diff options
Diffstat (limited to 'fs')
62 files changed, 718 insertions, 581 deletions
diff --git a/fs/Kconfig b/fs/Kconfig index 987b5d7cb21..ea5b3594762 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -1152,7 +1152,7 @@ config BEFS_DEBUG depends on BEFS_FS help If you say Y here, you can use the 'debug' mount option to enable - debugging output from the driver. + debugging output from the driver. config BFS_FS tristate "BFS file system support (EXPERIMENTAL)" @@ -1263,7 +1263,7 @@ config JFFS2_FS_XATTR Extended attributes are name:value pairs associated with inodes by the kernel or by users (see the attr(5) manual page, or visit <http://acl.bestbits.at/> for details). - + If unsure, say N. config JFFS2_FS_POSIX_ACL @@ -1274,10 +1274,10 @@ config JFFS2_FS_POSIX_ACL help Posix Access Control Lists (ACLs) support permissions for users and groups beyond the owner/group/world scheme. - + To learn more about Access Control Lists, visit the Posix ACLs for Linux website <http://acl.bestbits.at/>. - + If you don't know what Access Control Lists are, say N config JFFS2_FS_SECURITY @@ -1289,7 +1289,7 @@ config JFFS2_FS_SECURITY implemented by security modules like SELinux. This option enables an extended attribute handler for file security labels in the jffs2 filesystem. - + If you are not using a security module that requires using extended attributes for file security labels, say N. @@ -1835,7 +1835,7 @@ config RPCSEC_GSS_SPKM3 If unsure, say N. config SMB_FS - tristate "SMB file system support (to mount Windows shares etc.)" + tristate "SMB file system support (OBSOLETE, please use CIFS)" depends on INET select NLS help @@ -1858,8 +1858,8 @@ config SMB_FS General information about how to connect Linux, Windows machines and Macs is on the WWW at <http://www.eats.com/linux_mac_win.html>. - To compile the SMB support as a module, choose M here: the module will - be called smbfs. Most people say N, however. + To compile the SMB support as a module, choose M here: + the module will be called smbfs. Most people say N, however. config SMB_NLS_DEFAULT bool "Use a default NLS" @@ -1891,7 +1891,7 @@ config SMB_NLS_REMOTE smbmount from samba 2.2.0 or later supports this. config CIFS - tristate "CIFS support (advanced network filesystem for Samba, Window and other CIFS compliant servers)" + tristate "CIFS support (advanced network filesystem, SMBFS successor)" depends on INET select NLS help @@ -1949,16 +1949,16 @@ config CIFS_WEAK_PW_HASH LANMAN based servers such as OS/2 and Windows 95, but such mounts may be less secure than mounts using NTLM or more recent security mechanisms if you are on a public network. Unless you - have a need to access old SMB servers (and are on a private + have a need to access old SMB servers (and are on a private network) you probably want to say N. Even if this support is enabled in the kernel build, LANMAN authentication will not be used automatically. At runtime LANMAN mounts are disabled but can be set to required (or optional) either in /proc/fs/cifs (see fs/cifs/README for more detail) or via an - option on the mount command. This support is disabled by + option on the mount command. This support is disabled by default in order to reduce the possibility of a downgrade attack. - + If unsure, say N. config CIFS_XATTR @@ -1999,7 +1999,7 @@ config CIFS_DEBUG2 messages in some error paths, slowing performance. This option can be turned off unless you are debugging cifs problems. If unsure, say N. - + config CIFS_EXPERIMENTAL bool "CIFS Experimental Features (EXPERIMENTAL)" depends on CIFS && EXPERIMENTAL @@ -2090,7 +2090,7 @@ config CODA_FS_OLD_API However this new API is not backward compatible with older clients. If you really need to run the old Coda userspace cache manager then say Y. - + For most cases you probably want to say N. config AFS_FS diff --git a/fs/block_dev.c b/fs/block_dev.c index e48a630ae26..e63067d25cd 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -534,7 +534,6 @@ void __init bdev_cache_init(void) if (err) panic("Cannot register bdev pseudo-fs"); bd_mnt = kern_mount(&bd_type); - err = PTR_ERR(bd_mnt); if (IS_ERR(bd_mnt)) panic("Cannot create bdev pseudo-fs"); blockdev_superblock = bd_mnt->mnt_sb; /* For writeback */ diff --git a/fs/compat.c b/fs/compat.c index 69baca5ad60..ee80ff341d3 100644 --- a/fs/compat.c +++ b/fs/compat.c @@ -2083,51 +2083,6 @@ long asmlinkage compat_sys_nfsservctl(int cmd, void *notused, void *notused2) #ifdef CONFIG_EPOLL -#ifdef CONFIG_HAS_COMPAT_EPOLL_EVENT -asmlinkage long compat_sys_epoll_ctl(int epfd, int op, int fd, - struct compat_epoll_event __user *event) -{ - long err = 0; - struct compat_epoll_event user; - struct epoll_event __user *kernel = NULL; - - if (event) { - if (copy_from_user(&user, event, sizeof(user))) - return -EFAULT; - kernel = compat_alloc_user_space(sizeof(struct epoll_event)); - err |= __put_user(user.events, &kernel->events); - err |= __put_user(user.data, &kernel->data); - } - - return err ? err : sys_epoll_ctl(epfd, op, fd, kernel); -} - - -asmlinkage long compat_sys_epoll_wait(int epfd, - struct compat_epoll_event __user *events, - int maxevents, int timeout) -{ - long i, ret, err = 0; - struct epoll_event __user *kbuf; - struct epoll_event ev; - - if ((maxevents <= 0) || - (maxevents > (INT_MAX / sizeof(struct epoll_event)))) - return -EINVAL; - kbuf = compat_alloc_user_space(sizeof(struct epoll_event) * maxevents); - ret = sys_epoll_wait(epfd, kbuf, maxevents, timeout); - for (i = 0; i < ret; i++) { - err |= __get_user(ev.events, &kbuf[i].events); - err |= __get_user(ev.data, &kbuf[i].data); - err |= __put_user(ev.events, &events->events); - err |= __put_user_unaligned(ev.data, &events->data); - events++; - } - - return err ? -EFAULT: ret; -} -#endif /* CONFIG_HAS_COMPAT_EPOLL_EVENT */ - #ifdef TIF_RESTORE_SIGMASK asmlinkage long compat_sys_epoll_pwait(int epfd, struct compat_epoll_event __user *events, @@ -2153,11 +2108,7 @@ asmlinkage long compat_sys_epoll_pwait(int epfd, sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved); } -#ifdef CONFIG_HAS_COMPAT_EPOLL_EVENT - err = compat_sys_epoll_wait(epfd, events, maxevents, timeout); -#else err = sys_epoll_wait(epfd, events, maxevents, timeout); -#endif /* * If we changed the signal mask, we need to restore the original one. diff --git a/fs/dcache.c b/fs/dcache.c index d9ca1e5ceb9..44f6cf23b70 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -89,7 +89,7 @@ static void d_free(struct dentry *dentry) if (dentry->d_op && dentry->d_op->d_release) dentry->d_op->d_release(dentry); /* if dentry was never inserted into hash, immediate free is OK */ - if (dentry->d_hash.pprev == NULL) + if (hlist_unhashed(&dentry->d_hash)) __d_free(dentry); else call_rcu(&dentry->d_u.d_rcu, d_callback); @@ -1408,9 +1408,6 @@ void d_delete(struct dentry * dentry) if (atomic_read(&dentry->d_count) == 1) { dentry_iput(dentry); fsnotify_nameremove(dentry, isdir); - - /* remove this and other inotify debug checks after 2.6.18 */ - dentry->d_flags &= ~DCACHE_INOTIFY_PARENT_WATCHED; return; } diff --git a/fs/dquot.c b/fs/dquot.c index cee7c6f428f..def4e969df7 100644 --- a/fs/dquot.c +++ b/fs/dquot.c @@ -696,9 +696,8 @@ static int dqinit_needed(struct inode *inode, int type) /* This routine is guarded by dqonoff_mutex mutex */ static void add_dquot_ref(struct super_block *sb, int type) { - struct inode *inode; + struct inode *inode, *old_inode = NULL; -restart: spin_lock(&inode_lock); list_for_each_entry(inode, &sb->s_inodes, i_sb_list) { if (!atomic_read(&inode->i_writecount)) @@ -711,12 +710,18 @@ restart: __iget(inode); spin_unlock(&inode_lock); + iput(old_inode); sb->dq_op->initialize(inode, type); - iput(inode); - /* As we may have blocked we had better restart... */ - goto restart; + /* We hold a reference to 'inode' so it couldn't have been + * removed from s_inodes list while we dropped the inode_lock. + * We cannot iput the inode now as we can be holding the last + * reference and we cannot iput it under inode_lock. So we + * keep the reference and iput it later. */ + old_inode = inode; + spin_lock(&inode_lock); } spin_unlock(&inode_lock); + iput(old_inode); } /* Return 0 if dqput() won't block (note that 1 doesn't necessarily mean blocking) */ diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c index f8ef0af919e..a066e109ad9 100644 --- a/fs/ecryptfs/crypto.c +++ b/fs/ecryptfs/crypto.c @@ -355,8 +355,11 @@ static int encrypt_scatterlist(struct ecryptfs_crypt_stat *crypt_stat, } /* Consider doing this once, when the file is opened */ mutex_lock(&crypt_stat->cs_tfm_mutex); - rc = crypto_blkcipher_setkey(crypt_stat->tfm, crypt_stat->key, - crypt_stat->key_size); + if (!(crypt_stat->flags & ECRYPTFS_KEY_SET)) { + rc = crypto_blkcipher_setkey(crypt_stat->tfm, crypt_stat->key, + crypt_stat->key_size); + crypt_stat->flags |= ECRYPTFS_KEY_SET; + } if (rc) { ecryptfs_printk(KERN_ERR, "Error setting key; rc = [%d]\n", rc); @@ -376,11 +379,10 @@ out: * * Convert an eCryptfs page index into a lower byte offset */ -void ecryptfs_lower_offset_for_extent(loff_t *offset, loff_t extent_num, - struct ecryptfs_crypt_stat *crypt_stat) +static void ecryptfs_lower_offset_for_extent(loff_t *offset, loff_t extent_num, + struct ecryptfs_crypt_stat *crypt_stat) { - (*offset) = ((crypt_stat->extent_size - * crypt_stat->num_header_extents_at_front) + (*offset) = (crypt_stat->num_header_bytes_at_front + (crypt_stat->extent_size * extent_num)); } @@ -842,15 +844,13 @@ void ecryptfs_set_default_sizes(struct ecryptfs_crypt_stat *crypt_stat) set_extent_mask_and_shift(crypt_stat); crypt_stat->iv_bytes = ECRYPTFS_DEFAULT_IV_BYTES; if (crypt_stat->flags & ECRYPTFS_METADATA_IN_XATTR) - crypt_stat->num_header_extents_at_front = 0; + crypt_stat->num_header_bytes_at_front = 0; else { if (PAGE_CACHE_SIZE <= ECRYPTFS_MINIMUM_HEADER_EXTENT_SIZE) - crypt_stat->num_header_extents_at_front = - (ECRYPTFS_MINIMUM_HEADER_EXTENT_SIZE - / crypt_stat->extent_size); + crypt_stat->num_header_bytes_at_front = + ECRYPTFS_MINIMUM_HEADER_EXTENT_SIZE; else - crypt_stat->num_header_extents_at_front = - (PAGE_CACHE_SIZE / crypt_stat->extent_size); + crypt_stat->num_header_bytes_at_front = PAGE_CACHE_SIZE; } } @@ -1128,7 +1128,7 @@ write_ecryptfs_flags(char *page_virt, struct ecryptfs_crypt_stat *crypt_stat, struct ecryptfs_cipher_code_str_map_elem { char cipher_str[16]; - u16 cipher_code; + u8 cipher_code; }; /* Add support for additional ciphers by adding elements here. The @@ -1152,10 +1152,10 @@ ecryptfs_cipher_code_str_map[] = { * * Returns zero on no match, or the cipher code on match */ -u16 ecryptfs_code_for_cipher_string(struct ecryptfs_crypt_stat *crypt_stat) +u8 ecryptfs_code_for_cipher_string(struct ecryptfs_crypt_stat *crypt_stat) { int i; - u16 code = 0; + u8 code = 0; struct ecryptfs_cipher_code_str_map_elem *map = ecryptfs_cipher_code_str_map; @@ -1187,7 +1187,7 @@ u16 ecryptfs_code_for_cipher_string(struct ecryptfs_crypt_stat *crypt_stat) * * Returns zero on success */ -int ecryptfs_cipher_code_to_string(char *str, u16 cipher_code) +int ecryptfs_cipher_code_to_string(char *str, u8 cipher_code) { int rc = 0; int i; @@ -1236,7 +1236,8 @@ ecryptfs_write_header_metadata(char *virt, header_extent_size = (u32)crypt_stat->extent_size; num_header_extents_at_front = - (u16)crypt_stat->num_header_extents_at_front; + (u16)(crypt_stat->num_header_bytes_at_front + / crypt_stat->extent_size); header_extent_size = cpu_to_be32(header_extent_size); memcpy(virt, &header_extent_size, 4); virt += 4; @@ -1311,40 +1312,16 @@ static int ecryptfs_write_headers_virt(char *page_virt, size_t *size, static int ecryptfs_write_metadata_to_contents(struct ecryptfs_crypt_stat *crypt_stat, struct dentry *ecryptfs_dentry, - char *page_virt) + char *virt) { - int current_header_page; - int header_pages; int rc; - rc = ecryptfs_write_lower(ecryptfs_dentry->d_inode, page_virt, - 0, PAGE_CACHE_SIZE); - if (rc) { + rc = ecryptfs_write_lower(ecryptfs_dentry->d_inode, virt, + 0, crypt_stat->num_header_bytes_at_front); + if (rc) printk(KERN_ERR "%s: Error attempting to write header " "information to lower file; rc = [%d]\n", __FUNCTION__, rc); - goto out; - } - header_pages = ((crypt_stat->extent_size - * crypt_stat->num_header_extents_at_front) - / PAGE_CACHE_SIZE); - memset(page_virt, 0, PAGE_CACHE_SIZE); - current_header_page = 1; - while (current_header_page < header_pages) { - loff_t offset; - - offset = (((loff_t)current_header_page) << PAGE_CACHE_SHIFT); - if ((rc = ecryptfs_write_lower(ecryptfs_dentry->d_inode, - page_virt, offset, - PAGE_CACHE_SIZE))) { - printk(KERN_ERR "%s: Error attempting to write header " - "information to lower file; rc = [%d]\n", - __FUNCTION__, rc); - goto out; - } - current_header_page++; - } -out: return rc; } @@ -1370,15 +1347,13 @@ ecryptfs_write_metadata_to_xattr(struct dentry *ecryptfs_dentry, * retrieved via a prompt. Exactly what happens at this point should * be policy-dependent. * - * TODO: Support header information spanning multiple pages - * * Returns zero on success; non-zero on error */ int ecryptfs_write_metadata(struct dentry *ecryptfs_dentry) { struct ecryptfs_crypt_stat *crypt_stat = &ecryptfs_inode_to_private(ecryptfs_dentry->d_inode)->crypt_stat; - char *page_virt; + char *virt; size_t size = 0; int rc = 0; @@ -1389,40 +1364,39 @@ int ecryptfs_write_metadata(struct dentry *ecryptfs_dentry) goto out; } } else { + printk(KERN_WARNING "%s: Encrypted flag not set\n", + __FUNCTION__); rc = -EINVAL; - ecryptfs_printk(KERN_WARNING, - "Called with crypt_stat->encrypted == 0\n"); goto out; } /* Released in this function */ - page_virt = kmem_cache_zalloc(ecryptfs_header_cache_0, GFP_USER); - if (!page_virt) { - ecryptfs_printk(KERN_ERR, "Out of memory\n"); + virt = kzalloc(crypt_stat->num_header_bytes_at_front, GFP_KERNEL); + if (!virt) { + printk(KERN_ERR "%s: Out of memory\n", __FUNCTION__); rc = -ENOMEM; goto out; } - rc = ecryptfs_write_headers_virt(page_virt, &size, crypt_stat, - ecryptfs_dentry); + rc = ecryptfs_write_headers_virt(virt, &size, crypt_stat, + ecryptfs_dentry); if (unlikely(rc)) { - ecryptfs_printk(KERN_ERR, "Error whilst writing headers\n"); - memset(page_virt, 0, PAGE_CACHE_SIZE); + printk(KERN_ERR "%s: Error whilst writing headers; rc = [%d]\n", + __FUNCTION__, rc); goto out_free; } if (crypt_stat->flags & ECRYPTFS_METADATA_IN_XATTR) rc = ecryptfs_write_metadata_to_xattr(ecryptfs_dentry, - crypt_stat, page_virt, - size); + crypt_stat, virt, size); else rc = ecryptfs_write_metadata_to_contents(crypt_stat, - ecryptfs_dentry, - page_virt); + ecryptfs_dentry, virt); if (rc) { - printk(KERN_ERR "Error writing metadata out to lower file; " - "rc = [%d]\n", rc); + printk(KERN_ERR "%s: Error writing metadata out to lower file; " + "rc = [%d]\n", __FUNCTION__, rc); goto out_free; } out_free: - kmem_cache_free(ecryptfs_header_cache_0, page_virt); + memset(virt, 0, crypt_stat->num_header_bytes_at_front); + kfree(virt); out: return rc; } @@ -1442,16 +1416,16 @@ static int parse_header_metadata(struct ecryptfs_crypt_stat *crypt_stat, virt += sizeof(u32); memcpy(&num_header_extents_at_front, virt, sizeof(u16)); num_header_extents_at_front = be16_to_cpu(num_header_extents_at_front); - crypt_stat->num_header_extents_at_front = - (int)num_header_extents_at_front; + crypt_stat->num_header_bytes_at_front = + (((size_t)num_header_extents_at_front + * (size_t)header_extent_size)); (*bytes_read) = (sizeof(u32) + sizeof(u16)); if ((validate_header_size == ECRYPTFS_VALIDATE_HEADER_SIZE) - && ((crypt_stat->extent_size - * crypt_stat->num_header_extents_at_front) + && (crypt_stat->num_header_bytes_at_front < ECRYPTFS_MINIMUM_HEADER_EXTENT_SIZE)) { rc = -EINVAL; - printk(KERN_WARNING "Invalid number of header extents: [%zd]\n", - crypt_stat->num_header_extents_at_front); + printk(KERN_WARNING "Invalid header size: [%zd]\n", + crypt_stat->num_header_bytes_at_front); } return rc; } @@ -1466,7 +1440,8 @@ static int parse_header_metadata(struct ecryptfs_crypt_stat *crypt_stat, */ static void set_default_header_data(struct ecryptfs_crypt_stat *crypt_stat) { - crypt_stat->num_header_extents_at_front = 2; + crypt_stat->num_header_bytes_at_front = + ECRYPTFS_MINIMUM_HEADER_EXTENT_SIZE; } /** @@ -1552,9 +1527,10 @@ int ecryptfs_read_xattr_region(char *page_virt, struct inode *ecryptfs_inode) size = ecryptfs_getxattr_lower(lower_dentry, ECRYPTFS_XATTR_NAME, page_virt, ECRYPTFS_DEFAULT_EXTENT_SIZE); if (size < 0) { - printk(KERN_ERR "Error attempting to read the [%s] " - "xattr from the lower file; return value = [%zd]\n", - ECRYPTFS_XATTR_NAME, size); + if (unlikely(ecryptfs_verbosity > 0)) + printk(KERN_INFO "Error attempting to read the [%s] " + "xattr from the lower file; return value = " + "[%zd]\n", ECRYPTFS_XATTR_NAME, size); rc = -EINVAL; goto out; } @@ -1802,7 +1778,7 @@ out: } struct kmem_cache *ecryptfs_key_tfm_cache; -struct list_head key_tfm_list; +static struct list_head key_tfm_list; struct mutex key_tfm_list_mutex; int ecryptfs_init_crypto(void) @@ -1812,6 +1788,11 @@ int ecryptfs_init_crypto(void) return 0; } +/** + * ecryptfs_destroy_crypto - free all cached key_tfms on key_tfm_list + * + * Called only at module unload time + */ int ecryptfs_destroy_crypto(void) { struct ecryptfs_key_tfm *key_tfm, *key_tfm_tmp; @@ -1835,6 +1816,8 @@ ecryptfs_add_new_key_tfm(struct ecryptfs_key_tfm **key_tfm, char *cipher_name, struct ecryptfs_key_tfm *tmp_tfm; int rc = 0; + BUG_ON(!mutex_is_locked(&key_tfm_list_mutex)); + tmp_tfm = kmem_cache_alloc(ecryptfs_key_tfm_cache, GFP_KERNEL); if (key_tfm != NULL) (*key_tfm) = tmp_tfm; @@ -1861,13 +1844,50 @@ ecryptfs_add_new_key_tfm(struct ecryptfs_key_tfm **key_tfm, char *cipher_name, (*key_tfm) = NULL; goto out; } - mutex_lock(&key_tfm_list_mutex); list_add(&tmp_tfm->key_tfm_list, &key_tfm_list); - mutex_unlock(&key_tfm_list_mutex); out: return rc; } +/** + * ecryptfs_tfm_exists - Search for existing tfm for cipher_name. + * @cipher_name: the name of the cipher to search for + * @key_tfm: set to corresponding tfm if found + * + * Searches for cached key_tfm matching @cipher_name + * Must be called with &key_tfm_list_mutex held + * Returns 1 if found, with @key_tfm set + * Returns 0 if not found, with @key_tfm set to NULL + */ +int ecryptfs_tfm_exists(char *cipher_name, struct ecryptfs_key_tfm **key_tfm) +{ + struct ecryptfs_key_tfm *tmp_key_tfm; + + BUG_ON(!mutex_is_locked(&key_tfm_list_mutex)); + + list_for_each_entry(tmp_key_tfm, &key_tfm_list, key_tfm_list) { + if (strcmp(tmp_key_tfm->cipher_name, cipher_name) == 0) { + if (key_tfm) + (*key_tfm) = tmp_key_tfm; + return 1; + } + } + if (key_tfm) + (*key_tfm) = NULL; + return 0; +} + +/** + * ecryptfs_get_tfm_and_mutex_for_cipher_name + * + * @tfm: set to cached tfm found, or new tfm created + * @tfm_mutex: set to mutex for cached tfm found, or new tfm created + * @cipher_name: the name of the cipher to search for and/or add + * + * Sets pointers to @tfm & @tfm_mutex matching @cipher_name. + * Searches for cached item first, and creates new if not found. + * Returns 0 on success, non-zero if adding new cipher failed + */ int ecryptfs_get_tfm_and_mutex_for_cipher_name(struct crypto_blkcipher **tfm, struct mutex **tfm_mutex, char *cipher_name) @@ -1877,22 +1897,17 @@ int ecryptfs_get_tfm_and_mutex_for_cipher_name(struct crypto_blkcipher **tfm, (*tfm) = NULL; (*tfm_mutex) = NULL; + mutex_lock(&key_tfm_list_mutex); - list_for_each_entry(key_tfm, &key_tfm_list, key_tfm_list) { - if (strcmp(key_tfm->cipher_name, cipher_name) == 0) { - (*tfm) = key_tfm->key_tfm; - (*tfm_mutex) = &key_tfm->key_tfm_mutex; - mutex_unlock(&key_tfm_list_mutex); + if (!ecryptfs_tfm_exists(cipher_name, &key_tfm)) { + rc = ecryptfs_add_new_key_tfm(&key_tfm, cipher_name, 0); + if (rc) { + printk(KERN_ERR "Error adding new key_tfm to list; " + "rc = [%d]\n", rc); goto out; } } mutex_unlock(&key_tfm_list_mutex); - rc = ecryptfs_add_new_key_tfm(&key_tfm, cipher_name, 0); - if (rc) { - printk(KERN_ERR "Error adding new key_tfm to list; rc = [%d]\n", - rc); - goto out; - } (*tfm) = key_tfm->key_tfm; (*tfm_mutex) = &key_tfm->key_tfm_mutex; out: diff --git a/fs/ecryptfs/ecryptfs_kernel.h b/fs/ecryptfs/ecryptfs_kernel.h index ce7a5d4aec3..5007f788da0 100644 --- a/fs/ecryptfs/ecryptfs_kernel.h +++ b/fs/ecryptfs/ecryptfs_kernel.h @@ -234,10 +234,11 @@ struct ecryptfs_crypt_stat { #define ECRYPTFS_KEY_VALID 0x00000080 #define ECRYPTFS_METADATA_IN_XATTR 0x00000100 #define ECRYPTFS_VIEW_AS_ENCRYPTED 0x00000200 +#define ECRYPTFS_KEY_SET 0x00000400 u32 flags; unsigned int file_version; size_t iv_bytes; - size_t num_header_extents_at_front; + size_t num_header_bytes_at_front; size_t extent_size; /* Data extent size; default is 4096 */ size_t key_size; size_t extent_shift; @@ -322,7 +323,6 @@ struct ecryptfs_key_tfm { unsigned char cipher_name[ECRYPTFS_MAX_CIPHER_NAME_SIZE + 1]; }; -extern struct list_head key_tfm_list; extern struct mutex key_tfm_list_mutex; /** @@ -521,11 +521,9 @@ extern struct kmem_cache *ecryptfs_file_info_cache; extern struct kmem_cache *ecryptfs_dentry_info_cache; extern struct kmem_cache *ecryptfs_inode_info_cache; extern struct kmem_cache *ecryptfs_sb_info_cache; -extern struct kmem_cache *ecryptfs_header_cache_0; extern struct kmem_cache *ecryptfs_header_cache_1; extern struct kmem_cache *ecryptfs_header_cache_2; extern struct kmem_cache *ecryptfs_xattr_cache; -extern struct kmem_cache *ecryptfs_lower_page_cache; extern struct kmem_cache *ecryptfs_key_record_cache; extern struct kmem_cache *ecryptfs_key_sig_cache; extern struct kmem_cache *ecryptfs_global_auth_tok_cache; @@ -562,8 +560,8 @@ int ecryptfs_read_and_validate_header_region(char *data, struct inode *ecryptfs_inode); int ecryptfs_read_and_validate_xattr_region(char *page_virt, struct dentry *ecryptfs_dentry); -u16 ecryptfs_code_for_cipher_string(struct ecryptfs_crypt_stat *crypt_stat); -int ecryptfs_cipher_code_to_string(char *str, u16 cipher_code); +u8 ecryptfs_code_for_cipher_string(struct ecryptfs_crypt_stat *crypt_stat); +int ecryptfs_cipher_code_to_string(char *str, u8 cipher_code); void ecryptfs_set_default_sizes(struct ecryptfs_crypt_stat *crypt_stat); int ecryptfs_generate_key_packet_set(char *dest_base, struct ecryptfs_crypt_stat *crypt_stat, @@ -576,8 +574,6 @@ int ecryptfs_truncate(struct dentry *dentry, loff_t new_length); int ecryptfs_inode_test(struct inode *inode, void *candidate_lower_inode); int ecryptfs_inode_set(struct inode *inode, void *lower_inode); void ecryptfs_init_inode(struct inode *inode, struct inode *lower_inode); -ssize_t ecryptfs_getxattr(struct dentry *dentry, const char *name, void *value, - size_t size); ssize_t ecryptfs_getxattr_lower(struct dentry *lower_dentry, const char *name, void *value, size_t size); @@ -623,6 +619,7 @@ ecryptfs_add_new_key_tfm(struct ecryptfs_key_tfm **key_tfm, char *cipher_name, size_t key_size); int ecryptfs_init_crypto(void); int ecryptfs_destroy_crypto(void); +int ecryptfs_tfm_exists(char *cipher_name, struct ecryptfs_key_tfm **key_tfm); int ecryptfs_get_tfm_and_mutex_for_cipher_name(struct crypto_blkcipher **tfm, struct mutex **tfm_mutex, char *cipher_name); @@ -631,8 +628,6 @@ int ecryptfs_keyring_auth_tok_for_sig(struct key **auth_tok_key, char *sig); int ecryptfs_write_zeros(struct file *file, pgoff_t index, int start, int num_zeros); -void ecryptfs_lower_offset_for_extent(loff_t *offset, loff_t extent_num, - struct ecryptfs_crypt_stat *crypt_stat); int ecryptfs_write_lower(struct inode *ecryptfs_inode, char *data, loff_t offset, size_t size); int ecryptfs_write_lower_page_segment(struct inode *ecryptfs_inode, @@ -646,8 +641,6 @@ int ecryptfs_read_lower_page_segment(struct page *page_for_ecryptfs, pgoff_t page_index, size_t offset_in_page, size_t size, struct inode *ecryptfs_inode); -int ecryptfs_read(char *data, loff_t offset, size_t size, - struct file *ecryptfs_file); struct page *ecryptfs_get_locked_page(struct file *file, loff_t index); #endif /* #ifndef ECRYPTFS_KERNEL_H */ diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c index c98c4690a77..2b8f5ed4ade 100644 --- a/fs/ecryptfs/file.c +++ b/fs/ecryptfs/file.c @@ -209,9 +209,10 @@ static int ecryptfs_open(struct inode *inode, struct file *file) if (!(mount_crypt_stat->flags & ECRYPTFS_PLAINTEXT_PASSTHROUGH_ENABLED)) { rc = -EIO; - printk(KERN_WARNING "Attempt to read file that " + printk(KERN_WARNING "Either the lower file " "is not in a valid eCryptfs format, " - "and plaintext passthrough mode is not " + "or the key could not be retrieved. " + "Plaintext passthrough mode is not " "enabled; returning -EIO\n"); mutex_unlock(&crypt_stat->cs_mutex); goto out_free; diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c index 5a719180983..edd1e44e9d4 100644 --- a/fs/ecryptfs/inode.c +++ b/fs/ecryptfs/inode.c @@ -365,8 +365,7 @@ static struct dentry *ecryptfs_lookup(struct inode *dir, struct dentry *dentry, dentry->d_sb)->mount_crypt_stat; if (mount_crypt_stat->flags & ECRYPTFS_ENCRYPTED_VIEW_ENABLED) { if (crypt_stat->flags & ECRYPTFS_METADATA_IN_XATTR) - file_size = ((crypt_stat->extent_size - * crypt_stat->num_header_extents_at_front) + file_size = (crypt_stat->num_header_bytes_at_front + i_size_read(lower_dentry->d_inode)); else file_size = i_size_read(lower_dentry->d_inode); @@ -685,7 +684,7 @@ ecryptfs_put_link(struct dentry *dentry, struct nameidata *nd, void *ptr) * @crypt_stat: Crypt_stat associated with file * @upper_size: Size of the upper file * - * Calculate the requried size of the lower file based on the + * Calculate the required size of the lower file based on the * specified size of the upper file. This calculation is based on the * number of headers in the underlying file and the extent size. * @@ -697,8 +696,7 @@ upper_size_to_lower_size(struct ecryptfs_crypt_stat *crypt_stat, { loff_t lower_size; - lower_size = (crypt_stat->extent_size - * crypt_stat->num_header_extents_at_front); + lower_size = crypt_stat->num_header_bytes_at_front; if (upper_size != 0) { loff_t num_extents; @@ -875,11 +873,11 @@ static int ecryptfs_setattr(struct dentry *dentry, struct iattr *ia) if (!(mount_crypt_stat->flags & ECRYPTFS_PLAINTEXT_PASSTHROUGH_ENABLED)) { rc = -EIO; - printk(KERN_WARNING "Attempt to read file that " + printk(KERN_WARNING "Either the lower file " "is not in a valid eCryptfs format, " - "and plaintext passthrough mode is not " + "or the key could not be retrieved. " + "Plaintext passthrough mode is not " "enabled; returning -EIO\n"); - mutex_unlock(&crypt_stat->cs_mutex); goto out; } @@ -954,7 +952,7 @@ out: return rc; } -ssize_t +static ssize_t ecryptfs_getxattr(struct dentry *dentry, const char *name, void *value, size_t size) { diff --git a/fs/ecryptfs/keystore.c b/fs/ecryptfs/keystore.c index f458c1f3556..682b1b2482c 100644 --- a/fs/ecryptfs/keystore.c +++ b/fs/ecryptfs/keystore.c @@ -189,7 +189,7 @@ out: } static int -parse_tag_65_packet(struct ecryptfs_session_key *session_key, u16 *cipher_code, +parse_tag_65_packet(struct ecryptfs_session_key *session_key, u8 *cipher_code, struct ecryptfs_message *msg) { size_t i = 0; @@ -275,7 +275,7 @@ out: static int -write_tag_66_packet(char *signature, size_t cipher_code, +write_tag_66_packet(char *signature, u8 cipher_code, struct ecryptfs_crypt_stat *crypt_stat, char **packet, size_t *packet_len) { @@ -428,7 +428,7 @@ static int decrypt_pki_encrypted_session_key(struct ecryptfs_auth_tok *auth_tok, struct ecryptfs_crypt_stat *crypt_stat) { - u16 cipher_code = 0; + u8 cipher_code = 0; struct ecryptfs_msg_ctx *msg_ctx; struct ecryptfs_message *msg = NULL; char *auth_tok_sig; @@ -1537,7 +1537,7 @@ write_tag_3_packet(char *dest, size_t *remaining_bytes, struct scatterlist dst_sg; struct scatterlist src_sg; struct mutex *tfm_mutex = NULL; - size_t cipher_code; + u8 cipher_code; size_t packet_size_length; size_t max_packet_size; struct ecryptfs_mount_crypt_stat *mount_crypt_stat = diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c index 0249aa4ae18..778c420e4ca 100644 --- a/fs/ecryptfs/main.c +++ b/fs/ecryptfs/main.c @@ -117,7 +117,7 @@ void __ecryptfs_printk(const char *fmt, ...) * * Returns zero on success; non-zero otherwise */ -int ecryptfs_init_persistent_file(struct dentry *ecryptfs_dentry) +static int ecryptfs_init_persistent_file(struct dentry *ecryptfs_dentry) { struct ecryptfs_inode_info *inode_info = ecryptfs_inode_to_private(ecryptfs_dentry->d_inode); @@ -226,17 +226,15 @@ out: return rc; } -enum { ecryptfs_opt_sig, ecryptfs_opt_ecryptfs_sig, ecryptfs_opt_debug, - ecryptfs_opt_ecryptfs_debug, ecryptfs_opt_cipher, - ecryptfs_opt_ecryptfs_cipher, ecryptfs_opt_ecryptfs_key_bytes, +enum { ecryptfs_opt_sig, ecryptfs_opt_ecryptfs_sig, + ecryptfs_opt_cipher, ecryptfs_opt_ecryptfs_cipher, + ecryptfs_opt_ecryptfs_key_bytes, ecryptfs_opt_passthrough, ecryptfs_opt_xattr_metadata, ecryptfs_opt_encrypted_view, ecryptfs_opt_err }; static match_table_t tokens = { {ecryptfs_opt_sig, "sig=%s"}, {ecryptfs_opt_ecryptfs_sig, "ecryptfs_sig=%s"}, - {ecryptfs_opt_debug, "debug=%u"}, - {ecryptfs_opt_ecryptfs_debug, "ecryptfs_debug=%u"}, {ecryptfs_opt_cipher, "cipher=%s"}, {ecryptfs_opt_ecryptfs_cipher, "ecryptfs_cipher=%s"}, {ecryptfs_opt_ecryptfs_key_bytes, "ecryptfs_key_bytes=%u"}, @@ -313,7 +311,6 @@ static int ecryptfs_parse_options(struct super_block *sb, char *options) substring_t args[MAX_OPT_ARGS]; int token; char *sig_src; - char *debug_src; char *cipher_name_dst; char *cipher_name_src; char *cipher_key_bytes_src; @@ -341,16 +338,6 @@ static int ecryptfs_parse_options(struct super_block *sb, char *options) } sig_set = 1; break; - case ecryptfs_opt_debug: - case ecryptfs_opt_ecryptfs_debug: - debug_src = args[0].from; - ecryptfs_verbosity = - (int)simple_strtol(debug_src, &debug_src, - 0); - ecryptfs_printk(KERN_DEBUG, - "Verbosity set to [%d]" "\n", - ecryptfs_verbosity); - break; case ecryptfs_opt_cipher: case ecryptfs_opt_ecryptfs_cipher: cipher_name_src = args[0].from; @@ -423,9 +410,13 @@ static int ecryptfs_parse_options(struct super_block *sb, char *options) if (!cipher_key_bytes_set) { mount_crypt_stat->global_default_cipher_key_size = 0; } - rc = ecryptfs_add_new_key_tfm( - NULL, mount_crypt_stat->global_default_cipher_name, - mount_crypt_stat->global_default_cipher_key_size); + mutex_lock(&key_tfm_list_mutex); + if (!ecryptfs_tfm_exists(mount_crypt_stat->global_default_cipher_name, + NULL)) + rc = ecryptfs_add_new_key_tfm( + NULL, mount_crypt_stat->global_default_cipher_name, + mount_crypt_stat->global_default_cipher_key_size); + mutex_unlock(&key_tfm_list_mutex); if (rc) { printk(KERN_ERR "Error attempting to initialize cipher with " "name = [%s] and key size = [%td]; rc = [%d]\n", @@ -654,11 +645,6 @@ static struct ecryptfs_cache_info { .size = sizeof(struct ecryptfs_sb_info), }, { - .cache = &ecryptfs_header_cache_0, - .name = "ecryptfs_headers_0", - .size = PAGE_CACHE_SIZE, - }, - { .cache = &ecryptfs_header_cache_1, .name = "ecryptfs_headers_1", .size = PAGE_CACHE_SIZE, @@ -821,6 +807,10 @@ static int __init ecryptfs_init(void) "rc = [%d]\n", rc); goto out_release_messaging; } + if (ecryptfs_verbosity > 0) + printk(KERN_CRIT "eCryptfs verbosity set to %d. Secret values " + "will be written to the syslog!\n", ecryptfs_verbosity); + goto out; out_release_messaging: ecryptfs_release_messaging(ecryptfs_transport); diff --git a/fs/ecryptfs/mmap.c b/fs/ecryptfs/mmap.c index 0535412d8c6..dc74b186145 100644 --- a/fs/ecryptfs/mmap.c +++ b/fs/ecryptfs/mmap.c @@ -34,8 +34,6 @@ #include <linux/scatterlist.h> #include "ecryptfs_kernel.h" -struct kmem_cache *ecryptfs_lower_page_cache; - /** * ecryptfs_get_locked_page * @@ -102,13 +100,14 @@ static void set_header_info(char *page_virt, struct ecryptfs_crypt_stat *crypt_stat) { size_t written; - int save_num_header_extents_at_front = - crypt_stat->num_header_extents_at_front; + size_t save_num_header_bytes_at_front = + crypt_stat->num_header_bytes_at_front; - crypt_stat->num_header_extents_at_front = 1; + crypt_stat->num_header_bytes_at_front = + ECRYPTFS_MINIMUM_HEADER_EXTENT_SIZE; ecryptfs_write_header_metadata(page_virt + 20, crypt_stat, &written); - crypt_stat->num_header_extents_at_front = - save_num_header_extents_at_front; + crypt_stat->num_header_bytes_at_front = + save_num_header_bytes_at_front; } /** @@ -134,8 +133,11 @@ ecryptfs_copy_up_encrypted_with_header(struct page *page, loff_t view_extent_num = ((((loff_t)page->index) * num_extents_per_page) + extent_num_in_page); + size_t num_header_extents_at_front = + (crypt_stat->num_header_bytes_at_front + / crypt_stat->extent_size); - if (view_extent_num < crypt_stat->num_header_extents_at_front) { + if (view_extent_num < num_header_extents_at_front) { /* This is a header extent */ char *page_virt; @@ -157,9 +159,8 @@ ecryptfs_copy_up_encrypted_with_header(struct page *page, } else { /* This is an encrypted data extent */ loff_t lower_offset = - ((view_extent_num - - crypt_stat->num_header_extents_at_front) - * crypt_stat->extent_size); + ((view_extent_num * crypt_stat->extent_size) + - crypt_stat->num_header_bytes_at_front); rc = ecryptfs_read_lower_page_segment( page, (lower_offset >> PAGE_CACHE_SHIFT), diff --git a/fs/ecryptfs/read_write.c b/fs/ecryptfs/read_write.c index 948f57624c0..0c4928623bb 100644 --- a/fs/ecryptfs/read_write.c +++ b/fs/ecryptfs/read_write.c @@ -293,6 +293,7 @@ int ecryptfs_read_lower_page_segment(struct page *page_for_ecryptfs, return rc; } +#if 0 /** * ecryptfs_read * @data: The virtual address into which to write the data read (and @@ -371,3 +372,4 @@ int ecryptfs_read(char *data, loff_t offset, size_t size, out: return rc; } +#endif /* 0 */ diff --git a/fs/ecryptfs/super.c b/fs/ecryptfs/super.c index 4859c4eecd6..c27ac2b358a 100644 --- a/fs/ecryptfs/super.c +++ b/fs/ecryptfs/super.c @@ -156,32 +156,38 @@ static void ecryptfs_clear_inode(struct inode *inode) /** * ecryptfs_show_options * - * Prints the directory we are currently mounted over. - * Returns zero on success; non-zero otherwise + * Prints the mount options for a given superblock. + * Returns zero; does not fail. */ static int ecryptfs_show_options(struct seq_file *m, struct vfsmount *mnt) { struct super_block *sb = mnt->mnt_sb; - struct dentry *lower_root_dentry = ecryptfs_dentry_to_lower(sb->s_root); - struct vfsmount *lower_mnt = ecryptfs_dentry_to_lower_mnt(sb->s_root); - char *tmp_page; - char *path; - int rc = 0; - - tmp_page = (char *)__get_free_page(GFP_KERNEL); - if (!tmp_page) { - rc = -ENOMEM; - goto out; - } - path = d_path(lower_root_dentry, lower_mnt, tmp_page, PAGE_SIZE); - if (IS_ERR(path)) { - rc = PTR_ERR(path); - goto out; + struct ecryptfs_mount_crypt_stat *mount_crypt_stat = + &ecryptfs_superblock_to_private(sb)->mount_crypt_stat; + struct ecryptfs_global_auth_tok *walker; + + mutex_lock(&mount_crypt_stat->global_auth_tok_list_mutex); + list_for_each_entry(walker, + &mount_crypt_stat->global_auth_tok_list, + mount_crypt_stat_list) { + seq_printf(m, ",ecryptfs_sig=%s", walker->sig); } - seq_printf(m, ",dir=%s", path); - free_page((unsigned long)tmp_page); -out: - return rc; + mutex_unlock(&mount_crypt_stat->global_auth_tok_list_mutex); + + seq_printf(m, ",ecryptfs_cipher=%s", + mount_crypt_stat->global_default_cipher_name); + + if (mount_crypt_stat->global_default_cipher_key_size) + seq_printf(m, ",ecryptfs_key_bytes=%zd", + mount_crypt_stat->global_default_cipher_key_size); + if (mount_crypt_stat->flags & ECRYPTFS_PLAINTEXT_PASSTHROUGH_ENABLED) + seq_printf(m, ",ecryptfs_passthrough"); + if (mount_crypt_stat->flags & ECRYPTFS_XATTR_METADATA_ENABLED) + seq_printf(m, ",ecryptfs_xattr_metadata"); + if (mount_crypt_stat->flags & ECRYPTFS_ENCRYPTED_VIEW_ENABLED) + seq_printf(m, ",ecryptfs_encrypted_view"); + + return 0; } const struct super_operations ecryptfs_sops = { diff --git a/fs/eventfd.c b/fs/eventfd.c index 2ce19c000d2..a9f130cd50a 100644 --- a/fs/eventfd.c +++ b/fs/eventfd.c @@ -15,6 +15,7 @@ #include <linux/spinlock.h> #include <linux/anon_inodes.h> #include <linux/eventfd.h> +#include <linux/syscalls.h> struct eventfd_ctx { wait_queue_head_t wqh; diff --git a/fs/ext2/balloc.c b/fs/ext2/balloc.c index 377ad172d74..e7b2bafa1dd 100644 --- a/fs/ext2/balloc.c +++ b/fs/ext2/balloc.c @@ -69,9 +69,53 @@ struct ext2_group_desc * ext2_get_group_desc(struct super_block * sb, return desc + offset; } +static int ext2_valid_block_bitmap(struct super_block *sb, + struct ext2_group_desc *desc, + unsigned int block_group, + struct buffer_head *bh) +{ + ext2_grpblk_t offset; + ext2_grpblk_t next_zero_bit; + ext2_fsblk_t bitmap_blk; + ext2_fsblk_t group_first_block; + + group_first_block = ext2_group_first_block_no(sb, block_group); + + /* check whether block bitmap block number is set */ + bitmap_blk = le32_to_cpu(desc->bg_block_bitmap); + offset = bitmap_blk - group_first_block; + if (!ext2_test_bit(offset, bh->b_data)) + /* bad block bitmap */ + goto err_out; + + /* check whether the inode bitmap block number is set */ + bitmap_blk = le32_to_cpu(desc->bg_inode_bitmap); + offset = bitmap_blk - group_first_block; + if (!ext2_test_bit(offset, bh->b_data)) + /* bad block bitmap */ + goto err_out; + + /* check whether the inode table block number is set */ + bitmap_blk = le32_to_cpu(desc->bg_inode_table); + offset = bitmap_blk - group_first_block; + next_zero_bit = ext2_find_next_zero_bit(bh->b_data, + offset + EXT2_SB(sb)->s_itb_per_group, + offset); + if (next_zero_bit >= offset + EXT2_SB(sb)->s_itb_per_group) + /* good bitmap for inode tables */ + return 1; + +err_out: + ext2_error(sb, __FUNCTION__, + "Invalid block bitmap - " + "block_group = %d, block = %lu", + block_group, bitmap_blk); + return 0; +} + /* - * Read the bitmap for a given block_group, reading into the specified - * slot in the superblock's bitmap cache. + * Read the bitmap for a given block_group,and validate the + * bits for block/inode/inode tables are set in the bitmaps * * Return buffer_head on success or NULL in case of failure. */ @@ -80,17 +124,36 @@ read_block_bitmap(struct super_block *sb, unsigned int block_group) { struct ext2_group_desc * desc; struct buffer_head * bh = NULL; - - desc = ext2_get_group_desc (sb, block_group, NULL); + ext2_fsblk_t bitmap_blk; + + desc = ext2_get_group_desc(sb, block_group, NULL); if (!desc) - goto error_out; - bh = sb_bread(sb, le32_to_cpu(desc->bg_block_bitmap)); - if (!bh) - ext2_error (sb, "read_block_bitmap", + return NULL; + bitmap_blk = le32_to_cpu(desc->bg_block_bitmap); + bh = sb_getblk(sb, bitmap_blk); + if (unlikely(!bh)) { + ext2_error(sb, __FUNCTION__, + "Cannot read block bitmap - " + "block_group = %d, block_bitmap = %u", + block_group, le32_to_cpu(desc->bg_block_bitmap)); + return NULL; + } + if (likely(bh_uptodate_or_lock(bh))) + return bh; + + if (bh_submit_read(bh) < 0) { + brelse(bh); + ext2_error(sb, __FUNCTION__, "Cannot read block bitmap - " "block_group = %d, block_bitmap = %u", block_group, le32_to_cpu(desc->bg_block_bitmap)); -error_out: + return NULL; + } + if (!ext2_valid_block_bitmap(sb, desc, block_group, bh)) { + brelse(bh); + return NULL; + } + return bh; } @@ -474,11 +537,13 @@ do_more: in_range (block, le32_to_cpu(desc->bg_inode_table), sbi->s_itb_per_group) || in_range (block + count - 1, le32_to_cpu(desc->bg_inode_table), - sbi->s_itb_per_group)) + sbi->s_itb_per_group)) { ext2_error (sb, "ext2_free_blocks", "Freeing blocks in system zones - " "Block = %lu, count = %lu", block, count); + goto error_return; + } for (i = 0, group_freed = 0; i < count; i++) { if (!ext2_clear_bit_atomic(sb_bgl_lock(sbi, block_group), @@ -1250,8 +1315,8 @@ retry_alloc: smp_rmb(); /* - * Now search the rest of the groups. We assume that - * i and gdp correctly point to the last group visited. + * Now search the rest of the groups. We assume that + * group_no and gdp correctly point to the last group visited. */ for (bgi = 0; bgi < ngroups; bgi++) { group_no++; @@ -1311,11 +1376,13 @@ allocated: in_range(ret_block, le32_to_cpu(gdp->bg_inode_table), EXT2_SB(sb)->s_itb_per_group) || in_range(ret_block + num - 1, le32_to_cpu(gdp->bg_inode_table), - EXT2_SB(sb)->s_itb_per_group)) + EXT2_SB(sb)->s_itb_per_group)) { ext2_error(sb, "ext2_new_blocks", "Allocating block in system zone - " "blocks from "E2FSBLK", length %lu", ret_block, num); + goto out; + } performed_allocation = 1; @@ -1466,9 +1533,6 @@ int ext2_bg_has_super(struct super_block *sb, int group) */ unsigned long ext2_bg_num_gdb(struct super_block *sb, int group) { - if (EXT2_HAS_RO_COMPAT_FEATURE(sb,EXT2_FEATURE_RO_COMPAT_SPARSE_SUPER)&& - !ext2_group_sparse(group)) - return 0; - return EXT2_SB(sb)->s_gdb_count; + return ext2_bg_has_super(sb, group) ? EXT2_SB(sb)->s_gdb_count : 0; } diff --git a/fs/ext2/dir.c b/fs/ext2/dir.c index d868e26c15e..8dededd80fe 100644 --- a/fs/ext2/dir.c +++ b/fs/ext2/dir.c @@ -703,7 +703,7 @@ const struct file_operations ext2_dir_operations = { .llseek = generic_file_llseek, .read = generic_read_dir, .readdir = ext2_readdir, - .ioctl = ext2_ioctl, + .unlocked_ioctl = ext2_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = ext2_compat_ioctl, #endif diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h index c87ae29c19c..bb9948cdd50 100644 --- a/fs/ext2/ext2.h +++ b/fs/ext2/ext2.h @@ -139,8 +139,7 @@ int __ext2_write_begin(struct file *file, struct address_space *mapping, struct page **pagep, void **fsdata); /* ioctl.c */ -extern int ext2_ioctl (struct inode *, struct file *, unsigned int, - unsigned long); +extern long ext2_ioctl(struct file *, unsigned int, unsigned long); extern long ext2_compat_ioctl(struct file *, unsigned int, unsigned long); /* namei.c */ diff --git a/fs/ext2/file.c b/fs/ext2/file.c index c051798459a..5f2fa9c3629 100644 --- a/fs/ext2/file.c +++ b/fs/ext2/file.c @@ -48,7 +48,7 @@ const struct file_operations ext2_file_operations = { .write = do_sync_write, .aio_read = generic_file_aio_read, .aio_write = generic_file_aio_write, - .ioctl = ext2_ioctl, + .unlocked_ioctl = ext2_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = ext2_compat_ioctl, #endif @@ -65,7 +65,7 @@ const struct file_operations ext2_xip_file_operations = { .llseek = generic_file_llseek, .read = xip_file_read, .write = xip_file_write, - .ioctl = ext2_ioctl, + .unlocked_ioctl = ext2_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = ext2_compat_ioctl, #endif diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index b1ab32ab5a7..03978ec2a91 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -286,15 +286,12 @@ static unsigned long ext2_find_near(struct inode *inode, Indirect *ind) * ext2_find_goal - find a prefered place for allocation. * @inode: owner * @block: block we want - * @chain: chain of indirect blocks * @partial: pointer to the last triple within a chain * * Returns preferred place for a block (the goal). */ -static inline int ext2_find_goal(struct inode *inode, - long block, - Indirect chain[4], +static inline int ext2_find_goal(struct inode *inode, long block, Indirect *partial) { struct ext2_block_alloc_info *block_i; @@ -569,7 +566,6 @@ static void ext2_splice_branch(struct inode *inode, * * `handle' can be NULL if create == 0. * - * The BKL may not be held on entry here. Be sure to take it early. * return > 0, # of blocks mapped or allocated. * return = 0, if plain lookup failed. * return < 0, error case. @@ -639,7 +635,7 @@ reread: if (S_ISREG(inode->i_mode) && (!ei->i_block_alloc_info)) ext2_init_block_alloc_info(inode); - goal = ext2_find_goal(inode, iblock, chain, partial); + goal = ext2_find_goal(inode, iblock, partial); /* the number of blocks need to allocate for [d,t]indirect blocks */ indirect_blks = (chain + depth) - partial - 1; diff --git a/fs/ext2/ioctl.c b/fs/ext2/ioctl.c index 320b2cb3d4d..b8ea11fee5c 100644 --- a/fs/ext2/ioctl.c +++ b/fs/ext2/ioctl.c @@ -17,9 +17,9 @@ #include <asm/uaccess.h> -int ext2_ioctl (struct inode * inode, struct file * filp, unsigned int cmd, - unsigned long arg) +long ext2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { + struct inode *inode = filp->f_dentry->d_inode; struct ext2_inode_info *ei = EXT2_I(inode); unsigned int flags; unsigned short rsv_window_size; @@ -141,9 +141,6 @@ int ext2_ioctl (struct inode * inode, struct file * filp, unsigned int cmd, #ifdef CONFIG_COMPAT long ext2_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { - struct inode *inode = file->f_path.dentry->d_inode; - int ret; - /* These are just misnamed, they actually get/put from/to user an int */ switch (cmd) { case EXT2_IOC32_GETFLAGS: @@ -161,9 +158,6 @@ long ext2_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) default: return -ENOIOCTLCMD; } - lock_kernel(); - ret = ext2_ioctl(inode, file, cmd, (unsigned long) compat_ptr(arg)); - unlock_kernel(); - return ret; + return ext2_ioctl(file, cmd, (unsigned long) compat_ptr(arg)); } #endif diff --git a/fs/ext2/super.c b/fs/ext2/super.c index 6abaf75163f..1ba18b72d43 100644 --- a/fs/ext2/super.c +++ b/fs/ext2/super.c @@ -234,16 +234,16 @@ static int ext2_show_options(struct seq_file *seq, struct vfsmount *vfs) le16_to_cpu(es->s_def_resgid) != EXT2_DEF_RESGID) { seq_printf(seq, ",resgid=%u", sbi->s_resgid); } - if (test_opt(sb, ERRORS_CONT)) { + if (test_opt(sb, ERRORS_RO)) { int def_errors = le16_to_cpu(es->s_errors); if (def_errors == EXT2_ERRORS_PANIC || - def_errors == EXT2_ERRORS_RO) { - seq_puts(seq, ",errors=continue"); + def_errors == EXT2_ERRORS_CONTINUE) { + seq_puts(seq, ",errors=remount-ro"); } } - if (test_opt(sb, ERRORS_RO)) - seq_puts(seq, ",errors=remount-ro"); + if (test_opt(sb, ERRORS_CONT)) + seq_puts(seq, ",errors=continue"); if (test_opt(sb, ERRORS_PANIC)) seq_puts(seq, ",errors=panic"); if (test_opt(sb, NO_UID32)) @@ -617,27 +617,24 @@ static int ext2_setup_super (struct super_block * sb, return res; } -static int ext2_check_descriptors (struct super_block * sb) +static int ext2_check_descriptors(struct super_block *sb) { int i; - int desc_block = 0; struct ext2_sb_info *sbi = EXT2_SB(sb); unsigned long first_block = le32_to_cpu(sbi->s_es->s_first_data_block); unsigned long last_block; - struct ext2_group_desc * gdp = NULL; ext2_debug ("Checking group descriptors"); - for (i = 0; i < sbi->s_groups_count; i++) - { + for (i = 0; i < sbi->s_groups_count; i++) { + struct ext2_group_desc *gdp = ext2_get_group_desc(sb, i, NULL); + if (i == sbi->s_groups_count - 1) last_block = le32_to_cpu(sbi->s_es->s_blocks_count) - 1; else last_block = first_block + (EXT2_BLOCKS_PER_GROUP(sb) - 1); - if ((i % EXT2_DESC_PER_BLOCK(sb)) == 0) - gdp = (struct ext2_group_desc *) sbi->s_group_desc[desc_block++]->b_data; if (le32_to_cpu(gdp->bg_block_bitmap) < first_block || le32_to_cpu(gdp->bg_block_bitmap) > last_block) { @@ -667,7 +664,6 @@ static int ext2_check_descriptors (struct super_block * sb) return 0; } first_block += EXT2_BLOCKS_PER_GROUP(sb); - gdp++; } return 1; } @@ -820,10 +816,10 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent) if (le16_to_cpu(sbi->s_es->s_errors) == EXT2_ERRORS_PANIC) set_opt(sbi->s_mount_opt, ERRORS_PANIC); - else if (le16_to_cpu(sbi->s_es->s_errors) == EXT2_ERRORS_RO) - set_opt(sbi->s_mount_opt, ERRORS_RO); - else + else if (le16_to_cpu(sbi->s_es->s_errors) == EXT2_ERRORS_CONTINUE) set_opt(sbi->s_mount_opt, ERRORS_CONT); + else + set_opt(sbi->s_mount_opt, ERRORS_RO); sbi->s_resuid = le16_to_cpu(es->s_def_resuid); sbi->s_resgid = le16_to_cpu(es->s_def_resgid); @@ -868,8 +864,7 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent) blocksize = BLOCK_SIZE << le32_to_cpu(sbi->s_es->s_log_block_size); - if ((ext2_use_xip(sb)) && ((blocksize != PAGE_SIZE) || - (sb->s_blocksize != blocksize))) { + if (ext2_use_xip(sb) && blocksize != PAGE_SIZE) { if (!silent) printk("XIP: Unsupported blocksize\n"); goto failed_mount; diff --git a/fs/ext3/balloc.c b/fs/ext3/balloc.c index a8ba7e83127..a7571303110 100644 --- a/fs/ext3/balloc.c +++ b/fs/ext3/balloc.c @@ -80,13 +80,57 @@ struct ext3_group_desc * ext3_get_group_desc(struct super_block * sb, return desc + offset; } +static int ext3_valid_block_bitmap(struct super_block *sb, + struct ext3_group_desc *desc, + unsigned int block_group, + struct buffer_head *bh) +{ + ext3_grpblk_t offset; + ext3_grpblk_t next_zero_bit; + ext3_fsblk_t bitmap_blk; + ext3_fsblk_t group_first_block; + + group_first_block = ext3_group_first_block_no(sb, block_group); + + /* check whether block bitmap block number is set */ + bitmap_blk = le32_to_cpu(desc->bg_block_bitmap); + offset = bitmap_blk - group_first_block; + if (!ext3_test_bit(offset, bh->b_data)) + /* bad block bitmap */ + goto err_out; + + /* check whether the inode bitmap block number is set */ + bitmap_blk = le32_to_cpu(desc->bg_inode_bitmap); + offset = bitmap_blk - group_first_block; + if (!ext3_test_bit(offset, bh->b_data)) + /* bad block bitmap */ + goto err_out; + + /* check whether the inode table block number is set */ + bitmap_blk = le32_to_cpu(desc->bg_inode_table); + offset = bitmap_blk - group_first_block; + next_zero_bit = ext3_find_next_zero_bit(bh->b_data, + offset + EXT3_SB(sb)->s_itb_per_group, + offset); + if (next_zero_bit >= offset + EXT3_SB(sb)->s_itb_per_group) + /* good bitmap for inode tables */ + return 1; + +err_out: + ext3_error(sb, __FUNCTION__, + "Invalid block bitmap - " + "block_group = %d, block = %lu", + block_group, bitmap_blk); + return 0; +} + /** * read_block_bitmap() * @sb: super block * @block_group: given block group * - * Read the bitmap for a given block_group, reading into the specified - * slot in the superblock's bitmap cache. + * Read the bitmap for a given block_group,and validate the + * bits for block/inode/inode tables are set in the bitmaps * * Return buffer_head on success or NULL in case of failure. */ @@ -95,17 +139,35 @@ read_block_bitmap(struct super_block *sb, unsigned int block_group) { struct ext3_group_desc * desc; struct buffer_head * bh = NULL; + ext3_fsblk_t bitmap_blk; - desc = ext3_get_group_desc (sb, block_group, NULL); + desc = ext3_get_group_desc(sb, block_group, NULL); if (!desc) - goto error_out; - bh = sb_bread(sb, le32_to_cpu(desc->bg_block_bitmap)); - if (!bh) - ext3_error (sb, "read_block_bitmap", + return NULL; + bitmap_blk = le32_to_cpu(desc->bg_block_bitmap); + bh = sb_getblk(sb, bitmap_blk); + if (unlikely(!bh)) { + ext3_error(sb, __FUNCTION__, "Cannot read block bitmap - " "block_group = %d, block_bitmap = %u", block_group, le32_to_cpu(desc->bg_block_bitmap)); -error_out: + return NULL; + } + if (likely(bh_uptodate_or_lock(bh))) + return bh; + + if (bh_submit_read(bh) < 0) { + brelse(bh); + ext3_error(sb, __FUNCTION__, + "Cannot read block bitmap - " + "block_group = %d, block_bitmap = %u", + block_group, le32_to_cpu(desc->bg_block_bitmap)); + return NULL; + } + if (!ext3_valid_block_bitmap(sb, desc, block_group, bh)) { + brelse(bh); + return NULL; + } return bh; } /* @@ -468,11 +530,13 @@ do_more: in_range (block, le32_to_cpu(desc->bg_inode_table), sbi->s_itb_per_group) || in_range (block + count - 1, le32_to_cpu(desc->bg_inode_table), - sbi->s_itb_per_group)) + sbi->s_itb_per_group)) { ext3_error (sb, "ext3_free_blocks", "Freeing blocks in system zones - " "Block = "E3FSBLK", count = %lu", block, count); + goto error_return; + } /* * We are about to start releasing blocks in the bitmap, @@ -1508,7 +1572,7 @@ retry_alloc: /* * Now search the rest of the groups. We assume that - * i and gdp correctly point to the last group visited. + * group_no and gdp correctly point to the last group visited. */ for (bgi = 0; bgi < ngroups; bgi++) { group_no++; @@ -1575,11 +1639,13 @@ allocated: in_range(ret_block, le32_to_cpu(gdp->bg_inode_table), EXT3_SB(sb)->s_itb_per_group) || in_range(ret_block + num - 1, le32_to_cpu(gdp->bg_inode_table), - EXT3_SB(sb)->s_itb_per_group)) + EXT3_SB(sb)->s_itb_per_group)) { ext3_error(sb, "ext3_new_block", "Allocating block in system zone - " "blocks from "E3FSBLK", length %lu", ret_block, num); + goto out; + } performed_allocation = 1; @@ -1782,11 +1848,7 @@ static unsigned long ext3_bg_num_gdb_meta(struct super_block *sb, int group) static unsigned long ext3_bg_num_gdb_nometa(struct super_block *sb, int group) { - if (EXT3_HAS_RO_COMPAT_FEATURE(sb, - EXT3_FEATURE_RO_COMPAT_SPARSE_SUPER) && - !ext3_group_sparse(group)) - return 0; - return EXT3_SB(sb)->s_gdb_count; + return ext3_bg_has_super(sb, group) ? EXT3_SB(sb)->s_gdb_count : 0; } /** diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c index 07753543928..8a9ce2d09bd 100644 --- a/fs/ext3/inode.c +++ b/fs/ext3/inode.c @@ -439,16 +439,14 @@ static ext3_fsblk_t ext3_find_near(struct inode *inode, Indirect *ind) * ext3_find_goal - find a prefered place for allocation. * @inode: owner * @block: block we want - * @chain: chain of indirect blocks * @partial: pointer to the last triple within a chain - * @goal: place to store the result. * * Normally this function find the prefered place for block allocation, - * stores it in *@goal and returns zero. + * returns it. */ static ext3_fsblk_t ext3_find_goal(struct inode *inode, long block, - Indirect chain[4], Indirect *partial) + Indirect *partial) { struct ext3_block_alloc_info *block_i; @@ -884,7 +882,7 @@ int ext3_get_blocks_handle(handle_t *handle, struct inode *inode, if (S_ISREG(inode->i_mode) && (!ei->i_block_alloc_info)) ext3_init_block_alloc_info(inode); - goal = ext3_find_goal(inode, iblock, chain, partial); + goal = ext3_find_goal(inode, iblock, partial); /* the number of blocks need to allocate for [d,t]indirect blocks */ indirect_blks = (chain + depth) - partial - 1; @@ -941,55 +939,45 @@ out: return err; } -#define DIO_CREDITS (EXT3_RESERVE_TRANS_BLOCKS + 32) +/* Maximum number of blocks we map for direct IO at once. */ +#define DIO_MAX_BLOCKS 4096 +/* + * Number of credits we need for writing DIO_MAX_BLOCKS: + * We need sb + group descriptor + bitmap + inode -> 4 + * For B blocks with A block pointers per block we need: + * 1 (triple ind.) + (B/A/A + 2) (doubly ind.) + (B/A + 2) (indirect). + * If we plug in 4096 for B and 256 for A (for 1KB block size), we get 25. + */ +#define DIO_CREDITS 25 static int ext3_get_block(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create) { handle_t *handle = ext3_journal_current_handle(); - int ret = 0; + int ret = 0, started = 0; unsigned max_blocks = bh_result->b_size >> inode->i_blkbits; - if (!create) - goto get_block; /* A read */ - - if (max_blocks == 1) - goto get_block; /* A single block get */ - - if (handle->h_transaction->t_state == T_LOCKED) { - /* - * Huge direct-io writes can hold off commits for long - * periods of time. Let this commit run. - */ - ext3_journal_stop(handle); - handle = ext3_journal_start(inode, DIO_CREDITS); - if (IS_ERR(handle)) + if (create && !handle) { /* Direct IO write... */ + if (max_blocks > DIO_MAX_BLOCKS) + max_blocks = DIO_MAX_BLOCKS; + handle = ext3_journal_start(inode, DIO_CREDITS + + 2 * EXT3_QUOTA_TRANS_BLOCKS(inode->i_sb)); + if (IS_ERR(handle)) { ret = PTR_ERR(handle); - goto get_block; - } - - if (handle->h_buffer_credits <= EXT3_RESERVE_TRANS_BLOCKS) { - /* - * Getting low on buffer credits... - */ - ret = ext3_journal_extend(handle, DIO_CREDITS); - if (ret > 0) { - /* - * Couldn't extend the transaction. Start a new one. - */ - ret = ext3_journal_restart(handle, DIO_CREDITS); + goto out; } + started = 1; } -get_block: - if (ret == 0) { - ret = ext3_get_blocks_handle(handle, inode, iblock, + ret = ext3_get_blocks_handle(handle, inode, iblock, max_blocks, bh_result, create, 0); - if (ret > 0) { - bh_result->b_size = (ret << inode->i_blkbits); - ret = 0; - } + if (ret > 0) { + bh_result->b_size = (ret << inode->i_blkbits); + ret = 0; } + if (started) + ext3_journal_stop(handle); +out: return ret; } @@ -1680,7 +1668,8 @@ static int ext3_releasepage(struct page *page, gfp_t wait) * if the machine crashes during the write. * * If the O_DIRECT write is intantiating holes inside i_size and the machine - * crashes then stale disk data _may_ be exposed inside the file. + * crashes then stale disk data _may_ be exposed inside the file. But current + * VFS code falls back into buffered path in that case so we are safe. */ static ssize_t ext3_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, loff_t offset, @@ -1689,7 +1678,7 @@ static ssize_t ext3_direct_IO(int rw, struct kiocb *iocb, struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; struct ext3_inode_info *ei = EXT3_I(inode); - handle_t *handle = NULL; + handle_t *handle; ssize_t ret; int orphan = 0; size_t count = iov_length(iov, nr_segs); @@ -1697,17 +1686,21 @@ static ssize_t ext3_direct_IO(int rw, struct kiocb *iocb, if (rw == WRITE) { loff_t final_size = offset + count; - handle = ext3_journal_start(inode, DIO_CREDITS); - if (IS_ERR(handle)) { - ret = PTR_ERR(handle); - goto out; - } if (final_size > inode->i_size) { + /* Credits for sb + inode write */ + handle = ext3_journal_start(inode, 2); + if (IS_ERR(handle)) { + ret = PTR_ERR(handle); + goto out; + } ret = ext3_orphan_add(handle, inode); - if (ret) - goto out_stop; + if (ret) { + ext3_journal_stop(handle); + goto out; + } orphan = 1; ei->i_disksize = inode->i_size; + ext3_journal_stop(handle); } } @@ -1715,18 +1708,21 @@ static ssize_t ext3_direct_IO(int rw, struct kiocb *iocb, offset, nr_segs, ext3_get_block, NULL); - /* - * Reacquire the handle: ext3_get_block() can restart the transaction - */ - handle = ext3_journal_current_handle(); - -out_stop: - if (handle) { + if (orphan) { int err; - if (orphan && inode->i_nlink) + /* Credits for sb + inode write */ + handle = ext3_journal_start(inode, 2); + if (IS_ERR(handle)) { + /* This is really bad luck. We've written the data + * but cannot extend i_size. Bail out and pretend + * the write failed... */ + ret = PTR_ERR(handle); + goto out; + } + if (inode->i_nlink) ext3_orphan_del(handle, inode); - if (orphan && ret > 0) { + if (ret > 0) { loff_t end = offset + ret; if (end > inode->i_size) { ei->i_disksize = end; diff --git a/fs/ext3/namei.c b/fs/ext3/namei.c index 4ab6f76e63d..92b83b004dd 100644 --- a/fs/ext3/namei.c +++ b/fs/ext3/namei.c @@ -860,14 +860,10 @@ static struct buffer_head * ext3_find_entry (struct dentry *dentry, int nblocks, i, err; struct inode *dir = dentry->d_parent->d_inode; int namelen; - const u8 *name; - unsigned blocksize; *res_dir = NULL; sb = dir->i_sb; - blocksize = sb->s_blocksize; namelen = dentry->d_name.len; - name = dentry->d_name.name; if (namelen > EXT3_NAME_LEN) return NULL; if (is_dx(dir)) { diff --git a/fs/ext3/super.c b/fs/ext3/super.c index f3675cc630e..343677e8c35 100644 --- a/fs/ext3/super.c +++ b/fs/ext3/super.c @@ -575,16 +575,16 @@ static int ext3_show_options(struct seq_file *seq, struct vfsmount *vfs) le16_to_cpu(es->s_def_resgid) != EXT3_DEF_RESGID) { seq_printf(seq, ",resgid=%u", sbi->s_resgid); } - if (test_opt(sb, ERRORS_CONT)) { + if (test_opt(sb, ERRORS_RO)) { int def_errors = le16_to_cpu(es->s_errors); if (def_errors == EXT3_ERRORS_PANIC || - def_errors == EXT3_ERRORS_RO) { - seq_puts(seq, ",errors=continue"); + def_errors == EXT3_ERRORS_CONTINUE) { + seq_puts(seq, ",errors=remount-ro"); } } - if (test_opt(sb, ERRORS_RO)) - seq_puts(seq, ",errors=remount-ro"); + if (test_opt(sb, ERRORS_CONT)) + seq_puts(seq, ",errors=continue"); if (test_opt(sb, ERRORS_PANIC)) seq_puts(seq, ",errors=panic"); if (test_opt(sb, NO_UID32)) @@ -1252,28 +1252,24 @@ static int ext3_setup_super(struct super_block *sb, struct ext3_super_block *es, } /* Called at mount-time, super-block is locked */ -static int ext3_check_descriptors (struct super_block * sb) +static int ext3_check_descriptors(struct super_block *sb) { struct ext3_sb_info *sbi = EXT3_SB(sb); ext3_fsblk_t first_block = le32_to_cpu(sbi->s_es->s_first_data_block); ext3_fsblk_t last_block; - struct ext3_group_desc * gdp = NULL; - int desc_block = 0; int i; ext3_debug ("Checking group descriptors"); - for (i = 0; i < sbi->s_groups_count; i++) - { + for (i = 0; i < sbi->s_groups_count; i++) { + struct ext3_group_desc *gdp = ext3_get_group_desc(sb, i, NULL); + if (i == sbi->s_groups_count - 1) last_block = le32_to_cpu(sbi->s_es->s_blocks_count) - 1; else last_block = first_block + (EXT3_BLOCKS_PER_GROUP(sb) - 1); - if ((i % EXT3_DESC_PER_BLOCK(sb)) == 0) - gdp = (struct ext3_group_desc *) - sbi->s_group_desc[desc_block++]->b_data; if (le32_to_cpu(gdp->bg_block_bitmap) < first_block || le32_to_cpu(gdp->bg_block_bitmap) > last_block) { @@ -1306,7 +1302,6 @@ static int ext3_check_descriptors (struct super_block * sb) return 0; } first_block += EXT3_BLOCKS_PER_GROUP(sb); - gdp++; } sbi->s_es->s_free_blocks_count=cpu_to_le32(ext3_count_free_blocks(sb)); @@ -1583,10 +1578,10 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent) if (le16_to_cpu(sbi->s_es->s_errors) == EXT3_ERRORS_PANIC) set_opt(sbi->s_mount_opt, ERRORS_PANIC); - else if (le16_to_cpu(sbi->s_es->s_errors) == EXT3_ERRORS_RO) - set_opt(sbi->s_mount_opt, ERRORS_RO); - else + else if (le16_to_cpu(sbi->s_es->s_errors) == EXT3_ERRORS_CONTINUE) set_opt(sbi->s_mount_opt, ERRORS_CONT); + else + set_opt(sbi->s_mount_opt, ERRORS_RO); sbi->s_resuid = le16_to_cpu(es->s_def_resuid); sbi->s_resgid = le16_to_cpu(es->s_def_resgid); diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index ac75ea953d8..0737e05ba3d 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -1700,7 +1700,7 @@ retry_alloc: /* * Now search the rest of the groups. We assume that - * i and gdp correctly point to the last group visited. + * group_no and gdp correctly point to the last group visited. */ for (bgi = 0; bgi < ngroups; bgi++) { group_no++; @@ -2011,11 +2011,7 @@ static unsigned long ext4_bg_num_gdb_meta(struct super_block *sb, static unsigned long ext4_bg_num_gdb_nometa(struct super_block *sb, ext4_group_t group) { - if (EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER) && - !ext4_group_sparse(group)) - return 0; - return EXT4_SB(sb)->s_gdb_count; + return ext4_bg_has_super(sb, group) ? EXT4_SB(sb)->s_gdb_count : 0; } /** diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 05c4145dd27..0e9055cf700 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -429,16 +429,13 @@ static ext4_fsblk_t ext4_find_near(struct inode *inode, Indirect *ind) * ext4_find_goal - find a prefered place for allocation. * @inode: owner * @block: block we want - * @chain: chain of indirect blocks * @partial: pointer to the last triple within a chain - * @goal: place to store the result. * * Normally this function find the prefered place for block allocation, - * stores it in *@goal and returns zero. + * returns it. */ - static ext4_fsblk_t ext4_find_goal(struct inode *inode, ext4_lblk_t block, - Indirect chain[4], Indirect *partial) + Indirect *partial) { struct ext4_block_alloc_info *block_i; @@ -839,7 +836,7 @@ int ext4_get_blocks_handle(handle_t *handle, struct inode *inode, if (S_ISREG(inode->i_mode) && (!ei->i_block_alloc_info)) ext4_init_block_alloc_info(inode); - goal = ext4_find_goal(inode, iblock, chain, partial); + goal = ext4_find_goal(inode, iblock, partial); /* the number of blocks need to allocate for [d,t]indirect blocks */ indirect_blks = (chain + depth) - partial - 1; diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 055a0cd0168..c89bb879776 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1458,7 +1458,7 @@ int ext4_group_desc_csum_verify(struct ext4_sb_info *sbi, __u32 block_group, } /* Called at mount-time, super-block is locked */ -static int ext4_check_descriptors (struct super_block * sb) +static int ext4_check_descriptors(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_fsblk_t first_block = le32_to_cpu(sbi->s_es->s_first_data_block); @@ -1466,8 +1466,6 @@ static int ext4_check_descriptors (struct super_block * sb) ext4_fsblk_t block_bitmap; ext4_fsblk_t inode_bitmap; ext4_fsblk_t inode_table; - struct ext4_group_desc * gdp = NULL; - int desc_block = 0; int flexbg_flag = 0; ext4_group_t i; @@ -1476,17 +1474,15 @@ static int ext4_check_descriptors (struct super_block * sb) ext4_debug ("Checking group descriptors"); - for (i = 0; i < sbi->s_groups_count; i++) - { + for (i = 0; i < sbi->s_groups_count; i++) { + struct ext4_group_desc *gdp = ext4_get_group_desc(sb, i, NULL); + if (i == sbi->s_groups_count - 1 || flexbg_flag) last_block = ext4_blocks_count(sbi->s_es) - 1; else last_block = first_block + (EXT4_BLOCKS_PER_GROUP(sb) - 1); - if ((i % EXT4_DESC_PER_BLOCK(sb)) == 0) - gdp = (struct ext4_group_desc *) - sbi->s_group_desc[desc_block++]->b_data; block_bitmap = ext4_block_bitmap(sb, gdp); if (block_bitmap < first_block || block_bitmap > last_block) { @@ -1524,8 +1520,6 @@ static int ext4_check_descriptors (struct super_block * sb) } if (!flexbg_flag) first_block += EXT4_BLOCKS_PER_GROUP(sb); - gdp = (struct ext4_group_desc *) - ((__u8 *)gdp + EXT4_DESC_SIZE(sb)); } ext4_free_blocks_count_set(sbi->s_es, ext4_count_free_blocks(sb)); diff --git a/fs/fat/file.c b/fs/fat/file.c index 69a83b59dce..c614175876e 100644 --- a/fs/fat/file.c +++ b/fs/fat/file.c @@ -155,6 +155,42 @@ out: return err; } +static int check_mode(const struct msdos_sb_info *sbi, mode_t mode) +{ + mode_t req = mode & ~S_IFMT; + + /* + * Of the r and x bits, all (subject to umask) must be present. Of the + * w bits, either all (subject to umask) or none must be present. + */ + + if (S_ISREG(mode)) { + req &= ~sbi->options.fs_fmask; + + if ((req & (S_IRUGO | S_IXUGO)) != + ((S_IRUGO | S_IXUGO) & ~sbi->options.fs_fmask)) + return -EPERM; + + if ((req & S_IWUGO) != 0 && + (req & S_IWUGO) != (S_IWUGO & ~sbi->options.fs_fmask)) + return -EPERM; + } else if (S_ISDIR(mode)) { + req &= ~sbi->options.fs_dmask; + + if ((req & (S_IRUGO | S_IXUGO)) != + ((S_IRUGO | S_IXUGO) & ~sbi->options.fs_dmask)) + return -EPERM; + + if ((req & S_IWUGO) != 0 && + (req & S_IWUGO) != (S_IWUGO & ~sbi->options.fs_dmask)) + return -EPERM; + } else { + return -EPERM; + } + + return 0; +} + int fat_notify_change(struct dentry *dentry, struct iattr *attr) { struct msdos_sb_info *sbi = MSDOS_SB(dentry->d_sb); @@ -186,9 +222,7 @@ int fat_notify_change(struct dentry *dentry, struct iattr *attr) if (((attr->ia_valid & ATTR_UID) && (attr->ia_uid != sbi->options.fs_uid)) || ((attr->ia_valid & ATTR_GID) && - (attr->ia_gid != sbi->options.fs_gid)) || - ((attr->ia_valid & ATTR_MODE) && - (attr->ia_mode & ~MSDOS_VALID_MODE))) + (attr->ia_gid != sbi->options.fs_gid))) error = -EPERM; if (error) { @@ -196,6 +230,13 @@ int fat_notify_change(struct dentry *dentry, struct iattr *attr) error = 0; goto out; } + + if (attr->ia_valid & ATTR_MODE) { + error = check_mode(sbi, attr->ia_mode); + if (error != 0 && !sbi->options.quiet) + goto out; + } + error = inode_setattr(inode, attr); if (error) goto out; diff --git a/fs/fat/inode.c b/fs/fat/inode.c index 920a576e1c2..24c0aaa5ae8 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -1295,10 +1295,8 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, fsinfo = (struct fat_boot_fsinfo *)fsinfo_bh->b_data; if (!IS_FSINFO(fsinfo)) { - printk(KERN_WARNING - "FAT: Did not find valid FSINFO signature.\n" - " Found signature1 0x%08x signature2 0x%08x" - " (sector = %lu)\n", + printk(KERN_WARNING "FAT: Invalid FSINFO signature: " + "0x%08x, 0x%08x (sector = %lu)\n", le32_to_cpu(fsinfo->signature1), le32_to_cpu(fsinfo->signature2), sbi->fsinfo_sector); diff --git a/fs/fat/misc.c b/fs/fat/misc.c index 308f2b6b502..61f23511eac 100644 --- a/fs/fat/misc.c +++ b/fs/fat/misc.c @@ -55,9 +55,8 @@ void fat_clusters_flush(struct super_block *sb) fsinfo = (struct fat_boot_fsinfo *)bh->b_data; /* Sanity check */ if (!IS_FSINFO(fsinfo)) { - printk(KERN_ERR "FAT: Did not find valid FSINFO signature.\n" - " Found signature1 0x%08x signature2 0x%08x" - " (sector = %lu)\n", + printk(KERN_ERR "FAT: Invalid FSINFO signature: " + "0x%08x, 0x%08x (sector = %lu)\n", le32_to_cpu(fsinfo->signature1), le32_to_cpu(fsinfo->signature2), sbi->fsinfo_sector); diff --git a/fs/file.c b/fs/file.c index c5575de0111..5110acb1c9e 100644 --- a/fs/file.c +++ b/fs/file.c @@ -24,6 +24,8 @@ struct fdtable_defer { struct fdtable *next; }; +int sysctl_nr_open __read_mostly = 1024*1024; + /* * We use this list to defer free fdtables that have vmalloced * sets/arrays. By keeping a per-cpu list, we avoid having to embed @@ -147,8 +149,8 @@ static struct fdtable * alloc_fdtable(unsigned int nr) nr /= (1024 / sizeof(struct file *)); nr = roundup_pow_of_two(nr + 1); nr *= (1024 / sizeof(struct file *)); - if (nr > NR_OPEN) - nr = NR_OPEN; + if (nr > sysctl_nr_open) + nr = sysctl_nr_open; fdt = kmalloc(sizeof(struct fdtable), GFP_KERNEL); if (!fdt) @@ -233,7 +235,7 @@ int expand_files(struct files_struct *files, int nr) if (nr < fdt->max_fds) return 0; /* Can we expand? */ - if (nr >= NR_OPEN) + if (nr >= sysctl_nr_open) return -EMFILE; /* All good, so we try */ diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 0b3064079fa..db80ce9eb1d 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -515,8 +515,7 @@ writeback_inodes(struct writeback_control *wbc) might_sleep(); spin_lock(&sb_lock); restart: - sb = sb_entry(super_blocks.prev); - for (; sb != sb_entry(&super_blocks); sb = sb_entry(sb->s_list.prev)) { + list_for_each_entry_reverse(sb, &super_blocks, s_list) { if (sb_has_dirty_inodes(sb)) { /* we're making our own get_super here */ sb->s_count++; @@ -581,10 +580,8 @@ static void set_sb_syncing(int val) { struct super_block *sb; spin_lock(&sb_lock); - sb = sb_entry(super_blocks.prev); - for (; sb != sb_entry(&super_blocks); sb = sb_entry(sb->s_list.prev)) { + list_for_each_entry_reverse(sb, &super_blocks, s_list) sb->s_syncing = val; - } spin_unlock(&sb_lock); } diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index db534bcde45..af639807524 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -201,6 +201,55 @@ void fuse_put_request(struct fuse_conn *fc, struct fuse_req *req) } } +static unsigned len_args(unsigned numargs, struct fuse_arg *args) +{ + unsigned nbytes = 0; + unsigned i; + + for (i = 0; i < numargs; i++) + nbytes += args[i].size; + + return nbytes; +} + +static u64 fuse_get_unique(struct fuse_conn *fc) +{ + fc->reqctr++; + /* zero is special */ + if (fc->reqctr == 0) + fc->reqctr = 1; + + return fc->reqctr; +} + +static void queue_request(struct fuse_conn *fc, struct fuse_req *req) +{ + req->in.h.unique = fuse_get_unique(fc); + req->in.h.len = sizeof(struct fuse_in_header) + + len_args(req->in.numargs, (struct fuse_arg *) req->in.args); + list_add_tail(&req->list, &fc->pending); + req->state = FUSE_REQ_PENDING; + if (!req->waiting) { + req->waiting = 1; + atomic_inc(&fc->num_waiting); + } + wake_up(&fc->waitq); + kill_fasync(&fc->fasync, SIGIO, POLL_IN); +} + +static void flush_bg_queue(struct fuse_conn *fc) +{ + while (fc->active_background < FUSE_MAX_BACKGROUND && + !list_empty(&fc->bg_queue)) { + struct fuse_req *req; + + req = list_entry(fc->bg_queue.next, struct fuse_req, list); + list_del(&req->list); + fc->active_background++; + queue_request(fc, req); + } +} + /* * This function is called when a request is finished. Either a reply * has arrived or it was aborted (and not yet sent) or some error @@ -229,6 +278,8 @@ static void request_end(struct fuse_conn *fc, struct fuse_req *req) clear_bdi_congested(&fc->bdi, WRITE); } fc->num_background--; + fc->active_background--; + flush_bg_queue(fc); } spin_unlock(&fc->lock); wake_up(&req->waitq); @@ -320,42 +371,6 @@ static void request_wait_answer(struct fuse_conn *fc, struct fuse_req *req) } } -static unsigned len_args(unsigned numargs, struct fuse_arg *args) -{ - unsigned nbytes = 0; - unsigned i; - - for (i = 0; i < numargs; i++) - nbytes += args[i].size; - - return nbytes; -} - -static u64 fuse_get_unique(struct fuse_conn *fc) - { - fc->reqctr++; - /* zero is special */ - if (fc->reqctr == 0) - fc->reqctr = 1; - - return fc->reqctr; -} - -static void queue_request(struct fuse_conn *fc, struct fuse_req *req) -{ - req->in.h.unique = fuse_get_unique(fc); - req->in.h.len = sizeof(struct fuse_in_header) + - len_args(req->in.numargs, (struct fuse_arg *) req->in.args); - list_add_tail(&req->list, &fc->pending); - req->state = FUSE_REQ_PENDING; - if (!req->waiting) { - req->waiting = 1; - atomic_inc(&fc->num_waiting); - } - wake_up(&fc->waitq); - kill_fasync(&fc->fasync, SIGIO, POLL_IN); -} - void request_send(struct fuse_conn *fc, struct fuse_req *req) { req->isreply = 1; @@ -375,20 +390,26 @@ void request_send(struct fuse_conn *fc, struct fuse_req *req) spin_unlock(&fc->lock); } +static void request_send_nowait_locked(struct fuse_conn *fc, + struct fuse_req *req) +{ + req->background = 1; + fc->num_background++; + if (fc->num_background == FUSE_MAX_BACKGROUND) + fc->blocked = 1; + if (fc->num_background == FUSE_CONGESTION_THRESHOLD) { + set_bdi_congested(&fc->bdi, READ); + set_bdi_congested(&fc->bdi, WRITE); + } + list_add_tail(&req->list, &fc->bg_queue); + flush_bg_queue(fc); +} + static void request_send_nowait(struct fuse_conn *fc, struct fuse_req *req) { spin_lock(&fc->lock); if (fc->connected) { - req->background = 1; - fc->num_background++; - if (fc->num_background == FUSE_MAX_BACKGROUND) - fc->blocked = 1; - if (fc->num_background == FUSE_CONGESTION_THRESHOLD) { - set_bdi_congested(&fc->bdi, READ); - set_bdi_congested(&fc->bdi, WRITE); - } - - queue_request(fc, req); + request_send_nowait_locked(fc, req); spin_unlock(&fc->lock); } else { req->out.h.error = -ENOTCONN; diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 80d2f5292cf..f56f91bd38b 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -416,6 +416,7 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry, int mode, fuse_put_request(fc, forget_req); d_instantiate(entry, inode); fuse_change_entry_timeout(entry, &outentry); + fuse_invalidate_attr(dir); file = lookup_instantiate_filp(nd, entry, generic_file_open); if (IS_ERR(file)) { ff->fh = outopen.fh; diff --git a/fs/fuse/file.c b/fs/fuse/file.c index bb05d227cf3..676b0bc8a86 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -77,8 +77,8 @@ static struct fuse_file *fuse_file_get(struct fuse_file *ff) static void fuse_release_end(struct fuse_conn *fc, struct fuse_req *req) { - dput(req->dentry); - mntput(req->vfsmount); + dput(req->misc.release.dentry); + mntput(req->misc.release.vfsmount); fuse_put_request(fc, req); } @@ -86,7 +86,8 @@ static void fuse_file_put(struct fuse_file *ff) { if (atomic_dec_and_test(&ff->count)) { struct fuse_req *req = ff->reserved_req; - struct fuse_conn *fc = get_fuse_conn(req->dentry->d_inode); + struct inode *inode = req->misc.release.dentry->d_inode; + struct fuse_conn *fc = get_fuse_conn(inode); req->end = fuse_release_end; request_send_background(fc, req); kfree(ff); @@ -137,7 +138,7 @@ int fuse_open_common(struct inode *inode, struct file *file, int isdir) void fuse_release_fill(struct fuse_file *ff, u64 nodeid, int flags, int opcode) { struct fuse_req *req = ff->reserved_req; - struct fuse_release_in *inarg = &req->misc.release_in; + struct fuse_release_in *inarg = &req->misc.release.in; inarg->fh = ff->fh; inarg->flags = flags; @@ -153,13 +154,14 @@ int fuse_release_common(struct inode *inode, struct file *file, int isdir) struct fuse_file *ff = file->private_data; if (ff) { struct fuse_conn *fc = get_fuse_conn(inode); + struct fuse_req *req = ff->reserved_req; fuse_release_fill(ff, get_node_id(inode), file->f_flags, isdir ? FUSE_RELEASEDIR : FUSE_RELEASE); /* Hold vfsmount and dentry until release is finished */ - ff->reserved_req->vfsmount = mntget(file->f_path.mnt); - ff->reserved_req->dentry = dget(file->f_path.dentry); + req->misc.release.vfsmount = mntget(file->f_path.mnt); + req->misc.release.dentry = dget(file->f_path.dentry); spin_lock(&fc->lock); list_del(&ff->write_entry); diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index 3ab8a3048e8..67aaf6ee38e 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -215,7 +215,11 @@ struct fuse_req { /** Data for asynchronous requests */ union { struct fuse_forget_in forget_in; - struct fuse_release_in release_in; + struct { + struct fuse_release_in in; + struct vfsmount *vfsmount; + struct dentry *dentry; + } release; struct fuse_init_in init_in; struct fuse_init_out init_out; struct fuse_read_in read_in; @@ -238,12 +242,6 @@ struct fuse_req { /** File used in the request (or NULL) */ struct fuse_file *ff; - /** vfsmount used in release */ - struct vfsmount *vfsmount; - - /** dentry used in release */ - struct dentry *dentry; - /** Request completion callback */ void (*end)(struct fuse_conn *, struct fuse_req *); @@ -298,6 +296,12 @@ struct fuse_conn { /** Number of requests currently in the background */ unsigned num_background; + /** Number of background requests currently queued for userspace */ + unsigned active_background; + + /** The list of background requests set aside for later queuing */ + struct list_head bg_queue; + /** Pending interrupts */ struct list_head interrupts; diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index e5e80d1a468..c90f633d0b5 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -465,6 +465,7 @@ static struct fuse_conn *new_conn(void) INIT_LIST_HEAD(&fc->processing); INIT_LIST_HEAD(&fc->io); INIT_LIST_HEAD(&fc->interrupts); + INIT_LIST_HEAD(&fc->bg_queue); atomic_set(&fc->num_waiting, 0); fc->bdi.ra_pages = (VM_MAX_READAHEAD * 1024) / PAGE_CACHE_SIZE; fc->bdi.unplug_io_fn = default_unplug_io_fn; diff --git a/fs/hfs/bfind.c b/fs/hfs/bfind.c index f8452a0eab5..4129cdb3f0d 100644 --- a/fs/hfs/bfind.c +++ b/fs/hfs/bfind.c @@ -52,9 +52,9 @@ int __hfs_brec_find(struct hfs_bnode *bnode, struct hfs_find_data *fd) rec = (e + b) / 2; len = hfs_brec_lenoff(bnode, rec, &off); keylen = hfs_brec_keylen(bnode, rec); - if (keylen == HFS_BAD_KEYLEN) { + if (keylen == 0) { res = -EINVAL; - goto done; + goto fail; } hfs_bnode_read(bnode, fd->key, off, keylen); cmpval = bnode->tree->keycmp(fd->key, fd->search_key); @@ -71,9 +71,9 @@ int __hfs_brec_find(struct hfs_bnode *bnode, struct hfs_find_data *fd) if (rec != e && e >= 0) { len = hfs_brec_lenoff(bnode, e, &off); keylen = hfs_brec_keylen(bnode, e); - if (keylen == HFS_BAD_KEYLEN) { + if (keylen == 0) { res = -EINVAL; - goto done; + goto fail; } hfs_bnode_read(bnode, fd->key, off, keylen); } @@ -83,6 +83,7 @@ done: fd->keylength = keylen; fd->entryoffset = off + keylen; fd->entrylength = len - keylen; +fail: return res; } @@ -206,7 +207,7 @@ int hfs_brec_goto(struct hfs_find_data *fd, int cnt) len = hfs_brec_lenoff(bnode, fd->record, &off); keylen = hfs_brec_keylen(bnode, fd->record); - if (keylen == HFS_BAD_KEYLEN) { + if (keylen == 0) { res = -EINVAL; goto out; } diff --git a/fs/hfs/brec.c b/fs/hfs/brec.c index 8626ee375ea..878bf25dbc6 100644 --- a/fs/hfs/brec.c +++ b/fs/hfs/brec.c @@ -49,14 +49,14 @@ u16 hfs_brec_keylen(struct hfs_bnode *node, u16 rec) if (retval > node->tree->max_key_len + 2) { printk(KERN_ERR "hfs: keylen %d too large\n", retval); - retval = HFS_BAD_KEYLEN; + retval = 0; } } else { retval = (hfs_bnode_read_u8(node, recoff) | 1) + 1; if (retval > node->tree->max_key_len + 1) { printk(KERN_ERR "hfs: keylen %d too large\n", retval); - retval = HFS_BAD_KEYLEN; + retval = 0; } } } diff --git a/fs/hfs/btree.c b/fs/hfs/btree.c index 110dd3515dc..24cf6fc4302 100644 --- a/fs/hfs/btree.c +++ b/fs/hfs/btree.c @@ -81,15 +81,23 @@ struct hfs_btree *hfs_btree_open(struct super_block *sb, u32 id, btree_keycmp ke goto fail_page; if (!tree->node_count) goto fail_page; - if ((id == HFS_EXT_CNID) && (tree->max_key_len != HFS_MAX_EXT_KEYLEN)) { - printk(KERN_ERR "hfs: invalid extent max_key_len %d\n", - tree->max_key_len); - goto fail_page; - } - if ((id == HFS_CAT_CNID) && (tree->max_key_len != HFS_MAX_CAT_KEYLEN)) { - printk(KERN_ERR "hfs: invalid catalog max_key_len %d\n", - tree->max_key_len); - goto fail_page; + switch (id) { + case HFS_EXT_CNID: + if (tree->max_key_len != HFS_MAX_EXT_KEYLEN) { + printk(KERN_ERR "hfs: invalid extent max_key_len %d\n", + tree->max_key_len); + goto fail_page; + } + break; + case HFS_CAT_CNID: + if (tree->max_key_len != HFS_MAX_CAT_KEYLEN) { + printk(KERN_ERR "hfs: invalid catalog max_key_len %d\n", + tree->max_key_len); + goto fail_page; + } + break; + default: + BUG(); } tree->node_size_shift = ffs(size) - 1; diff --git a/fs/hfs/hfs.h b/fs/hfs/hfs.h index c6aae61adfe..6f194d0768b 100644 --- a/fs/hfs/hfs.h +++ b/fs/hfs/hfs.h @@ -28,8 +28,6 @@ #define HFS_MAX_NAMELEN 128 #define HFS_MAX_VALENCE 32767U -#define HFS_BAD_KEYLEN 0xFF - /* Meanings of the drAtrb field of the MDB, * Reference: _Inside Macintosh: Files_ p. 2-61 */ diff --git a/fs/hfs/super.c b/fs/hfs/super.c index 16cbd902f8b..32de44ed002 100644 --- a/fs/hfs/super.c +++ b/fs/hfs/super.c @@ -6,7 +6,7 @@ * This file may be distributed under the terms of the GNU General Public License. * * This file contains hfs_read_super(), some of the super_ops and - * init_module() and cleanup_module(). The remaining super_ops are in + * init_hfs_fs() and exit_hfs_fs(). The remaining super_ops are in * inode.c since they deal with inodes. * * Based on the minix file system code, (C) 1991, 1992 by Linus Torvalds diff --git a/fs/inotify.c b/fs/inotify.c index 2c5b9215287..690e72595e6 100644 --- a/fs/inotify.c +++ b/fs/inotify.c @@ -168,20 +168,14 @@ static void set_dentry_child_flags(struct inode *inode, int watched) struct dentry *child; list_for_each_entry(child, &alias->d_subdirs, d_u.d_child) { - if (!child->d_inode) { - WARN_ON(child->d_flags & DCACHE_INOTIFY_PARENT_WATCHED); + if (!child->d_inode) continue; - } + spin_lock(&child->d_lock); - if (watched) { - WARN_ON(child->d_flags & - DCACHE_INOTIFY_PARENT_WATCHED); + if (watched) child->d_flags |= DCACHE_INOTIFY_PARENT_WATCHED; - } else { - WARN_ON(!(child->d_flags & - DCACHE_INOTIFY_PARENT_WATCHED)); - child->d_flags&=~DCACHE_INOTIFY_PARENT_WATCHED; - } + else + child->d_flags &=~DCACHE_INOTIFY_PARENT_WATCHED; spin_unlock(&child->d_lock); } } @@ -253,7 +247,6 @@ void inotify_d_instantiate(struct dentry *entry, struct inode *inode) if (!inode) return; - WARN_ON(entry->d_flags & DCACHE_INOTIFY_PARENT_WATCHED); spin_lock(&entry->d_lock); parent = entry->d_parent; if (parent->d_inode && inotify_inode_watched(parent->d_inode)) @@ -627,6 +620,7 @@ s32 inotify_add_watch(struct inotify_handle *ih, struct inotify_watch *watch, struct inode *inode, u32 mask) { int ret = 0; + int newly_watched; /* don't allow invalid bits: we don't want flags set */ mask &= IN_ALL_EVENTS | IN_ONESHOT; @@ -653,12 +647,18 @@ s32 inotify_add_watch(struct inotify_handle *ih, struct inotify_watch *watch, */ watch->inode = igrab(inode); - if (!inotify_inode_watched(inode)) - set_dentry_child_flags(inode, 1); - /* Add the watch to the handle's and the inode's list */ + newly_watched = !inotify_inode_watched(inode); list_add(&watch->h_list, &ih->watches); list_add(&watch->i_list, &inode->inotify_watches); + /* + * Set child flags _after_ adding the watch, so there is no race + * windows where newly instantiated children could miss their parent's + * watched flag. + */ + if (newly_watched) + set_dentry_child_flags(inode, 1); + out: mutex_unlock(&ih->mutex); mutex_unlock(&inode->inotify_mutex); diff --git a/fs/inotify_user.c b/fs/inotify_user.c index 5e009331c01..a336c9709f3 100644 --- a/fs/inotify_user.c +++ b/fs/inotify_user.c @@ -79,6 +79,7 @@ struct inotify_device { atomic_t count; /* reference count */ struct user_struct *user; /* user who opened this dev */ struct inotify_handle *ih; /* inotify handle */ + struct fasync_struct *fa; /* async notification */ unsigned int queue_size; /* size of the queue (bytes) */ unsigned int event_count; /* number of pending events */ unsigned int max_events; /* maximum number of events */ @@ -248,6 +249,19 @@ inotify_dev_get_event(struct inotify_device *dev) } /* + * inotify_dev_get_last_event - return the last event in the given dev's queue + * + * Caller must hold dev->ev_mutex. + */ +static inline struct inotify_kernel_event * +inotify_dev_get_last_event(struct inotify_device *dev) +{ + if (list_empty(&dev->events)) + return NULL; + return list_entry(dev->events.prev, struct inotify_kernel_event, list); +} + +/* * inotify_dev_queue_event - event handler registered with core inotify, adds * a new event to the given device * @@ -273,7 +287,7 @@ static void inotify_dev_queue_event(struct inotify_watch *w, u32 wd, u32 mask, put_inotify_watch(w); /* final put */ /* coalescing: drop this event if it is a dupe of the previous */ - last = inotify_dev_get_event(dev); + last = inotify_dev_get_last_event(dev); if (last && last->event.mask == mask && last->event.wd == wd && last->event.cookie == cookie) { const char *lastname = last->name; @@ -302,6 +316,7 @@ static void inotify_dev_queue_event(struct inotify_watch *w, u32 wd, u32 mask, dev->queue_size += sizeof(struct inotify_event) + kevent->event.len; list_add_tail(&kevent->list, &dev->events); wake_up_interruptible(&dev->wq); + kill_fasync(&dev->fa, SIGIO, POLL_IN); out: mutex_unlock(&dev->ev_mutex); @@ -490,6 +505,13 @@ static ssize_t inotify_read(struct file *file, char __user *buf, return ret; } +static int inotify_fasync(int fd, struct file *file, int on) +{ + struct inotify_device *dev = file->private_data; + + return fasync_helper(fd, file, on, &dev->fa) >= 0 ? 0 : -EIO; +} + static int inotify_release(struct inode *ignored, struct file *file) { struct inotify_device *dev = file->private_data; @@ -502,6 +524,9 @@ static int inotify_release(struct inode *ignored, struct file *file) inotify_dev_event_dequeue(dev); mutex_unlock(&dev->ev_mutex); + if (file->f_flags & FASYNC) + inotify_fasync(-1, file, 0); + /* free this device: the put matching the get in inotify_init() */ put_inotify_dev(dev); @@ -530,6 +555,7 @@ static long inotify_ioctl(struct file *file, unsigned int cmd, static const struct file_operations inotify_fops = { .poll = inotify_poll, .read = inotify_read, + .fasync = inotify_fasync, .release = inotify_release, .unlocked_ioctl = inotify_ioctl, .compat_ioctl = inotify_ioctl, @@ -577,6 +603,7 @@ asmlinkage long sys_inotify_init(void) goto out_free_dev; } dev->ih = ih; + dev->fa = NULL; filp->f_op = &inotify_fops; filp->f_path.mnt = mntget(inotify_mnt); diff --git a/fs/jbd/journal.c b/fs/jbd/journal.c index 5d14243499d..3943a8905eb 100644 --- a/fs/jbd/journal.c +++ b/fs/jbd/journal.c @@ -1457,7 +1457,7 @@ static const char *journal_dev_name(journal_t *journal, char *buffer) * Aborts hard --- we mark the abort as occurred, but do _nothing_ else, * and don't attempt to make any other journal updates. */ -void __journal_abort_hard(journal_t *journal) +static void __journal_abort_hard(journal_t *journal) { transaction_t *transaction; char b[BDEVNAME_SIZE]; diff --git a/fs/jbd/recovery.c b/fs/jbd/recovery.c index c5d9694b6a2..2b8edf4d6ea 100644 --- a/fs/jbd/recovery.c +++ b/fs/jbd/recovery.c @@ -354,7 +354,7 @@ static int do_one_pass(journal_t *journal, struct buffer_head * obh; struct buffer_head * nbh; - cond_resched(); /* We're under lock_kernel() */ + cond_resched(); /* If we already know where to stop the log traversal, * check right now that we haven't gone past the end of diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c index 921680663fa..d36356f7d22 100644 --- a/fs/jbd2/recovery.c +++ b/fs/jbd2/recovery.c @@ -397,7 +397,7 @@ static int do_one_pass(journal_t *journal, struct buffer_head * obh; struct buffer_head * nbh; - cond_resched(); /* We're under lock_kernel() */ + cond_resched(); /* If we already know where to stop the log traversal, * check right now that we haven't gone past the end of diff --git a/fs/namei.c b/fs/namei.c index 73e2e665817..241cff42365 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -2188,6 +2188,7 @@ int vfs_unlink(struct inode *dir, struct dentry *dentry) /* We don't d_delete() NFS sillyrenamed files--they still exist. */ if (!error && !(dentry->d_flags & DCACHE_NFSFS_RENAMED)) { + fsnotify_link_count(dentry->d_inode); d_delete(dentry); } @@ -2360,7 +2361,7 @@ int vfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_de error = dir->i_op->link(old_dentry, dir, new_dentry); mutex_unlock(&old_dentry->d_inode->i_mutex); if (!error) - fsnotify_create(dir, new_dentry); + fsnotify_link(dir, old_dentry->d_inode, new_dentry); return error; } diff --git a/fs/namespace.c b/fs/namespace.c index 61bf376e29e..e9c10cd01e1 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -25,18 +25,21 @@ #include <linux/security.h> #include <linux/mount.h> #include <linux/ramfs.h> +#include <linux/log2.h> #include <asm/uaccess.h> #include <asm/unistd.h> #include "pnode.h" #include "internal.h" +#define HASH_SHIFT ilog2(PAGE_SIZE / sizeof(struct list_head)) +#define HASH_SIZE (1UL << HASH_SHIFT) + /* spinlock for vfsmount related operations, inplace of dcache_lock */ __cacheline_aligned_in_smp DEFINE_SPINLOCK(vfsmount_lock); static int event; static struct list_head *mount_hashtable __read_mostly; -static int hash_mask __read_mostly, hash_bits __read_mostly; static struct kmem_cache *mnt_cache __read_mostly; static struct rw_semaphore namespace_sem; @@ -48,8 +51,8 @@ static inline unsigned long hash(struct vfsmount *mnt, struct dentry *dentry) { unsigned long tmp = ((unsigned long)mnt / L1_CACHE_BYTES); tmp += ((unsigned long)dentry / L1_CACHE_BYTES); - tmp = tmp + (tmp >> hash_bits); - return tmp & hash_mask; + tmp = tmp + (tmp >> HASH_SHIFT); + return tmp & (HASH_SIZE - 1); } struct vfsmount *alloc_vfsmnt(const char *name) @@ -1813,9 +1816,7 @@ static void __init init_mount_tree(void) void __init mnt_init(void) { - struct list_head *d; - unsigned int nr_hash; - int i; + unsigned u; int err; init_rwsem(&namespace_sem); @@ -1828,35 +1829,11 @@ void __init mnt_init(void) if (!mount_hashtable) panic("Failed to allocate mount hash table\n"); - /* - * Find the power-of-two list-heads that can fit into the allocation.. - * We don't guarantee that "sizeof(struct list_head)" is necessarily - * a power-of-two. - */ - nr_hash = PAGE_SIZE / sizeof(struct list_head); - hash_bits = 0; - do { - hash_bits++; - } while ((nr_hash >> hash_bits) != 0); - hash_bits--; + printk("Mount-cache hash table entries: %lu\n", HASH_SIZE); + + for (u = 0; u < HASH_SIZE; u++) + INIT_LIST_HEAD(&mount_hashtable[u]); - /* - * Re-calculate the actual number of entries and the mask - * from the number of bits we can fit. - */ - nr_hash = 1UL << hash_bits; - hash_mask = nr_hash - 1; - - printk("Mount-cache hash table entries: %d\n", nr_hash); - - /* And initialize the newly allocated array */ - d = mount_hashtable; - i = nr_hash; - do { - INIT_LIST_HEAD(d); - d++; - i--; - } while (i); err = sysfs_init(); if (err) printk(KERN_WARNING "%s: sysfs_init error: %d\n", diff --git a/fs/ncpfs/inode.c b/fs/ncpfs/inode.c index e1cb70c643f..eff1f18d034 100644 --- a/fs/ncpfs/inode.c +++ b/fs/ncpfs/inode.c @@ -987,7 +987,7 @@ static struct file_system_type ncp_fs_type = { static int __init init_ncp_fs(void) { int err; - DPRINTK("ncpfs: init_module called\n"); + DPRINTK("ncpfs: init_ncp_fs called\n"); err = init_inodecache(); if (err) @@ -1004,7 +1004,7 @@ out1: static void __exit exit_ncp_fs(void) { - DPRINTK("ncpfs: cleanup_module called\n"); + DPRINTK("ncpfs: exit_ncp_fs called\n"); unregister_filesystem(&ncp_fs_type); destroy_inodecache(); } diff --git a/fs/partitions/Kconfig b/fs/partitions/Kconfig index a99acd8de35..cb5f0a3f1b0 100644 --- a/fs/partitions/Kconfig +++ b/fs/partitions/Kconfig @@ -198,7 +198,7 @@ config LDM_DEBUG config SGI_PARTITION bool "SGI partition support" if PARTITION_ADVANCED - default y if (SGI_IP22 || SGI_IP27 || ((MACH_JAZZ || SNI_RM) && !CPU_LITTLE_ENDIAN)) + default y if DEFAULT_SGI_PARTITION help Say Y here if you would like to be able to read the hard disk partition table format used by SGI machines. diff --git a/fs/pnode.c b/fs/pnode.c index 89940f243fc..05ba692bc54 100644 --- a/fs/pnode.c +++ b/fs/pnode.c @@ -83,6 +83,8 @@ void change_mnt_propagation(struct vfsmount *mnt, int type) mnt->mnt_master = NULL; if (type == MS_UNBINDABLE) mnt->mnt_flags |= MNT_UNBINDABLE; + else + mnt->mnt_flags &= ~MNT_UNBINDABLE; } } diff --git a/fs/proc/proc_misc.c b/fs/proc/proc_misc.c index 51288db37a0..2686592dbcb 100644 --- a/fs/proc/proc_misc.c +++ b/fs/proc/proc_misc.c @@ -29,6 +29,7 @@ #include <linux/mm.h> #include <linux/mmzone.h> #include <linux/pagemap.h> +#include <linux/interrupt.h> #include <linux/swap.h> #include <linux/slab.h> #include <linux/smp.h> @@ -64,7 +65,6 @@ */ extern int get_hardware_list(char *); extern int get_stram_list(char *); -extern int get_filesystem_list(char *); extern int get_exec_domain_list(char *); extern int get_dma_list(char *); @@ -84,10 +84,15 @@ static int loadavg_read_proc(char *page, char **start, off_t off, { int a, b, c; int len; + unsigned long seq; + + do { + seq = read_seqbegin(&xtime_lock); + a = avenrun[0] + (FIXED_1/200); + b = avenrun[1] + (FIXED_1/200); + c = avenrun[2] + (FIXED_1/200); + } while (read_seqretry(&xtime_lock, seq)); - a = avenrun[0] + (FIXED_1/200); - b = avenrun[1] + (FIXED_1/200); - c = avenrun[2] + (FIXED_1/200); len = sprintf(page,"%d.%02d %d.%02d %d.%02d %ld/%d %d\n", LOAD_INT(a), LOAD_FRAC(a), LOAD_INT(b), LOAD_FRAC(b), @@ -599,7 +604,6 @@ static void int_seq_stop(struct seq_file *f, void *v) } -extern int show_interrupts(struct seq_file *f, void *v); /* In arch code */ static struct seq_operations int_seq_ops = { .start = int_seq_start, .next = int_seq_next, diff --git a/fs/reiserfs/prints.c b/fs/reiserfs/prints.c index 5e7388b32d0..740bb8c0c1a 100644 --- a/fs/reiserfs/prints.c +++ b/fs/reiserfs/prints.c @@ -575,6 +575,8 @@ void print_block(struct buffer_head *bh, ...) //int print_mode, int first, int l printk ("Block %llu contains unformatted data\n", (unsigned long long)bh->b_blocknr); + + va_end(args); } static char print_tb_buf[2048]; diff --git a/fs/reiserfs/xattr.c b/fs/reiserfs/xattr.c index 1597f6b649e..a5bd23ce0e4 100644 --- a/fs/reiserfs/xattr.c +++ b/fs/reiserfs/xattr.c @@ -1084,7 +1084,7 @@ ssize_t reiserfs_listxattr(struct dentry * dentry, char *buffer, size_t size) } /* This is the implementation for the xattr plugin infrastructure */ -static struct list_head xattr_handlers = LIST_HEAD_INIT(xattr_handlers); +static LIST_HEAD(xattr_handlers); static DEFINE_RWLOCK(handler_lock); static struct reiserfs_xattr_handler *find_xattr_handler_prefix(const char diff --git a/fs/select.c b/fs/select.c index 47f47925aea..5633fe98078 100644 --- a/fs/select.c +++ b/fs/select.c @@ -739,7 +739,7 @@ asmlinkage long sys_poll(struct pollfd __user *ufds, unsigned int nfds, timeout_jiffies = -1; else #endif - timeout_jiffies = msecs_to_jiffies(timeout_msecs); + timeout_jiffies = msecs_to_jiffies(timeout_msecs) + 1; } else { /* Infinite (< 0) or no (0) timeout */ timeout_jiffies = timeout_msecs; diff --git a/fs/signalfd.c b/fs/signalfd.c index 2d3e107da2d..cb2b63ae0bf 100644 --- a/fs/signalfd.c +++ b/fs/signalfd.c @@ -27,6 +27,7 @@ #include <linux/list.h> #include <linux/anon_inodes.h> #include <linux/signalfd.h> +#include <linux/syscalls.h> struct signalfd_ctx { sigset_t sigmask; diff --git a/fs/smbfs/inode.c b/fs/smbfs/inode.c index 9416ead0c7a..4e5c22ca802 100644 --- a/fs/smbfs/inode.c +++ b/fs/smbfs/inode.c @@ -500,6 +500,13 @@ static int smb_fill_super(struct super_block *sb, void *raw_data, int silent) struct smb_fattr root; int ver; void *mem; + static int warn_count; + + if (warn_count < 5) { + warn_count++; + printk(KERN_EMERG "smbfs is deprecated and will be removed" + "from the 2.6.27 kernel. Please migrate to cifs\n"); + } if (!raw_data) goto out_no_data; diff --git a/fs/smbfs/sock.c b/fs/smbfs/sock.c index e48bd8235a8..e37fe4deebd 100644 --- a/fs/smbfs/sock.c +++ b/fs/smbfs/sock.c @@ -329,9 +329,8 @@ smb_receive(struct smb_sb_info *server, struct smb_request *req) msg.msg_control = NULL; /* Dont repeat bytes and count available bufferspace */ - rlen = smb_move_iov(&p, &num, iov, req->rq_bytes_recvd); - if (req->rq_rlen < rlen) - rlen = req->rq_rlen; + rlen = min_t(int, smb_move_iov(&p, &num, iov, req->rq_bytes_recvd), + (req->rq_rlen - req->rq_bytes_recvd)); result = kernel_recvmsg(sock, &msg, p, num, rlen, flags); diff --git a/fs/utimes.c b/fs/utimes.c index b9912ecbee2..e5588cd8530 100644 --- a/fs/utimes.c +++ b/fs/utimes.c @@ -6,6 +6,7 @@ #include <linux/sched.h> #include <linux/stat.h> #include <linux/utime.h> +#include <linux/syscalls.h> #include <asm/uaccess.h> #include <asm/unistd.h> |