diff options
Diffstat (limited to 'fs')
74 files changed, 1012 insertions, 445 deletions
diff --git a/fs/9p/v9fs.c b/fs/9p/v9fs.c index 45c35986d49..0a7068e30ec 100644 --- a/fs/9p/v9fs.c +++ b/fs/9p/v9fs.c @@ -131,7 +131,9 @@ static void v9fs_parse_options(char *options, struct v9fs_session_info *v9ses) switch (token) { case Opt_debug: v9ses->debug = option; +#ifdef CONFIG_NET_9P_DEBUG p9_debug_level = option; +#endif break; case Opt_port: v9ses->port = option; diff --git a/fs/Kconfig b/fs/Kconfig index ee11f8d9408..613df554728 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -1675,6 +1675,7 @@ config NFSD_V3_ACL config NFSD_V4 bool "Provide NFSv4 server support (EXPERIMENTAL)" depends on NFSD_V3 && EXPERIMENTAL + select RPCSEC_GSS_KRB5 help If you would like to include the NFSv4 server as well as the NFSv2 and NFSv3 servers, say Y here. This feature is experimental, and diff --git a/fs/anon_inodes.c b/fs/anon_inodes.c index a260198306c..b4a75880f6f 100644 --- a/fs/anon_inodes.c +++ b/fs/anon_inodes.c @@ -139,6 +139,7 @@ err_put_filp: put_filp(file); return error; } +EXPORT_SYMBOL_GPL(anon_inode_getfd); /* * A single inode exists for all anon_inode files. Contrary to pipes, diff --git a/fs/attr.c b/fs/attr.c index a0a0c7b07ba..f8dfc2269d8 100644 --- a/fs/attr.c +++ b/fs/attr.c @@ -42,7 +42,7 @@ int inode_change_ok(struct inode *inode, struct iattr *attr) /* Make sure a caller can chmod. */ if (ia_valid & ATTR_MODE) { - if ((current->fsuid != inode->i_uid) && !capable(CAP_FOWNER)) + if (!is_owner_or_cap(inode)) goto error; /* Also check the setgid bit! */ if (!in_group_p((ia_valid & ATTR_GID) ? attr->ia_gid : @@ -52,7 +52,7 @@ int inode_change_ok(struct inode *inode, struct iattr *attr) /* Check for setting the inode time. */ if (ia_valid & (ATTR_MTIME_SET | ATTR_ATIME_SET)) { - if (current->fsuid != inode->i_uid && !capable(CAP_FOWNER)) + if (!is_owner_or_cap(inode)) goto error; } fine: diff --git a/fs/buffer.c b/fs/buffer.c index 424165b569f..0f900671423 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -356,7 +356,7 @@ static void free_more_memory(void) for_each_online_pgdat(pgdat) { zones = pgdat->node_zonelists[gfp_zone(GFP_NOFS)].zones; if (*zones) - try_to_free_pages(zones, GFP_NOFS); + try_to_free_pages(zones, 0, GFP_NOFS); } } @@ -676,6 +676,39 @@ void mark_buffer_dirty_inode(struct buffer_head *bh, struct inode *inode) EXPORT_SYMBOL(mark_buffer_dirty_inode); /* + * Mark the page dirty, and set it dirty in the radix tree, and mark the inode + * dirty. + * + * If warn is true, then emit a warning if the page is not uptodate and has + * not been truncated. + */ +static int __set_page_dirty(struct page *page, + struct address_space *mapping, int warn) +{ + if (unlikely(!mapping)) + return !TestSetPageDirty(page); + + if (TestSetPageDirty(page)) + return 0; + + write_lock_irq(&mapping->tree_lock); + if (page->mapping) { /* Race with truncate? */ + WARN_ON_ONCE(warn && !PageUptodate(page)); + + if (mapping_cap_account_dirty(mapping)) { + __inc_zone_page_state(page, NR_FILE_DIRTY); + task_io_account_write(PAGE_CACHE_SIZE); + } + radix_tree_tag_set(&mapping->page_tree, + page_index(page), PAGECACHE_TAG_DIRTY); + } + write_unlock_irq(&mapping->tree_lock); + __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); + + return 1; +} + +/* * Add a page to the dirty page list. * * It is a sad fact of life that this function is called from several places @@ -702,7 +735,7 @@ EXPORT_SYMBOL(mark_buffer_dirty_inode); */ int __set_page_dirty_buffers(struct page *page) { - struct address_space * const mapping = page_mapping(page); + struct address_space *mapping = page_mapping(page); if (unlikely(!mapping)) return !TestSetPageDirty(page); @@ -719,21 +752,7 @@ int __set_page_dirty_buffers(struct page *page) } spin_unlock(&mapping->private_lock); - if (TestSetPageDirty(page)) - return 0; - - write_lock_irq(&mapping->tree_lock); - if (page->mapping) { /* Race with truncate? */ - if (mapping_cap_account_dirty(mapping)) { - __inc_zone_page_state(page, NR_FILE_DIRTY); - task_io_account_write(PAGE_CACHE_SIZE); - } - radix_tree_tag_set(&mapping->page_tree, - page_index(page), PAGECACHE_TAG_DIRTY); - } - write_unlock_irq(&mapping->tree_lock); - __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); - return 1; + return __set_page_dirty(page, mapping, 1); } EXPORT_SYMBOL(__set_page_dirty_buffers); @@ -982,7 +1001,7 @@ grow_dev_page(struct block_device *bdev, sector_t block, struct buffer_head *bh; page = find_or_create_page(inode->i_mapping, index, - mapping_gfp_mask(inode->i_mapping) & ~__GFP_FS); + (mapping_gfp_mask(inode->i_mapping) & ~__GFP_FS)|__GFP_MOVABLE); if (!page) return NULL; @@ -1132,8 +1151,9 @@ __getblk_slow(struct block_device *bdev, sector_t block, int size) */ void fastcall mark_buffer_dirty(struct buffer_head *bh) { + WARN_ON_ONCE(!buffer_uptodate(bh)); if (!buffer_dirty(bh) && !test_set_buffer_dirty(bh)) - __set_page_dirty_nobuffers(bh->b_page); + __set_page_dirty(bh->b_page, page_mapping(bh->b_page), 0); } /* diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index 8b0cbf4a4ad..bd0f2f2353c 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -849,6 +849,7 @@ static int cifs_oplock_thread(void * dummyarg) __u16 netfid; int rc; + set_freezable(); do { if (try_to_freeze()) continue; diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index f4e92661b22..0a1b8bd1dfc 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -363,6 +363,7 @@ cifs_demultiplex_thread(struct TCP_Server_Info *server) GFP_KERNEL); } + set_freezable(); while (!kthread_should_stop()) { if (try_to_freeze()) continue; diff --git a/fs/cifs/export.c b/fs/cifs/export.c index 1d716392c3a..96df1d51fdc 100644 --- a/fs/cifs/export.c +++ b/fs/cifs/export.c @@ -29,6 +29,7 @@ */ #include <linux/fs.h> +#include <linux/exportfs.h> #ifdef CONFIG_CIFS_EXPERIMENTAL diff --git a/fs/dcache.c b/fs/dcache.c index 0e73aa0a0e8..cb9d05056b5 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -883,6 +883,11 @@ static int shrink_dcache_memory(int nr, gfp_t gfp_mask) return (dentry_stat.nr_unused / 100) * sysctl_vfs_cache_pressure; } +static struct shrinker dcache_shrinker = { + .shrink = shrink_dcache_memory, + .seeks = DEFAULT_SEEKS, +}; + /** * d_alloc - allocate a dcache entry * @parent: parent of entry to allocate @@ -2115,7 +2120,7 @@ static void __init dcache_init(unsigned long mempages) dentry_cache = KMEM_CACHE(dentry, SLAB_RECLAIM_ACCOUNT|SLAB_PANIC|SLAB_MEM_SPREAD); - set_shrinker(DEFAULT_SEEKS, shrink_dcache_memory); + register_shrinker(&dcache_shrinker); /* Hash may have been set up in dcache_init_early */ if (!hashdist) diff --git a/fs/dquot.c b/fs/dquot.c index 8819d281500..7e273151f58 100644 --- a/fs/dquot.c +++ b/fs/dquot.c @@ -538,6 +538,11 @@ static int shrink_dqcache_memory(int nr, gfp_t gfp_mask) return (dqstats.free_dquots / 100) * sysctl_vfs_cache_pressure; } +static struct shrinker dqcache_shrinker = { + .shrink = shrink_dqcache_memory, + .seeks = DEFAULT_SEEKS, +}; + /* * Put reference to dquot * NOTE: If you change this function please check whether dqput_blocks() works right... @@ -1870,7 +1875,7 @@ static int __init dquot_init(void) printk("Dquot-cache hash table entries: %ld (order %ld, %ld bytes)\n", nr_hash, order, (PAGE_SIZE << order)); - set_shrinker(DEFAULT_SEEKS, shrink_dqcache_memory); + register_shrinker(&dqcache_shrinker); return 0; } diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c index 83e94fedd4e..e77a2ec71aa 100644 --- a/fs/ecryptfs/inode.c +++ b/fs/ecryptfs/inode.c @@ -282,7 +282,7 @@ static struct dentry *ecryptfs_lookup(struct inode *dir, struct dentry *dentry, struct dentry *lower_dentry; struct vfsmount *lower_mnt; char *encoded_name; - unsigned int encoded_namelen; + int encoded_namelen; struct ecryptfs_crypt_stat *crypt_stat = NULL; struct ecryptfs_mount_crypt_stat *mount_crypt_stat; char *page_virt = NULL; @@ -473,7 +473,7 @@ static int ecryptfs_symlink(struct inode *dir, struct dentry *dentry, struct dentry *lower_dir_dentry; umode_t mode; char *encoded_symname; - unsigned int encoded_symlen; + int encoded_symlen; struct ecryptfs_crypt_stat *crypt_stat = NULL; lower_dentry = ecryptfs_dentry_to_lower(dentry); diff --git a/fs/efs/namei.c b/fs/efs/namei.c index ed4a207fe22..5276b19423c 100644 --- a/fs/efs/namei.c +++ b/fs/efs/namei.c @@ -75,6 +75,38 @@ struct dentry *efs_lookup(struct inode *dir, struct dentry *dentry, struct namei return NULL; } +struct dentry *efs_get_dentry(struct super_block *sb, void *vobjp) +{ + __u32 *objp = vobjp; + unsigned long ino = objp[0]; + __u32 generation = objp[1]; + struct inode *inode; + struct dentry *result; + + if (ino == 0) + return ERR_PTR(-ESTALE); + inode = iget(sb, ino); + if (inode == NULL) + return ERR_PTR(-ENOMEM); + + if (is_bad_inode(inode) || + (generation && inode->i_generation != generation)) { + result = ERR_PTR(-ESTALE); + goto out_iput; + } + + result = d_alloc_anon(inode); + if (!result) { + result = ERR_PTR(-ENOMEM); + goto out_iput; + } + return result; + + out_iput: + iput(inode); + return result; +} + struct dentry *efs_get_parent(struct dentry *child) { struct dentry *parent; diff --git a/fs/efs/super.c b/fs/efs/super.c index e0a6839e68a..d360c81f3a7 100644 --- a/fs/efs/super.c +++ b/fs/efs/super.c @@ -11,6 +11,7 @@ #include <linux/efs_fs.h> #include <linux/efs_vh.h> #include <linux/efs_fs_sb.h> +#include <linux/exportfs.h> #include <linux/slab.h> #include <linux/buffer_head.h> #include <linux/vfs.h> @@ -113,6 +114,7 @@ static const struct super_operations efs_superblock_operations = { }; static struct export_operations efs_export_ops = { + .get_dentry = efs_get_dentry, .get_parent = efs_get_parent, }; diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c index e98f6cd7200..8adb32a9387 100644 --- a/fs/exportfs/expfs.c +++ b/fs/exportfs/expfs.c @@ -1,15 +1,45 @@ +#include <linux/exportfs.h> #include <linux/fs.h> #include <linux/file.h> #include <linux/module.h> +#include <linux/mount.h> #include <linux/namei.h> -struct export_operations export_op_default; +#define dprintk(fmt, args...) do{}while(0) -#define CALL(ops,fun) ((ops->fun)?(ops->fun):export_op_default.fun) -#define dprintk(fmt, args...) do{}while(0) +static int get_name(struct dentry *dentry, char *name, + struct dentry *child); + + +static struct dentry *exportfs_get_dentry(struct super_block *sb, void *obj) +{ + struct dentry *result = ERR_PTR(-ESTALE); + + if (sb->s_export_op->get_dentry) { + result = sb->s_export_op->get_dentry(sb, obj); + if (!result) + result = ERR_PTR(-ESTALE); + } + + return result; +} + +static int exportfs_get_name(struct dentry *dir, char *name, + struct dentry *child) +{ + struct export_operations *nop = dir->d_sb->s_export_op; + if (nop->get_name) + return nop->get_name(dir, name, child); + else + return get_name(dir, name, child); +} + +/* + * Check if the dentry or any of it's aliases is acceptable. + */ static struct dentry * find_acceptable_alias(struct dentry *result, int (*acceptable)(void *context, struct dentry *dentry), @@ -17,6 +47,9 @@ find_acceptable_alias(struct dentry *result, { struct dentry *dentry, *toput = NULL; + if (acceptable(context, result)) + return result; + spin_lock(&dcache_lock); list_for_each_entry(dentry, &result->d_inode->i_dentry, d_alias) { dget_locked(dentry); @@ -37,130 +70,50 @@ find_acceptable_alias(struct dentry *result, return NULL; } -/** - * find_exported_dentry - helper routine to implement export_operations->decode_fh - * @sb: The &super_block identifying the filesystem - * @obj: An opaque identifier of the object to be found - passed to - * get_inode - * @parent: An optional opqaue identifier of the parent of the object. - * @acceptable: A function used to test possible &dentries to see if they are - * acceptable - * @context: A parameter to @acceptable so that it knows on what basis to - * judge. - * - * find_exported_dentry is the central helper routine to enable file systems - * to provide the decode_fh() export_operation. It's main task is to take - * an &inode, find or create an appropriate &dentry structure, and possibly - * splice this into the dcache in the correct place. - * - * The decode_fh() operation provided by the filesystem should call - * find_exported_dentry() with the same parameters that it received except - * that instead of the file handle fragment, pointers to opaque identifiers - * for the object and optionally its parent are passed. The default decode_fh - * routine passes one pointer to the start of the filehandle fragment, and - * one 8 bytes into the fragment. It is expected that most filesystems will - * take this approach, though the offset to the parent identifier may well be - * different. - * - * find_exported_dentry() will call get_dentry to get an dentry pointer from - * the file system. If any &dentry in the d_alias list is acceptable, it will - * be returned. Otherwise find_exported_dentry() will attempt to splice a new - * &dentry into the dcache using get_name() and get_parent() to find the - * appropriate place. +/* + * Find root of a disconnected subtree and return a reference to it. */ - -struct dentry * -find_exported_dentry(struct super_block *sb, void *obj, void *parent, - int (*acceptable)(void *context, struct dentry *de), - void *context) +static struct dentry * +find_disconnected_root(struct dentry *dentry) { - struct dentry *result = NULL; - struct dentry *target_dir; - int err; - struct export_operations *nops = sb->s_export_op; - struct dentry *alias; - int noprogress; - char nbuf[NAME_MAX+1]; - - /* - * Attempt to find the inode. - */ - result = CALL(sb->s_export_op,get_dentry)(sb,obj); - err = -ESTALE; - if (result == NULL) - goto err_out; - if (IS_ERR(result)) { - err = PTR_ERR(result); - goto err_out; + dget(dentry); + spin_lock(&dentry->d_lock); + while (!IS_ROOT(dentry) && + (dentry->d_parent->d_flags & DCACHE_DISCONNECTED)) { + struct dentry *parent = dentry->d_parent; + dget(parent); + spin_unlock(&dentry->d_lock); + dput(dentry); + dentry = parent; + spin_lock(&dentry->d_lock); } - if (S_ISDIR(result->d_inode->i_mode) && - (result->d_flags & DCACHE_DISCONNECTED)) { - /* it is an unconnected directory, we must connect it */ - ; - } else { - if (acceptable(context, result)) - return result; - if (S_ISDIR(result->d_inode->i_mode)) { - err = -EACCES; - goto err_result; - } + spin_unlock(&dentry->d_lock); + return dentry; +} - alias = find_acceptable_alias(result, acceptable, context); - if (alias) - return alias; - } - - /* It's a directory, or we are required to confirm the file's - * location in the tree based on the parent information - */ - dprintk("find_exported_dentry: need to look harder for %s/%d\n",sb->s_id,*(int*)obj); - if (S_ISDIR(result->d_inode->i_mode)) - target_dir = dget(result); - else { - if (parent == NULL) - goto err_result; - target_dir = CALL(sb->s_export_op,get_dentry)(sb,parent); - if (IS_ERR(target_dir)) - err = PTR_ERR(target_dir); - if (target_dir == NULL || IS_ERR(target_dir)) - goto err_result; - } - /* - * Now we need to make sure that target_dir is properly connected. - * It may already be, as the flag isn't always updated when connection - * happens. - * So, we walk up parent links until we find a connected directory, - * or we run out of directories. Then we find the parent, find - * the name of the child in that parent, and do a lookup. - * This should connect the child into the parent - * We then repeat. - */ +/* + * Make sure target_dir is fully connected to the dentry tree. + * + * It may already be, as the flag isn't always updated when connection happens. + */ +static int +reconnect_path(struct super_block *sb, struct dentry *target_dir) +{ + char nbuf[NAME_MAX+1]; + int noprogress = 0; + int err = -ESTALE; - /* it is possible that a confused file system might not let us complete + /* + * It is possible that a confused file system might not let us complete * the path to the root. For example, if get_parent returns a directory * in which we cannot find a name for the child. While this implies a * very sick filesystem we don't want it to cause knfsd to spin. Hence * the noprogress counter. If we go through the loop 10 times (2 is * probably enough) without getting anywhere, we just give up */ - noprogress= 0; while (target_dir->d_flags & DCACHE_DISCONNECTED && noprogress++ < 10) { - struct dentry *pd = target_dir; - - dget(pd); - spin_lock(&pd->d_lock); - while (!IS_ROOT(pd) && - (pd->d_parent->d_flags&DCACHE_DISCONNECTED)) { - struct dentry *parent = pd->d_parent; - - dget(parent); - spin_unlock(&pd->d_lock); - dput(pd); - pd = parent; - spin_lock(&pd->d_lock); - } - spin_unlock(&pd->d_lock); + struct dentry *pd = find_disconnected_root(target_dir); if (!IS_ROOT(pd)) { /* must have found a connected parent - great */ @@ -175,29 +128,40 @@ find_exported_dentry(struct super_block *sb, void *obj, void *parent, spin_unlock(&pd->d_lock); noprogress = 0; } else { - /* we have hit the top of a disconnected path. Try - * to find parent and connect - * note: racing with some other process renaming a - * directory isn't much of a problem here. If someone - * renames the directory, it will end up properly - * connected, which is what we want + /* + * We have hit the top of a disconnected path, try to + * find parent and connect. + * + * Racing with some other process renaming a directory + * isn't much of a problem here. If someone renames + * the directory, it will end up properly connected, + * which is what we want + * + * Getting the parent can't be supported generically, + * the locking is too icky. + * + * Instead we just return EACCES. If server reboots + * or inodes get flushed, you lose */ - struct dentry *ppd; + struct dentry *ppd = ERR_PTR(-EACCES); struct dentry *npd; mutex_lock(&pd->d_inode->i_mutex); - ppd = CALL(nops,get_parent)(pd); + if (sb->s_export_op->get_parent) + ppd = sb->s_export_op->get_parent(pd); mutex_unlock(&pd->d_inode->i_mutex); if (IS_ERR(ppd)) { err = PTR_ERR(ppd); - dprintk("find_exported_dentry: get_parent of %ld failed, err %d\n", - pd->d_inode->i_ino, err); + dprintk("%s: get_parent of %ld failed, err %d\n", + __FUNCTION__, pd->d_inode->i_ino, err); dput(pd); break; } - dprintk("find_exported_dentry: find name of %lu in %lu\n", pd->d_inode->i_ino, ppd->d_inode->i_ino); - err = CALL(nops,get_name)(ppd, nbuf, pd); + + dprintk("%s: find name of %lu in %lu\n", __FUNCTION__, + pd->d_inode->i_ino, ppd->d_inode->i_ino); + err = exportfs_get_name(ppd, nbuf, pd); if (err) { dput(ppd); dput(pd); @@ -208,13 +172,14 @@ find_exported_dentry(struct super_block *sb, void *obj, void *parent, continue; break; } - dprintk("find_exported_dentry: found name: %s\n", nbuf); + dprintk("%s: found name: %s\n", __FUNCTION__, nbuf); mutex_lock(&ppd->d_inode->i_mutex); npd = lookup_one_len(nbuf, ppd, strlen(nbuf)); mutex_unlock(&ppd->d_inode->i_mutex); if (IS_ERR(npd)) { err = PTR_ERR(npd); - dprintk("find_exported_dentry: lookup failed: %d\n", err); + dprintk("%s: lookup failed: %d\n", + __FUNCTION__, err); dput(ppd); dput(pd); break; @@ -227,7 +192,7 @@ find_exported_dentry(struct super_block *sb, void *obj, void *parent, if (npd == pd) noprogress = 0; else - printk("find_exported_dentry: npd != pd\n"); + printk("%s: npd != pd\n", __FUNCTION__); dput(npd); dput(ppd); if (IS_ROOT(pd)) { @@ -243,15 +208,101 @@ find_exported_dentry(struct super_block *sb, void *obj, void *parent, /* something went wrong - oh-well */ if (!err) err = -ESTALE; - goto err_target; + return err; } - /* if we weren't after a directory, have one more step to go */ - if (result != target_dir) { - struct dentry *nresult; - err = CALL(nops,get_name)(target_dir, nbuf, result); + + return 0; +} + +/** + * find_exported_dentry - helper routine to implement export_operations->decode_fh + * @sb: The &super_block identifying the filesystem + * @obj: An opaque identifier of the object to be found - passed to + * get_inode + * @parent: An optional opqaue identifier of the parent of the object. + * @acceptable: A function used to test possible &dentries to see if they are + * acceptable + * @context: A parameter to @acceptable so that it knows on what basis to + * judge. + * + * find_exported_dentry is the central helper routine to enable file systems + * to provide the decode_fh() export_operation. It's main task is to take + * an &inode, find or create an appropriate &dentry structure, and possibly + * splice this into the dcache in the correct place. + * + * The decode_fh() operation provided by the filesystem should call + * find_exported_dentry() with the same parameters that it received except + * that instead of the file handle fragment, pointers to opaque identifiers + * for the object and optionally its parent are passed. The default decode_fh + * routine passes one pointer to the start of the filehandle fragment, and + * one 8 bytes into the fragment. It is expected that most filesystems will + * take this approach, though the offset to the parent identifier may well be + * different. + * + * find_exported_dentry() will call get_dentry to get an dentry pointer from + * the file system. If any &dentry in the d_alias list is acceptable, it will + * be returned. Otherwise find_exported_dentry() will attempt to splice a new + * &dentry into the dcache using get_name() and get_parent() to find the + * appropriate place. + */ + +struct dentry * +find_exported_dentry(struct super_block *sb, void *obj, void *parent, + int (*acceptable)(void *context, struct dentry *de), + void *context) +{ + struct dentry *result, *alias; + int err = -ESTALE; + + /* + * Attempt to find the inode. + */ + result = exportfs_get_dentry(sb, obj); + if (IS_ERR(result)) + return result; + + if (S_ISDIR(result->d_inode->i_mode)) { + if (!(result->d_flags & DCACHE_DISCONNECTED)) { + if (acceptable(context, result)) + return result; + err = -EACCES; + goto err_result; + } + + err = reconnect_path(sb, result); + if (err) + goto err_result; + } else { + struct dentry *target_dir, *nresult; + char nbuf[NAME_MAX+1]; + + alias = find_acceptable_alias(result, acceptable, context); + if (alias) + return alias; + + if (parent == NULL) + goto err_result; + + target_dir = exportfs_get_dentry(sb,parent); + if (IS_ERR(target_dir)) { + err = PTR_ERR(target_dir); + goto err_result; + } + + err = reconnect_path(sb, target_dir); + if (err) { + dput(target_dir); + goto err_result; + } + + /* + * As we weren't after a directory, have one more step to go. + */ + err = exportfs_get_name(target_dir, nbuf, result); if (!err) { mutex_lock(&target_dir->d_inode->i_mutex); - nresult = lookup_one_len(nbuf, target_dir, strlen(nbuf)); + nresult = lookup_one_len(nbuf, target_dir, + strlen(nbuf)); mutex_unlock(&target_dir->d_inode->i_mutex); if (!IS_ERR(nresult)) { if (nresult->d_inode) { @@ -261,11 +312,8 @@ find_exported_dentry(struct super_block *sb, void *obj, void *parent, dput(nresult); } } + dput(target_dir); } - dput(target_dir); - /* now result is properly connected, it is our best bet */ - if (acceptable(context, result)) - return result; alias = find_acceptable_alias(result, acceptable, context); if (alias) @@ -275,32 +323,16 @@ find_exported_dentry(struct super_block *sb, void *obj, void *parent, dput(result); /* It might be justifiable to return ESTALE here, * but the filehandle at-least looks reasonable good - * and it just be a permission problem, so returning + * and it may just be a permission problem, so returning * -EACCESS is safer */ return ERR_PTR(-EACCES); - err_target: - dput(target_dir); err_result: dput(result); - err_out: return ERR_PTR(err); } - - -static struct dentry *get_parent(struct dentry *child) -{ - /* get_parent cannot be supported generically, the locking - * is too icky. - * instead, we just return EACCES. If server reboots or inodes - * get flushed, you lose - */ - return ERR_PTR(-EACCES); -} - - struct getdents_callback { char *name; /* name that was found. It already points to a buffer NAME_MAX+1 is size */ @@ -390,61 +422,6 @@ out: return error; } - -static struct dentry *export_iget(struct super_block *sb, unsigned long ino, __u32 generation) -{ - - /* iget isn't really right if the inode is currently unallocated!! - * This should really all be done inside each filesystem - * - * ext2fs' read_inode has been strengthed to return a bad_inode if - * the inode had been deleted. - * - * Currently we don't know the generation for parent directory, so - * a generation of 0 means "accept any" - */ - struct inode *inode; - struct dentry *result; - if (ino == 0) - return ERR_PTR(-ESTALE); - inode = iget(sb, ino); - if (inode == NULL) - return ERR_PTR(-ENOMEM); - if (is_bad_inode(inode) - || (generation && inode->i_generation != generation) - ) { - /* we didn't find the right inode.. */ - dprintk("fh_verify: Inode %lu, Bad count: %d %d or version %u %u\n", - inode->i_ino, - inode->i_nlink, atomic_read(&inode->i_count), - inode->i_generation, - generation); - - iput(inode); - return ERR_PTR(-ESTALE); - } - /* now to find a dentry. - * If possible, get a well-connected one - */ - result = d_alloc_anon(inode); - if (!result) { - iput(inode); - return ERR_PTR(-ENOMEM); - } - return result; -} - - -static struct dentry *get_object(struct super_block *sb, void *vobjp) -{ - __u32 *objp = vobjp; - unsigned long ino = objp[0]; - __u32 generation = objp[1]; - - return export_iget(sb, ino, generation); -} - - /** * export_encode_fh - default export_operations->encode_fh function * @dentry: the dentry to encode @@ -517,16 +494,40 @@ static struct dentry *export_decode_fh(struct super_block *sb, __u32 *fh, int fh acceptable, context); } -struct export_operations export_op_default = { - .decode_fh = export_decode_fh, - .encode_fh = export_encode_fh, +int exportfs_encode_fh(struct dentry *dentry, __u32 *fh, int *max_len, + int connectable) +{ + struct export_operations *nop = dentry->d_sb->s_export_op; + int error; + + if (nop->encode_fh) + error = nop->encode_fh(dentry, fh, max_len, connectable); + else + error = export_encode_fh(dentry, fh, max_len, connectable); - .get_name = get_name, - .get_parent = get_parent, - .get_dentry = get_object, -}; + return error; +} +EXPORT_SYMBOL_GPL(exportfs_encode_fh); + +struct dentry *exportfs_decode_fh(struct vfsmount *mnt, __u32 *fh, int fh_len, + int fileid_type, int (*acceptable)(void *, struct dentry *), + void *context) +{ + struct export_operations *nop = mnt->mnt_sb->s_export_op; + struct dentry *result; + + if (nop->decode_fh) { + result = nop->decode_fh(mnt->mnt_sb, fh, fh_len, fileid_type, + acceptable, context); + } else { + result = export_decode_fh(mnt->mnt_sb, fh, fh_len, fileid_type, + acceptable, context); + } + + return result; +} +EXPORT_SYMBOL_GPL(exportfs_decode_fh); -EXPORT_SYMBOL(export_op_default); EXPORT_SYMBOL(find_exported_dentry); MODULE_LICENSE("GPL"); diff --git a/fs/ext2/acl.c b/fs/ext2/acl.c index 7c420b800c3..e58669e1b87 100644 --- a/fs/ext2/acl.c +++ b/fs/ext2/acl.c @@ -464,7 +464,7 @@ ext2_xattr_set_acl(struct inode *inode, int type, const void *value, if (!test_opt(inode->i_sb, POSIX_ACL)) return -EOPNOTSUPP; - if ((current->fsuid != inode->i_uid) && !capable(CAP_FOWNER)) + if (!is_owner_or_cap(inode)) return -EPERM; if (value) { diff --git a/fs/ext2/ioctl.c b/fs/ext2/ioctl.c index e85c4821823..3bcd25422ee 100644 --- a/fs/ext2/ioctl.c +++ b/fs/ext2/ioctl.c @@ -36,7 +36,7 @@ int ext2_ioctl (struct inode * inode, struct file * filp, unsigned int cmd, if (IS_RDONLY(inode)) return -EROFS; - if ((current->fsuid != inode->i_uid) && !capable(CAP_FOWNER)) + if (!is_owner_or_cap(inode)) return -EACCES; if (get_user(flags, (int __user *) arg)) @@ -74,7 +74,7 @@ int ext2_ioctl (struct inode * inode, struct file * filp, unsigned int cmd, case EXT2_IOC_GETVERSION: return put_user(inode->i_generation, (int __user *) arg); case EXT2_IOC_SETVERSION: - if ((current->fsuid != inode->i_uid) && !capable(CAP_FOWNER)) + if (!is_owner_or_cap(inode)) return -EPERM; if (IS_RDONLY(inode)) return -EROFS; diff --git a/fs/ext2/super.c b/fs/ext2/super.c index b2efd9083b9..3eefa97fe20 100644 --- a/fs/ext2/super.c +++ b/fs/ext2/super.c @@ -25,6 +25,7 @@ #include <linux/parser.h> #include <linux/random.h> #include <linux/buffer_head.h> +#include <linux/exportfs.h> #include <linux/smp_lock.h> #include <linux/vfs.h> #include <linux/seq_file.h> diff --git a/fs/ext3/acl.c b/fs/ext3/acl.c index 1e5038d9a01..d34e9967430 100644 --- a/fs/ext3/acl.c +++ b/fs/ext3/acl.c @@ -489,7 +489,7 @@ ext3_xattr_set_acl(struct inode *inode, int type, const void *value, if (!test_opt(inode->i_sb, POSIX_ACL)) return -EOPNOTSUPP; - if ((current->fsuid != inode->i_uid) && !capable(CAP_FOWNER)) + if (!is_owner_or_cap(inode)) return -EPERM; if (value) { diff --git a/fs/ext3/ioctl.c b/fs/ext3/ioctl.c index 965006dba6b..4a2a02c95bf 100644 --- a/fs/ext3/ioctl.c +++ b/fs/ext3/ioctl.c @@ -41,7 +41,7 @@ int ext3_ioctl (struct inode * inode, struct file * filp, unsigned int cmd, if (IS_RDONLY(inode)) return -EROFS; - if ((current->fsuid != inode->i_uid) && !capable(CAP_FOWNER)) + if (!is_owner_or_cap(inode)) return -EACCES; if (get_user(flags, (int __user *) arg)) @@ -122,7 +122,7 @@ flags_err: __u32 generation; int err; - if ((current->fsuid != inode->i_uid) && !capable(CAP_FOWNER)) + if (!is_owner_or_cap(inode)) return -EPERM; if (IS_RDONLY(inode)) return -EROFS; @@ -181,7 +181,7 @@ flags_err: if (IS_RDONLY(inode)) return -EROFS; - if ((current->fsuid != inode->i_uid) && !capable(CAP_FOWNER)) + if (!is_owner_or_cap(inode)) return -EACCES; if (get_user(rsv_window_size, (int __user *)arg)) diff --git a/fs/ext3/super.c b/fs/ext3/super.c index 51d1c456cda..4f84dc86628 100644 --- a/fs/ext3/super.c +++ b/fs/ext3/super.c @@ -29,6 +29,7 @@ #include <linux/parser.h> #include <linux/smp_lock.h> #include <linux/buffer_head.h> +#include <linux/exportfs.h> #include <linux/vfs.h> #include <linux/random.h> #include <linux/mount.h> diff --git a/fs/ext4/acl.c b/fs/ext4/acl.c index 9e882546d91..a8bae8cd1d5 100644 --- a/fs/ext4/acl.c +++ b/fs/ext4/acl.c @@ -489,7 +489,7 @@ ext4_xattr_set_acl(struct inode *inode, int type, const void *value, if (!test_opt(inode->i_sb, POSIX_ACL)) return -EOPNOTSUPP; - if ((current->fsuid != inode->i_uid) && !capable(CAP_FOWNER)) + if (!is_owner_or_cap(inode)) return -EPERM; if (value) { diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index 500567dd53b..7b4aa4543c8 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -40,7 +40,7 @@ int ext4_ioctl (struct inode * inode, struct file * filp, unsigned int cmd, if (IS_RDONLY(inode)) return -EROFS; - if ((current->fsuid != inode->i_uid) && !capable(CAP_FOWNER)) + if (!is_owner_or_cap(inode)) return -EACCES; if (get_user(flags, (int __user *) arg)) @@ -121,7 +121,7 @@ flags_err: __u32 generation; int err; - if ((current->fsuid != inode->i_uid) && !capable(CAP_FOWNER)) + if (!is_owner_or_cap(inode)) return -EPERM; if (IS_RDONLY(inode)) return -EROFS; @@ -180,7 +180,7 @@ flags_err: if (IS_RDONLY(inode)) return -EROFS; - if ((current->fsuid != inode->i_uid) && !capable(CAP_FOWNER)) + if (!is_owner_or_cap(inode)) return -EACCES; if (get_user(rsv_window_size, (int __user *)arg)) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index d0d8c76c7ed..b806e689c4a 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -29,6 +29,7 @@ #include <linux/parser.h> #include <linux/smp_lock.h> #include <linux/buffer_head.h> +#include <linux/exportfs.h> #include <linux/vfs.h> #include <linux/random.h> #include <linux/mount.h> diff --git a/fs/fat/inode.c b/fs/fat/inode.c index cfaf5877d98..0a7ddb39a59 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -20,6 +20,7 @@ #include <linux/pagemap.h> #include <linux/mpage.h> #include <linux/buffer_head.h> +#include <linux/exportfs.h> #include <linux/mount.h> #include <linux/vfs.h> #include <linux/parser.h> diff --git a/fs/fcntl.c b/fs/fcntl.c index 8e382a5d51b..3f22e9f4f69 100644 --- a/fs/fcntl.c +++ b/fs/fcntl.c @@ -215,7 +215,7 @@ static int setfl(int fd, struct file * filp, unsigned long arg) /* O_NOATIME can only be set by the owner or superuser */ if ((arg & O_NOATIME) && !(filp->f_flags & O_NOATIME)) - if (current->fsuid != inode->i_uid && !capable(CAP_FOWNER)) + if (!is_owner_or_cap(inode)) return -EPERM; /* required for strict SunOS emulation */ diff --git a/fs/generic_acl.c b/fs/generic_acl.c index 9ccb7894717..995d63b2e74 100644 --- a/fs/generic_acl.c +++ b/fs/generic_acl.c @@ -78,7 +78,7 @@ generic_acl_set(struct inode *inode, struct generic_acl_operations *ops, if (S_ISLNK(inode->i_mode)) return -EOPNOTSUPP; - if (current->fsuid != inode->i_uid && !capable(CAP_FOWNER)) + if (!is_owner_or_cap(inode)) return -EPERM; if (value) { acl = posix_acl_from_xattr(value, size); diff --git a/fs/gfs2/acl.c b/fs/gfs2/acl.c index 6e80844367e..1047a8c7226 100644 --- a/fs/gfs2/acl.c +++ b/fs/gfs2/acl.c @@ -74,7 +74,7 @@ int gfs2_acl_validate_remove(struct gfs2_inode *ip, int access) { if (!GFS2_SB(&ip->i_inode)->sd_args.ar_posix_acl) return -EOPNOTSUPP; - if (current->fsuid != ip->i_inode.i_uid && !capable(CAP_FOWNER)) + if (!is_owner_or_cap(&ip->i_inode)) return -EPERM; if (S_ISLNK(ip->i_inode.i_mode)) return -EOPNOTSUPP; diff --git a/fs/gfs2/ops_export.c b/fs/gfs2/ops_export.c index 99ea5659bc2..b8312edee0e 100644 --- a/fs/gfs2/ops_export.c +++ b/fs/gfs2/ops_export.c @@ -11,6 +11,7 @@ #include <linux/spinlock.h> #include <linux/completion.h> #include <linux/buffer_head.h> +#include <linux/exportfs.h> #include <linux/gfs2_ondisk.h> #include <linux/crc32.h> #include <linux/lm_interface.h> diff --git a/fs/hfsplus/ioctl.c b/fs/hfsplus/ioctl.c index 79fd10402ea..b60c0affbec 100644 --- a/fs/hfsplus/ioctl.c +++ b/fs/hfsplus/ioctl.c @@ -38,7 +38,7 @@ int hfsplus_ioctl(struct inode *inode, struct file *filp, unsigned int cmd, if (IS_RDONLY(inode)) return -EROFS; - if ((current->fsuid != inode->i_uid) && !capable(CAP_FOWNER)) + if (!is_owner_or_cap(inode)) return -EACCES; if (get_user(flags, (int __user *)arg)) diff --git a/fs/inode.c b/fs/inode.c index 9a012cc5b6c..320e088d0b2 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -145,7 +145,7 @@ static struct inode *alloc_inode(struct super_block *sb) mapping->a_ops = &empty_aops; mapping->host = inode; mapping->flags = 0; - mapping_set_gfp_mask(mapping, GFP_HIGHUSER); + mapping_set_gfp_mask(mapping, GFP_HIGHUSER_PAGECACHE); mapping->assoc_mapping = NULL; mapping->backing_dev_info = &default_backing_dev_info; @@ -462,6 +462,11 @@ static int shrink_icache_memory(int nr, gfp_t gfp_mask) return (inodes_stat.nr_unused / 100) * sysctl_vfs_cache_pressure; } +static struct shrinker icache_shrinker = { + .shrink = shrink_icache_memory, + .seeks = DEFAULT_SEEKS, +}; + static void __wait_on_freeing_inode(struct inode *inode); /* * Called with the inode lock held. @@ -519,7 +524,13 @@ repeat: * new_inode - obtain an inode * @sb: superblock * - * Allocates a new inode for given superblock. + * Allocates a new inode for given superblock. The default gfp_mask + * for allocations related to inode->i_mapping is GFP_HIGHUSER_PAGECACHE. + * If HIGHMEM pages are unsuitable or it is known that pages allocated + * for the page cache are not reclaimable or migratable, + * mapping_set_gfp_mask() must be called with suitable flags on the + * newly created inode's mapping + * */ struct inode *new_inode(struct super_block *sb) { @@ -1379,7 +1390,7 @@ void __init inode_init(unsigned long mempages) SLAB_MEM_SPREAD), init_once, NULL); - set_shrinker(DEFAULT_SEEKS, shrink_icache_memory); + register_shrinker(&icache_shrinker); /* Hash may have been set up in inode_init_early */ if (!hashdist) diff --git a/fs/isofs/isofs.h b/fs/isofs/isofs.h index efe2872cd4e..a07e67b1ea7 100644 --- a/fs/isofs/isofs.h +++ b/fs/isofs/isofs.h @@ -1,5 +1,6 @@ #include <linux/fs.h> #include <linux/buffer_head.h> +#include <linux/exportfs.h> #include <linux/iso_fs.h> #include <asm/unaligned.h> diff --git a/fs/jffs2/acl.c b/fs/jffs2/acl.c index a46101ee867..65b3a1b5b88 100644 --- a/fs/jffs2/acl.c +++ b/fs/jffs2/acl.c @@ -435,7 +435,7 @@ static int jffs2_acl_setxattr(struct inode *inode, int type, const void *value, struct posix_acl *acl; int rc; - if ((current->fsuid != inode->i_uid) && !capable(CAP_FOWNER)) + if (!is_owner_or_cap(inode)) return -EPERM; if (value) { diff --git a/fs/jffs2/background.c b/fs/jffs2/background.c index 0c82dfcfd24..143c5530caf 100644 --- a/fs/jffs2/background.c +++ b/fs/jffs2/background.c @@ -81,6 +81,7 @@ static int jffs2_garbage_collect_thread(void *_c) set_user_nice(current, 10); + set_freezable(); for (;;) { allow_signal(SIGHUP); diff --git a/fs/jfs/ioctl.c b/fs/jfs/ioctl.c index fe063af6fd2..3c8663bea98 100644 --- a/fs/jfs/ioctl.c +++ b/fs/jfs/ioctl.c @@ -69,7 +69,7 @@ int jfs_ioctl(struct inode * inode, struct file * filp, unsigned int cmd, if (IS_RDONLY(inode)) return -EROFS; - if ((current->fsuid != inode->i_uid) && !capable(CAP_FOWNER)) + if (!is_owner_or_cap(inode)) return -EACCES; if (get_user(flags, (int __user *) arg)) diff --git a/fs/jfs/jfs_inode.h b/fs/jfs/jfs_inode.h index 2374b595f2e..f0ec72b263f 100644 --- a/fs/jfs/jfs_inode.h +++ b/fs/jfs/jfs_inode.h @@ -32,6 +32,7 @@ extern void jfs_truncate_nolock(struct inode *, loff_t); extern void jfs_free_zero_link(struct inode *); extern struct dentry *jfs_get_parent(struct dentry *dentry); extern void jfs_get_inode_flags(struct jfs_inode_info *); +extern struct dentry *jfs_get_dentry(struct super_block *sb, void *vobjp); extern void jfs_set_inode_flags(struct inode *); extern int jfs_get_block(struct inode *, sector_t, struct buffer_head *, int); diff --git a/fs/jfs/namei.c b/fs/jfs/namei.c index 25161c4121e..932797ba433 100644 --- a/fs/jfs/namei.c +++ b/fs/jfs/namei.c @@ -1477,6 +1477,38 @@ static struct dentry *jfs_lookup(struct inode *dip, struct dentry *dentry, struc return dentry; } +struct dentry *jfs_get_dentry(struct super_block *sb, void *vobjp) +{ + __u32 *objp = vobjp; + unsigned long ino = objp[0]; + __u32 generation = objp[1]; + struct inode *inode; + struct dentry *result; + + if (ino == 0) + return ERR_PTR(-ESTALE); + inode = iget(sb, ino); + if (inode == NULL) + return ERR_PTR(-ENOMEM); + + if (is_bad_inode(inode) || + (generation && inode->i_generation != generation)) { + result = ERR_PTR(-ESTALE); + goto out_iput; + } + + result = d_alloc_anon(inode); + if (!result) { + result = ERR_PTR(-ENOMEM); + goto out_iput; + } + return result; + + out_iput: + iput(inode); + return result; +} + struct dentry *jfs_get_parent(struct dentry *dentry) { struct super_block *sb = dentry->d_inode->i_sb; diff --git a/fs/jfs/super.c b/fs/jfs/super.c index 20e4ac1c79a..929fceca799 100644 --- a/fs/jfs/super.c +++ b/fs/jfs/super.c @@ -27,6 +27,7 @@ #include <linux/kthread.h> #include <linux/posix_acl.h> #include <linux/buffer_head.h> +#include <linux/exportfs.h> #include <asm/uaccess.h> #include <linux/seq_file.h> @@ -737,6 +738,7 @@ static const struct super_operations jfs_super_operations = { }; static struct export_operations jfs_export_operations = { + .get_dentry = jfs_get_dentry, .get_parent = jfs_get_parent, }; diff --git a/fs/jfs/xattr.c b/fs/jfs/xattr.c index b2375f0774b..9b7f2cdaae0 100644 --- a/fs/jfs/xattr.c +++ b/fs/jfs/xattr.c @@ -697,7 +697,7 @@ static int can_set_system_xattr(struct inode *inode, const char *name, struct posix_acl *acl; int rc; - if ((current->fsuid != inode->i_uid) && !capable(CAP_FOWNER)) + if (!is_owner_or_cap(inode)) return -EPERM; /* diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c index 26809325469..82e2192a0d5 100644 --- a/fs/lockd/svc.c +++ b/fs/lockd/svc.c @@ -25,6 +25,7 @@ #include <linux/smp.h> #include <linux/smp_lock.h> #include <linux/mutex.h> +#include <linux/freezer.h> #include <linux/sunrpc/types.h> #include <linux/sunrpc/stats.h> @@ -75,18 +76,31 @@ static const int nlm_port_min = 0, nlm_port_max = 65535; static struct ctl_table_header * nlm_sysctl_table; -static unsigned long set_grace_period(void) +static unsigned long get_lockd_grace_period(void) { - unsigned long grace_period; - /* Note: nlm_timeout should always be nonzero */ if (nlm_grace_period) - grace_period = ((nlm_grace_period + nlm_timeout - 1) - / nlm_timeout) * nlm_timeout * HZ; + return roundup(nlm_grace_period, nlm_timeout) * HZ; else - grace_period = nlm_timeout * 5 * HZ; + return nlm_timeout * 5 * HZ; +} + +unsigned long get_nfs_grace_period(void) +{ + unsigned long lockdgrace = get_lockd_grace_period(); + unsigned long nfsdgrace = 0; + + if (nlmsvc_ops) + nfsdgrace = nlmsvc_ops->get_grace_period(); + + return max(lockdgrace, nfsdgrace); +} +EXPORT_SYMBOL(get_nfs_grace_period); + +static unsigned long set_grace_period(void) +{ nlmsvc_grace_period = 1; - return grace_period + jiffies; + return get_nfs_grace_period() + jiffies; } static inline void clear_grace_period(void) @@ -119,6 +133,7 @@ lockd(struct svc_rqst *rqstp) complete(&lockd_start_done); daemonize("lockd"); + set_freezable(); /* Process request with signals blocked, but allow SIGKILL. */ allow_signal(SIGKILL); diff --git a/fs/mbcache.c b/fs/mbcache.c index deeb9dc062d..fbb1d02f879 100644 --- a/fs/mbcache.c +++ b/fs/mbcache.c @@ -100,7 +100,6 @@ struct mb_cache { static LIST_HEAD(mb_cache_list); static LIST_HEAD(mb_cache_lru_list); static DEFINE_SPINLOCK(mb_cache_spinlock); -static struct shrinker *mb_shrinker; static inline int mb_cache_indexes(struct mb_cache *cache) @@ -118,6 +117,10 @@ mb_cache_indexes(struct mb_cache *cache) static int mb_cache_shrink_fn(int nr_to_scan, gfp_t gfp_mask); +static struct shrinker mb_cache_shrinker = { + .shrink = mb_cache_shrink_fn, + .seeks = DEFAULT_SEEKS, +}; static inline int __mb_cache_entry_is_hashed(struct mb_cache_entry *ce) @@ -662,13 +665,13 @@ mb_cache_entry_find_next(struct mb_cache_entry *prev, int index, static int __init init_mbcache(void) { - mb_shrinker = set_shrinker(DEFAULT_SEEKS, mb_cache_shrink_fn); + register_shrinker(&mb_cache_shrinker); return 0; } static void __exit exit_mbcache(void) { - remove_shrinker(mb_shrinker); + unregister_shrinker(&mb_cache_shrinker); } module_init(init_mbcache) diff --git a/fs/namei.c b/fs/namei.c index 5e2d98d10c5..defaa47c11d 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -1576,7 +1576,7 @@ int may_open(struct nameidata *nd, int acc_mode, int flag) /* O_NOATIME can only be set by the owner or superuser */ if (flag & O_NOATIME) - if (current->fsuid != inode->i_uid && !capable(CAP_FOWNER)) + if (!is_owner_or_cap(inode)) return -EPERM; /* diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c index 75f309c8741..a796be5051b 100644 --- a/fs/nfs/callback.c +++ b/fs/nfs/callback.c @@ -14,6 +14,7 @@ #include <linux/sunrpc/svcsock.h> #include <linux/nfs_fs.h> #include <linux/mutex.h> +#include <linux/freezer.h> #include <net/inet_sock.h> @@ -67,6 +68,7 @@ static void nfs_callback_svc(struct svc_rqst *rqstp) daemonize("nfsv4-svc"); /* Process request with signals blocked, but allow SIGKILL. */ allow_signal(SIGKILL); + set_freezable(); complete(&nfs_callback_info.started); diff --git a/fs/nfs/super.c b/fs/nfs/super.c index a2b1af89ca1..adffe1615c5 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -300,7 +300,10 @@ static const struct super_operations nfs4_sops = { }; #endif -static struct shrinker *acl_shrinker; +static struct shrinker acl_shrinker = { + .shrink = nfs_access_cache_shrinker, + .seeks = DEFAULT_SEEKS, +}; /* * Register the NFS filesystems @@ -321,7 +324,7 @@ int __init register_nfs_fs(void) if (ret < 0) goto error_2; #endif - acl_shrinker = set_shrinker(DEFAULT_SEEKS, nfs_access_cache_shrinker); + register_shrinker(&acl_shrinker); return 0; #ifdef CONFIG_NFS_V4 @@ -339,8 +342,7 @@ error_0: */ void __exit unregister_nfs_fs(void) { - if (acl_shrinker != NULL) - remove_shrinker(acl_shrinker); + unregister_shrinker(&acl_shrinker); #ifdef CONFIG_NFS_V4 unregister_filesystem(&nfs4_fs_type); nfs_unregister_sysctl(); diff --git a/fs/nfsd/auth.c b/fs/nfsd/auth.c index 6e92b0fe532..cf61dc8ae94 100644 --- a/fs/nfsd/auth.c +++ b/fs/nfsd/auth.c @@ -12,17 +12,31 @@ #define CAP_NFSD_MASK (CAP_FS_MASK|CAP_TO_MASK(CAP_SYS_RESOURCE)) +static int nfsexp_flags(struct svc_rqst *rqstp, struct svc_export *exp) +{ + struct exp_flavor_info *f; + struct exp_flavor_info *end = exp->ex_flavors + exp->ex_nflavors; + + for (f = exp->ex_flavors; f < end; f++) { + if (f->pseudoflavor == rqstp->rq_flavor) + return f->flags; + } + return exp->ex_flags; + +} + int nfsd_setuser(struct svc_rqst *rqstp, struct svc_export *exp) { struct svc_cred cred = rqstp->rq_cred; int i; + int flags = nfsexp_flags(rqstp, exp); int ret; - if (exp->ex_flags & NFSEXP_ALLSQUASH) { + if (flags & NFSEXP_ALLSQUASH) { cred.cr_uid = exp->ex_anon_uid; cred.cr_gid = exp->ex_anon_gid; cred.cr_group_info = groups_alloc(0); - } else if (exp->ex_flags & NFSEXP_ROOTSQUASH) { + } else if (flags & NFSEXP_ROOTSQUASH) { struct group_info *gi; if (!cred.cr_uid) cred.cr_uid = exp->ex_anon_uid; diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c index 79bd03b8bbf..c7bbf460b00 100644 --- a/fs/nfsd/export.c +++ b/fs/nfsd/export.c @@ -26,12 +26,15 @@ #include <linux/mount.h> #include <linux/hash.h> #include <linux/module.h> +#include <linux/exportfs.h> #include <linux/sunrpc/svc.h> #include <linux/nfsd/nfsd.h> #include <linux/nfsd/nfsfh.h> #include <linux/nfsd/syscall.h> #include <linux/lockd/bind.h> +#include <linux/sunrpc/msg_prot.h> +#include <linux/sunrpc/gss_api.h> #define NFSDDBG_FACILITY NFSDDBG_EXPORT @@ -451,8 +454,48 @@ out_free_all: return err; } +static int secinfo_parse(char **mesg, char *buf, struct svc_export *exp) +{ + int listsize, err; + struct exp_flavor_info *f; + + err = get_int(mesg, &listsize); + if (err) + return err; + if (listsize < 0 || listsize > MAX_SECINFO_LIST) + return -EINVAL; + + for (f = exp->ex_flavors; f < exp->ex_flavors + listsize; f++) { + err = get_int(mesg, &f->pseudoflavor); + if (err) + return err; + /* + * Just a quick sanity check; we could also try to check + * whether this pseudoflavor is supported, but at worst + * an unsupported pseudoflavor on the export would just + * be a pseudoflavor that won't match the flavor of any + * authenticated request. The administrator will + * probably discover the problem when someone fails to + * authenticate. + */ + if (f->pseudoflavor < 0) + return -EINVAL; + err = get_int(mesg, &f->flags); + if (err) + return err; + /* Only some flags are allowed to differ between flavors: */ + if (~NFSEXP_SECINFO_FLAGS & (f->flags ^ exp->ex_flags)) + return -EINVAL; + } + exp->ex_nflavors = listsize; + return 0; +} + #else /* CONFIG_NFSD_V4 */ -static inline int fsloc_parse(char **mesg, char *buf, struct nfsd4_fs_locations *fsloc) { return 0; } +static inline int +fsloc_parse(char **mesg, char *buf, struct nfsd4_fs_locations *fsloc){return 0;} +static inline int +secinfo_parse(char **mesg, char *buf, struct svc_export *exp) { return 0; } #endif static int svc_export_parse(struct cache_detail *cd, char *mesg, int mlen) @@ -476,6 +519,9 @@ static int svc_export_parse(struct cache_detail *cd, char *mesg, int mlen) exp.ex_uuid = NULL; + /* secinfo */ + exp.ex_nflavors = 0; + if (mesg[mlen-1] != '\n') return -EINVAL; mesg[mlen-1] = 0; @@ -553,7 +599,9 @@ static int svc_export_parse(struct cache_detail *cd, char *mesg, int mlen) if (exp.ex_uuid == NULL) err = -ENOMEM; } - } else + } else if (strcmp(buf, "secinfo") == 0) + err = secinfo_parse(&mesg, buf, &exp); + else /* quietly ignore unknown words and anything * following. Newer user-space can try to set * new values, then see what the result was. @@ -593,6 +641,7 @@ static int svc_export_parse(struct cache_detail *cd, char *mesg, int mlen) static void exp_flags(struct seq_file *m, int flag, int fsid, uid_t anonu, uid_t anong, struct nfsd4_fs_locations *fslocs); +static void show_secinfo(struct seq_file *m, struct svc_export *exp); static int svc_export_show(struct seq_file *m, struct cache_detail *cd, @@ -622,6 +671,7 @@ static int svc_export_show(struct seq_file *m, seq_printf(m, "%02x", exp->ex_uuid[i]); } } + show_secinfo(m, exp); } seq_puts(m, ")\n"); return 0; @@ -654,6 +704,7 @@ static void export_update(struct cache_head *cnew, struct cache_head *citem) { struct svc_export *new = container_of(cnew, struct svc_export, h); struct svc_export *item = container_of(citem, struct svc_export, h); + int i; new->ex_flags = item->ex_flags; new->ex_anon_uid = item->ex_anon_uid; @@ -669,6 +720,10 @@ static void export_update(struct cache_head *cnew, struct cache_head *citem) item->ex_fslocs.locations_count = 0; new->ex_fslocs.migrated = item->ex_fslocs.migrated; item->ex_fslocs.migrated = 0; + new->ex_nflavors = item->ex_nflavors; + for (i = 0; i < MAX_SECINFO_LIST; i++) { + new->ex_flavors[i] = item->ex_flavors[i]; + } } static struct cache_head *svc_export_alloc(void) @@ -738,16 +793,18 @@ exp_find_key(svc_client *clp, int fsid_type, u32 *fsidv, struct cache_req *reqp) int err; if (!clp) - return NULL; + return ERR_PTR(-ENOENT); key.ek_client = clp; key.ek_fsidtype = fsid_type; memcpy(key.ek_fsid, fsidv, key_len(fsid_type)); ek = svc_expkey_lookup(&key); - if (ek != NULL) - if ((err = cache_check(&svc_expkey_cache, &ek->h, reqp))) - ek = ERR_PTR(err); + if (ek == NULL) + return ERR_PTR(-ENOMEM); + err = cache_check(&svc_expkey_cache, &ek->h, reqp); + if (err) + return ERR_PTR(err); return ek; } @@ -808,30 +865,21 @@ exp_get_by_name(svc_client *clp, struct vfsmount *mnt, struct dentry *dentry, struct cache_req *reqp) { struct svc_export *exp, key; + int err; if (!clp) - return NULL; + return ERR_PTR(-ENOENT); key.ex_client = clp; key.ex_mnt = mnt; key.ex_dentry = dentry; exp = svc_export_lookup(&key); - if (exp != NULL) { - int err; - - err = cache_check(&svc_export_cache, &exp->h, reqp); - switch (err) { - case 0: break; - case -EAGAIN: - case -ETIMEDOUT: - exp = ERR_PTR(err); - break; - default: - exp = NULL; - } - } - + if (exp == NULL) + return ERR_PTR(-ENOMEM); + err = cache_check(&svc_export_cache, &exp->h, reqp); + if (err) + return ERR_PTR(err); return exp; } @@ -847,7 +895,7 @@ exp_parent(svc_client *clp, struct vfsmount *mnt, struct dentry *dentry, dget(dentry); exp = exp_get_by_name(clp, mnt, dentry, reqp); - while (exp == NULL && !IS_ROOT(dentry)) { + while (PTR_ERR(exp) == -ENOENT && !IS_ROOT(dentry)) { struct dentry *parent; parent = dget_parent(dentry); @@ -900,7 +948,7 @@ static void exp_fsid_unhash(struct svc_export *exp) return; ek = exp_get_fsid_key(exp->ex_client, exp->ex_fsid); - if (ek && !IS_ERR(ek)) { + if (!IS_ERR(ek)) { ek->h.expiry_time = get_seconds()-1; cache_put(&ek->h, &svc_expkey_cache); } @@ -938,7 +986,7 @@ static void exp_unhash(struct svc_export *exp) struct inode *inode = exp->ex_dentry->d_inode; ek = exp_get_key(exp->ex_client, inode->i_sb->s_dev, inode->i_ino); - if (ek && !IS_ERR(ek)) { + if (!IS_ERR(ek)) { ek->h.expiry_time = get_seconds()-1; cache_put(&ek->h, &svc_expkey_cache); } @@ -989,13 +1037,12 @@ exp_export(struct nfsctl_export *nxp) /* must make sure there won't be an ex_fsid clash */ if ((nxp->ex_flags & NFSEXP_FSID) && - (fsid_key = exp_get_fsid_key(clp, nxp->ex_dev)) && - !IS_ERR(fsid_key) && + (!IS_ERR(fsid_key = exp_get_fsid_key(clp, nxp->ex_dev))) && fsid_key->ek_mnt && (fsid_key->ek_mnt != nd.mnt || fsid_key->ek_dentry != nd.dentry) ) goto finish; - if (exp) { + if (!IS_ERR(exp)) { /* just a flags/id/fsid update */ exp_fsid_unhash(exp); @@ -1104,7 +1151,7 @@ exp_unexport(struct nfsctl_export *nxp) err = -EINVAL; exp = exp_get_by_name(dom, nd.mnt, nd.dentry, NULL); path_release(&nd); - if (!exp) + if (IS_ERR(exp)) goto out_domain; exp_do_unexport(exp); @@ -1149,10 +1196,6 @@ exp_rootfh(svc_client *clp, char *path, struct knfsd_fh *f, int maxsize) err = PTR_ERR(exp); goto out; } - if (!exp) { - dprintk("nfsd: exp_rootfh export not found.\n"); - goto out; - } /* * fh must be initialized before calling fh_compose @@ -1176,17 +1219,130 @@ exp_find(struct auth_domain *clp, int fsid_type, u32 *fsidv, { struct svc_export *exp; struct svc_expkey *ek = exp_find_key(clp, fsid_type, fsidv, reqp); - if (!ek || IS_ERR(ek)) + if (IS_ERR(ek)) return ERR_PTR(PTR_ERR(ek)); exp = exp_get_by_name(clp, ek->ek_mnt, ek->ek_dentry, reqp); cache_put(&ek->h, &svc_expkey_cache); - if (!exp || IS_ERR(exp)) + if (IS_ERR(exp)) return ERR_PTR(PTR_ERR(exp)); return exp; } +__be32 check_nfsd_access(struct svc_export *exp, struct svc_rqst *rqstp) +{ + struct exp_flavor_info *f; + struct exp_flavor_info *end = exp->ex_flavors + exp->ex_nflavors; + + /* legacy gss-only clients are always OK: */ + if (exp->ex_client == rqstp->rq_gssclient) + return 0; + /* ip-address based client; check sec= export option: */ + for (f = exp->ex_flavors; f < end; f++) { + if (f->pseudoflavor == rqstp->rq_flavor) + return 0; + } + /* defaults in absence of sec= options: */ + if (exp->ex_nflavors == 0) { + if (rqstp->rq_flavor == RPC_AUTH_NULL || + rqstp->rq_flavor == RPC_AUTH_UNIX) + return 0; + } + return nfserr_wrongsec; +} + +/* + * Uses rq_client and rq_gssclient to find an export; uses rq_client (an + * auth_unix client) if it's available and has secinfo information; + * otherwise, will try to use rq_gssclient. + * + * Called from functions that handle requests; functions that do work on + * behalf of mountd are passed a single client name to use, and should + * use exp_get_by_name() or exp_find(). + */ +struct svc_export * +rqst_exp_get_by_name(struct svc_rqst *rqstp, struct vfsmount *mnt, + struct dentry *dentry) +{ + struct svc_export *gssexp, *exp = NULL; + + if (rqstp->rq_client == NULL) + goto gss; + + /* First try the auth_unix client: */ + exp = exp_get_by_name(rqstp->rq_client, mnt, dentry, + &rqstp->rq_chandle); + if (PTR_ERR(exp) == -ENOENT) + goto gss; + if (IS_ERR(exp)) + return exp; + /* If it has secinfo, assume there are no gss/... clients */ + if (exp->ex_nflavors > 0) + return exp; +gss: + /* Otherwise, try falling back on gss client */ + if (rqstp->rq_gssclient == NULL) + return exp; + gssexp = exp_get_by_name(rqstp->rq_gssclient, mnt, dentry, + &rqstp->rq_chandle); + if (PTR_ERR(gssexp) == -ENOENT) + return exp; + if (exp && !IS_ERR(exp)) + exp_put(exp); + return gssexp; +} + +struct svc_export * +rqst_exp_find(struct svc_rqst *rqstp, int fsid_type, u32 *fsidv) +{ + struct svc_export *gssexp, *exp = NULL; + + if (rqstp->rq_client == NULL) + goto gss; + + /* First try the auth_unix client: */ + exp = exp_find(rqstp->rq_client, fsid_type, fsidv, &rqstp->rq_chandle); + if (PTR_ERR(exp) == -ENOENT) + goto gss; + if (IS_ERR(exp)) + return exp; + /* If it has secinfo, assume there are no gss/... clients */ + if (exp->ex_nflavors > 0) + return exp; +gss: + /* Otherwise, try falling back on gss client */ + if (rqstp->rq_gssclient == NULL) + return exp; + gssexp = exp_find(rqstp->rq_gssclient, fsid_type, fsidv, + &rqstp->rq_chandle); + if (PTR_ERR(gssexp) == -ENOENT) + return exp; + if (exp && !IS_ERR(exp)) + exp_put(exp); + return gssexp; +} + +struct svc_export * +rqst_exp_parent(struct svc_rqst *rqstp, struct vfsmount *mnt, + struct dentry *dentry) +{ + struct svc_export *exp; + + dget(dentry); + exp = rqst_exp_get_by_name(rqstp, mnt, dentry); + + while (PTR_ERR(exp) == -ENOENT && !IS_ROOT(dentry)) { + struct dentry *parent; + + parent = dget_parent(dentry); + dput(dentry); + dentry = parent; + exp = rqst_exp_get_by_name(rqstp, mnt, dentry); + } + dput(dentry); + return exp; +} /* * Called when we need the filehandle for the root of the pseudofs, @@ -1194,8 +1350,7 @@ exp_find(struct auth_domain *clp, int fsid_type, u32 *fsidv, * export point with fsid==0 */ __be32 -exp_pseudoroot(struct auth_domain *clp, struct svc_fh *fhp, - struct cache_req *creq) +exp_pseudoroot(struct svc_rqst *rqstp, struct svc_fh *fhp) { struct svc_export *exp; __be32 rv; @@ -1203,12 +1358,16 @@ exp_pseudoroot(struct auth_domain *clp, struct svc_fh *fhp, mk_fsid(FSID_NUM, fsidv, 0, 0, 0, NULL); - exp = exp_find(clp, FSID_NUM, fsidv, creq); + exp = rqst_exp_find(rqstp, FSID_NUM, fsidv); + if (PTR_ERR(exp) == -ENOENT) + return nfserr_perm; if (IS_ERR(exp)) return nfserrno(PTR_ERR(exp)); - if (exp == NULL) - return nfserr_perm; rv = fh_compose(fhp, exp, exp->ex_dentry, NULL); + if (rv) + goto out; + rv = check_nfsd_access(exp, rqstp); +out: exp_put(exp); return rv; } @@ -1296,28 +1455,62 @@ static struct flags { { 0, {"", ""}} }; -static void exp_flags(struct seq_file *m, int flag, int fsid, - uid_t anonu, uid_t anong, struct nfsd4_fs_locations *fsloc) +static void show_expflags(struct seq_file *m, int flags, int mask) { - int first = 0; struct flags *flg; + int state, first = 0; for (flg = expflags; flg->flag; flg++) { - int state = (flg->flag & flag)?0:1; + if (flg->flag & ~mask) + continue; + state = (flg->flag & flags) ? 0 : 1; if (*flg->name[state]) seq_printf(m, "%s%s", first++?",":"", flg->name[state]); } +} + +static void show_secinfo_flags(struct seq_file *m, int flags) +{ + seq_printf(m, ","); + show_expflags(m, flags, NFSEXP_SECINFO_FLAGS); +} + +static void show_secinfo(struct seq_file *m, struct svc_export *exp) +{ + struct exp_flavor_info *f; + struct exp_flavor_info *end = exp->ex_flavors + exp->ex_nflavors; + int lastflags = 0, first = 0; + + if (exp->ex_nflavors == 0) + return; + for (f = exp->ex_flavors; f < end; f++) { + if (first || f->flags != lastflags) { + if (!first) + show_secinfo_flags(m, lastflags); + seq_printf(m, ",sec=%d", f->pseudoflavor); + lastflags = f->flags; + } else { + seq_printf(m, ":%d", f->pseudoflavor); + } + } + show_secinfo_flags(m, lastflags); +} + +static void exp_flags(struct seq_file *m, int flag, int fsid, + uid_t anonu, uid_t anong, struct nfsd4_fs_locations *fsloc) +{ + show_expflags(m, flag, NFSEXP_ALLFLAGS); if (flag & NFSEXP_FSID) - seq_printf(m, "%sfsid=%d", first++?",":"", fsid); + seq_printf(m, ",fsid=%d", fsid); if (anonu != (uid_t)-2 && anonu != (0x10000-2)) - seq_printf(m, "%sanonuid=%d", first++?",":"", anonu); + seq_printf(m, ",sanonuid=%d", anonu); if (anong != (gid_t)-2 && anong != (0x10000-2)) - seq_printf(m, "%sanongid=%d", first++?",":"", anong); + seq_printf(m, ",sanongid=%d", anong); if (fsloc && fsloc->locations_count > 0) { char *loctype = (fsloc->migrated) ? "refer" : "replicas"; int i; - seq_printf(m, "%s%s=", first++?",":"", loctype); + seq_printf(m, ",%s=", loctype); seq_escape(m, fsloc->locations[0].path, ",;@ \t\n\\"); seq_putc(m, '@'); seq_escape(m, fsloc->locations[0].hosts, ",;@ \t\n\\"); diff --git a/fs/nfsd/lockd.c b/fs/nfsd/lockd.c index 221acd1f11f..9e4a568a501 100644 --- a/fs/nfsd/lockd.c +++ b/fs/nfsd/lockd.c @@ -65,6 +65,7 @@ nlm_fclose(struct file *filp) static struct nlmsvc_binding nfsd_nlm_ops = { .fopen = nlm_fopen, /* open file for locking */ .fclose = nlm_fclose, /* close file */ + .get_grace_period = get_nfs4_grace_period, }; void diff --git a/fs/nfsd/nfs4acl.c b/fs/nfsd/nfs4acl.c index cc3b7badd48..b6ed38380ab 100644 --- a/fs/nfsd/nfs4acl.c +++ b/fs/nfsd/nfs4acl.c @@ -183,8 +183,13 @@ static void summarize_posix_acl(struct posix_acl *acl, struct posix_acl_summary *pas) { struct posix_acl_entry *pa, *pe; - pas->users = 0; - pas->groups = 0; + + /* + * Only pas.users and pas.groups need initialization; previous + * posix_acl_valid() calls ensure that the other fields will be + * initialized in the following loop. But, just to placate gcc: + */ + memset(pas, 0, sizeof(*pas)); pas->mask = 07; pe = acl->a_entries + acl->a_count; @@ -732,13 +737,16 @@ int nfs4_acl_nfsv4_to_posix(struct nfs4_acl *acl, struct posix_acl **pacl, *pacl = posix_state_to_acl(&effective_acl_state, flags); if (IS_ERR(*pacl)) { ret = PTR_ERR(*pacl); + *pacl = NULL; goto out_dstate; } *dpacl = posix_state_to_acl(&default_acl_state, flags | NFS4_ACL_TYPE_DEFAULT); if (IS_ERR(*dpacl)) { ret = PTR_ERR(*dpacl); + *dpacl = NULL; posix_acl_release(*pacl); + *pacl = NULL; goto out_dstate; } sort_pacl(*pacl); diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index 5443c52b57a..31d6633c7fe 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -75,7 +75,7 @@ enum nfs_cb_opnum4 { #define op_enc_sz 1 #define op_dec_sz 2 #define enc_nfs4_fh_sz (1 + (NFS4_FHSIZE >> 2)) -#define enc_stateid_sz 16 +#define enc_stateid_sz (NFS4_STATEID_SIZE >> 2) #define NFS4_enc_cb_recall_sz (cb_compound_enc_hdr_sz + \ 1 + enc_stateid_sz + \ enc_nfs4_fh_sz) diff --git a/fs/nfsd/nfs4idmap.c b/fs/nfsd/nfs4idmap.c index 45aa21ce678..2cf9a9a2d89 100644 --- a/fs/nfsd/nfs4idmap.c +++ b/fs/nfsd/nfs4idmap.c @@ -587,6 +587,15 @@ idmap_lookup(struct svc_rqst *rqstp, return ret; } +static char * +rqst_authname(struct svc_rqst *rqstp) +{ + struct auth_domain *clp; + + clp = rqstp->rq_gssclient ? rqstp->rq_gssclient : rqstp->rq_client; + return clp->name; +} + static int idmap_name_to_id(struct svc_rqst *rqstp, int type, const char *name, u32 namelen, uid_t *id) @@ -600,7 +609,7 @@ idmap_name_to_id(struct svc_rqst *rqstp, int type, const char *name, u32 namelen return -EINVAL; memcpy(key.name, name, namelen); key.name[namelen] = '\0'; - strlcpy(key.authname, rqstp->rq_client->name, sizeof(key.authname)); + strlcpy(key.authname, rqst_authname(rqstp), sizeof(key.authname)); ret = idmap_lookup(rqstp, nametoid_lookup, &key, &nametoid_cache, &item); if (ret == -ENOENT) ret = -ESRCH; /* nfserr_badname */ @@ -620,7 +629,7 @@ idmap_id_to_name(struct svc_rqst *rqstp, int type, uid_t id, char *name) }; int ret; - strlcpy(key.authname, rqstp->rq_client->name, sizeof(key.authname)); + strlcpy(key.authname, rqst_authname(rqstp), sizeof(key.authname)); ret = idmap_lookup(rqstp, idtoname_lookup, &key, &idtoname_cache, &item); if (ret == -ENOENT) return sprintf(name, "%u", id); diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index 8522729830d..3c627128e20 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -47,6 +47,7 @@ #include <linux/nfsd/state.h> #include <linux/nfsd/xdr4.h> #include <linux/nfs4_acl.h> +#include <linux/sunrpc/gss_api.h> #define NFSDDBG_FACILITY NFSDDBG_PROC @@ -286,8 +287,7 @@ nfsd4_putrootfh(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, __be32 status; fh_put(&cstate->current_fh); - status = exp_pseudoroot(rqstp->rq_client, &cstate->current_fh, - &rqstp->rq_chandle); + status = exp_pseudoroot(rqstp, &cstate->current_fh); return status; } @@ -474,8 +474,8 @@ nfsd4_lookupp(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, __be32 ret; fh_init(&tmp_fh, NFS4_FHSIZE); - if((ret = exp_pseudoroot(rqstp->rq_client, &tmp_fh, - &rqstp->rq_chandle)) != 0) + ret = exp_pseudoroot(rqstp, &tmp_fh); + if (ret) return ret; if (tmp_fh.fh_dentry == cstate->current_fh.fh_dentry) { fh_put(&tmp_fh); @@ -611,6 +611,30 @@ nfsd4_rename(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, } static __be32 +nfsd4_secinfo(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, + struct nfsd4_secinfo *secinfo) +{ + struct svc_fh resfh; + struct svc_export *exp; + struct dentry *dentry; + __be32 err; + + fh_init(&resfh, NFS4_FHSIZE); + err = nfsd_lookup_dentry(rqstp, &cstate->current_fh, + secinfo->si_name, secinfo->si_namelen, + &exp, &dentry); + if (err) + return err; + if (dentry->d_inode == NULL) { + exp_put(exp); + err = nfserr_noent; + } else + secinfo->si_exp = exp; + dput(dentry); + return err; +} + +static __be32 nfsd4_setattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfsd4_setattr *setattr) { @@ -1009,6 +1033,9 @@ static struct nfsd4_operation nfsd4_ops[OP_RELEASE_LOCKOWNER+1] = { [OP_SAVEFH] = { .op_func = (nfsd4op_func)nfsd4_savefh, }, + [OP_SECINFO] = { + .op_func = (nfsd4op_func)nfsd4_secinfo, + }, [OP_SETATTR] = { .op_func = (nfsd4op_func)nfsd4_setattr, }, diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 8c52913d7cb..e4a4c87ec8c 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -49,8 +49,10 @@ #include <linux/nfsd/state.h> #include <linux/nfsd/xdr4.h> #include <linux/namei.h> +#include <linux/swap.h> #include <linux/mutex.h> #include <linux/lockd/bind.h> +#include <linux/module.h> #define NFSDDBG_FACILITY NFSDDBG_PROC @@ -149,6 +151,7 @@ get_nfs4_file(struct nfs4_file *fi) } static int num_delegations; +unsigned int max_delegations; /* * Open owner state (share locks) @@ -192,7 +195,9 @@ alloc_init_deleg(struct nfs4_client *clp, struct nfs4_stateid *stp, struct svc_f struct nfs4_callback *cb = &stp->st_stateowner->so_client->cl_callback; dprintk("NFSD alloc_init_deleg\n"); - if (num_delegations > STATEID_HASH_SIZE * 4) + if (fp->fi_had_conflict) + return NULL; + if (num_delegations > max_delegations) return NULL; dp = kmem_cache_alloc(deleg_slab, GFP_KERNEL); if (dp == NULL) @@ -999,6 +1004,7 @@ alloc_init_file(struct inode *ino) list_add(&fp->fi_hash, &file_hashtbl[hashval]); fp->fi_inode = igrab(ino); fp->fi_id = current_fileid++; + fp->fi_had_conflict = false; return fp; } return NULL; @@ -1325,6 +1331,7 @@ do_recall(void *__dp) { struct nfs4_delegation *dp = __dp; + dp->dl_file->fi_had_conflict = true; nfsd4_cb_recall(dp); return 0; } @@ -3190,20 +3197,49 @@ nfsd4_load_reboot_recovery_data(void) printk("NFSD: Failure reading reboot recovery data\n"); } +unsigned long +get_nfs4_grace_period(void) +{ + return max(user_lease_time, lease_time) * HZ; +} + +/* + * Since the lifetime of a delegation isn't limited to that of an open, a + * client may quite reasonably hang on to a delegation as long as it has + * the inode cached. This becomes an obvious problem the first time a + * client's inode cache approaches the size of the server's total memory. + * + * For now we avoid this problem by imposing a hard limit on the number + * of delegations, which varies according to the server's memory size. + */ +static void +set_max_delegations(void) +{ + /* + * Allow at most 4 delegations per megabyte of RAM. Quick + * estimates suggest that in the worst case (where every delegation + * is for a different inode), a delegation could take about 1.5K, + * giving a worst case usage of about 6% of memory. + */ + max_delegations = nr_free_buffer_pages() >> (20 - 2 - PAGE_SHIFT); +} + /* initialization to perform when the nfsd service is started: */ static void __nfs4_state_start(void) { - time_t grace_time; + unsigned long grace_time; boot_time = get_seconds(); - grace_time = max(user_lease_time, lease_time); + grace_time = get_nfs_grace_period(); lease_time = user_lease_time; in_grace = 1; - printk("NFSD: starting %ld-second grace period\n", grace_time); + printk(KERN_INFO "NFSD: starting %ld-second grace period\n", + grace_time/HZ); laundry_wq = create_singlethread_workqueue("nfsd4"); - queue_delayed_work(laundry_wq, &laundromat_work, grace_time*HZ); + queue_delayed_work(laundry_wq, &laundromat_work, grace_time); + set_max_delegations(); } int diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 15809dfd88a..b3d55c6747f 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -56,6 +56,8 @@ #include <linux/nfsd_idmap.h> #include <linux/nfs4.h> #include <linux/nfs4_acl.h> +#include <linux/sunrpc/gss_api.h> +#include <linux/sunrpc/svcauth_gss.h> #define NFSDDBG_FACILITY NFSDDBG_XDR @@ -819,6 +821,23 @@ nfsd4_decode_renew(struct nfsd4_compoundargs *argp, clientid_t *clientid) } static __be32 +nfsd4_decode_secinfo(struct nfsd4_compoundargs *argp, + struct nfsd4_secinfo *secinfo) +{ + DECODE_HEAD; + + READ_BUF(4); + READ32(secinfo->si_namelen); + READ_BUF(secinfo->si_namelen); + SAVEMEM(secinfo->si_name, secinfo->si_namelen); + status = check_filename(secinfo->si_name, secinfo->si_namelen, + nfserr_noent); + if (status) + return status; + DECODE_TAIL; +} + +static __be32 nfsd4_decode_setattr(struct nfsd4_compoundargs *argp, struct nfsd4_setattr *setattr) { DECODE_HEAD; @@ -1131,6 +1150,9 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp) case OP_SAVEFH: op->status = nfs_ok; break; + case OP_SECINFO: + op->status = nfsd4_decode_secinfo(argp, &op->u.secinfo); + break; case OP_SETATTR: op->status = nfsd4_decode_setattr(argp, &op->u.setattr); break; @@ -1296,7 +1318,7 @@ static char *nfsd4_path(struct svc_rqst *rqstp, struct svc_export *exp, __be32 * char *path, *rootpath; fh_init(&tmp_fh, NFS4_FHSIZE); - *stat = exp_pseudoroot(rqstp->rq_client, &tmp_fh, &rqstp->rq_chandle); + *stat = exp_pseudoroot(rqstp, &tmp_fh); if (*stat) return NULL; rootpath = tmp_fh.fh_export->ex_path; @@ -1847,11 +1869,19 @@ nfsd4_encode_dirent_fattr(struct nfsd4_readdir *cd, if (d_mountpoint(dentry)) { int err; + /* + * Why the heck aren't we just using nfsd_lookup?? + * Different "."/".." handling? Something else? + * At least, add a comment here to explain.... + */ err = nfsd_cross_mnt(cd->rd_rqstp, &dentry, &exp); if (err) { nfserr = nfserrno(err); goto out_put; } + nfserr = check_nfsd_access(exp, cd->rd_rqstp); + if (nfserr) + goto out_put; } nfserr = nfsd4_encode_fattr(NULL, exp, dentry, p, buflen, cd->rd_bmval, @@ -2419,6 +2449,72 @@ nfsd4_encode_rename(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_ } } +static void +nfsd4_encode_secinfo(struct nfsd4_compoundres *resp, int nfserr, + struct nfsd4_secinfo *secinfo) +{ + int i = 0; + struct svc_export *exp = secinfo->si_exp; + u32 nflavs; + struct exp_flavor_info *flavs; + struct exp_flavor_info def_flavs[2]; + ENCODE_HEAD; + + if (nfserr) + goto out; + if (exp->ex_nflavors) { + flavs = exp->ex_flavors; + nflavs = exp->ex_nflavors; + } else { /* Handling of some defaults in absence of real secinfo: */ + flavs = def_flavs; + if (exp->ex_client->flavour->flavour == RPC_AUTH_UNIX) { + nflavs = 2; + flavs[0].pseudoflavor = RPC_AUTH_UNIX; + flavs[1].pseudoflavor = RPC_AUTH_NULL; + } else if (exp->ex_client->flavour->flavour == RPC_AUTH_GSS) { + nflavs = 1; + flavs[0].pseudoflavor + = svcauth_gss_flavor(exp->ex_client); + } else { + nflavs = 1; + flavs[0].pseudoflavor + = exp->ex_client->flavour->flavour; + } + } + + RESERVE_SPACE(4); + WRITE32(nflavs); + ADJUST_ARGS(); + for (i = 0; i < nflavs; i++) { + u32 flav = flavs[i].pseudoflavor; + struct gss_api_mech *gm = gss_mech_get_by_pseudoflavor(flav); + + if (gm) { + RESERVE_SPACE(4); + WRITE32(RPC_AUTH_GSS); + ADJUST_ARGS(); + RESERVE_SPACE(4 + gm->gm_oid.len); + WRITE32(gm->gm_oid.len); + WRITEMEM(gm->gm_oid.data, gm->gm_oid.len); + ADJUST_ARGS(); + RESERVE_SPACE(4); + WRITE32(0); /* qop */ + ADJUST_ARGS(); + RESERVE_SPACE(4); + WRITE32(gss_pseudoflavor_to_service(gm, flav)); + ADJUST_ARGS(); + gss_mech_put(gm); + } else { + RESERVE_SPACE(4); + WRITE32(flav); + ADJUST_ARGS(); + } + } +out: + if (exp) + exp_put(exp); +} + /* * The SETATTR encode routine is special -- it always encodes a bitmap, * regardless of the error status. @@ -2559,6 +2655,9 @@ nfsd4_encode_operation(struct nfsd4_compoundres *resp, struct nfsd4_op *op) break; case OP_SAVEFH: break; + case OP_SECINFO: + nfsd4_encode_secinfo(resp, op->status, &op->u.secinfo); + break; case OP_SETATTR: nfsd4_encode_setattr(resp, op->status, &op->u.setattr); break; diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index 71c686dc725..baac89d917c 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -35,7 +35,6 @@ #include <linux/nfsd/cache.h> #include <linux/nfsd/xdr.h> #include <linux/nfsd/syscall.h> -#include <linux/nfsd/interface.h> #include <asm/uaccess.h> @@ -245,7 +244,7 @@ static ssize_t write_getfs(struct file *file, char *buf, size_t size) } exp_readunlock(); if (err == 0) - err = res->fh_size + (int)&((struct knfsd_fh*)0)->fh_base; + err = res->fh_size + offsetof(struct knfsd_fh, fh_base); out: return err; } diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c index 6ca2d24fc21..0eb464a39aa 100644 --- a/fs/nfsd/nfsfh.c +++ b/fs/nfsd/nfsfh.c @@ -15,10 +15,12 @@ #include <linux/string.h> #include <linux/stat.h> #include <linux/dcache.h> +#include <linux/exportfs.h> #include <linux/mount.h> #include <linux/sunrpc/clnt.h> #include <linux/sunrpc/svc.h> +#include <linux/sunrpc/svcauth_gss.h> #include <linux/nfsd/nfsd.h> #define NFSDDBG_FACILITY NFSDDBG_FH @@ -27,10 +29,6 @@ static int nfsd_nr_verified; static int nfsd_nr_put; -extern struct export_operations export_op_default; - -#define CALL(ops,fun) ((ops->fun)?(ops->fun):export_op_default.fun) - /* * our acceptability function. * if NOSUBTREECHECK, accept anything @@ -123,8 +121,6 @@ fh_verify(struct svc_rqst *rqstp, struct svc_fh *fhp, int type, int access) int data_left = fh->fh_size/4; error = nfserr_stale; - if (rqstp->rq_client == NULL) - goto out; if (rqstp->rq_vers > 2) error = nfserr_badhandle; if (rqstp->rq_vers == 4 && fh->fh_size == 0) @@ -148,7 +144,7 @@ fh_verify(struct svc_rqst *rqstp, struct svc_fh *fhp, int type, int access) fh->fh_fsid[1] = fh->fh_fsid[2]; } if ((data_left -= len)<0) goto out; - exp = exp_find(rqstp->rq_client, fh->fh_fsid_type, datap, &rqstp->rq_chandle); + exp = rqst_exp_find(rqstp, fh->fh_fsid_type, datap); datap += len; } else { dev_t xdev; @@ -159,19 +155,17 @@ fh_verify(struct svc_rqst *rqstp, struct svc_fh *fhp, int type, int access) xdev = old_decode_dev(fh->ofh_xdev); xino = u32_to_ino_t(fh->ofh_xino); mk_fsid(FSID_DEV, tfh, xdev, xino, 0, NULL); - exp = exp_find(rqstp->rq_client, FSID_DEV, tfh, - &rqstp->rq_chandle); + exp = rqst_exp_find(rqstp, FSID_DEV, tfh); } - if (IS_ERR(exp) && (PTR_ERR(exp) == -EAGAIN - || PTR_ERR(exp) == -ETIMEDOUT)) { - error = nfserrno(PTR_ERR(exp)); + error = nfserr_stale; + if (PTR_ERR(exp) == -ENOENT) goto out; - } - error = nfserr_stale; - if (!exp || IS_ERR(exp)) + if (IS_ERR(exp)) { + error = nfserrno(PTR_ERR(exp)); goto out; + } /* Check if the request originated from a secure port. */ error = nfserr_perm; @@ -211,11 +205,9 @@ fh_verify(struct svc_rqst *rqstp, struct svc_fh *fhp, int type, int access) if (fileid_type == 0) dentry = dget(exp->ex_dentry); else { - struct export_operations *nop = exp->ex_mnt->mnt_sb->s_export_op; - dentry = CALL(nop,decode_fh)(exp->ex_mnt->mnt_sb, - datap, data_left, - fileid_type, - nfsd_acceptable, exp); + dentry = exportfs_decode_fh(exp->ex_mnt, datap, + data_left, fileid_type, + nfsd_acceptable, exp); } if (dentry == NULL) goto out; @@ -257,8 +249,19 @@ fh_verify(struct svc_rqst *rqstp, struct svc_fh *fhp, int type, int access) if (error) goto out; + if (!(access & MAY_LOCK)) { + /* + * pseudoflavor restrictions are not enforced on NLM, + * which clients virtually always use auth_sys for, + * even while using RPCSEC_GSS for NFS. + */ + error = check_nfsd_access(exp, rqstp); + if (error) + goto out; + } + /* Finally, check access permissions. */ - error = nfsd_permission(exp, dentry, access); + error = nfsd_permission(rqstp, exp, dentry, access); if (error) { dprintk("fh_verify: %s/%s permission failure, " @@ -286,15 +289,13 @@ out: static inline int _fh_update(struct dentry *dentry, struct svc_export *exp, __u32 *datap, int *maxsize) { - struct export_operations *nop = exp->ex_mnt->mnt_sb->s_export_op; - if (dentry == exp->ex_dentry) { *maxsize = 0; return 0; } - return CALL(nop,encode_fh)(dentry, datap, maxsize, - !(exp->ex_flags&NFSEXP_NOSUBTREECHECK)); + return exportfs_encode_fh(dentry, datap, maxsize, + !(exp->ex_flags & NFSEXP_NOSUBTREECHECK)); } /* diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c index b2c7147aa92..977a71f64e1 100644 --- a/fs/nfsd/nfsproc.c +++ b/fs/nfsd/nfsproc.c @@ -278,7 +278,8 @@ nfsd_proc_create(struct svc_rqst *rqstp, struct nfsd_createargs *argp, * echo thing > device-special-file-or-pipe * by doing a CREATE with type==0 */ - nfserr = nfsd_permission(newfhp->fh_export, + nfserr = nfsd_permission(rqstp, + newfhp->fh_export, newfhp->fh_dentry, MAY_WRITE|MAY_LOCAL_ACCESS); if (nfserr && nfserr != nfserr_rofs) diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index ff55950efb4..a8c89ae4c74 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -19,6 +19,7 @@ #include <linux/slab.h> #include <linux/smp.h> #include <linux/smp_lock.h> +#include <linux/freezer.h> #include <linux/fs_struct.h> #include <linux/sunrpc/types.h> @@ -432,6 +433,7 @@ nfsd(struct svc_rqst *rqstp) * dirty pages. */ current->flags |= PF_LESS_THROTTLE; + set_freezable(); /* * The main request loop @@ -492,6 +494,15 @@ out: module_put_and_exit(0); } +static __be32 map_new_errors(u32 vers, __be32 nfserr) +{ + if (nfserr == nfserr_jukebox && vers == 2) + return nfserr_dropit; + if (nfserr == nfserr_wrongsec && vers < 4) + return nfserr_acces; + return nfserr; +} + int nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp) { @@ -534,6 +545,7 @@ nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp) /* Now call the procedure handler, and encode NFS status. */ nfserr = proc->pc_func(rqstp, rqstp->rq_argp, rqstp->rq_resp); + nfserr = map_new_errors(rqstp->rq_vers, nfserr); if (nfserr == nfserr_jukebox && rqstp->rq_vers == 2) nfserr = nfserr_dropit; if (nfserr == nfserr_dropit) { diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 945b1cedde2..e90f4a8a1d0 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -113,7 +113,7 @@ nfsd_cross_mnt(struct svc_rqst *rqstp, struct dentry **dpp, while (follow_down(&mnt,&mounts)&&d_mountpoint(mounts)); - exp2 = exp_get_by_name(exp->ex_client, mnt, mounts, &rqstp->rq_chandle); + exp2 = rqst_exp_get_by_name(rqstp, mnt, mounts); if (IS_ERR(exp2)) { err = PTR_ERR(exp2); dput(mounts); @@ -135,21 +135,10 @@ out: return err; } -/* - * Look up one component of a pathname. - * N.B. After this call _both_ fhp and resfh need an fh_put - * - * If the lookup would cross a mountpoint, and the mounted filesystem - * is exported to the client with NFSEXP_NOHIDE, then the lookup is - * accepted as it stands and the mounted directory is - * returned. Otherwise the covered directory is returned. - * NOTE: this mountpoint crossing is not supported properly by all - * clients and is explicitly disallowed for NFSv3 - * NeilBrown <neilb@cse.unsw.edu.au> - */ __be32 -nfsd_lookup(struct svc_rqst *rqstp, struct svc_fh *fhp, const char *name, - int len, struct svc_fh *resfh) +nfsd_lookup_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp, + const char *name, int len, + struct svc_export **exp_ret, struct dentry **dentry_ret) { struct svc_export *exp; struct dentry *dparent; @@ -168,8 +157,6 @@ nfsd_lookup(struct svc_rqst *rqstp, struct svc_fh *fhp, const char *name, exp = fhp->fh_export; exp_get(exp); - err = nfserr_acces; - /* Lookup the name, but don't follow links */ if (isdotent(name, len)) { if (len==1) @@ -190,17 +177,15 @@ nfsd_lookup(struct svc_rqst *rqstp, struct svc_fh *fhp, const char *name, dput(dentry); dentry = dp; - exp2 = exp_parent(exp->ex_client, mnt, dentry, - &rqstp->rq_chandle); - if (IS_ERR(exp2)) { + exp2 = rqst_exp_parent(rqstp, mnt, dentry); + if (PTR_ERR(exp2) == -ENOENT) { + dput(dentry); + dentry = dget(dparent); + } else if (IS_ERR(exp2)) { host_err = PTR_ERR(exp2); dput(dentry); mntput(mnt); goto out_nfserr; - } - if (!exp2) { - dput(dentry); - dentry = dget(dparent); } else { exp_put(exp); exp = exp2; @@ -223,6 +208,41 @@ nfsd_lookup(struct svc_rqst *rqstp, struct svc_fh *fhp, const char *name, } } } + *dentry_ret = dentry; + *exp_ret = exp; + return 0; + +out_nfserr: + exp_put(exp); + return nfserrno(host_err); +} + +/* + * Look up one component of a pathname. + * N.B. After this call _both_ fhp and resfh need an fh_put + * + * If the lookup would cross a mountpoint, and the mounted filesystem + * is exported to the client with NFSEXP_NOHIDE, then the lookup is + * accepted as it stands and the mounted directory is + * returned. Otherwise the covered directory is returned. + * NOTE: this mountpoint crossing is not supported properly by all + * clients and is explicitly disallowed for NFSv3 + * NeilBrown <neilb@cse.unsw.edu.au> + */ +__be32 +nfsd_lookup(struct svc_rqst *rqstp, struct svc_fh *fhp, const char *name, + int len, struct svc_fh *resfh) +{ + struct svc_export *exp; + struct dentry *dentry; + __be32 err; + + err = nfsd_lookup_dentry(rqstp, fhp, name, len, &exp, &dentry); + if (err) + return err; + err = check_nfsd_access(exp, rqstp); + if (err) + goto out; /* * Note: we compose the file handle now, but as the * dentry may be negative, it may need to be updated. @@ -230,16 +250,13 @@ nfsd_lookup(struct svc_rqst *rqstp, struct svc_fh *fhp, const char *name, err = fh_compose(resfh, exp, dentry, fhp); if (!err && !dentry->d_inode) err = nfserr_noent; - dput(dentry); out: + dput(dentry); exp_put(exp); return err; - -out_nfserr: - err = nfserrno(host_err); - goto out; } + /* * Set various file attributes. * N.B. After this call fhp needs an fh_put @@ -311,7 +328,7 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap, /* The size case is special. It changes the file as well as the attributes. */ if (iap->ia_valid & ATTR_SIZE) { if (iap->ia_size < inode->i_size) { - err = nfsd_permission(fhp->fh_export, dentry, MAY_TRUNC|MAY_OWNER_OVERRIDE); + err = nfsd_permission(rqstp, fhp->fh_export, dentry, MAY_TRUNC|MAY_OWNER_OVERRIDE); if (err) goto out; } @@ -435,7 +452,7 @@ nfsd4_set_nfs4_acl(struct svc_rqst *rqstp, struct svc_fh *fhp, /* Get inode */ error = fh_verify(rqstp, fhp, 0 /* S_IFREG */, MAY_SATTR); if (error) - goto out; + return error; dentry = fhp->fh_dentry; inode = dentry->d_inode; @@ -444,33 +461,25 @@ nfsd4_set_nfs4_acl(struct svc_rqst *rqstp, struct svc_fh *fhp, host_error = nfs4_acl_nfsv4_to_posix(acl, &pacl, &dpacl, flags); if (host_error == -EINVAL) { - error = nfserr_attrnotsupp; - goto out; + return nfserr_attrnotsupp; } else if (host_error < 0) goto out_nfserr; host_error = set_nfsv4_acl_one(dentry, pacl, POSIX_ACL_XATTR_ACCESS); if (host_error < 0) - goto out_nfserr; + goto out_release; - if (S_ISDIR(inode->i_mode)) { + if (S_ISDIR(inode->i_mode)) host_error = set_nfsv4_acl_one(dentry, dpacl, POSIX_ACL_XATTR_DEFAULT); - if (host_error < 0) - goto out_nfserr; - } - - error = nfs_ok; -out: +out_release: posix_acl_release(pacl); posix_acl_release(dpacl); - return (error); out_nfserr: if (host_error == -EOPNOTSUPP) - error = nfserr_attrnotsupp; + return nfserr_attrnotsupp; else - error = nfserrno(host_error); - goto out; + return nfserrno(host_error); } static struct posix_acl * @@ -607,7 +616,7 @@ nfsd_access(struct svc_rqst *rqstp, struct svc_fh *fhp, u32 *access, u32 *suppor sresult |= map->access; - err2 = nfsd_permission(export, dentry, map->how); + err2 = nfsd_permission(rqstp, export, dentry, map->how); switch (err2) { case nfs_ok: result |= map->access; @@ -1034,7 +1043,7 @@ nfsd_read(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file, __be32 err; if (file) { - err = nfsd_permission(fhp->fh_export, fhp->fh_dentry, + err = nfsd_permission(rqstp, fhp->fh_export, fhp->fh_dentry, MAY_READ|MAY_OWNER_OVERRIDE); if (err) goto out; @@ -1063,7 +1072,7 @@ nfsd_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file, __be32 err = 0; if (file) { - err = nfsd_permission(fhp->fh_export, fhp->fh_dentry, + err = nfsd_permission(rqstp, fhp->fh_export, fhp->fh_dentry, MAY_WRITE|MAY_OWNER_OVERRIDE); if (err) goto out; @@ -1792,7 +1801,8 @@ nfsd_statfs(struct svc_rqst *rqstp, struct svc_fh *fhp, struct kstatfs *stat) * Check for a user's access permissions to this inode. */ __be32 -nfsd_permission(struct svc_export *exp, struct dentry *dentry, int acc) +nfsd_permission(struct svc_rqst *rqstp, struct svc_export *exp, + struct dentry *dentry, int acc) { struct inode *inode = dentry->d_inode; int err; @@ -1823,7 +1833,7 @@ nfsd_permission(struct svc_export *exp, struct dentry *dentry, int acc) */ if (!(acc & MAY_LOCAL_ACCESS)) if (acc & (MAY_WRITE | MAY_SATTR | MAY_TRUNC)) { - if (EX_RDONLY(exp) || IS_RDONLY(inode)) + if (EX_RDONLY(exp, rqstp) || IS_RDONLY(inode)) return nfserr_rofs; if (/* (acc & MAY_WRITE) && */ IS_IMMUTABLE(inode)) return nfserr_perm; diff --git a/fs/ntfs/namei.c b/fs/ntfs/namei.c index bff01a54675..e93c6142b23 100644 --- a/fs/ntfs/namei.c +++ b/fs/ntfs/namei.c @@ -21,6 +21,7 @@ */ #include <linux/dcache.h> +#include <linux/exportfs.h> #include <linux/security.h> #include "attrib.h" diff --git a/fs/ocfs2/export.h b/fs/ocfs2/export.h index 5b77ee7866e..e08bed9e45a 100644 --- a/fs/ocfs2/export.h +++ b/fs/ocfs2/export.h @@ -26,6 +26,8 @@ #ifndef OCFS2_EXPORT_H #define OCFS2_EXPORT_H +#include <linux/exportfs.h> + extern struct export_operations ocfs2_export_ops; #endif /* OCFS2_EXPORT_H */ diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index f04c7aa834c..004c2abbc73 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -1867,7 +1867,8 @@ static ssize_t ocfs2_file_buffered_write(struct file *file, loff_t *ppos, loff_t pos; const struct iovec *cur_iov = iov; struct page *user_page, *page; - char *buf, *dst; + char * uninitialized_var(buf); + char *dst; void *fsdata; /* diff --git a/fs/ocfs2/ioctl.c b/fs/ocfs2/ioctl.c index bd68c3f2afb..87dcece7e1b 100644 --- a/fs/ocfs2/ioctl.c +++ b/fs/ocfs2/ioctl.c @@ -63,7 +63,7 @@ static int ocfs2_set_inode_attr(struct inode *inode, unsigned flags, goto bail_unlock; status = -EACCES; - if ((current->fsuid != inode->i_uid) && !capable(CAP_FOWNER)) + if (!is_owner_or_cap(inode)) goto bail_unlock; if (!S_ISDIR(inode->i_mode)) diff --git a/fs/proc/base.c b/fs/proc/base.c index ae3627337a9..42cb4f5613b 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -283,7 +283,7 @@ static int proc_pid_auxv(struct task_struct *task, char *buffer) static int proc_pid_wchan(struct task_struct *task, char *buffer) { unsigned long wchan; - char symname[KSYM_NAME_LEN+1]; + char symname[KSYM_NAME_LEN]; wchan = get_wchan(task); diff --git a/fs/ramfs/inode.c b/fs/ramfs/inode.c index d40d22b347b..ef2b46d099f 100644 --- a/fs/ramfs/inode.c +++ b/fs/ramfs/inode.c @@ -60,6 +60,7 @@ struct inode *ramfs_get_inode(struct super_block *sb, int mode, dev_t dev) inode->i_blocks = 0; inode->i_mapping->a_ops = &ramfs_aops; inode->i_mapping->backing_dev_info = &ramfs_backing_dev_info; + mapping_set_gfp_mask(inode->i_mapping, GFP_HIGHUSER); inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; switch (mode & S_IFMT) { default: diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c index 1272d11399f..ddde489f1cb 100644 --- a/fs/reiserfs/inode.c +++ b/fs/reiserfs/inode.c @@ -7,6 +7,7 @@ #include <linux/reiserfs_fs.h> #include <linux/reiserfs_acl.h> #include <linux/reiserfs_xattr.h> +#include <linux/exportfs.h> #include <linux/smp_lock.h> #include <linux/pagemap.h> #include <linux/highmem.h> diff --git a/fs/reiserfs/ioctl.c b/fs/reiserfs/ioctl.c index b484d2913c0..11a0fcc2d40 100644 --- a/fs/reiserfs/ioctl.c +++ b/fs/reiserfs/ioctl.c @@ -51,8 +51,7 @@ int reiserfs_ioctl(struct inode *inode, struct file *filp, unsigned int cmd, if (IS_RDONLY(inode)) return -EROFS; - if ((current->fsuid != inode->i_uid) - && !capable(CAP_FOWNER)) + if (!is_owner_or_cap(inode)) return -EPERM; if (get_user(flags, (int __user *)arg)) @@ -81,7 +80,7 @@ int reiserfs_ioctl(struct inode *inode, struct file *filp, unsigned int cmd, case REISERFS_IOC_GETVERSION: return put_user(inode->i_generation, (int __user *)arg); case REISERFS_IOC_SETVERSION: - if ((current->fsuid != inode->i_uid) && !capable(CAP_FOWNER)) + if (!is_owner_or_cap(inode)) return -EPERM; if (IS_RDONLY(inode)) return -EROFS; diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c index b4ac9119200..5a93cfe1a03 100644 --- a/fs/reiserfs/super.c +++ b/fs/reiserfs/super.c @@ -21,6 +21,7 @@ #include <linux/init.h> #include <linux/blkdev.h> #include <linux/buffer_head.h> +#include <linux/exportfs.h> #include <linux/vfs.h> #include <linux/mnt_namespace.h> #include <linux/mount.h> diff --git a/fs/reiserfs/xattr_acl.c b/fs/reiserfs/xattr_acl.c index 5296a29cc5e..b7e4fa4539d 100644 --- a/fs/reiserfs/xattr_acl.c +++ b/fs/reiserfs/xattr_acl.c @@ -21,7 +21,7 @@ xattr_set_acl(struct inode *inode, int type, const void *value, size_t size) if (!reiserfs_posixacl(inode->i_sb)) return -EOPNOTSUPP; - if ((current->fsuid != inode->i_uid) && !capable(CAP_FOWNER)) + if (!is_owner_or_cap(inode)) return -EPERM; if (value) { diff --git a/fs/udf/super.c b/fs/udf/super.c index 6658afb41cc..d6a504f5d75 100644 --- a/fs/udf/super.c +++ b/fs/udf/super.c @@ -1356,7 +1356,7 @@ udf_load_partition(struct super_block *sb, kernel_lb_addr *fileset) case UDF_VIRTUAL_MAP15: case UDF_VIRTUAL_MAP20: { - kernel_lb_addr ino; + kernel_lb_addr uninitialized_var(ino); if (!UDF_SB_LASTBLOCK(sb)) { diff --git a/fs/utimes.c b/fs/utimes.c index 83a7e69e706..682eb63b20a 100644 --- a/fs/utimes.c +++ b/fs/utimes.c @@ -106,7 +106,7 @@ long do_utimes(int dfd, char __user *filename, struct timespec *times, int flags if (IS_IMMUTABLE(inode)) goto dput_and_out; - if ((current->fsuid != inode->i_uid) && !capable(CAP_FOWNER)) { + if (!is_owner_or_cap(inode)) { if (f) { if (!(f->f_mode & FMODE_WRITE)) goto dput_and_out; diff --git a/fs/xattr.c b/fs/xattr.c index 4523aca7965..a44fd92caca 100644 --- a/fs/xattr.c +++ b/fs/xattr.c @@ -60,8 +60,7 @@ xattr_permission(struct inode *inode, const char *name, int mask) if (!S_ISREG(inode->i_mode) && !S_ISDIR(inode->i_mode)) return -EPERM; if (S_ISDIR(inode->i_mode) && (inode->i_mode & S_ISVTX) && - (mask & MAY_WRITE) && (current->fsuid != inode->i_uid) && - !capable(CAP_FOWNER)) + (mask & MAY_WRITE) && !is_owner_or_cap(inode)) return -EPERM; } diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/linux-2.6/xfs_buf.c index 2df63622354..b0f0e58866d 100644 --- a/fs/xfs/linux-2.6/xfs_buf.c +++ b/fs/xfs/linux-2.6/xfs_buf.c @@ -35,10 +35,13 @@ #include <linux/freezer.h> static kmem_zone_t *xfs_buf_zone; -static struct shrinker *xfs_buf_shake; STATIC int xfsbufd(void *); STATIC int xfsbufd_wakeup(int, gfp_t); STATIC void xfs_buf_delwri_queue(xfs_buf_t *, int); +static struct shrinker xfs_buf_shake = { + .shrink = xfsbufd_wakeup, + .seeks = DEFAULT_SEEKS, +}; static struct workqueue_struct *xfslogd_workqueue; struct workqueue_struct *xfsdatad_workqueue; @@ -1832,14 +1835,9 @@ xfs_buf_init(void) if (!xfsdatad_workqueue) goto out_destroy_xfslogd_workqueue; - xfs_buf_shake = set_shrinker(DEFAULT_SEEKS, xfsbufd_wakeup); - if (!xfs_buf_shake) - goto out_destroy_xfsdatad_workqueue; - + register_shrinker(&xfs_buf_shake); return 0; - out_destroy_xfsdatad_workqueue: - destroy_workqueue(xfsdatad_workqueue); out_destroy_xfslogd_workqueue: destroy_workqueue(xfslogd_workqueue); out_free_buf_zone: @@ -1854,7 +1852,7 @@ xfs_buf_init(void) void xfs_buf_terminate(void) { - remove_shrinker(xfs_buf_shake); + unregister_shrinker(&xfs_buf_shake); destroy_workqueue(xfsdatad_workqueue); destroy_workqueue(xfslogd_workqueue); kmem_zone_destroy(xfs_buf_zone); diff --git a/fs/xfs/linux-2.6/xfs_super.c b/fs/xfs/linux-2.6/xfs_super.c index 06894cf00b1..4528f9a3f30 100644 --- a/fs/xfs/linux-2.6/xfs_super.c +++ b/fs/xfs/linux-2.6/xfs_super.c @@ -562,6 +562,7 @@ xfssyncd( bhv_vfs_sync_work_t *work, *n; LIST_HEAD (tmp); + set_freezable(); timeleft = xfs_syncd_centisecs * msecs_to_jiffies(10); for (;;) { timeleft = schedule_timeout_interruptible(timeleft); diff --git a/fs/xfs/linux-2.6/xfs_super.h b/fs/xfs/linux-2.6/xfs_super.h index 33dd1ca1324..201cc3273c8 100644 --- a/fs/xfs/linux-2.6/xfs_super.h +++ b/fs/xfs/linux-2.6/xfs_super.h @@ -18,6 +18,8 @@ #ifndef __XFS_SUPER_H__ #define __XFS_SUPER_H__ +#include <linux/exportfs.h> + #ifdef CONFIG_XFS_DMAPI # define vfs_insertdmapi(vfs) vfs_insertops(vfsp, &xfs_dmops) # define vfs_initdmapi() dmapi_init() diff --git a/fs/xfs/quota/xfs_qm.c b/fs/xfs/quota/xfs_qm.c index 7def4c69934..2d274b23ade 100644 --- a/fs/xfs/quota/xfs_qm.c +++ b/fs/xfs/quota/xfs_qm.c @@ -62,7 +62,6 @@ uint ndquot; kmem_zone_t *qm_dqzone; kmem_zone_t *qm_dqtrxzone; -static struct shrinker *xfs_qm_shaker; static cred_t xfs_zerocr; @@ -78,6 +77,11 @@ STATIC int xfs_qm_init_quotainos(xfs_mount_t *); STATIC int xfs_qm_init_quotainfo(xfs_mount_t *); STATIC int xfs_qm_shake(int, gfp_t); +static struct shrinker xfs_qm_shaker = { + .shrink = xfs_qm_shake, + .seeks = DEFAULT_SEEKS, +}; + #ifdef DEBUG extern mutex_t qcheck_lock; #endif @@ -149,7 +153,7 @@ xfs_Gqm_init(void) } else xqm->qm_dqzone = qm_dqzone; - xfs_qm_shaker = set_shrinker(DEFAULT_SEEKS, xfs_qm_shake); + register_shrinker(&xfs_qm_shaker); /* * The t_dqinfo portion of transactions. @@ -181,7 +185,7 @@ xfs_qm_destroy( ASSERT(xqm != NULL); ASSERT(xqm->qm_nrefs == 0); - remove_shrinker(xfs_qm_shaker); + unregister_shrinker(&xfs_qm_shaker); hsize = xqm->qm_dqhashmask + 1; for (i = 0; i < hsize; i++) { xfs_qm_list_destroy(&(xqm->qm_usr_dqhtable[i])); |