diff options
Diffstat (limited to 'fs')
37 files changed, 447 insertions, 398 deletions
diff --git a/fs/9p/v9fs_vfs.h b/fs/9p/v9fs_vfs.h index fd01d90cada..57997fa14e6 100644 --- a/fs/9p/v9fs_vfs.h +++ b/fs/9p/v9fs_vfs.h @@ -51,4 +51,4 @@ int v9fs_dir_release(struct inode *inode, struct file *filp); int v9fs_file_open(struct inode *inode, struct file *file); void v9fs_inode2stat(struct inode *inode, struct p9_stat *stat); void v9fs_dentry_release(struct dentry *); -int v9fs_uflags2omode(int uflags); +int v9fs_uflags2omode(int uflags, int extended); diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c index 0d55affe37d..52944d2249a 100644 --- a/fs/9p/vfs_file.c +++ b/fs/9p/vfs_file.c @@ -59,7 +59,7 @@ int v9fs_file_open(struct inode *inode, struct file *file) P9_DPRINTK(P9_DEBUG_VFS, "inode: %p file: %p \n", inode, file); v9ses = v9fs_inode2v9ses(inode); - omode = v9fs_uflags2omode(file->f_flags); + omode = v9fs_uflags2omode(file->f_flags, v9fs_extended(v9ses)); fid = file->private_data; if (!fid) { fid = v9fs_fid_clone(file->f_path.dentry); @@ -75,6 +75,8 @@ int v9fs_file_open(struct inode *inode, struct file *file) inode->i_size = 0; inode->i_blocks = 0; } + if ((file->f_flags & O_APPEND) && (!v9fs_extended(v9ses))) + generic_file_llseek(file, 0, SEEK_END); } file->private_data = fid; diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index 40fa807bd92..c95295c6504 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -132,10 +132,10 @@ static int p9mode2unixmode(struct v9fs_session_info *v9ses, int mode) /** * v9fs_uflags2omode- convert posix open flags to plan 9 mode bits * @uflags: flags to convert - * + * @extended: if .u extensions are active */ -int v9fs_uflags2omode(int uflags) +int v9fs_uflags2omode(int uflags, int extended) { int ret; @@ -155,14 +155,16 @@ int v9fs_uflags2omode(int uflags) break; } - if (uflags & O_EXCL) - ret |= P9_OEXCL; - if (uflags & O_TRUNC) ret |= P9_OTRUNC; - if (uflags & O_APPEND) - ret |= P9_OAPPEND; + if (extended) { + if (uflags & O_EXCL) + ret |= P9_OEXCL; + + if (uflags & O_APPEND) + ret |= P9_OAPPEND; + } return ret; } @@ -506,7 +508,7 @@ v9fs_vfs_create(struct inode *dir, struct dentry *dentry, int mode, flags = O_RDWR; fid = v9fs_create(v9ses, dir, dentry, NULL, perm, - v9fs_uflags2omode(flags)); + v9fs_uflags2omode(flags, v9fs_extended(v9ses))); if (IS_ERR(fid)) { err = PTR_ERR(fid); fid = NULL; diff --git a/fs/Kconfig b/fs/Kconfig index cf12c403b8c..2694648cbd1 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -830,7 +830,7 @@ config NTFS_FS from the project web site. For more information see <file:Documentation/filesystems/ntfs.txt> - and <http://linux-ntfs.sourceforge.net/>. + and <http://www.linux-ntfs.org/>. To compile this file system support as a module, choose M here: the module will be called ntfs. diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 0fa95b198e6..d48ff5f370f 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -16,7 +16,6 @@ #include <linux/time.h> #include <linux/mm.h> #include <linux/mman.h> -#include <linux/a.out.h> #include <linux/errno.h> #include <linux/signal.h> #include <linux/binfmts.h> @@ -548,7 +547,6 @@ static int load_elf_binary(struct linux_binprm *bprm, struct pt_regs *regs) struct { struct elfhdr elf_ex; struct elfhdr interp_elf_ex; - struct exec interp_ex; } *loc; loc = kmalloc(sizeof(*loc), GFP_KERNEL); @@ -680,7 +678,6 @@ static int load_elf_binary(struct linux_binprm *bprm, struct pt_regs *regs) } /* Get the exec headers */ - loc->interp_ex = *((struct exec *)bprm->buf); loc->interp_elf_ex = *((struct elfhdr *)bprm->buf); break; } diff --git a/fs/block_dev.c b/fs/block_dev.c index 470c10ceb0f..10d8a0aa871 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -931,8 +931,16 @@ static int do_open(struct block_device *bdev, struct file *file, int for_part) struct gendisk *disk; int ret; int part; + int perm = 0; - ret = devcgroup_inode_permission(bdev->bd_inode, file->f_mode); + if (file->f_mode & FMODE_READ) + perm |= MAY_READ; + if (file->f_mode & FMODE_WRITE) + perm |= MAY_WRITE; + /* + * hooks: /n/, see "layering violations". + */ + ret = devcgroup_inode_permission(bdev->bd_inode, perm); if (ret != 0) return ret; diff --git a/fs/buffer.c b/fs/buffer.c index a073f3f4f01..0f51c0f7c26 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -821,7 +821,7 @@ static int fsync_buffers_list(spinlock_t *lock, struct list_head *list) * contents - it is a noop if I/O is still in * flight on potentially older contents. */ - ll_rw_block(SWRITE, 1, &bh); + ll_rw_block(SWRITE_SYNC, 1, &bh); brelse(bh); spin_lock(lock); } @@ -2940,16 +2940,19 @@ void ll_rw_block(int rw, int nr, struct buffer_head *bhs[]) for (i = 0; i < nr; i++) { struct buffer_head *bh = bhs[i]; - if (rw == SWRITE) + if (rw == SWRITE || rw == SWRITE_SYNC) lock_buffer(bh); else if (test_set_buffer_locked(bh)) continue; - if (rw == WRITE || rw == SWRITE) { + if (rw == WRITE || rw == SWRITE || rw == SWRITE_SYNC) { if (test_clear_buffer_dirty(bh)) { bh->b_end_io = end_buffer_write_sync; get_bh(bh); - submit_bh(WRITE, bh); + if (rw == SWRITE_SYNC) + submit_bh(WRITE_SYNC, bh); + else + submit_bh(WRITE, bh); continue; } } else { @@ -2978,7 +2981,7 @@ int sync_dirty_buffer(struct buffer_head *bh) if (test_clear_buffer_dirty(bh)) { get_bh(bh); bh->b_end_io = end_buffer_write_sync; - ret = submit_bh(WRITE, bh); + ret = submit_bh(WRITE_SYNC, bh); wait_on_buffer(bh); if (buffer_eopnotsupp(bh)) { clear_buffer_eopnotsupp(bh); diff --git a/fs/dcache.c b/fs/dcache.c index 3ee588d5f58..6068c25b393 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -17,6 +17,7 @@ #include <linux/syscalls.h> #include <linux/string.h> #include <linux/mm.h> +#include <linux/fdtable.h> #include <linux/fs.h> #include <linux/fsnotify.h> #include <linux/slab.h> @@ -106,9 +107,10 @@ static void dentry_lru_remove(struct dentry *dentry) /* * Release the dentry's inode, using the filesystem * d_iput() operation if defined. - * Called with dcache_lock and per dentry lock held, drops both. */ static void dentry_iput(struct dentry * dentry) + __releases(dentry->d_lock) + __releases(dcache_lock) { struct inode *inode = dentry->d_inode; if (inode) { @@ -132,12 +134,13 @@ static void dentry_iput(struct dentry * dentry) * d_kill - kill dentry and return parent * @dentry: dentry to kill * - * Called with dcache_lock and d_lock, releases both. The dentry must - * already be unhashed and removed from the LRU. + * The dentry must already be unhashed and removed from the LRU. * * If this is the root of the dentry tree, return NULL. */ static struct dentry *d_kill(struct dentry *dentry) + __releases(dentry->d_lock) + __releases(dcache_lock) { struct dentry *parent; @@ -383,11 +386,11 @@ restart: * Try to prune ancestors as well. This is necessary to prevent * quadratic behavior of shrink_dcache_parent(), but is also expected * to be beneficial in reducing dentry cache fragmentation. - * - * Called with dcache_lock, drops it and then regains. - * Called with dentry->d_lock held, drops it. */ static void prune_one_dentry(struct dentry * dentry) + __releases(dentry->d_lock) + __releases(dcache_lock) + __acquires(dcache_lock) { __d_drop(dentry); dentry = d_kill(dentry); @@ -1604,10 +1607,9 @@ static int d_isparent(struct dentry *p1, struct dentry *p2) * * Note: If ever the locking in lock_rename() changes, then please * remember to update this too... - * - * On return, dcache_lock will have been unlocked. */ static struct dentry *__d_unalias(struct dentry *dentry, struct dentry *alias) + __releases(dcache_lock) { struct mutex *m1 = NULL, *m2 = NULL; struct dentry *ret; @@ -1743,11 +1745,9 @@ out_nolock: shouldnt_be_hashed: spin_unlock(&dcache_lock); BUG(); - goto shouldnt_be_hashed; } -static int prepend(char **buffer, int *buflen, const char *str, - int namelen) +static int prepend(char **buffer, int *buflen, const char *str, int namelen) { *buflen -= namelen; if (*buflen < 0) @@ -1757,8 +1757,13 @@ static int prepend(char **buffer, int *buflen, const char *str, return 0; } +static int prepend_name(char **buffer, int *buflen, struct qstr *name) +{ + return prepend(buffer, buflen, name->name, name->len); +} + /** - * d_path - return the path of a dentry + * __d_path - return the path of a dentry * @path: the dentry/vfsmount to report * @root: root vfsmnt/dentry (may be modified by this function) * @buffer: buffer to return value in @@ -1779,9 +1784,10 @@ char *__d_path(const struct path *path, struct path *root, { struct dentry *dentry = path->dentry; struct vfsmount *vfsmnt = path->mnt; - char * end = buffer+buflen; - char * retval; + char *end = buffer + buflen; + char *retval; + spin_lock(&vfsmount_lock); prepend(&end, &buflen, "\0", 1); if (!IS_ROOT(dentry) && d_unhashed(dentry) && (prepend(&end, &buflen, " (deleted)", 10) != 0)) @@ -1800,38 +1806,37 @@ char *__d_path(const struct path *path, struct path *root, break; if (dentry == vfsmnt->mnt_root || IS_ROOT(dentry)) { /* Global root? */ - spin_lock(&vfsmount_lock); if (vfsmnt->mnt_parent == vfsmnt) { - spin_unlock(&vfsmount_lock); goto global_root; } dentry = vfsmnt->mnt_mountpoint; vfsmnt = vfsmnt->mnt_parent; - spin_unlock(&vfsmount_lock); continue; } parent = dentry->d_parent; prefetch(parent); - if ((prepend(&end, &buflen, dentry->d_name.name, - dentry->d_name.len) != 0) || + if ((prepend_name(&end, &buflen, &dentry->d_name) != 0) || (prepend(&end, &buflen, "/", 1) != 0)) goto Elong; retval = end; dentry = parent; } +out: + spin_unlock(&vfsmount_lock); return retval; global_root: retval += 1; /* hit the slash */ - if (prepend(&retval, &buflen, dentry->d_name.name, - dentry->d_name.len) != 0) + if (prepend_name(&retval, &buflen, &dentry->d_name) != 0) goto Elong; root->mnt = vfsmnt; root->dentry = dentry; - return retval; + goto out; + Elong: - return ERR_PTR(-ENAMETOOLONG); + retval = ERR_PTR(-ENAMETOOLONG); + goto out; } /** @@ -1845,9 +1850,9 @@ Elong: * * Returns the buffer or an error code if the path was too long. * - * "buflen" should be positive. Caller holds the dcache_lock. + * "buflen" should be positive. */ -char *d_path(struct path *path, char *buf, int buflen) +char *d_path(const struct path *path, char *buf, int buflen) { char *res; struct path root; @@ -1915,16 +1920,11 @@ char *dentry_path(struct dentry *dentry, char *buf, int buflen) retval = end-1; *retval = '/'; - for (;;) { - struct dentry *parent; - if (IS_ROOT(dentry)) - break; + while (!IS_ROOT(dentry)) { + struct dentry *parent = dentry->d_parent; - parent = dentry->d_parent; prefetch(parent); - - if ((prepend(&end, &buflen, dentry->d_name.name, - dentry->d_name.len) != 0) || + if ((prepend_name(&end, &buflen, &dentry->d_name) != 0) || (prepend(&end, &buflen, "/", 1) != 0)) goto Elong; @@ -1975,7 +1975,7 @@ asmlinkage long sys_getcwd(char __user *buf, unsigned long size) error = -ENOENT; /* Has the current directory has been unlinked? */ spin_lock(&dcache_lock); - if (pwd.dentry->d_parent == pwd.dentry || !d_unhashed(pwd.dentry)) { + if (IS_ROOT(pwd.dentry) || !d_unhashed(pwd.dentry)) { unsigned long len; struct path tmp = root; char * cwd; diff --git a/fs/ecryptfs/miscdev.c b/fs/ecryptfs/miscdev.c index 50c994a249a..09a4522f65e 100644 --- a/fs/ecryptfs/miscdev.c +++ b/fs/ecryptfs/miscdev.c @@ -575,13 +575,11 @@ int ecryptfs_init_ecryptfs_miscdev(void) int rc; atomic_set(&ecryptfs_num_miscdev_opens, 0); - mutex_lock(&ecryptfs_daemon_hash_mux); rc = misc_register(&ecryptfs_miscdev); if (rc) printk(KERN_ERR "%s: Failed to register miscellaneous device " "for communications with userspace daemons; rc = [%d]\n", __func__, rc); - mutex_unlock(&ecryptfs_daemon_hash_mux); return rc; } diff --git a/fs/exec.c b/fs/exec.c index 9448f1b50b4..da94a6f05df 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -26,7 +26,6 @@ #include <linux/file.h> #include <linux/fdtable.h> #include <linux/mman.h> -#include <linux/a.out.h> #include <linux/stat.h> #include <linux/fcntl.h> #include <linux/smp_lock.h> @@ -61,6 +60,11 @@ #include <linux/kmod.h> #endif +#ifdef __alpha__ +/* for /sbin/loader handling in search_binary_handler() */ +#include <linux/a.out.h> +#endif + int core_uses_pid; char core_pattern[CORENAME_MAX_SIZE] = "core"; int suid_dumpable = 0; @@ -1155,7 +1159,7 @@ int search_binary_handler(struct linux_binprm *bprm,struct pt_regs *regs) { int try,retval; struct linux_binfmt *fmt; -#if defined(__alpha__) && defined(CONFIG_ARCH_SUPPORTS_AOUT) +#ifdef __alpha__ /* handle /sbin/loader.. */ { struct exec * eh = (struct exec *) bprm->buf; diff --git a/fs/ext3/super.c b/fs/ext3/super.c index fe3119a71ad..2845425077e 100644 --- a/fs/ext3/super.c +++ b/fs/ext3/super.c @@ -2875,8 +2875,10 @@ static ssize_t ext3_quota_write(struct super_block *sb, int type, blk++; } out: - if (len == towrite) + if (len == towrite) { + mutex_unlock(&inode->i_mutex); return err; + } if (inode->i_size < off+len-towrite) { i_size_write(inode, off+len-towrite); EXT3_I(inode)->i_disksize = inode->i_size; diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index 9ecb92f6854..9ff7b1c0423 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -855,7 +855,8 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input) */ /* Update group descriptor block for new group */ - gdp = (struct ext4_group_desc *)primary->b_data + gdb_off; + gdp = (struct ext4_group_desc *)((char *)primary->b_data + + gdb_off * EXT4_DESC_SIZE(sb)); ext4_block_bitmap_set(sb, gdp, input->block_bitmap); /* LV FIXME */ ext4_inode_bitmap_set(sb, gdp, input->inode_bitmap); /* LV FIXME */ diff --git a/fs/ext4/super.c b/fs/ext4/super.c index cb96f127c36..02bf2434397 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -3337,8 +3337,10 @@ static ssize_t ext4_quota_write(struct super_block *sb, int type, blk++; } out: - if (len == towrite) + if (len == towrite) { + mutex_unlock(&inode->i_mutex); return err; + } if (inode->i_size < off+len-towrite) { i_size_write(inode, off+len-towrite); EXT4_I(inode)->i_disksize = inode->i_size; diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 43e99513334..3141690558c 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -591,7 +591,7 @@ static void process_init_reply(struct fuse_conn *fc, struct fuse_req *req) fc->bdi.ra_pages = min(fc->bdi.ra_pages, ra_pages); fc->minor = arg->minor; fc->max_write = arg->minor < 5 ? 4096 : arg->max_write; - fc->max_write = min_t(unsigned, 4096, fc->max_write); + fc->max_write = max_t(unsigned, 4096, fc->max_write); fc->conn_init = 1; } fuse_put_request(fc, req); @@ -667,7 +667,7 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent) fc->flags = d.flags; fc->user_id = d.user_id; fc->group_id = d.group_id; - fc->max_read = min_t(unsigned, 4096, d.max_read); + fc->max_read = max_t(unsigned, 4096, d.max_read); /* Used by get_root_inode() */ sb->s_fs_info = fc; diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index c19184f2e70..bec76b1c2bb 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -246,15 +246,11 @@ static void find_metapath(const struct gfs2_sbd *sdp, u64 block, } -static inline unsigned int zero_metapath_length(const struct metapath *mp, - unsigned height) +static inline unsigned int metapath_branch_start(const struct metapath *mp) { - unsigned int i; - for (i = 0; i < height - 1; i++) { - if (mp->mp_list[i] != 0) - return i; - } - return height; + if (mp->mp_list[0] == 0) + return 2; + return 1; } /** @@ -436,7 +432,7 @@ static int gfs2_bmap_alloc(struct inode *inode, const sector_t lblock, struct gfs2_sbd *sdp = GFS2_SB(inode); struct buffer_head *dibh = mp->mp_bh[0]; u64 bn, dblock = 0; - unsigned n, i, blks, alloced = 0, iblks = 0, zmpl = 0; + unsigned n, i, blks, alloced = 0, iblks = 0, branch_start = 0; unsigned dblks = 0; unsigned ptrs_per_blk; const unsigned end_of_metadata = height - 1; @@ -471,9 +467,8 @@ static int gfs2_bmap_alloc(struct inode *inode, const sector_t lblock, /* Building up tree height */ state = ALLOC_GROW_HEIGHT; iblks = height - ip->i_height; - zmpl = zero_metapath_length(mp, height); - iblks -= zmpl; - iblks += height; + branch_start = metapath_branch_start(mp); + iblks += (height - branch_start); } } @@ -509,13 +504,13 @@ static int gfs2_bmap_alloc(struct inode *inode, const sector_t lblock, sizeof(struct gfs2_meta_header)); *ptr = zero_bn; state = ALLOC_GROW_DEPTH; - for(i = zmpl; i < height; i++) { + for(i = branch_start; i < height; i++) { if (mp->mp_bh[i] == NULL) break; brelse(mp->mp_bh[i]); mp->mp_bh[i] = NULL; } - i = zmpl; + i = branch_start; } if (n == 0) break; diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c index 6387523a315..3401628d742 100644 --- a/fs/gfs2/rgrp.c +++ b/fs/gfs2/rgrp.c @@ -195,7 +195,7 @@ ulong_aligned: depending on architecture. I've experimented with several ways of writing this section such as using an else before the goto but this one seems to be the fastest. */ - while ((unsigned char *)plong < end - 1) { + while ((unsigned char *)plong < end - sizeof(unsigned long)) { prefetch(plong + 1); if (((*plong) & LBITMASK) != lskipval) break; diff --git a/fs/libfs.c b/fs/libfs.c index 892d41cb338..baeb71ee1cd 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -512,6 +512,20 @@ void simple_release_fs(struct vfsmount **mount, int *count) mntput(mnt); } +/** + * simple_read_from_buffer - copy data from the buffer to user space + * @to: the user space buffer to read to + * @count: the maximum number of bytes to read + * @ppos: the current position in the buffer + * @from: the buffer to read from + * @available: the size of the buffer + * + * The simple_read_from_buffer() function reads up to @count bytes from the + * buffer @from at offset @ppos into the user space address starting at @to. + * + * On success, the number of bytes read is returned and the offset @ppos is + * advanced by this number, or negative value is returned on error. + **/ ssize_t simple_read_from_buffer(void __user *to, size_t count, loff_t *ppos, const void *from, size_t available) { @@ -528,6 +542,20 @@ ssize_t simple_read_from_buffer(void __user *to, size_t count, loff_t *ppos, return count; } +/** + * memory_read_from_buffer - copy data from the buffer + * @to: the kernel space buffer to read to + * @count: the maximum number of bytes to read + * @ppos: the current position in the buffer + * @from: the buffer to read from + * @available: the size of the buffer + * + * The memory_read_from_buffer() function reads up to @count bytes from the + * buffer @from at offset @ppos into the kernel space address starting at @to. + * + * On success, the number of bytes read is returned and the offset @ppos is + * advanced by this number, or negative value is returned on error. + **/ ssize_t memory_read_from_buffer(void *to, size_t count, loff_t *ppos, const void *from, size_t available) { diff --git a/fs/locks.c b/fs/locks.c index 11dbf08651b..dce8c747371 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -561,9 +561,6 @@ static void locks_insert_lock(struct file_lock **pos, struct file_lock *fl) /* insert into file's list */ fl->fl_next = *pos; *pos = fl; - - if (fl->fl_ops && fl->fl_ops->fl_insert) - fl->fl_ops->fl_insert(fl); } /* @@ -586,9 +583,6 @@ static void locks_delete_lock(struct file_lock **thisfl_p) fl->fl_fasync = NULL; } - if (fl->fl_ops && fl->fl_ops->fl_remove) - fl->fl_ops->fl_remove(fl); - if (fl->fl_nspid) { put_pid(fl->fl_nspid); fl->fl_nspid = NULL; diff --git a/fs/namei.c b/fs/namei.c index c7e43536c49..01e67dddcc3 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -581,15 +581,13 @@ static __always_inline int link_path_walk(const char *name, struct nameidata *nd int result; /* make sure the stuff we saved doesn't go away */ - dget(save.dentry); - mntget(save.mnt); + path_get(&save); result = __link_path_walk(name, nd); if (result == -ESTALE) { /* nd->path had been dropped */ nd->path = save; - dget(nd->path.dentry); - mntget(nd->path.mnt); + path_get(&nd->path); nd->flags |= LOOKUP_REVAL; result = __link_path_walk(name, nd); } @@ -1216,8 +1214,9 @@ int vfs_path_lookup(struct dentry *dentry, struct vfsmount *mnt, nd->flags = flags; nd->depth = 0; - nd->path.mnt = mntget(mnt); - nd->path.dentry = dget(dentry); + nd->path.dentry = dentry; + nd->path.mnt = mnt; + path_get(&nd->path); retval = path_walk(name, nd); if (unlikely(!retval && !audit_dummy_context() && nd->path.dentry && @@ -2857,16 +2856,17 @@ int generic_readlink(struct dentry *dentry, char __user *buffer, int buflen) { struct nameidata nd; void *cookie; + int res; nd.depth = 0; cookie = dentry->d_inode->i_op->follow_link(dentry, &nd); - if (!IS_ERR(cookie)) { - int res = vfs_readlink(dentry, buffer, buflen, nd_get_link(&nd)); - if (dentry->d_inode->i_op->put_link) - dentry->d_inode->i_op->put_link(dentry, &nd, cookie); - cookie = ERR_PTR(res); - } - return PTR_ERR(cookie); + if (IS_ERR(cookie)) + return PTR_ERR(cookie); + + res = vfs_readlink(dentry, buffer, buflen, nd_get_link(&nd)); + if (dentry->d_inode->i_op->put_link) + dentry->d_inode->i_op->put_link(dentry, &nd, cookie); + return res; } int vfs_follow_link(struct nameidata *nd, const char *link) diff --git a/fs/nfs/mount_clnt.c b/fs/nfs/mount_clnt.c index 49c7cd0502c..779d2eb649c 100644 --- a/fs/nfs/mount_clnt.c +++ b/fs/nfs/mount_clnt.c @@ -130,10 +130,11 @@ static int xdr_decode_fhstatus3(struct rpc_rqst *req, __be32 *p, struct mnt_fhstatus *res) { struct nfs_fh *fh = res->fh; + unsigned size; if ((res->status = ntohl(*p++)) == 0) { - int size = ntohl(*p++); - if (size <= NFS3_FHSIZE) { + size = ntohl(*p++); + if (size <= NFS3_FHSIZE && size != 0) { fh->size = size; memcpy(fh->data, p, size); } else diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 2a4a024a4e7..614efeed543 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -1216,8 +1216,6 @@ static int nfs_validate_mount_data(void *options, { struct nfs_mount_data *data = (struct nfs_mount_data *)options; - memset(args, 0, sizeof(*args)); - if (data == NULL) goto out_no_data; @@ -1251,13 +1249,13 @@ static int nfs_validate_mount_data(void *options, case 5: memset(data->context, 0, sizeof(data->context)); case 6: - if (data->flags & NFS_MOUNT_VER3) + if (data->flags & NFS_MOUNT_VER3) { + if (data->root.size > NFS3_FHSIZE || data->root.size == 0) + goto out_invalid_fh; mntfh->size = data->root.size; - else + } else mntfh->size = NFS2_FHSIZE; - if (mntfh->size > sizeof(mntfh->data)) - goto out_invalid_fh; memcpy(mntfh->data, data->root.data, mntfh->size); if (mntfh->size < sizeof(mntfh->data)) @@ -1585,24 +1583,29 @@ static int nfs_get_sb(struct file_system_type *fs_type, { struct nfs_server *server = NULL; struct super_block *s; - struct nfs_fh mntfh; - struct nfs_parsed_mount_data data; + struct nfs_parsed_mount_data *data; + struct nfs_fh *mntfh; struct dentry *mntroot; int (*compare_super)(struct super_block *, void *) = nfs_compare_super; struct nfs_sb_mountdata sb_mntdata = { .mntflags = flags, }; - int error; + int error = -ENOMEM; + + data = kzalloc(sizeof(*data), GFP_KERNEL); + mntfh = kzalloc(sizeof(*mntfh), GFP_KERNEL); + if (data == NULL || mntfh == NULL) + goto out_free_fh; - security_init_mnt_opts(&data.lsm_opts); + security_init_mnt_opts(&data->lsm_opts); /* Validate the mount data */ - error = nfs_validate_mount_data(raw_data, &data, &mntfh, dev_name); + error = nfs_validate_mount_data(raw_data, data, mntfh, dev_name); if (error < 0) goto out; /* Get a volume representation */ - server = nfs_create_server(&data, &mntfh); + server = nfs_create_server(data, mntfh); if (IS_ERR(server)) { error = PTR_ERR(server); goto out; @@ -1630,16 +1633,16 @@ static int nfs_get_sb(struct file_system_type *fs_type, if (!s->s_root) { /* initial superblock/root creation */ - nfs_fill_super(s, &data); + nfs_fill_super(s, data); } - mntroot = nfs_get_root(s, &mntfh); + mntroot = nfs_get_root(s, mntfh); if (IS_ERR(mntroot)) { error = PTR_ERR(mntroot); goto error_splat_super; } - error = security_sb_set_mnt_opts(s, &data.lsm_opts); + error = security_sb_set_mnt_opts(s, &data->lsm_opts); if (error) goto error_splat_root; @@ -1649,9 +1652,12 @@ static int nfs_get_sb(struct file_system_type *fs_type, error = 0; out: - kfree(data.nfs_server.hostname); - kfree(data.mount_server.hostname); - security_free_mnt_opts(&data.lsm_opts); + kfree(data->nfs_server.hostname); + kfree(data->mount_server.hostname); + security_free_mnt_opts(&data->lsm_opts); +out_free_fh: + kfree(mntfh); + kfree(data); return error; out_err_nosb: @@ -1800,8 +1806,6 @@ static int nfs4_validate_mount_data(void *options, struct nfs4_mount_data *data = (struct nfs4_mount_data *)options; char *c; - memset(args, 0, sizeof(*args)); - if (data == NULL) goto out_no_data; @@ -1959,26 +1963,31 @@ out_no_client_address: static int nfs4_get_sb(struct file_system_type *fs_type, int flags, const char *dev_name, void *raw_data, struct vfsmount *mnt) { - struct nfs_parsed_mount_data data; + struct nfs_parsed_mount_data *data; struct super_block *s; struct nfs_server *server; - struct nfs_fh mntfh; + struct nfs_fh *mntfh; struct dentry *mntroot; int (*compare_super)(struct super_block *, void *) = nfs_compare_super; struct nfs_sb_mountdata sb_mntdata = { .mntflags = flags, }; - int error; + int error = -ENOMEM; - security_init_mnt_opts(&data.lsm_opts); + data = kzalloc(sizeof(*data), GFP_KERNEL); + mntfh = kzalloc(sizeof(*mntfh), GFP_KERNEL); + if (data == NULL || mntfh == NULL) + goto out_free_fh; + + security_init_mnt_opts(&data->lsm_opts); /* Validate the mount data */ - error = nfs4_validate_mount_data(raw_data, &data, dev_name); + error = nfs4_validate_mount_data(raw_data, data, dev_name); if (error < 0) goto out; /* Get a volume representation */ - server = nfs4_create_server(&data, &mntfh); + server = nfs4_create_server(data, mntfh); if (IS_ERR(server)) { error = PTR_ERR(server); goto out; @@ -2009,13 +2018,13 @@ static int nfs4_get_sb(struct file_system_type *fs_type, nfs4_fill_super(s); } - mntroot = nfs4_get_root(s, &mntfh); + mntroot = nfs4_get_root(s, mntfh); if (IS_ERR(mntroot)) { error = PTR_ERR(mntroot); goto error_splat_super; } - error = security_sb_set_mnt_opts(s, &data.lsm_opts); + error = security_sb_set_mnt_opts(s, &data->lsm_opts); if (error) goto error_splat_root; @@ -2025,10 +2034,13 @@ static int nfs4_get_sb(struct file_system_type *fs_type, error = 0; out: - kfree(data.client_address); - kfree(data.nfs_server.export_path); - kfree(data.nfs_server.hostname); - security_free_mnt_opts(&data.lsm_opts); + kfree(data->client_address); + kfree(data->nfs_server.export_path); + kfree(data->nfs_server.hostname); + security_free_mnt_opts(&data->lsm_opts); +out_free_fh: + kfree(mntfh); + kfree(data); return error; out_free: diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 6d8ace3e325..f333848fd3b 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -739,12 +739,13 @@ int nfs_updatepage(struct file *file, struct page *page, } status = nfs_writepage_setup(ctx, page, offset, count); - __set_page_dirty_nobuffers(page); + if (status < 0) + nfs_set_pageerror(page); + else + __set_page_dirty_nobuffers(page); dprintk("NFS: nfs_updatepage returns %d (isize %Ld)\n", status, (long long)i_size_read(inode)); - if (status < 0) - nfs_set_pageerror(page); return status; } diff --git a/fs/ocfs2/cluster/nodemanager.c b/fs/ocfs2/cluster/nodemanager.c index cf9401e8cd0..cfdb08b484e 100644 --- a/fs/ocfs2/cluster/nodemanager.c +++ b/fs/ocfs2/cluster/nodemanager.c @@ -21,7 +21,6 @@ #include <linux/kernel.h> #include <linux/module.h> -#include <linux/sysctl.h> #include <linux/configfs.h> #include "tcp.h" @@ -36,65 +35,6 @@ * cluster references throughout where nodes are looked up */ struct o2nm_cluster *o2nm_single_cluster = NULL; -#define OCFS2_MAX_HB_CTL_PATH 256 -static char ocfs2_hb_ctl_path[OCFS2_MAX_HB_CTL_PATH] = "/sbin/ocfs2_hb_ctl"; - -static ctl_table ocfs2_nm_table[] = { - { - .ctl_name = 1, - .procname = "hb_ctl_path", - .data = ocfs2_hb_ctl_path, - .maxlen = OCFS2_MAX_HB_CTL_PATH, - .mode = 0644, - .proc_handler = &proc_dostring, - .strategy = &sysctl_string, - }, - { .ctl_name = 0 } -}; - -static ctl_table ocfs2_mod_table[] = { - { - .ctl_name = FS_OCFS2_NM, - .procname = "nm", - .data = NULL, - .maxlen = 0, - .mode = 0555, - .child = ocfs2_nm_table - }, - { .ctl_name = 0} -}; - -static ctl_table ocfs2_kern_table[] = { - { - .ctl_name = FS_OCFS2, - .procname = "ocfs2", - .data = NULL, - .maxlen = 0, - .mode = 0555, - .child = ocfs2_mod_table - }, - { .ctl_name = 0} -}; - -static ctl_table ocfs2_root_table[] = { - { - .ctl_name = CTL_FS, - .procname = "fs", - .data = NULL, - .maxlen = 0, - .mode = 0555, - .child = ocfs2_kern_table - }, - { .ctl_name = 0 } -}; - -static struct ctl_table_header *ocfs2_table_header = NULL; - -const char *o2nm_get_hb_ctl_path(void) -{ - return ocfs2_hb_ctl_path; -} -EXPORT_SYMBOL_GPL(o2nm_get_hb_ctl_path); struct o2nm_node *o2nm_get_node_by_num(u8 node_num) { @@ -941,9 +881,6 @@ void o2nm_undepend_this_node(void) static void __exit exit_o2nm(void) { - if (ocfs2_table_header) - unregister_sysctl_table(ocfs2_table_header); - /* XXX sync with hb callbacks and shut down hb? */ o2net_unregister_hb_callbacks(); configfs_unregister_subsystem(&o2nm_cluster_group.cs_subsys); @@ -964,16 +901,9 @@ static int __init init_o2nm(void) if (ret) goto out; - ocfs2_table_header = register_sysctl_table(ocfs2_root_table); - if (!ocfs2_table_header) { - printk(KERN_ERR "nodemanager: unable to register sysctl\n"); - ret = -ENOMEM; /* or something. */ - goto out_o2net; - } - ret = o2net_register_hb_callbacks(); if (ret) - goto out_sysctl; + goto out_o2net; config_group_init(&o2nm_cluster_group.cs_subsys.su_group); mutex_init(&o2nm_cluster_group.cs_subsys.su_mutex); @@ -990,8 +920,6 @@ static int __init init_o2nm(void) configfs_unregister_subsystem(&o2nm_cluster_group.cs_subsys); out_callbacks: o2net_unregister_hb_callbacks(); -out_sysctl: - unregister_sysctl_table(ocfs2_table_header); out_o2net: o2net_exit(); out: diff --git a/fs/ocfs2/cluster/nodemanager.h b/fs/ocfs2/cluster/nodemanager.h index 7c860361b8d..c992ea0da4a 100644 --- a/fs/ocfs2/cluster/nodemanager.h +++ b/fs/ocfs2/cluster/nodemanager.h @@ -33,10 +33,6 @@ #include <linux/configfs.h> #include <linux/rbtree.h> -#define FS_OCFS2_NM 1 - -const char *o2nm_get_hb_ctl_path(void); - struct o2nm_node { spinlock_t nd_lock; struct config_item nd_item; diff --git a/fs/ocfs2/stack_o2cb.c b/fs/ocfs2/stack_o2cb.c index bbd1667aa7d..fcd120f1493 100644 --- a/fs/ocfs2/stack_o2cb.c +++ b/fs/ocfs2/stack_o2cb.c @@ -317,8 +317,7 @@ out: return rc; } -static int o2cb_cluster_disconnect(struct ocfs2_cluster_connection *conn, - int hangup_pending) +static int o2cb_cluster_disconnect(struct ocfs2_cluster_connection *conn) { struct dlm_ctxt *dlm = conn->cc_lockspace; struct o2dlm_private *priv = conn->cc_private; @@ -333,43 +332,6 @@ static int o2cb_cluster_disconnect(struct ocfs2_cluster_connection *conn, return 0; } -static void o2hb_stop(const char *group) -{ - int ret; - char *argv[5], *envp[3]; - - argv[0] = (char *)o2nm_get_hb_ctl_path(); - argv[1] = "-K"; - argv[2] = "-u"; - argv[3] = (char *)group; - argv[4] = NULL; - - mlog(0, "Run: %s %s %s %s\n", argv[0], argv[1], argv[2], argv[3]); - - /* minimal command environment taken from cpu_run_sbin_hotplug */ - envp[0] = "HOME=/"; - envp[1] = "PATH=/sbin:/bin:/usr/sbin:/usr/bin"; - envp[2] = NULL; - - ret = call_usermodehelper(argv[0], argv, envp, UMH_WAIT_PROC); - if (ret < 0) - mlog_errno(ret); -} - -/* - * Hangup is a hack for tools compatibility. Older ocfs2-tools software - * expects the filesystem to call "ocfs2_hb_ctl" during unmount. This - * happens regardless of whether the DLM got started, so we can't do it - * in ocfs2_cluster_disconnect(). We bring the o2hb_stop() function into - * the glue and provide a "hangup" API for super.c to call. - * - * Other stacks will eventually provide a NULL ->hangup() pointer. - */ -static void o2cb_cluster_hangup(const char *group, int grouplen) -{ - o2hb_stop(group); -} - static int o2cb_cluster_this_node(unsigned int *node) { int node_num; @@ -388,7 +350,6 @@ static int o2cb_cluster_this_node(unsigned int *node) static struct ocfs2_stack_operations o2cb_stack_ops = { .connect = o2cb_cluster_connect, .disconnect = o2cb_cluster_disconnect, - .hangup = o2cb_cluster_hangup, .this_node = o2cb_cluster_this_node, .dlm_lock = o2cb_dlm_lock, .dlm_unlock = o2cb_dlm_unlock, diff --git a/fs/ocfs2/stack_user.c b/fs/ocfs2/stack_user.c index 6b97d11f6bf..c021280dd46 100644 --- a/fs/ocfs2/stack_user.c +++ b/fs/ocfs2/stack_user.c @@ -816,8 +816,7 @@ out: return rc; } -static int user_cluster_disconnect(struct ocfs2_cluster_connection *conn, - int hangup_pending) +static int user_cluster_disconnect(struct ocfs2_cluster_connection *conn) { dlm_release_lockspace(conn->cc_lockspace, 2); conn->cc_lockspace = NULL; diff --git a/fs/ocfs2/stackglue.c b/fs/ocfs2/stackglue.c index 119f60cea9c..10e149ae5e3 100644 --- a/fs/ocfs2/stackglue.c +++ b/fs/ocfs2/stackglue.c @@ -26,6 +26,7 @@ #include <linux/fs.h> #include <linux/kobject.h> #include <linux/sysfs.h> +#include <linux/sysctl.h> #include "ocfs2_fs.h" @@ -33,11 +34,13 @@ #define OCFS2_STACK_PLUGIN_O2CB "o2cb" #define OCFS2_STACK_PLUGIN_USER "user" +#define OCFS2_MAX_HB_CTL_PATH 256 static struct ocfs2_locking_protocol *lproto; static DEFINE_SPINLOCK(ocfs2_stack_lock); static LIST_HEAD(ocfs2_stack_list); static char cluster_stack_name[OCFS2_STACK_LABEL_LEN + 1]; +static char ocfs2_hb_ctl_path[OCFS2_MAX_HB_CTL_PATH] = "/sbin/ocfs2_hb_ctl"; /* * The stack currently in use. If not null, active_stack->sp_count > 0, @@ -349,7 +352,7 @@ int ocfs2_cluster_disconnect(struct ocfs2_cluster_connection *conn, BUG_ON(conn == NULL); - ret = active_stack->sp_ops->disconnect(conn, hangup_pending); + ret = active_stack->sp_ops->disconnect(conn); /* XXX Should we free it anyway? */ if (!ret) { @@ -362,13 +365,48 @@ int ocfs2_cluster_disconnect(struct ocfs2_cluster_connection *conn, } EXPORT_SYMBOL_GPL(ocfs2_cluster_disconnect); +/* + * Leave the group for this filesystem. This is executed by a userspace + * program (stored in ocfs2_hb_ctl_path). + */ +static void ocfs2_leave_group(const char *group) +{ + int ret; + char *argv[5], *envp[3]; + + argv[0] = ocfs2_hb_ctl_path; + argv[1] = "-K"; + argv[2] = "-u"; + argv[3] = (char *)group; + argv[4] = NULL; + + /* minimal command environment taken from cpu_run_sbin_hotplug */ + envp[0] = "HOME=/"; + envp[1] = "PATH=/sbin:/bin:/usr/sbin:/usr/bin"; + envp[2] = NULL; + + ret = call_usermodehelper(argv[0], argv, envp, UMH_WAIT_PROC); + if (ret < 0) { + printk(KERN_ERR + "ocfs2: Error %d running user helper " + "\"%s %s %s %s\"\n", + ret, argv[0], argv[1], argv[2], argv[3]); + } +} + +/* + * Hangup is a required post-umount. ocfs2-tools software expects the + * filesystem to call "ocfs2_hb_ctl" during unmount. This happens + * regardless of whether the DLM got started, so we can't do it + * in ocfs2_cluster_disconnect(). The ocfs2_leave_group() function does + * the actual work. + */ void ocfs2_cluster_hangup(const char *group, int grouplen) { BUG_ON(group == NULL); BUG_ON(group[grouplen] != '\0'); - if (active_stack->sp_ops->hangup) - active_stack->sp_ops->hangup(group, grouplen); + ocfs2_leave_group(group); /* cluster_disconnect() was called with hangup_pending==1 */ ocfs2_stack_driver_put(); @@ -548,10 +586,83 @@ error: return ret; } +/* + * Sysctl bits + * + * The sysctl lives at /proc/sys/fs/ocfs2/nm/hb_ctl_path. The 'nm' doesn't + * make as much sense in a multiple cluster stack world, but it's safer + * and easier to preserve the name. + */ + +#define FS_OCFS2_NM 1 + +static ctl_table ocfs2_nm_table[] = { + { + .ctl_name = 1, + .procname = "hb_ctl_path", + .data = ocfs2_hb_ctl_path, + .maxlen = OCFS2_MAX_HB_CTL_PATH, + .mode = 0644, + .proc_handler = &proc_dostring, + .strategy = &sysctl_string, + }, + { .ctl_name = 0 } +}; + +static ctl_table ocfs2_mod_table[] = { + { + .ctl_name = FS_OCFS2_NM, + .procname = "nm", + .data = NULL, + .maxlen = 0, + .mode = 0555, + .child = ocfs2_nm_table + }, + { .ctl_name = 0} +}; + +static ctl_table ocfs2_kern_table[] = { + { + .ctl_name = FS_OCFS2, + .procname = "ocfs2", + .data = NULL, + .maxlen = 0, + .mode = 0555, + .child = ocfs2_mod_table + }, + { .ctl_name = 0} +}; + +static ctl_table ocfs2_root_table[] = { + { + .ctl_name = CTL_FS, + .procname = "fs", + .data = NULL, + .maxlen = 0, + .mode = 0555, + .child = ocfs2_kern_table + }, + { .ctl_name = 0 } +}; + +static struct ctl_table_header *ocfs2_table_header = NULL; + + +/* + * Initialization + */ + static int __init ocfs2_stack_glue_init(void) { strcpy(cluster_stack_name, OCFS2_STACK_PLUGIN_O2CB); + ocfs2_table_header = register_sysctl_table(ocfs2_root_table); + if (!ocfs2_table_header) { + printk(KERN_ERR + "ocfs2 stack glue: unable to register sysctl\n"); + return -ENOMEM; /* or something. */ + } + return ocfs2_sysfs_init(); } @@ -559,6 +670,8 @@ static void __exit ocfs2_stack_glue_exit(void) { lproto = NULL; ocfs2_sysfs_exit(); + if (ocfs2_table_header) + unregister_sysctl_table(ocfs2_table_header); } MODULE_AUTHOR("Oracle"); diff --git a/fs/ocfs2/stackglue.h b/fs/ocfs2/stackglue.h index 005e4f170e0..db56281dd1b 100644 --- a/fs/ocfs2/stackglue.h +++ b/fs/ocfs2/stackglue.h @@ -134,22 +134,10 @@ struct ocfs2_stack_operations { * be freed. Thus, a stack must not return from ->disconnect() * until it will no longer reference the conn pointer. * - * If hangup_pending is zero, ocfs2_cluster_disconnect() will also - * be dropping the reference on the module. + * Once this call returns, the stack glue will be dropping this + * connection's reference on the module. */ - int (*disconnect)(struct ocfs2_cluster_connection *conn, - int hangup_pending); - - /* - * ocfs2_cluster_hangup() exists for compatibility with older - * ocfs2 tools. Only the classic stack really needs it. As such - * ->hangup() is not required of all stacks. See the comment by - * ocfs2_cluster_hangup() for more details. - * - * Note that ocfs2_cluster_hangup() can only be called if - * hangup_pending was passed to ocfs2_cluster_disconnect(). - */ - void (*hangup)(const char *group, int grouplen); + int (*disconnect)(struct ocfs2_cluster_connection *conn); /* * ->this_node() returns the cluster's unique identifier for the @@ -258,4 +246,5 @@ void ocfs2_stack_glue_set_locking_protocol(struct ocfs2_locking_protocol *proto) /* Used by stack plugins */ int ocfs2_stack_glue_register(struct ocfs2_stack_plugin *plugin); void ocfs2_stack_glue_unregister(struct ocfs2_stack_plugin *plugin); + #endif /* STACKGLUE_H */ diff --git a/fs/open.c b/fs/open.c index a1450086e92..a99ad09c319 100644 --- a/fs/open.c +++ b/fs/open.c @@ -16,6 +16,7 @@ #include <linux/namei.h> #include <linux/backing-dev.h> #include <linux/capability.h> +#include <linux/securebits.h> #include <linux/security.h> #include <linux/mount.h> #include <linux/vfs.h> @@ -425,7 +426,7 @@ asmlinkage long sys_faccessat(int dfd, const char __user *filename, int mode) { struct nameidata nd; int old_fsuid, old_fsgid; - kernel_cap_t old_cap; + kernel_cap_t uninitialized_var(old_cap); /* !SECURE_NO_SETUID_FIXUP */ int res; if (mode & ~S_IRWXO) /* where's F_OK, X_OK, W_OK, R_OK? */ @@ -433,23 +434,27 @@ asmlinkage long sys_faccessat(int dfd, const char __user *filename, int mode) old_fsuid = current->fsuid; old_fsgid = current->fsgid; - old_cap = current->cap_effective; current->fsuid = current->uid; current->fsgid = current->gid; - /* - * Clear the capabilities if we switch to a non-root user - * - * FIXME: There is a race here against sys_capset. The - * capabilities can change yet we will restore the old - * value below. We should hold task_capabilities_lock, - * but we cannot because user_path_walk can sleep. - */ - if (current->uid) - cap_clear(current->cap_effective); - else - current->cap_effective = current->cap_permitted; + if (!issecure(SECURE_NO_SETUID_FIXUP)) { + /* + * Clear the capabilities if we switch to a non-root user + */ +#ifndef CONFIG_SECURITY_FILE_CAPABILITIES + /* + * FIXME: There is a race here against sys_capset. The + * capabilities can change yet we will restore the old + * value below. We should hold task_capabilities_lock, + * but we cannot because user_path_walk can sleep. + */ +#endif /* ndef CONFIG_SECURITY_FILE_CAPABILITIES */ + if (current->uid) + old_cap = cap_set_effective(__cap_empty_set); + else + old_cap = cap_set_effective(current->cap_permitted); + } res = __user_walk_fd(dfd, filename, LOOKUP_FOLLOW|LOOKUP_ACCESS, &nd); if (res) @@ -478,7 +483,9 @@ out_path_release: out: current->fsuid = old_fsuid; current->fsgid = old_fsgid; - current->cap_effective = old_cap; + + if (!issecure(SECURE_NO_SETUID_FIXUP)) + cap_set_effective(old_cap); return res; } diff --git a/fs/pipe.c b/fs/pipe.c index ec228bc9f88..700f4e0d957 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -1003,8 +1003,7 @@ struct file *create_write_pipe(void) void free_write_pipe(struct file *f) { free_pipe_info(f->f_dentry->d_inode); - dput(f->f_path.dentry); - mntput(f->f_path.mnt); + path_put(&f->f_path); put_filp(f); } @@ -1015,8 +1014,8 @@ struct file *create_read_pipe(struct file *wrf) return ERR_PTR(-ENFILE); /* Grab pipe from the writer */ - f->f_path.mnt = mntget(wrf->f_path.mnt); - f->f_path.dentry = dget(wrf->f_path.dentry); + f->f_path = wrf->f_path; + path_get(&wrf->f_path); f->f_mapping = wrf->f_path.dentry->d_inode->i_mapping; f->f_pos = 0; @@ -1068,8 +1067,7 @@ int do_pipe(int *fd) err_fdr: put_unused_fd(fdr); err_read_pipe: - dput(fr->f_dentry); - mntput(fr->f_vfsmnt); + path_put(&fr->f_path); put_filp(fr); err_write_pipe: free_write_pipe(fw); diff --git a/fs/proc/proc_misc.c b/fs/proc/proc_misc.c index 7e277f2ad46..c652d469dc0 100644 --- a/fs/proc/proc_misc.c +++ b/fs/proc/proc_misc.c @@ -123,6 +123,11 @@ static int uptime_read_proc(char *page, char **start, off_t off, return proc_calc_metrics(page, start, off, count, eof, len); } +int __attribute__((weak)) arch_report_meminfo(char *page) +{ + return 0; +} + static int meminfo_read_proc(char *page, char **start, off_t off, int count, int *eof, void *data) { @@ -221,6 +226,8 @@ static int meminfo_read_proc(char *page, char **start, off_t off, len += hugetlb_report_meminfo(page + len); + len += arch_report_meminfo(page + len); + return proc_calc_metrics(page, start, off, count, eof, len); #undef K } @@ -472,6 +479,13 @@ static const struct file_operations proc_vmalloc_operations = { }; #endif +#ifndef arch_irq_stat_cpu +#define arch_irq_stat_cpu(cpu) 0 +#endif +#ifndef arch_irq_stat +#define arch_irq_stat() 0 +#endif + static int show_stat(struct seq_file *p, void *v) { int i; @@ -509,7 +523,9 @@ static int show_stat(struct seq_file *p, void *v) sum += temp; per_irq_sum[j] += temp; } + sum += arch_irq_stat_cpu(i); } + sum += arch_irq_stat(); seq_printf(p, "cpu %llu %llu %llu %llu %llu %llu %llu %llu %llu\n", (unsigned long long)cputime64_to_clock_t(user), diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index ab8ccc9d14f..c492449f3b4 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -476,10 +476,10 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf, return -ESRCH; mm = get_task_mm(task); if (mm) { - static struct mm_walk clear_refs_walk; - memset(&clear_refs_walk, 0, sizeof(clear_refs_walk)); - clear_refs_walk.pmd_entry = clear_refs_pte_range; - clear_refs_walk.mm = mm; + struct mm_walk clear_refs_walk = { + .pmd_entry = clear_refs_pte_range, + .mm = mm, + }; down_read(&mm->mmap_sem); for (vma = mm->mmap; vma; vma = vma->vm_next) { clear_refs_walk.private = vma; @@ -602,11 +602,6 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, return err; } -static struct mm_walk pagemap_walk = { - .pmd_entry = pagemap_pte_range, - .pte_hole = pagemap_pte_hole -}; - /* * /proc/pid/pagemap - an array mapping virtual pages to pfns * @@ -641,6 +636,11 @@ static ssize_t pagemap_read(struct file *file, char __user *buf, struct pagemapread pm; int pagecount; int ret = -ESRCH; + struct mm_walk pagemap_walk; + unsigned long src; + unsigned long svpfn; + unsigned long start_vaddr; + unsigned long end_vaddr; if (!task) goto out; @@ -659,11 +659,15 @@ static ssize_t pagemap_read(struct file *file, char __user *buf, if (!mm) goto out_task; - ret = -ENOMEM; + uaddr = (unsigned long)buf & PAGE_MASK; uend = (unsigned long)(buf + count); pagecount = (PAGE_ALIGN(uend) - uaddr) / PAGE_SIZE; - pages = kmalloc(pagecount * sizeof(struct page *), GFP_KERNEL); + ret = 0; + if (pagecount == 0) + goto out_mm; + pages = kcalloc(pagecount, sizeof(struct page *), GFP_KERNEL); + ret = -ENOMEM; if (!pages) goto out_mm; @@ -684,33 +688,33 @@ static ssize_t pagemap_read(struct file *file, char __user *buf, pm.out = (u64 *)buf; pm.end = (u64 *)(buf + count); - if (!ptrace_may_attach(task)) { - ret = -EIO; - } else { - unsigned long src = *ppos; - unsigned long svpfn = src / PM_ENTRY_BYTES; - unsigned long start_vaddr = svpfn << PAGE_SHIFT; - unsigned long end_vaddr = TASK_SIZE_OF(task); - - /* watch out for wraparound */ - if (svpfn > TASK_SIZE_OF(task) >> PAGE_SHIFT) - start_vaddr = end_vaddr; - - /* - * The odds are that this will stop walking way - * before end_vaddr, because the length of the - * user buffer is tracked in "pm", and the walk - * will stop when we hit the end of the buffer. - */ - ret = walk_page_range(start_vaddr, end_vaddr, - &pagemap_walk); - if (ret == PM_END_OF_BUFFER) - ret = 0; - /* don't need mmap_sem for these, but this looks cleaner */ - *ppos += (char *)pm.out - buf; - if (!ret) - ret = (char *)pm.out - buf; - } + pagemap_walk.pmd_entry = pagemap_pte_range; + pagemap_walk.pte_hole = pagemap_pte_hole; + pagemap_walk.mm = mm; + pagemap_walk.private = ± + + src = *ppos; + svpfn = src / PM_ENTRY_BYTES; + start_vaddr = svpfn << PAGE_SHIFT; + end_vaddr = TASK_SIZE_OF(task); + + /* watch out for wraparound */ + if (svpfn > TASK_SIZE_OF(task) >> PAGE_SHIFT) + start_vaddr = end_vaddr; + + /* + * The odds are that this will stop walking way + * before end_vaddr, because the length of the + * user buffer is tracked in "pm", and the walk + * will stop when we hit the end of the buffer. + */ + ret = walk_page_range(start_vaddr, end_vaddr, &pagemap_walk); + if (ret == PM_END_OF_BUFFER) + ret = 0; + /* don't need mmap_sem for these, but this looks cleaner */ + *ppos += (char *)pm.out - buf; + if (!ret) + ret = (char *)pm.out - buf; out_pages: for (; pagecount; pagecount--) { diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c index ed424d708e6..1d40f2bd197 100644 --- a/fs/reiserfs/super.c +++ b/fs/reiserfs/super.c @@ -2165,8 +2165,10 @@ static ssize_t reiserfs_quota_write(struct super_block *sb, int type, blk++; } out: - if (len == towrite) + if (len == towrite) { + mutex_unlock(&inode->i_mutex); return err; + } if (inode->i_size < off + len - towrite) i_size_write(inode, off + len - towrite); inode->i_version++; diff --git a/fs/select.c b/fs/select.c index 8dda969614a..da0e88201c3 100644 --- a/fs/select.c +++ b/fs/select.c @@ -249,7 +249,6 @@ int do_select(int n, fd_set_bits *fds, s64 *timeout) retval++; } } - cond_resched(); } if (res_in) *rinp = res_in; @@ -257,6 +256,7 @@ int do_select(int n, fd_set_bits *fds, s64 *timeout) *routp = res_out; if (res_ex) *rexp = res_ex; + cond_resched(); } wait = NULL; if (retval || !*timeout || signal_pending(current)) diff --git a/fs/udf/super.c b/fs/udf/super.c index 7a5f69be6ac..44cc702f96c 100644 --- a/fs/udf/super.c +++ b/fs/udf/super.c @@ -682,38 +682,26 @@ static int udf_vrs(struct super_block *sb, int silent) /* * Check whether there is an anchor block in the given block */ -static int udf_check_anchor_block(struct super_block *sb, sector_t block, - bool varconv) +static int udf_check_anchor_block(struct super_block *sb, sector_t block) { - struct buffer_head *bh = NULL; - tag *t; + struct buffer_head *bh; uint16_t ident; - uint32_t location; - if (varconv) { - if (udf_fixed_to_variable(block) >= - sb->s_bdev->bd_inode->i_size >> sb->s_blocksize_bits) - return 0; - bh = sb_bread(sb, udf_fixed_to_variable(block)); - } - else - bh = sb_bread(sb, block); + if (UDF_QUERY_FLAG(sb, UDF_FLAG_VARCONV) && + udf_fixed_to_variable(block) >= + sb->s_bdev->bd_inode->i_size >> sb->s_blocksize_bits) + return 0; + bh = udf_read_tagged(sb, block, block, &ident); if (!bh) return 0; - - t = (tag *)bh->b_data; - ident = le16_to_cpu(t->tagIdent); - location = le32_to_cpu(t->tagLocation); brelse(bh); - if (ident != TAG_IDENT_AVDP) - return 0; - return location == block; + + return ident == TAG_IDENT_AVDP; } /* Search for an anchor volume descriptor pointer */ -static sector_t udf_scan_anchors(struct super_block *sb, bool varconv, - sector_t lastblock) +static sector_t udf_scan_anchors(struct super_block *sb, sector_t lastblock) { sector_t last[6]; int i; @@ -739,7 +727,7 @@ static sector_t udf_scan_anchors(struct super_block *sb, bool varconv, sb->s_blocksize_bits) continue; - if (udf_check_anchor_block(sb, last[i], varconv)) { + if (udf_check_anchor_block(sb, last[i])) { sbi->s_anchor[0] = last[i]; sbi->s_anchor[1] = last[i] - 256; return last[i]; @@ -748,17 +736,17 @@ static sector_t udf_scan_anchors(struct super_block *sb, bool varconv, if (last[i] < 256) continue; - if (udf_check_anchor_block(sb, last[i] - 256, varconv)) { + if (udf_check_anchor_block(sb, last[i] - 256)) { sbi->s_anchor[1] = last[i] - 256; return last[i]; } } - if (udf_check_anchor_block(sb, sbi->s_session + 256, varconv)) { + if (udf_check_anchor_block(sb, sbi->s_session + 256)) { sbi->s_anchor[0] = sbi->s_session + 256; return last[0]; } - if (udf_check_anchor_block(sb, sbi->s_session + 512, varconv)) { + if (udf_check_anchor_block(sb, sbi->s_session + 512)) { sbi->s_anchor[0] = sbi->s_session + 512; return last[0]; } @@ -780,23 +768,24 @@ static void udf_find_anchor(struct super_block *sb) int i; struct udf_sb_info *sbi = UDF_SB(sb); - lastblock = udf_scan_anchors(sb, 0, sbi->s_last_block); + lastblock = udf_scan_anchors(sb, sbi->s_last_block); if (lastblock) goto check_anchor; /* No anchor found? Try VARCONV conversion of block numbers */ + UDF_SET_FLAG(sb, UDF_FLAG_VARCONV); /* Firstly, we try to not convert number of the last block */ - lastblock = udf_scan_anchors(sb, 1, + lastblock = udf_scan_anchors(sb, udf_variable_to_fixed(sbi->s_last_block)); - if (lastblock) { - UDF_SET_FLAG(sb, UDF_FLAG_VARCONV); + if (lastblock) goto check_anchor; - } /* Secondly, we try with converted number of the last block */ - lastblock = udf_scan_anchors(sb, 1, sbi->s_last_block); - if (lastblock) - UDF_SET_FLAG(sb, UDF_FLAG_VARCONV); + lastblock = udf_scan_anchors(sb, sbi->s_last_block); + if (!lastblock) { + /* VARCONV didn't help. Clear it. */ + UDF_CLEAR_FLAG(sb, UDF_FLAG_VARCONV); + } check_anchor: /* diff --git a/fs/udf/udfdecl.h b/fs/udf/udfdecl.h index 8fa9c2d7091..8ec865de5f1 100644 --- a/fs/udf/udfdecl.h +++ b/fs/udf/udfdecl.h @@ -16,7 +16,7 @@ #define UDF_PREALLOCATE #define UDF_DEFAULT_PREALLOC_BLOCKS 8 -#define UDFFS_DEBUG +#undef UDFFS_DEBUG #ifdef UDFFS_DEBUG #define udf_debug(f, a...) \ diff --git a/fs/utimes.c b/fs/utimes.c index af059d5cb48..b6b664e7145 100644 --- a/fs/utimes.c +++ b/fs/utimes.c @@ -40,14 +40,9 @@ asmlinkage long sys_utime(char __user *filename, struct utimbuf __user *times) #endif -static bool nsec_special(long nsec) -{ - return nsec == UTIME_OMIT || nsec == UTIME_NOW; -} - static bool nsec_valid(long nsec) { - if (nsec_special(nsec)) + if (nsec == UTIME_OMIT || nsec == UTIME_NOW) return true; return nsec >= 0 && nsec <= 999999999; @@ -102,7 +97,11 @@ long do_utimes(int dfd, char __user *filename, struct timespec *times, int flags if (error) goto dput_and_out; - /* Don't worry, the checks are done in inode_change_ok() */ + if (times && times[0].tv_nsec == UTIME_NOW && + times[1].tv_nsec == UTIME_NOW) + times = NULL; + + /* In most cases, the checks are done in inode_change_ok() */ newattrs.ia_valid = ATTR_CTIME | ATTR_MTIME | ATTR_ATIME; if (times) { error = -EPERM; @@ -124,28 +123,34 @@ long do_utimes(int dfd, char __user *filename, struct timespec *times, int flags newattrs.ia_mtime.tv_nsec = times[1].tv_nsec; newattrs.ia_valid |= ATTR_MTIME_SET; } - } - /* - * If times is NULL or both times are either UTIME_OMIT or - * UTIME_NOW, then need to check permissions, because - * inode_change_ok() won't do it. - */ - if (!times || (nsec_special(times[0].tv_nsec) && - nsec_special(times[1].tv_nsec))) { + /* + * For the UTIME_OMIT/UTIME_NOW and UTIME_NOW/UTIME_OMIT + * cases, we need to make an extra check that is not done by + * inode_change_ok(). + */ + if (((times[0].tv_nsec == UTIME_NOW && + times[1].tv_nsec == UTIME_OMIT) + || + (times[0].tv_nsec == UTIME_OMIT && + times[1].tv_nsec == UTIME_NOW)) + && !is_owner_or_cap(inode)) + goto mnt_drop_write_and_out; + } else { + + /* + * If times is NULL (or both times are UTIME_NOW), + * then we need to check permissions, because + * inode_change_ok() won't do it. + */ error = -EACCES; if (IS_IMMUTABLE(inode)) goto mnt_drop_write_and_out; if (!is_owner_or_cap(inode)) { - if (f) { - if (!(f->f_mode & FMODE_WRITE)) - goto mnt_drop_write_and_out; - } else { - error = vfs_permission(&nd, MAY_WRITE); - if (error) - goto mnt_drop_write_and_out; - } + error = permission(inode, MAY_WRITE, NULL); + if (error) + goto mnt_drop_write_and_out; } } mutex_lock(&inode->i_mutex); @@ -169,14 +174,6 @@ asmlinkage long sys_utimensat(int dfd, char __user *filename, struct timespec __ if (utimes) { if (copy_from_user(&tstimes, utimes, sizeof(tstimes))) return -EFAULT; - if ((tstimes[0].tv_nsec == UTIME_OMIT || - tstimes[0].tv_nsec == UTIME_NOW) && - tstimes[0].tv_sec != 0) - return -EINVAL; - if ((tstimes[1].tv_nsec == UTIME_OMIT || - tstimes[1].tv_nsec == UTIME_NOW) && - tstimes[1].tv_sec != 0) - return -EINVAL; /* Nothing to do, we must not even check the path. */ if (tstimes[0].tv_nsec == UTIME_OMIT && |