CREATED; - dentry = lookup_dcache(&nd->last, dir, nd->flags); - if (IS_ERR(dentry)) - return PTR_ERR(dentry); + dentry = d_lookup(dir, &nd->last); + for (;;) { + if (!dentry) { + dentry = d_alloc_parallel(dir, &nd->last, &wq); + if (IS_ERR(dentry)) + return PTR_ERR(dentry); + } + if (d_in_lookup(dentry)) + break; - if (!dentry) { - dentry = d_alloc(dir, &nd->last); - if (unlikely(!dentry)) - return -ENOMEM; - need_lookup = true; - } else if (dentry->d_inode) { + if (!(dentry->d_flags & DCACHE_OP_REVALIDATE)) + break; + + error = d_revalidate(dentry, nd->flags); + if (likely(error > 0)) + break; + if (error) + goto out_dput; + d_invalidate(dentry); + dput(dentry); + dentry = NULL; + } + if (dentry->d_inode) { /* Cached positive dentry: will open in f_op->open */ goto out_no_open; } - if ((nd->flags & LOOKUP_OPEN) && dir_inode->i_op->atomic_open) { - return atomic_open(nd, dentry, path, file, op, got_write, - need_lookup, opened); + /* + * Checking write permission is tricky, bacuse we don't know if we are + * going to actually need it: O_CREAT opens should work as long as the + * file exists. But checking existence breaks atomicity. The trick is + * to check access and if not granted clear O_CREAT from the flags. + * + * Another problem is returing the "right" error value (e.g. for an + * O_EXCL open we want to return EEXIST not EROFS). + */ + if (open_flag & O_CREAT) { + if (!IS_POSIXACL(dir->d_inode)) + mode &= ~current_umask(); + if (unlikely(!got_write)) { + create_error = -EROFS; + open_flag &= ~O_CREAT; + if (open_flag & (O_EXCL | O_TRUNC)) + goto no_open; + /* No side effects, safe to clear O_CREAT */ + } else { + create_error = may_o_create(&nd->path, dentry, mode); + if (create_error) { + open_flag &= ~O_CREAT; + if (open_flag & O_EXCL) + goto no_open; + } + } + } else if ((open_flag & (O_TRUNC|O_WRONLY|O_RDWR)) && + unlikely(!got_write)) { + /* + * No O_CREATE -> atomicity not a requirement -> fall + * back to lookup + open + */ + goto no_open; } - if (need_lookup) { - BUG_ON(dentry->d_inode); + if (dir_inode->i_op->atomic_open) { + error = atomic_open(nd, dentry, path, file, op, open_flag, + mode, opened); + if (unlikely(error == -ENOENT) && create_error) + error = create_error; + return error; + } - dentry = lookup_real(dir_inode, dentry, nd->flags); - if (IS_ERR(dentry)) - return PTR_ERR(dentry); +no_open: + if (d_in_lookup(dentry)) { + struct dentry *res = dir_inode->i_op->lookup(dir_inode, dentry, + nd->flags); + d_lookup_done(dentry); + if (unlikely(res)) { + if (IS_ERR(res)) { + error = PTR_ERR(res); + goto out_dput; + } + dput(dentry); + dentry = res; + } } /* Negative dentry, just create the file */ - if (!dentry->d_inode && (op->open_flag & O_CREAT)) { - umode_t mode = op->mode; - if (!IS_POSIXACL(dir->d_inode)) - mode &= ~current_umask(); - /* - * This write is needed to ensure that a - * rw->ro transition does not occur between - * the time when the file is created and when - * a permanent write count is taken through - * the 'struct file' in finish_open(). - */ - if (!got_write) { - error = -EROFS; - goto out_dput; - } + if (!dentry->d_inode && (open_flag & O_CREAT)) { *opened |= FILE_CREATED; - error = security_path_mknod(&nd->path, dentry, mode, 0); - if (error) + audit_inode_child(dir_inode, dentry, AUDIT_TYPE_CHILD_CREATE); + if (!dir_inode->i_op->create) { + error = -EACCES; goto out_dput; - error = vfs_create(dir->d_inode, dentry, mode, - nd->flags & LOOKUP_EXCL); + } + error = dir_inode->i_op->create(dir_inode, dentry, mode, + open_flag & O_EXCL); if (error) goto out_dput; + fsnotify_create(dir_inode, dentry); + } + if (unlikely(create_error) && !dentry->d_inode) { + error = create_error; + goto out_dput; } out_no_open: path->dentry = dentry; @@ -3117,7 +3126,7 @@ static int do_last(struct nameidata *nd, } retry_lookup: - if (op->open_flag & (O_CREAT | O_TRUNC | O_WRONLY | O_RDWR)) { + if (open_flag & (O_CREAT | O_TRUNC | O_WRONLY | O_RDWR)) { error = mnt_want_write(nd->path.mnt); if (!error) got_write = true; @@ -3127,9 +3136,15 @@ retry_lookup: * dropping this one anyway. */ } - inode_lock(dir->d_inode); + if (open_flag & O_CREAT) + inode_lock(dir->d_inode); + else + inode_lock_shared(dir->d_inode); error = lookup_open(nd, &path, file, op, got_write, opened); - inode_unlock(dir->d_inode); + if (open_flag & O_CREAT) + inode_unlock(dir->d_inode); + else + inode_unlock_shared(dir->d_inode); if (error <= 0) { if (error) @@ -3209,10 +3224,6 @@ finish_open: return error; } audit_inode(nd->name, nd->path.dentry, 0); - if (unlikely(d_is_symlink(nd->path.dentry)) && !(open_flag & O_PATH)) { - error = -ELOOP; - goto out; - } error = -EISDIR; if ((open_flag & O_CREAT) && d_is_dir(nd->path.dentry)) goto out; @@ -3229,11 +3240,9 @@ finish_open: got_write = true; } finish_open_created: - if (likely(!(open_flag & O_PATH))) { - error = may_open(&nd->path, acc_mode, open_flag); - if (error) - goto out; - } + error = may_open(&nd->path, acc_mode, open_flag); + if (error) + goto out; BUG_ON(*opened & FILE_OPENED); /* once it's opened, it's opened */ error = vfs_open(&nd->path, file, current_cred()); if (!error) { @@ -3245,18 +3254,13 @@ finish_open_created: } opened: error = open_check_o_direct(file); - if (error) - goto exit_fput; - error = ima_file_check(file, op->acc_mode, *opened); - if (error) - goto exit_fput; - - if (will_truncate) { + if (!error) + error = ima_file_check(file, op->acc_mode, *opened); + if (!error && will_truncate) error = handle_truncate(file); - if (error) - goto exit_fput; - } out: + if (unlikely(error) && (*opened & FILE_OPENED)) + fput(file); if (unlikely(error > 0)) { WARN_ON(1); error = -EINVAL; @@ -3266,10 +3270,6 @@ out: path_put(&save_parent); return error; -exit_fput: - fput(file); - goto out; - stale_open: /* If no saved parent or already retried then can't retry */ if (!save_parent.dentry || retried) @@ -3347,6 +3347,18 @@ out: return error; } +static int do_o_path(struct nameidata *nd, unsigned flags, struct file *file) +{ + struct path path; + int error = path_lookupat(nd, flags, &path); + if (!error) { + audit_inode(nd->name, path.dentry, 0); + error = vfs_open(&path, file, current_cred()); + path_put(&path); + } + return error; +} + static struct file *path_openat(struct nameidata *nd, const struct open_flags *op, unsigned flags) { @@ -3366,6 +3378,13 @@ static struct file *path_openat(struct nameidata *nd, goto out2; } + if (unlikely(file->f_flags & O_PATH)) { + error = do_o_path(nd, flags, file); + if (!error) + opened |= FILE_OPENED; + goto out2; + } + s = path_init(nd, flags); if (IS_ERR(s)) { put_filp(file); @@ -3608,6 +3627,8 @@ retry: switch (mode & S_IFMT) { case 0: case S_IFREG: error = vfs_create(path.dentry->d_inode,dentry,mode,true); + if (!error) + ima_post_path_mknod(dentry); break; case S_IFCHR: case S_IFBLK: error = vfs_mknod(path.dentry->d_inode,dentry,mode, @@ -4213,7 +4234,11 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry, bool new_is_dir = false; unsigned max_links = new_dir->i_sb->s_max_links; - if (source == target) + /* + * Check source == target. + * On overlayfs need to look at underlying inodes. + */ + if (vfs_select_inode(old_dentry, 0) == vfs_select_inode(new_dentry, 0)) return 0; error = may_delete(old_dir, old_dentry, is_dir); diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 33eb817..aaf7bd0 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -57,7 +57,7 @@ static void nfs_readdir_clear_array(struct page*); const struct file_operations nfs_dir_operations = { .llseek = nfs_llseek_dir, .read = generic_read_dir, - .iterate = nfs_readdir, + .iterate_shared = nfs_readdir, .open = nfs_opendir, .release = nfs_closedir, .fsync = nfs_fsync_dir, @@ -145,6 +145,7 @@ struct nfs_cache_array_entry { }; struct nfs_cache_array { + atomic_t refcount; int size; int eof_index; u64 last_cookie; @@ -200,11 +201,20 @@ void nfs_readdir_clear_array(struct page *page) int i; array = kmap_atomic(page); - for (i = 0; i < array->size; i++) - kfree(array->array[i].string.name); + if (atomic_dec_and_test(&array->refcount)) + for (i = 0; i < array->size; i++) + kfree(array->array[i].string.name); kunmap_atomic(array); } +static bool grab_page(struct page *page) +{ + struct nfs_cache_array *array = kmap_atomic(page); + bool res = atomic_inc_not_zero(&array->refcount); + kunmap_atomic(array); + return res; +} + /* * the caller is responsible for freeing qstr.name * when called by nfs_readdir_add_to_array, the strings will be freed in @@ -470,6 +480,7 @@ static void nfs_prime_dcache(struct dentry *parent, struct nfs_entry *entry) { struct qstr filename = QSTR_INIT(entry->name, entry->len); + DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq); struct dentry *dentry; struct dentry *alias; struct inode *dir = d_inode(parent); @@ -489,7 +500,13 @@ void nfs_prime_dcache(struct dentry *parent, struct nfs_entry *entry) filename.hash = full_name_hash(filename.name, filename.len); dentry = d_lookup(parent, &filename); - if (dentry != NULL) { +again: + if (!dentry) { + dentry = d_alloc_parallel(parent, &filename, &wq); + if (IS_ERR(dentry)) + return; + } + if (!d_in_lookup(dentry)) { /* Is there a mountpoint here? If so, just exit */ if (!nfs_fsid_equal(&NFS_SB(dentry->d_sb)->fsid, &entry->fattr->fsid)) @@ -503,26 +520,21 @@ void nfs_prime_dcache(struct dentry *parent, struct nfs_entry *entry) } else { d_invalidate(dentry); dput(dentry); + dentry = NULL; + goto again; } } - dentry = d_alloc(parent, &filename); - if (dentry == NULL) - return; - inode = nfs_fhget(dentry->d_sb, entry->fh, entry->fattr, entry->label); - if (IS_ERR(inode)) - goto out; - alias = d_splice_alias(inode, dentry); - if (IS_ERR(alias)) - goto out; - else if (alias) { - nfs_set_verifier(alias, nfs_save_change_attribute(dir)); - dput(alias); - } else - nfs_set_verifier(dentry, nfs_save_change_attribute(dir)); - + d_lookup_done(dentry); + if (alias) { + if (IS_ERR(alias)) + goto out; + dput(dentry); + dentry = alias; + } + nfs_set_verifier(dentry, nfs_save_change_attribute(dir)); out: dput(dentry); } @@ -643,6 +655,7 @@ int nfs_readdir_xdr_to_array(nfs_readdir_descriptor_t *desc, struct page *page, goto out_label_free; } memset(array, 0, sizeof(struct nfs_cache_array)); + atomic_set(&array->refcount, 1); array->eof_index = -1; status = nfs_readdir_alloc_pages(pages, array_size); @@ -705,8 +718,7 @@ int nfs_readdir_filler(nfs_readdir_descriptor_t *desc, struct page* page) static void cache_page_release(nfs_readdir_descriptor_t *desc) { - if (!desc->page->mapping) - nfs_readdir_clear_array(desc->page); + nfs_readdir_clear_array(desc->page); put_page(desc->page); desc->page = NULL; } @@ -714,8 +726,16 @@ void cache_page_release(nfs_readdir_descriptor_t *desc) static struct page *get_cache_page(nfs_readdir_descriptor_t *desc) { - return read_cache_page(file_inode(desc->file)->i_mapping, + struct page *page; + + for (;;) { + page = read_cache_page(file_inode(desc->file)->i_mapping, desc->page_index, (filler_t *)nfs_readdir_filler, desc); + if (IS_ERR(page) || grab_page(page)) + break; + put_page(page); + } + return page; } /* @@ -889,7 +909,6 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx) desc->decode = NFS_PROTO(inode)->decode_dirent; desc->plus = nfs_use_readdirplus(inode, ctx) ? 1 : 0; - nfs_block_sillyrename(dentry); if (ctx->pos == 0 || nfs_dir_mapping_need_revalidate(inode)) res = nfs_revalidate_mapping(inode, file->f_mapping); if (res < 0) @@ -925,7 +944,6 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx) break; } while (!desc->eof); out: - nfs_unblock_sillyrename(dentry); if (res > 0) res = 0; dfprintk(FILE, "NFS: readdir(%pD2) returns %d\n", file, res); @@ -934,13 +952,11 @@ out: static loff_t nfs_llseek_dir(struct file *filp, loff_t offset, int whence) { - struct inode *inode = file_inode(filp); struct nfs_open_dir_context *dir_ctx = filp->private_data; dfprintk(FILE, "NFS: llseek dir(%pD2, %lld, %d)\n", filp, offset, whence); - inode_lock(inode); switch (whence) { case 1: offset += filp->f_pos; @@ -948,16 +964,13 @@ static loff_t nfs_llseek_dir(struct file *filp, loff_t offset, int whence) if (offset >= 0) break; default: - offset = -EINVAL; - goto out; + return -EINVAL; } if (offset != filp->f_pos) { filp->f_pos = offset; dir_ctx->dir_cookie = 0; dir_ctx->duped = 0; } -out: - inode_unlock(inode); return offset; } @@ -1383,7 +1396,6 @@ struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, unsigned in parent = dentry->d_parent; /* Protect against concurrent sillydeletes */ trace_nfs_lookup_enter(dir, dentry, flags); - nfs_block_sillyrename(parent); error = NFS_PROTO(dir)->lookup(dir, &dentry->d_name, fhandle, fattr, label); if (error == -ENOENT) goto no_entry; @@ -1408,7 +1420,6 @@ no_entry: } nfs_set_verifier(dentry, nfs_save_change_attribute(dir)); out_unblock_sillyrename: - nfs_unblock_sillyrename(parent); trace_nfs_lookup_exit(dir, dentry, flags, error); nfs4_label_free(label); out: @@ -1520,9 +1531,7 @@ int nfs_atomic_open(struct inode *dir, struct dentry *dentry, goto out; trace_nfs_atomic_open_enter(dir, ctx, open_flags); - nfs_block_sillyrename(dentry->d_parent); inode = NFS_PROTO(dir)->open_context(dir, ctx, open_flags, &attr, opened); - nfs_unblock_sillyrename(dentry->d_parent); if (IS_ERR(inode)) { err = PTR_ERR(inode); trace_nfs_atomic_open_exit(dir, ctx, open_flags, err); @@ -1766,7 +1775,7 @@ int nfs_rmdir(struct inode *dir, struct dentry *dentry) trace_nfs_rmdir_enter(dir, dentry); if (d_really_is_positive(dentry)) { - nfs_wait_on_sillyrename(dentry); + down_write(&NFS_I(d_inode(dentry))->rmdir_sem); error = NFS_PROTO(dir)->rmdir(dir, &dentry->d_name); /* Ensure the VFS deletes this inode */ switch (error) { @@ -1776,6 +1785,7 @@ int nfs_rmdir(struct inode *dir, struct dentry *dentry) case -ENOENT: nfs_dentry_handle_enoent(dentry); } + up_write(&NFS_I(d_inode(dentry))->rmdir_sem); } else error = NFS_PROTO(dir)->rmdir(dir, &dentry->d_name); trace_nfs_rmdir_exit(dir, dentry, error); diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index c93826e..741a92c 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -250,7 +250,7 @@ static int nfs_direct_cmp_commit_data_verf(struct nfs_direct_req *dreq, * shunt off direct read and write requests before the VFS gets them, * so this method is only ever called for swap. */ -ssize_t nfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t pos) +ssize_t nfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) { struct inode *inode = iocb->ki_filp->f_mapping->host; @@ -261,7 +261,7 @@ ssize_t nfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t pos) VM_BUG_ON(iov_iter_count(iter) != PAGE_SIZE); if (iov_iter_rw(iter) == READ) - return nfs_file_direct_read(iocb, iter, pos); + return nfs_file_direct_read(iocb, iter); return nfs_file_direct_write(iocb, iter); } @@ -396,7 +396,7 @@ static void nfs_direct_complete(struct nfs_direct_req *dreq, bool write) static void nfs_direct_readpage_release(struct nfs_page *req) { dprintk("NFS: direct read done (%s/%llu %d@%lld)\n", - d_inode(req->wb_context->dentry)->i_sb->s_id, + req->wb_context->dentry->d_sb->s_id, (unsigned long long)NFS_FILEID(d_inode(req->wb_context->dentry)), req->wb_bytes, (long long)req_offset(req)); @@ -545,7 +545,6 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq, * nfs_file_direct_read - file direct read operation for NFS files * @iocb: target I/O control block * @iter: vector of user buffers into which to read data - * @pos: byte offset in file where reading starts * * We use this function for direct reads instead of calling * generic_file_aio_read() in order to avoid gfar's check to see if @@ -561,8 +560,7 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq, * client must read the updated atime from the server back into its * cache. */ -ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter, - loff_t pos) +ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; @@ -574,7 +572,7 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter, nfs_add_stats(mapping->host, NFSIOS_DIRECTREADBYTES, count); dfprintk(FILE, "NFS: direct read(%pD2, %zd@%Ld)\n", - file, count, (long long) pos); + file, count, (long long) iocb->ki_pos); result = 0; if (!count) @@ -594,7 +592,7 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter, dreq->inode = inode; dreq->bytes_left = count; - dreq->io_start = pos; + dreq->io_start = iocb->ki_pos; dreq->ctx = get_nfs_open_context(nfs_file_open_context(iocb->ki_filp)); l_ctx = nfs_get_lock_context(dreq->ctx); if (IS_ERR(l_ctx)) { @@ -606,14 +604,14 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter, dreq->iocb = iocb; NFS_I(inode)->read_io += count; - result = nfs_direct_read_schedule_iovec(dreq, iter, pos); + result = nfs_direct_read_schedule_iovec(dreq, iter, iocb->ki_pos); inode_unlock(inode); if (!result) { result = nfs_direct_wait(dreq); if (result > 0) - iocb->ki_pos = pos + result; + iocb->ki_pos += result; } nfs_direct_req_release(dreq); @@ -969,7 +967,6 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq, * nfs_file_direct_write - file direct write operation for NFS files * @iocb: target I/O control block * @iter: vector of user buffers from which to write data - * @pos: byte offset in file where writing starts * * We use this function for direct writes instead of calling * generic_file_aio_write() in order to avoid taking the inode @@ -1057,7 +1054,9 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter) if (i_size_read(inode) < iocb->ki_pos) i_size_write(inode, iocb->ki_pos); spin_unlock(&inode->i_lock); - generic_write_sync(file, pos, result); + + /* XXX: should check the generic_write_sync retval */ + generic_write_sync(iocb, result); } } nfs_direct_req_release(dreq); diff --git a/fs/nfs/file.c b/fs/nfs/file.c index be01095..717a8d6 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -164,7 +164,7 @@ nfs_file_read(struct kiocb *iocb, struct iov_iter *to) ssize_t result; if (iocb->ki_flags & IOCB_DIRECT) - return nfs_file_direct_read(iocb, to, iocb->ki_pos); + return nfs_file_direct_read(iocb, to); dprintk("NFS: read(%pD2, %zu@%lu)\n", iocb->ki_filp, diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 738c84a..52e7d68 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -1958,9 +1958,7 @@ static void init_once(void *foo) nfsi->nrequests = 0; nfsi->commit_info.ncommit = 0; atomic_set(&nfsi->commit_info.rpcs_out, 0); - atomic_set(&nfsi->silly_count, 1); - INIT_HLIST_HEAD(&nfsi->silly_list); - init_waitqueue_head(&nfsi->waitqueue); + init_rwsem(&nfsi->rmdir_sem); nfs4_init_once(nfsi); } diff --git a/fs/nfs/nfs3acl.c b/fs/nfs/nfs3acl.c index 17c0fa1..720d92f5 100644 --- a/fs/nfs/nfs3acl.c +++ b/fs/nfs/nfs3acl.c @@ -11,6 +11,38 @@ #define NFSDBG_FACILITY NFSDBG_PROC +/* + * nfs3_prepare_get_acl, nfs3_complete_get_acl, nfs3_abort_get_acl: Helpers for + * caching get_acl results in a race-free way. See fs/posix_acl.c:get_acl() + * for explanations. + */ +static void nfs3_prepare_get_acl(struct posix_acl **p) +{ + struct posix_acl *sentinel = uncached_acl_sentinel(current); + + if (cmpxchg(p, ACL_NOT_CACHED, sentinel) != ACL_NOT_CACHED) { + /* Not the first reader or sentinel already in place. */ + } +} + +static void nfs3_complete_get_acl(struct posix_acl **p, struct posix_acl *acl) +{ + struct posix_acl *sentinel = uncached_acl_sentinel(current); + + /* Only cache the ACL if our sentinel is still in place. */ + posix_acl_dup(acl); + if (cmpxchg(p, sentinel, acl) != sentinel) + posix_acl_release(acl); +} + +static void nfs3_abort_get_acl(struct posix_acl **p) +{ + struct posix_acl *sentinel = uncached_acl_sentinel(current); + + /* Remove our sentinel upon failure. */ + cmpxchg(p, sentinel, ACL_NOT_CACHED); +} + struct posix_acl *nfs3_get_acl(struct inode *inode, int type) { struct nfs_server *server = NFS_SERVER(inode); @@ -55,6 +87,11 @@ struct posix_acl *nfs3_get_acl(struct inode *inode, int type) if (res.fattr == NULL) return ERR_PTR(-ENOMEM); + if (args.mask & NFS_ACL) + nfs3_prepare_get_acl(&inode->i_acl); + if (args.mask & NFS_DFACL) + nfs3_prepare_get_acl(&inode->i_default_acl); + status = rpc_call_sync(server->client_acl, &msg, 0); dprintk("NFS reply getacl: %d\n", status); @@ -89,12 +126,12 @@ struct posix_acl *nfs3_get_acl(struct inode *inode, int type) } if (res.mask & NFS_ACL) - set_cached_acl(inode, ACL_TYPE_ACCESS, res.acl_access); + nfs3_complete_get_acl(&inode->i_acl, res.acl_access); else forget_cached_acl(inode, ACL_TYPE_ACCESS); if (res.mask & NFS_DFACL) - set_cached_acl(inode, ACL_TYPE_DEFAULT, res.acl_default); + nfs3_complete_get_acl(&inode->i_default_acl, res.acl_default); else forget_cached_acl(inode, ACL_TYPE_DEFAULT); @@ -108,6 +145,8 @@ struct posix_acl *nfs3_get_acl(struct inode *inode, int type) } getout: + nfs3_abort_get_acl(&inode->i_acl); + nfs3_abort_get_acl(&inode->i_default_acl); posix_acl_release(res.acl_access); posix_acl_release(res.acl_default); nfs_free_fattr(res.fattr); diff --git a/fs/nfs/nfs4idmap.c b/fs/nfs/nfs4idmap.c index 5ba22c6..c444285 100644 --- a/fs/nfs/nfs4idmap.c +++ b/fs/nfs/nfs4idmap.c @@ -201,7 +201,7 @@ int nfs_idmap_init(void) GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, cred, (KEY_POS_ALL & ~KEY_POS_SETATTR) | KEY_USR_VIEW | KEY_USR_READ, - KEY_ALLOC_NOT_IN_QUOTA, NULL); + KEY_ALLOC_NOT_IN_QUOTA, NULL, NULL); if (IS_ERR(keyring)) { ret = PTR_ERR(keyring); goto failed_put_cred; diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 327b8c3..084e857 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -3777,7 +3777,7 @@ static void nfs4_proc_unlink_setup(struct rpc_message *msg, struct inode *dir) static void nfs4_proc_unlink_rpc_prepare(struct rpc_task *task, struct nfs_unlinkdata *data) { - nfs4_setup_sequence(NFS_SERVER(data->dir), + nfs4_setup_sequence(NFS_SB(data->dentry->d_sb), &data->args.seq_args, &data->res.seq_res, task); @@ -6263,10 +6263,10 @@ static int nfs4_xattr_set_nfs4_acl(const struct xattr_handler *handler, } static int nfs4_xattr_get_nfs4_acl(const struct xattr_handler *handler, - struct dentry *dentry, const char *key, - void *buf, size_t buflen) + struct dentry *unused, struct inode *inode, + const char *key, void *buf, size_t buflen) { - return nfs4_proc_get_acl(d_inode(dentry), buf, buflen); + return nfs4_proc_get_acl(inode, buf, buflen); } static bool nfs4_xattr_list_nfs4_acl(struct dentry *dentry) @@ -6288,11 +6288,11 @@ static int nfs4_xattr_set_nfs4_label(const struct xattr_handler *handler, } static int nfs4_xattr_get_nfs4_label(const struct xattr_handler *handler, - struct dentry *dentry, const char *key, - void *buf, size_t buflen) + struct dentry *unused, struct inode *inode, + const char *key, void *buf, size_t buflen) { if (security_ismaclabel(key)) - return nfs4_get_security_label(d_inode(dentry), buf, buflen); + return nfs4_get_security_label(inode, buf, buflen); return -EOPNOTSUPP; } diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h index 9f80a08..0b9e5cc 100644 --- a/fs/nfs/nfstrace.h +++ b/fs/nfs/nfstrace.h @@ -702,7 +702,7 @@ TRACE_EVENT(nfs_sillyrename_unlink, ), TP_fast_assign( - struct inode *dir = data->dir; + struct inode *dir = d_inode(data->dentry->d_parent); size_t len = data->args.name.len; __entry->dev = dir->i_sb->s_dev; __entry->dir = NFS_FILEID(dir); diff --git a/fs/nfs/unlink.c b/fs/nfs/unlink.c index fa538b2..1868246 100644 --- a/fs/nfs/unlink.c +++ b/fs/nfs/unlink.c @@ -30,45 +30,11 @@ static void nfs_free_unlinkdata(struct nfs_unlinkdata *data) { - iput(data->dir); put_rpccred(data->cred); kfree(data->args.name.name); kfree(data); } -#define NAME_ALLOC_LEN(len) ((len+16) & ~15) -/** - * nfs_copy_dname - copy dentry name to data structure - * @dentry: pointer to dentry - * @data: nfs_unlinkdata - */ -static int nfs_copy_dname(struct dentry *dentry, struct nfs_unlinkdata *data) -{ - char *str; - int len = dentry->d_name.len; - - str = kmemdup(dentry->d_name.name, NAME_ALLOC_LEN(len), GFP_KERNEL); - if (!str) - return -ENOMEM; - data->args.name.len = len; - data->args.name.name = str; - return 0; -} - -static void nfs_free_dname(struct nfs_unlinkdata *data) -{ - kfree(data->args.name.name); - data->args.name.name = NULL; - data->args.name.len = 0; -} - -static void nfs_dec_sillycount(struct inode *dir) -{ - struct nfs_inode *nfsi = NFS_I(dir); - if (atomic_dec_return(&nfsi->silly_count) == 1) - wake_up(&nfsi->waitqueue); -} - /** * nfs_async_unlink_done - Sillydelete post-processing * @task: rpc_task of the sillydelete @@ -78,7 +44,7 @@ static void nfs_dec_sillycount(struct inode *dir) static void nfs_async_unlink_done(struct rpc_task *task, void *calldata) { struct nfs_unlinkdata *data = calldata; - struct inode *dir = data->dir; + struct inode *dir = d_inode(data->dentry->d_parent); trace_nfs_sillyrename_unlink(data, task->tk_status); if (!NFS_PROTO(dir)->unlink_done(task, dir)) @@ -95,17 +61,21 @@ static void nfs_async_unlink_done(struct rpc_task *task, void *calldata) static void nfs_async_unlink_release(void *calldata) { struct nfs_unlinkdata *data = calldata; - struct super_block *sb = data->dir->i_sb; + struct dentry *dentry = data->dentry; + struct super_block *sb = dentry->d_sb; - nfs_dec_sillycount(data->dir); + up_read_non_owner(&NFS_I(d_inode(dentry->d_parent))->rmdir_sem); + d_lookup_done(dentry); nfs_free_unlinkdata(data); + dput(dentry); nfs_sb_deactive(sb); } static void nfs_unlink_prepare(struct rpc_task *task, void *calldata) { struct nfs_unlinkdata *data = calldata; - NFS_PROTO(data->dir)->unlink_rpc_prepare(task, data); + struct inode *dir = d_inode(data->dentry->d_parent); + NFS_PROTO(dir)->unlink_rpc_prepare(task, data); } static const struct rpc_call_ops nfs_unlink_ops = { @@ -114,7 +84,7 @@ static const struct rpc_call_ops nfs_unlink_ops = { .rpc_call_prepare = nfs_unlink_prepare, }; -static int nfs_do_call_unlink(struct dentry *parent, struct inode *dir, struct nfs_unlinkdata *data) +static void nfs_do_call_unlink(struct nfs_unlinkdata *data) { struct rpc_message msg = { .rpc_argp = &data->args, @@ -129,10 +99,31 @@ static int nfs_do_call_unlink(struct dentry *parent, struct inode *dir, struct n .flags = RPC_TASK_ASYNC, }; struct rpc_task *task; + struct inode *dir = d_inode(data->dentry->d_parent); + nfs_sb_active(dir->i_sb); + data->args.fh = NFS_FH(dir); + nfs_fattr_init(data->res.dir_attr); + + NFS_PROTO(dir)->unlink_setup(&msg, dir); + + task_setup_data.rpc_client = NFS_CLIENT(dir); + task = rpc_run_task(&task_setup_data); + if (!IS_ERR(task)) + rpc_put_task_async(task); +} + +static int nfs_call_unlink(struct dentry *dentry, struct nfs_unlinkdata *data) +{ + struct inode *dir = d_inode(dentry->d_parent); struct dentry *alias; - alias = d_lookup(parent, &data->args.name); - if (alias != NULL) { + down_read_non_owner(&NFS_I(dir)->rmdir_sem); + alias = d_alloc_parallel(dentry->d_parent, &data->args.name, &data->wq); + if (IS_ERR(alias)) { + up_read_non_owner(&NFS_I(dir)->rmdir_sem); + return 0; + } + if (!d_in_lookup(alias)) { int ret; void *devname_garbage = NULL; @@ -140,10 +131,8 @@ static int nfs_do_call_unlink(struct dentry *parent, struct inode *dir, struct n * Hey, we raced with lookup... See if we need to transfer * the sillyrename information to the aliased dentry. */ - nfs_free_dname(data); - ret = nfs_copy_dname(alias, data); spin_lock(&alias->d_lock); - if (ret == 0 && d_really_is_positive(alias) && + if (d_really_is_positive(alias) && !(alias->d_flags & DCACHE_NFSFS_RENAMED)) { devname_garbage = alias->d_fsdata; alias->d_fsdata = data; @@ -152,8 +141,8 @@ static int nfs_do_call_unlink(struct dentry *parent, struct inode *dir, struct n } else ret = 0; spin_unlock(&alias->d_lock); - nfs_dec_sillycount(dir); dput(alias); + up_read_non_owner(&NFS_I(dir)->rmdir_sem); /* * If we'd displaced old cached devname, free it. At that * point dentry is definitely not a root, so we won't need @@ -162,94 +151,18 @@ static int nfs_do_call_unlink(struct dentry *parent, struct inode *dir, struct n kfree(devname_garbage); return ret; } - data->dir = igrab(dir); - if (!data->dir) { - nfs_dec_sillycount(dir); - return 0; - } - nfs_sb_active(dir->i_sb); - data->args.fh = NFS_FH(dir); - nfs_fattr_init(data->res.dir_attr); - - NFS_PROTO(dir)->unlink_setup(&msg, dir); - - task_setup_data.rpc_client = NFS_CLIENT(dir); - task = rpc_run_task(&task_setup_data); - if (!IS_ERR(task)) - rpc_put_task_async(task); + data->dentry = alias; + nfs_do_call_unlink(data); return 1; } -static int nfs_call_unlink(struct dentry *dentry, struct nfs_unlinkdata *data) -{ - struct dentry *parent; - struct inode *dir; - int ret = 0; - - - parent = dget_parent(dentry); - if (parent == NULL) - goto out_free; - dir = d_inode(parent); - /* Non-exclusive lock protects against concurrent lookup() calls */ - spin_lock(&dir->i_lock); - if (atomic_inc_not_zero(&NFS_I(dir)->silly_count) == 0) { - /* Deferred delete */ - hlist_add_head(&data->list, &NFS_I(dir)->silly_list); - spin_unlock(&dir->i_lock); - ret = 1; - goto out_dput; - } - spin_unlock(&dir->i_lock); - ret = nfs_do_call_unlink(parent, dir, data); -out_dput: - dput(parent); -out_free: - return ret; -} - -void nfs_wait_on_sillyrename(struct dentry *dentry) -{ - struct nfs_inode *nfsi = NFS_I(d_inode(dentry)); - - wait_event(nfsi->waitqueue, atomic_read(&nfsi->silly_count) <= 1); -} - -void nfs_block_sillyrename(struct dentry *dentry) -{ - struct nfs_inode *nfsi = NFS_I(d_inode(dentry)); - - wait_event(nfsi->waitqueue, atomic_cmpxchg(&nfsi->silly_count, 1, 0) == 1); -} - -void nfs_unblock_sillyrename(struct dentry *dentry) -{ - struct inode *dir = d_inode(dentry); - struct nfs_inode *nfsi = NFS_I(dir); - struct nfs_unlinkdata *data; - - atomic_inc(&nfsi->silly_count); - spin_lock(&dir->i_lock); - while (!hlist_empty(&nfsi->silly_list)) { - if (!atomic_inc_not_zero(&nfsi->silly_count)) - break; - data = hlist_entry(nfsi->silly_list.first, struct nfs_unlinkdata, list); - hlist_del(&data->list); - spin_unlock(&dir->i_lock); - if (nfs_do_call_unlink(dentry, dir, data) == 0) - nfs_free_unlinkdata(data); - spin_lock(&dir->i_lock); - } - spin_unlock(&dir->i_lock); -} - /** * nfs_async_unlink - asynchronous unlinking of a file * @dir: parent directory of dentry * @dentry: dentry to unlink */ static int -nfs_async_unlink(struct inode *dir, struct dentry *dentry) +nfs_async_unlink(struct dentry *dentry, struct qstr *name) { struct nfs_unlinkdata *data; int status = -ENOMEM; @@ -258,13 +171,18 @@ nfs_async_unlink(struct inode *dir, struct dentry *dentry) data = kzalloc(sizeof(*data), GFP_KERNEL); if (data == NULL) goto out; + data->args.name.name = kstrdup(name->name, GFP_KERNEL); + if (!data->args.name.name) + goto out_free; + data->args.name.len = name->len; data->cred = rpc_lookup_cred(); if (IS_ERR(data->cred)) { status = PTR_ERR(data->cred); - goto out_free; + goto out_free_name; } data->res.dir_attr = &data->dir_attr; + init_waitqueue_head(&data->wq); status = -EBUSY; spin_lock(&dentry->d_lock); @@ -284,6 +202,8 @@ nfs_async_unlink(struct inode *dir, struct dentry *dentry) out_unlock: spin_unlock(&dentry->d_lock); put_rpccred(data->cred); +out_free_name: + kfree(data->args.name.name); out_free: kfree(data); out: @@ -302,17 +222,15 @@ out: void nfs_complete_unlink(struct dentry *dentry, struct inode *inode) { - struct nfs_unlinkdata *data = NULL; + struct nfs_unlinkdata *data; spin_lock(&dentry->d_lock); - if (dentry->d_flags & DCACHE_NFSFS_RENAMED) { - dentry->d_flags &= ~DCACHE_NFSFS_RENAMED; - data = dentry->d_fsdata; - dentry->d_fsdata = NULL; - } + dentry->d_flags &= ~DCACHE_NFSFS_RENAMED; + data = dentry->d_fsdata; + dentry->d_fsdata = NULL; spin_unlock(&dentry->d_lock); - if (data != NULL && (NFS_STALE(inode) || !nfs_call_unlink(dentry, data))) + if (NFS_STALE(inode) || !nfs_call_unlink(dentry, data)) nfs_free_unlinkdata(data); } @@ -559,18 +477,10 @@ nfs_sillyrename(struct inode *dir, struct dentry *dentry) /* queue unlink first. Can't do this from rpc_release as it * has to allocate memory */ - error = nfs_async_unlink(dir, dentry); + error = nfs_async_unlink(dentry, &sdentry->d_name); if (error) goto out_dput; - /* populate unlinkdata with the right dname */ - error = nfs_copy_dname(sdentry, - (struct nfs_unlinkdata *)dentry->d_fsdata); - if (error) { - nfs_cancel_async_unlink(dentry); - goto out_dput; - } - /* run the rename task, undo unlink if it fails */ task = nfs_async_rename(dir, dir, dentry, sdentry, nfs_complete_sillyrename); diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c index 51c3b06..d818e4f 100644 --- a/fs/nfsd/nfs3proc.c +++ b/fs/nfsd/nfs3proc.c @@ -552,7 +552,7 @@ nfsd3_proc_fsinfo(struct svc_rqst * rqstp, struct nfsd_fhandle *argp, * different read/write sizes for file systems known to have * problems with large blocks */ if (nfserr == 0) { - struct super_block *sb = d_inode(argp->fh.fh_dentry)->i_sb; + struct super_block *sb = argp->fh.fh_dentry->d_sb; /* Note that we don't care for remote fs's here */ if (sb->s_magic == MSDOS_SUPER_MAGIC) { @@ -588,7 +588,7 @@ nfsd3_proc_pathconf(struct svc_rqst * rqstp, struct nfsd_fhandle *argp, nfserr = fh_verify(rqstp, &argp->fh, 0, NFSD_MAY_NOP); if (nfserr == 0) { - struct super_block *sb = d_inode(argp->fh.fh_dentry)->i_sb; + struct super_block *sb = argp->fh.fh_dentry->d_sb; /* Note that we don't care for remote fs's here */ switch (sb->s_magic) { diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c index 2246454..93d5853 100644 --- a/fs/nfsd/nfs3xdr.c +++ b/fs/nfsd/nfs3xdr.c @@ -146,7 +146,7 @@ static __be32 *encode_fsid(__be32 *p, struct svc_fh *fhp) default: case FSIDSOURCE_DEV: p = xdr_encode_hyper(p, (u64)huge_encode_dev - (d_inode(fhp->fh_dentry)->i_sb->s_dev)); + (fhp->fh_dentry->d_sb->s_dev)); break; case FSIDSOURCE_FSID: p = xdr_encode_hyper(p, (u64) fhp->fh_export->ex_fsid); diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c index c1681ce..a891944 100644 --- a/fs/nfsd/nfsfh.c +++ b/fs/nfsd/nfsfh.c @@ -426,7 +426,7 @@ static bool is_root_export(struct svc_export *exp) static struct super_block *exp_sb(struct svc_export *exp) { - return d_inode(exp->ex_path.dentry)->i_sb; + return exp->ex_path.dentry->d_sb; } static bool fsid_type_ok_for_exp(u8 fsid_type, struct svc_export *exp) diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index d40010e..6fbd81e 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -935,8 +935,8 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file, int stable = *stablep; int use_wgather; loff_t pos = offset; - loff_t end = LLONG_MAX; unsigned int pflags = current->flags; + int flags = 0; if (test_bit(RQ_LOCAL, &rqstp->rq_flags)) /* @@ -955,9 +955,12 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file, if (!EX_ISSYNC(exp)) stable = 0; + if (stable && !use_wgather) + flags |= RWF_SYNC; + /* Write the data. */ oldfs = get_fs(); set_fs(KERNEL_DS); - host_err = vfs_writev(file, (struct iovec __user *)vec, vlen, &pos, 0); + host_err = vfs_writev(file, (struct iovec __user *)vec, vlen, &pos, flags); set_fs(oldfs); if (host_err < 0) goto out_nfserr; @@ -965,15 +968,8 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file, nfsdstats.io_write += host_err; fsnotify_modify(file); - if (stable) { - if (use_wgather) { - host_err = wait_for_concurrent_writes(file); - } else { - if (*cnt) - end = offset + *cnt - 1; - host_err = vfs_fsync_range(file, offset, end, 0); - } - } + if (stable && use_wgather) + host_err = wait_for_concurrent_writes(file); out_nfserr: dprintk("nfsd: write complete host_err=%d\n", host_err); diff --git a/fs/nilfs2/dir.c b/fs/nilfs2/dir.c index e08f064..6723d45 100644 --- a/fs/nilfs2/dir.c +++ b/fs/nilfs2/dir.c @@ -102,7 +102,7 @@ static void nilfs_commit_chunk(struct page *page, unlock_page(page); } -static void nilfs_check_page(struct page *page) +static bool nilfs_check_page(struct page *page) { struct inode *dir = page->mapping->host; struct super_block *sb = dir->i_sb; @@ -137,7 +137,7 @@ static void nilfs_check_page(struct page *page) goto Eend; out: SetPageChecked(page); - return; + return true; /* Too bad, we had an error */ @@ -173,8 +173,8 @@ Eend: dir->i_ino, (page->index<<PAGE_SHIFT)+offs, (unsigned long) le64_to_cpu(p->inode)); fail: - SetPageChecked(page); SetPageError(page); + return false; } static struct page *nilfs_get_page(struct inode *dir, unsigned long n) @@ -184,10 +184,10 @@ static struct page *nilfs_get_page(struct inode *dir, unsigned long n) if (!IS_ERR(page)) { kmap(page); - if (!PageChecked(page)) - nilfs_check_page(page); - if (PageError(page)) - goto fail; + if (unlikely(!PageChecked(page))) { + if (PageError(page) || !nilfs_check_page(page)) + goto fail; + } } return page; @@ -661,7 +661,7 @@ not_empty: const struct file_operations nilfs_dir_operations = { .llseek = generic_file_llseek, .read = generic_read_dir, - .iterate = nilfs_readdir, + .iterate_shared = nilfs_readdir, .unlocked_ioctl = nilfs_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = nilfs_compat_ioctl, diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index 5346313..cfebcd2 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -305,7 +305,7 @@ static int nilfs_write_end(struct file *file, struct address_space *mapping, } static ssize_t -nilfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset) +nilfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) { struct inode *inode = file_inode(iocb->ki_filp); @@ -313,7 +313,7 @@ nilfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset) return 0; /* Needs synchronization with the cleaner */ - return blockdev_direct_IO(iocb, inode, iter, offset, nilfs_get_block); + return blockdev_direct_IO(iocb, inode, iter, nilfs_get_block); } const struct address_space_operations nilfs_aops = { diff --git a/fs/nilfs2/namei.c b/fs/nilfs2/namei.c index 151bc19..3b2af05 100644 --- a/fs/nilfs2/namei.c +++ b/fs/nilfs2/namei.c @@ -457,7 +457,7 @@ static struct dentry *nilfs_get_parent(struct dentry *child) root = NILFS_I(d_inode(child))->i_root; - inode = nilfs_iget(d_inode(child)->i_sb, root, ino); + inode = nilfs_iget(child->d_sb, root, ino); if (IS_ERR(inode)) return ERR_CAST(inode); diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c index 91117ad..5622ed5 100644 --- a/fs/ntfs/file.c +++ b/fs/ntfs/file.c @@ -1952,12 +1952,9 @@ static ssize_t ntfs_file_write_iter(struct kiocb *iocb, struct iov_iter *from) written = ntfs_perform_write(file, from, iocb->ki_pos); current->backing_dev_info = NULL; inode_unlock(vi); - if (likely(written > 0)) { - err = generic_write_sync(file, iocb->ki_pos, written); - if (err < 0) - written = 0; - } iocb->ki_pos += written; + if (likely(written > 0)) + written = generic_write_sync(iocb, written); return written ? written : err; } diff --git a/fs/ocfs2/acl.c b/fs/ocfs2/acl.c index 0cdf497..2162434 100644 --- a/fs/ocfs2/acl.c +++ b/fs/ocfs2/acl.c @@ -322,3 +322,90 @@ struct posix_acl *ocfs2_iop_get_acl(struct inode *inode, int type) brelse(di_bh); return acl; } + +int ocfs2_acl_chmod(struct inode *inode, struct buffer_head *bh) +{ + struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); + struct posix_acl *acl; + int ret; + + if (S_ISLNK(inode->i_mode)) + return -EOPNOTSUPP; + + if (!(osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL)) + return 0; + + acl = ocfs2_get_acl_nolock(inode, ACL_TYPE_ACCESS, bh); + if (IS_ERR(acl) || !acl) + return PTR_ERR(acl); + ret = __posix_acl_chmod(&acl, GFP_KERNEL, inode->i_mode); + if (ret) + return ret; + ret = ocfs2_set_acl(NULL, inode, NULL, ACL_TYPE_ACCESS, + acl, NULL, NULL); + posix_acl_release(acl); + return ret; +} + +/* + * Initialize the ACLs of a new inode. If parent directory has default ACL, + * then clone to new inode. Called from ocfs2_mknod. + */ +int ocfs2_init_acl(handle_t *handle, + struct inode *inode, + struct inode *dir, + struct buffer_head *di_bh, + struct buffer_head *dir_bh, + struct ocfs2_alloc_context *meta_ac, + struct ocfs2_alloc_context *data_ac) +{ + struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); + struct posix_acl *acl = NULL; + int ret = 0, ret2; + umode_t mode; + + if (!S_ISLNK(inode->i_mode)) { + if (osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL) { + acl = ocfs2_get_acl_nolock(dir, ACL_TYPE_DEFAULT, + dir_bh); + if (IS_ERR(acl)) + return PTR_ERR(acl); + } + if (!acl) { + mode = inode->i_mode & ~current_umask(); + ret = ocfs2_acl_set_mode(inode, di_bh, handle, mode); + if (ret) { + mlog_errno(ret); + goto cleanup; + } + } + } + if ((osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL) && acl) { + if (S_ISDIR(inode->i_mode)) { + ret = ocfs2_set_acl(handle, inode, di_bh, + ACL_TYPE_DEFAULT, acl, + meta_ac, data_ac); + if (ret) + goto cleanup; + } + mode = inode->i_mode; + ret = __posix_acl_create(&acl, GFP_NOFS, &mode); + if (ret < 0) + return ret; + + ret2 = ocfs2_acl_set_mode(inode, di_bh, handle, mode); + if (ret2) { + mlog_errno(ret2); + ret = ret2; + goto cleanup; + } + if (ret > 0) { + ret = ocfs2_set_acl(handle, inode, + di_bh, ACL_TYPE_ACCESS, + acl, meta_ac, data_ac); + } + } +cleanup: + posix_acl_release(acl); + return ret; +} diff --git a/fs/ocfs2/acl.h b/fs/ocfs2/acl.h index 3fce68d..2783a75 100644 --- a/fs/ocfs2/acl.h +++ b/fs/ocfs2/acl.h @@ -35,5 +35,10 @@ int ocfs2_set_acl(handle_t *handle, struct posix_acl *acl, struct ocfs2_alloc_context *meta_ac, struct ocfs2_alloc_context *data_ac); +extern int ocfs2_acl_chmod(struct inode *, struct buffer_head *); +extern int ocfs2_init_acl(handle_t *, struct inode *, struct inode *, + struct buffer_head *, struct buffer_head *, + struct ocfs2_alloc_context *, + struct ocfs2_alloc_context *); #endif /* OCFS2_ACL_H */ diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index ad15773..c034edf 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -2311,7 +2311,7 @@ static void ocfs2_dio_end_io_write(struct inode *inode, /* ocfs2_file_write_iter will get i_mutex, so we need not lock if we * are in that context. */ if (dwc->dw_writer_pid != task_pid_nr(current)) { - mutex_lock(&inode->i_mutex); + inode_lock(inode); locked = 1; } @@ -2390,7 +2390,7 @@ out: ocfs2_free_alloc_context(meta_ac); ocfs2_run_deallocs(osb, &dealloc); if (locked) - mutex_unlock(&inode->i_mutex); + inode_unlock(inode); ocfs2_dio_free_write_ctx(inode, dwc); } @@ -2423,13 +2423,11 @@ static int ocfs2_dio_end_io(struct kiocb *iocb, return 0; } -static ssize_t ocfs2_direct_IO(struct kiocb *iocb, struct iov_iter *iter, - loff_t offset) +static ssize_t ocfs2_direct_IO(struct kiocb *iocb, struct iov_iter *iter) { struct file *file = iocb->ki_filp; struct inode *inode = file_inode(file)->i_mapping->host; struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); - loff_t end = offset + iter->count; get_block_t *get_block; /* @@ -2440,7 +2438,8 @@ static ssize_t ocfs2_direct_IO(struct kiocb *iocb, struct iov_iter *iter, return 0; /* Fallback to buffered I/O if we do not support append dio. */ - if (end > i_size_read(inode) && !ocfs2_supports_append_dio(osb)) + if (iocb->ki_pos + iter->count > i_size_read(inode) && + !ocfs2_supports_append_dio(osb)) return 0; if (iov_iter_rw(iter) == READ) @@ -2449,7 +2448,7 @@ static ssize_t ocfs2_direct_IO(struct kiocb *iocb, struct iov_iter *iter, get_block = ocfs2_dio_get_block; return __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev, - iter, offset, get_block, + iter, get_block, ocfs2_dio_end_io, NULL, 0); } diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c index 474e57f..1eaa910 100644 --- a/fs/ocfs2/dlmglue.c +++ b/fs/ocfs2/dlmglue.c @@ -54,6 +54,7 @@ #include "uptodate.h" #include "quota.h" #include "refcounttree.h" +#include "acl.h" #include "buffer_head_io.h" @@ -3623,6 +3624,8 @@ static int ocfs2_data_convert_worker(struct ocfs2_lock_res *lockres, filemap_fdatawait(mapping); } + forget_all_cached_acls(inode); + out: return UNBLOCK_CONTINUE; } diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 5308841..4e7b0dc 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -1268,20 +1268,20 @@ bail_unlock_rw: if (size_change) ocfs2_rw_unlock(inode, 1); bail: - brelse(bh); /* Release quota pointers in case we acquired them */ for (qtype = 0; qtype < OCFS2_MAXQUOTAS; qtype++) dqput(transfer_to[qtype]); if (!status && attr->ia_valid & ATTR_MODE) { - status = posix_acl_chmod(inode, inode->i_mode); + status = ocfs2_acl_chmod(inode, bh); if (status < 0) mlog_errno(status); } if (inode_locked) ocfs2_inode_unlock(inode, 1); + brelse(bh); return status; } @@ -1290,7 +1290,7 @@ int ocfs2_getattr(struct vfsmount *mnt, struct kstat *stat) { struct inode *inode = d_inode(dentry); - struct super_block *sb = d_inode(dentry)->i_sb; + struct super_block *sb = dentry->d_sb; struct ocfs2_super *osb = sb->s_fs_info; int err; diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c index 12f4a9e..0748777 100644 --- a/fs/ocfs2/inode.c +++ b/fs/ocfs2/inode.c @@ -262,7 +262,7 @@ static int ocfs2_init_locked_inode(struct inode *inode, void *opaque) inode->i_ino = args->fi_ino; OCFS2_I(inode)->ip_blkno = args->fi_blkno; if (args->fi_sysfile_type != 0) - lockdep_set_class(&inode->i_mutex, + lockdep_set_class(&inode->i_rwsem, &ocfs2_sysfile_lock_key[args->fi_sysfile_type]); if (args->fi_sysfile_type == USER_QUOTA_SYSTEM_INODE || args->fi_sysfile_type == GROUP_QUOTA_SYSTEM_INODE || diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c index 6b3e871..a8f1225 100644 --- a/fs/ocfs2/namei.c +++ b/fs/ocfs2/namei.c @@ -259,7 +259,6 @@ static int ocfs2_mknod(struct inode *dir, struct ocfs2_dir_lookup_result lookup = { NULL, }; sigset_t oldset; int did_block_signals = 0; - struct posix_acl *default_acl = NULL, *acl = NULL; struct ocfs2_dentry_lock *dl = NULL; trace_ocfs2_mknod(dir, dentry, dentry->d_name.len, dentry->d_name.name, @@ -367,12 +366,6 @@ static int ocfs2_mknod(struct inode *dir, goto leave; } - status = posix_acl_create(dir, &inode->i_mode, &default_acl, &acl); - if (status) { - mlog_errno(status); - goto leave; - } - handle = ocfs2_start_trans(osb, ocfs2_mknod_credits(osb->sb, S_ISDIR(mode), xattr_credits)); @@ -421,16 +414,8 @@ static int ocfs2_mknod(struct inode *dir, inc_nlink(dir); } - if (default_acl) { - status = ocfs2_set_acl(handle, inode, new_fe_bh, - ACL_TYPE_DEFAULT, default_acl, - meta_ac, data_ac); - } - if (!status && acl) { - status = ocfs2_set_acl(handle, inode, new_fe_bh, - ACL_TYPE_ACCESS, acl, - meta_ac, data_ac); - } + status = ocfs2_init_acl(handle, inode, dir, new_fe_bh, parent_fe_bh, + meta_ac, data_ac); if (status < 0) { mlog_errno(status); @@ -472,10 +457,6 @@ static int ocfs2_mknod(struct inode *dir, d_instantiate(dentry, inode); status = 0; leave: - if (default_acl) - posix_acl_release(default_acl); - if (acl) - posix_acl_release(acl); if (status < 0 && did_quota_inode) dquot_free_inode(inode); if (handle) diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c index 744d5d9..92bbe93 100644 --- a/fs/ocfs2/refcounttree.c +++ b/fs/ocfs2/refcounttree.c @@ -4248,20 +4248,12 @@ static int ocfs2_reflink(struct dentry *old_dentry, struct inode *dir, struct inode *inode = d_inode(old_dentry); struct buffer_head *old_bh = NULL; struct inode *new_orphan_inode = NULL; - struct posix_acl *default_acl, *acl; - umode_t mode; if (!ocfs2_refcount_tree(OCFS2_SB(inode->i_sb))) return -EOPNOTSUPP; - mode = inode->i_mode; - error = posix_acl_create(dir, &mode, &default_acl, &acl); - if (error) { - mlog_errno(error); - return error; - } - error = ocfs2_create_inode_in_orphan(dir, mode, + error = ocfs2_create_inode_in_orphan(dir, inode->i_mode, &new_orphan_inode); if (error) { mlog_errno(error); @@ -4300,16 +4292,11 @@ static int ocfs2_reflink(struct dentry *old_dentry, struct inode *dir, /* If the security isn't preserved, we need to re-initialize them. */ if (!preserve) { error = ocfs2_init_security_and_acl(dir, new_orphan_inode, - &new_dentry->d_name, - default_acl, acl); + &new_dentry->d_name); if (error) mlog_errno(error); } out: - if (default_acl) - posix_acl_release(default_acl); - if (acl) - posix_acl_release(acl); if (!error) { error = ocfs2_mv_orphaned_inode_to_new(dir, new_orphan_inode, new_dentry); diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c index 7d3d979..ad16995 100644 --- a/fs/ocfs2/xattr.c +++ b/fs/ocfs2/xattr.c @@ -7216,12 +7216,10 @@ out: */ int ocfs2_init_security_and_acl(struct inode *dir, struct inode *inode, - const struct qstr *qstr, - struct posix_acl *default_acl, - struct posix_acl *acl) + const struct qstr *qstr) { - struct buffer_head *dir_bh = NULL; int ret = 0; + struct buffer_head *dir_bh = NULL; ret = ocfs2_init_security_get(inode, dir, qstr, NULL); if (ret) { @@ -7234,11 +7232,9 @@ int ocfs2_init_security_and_acl(struct inode *dir, mlog_errno(ret); goto leave; } - - if (!ret && default_acl) - ret = ocfs2_iop_set_acl(inode, default_acl, ACL_TYPE_DEFAULT); - if (!ret && acl) - ret = ocfs2_iop_set_acl(inode, acl, ACL_TYPE_ACCESS); + ret = ocfs2_init_acl(NULL, inode, dir, NULL, dir_bh, NULL, NULL); + if (ret) + mlog_errno(ret); ocfs2_inode_unlock(dir, 0); brelse(dir_bh); @@ -7250,10 +7246,10 @@ leave: * 'security' attributes support */ static int ocfs2_xattr_security_get(const struct xattr_handler *handler, - struct dentry *dentry, const char *name, - void *buffer, size_t size) + struct dentry *unused, struct inode *inode, + const char *name, void *buffer, size_t size) { - return ocfs2_xattr_get(d_inode(dentry), OCFS2_XATTR_INDEX_SECURITY, + return ocfs2_xattr_get(inode, OCFS2_XATTR_INDEX_SECURITY, name, buffer, size); } @@ -7321,10 +7317,10 @@ const struct xattr_handler ocfs2_xattr_security_handler = { * 'trusted' attributes support */ static int ocfs2_xattr_trusted_get(const struct xattr_handler *handler, - struct dentry *dentry, const char *name, - void *buffer, size_t size) + struct dentry *unused, struct inode *inode, + const char *name, void *buffer, size_t size) { - return ocfs2_xattr_get(d_inode(dentry), OCFS2_XATTR_INDEX_TRUSTED, + return ocfs2_xattr_get(inode, OCFS2_XATTR_INDEX_TRUSTED, name, buffer, size); } @@ -7346,14 +7342,14 @@ const struct xattr_handler ocfs2_xattr_trusted_handler = { * 'user' attributes support */ static int ocfs2_xattr_user_get(const struct xattr_handler *handler, - struct dentry *dentry, const char *name, - void *buffer, size_t size) + struct dentry *unusde, struct inode *inode, + const char *name, void *buffer, size_t size) { - struct ocfs2_super *osb = OCFS2_SB(dentry->d_sb); + struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); if (osb->s_mount_opt & OCFS2_MOUNT_NOUSERXATTR) return -EOPNOTSUPP; - return ocfs2_xattr_get(d_inode(dentry), OCFS2_XATTR_INDEX_USER, name, + return ocfs2_xattr_get(inode, OCFS2_XATTR_INDEX_USER, name, buffer, size); } diff --git a/fs/ocfs2/xattr.h b/fs/ocfs2/xattr.h index f10d5b9..1633cc1 100644 --- a/fs/ocfs2/xattr.h +++ b/fs/ocfs2/xattr.h @@ -94,7 +94,5 @@ int ocfs2_reflink_xattrs(struct inode *old_inode, bool preserve_security); int ocfs2_init_security_and_acl(struct inode *dir, struct inode *inode, - const struct qstr *qstr, - struct posix_acl *default_acl, - struct posix_acl *acl); + const struct qstr *qstr); #endif /* OCFS2_XATTR_H */ diff --git a/fs/omfs/dir.c b/fs/omfs/dir.c index f833bf8..c8cbf3b 100644 --- a/fs/omfs/dir.c +++ b/fs/omfs/dir.c @@ -452,6 +452,6 @@ const struct inode_operations omfs_dir_inops = { const struct file_operations omfs_dir_operations = { .read = generic_read_dir, - .iterate = omfs_readdir, + .iterate_shared = omfs_readdir, .llseek = generic_file_llseek, }; @@ -65,7 +65,7 @@ int do_truncate(struct dentry *dentry, loff_t length, unsigned int time_attrs, return ret; } -long vfs_truncate(struct path *path, loff_t length) +long vfs_truncate(const struct path *path, loff_t length) { struct inode *inode; long error; @@ -499,7 +499,7 @@ out: return error; } -static int chmod_common(struct path *path, umode_t mode) +static int chmod_common(const struct path *path, umode_t mode) { struct inode *inode = path->dentry->d_inode; struct inode *delegated_inode = NULL; @@ -564,7 +564,7 @@ SYSCALL_DEFINE2(chmod, const char __user *, filename, umode_t, mode) return sys_fchmodat(AT_FDCWD, filename, mode); } -static int chown_common(struct path *path, uid_t user, gid_t group) +static int chown_common(const struct path *path, uid_t user, gid_t group) { struct inode *inode = path->dentry->d_inode; struct inode *delegated_inode = NULL; @@ -713,7 +713,7 @@ static int do_dentry_open(struct file *f, } /* POSIX.1-2008/SUSv4 Section XSI 2.9.7 */ - if (S_ISREG(inode->i_mode)) + if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode)) f->f_mode |= FMODE_ATOMIC_POS; f->f_op = fops_get(inode->i_fop); @@ -840,16 +840,12 @@ EXPORT_SYMBOL(file_path); int vfs_open(const struct path *path, struct file *file, const struct cred *cred) { - struct dentry *dentry = path->dentry; - struct inode *inode = dentry->d_inode; + struct inode *inode = vfs_select_inode(path->dentry, file->f_flags); - file->f_path = *path; - if (dentry->d_flags & DCACHE_OP_SELECT_INODE) { - inode = dentry->d_op->d_select_inode(dentry, file->f_flags); - if (IS_ERR(inode)) - return PTR_ERR(inode); - } + if (IS_ERR(inode)) + return PTR_ERR(inode); + file->f_path = *path; return do_dentry_open(file, inode, NULL, cred); } diff --git a/fs/openpromfs/inode.c b/fs/openpromfs/inode.c index b61b883..c7a8699 100644 --- a/fs/openpromfs/inode.c +++ b/fs/openpromfs/inode.c @@ -166,7 +166,7 @@ static int openpromfs_readdir(struct file *, struct dir_context *); static const struct file_operations openprom_operations = { .read = generic_read_dir, - .iterate = openpromfs_readdir, + .iterate_shared = openpromfs_readdir, .llseek = generic_file_llseek, }; diff --git a/fs/orangefs/file.c b/fs/orangefs/file.c index ae92795..491e82c 100644 --- a/fs/orangefs/file.c +++ b/fs/orangefs/file.c @@ -445,7 +445,7 @@ static ssize_t orangefs_file_write_iter(struct kiocb *iocb, struct iov_iter *ite gossip_debug(GOSSIP_FILE_DEBUG, "orangefs_file_write_iter\n"); - mutex_lock(&file->f_mapping->host->i_mutex); + inode_lock(file->f_mapping->host); /* Make sure generic_write_checks sees an up to date inode size. */ if (file->f_flags & O_APPEND) { @@ -492,7 +492,7 @@ static ssize_t orangefs_file_write_iter(struct kiocb *iocb, struct iov_iter *ite out: - mutex_unlock(&file->f_mapping->host->i_mutex); + inode_unlock(file->f_mapping->host); return rc; } diff --git a/fs/orangefs/orangefs-kernel.h b/fs/orangefs/orangefs-kernel.h index a9925e2..2281882 100644 --- a/fs/orangefs/orangefs-kernel.h +++ b/fs/orangefs/orangefs-kernel.h @@ -612,11 +612,11 @@ do { \ static inline void orangefs_i_size_write(struct inode *inode, loff_t i_size) { #if BITS_PER_LONG == 32 && defined(CONFIG_SMP) - mutex_lock(&inode->i_mutex); + inode_lock(inode); #endif i_size_write(inode, i_size); #if BITS_PER_LONG == 32 && defined(CONFIG_SMP) - mutex_unlock(&inode->i_mutex); + inode_unlock(inode); #endif } diff --git a/fs/orangefs/xattr.c b/fs/orangefs/xattr.c index 63a6280d..99c1954 100644 --- a/fs/orangefs/xattr.c +++ b/fs/orangefs/xattr.c @@ -463,12 +463,13 @@ static int orangefs_xattr_set_default(const struct xattr_handler *handler, } static int orangefs_xattr_get_default(const struct xattr_handler *handler, - struct dentry *dentry, + struct dentry *unused, + struct inode *inode, const char *name, void *buffer, size_t size) { - return orangefs_inode_getxattr(dentry->d_inode, + return orangefs_inode_getxattr(inode, ORANGEFS_XATTR_NAME_DEFAULT_PREFIX, name, buffer, @@ -492,12 +493,13 @@ static int orangefs_xattr_set_trusted(const struct xattr_handler *handler, } static int orangefs_xattr_get_trusted(const struct xattr_handler *handler, - struct dentry *dentry, + struct dentry *unused, + struct inode *inode, const char *name, void *buffer, size_t size) { - return orangefs_inode_getxattr(dentry->d_inode, + return orangefs_inode_getxattr(inode, ORANGEFS_XATTR_NAME_TRUSTED_PREFIX, name, buffer, diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index a4ff5d0..c7b31a0 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -246,8 +246,8 @@ static bool ovl_need_xattr_filter(struct dentry *dentry, return false; } -ssize_t ovl_getxattr(struct dentry *dentry, const char *name, - void *value, size_t size) +ssize_t ovl_getxattr(struct dentry *dentry, struct inode *inode, + const char *name, void *value, size_t size) { struct path realpath; enum ovl_path_type type = ovl_path_real(dentry, &realpath); diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h index 6a7090f..99ec4b0 100644 --- a/fs/overlayfs/overlayfs.h +++ b/fs/overlayfs/overlayfs.h @@ -173,8 +173,8 @@ int ovl_setattr(struct dentry *dentry, struct iattr *attr); int ovl_permission(struct inode *inode, int mask); int ovl_setxattr(struct dentry *dentry, const char *name, const void *value, size_t size, int flags); -ssize_t ovl_getxattr(struct dentry *dentry, const char *name, - void *value, size_t size); +ssize_t ovl_getxattr(struct dentry *dentry, struct inode *inode, + const char *name, void *value, size_t size); ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size); int ovl_removexattr(struct dentry *dentry, const char *name); struct inode *ovl_d_select_inode(struct dentry *dentry, unsigned file_flags); diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c index 6ec1e43..da186ee 100644 --- a/fs/overlayfs/readdir.c +++ b/fs/overlayfs/readdir.c @@ -218,7 +218,9 @@ static int ovl_check_whiteouts(struct dentry *dir, struct ovl_readdir_data *rdd) cap_raise(override_cred->cap_effective, CAP_DAC_OVERRIDE); old_cred = override_creds(override_cred); - err = mutex_lock_killable(&dir->d_inode->i_mutex); + inode_lock(dir->d_inode); + err = 0; + // XXX: err = mutex_lock_killable(&dir->d_inode->i_mutex); if (!err) { while (rdd->first_maybe_whiteout) { p = rdd->first_maybe_whiteout; diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index 5d972e6..ed53ae0 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -274,7 +274,7 @@ static bool ovl_is_opaquedir(struct dentry *dentry) if (!S_ISDIR(inode->i_mode) || !inode->i_op->getxattr) return false; - res = inode->i_op->getxattr(dentry, OVL_XATTR_OPAQUE, &val, 1); + res = inode->i_op->getxattr(dentry, inode, OVL_XATTR_OPAQUE, &val, 1); if (res == 1 && val == 'y') return true; @@ -411,9 +411,7 @@ static inline struct dentry *ovl_lookup_real(struct dentry *dir, { struct dentry *dentry; - inode_lock(dir->d_inode); - dentry = lookup_one_len(name->name, dir, name->len); - inode_unlock(dir->d_inode); + dentry = lookup_hash(name, dir); if (IS_ERR(dentry)) { if (PTR_ERR(dentry) == -ENOENT) diff --git a/fs/posix_acl.c b/fs/posix_acl.c index 711dd51..2c60f17 100644 --- a/fs/posix_acl.c +++ b/fs/posix_acl.c @@ -21,7 +21,7 @@ #include <linux/export.h> #include <linux/user_namespace.h> -struct posix_acl **acl_by_type(struct inode *inode, int type) +static struct posix_acl **acl_by_type(struct inode *inode, int type) { switch (type) { case ACL_TYPE_ACCESS: @@ -32,19 +32,22 @@ struct posix_acl **acl_by_type(struct inode *inode, int type) BUG(); } } -EXPORT_SYMBOL(acl_by_type); struct posix_acl *get_cached_acl(struct inode *inode, int type) { struct posix_acl **p = acl_by_type(inode, type); - struct posix_acl *acl = ACCESS_ONCE(*p); - if (acl) { - spin_lock(&inode->i_lock); - acl = *p; - if (acl != ACL_NOT_CACHED) - acl = posix_acl_dup(acl); - spin_unlock(&inode->i_lock); + struct posix_acl *acl; + + for (;;) { + rcu_read_lock(); + acl = rcu_dereference(*p); + if (!acl || is_uncached_acl(acl) || + atomic_inc_not_zero(&acl->a_refcount)) + break; + rcu_read_unlock(); + cpu_relax(); } + rcu_read_unlock(); return acl; } EXPORT_SYMBOL(get_cached_acl); @@ -59,58 +62,72 @@ void set_cached_acl(struct inode *inode, int type, struct posix_acl *acl) { struct posix_acl **p = acl_by_type(inode, type); struct posix_acl *old; - spin_lock(&inode->i_lock); - old = *p; - rcu_assign_pointer(*p, posix_acl_dup(acl)); - spin_unlock(&inode->i_lock); - if (old != ACL_NOT_CACHED) + + old = xchg(p, posix_acl_dup(acl)); + if (!is_uncached_acl(old)) posix_acl_release(old); } EXPORT_SYMBOL(set_cached_acl); -void forget_cached_acl(struct inode *inode, int type) +static void __forget_cached_acl(struct posix_acl **p) { - struct posix_acl **p = acl_by_type(inode, type); struct posix_acl *old; - spin_lock(&inode->i_lock); - old = *p; - *p = ACL_NOT_CACHED; - spin_unlock(&inode->i_lock); - if (old != ACL_NOT_CACHED) + + old = xchg(p, ACL_NOT_CACHED); + if (!is_uncached_acl(old)) posix_acl_release(old); } + +void forget_cached_acl(struct inode *inode, int type) +{ + __forget_cached_acl(acl_by_type(inode, type)); +} EXPORT_SYMBOL(forget_cached_acl); void forget_all_cached_acls(struct inode *inode) { - struct posix_acl *old_access, *old_default; - spin_lock(&inode->i_lock); - old_access = inode->i_acl; - old_default = inode->i_default_acl; - inode->i_acl = inode->i_default_acl = ACL_NOT_CACHED; - spin_unlock(&inode->i_lock); - if (old_access != ACL_NOT_CACHED) - posix_acl_release(old_access); - if (old_default != ACL_NOT_CACHED) - posix_acl_release(old_default); + __forget_cached_acl(&inode->i_acl); + __forget_cached_acl(&inode->i_default_acl); } EXPORT_SYMBOL(forget_all_cached_acls); struct posix_acl *get_acl(struct inode *inode, int type) { + void *sentinel; + struct posix_acl **p; struct posix_acl *acl; + /* + * The sentinel is used to detect when another operation like + * set_cached_acl() or forget_cached_acl() races with get_acl(). + * It is guaranteed that is_uncached_acl(sentinel) is true. + */ + acl = get_cached_acl(inode, type); - if (acl != ACL_NOT_CACHED) + if (!is_uncached_acl(acl)) return acl; if (!IS_POSIXACL(inode)) return NULL; + sentinel = uncached_acl_sentinel(current); + p = acl_by_type(inode, type); + /* - * A filesystem can force a ACL callback by just never filling the - * ACL cache. But normally you'd fill the cache either at inode - * instantiation time, or on the first ->get_acl call. + * If the ACL isn't being read yet, set our sentinel. Otherwise, the + * current value of the ACL will not be ACL_NOT_CACHED and so our own + * sentinel will not be set; another task will update the cache. We + * could wait for that other task to complete its job, but it's easier + * to just call ->get_acl to fetch the ACL ourself. (This is going to + * be an unlikely race.) + */ + if (cmpxchg(p, ACL_NOT_CACHED, sentinel) != ACL_NOT_CACHED) + /* fall through */ ; + + /* + * Normally, the ACL returned by ->get_acl will be cached. + * A filesystem can prevent that by calling + * forget_cached_acl(inode, type) in ->get_acl. * * If the filesystem doesn't have a get_acl() function at all, we'll * just create the negative cache entry. @@ -119,7 +136,24 @@ struct posix_acl *get_acl(struct inode *inode, int type) set_cached_acl(inode, type, NULL); return NULL; } - return inode->i_op->get_acl(inode, type); + acl = inode->i_op->get_acl(inode, type); + + if (IS_ERR(acl)) { + /* + * Remove our sentinel so that we don't block future attempts + * to cache the ACL. + */ + cmpxchg(p, sentinel, ACL_NOT_CACHED); + return acl; + } + + /* + * Cache the result, but only if our sentinel is still in place. + */ + posix_acl_dup(acl); + if (unlikely(cmpxchg(p, sentinel, acl) != sentinel)) + posix_acl_release(acl); + return acl; } EXPORT_SYMBOL(get_acl); @@ -763,18 +797,18 @@ EXPORT_SYMBOL (posix_acl_to_xattr); static int posix_acl_xattr_get(const struct xattr_handler *handler, - struct dentry *dentry, const char *name, - void *value, size_t size) + struct dentry *unused, struct inode *inode, + const char *name, void *value, size_t size) { struct posix_acl *acl; int error; - if (!IS_POSIXACL(d_backing_inode(dentry))) + if (!IS_POSIXACL(inode)) return -EOPNOTSUPP; - if (d_is_symlink(dentry)) + if (S_ISLNK(inode->i_mode)) return -EOPNOTSUPP; - acl = get_acl(d_backing_inode(dentry), handler->flags); + acl = get_acl(inode, handler->flags); if (IS_ERR(acl)) return PTR_ERR(acl); if (acl == NULL) diff --git a/fs/proc/base.c b/fs/proc/base.c index 92e37e2..ff4527d 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -434,7 +434,7 @@ static int proc_pid_wchan(struct seq_file *m, struct pid_namespace *ns, && !lookup_symbol_name(wchan, symname)) seq_printf(m, "%s", symname); else - seq_puts(m, "0\n"); + seq_putc(m, '0'); return 0; } @@ -1820,12 +1820,17 @@ bool proc_fill_cache(struct file *file, struct dir_context *ctx, child = d_hash_and_lookup(dir, &qname); if (!child) { - child = d_alloc(dir, &qname); - if (!child) - goto end_instantiate; - if (instantiate(d_inode(dir), child, task, ptr) < 0) { - dput(child); + DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq); + child = d_alloc_parallel(dir, &qname, &wq); + if (IS_ERR(child)) goto end_instantiate; + if (d_in_lookup(child)) { + int err = instantiate(d_inode(dir), child, task, ptr); + d_lookup_done(child); + if (err < 0) { + dput(child); + goto end_instantiate; + } } } inode = d_inode(child); @@ -2155,8 +2160,8 @@ out: static const struct file_operations proc_map_files_operations = { .read = generic_read_dir, - .iterate = proc_map_files_readdir, - .llseek = default_llseek, + .iterate_shared = proc_map_files_readdir, + .llseek = generic_file_llseek, }; #ifdef CONFIG_CHECKPOINT_RESTORE @@ -2503,8 +2508,8 @@ static int proc_attr_dir_readdir(struct file *file, struct dir_context *ctx) static const struct file_operations proc_attr_dir_operations = { .read = generic_read_dir, - .iterate = proc_attr_dir_readdir, - .llseek = default_llseek, + .iterate_shared = proc_attr_dir_readdir, + .llseek = generic_file_llseek, }; static struct dentry *proc_attr_dir_lookup(struct inode *dir, @@ -2911,8 +2916,8 @@ static int proc_tgid_base_readdir(struct file *file, struct dir_context *ctx) static const struct file_operations proc_tgid_base_operations = { .read = generic_read_dir, - .iterate = proc_tgid_base_readdir, - .llseek = default_llseek, + .iterate_shared = proc_tgid_base_readdir, + .llseek = generic_file_llseek, }; static struct dentry *proc_tgid_base_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) @@ -3259,8 +3264,8 @@ static struct dentry *proc_tid_base_lookup(struct inode *dir, struct dentry *den static const struct file_operations proc_tid_base_operations = { .read = generic_read_dir, - .iterate = proc_tid_base_readdir, - .llseek = default_llseek, + .iterate_shared = proc_tid_base_readdir, + .llseek = generic_file_llseek, }; static const struct inode_operations proc_tid_base_inode_operations = { @@ -3470,6 +3475,6 @@ static const struct inode_operations proc_task_inode_operations = { static const struct file_operations proc_task_operations = { .read = generic_read_dir, - .iterate = proc_task_readdir, - .llseek = default_llseek, + .iterate_shared = proc_task_readdir, + .llseek = generic_file_llseek, }; diff --git a/fs/proc/fd.c b/fs/proc/fd.c index 56afa5e..01df23c 100644 --- a/fs/proc/fd.c +++ b/fs/proc/fd.c @@ -276,8 +276,8 @@ static int proc_readfd(struct file *file, struct dir_context *ctx) const struct file_operations proc_fd_operations = { .read = generic_read_dir, - .iterate = proc_readfd, - .llseek = default_llseek, + .iterate_shared = proc_readfd, + .llseek = generic_file_llseek, }; static struct dentry *proc_lookupfd(struct inode *dir, struct dentry *dentry, @@ -361,6 +361,6 @@ const struct inode_operations proc_fdinfo_inode_operations = { const struct file_operations proc_fdinfo_operations = { .read = generic_read_dir, - .iterate = proc_readfdinfo, - .llseek = default_llseek, + .iterate_shared = proc_readfdinfo, + .llseek = generic_file_llseek, }; diff --git a/fs/proc/generic.c b/fs/proc/generic.c index ff3ffc7..c633476 100644 --- a/fs/proc/generic.c +++ b/fs/proc/generic.c @@ -318,7 +318,7 @@ int proc_readdir(struct file *file, struct dir_context *ctx) static const struct file_operations proc_dir_operations = { .llseek = generic_file_llseek, .read = generic_read_dir, - .iterate = proc_readdir, + .iterate_shared = proc_readdir, }; /* diff --git a/fs/proc/namespaces.c b/fs/proc/namespaces.c index 72cb26f..51b8b0a 100644 --- a/fs/proc/namespaces.c +++ b/fs/proc/namespaces.c @@ -139,7 +139,8 @@ out: const struct file_operations proc_ns_dir_operations = { .read = generic_read_dir, - .iterate = proc_ns_dir_readdir, + .iterate_shared = proc_ns_dir_readdir, + .llseek = generic_file_llseek, }; static struct dentry *proc_ns_dir_lookup(struct inode *dir, diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c index 350984a..c8bbc68 100644 --- a/fs/proc/proc_net.c +++ b/fs/proc/proc_net.c @@ -179,7 +179,7 @@ static int proc_tgid_net_readdir(struct file *file, struct dir_context *ctx) const struct file_operations proc_net_operations = { .llseek = generic_file_llseek, .read = generic_read_dir, - .iterate = proc_tgid_net_readdir, + .iterate_shared = proc_tgid_net_readdir, }; static __net_init int proc_net_ns_init(struct net *net) diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index fe5b6e6..5e57c3e 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -627,18 +627,19 @@ static bool proc_sys_fill_cache(struct file *file, child = d_lookup(dir, &qname); if (!child) { - child = d_alloc(dir, &qname); - if (child) { + DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq); + child = d_alloc_parallel(dir, &qname, &wq); + if (IS_ERR(child)) + return false; + if (d_in_lookup(child)) { inode = proc_sys_make_inode(dir->d_sb, head, table); if (!inode) { + d_lookup_done(child); dput(child); return false; - } else { - d_set_d_op(child, &proc_sys_dentry_operations); - d_add(child, inode); } - } else { - return false; + d_set_d_op(child, &proc_sys_dentry_operations); + d_add(child, inode); } } inode = d_inode(child); @@ -789,7 +790,7 @@ static const struct file_operations proc_sys_file_operations = { static const struct file_operations proc_sys_dir_file_operations = { .read = generic_read_dir, - .iterate = proc_sys_readdir, + .iterate_shared = proc_sys_readdir, .llseek = generic_file_llseek, }; diff --git a/fs/proc/root.c b/fs/proc/root.c index 361ab4e..55bc7d6 100644 --- a/fs/proc/root.c +++ b/fs/proc/root.c @@ -226,8 +226,8 @@ static int proc_root_readdir(struct file *file, struct dir_context *ctx) */ static const struct file_operations proc_root_operations = { .read = generic_read_dir, - .iterate = proc_root_readdir, - .llseek = default_llseek, + .iterate_shared = proc_root_readdir, + .llseek = generic_file_llseek, }; /* diff --git a/fs/qnx4/dir.c b/fs/qnx4/dir.c index b218f96..781056a 100644 --- a/fs/qnx4/dir.c +++ b/fs/qnx4/dir.c @@ -71,7 +71,7 @@ const struct file_operations qnx4_dir_operations = { .llseek = generic_file_llseek, .read = generic_read_dir, - .iterate = qnx4_readdir, + .iterate_shared = qnx4_readdir, .fsync = generic_file_fsync, }; diff --git a/fs/qnx6/dir.c b/fs/qnx6/dir.c index 144ceda..27637e0 100644 --- a/fs/qnx6/dir.c +++ b/fs/qnx6/dir.c @@ -272,7 +272,7 @@ found: const struct file_operations qnx6_dir_operations = { .llseek = generic_file_llseek, .read = generic_read_dir, - .iterate = qnx6_readdir, + .iterate_shared = qnx6_readdir, .fsync = generic_file_fsync, }; diff --git a/fs/quota/netlink.c b/fs/quota/netlink.c index d07a2f9..8b25267 100644 --- a/fs/quota/netlink.c +++ b/fs/quota/netlink.c @@ -47,7 +47,7 @@ void quota_send_warning(struct kqid qid, dev_t dev, void *msg_head; int ret; int msg_size = 4 * nla_total_size(sizeof(u32)) + - 2 * nla_total_size(sizeof(u64)); + 2 * nla_total_size_64bit(sizeof(u64)); /* We have to allocate using GFP_NOFS as we are called from a * filesystem performing write and thus further recursion into @@ -68,8 +68,9 @@ void quota_send_warning(struct kqid qid, dev_t dev, ret = nla_put_u32(skb, QUOTA_NL_A_QTYPE, qid.type); if (ret) goto attr_err_out; - ret = nla_put_u64(skb, QUOTA_NL_A_EXCESS_ID, - from_kqid_munged(&init_user_ns, qid)); + ret = nla_put_u64_64bit(skb, QUOTA_NL_A_EXCESS_ID, + from_kqid_munged(&init_user_ns, qid), + QUOTA_NL_A_PAD); if (ret) goto attr_err_out; ret = nla_put_u32(skb, QUOTA_NL_A_WARNING, warntype); @@ -81,8 +82,9 @@ void quota_send_warning(struct kqid qid, dev_t dev, ret = nla_put_u32(skb, QUOTA_NL_A_DEV_MINOR, MINOR(dev)); if (ret) goto attr_err_out; - ret = nla_put_u64(skb, QUOTA_NL_A_CAUSED_ID, - from_kuid_munged(&init_user_ns, current_uid())); + ret = nla_put_u64_64bit(skb, QUOTA_NL_A_CAUSED_ID, + from_kuid_munged(&init_user_ns, current_uid()), + QUOTA_NL_A_PAD); if (ret) goto attr_err_out; genlmsg_end(skb, msg_head); diff --git a/fs/read_write.c b/fs/read_write.c index cf377cf..933b53a 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -302,18 +302,6 @@ loff_t vfs_llseek(struct file *file, loff_t offset, int whence) } EXPORT_SYMBOL(vfs_llseek); -static inline struct fd fdget_pos(int fd) -{ - return __to_fd(__fdget_pos(fd)); -} - -static inline void fdput_pos(struct fd f) -{ - if (f.flags & FDPUT_POS_UNLOCK) - mutex_unlock(&f.file->f_pos_lock); - fdput(f); -} - SYSCALL_DEFINE3(lseek, unsigned int, fd, off_t, offset, unsigned int, whence) { off_t retval; @@ -410,11 +398,6 @@ ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos) } EXPORT_SYMBOL(vfs_iter_write); -/* - * rw_verify_area doesn't like huge counts. We limit - * them to something that fits in "int" so that others - * won't have to do range checks all the time. - */ int rw_verify_area(int read_write, struct file *file, const loff_t *ppos, size_t count) { struct inode *inode; @@ -441,11 +424,8 @@ int rw_verify_area(int read_write, struct file *file, const loff_t *ppos, size_t if (retval < 0) return retval; } - retval = security_file_permission(file, + return security_file_permission(file, read_write == READ ? MAY_READ : MAY_WRITE); - if (retval) - return retval; - return count > MAX_RW_COUNT ? MAX_RW_COUNT : count; } static ssize_t new_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos) @@ -489,8 +469,9 @@ ssize_t vfs_read(struct file *file, char __user *buf, size_t count, loff_t *pos) return -EFAULT; ret = rw_verify_area(READ, file, pos, count); - if (ret >= 0) { - count = ret; + if (!ret) { + if (count > MAX_RW_COUNT) + count = MAX_RW_COUNT; ret = __vfs_read(file, buf, count, pos); if (ret > 0) { fsnotify_access(file); @@ -572,8 +553,9 @@ ssize_t vfs_write(struct file *file, const char __user *buf, size_t count, loff_ return -EFAULT; ret = rw_verify_area(WRITE, file, pos, count); - if (ret >= 0) { - count = ret; + if (!ret) { + if (count > MAX_RW_COUNT) + count = MAX_RW_COUNT; file_start_write(file); ret = __vfs_write(file, buf, count, pos); if (ret > 0) { @@ -698,12 +680,16 @@ static ssize_t do_iter_readv_writev(struct file *filp, struct iov_iter *iter, struct kiocb kiocb; ssize_t ret; - if (flags & ~RWF_HIPRI) + if (flags & ~(RWF_HIPRI | RWF_DSYNC | RWF_SYNC)) return -EOPNOTSUPP; init_sync_kiocb(&kiocb, filp); if (flags & RWF_HIPRI) kiocb.ki_flags |= IOCB_HIPRI; + if (flags & RWF_DSYNC) + kiocb.ki_flags |= IOCB_DSYNC; + if (flags & RWF_SYNC) + kiocb.ki_flags |= (IOCB_DSYNC | IOCB_SYNC); kiocb.ki_pos = *ppos; ret = fn(&kiocb, iter); @@ -1323,7 +1309,8 @@ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos, retval = rw_verify_area(READ, in.file, &pos, count); if (retval < 0) goto fput_in; - count = retval; + if (count > MAX_RW_COUNT) + count = MAX_RW_COUNT; /* * Get output file, and verify that it is ok.. @@ -1341,7 +1328,6 @@ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos, retval = rw_verify_area(WRITE, out.file, &out_pos, count); if (retval < 0) goto fput_out; - count = retval; if (!max) max = min(in_inode->i_sb->s_maxbytes, out_inode->i_sb->s_maxbytes); @@ -1485,11 +1471,12 @@ ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in, if (flags != 0) return -EINVAL; - /* copy_file_range allows full ssize_t len, ignoring MAX_RW_COUNT */ ret = rw_verify_area(READ, file_in, &pos_in, len); - if (ret >= 0) - ret = rw_verify_area(WRITE, file_out, &pos_out, len); - if (ret < 0) + if (unlikely(ret)) + return ret; + + ret = rw_verify_area(WRITE, file_out, &pos_out, len); + if (unlikely(ret)) return ret; if (!(file_in->f_mode & FMODE_READ) || diff --git a/fs/readdir.c b/fs/readdir.c index e69ef3b..a86c6c0 100644 --- a/fs/readdir.c +++ b/fs/readdir.c @@ -24,27 +24,40 @@ int iterate_dir(struct file *file, struct dir_context *ctx) { struct inode *inode = file_inode(file); + bool shared = false; int res = -ENOTDIR; - if (!file->f_op->iterate) + if (file->f_op->iterate_shared) + shared = true; + else if (!file->f_op->iterate) goto out; res = security_file_permission(file, MAY_READ); if (res) goto out; - res = mutex_lock_killable(&inode->i_mutex); - if (res) - goto out; + if (shared) + inode_lock_shared(inode); + else + inode_lock(inode); + // res = mutex_lock_killable(&inode->i_mutex); + // if (res) + // goto out; res = -ENOENT; if (!IS_DEADDIR(inode)) { ctx->pos = file->f_pos; - res = file->f_op->iterate(file, ctx); + if (shared) + res = file->f_op->iterate_shared(file, ctx); + else + res = file->f_op->iterate(file, ctx); file->f_pos = ctx->pos; fsnotify_access(file); file_accessed(file); } - inode_unlock(inode); + if (shared) + inode_unlock_shared(inode); + else + inode_unlock(inode); out: return res; } @@ -111,7 +124,7 @@ SYSCALL_DEFINE3(old_readdir, unsigned int, fd, struct old_linux_dirent __user *, dirent, unsigned int, count) { int error; - struct fd f = fdget(fd); + struct fd f = fdget_pos(fd); struct readdir_callback buf = { .ctx.actor = fillonedir, .dirent = dirent @@ -124,7 +137,7 @@ SYSCALL_DEFINE3(old_readdir, unsigned int, fd, if (buf.result) error = buf.result; - fdput(f); + fdput_pos(f); return error; } @@ -208,7 +221,7 @@ SYSCALL_DEFINE3(getdents, unsigned int, fd, if (!access_ok(VERIFY_WRITE, dirent, count)) return -EFAULT; - f = fdget(fd); + f = fdget_pos(fd); if (!f.file) return -EBADF; @@ -222,7 +235,7 @@ SYSCALL_DEFINE3(getdents, unsigned int, fd, else error = count - buf.count; } - fdput(f); + fdput_pos(f); return error; } @@ -289,7 +302,7 @@ SYSCALL_DEFINE3(getdents64, unsigned int, fd, if (!access_ok(VERIFY_WRITE, dirent, count)) return -EFAULT; - f = fdget(fd); + f = fdget_pos(fd); if (!f.file) return -EBADF; @@ -304,6 +317,6 @@ SYSCALL_DEFINE3(getdents64, unsigned int, fd, else error = count - buf.count; } - fdput(f); + fdput_pos(f); return error; } diff --git a/fs/reiserfs/dir.c b/fs/reiserfs/dir.c index 3abd400..45aa05e 100644 --- a/fs/reiserfs/dir.c +++ b/fs/reiserfs/dir.c @@ -20,7 +20,7 @@ static int reiserfs_dir_fsync(struct file *filp, loff_t start, loff_t end, const struct file_operations reiserfs_dir_operations = { .llseek = generic_file_llseek, .read = generic_read_dir, - .iterate = reiserfs_readdir, + .iterate_shared = reiserfs_readdir, .fsync = reiserfs_dir_fsync, .unlocked_ioctl = reiserfs_ioctl, #ifdef CONFIG_COMPAT diff --git a/fs/reiserfs/file.c b/fs/reiserfs/file.c index 3897737..90f815b 100644 --- a/fs/reiserfs/file.c +++ b/fs/reiserfs/file.c @@ -260,10 +260,10 @@ const struct file_operations reiserfs_file_operations = { const struct inode_operations reiserfs_file_inode_operations = { .setattr = reiserfs_setattr, - .setxattr = reiserfs_setxattr, - .getxattr = reiserfs_getxattr, + .setxattr = generic_setxattr, + .getxattr = generic_getxattr, .listxattr = reiserfs_listxattr, - .removexattr = reiserfs_removexattr, + .removexattr = generic_removexattr, .permission = reiserfs_permission, .get_acl = reiserfs_get_acl, .set_acl = reiserfs_set_acl, diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c index d5c2e9c..825455d 100644 --- a/fs/reiserfs/inode.c +++ b/fs/reiserfs/inode.c @@ -3279,15 +3279,14 @@ static int reiserfs_releasepage(struct page *page, gfp_t unused_gfp_flags) * We thank Mingming Cao for helping us understand in great detail what * to do in this section of the code. */ -static ssize_t reiserfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, - loff_t offset) +static ssize_t reiserfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; size_t count = iov_iter_count(iter); ssize_t ret; - ret = blockdev_direct_IO(iocb, inode, iter, offset, + ret = blockdev_direct_IO(iocb, inode, iter, reiserfs_get_blocks_direct_io); /* @@ -3296,7 +3295,7 @@ static ssize_t reiserfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, */ if (unlikely(iov_iter_rw(iter) == WRITE && ret < 0)) { loff_t isize = i_size_read(inode); - loff_t end = offset + count; + loff_t end = iocb->ki_pos + count; if ((end > isize) && inode_newsize_ok(inode, isize) == 0) { truncate_setsize(inode, isize); diff --git a/fs/reiserfs/ioctl.c b/fs/reiserfs/ioctl.c index 57045f4..2f1ddc9 100644 --- a/fs/reiserfs/ioctl.c +++ b/fs/reiserfs/ioctl.c @@ -187,7 +187,11 @@ int reiserfs_unpack(struct inode *inode, struct file *filp) } /* we need to make sure nobody is changing the file size beneath us */ - reiserfs_mutex_lock_safe(&inode->i_mutex, inode->i_sb); +{ + int depth = reiserfs_write_unlock_nested(inode->i_sb); + inode_lock(inode); + reiserfs_write_lock_nested(inode->i_sb, depth); +} reiserfs_write_lock(inode->i_sb); diff --git a/fs/reiserfs/namei.c b/fs/reiserfs/namei.c index 2a12d46..8a36696 100644 --- a/fs/reiserfs/namei.c +++ b/fs/reiserfs/namei.c @@ -1650,10 +1650,10 @@ const struct inode_operations reiserfs_dir_inode_operations = { .mknod = reiserfs_mknod, .rename = reiserfs_rename, .setattr = reiserfs_setattr, - .setxattr = reiserfs_setxattr, - .getxattr = reiserfs_getxattr, + .setxattr = generic_setxattr, + .getxattr = generic_getxattr, .listxattr = reiserfs_listxattr, - .removexattr = reiserfs_removexattr, + .removexattr = generic_removexattr, .permission = reiserfs_permission, .get_acl = reiserfs_get_acl, .set_acl = reiserfs_set_acl, @@ -1667,10 +1667,10 @@ const struct inode_operations reiserfs_symlink_inode_operations = { .readlink = generic_readlink, .get_link = page_get_link, .setattr = reiserfs_setattr, - .setxattr = reiserfs_setxattr, - .getxattr = reiserfs_getxattr, + .setxattr = generic_setxattr, + .getxattr = generic_getxattr, .listxattr = reiserfs_listxattr, - .removexattr = reiserfs_removexattr, + .removexattr = generic_removexattr, .permission = reiserfs_permission, }; @@ -1679,10 +1679,10 @@ const struct inode_operations reiserfs_symlink_inode_operations = { */ const struct inode_operations reiserfs_special_inode_operations = { .setattr = reiserfs_setattr, - .setxattr = reiserfs_setxattr, - .getxattr = reiserfs_getxattr, + .setxattr = generic_setxattr, + .getxattr = generic_getxattr, .listxattr = reiserfs_listxattr, - .removexattr = reiserfs_removexattr, + .removexattr = generic_removexattr, .permission = reiserfs_permission, .get_acl = reiserfs_get_acl, .set_acl = reiserfs_set_acl, diff --git a/fs/reiserfs/xattr.c b/fs/reiserfs/xattr.c index 28f5f8b..a33812a 100644 --- a/fs/reiserfs/xattr.c +++ b/fs/reiserfs/xattr.c @@ -764,60 +764,6 @@ find_xattr_handler_prefix(const struct xattr_handler **handlers, return xah; } - -/* - * Inode operation getxattr() - */ -ssize_t -reiserfs_getxattr(struct dentry * dentry, const char *name, void *buffer, - size_t size) -{ - const struct xattr_handler *handler; - - handler = find_xattr_handler_prefix(dentry->d_sb->s_xattr, name); - - if (!handler || get_inode_sd_version(d_inode(dentry)) == STAT_DATA_V1) - return -EOPNOTSUPP; - - return handler->get(handler, dentry, name, buffer, size); -} - -/* - * Inode operation setxattr() - * - * d_inode(dentry)->i_mutex down - */ -int -reiserfs_setxattr(struct dentry *dentry, const char *name, const void *value, - size_t size, int flags) -{ - const struct xattr_handler *handler; - - handler = find_xattr_handler_prefix(dentry->d_sb->s_xattr, name); - - if (!handler || get_inode_sd_version(d_inode(dentry)) == STAT_DATA_V1) - return -EOPNOTSUPP; - - return handler->set(handler, dentry, name, value, size, flags); -} - -/* - * Inode operation removexattr() - * - * d_inode(dentry)->i_mutex down - */ -int reiserfs_removexattr(struct dentry *dentry, const char *name) -{ - const struct xattr_handler *handler; - - handler = find_xattr_handler_prefix(dentry->d_sb->s_xattr, name); - - if (!handler || get_inode_sd_version(d_inode(dentry)) == STAT_DATA_V1) - return -EOPNOTSUPP; - - return handler->set(handler, dentry, name, NULL, 0, XATTR_REPLACE); -} - struct listxattr_buf { struct dir_context ctx; size_t size; diff --git a/fs/reiserfs/xattr.h b/fs/reiserfs/xattr.h index 15dde62..613ff5a 100644 --- a/fs/reiserfs/xattr.h +++ b/fs/reiserfs/xattr.h @@ -2,6 +2,7 @@ #include <linux/init.h> #include <linux/list.h> #include <linux/rwsem.h> +#include <linux/xattr.h> struct inode; struct dentry; @@ -18,12 +19,7 @@ int reiserfs_permission(struct inode *inode, int mask); #ifdef CONFIG_REISERFS_FS_XATTR #define has_xattr_dir(inode) (REISERFS_I(inode)->i_flags & i_has_xattr_dir) -ssize_t reiserfs_getxattr(struct dentry *dentry, const char *name, - void *buffer, size_t size); -int reiserfs_setxattr(struct dentry *dentry, const char *name, - const void *value, size_t size, int flags); ssize_t reiserfs_listxattr(struct dentry *dentry, char *buffer, size_t size); -int reiserfs_removexattr(struct dentry *dentry, const char *name); int reiserfs_xattr_get(struct inode *, const char *, void *, size_t); int reiserfs_xattr_set(struct inode *, const char *, const void *, size_t, int); @@ -92,10 +88,7 @@ static inline void reiserfs_init_xattr_rwsem(struct inode *inode) #else -#define reiserfs_getxattr NULL -#define reiserfs_setxattr NULL #define reiserfs_listxattr NULL -#define reiserfs_removexattr NULL static inline void reiserfs_init_xattr_rwsem(struct inode *inode) { diff --git a/fs/reiserfs/xattr_acl.c b/fs/reiserfs/xattr_acl.c index 558a16b..dbed42f 100644 --- a/fs/reiserfs/xattr_acl.c +++ b/fs/reiserfs/xattr_acl.c @@ -197,10 +197,8 @@ struct posix_acl *reiserfs_get_acl(struct inode *inode, int type) size = reiserfs_xattr_get(inode, name, NULL, 0); if (size < 0) { - if (size == -ENODATA || size == -ENOSYS) { - set_cached_acl(inode, type, NULL); + if (size == -ENODATA || size == -ENOSYS) return NULL; - } return ERR_PTR(size); } @@ -220,8 +218,6 @@ struct posix_acl *reiserfs_get_acl(struct inode *inode, int type) } else { acl = reiserfs_posix_acl_from_disk(value, retval); } - if (!IS_ERR(acl)) - set_cached_acl(inode, type, acl); kfree(value); return acl; @@ -370,7 +366,7 @@ int reiserfs_cache_default_acl(struct inode *inode) if (IS_PRIVATE(inode)) return 0; - acl = reiserfs_get_acl(inode, ACL_TYPE_DEFAULT); + acl = get_acl(inode, ACL_TYPE_DEFAULT); if (acl && !IS_ERR(acl)) { int size = reiserfs_acl_size(acl->a_count); diff --git a/fs/reiserfs/xattr_security.c b/fs/reiserfs/xattr_security.c index ab0217d..86aeb9d 100644 --- a/fs/reiserfs/xattr_security.c +++ b/fs/reiserfs/xattr_security.c @@ -9,29 +9,26 @@ #include <linux/uaccess.h> static int -security_get(const struct xattr_handler *handler, struct dentry *dentry, - const char *name, void *buffer, size_t size) +security_get(const struct xattr_handler *handler, struct dentry *unused, + struct inode *inode, const char *name, void *buffer, size_t size) { - if (strlen(name) < sizeof(XATTR_SECURITY_PREFIX)) - return -EINVAL; - - if (IS_PRIVATE(d_inode(dentry))) + if (IS_PRIVATE(inode)) return -EPERM; - return reiserfs_xattr_get(d_inode(dentry), name, buffer, size); + return reiserfs_xattr_get(inode, xattr_full_name(handler, name), + buffer, size); } static int security_set(const struct xattr_handler *handler, struct dentry *dentry, const char *name, const void *buffer, size_t size, int flags) { - if (strlen(name) < sizeof(XATTR_SECURITY_PREFIX)) - return -EINVAL; - if (IS_PRIVATE(d_inode(dentry))) return -EPERM; - return reiserfs_xattr_set(d_inode(dentry), name, buffer, size, flags); + return reiserfs_xattr_set(d_inode(dentry), + xattr_full_name(handler, name), + buffer, size, flags); } static bool security_list(struct dentry *dentry) diff --git a/fs/reiserfs/xattr_trusted.c b/fs/reiserfs/xattr_trusted.c index 64b67aa..31837f0 100644 --- a/fs/reiserfs/xattr_trusted.c +++ b/fs/reiserfs/xattr_trusted.c @@ -8,29 +8,26 @@ #include <linux/uaccess.h> static int -trusted_get(const struct xattr_handler *handler, struct dentry *dentry, - const char *name, void *buffer, size_t size) +trusted_get(const struct xattr_handler *handler, struct dentry *unused, + struct inode *inode, const char *name, void *buffer, size_t size) { - if (strlen(name) < sizeof(XATTR_TRUSTED_PREFIX)) - return -EINVAL; - - if (!capable(CAP_SYS_ADMIN) || IS_PRIVATE(d_inode(dentry))) + if (!capable(CAP_SYS_ADMIN) || IS_PRIVATE(inode)) return -EPERM; - return reiserfs_xattr_get(d_inode(dentry), name, buffer, size); + return reiserfs_xattr_get(inode, xattr_full_name(handler, name), + buffer, size); } static int trusted_set(const struct xattr_handler *handler, struct dentry *dentry, const char *name, const void *buffer, size_t size, int flags) { - if (strlen(name) < sizeof(XATTR_TRUSTED_PREFIX)) - return -EINVAL; - if (!capable(CAP_SYS_ADMIN) || IS_PRIVATE(d_inode(dentry))) return -EPERM; - return reiserfs_xattr_set(d_inode(dentry), name, buffer, size, flags); + return reiserfs_xattr_set(d_inode(dentry), + xattr_full_name(handler, name), + buffer, size, flags); } static bool trusted_list(struct dentry *dentry) diff --git a/fs/reiserfs/xattr_user.c b/fs/reiserfs/xattr_user.c index 12e6306..f7c3973 100644 --- a/fs/reiserfs/xattr_user.c +++ b/fs/reiserfs/xattr_user.c @@ -7,27 +7,24 @@ #include <linux/uaccess.h> static int -user_get(const struct xattr_handler *handler, struct dentry *dentry, - const char *name, void *buffer, size_t size) +user_get(const struct xattr_handler *handler, struct dentry *unused, + struct inode *inode, const char *name, void *buffer, size_t size) { - - if (strlen(name) < sizeof(XATTR_USER_PREFIX)) - return -EINVAL; - if (!reiserfs_xattrs_user(dentry->d_sb)) + if (!reiserfs_xattrs_user(inode->i_sb)) return -EOPNOTSUPP; - return reiserfs_xattr_get(d_inode(dentry), name, buffer, size); + return reiserfs_xattr_get(inode, xattr_full_name(handler, name), + buffer, size); } static int user_set(const struct xattr_handler *handler, struct dentry *dentry, const char *name, const void *buffer, size_t size, int flags) { - if (strlen(name) < sizeof(XATTR_USER_PREFIX)) - return -EINVAL; - if (!reiserfs_xattrs_user(dentry->d_sb)) return -EOPNOTSUPP; - return reiserfs_xattr_set(d_inode(dentry), name, buffer, size, flags); + return reiserfs_xattr_set(d_inode(dentry), + xattr_full_name(handler, name), + buffer, size, flags); } static bool user_list(struct dentry *dentry) diff --git a/fs/romfs/super.c b/fs/romfs/super.c index 6b00ca3..d0f8a38 100644 --- a/fs/romfs/super.c +++ b/fs/romfs/super.c @@ -280,8 +280,8 @@ error: static const struct file_operations romfs_dir_operations = { .read = generic_read_dir, - .iterate = romfs_readdir, - .llseek = default_llseek, + .iterate_shared = romfs_readdir, + .llseek = generic_file_llseek, }; static const struct inode_operations romfs_dir_inode_operations = { diff --git a/fs/splice.c b/fs/splice.c index b018eb4..dd9bf7e 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -1143,6 +1143,9 @@ static long do_splice_to(struct file *in, loff_t *ppos, if (unlikely(ret < 0)) return ret; + if (unlikely(len > MAX_RW_COUNT)) + len = MAX_RW_COUNT; + if (in->f_op->splice_read) splice_read = in->f_op->splice_read; else diff --git a/fs/squashfs/dir.c b/fs/squashfs/dir.c index d8c2d74..a5845f9 100644 --- a/fs/squashfs/dir.c +++ b/fs/squashfs/dir.c @@ -231,6 +231,6 @@ failed_read: const struct file_operations squashfs_dir_ops = { .read = generic_read_dir, - .iterate = squashfs_readdir, - .llseek = default_llseek, + .iterate_shared = squashfs_readdir, + .llseek = generic_file_llseek, }; diff --git a/fs/squashfs/xattr.c b/fs/squashfs/xattr.c index 1e9de96..1548b37 100644 --- a/fs/squashfs/xattr.c +++ b/fs/squashfs/xattr.c @@ -214,10 +214,12 @@ failed: static int squashfs_xattr_handler_get(const struct xattr_handler *handler, - struct dentry *d, const char *name, + struct dentry *unused, + struct inode *inode, + const char *name, void *buffer, size_t size) { - return squashfs_xattr_get(d_inode(d), handler->flags, name, + return squashfs_xattr_get(inode, handler->flags, name, buffer, size); } @@ -285,7 +285,7 @@ static void put_super(struct super_block *sb) * deactivate_locked_super - drop an active reference to superblock * @s: superblock to deactivate * - * Drops an active reference to superblock, converting it into a temprory + * Drops an active reference to superblock, converting it into a temporary * one if there is no other active references left. In that case we * tell fs driver to shut it down and drop the temporary reference we * had just acquired. diff --git a/fs/sysv/dir.c b/fs/sysv/dir.c index c0f0a3e..2661b77 100644 --- a/fs/sysv/dir.c +++ b/fs/sysv/dir.c @@ -23,7 +23,7 @@ static int sysv_readdir(struct file *, struct dir_context *); const struct file_operations sysv_dir_operations = { .llseek = generic_file_llseek, .read = generic_read_dir, - .iterate = sysv_readdir, + .iterate_shared = sysv_readdir, .fsync = generic_file_fsync, }; diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c index 795992a..4b86d3a 100644 --- a/fs/ubifs/dir.c +++ b/fs/ubifs/dir.c @@ -1182,10 +1182,10 @@ const struct inode_operations ubifs_dir_inode_operations = { .rename = ubifs_rename, .setattr = ubifs_setattr, .getattr = ubifs_getattr, - .setxattr = ubifs_setxattr, - .getxattr = ubifs_getxattr, + .setxattr = generic_setxattr, + .getxattr = generic_getxattr, .listxattr = ubifs_listxattr, - .removexattr = ubifs_removexattr, + .removexattr = generic_removexattr, #ifdef CONFIG_UBIFS_ATIME_SUPPORT .update_time = ubifs_update_time, #endif @@ -1195,7 +1195,7 @@ const struct file_operations ubifs_dir_operations = { .llseek = generic_file_llseek, .release = ubifs_dir_release, .read = generic_read_dir, - .iterate = ubifs_readdir, + .iterate_shared = ubifs_readdir, .fsync = ubifs_fsync, .unlocked_ioctl = ubifs_ioctl, #ifdef CONFIG_COMPAT diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c index 446753d..0831697 100644 --- a/fs/ubifs/file.c +++ b/fs/ubifs/file.c @@ -1597,10 +1597,10 @@ const struct address_space_operations ubifs_file_address_operations = { const struct inode_operations ubifs_file_inode_operations = { .setattr = ubifs_setattr, .getattr = ubifs_getattr, - .setxattr = ubifs_setxattr, - .getxattr = ubifs_getxattr, + .setxattr = generic_setxattr, + .getxattr = generic_getxattr, .listxattr = ubifs_listxattr, - .removexattr = ubifs_removexattr, + .removexattr = generic_removexattr, #ifdef CONFIG_UBIFS_ATIME_SUPPORT .update_time = ubifs_update_time, #endif @@ -1611,10 +1611,10 @@ const struct inode_operations ubifs_symlink_inode_operations = { .get_link = simple_get_link, .setattr = ubifs_setattr, .getattr = ubifs_getattr, - .setxattr = ubifs_setxattr, - .getxattr = ubifs_getxattr, + .setxattr = generic_setxattr, + .getxattr = generic_getxattr, .listxattr = ubifs_listxattr, - .removexattr = ubifs_removexattr, + .removexattr = generic_removexattr, #ifdef CONFIG_UBIFS_ATIME_SUPPORT .update_time = ubifs_update_time, #endif diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index e98c24e..7034995 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -2040,6 +2040,7 @@ static int ubifs_fill_super(struct super_block *sb, void *data, int silent) if (c->max_inode_sz > MAX_LFS_FILESIZE) sb->s_maxbytes = c->max_inode_sz = MAX_LFS_FILESIZE; sb->s_op = &ubifs_super_operations; + sb->s_xattr = ubifs_xattr_handlers; mutex_lock(&c->umount_mutex); err = mount_ubifs(c); diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h index 4cd7e56..ddf9f6b9 100644 --- a/fs/ubifs/ubifs.h +++ b/fs/ubifs/ubifs.h @@ -37,6 +37,7 @@ #include <linux/pagemap.h> #include <linux/backing-dev.h> #include <linux/security.h> +#include <linux/xattr.h> #include "ubifs-media.h" /* Version of this UBIFS implementation */ @@ -1732,12 +1733,8 @@ int ubifs_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat); /* xattr.c */ -int ubifs_setxattr(struct dentry *dentry, const char *name, - const void *value, size_t size, int flags); -ssize_t ubifs_getxattr(struct dentry *dentry, const char *name, void *buf, - size_t size); +extern const struct xattr_handler *ubifs_xattr_handlers[]; ssize_t ubifs_listxattr(struct dentry *dentry, char *buffer, size_t size); -int ubifs_removexattr(struct dentry *dentry, const char *name); int ubifs_init_security(struct inode *dentry, struct inode *inode, const struct qstr *qstr); diff --git a/fs/ubifs/xattr.c b/fs/ubifs/xattr.c index b043e04..6c277eb 100644 --- a/fs/ubifs/xattr.c +++ b/fs/ubifs/xattr.c @@ -249,42 +249,6 @@ out_free: return err; } -/** - * check_namespace - check extended attribute name-space. - * @nm: extended attribute name - * - * This function makes sure the extended attribute name belongs to one of the - * supported extended attribute name-spaces. Returns name-space index in case - * of success and a negative error code in case of failure. - */ -static int check_namespace(const struct qstr *nm) -{ - int type; - - if (nm->len > UBIFS_MAX_NLEN) - return -ENAMETOOLONG; - - if (!strncmp(nm->name, XATTR_TRUSTED_PREFIX, - XATTR_TRUSTED_PREFIX_LEN)) { - if (nm->name[XATTR_TRUSTED_PREFIX_LEN] == '\0') - return -EINVAL; - type = TRUSTED_XATTR; - } else if (!strncmp(nm->name, XATTR_USER_PREFIX, - XATTR_USER_PREFIX_LEN)) { - if (nm->name[XATTR_USER_PREFIX_LEN] == '\0') - return -EINVAL; - type = USER_XATTR; - } else if (!strncmp(nm->name, XATTR_SECURITY_PREFIX, - XATTR_SECURITY_PREFIX_LEN)) { - if (nm->name[XATTR_SECURITY_PREFIX_LEN] == '\0') - return -EINVAL; - type = SECURITY_XATTR; - } else - return -EOPNOTSUPP; - - return type; -} - static struct inode *iget_xattr(struct ubifs_info *c, ino_t inum) { struct inode *inode; @@ -302,24 +266,23 @@ static struct inode *iget_xattr(struct ubifs_info *c, ino_t inum) return ERR_PTR(-EINVAL); } -static int setxattr(struct inode *host, const char *name, const void *value, - size_t size, int flags) +static int __ubifs_setxattr(struct inode *host, const char *name, + const void *value, size_t size, int flags) { struct inode *inode; struct ubifs_info *c = host->i_sb->s_fs_info; struct qstr nm = QSTR_INIT(name, strlen(name)); struct ubifs_dent_node *xent; union ubifs_key key; - int err, type; + int err; ubifs_assert(inode_is_locked(host)); if (size > UBIFS_MAX_INO_DATA) return -ERANGE; - type = check_namespace(&nm); - if (type < 0) - return type; + if (nm.len > UBIFS_MAX_NLEN) + return -ENAMETOOLONG; xent = kmalloc(UBIFS_MAX_XENT_NODE_SZ, GFP_NOFS); if (!xent) @@ -363,19 +326,10 @@ out_free: return err; } -int ubifs_setxattr(struct dentry *dentry, const char *name, - const void *value, size_t size, int flags) +static ssize_t __ubifs_getxattr(struct inode *host, const char *name, + void *buf, size_t size) { - dbg_gen("xattr '%s', host ino %lu ('%pd'), size %zd", - name, d_inode(dentry)->i_ino, dentry, size); - - return setxattr(d_inode(dentry), name, value, size, flags); -} - -ssize_t ubifs_getxattr(struct dentry *dentry, const char *name, void *buf, - size_t size) -{ - struct inode *inode, *host = d_inode(dentry); + struct inode *inode; struct ubifs_info *c = host->i_sb->s_fs_info; struct qstr nm = QSTR_INIT(name, strlen(name)); struct ubifs_inode *ui; @@ -383,12 +337,8 @@ ssize_t ubifs_getxattr(struct dentry *dentry, const char *name, void *buf, union ubifs_key key; int err; - dbg_gen("xattr '%s', ino %lu ('%pd'), buf size %zd", name, - host->i_ino, dentry, size); - - err = check_namespace(&nm); - if (err < 0) - return err; + if (nm.len > UBIFS_MAX_NLEN) + return -ENAMETOOLONG; xent = kmalloc(UBIFS_MAX_XENT_NODE_SZ, GFP_NOFS); if (!xent) @@ -460,8 +410,6 @@ ssize_t ubifs_listxattr(struct dentry *dentry, char *buffer, size_t size) lowest_xent_key(c, &key, host->i_ino); while (1) { - int type; - xent = ubifs_tnc_next_ent(c, &key, &nm); if (IS_ERR(xent)) { err = PTR_ERR(xent); @@ -471,14 +419,10 @@ ssize_t ubifs_listxattr(struct dentry *dentry, char *buffer, size_t size) nm.name = xent->name; nm.len = le16_to_cpu(xent->nlen); - type = check_namespace(&nm); - if (unlikely(type < 0)) { - err = type; - break; - } - /* Show trusted namespace only for "power" users */ - if (type != TRUSTED_XATTR || capable(CAP_SYS_ADMIN)) { + if (strncmp(xent->name, XATTR_TRUSTED_PREFIX, + XATTR_TRUSTED_PREFIX_LEN) || + capable(CAP_SYS_ADMIN)) { memcpy(buffer + written, nm.name, nm.len + 1); written += nm.len + 1; } @@ -538,22 +482,19 @@ out_cancel: return err; } -int ubifs_removexattr(struct dentry *dentry, const char *name) +static int __ubifs_removexattr(struct inode *host, const char *name) { - struct inode *inode, *host = d_inode(dentry); + struct inode *inode; struct ubifs_info *c = host->i_sb->s_fs_info; struct qstr nm = QSTR_INIT(name, strlen(name)); struct ubifs_dent_node *xent; union ubifs_key key; int err; - dbg_gen("xattr '%s', ino %lu ('%pd')", name, - host->i_ino, dentry); ubifs_assert(inode_is_locked(host)); - err = check_namespace(&nm); - if (err < 0) - return err; + if (nm.len > UBIFS_MAX_NLEN) + return -ENAMETOOLONG; xent = kmalloc(UBIFS_MAX_XENT_NODE_SZ, GFP_NOFS); if (!xent) @@ -603,7 +544,7 @@ static int init_xattrs(struct inode *inode, const struct xattr *xattr_array, } strcpy(name, XATTR_SECURITY_PREFIX); strcpy(name + XATTR_SECURITY_PREFIX_LEN, xattr->name); - err = setxattr(inode, name, xattr->value, xattr->value_len, 0); + err = __ubifs_setxattr(inode, name, xattr->value, xattr->value_len, 0); kfree(name); if (err < 0) break; @@ -626,3 +567,53 @@ int ubifs_init_security(struct inode *dentry, struct inode *inode, } return err; } + +static int ubifs_xattr_get(const struct xattr_handler *handler, + struct dentry *dentry, struct inode *inode, + const char *name, void *buffer, size_t size) +{ + dbg_gen("xattr '%s', ino %lu ('%pd'), buf size %zd", name, + inode->i_ino, dentry, size); + + return __ubifs_getxattr(inode, name, buffer, size); +} + +static int ubifs_xattr_set(const struct xattr_handler *handler, + struct dentry *dentry, const char *name, + const void *value, size_t size, int flags) +{ + struct inode *inode = d_inode(dentry); + + dbg_gen("xattr '%s', host ino %lu ('%pd'), size %zd", + name, inode->i_ino, dentry, size); + + if (value) + return __ubifs_setxattr(inode, name, value, size, flags); + else + return __ubifs_removexattr(inode, name); +} + +const struct xattr_handler ubifs_user_xattr_handler = { + .prefix = XATTR_USER_PREFIX, + .get = ubifs_xattr_get, + .set = ubifs_xattr_set, +}; + +const struct xattr_handler ubifs_trusted_xattr_handler = { + .prefix = XATTR_TRUSTED_PREFIX, + .get = ubifs_xattr_get, + .set = ubifs_xattr_set, +}; + +const struct xattr_handler ubifs_security_xattr_handler = { + .prefix = XATTR_SECURITY_PREFIX, + .get = ubifs_xattr_get, + .set = ubifs_xattr_set, +}; + +const struct xattr_handler *ubifs_xattr_handlers[] = { + &ubifs_user_xattr_handler, + &ubifs_trusted_xattr_handler, + &ubifs_security_xattr_handler, + NULL +}; diff --git a/fs/udf/dir.c b/fs/udf/dir.c index b51b371..4c5593a 100644 --- a/fs/udf/dir.c +++ b/fs/udf/dir.c @@ -202,7 +202,7 @@ out: const struct file_operations udf_dir_operations = { .llseek = generic_file_llseek, .read = generic_read_dir, - .iterate = udf_readdir, + .iterate_shared = udf_readdir, .unlocked_ioctl = udf_ioctl, .fsync = generic_file_fsync, }; diff --git a/fs/udf/file.c b/fs/udf/file.c index 877ba1c..6325706 100644 --- a/fs/udf/file.c +++ b/fs/udf/file.c @@ -99,8 +99,7 @@ static int udf_adinicb_write_begin(struct file *file, return 0; } -static ssize_t udf_adinicb_direct_IO(struct kiocb *iocb, struct iov_iter *iter, - loff_t offset) +static ssize_t udf_adinicb_direct_IO(struct kiocb *iocb, struct iov_iter *iter) { /* Fallback to buffered I/O. */ return 0; @@ -153,9 +152,7 @@ out: if (retval > 0) { mark_inode_dirty(inode); - err = generic_write_sync(file, iocb->ki_pos - retval, retval); - if (err < 0) - retval = err; + retval = generic_write_sync(iocb, retval); } return retval; diff --git a/fs/udf/inode.c b/fs/udf/inode.c index 2dc461e..f323aff 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -214,8 +214,7 @@ static int udf_write_begin(struct file *file, struct address_space *mapping, return ret; } -static ssize_t udf_direct_IO(struct kiocb *iocb, struct iov_iter *iter, - loff_t offset) +static ssize_t udf_direct_IO(struct kiocb *iocb, struct iov_iter *iter) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; @@ -223,9 +222,9 @@ static ssize_t udf_direct_IO(struct kiocb *iocb, struct iov_iter *iter, size_t count = iov_iter_count(iter); ssize_t ret; - ret = blockdev_direct_IO(iocb, inode, iter, offset, udf_get_block); + ret = blockdev_direct_IO(iocb, inode, iter, udf_get_block); if (unlikely(ret < 0 && iov_iter_rw(iter) == WRITE)) - udf_write_failed(mapping, offset + count); + udf_write_failed(mapping, iocb->ki_pos + count); return ret; } diff --git a/fs/udf/namei.c b/fs/udf/namei.c index a2ba11e..c3e5c96 100644 --- a/fs/udf/namei.c +++ b/fs/udf/namei.c @@ -1250,7 +1250,7 @@ static struct dentry *udf_get_parent(struct dentry *child) brelse(fibh.sbh); tloc = lelb_to_cpu(cfi.icb.extLocation); - inode = udf_iget(d_inode(child)->i_sb, &tloc); + inode = udf_iget(child->d_sb, &tloc); if (IS_ERR(inode)) return ERR_CAST(inode); diff --git a/fs/udf/super.c b/fs/udf/super.c index 36661ac..5e2c8c8 100644 --- a/fs/udf/super.c +++ b/fs/udf/super.c @@ -78,6 +78,15 @@ #define VSD_FIRST_SECTOR_OFFSET 32768 #define VSD_MAX_SECTOR_OFFSET 0x800000 +/* + * Maximum number of Terminating Descriptor / Logical Volume Integrity + * Descriptor redirections. The chosen numbers are arbitrary - just that we + * hopefully don't limit any real use of rewritten inode on write-once media + * but avoid looping for too long on corrupted media. + */ +#define UDF_MAX_TD_NESTING 64 +#define UDF_MAX_LVID_NESTING 1000 + enum { UDF_MAX_LINKS = 0xffff }; /* These are the "meat" - everything else is stuffing */ @@ -1541,42 +1550,52 @@ out_bh: } /* - * udf_load_logicalvolint - * + * Find the prevailing Logical Volume Integrity Descriptor. */ static void udf_load_logicalvolint(struct super_block *sb, struct kernel_extent_ad loc) { - struct buffer_head *bh = NULL; + struct buffer_head *bh, *final_bh; uint16_t ident; struct udf_sb_info *sbi = UDF_SB(sb); struct logicalVolIntegrityDesc *lvid; + int indirections = 0; + + while (++indirections <= UDF_MAX_LVID_NESTING) { + final_bh = NULL; + while (loc.extLength > 0 && + (bh = udf_read_tagged(sb, loc.extLocation, + loc.extLocation, &ident))) { + if (ident != TAG_IDENT_LVID) { + brelse(bh); + break; + } + + brelse(final_bh); + final_bh = bh; - while (loc.extLength > 0 && - (bh = udf_read_tagged(sb, loc.extLocation, - loc.extLocation, &ident)) && - ident == TAG_IDENT_LVID) { - sbi->s_lvid_bh = bh; - lvid = (struct logicalVolIntegrityDesc *)bh->b_data; + loc.extLength -= sb->s_blocksize; + loc.extLocation++; + } - if (lvid->nextIntegrityExt.extLength) - udf_load_logicalvolint(sb, - leea_to_cpu(lvid->nextIntegrityExt)); + if (!final_bh) + return; - if (sbi->s_lvid_bh != bh) - brelse(bh); - loc.extLength -= sb->s_blocksize; - loc.extLocation++; + brelse(sbi->s_lvid_bh); + sbi->s_lvid_bh = final_bh; + + lvid = (struct logicalVolIntegrityDesc *)final_bh->b_data; + if (lvid->nextIntegrityExt.extLength == 0) + return; + + loc = leea_to_cpu(lvid->nextIntegrityExt); } - if (sbi->s_lvid_bh != bh) - brelse(bh); + + udf_warn(sb, "Too many LVID indirections (max %u), ignoring.\n", + UDF_MAX_LVID_NESTING); + brelse(sbi->s_lvid_bh); + sbi->s_lvid_bh = NULL; } -/* - * Maximum number of Terminating Descriptor redirections. The chosen number is - * arbitrary - just that we hopefully don't limit any real use of rewritten - * inode on write-once media but avoid looping for too long on corrupted media. - */ -#define UDF_MAX_TD_NESTING 64 /* * Process a main/reserve volume descriptor sequence. diff --git a/fs/udf/udf_sb.h b/fs/udf/udf_sb.h index 1f32c7b..27b5335 100644 --- a/fs/udf/udf_sb.h +++ b/fs/udf/udf_sb.h @@ -3,9 +3,7 @@ #include <linux/mutex.h> #include <linux/bitops.h> - -/* Since UDF 2.01 is ISO 13346 based... */ -#define UDF_SUPER_MAGIC 0x15013346 +#include <linux/magic.h> #define UDF_MAX_READ_VERSION 0x0250 #define UDF_MAX_WRITE_VERSION 0x0201 diff --git a/fs/ufs/dir.c b/fs/ufs/dir.c index 0b14572..57dcced 100644 --- a/fs/ufs/dir.c +++ b/fs/ufs/dir.c @@ -105,7 +105,7 @@ void ufs_set_link(struct inode *dir, struct ufs_dir_entry *de, } -static void ufs_check_page(struct page *page) +static bool ufs_check_page(struct page *page) { struct inode *dir = page->mapping->host; struct super_block *sb = dir->i_sb; @@ -143,7 +143,7 @@ static void ufs_check_page(struct page *page) goto Eend; out: SetPageChecked(page); - return; + return true; /* Too bad, we had an error */ @@ -180,8 +180,8 @@ Eend: "offset=%lu", dir->i_ino, (page->index<<PAGE_SHIFT)+offs); fail: - SetPageChecked(page); SetPageError(page); + return false; } static struct page *ufs_get_page(struct inode *dir, unsigned long n) @@ -190,10 +190,10 @@ static struct page *ufs_get_page(struct inode *dir, unsigned long n) struct page *page = read_mapping_page(mapping, n, NULL); if (!IS_ERR(page)) { kmap(page); - if (!PageChecked(page)) - ufs_check_page(page); - if (PageError(page)) - goto fail; + if (unlikely(!PageChecked(page))) { + if (PageError(page) || !ufs_check_page(page)) + goto fail; + } } return page; @@ -653,7 +653,7 @@ not_empty: const struct file_operations ufs_dir_operations = { .read = generic_read_dir, - .iterate = ufs_readdir, + .iterate_shared = ufs_readdir, .fsync = generic_file_fsync, .llseek = generic_file_llseek, }; diff --git a/fs/ufs/super.c b/fs/ufs/super.c index 442fd52..f04ab23 100644 --- a/fs/ufs/super.c +++ b/fs/ufs/super.c @@ -132,7 +132,7 @@ static struct dentry *ufs_get_parent(struct dentry *child) ino = ufs_inode_by_name(d_inode(child), &dot_dot); if (!ino) return ERR_PTR(-ENOENT); - return d_obtain_alias(ufs_iget(d_inode(child)->i_sb, ino)); + return d_obtain_alias(ufs_iget(child->d_sb, ino)); } static const struct export_operations ufs_export_ops = { @@ -192,7 +192,7 @@ vfs_getxattr_alloc(struct dentry *dentry, const char *name, char **xattr_value, if (!inode->i_op->getxattr) return -EOPNOTSUPP; - error = inode->i_op->getxattr(dentry, name, NULL, 0); + error = inode->i_op->getxattr(dentry, inode, name, NULL, 0); if (error < 0) return error; @@ -203,7 +203,7 @@ vfs_getxattr_alloc(struct dentry *dentry, const char *name, char **xattr_value, memset(value, 0, error + 1); } - error = inode->i_op->getxattr(dentry, name, value, error); + error = inode->i_op->getxattr(dentry, inode, name, value, error); *xattr_value = value; return error; } @@ -236,7 +236,7 @@ vfs_getxattr(struct dentry *dentry, const char *name, void *value, size_t size) } nolsm: if (inode->i_op->getxattr) - error = inode->i_op->getxattr(dentry, name, value, size); + error = inode->i_op->getxattr(dentry, inode, name, value, size); else error = -EOPNOTSUPP; @@ -691,14 +691,16 @@ xattr_resolve_name(const struct xattr_handler **handlers, const char **name) * Find the handler for the prefix and dispatch its get() operation. */ ssize_t -generic_getxattr(struct dentry *dentry, const char *name, void *buffer, size_t size) +generic_getxattr(struct dentry *dentry, struct inode *inode, + const char *name, void *buffer, size_t size) { const struct xattr_handler *handler; handler = xattr_resolve_name(dentry->d_sb->s_xattr, &name); if (IS_ERR(handler)) return PTR_ERR(handler); - return handler->get(handler, dentry, name, buffer, size); + return handler->get(handler, dentry, inode, + name, buffer, size); } /* diff --git a/fs/xfs/xfs_acl.c b/fs/xfs/xfs_acl.c index 2d5df1f..b6e527b 100644 --- a/fs/xfs/xfs_acl.c +++ b/fs/xfs/xfs_acl.c @@ -158,22 +158,14 @@ xfs_get_acl(struct inode *inode, int type) if (error) { /* * If the attribute doesn't exist make sure we have a negative - * cache entry, for any other error assume it is transient and - * leave the cache entry as ACL_NOT_CACHED. + * cache entry, for any other error assume it is transient. */ - if (error == -ENOATTR) - goto out_update_cache; - acl = ERR_PTR(error); - goto out; + if (error != -ENOATTR) + acl = ERR_PTR(error); + } else { + acl = xfs_acl_from_disk(xfs_acl, len, + XFS_ACL_MAX_ENTRIES(ip->i_mount)); } - - acl = xfs_acl_from_disk(xfs_acl, len, XFS_ACL_MAX_ENTRIES(ip->i_mount)); - if (IS_ERR(acl)) - goto out; - -out_update_cache: - set_cached_acl(inode, type, acl); -out: kmem_free(xfs_acl); return acl; } diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index e49b240..c535887 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -1406,8 +1406,7 @@ xfs_end_io_direct_write( STATIC ssize_t xfs_vm_direct_IO( struct kiocb *iocb, - struct iov_iter *iter, - loff_t offset) + struct iov_iter *iter) { struct inode *inode = iocb->ki_filp->f_mapping->host; dio_iodone_t *endio = NULL; @@ -1420,12 +1419,12 @@ xfs_vm_direct_IO( } if (IS_DAX(inode)) { - return dax_do_io(iocb, inode, iter, offset, + return dax_do_io(iocb, inode, iter, xfs_get_blocks_direct, endio, 0); } bdev = xfs_find_bdev_for_inode(inode); - return __blockdev_direct_IO(iocb, inode, bdev, iter, offset, + return __blockdev_direct_IO(iocb, inode, bdev, iter, xfs_get_blocks_direct, endio, NULL, flags); } diff --git a/fs/xfs/xfs_dir2_readdir.c b/fs/xfs/xfs_dir2_readdir.c index 93b3ab0..f44f799 100644 --- a/fs/xfs/xfs_dir2_readdir.c +++ b/fs/xfs/xfs_dir2_readdir.c @@ -273,10 +273,11 @@ xfs_dir2_leaf_readbuf( size_t bufsize, struct xfs_dir2_leaf_map_info *mip, xfs_dir2_off_t *curoff, - struct xfs_buf **bpp) + struct xfs_buf **bpp, + bool trim_map) { struct xfs_inode *dp = args->dp; - struct xfs_buf *bp = *bpp; + struct xfs_buf *bp = NULL; struct xfs_bmbt_irec *map = mip->map; struct blk_plug plug; int error = 0; @@ -286,13 +287,10 @@ xfs_dir2_leaf_readbuf( struct xfs_da_geometry *geo = args->geo; /* - * If we have a buffer, we need to release it and - * take it out of the mapping. + * If the caller just finished processing a buffer, it will tell us + * we need to trim that block out of the mapping now it is done. */ - - if (bp) { - xfs_trans_brelse(NULL, bp); - bp = NULL; + if (trim_map) { mip->map_blocks -= geo->fsbcount; /* * Loop to get rid of the extents for the @@ -533,10 +531,17 @@ xfs_dir2_leaf_getdents( */ if (!bp || ptr >= (char *)bp->b_addr + geo->blksize) { int lock_mode; + bool trim_map = false; + + if (bp) { + xfs_trans_brelse(NULL, bp); + bp = NULL; + trim_map = true; + } lock_mode = xfs_ilock_data_map_shared(dp); error = xfs_dir2_leaf_readbuf(args, bufsize, map_info, - &curoff, &bp); + &curoff, &bp, trim_map); xfs_iunlock(dp, lock_mode); if (error || !map_info->map_valid) break; diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 569938a..85ce303 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -718,18 +718,19 @@ xfs_file_dio_aio_write( int unaligned_io = 0; int iolock; size_t count = iov_iter_count(from); - loff_t pos = iocb->ki_pos; loff_t end; struct iov_iter data; struct xfs_buftarg *target = XFS_IS_REALTIME_INODE(ip) ? mp->m_rtdev_targp : mp->m_ddev_targp; /* DIO must be aligned to device logical sector size */ - if (!IS_DAX(inode) && ((pos | count) & target->bt_logical_sectormask)) + if (!IS_DAX(inode) && + ((iocb->ki_pos | count) & target->bt_logical_sectormask)) return -EINVAL; /* "unaligned" here means not aligned to a filesystem block */ - if ((pos & mp->m_blockmask) || ((pos + count) & mp->m_blockmask)) + if ((iocb->ki_pos & mp->m_blockmask) || + ((iocb->ki_pos + count) & mp->m_blockmask)) unaligned_io = 1; /* @@ -760,8 +761,7 @@ xfs_file_dio_aio_write( if (ret) goto out; count = iov_iter_count(from); - pos = iocb->ki_pos; - end = pos + count - 1; + end = iocb->ki_pos + count - 1; /* * See xfs_file_read_iter() for why we do a full-file flush here. @@ -794,19 +794,18 @@ xfs_file_dio_aio_write( trace_xfs_file_direct_write(ip, count, iocb->ki_pos, 0); data = *from; - ret = mapping->a_ops->direct_IO(iocb, &data, pos); + ret = mapping->a_ops->direct_IO(iocb, &data); /* see generic_file_direct_write() for why this is necessary */ if (mapping->nrpages) { invalidate_inode_pages2_range(mapping, - pos >> PAGE_SHIFT, + iocb->ki_pos >> PAGE_SHIFT, end >> PAGE_SHIFT); } if (ret > 0) { - pos += ret; + iocb->ki_pos += ret; iov_iter_advance(from, ret); - iocb->ki_pos = pos; } out: xfs_rw_iunlock(ip, iolock); @@ -904,14 +903,10 @@ xfs_file_write_iter( ret = xfs_file_buffered_aio_write(iocb, from); if (ret > 0) { - ssize_t err; - XFS_STATS_ADD(ip->i_mount, xs_write_bytes, ret); /* Handle various SYNC-type writes */ - err = generic_write_sync(file, iocb->ki_pos - ret, ret); - if (err < 0) - ret = err; + ret = generic_write_sync(iocb, ret); } return ret; } @@ -1714,7 +1709,7 @@ const struct file_operations xfs_file_operations = { const struct file_operations xfs_dir_file_operations = { .open = xfs_dir_open, .read = generic_read_dir, - .iterate = xfs_file_readdir, + .iterate_shared = xfs_file_readdir, .llseek = generic_file_llseek, .unlocked_ioctl = xfs_file_ioctl, #ifdef CONFIG_COMPAT diff --git a/fs/xfs/xfs_xattr.c b/fs/xfs/xfs_xattr.c index 110f1d7..d111f69 100644 --- a/fs/xfs/xfs_xattr.c +++ b/fs/xfs/xfs_xattr.c @@ -32,11 +32,11 @@ static int -xfs_xattr_get(const struct xattr_handler *handler, struct dentry *dentry, - const char *name, void *value, size_t size) +xfs_xattr_get(const struct xattr_handler *handler, struct dentry *unused, + struct inode *inode, const char *name, void *value, size_t size) { int xflags = handler->flags; - struct xfs_inode *ip = XFS_I(d_inode(dentry)); + struct xfs_inode *ip = XFS_I(inode); int error, asize = size; /* Convert Linux syscall to XFS internal ATTR flags */ |