diff options
author | David S. Miller <davem@davemloft.net> | 2016-01-13 05:21:27 (GMT) |
---|---|---|
committer | David S. Miller <davem@davemloft.net> | 2016-01-13 05:21:27 (GMT) |
commit | ddb5388ffd0ad75d07e7b78181a0b579824ba6f0 (patch) | |
tree | be1e2bd103c69d7bbace3fffd97bc3d714bbc3d7 /fs | |
parent | ccdf6ce6a8dba374668ae9b4d763e19903611c38 (diff) | |
parent | 67990608c8b95d2b8ccc29932376ae73d5818727 (diff) | |
download | linux-ddb5388ffd0ad75d07e7b78181a0b579824ba6f0.tar.xz |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux
Diffstat (limited to 'fs')
221 files changed, 2986 insertions, 2498 deletions
diff --git a/fs/9p/acl.c b/fs/9p/acl.c index a7e2889..9da967f 100644 --- a/fs/9p/acl.c +++ b/fs/9p/acl.c @@ -67,8 +67,8 @@ int v9fs_get_acl(struct inode *inode, struct p9_fid *fid) return 0; } /* get the default/access acl values and cache them */ - dacl = __v9fs_get_acl(fid, POSIX_ACL_XATTR_DEFAULT); - pacl = __v9fs_get_acl(fid, POSIX_ACL_XATTR_ACCESS); + dacl = __v9fs_get_acl(fid, XATTR_NAME_POSIX_ACL_DEFAULT); + pacl = __v9fs_get_acl(fid, XATTR_NAME_POSIX_ACL_ACCESS); if (!IS_ERR(dacl) && !IS_ERR(pacl)) { set_cached_acl(inode, ACL_TYPE_DEFAULT, dacl); @@ -133,10 +133,10 @@ static int v9fs_set_acl(struct p9_fid *fid, int type, struct posix_acl *acl) goto err_free_out; switch (type) { case ACL_TYPE_ACCESS: - name = POSIX_ACL_XATTR_ACCESS; + name = XATTR_NAME_POSIX_ACL_ACCESS; break; case ACL_TYPE_DEFAULT: - name = POSIX_ACL_XATTR_DEFAULT; + name = XATTR_NAME_POSIX_ACL_DEFAULT; break; default: BUG(); @@ -220,15 +220,12 @@ static int v9fs_xattr_get_acl(const struct xattr_handler *handler, struct posix_acl *acl; int error; - if (strcmp(name, "") != 0) - return -EINVAL; - v9ses = v9fs_dentry2v9ses(dentry); /* * We allow set/get/list of acl when access=client is not specified */ if ((v9ses->flags & V9FS_ACCESS_MASK) != V9FS_ACCESS_CLIENT) - return v9fs_xattr_get(dentry, handler->prefix, buffer, size); + return v9fs_xattr_get(dentry, handler->name, buffer, size); acl = v9fs_get_cached_acl(d_inode(dentry), handler->flags); if (IS_ERR(acl)) @@ -250,16 +247,13 @@ static int v9fs_xattr_set_acl(const struct xattr_handler *handler, struct v9fs_session_info *v9ses; struct inode *inode = d_inode(dentry); - if (strcmp(name, "") != 0) - return -EINVAL; - v9ses = v9fs_dentry2v9ses(dentry); /* * set the attribute on the remote. Without even looking at the * xattr value. We leave it to the server to validate */ if ((v9ses->flags & V9FS_ACCESS_MASK) != V9FS_ACCESS_CLIENT) - return v9fs_xattr_set(dentry, handler->prefix, value, size, + return v9fs_xattr_set(dentry, handler->name, value, size, flags); if (S_ISLNK(inode->i_mode)) @@ -319,7 +313,7 @@ static int v9fs_xattr_set_acl(const struct xattr_handler *handler, default: BUG(); } - retval = v9fs_xattr_set(dentry, handler->prefix, value, size, flags); + retval = v9fs_xattr_set(dentry, handler->name, value, size, flags); if (!retval) set_cached_acl(inode, handler->flags, acl); err_out: @@ -328,14 +322,14 @@ err_out: } const struct xattr_handler v9fs_xattr_acl_access_handler = { - .prefix = POSIX_ACL_XATTR_ACCESS, + .name = XATTR_NAME_POSIX_ACL_ACCESS, .flags = ACL_TYPE_ACCESS, .get = v9fs_xattr_get_acl, .set = v9fs_xattr_set_acl, }; const struct xattr_handler v9fs_xattr_acl_default_handler = { - .prefix = POSIX_ACL_XATTR_DEFAULT, + .name = XATTR_NAME_POSIX_ACL_DEFAULT, .flags = ACL_TYPE_DEFAULT, .get = v9fs_xattr_get_acl, .set = v9fs_xattr_set_acl, diff --git a/fs/9p/cache.c b/fs/9p/cache.c index a69260f..103ca5e 100644 --- a/fs/9p/cache.c +++ b/fs/9p/cache.c @@ -243,14 +243,14 @@ void v9fs_cache_inode_set_cookie(struct inode *inode, struct file *filp) if (!v9inode->fscache) return; - spin_lock(&v9inode->fscache_lock); + mutex_lock(&v9inode->fscache_lock); if ((filp->f_flags & O_ACCMODE) != O_RDONLY) v9fs_cache_inode_flush_cookie(inode); else v9fs_cache_inode_get_cookie(inode); - spin_unlock(&v9inode->fscache_lock); + mutex_unlock(&v9inode->fscache_lock); } void v9fs_cache_inode_reset_cookie(struct inode *inode) @@ -264,7 +264,7 @@ void v9fs_cache_inode_reset_cookie(struct inode *inode) old = v9inode->fscache; - spin_lock(&v9inode->fscache_lock); + mutex_lock(&v9inode->fscache_lock); fscache_relinquish_cookie(v9inode->fscache, 1); v9ses = v9fs_inode2v9ses(inode); @@ -274,7 +274,7 @@ void v9fs_cache_inode_reset_cookie(struct inode *inode) p9_debug(P9_DEBUG_FSC, "inode %p revalidating cookie old %p new %p\n", inode, old, v9inode->fscache); - spin_unlock(&v9inode->fscache_lock); + mutex_unlock(&v9inode->fscache_lock); } int __v9fs_fscache_release_page(struct page *page, gfp_t gfp) diff --git a/fs/9p/v9fs.h b/fs/9p/v9fs.h index 0923f2c..6877050 100644 --- a/fs/9p/v9fs.h +++ b/fs/9p/v9fs.h @@ -123,7 +123,7 @@ struct v9fs_session_info { struct v9fs_inode { #ifdef CONFIG_9P_FSCACHE - spinlock_t fscache_lock; + struct mutex fscache_lock; struct fscache_cookie *fscache; #endif struct p9_qid qid; diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index 5110785..3a08b3e 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -244,7 +244,7 @@ struct inode *v9fs_alloc_inode(struct super_block *sb) return NULL; #ifdef CONFIG_9P_FSCACHE v9inode->fscache = NULL; - spin_lock_init(&v9inode->fscache_lock); + mutex_init(&v9inode->fscache_lock); #endif v9inode->writeback_fid = NULL; v9inode->cache_validity = 0; @@ -1223,18 +1223,26 @@ ino_t v9fs_qid2ino(struct p9_qid *qid) } /** - * v9fs_vfs_follow_link - follow a symlink path + * v9fs_vfs_get_link - follow a symlink path * @dentry: dentry for symlink - * @cookie: place to pass the data to put_link() + * @inode: inode for symlink + * @done: delayed call for when we are done with the return value */ -static const char *v9fs_vfs_follow_link(struct dentry *dentry, void **cookie) +static const char *v9fs_vfs_get_link(struct dentry *dentry, + struct inode *inode, + struct delayed_call *done) { - struct v9fs_session_info *v9ses = v9fs_dentry2v9ses(dentry); - struct p9_fid *fid = v9fs_fid_lookup(dentry); + struct v9fs_session_info *v9ses; + struct p9_fid *fid; struct p9_wstat *st; char *res; + if (!dentry) + return ERR_PTR(-ECHILD); + + v9ses = v9fs_dentry2v9ses(dentry); + fid = v9fs_fid_lookup(dentry); p9_debug(P9_DEBUG_VFS, "%pd\n", dentry); if (IS_ERR(fid)) @@ -1259,7 +1267,8 @@ static const char *v9fs_vfs_follow_link(struct dentry *dentry, void **cookie) p9stat_free(st); kfree(st); - return *cookie = res; + set_delayed_call(done, kfree_link, res); + return res; } /** @@ -1452,8 +1461,7 @@ static const struct inode_operations v9fs_file_inode_operations = { static const struct inode_operations v9fs_symlink_inode_operations = { .readlink = generic_readlink, - .follow_link = v9fs_vfs_follow_link, - .put_link = kfree_put_link, + .get_link = v9fs_vfs_get_link, .getattr = v9fs_vfs_getattr, .setattr = v9fs_vfs_setattr, }; diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c index cb899af..a34702c 100644 --- a/fs/9p/vfs_inode_dotl.c +++ b/fs/9p/vfs_inode_dotl.c @@ -899,26 +899,34 @@ error: } /** - * v9fs_vfs_follow_link_dotl - follow a symlink path + * v9fs_vfs_get_link_dotl - follow a symlink path * @dentry: dentry for symlink - * @cookie: place to pass the data to put_link() + * @inode: inode for symlink + * @done: destructor for return value */ static const char * -v9fs_vfs_follow_link_dotl(struct dentry *dentry, void **cookie) +v9fs_vfs_get_link_dotl(struct dentry *dentry, + struct inode *inode, + struct delayed_call *done) { - struct p9_fid *fid = v9fs_fid_lookup(dentry); + struct p9_fid *fid; char *target; int retval; + if (!dentry) + return ERR_PTR(-ECHILD); + p9_debug(P9_DEBUG_VFS, "%pd\n", dentry); + fid = v9fs_fid_lookup(dentry); if (IS_ERR(fid)) return ERR_CAST(fid); retval = p9_client_readlink(fid, &target); if (retval) return ERR_PTR(retval); - return *cookie = target; + set_delayed_call(done, kfree_link, target); + return target; } int v9fs_refresh_inode_dotl(struct p9_fid *fid, struct inode *inode) @@ -984,8 +992,7 @@ const struct inode_operations v9fs_file_inode_operations_dotl = { const struct inode_operations v9fs_symlink_inode_operations_dotl = { .readlink = generic_readlink, - .follow_link = v9fs_vfs_follow_link_dotl, - .put_link = kfree_put_link, + .get_link = v9fs_vfs_get_link_dotl, .getattr = v9fs_vfs_getattr_dotl, .setattr = v9fs_vfs_setattr_dotl, .setxattr = generic_setxattr, diff --git a/fs/9p/xattr.c b/fs/9p/xattr.c index e3d026a..9dd9b47 100644 --- a/fs/9p/xattr.c +++ b/fs/9p/xattr.c @@ -143,8 +143,6 @@ static int v9fs_xattr_handler_get(const struct xattr_handler *handler, { const char *full_name = xattr_full_name(handler, name); - if (strcmp(name, "") == 0) - return -EINVAL; return v9fs_xattr_get(dentry, full_name, buffer, size); } @@ -154,8 +152,6 @@ static int v9fs_xattr_handler_set(const struct xattr_handler *handler, { const char *full_name = xattr_full_name(handler, name); - if (strcmp(name, "") == 0) - return -EINVAL; return v9fs_xattr_set(dentry, full_name, value, size, flags); } @@ -73,6 +73,16 @@ config FILE_LOCKING for filesystems like NFS and for the flock() system call. Disabling this option saves about 11k. +config MANDATORY_FILE_LOCKING + bool "Enable Mandatory file locking" + depends on FILE_LOCKING + default y + help + This option enables files appropriately marked files on appropriely + mounted filesystems to support mandatory locking. + + To the best of my knowledge this is dead code that no one cares about. + source "fs/notify/Kconfig" source "fs/quota/Kconfig" diff --git a/fs/adfs/adfs.h b/fs/adfs/adfs.h index 24575d9..ea4aba5 100644 --- a/fs/adfs/adfs.h +++ b/fs/adfs/adfs.h @@ -45,7 +45,7 @@ struct adfs_dir_ops; struct adfs_sb_info { union { struct { struct adfs_discmap *s_map; /* bh list containing map */ - struct adfs_dir_ops *s_dir; /* directory operations */ + const struct adfs_dir_ops *s_dir; /* directory operations */ }; struct rcu_head rcu; /* used only at shutdown time */ }; @@ -168,8 +168,8 @@ void __adfs_error(struct super_block *sb, const char *function, extern const struct inode_operations adfs_dir_inode_operations; extern const struct file_operations adfs_dir_operations; extern const struct dentry_operations adfs_dentry_operations; -extern struct adfs_dir_ops adfs_f_dir_ops; -extern struct adfs_dir_ops adfs_fplus_dir_ops; +extern const struct adfs_dir_ops adfs_f_dir_ops; +extern const struct adfs_dir_ops adfs_fplus_dir_ops; extern int adfs_dir_update(struct super_block *sb, struct object_info *obj, int wait); diff --git a/fs/adfs/dir.c b/fs/adfs/dir.c index 51c279a..fd4cf2c 100644 --- a/fs/adfs/dir.c +++ b/fs/adfs/dir.c @@ -21,7 +21,7 @@ adfs_readdir(struct file *file, struct dir_context *ctx) { struct inode *inode = file_inode(file); struct super_block *sb = inode->i_sb; - struct adfs_dir_ops *ops = ADFS_SB(sb)->s_dir; + const struct adfs_dir_ops *ops = ADFS_SB(sb)->s_dir; struct object_info obj; struct adfs_dir dir; int ret = 0; @@ -69,7 +69,7 @@ adfs_dir_update(struct super_block *sb, struct object_info *obj, int wait) { int ret = -EINVAL; #ifdef CONFIG_ADFS_FS_RW - struct adfs_dir_ops *ops = ADFS_SB(sb)->s_dir; + const struct adfs_dir_ops *ops = ADFS_SB(sb)->s_dir; struct adfs_dir dir; printk(KERN_INFO "adfs_dir_update: object %06X in dir %06X\n", @@ -129,7 +129,7 @@ static int adfs_dir_lookup_byname(struct inode *inode, struct qstr *name, struct object_info *obj) { struct super_block *sb = inode->i_sb; - struct adfs_dir_ops *ops = ADFS_SB(sb)->s_dir; + const struct adfs_dir_ops *ops = ADFS_SB(sb)->s_dir; struct adfs_dir dir; int ret; diff --git a/fs/adfs/dir_f.c b/fs/adfs/dir_f.c index 4bbe853..0fbfd0b 100644 --- a/fs/adfs/dir_f.c +++ b/fs/adfs/dir_f.c @@ -476,7 +476,7 @@ adfs_f_free(struct adfs_dir *dir) dir->sb = NULL; } -struct adfs_dir_ops adfs_f_dir_ops = { +const struct adfs_dir_ops adfs_f_dir_ops = { .read = adfs_f_read, .setpos = adfs_f_setpos, .getnext = adfs_f_getnext, diff --git a/fs/adfs/dir_fplus.c b/fs/adfs/dir_fplus.c index 82d14cd..c92cfb6 100644 --- a/fs/adfs/dir_fplus.c +++ b/fs/adfs/dir_fplus.c @@ -256,7 +256,7 @@ adfs_fplus_free(struct adfs_dir *dir) dir->sb = NULL; } -struct adfs_dir_ops adfs_fplus_dir_ops = { +const struct adfs_dir_ops adfs_fplus_dir_ops = { .read = adfs_fplus_read, .setpos = adfs_fplus_setpos, .getnext = adfs_fplus_getnext, diff --git a/fs/affs/affs.h b/fs/affs/affs.h index c69a87e..cc2b2ef 100644 --- a/fs/affs/affs.h +++ b/fs/affs/affs.h @@ -138,7 +138,7 @@ extern int affs_remove_hash(struct inode *dir, struct buffer_head *rem_bh); extern int affs_remove_header(struct dentry *dentry); extern u32 affs_checksum_block(struct super_block *sb, struct buffer_head *bh); extern void affs_fix_checksum(struct super_block *sb, struct buffer_head *bh); -extern void secs_to_datestamp(time_t secs, struct affs_date *ds); +extern void secs_to_datestamp(time64_t secs, struct affs_date *ds); extern umode_t prot_to_mode(u32 prot); extern void mode_to_prot(struct inode *inode); __printf(3, 4) diff --git a/fs/affs/amigaffs.c b/fs/affs/amigaffs.c index 5fa92bc..d6c7a51 100644 --- a/fs/affs/amigaffs.c +++ b/fs/affs/amigaffs.c @@ -8,6 +8,7 @@ * Please send bug reports to: hjw@zvw.de */ +#include <linux/math64.h> #include "affs.h" /* @@ -366,22 +367,22 @@ affs_fix_checksum(struct super_block *sb, struct buffer_head *bh) } void -secs_to_datestamp(time_t secs, struct affs_date *ds) +secs_to_datestamp(time64_t secs, struct affs_date *ds) { u32 days; u32 minute; + s32 rem; secs -= sys_tz.tz_minuteswest * 60 + ((8 * 365 + 2) * 24 * 60 * 60); if (secs < 0) secs = 0; - days = secs / 86400; - secs -= days * 86400; - minute = secs / 60; - secs -= minute * 60; + days = div_s64_rem(secs, 86400, &rem); + minute = rem / 60; + rem -= minute * 60; ds->days = cpu_to_be32(days); ds->mins = cpu_to_be32(minute); - ds->ticks = cpu_to_be32(secs * 50); + ds->ticks = cpu_to_be32(rem * 50); } umode_t diff --git a/fs/affs/inode.c b/fs/affs/inode.c index 1734950..0fdb0f5 100644 --- a/fs/affs/inode.c +++ b/fs/affs/inode.c @@ -140,6 +140,7 @@ struct inode *affs_iget(struct super_block *sb, unsigned long ino) break; case ST_SOFTLINK: inode->i_mode |= S_IFLNK; + inode_nohighmem(inode); inode->i_op = &affs_symlink_inode_operations; inode->i_data.a_ops = &affs_symlink_aops; break; diff --git a/fs/affs/namei.c b/fs/affs/namei.c index 181e05b..00d3002 100644 --- a/fs/affs/namei.c +++ b/fs/affs/namei.c @@ -344,6 +344,7 @@ affs_symlink(struct inode *dir, struct dentry *dentry, const char *symname) return -ENOSPC; inode->i_op = &affs_symlink_inode_operations; + inode_nohighmem(inode); inode->i_data.a_ops = &affs_symlink_aops; inode->i_mode = S_IFLNK | 0777; mode_to_prot(inode); diff --git a/fs/affs/super.c b/fs/affs/super.c index 5b50c4c..8836df5 100644 --- a/fs/affs/super.c +++ b/fs/affs/super.c @@ -32,7 +32,7 @@ affs_commit_super(struct super_block *sb, int wait) struct affs_root_tail *tail = AFFS_ROOT_TAIL(sb, bh); lock_buffer(bh); - secs_to_datestamp(get_seconds(), &tail->disk_change); + secs_to_datestamp(ktime_get_real_seconds(), &tail->disk_change); affs_fix_checksum(sb, bh); unlock_buffer(bh); diff --git a/fs/affs/symlink.c b/fs/affs/symlink.c index ea5b69a..69b03db 100644 --- a/fs/affs/symlink.c +++ b/fs/affs/symlink.c @@ -14,13 +14,13 @@ static int affs_symlink_readpage(struct file *file, struct page *page) { struct buffer_head *bh; struct inode *inode = page->mapping->host; - char *link = kmap(page); + char *link = page_address(page); struct slink_front *lf; int i, j; char c; char lc; - pr_debug("follow_link(ino=%lu)\n", inode->i_ino); + pr_debug("get_link(ino=%lu)\n", inode->i_ino); bh = affs_bread(inode->i_sb, inode->i_ino); if (!bh) @@ -57,12 +57,10 @@ static int affs_symlink_readpage(struct file *file, struct page *page) link[i] = '\0'; affs_brelse(bh); SetPageUptodate(page); - kunmap(page); unlock_page(page); return 0; fail: SetPageError(page); - kunmap(page); unlock_page(page); return -EIO; } @@ -73,7 +71,6 @@ const struct address_space_operations affs_symlink_aops = { const struct inode_operations affs_symlink_inode_operations = { .readlink = generic_readlink, - .follow_link = page_follow_link_light, - .put_link = page_put_link, + .get_link = page_get_link, .setattr = affs_notify_change, }; diff --git a/fs/afs/inode.c b/fs/afs/inode.c index e06f5a2..86cc726 100644 --- a/fs/afs/inode.c +++ b/fs/afs/inode.c @@ -56,6 +56,7 @@ static int afs_inode_map_status(struct afs_vnode *vnode, struct key *key) case AFS_FTYPE_SYMLINK: inode->i_mode = S_IFLNK | vnode->status.mode; inode->i_op = &page_symlink_inode_operations; + inode_nohighmem(inode); break; default: printk("kAFS: AFS vnode with undefined type\n"); diff --git a/fs/afs/proc.c b/fs/afs/proc.c index 24a905b..2853b40 100644 --- a/fs/afs/proc.c +++ b/fs/afs/proc.c @@ -230,14 +230,9 @@ static ssize_t afs_proc_cells_write(struct file *file, const char __user *buf, if (size <= 1 || size >= PAGE_SIZE) return -EINVAL; - kbuf = kmalloc(size + 1, GFP_KERNEL); - if (!kbuf) - return -ENOMEM; - - ret = -EFAULT; - if (copy_from_user(kbuf, buf, size) != 0) - goto done; - kbuf[size] = 0; + kbuf = memdup_user_nul(buf, size); + if (IS_ERR(kbuf)) + return PTR_ERR(kbuf); /* trim to first NL */ name = memchr(kbuf, '\n', size); @@ -315,15 +310,9 @@ static ssize_t afs_proc_rootcell_write(struct file *file, if (size <= 1 || size >= PAGE_SIZE) return -EINVAL; - ret = -ENOMEM; - kbuf = kmalloc(size + 1, GFP_KERNEL); - if (!kbuf) - goto nomem; - - ret = -EFAULT; - if (copy_from_user(kbuf, buf, size) != 0) - goto infault; - kbuf[size] = 0; + kbuf = memdup_user_nul(buf, size); + if (IS_ERR(kbuf)) + return PTR_ERR(kbuf); /* trim to first NL */ s = memchr(kbuf, '\n', size); @@ -337,9 +326,7 @@ static ssize_t afs_proc_rootcell_write(struct file *file, if (ret >= 0) ret = size; /* consume everything, always */ -infault: kfree(kbuf); -nomem: _leave(" = %d", ret); return ret; } diff --git a/fs/autofs4/symlink.c b/fs/autofs4/symlink.c index da0c334..84e037d 100644 --- a/fs/autofs4/symlink.c +++ b/fs/autofs4/symlink.c @@ -12,10 +12,16 @@ #include "autofs_i.h" -static const char *autofs4_follow_link(struct dentry *dentry, void **cookie) +static const char *autofs4_get_link(struct dentry *dentry, + struct inode *inode, + struct delayed_call *done) { - struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb); - struct autofs_info *ino = autofs4_dentry_ino(dentry); + struct autofs_sb_info *sbi; + struct autofs_info *ino; + if (!dentry) + return ERR_PTR(-ECHILD); + sbi = autofs4_sbi(dentry->d_sb); + ino = autofs4_dentry_ino(dentry); if (ino && !autofs4_oz_mode(sbi)) ino->last_used = jiffies; return d_inode(dentry)->i_private; @@ -23,5 +29,5 @@ static const char *autofs4_follow_link(struct dentry *dentry, void **cookie) const struct inode_operations autofs4_symlink_inode_operations = { .readlink = generic_readlink, - .follow_link = autofs4_follow_link + .get_link = autofs4_get_link }; diff --git a/fs/bad_inode.c b/fs/bad_inode.c index 861b1e1..103f5d7 100644 --- a/fs/bad_inode.c +++ b/fs/bad_inode.c @@ -192,7 +192,7 @@ EXPORT_SYMBOL(make_bad_inode); * Returns true if the inode in question has been marked as bad. */ -int is_bad_inode(struct inode *inode) +bool is_bad_inode(struct inode *inode) { return (inode->i_op == &bad_inode_ops); } diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c index 46aedac..25250fa 100644 --- a/fs/befs/linuxvfs.c +++ b/fs/befs/linuxvfs.c @@ -42,7 +42,7 @@ static struct inode *befs_iget(struct super_block *, unsigned long); static struct inode *befs_alloc_inode(struct super_block *sb); static void befs_destroy_inode(struct inode *inode); static void befs_destroy_inodecache(void); -static const char *befs_follow_link(struct dentry *, void **); +static int befs_symlink_readpage(struct file *, struct page *); static int befs_utf2nls(struct super_block *sb, const char *in, int in_len, char **out, int *out_len); static int befs_nls2utf(struct super_block *sb, const char *in, int in_len, @@ -79,10 +79,8 @@ static const struct address_space_operations befs_aops = { .bmap = befs_bmap, }; -static const struct inode_operations befs_symlink_inode_operations = { - .readlink = generic_readlink, - .follow_link = befs_follow_link, - .put_link = kfree_put_link, +static const struct address_space_operations befs_symlink_aops = { + .readpage = befs_symlink_readpage, }; /* @@ -398,7 +396,9 @@ static struct inode *befs_iget(struct super_block *sb, unsigned long ino) inode->i_fop = &befs_dir_operations; } else if (S_ISLNK(inode->i_mode)) { if (befs_ino->i_flags & BEFS_LONG_SYMLINK) { - inode->i_op = &befs_symlink_inode_operations; + inode->i_op = &page_symlink_inode_operations; + inode_nohighmem(inode); + inode->i_mapping->a_ops = &befs_symlink_aops; } else { inode->i_link = befs_ino->i_data.symlink; inode->i_op = &simple_symlink_inode_operations; @@ -463,31 +463,33 @@ befs_destroy_inodecache(void) * The data stream become link name. Unless the LONG_SYMLINK * flag is set. */ -static const char * -befs_follow_link(struct dentry *dentry, void **cookie) +static int befs_symlink_readpage(struct file *unused, struct page *page) { - struct super_block *sb = dentry->d_sb; - struct befs_inode_info *befs_ino = BEFS_I(d_inode(dentry)); + struct inode *inode = page->mapping->host; + struct super_block *sb = inode->i_sb; + struct befs_inode_info *befs_ino = BEFS_I(inode); befs_data_stream *data = &befs_ino->i_data.ds; befs_off_t len = data->size; - char *link; + char *link = page_address(page); - if (len == 0) { + if (len == 0 || len > PAGE_SIZE) { befs_error(sb, "Long symlink with illegal length"); - return ERR_PTR(-EIO); + goto fail; } befs_debug(sb, "Follow long symlink"); - link = kmalloc(len, GFP_NOFS); - if (!link) - return ERR_PTR(-ENOMEM); if (befs_read_lsymlink(sb, data, link, len) != len) { - kfree(link); befs_error(sb, "Failed to read entire long symlink"); - return ERR_PTR(-EIO); + goto fail; } link[len - 1] = '\0'; - return *cookie = link; + SetPageUptodate(page); + unlock_page(page); + return 0; +fail: + SetPageError(page); + unlock_page(page); + return -EIO; } /* diff --git a/fs/block_dev.c b/fs/block_dev.c index 44d4a1e..01b8e0d 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1042,12 +1042,9 @@ EXPORT_SYMBOL_GPL(bd_unlink_disk_holder); static void flush_disk(struct block_device *bdev, bool kill_dirty) { if (__invalidate_device(bdev, kill_dirty)) { - char name[BDEVNAME_SIZE] = ""; - - if (bdev->bd_disk) - disk_name(bdev->bd_disk, 0, name); printk(KERN_WARNING "VFS: busy inodes on changed media or " - "resized disk %s\n", name); + "resized disk %s\n", + bdev->bd_disk ? bdev->bd_disk->disk_name : ""); } if (!bdev->bd_disk) @@ -1071,12 +1068,9 @@ void check_disk_size_change(struct gendisk *disk, struct block_device *bdev) disk_size = (loff_t)get_capacity(disk) << 9; bdev_size = i_size_read(bdev->bd_inode); if (disk_size != bdev_size) { - char name[BDEVNAME_SIZE]; - - disk_name(disk, 0, name); printk(KERN_INFO "%s: detected capacity change from %lld to %lld\n", - name, bdev_size, disk_size); + disk->disk_name, bdev_size, disk_size); i_size_write(bdev->bd_inode, disk_size); flush_disk(bdev, false); } diff --git a/fs/btrfs/acl.c b/fs/btrfs/acl.c index 9a0124a..f89db0c 100644 --- a/fs/btrfs/acl.c +++ b/fs/btrfs/acl.c @@ -37,10 +37,10 @@ struct posix_acl *btrfs_get_acl(struct inode *inode, int type) switch (type) { case ACL_TYPE_ACCESS: - name = POSIX_ACL_XATTR_ACCESS; + name = XATTR_NAME_POSIX_ACL_ACCESS; break; case ACL_TYPE_DEFAULT: - name = POSIX_ACL_XATTR_DEFAULT; + name = XATTR_NAME_POSIX_ACL_DEFAULT; break; default: BUG(); @@ -81,7 +81,7 @@ static int __btrfs_set_acl(struct btrfs_trans_handle *trans, switch (type) { case ACL_TYPE_ACCESS: - name = POSIX_ACL_XATTR_ACCESS; + name = XATTR_NAME_POSIX_ACL_ACCESS; if (acl) { ret = posix_acl_equiv_mode(acl, &inode->i_mode); if (ret < 0) @@ -94,7 +94,7 @@ static int __btrfs_set_acl(struct btrfs_trans_handle *trans, case ACL_TYPE_DEFAULT: if (!S_ISDIR(inode->i_mode)) return acl ? -EINVAL : 0; - name = POSIX_ACL_XATTR_DEFAULT; + name = XATTR_NAME_POSIX_ACL_DEFAULT; break; default: return -EINVAL; diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 35489e7..b7e4e34 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -4024,7 +4024,8 @@ void btrfs_get_block_group_info(struct list_head *groups_list, struct btrfs_ioctl_space_info *space); void update_ioctl_balance_args(struct btrfs_fs_info *fs_info, int lock, struct btrfs_ioctl_balance_args *bargs); - +ssize_t btrfs_dedupe_file_range(struct file *src_file, u64 loff, u64 olen, + struct file *dst_file, u64 dst_loff); /* file.c */ int btrfs_auto_defrag_init(void); @@ -4055,6 +4056,11 @@ int btrfs_dirty_pages(struct btrfs_root *root, struct inode *inode, loff_t pos, size_t write_bytes, struct extent_state **cached); int btrfs_fdatawrite_range(struct inode *inode, loff_t start, loff_t end); +ssize_t btrfs_copy_file_range(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + size_t len, unsigned int flags); +int btrfs_clone_file_range(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, u64 len); /* tree-defrag.c */ int btrfs_defrag_leaves(struct btrfs_trans_handle *trans, diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 974be09..42a378a 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -923,7 +923,7 @@ static int check_async_write(struct inode *inode, unsigned long bio_flags) if (bio_flags & EXTENT_BIO_TREE_LOG) return 0; #ifdef CONFIG_X86 - if (cpu_has_xmm4_2) + if (static_cpu_has_safe(X86_FEATURE_XMM4_2)) return 0; #endif return 1; diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 0f09526..e3d9022 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -2934,6 +2934,9 @@ const struct file_operations btrfs_file_operations = { #ifdef CONFIG_COMPAT .compat_ioctl = btrfs_ioctl, #endif + .copy_file_range = btrfs_copy_file_range, + .clone_file_range = btrfs_clone_file_range, + .dedupe_file_range = btrfs_dedupe_file_range, }; void btrfs_auto_defrag_exit(void) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index a70c579..3b8856e 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -3550,10 +3550,10 @@ static noinline int acls_after_inode_item(struct extent_buffer *leaf, int scanned = 0; if (!xattr_access) { - xattr_access = btrfs_name_hash(POSIX_ACL_XATTR_ACCESS, - strlen(POSIX_ACL_XATTR_ACCESS)); - xattr_default = btrfs_name_hash(POSIX_ACL_XATTR_DEFAULT, - strlen(POSIX_ACL_XATTR_DEFAULT)); + xattr_access = btrfs_name_hash(XATTR_NAME_POSIX_ACL_ACCESS, + strlen(XATTR_NAME_POSIX_ACL_ACCESS)); + xattr_default = btrfs_name_hash(XATTR_NAME_POSIX_ACL_DEFAULT, + strlen(XATTR_NAME_POSIX_ACL_DEFAULT)); } slot++; @@ -3774,6 +3774,7 @@ cache_acl: break; case S_IFLNK: inode->i_op = &btrfs_symlink_inode_operations; + inode_nohighmem(inode); inode->i_mapping->a_ops = &btrfs_symlink_aops; break; default: @@ -9705,6 +9706,7 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry, btrfs_free_path(path); inode->i_op = &btrfs_symlink_inode_operations; + inode_nohighmem(inode); inode->i_mapping->a_ops = &btrfs_symlink_aops; inode_set_bytes(inode, name_len); btrfs_i_size_write(inode, name_len); @@ -9994,7 +9996,7 @@ static const struct inode_operations btrfs_dir_inode_operations = { .setattr = btrfs_setattr, .mknod = btrfs_mknod, .setxattr = btrfs_setxattr, - .getxattr = btrfs_getxattr, + .getxattr = generic_getxattr, .listxattr = btrfs_listxattr, .removexattr = btrfs_removexattr, .permission = btrfs_permission, @@ -10071,7 +10073,7 @@ static const struct inode_operations btrfs_file_inode_operations = { .getattr = btrfs_getattr, .setattr = btrfs_setattr, .setxattr = btrfs_setxattr, - .getxattr = btrfs_getxattr, + .getxattr = generic_getxattr, .listxattr = btrfs_listxattr, .removexattr = btrfs_removexattr, .permission = btrfs_permission, @@ -10085,7 +10087,7 @@ static const struct inode_operations btrfs_special_inode_operations = { .setattr = btrfs_setattr, .permission = btrfs_permission, .setxattr = btrfs_setxattr, - .getxattr = btrfs_getxattr, + .getxattr = generic_getxattr, .listxattr = btrfs_listxattr, .removexattr = btrfs_removexattr, .get_acl = btrfs_get_acl, @@ -10094,13 +10096,12 @@ static const struct inode_operations btrfs_special_inode_operations = { }; static const struct inode_operations btrfs_symlink_inode_operations = { .readlink = generic_readlink, - .follow_link = page_follow_link_light, - .put_link = page_put_link, + .get_link = page_get_link, .getattr = btrfs_getattr, .setattr = btrfs_setattr, .permission = btrfs_permission, .setxattr = btrfs_setxattr, - .getxattr = btrfs_getxattr, + .getxattr = generic_getxattr, .listxattr = btrfs_listxattr, .removexattr = btrfs_removexattr, .update_time = btrfs_update_time, diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index da94138..e219973 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -2962,7 +2962,7 @@ static int btrfs_cmp_data(struct inode *src, u64 loff, struct inode *dst, flush_dcache_page(dst_page); if (memcmp(addr, dst_addr, cmp_len)) - ret = BTRFS_SAME_DATA_DIFFERS; + ret = -EBADE; kunmap_atomic(addr); kunmap_atomic(dst_addr); @@ -3098,53 +3098,16 @@ out_unlock: #define BTRFS_MAX_DEDUPE_LEN (16 * 1024 * 1024) -static long btrfs_ioctl_file_extent_same(struct file *file, - struct btrfs_ioctl_same_args __user *argp) +ssize_t btrfs_dedupe_file_range(struct file *src_file, u64 loff, u64 olen, + struct file *dst_file, u64 dst_loff) { - struct btrfs_ioctl_same_args *same = NULL; - struct btrfs_ioctl_same_extent_info *info; - struct inode *src = file_inode(file); - u64 off; - u64 len; - int i; - int ret; - unsigned long size; + struct inode *src = file_inode(src_file); + struct inode *dst = file_inode(dst_file); u64 bs = BTRFS_I(src)->root->fs_info->sb->s_blocksize; - bool is_admin = capable(CAP_SYS_ADMIN); - u16 count; - - if (!(file->f_mode & FMODE_READ)) - return -EINVAL; - - ret = mnt_want_write_file(file); - if (ret) - return ret; - - if (get_user(count, &argp->dest_count)) { - ret = -EFAULT; - goto out; - } - - size = offsetof(struct btrfs_ioctl_same_args __user, info[count]); - - same = memdup_user(argp, size); - - if (IS_ERR(same)) { - ret = PTR_ERR(same); - same = NULL; - goto out; - } + ssize_t res; - off = same->logical_offset; - len = same->length; - - /* - * Limit the total length we will dedupe for each operation. - * This is intended to bound the total time spent in this - * ioctl to something sane. - */ - if (len > BTRFS_MAX_DEDUPE_LEN) - len = BTRFS_MAX_DEDUPE_LEN; + if (olen > BTRFS_MAX_DEDUPE_LEN) + olen = BTRFS_MAX_DEDUPE_LEN; if (WARN_ON_ONCE(bs < PAGE_CACHE_SIZE)) { /* @@ -3152,58 +3115,13 @@ static long btrfs_ioctl_file_extent_same(struct file *file, * result, btrfs_cmp_data() won't correctly handle * this situation without an update. */ - ret = -EINVAL; - goto out; - } - - ret = -EISDIR; - if (S_ISDIR(src->i_mode)) - goto out; - - ret = -EACCES; - if (!S_ISREG(src->i_mode)) - goto out; - - /* pre-format output fields to sane values */ - for (i = 0; i < count; i++) { - same->info[i].bytes_deduped = 0ULL; - same->info[i].status = 0; - } - - for (i = 0, info = same->info; i < count; i++, info++) { - struct inode *dst; - struct fd dst_file = fdget(info->fd); - if (!dst_file.file) { - info->status = -EBADF; - continue; - } - dst = file_inode(dst_file.file); - - if (!(is_admin || (dst_file.file->f_mode & FMODE_WRITE))) { - info->status = -EINVAL; - } else if (file->f_path.mnt != dst_file.file->f_path.mnt) { - info->status = -EXDEV; - } else if (S_ISDIR(dst->i_mode)) { - info->status = -EISDIR; - } else if (!S_ISREG(dst->i_mode)) { - info->status = -EACCES; - } else { - info->status = btrfs_extent_same(src, off, len, dst, - info->logical_offset); - if (info->status == 0) - info->bytes_deduped += len; - } - fdput(dst_file); + return -EINVAL; } - ret = copy_to_user(argp, same, size); - if (ret) - ret = -EFAULT; - -out: - mnt_drop_write_file(file); - kfree(same); - return ret; + res = btrfs_extent_same(src, loff, olen, dst, dst_loff); + if (res) + return res; + return olen; } static int clone_finish_inode_update(struct btrfs_trans_handle *trans, @@ -3779,17 +3697,16 @@ out: return ret; } -static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd, - u64 off, u64 olen, u64 destoff) +static noinline int btrfs_clone_files(struct file *file, struct file *file_src, + u64 off, u64 olen, u64 destoff) { struct inode *inode = file_inode(file); + struct inode *src = file_inode(file_src); struct btrfs_root *root = BTRFS_I(inode)->root; - struct fd src_file; - struct inode *src; int ret; u64 len = olen; u64 bs = root->fs_info->sb->s_blocksize; - int same_inode = 0; + int same_inode = src == inode; /* * TODO: @@ -3802,49 +3719,20 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd, * be either compressed or non-compressed. */ - /* the destination must be opened for writing */ - if (!(file->f_mode & FMODE_WRITE) || (file->f_flags & O_APPEND)) - return -EINVAL; - if (btrfs_root_readonly(root)) return -EROFS; - ret = mnt_want_write_file(file); - if (ret) - return ret; - - src_file = fdget(srcfd); - if (!src_file.file) { - ret = -EBADF; - goto out_drop_write; - } - - ret = -EXDEV; - if (src_file.file->f_path.mnt != file->f_path.mnt) - goto out_fput; - - src = file_inode(src_file.file); - - ret = -EINVAL; - if (src == inode) - same_inode = 1; - - /* the src must be open for reading */ - if (!(src_file.file->f_mode & FMODE_READ)) - goto out_fput; + if (file_src->f_path.mnt != file->f_path.mnt || + src->i_sb != inode->i_sb) + return -EXDEV; /* don't make the dst file partly checksummed */ if ((BTRFS_I(src)->flags & BTRFS_INODE_NODATASUM) != (BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM)) - goto out_fput; + return -EINVAL; - ret = -EISDIR; if (S_ISDIR(src->i_mode) || S_ISDIR(inode->i_mode)) - goto out_fput; - - ret = -EXDEV; - if (src->i_sb != inode->i_sb) - goto out_fput; + return -EISDIR; if (!same_inode) { btrfs_double_inode_lock(src, inode); @@ -3921,21 +3809,25 @@ out_unlock: btrfs_double_inode_unlock(src, inode); else mutex_unlock(&src->i_mutex); -out_fput: - fdput(src_file); -out_drop_write: - mnt_drop_write_file(file); return ret; } -static long btrfs_ioctl_clone_range(struct file *file, void __user *argp) +ssize_t btrfs_copy_file_range(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + size_t len, unsigned int flags) { - struct btrfs_ioctl_clone_range_args args; + ssize_t ret; - if (copy_from_user(&args, argp, sizeof(args))) - return -EFAULT; - return btrfs_ioctl_clone(file, args.src_fd, args.src_offset, - args.src_length, args.dest_offset); + ret = btrfs_clone_files(file_out, file_in, pos_in, len, pos_out); + if (ret == 0) + ret = len; + return ret; +} + +int btrfs_clone_file_range(struct file *src_file, loff_t off, + struct file *dst_file, loff_t destoff, u64 len) +{ + return btrfs_clone_files(dst_file, src_file, off, len, destoff); } /* @@ -5485,10 +5377,6 @@ long btrfs_ioctl(struct file *file, unsigned int return btrfs_ioctl_dev_info(root, argp); case BTRFS_IOC_BALANCE: return btrfs_ioctl_balance(file, NULL); - case BTRFS_IOC_CLONE: - return btrfs_ioctl_clone(file, arg, 0, 0, 0); - case BTRFS_IOC_CLONE_RANGE: - return btrfs_ioctl_clone_range(file, argp); case BTRFS_IOC_TRANS_START: return btrfs_ioctl_trans_start(file); case BTRFS_IOC_TRANS_END: @@ -5566,8 +5454,6 @@ long btrfs_ioctl(struct file *file, unsigned int return btrfs_ioctl_get_fslabel(file, argp); case BTRFS_IOC_SET_FSLABEL: return btrfs_ioctl_set_fslabel(file, argp); - case BTRFS_IOC_FILE_EXTENT_SAME: - return btrfs_ioctl_file_extent_same(file, argp); case BTRFS_IOC_GET_SUPPORTED_FEATURES: return btrfs_ioctl_get_supported_features(file, argp); case BTRFS_IOC_GET_FEATURES: diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 24154e4..a0434c17 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -1514,9 +1514,7 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags, if ((flags ^ s->s_flags) & MS_RDONLY) error = -EBUSY; } else { - char b[BDEVNAME_SIZE]; - - strlcpy(s->s_id, bdevname(bdev, b), sizeof(s->s_id)); + snprintf(s->s_id, sizeof(s->s_id), "%pg", bdev); btrfs_sb(s)->bdev_holder = fs_type; error = btrfs_fill_super(s, fs_devices, data, flags & MS_SILENT ? 1 : 0); diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c index 1fcd7b6..7cbef1a 100644 --- a/fs/btrfs/xattr.c +++ b/fs/btrfs/xattr.c @@ -351,137 +351,89 @@ err: return ret; } -/* - * List of handlers for synthetic system.* attributes. All real ondisk - * attributes are handled directly. - */ -const struct xattr_handler *btrfs_xattr_handlers[] = { -#ifdef CONFIG_BTRFS_FS_POSIX_ACL - &posix_acl_access_xattr_handler, - &posix_acl_default_xattr_handler, -#endif - NULL, -}; - -/* - * Check if the attribute is in a supported namespace. - * - * This is applied after the check for the synthetic attributes in the system - * namespace. - */ -static int btrfs_is_valid_xattr(const char *name) +static int btrfs_xattr_handler_get(const struct xattr_handler *handler, + struct dentry *dentry, const char *name, + void *buffer, size_t size) { - int len = strlen(name); - int prefixlen = 0; - - if (!strncmp(name, XATTR_SECURITY_PREFIX, - XATTR_SECURITY_PREFIX_LEN)) - prefixlen = XATTR_SECURITY_PREFIX_LEN; - else if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN)) - prefixlen = XATTR_SYSTEM_PREFIX_LEN; - else if (!strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN)) - prefixlen = XATTR_TRUSTED_PREFIX_LEN; - else if (!strncmp(name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN)) - prefixlen = XATTR_USER_PREFIX_LEN; - else if (!strncmp(name, XATTR_BTRFS_PREFIX, XATTR_BTRFS_PREFIX_LEN)) - prefixlen = XATTR_BTRFS_PREFIX_LEN; - else - return -EOPNOTSUPP; - - /* - * The name cannot consist of just prefix - */ - if (len <= prefixlen) - return -EINVAL; + struct inode *inode = d_inode(dentry); - return 0; + name = xattr_full_name(handler, name); + return __btrfs_getxattr(inode, name, buffer, size); } -ssize_t btrfs_getxattr(struct dentry *dentry, const char *name, - void *buffer, size_t size) +static int btrfs_xattr_handler_set(const struct xattr_handler *handler, + struct dentry *dentry, const char *name, + const void *buffer, size_t size, + int flags) { - int ret; + struct inode *inode = d_inode(dentry); - /* - * 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, buffer, size); + name = xattr_full_name(handler, name); + return __btrfs_setxattr(NULL, inode, name, buffer, size, flags); +} - ret = btrfs_is_valid_xattr(name); - if (ret) - return ret; - return __btrfs_getxattr(d_inode(dentry), name, buffer, size); +static int btrfs_xattr_handler_set_prop(const struct xattr_handler *handler, + struct dentry *dentry, + const char *name, const void *value, + size_t size, int flags) +{ + name = xattr_full_name(handler, name); + return btrfs_set_prop(d_inode(dentry), name, value, size, flags); } +static const struct xattr_handler btrfs_security_xattr_handler = { + .prefix = XATTR_SECURITY_PREFIX, + .get = btrfs_xattr_handler_get, + .set = btrfs_xattr_handler_set, +}; + +static const struct xattr_handler btrfs_trusted_xattr_handler = { + .prefix = XATTR_TRUSTED_PREFIX, + .get = btrfs_xattr_handler_get, + .set = btrfs_xattr_handler_set, +}; + +static const struct xattr_handler btrfs_user_xattr_handler = { + .prefix = XATTR_USER_PREFIX, + .get = btrfs_xattr_handler_get, + .set = btrfs_xattr_handler_set, +}; + +static const struct xattr_handler btrfs_btrfs_xattr_handler = { + .prefix = XATTR_BTRFS_PREFIX, + .get = btrfs_xattr_handler_get, + .set = btrfs_xattr_handler_set_prop, +}; + +const struct xattr_handler *btrfs_xattr_handlers[] = { + &btrfs_security_xattr_handler, +#ifdef CONFIG_BTRFS_FS_POSIX_ACL + &posix_acl_access_xattr_handler, + &posix_acl_default_xattr_handler, +#endif + &btrfs_trusted_xattr_handler, + &btrfs_user_xattr_handler, + &btrfs_btrfs_xattr_handler, + 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; - int ret; - /* - * The permission on security.* and system.* is not checked - * in permission(). - */ if (btrfs_root_readonly(root)) return -EROFS; - - /* - * 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, size, flags); - - ret = btrfs_is_valid_xattr(name); - if (ret) - return ret; - - if (!strncmp(name, XATTR_BTRFS_PREFIX, XATTR_BTRFS_PREFIX_LEN)) - return btrfs_set_prop(d_inode(dentry), name, - value, size, flags); - - if (size == 0) - value = ""; /* empty EA, do not remove */ - - return __btrfs_setxattr(NULL, d_inode(dentry), name, value, size, - flags); + 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; - int ret; - /* - * The permission on security.* and system.* is not checked - * in permission(). - */ if (btrfs_root_readonly(root)) return -EROFS; - - /* - * 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); - - ret = btrfs_is_valid_xattr(name); - if (ret) - return ret; - - if (!strncmp(name, XATTR_BTRFS_PREFIX, XATTR_BTRFS_PREFIX_LEN)) - return btrfs_set_prop(d_inode(dentry), name, - NULL, 0, XATTR_REPLACE); - - return __btrfs_setxattr(NULL, d_inode(dentry), name, NULL, 0, - XATTR_REPLACE); + return generic_removexattr(dentry, name); } static int btrfs_initxattrs(struct inode *inode, diff --git a/fs/btrfs/xattr.h b/fs/btrfs/xattr.h index 5049608..96807b3 100644 --- a/fs/btrfs/xattr.h +++ b/fs/btrfs/xattr.h @@ -28,8 +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 ssize_t btrfs_getxattr(struct dentry *dentry, const char *name, - void *buffer, size_t size); 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); diff --git a/fs/buffer.c b/fs/buffer.c index 4f4cd95..e1632ab 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -134,13 +134,10 @@ __clear_page_buffers(struct page *page) static void buffer_io_error(struct buffer_head *bh, char *msg) { - char b[BDEVNAME_SIZE]; - if (!test_bit(BH_Quiet, &bh->b_state)) printk_ratelimited(KERN_ERR - "Buffer I/O error on dev %s, logical block %llu%s\n", - bdevname(bh->b_bdev, b), - (unsigned long long)bh->b_blocknr, msg); + "Buffer I/O error on dev %pg, logical block %llu%s\n", + bh->b_bdev, (unsigned long long)bh->b_blocknr, msg); } /* @@ -237,15 +234,13 @@ __find_get_block_slow(struct block_device *bdev, sector_t block) * elsewhere, don't buffer_error if we had some unmapped buffers */ if (all_mapped) { - char b[BDEVNAME_SIZE]; - printk("__find_get_block_slow() failed. " "block=%llu, b_blocknr=%llu\n", (unsigned long long)block, (unsigned long long)bh->b_blocknr); printk("b_state=0x%08lx, b_size=%zu\n", bh->b_state, bh->b_size); - printk("device %s blocksize: %d\n", bdevname(bdev, b), + printk("device %pg blocksize: %d\n", bdev, 1 << bd_inode->i_blkbits); } out_unlock: @@ -531,10 +526,8 @@ repeat: static void do_thaw_one(struct super_block *sb, void *unused) { - char b[BDEVNAME_SIZE]; while (sb->s_bdev && !thaw_bdev(sb->s_bdev, sb)) - printk(KERN_WARNING "Emergency Thaw on %s\n", - bdevname(sb->s_bdev, b)); + printk(KERN_WARNING "Emergency Thaw on %pg\n", sb->s_bdev); } static void do_thaw_all(struct work_struct *work) @@ -1074,12 +1067,10 @@ grow_buffers(struct block_device *bdev, sector_t block, int size, gfp_t gfp) * pagecache index. (this comparison is done using sector_t types). */ if (unlikely(index != block >> sizebits)) { - char b[BDEVNAME_SIZE]; - printk(KERN_ERR "%s: requested out-of-range block %llu for " - "device %s\n", + "device %pg\n", __func__, (unsigned long long)block, - bdevname(bdev, b)); + bdev); return -EIO; } diff --git a/fs/cachefiles/daemon.c b/fs/cachefiles/daemon.c index f601def..452e98d 100644 --- a/fs/cachefiles/daemon.c +++ b/fs/cachefiles/daemon.c @@ -226,15 +226,9 @@ static ssize_t cachefiles_daemon_write(struct file *file, return -EOPNOTSUPP; /* drag the command string into the kernel so we can parse it */ - data = kmalloc(datalen + 1, GFP_KERNEL); - if (!data) - return -ENOMEM; - - ret = -EFAULT; - if (copy_from_user(data, _data, datalen) != 0) - goto error; - - data[datalen] = '\0'; + data = memdup_user_nul(_data, datalen); + if (IS_ERR(data)) + return PTR_ERR(data); ret = -EINVAL; if (memchr(data, '\0', datalen)) diff --git a/fs/ceph/acl.c b/fs/ceph/acl.c index 8f84646..f197084 100644 --- a/fs/ceph/acl.c +++ b/fs/ceph/acl.c @@ -49,10 +49,10 @@ struct posix_acl *ceph_get_acl(struct inode *inode, int type) switch (type) { case ACL_TYPE_ACCESS: - name = POSIX_ACL_XATTR_ACCESS; + name = XATTR_NAME_POSIX_ACL_ACCESS; break; case ACL_TYPE_DEFAULT: - name = POSIX_ACL_XATTR_DEFAULT; + name = XATTR_NAME_POSIX_ACL_DEFAULT; break; default: BUG(); @@ -92,7 +92,7 @@ int ceph_set_acl(struct inode *inode, struct posix_acl *acl, int type) switch (type) { case ACL_TYPE_ACCESS: - name = POSIX_ACL_XATTR_ACCESS; + name = XATTR_NAME_POSIX_ACL_ACCESS; if (acl) { ret = posix_acl_equiv_mode(acl, &new_mode); if (ret < 0) @@ -106,7 +106,7 @@ int ceph_set_acl(struct inode *inode, struct posix_acl *acl, int type) ret = acl ? -EINVAL : 0; goto out; } - name = POSIX_ACL_XATTR_DEFAULT; + name = XATTR_NAME_POSIX_ACL_DEFAULT; break; default: ret = -EINVAL; @@ -202,11 +202,11 @@ int ceph_pre_init_acls(struct inode *dir, umode_t *mode, ceph_pagelist_encode_32(pagelist, acl && default_acl ? 2 : 1); if (acl) { - size_t len = strlen(POSIX_ACL_XATTR_ACCESS); + size_t len = strlen(XATTR_NAME_POSIX_ACL_ACCESS); err = ceph_pagelist_reserve(pagelist, len + val_size1 + 8); if (err) goto out_err; - ceph_pagelist_encode_string(pagelist, POSIX_ACL_XATTR_ACCESS, + ceph_pagelist_encode_string(pagelist, XATTR_NAME_POSIX_ACL_ACCESS, len); err = posix_acl_to_xattr(&init_user_ns, acl, tmp_buf, val_size1); @@ -216,12 +216,12 @@ int ceph_pre_init_acls(struct inode *dir, umode_t *mode, ceph_pagelist_append(pagelist, tmp_buf, val_size1); } if (default_acl) { - size_t len = strlen(POSIX_ACL_XATTR_DEFAULT); + size_t len = strlen(XATTR_NAME_POSIX_ACL_DEFAULT); err = ceph_pagelist_reserve(pagelist, len + val_size2 + 8); if (err) goto out_err; err = ceph_pagelist_encode_string(pagelist, - POSIX_ACL_XATTR_DEFAULT, len); + XATTR_NAME_POSIX_ACL_DEFAULT, len); err = posix_acl_to_xattr(&init_user_ns, default_acl, tmp_buf, val_size2); if (err < 0) diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index 498dcfa..da55eb8 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -1756,7 +1756,7 @@ retry: */ static const struct inode_operations ceph_symlink_iops = { .readlink = generic_readlink, - .follow_link = simple_follow_link, + .get_link = simple_get_link, .setattr = ceph_setattr, .getattr = ceph_getattr, .setxattr = ceph_setxattr, diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index cbc0f4b..b7fcb31 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -900,8 +900,7 @@ const struct inode_operations cifs_file_inode_ops = { const struct inode_operations cifs_symlink_inode_ops = { .readlink = generic_readlink, - .follow_link = cifs_follow_link, - .put_link = kfree_put_link, + .get_link = cifs_get_link, .permission = cifs_permission, /* BB add the following two eventually */ /* revalidate: cifs_revalidate, @@ -914,6 +913,59 @@ const struct inode_operations cifs_symlink_inode_ops = { #endif }; +static int cifs_clone_file_range(struct file *src_file, loff_t off, + struct file *dst_file, loff_t destoff, u64 len) +{ + struct inode *src_inode = file_inode(src_file); + struct inode *target_inode = file_inode(dst_file); + struct cifsFileInfo *smb_file_src = src_file->private_data; + struct cifsFileInfo *smb_file_target = dst_file->private_data; + struct cifs_tcon *target_tcon = tlink_tcon(smb_file_target->tlink); + unsigned int xid; + int rc; + + cifs_dbg(FYI, "clone range\n"); + + xid = get_xid(); + + if (!src_file->private_data || !dst_file->private_data) { + rc = -EBADF; + cifs_dbg(VFS, "missing cifsFileInfo on copy range src file\n"); + goto out; + } + + /* + * Note: cifs case is easier than btrfs since server responsible for + * checks for proper open modes and file type and if it wants + * server could even support copy of range where source = target + */ + lock_two_nondirectories(target_inode, src_inode); + + if (len == 0) + len = src_inode->i_size - off; + + cifs_dbg(FYI, "about to flush pages\n"); + /* should we flush first and last page first */ + truncate_inode_pages_range(&target_inode->i_data, destoff, + PAGE_CACHE_ALIGN(destoff + len)-1); + + if (target_tcon->ses->server->ops->duplicate_extents) + rc = target_tcon->ses->server->ops->duplicate_extents(xid, + smb_file_src, smb_file_target, off, len, destoff); + else + rc = -EOPNOTSUPP; + + /* force revalidate of size and timestamps of target file now + that target is updated on the server */ + CIFS_I(target_inode)->time = 0; + /* although unlocking in the reverse order from locking is not + strictly necessary here it is a little cleaner to be consistent */ + unlock_two_nondirectories(src_inode, target_inode); +out: + free_xid(xid); + return rc; +} + const struct file_operations cifs_file_ops = { .read_iter = cifs_loose_read_iter, .write_iter = cifs_file_write_iter, @@ -926,6 +978,7 @@ const struct file_operations cifs_file_ops = { .splice_read = generic_file_splice_read, .llseek = cifs_llseek, .unlocked_ioctl = cifs_ioctl, + .clone_file_range = cifs_clone_file_range, .setlease = cifs_setlease, .fallocate = cifs_fallocate, }; @@ -942,6 +995,8 @@ const struct file_operations cifs_file_strict_ops = { .splice_read = generic_file_splice_read, .llseek = cifs_llseek, .unlocked_ioctl = cifs_ioctl, + .clone_file_range = cifs_clone_file_range, + .clone_file_range = cifs_clone_file_range, .setlease = cifs_setlease, .fallocate = cifs_fallocate, }; @@ -958,6 +1013,7 @@ const struct file_operations cifs_file_direct_ops = { .mmap = cifs_file_mmap, .splice_read = generic_file_splice_read, .unlocked_ioctl = cifs_ioctl, + .clone_file_range = cifs_clone_file_range, .llseek = cifs_llseek, .setlease = cifs_setlease, .fallocate = cifs_fallocate, @@ -974,6 +1030,7 @@ const struct file_operations cifs_file_nobrl_ops = { .splice_read = generic_file_splice_read, .llseek = cifs_llseek, .unlocked_ioctl = cifs_ioctl, + .clone_file_range = cifs_clone_file_range, .setlease = cifs_setlease, .fallocate = cifs_fallocate, }; @@ -989,6 +1046,7 @@ const struct file_operations cifs_file_strict_nobrl_ops = { .splice_read = generic_file_splice_read, .llseek = cifs_llseek, .unlocked_ioctl = cifs_ioctl, + .clone_file_range = cifs_clone_file_range, .setlease = cifs_setlease, .fallocate = cifs_fallocate, }; @@ -1004,6 +1062,7 @@ const struct file_operations cifs_file_direct_nobrl_ops = { .mmap = cifs_file_mmap, .splice_read = generic_file_splice_read, .unlocked_ioctl = cifs_ioctl, + .clone_file_range = cifs_clone_file_range, .llseek = cifs_llseek, .setlease = cifs_setlease, .fallocate = cifs_fallocate, @@ -1014,6 +1073,7 @@ const struct file_operations cifs_dir_ops = { .release = cifs_closedir, .read = generic_read_dir, .unlocked_ioctl = cifs_ioctl, + .clone_file_range = cifs_clone_file_range, .llseek = generic_file_llseek, }; diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h index c3cc160..68c4547 100644 --- a/fs/cifs/cifsfs.h +++ b/fs/cifs/cifsfs.h @@ -120,9 +120,8 @@ extern struct vfsmount *cifs_dfs_d_automount(struct path *path); #endif /* Functions related to symlinks */ -extern const char *cifs_follow_link(struct dentry *direntry, void **cookie); -extern int cifs_readlink(struct dentry *direntry, char __user *buffer, - int buflen); +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 *); @@ -131,7 +130,6 @@ extern int cifs_setxattr(struct dentry *, const char *, const void *, extern ssize_t cifs_getxattr(struct dentry *, const char *, void *, size_t); extern ssize_t cifs_listxattr(struct dentry *, char *, size_t); 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 */ diff --git a/fs/cifs/ioctl.c b/fs/cifs/ioctl.c index 35cf990..7a3b84e 100644 --- a/fs/cifs/ioctl.c +++ b/fs/cifs/ioctl.c @@ -34,73 +34,36 @@ #include "cifs_ioctl.h" #include <linux/btrfs.h> -static long cifs_ioctl_clone(unsigned int xid, struct file *dst_file, - unsigned long srcfd, u64 off, u64 len, u64 destoff, - bool dup_extents) +static int cifs_file_clone_range(unsigned int xid, struct file *src_file, + struct file *dst_file) { - int rc; - struct cifsFileInfo *smb_file_target = dst_file->private_data; + struct inode *src_inode = file_inode(src_file); struct inode *target_inode = file_inode(dst_file); - struct cifs_tcon *target_tcon; - struct fd src_file; struct cifsFileInfo *smb_file_src; - struct inode *src_inode; + struct cifsFileInfo *smb_file_target; struct cifs_tcon *src_tcon; + struct cifs_tcon *target_tcon; + int rc; cifs_dbg(FYI, "ioctl clone range\n"); - /* the destination must be opened for writing */ - if (!(dst_file->f_mode & FMODE_WRITE)) { - cifs_dbg(FYI, "file target not open for write\n"); - return -EINVAL; - } - /* check if target volume is readonly and take reference */ - rc = mnt_want_write_file(dst_file); - if (rc) { - cifs_dbg(FYI, "mnt_want_write failed with rc %d\n", rc); - return rc; - } - - src_file = fdget(srcfd); - if (!src_file.file) { - rc = -EBADF; - goto out_drop_write; - } - - if (src_file.file->f_op->unlocked_ioctl != cifs_ioctl) { - rc = -EBADF; - cifs_dbg(VFS, "src file seems to be from a different filesystem type\n"); - goto out_fput; - } - - if ((!src_file.file->private_data) || (!dst_file->private_data)) { + if (!src_file->private_data || !dst_file->private_data) { rc = -EBADF; cifs_dbg(VFS, "missing cifsFileInfo on copy range src file\n"); - goto out_fput; + goto out; } rc = -EXDEV; smb_file_target = dst_file->private_data; - smb_file_src = src_file.file->private_data; + smb_file_src = src_file->private_data; src_tcon = tlink_tcon(smb_file_src->tlink); target_tcon = tlink_tcon(smb_file_target->tlink); - /* check source and target on same server (or volume if dup_extents) */ - if (dup_extents && (src_tcon != target_tcon)) { - cifs_dbg(VFS, "source and target of copy not on same share\n"); - goto out_fput; - } - - if (!dup_extents && (src_tcon->ses != target_tcon->ses)) { + if (src_tcon->ses != target_tcon->ses) { cifs_dbg(VFS, "source and target of copy not on same server\n"); - goto out_fput; + goto out; } - src_inode = file_inode(src_file.file); - rc = -EINVAL; - if (S_ISDIR(src_inode->i_mode)) - goto out_fput; - /* * Note: cifs case is easier than btrfs since server responsible for * checks for proper open modes and file type and if it wants @@ -108,34 +71,66 @@ static long cifs_ioctl_clone(unsigned int xid, struct file *dst_file, */ lock_two_nondirectories(target_inode, src_inode); - /* determine range to clone */ - rc = -EINVAL; - if (off + len > src_inode->i_size || off + len < off) - goto out_unlock; - if (len == 0) - len = src_inode->i_size - off; - cifs_dbg(FYI, "about to flush pages\n"); /* should we flush first and last page first */ - truncate_inode_pages_range(&target_inode->i_data, destoff, - PAGE_CACHE_ALIGN(destoff + len)-1); + truncate_inode_pages(&target_inode->i_data, 0); - if (dup_extents && target_tcon->ses->server->ops->duplicate_extents) - rc = target_tcon->ses->server->ops->duplicate_extents(xid, - smb_file_src, smb_file_target, off, len, destoff); - else if (!dup_extents && target_tcon->ses->server->ops->clone_range) + if (target_tcon->ses->server->ops->clone_range) rc = target_tcon->ses->server->ops->clone_range(xid, - smb_file_src, smb_file_target, off, len, destoff); + smb_file_src, smb_file_target, 0, src_inode->i_size, 0); else rc = -EOPNOTSUPP; /* force revalidate of size and timestamps of target file now that target is updated on the server */ CIFS_I(target_inode)->time = 0; -out_unlock: /* although unlocking in the reverse order from locking is not strictly necessary here it is a little cleaner to be consistent */ unlock_two_nondirectories(src_inode, target_inode); +out: + return rc; +} + +static long cifs_ioctl_clone(unsigned int xid, struct file *dst_file, + unsigned long srcfd) +{ + int rc; + struct fd src_file; + struct inode *src_inode; + + cifs_dbg(FYI, "ioctl clone range\n"); + /* the destination must be opened for writing */ + if (!(dst_file->f_mode & FMODE_WRITE)) { + cifs_dbg(FYI, "file target not open for write\n"); + return -EINVAL; + } + + /* check if target volume is readonly and take reference */ + rc = mnt_want_write_file(dst_file); + if (rc) { + cifs_dbg(FYI, "mnt_want_write failed with rc %d\n", rc); + return rc; + } + + src_file = fdget(srcfd); + if (!src_file.file) { + rc = -EBADF; + goto out_drop_write; + } + + if (src_file.file->f_op->unlocked_ioctl != cifs_ioctl) { + rc = -EBADF; + cifs_dbg(VFS, "src file seems to be from a different filesystem type\n"); + goto out_fput; + } + + src_inode = file_inode(src_file.file); + rc = -EINVAL; + if (S_ISDIR(src_inode->i_mode)) + goto out_fput; + + rc = cifs_file_clone_range(xid, src_file.file, dst_file); + out_fput: fdput(src_file); out_drop_write: @@ -256,10 +251,7 @@ long cifs_ioctl(struct file *filep, unsigned int command, unsigned long arg) } break; case CIFS_IOC_COPYCHUNK_FILE: - rc = cifs_ioctl_clone(xid, filep, arg, 0, 0, 0, false); - break; - case BTRFS_IOC_CLONE: - rc = cifs_ioctl_clone(xid, filep, arg, 0, 0, 0, true); + rc = cifs_ioctl_clone(xid, filep, arg); break; case CIFS_IOC_SET_INTEGRITY: if (pSMBFile == NULL) diff --git a/fs/cifs/link.c b/fs/cifs/link.c index e3548f7..062c237 100644 --- a/fs/cifs/link.c +++ b/fs/cifs/link.c @@ -627,9 +627,9 @@ cifs_hl_exit: } const char * -cifs_follow_link(struct dentry *direntry, void **cookie) +cifs_get_link(struct dentry *direntry, struct inode *inode, + struct delayed_call *done) { - struct inode *inode = d_inode(direntry); int rc = -ENOMEM; unsigned int xid; char *full_path = NULL; @@ -639,6 +639,9 @@ cifs_follow_link(struct dentry *direntry, void **cookie) struct cifs_tcon *tcon; struct TCP_Server_Info *server; + if (!direntry) + return ERR_PTR(-ECHILD); + xid = get_xid(); tlink = cifs_sb_tlink(cifs_sb); @@ -678,7 +681,8 @@ cifs_follow_link(struct dentry *direntry, void **cookie) kfree(target_path); return ERR_PTR(rc); } - return *cookie = target_path; + set_delayed_call(done, kfree_link, target_path); + return target_path; } int diff --git a/fs/cifs/xattr.c b/fs/cifs/xattr.c index ff9e1f8..f5dc2f0 100644 --- a/fs/cifs/xattr.c +++ b/fs/cifs/xattr.c @@ -190,8 +190,8 @@ int cifs_setxattr(struct dentry *direntry, const char *ea_name, #endif /* CONFIG_CIFS_ACL */ } else { int temp; - temp = strncmp(ea_name, POSIX_ACL_XATTR_ACCESS, - strlen(POSIX_ACL_XATTR_ACCESS)); + temp = strncmp(ea_name, XATTR_NAME_POSIX_ACL_ACCESS, + strlen(XATTR_NAME_POSIX_ACL_ACCESS)); if (temp == 0) { #ifdef CONFIG_CIFS_POSIX if (sb->s_flags & MS_POSIXACL) @@ -203,8 +203,8 @@ int cifs_setxattr(struct dentry *direntry, const char *ea_name, #else cifs_dbg(FYI, "set POSIX ACL not supported\n"); #endif - } else if (strncmp(ea_name, POSIX_ACL_XATTR_DEFAULT, - strlen(POSIX_ACL_XATTR_DEFAULT)) == 0) { + } else if (strncmp(ea_name, XATTR_NAME_POSIX_ACL_DEFAULT, + strlen(XATTR_NAME_POSIX_ACL_DEFAULT)) == 0) { #ifdef CONFIG_CIFS_POSIX if (sb->s_flags & MS_POSIXACL) rc = CIFSSMBSetPosixACL(xid, pTcon, full_path, @@ -292,8 +292,8 @@ ssize_t cifs_getxattr(struct dentry *direntry, const char *ea_name, 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, POSIX_ACL_XATTR_ACCESS, - strlen(POSIX_ACL_XATTR_ACCESS)) == 0) { + } else if (strncmp(ea_name, XATTR_NAME_POSIX_ACL_ACCESS, + strlen(XATTR_NAME_POSIX_ACL_ACCESS)) == 0) { #ifdef CONFIG_CIFS_POSIX if (sb->s_flags & MS_POSIXACL) rc = CIFSSMBGetPosixACL(xid, pTcon, full_path, @@ -303,8 +303,8 @@ ssize_t cifs_getxattr(struct dentry *direntry, const char *ea_name, #else cifs_dbg(FYI, "Query POSIX ACL not supported yet\n"); #endif /* CONFIG_CIFS_POSIX */ - } else if (strncmp(ea_name, POSIX_ACL_XATTR_DEFAULT, - strlen(POSIX_ACL_XATTR_DEFAULT)) == 0) { + } else if (strncmp(ea_name, XATTR_NAME_POSIX_ACL_DEFAULT, + strlen(XATTR_NAME_POSIX_ACL_DEFAULT)) == 0) { #ifdef CONFIG_CIFS_POSIX if (sb->s_flags & MS_POSIXACL) rc = CIFSSMBGetPosixACL(xid, pTcon, full_path, diff --git a/fs/coda/cnode.c b/fs/coda/cnode.c index 7740b1c..1bfb7ba 100644 --- a/fs/coda/cnode.c +++ b/fs/coda/cnode.c @@ -8,6 +8,7 @@ #include <linux/coda.h> #include <linux/coda_psdev.h> +#include <linux/pagemap.h> #include "coda_linux.h" static inline int coda_fideq(struct CodaFid *fid1, struct CodaFid *fid2) @@ -17,8 +18,7 @@ static inline int coda_fideq(struct CodaFid *fid1, struct CodaFid *fid2) static const struct inode_operations coda_symlink_inode_operations = { .readlink = generic_readlink, - .follow_link = page_follow_link_light, - .put_link = page_put_link, + .get_link = page_get_link, .setattr = coda_setattr, }; @@ -35,6 +35,7 @@ static void coda_fill_inode(struct inode *inode, struct coda_vattr *attr) inode->i_fop = &coda_dir_operations; } else if (S_ISLNK(inode->i_mode)) { inode->i_op = &coda_symlink_inode_operations; + inode_nohighmem(inode); inode->i_data.a_ops = &coda_symlink_aops; inode->i_mapping = &inode->i_data; } else diff --git a/fs/coda/symlink.c b/fs/coda/symlink.c index ab94ef6..03736e2 100644 --- a/fs/coda/symlink.c +++ b/fs/coda/symlink.c @@ -26,7 +26,7 @@ static int coda_symlink_filler(struct file *file, struct page *page) int error; struct coda_inode_info *cii; unsigned int len = PAGE_SIZE; - char *p = kmap(page); + char *p = page_address(page); cii = ITOC(inode); @@ -34,13 +34,11 @@ static int coda_symlink_filler(struct file *file, struct page *page) if (error) goto fail; SetPageUptodate(page); - kunmap(page); unlock_page(page); return 0; fail: SetPageError(page); - kunmap(page); unlock_page(page); return error; } diff --git a/fs/compat.c b/fs/compat.c index 6fd272d..a71936a 100644 --- a/fs/compat.c +++ b/fs/compat.c @@ -792,7 +792,7 @@ COMPAT_SYSCALL_DEFINE5(mount, const char __user *, dev_name, const void __user *, data) { char *kernel_type; - unsigned long data_page; + void *options; char *kernel_dev; int retval; @@ -806,26 +806,25 @@ COMPAT_SYSCALL_DEFINE5(mount, const char __user *, dev_name, if (IS_ERR(kernel_dev)) goto out1; - retval = copy_mount_options(data, &data_page); - if (retval < 0) + options = copy_mount_options(data); + retval = PTR_ERR(options); + if (IS_ERR(options)) goto out2; - retval = -EINVAL; - - if (kernel_type && data_page) { + if (kernel_type && options) { if (!strcmp(kernel_type, NCPFS_NAME)) { - do_ncp_super_data_conv((void *)data_page); + do_ncp_super_data_conv(options); } else if (!strcmp(kernel_type, NFS4_NAME)) { - if (do_nfs4_super_data_conv((void *) data_page)) + retval = -EINVAL; + if (do_nfs4_super_data_conv(options)) goto out3; } } - retval = do_mount(kernel_dev, dir_name, kernel_type, - flags, (void*)data_page); + retval = do_mount(kernel_dev, dir_name, kernel_type, flags, options); out3: - free_page(data_page); + kfree(options); out2: kfree(kernel_dev); out1: diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c index dcf2653..a5b8eb6 100644 --- a/fs/compat_ioctl.c +++ b/fs/compat_ioctl.c @@ -58,6 +58,8 @@ #include <linux/atalk.h> #include <linux/gfp.h> +#include "internal.h" + #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_sock.h> #include <net/bluetooth/rfcomm.h> @@ -115,19 +117,38 @@ #include <asm/fbio.h> #endif -static int w_long(unsigned int fd, unsigned int cmd, - compat_ulong_t __user *argp) +#define convert_in_user(srcptr, dstptr) \ +({ \ + typeof(*srcptr) val; \ + \ + get_user(val, srcptr) || put_user(val, dstptr); \ +}) + +static int do_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { - mm_segment_t old_fs = get_fs(); int err; - unsigned long val; - set_fs (KERNEL_DS); - err = sys_ioctl(fd, cmd, (unsigned long)&val); - set_fs (old_fs); - if (!err && put_user(val, argp)) + err = security_file_ioctl(file, cmd, arg); + if (err) + return err; + + return vfs_ioctl(file, cmd, arg); +} + +static int w_long(struct file *file, + unsigned int cmd, compat_ulong_t __user *argp) +{ + int err; + unsigned long __user *valp = compat_alloc_user_space(sizeof(*valp)); + + if (valp == NULL) return -EFAULT; - return err; + err = do_ioctl(file, cmd, (unsigned long)valp); + if (err) + return err; + if (convert_in_user(valp, argp)) + return -EFAULT; + return 0; } struct compat_video_event { @@ -139,23 +160,23 @@ struct compat_video_event { } u; }; -static int do_video_get_event(unsigned int fd, unsigned int cmd, - struct compat_video_event __user *up) +static int do_video_get_event(struct file *file, + unsigned int cmd, struct compat_video_event __user *up) { - struct video_event kevent; - mm_segment_t old_fs = get_fs(); + struct video_event __user *kevent = + compat_alloc_user_space(sizeof(*kevent)); int err; - set_fs(KERNEL_DS); - err = sys_ioctl(fd, cmd, (unsigned long) &kevent); - set_fs(old_fs); + if (kevent == NULL) + return -EFAULT; + err = do_ioctl(file, cmd, (unsigned long)kevent); if (!err) { - err = put_user(kevent.type, &up->type); - err |= put_user(kevent.timestamp, &up->timestamp); - err |= put_user(kevent.u.size.w, &up->u.size.w); - err |= put_user(kevent.u.size.h, &up->u.size.h); - err |= put_user(kevent.u.size.aspect_ratio, + err = convert_in_user(&kevent->type, &up->type); + err |= convert_in_user(&kevent->timestamp, &up->timestamp); + err |= convert_in_user(&kevent->u.size.w, &up->u.size.w); + err |= convert_in_user(&kevent->u.size.h, &up->u.size.h); + err |= convert_in_user(&kevent->u.size.aspect_ratio, &up->u.size.aspect_ratio); if (err) err = -EFAULT; @@ -169,8 +190,8 @@ struct compat_video_still_picture { int32_t size; }; -static int do_video_stillpicture(unsigned int fd, unsigned int cmd, - struct compat_video_still_picture __user *up) +static int do_video_stillpicture(struct file *file, + unsigned int cmd, struct compat_video_still_picture __user *up) { struct video_still_picture __user *up_native; compat_uptr_t fp; @@ -190,7 +211,7 @@ static int do_video_stillpicture(unsigned int fd, unsigned int cmd, if (err) return -EFAULT; - err = sys_ioctl(fd, cmd, (unsigned long) up_native); + err = do_ioctl(file, cmd, (unsigned long) up_native); return err; } @@ -200,8 +221,8 @@ struct compat_video_spu_palette { compat_uptr_t palette; }; -static int do_video_set_spu_palette(unsigned int fd, unsigned int cmd, - struct compat_video_spu_palette __user *up) +static int do_video_set_spu_palette(struct file *file, + unsigned int cmd, struct compat_video_spu_palette __user *up) { struct video_spu_palette __user *up_native; compat_uptr_t palp; @@ -218,7 +239,7 @@ static int do_video_set_spu_palette(unsigned int fd, unsigned int cmd, if (err) return -EFAULT; - err = sys_ioctl(fd, cmd, (unsigned long) up_native); + err = do_ioctl(file, cmd, (unsigned long) up_native); return err; } @@ -276,7 +297,7 @@ static int sg_build_iovec(sg_io_hdr_t __user *sgio, void __user *dxferp, u16 iov return 0; } -static int sg_ioctl_trans(unsigned int fd, unsigned int cmd, +static int sg_ioctl_trans(struct file *file, unsigned int cmd, sg_io_hdr32_t __user *sgio32) { sg_io_hdr_t __user *sgio; @@ -289,7 +310,7 @@ static int sg_ioctl_trans(unsigned int fd, unsigned int cmd, if (get_user(interface_id, &sgio32->interface_id)) return -EFAULT; if (interface_id != 'S') - return sys_ioctl(fd, cmd, (unsigned long)sgio32); + return do_ioctl(file, cmd, (unsigned long)sgio32); if (get_user(iovec_count, &sgio32->iovec_count)) return -EFAULT; @@ -349,7 +370,7 @@ static int sg_ioctl_trans(unsigned int fd, unsigned int cmd, if (put_user(compat_ptr(data), &sgio->usr_ptr)) return -EFAULT; - err = sys_ioctl(fd, cmd, (unsigned long) sgio); + err = do_ioctl(file, cmd, (unsigned long) sgio); if (err >= 0) { void __user *datap; @@ -380,13 +401,13 @@ struct compat_sg_req_info { /* used by SG_GET_REQUEST_TABLE ioctl() */ int unused; }; -static int sg_grt_trans(unsigned int fd, unsigned int cmd, struct - compat_sg_req_info __user *o) +static int sg_grt_trans(struct file *file, + unsigned int cmd, struct compat_sg_req_info __user *o) { int err, i; sg_req_info_t __user *r; r = compat_alloc_user_space(sizeof(sg_req_info_t)*SG_MAX_QUEUE); - err = sys_ioctl(fd,cmd,(unsigned long)r); + err = do_ioctl(file, cmd, (unsigned long)r); if (err < 0) return err; for (i = 0; i < SG_MAX_QUEUE; i++) { @@ -412,8 +433,8 @@ struct sock_fprog32 { #define PPPIOCSPASS32 _IOW('t', 71, struct sock_fprog32) #define PPPIOCSACTIVE32 _IOW('t', 70, struct sock_fprog32) -static int ppp_sock_fprog_ioctl_trans(unsigned int fd, unsigned int cmd, - struct sock_fprog32 __user *u_fprog32) +static int ppp_sock_fprog_ioctl_trans(struct file *file, + unsigned int cmd, struct sock_fprog32 __user *u_fprog32) { struct sock_fprog __user *u_fprog64 = compat_alloc_user_space(sizeof(struct sock_fprog)); void __user *fptr64; @@ -435,7 +456,7 @@ static int ppp_sock_fprog_ioctl_trans(unsigned int fd, unsigned int cmd, else cmd = PPPIOCSACTIVE; - return sys_ioctl(fd, cmd, (unsigned long) u_fprog64); + return do_ioctl(file, cmd, (unsigned long) u_fprog64); } struct ppp_option_data32 { @@ -451,7 +472,7 @@ struct ppp_idle32 { }; #define PPPIOCGIDLE32 _IOR('t', 63, struct ppp_idle32) -static int ppp_gidle(unsigned int fd, unsigned int cmd, +static int ppp_gidle(struct file *file, unsigned int cmd, struct ppp_idle32 __user *idle32) { struct ppp_idle __user *idle; @@ -460,7 +481,7 @@ static int ppp_gidle(unsigned int fd, unsigned int cmd, idle = compat_alloc_user_space(sizeof(*idle)); - err = sys_ioctl(fd, PPPIOCGIDLE, (unsigned long) idle); + err = do_ioctl(file, PPPIOCGIDLE, (unsigned long) idle); if (!err) { if (get_user(xmit, &idle->xmit_idle) || @@ -472,7 +493,7 @@ static int ppp_gidle(unsigned int fd, unsigned int cmd, return err; } -static int ppp_scompress(unsigned int fd, unsigned int cmd, +static int ppp_scompress(struct file *file, unsigned int cmd, struct ppp_option_data32 __user *odata32) { struct ppp_option_data __user *odata; @@ -492,7 +513,7 @@ static int ppp_scompress(unsigned int fd, unsigned int cmd, sizeof(__u32) + sizeof(int))) return -EFAULT; - return sys_ioctl(fd, PPPIOCSCOMPRESS, (unsigned long) odata); + return do_ioctl(file, PPPIOCSCOMPRESS, (unsigned long) odata); } #ifdef CONFIG_BLOCK @@ -512,12 +533,13 @@ struct mtpos32 { }; #define MTIOCPOS32 _IOR('m', 3, struct mtpos32) -static int mt_ioctl_trans(unsigned int fd, unsigned int cmd, void __user *argp) +static int mt_ioctl_trans(struct file *file, + unsigned int cmd, void __user *argp) { - mm_segment_t old_fs = get_fs(); - struct mtget get; + /* NULL initialization to make gcc shut up */ + struct mtget __user *get = NULL; struct mtget32 __user *umget32; - struct mtpos pos; + struct mtpos __user *pos = NULL; struct mtpos32 __user *upos32; unsigned long kcmd; void *karg; @@ -526,32 +548,34 @@ static int mt_ioctl_trans(unsigned int fd, unsigned int cmd, void __user *argp) switch(cmd) { case MTIOCPOS32: kcmd = MTIOCPOS; - karg = &pos; + pos = compat_alloc_user_space(sizeof(*pos)); + karg = pos; break; default: /* MTIOCGET32 */ kcmd = MTIOCGET; - karg = &get; + get = compat_alloc_user_space(sizeof(*get)); + karg = get; break; } - set_fs (KERNEL_DS); - err = sys_ioctl (fd, kcmd, (unsigned long)karg); - set_fs (old_fs); + if (karg == NULL) + return -EFAULT; + err = do_ioctl(file, kcmd, (unsigned long)karg); if (err) return err; switch (cmd) { case MTIOCPOS32: upos32 = argp; - err = __put_user(pos.mt_blkno, &upos32->mt_blkno); + err = convert_in_user(&pos->mt_blkno, &upos32->mt_blkno); break; case MTIOCGET32: umget32 = argp; - err = __put_user(get.mt_type, &umget32->mt_type); - err |= __put_user(get.mt_resid, &umget32->mt_resid); - err |= __put_user(get.mt_dsreg, &umget32->mt_dsreg); - err |= __put_user(get.mt_gstat, &umget32->mt_gstat); - err |= __put_user(get.mt_erreg, &umget32->mt_erreg); - err |= __put_user(get.mt_fileno, &umget32->mt_fileno); - err |= __put_user(get.mt_blkno, &umget32->mt_blkno); + err = convert_in_user(&get->mt_type, &umget32->mt_type); + err |= convert_in_user(&get->mt_resid, &umget32->mt_resid); + err |= convert_in_user(&get->mt_dsreg, &umget32->mt_dsreg); + err |= convert_in_user(&get->mt_gstat, &umget32->mt_gstat); + err |= convert_in_user(&get->mt_erreg, &umget32->mt_erreg); + err |= convert_in_user(&get->mt_fileno, &umget32->mt_fileno); + err |= convert_in_user(&get->mt_blkno, &umget32->mt_blkno); break; } return err ? -EFAULT: 0; @@ -605,42 +629,41 @@ struct serial_struct32 { compat_int_t reserved[1]; }; -static int serial_struct_ioctl(unsigned fd, unsigned cmd, - struct serial_struct32 __user *ss32) +static int serial_struct_ioctl(struct file *file, + unsigned cmd, struct serial_struct32 __user *ss32) { typedef struct serial_struct32 SS32; int err; - struct serial_struct ss; - mm_segment_t oldseg = get_fs(); + struct serial_struct __user *ss = compat_alloc_user_space(sizeof(*ss)); __u32 udata; unsigned int base; + unsigned char *iomem_base; + if (ss == NULL) + return -EFAULT; if (cmd == TIOCSSERIAL) { - if (!access_ok(VERIFY_READ, ss32, sizeof(SS32))) - return -EFAULT; - if (__copy_from_user(&ss, ss32, offsetof(SS32, iomem_base))) - return -EFAULT; - if (__get_user(udata, &ss32->iomem_base)) + if (copy_in_user(ss, ss32, offsetof(SS32, iomem_base)) || + get_user(udata, &ss32->iomem_base)) return -EFAULT; - ss.iomem_base = compat_ptr(udata); - if (__get_user(ss.iomem_reg_shift, &ss32->iomem_reg_shift) || - __get_user(ss.port_high, &ss32->port_high)) + iomem_base = compat_ptr(udata); + if (put_user(iomem_base, &ss->iomem_base) || + convert_in_user(&ss32->iomem_reg_shift, + &ss->iomem_reg_shift) || + convert_in_user(&ss32->port_high, &ss->port_high) || + put_user(0UL, &ss->iomap_base)) return -EFAULT; - ss.iomap_base = 0UL; } - set_fs(KERNEL_DS); - err = sys_ioctl(fd,cmd,(unsigned long)(&ss)); - set_fs(oldseg); + err = do_ioctl(file, cmd, (unsigned long)ss); if (cmd == TIOCGSERIAL && err >= 0) { - if (!access_ok(VERIFY_WRITE, ss32, sizeof(SS32))) - return -EFAULT; - if (__copy_to_user(ss32,&ss,offsetof(SS32,iomem_base))) + if (copy_in_user(ss32, ss, offsetof(SS32, iomem_base)) || + get_user(iomem_base, &ss->iomem_base)) return -EFAULT; - base = (unsigned long)ss.iomem_base >> 32 ? - 0xffffffff : (unsigned)(unsigned long)ss.iomem_base; - if (__put_user(base, &ss32->iomem_base) || - __put_user(ss.iomem_reg_shift, &ss32->iomem_reg_shift) || - __put_user(ss.port_high, &ss32->port_high)) + base = (unsigned long)iomem_base >> 32 ? + 0xffffffff : (unsigned)(unsigned long)iomem_base; + if (put_user(base, &ss32->iomem_base) || + convert_in_user(&ss->iomem_reg_shift, + &ss32->iomem_reg_shift) || + convert_in_user(&ss->port_high, &ss32->port_high)) return -EFAULT; } return err; @@ -674,8 +697,8 @@ struct i2c_rdwr_aligned { struct i2c_msg msgs[0]; }; -static int do_i2c_rdwr_ioctl(unsigned int fd, unsigned int cmd, - struct i2c_rdwr_ioctl_data32 __user *udata) +static int do_i2c_rdwr_ioctl(struct file *file, + unsigned int cmd, struct i2c_rdwr_ioctl_data32 __user *udata) { struct i2c_rdwr_aligned __user *tdata; struct i2c_msg __user *tmsgs; @@ -708,11 +731,11 @@ static int do_i2c_rdwr_ioctl(unsigned int fd, unsigned int cmd, put_user(compat_ptr(datap), &tmsgs[i].buf)) return -EFAULT; } - return sys_ioctl(fd, cmd, (unsigned long)tdata); + return do_ioctl(file, cmd, (unsigned long)tdata); } -static int do_i2c_smbus_ioctl(unsigned int fd, unsigned int cmd, - struct i2c_smbus_ioctl_data32 __user *udata) +static int do_i2c_smbus_ioctl(struct file *file, + unsigned int cmd, struct i2c_smbus_ioctl_data32 __user *udata) { struct i2c_smbus_ioctl_data __user *tdata; compat_caddr_t datap; @@ -734,7 +757,7 @@ static int do_i2c_smbus_ioctl(unsigned int fd, unsigned int cmd, __put_user(compat_ptr(datap), &tdata->data)) return -EFAULT; - return sys_ioctl(fd, cmd, (unsigned long)tdata); + return do_ioctl(file, cmd, (unsigned long)tdata); } #define RTC_IRQP_READ32 _IOR('p', 0x0b, compat_ulong_t) @@ -742,29 +765,27 @@ static int do_i2c_smbus_ioctl(unsigned int fd, unsigned int cmd, #define RTC_EPOCH_READ32 _IOR('p', 0x0d, compat_ulong_t) #define RTC_EPOCH_SET32 _IOW('p', 0x0e, compat_ulong_t) -static int rtc_ioctl(unsigned fd, unsigned cmd, void __user *argp) +static int rtc_ioctl(struct file *file, + unsigned cmd, void __user *argp) { - mm_segment_t oldfs = get_fs(); - compat_ulong_t val32; - unsigned long kval; + unsigned long __user *valp = compat_alloc_user_space(sizeof(*valp)); int ret; + if (valp == NULL) + return -EFAULT; switch (cmd) { case RTC_IRQP_READ32: case RTC_EPOCH_READ32: - set_fs(KERNEL_DS); - ret = sys_ioctl(fd, (cmd == RTC_IRQP_READ32) ? + ret = do_ioctl(file, (cmd == RTC_IRQP_READ32) ? RTC_IRQP_READ : RTC_EPOCH_READ, - (unsigned long)&kval); - set_fs(oldfs); + (unsigned long)valp); if (ret) return ret; - val32 = kval; - return put_user(val32, (unsigned int __user *)argp); + return convert_in_user(valp, (unsigned int __user *)argp); case RTC_IRQP_SET32: - return sys_ioctl(fd, RTC_IRQP_SET, (unsigned long)argp); + return do_ioctl(file, RTC_IRQP_SET, (unsigned long)argp); case RTC_EPOCH_SET32: - return sys_ioctl(fd, RTC_EPOCH_SET, (unsigned long)argp); + return do_ioctl(file, RTC_EPOCH_SET, (unsigned long)argp); } return -ENOIOCTLCMD; @@ -1284,12 +1305,6 @@ COMPATIBLE_IOCTL(PCIIOC_CONTROLLER) COMPATIBLE_IOCTL(PCIIOC_MMAP_IS_IO) COMPATIBLE_IOCTL(PCIIOC_MMAP_IS_MEM) COMPATIBLE_IOCTL(PCIIOC_WRITE_COMBINE) -/* NBD */ -COMPATIBLE_IOCTL(NBD_DO_IT) -COMPATIBLE_IOCTL(NBD_CLEAR_SOCK) -COMPATIBLE_IOCTL(NBD_CLEAR_QUE) -COMPATIBLE_IOCTL(NBD_PRINT_DEBUG) -COMPATIBLE_IOCTL(NBD_DISCONNECT) /* i2c */ COMPATIBLE_IOCTL(I2C_SLAVE) COMPATIBLE_IOCTL(I2C_SLAVE_FORCE) @@ -1436,53 +1451,53 @@ IGNORE_IOCTL(FBIOGCURSOR32) * a compat_ioctl operation in the place that handleÑ• the * ioctl for the native case. */ -static long do_ioctl_trans(int fd, unsigned int cmd, +static long do_ioctl_trans(unsigned int cmd, unsigned long arg, struct file *file) { void __user *argp = compat_ptr(arg); switch (cmd) { case PPPIOCGIDLE32: - return ppp_gidle(fd, cmd, argp); + return ppp_gidle(file, cmd, argp); case PPPIOCSCOMPRESS32: - return ppp_scompress(fd, cmd, argp); + return ppp_scompress(file, cmd, argp); case PPPIOCSPASS32: case PPPIOCSACTIVE32: - return ppp_sock_fprog_ioctl_trans(fd, cmd, argp); + return ppp_sock_fprog_ioctl_trans(file, cmd, argp); #ifdef CONFIG_BLOCK case SG_IO: - return sg_ioctl_trans(fd, cmd, argp); + return sg_ioctl_trans(file, cmd, argp); case SG_GET_REQUEST_TABLE: - return sg_grt_trans(fd, cmd, argp); + return sg_grt_trans(file, cmd, argp); case MTIOCGET32: case MTIOCPOS32: - return mt_ioctl_trans(fd, cmd, argp); + return mt_ioctl_trans(file, cmd, argp); #endif /* Serial */ case TIOCGSERIAL: case TIOCSSERIAL: - return serial_struct_ioctl(fd, cmd, argp); + return serial_struct_ioctl(file, cmd, argp); /* i2c */ case I2C_FUNCS: - return w_long(fd, cmd, argp); + return w_long(file, cmd, argp); case I2C_RDWR: - return do_i2c_rdwr_ioctl(fd, cmd, argp); + return do_i2c_rdwr_ioctl(file, cmd, argp); case I2C_SMBUS: - return do_i2c_smbus_ioctl(fd, cmd, argp); + return do_i2c_smbus_ioctl(file, cmd, argp); /* Not implemented in the native kernel */ case RTC_IRQP_READ32: case RTC_IRQP_SET32: case RTC_EPOCH_READ32: case RTC_EPOCH_SET32: - return rtc_ioctl(fd, cmd, argp); + return rtc_ioctl(file, cmd, argp); /* dvb */ case VIDEO_GET_EVENT: - return do_video_get_event(fd, cmd, argp); + return do_video_get_event(file, cmd, argp); case VIDEO_STILLPICTURE: - return do_video_stillpicture(fd, cmd, argp); + return do_video_stillpicture(file, cmd, argp); case VIDEO_SET_SPU_PALETTE: - return do_video_set_spu_palette(fd, cmd, argp); + return do_video_set_spu_palette(file, cmd, argp); } /* @@ -1508,12 +1523,7 @@ static long do_ioctl_trans(int fd, unsigned int cmd, case KDSKBMETA: case KDSKBLED: case KDSETLED: - /* NBD */ - case NBD_SET_SOCK: - case NBD_SET_BLKSIZE: - case NBD_SET_SIZE: - case NBD_SET_SIZE_BLOCKS: - return do_vfs_ioctl(file, fd, cmd, arg); + return vfs_ioctl(file, cmd, arg); } return -ENOIOCTLCMD; @@ -1580,6 +1590,11 @@ COMPAT_SYSCALL_DEFINE3(ioctl, unsigned int, fd, unsigned int, cmd, goto out_fput; #endif + case FICLONE: + case FICLONERANGE: + case FIDEDUPERANGE: + goto do_ioctl; + case FIBMAP: case FIGETBSZ: case FIONREAD: @@ -1602,7 +1617,7 @@ COMPAT_SYSCALL_DEFINE3(ioctl, unsigned int, fd, unsigned int, cmd, if (compat_ioctl_check_table(XFORM(cmd))) goto found_handler; - error = do_ioctl_trans(fd, cmd, arg, f.file); + error = do_ioctl_trans(cmd, arg, f.file); if (error == -ENOIOCTLCMD) error = -ENOTTY; diff --git a/fs/configfs/configfs_internal.h b/fs/configfs/configfs_internal.h index b65d1ef..ccc31fa 100644 --- a/fs/configfs/configfs_internal.h +++ b/fs/configfs/configfs_internal.h @@ -53,13 +53,14 @@ struct configfs_dirent { #define CONFIGFS_ROOT 0x0001 #define CONFIGFS_DIR 0x0002 #define CONFIGFS_ITEM_ATTR 0x0004 +#define CONFIGFS_ITEM_BIN_ATTR 0x0008 #define CONFIGFS_ITEM_LINK 0x0020 #define CONFIGFS_USET_DIR 0x0040 #define CONFIGFS_USET_DEFAULT 0x0080 #define CONFIGFS_USET_DROPPING 0x0100 #define CONFIGFS_USET_IN_MKDIR 0x0200 #define CONFIGFS_USET_CREATING 0x0400 -#define CONFIGFS_NOT_PINNED (CONFIGFS_ITEM_ATTR) +#define CONFIGFS_NOT_PINNED (CONFIGFS_ITEM_ATTR | CONFIGFS_ITEM_BIN_ATTR) extern struct mutex configfs_symlink_mutex; extern spinlock_t configfs_dirent_lock; @@ -72,6 +73,8 @@ extern struct inode * configfs_new_inode(umode_t mode, struct configfs_dirent *, extern int configfs_create(struct dentry *, umode_t mode, void (*init)(struct inode *)); extern int configfs_create_file(struct config_item *, const struct configfs_attribute *); +extern int configfs_create_bin_file(struct config_item *, + const struct configfs_bin_attribute *); extern int configfs_make_dirent(struct configfs_dirent *, struct dentry *, void *, umode_t, int); extern int configfs_dirent_is_ready(struct configfs_dirent *); @@ -88,7 +91,7 @@ extern void configfs_release_fs(void); extern struct rw_semaphore configfs_rename_sem; extern const struct file_operations configfs_dir_operations; extern const struct file_operations configfs_file_operations; -extern const struct file_operations bin_fops; +extern const struct file_operations configfs_bin_file_operations; extern const struct inode_operations configfs_dir_inode_operations; extern const struct inode_operations configfs_root_inode_operations; extern const struct inode_operations configfs_symlink_inode_operations; @@ -119,6 +122,13 @@ static inline struct configfs_attribute * to_attr(struct dentry * dentry) return ((struct configfs_attribute *) sd->s_element); } +static inline struct configfs_bin_attribute *to_bin_attr(struct dentry *dentry) +{ + struct configfs_attribute *attr = to_attr(dentry); + + return container_of(attr, struct configfs_bin_attribute, cb_attr); +} + static inline struct config_item *configfs_get_config_item(struct dentry *dentry) { struct config_item * item = NULL; diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c index a7a1b21..7ae97e8 100644 --- a/fs/configfs/dir.c +++ b/fs/configfs/dir.c @@ -255,6 +255,12 @@ static void configfs_init_file(struct inode * inode) inode->i_fop = &configfs_file_operations; } +static void configfs_init_bin_file(struct inode *inode) +{ + inode->i_size = 0; + inode->i_fop = &configfs_bin_file_operations; +} + static void init_symlink(struct inode * inode) { inode->i_op = &configfs_symlink_inode_operations; @@ -423,7 +429,9 @@ static int configfs_attach_attr(struct configfs_dirent * sd, struct dentry * den spin_unlock(&configfs_dirent_lock); error = configfs_create(dentry, (attr->ca_mode & S_IALLUGO) | S_IFREG, - configfs_init_file); + (sd->s_type & CONFIGFS_ITEM_BIN_ATTR) ? + configfs_init_bin_file : + configfs_init_file); if (error) { configfs_put(sd); return error; @@ -583,6 +591,7 @@ static int populate_attrs(struct config_item *item) { struct config_item_type *t = item->ci_type; struct configfs_attribute *attr; + struct configfs_bin_attribute *bin_attr; int error = 0; int i; @@ -594,6 +603,13 @@ static int populate_attrs(struct config_item *item) break; } } + if (t->ct_bin_attrs) { + for (i = 0; (bin_attr = t->ct_bin_attrs[i]) != NULL; i++) { + error = configfs_create_bin_file(item, bin_attr); + if (error) + break; + } + } if (error) detach_attrs(item); diff --git a/fs/configfs/file.c b/fs/configfs/file.c index d39099e..3687187 100644 --- a/fs/configfs/file.c +++ b/fs/configfs/file.c @@ -28,6 +28,7 @@ #include <linux/module.h> #include <linux/slab.h> #include <linux/mutex.h> +#include <linux/vmalloc.h> #include <asm/uaccess.h> #include <linux/configfs.h> @@ -48,6 +49,10 @@ struct configfs_buffer { struct configfs_item_operations * ops; struct mutex mutex; int needs_read_fill; + bool read_in_progress; + bool write_in_progress; + char *bin_buffer; + int bin_buffer_size; }; @@ -123,6 +128,87 @@ out: return retval; } +/** + * configfs_read_bin_file - read a binary attribute. + * @file: file pointer. + * @buf: buffer to fill. + * @count: number of bytes to read. + * @ppos: starting offset in file. + * + * Userspace wants to read a binary attribute file. The attribute + * descriptor is in the file's ->d_fsdata. The target item is in the + * directory's ->d_fsdata. + * + * We check whether we need to refill the buffer. If so we will + * call the attributes' attr->read() twice. The first time we + * will pass a NULL as a buffer pointer, which the attributes' method + * will use to return the size of the buffer required. If no error + * occurs we will allocate the buffer using vmalloc and call + * attr->read() again passing that buffer as an argument. + * Then we just copy to user-space using simple_read_from_buffer. + */ + +static ssize_t +configfs_read_bin_file(struct file *file, char __user *buf, + size_t count, loff_t *ppos) +{ + struct configfs_buffer *buffer = file->private_data; + struct dentry *dentry = file->f_path.dentry; + struct config_item *item = to_item(dentry->d_parent); + struct configfs_bin_attribute *bin_attr = to_bin_attr(dentry); + ssize_t retval = 0; + ssize_t len = min_t(size_t, count, PAGE_SIZE); + + mutex_lock(&buffer->mutex); + + /* we don't support switching read/write modes */ + if (buffer->write_in_progress) { + retval = -ETXTBSY; + goto out; + } + buffer->read_in_progress = 1; + + if (buffer->needs_read_fill) { + /* perform first read with buf == NULL to get extent */ + len = bin_attr->read(item, NULL, 0); + if (len <= 0) { + retval = len; + goto out; + } + + /* do not exceed the maximum value */ + if (bin_attr->cb_max_size && len > bin_attr->cb_max_size) { + retval = -EFBIG; + goto out; + } + + buffer->bin_buffer = vmalloc(len); + if (buffer->bin_buffer == NULL) { + retval = -ENOMEM; + goto out; + } + buffer->bin_buffer_size = len; + + /* perform second read to fill buffer */ + len = bin_attr->read(item, buffer->bin_buffer, len); + if (len < 0) { + retval = len; + vfree(buffer->bin_buffer); + buffer->bin_buffer_size = 0; + buffer->bin_buffer = NULL; + goto out; + } + + buffer->needs_read_fill = 0; + } + + retval = simple_read_from_buffer(buf, count, ppos, buffer->bin_buffer, + buffer->bin_buffer_size); +out: + mutex_unlock(&buffer->mutex); + return retval; +} + /** * fill_write_buffer - copy buffer from userspace. @@ -209,10 +295,80 @@ configfs_write_file(struct file *file, const char __user *buf, size_t count, lof return len; } -static int check_perm(struct inode * inode, struct file * file) +/** + * configfs_write_bin_file - write a binary attribute. + * @file: file pointer + * @buf: data to write + * @count: number of bytes + * @ppos: starting offset + * + * Writing to a binary attribute file is similar to a normal read. + * We buffer the consecutive writes (binary attribute files do not + * support lseek) in a continuously growing buffer, but we don't + * commit until the close of the file. + */ + +static ssize_t +configfs_write_bin_file(struct file *file, const char __user *buf, + size_t count, loff_t *ppos) +{ + struct configfs_buffer *buffer = file->private_data; + struct dentry *dentry = file->f_path.dentry; + struct configfs_bin_attribute *bin_attr = to_bin_attr(dentry); + void *tbuf = NULL; + ssize_t len; + + mutex_lock(&buffer->mutex); + + /* we don't support switching read/write modes */ + if (buffer->read_in_progress) { + len = -ETXTBSY; + goto out; + } + buffer->write_in_progress = 1; + + /* buffer grows? */ + if (*ppos + count > buffer->bin_buffer_size) { + + if (bin_attr->cb_max_size && + *ppos + count > bin_attr->cb_max_size) { + len = -EFBIG; + } + + tbuf = vmalloc(*ppos + count); + if (tbuf == NULL) { + len = -ENOMEM; + goto out; + } + + /* copy old contents */ + if (buffer->bin_buffer) { + memcpy(tbuf, buffer->bin_buffer, + buffer->bin_buffer_size); + vfree(buffer->bin_buffer); + } + + /* clear the new area */ + memset(tbuf + buffer->bin_buffer_size, 0, + *ppos + count - buffer->bin_buffer_size); + buffer->bin_buffer = tbuf; + buffer->bin_buffer_size = *ppos + count; + } + + len = simple_write_to_buffer(buffer->bin_buffer, + buffer->bin_buffer_size, ppos, buf, count); + if (len > 0) + *ppos += len; +out: + mutex_unlock(&buffer->mutex); + return len; +} + +static int check_perm(struct inode * inode, struct file * file, int type) { struct config_item *item = configfs_get_config_item(file->f_path.dentry->d_parent); struct configfs_attribute * attr = to_attr(file->f_path.dentry); + struct configfs_bin_attribute *bin_attr = NULL; struct configfs_buffer * buffer; struct configfs_item_operations * ops = NULL; int error = 0; @@ -220,6 +376,9 @@ static int check_perm(struct inode * inode, struct file * file) if (!item || !attr) goto Einval; + if (type & CONFIGFS_ITEM_BIN_ATTR) + bin_attr = to_bin_attr(file->f_path.dentry); + /* Grab the module reference for this attribute if we have one */ if (!try_module_get(attr->ca_owner)) { error = -ENODEV; @@ -236,9 +395,14 @@ static int check_perm(struct inode * inode, struct file * file) * and we must have a store method. */ if (file->f_mode & FMODE_WRITE) { - if (!(inode->i_mode & S_IWUGO) || !attr->store) + if (!(inode->i_mode & S_IWUGO)) + goto Eaccess; + + if ((type & CONFIGFS_ITEM_ATTR) && !attr->store) goto Eaccess; + if ((type & CONFIGFS_ITEM_BIN_ATTR) && !bin_attr->write) + goto Eaccess; } /* File needs read support. @@ -246,7 +410,13 @@ static int check_perm(struct inode * inode, struct file * file) * must be a show method for it. */ if (file->f_mode & FMODE_READ) { - if (!(inode->i_mode & S_IRUGO) || !attr->show) + if (!(inode->i_mode & S_IRUGO)) + goto Eaccess; + + if ((type & CONFIGFS_ITEM_ATTR) && !attr->show) + goto Eaccess; + + if ((type & CONFIGFS_ITEM_BIN_ATTR) && !bin_attr->read) goto Eaccess; } @@ -260,6 +430,8 @@ static int check_perm(struct inode * inode, struct file * file) } mutex_init(&buffer->mutex); buffer->needs_read_fill = 1; + buffer->read_in_progress = 0; + buffer->write_in_progress = 0; buffer->ops = ops; file->private_data = buffer; goto Done; @@ -277,12 +449,7 @@ static int check_perm(struct inode * inode, struct file * file) return error; } -static int configfs_open_file(struct inode * inode, struct file * filp) -{ - return check_perm(inode,filp); -} - -static int configfs_release(struct inode * inode, struct file * filp) +static int configfs_release(struct inode *inode, struct file *filp) { struct config_item * item = to_item(filp->f_path.dentry->d_parent); struct configfs_attribute * attr = to_attr(filp->f_path.dentry); @@ -303,6 +470,47 @@ static int configfs_release(struct inode * inode, struct file * filp) return 0; } +static int configfs_open_file(struct inode *inode, struct file *filp) +{ + return check_perm(inode, filp, CONFIGFS_ITEM_ATTR); +} + +static int configfs_open_bin_file(struct inode *inode, struct file *filp) +{ + return check_perm(inode, filp, CONFIGFS_ITEM_BIN_ATTR); +} + +static int configfs_release_bin_file(struct inode *inode, struct file *filp) +{ + struct configfs_buffer *buffer = filp->private_data; + struct dentry *dentry = filp->f_path.dentry; + struct config_item *item = to_item(dentry->d_parent); + struct configfs_bin_attribute *bin_attr = to_bin_attr(dentry); + ssize_t len = 0; + int ret; + + buffer->read_in_progress = 0; + + if (buffer->write_in_progress) { + buffer->write_in_progress = 0; + + len = bin_attr->write(item, buffer->bin_buffer, + buffer->bin_buffer_size); + + /* vfree on NULL is safe */ + vfree(buffer->bin_buffer); + buffer->bin_buffer = NULL; + buffer->bin_buffer_size = 0; + buffer->needs_read_fill = 1; + } + + ret = configfs_release(inode, filp); + if (len < 0) + return len; + return ret; +} + + const struct file_operations configfs_file_operations = { .read = configfs_read_file, .write = configfs_write_file, @@ -311,6 +519,14 @@ const struct file_operations configfs_file_operations = { .release = configfs_release, }; +const struct file_operations configfs_bin_file_operations = { + .read = configfs_read_bin_file, + .write = configfs_write_bin_file, + .llseek = NULL, /* bin file is not seekable */ + .open = configfs_open_bin_file, + .release = configfs_release_bin_file, +}; + /** * configfs_create_file - create an attribute file for an item. * @item: item we're creating for. @@ -332,3 +548,24 @@ int configfs_create_file(struct config_item * item, const struct configfs_attrib return error; } +/** + * configfs_create_bin_file - create a binary attribute file for an item. + * @item: item we're creating for. + * @attr: atrribute descriptor. + */ + +int configfs_create_bin_file(struct config_item *item, + const struct configfs_bin_attribute *bin_attr) +{ + struct dentry *dir = item->ci_dentry; + struct configfs_dirent *parent_sd = dir->d_fsdata; + umode_t mode = (bin_attr->cb_attr.ca_mode & S_IALLUGO) | S_IFREG; + int error = 0; + + mutex_lock_nested(&dir->d_inode->i_mutex, I_MUTEX_NORMAL); + error = configfs_make_dirent(parent_sd, NULL, (void *) bin_attr, mode, + CONFIGFS_ITEM_BIN_ATTR); + mutex_unlock(&dir->d_inode->i_mutex); + + return error; +} diff --git a/fs/configfs/inode.c b/fs/configfs/inode.c index eae8757..0cc810e 100644 --- a/fs/configfs/inode.c +++ b/fs/configfs/inode.c @@ -218,7 +218,7 @@ const unsigned char * configfs_get_name(struct configfs_dirent *sd) if (sd->s_type & (CONFIGFS_DIR | CONFIGFS_ITEM_LINK)) return sd->s_dentry->d_name.name; - if (sd->s_type & CONFIGFS_ITEM_ATTR) { + if (sd->s_type & (CONFIGFS_ITEM_ATTR | CONFIGFS_ITEM_BIN_ATTR)) { attr = sd->s_element; return attr->ca_name; } diff --git a/fs/configfs/symlink.c b/fs/configfs/symlink.c index ec5c832..db6d692 100644 --- a/fs/configfs/symlink.c +++ b/fs/configfs/symlink.c @@ -279,27 +279,33 @@ static int configfs_getlink(struct dentry *dentry, char * path) } -static const char *configfs_follow_link(struct dentry *dentry, void **cookie) +static const char *configfs_get_link(struct dentry *dentry, + struct inode *inode, + struct delayed_call *done) { - unsigned long page = get_zeroed_page(GFP_KERNEL); + char *body; int error; - if (!page) + if (!dentry) + return ERR_PTR(-ECHILD); + + body = kzalloc(PAGE_SIZE, GFP_KERNEL); + if (!body) return ERR_PTR(-ENOMEM); - error = configfs_getlink(dentry, (char *)page); + error = configfs_getlink(dentry, body); if (!error) { - return *cookie = (void *)page; + set_delayed_call(done, kfree_link, body); + return body; } - free_page(page); + kfree(body); return ERR_PTR(error); } const struct inode_operations configfs_symlink_inode_operations = { - .follow_link = configfs_follow_link, + .get_link = configfs_get_link, .readlink = generic_readlink, - .put_link = free_page_put_link, .setattr = configfs_setattr, }; diff --git a/fs/coredump.c b/fs/coredump.c index 1777331..b3c153c 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -32,6 +32,7 @@ #include <linux/pipe_fs_i.h> #include <linux/oom.h> #include <linux/compat.h> +#include <linux/timekeeping.h> #include <asm/uaccess.h> #include <asm/mmu_context.h> @@ -232,9 +233,10 @@ static int format_corename(struct core_name *cn, struct coredump_params *cprm) break; /* UNIX time of coredump */ case 't': { - struct timeval tv; - do_gettimeofday(&tv); - err = cn_printf(cn, "%lu", tv.tv_sec); + time64_t time; + + time = ktime_get_real_seconds(); + err = cn_printf(cn, "%lld", time); break; } /* hostname */ diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c index 355c522..b862bc2 100644 --- a/fs/cramfs/inode.c +++ b/fs/cramfs/inode.c @@ -100,6 +100,7 @@ static struct inode *get_cramfs_inode(struct super_block *sb, break; case S_IFLNK: inode->i_op = &page_symlink_inode_operations; + inode_nohighmem(inode); inode->i_data.a_ops = &cramfs_aops; break; default: diff --git a/fs/dcache.c b/fs/dcache.c index 5c33aeb..8d38cd0 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -1734,7 +1734,7 @@ static unsigned d_flags_for_inode(struct inode *inode) } if (unlikely(!(inode->i_opflags & IOP_NOFOLLOW))) { - if (unlikely(inode->i_op->follow_link)) { + if (unlikely(inode->i_op->get_link)) { add_flags = DCACHE_SYMLINK_TYPE; goto type_determined; } @@ -3303,18 +3303,18 @@ out: * @new_dentry: new dentry * @old_dentry: old dentry * - * Returns 1 if new_dentry is a subdirectory of the parent (at any depth). - * Returns 0 otherwise. + * Returns true if new_dentry is a subdirectory of the parent (at any depth). + * Returns false otherwise. * Caller must ensure that "new_dentry" is pinned before calling is_subdir() */ -int is_subdir(struct dentry *new_dentry, struct dentry *old_dentry) +bool is_subdir(struct dentry *new_dentry, struct dentry *old_dentry) { - int result; + bool result; unsigned seq; if (new_dentry == old_dentry) - return 1; + return true; do { /* for restarting inner loop in case of seq retry */ @@ -3325,9 +3325,9 @@ int is_subdir(struct dentry *new_dentry, struct dentry *old_dentry) */ rcu_read_lock(); if (d_ancestor(old_dentry, new_dentry)) - result = 1; + result = true; else - result = 0; + result = false; rcu_read_unlock(); } while (read_seqretry(&rename_lock, seq)); diff --git a/fs/dlm/user.c b/fs/dlm/user.c index 173b387..1925d6d 100644 --- a/fs/dlm/user.c +++ b/fs/dlm/user.c @@ -515,14 +515,9 @@ static ssize_t device_write(struct file *file, const char __user *buf, if (count > sizeof(struct dlm_write_request) + DLM_RESNAME_MAXLEN) return -EINVAL; - kbuf = kzalloc(count + 1, GFP_NOFS); - if (!kbuf) - return -ENOMEM; - - if (copy_from_user(kbuf, buf, count)) { - error = -EFAULT; - goto out_free; - } + kbuf = memdup_user_nul(buf, count); + if (!IS_ERR(kbuf)) + return PTR_ERR(kbuf); if (check_version(kbuf)) { error = -EBADE; diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c index e2e47ba..040aa87 100644 --- a/fs/ecryptfs/inode.c +++ b/fs/ecryptfs/inode.c @@ -282,9 +282,7 @@ ecryptfs_create(struct inode *directory_inode, struct dentry *ecryptfs_dentry, if (rc) { ecryptfs_do_unlink(directory_inode, ecryptfs_dentry, ecryptfs_inode); - make_bad_inode(ecryptfs_inode); - unlock_new_inode(ecryptfs_inode); - iput(ecryptfs_inode); + iget_failed(ecryptfs_inode); goto out; } unlock_new_inode(ecryptfs_inode); @@ -674,16 +672,24 @@ out: return rc ? ERR_PTR(rc) : buf; } -static const char *ecryptfs_follow_link(struct dentry *dentry, void **cookie) +static const char *ecryptfs_get_link(struct dentry *dentry, + struct inode *inode, + struct delayed_call *done) { size_t len; - char *buf = ecryptfs_readlink_lower(dentry, &len); + char *buf; + + if (!dentry) + return ERR_PTR(-ECHILD); + + buf = ecryptfs_readlink_lower(dentry, &len); if (IS_ERR(buf)) return buf; fsstack_copy_attr_atime(d_inode(dentry), d_inode(ecryptfs_dentry_to_lower(dentry))); buf[len] = '\0'; - return *cookie = buf; + set_delayed_call(done, kfree_link, buf); + return buf; } /** @@ -1095,8 +1101,7 @@ out: const struct inode_operations ecryptfs_symlink_iops = { .readlink = generic_readlink, - .follow_link = ecryptfs_follow_link, - .put_link = kfree_put_link, + .get_link = ecryptfs_get_link, .permission = ecryptfs_permission, .setattr = ecryptfs_setattr, .getattr = ecryptfs_getattr_link, diff --git a/fs/efs/inode.c b/fs/efs/inode.c index 079d203..cdf0872 100644 --- a/fs/efs/inode.c +++ b/fs/efs/inode.c @@ -151,6 +151,7 @@ struct inode *efs_iget(struct super_block *super, unsigned long ino) break; case S_IFLNK: inode->i_op = &page_symlink_inode_operations; + inode_nohighmem(inode); inode->i_data.a_ops = &efs_symlink_aops; break; case S_IFCHR: diff --git a/fs/efs/symlink.c b/fs/efs/symlink.c index 75117d0..4870cc8 100644 --- a/fs/efs/symlink.c +++ b/fs/efs/symlink.c @@ -13,7 +13,7 @@ static int efs_symlink_readpage(struct file *file, struct page *page) { - char *link = kmap(page); + char *link = page_address(page); struct buffer_head * bh; struct inode * inode = page->mapping->host; efs_block_t size = inode->i_size; @@ -39,12 +39,10 @@ static int efs_symlink_readpage(struct file *file, struct page *page) } link[size] = '\0'; SetPageUptodate(page); - kunmap(page); unlock_page(page); return 0; fail: SetPageError(page); - kunmap(page); unlock_page(page); return err; } @@ -119,7 +119,7 @@ SYSCALL_DEFINE1(uselib, const char __user *, library) int error = PTR_ERR(tmp); static const struct open_flags uselib_flags = { .open_flag = O_LARGEFILE | O_RDONLY | __FMODE_EXEC, - .acc_mode = MAY_READ | MAY_EXEC | MAY_OPEN, + .acc_mode = MAY_READ | MAY_EXEC, .intent = LOOKUP_OPEN, .lookup_flags = LOOKUP_FOLLOW, }; @@ -763,7 +763,7 @@ static struct file *do_open_execat(int fd, struct filename *name, int flags) int err; struct open_flags open_exec_flags = { .open_flag = O_LARGEFILE | O_RDONLY | __FMODE_EXEC, - .acc_mode = MAY_EXEC | MAY_OPEN, + .acc_mode = MAY_EXEC, .intent = LOOKUP_OPEN, .lookup_flags = LOOKUP_FOLLOW, }; diff --git a/fs/exofs/inode.c b/fs/exofs/inode.c index 60f03b7..9eaf595 100644 --- a/fs/exofs/inode.c +++ b/fs/exofs/inode.c @@ -1224,6 +1224,7 @@ struct inode *exofs_iget(struct super_block *sb, unsigned long ino) inode->i_link = (char *)oi->i_data; } else { inode->i_op = &page_symlink_inode_operations; + inode_nohighmem(inode); inode->i_mapping->a_ops = &exofs_aops; } } else { diff --git a/fs/exofs/namei.c b/fs/exofs/namei.c index 994e078..c20d77d 100644 --- a/fs/exofs/namei.c +++ b/fs/exofs/namei.c @@ -111,6 +111,7 @@ static int exofs_symlink(struct inode *dir, struct dentry *dentry, if (l > sizeof(oi->i_data)) { /* slow symlink */ inode->i_op = &page_symlink_inode_operations; + inode_nohighmem(inode); inode->i_mapping->a_ops = &exofs_aops; memset(oi->i_data, 0, sizeof(oi->i_data)); diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index 0aa9bf6..338eefd 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -1420,6 +1420,7 @@ struct inode *ext2_iget (struct super_block *sb, unsigned long ino) sizeof(ei->i_data) - 1); } else { inode->i_op = &ext2_symlink_inode_operations; + inode_nohighmem(inode); if (test_opt(inode->i_sb, NOBH)) inode->i_mapping->a_ops = &ext2_nobh_aops; else diff --git a/fs/ext2/namei.c b/fs/ext2/namei.c index 3267a80..7a2be8f 100644 --- a/fs/ext2/namei.c +++ b/fs/ext2/namei.c @@ -183,6 +183,7 @@ static int ext2_symlink (struct inode * dir, struct dentry * dentry, if (l > sizeof (EXT2_I(inode)->i_data)) { /* slow symlink */ inode->i_op = &ext2_symlink_inode_operations; + inode_nohighmem(inode); if (test_opt(inode->i_sb, NOBH)) inode->i_mapping->a_ops = &ext2_nobh_aops; else diff --git a/fs/ext2/symlink.c b/fs/ext2/symlink.c index ae17179..3495d8a 100644 --- a/fs/ext2/symlink.c +++ b/fs/ext2/symlink.c @@ -22,8 +22,7 @@ const struct inode_operations ext2_symlink_inode_operations = { .readlink = generic_readlink, - .follow_link = page_follow_link_light, - .put_link = page_put_link, + .get_link = page_get_link, .setattr = ext2_setattr, #ifdef CONFIG_EXT2_FS_XATTR .setxattr = generic_setxattr, @@ -35,7 +34,7 @@ const struct inode_operations ext2_symlink_inode_operations = { const struct inode_operations ext2_fast_symlink_inode_operations = { .readlink = generic_readlink, - .follow_link = simple_follow_link, + .get_link = simple_get_link, .setattr = ext2_setattr, #ifdef CONFIG_EXT2_FS_XATTR .setxattr = generic_setxattr, diff --git a/fs/ext2/xattr.c b/fs/ext2/xattr.c index fa70848..f57a7ab 100644 --- a/fs/ext2/xattr.c +++ b/fs/ext2/xattr.c @@ -77,10 +77,8 @@ printk("\n"); \ } while (0) # define ea_bdebug(bh, f...) do { \ - char b[BDEVNAME_SIZE]; \ - printk(KERN_DEBUG "block %s:%lu: ", \ - bdevname(bh->b_bdev, b), \ - (unsigned long) bh->b_blocknr); \ + printk(KERN_DEBUG "block %pg:%lu: ", \ + bh->b_bdev, (unsigned long) bh->b_blocknr); \ printk(f); \ printk("\n"); \ } while (0) @@ -292,16 +290,21 @@ bad_block: ext2_error(inode->i_sb, "ext2_xattr_list", const struct xattr_handler *handler = ext2_xattr_handler(entry->e_name_index); - if (handler) { - size_t size = handler->list(handler, dentry, buffer, - rest, entry->e_name, - entry->e_name_len); + if (handler && (!handler->list || handler->list(dentry))) { + const char *prefix = handler->prefix ?: handler->name; + size_t prefix_len = strlen(prefix); + size_t size = prefix_len + entry->e_name_len + 1; + if (buffer) { if (size > rest) { error = -ERANGE; goto cleanup; } - buffer += size; + memcpy(buffer, prefix, prefix_len); + buffer += prefix_len; + memcpy(buffer, entry->e_name, entry->e_name_len); + buffer += entry->e_name_len; + *buffer++ = 0; } rest -= size; } diff --git a/fs/ext2/xattr_security.c b/fs/ext2/xattr_security.c index dfb0875..ba97f24 100644 --- a/fs/ext2/xattr_security.c +++ b/fs/ext2/xattr_security.c @@ -7,29 +7,11 @@ #include <linux/security.h> #include "xattr.h" -static size_t -ext2_xattr_security_list(const struct xattr_handler *handler, - struct dentry *dentry, char *list, size_t list_size, - const char *name, size_t name_len) -{ - const int prefix_len = XATTR_SECURITY_PREFIX_LEN; - const size_t total_len = prefix_len + name_len + 1; - - if (list && total_len <= list_size) { - memcpy(list, XATTR_SECURITY_PREFIX, prefix_len); - memcpy(list+prefix_len, name, name_len); - list[prefix_len + name_len] = '\0'; - } - return total_len; -} - static int ext2_xattr_security_get(const struct xattr_handler *handler, struct dentry *dentry, const char *name, void *buffer, size_t size) { - if (strcmp(name, "") == 0) - return -EINVAL; return ext2_xattr_get(d_inode(dentry), EXT2_XATTR_INDEX_SECURITY, name, buffer, size); } @@ -39,8 +21,6 @@ ext2_xattr_security_set(const struct xattr_handler *handler, struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { - if (strcmp(name, "") == 0) - return -EINVAL; return ext2_xattr_set(d_inode(dentry), EXT2_XATTR_INDEX_SECURITY, name, value, size, flags); } @@ -71,7 +51,6 @@ ext2_init_security(struct inode *inode, struct inode *dir, const struct xattr_handler ext2_xattr_security_handler = { .prefix = XATTR_SECURITY_PREFIX, - .list = ext2_xattr_security_list, .get = ext2_xattr_security_get, .set = ext2_xattr_security_set, }; diff --git a/fs/ext2/xattr_trusted.c b/fs/ext2/xattr_trusted.c index 3150dd3..2c94d19 100644 --- a/fs/ext2/xattr_trusted.c +++ b/fs/ext2/xattr_trusted.c @@ -8,23 +8,10 @@ #include "ext2.h" #include "xattr.h" -static size_t -ext2_xattr_trusted_list(const struct xattr_handler *handler, - struct dentry *dentry, char *list, size_t list_size, - const char *name, size_t name_len) +static bool +ext2_xattr_trusted_list(struct dentry *dentry) { - const int prefix_len = XATTR_TRUSTED_PREFIX_LEN; - const size_t total_len = prefix_len + name_len + 1; - - if (!capable(CAP_SYS_ADMIN)) - return 0; - - if (list && total_len <= list_size) { - memcpy(list, XATTR_TRUSTED_PREFIX, prefix_len); - memcpy(list+prefix_len, name, name_len); - list[prefix_len + name_len] = '\0'; - } - return total_len; + return capable(CAP_SYS_ADMIN); } static int @@ -32,8 +19,6 @@ ext2_xattr_trusted_get(const struct xattr_handler *handler, struct dentry *dentry, const char *name, void *buffer, size_t size) { - if (strcmp(name, "") == 0) - return -EINVAL; return ext2_xattr_get(d_inode(dentry), EXT2_XATTR_INDEX_TRUSTED, name, buffer, size); } @@ -43,8 +28,6 @@ ext2_xattr_trusted_set(const struct xattr_handler *handler, struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { - if (strcmp(name, "") == 0) - return -EINVAL; return ext2_xattr_set(d_inode(dentry), EXT2_XATTR_INDEX_TRUSTED, name, value, size, flags); } diff --git a/fs/ext2/xattr_user.c b/fs/ext2/xattr_user.c index 339a49b..72a2a96 100644 --- a/fs/ext2/xattr_user.c +++ b/fs/ext2/xattr_user.c @@ -10,23 +10,10 @@ #include "ext2.h" #include "xattr.h" -static size_t -ext2_xattr_user_list(const struct xattr_handler *handler, - struct dentry *dentry, char *list, size_t list_size, - const char *name, size_t name_len) +static bool +ext2_xattr_user_list(struct dentry *dentry) { - const size_t prefix_len = XATTR_USER_PREFIX_LEN; - const size_t total_len = prefix_len + name_len + 1; - - if (!test_opt(dentry->d_sb, XATTR_USER)) - return 0; - - if (list && total_len <= list_size) { - memcpy(list, XATTR_USER_PREFIX, prefix_len); - memcpy(list+prefix_len, name, name_len); - list[prefix_len + name_len] = '\0'; - } - return total_len; + return test_opt(dentry->d_sb, XATTR_USER); } static int @@ -34,8 +21,6 @@ ext2_xattr_user_get(const struct xattr_handler *handler, struct dentry *dentry, const char *name, void *buffer, size_t size) { - if (strcmp(name, "") == 0) - return -EINVAL; if (!test_opt(dentry->d_sb, XATTR_USER)) return -EOPNOTSUPP; return ext2_xattr_get(d_inode(dentry), EXT2_XATTR_INDEX_USER, @@ -47,8 +32,6 @@ ext2_xattr_user_set(const struct xattr_handler *handler, struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { - if (strcmp(name, "") == 0) - return -EINVAL; if (!test_opt(dentry->d_sb, XATTR_USER)) return -EOPNOTSUPP; diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index ea433a7..b3bd912 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -4283,6 +4283,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino) inode->i_op = &ext4_symlink_inode_operations; ext4_set_aops(inode); } + inode_nohighmem(inode); } else if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode) || S_ISFIFO(inode->i_mode) || S_ISSOCK(inode->i_mode)) { inode->i_op = &ext4_special_inode_operations; diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index a969ab3..f27e0c2 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -3132,6 +3132,7 @@ static int ext4_symlink(struct inode *dir, if ((disk_link.len > EXT4_N_BLOCKS * 4)) { if (!encryption_required) inode->i_op = &ext4_symlink_inode_operations; + inode_nohighmem(inode); ext4_set_aops(inode); /* * We cannot call page_symlink() with transaction started diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c index 17fbe38..090b349 100644 --- a/fs/ext4/page-io.c +++ b/fs/ext4/page-io.c @@ -52,9 +52,8 @@ void ext4_exit_pageio(void) */ static void buffer_io_error(struct buffer_head *bh) { - char b[BDEVNAME_SIZE]; - printk_ratelimited(KERN_ERR "Buffer I/O error on device %s, logical block %llu\n", - bdevname(bh->b_bdev, b), + printk_ratelimited(KERN_ERR "Buffer I/O error on device %pg, logical block %llu\n", + bh->b_bdev, (unsigned long long)bh->b_blocknr); } diff --git a/fs/ext4/symlink.c b/fs/ext4/symlink.c index e8e7af6..6f7ee30 100644 --- a/fs/ext4/symlink.c +++ b/fs/ext4/symlink.c @@ -23,17 +23,21 @@ #include "xattr.h" #ifdef CONFIG_EXT4_FS_ENCRYPTION -static const char *ext4_encrypted_follow_link(struct dentry *dentry, void **cookie) +static const char *ext4_encrypted_get_link(struct dentry *dentry, + struct inode *inode, + struct delayed_call *done) { struct page *cpage = NULL; char *caddr, *paddr = NULL; struct ext4_str cstr, pstr; - struct inode *inode = d_inode(dentry); struct ext4_encrypted_symlink_data *sd; loff_t size = min_t(loff_t, i_size_read(inode), PAGE_SIZE - 1); int res; u32 plen, max_size = inode->i_sb->s_blocksize; + if (!dentry) + return ERR_PTR(-ECHILD); + res = ext4_get_encryption_info(inode); if (res) return ERR_PTR(res); @@ -45,7 +49,7 @@ static const char *ext4_encrypted_follow_link(struct dentry *dentry, void **cook cpage = read_mapping_page(inode->i_mapping, 0, NULL); if (IS_ERR(cpage)) return ERR_CAST(cpage); - caddr = kmap(cpage); + caddr = page_address(cpage); caddr[size] = 0; } @@ -75,24 +79,20 @@ static const char *ext4_encrypted_follow_link(struct dentry *dentry, void **cook /* Null-terminate the name */ if (res <= plen) paddr[res] = '\0'; - if (cpage) { - kunmap(cpage); + if (cpage) page_cache_release(cpage); - } - return *cookie = paddr; + set_delayed_call(done, kfree_link, paddr); + return paddr; errout: - if (cpage) { - kunmap(cpage); + if (cpage) page_cache_release(cpage); - } kfree(paddr); return ERR_PTR(res); } const struct inode_operations ext4_encrypted_symlink_inode_operations = { .readlink = generic_readlink, - .follow_link = ext4_encrypted_follow_link, - .put_link = kfree_put_link, + .get_link = ext4_encrypted_get_link, .setattr = ext4_setattr, .setxattr = generic_setxattr, .getxattr = generic_getxattr, @@ -103,8 +103,7 @@ const struct inode_operations ext4_encrypted_symlink_inode_operations = { const struct inode_operations ext4_symlink_inode_operations = { .readlink = generic_readlink, - .follow_link = page_follow_link_light, - .put_link = page_put_link, + .get_link = page_get_link, .setattr = ext4_setattr, .setxattr = generic_setxattr, .getxattr = generic_getxattr, @@ -114,7 +113,7 @@ const struct inode_operations ext4_symlink_inode_operations = { const struct inode_operations ext4_fast_symlink_inode_operations = { .readlink = generic_readlink, - .follow_link = simple_follow_link, + .get_link = simple_get_link, .setattr = ext4_setattr, .setxattr = generic_setxattr, .getxattr = generic_getxattr, diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 6b6b3e7..a95151e 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -68,10 +68,8 @@ printk("\n"); \ } while (0) # define ea_bdebug(bh, f...) do { \ - char b[BDEVNAME_SIZE]; \ - printk(KERN_DEBUG "block %s:%lu: ", \ - bdevname(bh->b_bdev, b), \ - (unsigned long) bh->b_blocknr); \ + printk(KERN_DEBUG "block %pg:%lu: ", \ + bh->b_bdev, (unsigned long) bh->b_blocknr); \ printk(f); \ printk("\n"); \ } while (0) @@ -404,19 +402,24 @@ ext4_xattr_list_entries(struct dentry *dentry, struct ext4_xattr_entry *entry, const struct xattr_handler *handler = ext4_xattr_handler(entry->e_name_index); - if (handler) { - size_t size = handler->list(handler, dentry, buffer, - rest, entry->e_name, - entry->e_name_len); + if (handler && (!handler->list || handler->list(dentry))) { + const char *prefix = handler->prefix ?: handler->name; + size_t prefix_len = strlen(prefix); + size_t size = prefix_len + entry->e_name_len + 1; + if (buffer) { if (size > rest) return -ERANGE; - buffer += size; + memcpy(buffer, prefix, prefix_len); + buffer += prefix_len; + memcpy(buffer, entry->e_name, entry->e_name_len); + buffer += entry->e_name_len; + *buffer++ = 0; } rest -= size; } } - return buffer_size - rest; + return buffer_size - rest; /* total size */ } static int diff --git a/fs/ext4/xattr_security.c b/fs/ext4/xattr_security.c index 36f4c1a..3e81bdc 100644 --- a/fs/ext4/xattr_security.c +++ b/fs/ext4/xattr_security.c @@ -11,30 +11,11 @@ #include "ext4.h" #include "xattr.h" -static size_t -ext4_xattr_security_list(const struct xattr_handler *handler, - struct dentry *dentry, char *list, size_t list_size, - const char *name, size_t name_len) -{ - const size_t prefix_len = sizeof(XATTR_SECURITY_PREFIX)-1; - const size_t total_len = prefix_len + name_len + 1; - - - if (list && total_len <= list_size) { - memcpy(list, XATTR_SECURITY_PREFIX, prefix_len); - memcpy(list+prefix_len, name, name_len); - list[prefix_len + name_len] = '\0'; - } - return total_len; -} - static int ext4_xattr_security_get(const struct xattr_handler *handler, struct dentry *dentry, const char *name, void *buffer, size_t size) { - if (strcmp(name, "") == 0) - return -EINVAL; return ext4_xattr_get(d_inode(dentry), EXT4_XATTR_INDEX_SECURITY, name, buffer, size); } @@ -44,8 +25,6 @@ ext4_xattr_security_set(const struct xattr_handler *handler, struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { - if (strcmp(name, "") == 0) - return -EINVAL; return ext4_xattr_set(d_inode(dentry), EXT4_XATTR_INDEX_SECURITY, name, value, size, flags); } @@ -79,7 +58,6 @@ ext4_init_security(handle_t *handle, struct inode *inode, struct inode *dir, const struct xattr_handler ext4_xattr_security_handler = { .prefix = XATTR_SECURITY_PREFIX, - .list = ext4_xattr_security_list, .get = ext4_xattr_security_get, .set = ext4_xattr_security_set, }; diff --git a/fs/ext4/xattr_trusted.c b/fs/ext4/xattr_trusted.c index 4880890..2a3c6f9 100644 --- a/fs/ext4/xattr_trusted.c +++ b/fs/ext4/xattr_trusted.c @@ -12,23 +12,10 @@ #include "ext4.h" #include "xattr.h" -static size_t -ext4_xattr_trusted_list(const struct xattr_handler *handler, - struct dentry *dentry, char *list, size_t list_size, - const char *name, size_t name_len) +static bool +ext4_xattr_trusted_list(struct dentry *dentry) { - const size_t prefix_len = XATTR_TRUSTED_PREFIX_LEN; - const size_t total_len = prefix_len + name_len + 1; - - if (!capable(CAP_SYS_ADMIN)) - return 0; - - if (list && total_len <= list_size) { - memcpy(list, XATTR_TRUSTED_PREFIX, prefix_len); - memcpy(list+prefix_len, name, name_len); - list[prefix_len + name_len] = '\0'; - } - return total_len; + return capable(CAP_SYS_ADMIN); } static int @@ -36,8 +23,6 @@ ext4_xattr_trusted_get(const struct xattr_handler *handler, struct dentry *dentry, const char *name, void *buffer, size_t size) { - if (strcmp(name, "") == 0) - return -EINVAL; return ext4_xattr_get(d_inode(dentry), EXT4_XATTR_INDEX_TRUSTED, name, buffer, size); } @@ -47,8 +32,6 @@ ext4_xattr_trusted_set(const struct xattr_handler *handler, struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { - if (strcmp(name, "") == 0) - return -EINVAL; return ext4_xattr_set(d_inode(dentry), EXT4_XATTR_INDEX_TRUSTED, name, value, size, flags); } diff --git a/fs/ext4/xattr_user.c b/fs/ext4/xattr_user.c index d2dec33..d152f43 100644 --- a/fs/ext4/xattr_user.c +++ b/fs/ext4/xattr_user.c @@ -11,23 +11,10 @@ #include "ext4.h" #include "xattr.h" -static size_t -ext4_xattr_user_list(const struct xattr_handler *handler, - struct dentry *dentry, char *list, size_t list_size, - const char *name, size_t name_len) +static bool +ext4_xattr_user_list(struct dentry *dentry) { - const size_t prefix_len = XATTR_USER_PREFIX_LEN; - const size_t total_len = prefix_len + name_len + 1; - - if (!test_opt(dentry->d_sb, XATTR_USER)) - return 0; - - if (list && total_len <= list_size) { - memcpy(list, XATTR_USER_PREFIX, prefix_len); - memcpy(list+prefix_len, name, name_len); - list[prefix_len + name_len] = '\0'; - } - return total_len; + return test_opt(dentry->d_sb, XATTR_USER); } static int @@ -35,8 +22,6 @@ ext4_xattr_user_get(const struct xattr_handler *handler, struct dentry *dentry, const char *name, void *buffer, size_t size) { - if (strcmp(name, "") == 0) - return -EINVAL; if (!test_opt(dentry->d_sb, XATTR_USER)) return -EOPNOTSUPP; return ext4_xattr_get(d_inode(dentry), EXT4_XATTR_INDEX_USER, @@ -48,8 +33,6 @@ ext4_xattr_user_set(const struct xattr_handler *handler, struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { - if (strcmp(name, "") == 0) - return -EINVAL; if (!test_opt(dentry->d_sb, XATTR_USER)) return -EOPNOTSUPP; return ext4_xattr_set(d_inode(dentry), EXT4_XATTR_INDEX_USER, diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c index 478e5d5..ad1b18a 100644 --- a/fs/f2fs/debug.c +++ b/fs/f2fs/debug.c @@ -211,12 +211,10 @@ static int stat_show(struct seq_file *s, void *v) mutex_lock(&f2fs_stat_mutex); list_for_each_entry(si, &f2fs_stat_list, stat_list) { - char devname[BDEVNAME_SIZE]; - update_general_status(si->sbi); - seq_printf(s, "\n=====[ partition info(%s). #%d ]=====\n", - bdevname(si->sbi->sb->s_bdev, devname), i++); + seq_printf(s, "\n=====[ partition info(%pg). #%d ]=====\n", + si->sbi->sb->s_bdev, i++); seq_printf(s, "[SB: 1] [CP: 2] [SIT: %d] [NAT: %d] ", si->sit_area_segs, si->nat_area_segs); seq_printf(s, "[SSA: %d] [MAIN: %d", diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 9db5500..ec6067c 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -1602,13 +1602,11 @@ static inline bool is_dot_dotdot(const struct qstr *str) static inline bool f2fs_may_extent_tree(struct inode *inode) { - mode_t mode = inode->i_mode; - if (!test_opt(F2FS_I_SB(inode), EXTENT_CACHE) || is_inode_flag_set(F2FS_I(inode), FI_NO_EXTENT)) return false; - return S_ISREG(mode); + return S_ISREG(inode->i_mode); } static inline void *f2fs_kvmalloc(size_t size, gfp_t flags) @@ -2121,7 +2119,7 @@ static inline int f2fs_sb_has_crypto(struct super_block *sb) static inline bool f2fs_may_encrypt(struct inode *inode) { #ifdef CONFIG_F2FS_FS_ENCRYPTION - mode_t mode = inode->i_mode; + umode_t mode = inode->i_mode; return (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode)); #else diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c index 97e20de..5528801 100644 --- a/fs/f2fs/inode.c +++ b/fs/f2fs/inode.c @@ -202,6 +202,7 @@ make_now: inode->i_op = &f2fs_encrypted_symlink_inode_operations; else inode->i_op = &f2fs_symlink_inode_operations; + inode_nohighmem(inode); inode->i_mapping->a_ops = &f2fs_dblock_aops; } else if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode) || S_ISFIFO(inode->i_mode) || S_ISSOCK(inode->i_mode)) { diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c index 2c32110..e7587fc 100644 --- a/fs/f2fs/namei.c +++ b/fs/f2fs/namei.c @@ -315,12 +315,15 @@ fail: return err; } -static const char *f2fs_follow_link(struct dentry *dentry, void **cookie) +static const char *f2fs_get_link(struct dentry *dentry, + struct inode *inode, + struct delayed_call *done) { - const char *link = page_follow_link_light(dentry, cookie); + const char *link = page_get_link(dentry, inode, done); if (!IS_ERR(link) && !*link) { /* this is broken symlink case */ - page_put_link(NULL, *cookie); + do_delayed_call(done); + clear_delayed_call(done); link = ERR_PTR(-ENOENT); } return link; @@ -351,6 +354,7 @@ static int f2fs_symlink(struct inode *dir, struct dentry *dentry, inode->i_op = &f2fs_encrypted_symlink_inode_operations; else inode->i_op = &f2fs_symlink_inode_operations; + inode_nohighmem(inode); inode->i_mapping->a_ops = &f2fs_dblock_aops; f2fs_lock_op(sbi); @@ -923,18 +927,22 @@ static int f2fs_rename2(struct inode *old_dir, struct dentry *old_dentry, } #ifdef CONFIG_F2FS_FS_ENCRYPTION -static const char *f2fs_encrypted_follow_link(struct dentry *dentry, void **cookie) +static const char *f2fs_encrypted_get_link(struct dentry *dentry, + struct inode *inode, + struct delayed_call *done) { struct page *cpage = NULL; char *caddr, *paddr = NULL; struct f2fs_str cstr; struct f2fs_str pstr = FSTR_INIT(NULL, 0); - struct inode *inode = d_inode(dentry); struct f2fs_encrypted_symlink_data *sd; loff_t size = min_t(loff_t, i_size_read(inode), PAGE_SIZE - 1); u32 max_size = inode->i_sb->s_blocksize; int res; + if (!dentry) + return ERR_PTR(-ECHILD); + res = f2fs_get_encryption_info(inode); if (res) return ERR_PTR(res); @@ -942,7 +950,7 @@ static const char *f2fs_encrypted_follow_link(struct dentry *dentry, void **cook cpage = read_mapping_page(inode->i_mapping, 0, NULL); if (IS_ERR(cpage)) return ERR_CAST(cpage); - caddr = kmap(cpage); + caddr = page_address(cpage); caddr[size] = 0; /* Symlink is encrypted */ @@ -982,21 +990,19 @@ static const char *f2fs_encrypted_follow_link(struct dentry *dentry, void **cook /* Null-terminate the name */ paddr[res] = '\0'; - kunmap(cpage); page_cache_release(cpage); - return *cookie = paddr; + set_delayed_call(done, kfree_link, paddr); + return paddr; errout: kfree(cstr.name); f2fs_fname_crypto_free_buffer(&pstr); - kunmap(cpage); page_cache_release(cpage); return ERR_PTR(res); } const struct inode_operations f2fs_encrypted_symlink_inode_operations = { .readlink = generic_readlink, - .follow_link = f2fs_encrypted_follow_link, - .put_link = kfree_put_link, + .get_link = f2fs_encrypted_get_link, .getattr = f2fs_getattr, .setattr = f2fs_setattr, .setxattr = generic_setxattr, @@ -1031,8 +1037,7 @@ const struct inode_operations f2fs_dir_inode_operations = { const struct inode_operations f2fs_symlink_inode_operations = { .readlink = generic_readlink, - .follow_link = f2fs_follow_link, - .put_link = page_put_link, + .get_link = f2fs_get_link, .getattr = f2fs_getattr, .setattr = f2fs_setattr, #ifdef CONFIG_F2FS_FS_XATTR diff --git a/fs/f2fs/xattr.c b/fs/f2fs/xattr.c index 862368a..036952a 100644 --- a/fs/f2fs/xattr.c +++ b/fs/f2fs/xattr.c @@ -25,38 +25,6 @@ #include "f2fs.h" #include "xattr.h" -static size_t f2fs_xattr_generic_list(const struct xattr_handler *handler, - struct dentry *dentry, char *list, size_t list_size, - const char *name, size_t len) -{ - struct f2fs_sb_info *sbi = F2FS_SB(dentry->d_sb); - int total_len, prefix_len; - - switch (handler->flags) { - case F2FS_XATTR_INDEX_USER: - if (!test_opt(sbi, XATTR_USER)) - return -EOPNOTSUPP; - break; - case F2FS_XATTR_INDEX_TRUSTED: - if (!capable(CAP_SYS_ADMIN)) - return -EPERM; - break; - case F2FS_XATTR_INDEX_SECURITY: - break; - default: - return -EINVAL; - } - - prefix_len = strlen(handler->prefix); - total_len = prefix_len + len + 1; - if (list && total_len <= list_size) { - memcpy(list, handler->prefix, prefix_len); - memcpy(list + prefix_len, name, len); - list[prefix_len + len] = '\0'; - } - return total_len; -} - static int f2fs_xattr_generic_get(const struct xattr_handler *handler, struct dentry *dentry, const char *name, void *buffer, size_t size) @@ -77,8 +45,6 @@ static int f2fs_xattr_generic_get(const struct xattr_handler *handler, default: return -EINVAL; } - if (strcmp(name, "") == 0) - return -EINVAL; return f2fs_getxattr(d_inode(dentry), handler->flags, name, buffer, size, NULL); } @@ -103,24 +69,20 @@ static int f2fs_xattr_generic_set(const struct xattr_handler *handler, default: return -EINVAL; } - if (strcmp(name, "") == 0) - return -EINVAL; - return f2fs_setxattr(d_inode(dentry), handler->flags, name, value, size, NULL, flags); } -static size_t f2fs_xattr_advise_list(const struct xattr_handler *handler, - struct dentry *dentry, char *list, size_t list_size, - const char *name, size_t len) +static bool f2fs_xattr_user_list(struct dentry *dentry) { - const char *xname = F2FS_SYSTEM_ADVISE_PREFIX; - size_t size; + struct f2fs_sb_info *sbi = F2FS_SB(dentry->d_sb); - size = strlen(xname) + 1; - if (list && size <= list_size) - memcpy(list, xname, size); - return size; + return test_opt(sbi, XATTR_USER); +} + +static bool f2fs_xattr_trusted_list(struct dentry *dentry) +{ + return capable(CAP_SYS_ADMIN); } static int f2fs_xattr_advise_get(const struct xattr_handler *handler, @@ -129,9 +91,6 @@ static int f2fs_xattr_advise_get(const struct xattr_handler *handler, { struct inode *inode = d_inode(dentry); - if (strcmp(name, "") != 0) - return -EINVAL; - if (buffer) *((char *)buffer) = F2FS_I(inode)->i_advise; return sizeof(char); @@ -143,8 +102,6 @@ static int f2fs_xattr_advise_set(const struct xattr_handler *handler, { struct inode *inode = d_inode(dentry); - if (strcmp(name, "") != 0) - return -EINVAL; if (!inode_owner_or_capable(inode)) return -EPERM; if (value == NULL) @@ -183,7 +140,7 @@ int f2fs_init_security(struct inode *inode, struct inode *dir, const struct xattr_handler f2fs_xattr_user_handler = { .prefix = XATTR_USER_PREFIX, .flags = F2FS_XATTR_INDEX_USER, - .list = f2fs_xattr_generic_list, + .list = f2fs_xattr_user_list, .get = f2fs_xattr_generic_get, .set = f2fs_xattr_generic_set, }; @@ -191,15 +148,14 @@ const struct xattr_handler f2fs_xattr_user_handler = { const struct xattr_handler f2fs_xattr_trusted_handler = { .prefix = XATTR_TRUSTED_PREFIX, .flags = F2FS_XATTR_INDEX_TRUSTED, - .list = f2fs_xattr_generic_list, + .list = f2fs_xattr_trusted_list, .get = f2fs_xattr_generic_get, .set = f2fs_xattr_generic_set, }; const struct xattr_handler f2fs_xattr_advise_handler = { - .prefix = F2FS_SYSTEM_ADVISE_PREFIX, + .name = F2FS_SYSTEM_ADVISE_NAME, .flags = F2FS_XATTR_INDEX_ADVISE, - .list = f2fs_xattr_advise_list, .get = f2fs_xattr_advise_get, .set = f2fs_xattr_advise_set, }; @@ -207,7 +163,6 @@ const struct xattr_handler f2fs_xattr_advise_handler = { const struct xattr_handler f2fs_xattr_security_handler = { .prefix = XATTR_SECURITY_PREFIX, .flags = F2FS_XATTR_INDEX_SECURITY, - .list = f2fs_xattr_generic_list, .get = f2fs_xattr_generic_get, .set = f2fs_xattr_generic_set, }; @@ -455,20 +410,27 @@ ssize_t f2fs_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size) list_for_each_xattr(entry, base_addr) { const struct xattr_handler *handler = f2fs_xattr_handler(entry->e_name_index); + const char *prefix; + size_t prefix_len; size_t size; - if (!handler) + if (!handler || (handler->list && !handler->list(dentry))) continue; - size = handler->list(handler, dentry, buffer, rest, - entry->e_name, entry->e_name_len); - if (buffer && size > rest) { - error = -ERANGE; - goto cleanup; + prefix = handler->prefix ?: handler->name; + prefix_len = strlen(prefix); + size = prefix_len + entry->e_name_len + 1; + if (buffer) { + if (size > rest) { + error = -ERANGE; + goto cleanup; + } + memcpy(buffer, prefix, prefix_len); + buffer += prefix_len; + memcpy(buffer, entry->e_name, entry->e_name_len); + buffer += entry->e_name_len; + *buffer++ = 0; } - - if (buffer) - buffer += size; rest -= size; } error = buffer_size - rest; diff --git a/fs/f2fs/xattr.h b/fs/f2fs/xattr.h index 71a7100..79dccc8 100644 --- a/fs/f2fs/xattr.h +++ b/fs/f2fs/xattr.h @@ -27,7 +27,7 @@ #define F2FS_XATTR_REFCOUNT_MAX 1024 /* Name indexes */ -#define F2FS_SYSTEM_ADVISE_PREFIX "system.advise" +#define F2FS_SYSTEM_ADVISE_NAME "system.advise" #define F2FS_XATTR_INDEX_USER 1 #define F2FS_XATTR_INDEX_POSIX_ACL_ACCESS 2 #define F2FS_XATTR_INDEX_POSIX_ACL_DEFAULT 3 @@ -51,7 +51,8 @@ static int setfl(int fd, struct file * filp, unsigned long arg) if (arg & O_NDELAY) arg |= O_NONBLOCK; - if (arg & O_DIRECT) { + /* Pipe packetized mode is controlled by O_DIRECT flag */ + if (!S_ISFIFO(filp->f_inode->i_mode) && (arg & O_DIRECT)) { if (!filp->f_mapping || !filp->f_mapping->a_ops || !filp->f_mapping->a_ops->direct_IO) return -EINVAL; @@ -25,9 +25,9 @@ int sysctl_nr_open __read_mostly = 1024*1024; int sysctl_nr_open_min = BITS_PER_LONG; -/* our max() is unusable in constant expressions ;-/ */ -#define __const_max(x, y) ((x) < (y) ? (x) : (y)) -int sysctl_nr_open_max = __const_max(INT_MAX, ~(size_t)0/sizeof(void *)) & +/* our min() is unusable in constant expressions ;-/ */ +#define __const_min(x, y) ((x) < (y) ? (x) : (y)) +int sysctl_nr_open_max = __const_min(INT_MAX, ~(size_t)0/sizeof(void *)) & -BITS_PER_LONG; static void *alloc_fdmem(size_t size) diff --git a/fs/freevxfs/vxfs_inode.c b/fs/freevxfs/vxfs_inode.c index ef73ed6..3e2ccad 100644 --- a/fs/freevxfs/vxfs_inode.c +++ b/fs/freevxfs/vxfs_inode.c @@ -326,6 +326,7 @@ vxfs_iget(struct super_block *sbp, ino_t ino) } else if (S_ISLNK(ip->i_mode)) { if (!VXFS_ISIMMED(vip)) { ip->i_op = &page_symlink_inode_operations; + inode_nohighmem(ip); ip->i_mapping->a_ops = &vxfs_aops; } else { ip->i_op = &simple_symlink_inode_operations; diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 5e2e087..712601f 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -1365,15 +1365,19 @@ static int fuse_readdir(struct file *file, struct dir_context *ctx) return err; } -static const char *fuse_follow_link(struct dentry *dentry, void **cookie) +static const char *fuse_get_link(struct dentry *dentry, + struct inode *inode, + struct delayed_call *done) { - struct inode *inode = d_inode(dentry); struct fuse_conn *fc = get_fuse_conn(inode); FUSE_ARGS(args); char *link; ssize_t ret; - link = (char *) __get_free_page(GFP_KERNEL); + if (!dentry) + return ERR_PTR(-ECHILD); + + link = kmalloc(PAGE_SIZE, GFP_KERNEL); if (!link) return ERR_PTR(-ENOMEM); @@ -1385,11 +1389,11 @@ static const char *fuse_follow_link(struct dentry *dentry, void **cookie) args.out.args[0].value = link; ret = fuse_simple_request(fc, &args); if (ret < 0) { - free_page((unsigned long) link); + kfree(link); link = ERR_PTR(ret); } else { link[ret] = '\0'; - *cookie = link; + set_delayed_call(done, kfree_link, link); } fuse_invalidate_atime(inode); return link; @@ -1909,8 +1913,7 @@ static const struct inode_operations fuse_common_inode_operations = { static const struct inode_operations fuse_symlink_inode_operations = { .setattr = fuse_setattr, - .follow_link = fuse_follow_link, - .put_link = free_page_put_link, + .get_link = fuse_get_link, .readlink = generic_readlink, .getattr = fuse_getattr, .setxattr = fuse_setxattr, diff --git a/fs/gfs2/acl.c b/fs/gfs2/acl.c index 1be3b06..7919326 100644 --- a/fs/gfs2/acl.c +++ b/fs/gfs2/acl.c @@ -31,9 +31,9 @@ static const char *gfs2_acl_name(int type) { switch (type) { case ACL_TYPE_ACCESS: - return GFS2_POSIX_ACL_ACCESS; + return XATTR_POSIX_ACL_ACCESS; case ACL_TYPE_DEFAULT: - return GFS2_POSIX_ACL_DEFAULT; + return XATTR_POSIX_ACL_DEFAULT; } return NULL; } diff --git a/fs/gfs2/acl.h b/fs/gfs2/acl.h index 2d65ec4..3af4f40 100644 --- a/fs/gfs2/acl.h +++ b/fs/gfs2/acl.h @@ -12,8 +12,6 @@ #include "incore.h" -#define GFS2_POSIX_ACL_ACCESS "posix_acl_access" -#define GFS2_POSIX_ACL_DEFAULT "posix_acl_default" #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); diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c index 1caee05..93f0746 100644 --- a/fs/gfs2/aops.c +++ b/fs/gfs2/aops.c @@ -914,7 +914,7 @@ static int gfs2_write_end(struct file *file, struct address_space *mapping, failed: gfs2_trans_end(sdp); gfs2_inplace_release(ip); - if (ip->i_res->rs_qa_qd_num) + if (ip->i_qadata && ip->i_qadata->qa_qd_num) gfs2_quota_unlock(ip); if (inode == sdp->sd_rindex) { gfs2_glock_dq(&m_ip->i_gh); diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index 61296ec..0860f0b 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -787,8 +787,8 @@ static int do_strip(struct gfs2_inode *ip, struct buffer_head *dibh, if (error) goto out_rlist; - if (gfs2_rs_active(ip->i_res)) /* needs to be done with the rgrp glock held */ - gfs2_rs_deltree(ip->i_res); + if (gfs2_rs_active(&ip->i_res)) /* needs to be done with the rgrp glock held */ + gfs2_rs_deltree(&ip->i_res); error = gfs2_trans_begin(sdp, rg_blocks + RES_DINODE + RES_INDIRECT + RES_STATFS + RES_QUOTA, @@ -1291,13 +1291,9 @@ int gfs2_setattr_size(struct inode *inode, u64 newsize) if (ret) return ret; - ret = get_write_access(inode); - if (ret) - return ret; - inode_dio_wait(inode); - ret = gfs2_rs_alloc(ip); + ret = gfs2_rsqa_alloc(ip); if (ret) goto out; @@ -1307,10 +1303,9 @@ int gfs2_setattr_size(struct inode *inode, u64 newsize) goto out; } - gfs2_rs_deltree(ip->i_res); ret = do_shrink(inode, oldsize, newsize); out: - put_write_access(inode); + gfs2_rsqa_delete(ip, NULL); return ret; } diff --git a/fs/gfs2/dir.c b/fs/gfs2/dir.c index ad8a5b7..6a92592 100644 --- a/fs/gfs2/dir.c +++ b/fs/gfs2/dir.c @@ -82,6 +82,8 @@ #define gfs2_disk_hash2offset(h) (((u64)(h)) >> 1) #define gfs2_dir_offset2hash(p) ((u32)(((u64)(p)) << 1)) +#define GFS2_HASH_INDEX_MASK 0xffffc000 +#define GFS2_USE_HASH_FLAG 0x2000 struct qstr gfs2_qdot __read_mostly; struct qstr gfs2_qdotdot __read_mostly; @@ -108,7 +110,7 @@ static int gfs2_dir_get_existing_buffer(struct gfs2_inode *ip, u64 block, struct buffer_head *bh; int error; - error = gfs2_meta_read(ip->i_gl, block, DIO_WAIT, &bh); + error = gfs2_meta_read(ip->i_gl, block, DIO_WAIT, 0, &bh); if (error) return error; if (gfs2_metatype_check(GFS2_SB(&ip->i_inode), bh, GFS2_METATYPE_JD)) { @@ -305,7 +307,7 @@ static int gfs2_dir_read_data(struct gfs2_inode *ip, __be64 *buf, BUG_ON(extlen < 1); bh = gfs2_meta_ra(ip->i_gl, dblock, extlen); } else { - error = gfs2_meta_read(ip->i_gl, dblock, DIO_WAIT, &bh); + error = gfs2_meta_read(ip->i_gl, dblock, DIO_WAIT, 0, &bh); if (error) goto fail; } @@ -443,6 +445,27 @@ static int gfs2_dirent_last(const struct gfs2_dirent *dent, return 0; } +/* Look for the dirent that contains the offset specified in data. Once we + * find that dirent, there must be space available there for the new dirent */ +static int gfs2_dirent_find_offset(const struct gfs2_dirent *dent, + const struct qstr *name, + void *ptr) +{ + unsigned required = GFS2_DIRENT_SIZE(name->len); + unsigned actual = GFS2_DIRENT_SIZE(be16_to_cpu(dent->de_name_len)); + unsigned totlen = be16_to_cpu(dent->de_rec_len); + + if (ptr < (void *)dent || ptr >= (void *)dent + totlen) + return 0; + if (gfs2_dirent_sentinel(dent)) + actual = 0; + if (ptr < (void *)dent + actual) + return -1; + if ((void *)dent + totlen >= ptr + required) + return 1; + return -1; +} + static int gfs2_dirent_find_space(const struct gfs2_dirent *dent, const struct qstr *name, void *opaque) @@ -682,6 +705,27 @@ static void dirent_del(struct gfs2_inode *dip, struct buffer_head *bh, prev->de_rec_len = cpu_to_be16(prev_rec_len); } + +static struct gfs2_dirent *do_init_dirent(struct inode *inode, + struct gfs2_dirent *dent, + const struct qstr *name, + struct buffer_head *bh, + unsigned offset) +{ + struct gfs2_inode *ip = GFS2_I(inode); + struct gfs2_dirent *ndent; + unsigned totlen; + + totlen = be16_to_cpu(dent->de_rec_len); + BUG_ON(offset + name->len > totlen); + gfs2_trans_add_meta(ip->i_gl, bh); + ndent = (struct gfs2_dirent *)((char *)dent + offset); + dent->de_rec_len = cpu_to_be16(offset); + gfs2_qstr2dirent(name, totlen - offset, ndent); + return ndent; +} + + /* * Takes a dent from which to grab space as an argument. Returns the * newly created dent. @@ -691,31 +735,25 @@ static struct gfs2_dirent *gfs2_init_dirent(struct inode *inode, const struct qstr *name, struct buffer_head *bh) { - struct gfs2_inode *ip = GFS2_I(inode); - struct gfs2_dirent *ndent; - unsigned offset = 0, totlen; + unsigned offset = 0; if (!gfs2_dirent_sentinel(dent)) offset = GFS2_DIRENT_SIZE(be16_to_cpu(dent->de_name_len)); - totlen = be16_to_cpu(dent->de_rec_len); - BUG_ON(offset + name->len > totlen); - gfs2_trans_add_meta(ip->i_gl, bh); - ndent = (struct gfs2_dirent *)((char *)dent + offset); - dent->de_rec_len = cpu_to_be16(offset); - gfs2_qstr2dirent(name, totlen - offset, ndent); - return ndent; + return do_init_dirent(inode, dent, name, bh, offset); } -static struct gfs2_dirent *gfs2_dirent_alloc(struct inode *inode, - struct buffer_head *bh, - const struct qstr *name) +static struct gfs2_dirent *gfs2_dirent_split_alloc(struct inode *inode, + struct buffer_head *bh, + const struct qstr *name, + void *ptr) { struct gfs2_dirent *dent; dent = gfs2_dirent_scan(inode, bh->b_data, bh->b_size, - gfs2_dirent_find_space, name, NULL); + gfs2_dirent_find_offset, name, ptr); if (!dent || IS_ERR(dent)) return dent; - return gfs2_init_dirent(inode, dent, name, bh); + return do_init_dirent(inode, dent, name, bh, + (unsigned)(ptr - (void *)dent)); } static int get_leaf(struct gfs2_inode *dip, u64 leaf_no, @@ -723,7 +761,7 @@ static int get_leaf(struct gfs2_inode *dip, u64 leaf_no, { int error; - error = gfs2_meta_read(dip->i_gl, leaf_no, DIO_WAIT, bhp); + error = gfs2_meta_read(dip->i_gl, leaf_no, DIO_WAIT, 0, bhp); if (!error && gfs2_metatype_check(GFS2_SB(&dip->i_inode), *bhp, GFS2_METATYPE_LF)) { /* pr_info("block num=%llu\n", leaf_no); */ error = -EIO; @@ -1051,10 +1089,11 @@ static int dir_split_leaf(struct inode *inode, const struct qstr *name) if (!gfs2_dirent_sentinel(dent) && be32_to_cpu(dent->de_hash) < divider) { struct qstr str; + void *ptr = ((char *)dent - obh->b_data) + nbh->b_data; str.name = (char*)(dent+1); str.len = be16_to_cpu(dent->de_name_len); str.hash = be32_to_cpu(dent->de_hash); - new = gfs2_dirent_alloc(inode, nbh, &str); + new = gfs2_dirent_split_alloc(inode, nbh, &str, ptr); if (IS_ERR(new)) { error = PTR_ERR(new); break; @@ -1186,10 +1225,10 @@ static int compare_dents(const void *a, const void *b) int ret = 0; dent_a = *(const struct gfs2_dirent **)a; - hash_a = be32_to_cpu(dent_a->de_hash); + hash_a = dent_a->de_cookie; dent_b = *(const struct gfs2_dirent **)b; - hash_b = be32_to_cpu(dent_b->de_hash); + hash_b = dent_b->de_cookie; if (hash_a > hash_b) ret = 1; @@ -1227,19 +1266,20 @@ static int compare_dents(const void *a, const void *b) */ static int do_filldir_main(struct gfs2_inode *dip, struct dir_context *ctx, - const struct gfs2_dirent **darr, u32 entries, - int *copied) + struct gfs2_dirent **darr, u32 entries, + u32 sort_start, int *copied) { const struct gfs2_dirent *dent, *dent_next; u64 off, off_next; unsigned int x, y; int run = 0; - sort(darr, entries, sizeof(struct gfs2_dirent *), compare_dents, NULL); + if (sort_start < entries) + sort(&darr[sort_start], entries - sort_start, + sizeof(struct gfs2_dirent *), compare_dents, NULL); dent_next = darr[0]; - off_next = be32_to_cpu(dent_next->de_hash); - off_next = gfs2_disk_hash2offset(off_next); + off_next = dent_next->de_cookie; for (x = 0, y = 1; x < entries; x++, y++) { dent = dent_next; @@ -1247,8 +1287,7 @@ static int do_filldir_main(struct gfs2_inode *dip, struct dir_context *ctx, if (y < entries) { dent_next = darr[y]; - off_next = be32_to_cpu(dent_next->de_hash); - off_next = gfs2_disk_hash2offset(off_next); + off_next = dent_next->de_cookie; if (off < ctx->pos) continue; @@ -1295,6 +1334,40 @@ static void *gfs2_alloc_sort_buffer(unsigned size) return ptr; } + +static int gfs2_set_cookies(struct gfs2_sbd *sdp, struct buffer_head *bh, + unsigned leaf_nr, struct gfs2_dirent **darr, + unsigned entries) +{ + int sort_id = -1; + int i; + + for (i = 0; i < entries; i++) { + unsigned offset; + + darr[i]->de_cookie = be32_to_cpu(darr[i]->de_hash); + darr[i]->de_cookie = gfs2_disk_hash2offset(darr[i]->de_cookie); + + if (!sdp->sd_args.ar_loccookie) + continue; + offset = (char *)(darr[i]) - + (bh->b_data + gfs2_dirent_offset(bh->b_data)); + offset /= GFS2_MIN_DIRENT_SIZE; + offset += leaf_nr * sdp->sd_max_dents_per_leaf; + if (offset >= GFS2_USE_HASH_FLAG || + leaf_nr >= GFS2_USE_HASH_FLAG) { + darr[i]->de_cookie |= GFS2_USE_HASH_FLAG; + if (sort_id < 0) + sort_id = i; + continue; + } + darr[i]->de_cookie &= GFS2_HASH_INDEX_MASK; + darr[i]->de_cookie |= offset; + } + return sort_id; +} + + static int gfs2_dir_read_leaf(struct inode *inode, struct dir_context *ctx, int *copied, unsigned *depth, u64 leaf_no) @@ -1304,12 +1377,11 @@ static int gfs2_dir_read_leaf(struct inode *inode, struct dir_context *ctx, struct buffer_head *bh; struct gfs2_leaf *lf; unsigned entries = 0, entries2 = 0; - unsigned leaves = 0; - const struct gfs2_dirent **darr, *dent; + unsigned leaves = 0, leaf = 0, offset, sort_offset; + struct gfs2_dirent **darr, *dent; struct dirent_gather g; struct buffer_head **larr; - int leaf = 0; - int error, i; + int error, i, need_sort = 0, sort_id; u64 lfn = leaf_no; do { @@ -1325,6 +1397,11 @@ static int gfs2_dir_read_leaf(struct inode *inode, struct dir_context *ctx, brelse(bh); } while(lfn); + if (*depth < GFS2_DIR_MAX_DEPTH || !sdp->sd_args.ar_loccookie) { + need_sort = 1; + sort_offset = 0; + } + if (!entries) return 0; @@ -1338,8 +1415,8 @@ static int gfs2_dir_read_leaf(struct inode *inode, struct dir_context *ctx, larr = gfs2_alloc_sort_buffer((leaves + entries + 99) * sizeof(void *)); if (!larr) goto out; - darr = (const struct gfs2_dirent **)(larr + leaves); - g.pdent = darr; + darr = (struct gfs2_dirent **)(larr + leaves); + g.pdent = (const struct gfs2_dirent **)darr; g.offset = 0; lfn = leaf_no; @@ -1350,6 +1427,7 @@ static int gfs2_dir_read_leaf(struct inode *inode, struct dir_context *ctx, lf = (struct gfs2_leaf *)bh->b_data; lfn = be64_to_cpu(lf->lf_next); if (lf->lf_entries) { + offset = g.offset; entries2 += be16_to_cpu(lf->lf_entries); dent = gfs2_dirent_scan(inode, bh->b_data, bh->b_size, gfs2_dirent_gather, NULL, &g); @@ -1367,17 +1445,26 @@ static int gfs2_dir_read_leaf(struct inode *inode, struct dir_context *ctx, goto out_free; } error = 0; + sort_id = gfs2_set_cookies(sdp, bh, leaf, &darr[offset], + be16_to_cpu(lf->lf_entries)); + if (!need_sort && sort_id >= 0) { + need_sort = 1; + sort_offset = offset + sort_id; + } larr[leaf++] = bh; } else { + larr[leaf++] = NULL; brelse(bh); } } while(lfn); BUG_ON(entries2 != entries); - error = do_filldir_main(ip, ctx, darr, entries, copied); + error = do_filldir_main(ip, ctx, darr, entries, need_sort ? + sort_offset : entries, copied); out_free: for(i = 0; i < leaf; i++) - brelse(larr[i]); + if (larr[i]) + brelse(larr[i]); kvfree(larr); out: return error; @@ -1483,7 +1570,7 @@ int gfs2_dir_read(struct inode *inode, struct dir_context *ctx, struct gfs2_inode *dip = GFS2_I(inode); struct gfs2_sbd *sdp = GFS2_SB(inode); struct dirent_gather g; - const struct gfs2_dirent **darr, *dent; + struct gfs2_dirent **darr, *dent; struct buffer_head *dibh; int copied = 0; int error; @@ -1507,7 +1594,7 @@ int gfs2_dir_read(struct inode *inode, struct dir_context *ctx, /* 96 is max number of dirents which can be stuffed into an inode */ darr = kmalloc(96 * sizeof(struct gfs2_dirent *), GFP_NOFS); if (darr) { - g.pdent = darr; + g.pdent = (const struct gfs2_dirent **)darr; g.offset = 0; dent = gfs2_dirent_scan(inode, dibh->b_data, dibh->b_size, gfs2_dirent_gather, NULL, &g); @@ -1524,8 +1611,9 @@ int gfs2_dir_read(struct inode *inode, struct dir_context *ctx, error = -EIO; goto out; } + gfs2_set_cookies(sdp, dibh, 0, darr, dip->i_entries); error = do_filldir_main(dip, ctx, darr, - dip->i_entries, &copied); + dip->i_entries, 0, &copied); out: kfree(darr); } @@ -1560,15 +1648,22 @@ struct inode *gfs2_dir_search(struct inode *dir, const struct qstr *name, dent = gfs2_dirent_search(dir, name, gfs2_dirent_find, &bh); if (dent) { + struct inode *inode; + u16 rahead; + if (IS_ERR(dent)) return ERR_CAST(dent); dtype = be16_to_cpu(dent->de_type); + rahead = be16_to_cpu(dent->de_rahead); addr = be64_to_cpu(dent->de_inum.no_addr); formal_ino = be64_to_cpu(dent->de_inum.no_formal_ino); brelse(bh); if (fail_on_exist) return ERR_PTR(-EEXIST); - return gfs2_inode_lookup(dir->i_sb, dtype, addr, formal_ino, 0); + inode = gfs2_inode_lookup(dir->i_sb, dtype, addr, formal_ino, 0); + if (!IS_ERR(inode)) + GFS2_I(inode)->i_rahead = rahead; + return inode; } return ERR_PTR(-ENOENT); } diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index 5e42546..7412863 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -298,9 +298,9 @@ static int gfs2_set_flags(struct file *filp, u32 __user *ptr) gfsflags &= ~GFS2_DIF_TOPDIR; if (gfsflags & GFS2_DIF_INHERIT_JDATA) gfsflags ^= (GFS2_DIF_JDATA | GFS2_DIF_INHERIT_JDATA); - return do_gfs2_set_flags(filp, gfsflags, ~0); + return do_gfs2_set_flags(filp, gfsflags, ~GFS2_DIF_SYSTEM); } - return do_gfs2_set_flags(filp, gfsflags, ~GFS2_DIF_JDATA); + return do_gfs2_set_flags(filp, gfsflags, ~(GFS2_DIF_SYSTEM | GFS2_DIF_JDATA)); } static long gfs2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) @@ -336,8 +336,8 @@ static void gfs2_size_hint(struct file *filep, loff_t offset, size_t size) size_t blks = (size + sdp->sd_sb.sb_bsize - 1) >> sdp->sd_sb.sb_bsize_shift; int hint = min_t(size_t, INT_MAX, blks); - if (hint > atomic_read(&ip->i_res->rs_sizehint)) - atomic_set(&ip->i_res->rs_sizehint, hint); + if (hint > atomic_read(&ip->i_res.rs_sizehint)) + atomic_set(&ip->i_res.rs_sizehint, hint); } /** @@ -397,14 +397,10 @@ static int gfs2_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) /* Update file times before taking page lock */ file_update_time(vma->vm_file); - ret = get_write_access(inode); + ret = gfs2_rsqa_alloc(ip); if (ret) goto out; - ret = gfs2_rs_alloc(ip); - if (ret) - goto out_write_access; - gfs2_size_hint(vma->vm_file, pos, PAGE_CACHE_SIZE); gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh); @@ -486,8 +482,6 @@ out_uninit: set_page_dirty(page); wait_for_stable_page(page); } -out_write_access: - put_write_access(inode); out: sb_end_pagefault(inode->i_sb); return block_page_mkwrite_return(ret); @@ -623,7 +617,7 @@ static int gfs2_release(struct inode *inode, struct file *file) if (!(file->f_mode & FMODE_WRITE)) return 0; - gfs2_rs_delete(ip, &inode->i_writecount); + gfs2_rsqa_delete(ip, &inode->i_writecount); return 0; } @@ -703,7 +697,7 @@ static ssize_t gfs2_file_write_iter(struct kiocb *iocb, struct iov_iter *from) struct gfs2_inode *ip = GFS2_I(file_inode(file)); int ret; - ret = gfs2_rs_alloc(ip); + ret = gfs2_rsqa_alloc(ip); if (ret) return ret; @@ -938,13 +932,14 @@ static long gfs2_fallocate(struct file *file, int mode, loff_t offset, loff_t le if (ret) goto out_unlock; - ret = gfs2_rs_alloc(ip); + ret = gfs2_rsqa_alloc(ip); if (ret) goto out_putw; ret = __gfs2_fallocate(file, mode, offset, len); if (ret) - gfs2_rs_deltree(ip->i_res); + gfs2_rs_deltree(&ip->i_res); + out_putw: put_write_access(inode); out_unlock: @@ -962,7 +957,7 @@ static ssize_t gfs2_file_splice_write(struct pipe_inode_info *pipe, int error; struct gfs2_inode *ip = GFS2_I(out->f_mapping->host); - error = gfs2_rs_alloc(ip); + error = gfs2_rsqa_alloc(ip); if (error) return (ssize_t)error; @@ -1018,7 +1013,7 @@ static int do_flock(struct file *file, int cmd, struct file_lock *fl) struct gfs2_inode *ip = GFS2_I(file_inode(file)); struct gfs2_glock *gl; unsigned int state; - int flags; + u16 flags; int error = 0; int sleeptime; @@ -1032,7 +1027,10 @@ static int do_flock(struct file *file, int cmd, struct file_lock *fl) if (fl_gh->gh_state == state) goto out; locks_lock_file_wait(file, - &(struct file_lock){.fl_type = F_UNLCK}); + &(struct file_lock) { + .fl_type = F_UNLCK, + .fl_flags = FL_FLOCK + }); gfs2_glock_dq(fl_gh); gfs2_holder_reinit(state, flags, fl_gh); } else { diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index 32e7471..a4ff7b5 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -446,7 +446,7 @@ __acquires(&gl->gl_lockref.lock) { const struct gfs2_glock_operations *glops = gl->gl_ops; struct gfs2_sbd *sdp = gl->gl_name.ln_sbd; - unsigned int lck_flags = gh ? gh->gh_flags : 0; + unsigned int lck_flags = (unsigned int)(gh ? gh->gh_flags : 0); int ret; lck_flags &= (LM_FLAG_TRY | LM_FLAG_TRY_1CB | LM_FLAG_NOEXP | @@ -750,7 +750,7 @@ again: * */ -void gfs2_holder_init(struct gfs2_glock *gl, unsigned int state, unsigned flags, +void gfs2_holder_init(struct gfs2_glock *gl, unsigned int state, u16 flags, struct gfs2_holder *gh) { INIT_LIST_HEAD(&gh->gh_list); @@ -774,7 +774,7 @@ void gfs2_holder_init(struct gfs2_glock *gl, unsigned int state, unsigned flags, * */ -void gfs2_holder_reinit(unsigned int state, unsigned flags, struct gfs2_holder *gh) +void gfs2_holder_reinit(unsigned int state, u16 flags, struct gfs2_holder *gh) { gh->gh_state = state; gh->gh_flags = flags; @@ -1080,7 +1080,7 @@ void gfs2_glock_dq_uninit(struct gfs2_holder *gh) int gfs2_glock_nq_num(struct gfs2_sbd *sdp, u64 number, const struct gfs2_glock_operations *glops, - unsigned int state, int flags, struct gfs2_holder *gh) + unsigned int state, u16 flags, struct gfs2_holder *gh) { struct gfs2_glock *gl; int error; @@ -1417,14 +1417,14 @@ static struct shrinker glock_shrinker = { static void glock_hash_walk(glock_examiner examiner, const struct gfs2_sbd *sdp) { struct gfs2_glock *gl; - struct rhash_head *pos, *next; + struct rhash_head *pos; const struct bucket_table *tbl; int i; rcu_read_lock(); tbl = rht_dereference_rcu(gl_hash_table.tbl, &gl_hash_table); for (i = 0; i < tbl->size; i++) { - rht_for_each_entry_safe(gl, pos, next, tbl, i, gl_node) { + rht_for_each_entry_rcu(gl, pos, tbl, i, gl_node) { if ((gl->gl_name.ln_sbd == sdp) && lockref_get_not_dead(&gl->gl_lockref)) examiner(gl); @@ -1506,7 +1506,9 @@ void gfs2_gl_hash_clear(struct gfs2_sbd *sdp) flush_workqueue(glock_workqueue); glock_hash_walk(clear_glock, sdp); flush_workqueue(glock_workqueue); - wait_event(sdp->sd_glock_wait, atomic_read(&sdp->sd_glock_disposal) == 0); + wait_event_timeout(sdp->sd_glock_wait, + atomic_read(&sdp->sd_glock_disposal) == 0, + HZ * 600); glock_hash_walk(dump_glock_func, sdp); } @@ -1539,7 +1541,7 @@ static const char *state2str(unsigned state) return "??"; } -static const char *hflags2str(char *buf, unsigned flags, unsigned long iflags) +static const char *hflags2str(char *buf, u16 flags, unsigned long iflags) { char *p = buf; if (flags & LM_FLAG_TRY) diff --git a/fs/gfs2/glock.h b/fs/gfs2/glock.h index f7cdaa8..46ab67f 100644 --- a/fs/gfs2/glock.h +++ b/fs/gfs2/glock.h @@ -79,15 +79,15 @@ enum { * requested had acquired and released the lock. */ -#define LM_FLAG_TRY 0x00000001 -#define LM_FLAG_TRY_1CB 0x00000002 -#define LM_FLAG_NOEXP 0x00000004 -#define LM_FLAG_ANY 0x00000008 -#define LM_FLAG_PRIORITY 0x00000010 -#define GL_ASYNC 0x00000040 -#define GL_EXACT 0x00000080 -#define GL_SKIP 0x00000100 -#define GL_NOCACHE 0x00000400 +#define LM_FLAG_TRY 0x0001 +#define LM_FLAG_TRY_1CB 0x0002 +#define LM_FLAG_NOEXP 0x0004 +#define LM_FLAG_ANY 0x0008 +#define LM_FLAG_PRIORITY 0x0010 +#define GL_ASYNC 0x0040 +#define GL_EXACT 0x0080 +#define GL_SKIP 0x0100 +#define GL_NOCACHE 0x0400 /* * lm_async_cb return flags @@ -183,8 +183,8 @@ extern int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number, int create, struct gfs2_glock **glp); extern void gfs2_glock_put(struct gfs2_glock *gl); extern void gfs2_holder_init(struct gfs2_glock *gl, unsigned int state, - unsigned flags, struct gfs2_holder *gh); -extern void gfs2_holder_reinit(unsigned int state, unsigned flags, + u16 flags, struct gfs2_holder *gh); +extern void gfs2_holder_reinit(unsigned int state, u16 flags, struct gfs2_holder *gh); extern void gfs2_holder_uninit(struct gfs2_holder *gh); extern int gfs2_glock_nq(struct gfs2_holder *gh); @@ -195,7 +195,7 @@ extern void gfs2_glock_dq_wait(struct gfs2_holder *gh); extern void gfs2_glock_dq_uninit(struct gfs2_holder *gh); extern int gfs2_glock_nq_num(struct gfs2_sbd *sdp, u64 number, const struct gfs2_glock_operations *glops, - unsigned int state, int flags, + unsigned int state, u16 flags, struct gfs2_holder *gh); extern int gfs2_glock_nq_m(unsigned int num_gh, struct gfs2_holder *ghs); extern void gfs2_glock_dq_m(unsigned int num_gh, struct gfs2_holder *ghs); @@ -215,7 +215,7 @@ void gfs2_print_dbg(struct seq_file *seq, const char *fmt, ...); */ static inline int gfs2_glock_nq_init(struct gfs2_glock *gl, - unsigned int state, int flags, + unsigned int state, u16 flags, struct gfs2_holder *gh) { int error; diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h index de7b4f9..845fb09 100644 --- a/fs/gfs2/incore.h +++ b/fs/gfs2/incore.h @@ -259,8 +259,8 @@ struct gfs2_holder { struct gfs2_glock *gh_gl; struct pid *gh_owner_pid; - unsigned int gh_state; - unsigned gh_flags; + u16 gh_flags; + u16 gh_state; int gh_error; unsigned long gh_iflags; /* HIF_... */ @@ -270,6 +270,13 @@ struct gfs2_holder { /* Number of quota types we support */ #define GFS2_MAXQUOTAS 2 +struct gfs2_qadata { /* quota allocation data */ + /* Quota stuff */ + struct gfs2_quota_data *qa_qd[2 * GFS2_MAXQUOTAS]; + struct gfs2_holder qa_qd_ghs[2 * GFS2_MAXQUOTAS]; + unsigned int qa_qd_num; +}; + /* Resource group multi-block reservation, in order of appearance: Step 1. Function prepares to write, allocates a mb, sets the size hint. @@ -288,11 +295,6 @@ struct gfs2_blkreserv { struct gfs2_rbm rs_rbm; /* Start of reservation */ u32 rs_free; /* how many blocks are still free */ u64 rs_inum; /* Inode number for reservation */ - - /* ancillary quota stuff */ - struct gfs2_quota_data *rs_qa_qd[2 * GFS2_MAXQUOTAS]; - struct gfs2_holder rs_qa_qd_ghs[2 * GFS2_MAXQUOTAS]; - unsigned int rs_qa_qd_num; }; /* @@ -391,7 +393,8 @@ struct gfs2_inode { struct gfs2_glock *i_gl; /* Move into i_gh? */ struct gfs2_holder i_iopen_gh; struct gfs2_holder i_gh; /* for prepare/commit_write only */ - struct gfs2_blkreserv *i_res; /* rgrp multi-block reservation */ + struct gfs2_qadata *i_qadata; /* quota allocation data */ + struct gfs2_blkreserv i_res; /* rgrp multi-block reservation */ struct gfs2_rgrpd *i_rgd; u64 i_goal; /* goal block for allocations */ struct rw_semaphore i_rw_mutex; @@ -402,6 +405,7 @@ struct gfs2_inode { u32 i_diskflags; u8 i_height; u8 i_depth; + u16 i_rahead; }; /* @@ -558,6 +562,8 @@ struct gfs2_args { unsigned int ar_errors:2; /* errors=withdraw | panic */ unsigned int ar_nobarrier:1; /* do not send barriers */ unsigned int ar_rgrplvb:1; /* use lvbs for rgrp info */ + unsigned int ar_loccookie:1; /* use location based readdir + cookies */ int ar_commit; /* Commit interval */ int ar_statfs_quantum; /* The fast statfs interval */ int ar_quota_quantum; /* The quota interval */ @@ -685,6 +691,7 @@ struct gfs2_sbd { u64 sd_heightsize[GFS2_MAX_META_HEIGHT + 1]; u32 sd_max_jheight; /* Max height of journaled file's meta tree */ u64 sd_jheightsize[GFS2_MAX_META_HEIGHT + 1]; + u32 sd_max_dents_per_leaf; /* Max number of dirents in a leaf block */ struct gfs2_args sd_args; /* Mount arguments */ struct gfs2_tune sd_tune; /* Filesystem tuning structure */ diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index 063fdfc..3e94400 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -191,13 +191,13 @@ struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned int type, fail_refresh: ip->i_iopen_gh.gh_flags |= GL_NOCACHE; ip->i_iopen_gh.gh_gl->gl_object = NULL; - gfs2_glock_dq_uninit(&ip->i_iopen_gh); + gfs2_glock_dq_wait(&ip->i_iopen_gh); + gfs2_holder_uninit(&ip->i_iopen_gh); fail_iopen: if (io_gl) gfs2_glock_put(io_gl); fail_put: ip->i_gl->gl_object = NULL; - gfs2_glock_put(ip->i_gl); fail: iget_failed(inode); return ERR_PTR(error); @@ -593,7 +593,7 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, struct gfs2_inode *dip = GFS2_I(dir), *ip; struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode); struct gfs2_glock *io_gl; - int error, free_vfs_inode = 0; + int error, free_vfs_inode = 1; u32 aflags = 0; unsigned blocks = 1; struct gfs2_diradd da = { .bh = NULL, .save_loc = 1, }; @@ -601,7 +601,7 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, if (!name->len || name->len > GFS2_FNAMESIZE) return -ENAMETOOLONG; - error = gfs2_rs_alloc(dip); + error = gfs2_rsqa_alloc(dip); if (error) return error; @@ -650,10 +650,10 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, error = posix_acl_create(dir, &mode, &default_acl, &acl); if (error) - goto fail_free_vfs_inode; + goto fail_gunlock; ip = GFS2_I(inode); - error = gfs2_rs_alloc(ip); + error = gfs2_rsqa_alloc(ip); if (error) goto fail_free_acls; @@ -685,6 +685,11 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, ip->i_entries = 2; break; } + + /* Force SYSTEM flag on all files and subdirs of a SYSTEM directory */ + if (dip->i_diskflags & GFS2_DIF_SYSTEM) + ip->i_diskflags |= GFS2_DIF_SYSTEM; + gfs2_set_inode_flags(inode); if ((GFS2_I(d_inode(sdp->sd_root_dir)) == dip) || @@ -733,6 +738,9 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, gfs2_set_iop(inode); insert_inode_hash(inode); + free_vfs_inode = 0; /* After this point, the inode is no longer + considered free. Any failures need to undo + the gfs2 structures. */ if (default_acl) { error = gfs2_set_acl(inode, default_acl, ACL_TYPE_DEFAULT); posix_acl_release(default_acl); @@ -766,24 +774,19 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, return error; fail_gunlock3: - gfs2_glock_dq_uninit(ghs + 1); - if (ip->i_gl) - gfs2_glock_put(ip->i_gl); - goto fail_gunlock; - + gfs2_glock_dq_uninit(&ip->i_iopen_gh); + gfs2_glock_put(io_gl); fail_gunlock2: gfs2_glock_dq_uninit(ghs + 1); fail_free_inode: if (ip->i_gl) gfs2_glock_put(ip->i_gl); - gfs2_rs_delete(ip, NULL); + gfs2_rsqa_delete(ip, NULL); fail_free_acls: if (default_acl) posix_acl_release(default_acl); if (acl) posix_acl_release(acl); -fail_free_vfs_inode: - free_vfs_inode = 1; fail_gunlock: gfs2_dir_no_add(&da); gfs2_glock_dq_uninit(ghs); @@ -898,7 +901,7 @@ static int gfs2_link(struct dentry *old_dentry, struct inode *dir, if (S_ISDIR(inode->i_mode)) return -EPERM; - error = gfs2_rs_alloc(dip); + error = gfs2_rsqa_alloc(dip); if (error) return error; @@ -1371,7 +1374,7 @@ static int gfs2_rename(struct inode *odir, struct dentry *odentry, if (error) return error; - error = gfs2_rs_alloc(ndip); + error = gfs2_rsqa_alloc(ndip); if (error) return error; @@ -1712,24 +1715,30 @@ static int gfs2_rename2(struct inode *odir, struct dentry *odentry, } /** - * gfs2_follow_link - Follow a symbolic link + * gfs2_get_link - Follow a symbolic link * @dentry: The dentry of the link - * @nd: Data that we pass to vfs_follow_link() + * @inode: The inode of the link + * @done: destructor for return value * * This can handle symlinks of any size. * * Returns: 0 on success or error code */ -static const char *gfs2_follow_link(struct dentry *dentry, void **cookie) +static const char *gfs2_get_link(struct dentry *dentry, + struct inode *inode, + struct delayed_call *done) { - struct gfs2_inode *ip = GFS2_I(d_inode(dentry)); + struct gfs2_inode *ip = GFS2_I(inode); struct gfs2_holder i_gh; struct buffer_head *dibh; unsigned int size; char *buf; int error; + if (!dentry) + return ERR_PTR(-ECHILD); + gfs2_holder_init(ip->i_gl, LM_ST_SHARED, 0, &i_gh); error = gfs2_glock_nq(&i_gh); if (error) { @@ -1759,7 +1768,7 @@ static const char *gfs2_follow_link(struct dentry *dentry, void **cookie) out: gfs2_glock_dq_uninit(&i_gh); if (!IS_ERR(buf)) - *cookie = buf; + set_delayed_call(done, kfree_link, buf); return buf; } @@ -1854,11 +1863,7 @@ static int setattr_chown(struct inode *inode, struct iattr *attr) if (!(attr->ia_valid & ATTR_GID) || gid_eq(ogid, ngid)) ogid = ngid = NO_GID_QUOTA_CHANGE; - error = get_write_access(inode); - if (error) - return error; - - error = gfs2_rs_alloc(ip); + error = gfs2_rsqa_alloc(ip); if (error) goto out; @@ -1898,7 +1903,6 @@ out_end_trans: out_gunlock_q: gfs2_quota_unlock(ip); out: - put_write_access(inode); return error; } @@ -1920,7 +1924,7 @@ static int gfs2_setattr(struct dentry *dentry, struct iattr *attr) struct gfs2_holder i_gh; int error; - error = gfs2_rs_alloc(ip); + error = gfs2_rsqa_alloc(ip); if (error) return error; @@ -2002,7 +2006,7 @@ static int gfs2_setxattr(struct dentry *dentry, const char *name, gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh); ret = gfs2_glock_nq(&gh); if (ret == 0) { - ret = gfs2_rs_alloc(ip); + ret = gfs2_rsqa_alloc(ip); if (ret == 0) ret = generic_setxattr(dentry, name, data, size, flags); gfs2_glock_dq(&gh); @@ -2043,7 +2047,7 @@ static int gfs2_removexattr(struct dentry *dentry, const char *name) gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh); ret = gfs2_glock_nq(&gh); if (ret == 0) { - ret = gfs2_rs_alloc(ip); + ret = gfs2_rsqa_alloc(ip); if (ret == 0) ret = generic_removexattr(dentry, name); gfs2_glock_dq(&gh); @@ -2132,8 +2136,7 @@ const struct inode_operations gfs2_dir_iops = { const struct inode_operations gfs2_symlink_iops = { .readlink = generic_readlink, - .follow_link = gfs2_follow_link, - .put_link = kfree_put_link, + .get_link = gfs2_get_link, .permission = gfs2_permission, .setattr = gfs2_setattr, .getattr = gfs2_getattr, diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c index 536e7a6..0ff028c 100644 --- a/fs/gfs2/log.c +++ b/fs/gfs2/log.c @@ -716,6 +716,9 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl, } trace_gfs2_log_flush(sdp, 1); + if (type == SHUTDOWN_FLUSH) + clear_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags); + sdp->sd_log_flush_head = sdp->sd_log_head; sdp->sd_log_flush_wrapped = 0; tr = sdp->sd_log_tr; diff --git a/fs/gfs2/main.c b/fs/gfs2/main.c index fb2b42c..1d709d4 100644 --- a/fs/gfs2/main.c +++ b/fs/gfs2/main.c @@ -41,7 +41,9 @@ static void gfs2_init_inode_once(void *foo) inode_init_once(&ip->i_inode); init_rwsem(&ip->i_rw_mutex); INIT_LIST_HEAD(&ip->i_trunc_list); - ip->i_res = NULL; + ip->i_qadata = NULL; + memset(&ip->i_res, 0, sizeof(ip->i_res)); + RB_CLEAR_NODE(&ip->i_res.rs_node); ip->i_hash_cache = NULL; } @@ -135,10 +137,10 @@ static int __init init_gfs2_fs(void) if (!gfs2_quotad_cachep) goto fail; - gfs2_rsrv_cachep = kmem_cache_create("gfs2_mblk", - sizeof(struct gfs2_blkreserv), + gfs2_qadata_cachep = kmem_cache_create("gfs2_qadata", + sizeof(struct gfs2_qadata), 0, 0, NULL); - if (!gfs2_rsrv_cachep) + if (!gfs2_qadata_cachep) goto fail; register_shrinker(&gfs2_qd_shrinker); @@ -193,8 +195,8 @@ fail_lru: unregister_shrinker(&gfs2_qd_shrinker); gfs2_glock_exit(); - if (gfs2_rsrv_cachep) - kmem_cache_destroy(gfs2_rsrv_cachep); + if (gfs2_qadata_cachep) + kmem_cache_destroy(gfs2_qadata_cachep); if (gfs2_quotad_cachep) kmem_cache_destroy(gfs2_quotad_cachep); @@ -238,7 +240,7 @@ static void __exit exit_gfs2_fs(void) rcu_barrier(); mempool_destroy(gfs2_page_pool); - kmem_cache_destroy(gfs2_rsrv_cachep); + kmem_cache_destroy(gfs2_qadata_cachep); kmem_cache_destroy(gfs2_quotad_cachep); kmem_cache_destroy(gfs2_rgrpd_cachep); kmem_cache_destroy(gfs2_bufdata_cachep); diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c index 0e1d4be..e137d96 100644 --- a/fs/gfs2/meta_io.c +++ b/fs/gfs2/meta_io.c @@ -187,6 +187,52 @@ struct buffer_head *gfs2_meta_new(struct gfs2_glock *gl, u64 blkno) return bh; } +static void gfs2_meta_read_endio(struct bio *bio) +{ + struct bio_vec *bvec; + int i; + + bio_for_each_segment_all(bvec, bio, i) { + struct page *page = bvec->bv_page; + struct buffer_head *bh = page_buffers(page); + unsigned int len = bvec->bv_len; + + while (bh_offset(bh) < bvec->bv_offset) + bh = bh->b_this_page; + do { + struct buffer_head *next = bh->b_this_page; + len -= bh->b_size; + bh->b_end_io(bh, !bio->bi_error); + bh = next; + } while (bh && len); + } + bio_put(bio); +} + +/* + * Submit several consecutive buffer head I/O requests as a single bio I/O + * request. (See submit_bh_wbc.) + */ +static void gfs2_submit_bhs(int rw, struct buffer_head *bhs[], int num) +{ + struct buffer_head *bh = bhs[0]; + struct bio *bio; + int i; + + if (!num) + return; + + bio = bio_alloc(GFP_NOIO, num); + bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9); + bio->bi_bdev = bh->b_bdev; + for (i = 0; i < num; i++) { + bh = bhs[i]; + bio_add_page(bio, bh->b_page, bh->b_size, bh_offset(bh)); + } + bio->bi_end_io = gfs2_meta_read_endio; + submit_bio(rw, bio); +} + /** * gfs2_meta_read - Read a block from disk * @gl: The glock covering the block @@ -198,10 +244,11 @@ struct buffer_head *gfs2_meta_new(struct gfs2_glock *gl, u64 blkno) */ int gfs2_meta_read(struct gfs2_glock *gl, u64 blkno, int flags, - struct buffer_head **bhp) + int rahead, struct buffer_head **bhp) { struct gfs2_sbd *sdp = gl->gl_name.ln_sbd; - struct buffer_head *bh; + struct buffer_head *bh, *bhs[2]; + int num = 0; if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags))) { *bhp = NULL; @@ -213,14 +260,31 @@ int gfs2_meta_read(struct gfs2_glock *gl, u64 blkno, int flags, lock_buffer(bh); if (buffer_uptodate(bh)) { unlock_buffer(bh); - return 0; + flags &= ~DIO_WAIT; + } else { + bh->b_end_io = end_buffer_read_sync; + get_bh(bh); + bhs[num++] = bh; } - bh->b_end_io = end_buffer_read_sync; - get_bh(bh); - submit_bh(READ_SYNC | REQ_META | REQ_PRIO, bh); + + if (rahead) { + bh = gfs2_getbuf(gl, blkno + 1, CREATE); + + lock_buffer(bh); + if (buffer_uptodate(bh)) { + unlock_buffer(bh); + brelse(bh); + } else { + bh->b_end_io = end_buffer_read_sync; + bhs[num++] = bh; + } + } + + gfs2_submit_bhs(READ_SYNC | REQ_META | REQ_PRIO, bhs, num); if (!(flags & DIO_WAIT)) return 0; + bh = *bhp; wait_on_buffer(bh); if (unlikely(!buffer_uptodate(bh))) { struct gfs2_trans *tr = current->journal_info; @@ -341,8 +405,12 @@ int gfs2_meta_indirect_buffer(struct gfs2_inode *ip, int height, u64 num, struct buffer_head *bh; int ret = 0; u32 mtype = height ? GFS2_METATYPE_IN : GFS2_METATYPE_DI; + int rahead = 0; + + if (num == ip->i_no_addr) + rahead = ip->i_rahead; - ret = gfs2_meta_read(gl, num, DIO_WAIT, &bh); + ret = gfs2_meta_read(gl, num, DIO_WAIT, rahead, &bh); if (ret == 0 && gfs2_metatype_check(sdp, bh, mtype)) { brelse(bh); ret = -EIO; diff --git a/fs/gfs2/meta_io.h b/fs/gfs2/meta_io.h index 8ca1615..c5086c8 100644 --- a/fs/gfs2/meta_io.h +++ b/fs/gfs2/meta_io.h @@ -53,7 +53,7 @@ static inline struct gfs2_sbd *gfs2_mapping2sbd(struct address_space *mapping) extern struct buffer_head *gfs2_meta_new(struct gfs2_glock *gl, u64 blkno); extern int gfs2_meta_read(struct gfs2_glock *gl, u64 blkno, int flags, - struct buffer_head **bhp); + int rahead, struct buffer_head **bhp); extern int gfs2_meta_wait(struct gfs2_sbd *sdp, struct buffer_head *bh); extern struct buffer_head *gfs2_getbuf(struct gfs2_glock *gl, u64 blkno, int create); diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index baab99b..dbed9e2 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -352,6 +352,9 @@ static int gfs2_read_sb(struct gfs2_sbd *sdp, int silent) sdp->sd_jheightsize[x] = ~0; gfs2_assert(sdp, sdp->sd_max_jheight <= GFS2_MAX_META_HEIGHT); + sdp->sd_max_dents_per_leaf = (sdp->sd_sb.sb_bsize - + sizeof(struct gfs2_leaf)) / + GFS2_MIN_DIRENT_SIZE; return 0; } @@ -910,8 +913,7 @@ fail_qc_i: fail_ut_i: iput(sdp->sd_sc_inode); fail: - if (pn) - iput(pn); + iput(pn); return error; } @@ -1315,9 +1317,7 @@ static struct dentry *gfs2_mount(struct file_system_type *fs_type, int flags, if ((flags ^ s->s_flags) & MS_RDONLY) goto error_super; } else { - char b[BDEVNAME_SIZE]; - - strlcpy(s->s_id, bdevname(bdev, b), sizeof(s->s_id)); + snprintf(s->s_id, sizeof(s->s_id), "%pg", bdev); sb_set_blocksize(s, block_size(bdev)); error = fill_super(s, &args, flags & MS_SILENT ? 1 : 0); if (error) diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c index 3a31226..be6d9c4 100644 --- a/fs/gfs2/quota.c +++ b/fs/gfs2/quota.c @@ -388,7 +388,7 @@ static int bh_get(struct gfs2_quota_data *qd) error = gfs2_block_map(&ip->i_inode, block, &bh_map, 0); if (error) goto fail; - error = gfs2_meta_read(ip->i_gl, bh_map.b_blocknr, DIO_WAIT, &bh); + error = gfs2_meta_read(ip->i_gl, bh_map.b_blocknr, DIO_WAIT, 0, &bh); if (error) goto fail; error = -EIO; @@ -527,37 +527,70 @@ static void qdsb_put(struct gfs2_quota_data *qd) qd_put(qd); } +/** + * gfs2_qa_alloc - make sure we have a quota allocations data structure, + * if necessary + * @ip: the inode for this reservation + */ +int gfs2_qa_alloc(struct gfs2_inode *ip) +{ + int error = 0; + struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); + + if (sdp->sd_args.ar_quota == GFS2_QUOTA_OFF) + return 0; + + down_write(&ip->i_rw_mutex); + if (ip->i_qadata == NULL) { + ip->i_qadata = kmem_cache_zalloc(gfs2_qadata_cachep, GFP_NOFS); + if (!ip->i_qadata) + error = -ENOMEM; + } + up_write(&ip->i_rw_mutex); + return error; +} + +void gfs2_qa_delete(struct gfs2_inode *ip, atomic_t *wcount) +{ + down_write(&ip->i_rw_mutex); + if (ip->i_qadata && ((wcount == NULL) || (atomic_read(wcount) <= 1))) { + kmem_cache_free(gfs2_qadata_cachep, ip->i_qadata); + ip->i_qadata = NULL; + } + up_write(&ip->i_rw_mutex); +} + int gfs2_quota_hold(struct gfs2_inode *ip, kuid_t uid, kgid_t gid) { struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); struct gfs2_quota_data **qd; int error; - if (ip->i_res == NULL) { - error = gfs2_rs_alloc(ip); + if (sdp->sd_args.ar_quota == GFS2_QUOTA_OFF) + return 0; + + if (ip->i_qadata == NULL) { + error = gfs2_rsqa_alloc(ip); if (error) return error; } - qd = ip->i_res->rs_qa_qd; + qd = ip->i_qadata->qa_qd; - if (gfs2_assert_warn(sdp, !ip->i_res->rs_qa_qd_num) || + if (gfs2_assert_warn(sdp, !ip->i_qadata->qa_qd_num) || gfs2_assert_warn(sdp, !test_bit(GIF_QD_LOCKED, &ip->i_flags))) return -EIO; - if (sdp->sd_args.ar_quota == GFS2_QUOTA_OFF) - return 0; - error = qdsb_get(sdp, make_kqid_uid(ip->i_inode.i_uid), qd); if (error) goto out; - ip->i_res->rs_qa_qd_num++; + ip->i_qadata->qa_qd_num++; qd++; error = qdsb_get(sdp, make_kqid_gid(ip->i_inode.i_gid), qd); if (error) goto out; - ip->i_res->rs_qa_qd_num++; + ip->i_qadata->qa_qd_num++; qd++; if (!uid_eq(uid, NO_UID_QUOTA_CHANGE) && @@ -565,7 +598,7 @@ int gfs2_quota_hold(struct gfs2_inode *ip, kuid_t uid, kgid_t gid) error = qdsb_get(sdp, make_kqid_uid(uid), qd); if (error) goto out; - ip->i_res->rs_qa_qd_num++; + ip->i_qadata->qa_qd_num++; qd++; } @@ -574,7 +607,7 @@ int gfs2_quota_hold(struct gfs2_inode *ip, kuid_t uid, kgid_t gid) error = qdsb_get(sdp, make_kqid_gid(gid), qd); if (error) goto out; - ip->i_res->rs_qa_qd_num++; + ip->i_qadata->qa_qd_num++; qd++; } @@ -587,17 +620,17 @@ out: void gfs2_quota_unhold(struct gfs2_inode *ip) { struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); - unsigned int x; + u32 x; - if (ip->i_res == NULL) + if (ip->i_qadata == NULL) return; gfs2_assert_warn(sdp, !test_bit(GIF_QD_LOCKED, &ip->i_flags)); - for (x = 0; x < ip->i_res->rs_qa_qd_num; x++) { - qdsb_put(ip->i_res->rs_qa_qd[x]); - ip->i_res->rs_qa_qd[x] = NULL; + for (x = 0; x < ip->i_qadata->qa_qd_num; x++) { + qdsb_put(ip->i_qadata->qa_qd[x]); + ip->i_qadata->qa_qd[x] = NULL; } - ip->i_res->rs_qa_qd_num = 0; + ip->i_qadata->qa_qd_num = 0; } static int sort_qd(const void *a, const void *b) @@ -843,7 +876,7 @@ static int do_sync(unsigned int num_qd, struct gfs2_quota_data **qda) unsigned int nalloc = 0, blocks; int error; - error = gfs2_rs_alloc(ip); + error = gfs2_rsqa_alloc(ip); if (error) return error; @@ -1003,23 +1036,23 @@ int gfs2_quota_lock(struct gfs2_inode *ip, kuid_t uid, kgid_t gid) { struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); struct gfs2_quota_data *qd; - unsigned int x; + u32 x; int error = 0; - error = gfs2_quota_hold(ip, uid, gid); - if (error) - return error; - if (capable(CAP_SYS_RESOURCE) || sdp->sd_args.ar_quota != GFS2_QUOTA_ON) return 0; - sort(ip->i_res->rs_qa_qd, ip->i_res->rs_qa_qd_num, + error = gfs2_quota_hold(ip, uid, gid); + if (error) + return error; + + sort(ip->i_qadata->qa_qd, ip->i_qadata->qa_qd_num, sizeof(struct gfs2_quota_data *), sort_qd, NULL); - for (x = 0; x < ip->i_res->rs_qa_qd_num; x++) { - qd = ip->i_res->rs_qa_qd[x]; - error = do_glock(qd, NO_FORCE, &ip->i_res->rs_qa_qd_ghs[x]); + for (x = 0; x < ip->i_qadata->qa_qd_num; x++) { + qd = ip->i_qadata->qa_qd[x]; + error = do_glock(qd, NO_FORCE, &ip->i_qadata->qa_qd_ghs[x]); if (error) break; } @@ -1028,7 +1061,7 @@ int gfs2_quota_lock(struct gfs2_inode *ip, kuid_t uid, kgid_t gid) set_bit(GIF_QD_LOCKED, &ip->i_flags); else { while (x--) - gfs2_glock_dq_uninit(&ip->i_res->rs_qa_qd_ghs[x]); + gfs2_glock_dq_uninit(&ip->i_qadata->qa_qd_ghs[x]); gfs2_quota_unhold(ip); } @@ -1076,20 +1109,20 @@ void gfs2_quota_unlock(struct gfs2_inode *ip) struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); struct gfs2_quota_data *qda[4]; unsigned int count = 0; - unsigned int x; + u32 x; int found; if (!test_and_clear_bit(GIF_QD_LOCKED, &ip->i_flags)) goto out; - for (x = 0; x < ip->i_res->rs_qa_qd_num; x++) { + for (x = 0; x < ip->i_qadata->qa_qd_num; x++) { struct gfs2_quota_data *qd; int sync; - qd = ip->i_res->rs_qa_qd[x]; + qd = ip->i_qadata->qa_qd[x]; sync = need_sync(qd); - gfs2_glock_dq_uninit(&ip->i_res->rs_qa_qd_ghs[x]); + gfs2_glock_dq_uninit(&ip->i_qadata->qa_qd_ghs[x]); if (!sync) continue; @@ -1158,7 +1191,7 @@ int gfs2_quota_check(struct gfs2_inode *ip, kuid_t uid, kgid_t gid, struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); struct gfs2_quota_data *qd; s64 value, warn, limit; - unsigned int x; + u32 x; int error = 0; ap->allowed = UINT_MAX; /* Assume we are permitted a whole lot */ @@ -1168,8 +1201,8 @@ int gfs2_quota_check(struct gfs2_inode *ip, kuid_t uid, kgid_t gid, if (sdp->sd_args.ar_quota != GFS2_QUOTA_ON) return 0; - for (x = 0; x < ip->i_res->rs_qa_qd_num; x++) { - qd = ip->i_res->rs_qa_qd[x]; + for (x = 0; x < ip->i_qadata->qa_qd_num; x++) { + qd = ip->i_qadata->qa_qd[x]; if (!(qid_eq(qd->qd_id, make_kqid_uid(uid)) || qid_eq(qd->qd_id, make_kqid_gid(gid)))) @@ -1216,15 +1249,17 @@ void gfs2_quota_change(struct gfs2_inode *ip, s64 change, kuid_t uid, kgid_t gid) { struct gfs2_quota_data *qd; - unsigned int x; + u32 x; + struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); - if (gfs2_assert_warn(GFS2_SB(&ip->i_inode), change)) + if (sdp->sd_args.ar_quota != GFS2_QUOTA_ON || + gfs2_assert_warn(sdp, change)) return; if (ip->i_diskflags & GFS2_DIF_SYSTEM) return; - for (x = 0; x < ip->i_res->rs_qa_qd_num; x++) { - qd = ip->i_res->rs_qa_qd[x]; + for (x = 0; x < ip->i_qadata->qa_qd_num; x++) { + qd = ip->i_qadata->qa_qd[x]; if (qid_eq(qd->qd_id, make_kqid_uid(uid)) || qid_eq(qd->qd_id, make_kqid_gid(gid))) { @@ -1635,7 +1670,7 @@ static int gfs2_set_dqblk(struct super_block *sb, struct kqid qid, if (error) return error; - error = gfs2_rs_alloc(ip); + error = gfs2_rsqa_alloc(ip); if (error) goto out_put; diff --git a/fs/gfs2/quota.h b/fs/gfs2/quota.h index ad04b3a..5e47c93 100644 --- a/fs/gfs2/quota.h +++ b/fs/gfs2/quota.h @@ -18,6 +18,8 @@ struct gfs2_sbd; #define NO_UID_QUOTA_CHANGE INVALID_UID #define NO_GID_QUOTA_CHANGE INVALID_GID +extern int gfs2_qa_alloc(struct gfs2_inode *ip); +extern void gfs2_qa_delete(struct gfs2_inode *ip, atomic_t *wcount); extern int gfs2_quota_hold(struct gfs2_inode *ip, kuid_t uid, kgid_t gid); extern void gfs2_quota_unhold(struct gfs2_inode *ip); diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c index c134c04..07c0265 100644 --- a/fs/gfs2/rgrp.c +++ b/fs/gfs2/rgrp.c @@ -596,27 +596,13 @@ void gfs2_free_clones(struct gfs2_rgrpd *rgd) } /** - * gfs2_rs_alloc - make sure we have a reservation assigned to the inode + * gfs2_rsqa_alloc - make sure we have a reservation assigned to the inode + * plus a quota allocations data structure, if necessary * @ip: the inode for this reservation */ -int gfs2_rs_alloc(struct gfs2_inode *ip) +int gfs2_rsqa_alloc(struct gfs2_inode *ip) { - int error = 0; - - down_write(&ip->i_rw_mutex); - if (ip->i_res) - goto out; - - ip->i_res = kmem_cache_zalloc(gfs2_rsrv_cachep, GFP_NOFS); - if (!ip->i_res) { - error = -ENOMEM; - goto out; - } - - RB_CLEAR_NODE(&ip->i_res->rs_node); -out: - up_write(&ip->i_rw_mutex); - return error; + return gfs2_qa_alloc(ip); } static void dump_rs(struct seq_file *seq, const struct gfs2_blkreserv *rs) @@ -678,21 +664,20 @@ void gfs2_rs_deltree(struct gfs2_blkreserv *rs) } /** - * gfs2_rs_delete - delete a multi-block reservation + * gfs2_rsqa_delete - delete a multi-block reservation and quota allocation * @ip: The inode for this reservation * @wcount: The inode's write count, or NULL * */ -void gfs2_rs_delete(struct gfs2_inode *ip, atomic_t *wcount) +void gfs2_rsqa_delete(struct gfs2_inode *ip, atomic_t *wcount) { down_write(&ip->i_rw_mutex); - if (ip->i_res && ((wcount == NULL) || (atomic_read(wcount) <= 1))) { - gfs2_rs_deltree(ip->i_res); - BUG_ON(ip->i_res->rs_free); - kmem_cache_free(gfs2_rsrv_cachep, ip->i_res); - ip->i_res = NULL; + if ((wcount == NULL) || (atomic_read(wcount) <= 1)) { + gfs2_rs_deltree(&ip->i_res); + BUG_ON(ip->i_res.rs_free); } up_write(&ip->i_rw_mutex); + gfs2_qa_delete(ip, wcount); } /** @@ -1158,7 +1143,7 @@ static int gfs2_rgrp_bh_get(struct gfs2_rgrpd *rgd) for (x = 0; x < length; x++) { bi = rgd->rd_bits + x; - error = gfs2_meta_read(gl, rgd->rd_addr + x, 0, &bi->bi_bh); + error = gfs2_meta_read(gl, rgd->rd_addr + x, 0, 0, &bi->bi_bh); if (error) goto fail; } @@ -1456,7 +1441,7 @@ static void rs_insert(struct gfs2_inode *ip) { struct rb_node **newn, *parent = NULL; int rc; - struct gfs2_blkreserv *rs = ip->i_res; + struct gfs2_blkreserv *rs = &ip->i_res; struct gfs2_rgrpd *rgd = rs->rs_rbm.rgd; u64 fsblock = gfs2_rbm_to_block(&rs->rs_rbm); @@ -1503,7 +1488,7 @@ static void rg_mblk_search(struct gfs2_rgrpd *rgd, struct gfs2_inode *ip, { struct gfs2_rbm rbm = { .rgd = rgd, }; u64 goal; - struct gfs2_blkreserv *rs = ip->i_res; + struct gfs2_blkreserv *rs = &ip->i_res; u32 extlen; u32 free_blocks = rgd->rd_free_clone - rgd->rd_reserved; int ret; @@ -1574,7 +1559,7 @@ static u64 gfs2_next_unreserved_block(struct gfs2_rgrpd *rgd, u64 block, } if (n) { - while ((rs_cmp(block, length, rs) == 0) && (ip->i_res != rs)) { + while ((rs_cmp(block, length, rs) == 0) && (&ip->i_res != rs)) { block = gfs2_rbm_to_block(&rs->rs_rbm) + rs->rs_free; n = n->rb_right; if (n == NULL) @@ -1804,7 +1789,7 @@ static void try_rgrp_unlink(struct gfs2_rgrpd *rgd, u64 *last_unlinked, u64 skip continue; *last_unlinked = block; - error = gfs2_glock_get(sdp, block, &gfs2_inode_glops, CREATE, &gl); + error = gfs2_glock_get(sdp, block, &gfs2_iopen_glops, CREATE, &gl); if (error) continue; @@ -1984,7 +1969,7 @@ int gfs2_inplace_reserve(struct gfs2_inode *ip, struct gfs2_alloc_parms *ap) { struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); struct gfs2_rgrpd *begin = NULL; - struct gfs2_blkreserv *rs = ip->i_res; + struct gfs2_blkreserv *rs = &ip->i_res; int error = 0, rg_locked, flags = 0; u64 last_unlinked = NO_BLOCK; int loops = 0; @@ -2113,7 +2098,7 @@ next_rgrp: void gfs2_inplace_release(struct gfs2_inode *ip) { - struct gfs2_blkreserv *rs = ip->i_res; + struct gfs2_blkreserv *rs = &ip->i_res; if (rs->rs_rgd_gh.gh_gl) gfs2_glock_dq_uninit(&rs->rs_rgd_gh); @@ -2267,7 +2252,7 @@ static void gfs2_rgrp_error(struct gfs2_rgrpd *rgd) static void gfs2_adjust_reservation(struct gfs2_inode *ip, const struct gfs2_rbm *rbm, unsigned len) { - struct gfs2_blkreserv *rs = ip->i_res; + struct gfs2_blkreserv *rs = &ip->i_res; struct gfs2_rgrpd *rgd = rbm->rgd; unsigned rlen; u64 block; @@ -2310,8 +2295,8 @@ static void gfs2_set_alloc_start(struct gfs2_rbm *rbm, { u64 goal; - if (gfs2_rs_active(ip->i_res)) { - *rbm = ip->i_res->rs_rbm; + if (gfs2_rs_active(&ip->i_res)) { + *rbm = ip->i_res.rs_rbm; return; } @@ -2365,7 +2350,7 @@ int gfs2_alloc_blocks(struct gfs2_inode *ip, u64 *bn, unsigned int *nblocks, gfs2_alloc_extent(&rbm, dinode, nblocks); block = gfs2_rbm_to_block(&rbm); rbm.rgd->rd_last_alloc = block - rbm.rgd->rd_data0; - if (gfs2_rs_active(ip->i_res)) + if (gfs2_rs_active(&ip->i_res)) gfs2_adjust_reservation(ip, &rbm, *nblocks); ndata = *nblocks; if (dinode) diff --git a/fs/gfs2/rgrp.h b/fs/gfs2/rgrp.h index c0ab33f..66b51cf 100644 --- a/fs/gfs2/rgrp.h +++ b/fs/gfs2/rgrp.h @@ -49,9 +49,9 @@ extern void gfs2_inplace_release(struct gfs2_inode *ip); extern int gfs2_alloc_blocks(struct gfs2_inode *ip, u64 *bn, unsigned int *n, bool dinode, u64 *generation); -extern int gfs2_rs_alloc(struct gfs2_inode *ip); +extern int gfs2_rsqa_alloc(struct gfs2_inode *ip); extern void gfs2_rs_deltree(struct gfs2_blkreserv *rs); -extern void gfs2_rs_delete(struct gfs2_inode *ip, atomic_t *wcount); +extern void gfs2_rsqa_delete(struct gfs2_inode *ip, atomic_t *wcount); extern void __gfs2_free_blocks(struct gfs2_inode *ip, u64 bstart, u32 blen, int meta); extern void gfs2_free_meta(struct gfs2_inode *ip, u64 bstart, u32 blen); extern void gfs2_free_di(struct gfs2_rgrpd *rgd, struct gfs2_inode *ip); @@ -78,7 +78,7 @@ extern int gfs2_rgrp_send_discards(struct gfs2_sbd *sdp, u64 offset, extern int gfs2_fitrim(struct file *filp, void __user *argp); /* This is how to tell if a reservation is in the rgrp tree: */ -static inline bool gfs2_rs_active(struct gfs2_blkreserv *rs) +static inline bool gfs2_rs_active(const struct gfs2_blkreserv *rs) { return rs && !RB_EMPTY_NODE(&rs->rs_node); } diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index 894fb01..8f960a5 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -83,6 +83,8 @@ enum { Opt_nobarrier, Opt_rgrplvb, Opt_norgrplvb, + Opt_loccookie, + Opt_noloccookie, Opt_error, }; @@ -122,6 +124,8 @@ static const match_table_t tokens = { {Opt_nobarrier, "nobarrier"}, {Opt_rgrplvb, "rgrplvb"}, {Opt_norgrplvb, "norgrplvb"}, + {Opt_loccookie, "loccookie"}, + {Opt_noloccookie, "noloccookie"}, {Opt_error, NULL} }; @@ -278,6 +282,12 @@ int gfs2_mount_args(struct gfs2_args *args, char *options) case Opt_norgrplvb: args->ar_rgrplvb = 0; break; + case Opt_loccookie: + args->ar_loccookie = 1; + break; + case Opt_noloccookie: + args->ar_loccookie = 0; + break; case Opt_error: default: pr_warn("invalid mount option: %s\n", o); @@ -556,6 +566,7 @@ void update_statfs(struct gfs2_sbd *sdp, struct buffer_head *m_bh, struct gfs2_statfs_change_host *l_sc = &sdp->sd_statfs_local; gfs2_trans_add_meta(l_ip->i_gl, l_bh); + gfs2_trans_add_meta(m_ip->i_gl, m_bh); spin_lock(&sdp->sd_statfs_spin); m_sc->sc_total += l_sc->sc_total; @@ -564,10 +575,8 @@ void update_statfs(struct gfs2_sbd *sdp, struct buffer_head *m_bh, memset(l_sc, 0, sizeof(struct gfs2_statfs_change)); memset(l_bh->b_data + sizeof(struct gfs2_dinode), 0, sizeof(struct gfs2_statfs_change)); - spin_unlock(&sdp->sd_statfs_spin); - - gfs2_trans_add_meta(m_ip->i_gl, m_bh); gfs2_statfs_change_out(m_sc, m_bh->b_data + sizeof(struct gfs2_dinode)); + spin_unlock(&sdp->sd_statfs_spin); } int gfs2_statfs_sync(struct super_block *sb, int type) @@ -842,10 +851,6 @@ static int gfs2_make_fs_ro(struct gfs2_sbd *sdp) gfs2_quota_sync(sdp->sd_vfs, 0); gfs2_statfs_sync(sdp->sd_vfs, 0); - down_write(&sdp->sd_log_flush_lock); - clear_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags); - up_write(&sdp->sd_log_flush_lock); - gfs2_log_flush(sdp, NULL, SHUTDOWN_FLUSH); wait_event(sdp->sd_reserving_log_wait, atomic_read(&sdp->sd_reserving_log) == 0); gfs2_assert_warn(sdp, atomic_read(&sdp->sd_log_blks_free) == sdp->sd_jdesc->jd_blocks); @@ -1419,6 +1424,8 @@ static int gfs2_show_options(struct seq_file *s, struct dentry *root) seq_puts(s, ",demote_interface_used"); if (args->ar_rgrplvb) seq_puts(s, ",rgrplvb"); + if (args->ar_loccookie) + seq_puts(s, ",loccookie"); return 0; } @@ -1512,6 +1519,7 @@ static void gfs2_evict_inode(struct inode *inode) struct gfs2_sbd *sdp = sb->s_fs_info; struct gfs2_inode *ip = GFS2_I(inode); struct gfs2_holder gh; + struct address_space *metamapping; int error; if (test_bit(GIF_FREE_VFS_INODE, &ip->i_flags)) { @@ -1526,7 +1534,8 @@ static void gfs2_evict_inode(struct inode *inode) error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, GL_SKIP, &gh); if (unlikely(error)) { ip->i_iopen_gh.gh_flags |= GL_NOCACHE; - gfs2_glock_dq_uninit(&ip->i_iopen_gh); + gfs2_glock_dq_wait(&ip->i_iopen_gh); + gfs2_holder_uninit(&ip->i_iopen_gh); goto out; } @@ -1575,8 +1584,8 @@ static void gfs2_evict_inode(struct inode *inode) out_truncate: gfs2_log_flush(sdp, ip->i_gl, NORMAL_FLUSH); + metamapping = gfs2_glock2aspace(ip->i_gl); if (test_bit(GLF_DIRTY, &ip->i_gl->gl_flags)) { - struct address_space *metamapping = gfs2_glock2aspace(ip->i_gl); filemap_fdatawrite(metamapping); filemap_fdatawait(metamapping); } @@ -1589,16 +1598,17 @@ out_truncate: goto out_unlock; /* Needs to be done before glock release & also in a transaction */ truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages(metamapping, 0); gfs2_trans_end(sdp); out_unlock: /* Error path for case 1 */ - if (gfs2_rs_active(ip->i_res)) - gfs2_rs_deltree(ip->i_res); + if (gfs2_rs_active(&ip->i_res)) + gfs2_rs_deltree(&ip->i_res); if (test_bit(HIF_HOLDER, &ip->i_iopen_gh.gh_iflags)) { ip->i_iopen_gh.gh_flags |= GL_NOCACHE; - gfs2_glock_dq(&ip->i_iopen_gh); + gfs2_glock_dq_wait(&ip->i_iopen_gh); } gfs2_holder_uninit(&ip->i_iopen_gh); gfs2_glock_dq_uninit(&gh); @@ -1607,7 +1617,7 @@ out_unlock: out: /* Case 3 starts here */ truncate_inode_pages_final(&inode->i_data); - gfs2_rs_delete(ip, NULL); + gfs2_rsqa_delete(ip, NULL); gfs2_ordered_del_inode(ip); clear_inode(inode); gfs2_dir_hash_inval(ip); @@ -1619,7 +1629,8 @@ out: if (ip->i_iopen_gh.gh_gl) { ip->i_iopen_gh.gh_gl->gl_object = NULL; ip->i_iopen_gh.gh_flags |= GL_NOCACHE; - gfs2_glock_dq_uninit(&ip->i_iopen_gh); + gfs2_glock_dq_wait(&ip->i_iopen_gh); + gfs2_holder_uninit(&ip->i_iopen_gh); } } @@ -1632,7 +1643,9 @@ static struct inode *gfs2_alloc_inode(struct super_block *sb) ip->i_flags = 0; ip->i_gl = NULL; ip->i_rgd = NULL; - ip->i_res = NULL; + memset(&ip->i_res, 0, sizeof(ip->i_res)); + RB_CLEAR_NODE(&ip->i_res.rs_node); + ip->i_rahead = 0; } return &ip->i_inode; } diff --git a/fs/gfs2/util.c b/fs/gfs2/util.c index 86d2035..cf64583 100644 --- a/fs/gfs2/util.c +++ b/fs/gfs2/util.c @@ -27,7 +27,7 @@ struct kmem_cache *gfs2_inode_cachep __read_mostly; struct kmem_cache *gfs2_bufdata_cachep __read_mostly; struct kmem_cache *gfs2_rgrpd_cachep __read_mostly; struct kmem_cache *gfs2_quotad_cachep __read_mostly; -struct kmem_cache *gfs2_rsrv_cachep __read_mostly; +struct kmem_cache *gfs2_qadata_cachep __read_mostly; mempool_t *gfs2_page_pool __read_mostly; void gfs2_assert_i(struct gfs2_sbd *sdp) diff --git a/fs/gfs2/util.h b/fs/gfs2/util.h index cbdcbdf..c81295f 100644 --- a/fs/gfs2/util.h +++ b/fs/gfs2/util.h @@ -149,7 +149,7 @@ extern struct kmem_cache *gfs2_inode_cachep; extern struct kmem_cache *gfs2_bufdata_cachep; extern struct kmem_cache *gfs2_rgrpd_cachep; extern struct kmem_cache *gfs2_quotad_cachep; -extern struct kmem_cache *gfs2_rsrv_cachep; +extern struct kmem_cache *gfs2_qadata_cachep; extern mempool_t *gfs2_page_pool; static inline unsigned int gfs2_tune_get_i(struct gfs2_tune *gt, diff --git a/fs/gfs2/xattr.c b/fs/gfs2/xattr.c index 53ce76a..e8dfb47 100644 --- a/fs/gfs2/xattr.c +++ b/fs/gfs2/xattr.c @@ -119,7 +119,7 @@ static int ea_foreach(struct gfs2_inode *ip, ea_call_t ea_call, void *data) __be64 *eablk, *end; int error; - error = gfs2_meta_read(ip->i_gl, ip->i_eattr, DIO_WAIT, &bh); + error = gfs2_meta_read(ip->i_gl, ip->i_eattr, DIO_WAIT, 0, &bh); if (error) return error; @@ -143,7 +143,7 @@ static int ea_foreach(struct gfs2_inode *ip, ea_call_t ea_call, void *data) break; bn = be64_to_cpu(*eablk); - error = gfs2_meta_read(ip->i_gl, bn, DIO_WAIT, &eabh); + error = gfs2_meta_read(ip->i_gl, bn, DIO_WAIT, 0, &eabh); if (error) break; error = ea_foreach_i(ip, eabh, ea_call, data); @@ -477,7 +477,7 @@ static int gfs2_iter_unstuffed(struct gfs2_inode *ip, struct gfs2_ea_header *ea, return -ENOMEM; for (x = 0; x < nptrs; x++) { - error = gfs2_meta_read(ip->i_gl, be64_to_cpu(*dataptrs), 0, + error = gfs2_meta_read(ip->i_gl, be64_to_cpu(*dataptrs), 0, 0, bh + x); if (error) { while (x--) @@ -979,7 +979,7 @@ static int ea_set_block(struct gfs2_inode *ip, struct gfs2_ea_request *er, if (ip->i_diskflags & GFS2_DIF_EA_INDIRECT) { __be64 *end; - error = gfs2_meta_read(ip->i_gl, ip->i_eattr, DIO_WAIT, + error = gfs2_meta_read(ip->i_gl, ip->i_eattr, DIO_WAIT, 0, &indbh); if (error) return error; @@ -1237,56 +1237,6 @@ static int gfs2_xattr_set(const struct xattr_handler *handler, size, flags, handler->flags); } - -static int ea_acl_chmod_unstuffed(struct gfs2_inode *ip, - struct gfs2_ea_header *ea, char *data) -{ - struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); - unsigned int amount = GFS2_EA_DATA_LEN(ea); - unsigned int nptrs = DIV_ROUND_UP(amount, sdp->sd_jbsize); - int ret; - - ret = gfs2_trans_begin(sdp, nptrs + RES_DINODE, 0); - if (ret) - return ret; - - ret = gfs2_iter_unstuffed(ip, ea, data, NULL); - gfs2_trans_end(sdp); - - return ret; -} - -int gfs2_xattr_acl_chmod(struct gfs2_inode *ip, struct iattr *attr, char *data) -{ - struct inode *inode = &ip->i_inode; - struct gfs2_sbd *sdp = GFS2_SB(inode); - struct gfs2_ea_location el; - int error; - - error = gfs2_ea_find(ip, GFS2_EATYPE_SYS, GFS2_POSIX_ACL_ACCESS, &el); - if (error) - return error; - - if (GFS2_EA_IS_STUFFED(el.el_ea)) { - error = gfs2_trans_begin(sdp, RES_DINODE + RES_EATTR, 0); - if (error == 0) { - gfs2_trans_add_meta(ip->i_gl, el.el_bh); - memcpy(GFS2_EA2DATA(el.el_ea), data, - GFS2_EA_DATA_LEN(el.el_ea)); - } - } else { - error = ea_acl_chmod_unstuffed(ip, el.el_ea, data); - } - - brelse(el.el_bh); - if (error) - return error; - - error = gfs2_setattr_simple(inode, attr); - gfs2_trans_end(sdp); - return error; -} - static int ea_dealloc_indirect(struct gfs2_inode *ip) { struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); @@ -1306,7 +1256,7 @@ static int ea_dealloc_indirect(struct gfs2_inode *ip) memset(&rlist, 0, sizeof(struct gfs2_rgrp_list)); - error = gfs2_meta_read(ip->i_gl, ip->i_eattr, DIO_WAIT, &indbh); + error = gfs2_meta_read(ip->i_gl, ip->i_eattr, DIO_WAIT, 0, &indbh); if (error) return error; diff --git a/fs/gfs2/xattr.h b/fs/gfs2/xattr.h index d392f83..2d887c8 100644 --- a/fs/gfs2/xattr.h +++ b/fs/gfs2/xattr.h @@ -62,6 +62,5 @@ extern int gfs2_ea_dealloc(struct gfs2_inode *ip); /* Exported to acl.c */ extern int gfs2_xattr_acl_get(struct gfs2_inode *ip, const char *name, char **data); -extern int gfs2_xattr_acl_chmod(struct gfs2_inode *ip, struct iattr *attr, char *data); #endif /* __EATTR_DOT_H__ */ diff --git a/fs/hfs/mdb.c b/fs/hfs/mdb.c index aa3f0d6..a3ec3ae 100644 --- a/fs/hfs/mdb.c +++ b/fs/hfs/mdb.c @@ -166,7 +166,7 @@ int hfs_mdb_get(struct super_block *sb) pr_warn("continuing without an alternate MDB\n"); } - HFS_SB(sb)->bitmap = (__be32 *)__get_free_pages(GFP_KERNEL, PAGE_SIZE < 8192 ? 1 : 0); + HFS_SB(sb)->bitmap = kmalloc(8192, GFP_KERNEL); if (!HFS_SB(sb)->bitmap) goto out; @@ -360,7 +360,7 @@ void hfs_mdb_put(struct super_block *sb) unload_nls(HFS_SB(sb)->nls_io); unload_nls(HFS_SB(sb)->nls_disk); - free_pages((unsigned long)HFS_SB(sb)->bitmap, PAGE_SIZE < 8192 ? 1 : 0); + kfree(HFS_SB(sb)->bitmap); kfree(HFS_SB(sb)); sb->s_fs_info = NULL; } diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c index 6dd107d..19b33f8 100644 --- a/fs/hfsplus/inode.c +++ b/fs/hfsplus/inode.c @@ -403,6 +403,7 @@ struct inode *hfsplus_new_inode(struct super_block *sb, umode_t mode) } else if (S_ISLNK(inode->i_mode)) { sbi->file_count++; inode->i_op = &page_symlink_inode_operations; + inode_nohighmem(inode); inode->i_mapping->a_ops = &hfsplus_aops; hip->clump_blocks = 1; } else @@ -526,6 +527,7 @@ int hfsplus_cat_read_inode(struct inode *inode, struct hfs_find_data *fd) inode->i_mapping->a_ops = &hfsplus_aops; } else if (S_ISLNK(inode->i_mode)) { inode->i_op = &page_symlink_inode_operations; + inode_nohighmem(inode); inode->i_mapping->a_ops = &hfsplus_aops; } else { init_special_inode(inode, inode->i_mode, diff --git a/fs/hfsplus/posix_acl.c b/fs/hfsplus/posix_acl.c index df0c9af..afb33ed 100644 --- a/fs/hfsplus/posix_acl.c +++ b/fs/hfsplus/posix_acl.c @@ -21,10 +21,10 @@ struct posix_acl *hfsplus_get_posix_acl(struct inode *inode, int type) switch (type) { case ACL_TYPE_ACCESS: - xattr_name = POSIX_ACL_XATTR_ACCESS; + xattr_name = XATTR_NAME_POSIX_ACL_ACCESS; break; case ACL_TYPE_DEFAULT: - xattr_name = POSIX_ACL_XATTR_DEFAULT; + xattr_name = XATTR_NAME_POSIX_ACL_DEFAULT; break; default: return ERR_PTR(-EINVAL); @@ -66,7 +66,7 @@ int hfsplus_set_posix_acl(struct inode *inode, struct posix_acl *acl, switch (type) { case ACL_TYPE_ACCESS: - xattr_name = POSIX_ACL_XATTR_ACCESS; + xattr_name = XATTR_NAME_POSIX_ACL_ACCESS; if (acl) { err = posix_acl_equiv_mode(acl, &inode->i_mode); if (err < 0) @@ -76,7 +76,7 @@ int hfsplus_set_posix_acl(struct inode *inode, struct posix_acl *acl, break; case ACL_TYPE_DEFAULT: - xattr_name = POSIX_ACL_XATTR_DEFAULT; + xattr_name = XATTR_NAME_POSIX_ACL_DEFAULT; if (!S_ISDIR(inode->i_mode)) return acl ? -EACCES : 0; break; diff --git a/fs/hfsplus/xattr.c b/fs/hfsplus/xattr.c index e41a010..ab01530 100644 --- a/fs/hfsplus/xattr.c +++ b/fs/hfsplus/xattr.c @@ -431,9 +431,6 @@ int hfsplus_setxattr(struct dentry *dentry, const char *name, char *xattr_name; int res; - if (!strcmp(name, "")) - return -EINVAL; - xattr_name = kmalloc(NLS_MAX_CHARSET_SIZE * HFSPLUS_ATTR_MAX_STRLEN + 1, GFP_KERNEL); if (!xattr_name) @@ -589,9 +586,6 @@ ssize_t hfsplus_getxattr(struct dentry *dentry, const char *name, int res; char *xattr_name; - if (!strcmp(name, "")) - return -EINVAL; - xattr_name = kmalloc(NLS_MAX_CHARSET_SIZE * HFSPLUS_ATTR_MAX_STRLEN + 1, GFP_KERNEL); if (!xattr_name) @@ -853,9 +847,6 @@ static int hfsplus_osx_getxattr(const struct xattr_handler *handler, struct dentry *dentry, const char *name, void *buffer, size_t size) { - if (!strcmp(name, "")) - return -EINVAL; - /* * Don't allow retrieving properly prefixed attributes * by prepending them with "osx." @@ -876,9 +867,6 @@ static int hfsplus_osx_setxattr(const struct xattr_handler *handler, struct dentry *dentry, const char *name, const void *buffer, size_t size, int flags) { - if (!strcmp(name, "")) - return -EINVAL; - /* * Don't allow setting properly prefixed attributes * by prepending them with "osx." diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c index 2ac99db..f49be23 100644 --- a/fs/hostfs/hostfs_kern.c +++ b/fs/hostfs/hostfs_kern.c @@ -730,15 +730,13 @@ static int hostfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, init_special_inode(inode, mode, dev); err = do_mknod(name, mode, MAJOR(dev), MINOR(dev)); - if (!err) + if (err) goto out_free; err = read_name(inode, name); __putname(name); if (err) goto out_put; - if (err) - goto out_put; d_instantiate(dentry, inode); return 0; @@ -892,9 +890,14 @@ static const struct inode_operations hostfs_dir_iops = { .setattr = hostfs_setattr, }; -static const char *hostfs_follow_link(struct dentry *dentry, void **cookie) +static const char *hostfs_get_link(struct dentry *dentry, + struct inode *inode, + struct delayed_call *done) { - char *link = __getname(); + char *link; + if (!dentry) + return ERR_PTR(-ECHILD); + link = kmalloc(PATH_MAX, GFP_KERNEL); if (link) { char *path = dentry_name(dentry); int err = -ENOMEM; @@ -905,25 +908,20 @@ static const char *hostfs_follow_link(struct dentry *dentry, void **cookie) __putname(path); } if (err < 0) { - __putname(link); + kfree(link); return ERR_PTR(err); } } else { return ERR_PTR(-ENOMEM); } - return *cookie = link; -} - -static void hostfs_put_link(struct inode *unused, void *cookie) -{ - __putname(cookie); + set_delayed_call(done, kfree_link, link); + return link; } static const struct inode_operations hostfs_link_iops = { .readlink = generic_readlink, - .follow_link = hostfs_follow_link, - .put_link = hostfs_put_link, + .get_link = hostfs_get_link, }; static int hostfs_fill_sb_common(struct super_block *sb, void *d, int silent) diff --git a/fs/hpfs/inode.c b/fs/hpfs/inode.c index 933c737..1f3c6d7 100644 --- a/fs/hpfs/inode.c +++ b/fs/hpfs/inode.c @@ -77,6 +77,7 @@ void hpfs_read_inode(struct inode *i) kfree(ea); i->i_mode = S_IFLNK | 0777; i->i_op = &page_symlink_inode_operations; + inode_nohighmem(i); i->i_data.a_ops = &hpfs_symlink_aops; set_nlink(i, 1); i->i_size = ea_size; diff --git a/fs/hpfs/map.c b/fs/hpfs/map.c index a69bbc1..a136929 100644 --- a/fs/hpfs/map.c +++ b/fs/hpfs/map.c @@ -133,7 +133,7 @@ __le32 *hpfs_load_bitmap_directory(struct super_block *s, secno bmp) void hpfs_load_hotfix_map(struct super_block *s, struct hpfs_spare_block *spareblock) { struct quad_buffer_head qbh; - u32 *directory; + __le32 *directory; u32 n_hotfixes, n_used_hotfixes; unsigned i; diff --git a/fs/hpfs/namei.c b/fs/hpfs/namei.c index ae4d5a1..506765a 100644 --- a/fs/hpfs/namei.c +++ b/fs/hpfs/namei.c @@ -332,6 +332,7 @@ static int hpfs_symlink(struct inode *dir, struct dentry *dentry, const char *sy result->i_blocks = 1; set_nlink(result, 1); result->i_size = strlen(symlink); + inode_nohighmem(result); result->i_op = &page_symlink_inode_operations; result->i_data.a_ops = &hpfs_symlink_aops; @@ -500,7 +501,7 @@ out: static int hpfs_symlink_readpage(struct file *file, struct page *page) { - char *link = kmap(page); + char *link = page_address(page); struct inode *i = page->mapping->host; struct fnode *fnode; struct buffer_head *bh; @@ -516,14 +517,12 @@ static int hpfs_symlink_readpage(struct file *file, struct page *page) goto fail; hpfs_unlock(i->i_sb); SetPageUptodate(page); - kunmap(page); unlock_page(page); return 0; fail: hpfs_unlock(i->i_sb); SetPageError(page); - kunmap(page); unlock_page(page); return err; } diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index de4bdfa..d8f51ee 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -760,6 +760,7 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb, break; case S_IFLNK: inode->i_op = &page_symlink_inode_operations; + inode_nohighmem(inode); break; } lockdep_annotate_inode_mutex_key(inode); @@ -225,7 +225,7 @@ void __destroy_inode(struct inode *inode) inode_detach_wb(inode); security_inode_free(inode); fsnotify_inode_delete(inode); - locks_free_lock_context(inode->i_flctx); + locks_free_lock_context(inode); if (!inode->i_nlink) { WARN_ON(atomic_long_read(&inode->i_sb->s_remove_count) == 0); atomic_long_dec(&inode->i_sb->s_remove_count); @@ -2028,3 +2028,9 @@ void inode_set_flags(struct inode *inode, unsigned int flags, new_flags) != old_flags)); } EXPORT_SYMBOL(inode_set_flags); + +void inode_nohighmem(struct inode *inode) +{ + mapping_set_gfp_mask(inode->i_mapping, GFP_USER); +} +EXPORT_SYMBOL(inode_nohighmem); diff --git a/fs/internal.h b/fs/internal.h index 71859c4d..b71deee 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -55,7 +55,7 @@ extern int vfs_path_lookup(struct dentry *, struct vfsmount *, /* * namespace.c */ -extern int copy_mount_options(const void __user *, unsigned long *); +extern void *copy_mount_options(const void __user *); extern char *copy_mount_string(const void __user *); extern struct vfsmount *lookup_mnt(struct path *); @@ -151,3 +151,10 @@ extern void mnt_pin_kill(struct mount *m); * fs/nsfs.c */ extern struct dentry_operations ns_dentry_operations; + +/* + * fs/ioctl.c + */ +extern int do_vfs_ioctl(struct file *file, unsigned int fd, unsigned int cmd, + unsigned long arg); +extern long vfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg); @@ -15,6 +15,7 @@ #include <linux/writeback.h> #include <linux/buffer_head.h> #include <linux/falloc.h> +#include "internal.h" #include <asm/ioctls.h> @@ -32,8 +33,7 @@ * * Returns 0 on success, -errno on error. */ -static long vfs_ioctl(struct file *filp, unsigned int cmd, - unsigned long arg) +long vfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { int error = -ENOTTY; @@ -215,6 +215,29 @@ static int ioctl_fiemap(struct file *filp, unsigned long arg) return error; } +static long ioctl_file_clone(struct file *dst_file, unsigned long srcfd, + u64 off, u64 olen, u64 destoff) +{ + struct fd src_file = fdget(srcfd); + int ret; + + if (!src_file.file) + return -EBADF; + ret = vfs_clone_file_range(src_file.file, off, dst_file, destoff, olen); + fdput(src_file); + return ret; +} + +static long ioctl_file_clone_range(struct file *file, void __user *argp) +{ + struct file_clone_range args; + + if (copy_from_user(&args, argp, sizeof(args))) + return -EFAULT; + return ioctl_file_clone(file, args.src_fd, args.src_offset, + args.src_length, args.dest_offset); +} + #ifdef CONFIG_BLOCK static inline sector_t logical_to_blk(struct inode *inode, loff_t offset) @@ -545,6 +568,41 @@ static int ioctl_fsthaw(struct file *filp) return thaw_super(sb); } +static long ioctl_file_dedupe_range(struct file *file, void __user *arg) +{ + struct file_dedupe_range __user *argp = arg; + struct file_dedupe_range *same = NULL; + int ret; + unsigned long size; + u16 count; + + if (get_user(count, &argp->dest_count)) { + ret = -EFAULT; + goto out; + } + + size = offsetof(struct file_dedupe_range __user, info[count]); + + same = memdup_user(argp, size); + if (IS_ERR(same)) { + ret = PTR_ERR(same); + same = NULL; + goto out; + } + + ret = vfs_dedupe_file_range(file, same); + if (ret) + goto out; + + ret = copy_to_user(argp, same, size); + if (ret) + ret = -EFAULT; + +out: + kfree(same); + return ret; +} + /* * When you add any new common ioctls to the switches above and below * please update compat_sys_ioctl() too. @@ -600,6 +658,15 @@ int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd, case FIGETBSZ: return put_user(inode->i_sb->s_blocksize, argp); + case FICLONE: + return ioctl_file_clone(filp, arg, 0, 0, 0); + + case FICLONERANGE: + return ioctl_file_clone_range(filp, argp); + + case FIDEDUPERANGE: + return ioctl_file_dedupe_range(filp, argp); + default: if (S_ISREG(inode->i_mode)) error = file_ioctl(filp, cmd, arg); diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c index d67a16f..61abdc4 100644 --- a/fs/isofs/inode.c +++ b/fs/isofs/inode.c @@ -1417,6 +1417,7 @@ static int isofs_read_inode(struct inode *inode, int relocated) inode->i_fop = &isofs_dir_operations; } else if (S_ISLNK(inode->i_mode)) { inode->i_op = &page_symlink_inode_operations; + inode_nohighmem(inode); inode->i_data.a_ops = &isofs_symlink_aops; } else /* XXX - parse_rock_ridge_inode() had already set i_rdev. */ diff --git a/fs/isofs/rock.c b/fs/isofs/rock.c index 735d752..5384ceb 100644 --- a/fs/isofs/rock.c +++ b/fs/isofs/rock.c @@ -687,7 +687,7 @@ static int rock_ridge_symlink_readpage(struct file *file, struct page *page) struct inode *inode = page->mapping->host; struct iso_inode_info *ei = ISOFS_I(inode); struct isofs_sb_info *sbi = ISOFS_SB(inode->i_sb); - char *link = kmap(page); + char *link = page_address(page); unsigned long bufsize = ISOFS_BUFFER_SIZE(inode); struct buffer_head *bh; char *rpnt = link; @@ -774,7 +774,6 @@ repeat: brelse(bh); *rpnt = '\0'; SetPageUptodate(page); - kunmap(page); unlock_page(page); return 0; @@ -791,7 +790,6 @@ fail: brelse(bh); error: SetPageError(page); - kunmap(page); unlock_page(page); return -EIO; } diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index ca181e8..081dff0 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -764,13 +764,11 @@ void jbd2_journal_unlock_updates (journal_t *journal) static void warn_dirty_buffer(struct buffer_head *bh) { - char b[BDEVNAME_SIZE]; - printk(KERN_WARNING - "JBD2: Spotted dirty metadata buffer (dev = %s, blocknr = %llu). " + "JBD2: Spotted dirty metadata buffer (dev = %pg, blocknr = %llu). " "There's a risk of filesystem corruption in case of system " "crash.\n", - bdevname(bh->b_bdev, b), (unsigned long long)bh->b_blocknr); + bh->b_bdev, (unsigned long long)bh->b_blocknr); } /* Call t_frozen trigger and copy buffer data into jh->b_frozen_data. */ diff --git a/fs/jffs2/security.c b/fs/jffs2/security.c index bf12fe5..7a28fac 100644 --- a/fs/jffs2/security.c +++ b/fs/jffs2/security.c @@ -52,9 +52,6 @@ static int jffs2_security_getxattr(const struct xattr_handler *handler, struct dentry *dentry, const char *name, void *buffer, size_t size) { - if (!strcmp(name, "")) - return -EINVAL; - return do_jffs2_getxattr(d_inode(dentry), JFFS2_XPREFIX_SECURITY, name, buffer, size); } @@ -63,31 +60,12 @@ static int jffs2_security_setxattr(const struct xattr_handler *handler, struct dentry *dentry, const char *name, const void *buffer, size_t size, int flags) { - if (!strcmp(name, "")) - return -EINVAL; - return do_jffs2_setxattr(d_inode(dentry), JFFS2_XPREFIX_SECURITY, name, buffer, size, flags); } -static size_t jffs2_security_listxattr(const struct xattr_handler *handler, - struct dentry *dentry, char *list, - size_t list_size, const char *name, - size_t name_len) -{ - size_t retlen = XATTR_SECURITY_PREFIX_LEN + name_len + 1; - - if (list && retlen <= list_size) { - strcpy(list, XATTR_SECURITY_PREFIX); - strcpy(list + XATTR_SECURITY_PREFIX_LEN, name); - } - - return retlen; -} - const struct xattr_handler jffs2_security_xattr_handler = { .prefix = XATTR_SECURITY_PREFIX, - .list = jffs2_security_listxattr, .set = jffs2_security_setxattr, .get = jffs2_security_getxattr }; diff --git a/fs/jffs2/symlink.c b/fs/jffs2/symlink.c index 8ce2f24..2cabd64 100644 --- a/fs/jffs2/symlink.c +++ b/fs/jffs2/symlink.c @@ -14,7 +14,7 @@ const struct inode_operations jffs2_symlink_inode_operations = { .readlink = generic_readlink, - .follow_link = simple_follow_link, + .get_link = simple_get_link, .setattr = jffs2_setattr, .setxattr = jffs2_setxattr, .getxattr = jffs2_getxattr, diff --git a/fs/jffs2/xattr.c b/fs/jffs2/xattr.c index 4c2c036..da3e185 100644 --- a/fs/jffs2/xattr.c +++ b/fs/jffs2/xattr.c @@ -967,7 +967,8 @@ ssize_t jffs2_listxattr(struct dentry *dentry, char *buffer, size_t size) struct jffs2_xattr_ref *ref, **pref; struct jffs2_xattr_datum *xd; const struct xattr_handler *xhandle; - ssize_t len, rc; + const char *prefix; + ssize_t prefix_len, len, rc; int retry = 0; rc = check_xattr_ref_inode(c, ic); @@ -998,18 +999,23 @@ ssize_t jffs2_listxattr(struct dentry *dentry, char *buffer, size_t size) } } xhandle = xprefix_to_handler(xd->xprefix); - if (!xhandle) + if (!xhandle || (xhandle->list && !xhandle->list(dentry))) continue; + prefix = xhandle->prefix ?: xhandle->name; + prefix_len = strlen(prefix); + rc = prefix_len + xd->name_len + 1; + if (buffer) { - rc = xhandle->list(xhandle, dentry, buffer + len, - size - len, xd->xname, - xd->name_len); - } else { - rc = xhandle->list(xhandle, dentry, NULL, 0, - xd->xname, xd->name_len); + if (rc > size - len) { + rc = -ERANGE; + goto out; + } + memcpy(buffer, prefix, prefix_len); + buffer += prefix_len; + memcpy(buffer, xd->xname, xd->name_len); + buffer += xd->name_len; + *buffer++ = 0; } - if (rc < 0) - goto out; len += rc; } rc = len; diff --git a/fs/jffs2/xattr_trusted.c b/fs/jffs2/xattr_trusted.c index a562da0..b2555ef 100644 --- a/fs/jffs2/xattr_trusted.c +++ b/fs/jffs2/xattr_trusted.c @@ -20,8 +20,6 @@ static int jffs2_trusted_getxattr(const struct xattr_handler *handler, struct dentry *dentry, const char *name, void *buffer, size_t size) { - if (!strcmp(name, "")) - return -EINVAL; return do_jffs2_getxattr(d_inode(dentry), JFFS2_XPREFIX_TRUSTED, name, buffer, size); } @@ -30,28 +28,13 @@ static int jffs2_trusted_setxattr(const struct xattr_handler *handler, struct dentry *dentry, const char *name, const void *buffer, size_t size, int flags) { - if (!strcmp(name, "")) - return -EINVAL; return do_jffs2_setxattr(d_inode(dentry), JFFS2_XPREFIX_TRUSTED, name, buffer, size, flags); } -static size_t jffs2_trusted_listxattr(const struct xattr_handler *handler, - struct dentry *dentry, char *list, - size_t list_size, const char *name, - size_t name_len) +static bool jffs2_trusted_listxattr(struct dentry *dentry) { - size_t retlen = XATTR_TRUSTED_PREFIX_LEN + name_len + 1; - - if (!capable(CAP_SYS_ADMIN)) - return 0; - - if (list && retlen<=list_size) { - strcpy(list, XATTR_TRUSTED_PREFIX); - strcpy(list + XATTR_TRUSTED_PREFIX_LEN, name); - } - - return retlen; + return capable(CAP_SYS_ADMIN); } const struct xattr_handler jffs2_trusted_xattr_handler = { diff --git a/fs/jffs2/xattr_user.c b/fs/jffs2/xattr_user.c index cbc0472..539bd63 100644 --- a/fs/jffs2/xattr_user.c +++ b/fs/jffs2/xattr_user.c @@ -20,8 +20,6 @@ static int jffs2_user_getxattr(const struct xattr_handler *handler, struct dentry *dentry, const char *name, void *buffer, size_t size) { - if (!strcmp(name, "")) - return -EINVAL; return do_jffs2_getxattr(d_inode(dentry), JFFS2_XPREFIX_USER, name, buffer, size); } @@ -30,30 +28,12 @@ static int jffs2_user_setxattr(const struct xattr_handler *handler, struct dentry *dentry, const char *name, const void *buffer, size_t size, int flags) { - if (!strcmp(name, "")) - return -EINVAL; return do_jffs2_setxattr(d_inode(dentry), JFFS2_XPREFIX_USER, name, buffer, size, flags); } -static size_t jffs2_user_listxattr(const struct xattr_handler *handler, - struct dentry *dentry, char *list, - size_t list_size, const char *name, - size_t name_len) -{ - size_t retlen = XATTR_USER_PREFIX_LEN + name_len + 1; - - if (list && retlen <= list_size) { - strcpy(list, XATTR_USER_PREFIX); - strcpy(list + XATTR_USER_PREFIX_LEN, name); - } - - return retlen; -} - const struct xattr_handler jffs2_user_xattr_handler = { .prefix = XATTR_USER_PREFIX, - .list = jffs2_user_listxattr, .set = jffs2_user_setxattr, .get = jffs2_user_getxattr }; diff --git a/fs/jfs/acl.c b/fs/jfs/acl.c index 0c8ca83..4945685 100644 --- a/fs/jfs/acl.c +++ b/fs/jfs/acl.c @@ -40,10 +40,10 @@ struct posix_acl *jfs_get_acl(struct inode *inode, int type) switch(type) { case ACL_TYPE_ACCESS: - ea_name = POSIX_ACL_XATTR_ACCESS; + ea_name = XATTR_NAME_POSIX_ACL_ACCESS; break; case ACL_TYPE_DEFAULT: - ea_name = POSIX_ACL_XATTR_DEFAULT; + ea_name = XATTR_NAME_POSIX_ACL_DEFAULT; break; default: return ERR_PTR(-EINVAL); @@ -82,7 +82,7 @@ static int __jfs_set_acl(tid_t tid, struct inode *inode, int type, switch (type) { case ACL_TYPE_ACCESS: - ea_name = POSIX_ACL_XATTR_ACCESS; + ea_name = XATTR_NAME_POSIX_ACL_ACCESS; if (acl) { rc = posix_acl_equiv_mode(acl, &inode->i_mode); if (rc < 0) @@ -94,7 +94,7 @@ static int __jfs_set_acl(tid_t tid, struct inode *inode, int type, } break; case ACL_TYPE_DEFAULT: - ea_name = POSIX_ACL_XATTR_DEFAULT; + ea_name = XATTR_NAME_POSIX_ACL_DEFAULT; break; default: return -EINVAL; diff --git a/fs/jfs/inode.c b/fs/jfs/inode.c index 41aa3ca..9d9bae6 100644 --- a/fs/jfs/inode.c +++ b/fs/jfs/inode.c @@ -60,6 +60,7 @@ struct inode *jfs_iget(struct super_block *sb, unsigned long ino) } else if (S_ISLNK(inode->i_mode)) { if (inode->i_size >= IDATASIZE) { inode->i_op = &page_symlink_inode_operations; + inode_nohighmem(inode); inode->i_mapping->a_ops = &jfs_aops; } else { inode->i_op = &jfs_fast_symlink_inode_operations; diff --git a/fs/jfs/jfs_logmgr.c b/fs/jfs/jfs_logmgr.c index a69bdf2..a270cb7 100644 --- a/fs/jfs/jfs_logmgr.c +++ b/fs/jfs/jfs_logmgr.c @@ -1835,17 +1835,16 @@ static int lbmLogInit(struct jfs_log * log) for (i = 0; i < LOGPAGES;) { char *buffer; uint offset; - struct page *page; + struct page *page = alloc_page(GFP_KERNEL | __GFP_ZERO); - buffer = (char *) get_zeroed_page(GFP_KERNEL); - if (buffer == NULL) + if (!page) goto error; - page = virt_to_page(buffer); + buffer = page_address(page); for (offset = 0; offset < PAGE_SIZE; offset += LOGPSIZE) { lbuf = kmalloc(sizeof(struct lbuf), GFP_KERNEL); if (lbuf == NULL) { if (offset == 0) - free_page((unsigned long) buffer); + __free_page(page); goto error; } if (offset) /* we already have one reference */ diff --git a/fs/jfs/namei.c b/fs/jfs/namei.c index 9d7551f..701f893 100644 --- a/fs/jfs/namei.c +++ b/fs/jfs/namei.c @@ -983,6 +983,7 @@ static int jfs_symlink(struct inode *dip, struct dentry *dentry, jfs_info("jfs_symlink: allocate extent ip:0x%p", ip); ip->i_op = &jfs_symlink_inode_operations; + inode_nohighmem(ip); ip->i_mapping->a_ops = &jfs_aops; /* diff --git a/fs/jfs/symlink.c b/fs/jfs/symlink.c index 5929e23..f8db4fd 100644 --- a/fs/jfs/symlink.c +++ b/fs/jfs/symlink.c @@ -23,7 +23,7 @@ const struct inode_operations jfs_fast_symlink_inode_operations = { .readlink = generic_readlink, - .follow_link = simple_follow_link, + .get_link = simple_get_link, .setattr = jfs_setattr, .setxattr = jfs_setxattr, .getxattr = jfs_getxattr, @@ -33,8 +33,7 @@ const struct inode_operations jfs_fast_symlink_inode_operations = { const struct inode_operations jfs_symlink_inode_operations = { .readlink = generic_readlink, - .follow_link = page_follow_link_light, - .put_link = page_put_link, + .get_link = page_get_link, .setattr = jfs_setattr, .setxattr = jfs_setxattr, .getxattr = jfs_getxattr, diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c index 91e0045..742bf4a 100644 --- a/fs/kernfs/dir.c +++ b/fs/kernfs/dir.c @@ -694,6 +694,29 @@ static struct kernfs_node *kernfs_find_ns(struct kernfs_node *parent, return NULL; } +static struct kernfs_node *kernfs_walk_ns(struct kernfs_node *parent, + const unsigned char *path, + const void *ns) +{ + static char path_buf[PATH_MAX]; /* protected by kernfs_mutex */ + size_t len = strlcpy(path_buf, path, PATH_MAX); + char *p = path_buf; + char *name; + + lockdep_assert_held(&kernfs_mutex); + + if (len >= PATH_MAX) + return NULL; + + while ((name = strsep(&p, "/")) && parent) { + if (*name == '\0') + continue; + parent = kernfs_find_ns(parent, name, ns); + } + + return parent; +} + /** * kernfs_find_and_get_ns - find and get kernfs_node with the given name * @parent: kernfs_node to search under @@ -719,6 +742,29 @@ struct kernfs_node *kernfs_find_and_get_ns(struct kernfs_node *parent, EXPORT_SYMBOL_GPL(kernfs_find_and_get_ns); /** + * kernfs_walk_and_get_ns - find and get kernfs_node with the given path + * @parent: kernfs_node to search under + * @path: path to look for + * @ns: the namespace tag to use + * + * Look for kernfs_node with path @path under @parent and get a reference + * if found. This function may sleep and returns pointer to the found + * kernfs_node on success, %NULL on failure. + */ +struct kernfs_node *kernfs_walk_and_get_ns(struct kernfs_node *parent, + const char *path, const void *ns) +{ + struct kernfs_node *kn; + + mutex_lock(&kernfs_mutex); + kn = kernfs_walk_ns(parent, path, ns); + kernfs_get(kn); + mutex_unlock(&kernfs_mutex); + + return kn; +} + +/** * kernfs_create_root - create a new kernfs hierarchy * @scops: optional syscall operations for the hierarchy * @flags: KERNFS_ROOT_* flags diff --git a/fs/kernfs/inode.c b/fs/kernfs/inode.c index 756dd56..16405ae 100644 --- a/fs/kernfs/inode.c +++ b/fs/kernfs/inode.c @@ -205,7 +205,7 @@ int kernfs_iop_removexattr(struct dentry *dentry, const char *name) if (!attrs) return -ENOMEM; - return simple_xattr_remove(&attrs->xattrs, 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, @@ -230,7 +230,7 @@ ssize_t kernfs_iop_listxattr(struct dentry *dentry, char *buf, size_t size) if (!attrs) return -ENOMEM; - return simple_xattr_list(&attrs->xattrs, buf, size); + return simple_xattr_list(d_inode(dentry), &attrs->xattrs, buf, size); } static inline void set_default_inode_attr(struct inode *inode, umode_t mode) diff --git a/fs/kernfs/symlink.c b/fs/kernfs/symlink.c index db27252..117b8b3 100644 --- a/fs/kernfs/symlink.c +++ b/fs/kernfs/symlink.c @@ -112,18 +112,25 @@ static int kernfs_getlink(struct dentry *dentry, char *path) return error; } -static const char *kernfs_iop_follow_link(struct dentry *dentry, void **cookie) +static const char *kernfs_iop_get_link(struct dentry *dentry, + struct inode *inode, + struct delayed_call *done) { - int error = -ENOMEM; - unsigned long page = get_zeroed_page(GFP_KERNEL); - if (!page) + char *body; + int error; + + if (!dentry) + return ERR_PTR(-ECHILD); + body = kzalloc(PAGE_SIZE, GFP_KERNEL); + if (!body) return ERR_PTR(-ENOMEM); - error = kernfs_getlink(dentry, (char *)page); + error = kernfs_getlink(dentry, body); if (unlikely(error < 0)) { - free_page((unsigned long)page); + kfree(body); return ERR_PTR(error); } - return *cookie = (char *)page; + set_delayed_call(done, kfree_link, body); + return body; } const struct inode_operations kernfs_symlink_iops = { @@ -132,8 +139,7 @@ const struct inode_operations kernfs_symlink_iops = { .getxattr = kernfs_iop_getxattr, .listxattr = kernfs_iop_listxattr, .readlink = generic_readlink, - .follow_link = kernfs_iop_follow_link, - .put_link = free_page_put_link, + .get_link = kernfs_iop_get_link, .setattr = kernfs_iop_setattr, .getattr = kernfs_iop_getattr, .permission = kernfs_iop_permission, @@ -1019,17 +1019,12 @@ int noop_fsync(struct file *file, loff_t start, loff_t end, int datasync) } EXPORT_SYMBOL(noop_fsync); -void kfree_put_link(struct inode *unused, void *cookie) +/* Because kfree isn't assignment-compatible with void(void*) ;-/ */ +void kfree_link(void *p) { - kfree(cookie); + kfree(p); } -EXPORT_SYMBOL(kfree_put_link); - -void free_page_put_link(struct inode *unused, void *cookie) -{ - free_page((unsigned long) cookie); -} -EXPORT_SYMBOL(free_page_put_link); +EXPORT_SYMBOL(kfree_link); /* * nop .set_page_dirty method so that people can use .page_mkwrite on @@ -1092,14 +1087,15 @@ simple_nosetlease(struct file *filp, long arg, struct file_lock **flp, } EXPORT_SYMBOL(simple_nosetlease); -const char *simple_follow_link(struct dentry *dentry, void **cookie) +const char *simple_get_link(struct dentry *dentry, struct inode *inode, + struct delayed_call *done) { - return d_inode(dentry)->i_link; + return inode->i_link; } -EXPORT_SYMBOL(simple_follow_link); +EXPORT_SYMBOL(simple_get_link); const struct inode_operations simple_symlink_inode_operations = { - .follow_link = simple_follow_link, + .get_link = simple_get_link, .readlink = generic_readlink }; EXPORT_SYMBOL(simple_symlink_inode_operations); @@ -119,7 +119,6 @@ #include <linux/fdtable.h> #include <linux/fs.h> #include <linux/init.h> -#include <linux/module.h> #include <linux/security.h> #include <linux/slab.h> #include <linux/syscalls.h> @@ -230,16 +229,44 @@ locks_get_lock_context(struct inode *inode, int type) ctx = smp_load_acquire(&inode->i_flctx); } out: + trace_locks_get_lock_context(inode, type, ctx); return ctx; } +static void +locks_dump_ctx_list(struct list_head *list, char *list_type) +{ + struct file_lock *fl; + + list_for_each_entry(fl, list, fl_list) { + pr_warn("%s: fl_owner=%p fl_flags=0x%x fl_type=0x%x fl_pid=%u\n", list_type, fl->fl_owner, fl->fl_flags, fl->fl_type, fl->fl_pid); + } +} + +static void +locks_check_ctx_lists(struct inode *inode) +{ + struct file_lock_context *ctx = inode->i_flctx; + + if (unlikely(!list_empty(&ctx->flc_flock) || + !list_empty(&ctx->flc_posix) || + !list_empty(&ctx->flc_lease))) { + pr_warn("Leaked locks on dev=0x%x:0x%x ino=0x%lx:\n", + MAJOR(inode->i_sb->s_dev), MINOR(inode->i_sb->s_dev), + inode->i_ino); + locks_dump_ctx_list(&ctx->flc_flock, "FLOCK"); + locks_dump_ctx_list(&ctx->flc_posix, "POSIX"); + locks_dump_ctx_list(&ctx->flc_lease, "LEASE"); + } +} + void -locks_free_lock_context(struct file_lock_context *ctx) +locks_free_lock_context(struct inode *inode) { - if (ctx) { - WARN_ON_ONCE(!list_empty(&ctx->flc_flock)); - WARN_ON_ONCE(!list_empty(&ctx->flc_posix)); - WARN_ON_ONCE(!list_empty(&ctx->flc_lease)); + struct file_lock_context *ctx = inode->i_flctx; + + if (unlikely(ctx)) { + locks_check_ctx_lists(inode); kmem_cache_free(flctx_cache, ctx); } } @@ -934,7 +961,8 @@ out: return error; } -static int __posix_lock_file(struct inode *inode, struct file_lock *request, struct file_lock *conflock) +static int posix_lock_inode(struct inode *inode, struct file_lock *request, + struct file_lock *conflock) { struct file_lock *fl, *tmp; struct file_lock *new_fl = NULL; @@ -1142,6 +1170,8 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str if (new_fl2) locks_free_lock(new_fl2); locks_dispose_list(&dispose); + trace_posix_lock_inode(inode, request, error); + return error; } @@ -1162,7 +1192,7 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str int posix_lock_file(struct file *filp, struct file_lock *fl, struct file_lock *conflock) { - return __posix_lock_file(file_inode(filp), fl, conflock); + return posix_lock_inode(file_inode(filp), fl, conflock); } EXPORT_SYMBOL(posix_lock_file); @@ -1178,7 +1208,7 @@ static int posix_lock_inode_wait(struct inode *inode, struct file_lock *fl) int error; might_sleep (); for (;;) { - error = __posix_lock_file(inode, fl, NULL); + error = posix_lock_inode(inode, fl, NULL); if (error != FILE_LOCK_DEFERRED) break; error = wait_event_interruptible(fl->fl_wait, !fl->fl_next); @@ -1191,6 +1221,7 @@ static int posix_lock_inode_wait(struct inode *inode, struct file_lock *fl) return error; } +#ifdef CONFIG_MANDATORY_FILE_LOCKING /** * locks_mandatory_locked - Check for an active lock * @file: the file to check @@ -1227,20 +1258,16 @@ int locks_mandatory_locked(struct file *file) /** * locks_mandatory_area - Check for a conflicting lock - * @read_write: %FLOCK_VERIFY_WRITE for exclusive access, %FLOCK_VERIFY_READ - * for shared - * @inode: the file to check + * @inode: the file to check * @filp: how the file was opened (if it was) - * @offset: start of area to check - * @count: length of area to check + * @start: first byte in the file to check + * @end: lastbyte in the file to check + * @type: %F_WRLCK for a write lock, else %F_RDLCK * * Searches the inode's list of locks to find any POSIX locks which conflict. - * This function is called from rw_verify_area() and - * locks_verify_truncate(). */ -int locks_mandatory_area(int read_write, struct inode *inode, - struct file *filp, loff_t offset, - size_t count) +int locks_mandatory_area(struct inode *inode, struct file *filp, loff_t start, + loff_t end, unsigned char type) { struct file_lock fl; int error; @@ -1252,15 +1279,15 @@ int locks_mandatory_area(int read_write, struct inode *inode, fl.fl_flags = FL_POSIX | FL_ACCESS; if (filp && !(filp->f_flags & O_NONBLOCK)) sleep = true; - fl.fl_type = (read_write == FLOCK_VERIFY_WRITE) ? F_WRLCK : F_RDLCK; - fl.fl_start = offset; - fl.fl_end = offset + count - 1; + fl.fl_type = type; + fl.fl_start = start; + fl.fl_end = end; for (;;) { if (filp) { fl.fl_owner = filp; fl.fl_flags &= ~FL_SLEEP; - error = __posix_lock_file(inode, &fl, NULL); + error = posix_lock_inode(inode, &fl, NULL); if (!error) break; } @@ -1268,7 +1295,7 @@ int locks_mandatory_area(int read_write, struct inode *inode, if (sleep) fl.fl_flags |= FL_SLEEP; fl.fl_owner = current->files; - error = __posix_lock_file(inode, &fl, NULL); + error = posix_lock_inode(inode, &fl, NULL); if (error != FILE_LOCK_DEFERRED) break; error = wait_event_interruptible(fl.fl_wait, !fl.fl_next); @@ -1289,6 +1316,7 @@ int locks_mandatory_area(int read_write, struct inode *inode, } EXPORT_SYMBOL(locks_mandatory_area); +#endif /* CONFIG_MANDATORY_FILE_LOCKING */ static void lease_clear_pending(struct file_lock *fl, int arg) { @@ -1503,12 +1531,10 @@ void lease_get_mtime(struct inode *inode, struct timespec *time) ctx = smp_load_acquire(&inode->i_flctx); if (ctx && !list_empty_careful(&ctx->flc_lease)) { spin_lock(&ctx->flc_lock); - if (!list_empty(&ctx->flc_lease)) { - fl = list_first_entry(&ctx->flc_lease, - struct file_lock, fl_list); - if (fl->fl_type == F_WRLCK) - has_lease = true; - } + fl = list_first_entry_or_null(&ctx->flc_lease, + struct file_lock, fl_list); + if (fl && (fl->fl_type == F_WRLCK)) + has_lease = true; spin_unlock(&ctx->flc_lock); } @@ -2165,6 +2191,8 @@ int fcntl_setlk(unsigned int fd, struct file *filp, unsigned int cmd, if (file_lock == NULL) return -ENOLCK; + inode = file_inode(filp); + /* * This might block, so we do it before checking the inode. */ @@ -2172,8 +2200,6 @@ int fcntl_setlk(unsigned int fd, struct file *filp, unsigned int cmd, if (copy_from_user(&flock, l, sizeof(flock))) goto out; - inode = file_inode(filp); - /* Don't allow mandatory locks on files that may be memory mapped * and shared. */ @@ -2182,7 +2208,6 @@ int fcntl_setlk(unsigned int fd, struct file *filp, unsigned int cmd, goto out; } -again: error = flock_to_posix_lock(filp, file_lock, &flock); if (error) goto out; @@ -2221,23 +2246,29 @@ again: error = do_lock_file_wait(filp, cmd, file_lock); /* - * Attempt to detect a close/fcntl race and recover by - * releasing the lock that was just acquired. - */ - /* - * we need that spin_lock here - it prevents reordering between - * update of i_flctx->flc_posix and check for it done in close(). - * rcu_read_lock() wouldn't do. + * Attempt to detect a close/fcntl race and recover by releasing the + * lock that was just acquired. There is no need to do that when we're + * unlocking though, or for OFD locks. */ - spin_lock(¤t->files->file_lock); - f = fcheck(fd); - spin_unlock(¤t->files->file_lock); - if (!error && f != filp && flock.l_type != F_UNLCK) { - flock.l_type = F_UNLCK; - goto again; + if (!error && file_lock->fl_type != F_UNLCK && + !(file_lock->fl_flags & FL_OFDLCK)) { + /* + * We need that spin_lock here - it prevents reordering between + * update of i_flctx->flc_posix and check for it done in + * close(). rcu_read_lock() wouldn't do. + */ + spin_lock(¤t->files->file_lock); + f = fcheck(fd); + spin_unlock(¤t->files->file_lock); + if (f != filp) { + file_lock->fl_type = F_UNLCK; + error = do_lock_file_wait(filp, cmd, file_lock); + WARN_ON_ONCE(error); + error = -EBADF; + } } - out: + trace_fcntl_setlk(inode, file_lock, error); locks_free_lock(file_lock); return error; } @@ -2322,7 +2353,6 @@ int fcntl_setlk64(unsigned int fd, struct file *filp, unsigned int cmd, goto out; } -again: error = flock64_to_posix_lock(filp, file_lock, &flock); if (error) goto out; @@ -2361,17 +2391,27 @@ again: error = do_lock_file_wait(filp, cmd, file_lock); /* - * Attempt to detect a close/fcntl race and recover by - * releasing the lock that was just acquired. + * Attempt to detect a close/fcntl race and recover by releasing the + * lock that was just acquired. There is no need to do that when we're + * unlocking though, or for OFD locks. */ - spin_lock(¤t->files->file_lock); - f = fcheck(fd); - spin_unlock(¤t->files->file_lock); - if (!error && f != filp && flock.l_type != F_UNLCK) { - flock.l_type = F_UNLCK; - goto again; + if (!error && file_lock->fl_type != F_UNLCK && + !(file_lock->fl_flags & FL_OFDLCK)) { + /* + * We need that spin_lock here - it prevents reordering between + * update of i_flctx->flc_posix and check for it done in + * close(). rcu_read_lock() wouldn't do. + */ + spin_lock(¤t->files->file_lock); + f = fcheck(fd); + spin_unlock(¤t->files->file_lock); + if (f != filp) { + file_lock->fl_type = F_UNLCK; + error = do_lock_file_wait(filp, cmd, file_lock); + WARN_ON_ONCE(error); + error = -EBADF; + } } - out: locks_free_lock(file_lock); return error; @@ -2385,6 +2425,7 @@ out: */ void locks_remove_posix(struct file *filp, fl_owner_t owner) { + int error; struct file_lock lock; struct file_lock_context *ctx; @@ -2407,10 +2448,11 @@ void locks_remove_posix(struct file *filp, fl_owner_t owner) lock.fl_ops = NULL; lock.fl_lmops = NULL; - vfs_lock_file(filp, F_SETLK, &lock, NULL); + error = vfs_lock_file(filp, F_SETLK, &lock, NULL); if (lock.fl_ops && lock.fl_ops->fl_release_private) lock.fl_ops->fl_release_private(&lock); + trace_locks_remove_posix(file_inode(filp), &lock, error); } EXPORT_SYMBOL(locks_remove_posix); @@ -2706,7 +2748,7 @@ static int __init proc_locks_init(void) proc_create("locks", 0, NULL, &proc_locks_operations); return 0; } -module_init(proc_locks_init); +fs_initcall(proc_locks_init); #endif static int __init filelock_init(void) diff --git a/fs/logfs/dir.c b/fs/logfs/dir.c index f9b45d4..542468e 100644 --- a/fs/logfs/dir.c +++ b/fs/logfs/dir.c @@ -528,7 +528,8 @@ static int logfs_symlink(struct inode *dir, struct dentry *dentry, if (IS_ERR(inode)) return PTR_ERR(inode); - inode->i_op = &logfs_symlink_iops; + inode->i_op = &page_symlink_inode_operations; + inode_nohighmem(inode); inode->i_mapping->a_ops = &logfs_reg_aops; return __logfs_create(dir, dentry, inode, target, destlen); @@ -776,12 +777,6 @@ fail: return -EIO; } -const struct inode_operations logfs_symlink_iops = { - .readlink = generic_readlink, - .follow_link = page_follow_link_light, - .put_link = page_put_link, -}; - const struct inode_operations logfs_dir_iops = { .create = logfs_create, .link = logfs_link, diff --git a/fs/logfs/inode.c b/fs/logfs/inode.c index af49e2d..0fce46d 100644 --- a/fs/logfs/inode.c +++ b/fs/logfs/inode.c @@ -64,7 +64,8 @@ static void logfs_inode_setops(struct inode *inode) inode->i_mapping->a_ops = &logfs_reg_aops; break; case S_IFLNK: - inode->i_op = &logfs_symlink_iops; + inode->i_op = &page_symlink_inode_operations; + inode_nohighmem(inode); inode->i_mapping->a_ops = &logfs_reg_aops; break; case S_IFSOCK: /* fall through */ diff --git a/fs/logfs/logfs.h b/fs/logfs/logfs.h index 5f09376..39d91f8 100644 --- a/fs/logfs/logfs.h +++ b/fs/logfs/logfs.h @@ -302,7 +302,7 @@ struct logfs_block { struct inode *inode; struct logfs_transaction *ta; unsigned long alias_map[LOGFS_BLOCK_FACTOR / BITS_PER_LONG]; - struct logfs_block_ops *ops; + const struct logfs_block_ops *ops; int full; int partial; int reserved_bytes; @@ -495,7 +495,6 @@ static inline int logfs_get_sb_mtd(struct logfs_super *s, int mtdnr) #endif /* dir.c */ -extern const struct inode_operations logfs_symlink_iops; extern const struct inode_operations logfs_dir_iops; extern const struct file_operations logfs_dir_fops; int logfs_replay_journal(struct super_block *sb); @@ -579,7 +578,7 @@ int logfs_exist_block(struct inode *inode, u64 bix); int get_page_reserve(struct inode *inode, struct page *page); void logfs_get_wblocks(struct super_block *sb, struct page *page, int lock); void logfs_put_wblocks(struct super_block *sb, struct page *page, int lock); -extern struct logfs_block_ops indirect_block_ops; +extern const struct logfs_block_ops indirect_block_ops; /* segment.c */ int logfs_erase_segment(struct super_block *sb, u32 ofs, int ensure_erase); diff --git a/fs/logfs/readwrite.c b/fs/logfs/readwrite.c index 380d86e..20973c9 100644 --- a/fs/logfs/readwrite.c +++ b/fs/logfs/readwrite.c @@ -569,13 +569,13 @@ static void indirect_free_block(struct super_block *sb, } -static struct logfs_block_ops inode_block_ops = { +static const struct logfs_block_ops inode_block_ops = { .write_block = inode_write_block, .free_block = inode_free_block, .write_alias = inode_write_alias, }; -struct logfs_block_ops indirect_block_ops = { +const struct logfs_block_ops indirect_block_ops = { .write_block = indirect_write_block, .free_block = indirect_free_block, .write_alias = indirect_write_alias, diff --git a/fs/logfs/segment.c b/fs/logfs/segment.c index 6de0fbf..d270e4b 100644 --- a/fs/logfs/segment.c +++ b/fs/logfs/segment.c @@ -197,7 +197,7 @@ static int btree_write_alias(struct super_block *sb, struct logfs_block *block, return 0; } -static struct logfs_block_ops btree_block_ops = { +static const struct logfs_block_ops btree_block_ops = { .write_block = btree_write_block, .free_block = __free_block, .write_alias = btree_write_alias, diff --git a/fs/minix/inode.c b/fs/minix/inode.c index 086cd0a..cb1789c 100644 --- a/fs/minix/inode.c +++ b/fs/minix/inode.c @@ -435,8 +435,7 @@ static const struct address_space_operations minix_aops = { static const struct inode_operations minix_symlink_inode_operations = { .readlink = generic_readlink, - .follow_link = page_follow_link_light, - .put_link = page_put_link, + .get_link = page_get_link, .getattr = minix_getattr, }; @@ -452,6 +451,7 @@ void minix_set_inode(struct inode *inode, dev_t rdev) inode->i_mapping->a_ops = &minix_aops; } else if (S_ISLNK(inode->i_mode)) { inode->i_op = &minix_symlink_inode_operations; + inode_nohighmem(inode); inode->i_mapping->a_ops = &minix_aops; } else init_special_inode(inode, inode->i_mode, rdev); diff --git a/fs/minix/itree_v1.c b/fs/minix/itree_v1.c index 282e15a..46ca39d 100644 --- a/fs/minix/itree_v1.c +++ b/fs/minix/itree_v1.c @@ -24,16 +24,15 @@ static inline block_t *i_data(struct inode *inode) static int block_to_path(struct inode * inode, long block, int offsets[DEPTH]) { int n = 0; - char b[BDEVNAME_SIZE]; if (block < 0) { - printk("MINIX-fs: block_to_path: block %ld < 0 on dev %s\n", - block, bdevname(inode->i_sb->s_bdev, b)); + printk("MINIX-fs: block_to_path: block %ld < 0 on dev %pg\n", + block, inode->i_sb->s_bdev); } else if (block >= (minix_sb(inode->i_sb)->s_max_size/BLOCK_SIZE)) { if (printk_ratelimit()) printk("MINIX-fs: block_to_path: " - "block %ld too big on dev %s\n", - block, bdevname(inode->i_sb->s_bdev, b)); + "block %ld too big on dev %pg\n", + block, inode->i_sb->s_bdev); } else if (block < 7) { offsets[n++] = block; } else if ((block -= 7) < 512) { diff --git a/fs/minix/itree_v2.c b/fs/minix/itree_v2.c index 78e2d93..1ee1013 100644 --- a/fs/minix/itree_v2.c +++ b/fs/minix/itree_v2.c @@ -26,18 +26,17 @@ static inline block_t *i_data(struct inode *inode) static int block_to_path(struct inode * inode, long block, int offsets[DEPTH]) { int n = 0; - char b[BDEVNAME_SIZE]; struct super_block *sb = inode->i_sb; if (block < 0) { - printk("MINIX-fs: block_to_path: block %ld < 0 on dev %s\n", - block, bdevname(sb->s_bdev, b)); + printk("MINIX-fs: block_to_path: block %ld < 0 on dev %pg\n", + block, sb->s_bdev); } else if ((u64)block * (u64)sb->s_blocksize >= minix_sb(sb)->s_max_size) { if (printk_ratelimit()) printk("MINIX-fs: block_to_path: " - "block %ld too big on dev %s\n", - block, bdevname(sb->s_bdev, b)); + "block %ld too big on dev %pg\n", + block, sb->s_bdev); } else if (block < DIRCOUNT) { offsets[n++] = block; } else if ((block -= DIRCOUNT) < INDIRCOUNT(sb)) { @@ -505,13 +505,13 @@ struct nameidata { int total_link_count; struct saved { struct path link; - void *cookie; + struct delayed_call done; const char *name; - struct inode *inode; unsigned seq; } *stack, internal[EMBEDDED_LEVELS]; struct filename *name; struct nameidata *saved; + struct inode *link_inode; unsigned root_seq; int dfd; }; @@ -534,10 +534,8 @@ static void restore_nameidata(void) current->nameidata = old; if (old) old->total_link_count = now->total_link_count; - if (now->stack != now->internal) { + if (now->stack != now->internal) kfree(now->stack); - now->stack = now->internal; - } } static int __nd_alloc_stack(struct nameidata *nd) @@ -592,11 +590,8 @@ static void drop_links(struct nameidata *nd) int i = nd->depth; while (i--) { struct saved *last = nd->stack + i; - struct inode *inode = last->inode; - if (last->cookie && inode->i_op->put_link) { - inode->i_op->put_link(inode, last->cookie); - last->cookie = NULL; - } + do_delayed_call(&last->done); + clear_delayed_call(&last->done); } } @@ -657,7 +652,7 @@ static bool legitimize_links(struct nameidata *nd) * Path walking has 2 modes, rcu-walk and ref-walk (see * Documentation/filesystems/path-lookup.txt). In situations when we can't * continue in RCU mode, we attempt to drop out of rcu-walk mode and grab - * normal reference counts on dentries and vfsmounts to transition to rcu-walk + * normal reference counts on dentries and vfsmounts to transition to ref-walk * mode. Refcounts are grabbed at the last known good point before rcu-walk * got stuck, so ref-walk may continue from there. If this is not successful * (eg. a seqcount has changed), then failure is returned and it's up to caller @@ -807,19 +802,19 @@ static int complete_walk(struct nameidata *nd) static void set_root(struct nameidata *nd) { - get_fs_root(current->fs, &nd->root); -} - -static void set_root_rcu(struct nameidata *nd) -{ struct fs_struct *fs = current->fs; - unsigned seq; - do { - seq = read_seqcount_begin(&fs->seq); - nd->root = fs->root; - nd->root_seq = __read_seqcount_begin(&nd->root.dentry->d_seq); - } while (read_seqcount_retry(&fs->seq, seq)); + if (nd->flags & LOOKUP_RCU) { + unsigned seq; + + do { + seq = read_seqcount_begin(&fs->seq); + nd->root = fs->root; + nd->root_seq = __read_seqcount_begin(&nd->root.dentry->d_seq); + } while (read_seqcount_retry(&fs->seq, seq)); + } else { + get_fs_root(fs, &nd->root); + } } static void path_put_conditional(struct path *path, struct nameidata *nd) @@ -841,8 +836,28 @@ static inline void path_to_nameidata(const struct path *path, nd->path.dentry = path->dentry; } +static int nd_jump_root(struct nameidata *nd) +{ + if (nd->flags & LOOKUP_RCU) { + struct dentry *d; + nd->path = nd->root; + d = nd->path.dentry; + nd->inode = d->d_inode; + nd->seq = nd->root_seq; + if (unlikely(read_seqcount_retry(&d->d_seq, nd->seq))) + return -ECHILD; + } else { + path_put(&nd->path); + nd->path = nd->root; + path_get(&nd->path); + nd->inode = nd->path.dentry->d_inode; + } + nd->flags |= LOOKUP_JUMPED; + return 0; +} + /* - * Helper to directly jump to a known parsed path from ->follow_link, + * Helper to directly jump to a known parsed path from ->get_link, * caller must have taken a reference to path beforehand. */ void nd_jump_link(struct path *path) @@ -858,9 +873,7 @@ void nd_jump_link(struct path *path) static inline void put_link(struct nameidata *nd) { struct saved *last = nd->stack + --nd->depth; - struct inode *inode = last->inode; - if (last->cookie && inode->i_op->put_link) - inode->i_op->put_link(inode, last->cookie); + do_delayed_call(&last->done); if (!(nd->flags & LOOKUP_RCU)) path_put(&last->link); } @@ -892,7 +905,7 @@ static inline int may_follow_link(struct nameidata *nd) return 0; /* Allowed if owner and follower match. */ - inode = nd->stack[0].inode; + inode = nd->link_inode; if (uid_eq(current_cred()->fsuid, inode->i_uid)) return 0; @@ -983,7 +996,7 @@ const char *get_link(struct nameidata *nd) { struct saved *last = nd->stack + nd->depth - 1; struct dentry *dentry = last->link.dentry; - struct inode *inode = last->inode; + struct inode *inode = nd->link_inode; int error; const char *res; @@ -1004,36 +1017,27 @@ const char *get_link(struct nameidata *nd) nd->last_type = LAST_BIND; res = inode->i_link; if (!res) { + const char * (*get)(struct dentry *, struct inode *, + struct delayed_call *); + get = inode->i_op->get_link; if (nd->flags & LOOKUP_RCU) { - if (unlikely(unlazy_walk(nd, NULL, 0))) - return ERR_PTR(-ECHILD); + res = get(NULL, inode, &last->done); + if (res == ERR_PTR(-ECHILD)) { + if (unlikely(unlazy_walk(nd, NULL, 0))) + return ERR_PTR(-ECHILD); + res = get(dentry, inode, &last->done); + } + } else { + res = get(dentry, inode, &last->done); } - res = inode->i_op->follow_link(dentry, &last->cookie); - if (IS_ERR_OR_NULL(res)) { - last->cookie = NULL; + if (IS_ERR_OR_NULL(res)) return res; - } } if (*res == '/') { - if (nd->flags & LOOKUP_RCU) { - struct dentry *d; - if (!nd->root.mnt) - set_root_rcu(nd); - nd->path = nd->root; - d = nd->path.dentry; - nd->inode = d->d_inode; - nd->seq = nd->root_seq; - if (unlikely(read_seqcount_retry(&d->d_seq, nd->seq))) - return ERR_PTR(-ECHILD); - } else { - if (!nd->root.mnt) - set_root(nd); - path_put(&nd->path); - nd->path = nd->root; - path_get(&nd->root); - nd->inode = nd->path.dentry->d_inode; - } - nd->flags |= LOOKUP_JUMPED; + if (!nd->root.mnt) + set_root(nd); + if (unlikely(nd_jump_root(nd))) + return ERR_PTR(-ECHILD); while (unlikely(*++res == '/')) ; } @@ -1294,8 +1298,6 @@ static bool __follow_mount_rcu(struct nameidata *nd, struct path *path, static int follow_dotdot_rcu(struct nameidata *nd) { struct inode *inode = nd->inode; - if (!nd->root.mnt) - set_root_rcu(nd); while (1) { if (path_equal(&nd->path, &nd->root)) @@ -1415,9 +1417,6 @@ static void follow_mount(struct path *path) static int follow_dotdot(struct nameidata *nd) { - if (!nd->root.mnt) - set_root(nd); - while(1) { struct dentry *old = nd->path.dentry; @@ -1655,6 +1654,8 @@ static inline int may_lookup(struct nameidata *nd) static inline int handle_dots(struct nameidata *nd, int type) { if (type == LAST_DOTDOT) { + if (!nd->root.mnt) + set_root(nd); if (nd->flags & LOOKUP_RCU) { return follow_dotdot_rcu(nd); } else @@ -1691,8 +1692,8 @@ static int pick_link(struct nameidata *nd, struct path *link, last = nd->stack + nd->depth++; last->link = *link; - last->cookie = NULL; - last->inode = inode; + clear_delayed_call(&last->done); + nd->link_inode = inode; last->seq = seq; return 1; } @@ -2020,18 +2021,19 @@ static const char *path_init(struct nameidata *nd, unsigned flags) } nd->root.mnt = NULL; + nd->path.mnt = NULL; + nd->path.dentry = NULL; nd->m_seq = read_seqbegin(&mount_lock); if (*s == '/') { - if (flags & LOOKUP_RCU) { + if (flags & LOOKUP_RCU) rcu_read_lock(); - set_root_rcu(nd); - nd->seq = nd->root_seq; - } else { - set_root(nd); - path_get(&nd->root); - } - nd->path = nd->root; + set_root(nd); + if (likely(!nd_jump_root(nd))) + return s; + nd->root.mnt = NULL; + rcu_read_unlock(); + return ERR_PTR(-ECHILD); } else if (nd->dfd == AT_FDCWD) { if (flags & LOOKUP_RCU) { struct fs_struct *fs = current->fs; @@ -2042,11 +2044,14 @@ static const char *path_init(struct nameidata *nd, unsigned flags) do { seq = read_seqcount_begin(&fs->seq); nd->path = fs->pwd; + nd->inode = nd->path.dentry->d_inode; nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq); } while (read_seqcount_retry(&fs->seq, seq)); } else { get_fs_pwd(current->fs, &nd->path); + nd->inode = nd->path.dentry->d_inode; } + return s; } else { /* Caller must check execute permissions on the starting path component */ struct fd f = fdget_raw(nd->dfd); @@ -2076,16 +2081,6 @@ static const char *path_init(struct nameidata *nd, unsigned flags) fdput(f); return s; } - - nd->inode = nd->path.dentry->d_inode; - if (!(flags & LOOKUP_RCU)) - return s; - if (likely(!read_seqcount_retry(&nd->path.dentry->d_seq, nd->seq))) - return s; - if (!(nd->flags & LOOKUP_ROOT)) - nd->root.mnt = NULL; - rcu_read_unlock(); - return ERR_PTR(-ECHILD); } static const char *trailing_symlink(struct nameidata *nd) @@ -2278,6 +2273,8 @@ EXPORT_SYMBOL(vfs_path_lookup); * * Note that this routine is purely a helper for filesystem usage and should * not be called by generic code. + * + * The caller must hold base->i_mutex. */ struct dentry *lookup_one_len(const char *name, struct dentry *base, int len) { @@ -2321,6 +2318,75 @@ struct dentry *lookup_one_len(const char *name, struct dentry *base, int len) } EXPORT_SYMBOL(lookup_one_len); +/** + * lookup_one_len_unlocked - filesystem helper to lookup single pathname component + * @name: pathname component to lookup + * @base: base directory to lookup from + * @len: maximum length @len should be interpreted to + * + * Note that this routine is purely a helper for filesystem usage and should + * not be called by generic code. + * + * Unlike lookup_one_len, it should be called without the parent + * i_mutex held, and will take the i_mutex itself if necessary. + */ +struct dentry *lookup_one_len_unlocked(const char *name, + struct dentry *base, int len) +{ + struct qstr this; + unsigned int c; + int err; + struct dentry *ret; + + this.name = name; + this.len = len; + this.hash = full_name_hash(name, len); + if (!len) + return ERR_PTR(-EACCES); + + if (unlikely(name[0] == '.')) { + if (len < 2 || (len == 2 && name[1] == '.')) + return ERR_PTR(-EACCES); + } + + while (len--) { + c = *(const unsigned char *)name++; + if (c == '/' || c == '\0') + return ERR_PTR(-EACCES); + } + /* + * See if the low-level filesystem might want + * to use its own hash.. + */ + if (base->d_flags & DCACHE_OP_HASH) { + int err = base->d_op->d_hash(base, &this); + if (err < 0) + return ERR_PTR(err); + } + + err = inode_permission(base->d_inode, MAY_EXEC); + if (err) + return ERR_PTR(err); + + /* + * __d_lookup() is used to try to get a quick answer and avoid the + * mutex. A false-negative does no harm. + */ + ret = __d_lookup(base, &this); + if (ret && unlikely(ret->d_flags & DCACHE_OP_REVALIDATE)) { + dput(ret); + ret = NULL; + } + if (ret) + return ret; + + mutex_lock(&base->d_inode->i_mutex); + ret = __lookup_hash(&this, base, 0); + mutex_unlock(&base->d_inode->i_mutex); + return ret; +} +EXPORT_SYMBOL(lookup_one_len_unlocked); + int user_path_at_empty(int dfd, const char __user *name, unsigned flags, struct path *path, int *empty) { @@ -2669,10 +2735,6 @@ static int may_open(struct path *path, int acc_mode, int flag) struct inode *inode = dentry->d_inode; int error; - /* O_PATH? */ - if (!acc_mode) - return 0; - if (!inode) return -ENOENT; @@ -2694,7 +2756,7 @@ static int may_open(struct path *path, int acc_mode, int flag) break; } - error = inode_permission(inode, acc_mode); + error = inode_permission(inode, MAY_OPEN | acc_mode); if (error) return error; @@ -2886,7 +2948,7 @@ static int atomic_open(struct nameidata *nd, struct dentry *dentry, if (*opened & FILE_CREATED) { WARN_ON(!(open_flag & O_CREAT)); fsnotify_create(dir, dentry); - acc_mode = MAY_OPEN; + acc_mode = 0; } error = may_open(&file->f_path, acc_mode, open_flag); if (error) @@ -3099,7 +3161,7 @@ retry_lookup: /* Don't check for write permission, don't truncate */ open_flag &= ~O_TRUNC; will_truncate = false; - acc_mode = MAY_OPEN; + acc_mode = 0; path_to_nameidata(&path, nd); goto finish_open_created; } @@ -3183,10 +3245,11 @@ finish_open: got_write = true; } finish_open_created: - error = may_open(&nd->path, acc_mode, open_flag); - if (error) - goto out; - + if (likely(!(open_flag & O_PATH))) { + 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) { @@ -3273,7 +3336,7 @@ static int do_tmpfile(struct nameidata *nd, unsigned flags, goto out2; audit_inode(nd->name, child, 0); /* Don't check for other permissions, the inode was just created */ - error = may_open(&path, MAY_OPEN, op->open_flag); + error = may_open(&path, 0, op->open_flag); if (error) goto out2; file->f_path.mnt = path.mnt; @@ -4495,72 +4558,73 @@ EXPORT_SYMBOL(readlink_copy); /* * A helper for ->readlink(). This should be used *ONLY* for symlinks that - * have ->follow_link() touching nd only in nd_set_link(). Using (or not - * using) it for any given inode is up to filesystem. + * have ->get_link() not calling nd_jump_link(). Using (or not using) it + * for any given inode is up to filesystem. */ int generic_readlink(struct dentry *dentry, char __user *buffer, int buflen) { - void *cookie; + DEFINE_DELAYED_CALL(done); struct inode *inode = d_inode(dentry); const char *link = inode->i_link; int res; if (!link) { - link = inode->i_op->follow_link(dentry, &cookie); + link = inode->i_op->get_link(dentry, inode, &done); if (IS_ERR(link)) return PTR_ERR(link); } res = readlink_copy(buffer, buflen, link); - if (inode->i_op->put_link) - inode->i_op->put_link(inode, cookie); + do_delayed_call(&done); return res; } EXPORT_SYMBOL(generic_readlink); /* get the link contents into pagecache */ -static char *page_getlink(struct dentry * dentry, struct page **ppage) +const char *page_get_link(struct dentry *dentry, struct inode *inode, + struct delayed_call *callback) { char *kaddr; struct page *page; - struct address_space *mapping = dentry->d_inode->i_mapping; - page = read_mapping_page(mapping, 0, NULL); - if (IS_ERR(page)) - return (char*)page; - *ppage = page; - kaddr = kmap(page); - nd_terminate_link(kaddr, dentry->d_inode->i_size, PAGE_SIZE - 1); + struct address_space *mapping = inode->i_mapping; + + if (!dentry) { + page = find_get_page(mapping, 0); + if (!page) + return ERR_PTR(-ECHILD); + if (!PageUptodate(page)) { + put_page(page); + return ERR_PTR(-ECHILD); + } + } else { + page = read_mapping_page(mapping, 0, NULL); + if (IS_ERR(page)) + return (char*)page; + } + set_delayed_call(callback, page_put_link, page); + BUG_ON(mapping_gfp_mask(mapping) & __GFP_HIGHMEM); + kaddr = page_address(page); + nd_terminate_link(kaddr, inode->i_size, PAGE_SIZE - 1); return kaddr; } -int page_readlink(struct dentry *dentry, char __user *buffer, int buflen) -{ - struct page *page = NULL; - int res = readlink_copy(buffer, buflen, page_getlink(dentry, &page)); - if (page) { - kunmap(page); - page_cache_release(page); - } - return res; -} -EXPORT_SYMBOL(page_readlink); +EXPORT_SYMBOL(page_get_link); -const char *page_follow_link_light(struct dentry *dentry, void **cookie) +void page_put_link(void *arg) { - struct page *page = NULL; - char *res = page_getlink(dentry, &page); - if (!IS_ERR(res)) - *cookie = page; - return res; + put_page(arg); } -EXPORT_SYMBOL(page_follow_link_light); +EXPORT_SYMBOL(page_put_link); -void page_put_link(struct inode *unused, void *cookie) +int page_readlink(struct dentry *dentry, char __user *buffer, int buflen) { - struct page *page = cookie; - kunmap(page); - page_cache_release(page); + DEFINE_DELAYED_CALL(done); + int res = readlink_copy(buffer, buflen, + page_get_link(dentry, d_inode(dentry), + &done)); + do_delayed_call(&done); + return res; } -EXPORT_SYMBOL(page_put_link); +EXPORT_SYMBOL(page_readlink); /* * The nofs argument instructs pagecache_write_begin to pass AOP_FLAG_NOFS @@ -4571,7 +4635,6 @@ int __page_symlink(struct inode *inode, const char *symname, int len, int nofs) struct page *page; void *fsdata; int err; - char *kaddr; unsigned int flags = AOP_FLAG_UNINTERRUPTIBLE; if (nofs) flags |= AOP_FLAG_NOFS; @@ -4582,9 +4645,7 @@ retry: if (err) goto fail; - kaddr = kmap_atomic(page); - memcpy(kaddr, symname, len-1); - kunmap_atomic(kaddr); + memcpy(page_address(page), symname, len-1); err = pagecache_write_end(NULL, mapping, 0, len-1, len-1, page, fsdata); @@ -4609,7 +4670,6 @@ EXPORT_SYMBOL(page_symlink); const struct inode_operations page_symlink_inode_operations = { .readlink = generic_readlink, - .follow_link = page_follow_link_light, - .put_link = page_put_link, + .get_link = page_get_link, }; EXPORT_SYMBOL(page_symlink_inode_operations); diff --git a/fs/namespace.c b/fs/namespace.c index 0570729..a830e14 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -1584,6 +1584,14 @@ static inline bool may_mount(void) return ns_capable(current->nsproxy->mnt_ns->user_ns, CAP_SYS_ADMIN); } +static inline bool may_mandlock(void) +{ +#ifndef CONFIG_MANDATORY_FILE_LOCKING + return false; +#endif + return capable(CAP_SYS_ADMIN); +} + /* * Now umount can handle mount points as well as block devices. * This is important for filesystems which use unnamed block devices. @@ -2601,18 +2609,18 @@ static long exact_copy_from_user(void *to, const void __user * from, return n; } -int copy_mount_options(const void __user * data, unsigned long *where) +void *copy_mount_options(const void __user * data) { int i; - unsigned long page; unsigned long size; + char *copy; - *where = 0; if (!data) - return 0; + return NULL; - if (!(page = __get_free_page(GFP_KERNEL))) - return -ENOMEM; + copy = kmalloc(PAGE_SIZE, GFP_KERNEL); + if (!copy) + return ERR_PTR(-ENOMEM); /* We only care that *some* data at the address the user * gave us is valid. Just in case, we'll zero @@ -2623,15 +2631,14 @@ int copy_mount_options(const void __user * data, unsigned long *where) if (size > PAGE_SIZE) size = PAGE_SIZE; - i = size - exact_copy_from_user((void *)page, data, size); + i = size - exact_copy_from_user(copy, data, size); if (!i) { - free_page(page); - return -EFAULT; + kfree(copy); + return ERR_PTR(-EFAULT); } if (i != PAGE_SIZE) - memset((char *)page + i, 0, PAGE_SIZE - i); - *where = page; - return 0; + memset(copy + i, 0, PAGE_SIZE - i); + return copy; } char *copy_mount_string(const void __user *data) @@ -2677,6 +2684,8 @@ long do_mount(const char *dev_name, const char __user *dir_name, type_page, flags, data_page); if (!retval && !may_mount()) retval = -EPERM; + if (!retval && (flags & MS_MANDLOCK) && !may_mandlock()) + retval = -EPERM; if (retval) goto dput_out; @@ -2896,7 +2905,7 @@ SYSCALL_DEFINE5(mount, char __user *, dev_name, char __user *, dir_name, int ret; char *kernel_type; char *kernel_dev; - unsigned long data_page; + void *options; kernel_type = copy_mount_string(type); ret = PTR_ERR(kernel_type); @@ -2908,14 +2917,14 @@ SYSCALL_DEFINE5(mount, char __user *, dev_name, char __user *, dir_name, if (IS_ERR(kernel_dev)) goto out_dev; - ret = copy_mount_options(data, &data_page); - if (ret < 0) + options = copy_mount_options(data); + ret = PTR_ERR(options); + if (IS_ERR(options)) goto out_data; - ret = do_mount(kernel_dev, dir_name, kernel_type, flags, - (void *) data_page); + ret = do_mount(kernel_dev, dir_name, kernel_type, flags, options); - free_page(data_page); + kfree(options); out_data: kfree(kernel_dev); out_dev: @@ -2939,9 +2948,9 @@ bool is_path_reachable(struct mount *mnt, struct dentry *dentry, return &mnt->mnt == root->mnt && is_subdir(dentry, root->dentry); } -int path_is_under(struct path *path1, struct path *path2) +bool path_is_under(struct path *path1, struct path *path2) { - int res; + bool res; read_seqlock_excl(&mount_lock); res = is_path_reachable(real_mount(path1->mnt), path1->dentry, path2); read_sequnlock_excl(&mount_lock); diff --git a/fs/ncpfs/inode.c b/fs/ncpfs/inode.c index 9605a2f..ce1eb3f 100644 --- a/fs/ncpfs/inode.c +++ b/fs/ncpfs/inode.c @@ -244,8 +244,7 @@ static void ncp_set_attr(struct inode *inode, struct ncp_entry_info *nwinfo) #if defined(CONFIG_NCPFS_EXTRAS) || defined(CONFIG_NCPFS_NFS_NS) static const struct inode_operations ncp_symlink_inode_operations = { .readlink = generic_readlink, - .follow_link = page_follow_link_light, - .put_link = page_put_link, + .get_link = page_get_link, .setattr = ncp_notify_change, }; #endif @@ -283,6 +282,7 @@ ncp_iget(struct super_block *sb, struct ncp_entry_info *info) #if defined(CONFIG_NCPFS_EXTRAS) || defined(CONFIG_NCPFS_NFS_NS) } else if (S_ISLNK(inode->i_mode)) { inode->i_op = &ncp_symlink_inode_operations; + inode_nohighmem(inode); inode->i_data.a_ops = &ncp_symlink_aops; #endif } else { diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index c7e8b87..bdb4dc7 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -408,9 +408,10 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr, st inode->i_fop = NULL; inode->i_flags |= S_AUTOMOUNT; } - } else if (S_ISLNK(inode->i_mode)) + } else if (S_ISLNK(inode->i_mode)) { inode->i_op = &nfs_symlink_inode_operations; - else + inode_nohighmem(inode); + } else init_special_inode(inode, inode->i_mode, fattr->rdev); memset(&inode->i_atime, 0, sizeof(inode->i_atime)); @@ -1086,6 +1087,27 @@ static bool nfs_mapping_need_revalidate_inode(struct inode *inode) || NFS_STALE(inode); } +int nfs_revalidate_mapping_rcu(struct inode *inode) +{ + struct nfs_inode *nfsi = NFS_I(inode); + unsigned long *bitlock = &nfsi->flags; + int ret = 0; + + if (IS_SWAPFILE(inode)) + goto out; + if (nfs_mapping_need_revalidate_inode(inode)) { + ret = -ECHILD; + goto out; + } + spin_lock(&inode->i_lock); + if (test_bit(NFS_INO_INVALIDATING, bitlock) || + (nfsi->cache_validity & NFS_INO_INVALID_DATA)) + ret = -ECHILD; + spin_unlock(&inode->i_lock); +out: + return ret; +} + /** * __nfs_revalidate_mapping - Revalidate the pagecache * @inode - pointer to host inode diff --git a/fs/nfs/nfs3acl.c b/fs/nfs/nfs3acl.c index 1ebe2fc..17c0fa1 100644 --- a/fs/nfs/nfs3acl.c +++ b/fs/nfs/nfs3acl.c @@ -284,12 +284,12 @@ nfs3_listxattr(struct dentry *dentry, char *data, size_t size) int error; error = nfs3_list_one_acl(inode, ACL_TYPE_ACCESS, - POSIX_ACL_XATTR_ACCESS, data, size, &result); + XATTR_NAME_POSIX_ACL_ACCESS, data, size, &result); if (error) return error; error = nfs3_list_one_acl(inode, ACL_TYPE_DEFAULT, - POSIX_ACL_XATTR_DEFAULT, data, size, &result); + XATTR_NAME_POSIX_ACL_DEFAULT, data, size, &result); if (error) return error; return result; diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c index db9b5fe..26f9a23 100644 --- a/fs/nfs/nfs4file.c +++ b/fs/nfs/nfs4file.c @@ -195,65 +195,27 @@ static long nfs42_fallocate(struct file *filep, int mode, loff_t offset, loff_t return nfs42_proc_allocate(filep, offset, len); } -static noinline long -nfs42_ioctl_clone(struct file *dst_file, unsigned long srcfd, - u64 src_off, u64 dst_off, u64 count) +static int nfs42_clone_file_range(struct file *src_file, loff_t src_off, + struct file *dst_file, loff_t dst_off, u64 count) { struct inode *dst_inode = file_inode(dst_file); struct nfs_server *server = NFS_SERVER(dst_inode); - struct fd src_file; - struct inode *src_inode; + struct inode *src_inode = file_inode(src_file); unsigned int bs = server->clone_blksize; bool same_inode = false; int ret; - /* dst file must be opened for writing */ - if (!(dst_file->f_mode & FMODE_WRITE)) - return -EINVAL; - - ret = mnt_want_write_file(dst_file); - if (ret) - return ret; - - src_file = fdget(srcfd); - if (!src_file.file) { - ret = -EBADF; - goto out_drop_write; - } - - src_inode = file_inode(src_file.file); - - if (src_inode == dst_inode) - same_inode = true; - - /* src file must be opened for reading */ - if (!(src_file.file->f_mode & FMODE_READ)) - goto out_fput; - - /* src and dst must be regular files */ - ret = -EISDIR; - if (!S_ISREG(src_inode->i_mode) || !S_ISREG(dst_inode->i_mode)) - goto out_fput; - - ret = -EXDEV; - if (src_file.file->f_path.mnt != dst_file->f_path.mnt || - src_inode->i_sb != dst_inode->i_sb) - goto out_fput; - /* check alignment w.r.t. clone_blksize */ ret = -EINVAL; if (bs) { if (!IS_ALIGNED(src_off, bs) || !IS_ALIGNED(dst_off, bs)) - goto out_fput; + goto out; if (!IS_ALIGNED(count, bs) && i_size_read(src_inode) != (src_off + count)) - goto out_fput; + goto out; } - /* verify if ranges are overlapped within the same file */ - if (same_inode) { - if (dst_off + count > src_off && dst_off < src_off + count) - goto out_fput; - } + if (src_inode == dst_inode) + same_inode = true; /* XXX: do we lock at all? what if server needs CB_RECALL_LAYOUT? */ if (same_inode) { @@ -275,7 +237,7 @@ nfs42_ioctl_clone(struct file *dst_file, unsigned long srcfd, if (ret) goto out_unlock; - ret = nfs42_proc_clone(src_file.file, dst_file, src_off, dst_off, count); + ret = nfs42_proc_clone(src_file, dst_file, src_off, dst_off, count); /* truncate inode page cache of the dst range so that future reads can fetch * new data from server */ @@ -292,37 +254,9 @@ out_unlock: mutex_unlock(&dst_inode->i_mutex); mutex_unlock(&src_inode->i_mutex); } -out_fput: - fdput(src_file); -out_drop_write: - mnt_drop_write_file(dst_file); +out: return ret; } - -static long nfs42_ioctl_clone_range(struct file *dst_file, void __user *argp) -{ - struct btrfs_ioctl_clone_range_args args; - - if (copy_from_user(&args, argp, sizeof(args))) - return -EFAULT; - - return nfs42_ioctl_clone(dst_file, args.src_fd, args.src_offset, - args.dest_offset, args.src_length); -} - -long nfs4_ioctl(struct file *file, unsigned int cmd, unsigned long arg) -{ - void __user *argp = (void __user *)arg; - - switch (cmd) { - case BTRFS_IOC_CLONE: - return nfs42_ioctl_clone(file, arg, 0, 0, 0); - case BTRFS_IOC_CLONE_RANGE: - return nfs42_ioctl_clone_range(file, argp); - } - - return -ENOTTY; -} #endif /* CONFIG_NFS_V4_2 */ const struct file_operations nfs4_file_operations = { @@ -342,8 +276,7 @@ const struct file_operations nfs4_file_operations = { #ifdef CONFIG_NFS_V4_2 .llseek = nfs4_file_llseek, .fallocate = nfs42_fallocate, - .unlocked_ioctl = nfs4_ioctl, - .compat_ioctl = nfs4_ioctl, + .clone_file_range = nfs42_clone_file_range, #else .llseek = nfs_file_llseek, #endif diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 8981803..c57d133 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -6253,9 +6253,6 @@ static int nfs4_xattr_set_nfs4_acl(const struct xattr_handler *handler, const void *buf, size_t buflen, int flags) { - if (strcmp(key, "") != 0) - return -EINVAL; - return nfs4_proc_set_acl(d_inode(dentry), buf, buflen); } @@ -6263,32 +6260,15 @@ static int nfs4_xattr_get_nfs4_acl(const struct xattr_handler *handler, struct dentry *dentry, const char *key, void *buf, size_t buflen) { - if (strcmp(key, "") != 0) - return -EINVAL; - return nfs4_proc_get_acl(d_inode(dentry), buf, buflen); } -static size_t nfs4_xattr_list_nfs4_acl(const struct xattr_handler *handler, - struct dentry *dentry, char *list, - size_t list_len, const char *name, - size_t name_len) +static bool nfs4_xattr_list_nfs4_acl(struct dentry *dentry) { - size_t len = sizeof(XATTR_NAME_NFSV4_ACL); - - if (!nfs4_server_supports_acls(NFS_SERVER(d_inode(dentry)))) - return 0; - - if (list && len <= list_len) - memcpy(list, XATTR_NAME_NFSV4_ACL, len); - return len; + return nfs4_server_supports_acls(NFS_SERVER(d_inode(dentry))); } #ifdef CONFIG_NFS_V4_SECURITY_LABEL -static inline int nfs4_server_supports_labels(struct nfs_server *server) -{ - return server->caps & NFS_CAP_SECURITY_LABEL; -} static int nfs4_xattr_set_nfs4_label(const struct xattr_handler *handler, struct dentry *dentry, const char *key, @@ -6310,29 +6290,34 @@ static int nfs4_xattr_get_nfs4_label(const struct xattr_handler *handler, return -EOPNOTSUPP; } -static size_t nfs4_xattr_list_nfs4_label(const struct xattr_handler *handler, - struct dentry *dentry, char *list, - size_t list_len, const char *name, - size_t name_len) +static ssize_t +nfs4_listxattr_nfs4_label(struct inode *inode, char *list, size_t list_len) { - size_t len = 0; + int len = 0; - if (nfs_server_capable(d_inode(dentry), NFS_CAP_SECURITY_LABEL)) { - len = security_inode_listsecurity(d_inode(dentry), NULL, 0); - if (list && len <= list_len) - security_inode_listsecurity(d_inode(dentry), list, len); + if (nfs_server_capable(inode, NFS_CAP_SECURITY_LABEL)) { + len = security_inode_listsecurity(inode, list, list_len); + if (list_len && len > list_len) + return -ERANGE; } return len; } static const struct xattr_handler nfs4_xattr_nfs4_label_handler = { .prefix = XATTR_SECURITY_PREFIX, - .list = nfs4_xattr_list_nfs4_label, .get = nfs4_xattr_get_nfs4_label, .set = nfs4_xattr_set_nfs4_label, }; -#endif +#else + +static ssize_t +nfs4_listxattr_nfs4_label(struct inode *inode, char *list, size_t list_len) +{ + return 0; +} + +#endif /* * nfs_fhget will use either the mounted_on_fileid or the fileid @@ -8749,6 +8734,24 @@ const struct nfs4_minor_version_ops *nfs_v4_minor_ops[] = { #endif }; +ssize_t nfs4_listxattr(struct dentry *dentry, char *list, size_t size) +{ + ssize_t error, error2; + + error = generic_listxattr(dentry, list, size); + if (error < 0) + return error; + if (list) { + list += error; + size -= error; + } + + error2 = nfs4_listxattr_nfs4_label(d_inode(dentry), list, size); + if (error2 < 0) + return error2; + return error + error2; +} + static const struct inode_operations nfs4_dir_inode_operations = { .create = nfs_create, .lookup = nfs_lookup, @@ -8765,7 +8768,7 @@ static const struct inode_operations nfs4_dir_inode_operations = { .setattr = nfs_setattr, .getxattr = generic_getxattr, .setxattr = generic_setxattr, - .listxattr = generic_listxattr, + .listxattr = nfs4_listxattr, .removexattr = generic_removexattr, }; @@ -8775,7 +8778,7 @@ static const struct inode_operations nfs4_file_inode_operations = { .setattr = nfs_setattr, .getxattr = generic_getxattr, .setxattr = generic_setxattr, - .listxattr = generic_listxattr, + .listxattr = nfs4_listxattr, .removexattr = generic_removexattr, }; @@ -8834,7 +8837,7 @@ const struct nfs_rpc_ops nfs_v4_clientops = { }; static const struct xattr_handler nfs4_xattr_nfs4_acl_handler = { - .prefix = XATTR_NAME_NFSV4_ACL, + .name = XATTR_NAME_NFSV4_ACL, .list = nfs4_xattr_list_nfs4_acl, .get = nfs4_xattr_get_nfs4_acl, .set = nfs4_xattr_set_nfs4_acl, diff --git a/fs/nfs/symlink.c b/fs/nfs/symlink.c index b6de433..4fe3eea 100644 --- a/fs/nfs/symlink.c +++ b/fs/nfs/symlink.c @@ -42,21 +42,35 @@ error: return -EIO; } -static const char *nfs_follow_link(struct dentry *dentry, void **cookie) +static const char *nfs_get_link(struct dentry *dentry, + struct inode *inode, + struct delayed_call *done) { - struct inode *inode = d_inode(dentry); struct page *page; void *err; - err = ERR_PTR(nfs_revalidate_mapping(inode, inode->i_mapping)); - if (err) - return err; - page = read_cache_page(&inode->i_data, 0, - (filler_t *)nfs_symlink_filler, inode); - if (IS_ERR(page)) - return ERR_CAST(page); - *cookie = page; - return kmap(page); + if (!dentry) { + err = ERR_PTR(nfs_revalidate_mapping_rcu(inode)); + if (err) + return err; + page = find_get_page(inode->i_mapping, 0); + if (!page) + return ERR_PTR(-ECHILD); + if (!PageUptodate(page)) { + put_page(page); + return ERR_PTR(-ECHILD); + } + } else { + err = ERR_PTR(nfs_revalidate_mapping(inode, inode->i_mapping)); + if (err) + return err; + page = read_cache_page(&inode->i_data, 0, + (filler_t *)nfs_symlink_filler, inode); + if (IS_ERR(page)) + return ERR_CAST(page); + } + set_delayed_call(done, page_put_link, page); + return page_address(page); } /* @@ -64,8 +78,7 @@ static const char *nfs_follow_link(struct dentry *dentry, void **cookie) */ const struct inode_operations nfs_symlink_inode_operations = { .readlink = generic_readlink, - .follow_link = nfs_follow_link, - .put_link = page_put_link, + .get_link = nfs_get_link, .getattr = nfs_getattr, .setattr = nfs_setattr, }; diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c index 00575d7..2246454 100644 --- a/fs/nfsd/nfs3xdr.c +++ b/fs/nfsd/nfs3xdr.c @@ -823,7 +823,7 @@ compose_entry_fh(struct nfsd3_readdirres *cd, struct svc_fh *fhp, } else dchild = dget(dparent); } else - dchild = lookup_one_len(name, dparent, namlen); + dchild = lookup_one_len_unlocked(name, dparent, namlen); if (IS_ERR(dchild)) return rv; if (d_mountpoint(dchild)) diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index a9f096c..819ad81 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -774,8 +774,9 @@ nfsd4_read(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, clear_bit(RQ_SPLICE_OK, &rqstp->rq_flags); /* check stateid */ - status = nfs4_preprocess_stateid_op(rqstp, cstate, &read->rd_stateid, - RD_STATE, &read->rd_filp, &read->rd_tmp_file); + status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh, + &read->rd_stateid, RD_STATE, + &read->rd_filp, &read->rd_tmp_file); if (status) { dprintk("NFSD: nfsd4_read: couldn't process stateid!\n"); goto out; @@ -921,7 +922,8 @@ nfsd4_setattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, if (setattr->sa_iattr.ia_valid & ATTR_SIZE) { status = nfs4_preprocess_stateid_op(rqstp, cstate, - &setattr->sa_stateid, WR_STATE, NULL, NULL); + &cstate->current_fh, &setattr->sa_stateid, + WR_STATE, NULL, NULL); if (status) { dprintk("NFSD: nfsd4_setattr: couldn't process stateid!\n"); return status; @@ -985,8 +987,8 @@ nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, if (write->wr_offset >= OFFSET_MAX) return nfserr_inval; - status = nfs4_preprocess_stateid_op(rqstp, cstate, stateid, WR_STATE, - &filp, NULL); + status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh, + stateid, WR_STATE, &filp, NULL); if (status) { dprintk("NFSD: nfsd4_write: couldn't process stateid!\n"); return status; @@ -1010,13 +1012,54 @@ nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, } static __be32 +nfsd4_clone(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, + struct nfsd4_clone *clone) +{ + struct file *src, *dst; + __be32 status; + + status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->save_fh, + &clone->cl_src_stateid, RD_STATE, + &src, NULL); + if (status) { + dprintk("NFSD: %s: couldn't process src stateid!\n", __func__); + goto out; + } + + status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh, + &clone->cl_dst_stateid, WR_STATE, + &dst, NULL); + if (status) { + dprintk("NFSD: %s: couldn't process dst stateid!\n", __func__); + goto out_put_src; + } + + /* fix up for NFS-specific error code */ + if (!S_ISREG(file_inode(src)->i_mode) || + !S_ISREG(file_inode(dst)->i_mode)) { + status = nfserr_wrong_type; + goto out_put_dst; + } + + status = nfsd4_clone_file_range(src, clone->cl_src_pos, + dst, clone->cl_dst_pos, clone->cl_count); + +out_put_dst: + fput(dst); +out_put_src: + fput(src); +out: + return status; +} + +static __be32 nfsd4_fallocate(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfsd4_fallocate *fallocate, int flags) { __be32 status = nfserr_notsupp; struct file *file; - status = nfs4_preprocess_stateid_op(rqstp, cstate, + status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh, &fallocate->falloc_stateid, WR_STATE, &file, NULL); if (status != nfs_ok) { @@ -1055,7 +1098,7 @@ nfsd4_seek(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, __be32 status; struct file *file; - status = nfs4_preprocess_stateid_op(rqstp, cstate, + status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh, &seek->seek_stateid, RD_STATE, &file, NULL); if (status) { @@ -2279,6 +2322,12 @@ static struct nfsd4_operation nfsd4_ops[] = { .op_name = "OP_DEALLOCATE", .op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize, }, + [OP_CLONE] = { + .op_func = (nfsd4op_func)nfsd4_clone, + .op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME, + .op_name = "OP_CLONE", + .op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize, + }, [OP_SEEK] = { .op_func = (nfsd4op_func)nfsd4_seek, .op_name = "OP_SEEK", diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 6b800b5b..df5dba6 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -4797,10 +4797,9 @@ nfs4_check_file(struct svc_rqst *rqstp, struct svc_fh *fhp, struct nfs4_stid *s, */ __be32 nfs4_preprocess_stateid_op(struct svc_rqst *rqstp, - struct nfsd4_compound_state *cstate, stateid_t *stateid, - int flags, struct file **filpp, bool *tmp_file) + struct nfsd4_compound_state *cstate, struct svc_fh *fhp, + stateid_t *stateid, int flags, struct file **filpp, bool *tmp_file) { - struct svc_fh *fhp = &cstate->current_fh; struct inode *ino = d_inode(fhp->fh_dentry); struct net *net = SVC_NET(rqstp); struct nfsd_net *nn = net_generic(net, nfsd_net_id); diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 51c9e9c..d6ef095 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -1675,6 +1675,25 @@ nfsd4_decode_fallocate(struct nfsd4_compoundargs *argp, } static __be32 +nfsd4_decode_clone(struct nfsd4_compoundargs *argp, struct nfsd4_clone *clone) +{ + DECODE_HEAD; + + status = nfsd4_decode_stateid(argp, &clone->cl_src_stateid); + if (status) + return status; + status = nfsd4_decode_stateid(argp, &clone->cl_dst_stateid); + if (status) + return status; + + READ_BUF(8 + 8 + 8); + p = xdr_decode_hyper(p, &clone->cl_src_pos); + p = xdr_decode_hyper(p, &clone->cl_dst_pos); + p = xdr_decode_hyper(p, &clone->cl_count); + DECODE_TAIL; +} + +static __be32 nfsd4_decode_seek(struct nfsd4_compoundargs *argp, struct nfsd4_seek *seek) { DECODE_HEAD; @@ -1785,6 +1804,7 @@ static nfsd4_dec nfsd4_dec_ops[] = { [OP_READ_PLUS] = (nfsd4_dec)nfsd4_decode_notsupp, [OP_SEEK] = (nfsd4_dec)nfsd4_decode_seek, [OP_WRITE_SAME] = (nfsd4_dec)nfsd4_decode_notsupp, + [OP_CLONE] = (nfsd4_dec)nfsd4_decode_clone, }; static inline bool @@ -2838,14 +2858,14 @@ nfsd4_encode_dirent_fattr(struct xdr_stream *xdr, struct nfsd4_readdir *cd, __be32 nfserr; int ignore_crossmnt = 0; - dentry = lookup_one_len(name, cd->rd_fhp->fh_dentry, namlen); + dentry = lookup_one_len_unlocked(name, cd->rd_fhp->fh_dentry, namlen); if (IS_ERR(dentry)) return nfserrno(PTR_ERR(dentry)); if (d_really_is_negative(dentry)) { /* - * nfsd_buffered_readdir drops the i_mutex between - * readdir and calling this callback, leaving a window - * where this directory entry could have gone away. + * we're not holding the i_mutex here, so there's + * a window where this directory entry could have gone + * away. */ dput(dentry); return nfserr_noent; @@ -4292,6 +4312,7 @@ static nfsd4_enc nfsd4_enc_ops[] = { [OP_READ_PLUS] = (nfsd4_enc)nfsd4_encode_noop, [OP_SEEK] = (nfsd4_enc)nfsd4_encode_seek, [OP_WRITE_SAME] = (nfsd4_enc)nfsd4_encode_noop, + [OP_CLONE] = (nfsd4_enc)nfsd4_encode_noop, }; /* diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h index 77fdf4d..99432b7 100644 --- a/fs/nfsd/state.h +++ b/fs/nfsd/state.h @@ -578,8 +578,8 @@ struct nfsd4_compound_state; struct nfsd_net; extern __be32 nfs4_preprocess_stateid_op(struct svc_rqst *rqstp, - struct nfsd4_compound_state *cstate, stateid_t *stateid, - int flags, struct file **filp, bool *tmp_file); + struct nfsd4_compound_state *cstate, struct svc_fh *fhp, + stateid_t *stateid, int flags, struct file **filp, bool *tmp_file); __be32 nfsd4_lookup_stateid(struct nfsd4_compound_state *cstate, stateid_t *stateid, unsigned char typemask, struct nfs4_stid **s, struct nfsd_net *nn); diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 994d66f..d41c149 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -36,6 +36,7 @@ #endif /* CONFIG_NFSD_V3 */ #ifdef CONFIG_NFSD_V4 +#include "../internal.h" #include "acl.h" #include "idmap.h" #endif /* CONFIG_NFSD_V4 */ @@ -217,10 +218,16 @@ nfsd_lookup_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp, host_err = PTR_ERR(dentry); if (IS_ERR(dentry)) goto out_nfserr; - /* - * check if we have crossed a mount point ... - */ if (nfsd_mountpoint(dentry, exp)) { + /* + * We don't need the i_mutex after all. It's + * still possible we could open this (regular + * files can be mountpoints too), but the + * i_mutex is just there to prevent renames of + * something that we might be about to delegate, + * and a mountpoint won't be renamed: + */ + fh_unlock(fhp); if ((host_err = nfsd_cross_mnt(rqstp, &dentry, &exp))) { dput(dentry); goto out_nfserr; @@ -498,6 +505,13 @@ __be32 nfsd4_set_nfs4_label(struct svc_rqst *rqstp, struct svc_fh *fhp, } #endif +__be32 nfsd4_clone_file_range(struct file *src, u64 src_pos, struct file *dst, + u64 dst_pos, u64 count) +{ + return nfserrno(vfs_clone_file_range(src, src_pos, dst, dst_pos, + count)); +} + __be32 nfsd4_vfs_fallocate(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file, loff_t offset, loff_t len, int flags) @@ -1809,7 +1823,6 @@ static __be32 nfsd_buffered_readdir(struct file *file, nfsd_filldir_t func, offset = *offsetp; while (1) { - struct inode *dir_inode = file_inode(file); unsigned int reclen; cdp->err = nfserr_eof; /* will be cleared on successful read */ @@ -1828,15 +1841,6 @@ static __be32 nfsd_buffered_readdir(struct file *file, nfsd_filldir_t func, if (!size) break; - /* - * Various filldir functions may end up calling back into - * lookup_one_len() and the file system's ->lookup() method. - * These expect i_mutex to be held, as it would within readdir. - */ - host_err = mutex_lock_killable(&dir_inode->i_mutex); - if (host_err) - break; - de = (struct buffered_dirent *)buf.dirent; while (size > 0) { offset = de->offset; @@ -1853,7 +1857,6 @@ static __be32 nfsd_buffered_readdir(struct file *file, nfsd_filldir_t func, size -= reclen; de = (struct buffered_dirent *)((char *)de + reclen); } - mutex_unlock(&dir_inode->i_mutex); if (size > 0) /* We bailed out early */ break; diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h index fcfc48c..c11ba31 100644 --- a/fs/nfsd/vfs.h +++ b/fs/nfsd/vfs.h @@ -56,6 +56,8 @@ __be32 nfsd4_set_nfs4_label(struct svc_rqst *, struct svc_fh *, struct xdr_netobj *); __be32 nfsd4_vfs_fallocate(struct svc_rqst *, struct svc_fh *, struct file *, loff_t, loff_t, int); +__be32 nfsd4_clone_file_range(struct file *, u64, struct file *, + u64, u64); #endif /* CONFIG_NFSD_V4 */ __be32 nfsd_create(struct svc_rqst *, struct svc_fh *, char *name, int len, struct iattr *attrs, diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h index ce7362c..d955481 100644 --- a/fs/nfsd/xdr4.h +++ b/fs/nfsd/xdr4.h @@ -491,6 +491,15 @@ struct nfsd4_fallocate { u64 falloc_length; }; +struct nfsd4_clone { + /* request */ + stateid_t cl_src_stateid; + stateid_t cl_dst_stateid; + u64 cl_src_pos; + u64 cl_dst_pos; + u64 cl_count; +}; + struct nfsd4_seek { /* request */ stateid_t seek_stateid; @@ -555,6 +564,7 @@ struct nfsd4_op { /* NFSv4.2 */ struct nfsd4_fallocate allocate; struct nfsd4_fallocate deallocate; + struct nfsd4_clone clone; struct nfsd4_seek seek; } u; struct nfs4_replay * replay; diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index ac2f649..10b2252 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -510,6 +510,7 @@ static int __nilfs_read_inode(struct super_block *sb, inode->i_mapping->a_ops = &nilfs_aops; } else if (S_ISLNK(inode->i_mode)) { inode->i_op = &nilfs_symlink_inode_operations; + inode_nohighmem(inode); inode->i_mapping->a_ops = &nilfs_aops; } else { inode->i_op = &nilfs_special_inode_operations; diff --git a/fs/nilfs2/namei.c b/fs/nilfs2/namei.c index c9a1a49..7ccdb96 100644 --- a/fs/nilfs2/namei.c +++ b/fs/nilfs2/namei.c @@ -161,6 +161,7 @@ static int nilfs_symlink(struct inode *dir, struct dentry *dentry, /* slow symlink */ inode->i_op = &nilfs_symlink_inode_operations; + inode_nohighmem(inode); inode->i_mapping->a_ops = &nilfs_aops; err = page_symlink(inode, symname, l); if (err) @@ -568,8 +569,7 @@ const struct inode_operations nilfs_special_inode_operations = { const struct inode_operations nilfs_symlink_inode_operations = { .readlink = generic_readlink, - .follow_link = page_follow_link_light, - .put_link = page_put_link, + .get_link = page_get_link, .permission = nilfs_permission, }; diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c index 354013e..c734384 100644 --- a/fs/nilfs2/super.c +++ b/fs/nilfs2/super.c @@ -1316,13 +1316,11 @@ nilfs_mount(struct file_system_type *fs_type, int flags, } if (!s->s_root) { - char b[BDEVNAME_SIZE]; - - s_new = true; + s_new = true; /* New superblock instance created */ s->s_mode = mode; - strlcpy(s->s_id, bdevname(sd.bdev, b), sizeof(s->s_id)); + snprintf(s->s_id, sizeof(s->s_id), "%pg", sd.bdev); sb_set_blocksize(s, block_size(sd.bdev)); err = nilfs_fill_super(s, data, flags & MS_SILENT ? 1 : 0); diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c index 8f87e05..97a563b 100644 --- a/fs/ocfs2/inode.c +++ b/fs/ocfs2/inode.c @@ -361,6 +361,7 @@ void ocfs2_populate_inode(struct inode *inode, struct ocfs2_dinode *fe, break; case S_IFLNK: inode->i_op = &ocfs2_symlink_inode_operations; + inode_nohighmem(inode); i_size_write(inode, le64_to_cpu(fe->i_size)); break; default: diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c index 3123408..afb81ea 100644 --- a/fs/ocfs2/namei.c +++ b/fs/ocfs2/namei.c @@ -1958,6 +1958,7 @@ static int ocfs2_symlink(struct inode *dir, inode->i_rdev = 0; newsize = l - 1; inode->i_op = &ocfs2_symlink_inode_operations; + inode_nohighmem(inode); if (l > ocfs2_fast_symlink_chars(sb)) { u32 offset = 0; diff --git a/fs/ocfs2/symlink.c b/fs/ocfs2/symlink.c index 66edce7..6c2a3e3 100644 --- a/fs/ocfs2/symlink.c +++ b/fs/ocfs2/symlink.c @@ -88,8 +88,7 @@ const struct address_space_operations ocfs2_fast_symlink_aops = { const struct inode_operations ocfs2_symlink_inode_operations = { .readlink = generic_readlink, - .follow_link = page_follow_link_light, - .put_link = page_put_link, + .get_link = page_get_link, .getattr = ocfs2_getattr, .setattr = ocfs2_setattr, .setxattr = generic_setxattr, diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c index e9164f0..f0e241f 100644 --- a/fs/ocfs2/xattr.c +++ b/fs/ocfs2/xattr.c @@ -544,8 +544,7 @@ static inline const char *ocfs2_xattr_prefix(int name_index) if (name_index > 0 && name_index < OCFS2_XATTR_MAX) handler = ocfs2_xattr_handler_map[name_index]; - - return handler ? handler->prefix : NULL; + return handler ? xattr_prefix(handler) : NULL; } static u32 ocfs2_xattr_name_hash(struct inode *inode, @@ -884,14 +883,39 @@ static int ocfs2_xattr_value_truncate(struct inode *inode, return ret; } -static int ocfs2_xattr_list_entry(char *buffer, size_t size, - size_t *result, const char *prefix, +static int ocfs2_xattr_list_entry(struct super_block *sb, + char *buffer, size_t size, + size_t *result, int type, const char *name, int name_len) { char *p = buffer + *result; - int prefix_len = strlen(prefix); - int total_len = prefix_len + name_len + 1; + const char *prefix; + int prefix_len; + int total_len; + switch(type) { + case OCFS2_XATTR_INDEX_USER: + if (OCFS2_SB(sb)->s_mount_opt & OCFS2_MOUNT_NOUSERXATTR) + return 0; + break; + + case OCFS2_XATTR_INDEX_POSIX_ACL_ACCESS: + case OCFS2_XATTR_INDEX_POSIX_ACL_DEFAULT: + if (!(sb->s_flags & MS_POSIXACL)) + return 0; + break; + + case OCFS2_XATTR_INDEX_TRUSTED: + if (!capable(CAP_SYS_ADMIN)) + return 0; + break; + } + + prefix = ocfs2_xattr_prefix(type); + if (!prefix) + return 0; + prefix_len = strlen(prefix); + total_len = prefix_len + name_len + 1; *result += total_len; /* we are just looking for how big our buffer needs to be */ @@ -914,23 +938,20 @@ static int ocfs2_xattr_list_entries(struct inode *inode, { size_t result = 0; int i, type, ret; - const char *prefix, *name; + const char *name; for (i = 0 ; i < le16_to_cpu(header->xh_count); i++) { struct ocfs2_xattr_entry *entry = &header->xh_entries[i]; type = ocfs2_xattr_get_type(entry); - prefix = ocfs2_xattr_prefix(type); - - if (prefix) { - name = (const char *)header + - le16_to_cpu(entry->xe_name_offset); + name = (const char *)header + + le16_to_cpu(entry->xe_name_offset); - ret = ocfs2_xattr_list_entry(buffer, buffer_size, - &result, prefix, name, - entry->xe_name_len); - if (ret) - return ret; - } + ret = ocfs2_xattr_list_entry(inode->i_sb, + buffer, buffer_size, + &result, type, name, + entry->xe_name_len); + if (ret) + return ret; } return result; @@ -4033,32 +4054,30 @@ static int ocfs2_list_xattr_bucket(struct inode *inode, int ret = 0, type; struct ocfs2_xattr_tree_list *xl = (struct ocfs2_xattr_tree_list *)para; int i, block_off, new_offset; - const char *prefix, *name; + const char *name; for (i = 0 ; i < le16_to_cpu(bucket_xh(bucket)->xh_count); i++) { struct ocfs2_xattr_entry *entry = &bucket_xh(bucket)->xh_entries[i]; type = ocfs2_xattr_get_type(entry); - prefix = ocfs2_xattr_prefix(type); - if (prefix) { - ret = ocfs2_xattr_bucket_get_name_value(inode->i_sb, - bucket_xh(bucket), - i, - &block_off, - &new_offset); - if (ret) - break; + ret = ocfs2_xattr_bucket_get_name_value(inode->i_sb, + bucket_xh(bucket), + i, + &block_off, + &new_offset); + if (ret) + break; - name = (const char *)bucket_block(bucket, block_off) + - new_offset; - ret = ocfs2_xattr_list_entry(xl->buffer, - xl->buffer_size, - &xl->result, - prefix, name, - entry->xe_name_len); - if (ret) - break; - } + name = (const char *)bucket_block(bucket, block_off) + + new_offset; + ret = ocfs2_xattr_list_entry(inode->i_sb, + xl->buffer, + xl->buffer_size, + &xl->result, + type, name, + entry->xe_name_len); + if (ret) + break; } return ret; @@ -7226,31 +7245,14 @@ int ocfs2_init_security_and_acl(struct inode *dir, leave: return ret; } + /* * 'security' attributes support */ -static size_t ocfs2_xattr_security_list(const struct xattr_handler *handler, - struct dentry *dentry, char *list, - size_t list_size, const char *name, - size_t name_len) -{ - const size_t prefix_len = XATTR_SECURITY_PREFIX_LEN; - const size_t total_len = prefix_len + name_len + 1; - - if (list && total_len <= list_size) { - memcpy(list, XATTR_SECURITY_PREFIX, prefix_len); - memcpy(list + prefix_len, name, name_len); - list[prefix_len + name_len] = '\0'; - } - return total_len; -} - static int ocfs2_xattr_security_get(const struct xattr_handler *handler, struct dentry *dentry, const char *name, void *buffer, size_t size) { - if (strcmp(name, "") == 0) - return -EINVAL; return ocfs2_xattr_get(d_inode(dentry), OCFS2_XATTR_INDEX_SECURITY, name, buffer, size); } @@ -7259,9 +7261,6 @@ static int ocfs2_xattr_security_set(const struct xattr_handler *handler, struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { - if (strcmp(name, "") == 0) - return -EINVAL; - return ocfs2_xattr_set(d_inode(dentry), OCFS2_XATTR_INDEX_SECURITY, name, value, size, flags); } @@ -7314,7 +7313,6 @@ int ocfs2_init_security_set(handle_t *handle, const struct xattr_handler ocfs2_xattr_security_handler = { .prefix = XATTR_SECURITY_PREFIX, - .list = ocfs2_xattr_security_list, .get = ocfs2_xattr_security_get, .set = ocfs2_xattr_security_set, }; @@ -7322,31 +7320,10 @@ const struct xattr_handler ocfs2_xattr_security_handler = { /* * 'trusted' attributes support */ -static size_t ocfs2_xattr_trusted_list(const struct xattr_handler *handler, - struct dentry *dentry, char *list, - size_t list_size, const char *name, - size_t name_len) -{ - const size_t prefix_len = XATTR_TRUSTED_PREFIX_LEN; - const size_t total_len = prefix_len + name_len + 1; - - if (!capable(CAP_SYS_ADMIN)) - return 0; - - if (list && total_len <= list_size) { - memcpy(list, XATTR_TRUSTED_PREFIX, prefix_len); - memcpy(list + prefix_len, name, name_len); - list[prefix_len + name_len] = '\0'; - } - return total_len; -} - static int ocfs2_xattr_trusted_get(const struct xattr_handler *handler, struct dentry *dentry, const char *name, void *buffer, size_t size) { - if (strcmp(name, "") == 0) - return -EINVAL; return ocfs2_xattr_get(d_inode(dentry), OCFS2_XATTR_INDEX_TRUSTED, name, buffer, size); } @@ -7355,16 +7332,12 @@ static int ocfs2_xattr_trusted_set(const struct xattr_handler *handler, struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { - if (strcmp(name, "") == 0) - return -EINVAL; - return ocfs2_xattr_set(d_inode(dentry), OCFS2_XATTR_INDEX_TRUSTED, name, value, size, flags); } const struct xattr_handler ocfs2_xattr_trusted_handler = { .prefix = XATTR_TRUSTED_PREFIX, - .list = ocfs2_xattr_trusted_list, .get = ocfs2_xattr_trusted_get, .set = ocfs2_xattr_trusted_set, }; @@ -7372,34 +7345,12 @@ const struct xattr_handler ocfs2_xattr_trusted_handler = { /* * 'user' attributes support */ -static size_t ocfs2_xattr_user_list(const struct xattr_handler *handler, - struct dentry *dentry, char *list, - size_t list_size, const char *name, - size_t name_len) -{ - const size_t prefix_len = XATTR_USER_PREFIX_LEN; - const size_t total_len = prefix_len + name_len + 1; - struct ocfs2_super *osb = OCFS2_SB(dentry->d_sb); - - if (osb->s_mount_opt & OCFS2_MOUNT_NOUSERXATTR) - return 0; - - if (list && total_len <= list_size) { - memcpy(list, XATTR_USER_PREFIX, prefix_len); - memcpy(list + prefix_len, name, name_len); - list[prefix_len + name_len] = '\0'; - } - return total_len; -} - static int ocfs2_xattr_user_get(const struct xattr_handler *handler, struct dentry *dentry, const char *name, void *buffer, size_t size) { struct ocfs2_super *osb = OCFS2_SB(dentry->d_sb); - if (strcmp(name, "") == 0) - return -EINVAL; if (osb->s_mount_opt & OCFS2_MOUNT_NOUSERXATTR) return -EOPNOTSUPP; return ocfs2_xattr_get(d_inode(dentry), OCFS2_XATTR_INDEX_USER, name, @@ -7412,8 +7363,6 @@ static int ocfs2_xattr_user_set(const struct xattr_handler *handler, { struct ocfs2_super *osb = OCFS2_SB(dentry->d_sb); - if (strcmp(name, "") == 0) - return -EINVAL; if (osb->s_mount_opt & OCFS2_MOUNT_NOUSERXATTR) return -EOPNOTSUPP; @@ -7423,7 +7372,6 @@ static int ocfs2_xattr_user_set(const struct xattr_handler *handler, const struct xattr_handler ocfs2_xattr_user_handler = { .prefix = XATTR_USER_PREFIX, - .list = ocfs2_xattr_user_list, .get = ocfs2_xattr_user_get, .set = ocfs2_xattr_user_set, }; @@ -887,7 +887,7 @@ EXPORT_SYMBOL(dentry_open); static inline int build_open_flags(int flags, umode_t mode, struct open_flags *op) { int lookup_flags = 0; - int acc_mode; + int acc_mode = ACC_MODE(flags); if (flags & (O_CREAT | __O_TMPFILE)) op->mode = (mode & S_IALLUGO) | S_IFREG; @@ -909,7 +909,6 @@ static inline int build_open_flags(int flags, umode_t mode, struct open_flags *o if (flags & __O_TMPFILE) { if ((flags & O_TMPFILE_MASK) != O_TMPFILE) return -EINVAL; - acc_mode = MAY_OPEN | ACC_MODE(flags); if (!(acc_mode & MAY_WRITE)) return -EINVAL; } else if (flags & O_PATH) { @@ -919,8 +918,6 @@ static inline int build_open_flags(int flags, umode_t mode, struct open_flags *o */ flags &= O_DIRECTORY | O_NOFOLLOW | O_PATH; acc_mode = 0; - } else { - acc_mode = MAY_OPEN | ACC_MODE(flags); } op->open_flag = flags; diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index 4060ffd..964a60f 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -131,57 +131,23 @@ out_dput: return err; } - -struct ovl_link_data { - struct dentry *realdentry; - void *cookie; -}; - -static const char *ovl_follow_link(struct dentry *dentry, void **cookie) +static const char *ovl_get_link(struct dentry *dentry, + struct inode *inode, + struct delayed_call *done) { struct dentry *realdentry; struct inode *realinode; - struct ovl_link_data *data = NULL; - const char *ret; + + if (!dentry) + return ERR_PTR(-ECHILD); realdentry = ovl_dentry_real(dentry); realinode = realdentry->d_inode; - if (WARN_ON(!realinode->i_op->follow_link)) + if (WARN_ON(!realinode->i_op->get_link)) return ERR_PTR(-EPERM); - if (realinode->i_op->put_link) { - data = kmalloc(sizeof(struct ovl_link_data), GFP_KERNEL); - if (!data) - return ERR_PTR(-ENOMEM); - data->realdentry = realdentry; - } - - ret = realinode->i_op->follow_link(realdentry, cookie); - if (IS_ERR_OR_NULL(ret)) { - kfree(data); - return ret; - } - - if (data) - data->cookie = *cookie; - - *cookie = data; - - return ret; -} - -static void ovl_put_link(struct inode *unused, void *c) -{ - struct inode *realinode; - struct ovl_link_data *data = c; - - if (!data) - return; - - realinode = data->realdentry->d_inode; - realinode->i_op->put_link(realinode, data->cookie); - kfree(data); + return realinode->i_op->get_link(realdentry, realinode, done); } static int ovl_readlink(struct dentry *dentry, char __user *buf, int bufsiz) @@ -378,8 +344,7 @@ static const struct inode_operations ovl_file_inode_operations = { static const struct inode_operations ovl_symlink_inode_operations = { .setattr = ovl_setattr, - .follow_link = ovl_follow_link, - .put_link = ovl_put_link, + .get_link = ovl_get_link, .readlink = ovl_readlink, .getattr = ovl_getattr, .setxattr = ovl_setxattr, diff --git a/fs/posix_acl.c b/fs/posix_acl.c index 4adde1e..711dd51 100644 --- a/fs/posix_acl.c +++ b/fs/posix_acl.c @@ -769,8 +769,6 @@ posix_acl_xattr_get(const struct xattr_handler *handler, struct posix_acl *acl; int error; - if (strcmp(name, "") != 0) - return -EINVAL; if (!IS_POSIXACL(d_backing_inode(dentry))) return -EOPNOTSUPP; if (d_is_symlink(dentry)) @@ -797,8 +795,6 @@ posix_acl_xattr_set(const struct xattr_handler *handler, struct posix_acl *acl = NULL; int ret; - if (strcmp(name, "") != 0) - return -EINVAL; if (!IS_POSIXACL(inode)) return -EOPNOTSUPP; if (!inode->i_op->set_acl) @@ -827,25 +823,14 @@ out: return ret; } -static size_t -posix_acl_xattr_list(const struct xattr_handler *handler, - struct dentry *dentry, char *list, size_t list_size, - const char *name, size_t name_len) +static bool +posix_acl_xattr_list(struct dentry *dentry) { - const char *xname = handler->prefix; - size_t size; - - if (!IS_POSIXACL(d_backing_inode(dentry))) - return 0; - - size = strlen(xname) + 1; - if (list && size <= list_size) - memcpy(list, xname, size); - return size; + return IS_POSIXACL(d_backing_inode(dentry)); } const struct xattr_handler posix_acl_access_xattr_handler = { - .prefix = POSIX_ACL_XATTR_ACCESS, + .name = XATTR_NAME_POSIX_ACL_ACCESS, .flags = ACL_TYPE_ACCESS, .list = posix_acl_xattr_list, .get = posix_acl_xattr_get, @@ -854,7 +839,7 @@ const struct xattr_handler posix_acl_access_xattr_handler = { EXPORT_SYMBOL_GPL(posix_acl_access_xattr_handler); const struct xattr_handler posix_acl_default_xattr_handler = { - .prefix = POSIX_ACL_XATTR_DEFAULT, + .name = XATTR_NAME_POSIX_ACL_DEFAULT, .flags = ACL_TYPE_DEFAULT, .list = posix_acl_xattr_list, .get = posix_acl_xattr_get, diff --git a/fs/proc/base.c b/fs/proc/base.c index 4bd5d31..2cf5d7e 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -1564,12 +1564,16 @@ static int proc_exe_link(struct dentry *dentry, struct path *exe_path) return -ENOENT; } -static const char *proc_pid_follow_link(struct dentry *dentry, void **cookie) +static const char *proc_pid_get_link(struct dentry *dentry, + struct inode *inode, + struct delayed_call *done) { - struct inode *inode = d_inode(dentry); struct path path; int error = -EACCES; + if (!dentry) + return ERR_PTR(-ECHILD); + /* Are we allowed to snoop on the tasks file descriptors? */ if (!proc_fd_access_allowed(inode)) goto out; @@ -1630,7 +1634,7 @@ out: const struct inode_operations proc_pid_link_inode_operations = { .readlink = proc_pid_readlink, - .follow_link = proc_pid_follow_link, + .get_link = proc_pid_get_link, .setattr = proc_setattr, }; @@ -1895,7 +1899,7 @@ static const struct dentry_operations tid_map_files_dentry_operations = { .d_delete = pid_delete_dentry, }; -static int proc_map_files_get_link(struct dentry *dentry, struct path *path) +static int map_files_get_link(struct dentry *dentry, struct path *path) { unsigned long vm_start, vm_end; struct vm_area_struct *vma; @@ -1945,20 +1949,22 @@ struct map_files_info { * path to the file in question. */ static const char * -proc_map_files_follow_link(struct dentry *dentry, void **cookie) +proc_map_files_get_link(struct dentry *dentry, + struct inode *inode, + struct delayed_call *done) { if (!capable(CAP_SYS_ADMIN)) return ERR_PTR(-EPERM); - return proc_pid_follow_link(dentry, NULL); + return proc_pid_get_link(dentry, inode, done); } /* - * Identical to proc_pid_link_inode_operations except for follow_link() + * Identical to proc_pid_link_inode_operations except for get_link() */ static const struct inode_operations proc_map_files_link_inode_operations = { .readlink = proc_pid_readlink, - .follow_link = proc_map_files_follow_link, + .get_link = proc_map_files_get_link, .setattr = proc_setattr, }; @@ -1975,7 +1981,7 @@ proc_map_files_instantiate(struct inode *dir, struct dentry *dentry, return -ENOENT; ei = PROC_I(inode); - ei->op.proc_get_link = proc_map_files_get_link; + ei->op.proc_get_link = map_files_get_link; inode->i_op = &proc_map_files_link_inode_operations; inode->i_size = 64; @@ -2359,7 +2365,7 @@ static ssize_t proc_pid_attr_write(struct file * file, const char __user * buf, size_t count, loff_t *ppos) { struct inode * inode = file_inode(file); - char *page; + void *page; ssize_t length; struct task_struct *task = get_proc_task(inode); @@ -2374,14 +2380,11 @@ static ssize_t proc_pid_attr_write(struct file * file, const char __user * buf, if (*ppos != 0) goto out; - length = -ENOMEM; - page = (char*)__get_free_page(GFP_TEMPORARY); - if (!page) + page = memdup_user(buf, count); + if (IS_ERR(page)) { + length = PTR_ERR(page); goto out; - - length = -EFAULT; - if (copy_from_user(page, buf, count)) - goto out_free; + } /* Guard against adverse ptrace interaction */ length = mutex_lock_interruptible(&task->signal->cred_guard_mutex); @@ -2390,10 +2393,10 @@ static ssize_t proc_pid_attr_write(struct file * file, const char __user * buf, length = security_setprocattr(task, (char*)file->f_path.dentry->d_name.name, - (void*)page, count); + page, count); mutex_unlock(&task->signal->cred_guard_mutex); out_free: - free_page((unsigned long) page); + kfree(page); out: put_task_struct(task); out_no_task: diff --git a/fs/proc/fd.c b/fs/proc/fd.c index 3c2a915..56afa5e 100644 --- a/fs/proc/fd.c +++ b/fs/proc/fd.c @@ -258,6 +258,7 @@ static int proc_readfd_common(struct file *file, struct dir_context *ctx, name, len, instantiate, p, (void *)(unsigned long)fd)) goto out_fd_loop; + cond_resched(); rcu_read_lock(); } rcu_read_unlock(); diff --git a/fs/proc/inode.c b/fs/proc/inode.c index bd95b9f..d0e9b9b 100644 --- a/fs/proc/inode.c +++ b/fs/proc/inode.c @@ -393,24 +393,25 @@ static const struct file_operations proc_reg_file_ops_no_compat = { }; #endif -static const char *proc_follow_link(struct dentry *dentry, void **cookie) +static void proc_put_link(void *p) { - struct proc_dir_entry *pde = PDE(d_inode(dentry)); - if (unlikely(!use_pde(pde))) - return ERR_PTR(-EINVAL); - *cookie = pde; - return pde->data; + unuse_pde(p); } -static void proc_put_link(struct inode *unused, void *p) +static const char *proc_get_link(struct dentry *dentry, + struct inode *inode, + struct delayed_call *done) { - unuse_pde(p); + struct proc_dir_entry *pde = PDE(inode); + if (unlikely(!use_pde(pde))) + return ERR_PTR(-EINVAL); + set_delayed_call(done, proc_put_link, pde); + return pde->data; } const struct inode_operations proc_link_inode_operations = { .readlink = generic_readlink, - .follow_link = proc_follow_link, - .put_link = proc_put_link, + .get_link = proc_get_link, }; struct inode *proc_get_inode(struct super_block *sb, struct proc_dir_entry *de) diff --git a/fs/proc/namespaces.c b/fs/proc/namespaces.c index f6e8354..1dece87 100644 --- a/fs/proc/namespaces.c +++ b/fs/proc/namespaces.c @@ -30,14 +30,18 @@ static const struct proc_ns_operations *ns_entries[] = { &mntns_operations, }; -static const char *proc_ns_follow_link(struct dentry *dentry, void **cookie) +static const char *proc_ns_get_link(struct dentry *dentry, + struct inode *inode, + struct delayed_call *done) { - struct inode *inode = d_inode(dentry); const struct proc_ns_operations *ns_ops = PROC_I(inode)->ns_ops; struct task_struct *task; struct path ns_path; void *error = ERR_PTR(-EACCES); + if (!dentry) + return ERR_PTR(-ECHILD); + task = get_proc_task(inode); if (!task) return error; @@ -74,7 +78,7 @@ static int proc_ns_readlink(struct dentry *dentry, char __user *buffer, int bufl static const struct inode_operations proc_ns_link_inode_operations = { .readlink = proc_ns_readlink, - .follow_link = proc_ns_follow_link, + .get_link = proc_ns_get_link, .setattr = proc_setattr, }; diff --git a/fs/proc/self.c b/fs/proc/self.c index 113b8d0..67e8db4 100644 --- a/fs/proc/self.c +++ b/fs/proc/self.c @@ -18,26 +18,28 @@ static int proc_self_readlink(struct dentry *dentry, char __user *buffer, return readlink_copy(buffer, buflen, tmp); } -static const char *proc_self_follow_link(struct dentry *dentry, void **cookie) +static const char *proc_self_get_link(struct dentry *dentry, + struct inode *inode, + struct delayed_call *done) { - struct pid_namespace *ns = dentry->d_sb->s_fs_info; + struct pid_namespace *ns = inode->i_sb->s_fs_info; pid_t tgid = task_tgid_nr_ns(current, ns); char *name; if (!tgid) return ERR_PTR(-ENOENT); /* 11 for max length of signed int in decimal + NULL term */ - name = kmalloc(12, GFP_KERNEL); - if (!name) - return ERR_PTR(-ENOMEM); + name = kmalloc(12, dentry ? GFP_KERNEL : GFP_ATOMIC); + if (unlikely(!name)) + return dentry ? ERR_PTR(-ENOMEM) : ERR_PTR(-ECHILD); sprintf(name, "%d", tgid); - return *cookie = name; + set_delayed_call(done, kfree_link, name); + return name; } static const struct inode_operations proc_self_inode_operations = { .readlink = proc_self_readlink, - .follow_link = proc_self_follow_link, - .put_link = kfree_put_link, + .get_link = proc_self_get_link, }; static unsigned self_inum; diff --git a/fs/proc/thread_self.c b/fs/proc/thread_self.c index 947b0f4..9eacd59 100644 --- a/fs/proc/thread_self.c +++ b/fs/proc/thread_self.c @@ -19,26 +19,29 @@ static int proc_thread_self_readlink(struct dentry *dentry, char __user *buffer, return readlink_copy(buffer, buflen, tmp); } -static const char *proc_thread_self_follow_link(struct dentry *dentry, void **cookie) +static const char *proc_thread_self_get_link(struct dentry *dentry, + struct inode *inode, + struct delayed_call *done) { - struct pid_namespace *ns = dentry->d_sb->s_fs_info; + struct pid_namespace *ns = inode->i_sb->s_fs_info; pid_t tgid = task_tgid_nr_ns(current, ns); pid_t pid = task_pid_nr_ns(current, ns); char *name; if (!pid) return ERR_PTR(-ENOENT); - name = kmalloc(PROC_NUMBUF + 6 + PROC_NUMBUF, GFP_KERNEL); - if (!name) - return ERR_PTR(-ENOMEM); + name = kmalloc(PROC_NUMBUF + 6 + PROC_NUMBUF, + dentry ? GFP_KERNEL : GFP_ATOMIC); + if (unlikely(!name)) + return dentry ? ERR_PTR(-ENOMEM) : ERR_PTR(-ECHILD); sprintf(name, "%d/task/%d", tgid, pid); - return *cookie = name; + set_delayed_call(done, kfree_link, name); + return name; } static const struct inode_operations proc_thread_self_inode_operations = { .readlink = proc_thread_self_readlink, - .follow_link = proc_thread_self_follow_link, - .put_link = kfree_put_link, + .get_link = proc_thread_self_get_link, }; static unsigned thread_self_inum; diff --git a/fs/proc_namespace.c b/fs/proc_namespace.c index 8ebd9a3..2256e7e 100644 --- a/fs/proc_namespace.c +++ b/fs/proc_namespace.c @@ -95,9 +95,9 @@ static int show_vfsmnt(struct seq_file *m, struct vfsmount *mnt) { struct proc_mounts *p = m->private; struct mount *r = real_mount(mnt); - int err = 0; struct path mnt_path = { .dentry = mnt->mnt_root, .mnt = mnt }; struct super_block *sb = mnt_path.dentry->d_sb; + int err; if (sb->s_op->show_devname) { err = sb->s_op->show_devname(m, mnt_path.dentry); @@ -131,16 +131,17 @@ static int show_mountinfo(struct seq_file *m, struct vfsmount *mnt) struct mount *r = real_mount(mnt); struct super_block *sb = mnt->mnt_sb; struct path mnt_path = { .dentry = mnt->mnt_root, .mnt = mnt }; - int err = 0; + int err; seq_printf(m, "%i %i %u:%u ", r->mnt_id, r->mnt_parent->mnt_id, MAJOR(sb->s_dev), MINOR(sb->s_dev)); - if (sb->s_op->show_path) + if (sb->s_op->show_path) { err = sb->s_op->show_path(m, mnt->mnt_root); - else + if (err) + goto out; + } else { seq_dentry(m, mnt->mnt_root, " \t\n\\"); - if (err) - goto out; + } seq_putc(m, ' '); /* mountpoints outside of chroot jail will give SEQ_SKIP on this */ @@ -168,12 +169,13 @@ static int show_mountinfo(struct seq_file *m, struct vfsmount *mnt) seq_puts(m, " - "); show_type(m, sb); seq_putc(m, ' '); - if (sb->s_op->show_devname) + if (sb->s_op->show_devname) { err = sb->s_op->show_devname(m, mnt->mnt_root); - else + if (err) + goto out; + } else { mangle(m, r->mnt_devname ? r->mnt_devname : "none"); - if (err) - goto out; + } seq_puts(m, sb->s_flags & MS_RDONLY ? " ro" : " rw"); err = show_sb_opts(m, sb); if (err) @@ -191,7 +193,7 @@ static int show_vfsstat(struct seq_file *m, struct vfsmount *mnt) struct mount *r = real_mount(mnt); struct path mnt_path = { .dentry = mnt->mnt_root, .mnt = mnt }; struct super_block *sb = mnt_path.dentry->d_sb; - int err = 0; + int err; /* device */ if (sb->s_op->show_devname) { @@ -220,8 +222,7 @@ static int show_vfsstat(struct seq_file *m, struct vfsmount *mnt) /* optional statistics */ if (sb->s_op->show_stats) { seq_putc(m, ' '); - if (!err) - err = sb->s_op->show_stats(m, mnt_path.dentry); + err = sb->s_op->show_stats(m, mnt_path.dentry); } seq_putc(m, '\n'); diff --git a/fs/qnx4/inode.c b/fs/qnx4/inode.c index c4bcb77..f37b3de 100644 --- a/fs/qnx4/inode.c +++ b/fs/qnx4/inode.c @@ -316,6 +316,7 @@ struct inode *qnx4_iget(struct super_block *sb, unsigned long ino) inode->i_fop = &qnx4_dir_operations; } else if (S_ISLNK(inode->i_mode)) { inode->i_op = &page_symlink_inode_operations; + inode_nohighmem(inode); inode->i_mapping->a_ops = &qnx4_aops; qnx4_i(inode)->mmu_private = inode->i_size; } else { diff --git a/fs/qnx6/inode.c b/fs/qnx6/inode.c index 32d2e1a..9728b54 100644 --- a/fs/qnx6/inode.c +++ b/fs/qnx6/inode.c @@ -582,6 +582,7 @@ struct inode *qnx6_iget(struct super_block *sb, unsigned ino) inode->i_mapping->a_ops = &qnx6_aops; } else if (S_ISLNK(inode->i_mode)) { inode->i_op = &page_symlink_inode_operations; + inode_nohighmem(inode); inode->i_mapping->a_ops = &qnx6_aops; } else init_special_inode(inode, inode->i_mode, 0); diff --git a/fs/ramfs/inode.c b/fs/ramfs/inode.c index 889d558..38981b0 100644 --- a/fs/ramfs/inode.c +++ b/fs/ramfs/inode.c @@ -79,6 +79,7 @@ struct inode *ramfs_get_inode(struct super_block *sb, break; case S_IFLNK: inode->i_op = &page_symlink_inode_operations; + inode_nohighmem(inode); break; } } diff --git a/fs/read_write.c b/fs/read_write.c index 819ef3f..06b07d5 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -16,6 +16,7 @@ #include <linux/pagemap.h> #include <linux/splice.h> #include <linux/compat.h> +#include <linux/mount.h> #include "internal.h" #include <asm/uaccess.h> @@ -171,6 +172,45 @@ loff_t fixed_size_llseek(struct file *file, loff_t offset, int whence, loff_t si EXPORT_SYMBOL(fixed_size_llseek); /** + * no_seek_end_llseek - llseek implementation for fixed-sized devices + * @file: file structure to seek on + * @offset: file offset to seek to + * @whence: type of seek + * + */ +loff_t no_seek_end_llseek(struct file *file, loff_t offset, int whence) +{ + switch (whence) { + case SEEK_SET: case SEEK_CUR: + return generic_file_llseek_size(file, offset, whence, + ~0ULL, 0); + default: + return -EINVAL; + } +} +EXPORT_SYMBOL(no_seek_end_llseek); + +/** + * no_seek_end_llseek_size - llseek implementation for fixed-sized devices + * @file: file structure to seek on + * @offset: file offset to seek to + * @whence: type of seek + * @size: maximal offset allowed + * + */ +loff_t no_seek_end_llseek_size(struct file *file, loff_t offset, int whence, loff_t size) +{ + switch (whence) { + case SEEK_SET: case SEEK_CUR: + return generic_file_llseek_size(file, offset, whence, + size, 0); + default: + return -EINVAL; + } +} +EXPORT_SYMBOL(no_seek_end_llseek_size); + +/** * noop_llseek - No Operation Performed llseek implementation * @file: file structure to seek on * @offset: file offset to seek to @@ -395,9 +435,8 @@ int rw_verify_area(int read_write, struct file *file, const loff_t *ppos, size_t } if (unlikely(inode->i_flctx && mandatory_lock(inode))) { - retval = locks_mandatory_area( - read_write == READ ? FLOCK_VERIFY_READ : FLOCK_VERIFY_WRITE, - inode, file, pos, count); + retval = locks_mandatory_area(inode, file, pos, pos + count - 1, + read_write == READ ? F_RDLCK : F_WRLCK); if (retval < 0) return retval; } @@ -1327,3 +1366,299 @@ COMPAT_SYSCALL_DEFINE4(sendfile64, int, out_fd, int, in_fd, return do_sendfile(out_fd, in_fd, NULL, count, 0); } #endif + +/* + * copy_file_range() differs from regular file read and write in that it + * specifically allows return partial success. When it does so is up to + * the copy_file_range method. + */ +ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + size_t len, unsigned int flags) +{ + struct inode *inode_in = file_inode(file_in); + struct inode *inode_out = file_inode(file_out); + ssize_t ret; + + 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) + return ret; + + if (!(file_in->f_mode & FMODE_READ) || + !(file_out->f_mode & FMODE_WRITE) || + (file_out->f_flags & O_APPEND)) + return -EBADF; + + /* this could be relaxed once a method supports cross-fs copies */ + if (inode_in->i_sb != inode_out->i_sb) + return -EXDEV; + + if (len == 0) + return 0; + + ret = mnt_want_write_file(file_out); + if (ret) + return ret; + + ret = -EOPNOTSUPP; + if (file_out->f_op->copy_file_range) + ret = file_out->f_op->copy_file_range(file_in, pos_in, file_out, + pos_out, len, flags); + if (ret == -EOPNOTSUPP) + ret = do_splice_direct(file_in, &pos_in, file_out, &pos_out, + len > MAX_RW_COUNT ? MAX_RW_COUNT : len, 0); + + if (ret > 0) { + fsnotify_access(file_in); + add_rchar(current, ret); + fsnotify_modify(file_out); + add_wchar(current, ret); + } + inc_syscr(current); + inc_syscw(current); + + mnt_drop_write_file(file_out); + + return ret; +} +EXPORT_SYMBOL(vfs_copy_file_range); + +SYSCALL_DEFINE6(copy_file_range, int, fd_in, loff_t __user *, off_in, + int, fd_out, loff_t __user *, off_out, + size_t, len, unsigned int, flags) +{ + loff_t pos_in; + loff_t pos_out; + struct fd f_in; + struct fd f_out; + ssize_t ret = -EBADF; + + f_in = fdget(fd_in); + if (!f_in.file) + goto out2; + + f_out = fdget(fd_out); + if (!f_out.file) + goto out1; + + ret = -EFAULT; + if (off_in) { + if (copy_from_user(&pos_in, off_in, sizeof(loff_t))) + goto out; + } else { + pos_in = f_in.file->f_pos; + } + + if (off_out) { + if (copy_from_user(&pos_out, off_out, sizeof(loff_t))) + goto out; + } else { + pos_out = f_out.file->f_pos; + } + + ret = vfs_copy_file_range(f_in.file, pos_in, f_out.file, pos_out, len, + flags); + if (ret > 0) { + pos_in += ret; + pos_out += ret; + + if (off_in) { + if (copy_to_user(off_in, &pos_in, sizeof(loff_t))) + ret = -EFAULT; + } else { + f_in.file->f_pos = pos_in; + } + + if (off_out) { + if (copy_to_user(off_out, &pos_out, sizeof(loff_t))) + ret = -EFAULT; + } else { + f_out.file->f_pos = pos_out; + } + } + +out: + fdput(f_out); +out1: + fdput(f_in); +out2: + return ret; +} + +static int clone_verify_area(struct file *file, loff_t pos, u64 len, bool write) +{ + struct inode *inode = file_inode(file); + + if (unlikely(pos < 0)) + return -EINVAL; + + if (unlikely((loff_t) (pos + len) < 0)) + return -EINVAL; + + if (unlikely(inode->i_flctx && mandatory_lock(inode))) { + loff_t end = len ? pos + len - 1 : OFFSET_MAX; + int retval; + + retval = locks_mandatory_area(inode, file, pos, end, + write ? F_WRLCK : F_RDLCK); + if (retval < 0) + return retval; + } + + return security_file_permission(file, write ? MAY_WRITE : MAY_READ); +} + +int vfs_clone_file_range(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, u64 len) +{ + struct inode *inode_in = file_inode(file_in); + struct inode *inode_out = file_inode(file_out); + int ret; + + if (inode_in->i_sb != inode_out->i_sb || + file_in->f_path.mnt != file_out->f_path.mnt) + return -EXDEV; + + if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode)) + return -EISDIR; + if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode)) + return -EINVAL; + + if (!(file_in->f_mode & FMODE_READ) || + !(file_out->f_mode & FMODE_WRITE) || + (file_out->f_flags & O_APPEND) || + !file_in->f_op->clone_file_range) + return -EBADF; + + ret = clone_verify_area(file_in, pos_in, len, false); + if (ret) + return ret; + + ret = clone_verify_area(file_out, pos_out, len, true); + if (ret) + return ret; + + if (pos_in + len > i_size_read(inode_in)) + return -EINVAL; + + ret = mnt_want_write_file(file_out); + if (ret) + return ret; + + ret = file_in->f_op->clone_file_range(file_in, pos_in, + file_out, pos_out, len); + if (!ret) { + fsnotify_access(file_in); + fsnotify_modify(file_out); + } + + mnt_drop_write_file(file_out); + return ret; +} +EXPORT_SYMBOL(vfs_clone_file_range); + +int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same) +{ + struct file_dedupe_range_info *info; + struct inode *src = file_inode(file); + u64 off; + u64 len; + int i; + int ret; + bool is_admin = capable(CAP_SYS_ADMIN); + u16 count = same->dest_count; + struct file *dst_file; + loff_t dst_off; + ssize_t deduped; + + if (!(file->f_mode & FMODE_READ)) + return -EINVAL; + + if (same->reserved1 || same->reserved2) + return -EINVAL; + + off = same->src_offset; + len = same->src_length; + + ret = -EISDIR; + if (S_ISDIR(src->i_mode)) + goto out; + + ret = -EINVAL; + if (!S_ISREG(src->i_mode)) + goto out; + + ret = clone_verify_area(file, off, len, false); + if (ret < 0) + goto out; + ret = 0; + + /* pre-format output fields to sane values */ + for (i = 0; i < count; i++) { + same->info[i].bytes_deduped = 0ULL; + same->info[i].status = FILE_DEDUPE_RANGE_SAME; + } + + for (i = 0, info = same->info; i < count; i++, info++) { + struct inode *dst; + struct fd dst_fd = fdget(info->dest_fd); + + dst_file = dst_fd.file; + if (!dst_file) { + info->status = -EBADF; + goto next_loop; + } + dst = file_inode(dst_file); + + ret = mnt_want_write_file(dst_file); + if (ret) { + info->status = ret; + goto next_loop; + } + + dst_off = info->dest_offset; + ret = clone_verify_area(dst_file, dst_off, len, true); + if (ret < 0) { + info->status = ret; + goto next_file; + } + ret = 0; + + if (info->reserved) { + info->status = -EINVAL; + } else if (!(is_admin || (dst_file->f_mode & FMODE_WRITE))) { + info->status = -EINVAL; + } else if (file->f_path.mnt != dst_file->f_path.mnt) { + info->status = -EXDEV; + } else if (S_ISDIR(dst->i_mode)) { + info->status = -EISDIR; + } else if (dst_file->f_op->dedupe_file_range == NULL) { + info->status = -EINVAL; + } else { + deduped = dst_file->f_op->dedupe_file_range(file, off, + len, dst_file, + info->dest_offset); + if (deduped == -EBADE) + info->status = FILE_DEDUPE_RANGE_DIFFERS; + else if (deduped < 0) + info->status = deduped; + else + info->bytes_deduped += deduped; + } + +next_file: + mnt_drop_write_file(dst_file); +next_loop: + fdput(dst_fd); + } + +out: + return ret; +} +EXPORT_SYMBOL(vfs_dedupe_file_range); diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c index 3d8e7e6..ae9e5b3 100644 --- a/fs/reiserfs/inode.c +++ b/fs/reiserfs/inode.c @@ -1361,6 +1361,7 @@ static void init_inode(struct inode *inode, struct treepath *path) inode->i_fop = &reiserfs_dir_operations; } else if (S_ISLNK(inode->i_mode)) { inode->i_op = &reiserfs_symlink_inode_operations; + inode_nohighmem(inode); inode->i_mapping->a_ops = &reiserfs_address_space_operations; } else { inode->i_blocks = 0; diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c index 9d6486d..44c2bdc 100644 --- a/fs/reiserfs/journal.c +++ b/fs/reiserfs/journal.c @@ -618,12 +618,10 @@ static void release_buffer_page(struct buffer_head *bh) static void reiserfs_end_buffer_io_sync(struct buffer_head *bh, int uptodate) { - char b[BDEVNAME_SIZE]; - if (buffer_journaled(bh)) { reiserfs_warning(NULL, "clm-2084", - "pinned buffer %lu:%s sent to disk", - bh->b_blocknr, bdevname(bh->b_bdev, b)); + "pinned buffer %lu:%pg sent to disk", + bh->b_blocknr, bh->b_bdev); } if (uptodate) set_buffer_uptodate(bh); @@ -2387,11 +2385,10 @@ static int journal_read(struct super_block *sb) int replay_count = 0; int continue_replay = 1; int ret; - char b[BDEVNAME_SIZE]; cur_dblock = SB_ONDISK_JOURNAL_1st_BLOCK(sb); - reiserfs_info(sb, "checking transaction log (%s)\n", - bdevname(journal->j_dev_bd, b)); + reiserfs_info(sb, "checking transaction log (%pg)\n", + journal->j_dev_bd); start = get_seconds(); /* @@ -2651,8 +2648,8 @@ static int journal_init_dev(struct super_block *super, set_blocksize(journal->j_dev_bd, super->s_blocksize); reiserfs_info(super, - "journal_init_dev: journal device: %s\n", - bdevname(journal->j_dev_bd, b)); + "journal_init_dev: journal device: %pg\n", + journal->j_dev_bd); return 0; } @@ -2724,7 +2721,6 @@ int journal_init(struct super_block *sb, const char *j_dev_name, struct reiserfs_journal_header *jh; struct reiserfs_journal *journal; struct reiserfs_journal_list *jl; - char b[BDEVNAME_SIZE]; int ret; journal = SB_JOURNAL(sb) = vzalloc(sizeof(struct reiserfs_journal)); @@ -2794,10 +2790,10 @@ int journal_init(struct super_block *sb, const char *j_dev_name, && (le32_to_cpu(jh->jh_journal.jp_journal_magic) != sb_jp_journal_magic(rs))) { reiserfs_warning(sb, "sh-460", - "journal header magic %x (device %s) does " + "journal header magic %x (device %pg) does " "not match to magic found in super block %x", jh->jh_journal.jp_journal_magic, - bdevname(journal->j_dev_bd, b), + journal->j_dev_bd, sb_jp_journal_magic(rs)); brelse(bhjh); goto free_and_return; @@ -2818,10 +2814,10 @@ int journal_init(struct super_block *sb, const char *j_dev_name, journal->j_max_trans_age = commit_max_age; } - reiserfs_info(sb, "journal params: device %s, size %u, " + reiserfs_info(sb, "journal params: device %pg, size %u, " "journal first block %u, max trans len %u, max batch %u, " "max commit age %u, max trans age %u\n", - bdevname(journal->j_dev_bd, b), + journal->j_dev_bd, SB_ONDISK_JOURNAL_SIZE(sb), SB_ONDISK_JOURNAL_1st_BLOCK(sb), journal->j_trans_max, diff --git a/fs/reiserfs/namei.c b/fs/reiserfs/namei.c index 47f9698..2a12d46 100644 --- a/fs/reiserfs/namei.c +++ b/fs/reiserfs/namei.c @@ -1170,6 +1170,7 @@ static int reiserfs_symlink(struct inode *parent_dir, reiserfs_update_inode_transaction(parent_dir); inode->i_op = &reiserfs_symlink_inode_operations; + inode_nohighmem(inode); inode->i_mapping->a_ops = &reiserfs_address_space_operations; retval = reiserfs_add_entry(&th, parent_dir, dentry->d_name.name, @@ -1664,8 +1665,7 @@ const struct inode_operations reiserfs_dir_inode_operations = { */ const struct inode_operations reiserfs_symlink_inode_operations = { .readlink = generic_readlink, - .follow_link = page_follow_link_light, - .put_link = page_put_link, + .get_link = page_get_link, .setattr = reiserfs_setattr, .setxattr = reiserfs_setxattr, .getxattr = reiserfs_getxattr, diff --git a/fs/reiserfs/prints.c b/fs/reiserfs/prints.c index ae1dc84..4f3f928 100644 --- a/fs/reiserfs/prints.c +++ b/fs/reiserfs/prints.c @@ -139,11 +139,9 @@ static void sprintf_block_head(char *buf, struct buffer_head *bh) static void sprintf_buffer_head(char *buf, struct buffer_head *bh) { - char b[BDEVNAME_SIZE]; - sprintf(buf, - "dev %s, size %zd, blocknr %llu, count %d, state 0x%lx, page %p, (%s, %s, %s)", - bdevname(bh->b_bdev, b), bh->b_size, + "dev %pg, size %zd, blocknr %llu, count %d, state 0x%lx, page %p, (%s, %s, %s)", + bh->b_bdev, bh->b_size, (unsigned long long)bh->b_blocknr, atomic_read(&(bh->b_count)), bh->b_state, bh->b_page, buffer_uptodate(bh) ? "UPTODATE" : "!UPTODATE", @@ -530,7 +528,6 @@ static int print_super_block(struct buffer_head *bh) (struct reiserfs_super_block *)(bh->b_data); int skipped, data_blocks; char *version; - char b[BDEVNAME_SIZE]; if (is_reiserfs_3_5(rs)) { version = "3.5"; @@ -543,7 +540,7 @@ static int print_super_block(struct buffer_head *bh) return 1; } - printk("%s\'s super block is in block %llu\n", bdevname(bh->b_bdev, b), + printk("%pg\'s super block is in block %llu\n", bh->b_bdev, (unsigned long long)bh->b_blocknr); printk("Reiserfs version %s\n", version); printk("Block count %u\n", sb_block_count(rs)); diff --git a/fs/reiserfs/procfs.c b/fs/reiserfs/procfs.c index 621b9f3..fe99915 100644 --- a/fs/reiserfs/procfs.c +++ b/fs/reiserfs/procfs.c @@ -303,11 +303,10 @@ static int show_journal(struct seq_file *m, void *unused) struct reiserfs_sb_info *r = REISERFS_SB(sb); struct reiserfs_super_block *rs = r->s_rs; struct journal_params *jp = &rs->s_v1.s_journal; - char b[BDEVNAME_SIZE]; seq_printf(m, /* on-disk fields */ "jp_journal_1st_block: \t%i\n" - "jp_journal_dev: \t%s[%x]\n" + "jp_journal_dev: \t%pg[%x]\n" "jp_journal_size: \t%i\n" "jp_journal_trans_max: \t%i\n" "jp_journal_magic: \t%i\n" @@ -348,7 +347,7 @@ static int show_journal(struct seq_file *m, void *unused) "prepare: \t%12lu\n" "prepare_retry: \t%12lu\n", DJP(jp_journal_1st_block), - bdevname(SB_JOURNAL(sb)->j_dev_bd, b), + SB_JOURNAL(sb)->j_dev_bd, DJP(jp_journal_dev), DJP(jp_journal_size), DJP(jp_journal_trans_max), diff --git a/fs/reiserfs/xattr.c b/fs/reiserfs/xattr.c index 66b26fd..e5ddb4e 100644 --- a/fs/reiserfs/xattr.c +++ b/fs/reiserfs/xattr.c @@ -756,7 +756,8 @@ find_xattr_handler_prefix(const struct xattr_handler **handlers, return NULL; for_each_xattr_handler(handlers, xah) { - if (strncmp(xah->prefix, name, strlen(xah->prefix)) == 0) + const char *prefix = xattr_prefix(xah); + if (strncmp(prefix, name, strlen(prefix)) == 0) break; } @@ -839,19 +840,16 @@ static int listxattr_filler(struct dir_context *ctx, const char *name, handler = find_xattr_handler_prefix(b->dentry->d_sb->s_xattr, name); - if (!handler) /* Unsupported xattr name */ + if (!handler /* Unsupported xattr name */ || + (handler->list && !handler->list(b->dentry))) return 0; + size = namelen + 1; if (b->buf) { - size = handler->list(handler, b->dentry, - b->buf + b->pos, b->size, name, - namelen); if (size > b->size) return -ERANGE; - } else { - size = handler->list(handler, b->dentry, - NULL, 0, name, namelen); + memcpy(b->buf + b->pos, name, namelen); + b->buf[b->pos + namelen] = 0; } - b->pos += size; } return 0; diff --git a/fs/reiserfs/xattr_acl.c b/fs/reiserfs/xattr_acl.c index 4b34b9d..558a16b 100644 --- a/fs/reiserfs/xattr_acl.c +++ b/fs/reiserfs/xattr_acl.c @@ -186,10 +186,10 @@ struct posix_acl *reiserfs_get_acl(struct inode *inode, int type) switch (type) { case ACL_TYPE_ACCESS: - name = POSIX_ACL_XATTR_ACCESS; + name = XATTR_NAME_POSIX_ACL_ACCESS; break; case ACL_TYPE_DEFAULT: - name = POSIX_ACL_XATTR_DEFAULT; + name = XATTR_NAME_POSIX_ACL_DEFAULT; break; default: BUG(); @@ -244,7 +244,7 @@ __reiserfs_set_acl(struct reiserfs_transaction_handle *th, struct inode *inode, switch (type) { case ACL_TYPE_ACCESS: - name = POSIX_ACL_XATTR_ACCESS; + name = XATTR_NAME_POSIX_ACL_ACCESS; if (acl) { error = posix_acl_equiv_mode(acl, &inode->i_mode); if (error < 0) @@ -256,7 +256,7 @@ __reiserfs_set_acl(struct reiserfs_transaction_handle *th, struct inode *inode, } break; case ACL_TYPE_DEFAULT: - name = POSIX_ACL_XATTR_DEFAULT; + name = XATTR_NAME_POSIX_ACL_DEFAULT; if (!S_ISDIR(inode->i_mode)) return acl ? -EACCES : 0; break; diff --git a/fs/reiserfs/xattr_security.c b/fs/reiserfs/xattr_security.c index ac659af..ab0217d 100644 --- a/fs/reiserfs/xattr_security.c +++ b/fs/reiserfs/xattr_security.c @@ -34,21 +34,9 @@ security_set(const struct xattr_handler *handler, struct dentry *dentry, return reiserfs_xattr_set(d_inode(dentry), name, buffer, size, flags); } -static size_t security_list(const struct xattr_handler *handler, - struct dentry *dentry, char *list, size_t list_len, - const char *name, size_t namelen) +static bool security_list(struct dentry *dentry) { - const size_t len = namelen + 1; - - if (IS_PRIVATE(d_inode(dentry))) - return 0; - - if (list && len <= list_len) { - memcpy(list, name, namelen); - list[namelen] = '\0'; - } - - return len; + return !IS_PRIVATE(d_inode(dentry)); } /* Initializes the security context for a new inode and returns the number diff --git a/fs/reiserfs/xattr_trusted.c b/fs/reiserfs/xattr_trusted.c index a338adf..64b67aa 100644 --- a/fs/reiserfs/xattr_trusted.c +++ b/fs/reiserfs/xattr_trusted.c @@ -33,20 +33,9 @@ trusted_set(const struct xattr_handler *handler, struct dentry *dentry, return reiserfs_xattr_set(d_inode(dentry), name, buffer, size, flags); } -static size_t trusted_list(const struct xattr_handler *handler, - struct dentry *dentry, char *list, size_t list_size, - const char *name, size_t name_len) +static bool trusted_list(struct dentry *dentry) { - const size_t len = name_len + 1; - - if (!capable(CAP_SYS_ADMIN) || IS_PRIVATE(d_inode(dentry))) - return 0; - - if (list && len <= list_size) { - memcpy(list, name, name_len); - list[name_len] = '\0'; - } - return len; + return capable(CAP_SYS_ADMIN) && !IS_PRIVATE(d_inode(dentry)); } const struct xattr_handler reiserfs_xattr_trusted_handler = { diff --git a/fs/reiserfs/xattr_user.c b/fs/reiserfs/xattr_user.c index 39c9667..12e6306 100644 --- a/fs/reiserfs/xattr_user.c +++ b/fs/reiserfs/xattr_user.c @@ -30,19 +30,9 @@ user_set(const struct xattr_handler *handler, struct dentry *dentry, return reiserfs_xattr_set(d_inode(dentry), name, buffer, size, flags); } -static size_t user_list(const struct xattr_handler *handler, - struct dentry *dentry, char *list, size_t list_size, - const char *name, size_t name_len) +static bool user_list(struct dentry *dentry) { - const size_t len = name_len + 1; - - if (!reiserfs_xattrs_user(dentry->d_sb)) - return 0; - if (list && len <= list_size) { - memcpy(list, name, name_len); - list[name_len] = '\0'; - } - return len; + return reiserfs_xattrs_user(dentry->d_sb); } const struct xattr_handler reiserfs_xattr_user_handler = { diff --git a/fs/romfs/super.c b/fs/romfs/super.c index 268733c..bb894e7 100644 --- a/fs/romfs/super.c +++ b/fs/romfs/super.c @@ -360,6 +360,7 @@ static struct inode *romfs_iget(struct super_block *sb, unsigned long pos) break; case ROMFH_SYM: i->i_op = &page_symlink_inode_operations; + inode_nohighmem(i); i->i_data.a_ops = &romfs_aops; mode |= S_IRWXUGO; break; diff --git a/fs/select.c b/fs/select.c index 0155473..79d0d49 100644 --- a/fs/select.c +++ b/fs/select.c @@ -778,8 +778,8 @@ static inline unsigned int do_pollfd(struct pollfd *pollfd, poll_table *pwait, return mask; } -static int do_poll(unsigned int nfds, struct poll_list *list, - struct poll_wqueues *wait, struct timespec *end_time) +static int do_poll(struct poll_list *list, struct poll_wqueues *wait, + struct timespec *end_time) { poll_table* pt = &wait->pt; ktime_t expire, *to = NULL; @@ -908,7 +908,7 @@ int do_sys_poll(struct pollfd __user *ufds, unsigned int nfds, } poll_initwait(&table); - fdcount = do_poll(nfds, head, &table, end_time); + fdcount = do_poll(head, &table, end_time); poll_freewait(&table); for (walk = head; walk; walk = walk->next) { diff --git a/fs/splice.c b/fs/splice.c index 4cf700d..82bc0d6 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -415,6 +415,7 @@ __generic_file_splice_read(struct file *in, loff_t *ppos, */ if (!page->mapping) { unlock_page(page); +retry_lookup: page = find_or_create_page(mapping, index, mapping_gfp_mask(mapping)); @@ -439,13 +440,10 @@ __generic_file_splice_read(struct file *in, loff_t *ppos, error = mapping->a_ops->readpage(in, page); if (unlikely(error)) { /* - * We really should re-lookup the page here, - * but it complicates things a lot. Instead - * lets just do what we already stored, and - * we'll get it the next time we are called. + * Re-lookup the page */ if (error == AOP_TRUNCATED_PAGE) - error = 0; + goto retry_lookup; break; } diff --git a/fs/squashfs/inode.c b/fs/squashfs/inode.c index a1ce5ce..0927b1e 100644 --- a/fs/squashfs/inode.c +++ b/fs/squashfs/inode.c @@ -41,6 +41,7 @@ #include <linux/fs.h> #include <linux/vfs.h> #include <linux/xattr.h> +#include <linux/pagemap.h> #include "squashfs_fs.h" #include "squashfs_fs_sb.h" @@ -291,6 +292,7 @@ int squashfs_read_inode(struct inode *inode, long long ino) set_nlink(inode, le32_to_cpu(sqsh_ino->nlink)); inode->i_size = le32_to_cpu(sqsh_ino->symlink_size); inode->i_op = &squashfs_symlink_inode_ops; + inode_nohighmem(inode); inode->i_data.a_ops = &squashfs_symlink_aops; inode->i_mode |= S_IFLNK; squashfs_i(inode)->start = block; diff --git a/fs/squashfs/super.c b/fs/squashfs/super.c index 5056bab..dded920 100644 --- a/fs/squashfs/super.c +++ b/fs/squashfs/super.c @@ -80,7 +80,6 @@ static int squashfs_fill_super(struct super_block *sb, void *data, int silent) { struct squashfs_sb_info *msblk; struct squashfs_super_block *sblk = NULL; - char b[BDEVNAME_SIZE]; struct inode *root; long long root_inode; unsigned short flags; @@ -124,8 +123,8 @@ static int squashfs_fill_super(struct super_block *sb, void *data, int silent) sb->s_magic = le32_to_cpu(sblk->s_magic); if (sb->s_magic != SQUASHFS_MAGIC) { if (!silent) - ERROR("Can't find a SQUASHFS superblock on %s\n", - bdevname(sb->s_bdev, b)); + ERROR("Can't find a SQUASHFS superblock on %pg\n", + sb->s_bdev); goto failed_mount; } @@ -178,7 +177,7 @@ static int squashfs_fill_super(struct super_block *sb, void *data, int silent) msblk->inodes = le32_to_cpu(sblk->inodes); flags = le16_to_cpu(sblk->flags); - TRACE("Found valid superblock on %s\n", bdevname(sb->s_bdev, b)); + TRACE("Found valid superblock on %pg\n", sb->s_bdev); TRACE("Inodes are %scompressed\n", SQUASHFS_UNCOMPRESSED_INODES(flags) ? "un" : ""); TRACE("Data is %scompressed\n", SQUASHFS_UNCOMPRESSED_DATA(flags) diff --git a/fs/squashfs/symlink.c b/fs/squashfs/symlink.c index 12806df..dbcc2f5 100644 --- a/fs/squashfs/symlink.c +++ b/fs/squashfs/symlink.c @@ -119,8 +119,7 @@ const struct address_space_operations squashfs_symlink_aops = { const struct inode_operations squashfs_symlink_inode_ops = { .readlink = generic_readlink, - .follow_link = page_follow_link_light, - .put_link = page_put_link, + .get_link = page_get_link, .getxattr = generic_getxattr, .listxattr = squashfs_listxattr }; diff --git a/fs/squashfs/xattr.c b/fs/squashfs/xattr.c index 6a4cc34..1e9de96 100644 --- a/fs/squashfs/xattr.c +++ b/fs/squashfs/xattr.c @@ -58,7 +58,7 @@ ssize_t squashfs_listxattr(struct dentry *d, char *buffer, struct squashfs_xattr_entry entry; struct squashfs_xattr_val val; const struct xattr_handler *handler; - int name_size, prefix_size = 0; + int name_size; err = squashfs_read_metadata(sb, &entry, &start, &offset, sizeof(entry)); @@ -67,15 +67,16 @@ ssize_t squashfs_listxattr(struct dentry *d, char *buffer, name_size = le16_to_cpu(entry.size); handler = squashfs_xattr_handler(le16_to_cpu(entry.type)); - if (handler) - prefix_size = handler->list(handler, d, buffer, rest, - NULL, name_size); - if (prefix_size) { + if (handler && (!handler->list || handler->list(d))) { + const char *prefix = handler->prefix ?: handler->name; + size_t prefix_size = strlen(prefix); + if (buffer) { if (prefix_size + name_size + 1 > rest) { err = -ERANGE; goto failed; } + memcpy(buffer, prefix, prefix_size); buffer += prefix_size; } err = squashfs_read_metadata(sb, buffer, &start, @@ -212,25 +213,10 @@ failed: } -static size_t squashfs_xattr_handler_list(const struct xattr_handler *handler, - struct dentry *d, char *list, - size_t list_size, const char *name, - size_t name_len) -{ - int len = strlen(handler->prefix); - - if (list && len <= list_size) - memcpy(list, handler->prefix, len); - return len; -} - static int squashfs_xattr_handler_get(const struct xattr_handler *handler, struct dentry *d, const char *name, void *buffer, size_t size) { - if (name[0] == '\0') - return -EINVAL; - return squashfs_xattr_get(d_inode(d), handler->flags, name, buffer, size); } @@ -241,22 +227,15 @@ static int squashfs_xattr_handler_get(const struct xattr_handler *handler, static const struct xattr_handler squashfs_xattr_user_handler = { .prefix = XATTR_USER_PREFIX, .flags = SQUASHFS_XATTR_USER, - .list = squashfs_xattr_handler_list, .get = squashfs_xattr_handler_get }; /* * Trusted namespace support */ -static size_t squashfs_trusted_xattr_handler_list(const struct xattr_handler *handler, - struct dentry *d, char *list, - size_t list_size, const char *name, - size_t name_len) +static bool squashfs_trusted_xattr_handler_list(struct dentry *d) { - if (!capable(CAP_SYS_ADMIN)) - return 0; - return squashfs_xattr_handler_list(handler, d, list, list_size, name, - name_len); + return capable(CAP_SYS_ADMIN); } static const struct xattr_handler squashfs_xattr_trusted_handler = { @@ -272,7 +251,6 @@ static const struct xattr_handler squashfs_xattr_trusted_handler = { static const struct xattr_handler squashfs_xattr_security_handler = { .prefix = XATTR_SECURITY_PREFIX, .flags = SQUASHFS_XATTR_SECURITY, - .list = squashfs_xattr_handler_list, .get = squashfs_xattr_handler_get }; @@ -1012,10 +1012,8 @@ struct dentry *mount_bdev(struct file_system_type *fs_type, blkdev_put(bdev, mode); down_write(&s->s_umount); } else { - char b[BDEVNAME_SIZE]; - s->s_mode = mode; - strlcpy(s->s_id, bdevname(bdev, b), sizeof(s->s_id)); + snprintf(s->s_id, sizeof(s->s_id), "%pg", bdev); sb_set_blocksize(s, block_size(bdev)); error = fill_super(s, data, flags & MS_SILENT ? 1 : 0); if (error) { diff --git a/fs/sysv/inode.c b/fs/sysv/inode.c index 02fa1dc..07ac18c 100644 --- a/fs/sysv/inode.c +++ b/fs/sysv/inode.c @@ -146,8 +146,7 @@ static inline void write3byte(struct sysv_sb_info *sbi, static const struct inode_operations sysv_symlink_inode_operations = { .readlink = generic_readlink, - .follow_link = page_follow_link_light, - .put_link = page_put_link, + .get_link = page_get_link, .getattr = sysv_getattr, }; @@ -163,6 +162,7 @@ void sysv_set_inode(struct inode *inode, dev_t rdev) inode->i_mapping->a_ops = &sysv_aops; } else if (S_ISLNK(inode->i_mode)) { inode->i_op = &sysv_symlink_inode_operations; + inode_nohighmem(inode); inode->i_mapping->a_ops = &sysv_aops; } else init_special_inode(inode, inode->i_mode, rdev); diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c index 0edc128..eff6280 100644 --- a/fs/ubifs/file.c +++ b/fs/ubifs/file.c @@ -1608,7 +1608,7 @@ const struct inode_operations ubifs_file_inode_operations = { const struct inode_operations ubifs_symlink_inode_operations = { .readlink = generic_readlink, - .follow_link = simple_follow_link, + .get_link = simple_get_link, .setattr = ubifs_setattr, .getattr = ubifs_getattr, .setxattr = ubifs_setxattr, diff --git a/fs/ubifs/key.h b/fs/ubifs/key.h index 92a8491..c0a95e3 100644 --- a/fs/ubifs/key.h +++ b/fs/ubifs/key.h @@ -34,6 +34,12 @@ * node. We use "r5" hash borrowed from reiserfs. */ +/* + * Lot's of the key helpers require a struct ubifs_info *c as the first parameter. + * But we are not using it at all currently. That's designed for future extensions of + * different c->key_format. But right now, there is only one key type, UBIFS_SIMPLE_KEY_FMT. + */ + #ifndef __UBIFS_KEY_H__ #define __UBIFS_KEY_H__ diff --git a/fs/ubifs/xattr.c b/fs/ubifs/xattr.c index e8b01b7..e53292d 100644 --- a/fs/ubifs/xattr.c +++ b/fs/ubifs/xattr.c @@ -267,7 +267,7 @@ static int check_namespace(const struct qstr *nm) if (!strncmp(nm->name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN)) { - if (nm->name[sizeof(XATTR_TRUSTED_PREFIX) - 1] == '\0') + if (nm->name[XATTR_TRUSTED_PREFIX_LEN] == '\0') return -EINVAL; type = TRUSTED_XATTR; } else if (!strncmp(nm->name, XATTR_USER_PREFIX, @@ -277,7 +277,7 @@ static int check_namespace(const struct qstr *nm) type = USER_XATTR; } else if (!strncmp(nm->name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN)) { - if (nm->name[sizeof(XATTR_SECURITY_PREFIX) - 1] == '\0') + if (nm->name[XATTR_SECURITY_PREFIX_LEN] == '\0') return -EINVAL; type = SECURITY_XATTR; } else diff --git a/fs/udf/inode.c b/fs/udf/inode.c index 8d0b3ad..0557463 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -1540,7 +1540,8 @@ reread: break; case ICBTAG_FILE_TYPE_SYMLINK: inode->i_data.a_ops = &udf_symlink_aops; - inode->i_op = &udf_symlink_inode_operations; + inode->i_op = &page_symlink_inode_operations; + inode_nohighmem(inode); inode->i_mode = S_IFLNK | S_IRWXUGO; break; case ICBTAG_FILE_TYPE_MAIN: diff --git a/fs/udf/namei.c b/fs/udf/namei.c index c97b5a8..42eafb9 100644 --- a/fs/udf/namei.c +++ b/fs/udf/namei.c @@ -921,7 +921,8 @@ static int udf_symlink(struct inode *dir, struct dentry *dentry, } inode->i_data.a_ops = &udf_symlink_aops; - inode->i_op = &udf_symlink_inode_operations; + inode->i_op = &page_symlink_inode_operations; + inode_nohighmem(inode); if (iinfo->i_alloc_type != ICBTAG_FLAG_AD_IN_ICB) { struct kernel_lb_addr eloc; @@ -1344,8 +1345,3 @@ const struct inode_operations udf_dir_inode_operations = { .rename = udf_rename, .tmpfile = udf_tmpfile, }; -const struct inode_operations udf_symlink_inode_operations = { - .readlink = generic_readlink, - .follow_link = page_follow_link_light, - .put_link = page_put_link, -}; diff --git a/fs/udf/symlink.c b/fs/udf/symlink.c index 862535b..8d61977 100644 --- a/fs/udf/symlink.c +++ b/fs/udf/symlink.c @@ -107,7 +107,7 @@ static int udf_symlink_filler(struct file *file, struct page *page) struct buffer_head *bh = NULL; unsigned char *symlink; int err; - unsigned char *p = kmap(page); + unsigned char *p = page_address(page); struct udf_inode_info *iinfo; uint32_t pos; @@ -141,7 +141,6 @@ static int udf_symlink_filler(struct file *file, struct page *page) up_read(&iinfo->i_data_sem); SetPageUptodate(page); - kunmap(page); unlock_page(page); return 0; @@ -149,7 +148,6 @@ out_unlock_inode: up_read(&iinfo->i_data_sem); SetPageError(page); out_unmap: - kunmap(page); unlock_page(page); return err; } diff --git a/fs/udf/udfdecl.h b/fs/udf/udfdecl.h index 47bb3f5..ce169b4 100644 --- a/fs/udf/udfdecl.h +++ b/fs/udf/udfdecl.h @@ -85,7 +85,6 @@ extern const struct inode_operations udf_dir_inode_operations; extern const struct file_operations udf_dir_operations; extern const struct inode_operations udf_file_inode_operations; extern const struct file_operations udf_file_operations; -extern const struct inode_operations udf_symlink_inode_operations; extern const struct address_space_operations udf_aops; extern const struct address_space_operations udf_adinicb_aops; extern const struct address_space_operations udf_symlink_aops; diff --git a/fs/ufs/Makefile b/fs/ufs/Makefile index 392db25..ec4a6b4 100644 --- a/fs/ufs/Makefile +++ b/fs/ufs/Makefile @@ -5,5 +5,5 @@ obj-$(CONFIG_UFS_FS) += ufs.o ufs-objs := balloc.o cylinder.o dir.o file.o ialloc.o inode.o \ - namei.o super.o symlink.o util.o + namei.o super.o util.o ccflags-$(CONFIG_UFS_DEBUG) += -DDEBUG diff --git a/fs/ufs/inode.c b/fs/ufs/inode.c index a064cf44..d897e16 100644 --- a/fs/ufs/inode.c +++ b/fs/ufs/inode.c @@ -528,11 +528,12 @@ static void ufs_set_inode_ops(struct inode *inode) inode->i_mapping->a_ops = &ufs_aops; } else if (S_ISLNK(inode->i_mode)) { if (!inode->i_blocks) { - inode->i_op = &ufs_fast_symlink_inode_operations; inode->i_link = (char *)UFS_I(inode)->i_u1.i_symlink; + inode->i_op = &simple_symlink_inode_operations; } else { - inode->i_op = &ufs_symlink_inode_operations; inode->i_mapping->a_ops = &ufs_aops; + inode->i_op = &page_symlink_inode_operations; + inode_nohighmem(inode); } } else init_special_inode(inode, inode->i_mode, diff --git a/fs/ufs/namei.c b/fs/ufs/namei.c index 4796655..acf4a3b 100644 --- a/fs/ufs/namei.c +++ b/fs/ufs/namei.c @@ -123,14 +123,15 @@ static int ufs_symlink (struct inode * dir, struct dentry * dentry, if (l > UFS_SB(sb)->s_uspi->s_maxsymlinklen) { /* slow symlink */ - inode->i_op = &ufs_symlink_inode_operations; + inode->i_op = &page_symlink_inode_operations; + inode_nohighmem(inode); inode->i_mapping->a_ops = &ufs_aops; err = page_symlink(inode, symname, l); if (err) goto out_fail; } else { /* fast symlink */ - inode->i_op = &ufs_fast_symlink_inode_operations; + inode->i_op = &simple_symlink_inode_operations; inode->i_link = (char *)UFS_I(inode)->i_u1.i_symlink; memcpy(inode->i_link, symname, l); inode->i_size = l-1; diff --git a/fs/ufs/symlink.c b/fs/ufs/symlink.c deleted file mode 100644 index 874480b..0000000 --- a/fs/ufs/symlink.c +++ /dev/null @@ -1,42 +0,0 @@ -/* - * linux/fs/ufs/symlink.c - * - * Only fast symlinks left here - the rest is done by generic code. AV, 1999 - * - * Copyright (C) 1998 - * Daniel Pirkl <daniel.pirkl@emai.cz> - * Charles University, Faculty of Mathematics and Physics - * - * from - * - * linux/fs/ext2/symlink.c - * - * Copyright (C) 1992, 1993, 1994, 1995 - * Remy Card (card@masi.ibp.fr) - * Laboratoire MASI - Institut Blaise Pascal - * Universite Pierre et Marie Curie (Paris VI) - * - * from - * - * linux/fs/minix/symlink.c - * - * Copyright (C) 1991, 1992 Linus Torvalds - * - * ext2 symlink handling code - */ - -#include "ufs_fs.h" -#include "ufs.h" - -const struct inode_operations ufs_fast_symlink_inode_operations = { - .readlink = generic_readlink, - .follow_link = simple_follow_link, - .setattr = ufs_setattr, -}; - -const struct inode_operations ufs_symlink_inode_operations = { - .readlink = generic_readlink, - .follow_link = page_follow_link_light, - .put_link = page_put_link, - .setattr = ufs_setattr, -}; diff --git a/fs/ufs/ufs.h b/fs/ufs/ufs.h index 7da4aca..c87f4c3 100644 --- a/fs/ufs/ufs.h +++ b/fs/ufs/ufs.h @@ -136,10 +136,6 @@ extern __printf(3, 4) void ufs_panic(struct super_block *, const char *, const char *, ...); void ufs_mark_sb_dirty(struct super_block *sb); -/* symlink.c */ -extern const struct inode_operations ufs_fast_symlink_inode_operations; -extern const struct inode_operations ufs_symlink_inode_operations; - static inline struct ufs_sb_info *UFS_SB(struct super_block *sb) { return sb->s_fs_info; @@ -208,25 +208,6 @@ vfs_getxattr_alloc(struct dentry *dentry, const char *name, char **xattr_value, return error; } -/* Compare an extended attribute value with the given value */ -int vfs_xattr_cmp(struct dentry *dentry, const char *xattr_name, - const char *value, size_t size, gfp_t flags) -{ - char *xattr_value = NULL; - int rc; - - rc = vfs_getxattr_alloc(dentry, xattr_name, &xattr_value, 0, flags); - if (rc < 0) - return rc; - - if ((rc != size) || (memcmp(xattr_value, value, rc) != 0)) - rc = -EINVAL; - else - rc = 0; - kfree(xattr_value); - return rc; -} - ssize_t vfs_getxattr(struct dentry *dentry, const char *name, void *value, size_t size) { @@ -324,7 +305,6 @@ setxattr(struct dentry *d, const char __user *name, const void __user *value, { int error; void *kvalue = NULL; - void *vvalue = NULL; /* If non-NULL, we used vmalloc() */ char kname[XATTR_NAME_MAX + 1]; if (flags & ~(XATTR_CREATE|XATTR_REPLACE)) @@ -341,10 +321,9 @@ setxattr(struct dentry *d, const char __user *name, const void __user *value, return -E2BIG; kvalue = kmalloc(size, GFP_KERNEL | __GFP_NOWARN); if (!kvalue) { - vvalue = vmalloc(size); - if (!vvalue) + kvalue = vmalloc(size); + if (!kvalue) return -ENOMEM; - kvalue = vvalue; } if (copy_from_user(kvalue, value, size)) { error = -EFAULT; @@ -357,10 +336,8 @@ setxattr(struct dentry *d, const char __user *name, const void __user *value, error = vfs_setxattr(d, kname, kvalue, size, flags); out: - if (vvalue) - vfree(vvalue); - else - kfree(kvalue); + kvfree(kvalue); + return error; } @@ -428,7 +405,6 @@ getxattr(struct dentry *d, const char __user *name, void __user *value, { ssize_t error; void *kvalue = NULL; - void *vvalue = NULL; char kname[XATTR_NAME_MAX + 1]; error = strncpy_from_user(kname, name, sizeof(kname)); @@ -442,10 +418,9 @@ getxattr(struct dentry *d, const char __user *name, void __user *value, size = XATTR_SIZE_MAX; kvalue = kzalloc(size, GFP_KERNEL | __GFP_NOWARN); if (!kvalue) { - vvalue = vmalloc(size); - if (!vvalue) + kvalue = vmalloc(size); + if (!kvalue) return -ENOMEM; - kvalue = vvalue; } } @@ -461,10 +436,9 @@ getxattr(struct dentry *d, const char __user *name, void __user *value, than XATTR_SIZE_MAX bytes. Not possible. */ error = -E2BIG; } - if (vvalue) - vfree(vvalue); - else - kfree(kvalue); + + kvfree(kvalue); + return error; } @@ -521,17 +495,15 @@ listxattr(struct dentry *d, char __user *list, size_t size) { ssize_t error; char *klist = NULL; - char *vlist = NULL; /* If non-NULL, we used vmalloc() */ if (size) { if (size > XATTR_LIST_MAX) size = XATTR_LIST_MAX; klist = kmalloc(size, __GFP_NOWARN | GFP_KERNEL); if (!klist) { - vlist = vmalloc(size); - if (!vlist) + klist = vmalloc(size); + if (!klist) return -ENOMEM; - klist = vlist; } } @@ -544,10 +516,9 @@ listxattr(struct dentry *d, char __user *list, size_t size) than XATTR_LIST_MAX bytes. Not possible. */ error = -E2BIG; } - if (vlist) - vfree(vlist); - else - kfree(klist); + + kvfree(klist); + return error; } @@ -700,13 +671,20 @@ xattr_resolve_name(const struct xattr_handler **handlers, const char **name) return NULL; for_each_xattr_handler(handlers, handler) { - const char *n = strcmp_prefix(*name, handler->prefix); + const char *n; + + n = strcmp_prefix(*name, xattr_prefix(handler)); if (n) { + if (!handler->prefix ^ !*n) { + if (*n) + continue; + return ERR_PTR(-EINVAL); + } *name = n; - break; + return handler; } } - return handler; + return ERR_PTR(-EOPNOTSUPP); } /* @@ -718,8 +696,8 @@ generic_getxattr(struct dentry *dentry, const char *name, void *buffer, size_t s const struct xattr_handler *handler; handler = xattr_resolve_name(dentry->d_sb->s_xattr, &name); - if (!handler) - return -EOPNOTSUPP; + if (IS_ERR(handler)) + return PTR_ERR(handler); return handler->get(handler, dentry, name, buffer, size); } @@ -735,19 +713,25 @@ generic_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size) if (!buffer) { for_each_xattr_handler(handlers, handler) { - size += handler->list(handler, dentry, NULL, 0, - NULL, 0); + if (!handler->name || + (handler->list && !handler->list(dentry))) + continue; + size += strlen(handler->name) + 1; } } else { char *buf = buffer; + size_t len; for_each_xattr_handler(handlers, handler) { - size = handler->list(handler, dentry, buf, buffer_size, - NULL, 0); - if (size > buffer_size) + if (!handler->name || + (handler->list && !handler->list(dentry))) + continue; + len = strlen(handler->name); + if (len + 1 > buffer_size) return -ERANGE; - buf += size; - buffer_size -= size; + memcpy(buf, handler->name, len + 1); + buf += len + 1; + buffer_size -= len + 1; } size = buf - buffer; } @@ -765,8 +749,8 @@ generic_setxattr(struct dentry *dentry, const char *name, const void *value, siz if (size == 0) value = ""; /* empty EA, do not remove */ handler = xattr_resolve_name(dentry->d_sb->s_xattr, &name); - if (!handler) - return -EOPNOTSUPP; + if (IS_ERR(handler)) + return PTR_ERR(handler); return handler->set(handler, dentry, name, value, size, flags); } @@ -780,8 +764,8 @@ generic_removexattr(struct dentry *dentry, const char *name) const struct xattr_handler *handler; handler = xattr_resolve_name(dentry->d_sb->s_xattr, &name); - if (!handler) - return -EOPNOTSUPP; + if (IS_ERR(handler)) + return PTR_ERR(handler); return handler->set(handler, dentry, name, NULL, 0, XATTR_REPLACE); } @@ -808,7 +792,7 @@ EXPORT_SYMBOL(generic_removexattr); const char *xattr_full_name(const struct xattr_handler *handler, const char *name) { - size_t prefix_len = strlen(handler->prefix); + size_t prefix_len = strlen(xattr_prefix(handler)); return name - prefix_len; } @@ -863,8 +847,22 @@ int simple_xattr_get(struct simple_xattrs *xattrs, const char *name, return ret; } -static int __simple_xattr_set(struct simple_xattrs *xattrs, const char *name, - const void *value, size_t size, int flags) +/** + * simple_xattr_set - xattr SET operation for in-memory/pseudo filesystems + * @xattrs: target simple_xattr list + * @name: name of the extended attribute + * @value: value of the xattr. If %NULL, will remove the attribute. + * @size: size of the new xattr + * @flags: %XATTR_{CREATE|REPLACE} + * + * %XATTR_CREATE is set, the xattr shouldn't exist already; otherwise fails + * with -EEXIST. If %XATTR_REPLACE is set, the xattr should exist; + * otherwise, fails with -ENODATA. + * + * Returns 0 on success, -errno on failure. + */ +int simple_xattr_set(struct simple_xattrs *xattrs, const char *name, + const void *value, size_t size, int flags) { struct simple_xattr *xattr; struct simple_xattr *new_xattr = NULL; @@ -914,73 +912,64 @@ out: } -/** - * simple_xattr_set - xattr SET operation for in-memory/pseudo filesystems - * @xattrs: target simple_xattr list - * @name: name of the new extended attribute - * @value: value of the new xattr. If %NULL, will remove the attribute - * @size: size of the new xattr - * @flags: %XATTR_{CREATE|REPLACE} - * - * %XATTR_CREATE is set, the xattr shouldn't exist already; otherwise fails - * with -EEXIST. If %XATTR_REPLACE is set, the xattr should exist; - * otherwise, fails with -ENODATA. - * - * Returns 0 on success, -errno on failure. - */ -int simple_xattr_set(struct simple_xattrs *xattrs, const char *name, - const void *value, size_t size, int flags) -{ - if (size == 0) - value = ""; /* empty EA, do not remove */ - return __simple_xattr_set(xattrs, name, value, size, flags); -} - -/* - * xattr REMOVE operation for in-memory/pseudo filesystems - */ -int simple_xattr_remove(struct simple_xattrs *xattrs, const char *name) +static bool xattr_is_trusted(const char *name) { - return __simple_xattr_set(xattrs, name, NULL, 0, XATTR_REPLACE); + return !strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN); } -static bool xattr_is_trusted(const char *name) +static int xattr_list_one(char **buffer, ssize_t *remaining_size, + const char *name) { - return !strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN); + size_t len = strlen(name) + 1; + if (*buffer) { + if (*remaining_size < len) + return -ERANGE; + memcpy(*buffer, name, len); + *buffer += len; + } + *remaining_size -= len; + return 0; } /* * xattr LIST operation for in-memory/pseudo filesystems */ -ssize_t simple_xattr_list(struct simple_xattrs *xattrs, char *buffer, - size_t size) +ssize_t simple_xattr_list(struct inode *inode, struct simple_xattrs *xattrs, + char *buffer, size_t size) { bool trusted = capable(CAP_SYS_ADMIN); struct simple_xattr *xattr; - size_t used = 0; + ssize_t remaining_size = size; + int err; + +#ifdef CONFIG_FS_POSIX_ACL + if (inode->i_acl) { + err = xattr_list_one(&buffer, &remaining_size, + XATTR_NAME_POSIX_ACL_ACCESS); + if (err) + return err; + } + if (inode->i_default_acl) { + err = xattr_list_one(&buffer, &remaining_size, + XATTR_NAME_POSIX_ACL_DEFAULT); + if (err) + return err; + } +#endif spin_lock(&xattrs->lock); list_for_each_entry(xattr, &xattrs->head, list) { - size_t len; - /* skip "trusted." attributes for unprivileged callers */ if (!trusted && xattr_is_trusted(xattr->name)) continue; - len = strlen(xattr->name) + 1; - used += len; - if (buffer) { - if (size < used) { - used = -ERANGE; - break; - } - memcpy(buffer, xattr->name, len); - buffer += len; - } + err = xattr_list_one(&buffer, &remaining_size, xattr->name); + if (err) + return err; } spin_unlock(&xattrs->lock); - return used; + return size - remaining_size; } /* diff --git a/fs/xfs/xfs_acl.c b/fs/xfs/xfs_acl.c index 6bb470f..2d5df1f 100644 --- a/fs/xfs/xfs_acl.c +++ b/fs/xfs/xfs_acl.c @@ -252,29 +252,6 @@ xfs_set_mode(struct inode *inode, umode_t mode) return error; } -static int -xfs_acl_exists(struct inode *inode, unsigned char *name) -{ - int len = XFS_ACL_MAX_SIZE(XFS_M(inode->i_sb)); - - return (xfs_attr_get(XFS_I(inode), name, NULL, &len, - ATTR_ROOT|ATTR_KERNOVAL) == 0); -} - -int -posix_acl_access_exists(struct inode *inode) -{ - return xfs_acl_exists(inode, SGI_ACL_FILE); -} - -int -posix_acl_default_exists(struct inode *inode) -{ - if (!S_ISDIR(inode->i_mode)) - return 0; - return xfs_acl_exists(inode, SGI_ACL_DEFAULT); -} - int xfs_set_acl(struct inode *inode, struct posix_acl *acl, int type) { diff --git a/fs/xfs/xfs_acl.h b/fs/xfs/xfs_acl.h index 52f8255..286fa89 100644 --- a/fs/xfs/xfs_acl.h +++ b/fs/xfs/xfs_acl.h @@ -24,16 +24,12 @@ struct posix_acl; #ifdef CONFIG_XFS_POSIX_ACL extern struct posix_acl *xfs_get_acl(struct inode *inode, int type); extern int xfs_set_acl(struct inode *inode, struct posix_acl *acl, int type); -extern int posix_acl_access_exists(struct inode *inode); -extern int posix_acl_default_exists(struct inode *inode); #else static inline struct posix_acl *xfs_get_acl(struct inode *inode, int type) { return NULL; } # define xfs_set_acl NULL -# define posix_acl_access_exists(inode) 0 -# define posix_acl_default_exists(inode) 0 #endif /* CONFIG_XFS_POSIX_ACL */ extern void xfs_forget_acl(struct inode *inode, const char *name, int xflags); diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index 3243cdf..ace91e7 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -1632,13 +1632,9 @@ xfs_setsize_buftarg( btp->bt_meta_sectormask = sectorsize - 1; if (set_blocksize(btp->bt_bdev, sectorsize)) { - char name[BDEVNAME_SIZE]; - - bdevname(btp->bt_bdev, name); - xfs_warn(btp->bt_mount, - "Cannot set_blocksize to %u on device %s", - sectorsize, name); + "Cannot set_blocksize to %u on device %pg", + sectorsize, btp->bt_bdev); return -EINVAL; } diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index 245268a..06eafaf 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -414,13 +414,17 @@ xfs_vn_rename( * uio is kmalloced for this reason... */ STATIC const char * -xfs_vn_follow_link( +xfs_vn_get_link( struct dentry *dentry, - void **cookie) + struct inode *inode, + struct delayed_call *done) { char *link; int error = -ENOMEM; + if (!dentry) + return ERR_PTR(-ECHILD); + link = kmalloc(MAXPATHLEN+1, GFP_KERNEL); if (!link) goto out_err; @@ -429,7 +433,8 @@ xfs_vn_follow_link( if (unlikely(error)) goto out_kfree; - return *cookie = link; + set_delayed_call(done, kfree_link, link); + return link; out_kfree: kfree(link); @@ -1172,8 +1177,7 @@ static const struct inode_operations xfs_dir_ci_inode_operations = { static const struct inode_operations xfs_symlink_inode_operations = { .readlink = generic_readlink, - .follow_link = xfs_vn_follow_link, - .put_link = kfree_put_link, + .get_link = xfs_vn_get_link, .getattr = xfs_vn_getattr, .setattr = xfs_vn_setattr, .setxattr = generic_setxattr, diff --git a/fs/xfs/xfs_xattr.c b/fs/xfs/xfs_xattr.c index 839b35c..110f1d7 100644 --- a/fs/xfs/xfs_xattr.c +++ b/fs/xfs/xfs_xattr.c @@ -39,9 +39,6 @@ xfs_xattr_get(const struct xattr_handler *handler, struct dentry *dentry, struct xfs_inode *ip = XFS_I(d_inode(dentry)); int error, asize = size; - if (strcmp(name, "") == 0) - return -EINVAL; - /* Convert Linux syscall to XFS internal ATTR flags */ if (!size) { xflags |= ATTR_KERNOVAL; @@ -84,9 +81,6 @@ xfs_xattr_set(const struct xattr_handler *handler, struct dentry *dentry, struct xfs_inode *ip = XFS_I(d_inode(dentry)); int error; - if (strcmp(name, "") == 0) - return -EINVAL; - /* Convert Linux syscall to XFS internal ATTR flags */ if (flags & XATTR_CREATE) xflags |= ATTR_CREATE; @@ -135,47 +129,19 @@ const struct xattr_handler *xfs_xattr_handlers[] = { NULL }; -static unsigned int xfs_xattr_prefix_len(int flags) -{ - if (flags & XFS_ATTR_SECURE) - return sizeof("security"); - else if (flags & XFS_ATTR_ROOT) - return sizeof("trusted"); - else - return sizeof("user"); -} - -static const char *xfs_xattr_prefix(int flags) -{ - if (flags & XFS_ATTR_SECURE) - return xfs_xattr_security_handler.prefix; - else if (flags & XFS_ATTR_ROOT) - return xfs_xattr_trusted_handler.prefix; - else - return xfs_xattr_user_handler.prefix; -} - static int -xfs_xattr_put_listent( +__xfs_xattr_put_listent( struct xfs_attr_list_context *context, - int flags, - unsigned char *name, - int namelen, - int valuelen, - unsigned char *value) + char *prefix, + int prefix_len, + unsigned char *name, + int namelen) { - unsigned int prefix_len = xfs_xattr_prefix_len(flags); char *offset; int arraytop; - ASSERT(context->count >= 0); - - /* - * Only show root namespace entries if we are actually allowed to - * see them. - */ - if ((flags & XFS_ATTR_ROOT) && !capable(CAP_SYS_ADMIN)) - return 0; + if (!context->alist) + goto compute_size; arraytop = context->count + prefix_len + namelen + 1; if (arraytop > context->firstu) { @@ -183,17 +149,19 @@ xfs_xattr_put_listent( return 1; } offset = (char *)context->alist + context->count; - strncpy(offset, xfs_xattr_prefix(flags), prefix_len); + strncpy(offset, prefix, prefix_len); offset += prefix_len; strncpy(offset, (char *)name, namelen); /* real name */ offset += namelen; *offset = '\0'; + +compute_size: context->count += prefix_len + namelen + 1; return 0; } static int -xfs_xattr_put_listent_sizes( +xfs_xattr_put_listent( struct xfs_attr_list_context *context, int flags, unsigned char *name, @@ -201,24 +169,55 @@ xfs_xattr_put_listent_sizes( int valuelen, unsigned char *value) { - context->count += xfs_xattr_prefix_len(flags) + namelen + 1; - return 0; -} + char *prefix; + int prefix_len; -static int -list_one_attr(const char *name, const size_t len, void *data, - size_t size, ssize_t *result) -{ - char *p = data + *result; + ASSERT(context->count >= 0); - *result += len; - if (!size) - return 0; - if (*result > size) - return -ERANGE; + if (flags & XFS_ATTR_ROOT) { +#ifdef CONFIG_XFS_POSIX_ACL + if (namelen == SGI_ACL_FILE_SIZE && + strncmp(name, SGI_ACL_FILE, + SGI_ACL_FILE_SIZE) == 0) { + int ret = __xfs_xattr_put_listent( + context, XATTR_SYSTEM_PREFIX, + XATTR_SYSTEM_PREFIX_LEN, + XATTR_POSIX_ACL_ACCESS, + strlen(XATTR_POSIX_ACL_ACCESS)); + if (ret) + return ret; + } else if (namelen == SGI_ACL_DEFAULT_SIZE && + strncmp(name, SGI_ACL_DEFAULT, + SGI_ACL_DEFAULT_SIZE) == 0) { + int ret = __xfs_xattr_put_listent( + context, XATTR_SYSTEM_PREFIX, + XATTR_SYSTEM_PREFIX_LEN, + XATTR_POSIX_ACL_DEFAULT, + strlen(XATTR_POSIX_ACL_DEFAULT)); + if (ret) + return ret; + } +#endif - strcpy(p, name); - return 0; + /* + * Only show root namespace entries if we are actually allowed to + * see them. + */ + if (!capable(CAP_SYS_ADMIN)) + return 0; + + prefix = XATTR_TRUSTED_PREFIX; + prefix_len = XATTR_TRUSTED_PREFIX_LEN; + } else if (flags & XFS_ATTR_SECURE) { + prefix = XATTR_SECURITY_PREFIX; + prefix_len = XATTR_SECURITY_PREFIX_LEN; + } else { + prefix = XATTR_USER_PREFIX; + prefix_len = XATTR_USER_PREFIX_LEN; + } + + return __xfs_xattr_put_listent(context, prefix, prefix_len, name, + namelen); } ssize_t @@ -227,7 +226,6 @@ xfs_vn_listxattr(struct dentry *dentry, char *data, size_t size) struct xfs_attr_list_context context; struct attrlist_cursor_kern cursor = { 0 }; struct inode *inode = d_inode(dentry); - int error; /* * First read the regular on-disk attributes. @@ -236,37 +234,14 @@ xfs_vn_listxattr(struct dentry *dentry, char *data, size_t size) context.dp = XFS_I(inode); context.cursor = &cursor; context.resynch = 1; - context.alist = data; + context.alist = size ? data : NULL; context.bufsize = size; context.firstu = context.bufsize; - - if (size) - context.put_listent = xfs_xattr_put_listent; - else - context.put_listent = xfs_xattr_put_listent_sizes; + context.put_listent = xfs_xattr_put_listent; xfs_attr_list_int(&context); if (context.count < 0) return -ERANGE; - /* - * Then add the two synthetic ACL attributes. - */ - if (posix_acl_access_exists(inode)) { - error = list_one_attr(POSIX_ACL_XATTR_ACCESS, - strlen(POSIX_ACL_XATTR_ACCESS) + 1, - data, size, &context.count); - if (error) - return error; - } - - if (posix_acl_default_exists(inode)) { - error = list_one_attr(POSIX_ACL_XATTR_DEFAULT, - strlen(POSIX_ACL_XATTR_DEFAULT) + 1, - data, size, &context.count); - if (error) - return error; - } - return context.count; } |