OpenCloudOS-Kernel/fs/ext4/super.c

5697 lines
161 KiB
C
Raw Normal View History

/*
* linux/fs/ext4/super.c
*
* Copyright (C) 1992, 1993, 1994, 1995
* Remy Card (card@masi.ibp.fr)
* Laboratoire MASI - Institut Blaise Pascal
* Universite Pierre et Marie Curie (Paris VI)
*
* from
*
* linux/fs/minix/inode.c
*
* Copyright (C) 1991, 1992 Linus Torvalds
*
* Big-endian to little-endian byte-swapping/bitmaps by
* David S. Miller (davem@caip.rutgers.edu), 1995
*/
#include <linux/module.h>
#include <linux/string.h>
#include <linux/fs.h>
#include <linux/time.h>
#include <linux/vmalloc.h>
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/blkdev.h>
#include <linux/backing-dev.h>
#include <linux/parser.h>
#include <linux/buffer_head.h>
#include <linux/exportfs.h>
#include <linux/vfs.h>
#include <linux/random.h>
#include <linux/mount.h>
#include <linux/namei.h>
#include <linux/quotaops.h>
#include <linux/seq_file.h>
#include <linux/ctype.h>
#include <linux/log2.h>
Ext4: Uninitialized Block Groups In pass1 of e2fsck, every inode table in the fileystem is scanned and checked, regardless of whether it is in use. This is this the most time consuming part of the filesystem check. The unintialized block group feature can greatly reduce e2fsck time by eliminating checking of uninitialized inodes. With this feature, there is a a high water mark of used inodes for each block group. Block and inode bitmaps can be uninitialized on disk via a flag in the group descriptor to avoid reading or scanning them at e2fsck time. A checksum of each group descriptor is used to ensure that corruption in the group descriptor's bit flags does not cause incorrect operation. The feature is enabled through a mkfs option mke2fs /dev/ -O uninit_groups A patch adding support for uninitialized block groups to e2fsprogs tools has been posted to the linux-ext4 mailing list. The patches have been stress tested with fsstress and fsx. In performance tests testing e2fsck time, we have seen that e2fsck time on ext3 grows linearly with the total number of inodes in the filesytem. In ext4 with the uninitialized block groups feature, the e2fsck time is constant, based solely on the number of used inodes rather than the total inode count. Since typical ext4 filesystems only use 1-10% of their inodes, this feature can greatly reduce e2fsck time for users. With performance improvement of 2-20 times, depending on how full the filesystem is. The attached graph shows the major improvements in e2fsck times in filesystems with a large total inode count, but few inodes in use. In each group descriptor if we have EXT4_BG_INODE_UNINIT set in bg_flags: Inode table is not initialized/used in this group. So we can skip the consistency check during fsck. EXT4_BG_BLOCK_UNINIT set in bg_flags: No block in the group is used. So we can skip the block bitmap verification for this group. We also add two new fields to group descriptor as a part of uninitialized group patch. __le16 bg_itable_unused; /* Unused inodes count */ __le16 bg_checksum; /* crc16(sb_uuid+group+desc) */ bg_itable_unused: If we have EXT4_BG_INODE_UNINIT not set in bg_flags then bg_itable_unused will give the offset within the inode table till the inodes are used. This can be used by fsck to skip list of inodes that are marked unused. bg_checksum: Now that we depend on bg_flags and bg_itable_unused to determine the block and inode usage, we need to make sure group descriptor is not corrupt. We add checksum to group descriptor to detect corruption. If the descriptor is found to be corrupt, we mark all the blocks and inodes in the group used. Signed-off-by: Avantika Mathur <mathur@us.ibm.com> Signed-off-by: Andreas Dilger <adilger@clusterfs.com> Signed-off-by: Mingming Cao <cmm@us.ibm.com> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
2007-10-17 06:38:25 +08:00
#include <linux/crc16.h>
#include <linux/cleancache.h>
#include <linux/uaccess.h>
ext4: add support for lazy inode table initialization When the lazy_itable_init extended option is passed to mke2fs, it considerably speeds up filesystem creation because inode tables are not zeroed out. The fact that parts of the inode table are uninitialized is not a problem so long as the block group descriptors, which contain information regarding how much of the inode table has been initialized, has not been corrupted However, if the block group checksums are not valid, e2fsck must scan the entire inode table, and the the old, uninitialized data could potentially cause e2fsck to report false problems. Hence, it is important for the inode tables to be initialized as soon as possble. This commit adds this feature so that mke2fs can safely use the lazy inode table initialization feature to speed up formatting file systems. This is done via a new new kernel thread called ext4lazyinit, which is created on demand and destroyed, when it is no longer needed. There is only one thread for all ext4 filesystems in the system. When the first filesystem with inititable mount option is mounted, ext4lazyinit thread is created, then the filesystem can register its request in the request list. This thread then walks through the list of requests picking up scheduled requests and invoking ext4_init_inode_table(). Next schedule time for the request is computed by multiplying the time it took to zero out last inode table with wait multiplier, which can be set with the (init_itable=n) mount option (default is 10). We are doing this so we do not take the whole I/O bandwidth. When the thread is no longer necessary (request list is empty) it frees the appropriate structures and exits (and can be created later later by another filesystem). We do not disturb regular inode allocations in any way, it just do not care whether the inode table is, or is not zeroed. But when zeroing, we have to skip used inodes, obviously. Also we should prevent new inode allocations from the group, while zeroing is on the way. For that we take write alloc_sem lock in ext4_init_inode_table() and read alloc_sem in the ext4_claim_inode, so when we are unlucky and allocator hits the group which is currently being zeroed, it just has to wait. This can be suppresed using the mount option no_init_itable. Signed-off-by: Lukas Czerner <lczerner@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2010-10-28 09:30:05 +08:00
#include <linux/kthread.h>
#include <linux/freezer.h>
#include "ext4.h"
#include "ext4_extents.h" /* Needed for trace points definition */
#include "ext4_jbd2.h"
#include "xattr.h"
#include "acl.h"
#include "mballoc.h"
#define CREATE_TRACE_POINTS
#include <trace/events/ext4.h>
static struct ext4_lazy_init *ext4_li_info;
static struct mutex ext4_li_mtx;
static struct ratelimit_state ext4_mount_msg_ratelimit;
static int ext4_load_journal(struct super_block *, struct ext4_super_block *,
unsigned long journal_devnum);
static int ext4_show_options(struct seq_file *seq, struct dentry *root);
static int ext4_commit_super(struct super_block *sb, int sync);
static void ext4_mark_recovery_complete(struct super_block *sb,
struct ext4_super_block *es);
static void ext4_clear_journal_err(struct super_block *sb,
struct ext4_super_block *es);
static int ext4_sync_fs(struct super_block *sb, int wait);
static int ext4_remount(struct super_block *sb, int *flags, char *data);
static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf);
filesystem freeze: add error handling of write_super_lockfs/unlockfs Currently, ext3 in mainline Linux doesn't have the freeze feature which suspends write requests. So, we cannot take a backup which keeps the filesystem's consistency with the storage device's features (snapshot and replication) while it is mounted. In many case, a commercial filesystem (e.g. VxFS) has the freeze feature and it would be used to get the consistent backup. If Linux's standard filesystem ext3 has the freeze feature, we can do it without a commercial filesystem. So I have implemented the ioctls of the freeze feature. I think we can take the consistent backup with the following steps. 1. Freeze the filesystem with the freeze ioctl. 2. Separate the replication volume or create the snapshot with the storage device's feature. 3. Unfreeze the filesystem with the unfreeze ioctl. 4. Take the backup from the separated replication volume or the snapshot. This patch: VFS: Changed the type of write_super_lockfs and unlockfs from "void" to "int" so that they can return an error. Rename write_super_lockfs and unlockfs of the super block operation freeze_fs and unfreeze_fs to avoid a confusion. ext3, ext4, xfs, gfs2, jfs: Changed the type of write_super_lockfs and unlockfs from "void" to "int" so that write_super_lockfs returns an error if needed, and unlockfs always returns 0. reiserfs: Changed the type of write_super_lockfs and unlockfs from "void" to "int" so that they always return 0 (success) to keep a current behavior. Signed-off-by: Takashi Sato <t-sato@yk.jp.nec.com> Signed-off-by: Masayuki Hamaguchi <m-hamaguchi@ys.jp.nec.com> Cc: <xfs-masters@oss.sgi.com> Cc: <linux-ext4@vger.kernel.org> Cc: Christoph Hellwig <hch@lst.de> Cc: Dave Kleikamp <shaggy@austin.ibm.com> Cc: Dave Chinner <david@fromorbit.com> Cc: Alasdair G Kergon <agk@redhat.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-10 08:40:58 +08:00
static int ext4_unfreeze(struct super_block *sb);
static int ext4_freeze(struct super_block *sb);
static struct dentry *ext4_mount(struct file_system_type *fs_type, int flags,
const char *dev_name, void *data);
static inline int ext2_feature_set_ok(struct super_block *sb);
static inline int ext3_feature_set_ok(struct super_block *sb);
static int ext4_feature_set_ok(struct super_block *sb, int readonly);
ext4: add support for lazy inode table initialization When the lazy_itable_init extended option is passed to mke2fs, it considerably speeds up filesystem creation because inode tables are not zeroed out. The fact that parts of the inode table are uninitialized is not a problem so long as the block group descriptors, which contain information regarding how much of the inode table has been initialized, has not been corrupted However, if the block group checksums are not valid, e2fsck must scan the entire inode table, and the the old, uninitialized data could potentially cause e2fsck to report false problems. Hence, it is important for the inode tables to be initialized as soon as possble. This commit adds this feature so that mke2fs can safely use the lazy inode table initialization feature to speed up formatting file systems. This is done via a new new kernel thread called ext4lazyinit, which is created on demand and destroyed, when it is no longer needed. There is only one thread for all ext4 filesystems in the system. When the first filesystem with inititable mount option is mounted, ext4lazyinit thread is created, then the filesystem can register its request in the request list. This thread then walks through the list of requests picking up scheduled requests and invoking ext4_init_inode_table(). Next schedule time for the request is computed by multiplying the time it took to zero out last inode table with wait multiplier, which can be set with the (init_itable=n) mount option (default is 10). We are doing this so we do not take the whole I/O bandwidth. When the thread is no longer necessary (request list is empty) it frees the appropriate structures and exits (and can be created later later by another filesystem). We do not disturb regular inode allocations in any way, it just do not care whether the inode table is, or is not zeroed. But when zeroing, we have to skip used inodes, obviously. Also we should prevent new inode allocations from the group, while zeroing is on the way. For that we take write alloc_sem lock in ext4_init_inode_table() and read alloc_sem in the ext4_claim_inode, so when we are unlucky and allocator hits the group which is currently being zeroed, it just has to wait. This can be suppresed using the mount option no_init_itable. Signed-off-by: Lukas Czerner <lczerner@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2010-10-28 09:30:05 +08:00
static void ext4_destroy_lazyinit_thread(void);
static void ext4_unregister_li_request(struct super_block *sb);
static void ext4_clear_request_list(void);
static struct inode *ext4_get_journal_inode(struct super_block *sb,
unsigned int journal_inum);
/*
* Lock ordering
*
* Note the difference between i_mmap_sem (EXT4_I(inode)->i_mmap_sem) and
* i_mmap_rwsem (inode->i_mmap_rwsem)!
*
* page fault path:
* mmap_sem -> sb_start_pagefault -> i_mmap_sem (r) -> transaction start ->
* page lock -> i_data_sem (rw)
*
* buffered write path:
* sb_start_write -> i_mutex -> mmap_sem
* sb_start_write -> i_mutex -> transaction start -> page lock ->
* i_data_sem (rw)
*
* truncate:
* sb_start_write -> i_mutex -> EXT4_STATE_DIOREAD_LOCK (w) -> i_mmap_sem (w) ->
* i_mmap_rwsem (w) -> page lock
* sb_start_write -> i_mutex -> EXT4_STATE_DIOREAD_LOCK (w) -> i_mmap_sem (w) ->
* transaction start -> i_data_sem (rw)
*
* direct IO:
* sb_start_write -> i_mutex -> EXT4_STATE_DIOREAD_LOCK (r) -> mmap_sem
* sb_start_write -> i_mutex -> EXT4_STATE_DIOREAD_LOCK (r) ->
* transaction start -> i_data_sem (rw)
*
* writepages:
* transaction start -> page lock(s) -> i_data_sem (rw)
*/
#if !defined(CONFIG_EXT2_FS) && !defined(CONFIG_EXT2_FS_MODULE) && defined(CONFIG_EXT4_USE_FOR_EXT2)
static struct file_system_type ext2_fs_type = {
.owner = THIS_MODULE,
.name = "ext2",
.mount = ext4_mount,
.kill_sb = kill_block_super,
.fs_flags = FS_REQUIRES_DEV,
};
fs: Limit sys_mount to only request filesystem modules. Modify the request_module to prefix the file system type with "fs-" and add aliases to all of the filesystems that can be built as modules to match. A common practice is to build all of the kernel code and leave code that is not commonly needed as modules, with the result that many users are exposed to any bug anywhere in the kernel. Looking for filesystems with a fs- prefix limits the pool of possible modules that can be loaded by mount to just filesystems trivially making things safer with no real cost. Using aliases means user space can control the policy of which filesystem modules are auto-loaded by editing /etc/modprobe.d/*.conf with blacklist and alias directives. Allowing simple, safe, well understood work-arounds to known problematic software. This also addresses a rare but unfortunate problem where the filesystem name is not the same as it's module name and module auto-loading would not work. While writing this patch I saw a handful of such cases. The most significant being autofs that lives in the module autofs4. This is relevant to user namespaces because we can reach the request module in get_fs_type() without having any special permissions, and people get uncomfortable when a user specified string (in this case the filesystem type) goes all of the way to request_module. After having looked at this issue I don't think there is any particular reason to perform any filtering or permission checks beyond making it clear in the module request that we want a filesystem module. The common pattern in the kernel is to call request_module() without regards to the users permissions. In general all a filesystem module does once loaded is call register_filesystem() and go to sleep. Which means there is not much attack surface exposed by loading a filesytem module unless the filesystem is mounted. In a user namespace filesystems are not mounted unless .fs_flags = FS_USERNS_MOUNT, which most filesystems do not set today. Acked-by: Serge Hallyn <serge.hallyn@canonical.com> Acked-by: Kees Cook <keescook@chromium.org> Reported-by: Kees Cook <keescook@google.com> Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
2013-03-03 11:39:14 +08:00
MODULE_ALIAS_FS("ext2");
MODULE_ALIAS("ext2");
#define IS_EXT2_SB(sb) ((sb)->s_bdev->bd_holder == &ext2_fs_type)
#else
#define IS_EXT2_SB(sb) (0)
#endif
static struct file_system_type ext3_fs_type = {
.owner = THIS_MODULE,
.name = "ext3",
.mount = ext4_mount,
.kill_sb = kill_block_super,
.fs_flags = FS_REQUIRES_DEV,
};
fs: Limit sys_mount to only request filesystem modules. Modify the request_module to prefix the file system type with "fs-" and add aliases to all of the filesystems that can be built as modules to match. A common practice is to build all of the kernel code and leave code that is not commonly needed as modules, with the result that many users are exposed to any bug anywhere in the kernel. Looking for filesystems with a fs- prefix limits the pool of possible modules that can be loaded by mount to just filesystems trivially making things safer with no real cost. Using aliases means user space can control the policy of which filesystem modules are auto-loaded by editing /etc/modprobe.d/*.conf with blacklist and alias directives. Allowing simple, safe, well understood work-arounds to known problematic software. This also addresses a rare but unfortunate problem where the filesystem name is not the same as it's module name and module auto-loading would not work. While writing this patch I saw a handful of such cases. The most significant being autofs that lives in the module autofs4. This is relevant to user namespaces because we can reach the request module in get_fs_type() without having any special permissions, and people get uncomfortable when a user specified string (in this case the filesystem type) goes all of the way to request_module. After having looked at this issue I don't think there is any particular reason to perform any filtering or permission checks beyond making it clear in the module request that we want a filesystem module. The common pattern in the kernel is to call request_module() without regards to the users permissions. In general all a filesystem module does once loaded is call register_filesystem() and go to sleep. Which means there is not much attack surface exposed by loading a filesytem module unless the filesystem is mounted. In a user namespace filesystems are not mounted unless .fs_flags = FS_USERNS_MOUNT, which most filesystems do not set today. Acked-by: Serge Hallyn <serge.hallyn@canonical.com> Acked-by: Kees Cook <keescook@chromium.org> Reported-by: Kees Cook <keescook@google.com> Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
2013-03-03 11:39:14 +08:00
MODULE_ALIAS_FS("ext3");
MODULE_ALIAS("ext3");
#define IS_EXT3_SB(sb) ((sb)->s_bdev->bd_holder == &ext3_fs_type)
static int ext4_verify_csum_type(struct super_block *sb,
struct ext4_super_block *es)
{
if (!ext4_has_feature_metadata_csum(sb))
return 1;
return es->s_checksum_type == EXT4_CRC32C_CHKSUM;
}
static __le32 ext4_superblock_csum(struct super_block *sb,
struct ext4_super_block *es)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
int offset = offsetof(struct ext4_super_block, s_checksum);
__u32 csum;
csum = ext4_chksum(sbi, ~0, (char *)es, offset);
return cpu_to_le32(csum);
}
static int ext4_superblock_csum_verify(struct super_block *sb,
struct ext4_super_block *es)
{
if (!ext4_has_metadata_csum(sb))
return 1;
return es->s_checksum == ext4_superblock_csum(sb, es);
}
void ext4_superblock_csum_set(struct super_block *sb)
{
struct ext4_super_block *es = EXT4_SB(sb)->s_es;
if (!ext4_has_metadata_csum(sb))
return;
es->s_checksum = ext4_superblock_csum(sb, es);
}
void *ext4_kvmalloc(size_t size, gfp_t flags)
{
void *ret;
ret = kmalloc(size, flags | __GFP_NOWARN);
if (!ret)
ret = __vmalloc(size, flags, PAGE_KERNEL);
return ret;
}
void *ext4_kvzalloc(size_t size, gfp_t flags)
{
void *ret;
ret = kzalloc(size, flags | __GFP_NOWARN);
if (!ret)
ret = __vmalloc(size, flags | __GFP_ZERO, PAGE_KERNEL);
return ret;
}
ext4_fsblk_t ext4_block_bitmap(struct super_block *sb,
struct ext4_group_desc *bg)
{
return le32_to_cpu(bg->bg_block_bitmap_lo) |
(EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ?
(ext4_fsblk_t)le32_to_cpu(bg->bg_block_bitmap_hi) << 32 : 0);
}
ext4_fsblk_t ext4_inode_bitmap(struct super_block *sb,
struct ext4_group_desc *bg)
{
return le32_to_cpu(bg->bg_inode_bitmap_lo) |
(EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ?
(ext4_fsblk_t)le32_to_cpu(bg->bg_inode_bitmap_hi) << 32 : 0);
}
ext4_fsblk_t ext4_inode_table(struct super_block *sb,
struct ext4_group_desc *bg)
{
return le32_to_cpu(bg->bg_inode_table_lo) |
(EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ?
(ext4_fsblk_t)le32_to_cpu(bg->bg_inode_table_hi) << 32 : 0);
}
__u32 ext4_free_group_clusters(struct super_block *sb,
struct ext4_group_desc *bg)
{
return le16_to_cpu(bg->bg_free_blocks_count_lo) |
(EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ?
(__u32)le16_to_cpu(bg->bg_free_blocks_count_hi) << 16 : 0);
}
__u32 ext4_free_inodes_count(struct super_block *sb,
struct ext4_group_desc *bg)
{
return le16_to_cpu(bg->bg_free_inodes_count_lo) |
(EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ?
(__u32)le16_to_cpu(bg->bg_free_inodes_count_hi) << 16 : 0);
}
__u32 ext4_used_dirs_count(struct super_block *sb,
struct ext4_group_desc *bg)
{
return le16_to_cpu(bg->bg_used_dirs_count_lo) |
(EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ?
(__u32)le16_to_cpu(bg->bg_used_dirs_count_hi) << 16 : 0);
}
__u32 ext4_itable_unused_count(struct super_block *sb,
struct ext4_group_desc *bg)
{
return le16_to_cpu(bg->bg_itable_unused_lo) |
(EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ?
(__u32)le16_to_cpu(bg->bg_itable_unused_hi) << 16 : 0);
}
void ext4_block_bitmap_set(struct super_block *sb,
struct ext4_group_desc *bg, ext4_fsblk_t blk)
{
bg->bg_block_bitmap_lo = cpu_to_le32((u32)blk);
if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT)
bg->bg_block_bitmap_hi = cpu_to_le32(blk >> 32);
}
void ext4_inode_bitmap_set(struct super_block *sb,
struct ext4_group_desc *bg, ext4_fsblk_t blk)
{
bg->bg_inode_bitmap_lo = cpu_to_le32((u32)blk);
if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT)
bg->bg_inode_bitmap_hi = cpu_to_le32(blk >> 32);
}
void ext4_inode_table_set(struct super_block *sb,
struct ext4_group_desc *bg, ext4_fsblk_t blk)
{
bg->bg_inode_table_lo = cpu_to_le32((u32)blk);
if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT)
bg->bg_inode_table_hi = cpu_to_le32(blk >> 32);
}
void ext4_free_group_clusters_set(struct super_block *sb,
struct ext4_group_desc *bg, __u32 count)
{
bg->bg_free_blocks_count_lo = cpu_to_le16((__u16)count);
if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT)
bg->bg_free_blocks_count_hi = cpu_to_le16(count >> 16);
}
void ext4_free_inodes_set(struct super_block *sb,
struct ext4_group_desc *bg, __u32 count)
{
bg->bg_free_inodes_count_lo = cpu_to_le16((__u16)count);
if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT)
bg->bg_free_inodes_count_hi = cpu_to_le16(count >> 16);
}
void ext4_used_dirs_set(struct super_block *sb,
struct ext4_group_desc *bg, __u32 count)
{
bg->bg_used_dirs_count_lo = cpu_to_le16((__u16)count);
if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT)
bg->bg_used_dirs_count_hi = cpu_to_le16(count >> 16);
}
void ext4_itable_unused_set(struct super_block *sb,
struct ext4_group_desc *bg, __u32 count)
{
bg->bg_itable_unused_lo = cpu_to_le16((__u16)count);
if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT)
bg->bg_itable_unused_hi = cpu_to_le16(count >> 16);
}
static void __save_error_info(struct super_block *sb, const char *func,
unsigned int line)
{
struct ext4_super_block *es = EXT4_SB(sb)->s_es;
EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
if (bdev_read_only(sb->s_bdev))
return;
es->s_state |= cpu_to_le16(EXT4_ERROR_FS);
es->s_last_error_time = cpu_to_le32(get_seconds());
strncpy(es->s_last_error_func, func, sizeof(es->s_last_error_func));
es->s_last_error_line = cpu_to_le32(line);
if (!es->s_first_error_time) {
es->s_first_error_time = es->s_last_error_time;
strncpy(es->s_first_error_func, func,
sizeof(es->s_first_error_func));
es->s_first_error_line = cpu_to_le32(line);
es->s_first_error_ino = es->s_last_error_ino;
es->s_first_error_block = es->s_last_error_block;
}
/*
* Start the daily error reporting function if it hasn't been
* started already
*/
if (!es->s_error_count)
mod_timer(&EXT4_SB(sb)->s_err_report, jiffies + 24*60*60*HZ);
le32_add_cpu(&es->s_error_count, 1);
}
static void save_error_info(struct super_block *sb, const char *func,
unsigned int line)
{
__save_error_info(sb, func, line);
ext4_commit_super(sb, 1);
}
Revert "ext4: remove block_device_ejected" This reverts commit 08439fec266c3cc5702953b4f54bdf5649357de0. Unfortunately we still need to test for bdi->dev to avoid a crash when a USB stick is yanked out while a file system is mounted: usb 2-2: USB disconnect, device number 2 Buffer I/O error on dev sdb1, logical block 15237120, lost sync page write JBD2: Error -5 detected when updating journal superblock for sdb1-8. BUG: unable to handle kernel paging request at 34beb000 IP: [<c136ce88>] __percpu_counter_add+0x18/0xc0 *pdpt = 0000000023db9001 *pde = 0000000000000000 Oops: 0000 [#1] SMP CPU: 0 PID: 4083 Comm: umount Tainted: G U OE 4.1.1-040101-generic #201507011435 Hardware name: LENOVO 7675CTO/7675CTO, BIOS 7NETC2WW (2.22 ) 03/22/2011 task: ebf06b50 ti: ebebc000 task.ti: ebebc000 EIP: 0060:[<c136ce88>] EFLAGS: 00010082 CPU: 0 EIP is at __percpu_counter_add+0x18/0xc0 EAX: f21c8e88 EBX: f21c8e88 ECX: 00000000 EDX: 00000001 ESI: 00000001 EDI: 00000000 EBP: ebebde60 ESP: ebebde40 DS: 007b ES: 007b FS: 00d8 GS: 00e0 SS: 0068 CR0: 8005003b CR2: 34beb000 CR3: 33354200 CR4: 000007f0 Stack: c1abe100 edcb0098 edcb00ec ffffffff f21c8e68 ffffffff f21c8e68 f286d160 ebebde84 c1160454 00000010 00000282 f72a77f8 00000984 f72a77f8 f286d160 f286d170 ebebdea0 c11e613f 00000000 00000282 f72a77f8 edd7f4d0 00000000 Call Trace: [<c1160454>] account_page_dirtied+0x74/0x110 [<c11e613f>] __set_page_dirty+0x3f/0xb0 [<c11e6203>] mark_buffer_dirty+0x53/0xc0 [<c124a0cb>] ext4_commit_super+0x17b/0x250 [<c124ac71>] ext4_put_super+0xc1/0x320 [<c11f04ba>] ? fsnotify_unmount_inodes+0x1aa/0x1c0 [<c11cfeda>] ? evict_inodes+0xca/0xe0 [<c11b925a>] generic_shutdown_super+0x6a/0xe0 [<c10a1df0>] ? prepare_to_wait_event+0xd0/0xd0 [<c1165a50>] ? unregister_shrinker+0x40/0x50 [<c11b92f6>] kill_block_super+0x26/0x70 [<c11b94f5>] deactivate_locked_super+0x45/0x80 [<c11ba007>] deactivate_super+0x47/0x60 [<c11d2b39>] cleanup_mnt+0x39/0x80 [<c11d2bc0>] __cleanup_mnt+0x10/0x20 [<c1080b51>] task_work_run+0x91/0xd0 [<c1011e3c>] do_notify_resume+0x7c/0x90 [<c1720da5>] work_notify Code: 8b 55 e8 e9 f4 fe ff ff 90 90 90 90 90 90 90 90 90 90 90 55 89 e5 83 ec 20 89 5d f4 89 c3 89 75 f8 89 d6 89 7d fc 89 cf 8b 48 14 <64> 8b 01 89 45 ec 89 c2 8b 45 08 c1 fa 1f 01 75 ec 89 55 f0 89 EIP: [<c136ce88>] __percpu_counter_add+0x18/0xc0 SS:ESP 0068:ebebde40 CR2: 0000000034beb000 ---[ end trace dd564a7bea834ecd ]--- Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=101011 Signed-off-by: Theodore Ts'o <tytso@mit.edu> Cc: stable@vger.kernel.org
2015-08-16 22:03:57 +08:00
/*
* The del_gendisk() function uninitializes the disk-specific data
* structures, including the bdi structure, without telling anyone
* else. Once this happens, any attempt to call mark_buffer_dirty()
* (for example, by ext4_commit_super), will cause a kernel OOPS.
* This is a kludge to prevent these oops until we can put in a proper
* hook in del_gendisk() to inform the VFS and file system layers.
*/
static int block_device_ejected(struct super_block *sb)
{
struct inode *bd_inode = sb->s_bdev->bd_inode;
struct backing_dev_info *bdi = inode_to_bdi(bd_inode);
return bdi->dev == NULL;
}
static void ext4_journal_commit_callback(journal_t *journal, transaction_t *txn)
{
struct super_block *sb = journal->j_private;
struct ext4_sb_info *sbi = EXT4_SB(sb);
int error = is_journal_aborted(journal);
ext4: fix journal callback list traversal It is incorrect to use list_for_each_entry_safe() for journal callback traversial because ->next may be removed by other task: ->ext4_mb_free_metadata() ->ext4_mb_free_metadata() ->ext4_journal_callback_del() This results in the following issue: WARNING: at lib/list_debug.c:62 __list_del_entry+0x1c0/0x250() Hardware name: list_del corruption. prev->next should be ffff88019a4ec198, but was 6b6b6b6b6b6b6b6b Modules linked in: cpufreq_ondemand acpi_cpufreq freq_table mperf coretemp kvm_intel kvm crc32c_intel ghash_clmulni_intel microcode sg xhci_hcd button sd_mod crc_t10dif aesni_intel ablk_helper cryptd lrw aes_x86_64 xts gf128mul ahci libahci pata_acpi ata_generic dm_mirror dm_region_hash dm_log dm_mod Pid: 16400, comm: jbd2/dm-1-8 Tainted: G W 3.8.0-rc3+ #107 Call Trace: [<ffffffff8106fb0d>] warn_slowpath_common+0xad/0xf0 [<ffffffff8106fc06>] warn_slowpath_fmt+0x46/0x50 [<ffffffff813637e9>] ? ext4_journal_commit_callback+0x99/0xc0 [<ffffffff8148cae0>] __list_del_entry+0x1c0/0x250 [<ffffffff813637bf>] ext4_journal_commit_callback+0x6f/0xc0 [<ffffffff813ca336>] jbd2_journal_commit_transaction+0x23a6/0x2570 [<ffffffff8108aa42>] ? try_to_del_timer_sync+0x82/0xa0 [<ffffffff8108b491>] ? del_timer_sync+0x91/0x1e0 [<ffffffff813d3ecf>] kjournald2+0x19f/0x6a0 [<ffffffff810ad630>] ? wake_up_bit+0x40/0x40 [<ffffffff813d3d30>] ? bit_spin_lock+0x80/0x80 [<ffffffff810ac6be>] kthread+0x10e/0x120 [<ffffffff810ac5b0>] ? __init_kthread_worker+0x70/0x70 [<ffffffff818ff6ac>] ret_from_fork+0x7c/0xb0 [<ffffffff810ac5b0>] ? __init_kthread_worker+0x70/0x70 This patch fix the issue as follows: - ext4_journal_commit_callback() make list truly traversial safe simply by always starting from list_head - fix race between two ext4_journal_callback_del() and ext4_journal_callback_try_del() Signed-off-by: Dmitry Monakhov <dmonakhov@openvz.org> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu> Reviewed-by: Jan Kara <jack@suse.cz> Cc: stable@vger.kernel.com
2013-04-04 10:08:52 +08:00
struct ext4_journal_cb_entry *jce;
ext4: fix journal callback list traversal It is incorrect to use list_for_each_entry_safe() for journal callback traversial because ->next may be removed by other task: ->ext4_mb_free_metadata() ->ext4_mb_free_metadata() ->ext4_journal_callback_del() This results in the following issue: WARNING: at lib/list_debug.c:62 __list_del_entry+0x1c0/0x250() Hardware name: list_del corruption. prev->next should be ffff88019a4ec198, but was 6b6b6b6b6b6b6b6b Modules linked in: cpufreq_ondemand acpi_cpufreq freq_table mperf coretemp kvm_intel kvm crc32c_intel ghash_clmulni_intel microcode sg xhci_hcd button sd_mod crc_t10dif aesni_intel ablk_helper cryptd lrw aes_x86_64 xts gf128mul ahci libahci pata_acpi ata_generic dm_mirror dm_region_hash dm_log dm_mod Pid: 16400, comm: jbd2/dm-1-8 Tainted: G W 3.8.0-rc3+ #107 Call Trace: [<ffffffff8106fb0d>] warn_slowpath_common+0xad/0xf0 [<ffffffff8106fc06>] warn_slowpath_fmt+0x46/0x50 [<ffffffff813637e9>] ? ext4_journal_commit_callback+0x99/0xc0 [<ffffffff8148cae0>] __list_del_entry+0x1c0/0x250 [<ffffffff813637bf>] ext4_journal_commit_callback+0x6f/0xc0 [<ffffffff813ca336>] jbd2_journal_commit_transaction+0x23a6/0x2570 [<ffffffff8108aa42>] ? try_to_del_timer_sync+0x82/0xa0 [<ffffffff8108b491>] ? del_timer_sync+0x91/0x1e0 [<ffffffff813d3ecf>] kjournald2+0x19f/0x6a0 [<ffffffff810ad630>] ? wake_up_bit+0x40/0x40 [<ffffffff813d3d30>] ? bit_spin_lock+0x80/0x80 [<ffffffff810ac6be>] kthread+0x10e/0x120 [<ffffffff810ac5b0>] ? __init_kthread_worker+0x70/0x70 [<ffffffff818ff6ac>] ret_from_fork+0x7c/0xb0 [<ffffffff810ac5b0>] ? __init_kthread_worker+0x70/0x70 This patch fix the issue as follows: - ext4_journal_commit_callback() make list truly traversial safe simply by always starting from list_head - fix race between two ext4_journal_callback_del() and ext4_journal_callback_try_del() Signed-off-by: Dmitry Monakhov <dmonakhov@openvz.org> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu> Reviewed-by: Jan Kara <jack@suse.cz> Cc: stable@vger.kernel.com
2013-04-04 10:08:52 +08:00
BUG_ON(txn->t_state == T_FINISHED);
spin_lock(&sbi->s_md_lock);
ext4: fix journal callback list traversal It is incorrect to use list_for_each_entry_safe() for journal callback traversial because ->next may be removed by other task: ->ext4_mb_free_metadata() ->ext4_mb_free_metadata() ->ext4_journal_callback_del() This results in the following issue: WARNING: at lib/list_debug.c:62 __list_del_entry+0x1c0/0x250() Hardware name: list_del corruption. prev->next should be ffff88019a4ec198, but was 6b6b6b6b6b6b6b6b Modules linked in: cpufreq_ondemand acpi_cpufreq freq_table mperf coretemp kvm_intel kvm crc32c_intel ghash_clmulni_intel microcode sg xhci_hcd button sd_mod crc_t10dif aesni_intel ablk_helper cryptd lrw aes_x86_64 xts gf128mul ahci libahci pata_acpi ata_generic dm_mirror dm_region_hash dm_log dm_mod Pid: 16400, comm: jbd2/dm-1-8 Tainted: G W 3.8.0-rc3+ #107 Call Trace: [<ffffffff8106fb0d>] warn_slowpath_common+0xad/0xf0 [<ffffffff8106fc06>] warn_slowpath_fmt+0x46/0x50 [<ffffffff813637e9>] ? ext4_journal_commit_callback+0x99/0xc0 [<ffffffff8148cae0>] __list_del_entry+0x1c0/0x250 [<ffffffff813637bf>] ext4_journal_commit_callback+0x6f/0xc0 [<ffffffff813ca336>] jbd2_journal_commit_transaction+0x23a6/0x2570 [<ffffffff8108aa42>] ? try_to_del_timer_sync+0x82/0xa0 [<ffffffff8108b491>] ? del_timer_sync+0x91/0x1e0 [<ffffffff813d3ecf>] kjournald2+0x19f/0x6a0 [<ffffffff810ad630>] ? wake_up_bit+0x40/0x40 [<ffffffff813d3d30>] ? bit_spin_lock+0x80/0x80 [<ffffffff810ac6be>] kthread+0x10e/0x120 [<ffffffff810ac5b0>] ? __init_kthread_worker+0x70/0x70 [<ffffffff818ff6ac>] ret_from_fork+0x7c/0xb0 [<ffffffff810ac5b0>] ? __init_kthread_worker+0x70/0x70 This patch fix the issue as follows: - ext4_journal_commit_callback() make list truly traversial safe simply by always starting from list_head - fix race between two ext4_journal_callback_del() and ext4_journal_callback_try_del() Signed-off-by: Dmitry Monakhov <dmonakhov@openvz.org> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu> Reviewed-by: Jan Kara <jack@suse.cz> Cc: stable@vger.kernel.com
2013-04-04 10:08:52 +08:00
while (!list_empty(&txn->t_private_list)) {
jce = list_entry(txn->t_private_list.next,
struct ext4_journal_cb_entry, jce_list);
list_del_init(&jce->jce_list);
spin_unlock(&sbi->s_md_lock);
jce->jce_func(sb, jce, error);
spin_lock(&sbi->s_md_lock);
}
spin_unlock(&sbi->s_md_lock);
}
/* Deal with the reporting of failure conditions on a filesystem such as
* inconsistencies detected or read IO failures.
*
* On ext2, we can store the error state of the filesystem in the
* superblock. That is not possible on ext4, because we may have other
* write ordering constraints on the superblock which prevent us from
* writing it out straight away; and given that the journal is about to
* be aborted, we can't rely on the current, or future, transactions to
* write out the superblock safely.
*
* We'll just use the jbd2_journal_abort() error code to record an error in
* the journal instead. On recovery, the journal will complain about
* that error until we've noted it down and cleared it.
*/
static void ext4_handle_error(struct super_block *sb)
{
if (sb->s_flags & MS_RDONLY)
return;
if (!test_opt(sb, ERRORS_CONT)) {
journal_t *journal = EXT4_SB(sb)->s_journal;
EXT4_SB(sb)->s_mount_flags |= EXT4_MF_FS_ABORTED;
if (journal)
jbd2_journal_abort(journal, -EIO);
}
if (test_opt(sb, ERRORS_RO)) {
ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only");
/*
* Make sure updated value of ->s_mount_flags will be visible
* before ->s_flags update
*/
smp_wmb();
sb->s_flags |= MS_RDONLY;
}
if (test_opt(sb, ERRORS_PANIC)) {
if (EXT4_SB(sb)->s_journal &&
!(EXT4_SB(sb)->s_journal->j_flags & JBD2_REC_ERR))
return;
panic("EXT4-fs (device %s): panic forced after error\n",
sb->s_id);
}
}
#define ext4_error_ratelimit(sb) \
___ratelimit(&(EXT4_SB(sb)->s_err_ratelimit_state), \
"EXT4-fs error")
void __ext4_error(struct super_block *sb, const char *function,
unsigned int line, const char *fmt, ...)
{
struct va_format vaf;
va_list args;
if (ext4_error_ratelimit(sb)) {
va_start(args, fmt);
vaf.fmt = fmt;
vaf.va = &args;
printk(KERN_CRIT
"EXT4-fs error (device %s): %s:%d: comm %s: %pV\n",
sb->s_id, function, line, current->comm, &vaf);
va_end(args);
}
save_error_info(sb, function, line);
ext4_handle_error(sb);
}
void __ext4_error_inode(struct inode *inode, const char *function,
unsigned int line, ext4_fsblk_t block,
const char *fmt, ...)
{
va_list args;
struct va_format vaf;
struct ext4_super_block *es = EXT4_SB(inode->i_sb)->s_es;
es->s_last_error_ino = cpu_to_le32(inode->i_ino);
es->s_last_error_block = cpu_to_le64(block);
if (ext4_error_ratelimit(inode->i_sb)) {
va_start(args, fmt);
vaf.fmt = fmt;
vaf.va = &args;
if (block)
printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: "
"inode #%lu: block %llu: comm %s: %pV\n",
inode->i_sb->s_id, function, line, inode->i_ino,
block, current->comm, &vaf);
else
printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: "
"inode #%lu: comm %s: %pV\n",
inode->i_sb->s_id, function, line, inode->i_ino,
current->comm, &vaf);
va_end(args);
}
save_error_info(inode->i_sb, function, line);
ext4_handle_error(inode->i_sb);
}
void __ext4_error_file(struct file *file, const char *function,
unsigned int line, ext4_fsblk_t block,
const char *fmt, ...)
{
va_list args;
struct va_format vaf;
struct ext4_super_block *es;
struct inode *inode = file_inode(file);
char pathname[80], *path;
es = EXT4_SB(inode->i_sb)->s_es;
es->s_last_error_ino = cpu_to_le32(inode->i_ino);
if (ext4_error_ratelimit(inode->i_sb)) {
path = file_path(file, pathname, sizeof(pathname));
if (IS_ERR(path))
path = "(unknown)";
va_start(args, fmt);
vaf.fmt = fmt;
vaf.va = &args;
if (block)
printk(KERN_CRIT
"EXT4-fs error (device %s): %s:%d: inode #%lu: "
"block %llu: comm %s: path %s: %pV\n",
inode->i_sb->s_id, function, line, inode->i_ino,
block, current->comm, path, &vaf);
else
printk(KERN_CRIT
"EXT4-fs error (device %s): %s:%d: inode #%lu: "
"comm %s: path %s: %pV\n",
inode->i_sb->s_id, function, line, inode->i_ino,
current->comm, path, &vaf);
va_end(args);
}
save_error_info(inode->i_sb, function, line);
ext4_handle_error(inode->i_sb);
}
const char *ext4_decode_error(struct super_block *sb, int errno,
char nbuf[16])
{
char *errstr = NULL;
switch (errno) {
case -EFSCORRUPTED:
errstr = "Corrupt filesystem";
break;
case -EFSBADCRC:
errstr = "Filesystem failed CRC";
break;
case -EIO:
errstr = "IO failure";
break;
case -ENOMEM:
errstr = "Out of memory";
break;
case -EROFS:
if (!sb || (EXT4_SB(sb)->s_journal &&
EXT4_SB(sb)->s_journal->j_flags & JBD2_ABORT))
errstr = "Journal has aborted";
else
errstr = "Readonly filesystem";
break;
default:
/* If the caller passed in an extra buffer for unknown
* errors, textualise them now. Else we just return
* NULL. */
if (nbuf) {
/* Check for truncated error codes... */
if (snprintf(nbuf, 16, "error %d", -errno) >= 0)
errstr = nbuf;
}
break;
}
return errstr;
}
/* __ext4_std_error decodes expected errors from journaling functions
* automatically and invokes the appropriate error response. */
void __ext4_std_error(struct super_block *sb, const char *function,
unsigned int line, int errno)
{
char nbuf[16];
const char *errstr;
/* Special case: if the error is EROFS, and we're not already
* inside a transaction, then there's really no point in logging
* an error. */
if (errno == -EROFS && journal_current_handle() == NULL &&
(sb->s_flags & MS_RDONLY))
return;
if (ext4_error_ratelimit(sb)) {
errstr = ext4_decode_error(sb, errno, nbuf);
printk(KERN_CRIT "EXT4-fs error (device %s) in %s:%d: %s\n",
sb->s_id, function, line, errstr);
}
save_error_info(sb, function, line);
ext4_handle_error(sb);
}
/*
* ext4_abort is a much stronger failure handler than ext4_error. The
* abort function may be used to deal with unrecoverable failures such
* as journal IO errors or ENOMEM at a critical moment in log management.
*
* We unconditionally force the filesystem into an ABORT|READONLY state,
* unless the error response on the fs has been set to panic in which
* case we take the easy way out and panic immediately.
*/
void __ext4_abort(struct super_block *sb, const char *function,
unsigned int line, const char *fmt, ...)
{
struct va_format vaf;
va_list args;
save_error_info(sb, function, line);
va_start(args, fmt);
vaf.fmt = fmt;
vaf.va = &args;
printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: %pV\n",
sb->s_id, function, line, &vaf);
va_end(args);
if ((sb->s_flags & MS_RDONLY) == 0) {
ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only");
EXT4_SB(sb)->s_mount_flags |= EXT4_MF_FS_ABORTED;
/*
* Make sure updated value of ->s_mount_flags will be visible
* before ->s_flags update
*/
smp_wmb();
sb->s_flags |= MS_RDONLY;
if (EXT4_SB(sb)->s_journal)
jbd2_journal_abort(EXT4_SB(sb)->s_journal, -EIO);
save_error_info(sb, function, line);
}
if (test_opt(sb, ERRORS_PANIC)) {
if (EXT4_SB(sb)->s_journal &&
!(EXT4_SB(sb)->s_journal->j_flags & JBD2_REC_ERR))
return;
panic("EXT4-fs panic from previous error\n");
}
}
void __ext4_msg(struct super_block *sb,
const char *prefix, const char *fmt, ...)
{
struct va_format vaf;
va_list args;
if (!___ratelimit(&(EXT4_SB(sb)->s_msg_ratelimit_state), "EXT4-fs"))
return;
va_start(args, fmt);
vaf.fmt = fmt;
vaf.va = &args;
printk("%sEXT4-fs (%s): %pV\n", prefix, sb->s_id, &vaf);
va_end(args);
}
#define ext4_warning_ratelimit(sb) \
___ratelimit(&(EXT4_SB(sb)->s_warning_ratelimit_state), \
"EXT4-fs warning")
void __ext4_warning(struct super_block *sb, const char *function,
unsigned int line, const char *fmt, ...)
{
struct va_format vaf;
va_list args;
if (!ext4_warning_ratelimit(sb))
return;
va_start(args, fmt);
vaf.fmt = fmt;
vaf.va = &args;
printk(KERN_WARNING "EXT4-fs warning (device %s): %s:%d: %pV\n",
sb->s_id, function, line, &vaf);
va_end(args);
}
void __ext4_warning_inode(const struct inode *inode, const char *function,
unsigned int line, const char *fmt, ...)
{
struct va_format vaf;
va_list args;
if (!ext4_warning_ratelimit(inode->i_sb))
return;
va_start(args, fmt);
vaf.fmt = fmt;
vaf.va = &args;
printk(KERN_WARNING "EXT4-fs warning (device %s): %s:%d: "
"inode #%lu: comm %s: %pV\n", inode->i_sb->s_id,
function, line, inode->i_ino, current->comm, &vaf);
va_end(args);
}
void __ext4_grp_locked_error(const char *function, unsigned int line,
struct super_block *sb, ext4_group_t grp,
unsigned long ino, ext4_fsblk_t block,
const char *fmt, ...)
__releases(bitlock)
__acquires(bitlock)
{
struct va_format vaf;
va_list args;
struct ext4_super_block *es = EXT4_SB(sb)->s_es;
es->s_last_error_ino = cpu_to_le32(ino);
es->s_last_error_block = cpu_to_le64(block);
__save_error_info(sb, function, line);
if (ext4_error_ratelimit(sb)) {
va_start(args, fmt);
vaf.fmt = fmt;
vaf.va = &args;
printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: group %u, ",
sb->s_id, function, line, grp);
if (ino)
printk(KERN_CONT "inode %lu: ", ino);
if (block)
printk(KERN_CONT "block %llu:",
(unsigned long long) block);
printk(KERN_CONT "%pV\n", &vaf);
va_end(args);
}
if (test_opt(sb, ERRORS_CONT)) {
ext4_commit_super(sb, 0);
return;
}
ext4_unlock_group(sb, grp);
ext4_handle_error(sb);
/*
* We only get here in the ERRORS_RO case; relocking the group
* may be dangerous, but nothing bad will happen since the
* filesystem will have already been marked read/only and the
* journal has been aborted. We return 1 as a hint to callers
* who might what to use the return value from
* ext4_grp_locked_error() to distinguish between the
* ERRORS_CONT and ERRORS_RO case, and perhaps return more
* aggressively from the ext4 function in question, with a
* more appropriate error code.
*/
ext4_lock_group(sb, grp);
return;
}
void ext4_update_dynamic_rev(struct super_block *sb)
{
struct ext4_super_block *es = EXT4_SB(sb)->s_es;
if (le32_to_cpu(es->s_rev_level) > EXT4_GOOD_OLD_REV)
return;
ext4_warning(sb,
"updating to rev %d because of new feature flag, "
"running e2fsck is recommended",
EXT4_DYNAMIC_REV);
es->s_first_ino = cpu_to_le32(EXT4_GOOD_OLD_FIRST_INO);
es->s_inode_size = cpu_to_le16(EXT4_GOOD_OLD_INODE_SIZE);
es->s_rev_level = cpu_to_le32(EXT4_DYNAMIC_REV);
/* leave es->s_feature_*compat flags alone */
/* es->s_uuid will be set by e2fsck if empty */
/*
* The rest of the superblock fields should be zero, and if not it
* means they are likely already in use, so leave them alone. We
* can leave it up to e2fsck to clean up any inconsistencies there.
*/
}
/*
* Open the external journal device
*/
static struct block_device *ext4_blkdev_get(dev_t dev, struct super_block *sb)
{
struct block_device *bdev;
char b[BDEVNAME_SIZE];
bdev = blkdev_get_by_dev(dev, FMODE_READ|FMODE_WRITE|FMODE_EXCL, sb);
if (IS_ERR(bdev))
goto fail;
return bdev;
fail:
ext4_msg(sb, KERN_ERR, "failed to open journal device %s: %ld",
__bdevname(dev, b), PTR_ERR(bdev));
return NULL;
}
/*
* Release the journal device
*/
static void ext4_blkdev_put(struct block_device *bdev)
{
blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL);
}
static void ext4_blkdev_remove(struct ext4_sb_info *sbi)
{
struct block_device *bdev;
bdev = sbi->journal_bdev;
if (bdev) {
ext4_blkdev_put(bdev);
sbi->journal_bdev = NULL;
}
}
static inline struct inode *orphan_list_entry(struct list_head *l)
{
return &list_entry(l, struct ext4_inode_info, i_orphan)->vfs_inode;
}
static void dump_orphan_list(struct super_block *sb, struct ext4_sb_info *sbi)
{
struct list_head *l;
ext4_msg(sb, KERN_ERR, "sb orphan head is %d",
le32_to_cpu(sbi->s_es->s_last_orphan));
printk(KERN_ERR "sb_info orphan list:\n");
list_for_each(l, &sbi->s_orphan) {
struct inode *inode = orphan_list_entry(l);
printk(KERN_ERR " "
"inode %s:%lu at %p: mode %o, nlink %d, next %d\n",
inode->i_sb->s_id, inode->i_ino, inode,
inode->i_mode, inode->i_nlink,
NEXT_ORPHAN(inode));
}
}
static void ext4_put_super(struct super_block *sb)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
struct ext4_super_block *es = sbi->s_es;
int i, err;
ext4_unregister_li_request(sb);
dquot_disable(sb, -1, DQUOT_USAGE_ENABLED | DQUOT_LIMITS_ENABLED);
flush_workqueue(sbi->rsv_conversion_wq);
destroy_workqueue(sbi->rsv_conversion_wq);
if (sbi->s_journal) {
err = jbd2_journal_destroy(sbi->s_journal);
sbi->s_journal = NULL;
if (err < 0)
ext4_abort(sb, "Couldn't clean up the journal");
}
ext4_unregister_sysfs(sb);
ext4: improve extent cache shrink mechanism to avoid to burn CPU time Now we maintain an proper in-order LRU list in ext4 to reclaim entries from extent status tree when we are under heavy memory pressure. For keeping this order, a spin lock is used to protect this list. But this lock burns a lot of CPU time. We can use the following steps to trigger it. % cd /dev/shm % dd if=/dev/zero of=ext4-img bs=1M count=2k % mkfs.ext4 ext4-img % mount -t ext4 -o loop ext4-img /mnt % cd /mnt % for ((i=0;i<160;i++)); do truncate -s 64g $i; done % for ((i=0;i<160;i++)); do cp $i /dev/null &; done % perf record -a -g % perf report This commit tries to fix this problem. Now a new member called i_touch_when is added into ext4_inode_info to record the last access time for an inode. Meanwhile we never need to keep a proper in-order LRU list. So this can avoid to burns some CPU time. When we try to reclaim some entries from extent status tree, we use list_sort() to get a proper in-order list. Then we traverse this list to discard some entries. In ext4_sb_info, we use s_es_last_sorted to record the last time of sorting this list. When we traverse the list, we skip the inode that is newer than this time, and move this inode to the tail of LRU list. When the head of the list is newer than s_es_last_sorted, we will sort the LRU list again. In this commit, we break the loop if s_extent_cache_cnt == 0 because that means that all extents in extent status tree have been reclaimed. Meanwhile in this commit, ext4_es_{un}register_shrinker()'s prototype is changed to save a local variable in these functions. Reported-by: Dave Hansen <dave.hansen@intel.com> Signed-off-by: Zheng Liu <wenqing.lz@taobao.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2013-07-01 20:12:37 +08:00
ext4_es_unregister_shrinker(sbi);
del_timer_sync(&sbi->s_err_report);
ext4_release_system_zone(sb);
ext4_mb_release(sb);
ext4_ext_release(sb);
if (!(sb->s_flags & MS_RDONLY)) {
ext4_clear_feature_journal_needs_recovery(sb);
es->s_state = cpu_to_le16(sbi->s_mount_state);
}
ext4: remove unnecessary superblock dirtying This patch changes the 'ext4_handle_dirty_super()' function which submits the superblock for I/O in the following cases: 1. When creating the first large file on a file system without EXT4_FEATURE_RO_COMPAT_LARGE_FILE feature. 2. When re-sizing the file-system. 3. When creating an xattr on a file-system without the EXT4_FEATURE_COMPAT_EXT_ATTR feature. If the file-system has journal enabled, the superblock is written via the journal. We do not modify this path. If the file-system has no journal, this function, falls back to just marking the superblock as dirty using the 's_dirt' superblock flag. This means that it delays the actual superblock I/O submission by 5 seconds (default setting). Namely, the 'sync_supers()' kernel thread will call 'ext4_write_super()' later and will actually submit the superblock for I/O. And this is the behavior this patch modifies: we stop using 's_dirt' and just mark the superblock buffer as dirty right away. Indeed, all 3 cases above are extremely rare and it does not add any value to delay the I/O submission for them. Note: 'ext4_handle_dirty_super()' executes '__ext4_handle_dirty_super()' with 'now = 0'. This patch basically makes the 'now' argument unneeded and it will be deleted in one of the next patches. This patch also removes 's_dirt' condition on the unmount path because we never set it anymore, so we should not test it. Tested using xfstests for both journalled and non-journalled ext4. Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu> Reviewed-by: Jan Kara <jack@suse.cz>
2012-07-23 08:33:31 +08:00
if (!(sb->s_flags & MS_RDONLY))
ext4_commit_super(sb, 1);
for (i = 0; i < sbi->s_gdb_count; i++)
brelse(sbi->s_group_desc[i]);
kvfree(sbi->s_group_desc);
kvfree(sbi->s_flex_groups);
percpu_counter_destroy(&sbi->s_freeclusters_counter);
percpu_counter_destroy(&sbi->s_freeinodes_counter);
percpu_counter_destroy(&sbi->s_dirs_counter);
percpu_counter_destroy(&sbi->s_dirtyclusters_counter);
percpu_free_rwsem(&sbi->s_journal_flag_rwsem);
#ifdef CONFIG_QUOTA
for (i = 0; i < EXT4_MAXQUOTAS; i++)
kfree(sbi->s_qf_names[i]);
#endif
/* Debugging code just in case the in-memory inode orphan list
* isn't empty. The on-disk one can be non-empty if we've
* detected an error and taken the fs readonly, but the
* in-memory list had better be clean by this point. */
if (!list_empty(&sbi->s_orphan))
dump_orphan_list(sb, sbi);
J_ASSERT(list_empty(&sbi->s_orphan));
sync_blockdev(sb->s_bdev);
invalidate_bdev(sb->s_bdev);
if (sbi->journal_bdev && sbi->journal_bdev != sb->s_bdev) {
/*
* Invalidate the journal device's buffers. We don't want them
* floating about in memory - the physical journal device may
* hotswapped, and it breaks the `ro-after' testing code.
*/
sync_blockdev(sbi->journal_bdev);
invalidate_bdev(sbi->journal_bdev);
ext4_blkdev_remove(sbi);
}
if (sbi->s_mb_cache) {
ext4_xattr_destroy_cache(sbi->s_mb_cache);
sbi->s_mb_cache = NULL;
}
if (sbi->s_mmp_tsk)
kthread_stop(sbi->s_mmp_tsk);
brelse(sbi->s_sbh);
sb->s_fs_info = NULL;
/*
* Now that we are completely done shutting down the
* superblock, we need to actually destroy the kobject.
*/
kobject_put(&sbi->s_kobj);
wait_for_completion(&sbi->s_kobj_unregister);
if (sbi->s_chksum_driver)
crypto_free_shash(sbi->s_chksum_driver);
kfree(sbi->s_blockgroup_lock);
kfree(sbi);
}
static struct kmem_cache *ext4_inode_cachep;
/*
* Called inside transaction, so use GFP_NOFS
*/
static struct inode *ext4_alloc_inode(struct super_block *sb)
{
struct ext4_inode_info *ei;
ei = kmem_cache_alloc(ext4_inode_cachep, GFP_NOFS);
if (!ei)
return NULL;
ei->vfs_inode.i_version = 1;
spin_lock_init(&ei->i_raw_lock);
INIT_LIST_HEAD(&ei->i_prealloc_list);
spin_lock_init(&ei->i_prealloc_lock);
ext4_es_init_tree(&ei->i_es_tree);
rwlock_init(&ei->i_es_lock);
INIT_LIST_HEAD(&ei->i_es_list);
ext4: track extent status tree shrinker delay statictics This commit adds some statictics in extent status tree shrinker. The purpose to add these is that we want to collect more details when we encounter a stall caused by extent status tree shrinker. Here we count the following statictics: stats: the number of all objects on all extent status trees the number of reclaimable objects on lru list cache hits/misses the last sorted interval the number of inodes on lru list average: scan time for shrinking some objects the number of shrunk objects maximum: the inode that has max nr. of objects on lru list the maximum scan time for shrinking some objects The output looks like below: $ cat /proc/fs/ext4/sda1/es_shrinker_info stats: 28228 objects 6341 reclaimable objects 5281/631 cache hits/misses 586 ms last sorted interval 250 inodes on lru list average: 153 us scan time 128 shrunk objects maximum: 255 inode (255 objects, 198 reclaimable) 125723 us max scan time If the lru list has never been sorted, the following line will not be printed: 586ms last sorted interval If there is an empty lru list, the following lines also will not be printed: 250 inodes on lru list ... maximum: 255 inode (255 objects, 198 reclaimable) 0 us max scan time Meanwhile in this commit a new trace point is defined to print some details in __ext4_es_shrink(). Cc: Andreas Dilger <adilger.kernel@dilger.ca> Cc: Jan Kara <jack@suse.cz> Reviewed-by: Jan Kara <jack@suse.cz> Signed-off-by: Zheng Liu <wenqing.lz@taobao.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2014-09-02 10:26:49 +08:00
ei->i_es_all_nr = 0;
ei->i_es_shk_nr = 0;
ei->i_es_shrink_lblk = 0;
ei->i_reserved_data_blocks = 0;
ei->i_reserved_meta_blocks = 0;
ei->i_allocated_meta_blocks = 0;
ei->i_da_metadata_calc_len = 0;
ei->i_da_metadata_calc_last_lblock = 0;
spin_lock_init(&(ei->i_block_reservation_lock));
#ifdef CONFIG_QUOTA
ei->i_reserved_quota = 0;
memset(&ei->i_dquot, 0, sizeof(ei->i_dquot));
#endif
ei->jinode = NULL;
INIT_LIST_HEAD(&ei->i_rsv_conversion_list);
spin_lock_init(&ei->i_completed_io_lock);
ei->i_sync_tid = 0;
ei->i_datasync_tid = 0;
atomic_set(&ei->i_unwritten, 0);
INIT_WORK(&ei->i_rsv_conversion_work, ext4_end_io_rsv_work);
return &ei->vfs_inode;
}
static int ext4_drop_inode(struct inode *inode)
{
int drop = generic_drop_inode(inode);
trace_ext4_drop_inode(inode, drop);
return drop;
}
2011-01-07 14:49:49 +08:00
static void ext4_i_callback(struct rcu_head *head)
{
struct inode *inode = container_of(head, struct inode, i_rcu);
kmem_cache_free(ext4_inode_cachep, EXT4_I(inode));
}
static void ext4_destroy_inode(struct inode *inode)
{
if (!list_empty(&(EXT4_I(inode)->i_orphan))) {
ext4_msg(inode->i_sb, KERN_ERR,
"Inode %lu (%p): orphan list check failed!",
inode->i_ino, EXT4_I(inode));
print_hex_dump(KERN_INFO, "", DUMP_PREFIX_ADDRESS, 16, 4,
EXT4_I(inode), sizeof(struct ext4_inode_info),
true);
dump_stack();
}
2011-01-07 14:49:49 +08:00
call_rcu(&inode->i_rcu, ext4_i_callback);
}
static void init_once(void *foo)
{
struct ext4_inode_info *ei = (struct ext4_inode_info *) foo;
INIT_LIST_HEAD(&ei->i_orphan);
init_rwsem(&ei->xattr_sem);
init_rwsem(&ei->i_data_sem);
init_rwsem(&ei->i_mmap_sem);
inode_init_once(&ei->vfs_inode);
}
static int __init init_inodecache(void)
{
ext4_inode_cachep = kmem_cache_create("ext4_inode_cache",
sizeof(struct ext4_inode_info),
0, (SLAB_RECLAIM_ACCOUNT|
2016-01-15 07:18:21 +08:00
SLAB_MEM_SPREAD|SLAB_ACCOUNT),
init_once);
if (ext4_inode_cachep == NULL)
return -ENOMEM;
return 0;
}
static void destroy_inodecache(void)
{
/*
* Make sure all delayed rcu free inodes are flushed before we
* destroy cache.
*/
rcu_barrier();
kmem_cache_destroy(ext4_inode_cachep);
}
void ext4_clear_inode(struct inode *inode)
{
invalidate_inode_buffers(inode);
clear_inode(inode);
dquot_drop(inode);
ext4_discard_preallocations(inode);
ext4_es_remove_extent(inode, 0, EXT_MAX_BLOCKS);
if (EXT4_I(inode)->jinode) {
jbd2_journal_release_jbd_inode(EXT4_JOURNAL(inode),
EXT4_I(inode)->jinode);
jbd2_free_inode(EXT4_I(inode)->jinode);
EXT4_I(inode)->jinode = NULL;
}
ext4 crypto: reorganize how we store keys in the inode This is a pretty massive patch which does a number of different things: 1) The per-inode encryption information is now stored in an allocated data structure, ext4_crypt_info, instead of directly in the node. This reduces the size usage of an in-memory inode when it is not using encryption. 2) We drop the ext4_fname_crypto_ctx entirely, and use the per-inode encryption structure instead. This remove an unnecessary memory allocation and free for the fname_crypto_ctx as well as allowing us to reuse the ctfm in a directory for multiple lookups and file creations. 3) We also cache the inode's policy information in the ext4_crypt_info structure so we don't have to continually read it out of the extended attributes. 4) We now keep the keyring key in the inode's encryption structure instead of releasing it after we are done using it to derive the per-inode key. This allows us to test to see if the key has been revoked; if it has, we prevent the use of the derived key and free it. 5) When an inode is released (or when the derived key is freed), we will use memset_explicit() to zero out the derived key, so it's not left hanging around in memory. This implies that when a user logs out, it is important to first revoke the key, and then unlink it, and then finally, to use "echo 3 > /proc/sys/vm/drop_caches" to release any decrypted pages and dcache entries from the system caches. 6) All this, and we also shrink the number of lines of code by around 100. :-) Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2015-05-19 01:17:47 +08:00
#ifdef CONFIG_EXT4_FS_ENCRYPTION
fscrypt_put_encryption_info(inode, NULL);
ext4 crypto: reorganize how we store keys in the inode This is a pretty massive patch which does a number of different things: 1) The per-inode encryption information is now stored in an allocated data structure, ext4_crypt_info, instead of directly in the node. This reduces the size usage of an in-memory inode when it is not using encryption. 2) We drop the ext4_fname_crypto_ctx entirely, and use the per-inode encryption structure instead. This remove an unnecessary memory allocation and free for the fname_crypto_ctx as well as allowing us to reuse the ctfm in a directory for multiple lookups and file creations. 3) We also cache the inode's policy information in the ext4_crypt_info structure so we don't have to continually read it out of the extended attributes. 4) We now keep the keyring key in the inode's encryption structure instead of releasing it after we are done using it to derive the per-inode key. This allows us to test to see if the key has been revoked; if it has, we prevent the use of the derived key and free it. 5) When an inode is released (or when the derived key is freed), we will use memset_explicit() to zero out the derived key, so it's not left hanging around in memory. This implies that when a user logs out, it is important to first revoke the key, and then unlink it, and then finally, to use "echo 3 > /proc/sys/vm/drop_caches" to release any decrypted pages and dcache entries from the system caches. 6) All this, and we also shrink the number of lines of code by around 100. :-) Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2015-05-19 01:17:47 +08:00
#endif
}
static struct inode *ext4_nfs_get_inode(struct super_block *sb,
u64 ino, u32 generation)
{
struct inode *inode;
if (ino < EXT4_FIRST_INO(sb) && ino != EXT4_ROOT_INO)
return ERR_PTR(-ESTALE);
if (ino > le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count))
return ERR_PTR(-ESTALE);
/* iget isn't really right if the inode is currently unallocated!!
*
* ext4_read_inode will return a bad_inode if the inode had been
* deleted, so we should be safe.
*
* Currently we don't know the generation for parent directory, so
* a generation of 0 means "accept any"
*/
inode = ext4_iget_normal(sb, ino);
if (IS_ERR(inode))
return ERR_CAST(inode);
if (generation && inode->i_generation != generation) {
iput(inode);
return ERR_PTR(-ESTALE);
}
return inode;
}
static struct dentry *ext4_fh_to_dentry(struct super_block *sb, struct fid *fid,
int fh_len, int fh_type)
{
return generic_fh_to_dentry(sb, fid, fh_len, fh_type,
ext4_nfs_get_inode);
}
static struct dentry *ext4_fh_to_parent(struct super_block *sb, struct fid *fid,
int fh_len, int fh_type)
{
return generic_fh_to_parent(sb, fid, fh_len, fh_type,
ext4_nfs_get_inode);
}
/*
* Try to release metadata pages (indirect blocks, directories) which are
* mapped via the block device. Since these pages could have journal heads
* which would prevent try_to_free_buffers() from freeing them, we must use
* jbd2 layer's try_to_free_buffers() function to release them.
*/
static int bdev_try_to_free_page(struct super_block *sb, struct page *page,
gfp_t wait)
{
journal_t *journal = EXT4_SB(sb)->s_journal;
WARN_ON(PageChecked(page));
if (!page_has_buffers(page))
return 0;
if (journal)
return jbd2_journal_try_to_free_buffers(journal, page,
mm, page_alloc: distinguish between being unable to sleep, unwilling to sleep and avoiding waking kswapd __GFP_WAIT has been used to identify atomic context in callers that hold spinlocks or are in interrupts. They are expected to be high priority and have access one of two watermarks lower than "min" which can be referred to as the "atomic reserve". __GFP_HIGH users get access to the first lower watermark and can be called the "high priority reserve". Over time, callers had a requirement to not block when fallback options were available. Some have abused __GFP_WAIT leading to a situation where an optimisitic allocation with a fallback option can access atomic reserves. This patch uses __GFP_ATOMIC to identify callers that are truely atomic, cannot sleep and have no alternative. High priority users continue to use __GFP_HIGH. __GFP_DIRECT_RECLAIM identifies callers that can sleep and are willing to enter direct reclaim. __GFP_KSWAPD_RECLAIM to identify callers that want to wake kswapd for background reclaim. __GFP_WAIT is redefined as a caller that is willing to enter direct reclaim and wake kswapd for background reclaim. This patch then converts a number of sites o __GFP_ATOMIC is used by callers that are high priority and have memory pools for those requests. GFP_ATOMIC uses this flag. o Callers that have a limited mempool to guarantee forward progress clear __GFP_DIRECT_RECLAIM but keep __GFP_KSWAPD_RECLAIM. bio allocations fall into this category where kswapd will still be woken but atomic reserves are not used as there is a one-entry mempool to guarantee progress. o Callers that are checking if they are non-blocking should use the helper gfpflags_allow_blocking() where possible. This is because checking for __GFP_WAIT as was done historically now can trigger false positives. Some exceptions like dm-crypt.c exist where the code intent is clearer if __GFP_DIRECT_RECLAIM is used instead of the helper due to flag manipulations. o Callers that built their own GFP flags instead of starting with GFP_KERNEL and friends now also need to specify __GFP_KSWAPD_RECLAIM. The first key hazard to watch out for is callers that removed __GFP_WAIT and was depending on access to atomic reserves for inconspicuous reasons. In some cases it may be appropriate for them to use __GFP_HIGH. The second key hazard is callers that assembled their own combination of GFP flags instead of starting with something like GFP_KERNEL. They may now wish to specify __GFP_KSWAPD_RECLAIM. It's almost certainly harmless if it's missed in most cases as other activity will wake kswapd. Signed-off-by: Mel Gorman <mgorman@techsingularity.net> Acked-by: Vlastimil Babka <vbabka@suse.cz> Acked-by: Michal Hocko <mhocko@suse.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Cc: Christoph Lameter <cl@linux.com> Cc: David Rientjes <rientjes@google.com> Cc: Vitaly Wool <vitalywool@gmail.com> Cc: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-11-07 08:28:21 +08:00
wait & ~__GFP_DIRECT_RECLAIM);
return try_to_free_buffers(page);
}
#ifdef CONFIG_EXT4_FS_ENCRYPTION
static int ext4_get_context(struct inode *inode, void *ctx, size_t len)
{
return ext4_xattr_get(inode, EXT4_XATTR_INDEX_ENCRYPTION,
EXT4_XATTR_NAME_ENCRYPTION_CONTEXT, ctx, len);
}
static int ext4_key_prefix(struct inode *inode, u8 **key)
{
*key = EXT4_SB(inode->i_sb)->key_prefix;
return EXT4_SB(inode->i_sb)->key_prefix_size;
}
static int ext4_prepare_context(struct inode *inode)
{
return ext4_convert_inline_data(inode);
}
static int ext4_set_context(struct inode *inode, const void *ctx, size_t len,
void *fs_data)
{
ext4: avoid lockdep warning when inheriting encryption context On a lockdep-enabled kernel, xfstests generic/027 fails due to a lockdep warning when run on ext4 mounted with -o test_dummy_encryption: xfs_io/4594 is trying to acquire lock: (jbd2_handle ){++++.+}, at: [<ffffffff813096ef>] jbd2_log_wait_commit+0x5/0x11b but task is already holding lock: (jbd2_handle ){++++.+}, at: [<ffffffff813000de>] start_this_handle+0x354/0x3d8 The abbreviated call stack is: [<ffffffff813096ef>] ? jbd2_log_wait_commit+0x5/0x11b [<ffffffff8130972a>] jbd2_log_wait_commit+0x40/0x11b [<ffffffff813096ef>] ? jbd2_log_wait_commit+0x5/0x11b [<ffffffff8130987b>] ? __jbd2_journal_force_commit+0x76/0xa6 [<ffffffff81309896>] __jbd2_journal_force_commit+0x91/0xa6 [<ffffffff813098b9>] jbd2_journal_force_commit_nested+0xe/0x18 [<ffffffff812a6049>] ext4_should_retry_alloc+0x72/0x79 [<ffffffff812f0c1f>] ext4_xattr_set+0xef/0x11f [<ffffffff812cc35b>] ext4_set_context+0x3a/0x16b [<ffffffff81258123>] fscrypt_inherit_context+0xe3/0x103 [<ffffffff812ab611>] __ext4_new_inode+0x12dc/0x153a [<ffffffff812bd371>] ext4_create+0xb7/0x161 When a file is created in an encrypted directory, ext4_set_context() is called to set an encryption context on the new file. This calls ext4_xattr_set(), which contains a retry loop where the journal is forced to commit if an ENOSPC error is encountered. If the task actually were to wait for the journal to commit in this case, then it would deadlock because a handle remains open from __ext4_new_inode(), so the running transaction can't be committed yet. Fortunately, __jbd2_journal_force_commit() avoids the deadlock by not allowing the running transaction to be committed while the current task has it open. However, the above lockdep warning is still triggered. This was a false positive which was introduced by: 1eaa566d368b: jbd2: track more dependencies on transaction commit Fix the problem by passing the handle through the 'fs_data' argument to ext4_set_context(), then using ext4_xattr_set_handle() instead of ext4_xattr_set(). And in the case where no journal handle is specified and ext4_set_context() has to open one, add an ENOSPC retry loop since in that case it is the outermost transaction. Signed-off-by: Eric Biggers <ebiggers@google.com>
2016-11-22 00:52:44 +08:00
handle_t *handle = fs_data;
int res, res2, retries = 0;
/*
* If a journal handle was specified, then the encryption context is
* being set on a new inode via inheritance and is part of a larger
* transaction to create the inode. Otherwise the encryption context is
* being set on an existing inode in its own transaction. Only in the
* latter case should the "retry on ENOSPC" logic be used.
*/
ext4: avoid lockdep warning when inheriting encryption context On a lockdep-enabled kernel, xfstests generic/027 fails due to a lockdep warning when run on ext4 mounted with -o test_dummy_encryption: xfs_io/4594 is trying to acquire lock: (jbd2_handle ){++++.+}, at: [<ffffffff813096ef>] jbd2_log_wait_commit+0x5/0x11b but task is already holding lock: (jbd2_handle ){++++.+}, at: [<ffffffff813000de>] start_this_handle+0x354/0x3d8 The abbreviated call stack is: [<ffffffff813096ef>] ? jbd2_log_wait_commit+0x5/0x11b [<ffffffff8130972a>] jbd2_log_wait_commit+0x40/0x11b [<ffffffff813096ef>] ? jbd2_log_wait_commit+0x5/0x11b [<ffffffff8130987b>] ? __jbd2_journal_force_commit+0x76/0xa6 [<ffffffff81309896>] __jbd2_journal_force_commit+0x91/0xa6 [<ffffffff813098b9>] jbd2_journal_force_commit_nested+0xe/0x18 [<ffffffff812a6049>] ext4_should_retry_alloc+0x72/0x79 [<ffffffff812f0c1f>] ext4_xattr_set+0xef/0x11f [<ffffffff812cc35b>] ext4_set_context+0x3a/0x16b [<ffffffff81258123>] fscrypt_inherit_context+0xe3/0x103 [<ffffffff812ab611>] __ext4_new_inode+0x12dc/0x153a [<ffffffff812bd371>] ext4_create+0xb7/0x161 When a file is created in an encrypted directory, ext4_set_context() is called to set an encryption context on the new file. This calls ext4_xattr_set(), which contains a retry loop where the journal is forced to commit if an ENOSPC error is encountered. If the task actually were to wait for the journal to commit in this case, then it would deadlock because a handle remains open from __ext4_new_inode(), so the running transaction can't be committed yet. Fortunately, __jbd2_journal_force_commit() avoids the deadlock by not allowing the running transaction to be committed while the current task has it open. However, the above lockdep warning is still triggered. This was a false positive which was introduced by: 1eaa566d368b: jbd2: track more dependencies on transaction commit Fix the problem by passing the handle through the 'fs_data' argument to ext4_set_context(), then using ext4_xattr_set_handle() instead of ext4_xattr_set(). And in the case where no journal handle is specified and ext4_set_context() has to open one, add an ENOSPC retry loop since in that case it is the outermost transaction. Signed-off-by: Eric Biggers <ebiggers@google.com>
2016-11-22 00:52:44 +08:00
if (handle) {
res = ext4_xattr_set_handle(handle, inode,
EXT4_XATTR_INDEX_ENCRYPTION,
EXT4_XATTR_NAME_ENCRYPTION_CONTEXT,
ctx, len, 0);
if (!res) {
ext4_set_inode_flag(inode, EXT4_INODE_ENCRYPT);
ext4_clear_inode_state(inode,
EXT4_STATE_MAY_INLINE_DATA);
/*
* Update inode->i_flags - e.g. S_DAX may get disabled
*/
ext4_set_inode_flags(inode);
}
return res;
}
ext4: avoid lockdep warning when inheriting encryption context On a lockdep-enabled kernel, xfstests generic/027 fails due to a lockdep warning when run on ext4 mounted with -o test_dummy_encryption: xfs_io/4594 is trying to acquire lock: (jbd2_handle ){++++.+}, at: [<ffffffff813096ef>] jbd2_log_wait_commit+0x5/0x11b but task is already holding lock: (jbd2_handle ){++++.+}, at: [<ffffffff813000de>] start_this_handle+0x354/0x3d8 The abbreviated call stack is: [<ffffffff813096ef>] ? jbd2_log_wait_commit+0x5/0x11b [<ffffffff8130972a>] jbd2_log_wait_commit+0x40/0x11b [<ffffffff813096ef>] ? jbd2_log_wait_commit+0x5/0x11b [<ffffffff8130987b>] ? __jbd2_journal_force_commit+0x76/0xa6 [<ffffffff81309896>] __jbd2_journal_force_commit+0x91/0xa6 [<ffffffff813098b9>] jbd2_journal_force_commit_nested+0xe/0x18 [<ffffffff812a6049>] ext4_should_retry_alloc+0x72/0x79 [<ffffffff812f0c1f>] ext4_xattr_set+0xef/0x11f [<ffffffff812cc35b>] ext4_set_context+0x3a/0x16b [<ffffffff81258123>] fscrypt_inherit_context+0xe3/0x103 [<ffffffff812ab611>] __ext4_new_inode+0x12dc/0x153a [<ffffffff812bd371>] ext4_create+0xb7/0x161 When a file is created in an encrypted directory, ext4_set_context() is called to set an encryption context on the new file. This calls ext4_xattr_set(), which contains a retry loop where the journal is forced to commit if an ENOSPC error is encountered. If the task actually were to wait for the journal to commit in this case, then it would deadlock because a handle remains open from __ext4_new_inode(), so the running transaction can't be committed yet. Fortunately, __jbd2_journal_force_commit() avoids the deadlock by not allowing the running transaction to be committed while the current task has it open. However, the above lockdep warning is still triggered. This was a false positive which was introduced by: 1eaa566d368b: jbd2: track more dependencies on transaction commit Fix the problem by passing the handle through the 'fs_data' argument to ext4_set_context(), then using ext4_xattr_set_handle() instead of ext4_xattr_set(). And in the case where no journal handle is specified and ext4_set_context() has to open one, add an ENOSPC retry loop since in that case it is the outermost transaction. Signed-off-by: Eric Biggers <ebiggers@google.com>
2016-11-22 00:52:44 +08:00
retry:
handle = ext4_journal_start(inode, EXT4_HT_MISC,
ext4_jbd2_credits_xattr(inode));
if (IS_ERR(handle))
return PTR_ERR(handle);
ext4: avoid lockdep warning when inheriting encryption context On a lockdep-enabled kernel, xfstests generic/027 fails due to a lockdep warning when run on ext4 mounted with -o test_dummy_encryption: xfs_io/4594 is trying to acquire lock: (jbd2_handle ){++++.+}, at: [<ffffffff813096ef>] jbd2_log_wait_commit+0x5/0x11b but task is already holding lock: (jbd2_handle ){++++.+}, at: [<ffffffff813000de>] start_this_handle+0x354/0x3d8 The abbreviated call stack is: [<ffffffff813096ef>] ? jbd2_log_wait_commit+0x5/0x11b [<ffffffff8130972a>] jbd2_log_wait_commit+0x40/0x11b [<ffffffff813096ef>] ? jbd2_log_wait_commit+0x5/0x11b [<ffffffff8130987b>] ? __jbd2_journal_force_commit+0x76/0xa6 [<ffffffff81309896>] __jbd2_journal_force_commit+0x91/0xa6 [<ffffffff813098b9>] jbd2_journal_force_commit_nested+0xe/0x18 [<ffffffff812a6049>] ext4_should_retry_alloc+0x72/0x79 [<ffffffff812f0c1f>] ext4_xattr_set+0xef/0x11f [<ffffffff812cc35b>] ext4_set_context+0x3a/0x16b [<ffffffff81258123>] fscrypt_inherit_context+0xe3/0x103 [<ffffffff812ab611>] __ext4_new_inode+0x12dc/0x153a [<ffffffff812bd371>] ext4_create+0xb7/0x161 When a file is created in an encrypted directory, ext4_set_context() is called to set an encryption context on the new file. This calls ext4_xattr_set(), which contains a retry loop where the journal is forced to commit if an ENOSPC error is encountered. If the task actually were to wait for the journal to commit in this case, then it would deadlock because a handle remains open from __ext4_new_inode(), so the running transaction can't be committed yet. Fortunately, __jbd2_journal_force_commit() avoids the deadlock by not allowing the running transaction to be committed while the current task has it open. However, the above lockdep warning is still triggered. This was a false positive which was introduced by: 1eaa566d368b: jbd2: track more dependencies on transaction commit Fix the problem by passing the handle through the 'fs_data' argument to ext4_set_context(), then using ext4_xattr_set_handle() instead of ext4_xattr_set(). And in the case where no journal handle is specified and ext4_set_context() has to open one, add an ENOSPC retry loop since in that case it is the outermost transaction. Signed-off-by: Eric Biggers <ebiggers@google.com>
2016-11-22 00:52:44 +08:00
res = ext4_xattr_set_handle(handle, inode, EXT4_XATTR_INDEX_ENCRYPTION,
EXT4_XATTR_NAME_ENCRYPTION_CONTEXT,
ctx, len, 0);
if (!res) {
ext4_set_inode_flag(inode, EXT4_INODE_ENCRYPT);
/* Update inode->i_flags - e.g. S_DAX may get disabled */
ext4_set_inode_flags(inode);
res = ext4_mark_inode_dirty(handle, inode);
if (res)
EXT4_ERROR_INODE(inode, "Failed to mark inode dirty");
}
res2 = ext4_journal_stop(handle);
ext4: avoid lockdep warning when inheriting encryption context On a lockdep-enabled kernel, xfstests generic/027 fails due to a lockdep warning when run on ext4 mounted with -o test_dummy_encryption: xfs_io/4594 is trying to acquire lock: (jbd2_handle ){++++.+}, at: [<ffffffff813096ef>] jbd2_log_wait_commit+0x5/0x11b but task is already holding lock: (jbd2_handle ){++++.+}, at: [<ffffffff813000de>] start_this_handle+0x354/0x3d8 The abbreviated call stack is: [<ffffffff813096ef>] ? jbd2_log_wait_commit+0x5/0x11b [<ffffffff8130972a>] jbd2_log_wait_commit+0x40/0x11b [<ffffffff813096ef>] ? jbd2_log_wait_commit+0x5/0x11b [<ffffffff8130987b>] ? __jbd2_journal_force_commit+0x76/0xa6 [<ffffffff81309896>] __jbd2_journal_force_commit+0x91/0xa6 [<ffffffff813098b9>] jbd2_journal_force_commit_nested+0xe/0x18 [<ffffffff812a6049>] ext4_should_retry_alloc+0x72/0x79 [<ffffffff812f0c1f>] ext4_xattr_set+0xef/0x11f [<ffffffff812cc35b>] ext4_set_context+0x3a/0x16b [<ffffffff81258123>] fscrypt_inherit_context+0xe3/0x103 [<ffffffff812ab611>] __ext4_new_inode+0x12dc/0x153a [<ffffffff812bd371>] ext4_create+0xb7/0x161 When a file is created in an encrypted directory, ext4_set_context() is called to set an encryption context on the new file. This calls ext4_xattr_set(), which contains a retry loop where the journal is forced to commit if an ENOSPC error is encountered. If the task actually were to wait for the journal to commit in this case, then it would deadlock because a handle remains open from __ext4_new_inode(), so the running transaction can't be committed yet. Fortunately, __jbd2_journal_force_commit() avoids the deadlock by not allowing the running transaction to be committed while the current task has it open. However, the above lockdep warning is still triggered. This was a false positive which was introduced by: 1eaa566d368b: jbd2: track more dependencies on transaction commit Fix the problem by passing the handle through the 'fs_data' argument to ext4_set_context(), then using ext4_xattr_set_handle() instead of ext4_xattr_set(). And in the case where no journal handle is specified and ext4_set_context() has to open one, add an ENOSPC retry loop since in that case it is the outermost transaction. Signed-off-by: Eric Biggers <ebiggers@google.com>
2016-11-22 00:52:44 +08:00
if (res == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
goto retry;
if (!res)
res = res2;
return res;
}
static int ext4_dummy_context(struct inode *inode)
{
return DUMMY_ENCRYPTION_ENABLED(EXT4_SB(inode->i_sb));
}
static unsigned ext4_max_namelen(struct inode *inode)
{
return S_ISLNK(inode->i_mode) ? inode->i_sb->s_blocksize :
EXT4_NAME_LEN;
}
static struct fscrypt_operations ext4_cryptops = {
.get_context = ext4_get_context,
.key_prefix = ext4_key_prefix,
.prepare_context = ext4_prepare_context,
.set_context = ext4_set_context,
.dummy_context = ext4_dummy_context,
.is_encrypted = ext4_encrypted_inode,
.empty_dir = ext4_empty_dir,
.max_namelen = ext4_max_namelen,
};
#else
static struct fscrypt_operations ext4_cryptops = {
.is_encrypted = ext4_encrypted_inode,
};
#endif
#ifdef CONFIG_QUOTA
static char *quotatypes[] = INITQFNAMES;
#define QTYPE2NAME(t) (quotatypes[t])
static int ext4_write_dquot(struct dquot *dquot);
static int ext4_acquire_dquot(struct dquot *dquot);
static int ext4_release_dquot(struct dquot *dquot);
static int ext4_mark_dquot_dirty(struct dquot *dquot);
static int ext4_write_info(struct super_block *sb, int type);
static int ext4_quota_on(struct super_block *sb, int type, int format_id,
const struct path *path);
static int ext4_quota_off(struct super_block *sb, int type);
static int ext4_quota_on_mount(struct super_block *sb, int type);
static ssize_t ext4_quota_read(struct super_block *sb, int type, char *data,
size_t len, loff_t off);
static ssize_t ext4_quota_write(struct super_block *sb, int type,
const char *data, size_t len, loff_t off);
ext4: make quota as first class supported feature This patch adds support for quotas as a first class feature in ext4; which is to say, the quota files are stored in hidden inodes as file system metadata, instead of as separate files visible in the file system directory hierarchy. It is based on the proposal at: https://ext4.wiki.kernel.org/index.php/Design_For_1st_Class_Quota_in_Ext4 This patch introduces a new feature - EXT4_FEATURE_RO_COMPAT_QUOTA which, when turned on, enables quota accounting at mount time iteself. Also, the quota inodes are stored in two additional superblock fields. Some changes introduced by this patch that should be pointed out are: 1) Two new ext4-superblock fields - s_usr_quota_inum and s_grp_quota_inum for storing the quota inodes in use. 2) Default quota inodes are: inode#3 for tracking userquota and inode#4 for tracking group quota. The superblock fields can be set to use other inodes as well. 3) If the QUOTA feature and corresponding quota inodes are set in superblock, the quota usage tracking is turned on at mount time. On 'quotaon' ioctl, the quota limits enforcement is turned on. 'quotaoff' ioctl turns off only the limits enforcement in this case. 4) When QUOTA feature is in use, the quota mount options 'quota', 'usrquota', 'grpquota' are ignored by the kernel. 5) mke2fs or tune2fs can be used to set the QUOTA feature and initialize quota inodes. The default reserved inodes will not be visible to user as regular files. 6) The quota-tools will need to be modified to support hidden quota files on ext4. E2fsprogs will also include support for creating and fixing quota files. 7) Support is only for the new V2 quota file format. Tested-by: Jan Kara <jack@suse.cz> Reviewed-by: Jan Kara <jack@suse.cz> Reviewed-by: Johann Lombardi <johann@whamcloud.com> Signed-off-by: Aditya Kali <adityakali@google.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2012-07-23 08:21:31 +08:00
static int ext4_quota_enable(struct super_block *sb, int type, int format_id,
unsigned int flags);
static int ext4_enable_quotas(struct super_block *sb);
static int ext4_get_next_id(struct super_block *sb, struct kqid *qid);
static struct dquot **ext4_get_dquots(struct inode *inode)
{
return EXT4_I(inode)->i_dquot;
}
static const struct dquot_operations ext4_quota_operations = {
.get_reserved_space = ext4_get_reserved_space,
.write_dquot = ext4_write_dquot,
.acquire_dquot = ext4_acquire_dquot,
.release_dquot = ext4_release_dquot,
.mark_dirty = ext4_mark_dquot_dirty,
.write_info = ext4_write_info,
.alloc_dquot = dquot_alloc,
.destroy_dquot = dquot_destroy,
.get_projid = ext4_get_projid,
.get_next_id = ext4_get_next_id,
};
static const struct quotactl_ops ext4_qctl_operations = {
.quota_on = ext4_quota_on,
.quota_off = ext4_quota_off,
.quota_sync = dquot_quota_sync,
.get_state = dquot_get_state,
.set_info = dquot_set_dqinfo,
.get_dqblk = dquot_get_dqblk,
.set_dqblk = dquot_set_dqblk,
.get_nextdqblk = dquot_get_next_dqblk,
};
#endif
static const struct super_operations ext4_sops = {
.alloc_inode = ext4_alloc_inode,
.destroy_inode = ext4_destroy_inode,
.write_inode = ext4_write_inode,
.dirty_inode = ext4_dirty_inode,
.drop_inode = ext4_drop_inode,
.evict_inode = ext4_evict_inode,
.put_super = ext4_put_super,
.sync_fs = ext4_sync_fs,
filesystem freeze: add error handling of write_super_lockfs/unlockfs Currently, ext3 in mainline Linux doesn't have the freeze feature which suspends write requests. So, we cannot take a backup which keeps the filesystem's consistency with the storage device's features (snapshot and replication) while it is mounted. In many case, a commercial filesystem (e.g. VxFS) has the freeze feature and it would be used to get the consistent backup. If Linux's standard filesystem ext3 has the freeze feature, we can do it without a commercial filesystem. So I have implemented the ioctls of the freeze feature. I think we can take the consistent backup with the following steps. 1. Freeze the filesystem with the freeze ioctl. 2. Separate the replication volume or create the snapshot with the storage device's feature. 3. Unfreeze the filesystem with the unfreeze ioctl. 4. Take the backup from the separated replication volume or the snapshot. This patch: VFS: Changed the type of write_super_lockfs and unlockfs from "void" to "int" so that they can return an error. Rename write_super_lockfs and unlockfs of the super block operation freeze_fs and unfreeze_fs to avoid a confusion. ext3, ext4, xfs, gfs2, jfs: Changed the type of write_super_lockfs and unlockfs from "void" to "int" so that write_super_lockfs returns an error if needed, and unlockfs always returns 0. reiserfs: Changed the type of write_super_lockfs and unlockfs from "void" to "int" so that they always return 0 (success) to keep a current behavior. Signed-off-by: Takashi Sato <t-sato@yk.jp.nec.com> Signed-off-by: Masayuki Hamaguchi <m-hamaguchi@ys.jp.nec.com> Cc: <xfs-masters@oss.sgi.com> Cc: <linux-ext4@vger.kernel.org> Cc: Christoph Hellwig <hch@lst.de> Cc: Dave Kleikamp <shaggy@austin.ibm.com> Cc: Dave Chinner <david@fromorbit.com> Cc: Alasdair G Kergon <agk@redhat.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-10 08:40:58 +08:00
.freeze_fs = ext4_freeze,
.unfreeze_fs = ext4_unfreeze,
.statfs = ext4_statfs,
.remount_fs = ext4_remount,
.show_options = ext4_show_options,
#ifdef CONFIG_QUOTA
.quota_read = ext4_quota_read,
.quota_write = ext4_quota_write,
.get_dquots = ext4_get_dquots,
#endif
.bdev_try_to_free_page = bdev_try_to_free_page,
};
static const struct export_operations ext4_export_ops = {
.fh_to_dentry = ext4_fh_to_dentry,
.fh_to_parent = ext4_fh_to_parent,
.get_parent = ext4_get_parent,
};
enum {
Opt_bsd_df, Opt_minix_df, Opt_grpid, Opt_nogrpid,
Opt_resgid, Opt_resuid, Opt_sb, Opt_err_cont, Opt_err_panic, Opt_err_ro,
Opt_nouid32, Opt_debug, Opt_removed,
Opt_user_xattr, Opt_nouser_xattr, Opt_acl, Opt_noacl,
Opt_auto_da_alloc, Opt_noauto_da_alloc, Opt_noload,
ext4: allow specifying external journal by pathname mount option It's always been a hassle that if an external journal's device number changes, the filesystem won't mount. And since boot-time enumeration can change, device number changes aren't unusual. The current mechanism to update the journal location is by passing in a mount option w/ a new devnum, but that's a hassle; it's a manual approach, fixing things after the fact. Adding a mount option, "-o journal_path=/dev/$DEVICE" would help, since then we can do i.e. # mount -o journal_path=/dev/disk/by-label/$JOURNAL_LABEL ... and it'll mount even if the devnum has changed, as shown here: # losetup /dev/loop0 journalfile # mke2fs -L mylabel-journal -O journal_dev /dev/loop0 # mkfs.ext4 -L mylabel -J device=/dev/loop0 /dev/sdb1 Change the journal device number: # losetup -d /dev/loop0 # losetup /dev/loop1 journalfile And today it will fail: # mount /dev/sdb1 /mnt/test mount: wrong fs type, bad option, bad superblock on /dev/sdb1, missing codepage or helper program, or other error In some cases useful info is found in syslog - try dmesg | tail or so # dmesg | tail -n 1 [17343.240702] EXT4-fs (sdb1): error: couldn't read superblock of external journal But with this new mount option, we can specify the new path: # mount -o journal_path=/dev/loop1 /dev/sdb1 /mnt/test # (which does update the encoded device number, incidentally): # umount /dev/sdb1 # dumpe2fs -h /dev/sdb1 | grep "Journal device" dumpe2fs 1.41.12 (17-May-2010) Journal device: 0x0701 But best of all we can just always mount by journal-path, and it'll always work: # mount -o journal_path=/dev/disk/by-label/mylabel-journal /dev/sdb1 /mnt/test # So the journal_path option can be specified in fstab, and as long as the disk is available somewhere, and findable by label (or by UUID), we can mount. Signed-off-by: Eric Sandeen <sandeen@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu> Reviewed-by: Jan Kara <jack@suse.cz> Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
2013-08-29 07:05:07 +08:00
Opt_commit, Opt_min_batch_time, Opt_max_batch_time, Opt_journal_dev,
Opt_journal_path, Opt_journal_checksum, Opt_journal_async_commit,
Opt_abort, Opt_data_journal, Opt_data_ordered, Opt_data_writeback,
Opt_data_err_abort, Opt_data_err_ignore, Opt_test_dummy_encryption,
Opt_usrjquota, Opt_grpjquota, Opt_offusrjquota, Opt_offgrpjquota,
Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0, Opt_jqfmt_vfsv1, Opt_quota,
Opt_noquota, Opt_barrier, Opt_nobarrier, Opt_err,
Opt_usrquota, Opt_grpquota, Opt_prjquota, Opt_i_version, Opt_dax,
Opt_stripe, Opt_delalloc, Opt_nodelalloc, Opt_mblk_io_submit,
Opt_lazytime, Opt_nolazytime,
Opt_nomblk_io_submit, Opt_block_validity, Opt_noblock_validity,
Opt_inode_readahead_blks, Opt_journal_ioprio,
Opt_dioread_nolock, Opt_dioread_lock,
Opt_discard, Opt_nodiscard, Opt_init_itable, Opt_noinit_itable,
Opt_max_dir_size_kb, Opt_nojournal_checksum,
};
static const match_table_t tokens = {
{Opt_bsd_df, "bsddf"},
{Opt_minix_df, "minixdf"},
{Opt_grpid, "grpid"},
{Opt_grpid, "bsdgroups"},
{Opt_nogrpid, "nogrpid"},
{Opt_nogrpid, "sysvgroups"},
{Opt_resgid, "resgid=%u"},
{Opt_resuid, "resuid=%u"},
{Opt_sb, "sb=%u"},
{Opt_err_cont, "errors=continue"},
{Opt_err_panic, "errors=panic"},
{Opt_err_ro, "errors=remount-ro"},
{Opt_nouid32, "nouid32"},
{Opt_debug, "debug"},
{Opt_removed, "oldalloc"},
{Opt_removed, "orlov"},
{Opt_user_xattr, "user_xattr"},
{Opt_nouser_xattr, "nouser_xattr"},
{Opt_acl, "acl"},
{Opt_noacl, "noacl"},
{Opt_noload, "norecovery"},
{Opt_noload, "noload"},
{Opt_removed, "nobh"},
{Opt_removed, "bh"},
{Opt_commit, "commit=%u"},
{Opt_min_batch_time, "min_batch_time=%u"},
{Opt_max_batch_time, "max_batch_time=%u"},
{Opt_journal_dev, "journal_dev=%u"},
ext4: allow specifying external journal by pathname mount option It's always been a hassle that if an external journal's device number changes, the filesystem won't mount. And since boot-time enumeration can change, device number changes aren't unusual. The current mechanism to update the journal location is by passing in a mount option w/ a new devnum, but that's a hassle; it's a manual approach, fixing things after the fact. Adding a mount option, "-o journal_path=/dev/$DEVICE" would help, since then we can do i.e. # mount -o journal_path=/dev/disk/by-label/$JOURNAL_LABEL ... and it'll mount even if the devnum has changed, as shown here: # losetup /dev/loop0 journalfile # mke2fs -L mylabel-journal -O journal_dev /dev/loop0 # mkfs.ext4 -L mylabel -J device=/dev/loop0 /dev/sdb1 Change the journal device number: # losetup -d /dev/loop0 # losetup /dev/loop1 journalfile And today it will fail: # mount /dev/sdb1 /mnt/test mount: wrong fs type, bad option, bad superblock on /dev/sdb1, missing codepage or helper program, or other error In some cases useful info is found in syslog - try dmesg | tail or so # dmesg | tail -n 1 [17343.240702] EXT4-fs (sdb1): error: couldn't read superblock of external journal But with this new mount option, we can specify the new path: # mount -o journal_path=/dev/loop1 /dev/sdb1 /mnt/test # (which does update the encoded device number, incidentally): # umount /dev/sdb1 # dumpe2fs -h /dev/sdb1 | grep "Journal device" dumpe2fs 1.41.12 (17-May-2010) Journal device: 0x0701 But best of all we can just always mount by journal-path, and it'll always work: # mount -o journal_path=/dev/disk/by-label/mylabel-journal /dev/sdb1 /mnt/test # So the journal_path option can be specified in fstab, and as long as the disk is available somewhere, and findable by label (or by UUID), we can mount. Signed-off-by: Eric Sandeen <sandeen@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu> Reviewed-by: Jan Kara <jack@suse.cz> Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
2013-08-29 07:05:07 +08:00
{Opt_journal_path, "journal_path=%s"},
{Opt_journal_checksum, "journal_checksum"},
{Opt_nojournal_checksum, "nojournal_checksum"},
{Opt_journal_async_commit, "journal_async_commit"},
{Opt_abort, "abort"},
{Opt_data_journal, "data=journal"},
{Opt_data_ordered, "data=ordered"},
{Opt_data_writeback, "data=writeback"},
{Opt_data_err_abort, "data_err=abort"},
{Opt_data_err_ignore, "data_err=ignore"},
{Opt_offusrjquota, "usrjquota="},
{Opt_usrjquota, "usrjquota=%s"},
{Opt_offgrpjquota, "grpjquota="},
{Opt_grpjquota, "grpjquota=%s"},
{Opt_jqfmt_vfsold, "jqfmt=vfsold"},
{Opt_jqfmt_vfsv0, "jqfmt=vfsv0"},
{Opt_jqfmt_vfsv1, "jqfmt=vfsv1"},
{Opt_grpquota, "grpquota"},
{Opt_noquota, "noquota"},
{Opt_quota, "quota"},
{Opt_usrquota, "usrquota"},
{Opt_prjquota, "prjquota"},
{Opt_barrier, "barrier=%u"},
{Opt_barrier, "barrier"},
{Opt_nobarrier, "nobarrier"},
{Opt_i_version, "i_version"},
{Opt_dax, "dax"},
{Opt_stripe, "stripe=%u"},
{Opt_delalloc, "delalloc"},
{Opt_lazytime, "lazytime"},
{Opt_nolazytime, "nolazytime"},
{Opt_nodelalloc, "nodelalloc"},
{Opt_removed, "mblk_io_submit"},
{Opt_removed, "nomblk_io_submit"},
{Opt_block_validity, "block_validity"},
{Opt_noblock_validity, "noblock_validity"},
{Opt_inode_readahead_blks, "inode_readahead_blks=%u"},
{Opt_journal_ioprio, "journal_ioprio=%u"},
{Opt_auto_da_alloc, "auto_da_alloc=%u"},
{Opt_auto_da_alloc, "auto_da_alloc"},
{Opt_noauto_da_alloc, "noauto_da_alloc"},
{Opt_dioread_nolock, "dioread_nolock"},
{Opt_dioread_lock, "dioread_lock"},
{Opt_discard, "discard"},
{Opt_nodiscard, "nodiscard"},
{Opt_init_itable, "init_itable=%u"},
{Opt_init_itable, "init_itable"},
{Opt_noinit_itable, "noinit_itable"},
{Opt_max_dir_size_kb, "max_dir_size_kb=%u"},
{Opt_test_dummy_encryption, "test_dummy_encryption"},
{Opt_removed, "check=none"}, /* mount option from ext2/3 */
{Opt_removed, "nocheck"}, /* mount option from ext2/3 */
{Opt_removed, "reservation"}, /* mount option from ext2/3 */
{Opt_removed, "noreservation"}, /* mount option from ext2/3 */
{Opt_removed, "journal=%u"}, /* mount option from ext2/3 */
{Opt_err, NULL},
};
static ext4_fsblk_t get_sb_block(void **data)
{
ext4_fsblk_t sb_block;
char *options = (char *) *data;
if (!options || strncmp(options, "sb=", 3) != 0)
return 1; /* Default location */
options += 3;
/* TODO: use simple_strtoll with >32bit ext4 */
sb_block = simple_strtoul(options, &options, 0);
if (*options && *options != ',') {
printk(KERN_ERR "EXT4-fs: Invalid sb specification: %s\n",
(char *) *data);
return 1;
}
if (*options == ',')
options++;
*data = (void *) options;
return sb_block;
}
#define DEFAULT_JOURNAL_IOPRIO (IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, 3))
static char deprecated_msg[] = "Mount option \"%s\" will be removed by %s\n"
"Contact linux-ext4@vger.kernel.org if you think we should keep it.\n";
#ifdef CONFIG_QUOTA
static int set_qf_name(struct super_block *sb, int qtype, substring_t *args)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
char *qname;
int ret = -1;
if (sb_any_quota_loaded(sb) &&
!sbi->s_qf_names[qtype]) {
ext4_msg(sb, KERN_ERR,
"Cannot change journaled "
"quota options when quota turned on");
return -1;
}
if (ext4_has_feature_quota(sb)) {
ext4_msg(sb, KERN_INFO, "Journaled quota options "
"ignored when QUOTA feature is enabled");
return 1;
}
qname = match_strdup(args);
if (!qname) {
ext4_msg(sb, KERN_ERR,
"Not enough memory for storing quotafile name");
return -1;
}
if (sbi->s_qf_names[qtype]) {
if (strcmp(sbi->s_qf_names[qtype], qname) == 0)
ret = 1;
else
ext4_msg(sb, KERN_ERR,
"%s quota file already specified",
QTYPE2NAME(qtype));
goto errout;
}
if (strchr(qname, '/')) {
ext4_msg(sb, KERN_ERR,
"quotafile must be on filesystem root");
goto errout;
}
sbi->s_qf_names[qtype] = qname;
set_opt(sb, QUOTA);
return 1;
errout:
kfree(qname);
return ret;
}
static int clear_qf_name(struct super_block *sb, int qtype)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
if (sb_any_quota_loaded(sb) &&
sbi->s_qf_names[qtype]) {
ext4_msg(sb, KERN_ERR, "Cannot change journaled quota options"
" when quota turned on");
return -1;
}
kfree(sbi->s_qf_names[qtype]);
sbi->s_qf_names[qtype] = NULL;
return 1;
}
#endif
#define MOPT_SET 0x0001
#define MOPT_CLEAR 0x0002
#define MOPT_NOSUPPORT 0x0004
#define MOPT_EXPLICIT 0x0008
#define MOPT_CLEAR_ERR 0x0010
#define MOPT_GTE0 0x0020
#ifdef CONFIG_QUOTA
#define MOPT_Q 0
#define MOPT_QFMT 0x0040
#else
#define MOPT_Q MOPT_NOSUPPORT
#define MOPT_QFMT MOPT_NOSUPPORT
#endif
#define MOPT_DATAJ 0x0080
#define MOPT_NO_EXT2 0x0100
#define MOPT_NO_EXT3 0x0200
#define MOPT_EXT4_ONLY (MOPT_NO_EXT2 | MOPT_NO_EXT3)
ext4: allow specifying external journal by pathname mount option It's always been a hassle that if an external journal's device number changes, the filesystem won't mount. And since boot-time enumeration can change, device number changes aren't unusual. The current mechanism to update the journal location is by passing in a mount option w/ a new devnum, but that's a hassle; it's a manual approach, fixing things after the fact. Adding a mount option, "-o journal_path=/dev/$DEVICE" would help, since then we can do i.e. # mount -o journal_path=/dev/disk/by-label/$JOURNAL_LABEL ... and it'll mount even if the devnum has changed, as shown here: # losetup /dev/loop0 journalfile # mke2fs -L mylabel-journal -O journal_dev /dev/loop0 # mkfs.ext4 -L mylabel -J device=/dev/loop0 /dev/sdb1 Change the journal device number: # losetup -d /dev/loop0 # losetup /dev/loop1 journalfile And today it will fail: # mount /dev/sdb1 /mnt/test mount: wrong fs type, bad option, bad superblock on /dev/sdb1, missing codepage or helper program, or other error In some cases useful info is found in syslog - try dmesg | tail or so # dmesg | tail -n 1 [17343.240702] EXT4-fs (sdb1): error: couldn't read superblock of external journal But with this new mount option, we can specify the new path: # mount -o journal_path=/dev/loop1 /dev/sdb1 /mnt/test # (which does update the encoded device number, incidentally): # umount /dev/sdb1 # dumpe2fs -h /dev/sdb1 | grep "Journal device" dumpe2fs 1.41.12 (17-May-2010) Journal device: 0x0701 But best of all we can just always mount by journal-path, and it'll always work: # mount -o journal_path=/dev/disk/by-label/mylabel-journal /dev/sdb1 /mnt/test # So the journal_path option can be specified in fstab, and as long as the disk is available somewhere, and findable by label (or by UUID), we can mount. Signed-off-by: Eric Sandeen <sandeen@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu> Reviewed-by: Jan Kara <jack@suse.cz> Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
2013-08-29 07:05:07 +08:00
#define MOPT_STRING 0x0400
static const struct mount_opts {
int token;
int mount_opt;
int flags;
} ext4_mount_opts[] = {
{Opt_minix_df, EXT4_MOUNT_MINIX_DF, MOPT_SET},
{Opt_bsd_df, EXT4_MOUNT_MINIX_DF, MOPT_CLEAR},
{Opt_grpid, EXT4_MOUNT_GRPID, MOPT_SET},
{Opt_nogrpid, EXT4_MOUNT_GRPID, MOPT_CLEAR},
{Opt_block_validity, EXT4_MOUNT_BLOCK_VALIDITY, MOPT_SET},
{Opt_noblock_validity, EXT4_MOUNT_BLOCK_VALIDITY, MOPT_CLEAR},
{Opt_dioread_nolock, EXT4_MOUNT_DIOREAD_NOLOCK,
MOPT_EXT4_ONLY | MOPT_SET},
{Opt_dioread_lock, EXT4_MOUNT_DIOREAD_NOLOCK,
MOPT_EXT4_ONLY | MOPT_CLEAR},
{Opt_discard, EXT4_MOUNT_DISCARD, MOPT_SET},
{Opt_nodiscard, EXT4_MOUNT_DISCARD, MOPT_CLEAR},
{Opt_delalloc, EXT4_MOUNT_DELALLOC,
MOPT_EXT4_ONLY | MOPT_SET | MOPT_EXPLICIT},
{Opt_nodelalloc, EXT4_MOUNT_DELALLOC,
MOPT_EXT4_ONLY | MOPT_CLEAR},
{Opt_nojournal_checksum, EXT4_MOUNT_JOURNAL_CHECKSUM,
MOPT_EXT4_ONLY | MOPT_CLEAR},
{Opt_journal_checksum, EXT4_MOUNT_JOURNAL_CHECKSUM,
MOPT_EXT4_ONLY | MOPT_SET | MOPT_EXPLICIT},
{Opt_journal_async_commit, (EXT4_MOUNT_JOURNAL_ASYNC_COMMIT |
EXT4_MOUNT_JOURNAL_CHECKSUM),
MOPT_EXT4_ONLY | MOPT_SET | MOPT_EXPLICIT},
{Opt_noload, EXT4_MOUNT_NOLOAD, MOPT_NO_EXT2 | MOPT_SET},
{Opt_err_panic, EXT4_MOUNT_ERRORS_PANIC, MOPT_SET | MOPT_CLEAR_ERR},
{Opt_err_ro, EXT4_MOUNT_ERRORS_RO, MOPT_SET | MOPT_CLEAR_ERR},
{Opt_err_cont, EXT4_MOUNT_ERRORS_CONT, MOPT_SET | MOPT_CLEAR_ERR},
{Opt_data_err_abort, EXT4_MOUNT_DATA_ERR_ABORT,
MOPT_NO_EXT2},
{Opt_data_err_ignore, EXT4_MOUNT_DATA_ERR_ABORT,
MOPT_NO_EXT2},
{Opt_barrier, EXT4_MOUNT_BARRIER, MOPT_SET},
{Opt_nobarrier, EXT4_MOUNT_BARRIER, MOPT_CLEAR},
{Opt_noauto_da_alloc, EXT4_MOUNT_NO_AUTO_DA_ALLOC, MOPT_SET},
{Opt_auto_da_alloc, EXT4_MOUNT_NO_AUTO_DA_ALLOC, MOPT_CLEAR},
{Opt_noinit_itable, EXT4_MOUNT_INIT_INODE_TABLE, MOPT_CLEAR},
{Opt_commit, 0, MOPT_GTE0},
{Opt_max_batch_time, 0, MOPT_GTE0},
{Opt_min_batch_time, 0, MOPT_GTE0},
{Opt_inode_readahead_blks, 0, MOPT_GTE0},
{Opt_init_itable, 0, MOPT_GTE0},
{Opt_dax, EXT4_MOUNT_DAX, MOPT_SET},
{Opt_stripe, 0, MOPT_GTE0},
{Opt_resuid, 0, MOPT_GTE0},
{Opt_resgid, 0, MOPT_GTE0},
{Opt_journal_dev, 0, MOPT_NO_EXT2 | MOPT_GTE0},
{Opt_journal_path, 0, MOPT_NO_EXT2 | MOPT_STRING},
{Opt_journal_ioprio, 0, MOPT_NO_EXT2 | MOPT_GTE0},
{Opt_data_journal, EXT4_MOUNT_JOURNAL_DATA, MOPT_NO_EXT2 | MOPT_DATAJ},
{Opt_data_ordered, EXT4_MOUNT_ORDERED_DATA, MOPT_NO_EXT2 | MOPT_DATAJ},
{Opt_data_writeback, EXT4_MOUNT_WRITEBACK_DATA,
MOPT_NO_EXT2 | MOPT_DATAJ},
{Opt_user_xattr, EXT4_MOUNT_XATTR_USER, MOPT_SET},
{Opt_nouser_xattr, EXT4_MOUNT_XATTR_USER, MOPT_CLEAR},
#ifdef CONFIG_EXT4_FS_POSIX_ACL
{Opt_acl, EXT4_MOUNT_POSIX_ACL, MOPT_SET},
{Opt_noacl, EXT4_MOUNT_POSIX_ACL, MOPT_CLEAR},
#else
{Opt_acl, 0, MOPT_NOSUPPORT},
{Opt_noacl, 0, MOPT_NOSUPPORT},
#endif
{Opt_nouid32, EXT4_MOUNT_NO_UID32, MOPT_SET},
{Opt_debug, EXT4_MOUNT_DEBUG, MOPT_SET},
{Opt_quota, EXT4_MOUNT_QUOTA | EXT4_MOUNT_USRQUOTA, MOPT_SET | MOPT_Q},
{Opt_usrquota, EXT4_MOUNT_QUOTA | EXT4_MOUNT_USRQUOTA,
MOPT_SET | MOPT_Q},
{Opt_grpquota, EXT4_MOUNT_QUOTA | EXT4_MOUNT_GRPQUOTA,
MOPT_SET | MOPT_Q},
{Opt_prjquota, EXT4_MOUNT_QUOTA | EXT4_MOUNT_PRJQUOTA,
MOPT_SET | MOPT_Q},
{Opt_noquota, (EXT4_MOUNT_QUOTA | EXT4_MOUNT_USRQUOTA |
EXT4_MOUNT_GRPQUOTA | EXT4_MOUNT_PRJQUOTA),
MOPT_CLEAR | MOPT_Q},
{Opt_usrjquota, 0, MOPT_Q},
{Opt_grpjquota, 0, MOPT_Q},
{Opt_offusrjquota, 0, MOPT_Q},
{Opt_offgrpjquota, 0, MOPT_Q},
{Opt_jqfmt_vfsold, QFMT_VFS_OLD, MOPT_QFMT},
{Opt_jqfmt_vfsv0, QFMT_VFS_V0, MOPT_QFMT},
{Opt_jqfmt_vfsv1, QFMT_VFS_V1, MOPT_QFMT},
{Opt_max_dir_size_kb, 0, MOPT_GTE0},
{Opt_test_dummy_encryption, 0, MOPT_GTE0},
{Opt_err, 0, 0}
};
static int handle_mount_opt(struct super_block *sb, char *opt, int token,
substring_t *args, unsigned long *journal_devnum,
unsigned int *journal_ioprio, int is_remount)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
const struct mount_opts *m;
kuid_t uid;
kgid_t gid;
int arg = 0;
#ifdef CONFIG_QUOTA
if (token == Opt_usrjquota)
return set_qf_name(sb, USRQUOTA, &args[0]);
else if (token == Opt_grpjquota)
return set_qf_name(sb, GRPQUOTA, &args[0]);
else if (token == Opt_offusrjquota)
return clear_qf_name(sb, USRQUOTA);
else if (token == Opt_offgrpjquota)
return clear_qf_name(sb, GRPQUOTA);
#endif
switch (token) {
case Opt_noacl:
case Opt_nouser_xattr:
ext4_msg(sb, KERN_WARNING, deprecated_msg, opt, "3.5");
break;
case Opt_sb:
return 1; /* handled by get_sb_block() */
case Opt_removed:
ext4_msg(sb, KERN_WARNING, "Ignoring removed %s option", opt);
return 1;
case Opt_abort:
sbi->s_mount_flags |= EXT4_MF_FS_ABORTED;
return 1;
case Opt_i_version:
sb->s_flags |= MS_I_VERSION;
return 1;
case Opt_lazytime:
sb->s_flags |= MS_LAZYTIME;
return 1;
case Opt_nolazytime:
sb->s_flags &= ~MS_LAZYTIME;
return 1;
}
for (m = ext4_mount_opts; m->token != Opt_err; m++)
if (token == m->token)
break;
if (m->token == Opt_err) {
ext4_msg(sb, KERN_ERR, "Unrecognized mount option \"%s\" "
"or missing value", opt);
return -1;
}
if ((m->flags & MOPT_NO_EXT2) && IS_EXT2_SB(sb)) {
ext4_msg(sb, KERN_ERR,
"Mount option \"%s\" incompatible with ext2", opt);
return -1;
}
if ((m->flags & MOPT_NO_EXT3) && IS_EXT3_SB(sb)) {
ext4_msg(sb, KERN_ERR,
"Mount option \"%s\" incompatible with ext3", opt);
return -1;
}
ext4: allow specifying external journal by pathname mount option It's always been a hassle that if an external journal's device number changes, the filesystem won't mount. And since boot-time enumeration can change, device number changes aren't unusual. The current mechanism to update the journal location is by passing in a mount option w/ a new devnum, but that's a hassle; it's a manual approach, fixing things after the fact. Adding a mount option, "-o journal_path=/dev/$DEVICE" would help, since then we can do i.e. # mount -o journal_path=/dev/disk/by-label/$JOURNAL_LABEL ... and it'll mount even if the devnum has changed, as shown here: # losetup /dev/loop0 journalfile # mke2fs -L mylabel-journal -O journal_dev /dev/loop0 # mkfs.ext4 -L mylabel -J device=/dev/loop0 /dev/sdb1 Change the journal device number: # losetup -d /dev/loop0 # losetup /dev/loop1 journalfile And today it will fail: # mount /dev/sdb1 /mnt/test mount: wrong fs type, bad option, bad superblock on /dev/sdb1, missing codepage or helper program, or other error In some cases useful info is found in syslog - try dmesg | tail or so # dmesg | tail -n 1 [17343.240702] EXT4-fs (sdb1): error: couldn't read superblock of external journal But with this new mount option, we can specify the new path: # mount -o journal_path=/dev/loop1 /dev/sdb1 /mnt/test # (which does update the encoded device number, incidentally): # umount /dev/sdb1 # dumpe2fs -h /dev/sdb1 | grep "Journal device" dumpe2fs 1.41.12 (17-May-2010) Journal device: 0x0701 But best of all we can just always mount by journal-path, and it'll always work: # mount -o journal_path=/dev/disk/by-label/mylabel-journal /dev/sdb1 /mnt/test # So the journal_path option can be specified in fstab, and as long as the disk is available somewhere, and findable by label (or by UUID), we can mount. Signed-off-by: Eric Sandeen <sandeen@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu> Reviewed-by: Jan Kara <jack@suse.cz> Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
2013-08-29 07:05:07 +08:00
if (args->from && !(m->flags & MOPT_STRING) && match_int(args, &arg))
return -1;
if (args->from && (m->flags & MOPT_GTE0) && (arg < 0))
return -1;
if (m->flags & MOPT_EXPLICIT) {
if (m->mount_opt & EXT4_MOUNT_DELALLOC) {
set_opt2(sb, EXPLICIT_DELALLOC);
} else if (m->mount_opt & EXT4_MOUNT_JOURNAL_CHECKSUM) {
set_opt2(sb, EXPLICIT_JOURNAL_CHECKSUM);
} else
return -1;
}
if (m->flags & MOPT_CLEAR_ERR)
clear_opt(sb, ERRORS_MASK);
if (token == Opt_noquota && sb_any_quota_loaded(sb)) {
ext4_msg(sb, KERN_ERR, "Cannot change quota "
"options when quota turned on");
return -1;
}
if (m->flags & MOPT_NOSUPPORT) {
ext4_msg(sb, KERN_ERR, "%s option not supported", opt);
} else if (token == Opt_commit) {
if (arg == 0)
arg = JBD2_DEFAULT_MAX_COMMIT_AGE;
sbi->s_commit_interval = HZ * arg;
} else if (token == Opt_max_batch_time) {
sbi->s_max_batch_time = arg;
} else if (token == Opt_min_batch_time) {
sbi->s_min_batch_time = arg;
} else if (token == Opt_inode_readahead_blks) {
if (arg && (arg > (1 << 30) || !is_power_of_2(arg))) {
ext4_msg(sb, KERN_ERR,
"EXT4-fs: inode_readahead_blks must be "
"0 or a power of 2 smaller than 2^31");
return -1;
}
sbi->s_inode_readahead_blks = arg;
} else if (token == Opt_init_itable) {
set_opt(sb, INIT_INODE_TABLE);
if (!args->from)
arg = EXT4_DEF_LI_WAIT_MULT;
sbi->s_li_wait_mult = arg;
} else if (token == Opt_max_dir_size_kb) {
sbi->s_max_dir_size_kb = arg;
} else if (token == Opt_stripe) {
sbi->s_stripe = arg;
} else if (token == Opt_resuid) {
uid = make_kuid(current_user_ns(), arg);
if (!uid_valid(uid)) {
ext4_msg(sb, KERN_ERR, "Invalid uid value %d", arg);
return -1;
}
sbi->s_resuid = uid;
} else if (token == Opt_resgid) {
gid = make_kgid(current_user_ns(), arg);
if (!gid_valid(gid)) {
ext4_msg(sb, KERN_ERR, "Invalid gid value %d", arg);
return -1;
}
sbi->s_resgid = gid;
} else if (token == Opt_journal_dev) {
if (is_remount) {
ext4_msg(sb, KERN_ERR,
"Cannot specify journal on remount");
return -1;
}
*journal_devnum = arg;
ext4: allow specifying external journal by pathname mount option It's always been a hassle that if an external journal's device number changes, the filesystem won't mount. And since boot-time enumeration can change, device number changes aren't unusual. The current mechanism to update the journal location is by passing in a mount option w/ a new devnum, but that's a hassle; it's a manual approach, fixing things after the fact. Adding a mount option, "-o journal_path=/dev/$DEVICE" would help, since then we can do i.e. # mount -o journal_path=/dev/disk/by-label/$JOURNAL_LABEL ... and it'll mount even if the devnum has changed, as shown here: # losetup /dev/loop0 journalfile # mke2fs -L mylabel-journal -O journal_dev /dev/loop0 # mkfs.ext4 -L mylabel -J device=/dev/loop0 /dev/sdb1 Change the journal device number: # losetup -d /dev/loop0 # losetup /dev/loop1 journalfile And today it will fail: # mount /dev/sdb1 /mnt/test mount: wrong fs type, bad option, bad superblock on /dev/sdb1, missing codepage or helper program, or other error In some cases useful info is found in syslog - try dmesg | tail or so # dmesg | tail -n 1 [17343.240702] EXT4-fs (sdb1): error: couldn't read superblock of external journal But with this new mount option, we can specify the new path: # mount -o journal_path=/dev/loop1 /dev/sdb1 /mnt/test # (which does update the encoded device number, incidentally): # umount /dev/sdb1 # dumpe2fs -h /dev/sdb1 | grep "Journal device" dumpe2fs 1.41.12 (17-May-2010) Journal device: 0x0701 But best of all we can just always mount by journal-path, and it'll always work: # mount -o journal_path=/dev/disk/by-label/mylabel-journal /dev/sdb1 /mnt/test # So the journal_path option can be specified in fstab, and as long as the disk is available somewhere, and findable by label (or by UUID), we can mount. Signed-off-by: Eric Sandeen <sandeen@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu> Reviewed-by: Jan Kara <jack@suse.cz> Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
2013-08-29 07:05:07 +08:00
} else if (token == Opt_journal_path) {
char *journal_path;
struct inode *journal_inode;
struct path path;
int error;
if (is_remount) {
ext4_msg(sb, KERN_ERR,
"Cannot specify journal on remount");
return -1;
}
journal_path = match_strdup(&args[0]);
if (!journal_path) {
ext4_msg(sb, KERN_ERR, "error: could not dup "
"journal device string");
return -1;
}
error = kern_path(journal_path, LOOKUP_FOLLOW, &path);
if (error) {
ext4_msg(sb, KERN_ERR, "error: could not find "
"journal device path: error %d", error);
kfree(journal_path);
return -1;
}
journal_inode = d_inode(path.dentry);
ext4: allow specifying external journal by pathname mount option It's always been a hassle that if an external journal's device number changes, the filesystem won't mount. And since boot-time enumeration can change, device number changes aren't unusual. The current mechanism to update the journal location is by passing in a mount option w/ a new devnum, but that's a hassle; it's a manual approach, fixing things after the fact. Adding a mount option, "-o journal_path=/dev/$DEVICE" would help, since then we can do i.e. # mount -o journal_path=/dev/disk/by-label/$JOURNAL_LABEL ... and it'll mount even if the devnum has changed, as shown here: # losetup /dev/loop0 journalfile # mke2fs -L mylabel-journal -O journal_dev /dev/loop0 # mkfs.ext4 -L mylabel -J device=/dev/loop0 /dev/sdb1 Change the journal device number: # losetup -d /dev/loop0 # losetup /dev/loop1 journalfile And today it will fail: # mount /dev/sdb1 /mnt/test mount: wrong fs type, bad option, bad superblock on /dev/sdb1, missing codepage or helper program, or other error In some cases useful info is found in syslog - try dmesg | tail or so # dmesg | tail -n 1 [17343.240702] EXT4-fs (sdb1): error: couldn't read superblock of external journal But with this new mount option, we can specify the new path: # mount -o journal_path=/dev/loop1 /dev/sdb1 /mnt/test # (which does update the encoded device number, incidentally): # umount /dev/sdb1 # dumpe2fs -h /dev/sdb1 | grep "Journal device" dumpe2fs 1.41.12 (17-May-2010) Journal device: 0x0701 But best of all we can just always mount by journal-path, and it'll always work: # mount -o journal_path=/dev/disk/by-label/mylabel-journal /dev/sdb1 /mnt/test # So the journal_path option can be specified in fstab, and as long as the disk is available somewhere, and findable by label (or by UUID), we can mount. Signed-off-by: Eric Sandeen <sandeen@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu> Reviewed-by: Jan Kara <jack@suse.cz> Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
2013-08-29 07:05:07 +08:00
if (!S_ISBLK(journal_inode->i_mode)) {
ext4_msg(sb, KERN_ERR, "error: journal path %s "
"is not a block device", journal_path);
path_put(&path);
kfree(journal_path);
return -1;
}
*journal_devnum = new_encode_dev(journal_inode->i_rdev);
path_put(&path);
kfree(journal_path);
} else if (token == Opt_journal_ioprio) {
if (arg > 7) {
ext4_msg(sb, KERN_ERR, "Invalid journal IO priority"
" (must be 0-7)");
return -1;
}
*journal_ioprio =
IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, arg);
} else if (token == Opt_test_dummy_encryption) {
#ifdef CONFIG_EXT4_FS_ENCRYPTION
sbi->s_mount_flags |= EXT4_MF_TEST_DUMMY_ENCRYPTION;
ext4_msg(sb, KERN_WARNING,
"Test dummy encryption mode enabled");
#else
ext4_msg(sb, KERN_WARNING,
"Test dummy encryption mount option ignored");
#endif
} else if (m->flags & MOPT_DATAJ) {
if (is_remount) {
if (!sbi->s_journal)
ext4_msg(sb, KERN_WARNING, "Remounting file system with no journal so ignoring journalled data option");
else if (test_opt(sb, DATA_FLAGS) != m->mount_opt) {
ext4_msg(sb, KERN_ERR,
"Cannot change data mode on remount");
return -1;
}
} else {
clear_opt(sb, DATA_FLAGS);
sbi->s_mount_opt |= m->mount_opt;
}
#ifdef CONFIG_QUOTA
} else if (m->flags & MOPT_QFMT) {
if (sb_any_quota_loaded(sb) &&
sbi->s_jquota_fmt != m->mount_opt) {
ext4_msg(sb, KERN_ERR, "Cannot change journaled "
"quota options when quota turned on");
return -1;
}
if (ext4_has_feature_quota(sb)) {
ext4_msg(sb, KERN_INFO,
"Quota format mount options ignored "
"when QUOTA feature is enabled");
return 1;
}
sbi->s_jquota_fmt = m->mount_opt;
#endif
} else if (token == Opt_dax) {
#ifdef CONFIG_FS_DAX
ext4_msg(sb, KERN_WARNING,
"DAX enabled. Warning: EXPERIMENTAL, use at your own risk");
sbi->s_mount_opt |= m->mount_opt;
#else
ext4_msg(sb, KERN_INFO, "dax option not supported");
return -1;
#endif
} else if (token == Opt_data_err_abort) {
sbi->s_mount_opt |= m->mount_opt;
} else if (token == Opt_data_err_ignore) {
sbi->s_mount_opt &= ~m->mount_opt;
} else {
if (!args->from)
arg = 1;
if (m->flags & MOPT_CLEAR)
arg = !arg;
else if (unlikely(!(m->flags & MOPT_SET))) {
ext4_msg(sb, KERN_WARNING,
"buggy handling of option %s", opt);
WARN_ON(1);
return -1;
}
if (arg != 0)
sbi->s_mount_opt |= m->mount_opt;
else
sbi->s_mount_opt &= ~m->mount_opt;
}
return 1;
}
static int parse_options(char *options, struct super_block *sb,
unsigned long *journal_devnum,
unsigned int *journal_ioprio,
int is_remount)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
char *p;
substring_t args[MAX_OPT_ARGS];
int token;
if (!options)
return 1;
while ((p = strsep(&options, ",")) != NULL) {
if (!*p)
continue;
/*
* Initialize args struct so we know whether arg was
* found; some options take optional arguments.
*/
args[0].to = args[0].from = NULL;
token = match_token(p, tokens, args);
if (handle_mount_opt(sb, p, token, args, journal_devnum,
journal_ioprio, is_remount) < 0)
return 0;
}
#ifdef CONFIG_QUOTA
/*
* We do the test below only for project quotas. 'usrquota' and
* 'grpquota' mount options are allowed even without quota feature
* to support legacy quotas in quota files.
*/
if (test_opt(sb, PRJQUOTA) && !ext4_has_feature_project(sb)) {
ext4_msg(sb, KERN_ERR, "Project quota feature not enabled. "
"Cannot enable project quota enforcement.");
return 0;
}
if (sbi->s_qf_names[USRQUOTA] || sbi->s_qf_names[GRPQUOTA]) {
if (test_opt(sb, USRQUOTA) && sbi->s_qf_names[USRQUOTA])
clear_opt(sb, USRQUOTA);
if (test_opt(sb, GRPQUOTA) && sbi->s_qf_names[GRPQUOTA])
clear_opt(sb, GRPQUOTA);
if (test_opt(sb, GRPQUOTA) || test_opt(sb, USRQUOTA)) {
ext4_msg(sb, KERN_ERR, "old and new quota "
"format mixing");
return 0;
}
if (!sbi->s_jquota_fmt) {
ext4_msg(sb, KERN_ERR, "journaled quota format "
"not specified");
return 0;
}
}
#endif
if (test_opt(sb, DIOREAD_NOLOCK)) {
int blocksize =
BLOCK_SIZE << le32_to_cpu(sbi->s_es->s_log_block_size);
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 20:29:47 +08:00
if (blocksize < PAGE_SIZE) {
ext4_msg(sb, KERN_ERR, "can't mount with "
"dioread_nolock if block size != PAGE_SIZE");
return 0;
}
}
return 1;
}
static inline void ext4_show_quota_options(struct seq_file *seq,
struct super_block *sb)
{
#if defined(CONFIG_QUOTA)
struct ext4_sb_info *sbi = EXT4_SB(sb);
if (sbi->s_jquota_fmt) {
char *fmtname = "";
switch (sbi->s_jquota_fmt) {
case QFMT_VFS_OLD:
fmtname = "vfsold";
break;
case QFMT_VFS_V0:
fmtname = "vfsv0";
break;
case QFMT_VFS_V1:
fmtname = "vfsv1";
break;
}
seq_printf(seq, ",jqfmt=%s", fmtname);
}
if (sbi->s_qf_names[USRQUOTA])
fs: create and use seq_show_option for escaping Many file systems that implement the show_options hook fail to correctly escape their output which could lead to unescaped characters (e.g. new lines) leaking into /proc/mounts and /proc/[pid]/mountinfo files. This could lead to confusion, spoofed entries (resulting in things like systemd issuing false d-bus "mount" notifications), and who knows what else. This looks like it would only be the root user stepping on themselves, but it's possible weird things could happen in containers or in other situations with delegated mount privileges. Here's an example using overlay with setuid fusermount trusting the contents of /proc/mounts (via the /etc/mtab symlink). Imagine the use of "sudo" is something more sneaky: $ BASE="ovl" $ MNT="$BASE/mnt" $ LOW="$BASE/lower" $ UP="$BASE/upper" $ WORK="$BASE/work/ 0 0 none /proc fuse.pwn user_id=1000" $ mkdir -p "$LOW" "$UP" "$WORK" $ sudo mount -t overlay -o "lowerdir=$LOW,upperdir=$UP,workdir=$WORK" none /mnt $ cat /proc/mounts none /root/ovl/mnt overlay rw,relatime,lowerdir=ovl/lower,upperdir=ovl/upper,workdir=ovl/work/ 0 0 none /proc fuse.pwn user_id=1000 0 0 $ fusermount -u /proc $ cat /proc/mounts cat: /proc/mounts: No such file or directory This fixes the problem by adding new seq_show_option and seq_show_option_n helpers, and updating the vulnerable show_option handlers to use them as needed. Some, like SELinux, need to be open coded due to unusual existing escape mechanisms. [akpm@linux-foundation.org: add lost chunk, per Kees] [keescook@chromium.org: seq_show_option should be using const parameters] Signed-off-by: Kees Cook <keescook@chromium.org> Acked-by: Serge Hallyn <serge.hallyn@canonical.com> Acked-by: Jan Kara <jack@suse.com> Acked-by: Paul Moore <paul@paul-moore.com> Cc: J. R. Okajima <hooanon05g@gmail.com> Signed-off-by: Kees Cook <keescook@chromium.org> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-05 06:44:57 +08:00
seq_show_option(seq, "usrjquota", sbi->s_qf_names[USRQUOTA]);
if (sbi->s_qf_names[GRPQUOTA])
fs: create and use seq_show_option for escaping Many file systems that implement the show_options hook fail to correctly escape their output which could lead to unescaped characters (e.g. new lines) leaking into /proc/mounts and /proc/[pid]/mountinfo files. This could lead to confusion, spoofed entries (resulting in things like systemd issuing false d-bus "mount" notifications), and who knows what else. This looks like it would only be the root user stepping on themselves, but it's possible weird things could happen in containers or in other situations with delegated mount privileges. Here's an example using overlay with setuid fusermount trusting the contents of /proc/mounts (via the /etc/mtab symlink). Imagine the use of "sudo" is something more sneaky: $ BASE="ovl" $ MNT="$BASE/mnt" $ LOW="$BASE/lower" $ UP="$BASE/upper" $ WORK="$BASE/work/ 0 0 none /proc fuse.pwn user_id=1000" $ mkdir -p "$LOW" "$UP" "$WORK" $ sudo mount -t overlay -o "lowerdir=$LOW,upperdir=$UP,workdir=$WORK" none /mnt $ cat /proc/mounts none /root/ovl/mnt overlay rw,relatime,lowerdir=ovl/lower,upperdir=ovl/upper,workdir=ovl/work/ 0 0 none /proc fuse.pwn user_id=1000 0 0 $ fusermount -u /proc $ cat /proc/mounts cat: /proc/mounts: No such file or directory This fixes the problem by adding new seq_show_option and seq_show_option_n helpers, and updating the vulnerable show_option handlers to use them as needed. Some, like SELinux, need to be open coded due to unusual existing escape mechanisms. [akpm@linux-foundation.org: add lost chunk, per Kees] [keescook@chromium.org: seq_show_option should be using const parameters] Signed-off-by: Kees Cook <keescook@chromium.org> Acked-by: Serge Hallyn <serge.hallyn@canonical.com> Acked-by: Jan Kara <jack@suse.com> Acked-by: Paul Moore <paul@paul-moore.com> Cc: J. R. Okajima <hooanon05g@gmail.com> Signed-off-by: Kees Cook <keescook@chromium.org> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-05 06:44:57 +08:00
seq_show_option(seq, "grpjquota", sbi->s_qf_names[GRPQUOTA]);
#endif
}
static const char *token2str(int token)
{
const struct match_token *t;
for (t = tokens; t->token != Opt_err; t++)
if (t->token == token && !strchr(t->pattern, '='))
break;
return t->pattern;
}
/*
* Show an option if
* - it's set to a non-default value OR
* - if the per-sb default is different from the global default
*/
static int _ext4_show_options(struct seq_file *seq, struct super_block *sb,
int nodefs)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
struct ext4_super_block *es = sbi->s_es;
int def_errors, def_mount_opt = nodefs ? 0 : sbi->s_def_mount_opt;
const struct mount_opts *m;
char sep = nodefs ? '\n' : ',';
#define SEQ_OPTS_PUTS(str) seq_printf(seq, "%c" str, sep)
#define SEQ_OPTS_PRINT(str, arg) seq_printf(seq, "%c" str, sep, arg)
if (sbi->s_sb_block != 1)
SEQ_OPTS_PRINT("sb=%llu", sbi->s_sb_block);
for (m = ext4_mount_opts; m->token != Opt_err; m++) {
int want_set = m->flags & MOPT_SET;
if (((m->flags & (MOPT_SET|MOPT_CLEAR)) == 0) ||
(m->flags & MOPT_CLEAR_ERR))
continue;
if (!(m->mount_opt & (sbi->s_mount_opt ^ def_mount_opt)))
continue; /* skip if same as the default */
if ((want_set &&
(sbi->s_mount_opt & m->mount_opt) != m->mount_opt) ||
(!want_set && (sbi->s_mount_opt & m->mount_opt)))
continue; /* select Opt_noFoo vs Opt_Foo */
SEQ_OPTS_PRINT("%s", token2str(m->token));
}
if (nodefs || !uid_eq(sbi->s_resuid, make_kuid(&init_user_ns, EXT4_DEF_RESUID)) ||
le16_to_cpu(es->s_def_resuid) != EXT4_DEF_RESUID)
SEQ_OPTS_PRINT("resuid=%u",
from_kuid_munged(&init_user_ns, sbi->s_resuid));
if (nodefs || !gid_eq(sbi->s_resgid, make_kgid(&init_user_ns, EXT4_DEF_RESGID)) ||
le16_to_cpu(es->s_def_resgid) != EXT4_DEF_RESGID)
SEQ_OPTS_PRINT("resgid=%u",
from_kgid_munged(&init_user_ns, sbi->s_resgid));
def_errors = nodefs ? -1 : le16_to_cpu(es->s_errors);
if (test_opt(sb, ERRORS_RO) && def_errors != EXT4_ERRORS_RO)
SEQ_OPTS_PUTS("errors=remount-ro");
if (test_opt(sb, ERRORS_CONT) && def_errors != EXT4_ERRORS_CONTINUE)
SEQ_OPTS_PUTS("errors=continue");
if (test_opt(sb, ERRORS_PANIC) && def_errors != EXT4_ERRORS_PANIC)
SEQ_OPTS_PUTS("errors=panic");
if (nodefs || sbi->s_commit_interval != JBD2_DEFAULT_MAX_COMMIT_AGE*HZ)
SEQ_OPTS_PRINT("commit=%lu", sbi->s_commit_interval / HZ);
if (nodefs || sbi->s_min_batch_time != EXT4_DEF_MIN_BATCH_TIME)
SEQ_OPTS_PRINT("min_batch_time=%u", sbi->s_min_batch_time);
if (nodefs || sbi->s_max_batch_time != EXT4_DEF_MAX_BATCH_TIME)
SEQ_OPTS_PRINT("max_batch_time=%u", sbi->s_max_batch_time);
if (sb->s_flags & MS_I_VERSION)
SEQ_OPTS_PUTS("i_version");
if (nodefs || sbi->s_stripe)
SEQ_OPTS_PRINT("stripe=%lu", sbi->s_stripe);
if (EXT4_MOUNT_DATA_FLAGS & (sbi->s_mount_opt ^ def_mount_opt)) {
if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA)
SEQ_OPTS_PUTS("data=journal");
else if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA)
SEQ_OPTS_PUTS("data=ordered");
else if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA)
SEQ_OPTS_PUTS("data=writeback");
}
if (nodefs ||
sbi->s_inode_readahead_blks != EXT4_DEF_INODE_READAHEAD_BLKS)
SEQ_OPTS_PRINT("inode_readahead_blks=%u",
sbi->s_inode_readahead_blks);
if (nodefs || (test_opt(sb, INIT_INODE_TABLE) &&
(sbi->s_li_wait_mult != EXT4_DEF_LI_WAIT_MULT)))
SEQ_OPTS_PRINT("init_itable=%u", sbi->s_li_wait_mult);
if (nodefs || sbi->s_max_dir_size_kb)
SEQ_OPTS_PRINT("max_dir_size_kb=%u", sbi->s_max_dir_size_kb);
if (test_opt(sb, DATA_ERR_ABORT))
SEQ_OPTS_PUTS("data_err=abort");
ext4_show_quota_options(seq, sb);
return 0;
}
static int ext4_show_options(struct seq_file *seq, struct dentry *root)
{
return _ext4_show_options(seq, root->d_sb, 0);
}
int ext4_seq_options_show(struct seq_file *seq, void *offset)
{
struct super_block *sb = seq->private;
int rc;
seq_puts(seq, (sb->s_flags & MS_RDONLY) ? "ro" : "rw");
rc = _ext4_show_options(seq, sb, 1);
seq_puts(seq, "\n");
return rc;
}
static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es,
int read_only)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
int res = 0;
if (le32_to_cpu(es->s_rev_level) > EXT4_MAX_SUPP_REV) {
ext4_msg(sb, KERN_ERR, "revision level too high, "
"forcing read-only mode");
res = MS_RDONLY;
}
if (read_only)
goto done;
if (!(sbi->s_mount_state & EXT4_VALID_FS))
ext4_msg(sb, KERN_WARNING, "warning: mounting unchecked fs, "
"running e2fsck is recommended");
else if (sbi->s_mount_state & EXT4_ERROR_FS)
ext4_msg(sb, KERN_WARNING,
"warning: mounting fs with errors, "
"running e2fsck is recommended");
else if ((__s16) le16_to_cpu(es->s_max_mnt_count) > 0 &&
le16_to_cpu(es->s_mnt_count) >=
(unsigned short) (__s16) le16_to_cpu(es->s_max_mnt_count))
ext4_msg(sb, KERN_WARNING,
"warning: maximal mount count reached, "
"running e2fsck is recommended");
else if (le32_to_cpu(es->s_checkinterval) &&
(le32_to_cpu(es->s_lastcheck) +
le32_to_cpu(es->s_checkinterval) <= get_seconds()))
ext4_msg(sb, KERN_WARNING,
"warning: checktime reached, "
"running e2fsck is recommended");
if (!sbi->s_journal)
es->s_state &= cpu_to_le16(~EXT4_VALID_FS);
if (!(__s16) le16_to_cpu(es->s_max_mnt_count))
es->s_max_mnt_count = cpu_to_le16(EXT4_DFL_MAX_MNT_COUNT);
le16_add_cpu(&es->s_mnt_count, 1);
es->s_mtime = cpu_to_le32(get_seconds());
ext4_update_dynamic_rev(sb);
if (sbi->s_journal)
ext4_set_feature_journal_needs_recovery(sb);
ext4_commit_super(sb, 1);
done:
if (test_opt(sb, DEBUG))
printk(KERN_INFO "[EXT4 FS bs=%lu, gc=%u, "
"bpg=%lu, ipg=%lu, mo=%04x, mo2=%04x]\n",
sb->s_blocksize,
sbi->s_groups_count,
EXT4_BLOCKS_PER_GROUP(sb),
EXT4_INODES_PER_GROUP(sb),
sbi->s_mount_opt, sbi->s_mount_opt2);
cleancache_init_fs(sb);
return res;
}
int ext4_alloc_flex_bg_array(struct super_block *sb, ext4_group_t ngroup)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
struct flex_groups *new_groups;
int size;
if (!sbi->s_log_groups_per_flex)
return 0;
size = ext4_flex_group(sbi, ngroup - 1) + 1;
if (size <= sbi->s_flex_groups_allocated)
return 0;
size = roundup_pow_of_two(size * sizeof(struct flex_groups));
new_groups = ext4_kvzalloc(size, GFP_KERNEL);
if (!new_groups) {
ext4_msg(sb, KERN_ERR, "not enough memory for %d flex groups",
size / (int) sizeof(struct flex_groups));
return -ENOMEM;
}
if (sbi->s_flex_groups) {
memcpy(new_groups, sbi->s_flex_groups,
(sbi->s_flex_groups_allocated *
sizeof(struct flex_groups)));
kvfree(sbi->s_flex_groups);
}
sbi->s_flex_groups = new_groups;
sbi->s_flex_groups_allocated = size / sizeof(struct flex_groups);
return 0;
}
static int ext4_fill_flex_info(struct super_block *sb)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
struct ext4_group_desc *gdp = NULL;
ext4_group_t flex_group;
int i, err;
sbi->s_log_groups_per_flex = sbi->s_es->s_log_groups_per_flex;
ext4: fix undefined behavior in ext4_fill_flex_info() Commit 503358ae01b70ce6909d19dd01287093f6b6271c ("ext4: avoid divide by zero when trying to mount a corrupted file system") fixes CVE-2009-4307 by performing a sanity check on s_log_groups_per_flex, since it can be set to a bogus value by an attacker. sbi->s_log_groups_per_flex = sbi->s_es->s_log_groups_per_flex; groups_per_flex = 1 << sbi->s_log_groups_per_flex; if (groups_per_flex < 2) { ... } This patch fixes two potential issues in the previous commit. 1) The sanity check might only work on architectures like PowerPC. On x86, 5 bits are used for the shifting amount. That means, given a large s_log_groups_per_flex value like 36, groups_per_flex = 1 << 36 is essentially 1 << 4 = 16, rather than 0. This will bypass the check, leaving s_log_groups_per_flex and groups_per_flex inconsistent. 2) The sanity check relies on undefined behavior, i.e., oversized shift. A standard-confirming C compiler could rewrite the check in unexpected ways. Consider the following equivalent form, assuming groups_per_flex is unsigned for simplicity. groups_per_flex = 1 << sbi->s_log_groups_per_flex; if (groups_per_flex == 0 || groups_per_flex == 1) { We compile the code snippet using Clang 3.0 and GCC 4.6. Clang will completely optimize away the check groups_per_flex == 0, leaving the patched code as vulnerable as the original. GCC keeps the check, but there is no guarantee that future versions will do the same. Signed-off-by: Xi Wang <xi.wang@gmail.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu> Cc: stable@vger.kernel.org
2012-01-11 00:51:10 +08:00
if (sbi->s_log_groups_per_flex < 1 || sbi->s_log_groups_per_flex > 31) {
sbi->s_log_groups_per_flex = 0;
return 1;
}
err = ext4_alloc_flex_bg_array(sb, sbi->s_groups_count);
if (err)
goto failed;
for (i = 0; i < sbi->s_groups_count; i++) {
gdp = ext4_get_group_desc(sb, i, NULL);
flex_group = ext4_flex_group(sbi, i);
atomic_add(ext4_free_inodes_count(sb, gdp),
&sbi->s_flex_groups[flex_group].free_inodes);
atomic64_add(ext4_free_group_clusters(sb, gdp),
&sbi->s_flex_groups[flex_group].free_clusters);
atomic_add(ext4_used_dirs_count(sb, gdp),
&sbi->s_flex_groups[flex_group].used_dirs);
}
return 1;
failed:
return 0;
}
static __le16 ext4_group_desc_csum(struct super_block *sb, __u32 block_group,
struct ext4_group_desc *gdp)
Ext4: Uninitialized Block Groups In pass1 of e2fsck, every inode table in the fileystem is scanned and checked, regardless of whether it is in use. This is this the most time consuming part of the filesystem check. The unintialized block group feature can greatly reduce e2fsck time by eliminating checking of uninitialized inodes. With this feature, there is a a high water mark of used inodes for each block group. Block and inode bitmaps can be uninitialized on disk via a flag in the group descriptor to avoid reading or scanning them at e2fsck time. A checksum of each group descriptor is used to ensure that corruption in the group descriptor's bit flags does not cause incorrect operation. The feature is enabled through a mkfs option mke2fs /dev/ -O uninit_groups A patch adding support for uninitialized block groups to e2fsprogs tools has been posted to the linux-ext4 mailing list. The patches have been stress tested with fsstress and fsx. In performance tests testing e2fsck time, we have seen that e2fsck time on ext3 grows linearly with the total number of inodes in the filesytem. In ext4 with the uninitialized block groups feature, the e2fsck time is constant, based solely on the number of used inodes rather than the total inode count. Since typical ext4 filesystems only use 1-10% of their inodes, this feature can greatly reduce e2fsck time for users. With performance improvement of 2-20 times, depending on how full the filesystem is. The attached graph shows the major improvements in e2fsck times in filesystems with a large total inode count, but few inodes in use. In each group descriptor if we have EXT4_BG_INODE_UNINIT set in bg_flags: Inode table is not initialized/used in this group. So we can skip the consistency check during fsck. EXT4_BG_BLOCK_UNINIT set in bg_flags: No block in the group is used. So we can skip the block bitmap verification for this group. We also add two new fields to group descriptor as a part of uninitialized group patch. __le16 bg_itable_unused; /* Unused inodes count */ __le16 bg_checksum; /* crc16(sb_uuid+group+desc) */ bg_itable_unused: If we have EXT4_BG_INODE_UNINIT not set in bg_flags then bg_itable_unused will give the offset within the inode table till the inodes are used. This can be used by fsck to skip list of inodes that are marked unused. bg_checksum: Now that we depend on bg_flags and bg_itable_unused to determine the block and inode usage, we need to make sure group descriptor is not corrupt. We add checksum to group descriptor to detect corruption. If the descriptor is found to be corrupt, we mark all the blocks and inodes in the group used. Signed-off-by: Avantika Mathur <mathur@us.ibm.com> Signed-off-by: Andreas Dilger <adilger@clusterfs.com> Signed-off-by: Mingming Cao <cmm@us.ibm.com> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
2007-10-17 06:38:25 +08:00
{
int offset = offsetof(struct ext4_group_desc, bg_checksum);
Ext4: Uninitialized Block Groups In pass1 of e2fsck, every inode table in the fileystem is scanned and checked, regardless of whether it is in use. This is this the most time consuming part of the filesystem check. The unintialized block group feature can greatly reduce e2fsck time by eliminating checking of uninitialized inodes. With this feature, there is a a high water mark of used inodes for each block group. Block and inode bitmaps can be uninitialized on disk via a flag in the group descriptor to avoid reading or scanning them at e2fsck time. A checksum of each group descriptor is used to ensure that corruption in the group descriptor's bit flags does not cause incorrect operation. The feature is enabled through a mkfs option mke2fs /dev/ -O uninit_groups A patch adding support for uninitialized block groups to e2fsprogs tools has been posted to the linux-ext4 mailing list. The patches have been stress tested with fsstress and fsx. In performance tests testing e2fsck time, we have seen that e2fsck time on ext3 grows linearly with the total number of inodes in the filesytem. In ext4 with the uninitialized block groups feature, the e2fsck time is constant, based solely on the number of used inodes rather than the total inode count. Since typical ext4 filesystems only use 1-10% of their inodes, this feature can greatly reduce e2fsck time for users. With performance improvement of 2-20 times, depending on how full the filesystem is. The attached graph shows the major improvements in e2fsck times in filesystems with a large total inode count, but few inodes in use. In each group descriptor if we have EXT4_BG_INODE_UNINIT set in bg_flags: Inode table is not initialized/used in this group. So we can skip the consistency check during fsck. EXT4_BG_BLOCK_UNINIT set in bg_flags: No block in the group is used. So we can skip the block bitmap verification for this group. We also add two new fields to group descriptor as a part of uninitialized group patch. __le16 bg_itable_unused; /* Unused inodes count */ __le16 bg_checksum; /* crc16(sb_uuid+group+desc) */ bg_itable_unused: If we have EXT4_BG_INODE_UNINIT not set in bg_flags then bg_itable_unused will give the offset within the inode table till the inodes are used. This can be used by fsck to skip list of inodes that are marked unused. bg_checksum: Now that we depend on bg_flags and bg_itable_unused to determine the block and inode usage, we need to make sure group descriptor is not corrupt. We add checksum to group descriptor to detect corruption. If the descriptor is found to be corrupt, we mark all the blocks and inodes in the group used. Signed-off-by: Avantika Mathur <mathur@us.ibm.com> Signed-off-by: Andreas Dilger <adilger@clusterfs.com> Signed-off-by: Mingming Cao <cmm@us.ibm.com> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
2007-10-17 06:38:25 +08:00
__u16 crc = 0;
__le32 le_group = cpu_to_le32(block_group);
struct ext4_sb_info *sbi = EXT4_SB(sb);
Ext4: Uninitialized Block Groups In pass1 of e2fsck, every inode table in the fileystem is scanned and checked, regardless of whether it is in use. This is this the most time consuming part of the filesystem check. The unintialized block group feature can greatly reduce e2fsck time by eliminating checking of uninitialized inodes. With this feature, there is a a high water mark of used inodes for each block group. Block and inode bitmaps can be uninitialized on disk via a flag in the group descriptor to avoid reading or scanning them at e2fsck time. A checksum of each group descriptor is used to ensure that corruption in the group descriptor's bit flags does not cause incorrect operation. The feature is enabled through a mkfs option mke2fs /dev/ -O uninit_groups A patch adding support for uninitialized block groups to e2fsprogs tools has been posted to the linux-ext4 mailing list. The patches have been stress tested with fsstress and fsx. In performance tests testing e2fsck time, we have seen that e2fsck time on ext3 grows linearly with the total number of inodes in the filesytem. In ext4 with the uninitialized block groups feature, the e2fsck time is constant, based solely on the number of used inodes rather than the total inode count. Since typical ext4 filesystems only use 1-10% of their inodes, this feature can greatly reduce e2fsck time for users. With performance improvement of 2-20 times, depending on how full the filesystem is. The attached graph shows the major improvements in e2fsck times in filesystems with a large total inode count, but few inodes in use. In each group descriptor if we have EXT4_BG_INODE_UNINIT set in bg_flags: Inode table is not initialized/used in this group. So we can skip the consistency check during fsck. EXT4_BG_BLOCK_UNINIT set in bg_flags: No block in the group is used. So we can skip the block bitmap verification for this group. We also add two new fields to group descriptor as a part of uninitialized group patch. __le16 bg_itable_unused; /* Unused inodes count */ __le16 bg_checksum; /* crc16(sb_uuid+group+desc) */ bg_itable_unused: If we have EXT4_BG_INODE_UNINIT not set in bg_flags then bg_itable_unused will give the offset within the inode table till the inodes are used. This can be used by fsck to skip list of inodes that are marked unused. bg_checksum: Now that we depend on bg_flags and bg_itable_unused to determine the block and inode usage, we need to make sure group descriptor is not corrupt. We add checksum to group descriptor to detect corruption. If the descriptor is found to be corrupt, we mark all the blocks and inodes in the group used. Signed-off-by: Avantika Mathur <mathur@us.ibm.com> Signed-off-by: Andreas Dilger <adilger@clusterfs.com> Signed-off-by: Mingming Cao <cmm@us.ibm.com> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
2007-10-17 06:38:25 +08:00
if (ext4_has_metadata_csum(sbi->s_sb)) {
/* Use new metadata_csum algorithm */
__u32 csum32;
__u16 dummy_csum = 0;
csum32 = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)&le_group,
sizeof(le_group));
csum32 = ext4_chksum(sbi, csum32, (__u8 *)gdp, offset);
csum32 = ext4_chksum(sbi, csum32, (__u8 *)&dummy_csum,
sizeof(dummy_csum));
offset += sizeof(dummy_csum);
if (offset < sbi->s_desc_size)
csum32 = ext4_chksum(sbi, csum32, (__u8 *)gdp + offset,
sbi->s_desc_size - offset);
crc = csum32 & 0xFFFF;
goto out;
Ext4: Uninitialized Block Groups In pass1 of e2fsck, every inode table in the fileystem is scanned and checked, regardless of whether it is in use. This is this the most time consuming part of the filesystem check. The unintialized block group feature can greatly reduce e2fsck time by eliminating checking of uninitialized inodes. With this feature, there is a a high water mark of used inodes for each block group. Block and inode bitmaps can be uninitialized on disk via a flag in the group descriptor to avoid reading or scanning them at e2fsck time. A checksum of each group descriptor is used to ensure that corruption in the group descriptor's bit flags does not cause incorrect operation. The feature is enabled through a mkfs option mke2fs /dev/ -O uninit_groups A patch adding support for uninitialized block groups to e2fsprogs tools has been posted to the linux-ext4 mailing list. The patches have been stress tested with fsstress and fsx. In performance tests testing e2fsck time, we have seen that e2fsck time on ext3 grows linearly with the total number of inodes in the filesytem. In ext4 with the uninitialized block groups feature, the e2fsck time is constant, based solely on the number of used inodes rather than the total inode count. Since typical ext4 filesystems only use 1-10% of their inodes, this feature can greatly reduce e2fsck time for users. With performance improvement of 2-20 times, depending on how full the filesystem is. The attached graph shows the major improvements in e2fsck times in filesystems with a large total inode count, but few inodes in use. In each group descriptor if we have EXT4_BG_INODE_UNINIT set in bg_flags: Inode table is not initialized/used in this group. So we can skip the consistency check during fsck. EXT4_BG_BLOCK_UNINIT set in bg_flags: No block in the group is used. So we can skip the block bitmap verification for this group. We also add two new fields to group descriptor as a part of uninitialized group patch. __le16 bg_itable_unused; /* Unused inodes count */ __le16 bg_checksum; /* crc16(sb_uuid+group+desc) */ bg_itable_unused: If we have EXT4_BG_INODE_UNINIT not set in bg_flags then bg_itable_unused will give the offset within the inode table till the inodes are used. This can be used by fsck to skip list of inodes that are marked unused. bg_checksum: Now that we depend on bg_flags and bg_itable_unused to determine the block and inode usage, we need to make sure group descriptor is not corrupt. We add checksum to group descriptor to detect corruption. If the descriptor is found to be corrupt, we mark all the blocks and inodes in the group used. Signed-off-by: Avantika Mathur <mathur@us.ibm.com> Signed-off-by: Andreas Dilger <adilger@clusterfs.com> Signed-off-by: Mingming Cao <cmm@us.ibm.com> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
2007-10-17 06:38:25 +08:00
}
/* old crc16 code */
if (!ext4_has_feature_gdt_csum(sb))
return 0;
crc = crc16(~0, sbi->s_es->s_uuid, sizeof(sbi->s_es->s_uuid));
crc = crc16(crc, (__u8 *)&le_group, sizeof(le_group));
crc = crc16(crc, (__u8 *)gdp, offset);
offset += sizeof(gdp->bg_checksum); /* skip checksum */
/* for checksum of struct ext4_group_desc do the rest...*/
if (ext4_has_feature_64bit(sb) &&
offset < le16_to_cpu(sbi->s_es->s_desc_size))
crc = crc16(crc, (__u8 *)gdp + offset,
le16_to_cpu(sbi->s_es->s_desc_size) -
offset);
out:
Ext4: Uninitialized Block Groups In pass1 of e2fsck, every inode table in the fileystem is scanned and checked, regardless of whether it is in use. This is this the most time consuming part of the filesystem check. The unintialized block group feature can greatly reduce e2fsck time by eliminating checking of uninitialized inodes. With this feature, there is a a high water mark of used inodes for each block group. Block and inode bitmaps can be uninitialized on disk via a flag in the group descriptor to avoid reading or scanning them at e2fsck time. A checksum of each group descriptor is used to ensure that corruption in the group descriptor's bit flags does not cause incorrect operation. The feature is enabled through a mkfs option mke2fs /dev/ -O uninit_groups A patch adding support for uninitialized block groups to e2fsprogs tools has been posted to the linux-ext4 mailing list. The patches have been stress tested with fsstress and fsx. In performance tests testing e2fsck time, we have seen that e2fsck time on ext3 grows linearly with the total number of inodes in the filesytem. In ext4 with the uninitialized block groups feature, the e2fsck time is constant, based solely on the number of used inodes rather than the total inode count. Since typical ext4 filesystems only use 1-10% of their inodes, this feature can greatly reduce e2fsck time for users. With performance improvement of 2-20 times, depending on how full the filesystem is. The attached graph shows the major improvements in e2fsck times in filesystems with a large total inode count, but few inodes in use. In each group descriptor if we have EXT4_BG_INODE_UNINIT set in bg_flags: Inode table is not initialized/used in this group. So we can skip the consistency check during fsck. EXT4_BG_BLOCK_UNINIT set in bg_flags: No block in the group is used. So we can skip the block bitmap verification for this group. We also add two new fields to group descriptor as a part of uninitialized group patch. __le16 bg_itable_unused; /* Unused inodes count */ __le16 bg_checksum; /* crc16(sb_uuid+group+desc) */ bg_itable_unused: If we have EXT4_BG_INODE_UNINIT not set in bg_flags then bg_itable_unused will give the offset within the inode table till the inodes are used. This can be used by fsck to skip list of inodes that are marked unused. bg_checksum: Now that we depend on bg_flags and bg_itable_unused to determine the block and inode usage, we need to make sure group descriptor is not corrupt. We add checksum to group descriptor to detect corruption. If the descriptor is found to be corrupt, we mark all the blocks and inodes in the group used. Signed-off-by: Avantika Mathur <mathur@us.ibm.com> Signed-off-by: Andreas Dilger <adilger@clusterfs.com> Signed-off-by: Mingming Cao <cmm@us.ibm.com> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
2007-10-17 06:38:25 +08:00
return cpu_to_le16(crc);
}
int ext4_group_desc_csum_verify(struct super_block *sb, __u32 block_group,
Ext4: Uninitialized Block Groups In pass1 of e2fsck, every inode table in the fileystem is scanned and checked, regardless of whether it is in use. This is this the most time consuming part of the filesystem check. The unintialized block group feature can greatly reduce e2fsck time by eliminating checking of uninitialized inodes. With this feature, there is a a high water mark of used inodes for each block group. Block and inode bitmaps can be uninitialized on disk via a flag in the group descriptor to avoid reading or scanning them at e2fsck time. A checksum of each group descriptor is used to ensure that corruption in the group descriptor's bit flags does not cause incorrect operation. The feature is enabled through a mkfs option mke2fs /dev/ -O uninit_groups A patch adding support for uninitialized block groups to e2fsprogs tools has been posted to the linux-ext4 mailing list. The patches have been stress tested with fsstress and fsx. In performance tests testing e2fsck time, we have seen that e2fsck time on ext3 grows linearly with the total number of inodes in the filesytem. In ext4 with the uninitialized block groups feature, the e2fsck time is constant, based solely on the number of used inodes rather than the total inode count. Since typical ext4 filesystems only use 1-10% of their inodes, this feature can greatly reduce e2fsck time for users. With performance improvement of 2-20 times, depending on how full the filesystem is. The attached graph shows the major improvements in e2fsck times in filesystems with a large total inode count, but few inodes in use. In each group descriptor if we have EXT4_BG_INODE_UNINIT set in bg_flags: Inode table is not initialized/used in this group. So we can skip the consistency check during fsck. EXT4_BG_BLOCK_UNINIT set in bg_flags: No block in the group is used. So we can skip the block bitmap verification for this group. We also add two new fields to group descriptor as a part of uninitialized group patch. __le16 bg_itable_unused; /* Unused inodes count */ __le16 bg_checksum; /* crc16(sb_uuid+group+desc) */ bg_itable_unused: If we have EXT4_BG_INODE_UNINIT not set in bg_flags then bg_itable_unused will give the offset within the inode table till the inodes are used. This can be used by fsck to skip list of inodes that are marked unused. bg_checksum: Now that we depend on bg_flags and bg_itable_unused to determine the block and inode usage, we need to make sure group descriptor is not corrupt. We add checksum to group descriptor to detect corruption. If the descriptor is found to be corrupt, we mark all the blocks and inodes in the group used. Signed-off-by: Avantika Mathur <mathur@us.ibm.com> Signed-off-by: Andreas Dilger <adilger@clusterfs.com> Signed-off-by: Mingming Cao <cmm@us.ibm.com> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
2007-10-17 06:38:25 +08:00
struct ext4_group_desc *gdp)
{
if (ext4_has_group_desc_csum(sb) &&
(gdp->bg_checksum != ext4_group_desc_csum(sb, block_group, gdp)))
Ext4: Uninitialized Block Groups In pass1 of e2fsck, every inode table in the fileystem is scanned and checked, regardless of whether it is in use. This is this the most time consuming part of the filesystem check. The unintialized block group feature can greatly reduce e2fsck time by eliminating checking of uninitialized inodes. With this feature, there is a a high water mark of used inodes for each block group. Block and inode bitmaps can be uninitialized on disk via a flag in the group descriptor to avoid reading or scanning them at e2fsck time. A checksum of each group descriptor is used to ensure that corruption in the group descriptor's bit flags does not cause incorrect operation. The feature is enabled through a mkfs option mke2fs /dev/ -O uninit_groups A patch adding support for uninitialized block groups to e2fsprogs tools has been posted to the linux-ext4 mailing list. The patches have been stress tested with fsstress and fsx. In performance tests testing e2fsck time, we have seen that e2fsck time on ext3 grows linearly with the total number of inodes in the filesytem. In ext4 with the uninitialized block groups feature, the e2fsck time is constant, based solely on the number of used inodes rather than the total inode count. Since typical ext4 filesystems only use 1-10% of their inodes, this feature can greatly reduce e2fsck time for users. With performance improvement of 2-20 times, depending on how full the filesystem is. The attached graph shows the major improvements in e2fsck times in filesystems with a large total inode count, but few inodes in use. In each group descriptor if we have EXT4_BG_INODE_UNINIT set in bg_flags: Inode table is not initialized/used in this group. So we can skip the consistency check during fsck. EXT4_BG_BLOCK_UNINIT set in bg_flags: No block in the group is used. So we can skip the block bitmap verification for this group. We also add two new fields to group descriptor as a part of uninitialized group patch. __le16 bg_itable_unused; /* Unused inodes count */ __le16 bg_checksum; /* crc16(sb_uuid+group+desc) */ bg_itable_unused: If we have EXT4_BG_INODE_UNINIT not set in bg_flags then bg_itable_unused will give the offset within the inode table till the inodes are used. This can be used by fsck to skip list of inodes that are marked unused. bg_checksum: Now that we depend on bg_flags and bg_itable_unused to determine the block and inode usage, we need to make sure group descriptor is not corrupt. We add checksum to group descriptor to detect corruption. If the descriptor is found to be corrupt, we mark all the blocks and inodes in the group used. Signed-off-by: Avantika Mathur <mathur@us.ibm.com> Signed-off-by: Andreas Dilger <adilger@clusterfs.com> Signed-off-by: Mingming Cao <cmm@us.ibm.com> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
2007-10-17 06:38:25 +08:00
return 0;
return 1;
}
void ext4_group_desc_csum_set(struct super_block *sb, __u32 block_group,
struct ext4_group_desc *gdp)
{
if (!ext4_has_group_desc_csum(sb))
return;
gdp->bg_checksum = ext4_group_desc_csum(sb, block_group, gdp);
}
/* Called at mount-time, super-block is locked */
ext4: add support for lazy inode table initialization When the lazy_itable_init extended option is passed to mke2fs, it considerably speeds up filesystem creation because inode tables are not zeroed out. The fact that parts of the inode table are uninitialized is not a problem so long as the block group descriptors, which contain information regarding how much of the inode table has been initialized, has not been corrupted However, if the block group checksums are not valid, e2fsck must scan the entire inode table, and the the old, uninitialized data could potentially cause e2fsck to report false problems. Hence, it is important for the inode tables to be initialized as soon as possble. This commit adds this feature so that mke2fs can safely use the lazy inode table initialization feature to speed up formatting file systems. This is done via a new new kernel thread called ext4lazyinit, which is created on demand and destroyed, when it is no longer needed. There is only one thread for all ext4 filesystems in the system. When the first filesystem with inititable mount option is mounted, ext4lazyinit thread is created, then the filesystem can register its request in the request list. This thread then walks through the list of requests picking up scheduled requests and invoking ext4_init_inode_table(). Next schedule time for the request is computed by multiplying the time it took to zero out last inode table with wait multiplier, which can be set with the (init_itable=n) mount option (default is 10). We are doing this so we do not take the whole I/O bandwidth. When the thread is no longer necessary (request list is empty) it frees the appropriate structures and exits (and can be created later later by another filesystem). We do not disturb regular inode allocations in any way, it just do not care whether the inode table is, or is not zeroed. But when zeroing, we have to skip used inodes, obviously. Also we should prevent new inode allocations from the group, while zeroing is on the way. For that we take write alloc_sem lock in ext4_init_inode_table() and read alloc_sem in the ext4_claim_inode, so when we are unlucky and allocator hits the group which is currently being zeroed, it just has to wait. This can be suppresed using the mount option no_init_itable. Signed-off-by: Lukas Czerner <lczerner@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2010-10-28 09:30:05 +08:00
static int ext4_check_descriptors(struct super_block *sb,
ext4_fsblk_t sb_block,
ext4: add support for lazy inode table initialization When the lazy_itable_init extended option is passed to mke2fs, it considerably speeds up filesystem creation because inode tables are not zeroed out. The fact that parts of the inode table are uninitialized is not a problem so long as the block group descriptors, which contain information regarding how much of the inode table has been initialized, has not been corrupted However, if the block group checksums are not valid, e2fsck must scan the entire inode table, and the the old, uninitialized data could potentially cause e2fsck to report false problems. Hence, it is important for the inode tables to be initialized as soon as possble. This commit adds this feature so that mke2fs can safely use the lazy inode table initialization feature to speed up formatting file systems. This is done via a new new kernel thread called ext4lazyinit, which is created on demand and destroyed, when it is no longer needed. There is only one thread for all ext4 filesystems in the system. When the first filesystem with inititable mount option is mounted, ext4lazyinit thread is created, then the filesystem can register its request in the request list. This thread then walks through the list of requests picking up scheduled requests and invoking ext4_init_inode_table(). Next schedule time for the request is computed by multiplying the time it took to zero out last inode table with wait multiplier, which can be set with the (init_itable=n) mount option (default is 10). We are doing this so we do not take the whole I/O bandwidth. When the thread is no longer necessary (request list is empty) it frees the appropriate structures and exits (and can be created later later by another filesystem). We do not disturb regular inode allocations in any way, it just do not care whether the inode table is, or is not zeroed. But when zeroing, we have to skip used inodes, obviously. Also we should prevent new inode allocations from the group, while zeroing is on the way. For that we take write alloc_sem lock in ext4_init_inode_table() and read alloc_sem in the ext4_claim_inode, so when we are unlucky and allocator hits the group which is currently being zeroed, it just has to wait. This can be suppresed using the mount option no_init_itable. Signed-off-by: Lukas Czerner <lczerner@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2010-10-28 09:30:05 +08:00
ext4_group_t *first_not_zeroed)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
ext4_fsblk_t first_block = le32_to_cpu(sbi->s_es->s_first_data_block);
ext4_fsblk_t last_block;
ext4_fsblk_t block_bitmap;
ext4_fsblk_t inode_bitmap;
ext4_fsblk_t inode_table;
int flexbg_flag = 0;
ext4: add support for lazy inode table initialization When the lazy_itable_init extended option is passed to mke2fs, it considerably speeds up filesystem creation because inode tables are not zeroed out. The fact that parts of the inode table are uninitialized is not a problem so long as the block group descriptors, which contain information regarding how much of the inode table has been initialized, has not been corrupted However, if the block group checksums are not valid, e2fsck must scan the entire inode table, and the the old, uninitialized data could potentially cause e2fsck to report false problems. Hence, it is important for the inode tables to be initialized as soon as possble. This commit adds this feature so that mke2fs can safely use the lazy inode table initialization feature to speed up formatting file systems. This is done via a new new kernel thread called ext4lazyinit, which is created on demand and destroyed, when it is no longer needed. There is only one thread for all ext4 filesystems in the system. When the first filesystem with inititable mount option is mounted, ext4lazyinit thread is created, then the filesystem can register its request in the request list. This thread then walks through the list of requests picking up scheduled requests and invoking ext4_init_inode_table(). Next schedule time for the request is computed by multiplying the time it took to zero out last inode table with wait multiplier, which can be set with the (init_itable=n) mount option (default is 10). We are doing this so we do not take the whole I/O bandwidth. When the thread is no longer necessary (request list is empty) it frees the appropriate structures and exits (and can be created later later by another filesystem). We do not disturb regular inode allocations in any way, it just do not care whether the inode table is, or is not zeroed. But when zeroing, we have to skip used inodes, obviously. Also we should prevent new inode allocations from the group, while zeroing is on the way. For that we take write alloc_sem lock in ext4_init_inode_table() and read alloc_sem in the ext4_claim_inode, so when we are unlucky and allocator hits the group which is currently being zeroed, it just has to wait. This can be suppresed using the mount option no_init_itable. Signed-off-by: Lukas Czerner <lczerner@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2010-10-28 09:30:05 +08:00
ext4_group_t i, grp = sbi->s_groups_count;
if (ext4_has_feature_flex_bg(sb))
flexbg_flag = 1;
ext4_debug("Checking group descriptors");
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);
ext4: add support for lazy inode table initialization When the lazy_itable_init extended option is passed to mke2fs, it considerably speeds up filesystem creation because inode tables are not zeroed out. The fact that parts of the inode table are uninitialized is not a problem so long as the block group descriptors, which contain information regarding how much of the inode table has been initialized, has not been corrupted However, if the block group checksums are not valid, e2fsck must scan the entire inode table, and the the old, uninitialized data could potentially cause e2fsck to report false problems. Hence, it is important for the inode tables to be initialized as soon as possble. This commit adds this feature so that mke2fs can safely use the lazy inode table initialization feature to speed up formatting file systems. This is done via a new new kernel thread called ext4lazyinit, which is created on demand and destroyed, when it is no longer needed. There is only one thread for all ext4 filesystems in the system. When the first filesystem with inititable mount option is mounted, ext4lazyinit thread is created, then the filesystem can register its request in the request list. This thread then walks through the list of requests picking up scheduled requests and invoking ext4_init_inode_table(). Next schedule time for the request is computed by multiplying the time it took to zero out last inode table with wait multiplier, which can be set with the (init_itable=n) mount option (default is 10). We are doing this so we do not take the whole I/O bandwidth. When the thread is no longer necessary (request list is empty) it frees the appropriate structures and exits (and can be created later later by another filesystem). We do not disturb regular inode allocations in any way, it just do not care whether the inode table is, or is not zeroed. But when zeroing, we have to skip used inodes, obviously. Also we should prevent new inode allocations from the group, while zeroing is on the way. For that we take write alloc_sem lock in ext4_init_inode_table() and read alloc_sem in the ext4_claim_inode, so when we are unlucky and allocator hits the group which is currently being zeroed, it just has to wait. This can be suppresed using the mount option no_init_itable. Signed-off-by: Lukas Czerner <lczerner@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2010-10-28 09:30:05 +08:00
if ((grp == sbi->s_groups_count) &&
!(gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_ZEROED)))
grp = i;
block_bitmap = ext4_block_bitmap(sb, gdp);
if (block_bitmap == sb_block) {
ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
"Block bitmap for group %u overlaps "
"superblock", i);
}
if (block_bitmap < first_block || block_bitmap > last_block) {
ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
"Block bitmap for group %u not in group "
"(block %llu)!", i, block_bitmap);
return 0;
}
inode_bitmap = ext4_inode_bitmap(sb, gdp);
if (inode_bitmap == sb_block) {
ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
"Inode bitmap for group %u overlaps "
"superblock", i);
}
if (inode_bitmap < first_block || inode_bitmap > last_block) {
ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
"Inode bitmap for group %u not in group "
"(block %llu)!", i, inode_bitmap);
return 0;
}
inode_table = ext4_inode_table(sb, gdp);
if (inode_table == sb_block) {
ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
"Inode table for group %u overlaps "
"superblock", i);
}
if (inode_table < first_block ||
inode_table + sbi->s_itb_per_group - 1 > last_block) {
ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
"Inode table for group %u not in group "
"(block %llu)!", i, inode_table);
return 0;
}
ext4_lock_group(sb, i);
if (!ext4_group_desc_csum_verify(sb, i, gdp)) {
ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
"Checksum for group %u failed (%u!=%u)",
i, le16_to_cpu(ext4_group_desc_csum(sb, i,
gdp)), le16_to_cpu(gdp->bg_checksum));
if (!(sb->s_flags & MS_RDONLY)) {
ext4_unlock_group(sb, i);
return 0;
}
Ext4: Uninitialized Block Groups In pass1 of e2fsck, every inode table in the fileystem is scanned and checked, regardless of whether it is in use. This is this the most time consuming part of the filesystem check. The unintialized block group feature can greatly reduce e2fsck time by eliminating checking of uninitialized inodes. With this feature, there is a a high water mark of used inodes for each block group. Block and inode bitmaps can be uninitialized on disk via a flag in the group descriptor to avoid reading or scanning them at e2fsck time. A checksum of each group descriptor is used to ensure that corruption in the group descriptor's bit flags does not cause incorrect operation. The feature is enabled through a mkfs option mke2fs /dev/ -O uninit_groups A patch adding support for uninitialized block groups to e2fsprogs tools has been posted to the linux-ext4 mailing list. The patches have been stress tested with fsstress and fsx. In performance tests testing e2fsck time, we have seen that e2fsck time on ext3 grows linearly with the total number of inodes in the filesytem. In ext4 with the uninitialized block groups feature, the e2fsck time is constant, based solely on the number of used inodes rather than the total inode count. Since typical ext4 filesystems only use 1-10% of their inodes, this feature can greatly reduce e2fsck time for users. With performance improvement of 2-20 times, depending on how full the filesystem is. The attached graph shows the major improvements in e2fsck times in filesystems with a large total inode count, but few inodes in use. In each group descriptor if we have EXT4_BG_INODE_UNINIT set in bg_flags: Inode table is not initialized/used in this group. So we can skip the consistency check during fsck. EXT4_BG_BLOCK_UNINIT set in bg_flags: No block in the group is used. So we can skip the block bitmap verification for this group. We also add two new fields to group descriptor as a part of uninitialized group patch. __le16 bg_itable_unused; /* Unused inodes count */ __le16 bg_checksum; /* crc16(sb_uuid+group+desc) */ bg_itable_unused: If we have EXT4_BG_INODE_UNINIT not set in bg_flags then bg_itable_unused will give the offset within the inode table till the inodes are used. This can be used by fsck to skip list of inodes that are marked unused. bg_checksum: Now that we depend on bg_flags and bg_itable_unused to determine the block and inode usage, we need to make sure group descriptor is not corrupt. We add checksum to group descriptor to detect corruption. If the descriptor is found to be corrupt, we mark all the blocks and inodes in the group used. Signed-off-by: Avantika Mathur <mathur@us.ibm.com> Signed-off-by: Andreas Dilger <adilger@clusterfs.com> Signed-off-by: Mingming Cao <cmm@us.ibm.com> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
2007-10-17 06:38:25 +08:00
}
ext4_unlock_group(sb, i);
if (!flexbg_flag)
first_block += EXT4_BLOCKS_PER_GROUP(sb);
}
ext4: add support for lazy inode table initialization When the lazy_itable_init extended option is passed to mke2fs, it considerably speeds up filesystem creation because inode tables are not zeroed out. The fact that parts of the inode table are uninitialized is not a problem so long as the block group descriptors, which contain information regarding how much of the inode table has been initialized, has not been corrupted However, if the block group checksums are not valid, e2fsck must scan the entire inode table, and the the old, uninitialized data could potentially cause e2fsck to report false problems. Hence, it is important for the inode tables to be initialized as soon as possble. This commit adds this feature so that mke2fs can safely use the lazy inode table initialization feature to speed up formatting file systems. This is done via a new new kernel thread called ext4lazyinit, which is created on demand and destroyed, when it is no longer needed. There is only one thread for all ext4 filesystems in the system. When the first filesystem with inititable mount option is mounted, ext4lazyinit thread is created, then the filesystem can register its request in the request list. This thread then walks through the list of requests picking up scheduled requests and invoking ext4_init_inode_table(). Next schedule time for the request is computed by multiplying the time it took to zero out last inode table with wait multiplier, which can be set with the (init_itable=n) mount option (default is 10). We are doing this so we do not take the whole I/O bandwidth. When the thread is no longer necessary (request list is empty) it frees the appropriate structures and exits (and can be created later later by another filesystem). We do not disturb regular inode allocations in any way, it just do not care whether the inode table is, or is not zeroed. But when zeroing, we have to skip used inodes, obviously. Also we should prevent new inode allocations from the group, while zeroing is on the way. For that we take write alloc_sem lock in ext4_init_inode_table() and read alloc_sem in the ext4_claim_inode, so when we are unlucky and allocator hits the group which is currently being zeroed, it just has to wait. This can be suppresed using the mount option no_init_itable. Signed-off-by: Lukas Czerner <lczerner@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2010-10-28 09:30:05 +08:00
if (NULL != first_not_zeroed)
*first_not_zeroed = grp;
return 1;
}
/* ext4_orphan_cleanup() walks a singly-linked list of inodes (starting at
* the superblock) which were deleted from all directories, but held open by
* a process at the time of a crash. We walk the list and try to delete these
* inodes at recovery time (only with a read-write filesystem).
*
* In order to keep the orphan inode chain consistent during traversal (in
* case of crash during recovery), we link each inode into the superblock
* orphan list_head and handle it the same way as an inode deletion during
* normal operation (which journals the operations for us).
*
* We only do an iget() and an iput() on each inode, which is very safe if we
* accidentally point at an in-use or already deleted inode. The worst that
* can happen in this case is that we get a "bit already cleared" message from
* ext4_free_inode(). The only reason we would point at a wrong inode is if
* e2fsck was run on this filesystem, and it must have already done the orphan
* inode cleanup for us, so we can safely abort without any further action.
*/
static void ext4_orphan_cleanup(struct super_block *sb,
struct ext4_super_block *es)
{
unsigned int s_flags = sb->s_flags;
int ret, nr_orphans = 0, nr_truncates = 0;
#ifdef CONFIG_QUOTA
int i;
#endif
if (!es->s_last_orphan) {
jbd_debug(4, "no orphan inodes to clean up\n");
return;
}
if (bdev_read_only(sb->s_bdev)) {
ext4_msg(sb, KERN_ERR, "write access "
"unavailable, skipping orphan cleanup");
return;
}
/* Check if feature set would not allow a r/w mount */
if (!ext4_feature_set_ok(sb, 0)) {
ext4_msg(sb, KERN_INFO, "Skipping orphan cleanup due to "
"unknown ROCOMPAT features");
return;
}
if (EXT4_SB(sb)->s_mount_state & EXT4_ERROR_FS) {
/* don't clear list on RO mount w/ errors */
if (es->s_last_orphan && !(s_flags & MS_RDONLY)) {
ext4_msg(sb, KERN_INFO, "Errors on filesystem, "
"clearing orphan list.\n");
es->s_last_orphan = 0;
}
jbd_debug(1, "Skipping orphan recovery on fs with errors.\n");
return;
}
if (s_flags & MS_RDONLY) {
ext4_msg(sb, KERN_INFO, "orphan cleanup on readonly fs");
sb->s_flags &= ~MS_RDONLY;
}
#ifdef CONFIG_QUOTA
/* Needed for iput() to work correctly and not trash data */
sb->s_flags |= MS_ACTIVE;
/* Turn on quotas so that they are updated correctly */
for (i = 0; i < EXT4_MAXQUOTAS; i++) {
if (EXT4_SB(sb)->s_qf_names[i]) {
int ret = ext4_quota_on_mount(sb, i);
if (ret < 0)
ext4_msg(sb, KERN_ERR,
"Cannot turn on journaled "
"quota: error %d", ret);
}
}
#endif
while (es->s_last_orphan) {
struct inode *inode;
ext4: short-cut orphan cleanup on error If we encounter a filesystem error during orphan cleanup, we should stop. Otherwise, we may end up in an infinite loop where the same inode is processed again and again. EXT4-fs (loop0): warning: checktime reached, running e2fsck is recommended EXT4-fs error (device loop0): ext4_mb_generate_buddy:758: group 2, block bitmap and bg descriptor inconsistent: 6117 vs 0 free clusters Aborting journal on device loop0-8. EXT4-fs (loop0): Remounting filesystem read-only EXT4-fs error (device loop0) in ext4_free_blocks:4895: Journal has aborted EXT4-fs error (device loop0) in ext4_do_update_inode:4893: Journal has aborted EXT4-fs error (device loop0) in ext4_do_update_inode:4893: Journal has aborted EXT4-fs error (device loop0) in ext4_ext_remove_space:3068: IO failure EXT4-fs error (device loop0) in ext4_ext_truncate:4667: Journal has aborted EXT4-fs error (device loop0) in ext4_orphan_del:2927: Journal has aborted EXT4-fs error (device loop0) in ext4_do_update_inode:4893: Journal has aborted EXT4-fs (loop0): Inode 16 (00000000618192a0): orphan list check failed! [...] EXT4-fs (loop0): Inode 16 (0000000061819748): orphan list check failed! [...] EXT4-fs (loop0): Inode 16 (0000000061819bf0): orphan list check failed! [...] See-also: c9eb13a9105 ("ext4: fix hang when processing corrupted orphaned inode list") Cc: Jan Kara <jack@suse.cz> Signed-off-by: Vegard Nossum <vegard.nossum@oracle.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Cc: stable@vger.kernel.org
2016-07-15 11:21:35 +08:00
/*
* We may have encountered an error during cleanup; if
* so, skip the rest.
*/
if (EXT4_SB(sb)->s_mount_state & EXT4_ERROR_FS) {
jbd_debug(1, "Skipping orphan recovery on fs with errors.\n");
es->s_last_orphan = 0;
break;
}
inode = ext4_orphan_get(sb, le32_to_cpu(es->s_last_orphan));
if (IS_ERR(inode)) {
es->s_last_orphan = 0;
break;
}
list_add(&EXT4_I(inode)->i_orphan, &EXT4_SB(sb)->s_orphan);
dquot_initialize(inode);
if (inode->i_nlink) {
if (test_opt(sb, DEBUG))
ext4_msg(sb, KERN_DEBUG,
"%s: truncating inode %lu to %lld bytes",
__func__, inode->i_ino, inode->i_size);
jbd_debug(2, "truncating inode %lu to %lld bytes\n",
inode->i_ino, inode->i_size);
inode_lock(inode);
truncate_inode_pages(inode->i_mapping, inode->i_size);
ret = ext4_truncate(inode);
if (ret)
ext4_std_error(inode->i_sb, ret);
inode_unlock(inode);
nr_truncates++;
} else {
if (test_opt(sb, DEBUG))
ext4_msg(sb, KERN_DEBUG,
"%s: deleting unreferenced inode %lu",
__func__, inode->i_ino);
jbd_debug(2, "deleting unreferenced inode %lu\n",
inode->i_ino);
nr_orphans++;
}
iput(inode); /* The delete magic happens here! */
}
#define PLURAL(x) (x), ((x) == 1) ? "" : "s"
if (nr_orphans)
ext4_msg(sb, KERN_INFO, "%d orphan inode%s deleted",
PLURAL(nr_orphans));
if (nr_truncates)
ext4_msg(sb, KERN_INFO, "%d truncate%s cleaned up",
PLURAL(nr_truncates));
#ifdef CONFIG_QUOTA
/* Turn quotas off */
for (i = 0; i < EXT4_MAXQUOTAS; i++) {
if (sb_dqopt(sb)->files[i])
dquot_quota_off(sb, i);
}
#endif
sb->s_flags = s_flags; /* Restore MS_RDONLY status */
}
/*
* Maximal extent format file size.
* Resulting logical blkno at s_maxbytes must fit in our on-disk
* extent format containers, within a sector_t, and within i_blocks
* in the vfs. ext4 inode has 48 bits of i_block in fsblock units,
* so that won't be a limiting factor.
*
ext4: Fix max file size and logical block counting of extent format file Kazuya Mio reported that he was able to hit BUG_ON(next == lblock) in ext4_ext_put_gap_in_cache() while creating a sparse file in extent format and fill the tail of file up to its end. We will hit the BUG_ON when we write the last block (2^32-1) into the sparse file. The root cause of the problem lies in the fact that we specifically set s_maxbytes so that block at s_maxbytes fit into on-disk extent format, which is 32 bit long. However, we are not storing start and end block number, but rather start block number and length in blocks. It means that in order to cover extent from 0 to EXT_MAX_BLOCK we need EXT_MAX_BLOCK+1 to fit into len (because we counting block 0 as well) - and it does not. The only way to fix it without changing the meaning of the struct ext4_extent members is, as Kazuya Mio suggested, to lower s_maxbytes by one fs block so we can cover the whole extent we can get by the on-disk extent format. Also in many places EXT_MAX_BLOCK is used as length instead of maximum logical block number as the name suggests, it is all a bit messy. So this commit renames it to EXT_MAX_BLOCKS and change its usage in some places to actually be maximum number of blocks in the extent. The bug which this commit fixes can be reproduced as follows: dd if=/dev/zero of=/mnt/mp1/file bs=<blocksize> count=1 seek=$((2**32-2)) sync dd if=/dev/zero of=/mnt/mp1/file bs=<blocksize> count=1 seek=$((2**32-1)) Reported-by: Kazuya Mio <k-mio@sx.jp.nec.com> Signed-off-by: Lukas Czerner <lczerner@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2011-06-06 12:05:17 +08:00
* However there is other limiting factor. We do store extents in the form
* of starting block and length, hence the resulting length of the extent
* covering maximum file size must fit into on-disk format containers as
* well. Given that length is always by 1 unit bigger than max unit (because
* we count 0 as well) we have to lower the s_maxbytes by one fs block.
*
* Note, this does *not* consider any metadata overhead for vfs i_blocks.
*/
static loff_t ext4_max_size(int blkbits, int has_huge_files)
{
loff_t res;
loff_t upper_limit = MAX_LFS_FILESIZE;
/* small i_blocks in vfs inode? */
if (!has_huge_files || sizeof(blkcnt_t) < sizeof(u64)) {
/*
* CONFIG_LBDAF is not enabled implies the inode
* i_block represent total blocks in 512 bytes
* 32 == size of vfs inode i_blocks * 8
*/
upper_limit = (1LL << 32) - 1;
/* total blocks in file system block size */
upper_limit >>= (blkbits - 9);
upper_limit <<= blkbits;
}
ext4: Fix max file size and logical block counting of extent format file Kazuya Mio reported that he was able to hit BUG_ON(next == lblock) in ext4_ext_put_gap_in_cache() while creating a sparse file in extent format and fill the tail of file up to its end. We will hit the BUG_ON when we write the last block (2^32-1) into the sparse file. The root cause of the problem lies in the fact that we specifically set s_maxbytes so that block at s_maxbytes fit into on-disk extent format, which is 32 bit long. However, we are not storing start and end block number, but rather start block number and length in blocks. It means that in order to cover extent from 0 to EXT_MAX_BLOCK we need EXT_MAX_BLOCK+1 to fit into len (because we counting block 0 as well) - and it does not. The only way to fix it without changing the meaning of the struct ext4_extent members is, as Kazuya Mio suggested, to lower s_maxbytes by one fs block so we can cover the whole extent we can get by the on-disk extent format. Also in many places EXT_MAX_BLOCK is used as length instead of maximum logical block number as the name suggests, it is all a bit messy. So this commit renames it to EXT_MAX_BLOCKS and change its usage in some places to actually be maximum number of blocks in the extent. The bug which this commit fixes can be reproduced as follows: dd if=/dev/zero of=/mnt/mp1/file bs=<blocksize> count=1 seek=$((2**32-2)) sync dd if=/dev/zero of=/mnt/mp1/file bs=<blocksize> count=1 seek=$((2**32-1)) Reported-by: Kazuya Mio <k-mio@sx.jp.nec.com> Signed-off-by: Lukas Czerner <lczerner@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2011-06-06 12:05:17 +08:00
/*
* 32-bit extent-start container, ee_block. We lower the maxbytes
* by one fs block, so ee_len can cover the extent of maximum file
* size
*/
res = (1LL << 32) - 1;
res <<= blkbits;
/* Sanity check against vm- & vfs- imposed limits */
if (res > upper_limit)
res = upper_limit;
return res;
}
/*
* Maximal bitmap file size. There is a direct, and {,double-,triple-}indirect
* block limit, and also a limit of (2^48 - 1) 512-byte sectors in i_blocks.
* We need to be 1 filesystem block less than the 2^48 sector limit.
*/
static loff_t ext4_max_bitmap_size(int bits, int has_huge_files)
{
loff_t res = EXT4_NDIR_BLOCKS;
int meta_blocks;
loff_t upper_limit;
/* This is calculated to be the largest file size for a dense, block
* mapped file such that the file's total number of 512-byte sectors,
* including data and all indirect blocks, does not exceed (2^48 - 1).
*
* __u32 i_blocks_lo and _u16 i_blocks_high represent the total
* number of 512-byte sectors of the file.
*/
if (!has_huge_files || sizeof(blkcnt_t) < sizeof(u64)) {
/*
* !has_huge_files or CONFIG_LBDAF not enabled implies that
* the inode i_block field represents total file blocks in
* 2^32 512-byte sectors == size of vfs inode i_blocks * 8
*/
upper_limit = (1LL << 32) - 1;
/* total blocks in file system block size */
upper_limit >>= (bits - 9);
} else {
/*
* We use 48 bit ext4_inode i_blocks
* With EXT4_HUGE_FILE_FL set the i_blocks
* represent total number of blocks in
* file system block size
*/
upper_limit = (1LL << 48) - 1;
}
/* indirect blocks */
meta_blocks = 1;
/* double indirect blocks */
meta_blocks += 1 + (1LL << (bits-2));
/* tripple indirect blocks */
meta_blocks += 1 + (1LL << (bits-2)) + (1LL << (2*(bits-2)));
upper_limit -= meta_blocks;
upper_limit <<= bits;
res += 1LL << (bits-2);
res += 1LL << (2*(bits-2));
res += 1LL << (3*(bits-2));
res <<= bits;
if (res > upper_limit)
res = upper_limit;
if (res > MAX_LFS_FILESIZE)
res = MAX_LFS_FILESIZE;
return res;
}
static ext4_fsblk_t descriptor_loc(struct super_block *sb,
ext4_fsblk_t logical_sb_block, int nr)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
ext4_group_t bg, first_meta_bg;
int has_super = 0;
first_meta_bg = le32_to_cpu(sbi->s_es->s_first_meta_bg);
if (!ext4_has_feature_meta_bg(sb) || nr < first_meta_bg)
return logical_sb_block + nr + 1;
bg = sbi->s_desc_per_block * nr;
if (ext4_bg_has_super(sb, bg))
has_super = 1;
/*
* If we have a meta_bg fs with 1k blocks, group 0's GDT is at
* block 2, not 1. If s_first_data_block == 0 (bigalloc is enabled
* on modern mke2fs or blksize > 1k on older mke2fs) then we must
* compensate.
*/
if (sb->s_blocksize == 1024 && nr == 0 &&
le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block) == 0)
has_super++;
return (has_super + ext4_group_first_block_no(sb, bg));
}
/**
* ext4_get_stripe_size: Get the stripe size.
* @sbi: In memory super block info
*
* If we have specified it via mount option, then
* use the mount option value. If the value specified at mount time is
* greater than the blocks per group use the super block value.
* If the super block value is greater than blocks per group return 0.
* Allocator needs it be less than blocks per group.
*
*/
static unsigned long ext4_get_stripe_size(struct ext4_sb_info *sbi)
{
unsigned long stride = le16_to_cpu(sbi->s_es->s_raid_stride);
unsigned long stripe_width =
le32_to_cpu(sbi->s_es->s_raid_stripe_width);
int ret;
if (sbi->s_stripe && sbi->s_stripe <= sbi->s_blocks_per_group)
ret = sbi->s_stripe;
else if (stripe_width <= sbi->s_blocks_per_group)
ret = stripe_width;
else if (stride <= sbi->s_blocks_per_group)
ret = stride;
else
ret = 0;
/*
* If the stripe width is 1, this makes no sense and
* we set it to 0 to turn off stripe handling code.
*/
if (ret <= 1)
ret = 0;
return ret;
}
/*
* Check whether this filesystem can be mounted based on
* the features present and the RDONLY/RDWR mount requested.
* Returns 1 if this filesystem can be mounted as requested,
* 0 if it cannot be.
*/
static int ext4_feature_set_ok(struct super_block *sb, int readonly)
{
if (ext4_has_unknown_ext4_incompat_features(sb)) {
ext4_msg(sb, KERN_ERR,
"Couldn't mount because of "
"unsupported optional features (%x)",
(le32_to_cpu(EXT4_SB(sb)->s_es->s_feature_incompat) &
~EXT4_FEATURE_INCOMPAT_SUPP));
return 0;
}
if (readonly)
return 1;
if (ext4_has_feature_readonly(sb)) {
ext4_msg(sb, KERN_INFO, "filesystem is read-only");
sb->s_flags |= MS_RDONLY;
return 1;
}
/* Check that feature set is OK for a read-write mount */
if (ext4_has_unknown_ext4_ro_compat_features(sb)) {
ext4_msg(sb, KERN_ERR, "couldn't mount RDWR because of "
"unsupported optional features (%x)",
(le32_to_cpu(EXT4_SB(sb)->s_es->s_feature_ro_compat) &
~EXT4_FEATURE_RO_COMPAT_SUPP));
return 0;
}
/*
* Large file size enabled file system can only be mounted
* read-write on 32-bit systems if kernel is built with CONFIG_LBDAF
*/
if (ext4_has_feature_huge_file(sb)) {
if (sizeof(blkcnt_t) < sizeof(u64)) {
ext4_msg(sb, KERN_ERR, "Filesystem with huge files "
"cannot be mounted RDWR without "
"CONFIG_LBDAF");
return 0;
}
}
if (ext4_has_feature_bigalloc(sb) && !ext4_has_feature_extents(sb)) {
ext4_msg(sb, KERN_ERR,
"Can't support bigalloc feature without "
"extents feature\n");
return 0;
}
ext4: make quota as first class supported feature This patch adds support for quotas as a first class feature in ext4; which is to say, the quota files are stored in hidden inodes as file system metadata, instead of as separate files visible in the file system directory hierarchy. It is based on the proposal at: https://ext4.wiki.kernel.org/index.php/Design_For_1st_Class_Quota_in_Ext4 This patch introduces a new feature - EXT4_FEATURE_RO_COMPAT_QUOTA which, when turned on, enables quota accounting at mount time iteself. Also, the quota inodes are stored in two additional superblock fields. Some changes introduced by this patch that should be pointed out are: 1) Two new ext4-superblock fields - s_usr_quota_inum and s_grp_quota_inum for storing the quota inodes in use. 2) Default quota inodes are: inode#3 for tracking userquota and inode#4 for tracking group quota. The superblock fields can be set to use other inodes as well. 3) If the QUOTA feature and corresponding quota inodes are set in superblock, the quota usage tracking is turned on at mount time. On 'quotaon' ioctl, the quota limits enforcement is turned on. 'quotaoff' ioctl turns off only the limits enforcement in this case. 4) When QUOTA feature is in use, the quota mount options 'quota', 'usrquota', 'grpquota' are ignored by the kernel. 5) mke2fs or tune2fs can be used to set the QUOTA feature and initialize quota inodes. The default reserved inodes will not be visible to user as regular files. 6) The quota-tools will need to be modified to support hidden quota files on ext4. E2fsprogs will also include support for creating and fixing quota files. 7) Support is only for the new V2 quota file format. Tested-by: Jan Kara <jack@suse.cz> Reviewed-by: Jan Kara <jack@suse.cz> Reviewed-by: Johann Lombardi <johann@whamcloud.com> Signed-off-by: Aditya Kali <adityakali@google.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2012-07-23 08:21:31 +08:00
#ifndef CONFIG_QUOTA
if (ext4_has_feature_quota(sb) && !readonly) {
ext4: make quota as first class supported feature This patch adds support for quotas as a first class feature in ext4; which is to say, the quota files are stored in hidden inodes as file system metadata, instead of as separate files visible in the file system directory hierarchy. It is based on the proposal at: https://ext4.wiki.kernel.org/index.php/Design_For_1st_Class_Quota_in_Ext4 This patch introduces a new feature - EXT4_FEATURE_RO_COMPAT_QUOTA which, when turned on, enables quota accounting at mount time iteself. Also, the quota inodes are stored in two additional superblock fields. Some changes introduced by this patch that should be pointed out are: 1) Two new ext4-superblock fields - s_usr_quota_inum and s_grp_quota_inum for storing the quota inodes in use. 2) Default quota inodes are: inode#3 for tracking userquota and inode#4 for tracking group quota. The superblock fields can be set to use other inodes as well. 3) If the QUOTA feature and corresponding quota inodes are set in superblock, the quota usage tracking is turned on at mount time. On 'quotaon' ioctl, the quota limits enforcement is turned on. 'quotaoff' ioctl turns off only the limits enforcement in this case. 4) When QUOTA feature is in use, the quota mount options 'quota', 'usrquota', 'grpquota' are ignored by the kernel. 5) mke2fs or tune2fs can be used to set the QUOTA feature and initialize quota inodes. The default reserved inodes will not be visible to user as regular files. 6) The quota-tools will need to be modified to support hidden quota files on ext4. E2fsprogs will also include support for creating and fixing quota files. 7) Support is only for the new V2 quota file format. Tested-by: Jan Kara <jack@suse.cz> Reviewed-by: Jan Kara <jack@suse.cz> Reviewed-by: Johann Lombardi <johann@whamcloud.com> Signed-off-by: Aditya Kali <adityakali@google.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2012-07-23 08:21:31 +08:00
ext4_msg(sb, KERN_ERR,
"Filesystem with quota feature cannot be mounted RDWR "
"without CONFIG_QUOTA");
return 0;
}
if (ext4_has_feature_project(sb) && !readonly) {
ext4_msg(sb, KERN_ERR,
"Filesystem with project quota feature cannot be mounted RDWR "
"without CONFIG_QUOTA");
return 0;
}
ext4: make quota as first class supported feature This patch adds support for quotas as a first class feature in ext4; which is to say, the quota files are stored in hidden inodes as file system metadata, instead of as separate files visible in the file system directory hierarchy. It is based on the proposal at: https://ext4.wiki.kernel.org/index.php/Design_For_1st_Class_Quota_in_Ext4 This patch introduces a new feature - EXT4_FEATURE_RO_COMPAT_QUOTA which, when turned on, enables quota accounting at mount time iteself. Also, the quota inodes are stored in two additional superblock fields. Some changes introduced by this patch that should be pointed out are: 1) Two new ext4-superblock fields - s_usr_quota_inum and s_grp_quota_inum for storing the quota inodes in use. 2) Default quota inodes are: inode#3 for tracking userquota and inode#4 for tracking group quota. The superblock fields can be set to use other inodes as well. 3) If the QUOTA feature and corresponding quota inodes are set in superblock, the quota usage tracking is turned on at mount time. On 'quotaon' ioctl, the quota limits enforcement is turned on. 'quotaoff' ioctl turns off only the limits enforcement in this case. 4) When QUOTA feature is in use, the quota mount options 'quota', 'usrquota', 'grpquota' are ignored by the kernel. 5) mke2fs or tune2fs can be used to set the QUOTA feature and initialize quota inodes. The default reserved inodes will not be visible to user as regular files. 6) The quota-tools will need to be modified to support hidden quota files on ext4. E2fsprogs will also include support for creating and fixing quota files. 7) Support is only for the new V2 quota file format. Tested-by: Jan Kara <jack@suse.cz> Reviewed-by: Jan Kara <jack@suse.cz> Reviewed-by: Johann Lombardi <johann@whamcloud.com> Signed-off-by: Aditya Kali <adityakali@google.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2012-07-23 08:21:31 +08:00
#endif /* CONFIG_QUOTA */
return 1;
}
/*
* This function is called once a day if we have errors logged
* on the file system
*/
static void print_daily_error_info(unsigned long arg)
{
struct super_block *sb = (struct super_block *) arg;
struct ext4_sb_info *sbi;
struct ext4_super_block *es;
sbi = EXT4_SB(sb);
es = sbi->s_es;
if (es->s_error_count)
/* fsck newer than v1.41.13 is needed to clean this condition. */
ext4_msg(sb, KERN_NOTICE, "error count since last fsck: %u",
le32_to_cpu(es->s_error_count));
if (es->s_first_error_time) {
printk(KERN_NOTICE "EXT4-fs (%s): initial error at time %u: %.*s:%d",
sb->s_id, le32_to_cpu(es->s_first_error_time),
(int) sizeof(es->s_first_error_func),
es->s_first_error_func,
le32_to_cpu(es->s_first_error_line));
if (es->s_first_error_ino)
printk(KERN_CONT ": inode %u",
le32_to_cpu(es->s_first_error_ino));
if (es->s_first_error_block)
printk(KERN_CONT ": block %llu", (unsigned long long)
le64_to_cpu(es->s_first_error_block));
printk(KERN_CONT "\n");
}
if (es->s_last_error_time) {
printk(KERN_NOTICE "EXT4-fs (%s): last error at time %u: %.*s:%d",
sb->s_id, le32_to_cpu(es->s_last_error_time),
(int) sizeof(es->s_last_error_func),
es->s_last_error_func,
le32_to_cpu(es->s_last_error_line));
if (es->s_last_error_ino)
printk(KERN_CONT ": inode %u",
le32_to_cpu(es->s_last_error_ino));
if (es->s_last_error_block)
printk(KERN_CONT ": block %llu", (unsigned long long)
le64_to_cpu(es->s_last_error_block));
printk(KERN_CONT "\n");
}
mod_timer(&sbi->s_err_report, jiffies + 24*60*60*HZ); /* Once a day */
}
ext4: add support for lazy inode table initialization When the lazy_itable_init extended option is passed to mke2fs, it considerably speeds up filesystem creation because inode tables are not zeroed out. The fact that parts of the inode table are uninitialized is not a problem so long as the block group descriptors, which contain information regarding how much of the inode table has been initialized, has not been corrupted However, if the block group checksums are not valid, e2fsck must scan the entire inode table, and the the old, uninitialized data could potentially cause e2fsck to report false problems. Hence, it is important for the inode tables to be initialized as soon as possble. This commit adds this feature so that mke2fs can safely use the lazy inode table initialization feature to speed up formatting file systems. This is done via a new new kernel thread called ext4lazyinit, which is created on demand and destroyed, when it is no longer needed. There is only one thread for all ext4 filesystems in the system. When the first filesystem with inititable mount option is mounted, ext4lazyinit thread is created, then the filesystem can register its request in the request list. This thread then walks through the list of requests picking up scheduled requests and invoking ext4_init_inode_table(). Next schedule time for the request is computed by multiplying the time it took to zero out last inode table with wait multiplier, which can be set with the (init_itable=n) mount option (default is 10). We are doing this so we do not take the whole I/O bandwidth. When the thread is no longer necessary (request list is empty) it frees the appropriate structures and exits (and can be created later later by another filesystem). We do not disturb regular inode allocations in any way, it just do not care whether the inode table is, or is not zeroed. But when zeroing, we have to skip used inodes, obviously. Also we should prevent new inode allocations from the group, while zeroing is on the way. For that we take write alloc_sem lock in ext4_init_inode_table() and read alloc_sem in the ext4_claim_inode, so when we are unlucky and allocator hits the group which is currently being zeroed, it just has to wait. This can be suppresed using the mount option no_init_itable. Signed-off-by: Lukas Czerner <lczerner@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2010-10-28 09:30:05 +08:00
/* Find next suitable group and run ext4_init_inode_table */
static int ext4_run_li_request(struct ext4_li_request *elr)
{
struct ext4_group_desc *gdp = NULL;
ext4_group_t group, ngroups;
struct super_block *sb;
unsigned long timeout = 0;
int ret = 0;
sb = elr->lr_super;
ngroups = EXT4_SB(sb)->s_groups_count;
for (group = elr->lr_next_group; group < ngroups; group++) {
gdp = ext4_get_group_desc(sb, group, NULL);
if (!gdp) {
ret = 1;
break;
}
if (!(gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_ZEROED)))
break;
}
if (group >= ngroups)
ext4: add support for lazy inode table initialization When the lazy_itable_init extended option is passed to mke2fs, it considerably speeds up filesystem creation because inode tables are not zeroed out. The fact that parts of the inode table are uninitialized is not a problem so long as the block group descriptors, which contain information regarding how much of the inode table has been initialized, has not been corrupted However, if the block group checksums are not valid, e2fsck must scan the entire inode table, and the the old, uninitialized data could potentially cause e2fsck to report false problems. Hence, it is important for the inode tables to be initialized as soon as possble. This commit adds this feature so that mke2fs can safely use the lazy inode table initialization feature to speed up formatting file systems. This is done via a new new kernel thread called ext4lazyinit, which is created on demand and destroyed, when it is no longer needed. There is only one thread for all ext4 filesystems in the system. When the first filesystem with inititable mount option is mounted, ext4lazyinit thread is created, then the filesystem can register its request in the request list. This thread then walks through the list of requests picking up scheduled requests and invoking ext4_init_inode_table(). Next schedule time for the request is computed by multiplying the time it took to zero out last inode table with wait multiplier, which can be set with the (init_itable=n) mount option (default is 10). We are doing this so we do not take the whole I/O bandwidth. When the thread is no longer necessary (request list is empty) it frees the appropriate structures and exits (and can be created later later by another filesystem). We do not disturb regular inode allocations in any way, it just do not care whether the inode table is, or is not zeroed. But when zeroing, we have to skip used inodes, obviously. Also we should prevent new inode allocations from the group, while zeroing is on the way. For that we take write alloc_sem lock in ext4_init_inode_table() and read alloc_sem in the ext4_claim_inode, so when we are unlucky and allocator hits the group which is currently being zeroed, it just has to wait. This can be suppresed using the mount option no_init_itable. Signed-off-by: Lukas Czerner <lczerner@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2010-10-28 09:30:05 +08:00
ret = 1;
if (!ret) {
timeout = jiffies;
ret = ext4_init_inode_table(sb, group,
elr->lr_timeout ? 0 : 1);
if (elr->lr_timeout == 0) {
timeout = (jiffies - timeout) *
elr->lr_sbi->s_li_wait_mult;
ext4: add support for lazy inode table initialization When the lazy_itable_init extended option is passed to mke2fs, it considerably speeds up filesystem creation because inode tables are not zeroed out. The fact that parts of the inode table are uninitialized is not a problem so long as the block group descriptors, which contain information regarding how much of the inode table has been initialized, has not been corrupted However, if the block group checksums are not valid, e2fsck must scan the entire inode table, and the the old, uninitialized data could potentially cause e2fsck to report false problems. Hence, it is important for the inode tables to be initialized as soon as possble. This commit adds this feature so that mke2fs can safely use the lazy inode table initialization feature to speed up formatting file systems. This is done via a new new kernel thread called ext4lazyinit, which is created on demand and destroyed, when it is no longer needed. There is only one thread for all ext4 filesystems in the system. When the first filesystem with inititable mount option is mounted, ext4lazyinit thread is created, then the filesystem can register its request in the request list. This thread then walks through the list of requests picking up scheduled requests and invoking ext4_init_inode_table(). Next schedule time for the request is computed by multiplying the time it took to zero out last inode table with wait multiplier, which can be set with the (init_itable=n) mount option (default is 10). We are doing this so we do not take the whole I/O bandwidth. When the thread is no longer necessary (request list is empty) it frees the appropriate structures and exits (and can be created later later by another filesystem). We do not disturb regular inode allocations in any way, it just do not care whether the inode table is, or is not zeroed. But when zeroing, we have to skip used inodes, obviously. Also we should prevent new inode allocations from the group, while zeroing is on the way. For that we take write alloc_sem lock in ext4_init_inode_table() and read alloc_sem in the ext4_claim_inode, so when we are unlucky and allocator hits the group which is currently being zeroed, it just has to wait. This can be suppresed using the mount option no_init_itable. Signed-off-by: Lukas Czerner <lczerner@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2010-10-28 09:30:05 +08:00
elr->lr_timeout = timeout;
}
elr->lr_next_sched = jiffies + elr->lr_timeout;
elr->lr_next_group = group + 1;
}
return ret;
}
/*
* Remove lr_request from the list_request and free the
* request structure. Should be called with li_list_mtx held
ext4: add support for lazy inode table initialization When the lazy_itable_init extended option is passed to mke2fs, it considerably speeds up filesystem creation because inode tables are not zeroed out. The fact that parts of the inode table are uninitialized is not a problem so long as the block group descriptors, which contain information regarding how much of the inode table has been initialized, has not been corrupted However, if the block group checksums are not valid, e2fsck must scan the entire inode table, and the the old, uninitialized data could potentially cause e2fsck to report false problems. Hence, it is important for the inode tables to be initialized as soon as possble. This commit adds this feature so that mke2fs can safely use the lazy inode table initialization feature to speed up formatting file systems. This is done via a new new kernel thread called ext4lazyinit, which is created on demand and destroyed, when it is no longer needed. There is only one thread for all ext4 filesystems in the system. When the first filesystem with inititable mount option is mounted, ext4lazyinit thread is created, then the filesystem can register its request in the request list. This thread then walks through the list of requests picking up scheduled requests and invoking ext4_init_inode_table(). Next schedule time for the request is computed by multiplying the time it took to zero out last inode table with wait multiplier, which can be set with the (init_itable=n) mount option (default is 10). We are doing this so we do not take the whole I/O bandwidth. When the thread is no longer necessary (request list is empty) it frees the appropriate structures and exits (and can be created later later by another filesystem). We do not disturb regular inode allocations in any way, it just do not care whether the inode table is, or is not zeroed. But when zeroing, we have to skip used inodes, obviously. Also we should prevent new inode allocations from the group, while zeroing is on the way. For that we take write alloc_sem lock in ext4_init_inode_table() and read alloc_sem in the ext4_claim_inode, so when we are unlucky and allocator hits the group which is currently being zeroed, it just has to wait. This can be suppresed using the mount option no_init_itable. Signed-off-by: Lukas Czerner <lczerner@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2010-10-28 09:30:05 +08:00
*/
static void ext4_remove_li_request(struct ext4_li_request *elr)
{
struct ext4_sb_info *sbi;
if (!elr)
return;
sbi = elr->lr_sbi;
list_del(&elr->lr_request);
sbi->s_li_request = NULL;
kfree(elr);
}
static void ext4_unregister_li_request(struct super_block *sb)
{
mutex_lock(&ext4_li_mtx);
if (!ext4_li_info) {
mutex_unlock(&ext4_li_mtx);
ext4: add support for lazy inode table initialization When the lazy_itable_init extended option is passed to mke2fs, it considerably speeds up filesystem creation because inode tables are not zeroed out. The fact that parts of the inode table are uninitialized is not a problem so long as the block group descriptors, which contain information regarding how much of the inode table has been initialized, has not been corrupted However, if the block group checksums are not valid, e2fsck must scan the entire inode table, and the the old, uninitialized data could potentially cause e2fsck to report false problems. Hence, it is important for the inode tables to be initialized as soon as possble. This commit adds this feature so that mke2fs can safely use the lazy inode table initialization feature to speed up formatting file systems. This is done via a new new kernel thread called ext4lazyinit, which is created on demand and destroyed, when it is no longer needed. There is only one thread for all ext4 filesystems in the system. When the first filesystem with inititable mount option is mounted, ext4lazyinit thread is created, then the filesystem can register its request in the request list. This thread then walks through the list of requests picking up scheduled requests and invoking ext4_init_inode_table(). Next schedule time for the request is computed by multiplying the time it took to zero out last inode table with wait multiplier, which can be set with the (init_itable=n) mount option (default is 10). We are doing this so we do not take the whole I/O bandwidth. When the thread is no longer necessary (request list is empty) it frees the appropriate structures and exits (and can be created later later by another filesystem). We do not disturb regular inode allocations in any way, it just do not care whether the inode table is, or is not zeroed. But when zeroing, we have to skip used inodes, obviously. Also we should prevent new inode allocations from the group, while zeroing is on the way. For that we take write alloc_sem lock in ext4_init_inode_table() and read alloc_sem in the ext4_claim_inode, so when we are unlucky and allocator hits the group which is currently being zeroed, it just has to wait. This can be suppresed using the mount option no_init_itable. Signed-off-by: Lukas Czerner <lczerner@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2010-10-28 09:30:05 +08:00
return;
}
ext4: add support for lazy inode table initialization When the lazy_itable_init extended option is passed to mke2fs, it considerably speeds up filesystem creation because inode tables are not zeroed out. The fact that parts of the inode table are uninitialized is not a problem so long as the block group descriptors, which contain information regarding how much of the inode table has been initialized, has not been corrupted However, if the block group checksums are not valid, e2fsck must scan the entire inode table, and the the old, uninitialized data could potentially cause e2fsck to report false problems. Hence, it is important for the inode tables to be initialized as soon as possble. This commit adds this feature so that mke2fs can safely use the lazy inode table initialization feature to speed up formatting file systems. This is done via a new new kernel thread called ext4lazyinit, which is created on demand and destroyed, when it is no longer needed. There is only one thread for all ext4 filesystems in the system. When the first filesystem with inititable mount option is mounted, ext4lazyinit thread is created, then the filesystem can register its request in the request list. This thread then walks through the list of requests picking up scheduled requests and invoking ext4_init_inode_table(). Next schedule time for the request is computed by multiplying the time it took to zero out last inode table with wait multiplier, which can be set with the (init_itable=n) mount option (default is 10). We are doing this so we do not take the whole I/O bandwidth. When the thread is no longer necessary (request list is empty) it frees the appropriate structures and exits (and can be created later later by another filesystem). We do not disturb regular inode allocations in any way, it just do not care whether the inode table is, or is not zeroed. But when zeroing, we have to skip used inodes, obviously. Also we should prevent new inode allocations from the group, while zeroing is on the way. For that we take write alloc_sem lock in ext4_init_inode_table() and read alloc_sem in the ext4_claim_inode, so when we are unlucky and allocator hits the group which is currently being zeroed, it just has to wait. This can be suppresed using the mount option no_init_itable. Signed-off-by: Lukas Czerner <lczerner@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2010-10-28 09:30:05 +08:00
mutex_lock(&ext4_li_info->li_list_mtx);
ext4_remove_li_request(EXT4_SB(sb)->s_li_request);
ext4: add support for lazy inode table initialization When the lazy_itable_init extended option is passed to mke2fs, it considerably speeds up filesystem creation because inode tables are not zeroed out. The fact that parts of the inode table are uninitialized is not a problem so long as the block group descriptors, which contain information regarding how much of the inode table has been initialized, has not been corrupted However, if the block group checksums are not valid, e2fsck must scan the entire inode table, and the the old, uninitialized data could potentially cause e2fsck to report false problems. Hence, it is important for the inode tables to be initialized as soon as possble. This commit adds this feature so that mke2fs can safely use the lazy inode table initialization feature to speed up formatting file systems. This is done via a new new kernel thread called ext4lazyinit, which is created on demand and destroyed, when it is no longer needed. There is only one thread for all ext4 filesystems in the system. When the first filesystem with inititable mount option is mounted, ext4lazyinit thread is created, then the filesystem can register its request in the request list. This thread then walks through the list of requests picking up scheduled requests and invoking ext4_init_inode_table(). Next schedule time for the request is computed by multiplying the time it took to zero out last inode table with wait multiplier, which can be set with the (init_itable=n) mount option (default is 10). We are doing this so we do not take the whole I/O bandwidth. When the thread is no longer necessary (request list is empty) it frees the appropriate structures and exits (and can be created later later by another filesystem). We do not disturb regular inode allocations in any way, it just do not care whether the inode table is, or is not zeroed. But when zeroing, we have to skip used inodes, obviously. Also we should prevent new inode allocations from the group, while zeroing is on the way. For that we take write alloc_sem lock in ext4_init_inode_table() and read alloc_sem in the ext4_claim_inode, so when we are unlucky and allocator hits the group which is currently being zeroed, it just has to wait. This can be suppresed using the mount option no_init_itable. Signed-off-by: Lukas Czerner <lczerner@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2010-10-28 09:30:05 +08:00
mutex_unlock(&ext4_li_info->li_list_mtx);
mutex_unlock(&ext4_li_mtx);
ext4: add support for lazy inode table initialization When the lazy_itable_init extended option is passed to mke2fs, it considerably speeds up filesystem creation because inode tables are not zeroed out. The fact that parts of the inode table are uninitialized is not a problem so long as the block group descriptors, which contain information regarding how much of the inode table has been initialized, has not been corrupted However, if the block group checksums are not valid, e2fsck must scan the entire inode table, and the the old, uninitialized data could potentially cause e2fsck to report false problems. Hence, it is important for the inode tables to be initialized as soon as possble. This commit adds this feature so that mke2fs can safely use the lazy inode table initialization feature to speed up formatting file systems. This is done via a new new kernel thread called ext4lazyinit, which is created on demand and destroyed, when it is no longer needed. There is only one thread for all ext4 filesystems in the system. When the first filesystem with inititable mount option is mounted, ext4lazyinit thread is created, then the filesystem can register its request in the request list. This thread then walks through the list of requests picking up scheduled requests and invoking ext4_init_inode_table(). Next schedule time for the request is computed by multiplying the time it took to zero out last inode table with wait multiplier, which can be set with the (init_itable=n) mount option (default is 10). We are doing this so we do not take the whole I/O bandwidth. When the thread is no longer necessary (request list is empty) it frees the appropriate structures and exits (and can be created later later by another filesystem). We do not disturb regular inode allocations in any way, it just do not care whether the inode table is, or is not zeroed. But when zeroing, we have to skip used inodes, obviously. Also we should prevent new inode allocations from the group, while zeroing is on the way. For that we take write alloc_sem lock in ext4_init_inode_table() and read alloc_sem in the ext4_claim_inode, so when we are unlucky and allocator hits the group which is currently being zeroed, it just has to wait. This can be suppresed using the mount option no_init_itable. Signed-off-by: Lukas Czerner <lczerner@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2010-10-28 09:30:05 +08:00
}
static struct task_struct *ext4_lazyinit_task;
ext4: add support for lazy inode table initialization When the lazy_itable_init extended option is passed to mke2fs, it considerably speeds up filesystem creation because inode tables are not zeroed out. The fact that parts of the inode table are uninitialized is not a problem so long as the block group descriptors, which contain information regarding how much of the inode table has been initialized, has not been corrupted However, if the block group checksums are not valid, e2fsck must scan the entire inode table, and the the old, uninitialized data could potentially cause e2fsck to report false problems. Hence, it is important for the inode tables to be initialized as soon as possble. This commit adds this feature so that mke2fs can safely use the lazy inode table initialization feature to speed up formatting file systems. This is done via a new new kernel thread called ext4lazyinit, which is created on demand and destroyed, when it is no longer needed. There is only one thread for all ext4 filesystems in the system. When the first filesystem with inititable mount option is mounted, ext4lazyinit thread is created, then the filesystem can register its request in the request list. This thread then walks through the list of requests picking up scheduled requests and invoking ext4_init_inode_table(). Next schedule time for the request is computed by multiplying the time it took to zero out last inode table with wait multiplier, which can be set with the (init_itable=n) mount option (default is 10). We are doing this so we do not take the whole I/O bandwidth. When the thread is no longer necessary (request list is empty) it frees the appropriate structures and exits (and can be created later later by another filesystem). We do not disturb regular inode allocations in any way, it just do not care whether the inode table is, or is not zeroed. But when zeroing, we have to skip used inodes, obviously. Also we should prevent new inode allocations from the group, while zeroing is on the way. For that we take write alloc_sem lock in ext4_init_inode_table() and read alloc_sem in the ext4_claim_inode, so when we are unlucky and allocator hits the group which is currently being zeroed, it just has to wait. This can be suppresed using the mount option no_init_itable. Signed-off-by: Lukas Czerner <lczerner@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2010-10-28 09:30:05 +08:00
/*
* This is the function where ext4lazyinit thread lives. It walks
* through the request list searching for next scheduled filesystem.
* When such a fs is found, run the lazy initialization request
* (ext4_rn_li_request) and keep track of the time spend in this
* function. Based on that time we compute next schedule time of
* the request. When walking through the list is complete, compute
* next waking time and put itself into sleep.
*/
static int ext4_lazyinit_thread(void *arg)
{
struct ext4_lazy_init *eli = (struct ext4_lazy_init *)arg;
struct list_head *pos, *n;
struct ext4_li_request *elr;
unsigned long next_wakeup, cur;
ext4: add support for lazy inode table initialization When the lazy_itable_init extended option is passed to mke2fs, it considerably speeds up filesystem creation because inode tables are not zeroed out. The fact that parts of the inode table are uninitialized is not a problem so long as the block group descriptors, which contain information regarding how much of the inode table has been initialized, has not been corrupted However, if the block group checksums are not valid, e2fsck must scan the entire inode table, and the the old, uninitialized data could potentially cause e2fsck to report false problems. Hence, it is important for the inode tables to be initialized as soon as possble. This commit adds this feature so that mke2fs can safely use the lazy inode table initialization feature to speed up formatting file systems. This is done via a new new kernel thread called ext4lazyinit, which is created on demand and destroyed, when it is no longer needed. There is only one thread for all ext4 filesystems in the system. When the first filesystem with inititable mount option is mounted, ext4lazyinit thread is created, then the filesystem can register its request in the request list. This thread then walks through the list of requests picking up scheduled requests and invoking ext4_init_inode_table(). Next schedule time for the request is computed by multiplying the time it took to zero out last inode table with wait multiplier, which can be set with the (init_itable=n) mount option (default is 10). We are doing this so we do not take the whole I/O bandwidth. When the thread is no longer necessary (request list is empty) it frees the appropriate structures and exits (and can be created later later by another filesystem). We do not disturb regular inode allocations in any way, it just do not care whether the inode table is, or is not zeroed. But when zeroing, we have to skip used inodes, obviously. Also we should prevent new inode allocations from the group, while zeroing is on the way. For that we take write alloc_sem lock in ext4_init_inode_table() and read alloc_sem in the ext4_claim_inode, so when we are unlucky and allocator hits the group which is currently being zeroed, it just has to wait. This can be suppresed using the mount option no_init_itable. Signed-off-by: Lukas Czerner <lczerner@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2010-10-28 09:30:05 +08:00
BUG_ON(NULL == eli);
cont_thread:
while (true) {
next_wakeup = MAX_JIFFY_OFFSET;
mutex_lock(&eli->li_list_mtx);
if (list_empty(&eli->li_request_list)) {
mutex_unlock(&eli->li_list_mtx);
goto exit_thread;
}
list_for_each_safe(pos, n, &eli->li_request_list) {
int err = 0;
int progress = 0;
ext4: add support for lazy inode table initialization When the lazy_itable_init extended option is passed to mke2fs, it considerably speeds up filesystem creation because inode tables are not zeroed out. The fact that parts of the inode table are uninitialized is not a problem so long as the block group descriptors, which contain information regarding how much of the inode table has been initialized, has not been corrupted However, if the block group checksums are not valid, e2fsck must scan the entire inode table, and the the old, uninitialized data could potentially cause e2fsck to report false problems. Hence, it is important for the inode tables to be initialized as soon as possble. This commit adds this feature so that mke2fs can safely use the lazy inode table initialization feature to speed up formatting file systems. This is done via a new new kernel thread called ext4lazyinit, which is created on demand and destroyed, when it is no longer needed. There is only one thread for all ext4 filesystems in the system. When the first filesystem with inititable mount option is mounted, ext4lazyinit thread is created, then the filesystem can register its request in the request list. This thread then walks through the list of requests picking up scheduled requests and invoking ext4_init_inode_table(). Next schedule time for the request is computed by multiplying the time it took to zero out last inode table with wait multiplier, which can be set with the (init_itable=n) mount option (default is 10). We are doing this so we do not take the whole I/O bandwidth. When the thread is no longer necessary (request list is empty) it frees the appropriate structures and exits (and can be created later later by another filesystem). We do not disturb regular inode allocations in any way, it just do not care whether the inode table is, or is not zeroed. But when zeroing, we have to skip used inodes, obviously. Also we should prevent new inode allocations from the group, while zeroing is on the way. For that we take write alloc_sem lock in ext4_init_inode_table() and read alloc_sem in the ext4_claim_inode, so when we are unlucky and allocator hits the group which is currently being zeroed, it just has to wait. This can be suppresed using the mount option no_init_itable. Signed-off-by: Lukas Czerner <lczerner@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2010-10-28 09:30:05 +08:00
elr = list_entry(pos, struct ext4_li_request,
lr_request);
if (time_before(jiffies, elr->lr_next_sched)) {
if (time_before(elr->lr_next_sched, next_wakeup))
next_wakeup = elr->lr_next_sched;
continue;
}
if (down_read_trylock(&elr->lr_super->s_umount)) {
if (sb_start_write_trylock(elr->lr_super)) {
progress = 1;
/*
* We hold sb->s_umount, sb can not
* be removed from the list, it is
* now safe to drop li_list_mtx
*/
mutex_unlock(&eli->li_list_mtx);
err = ext4_run_li_request(elr);
sb_end_write(elr->lr_super);
mutex_lock(&eli->li_list_mtx);
n = pos->next;
}
up_read((&elr->lr_super->s_umount));
}
/* error, remove the lazy_init job */
if (err) {
ext4_remove_li_request(elr);
continue;
}
if (!progress) {
elr->lr_next_sched = jiffies +
(prandom_u32()
% (EXT4_DEF_LI_MAX_START_DELAY * HZ));
ext4: add support for lazy inode table initialization When the lazy_itable_init extended option is passed to mke2fs, it considerably speeds up filesystem creation because inode tables are not zeroed out. The fact that parts of the inode table are uninitialized is not a problem so long as the block group descriptors, which contain information regarding how much of the inode table has been initialized, has not been corrupted However, if the block group checksums are not valid, e2fsck must scan the entire inode table, and the the old, uninitialized data could potentially cause e2fsck to report false problems. Hence, it is important for the inode tables to be initialized as soon as possble. This commit adds this feature so that mke2fs can safely use the lazy inode table initialization feature to speed up formatting file systems. This is done via a new new kernel thread called ext4lazyinit, which is created on demand and destroyed, when it is no longer needed. There is only one thread for all ext4 filesystems in the system. When the first filesystem with inititable mount option is mounted, ext4lazyinit thread is created, then the filesystem can register its request in the request list. This thread then walks through the list of requests picking up scheduled requests and invoking ext4_init_inode_table(). Next schedule time for the request is computed by multiplying the time it took to zero out last inode table with wait multiplier, which can be set with the (init_itable=n) mount option (default is 10). We are doing this so we do not take the whole I/O bandwidth. When the thread is no longer necessary (request list is empty) it frees the appropriate structures and exits (and can be created later later by another filesystem). We do not disturb regular inode allocations in any way, it just do not care whether the inode table is, or is not zeroed. But when zeroing, we have to skip used inodes, obviously. Also we should prevent new inode allocations from the group, while zeroing is on the way. For that we take write alloc_sem lock in ext4_init_inode_table() and read alloc_sem in the ext4_claim_inode, so when we are unlucky and allocator hits the group which is currently being zeroed, it just has to wait. This can be suppresed using the mount option no_init_itable. Signed-off-by: Lukas Czerner <lczerner@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2010-10-28 09:30:05 +08:00
}
if (time_before(elr->lr_next_sched, next_wakeup))
next_wakeup = elr->lr_next_sched;
}
mutex_unlock(&eli->li_list_mtx);
try_to_freeze();
ext4: add support for lazy inode table initialization When the lazy_itable_init extended option is passed to mke2fs, it considerably speeds up filesystem creation because inode tables are not zeroed out. The fact that parts of the inode table are uninitialized is not a problem so long as the block group descriptors, which contain information regarding how much of the inode table has been initialized, has not been corrupted However, if the block group checksums are not valid, e2fsck must scan the entire inode table, and the the old, uninitialized data could potentially cause e2fsck to report false problems. Hence, it is important for the inode tables to be initialized as soon as possble. This commit adds this feature so that mke2fs can safely use the lazy inode table initialization feature to speed up formatting file systems. This is done via a new new kernel thread called ext4lazyinit, which is created on demand and destroyed, when it is no longer needed. There is only one thread for all ext4 filesystems in the system. When the first filesystem with inititable mount option is mounted, ext4lazyinit thread is created, then the filesystem can register its request in the request list. This thread then walks through the list of requests picking up scheduled requests and invoking ext4_init_inode_table(). Next schedule time for the request is computed by multiplying the time it took to zero out last inode table with wait multiplier, which can be set with the (init_itable=n) mount option (default is 10). We are doing this so we do not take the whole I/O bandwidth. When the thread is no longer necessary (request list is empty) it frees the appropriate structures and exits (and can be created later later by another filesystem). We do not disturb regular inode allocations in any way, it just do not care whether the inode table is, or is not zeroed. But when zeroing, we have to skip used inodes, obviously. Also we should prevent new inode allocations from the group, while zeroing is on the way. For that we take write alloc_sem lock in ext4_init_inode_table() and read alloc_sem in the ext4_claim_inode, so when we are unlucky and allocator hits the group which is currently being zeroed, it just has to wait. This can be suppresed using the mount option no_init_itable. Signed-off-by: Lukas Czerner <lczerner@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2010-10-28 09:30:05 +08:00
cur = jiffies;
if ((time_after_eq(cur, next_wakeup)) ||
(MAX_JIFFY_OFFSET == next_wakeup)) {
ext4: add support for lazy inode table initialization When the lazy_itable_init extended option is passed to mke2fs, it considerably speeds up filesystem creation because inode tables are not zeroed out. The fact that parts of the inode table are uninitialized is not a problem so long as the block group descriptors, which contain information regarding how much of the inode table has been initialized, has not been corrupted However, if the block group checksums are not valid, e2fsck must scan the entire inode table, and the the old, uninitialized data could potentially cause e2fsck to report false problems. Hence, it is important for the inode tables to be initialized as soon as possble. This commit adds this feature so that mke2fs can safely use the lazy inode table initialization feature to speed up formatting file systems. This is done via a new new kernel thread called ext4lazyinit, which is created on demand and destroyed, when it is no longer needed. There is only one thread for all ext4 filesystems in the system. When the first filesystem with inititable mount option is mounted, ext4lazyinit thread is created, then the filesystem can register its request in the request list. This thread then walks through the list of requests picking up scheduled requests and invoking ext4_init_inode_table(). Next schedule time for the request is computed by multiplying the time it took to zero out last inode table with wait multiplier, which can be set with the (init_itable=n) mount option (default is 10). We are doing this so we do not take the whole I/O bandwidth. When the thread is no longer necessary (request list is empty) it frees the appropriate structures and exits (and can be created later later by another filesystem). We do not disturb regular inode allocations in any way, it just do not care whether the inode table is, or is not zeroed. But when zeroing, we have to skip used inodes, obviously. Also we should prevent new inode allocations from the group, while zeroing is on the way. For that we take write alloc_sem lock in ext4_init_inode_table() and read alloc_sem in the ext4_claim_inode, so when we are unlucky and allocator hits the group which is currently being zeroed, it just has to wait. This can be suppresed using the mount option no_init_itable. Signed-off-by: Lukas Czerner <lczerner@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2010-10-28 09:30:05 +08:00
cond_resched();
continue;
}
schedule_timeout_interruptible(next_wakeup - cur);
if (kthread_should_stop()) {
ext4_clear_request_list();
goto exit_thread;
}
ext4: add support for lazy inode table initialization When the lazy_itable_init extended option is passed to mke2fs, it considerably speeds up filesystem creation because inode tables are not zeroed out. The fact that parts of the inode table are uninitialized is not a problem so long as the block group descriptors, which contain information regarding how much of the inode table has been initialized, has not been corrupted However, if the block group checksums are not valid, e2fsck must scan the entire inode table, and the the old, uninitialized data could potentially cause e2fsck to report false problems. Hence, it is important for the inode tables to be initialized as soon as possble. This commit adds this feature so that mke2fs can safely use the lazy inode table initialization feature to speed up formatting file systems. This is done via a new new kernel thread called ext4lazyinit, which is created on demand and destroyed, when it is no longer needed. There is only one thread for all ext4 filesystems in the system. When the first filesystem with inititable mount option is mounted, ext4lazyinit thread is created, then the filesystem can register its request in the request list. This thread then walks through the list of requests picking up scheduled requests and invoking ext4_init_inode_table(). Next schedule time for the request is computed by multiplying the time it took to zero out last inode table with wait multiplier, which can be set with the (init_itable=n) mount option (default is 10). We are doing this so we do not take the whole I/O bandwidth. When the thread is no longer necessary (request list is empty) it frees the appropriate structures and exits (and can be created later later by another filesystem). We do not disturb regular inode allocations in any way, it just do not care whether the inode table is, or is not zeroed. But when zeroing, we have to skip used inodes, obviously. Also we should prevent new inode allocations from the group, while zeroing is on the way. For that we take write alloc_sem lock in ext4_init_inode_table() and read alloc_sem in the ext4_claim_inode, so when we are unlucky and allocator hits the group which is currently being zeroed, it just has to wait. This can be suppresed using the mount option no_init_itable. Signed-off-by: Lukas Czerner <lczerner@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2010-10-28 09:30:05 +08:00
}
exit_thread:
/*
* It looks like the request list is empty, but we need
* to check it under the li_list_mtx lock, to prevent any
* additions into it, and of course we should lock ext4_li_mtx
* to atomically free the list and ext4_li_info, because at
* this point another ext4 filesystem could be registering
* new one.
*/
mutex_lock(&ext4_li_mtx);
mutex_lock(&eli->li_list_mtx);
if (!list_empty(&eli->li_request_list)) {
mutex_unlock(&eli->li_list_mtx);
mutex_unlock(&ext4_li_mtx);
goto cont_thread;
}
mutex_unlock(&eli->li_list_mtx);
kfree(ext4_li_info);
ext4_li_info = NULL;
mutex_unlock(&ext4_li_mtx);
return 0;
}
static void ext4_clear_request_list(void)
{
struct list_head *pos, *n;
struct ext4_li_request *elr;
mutex_lock(&ext4_li_info->li_list_mtx);
list_for_each_safe(pos, n, &ext4_li_info->li_request_list) {
elr = list_entry(pos, struct ext4_li_request,
lr_request);
ext4_remove_li_request(elr);
}
mutex_unlock(&ext4_li_info->li_list_mtx);
}
static int ext4_run_lazyinit_thread(void)
{
ext4_lazyinit_task = kthread_run(ext4_lazyinit_thread,
ext4_li_info, "ext4lazyinit");
if (IS_ERR(ext4_lazyinit_task)) {
int err = PTR_ERR(ext4_lazyinit_task);
ext4: add support for lazy inode table initialization When the lazy_itable_init extended option is passed to mke2fs, it considerably speeds up filesystem creation because inode tables are not zeroed out. The fact that parts of the inode table are uninitialized is not a problem so long as the block group descriptors, which contain information regarding how much of the inode table has been initialized, has not been corrupted However, if the block group checksums are not valid, e2fsck must scan the entire inode table, and the the old, uninitialized data could potentially cause e2fsck to report false problems. Hence, it is important for the inode tables to be initialized as soon as possble. This commit adds this feature so that mke2fs can safely use the lazy inode table initialization feature to speed up formatting file systems. This is done via a new new kernel thread called ext4lazyinit, which is created on demand and destroyed, when it is no longer needed. There is only one thread for all ext4 filesystems in the system. When the first filesystem with inititable mount option is mounted, ext4lazyinit thread is created, then the filesystem can register its request in the request list. This thread then walks through the list of requests picking up scheduled requests and invoking ext4_init_inode_table(). Next schedule time for the request is computed by multiplying the time it took to zero out last inode table with wait multiplier, which can be set with the (init_itable=n) mount option (default is 10). We are doing this so we do not take the whole I/O bandwidth. When the thread is no longer necessary (request list is empty) it frees the appropriate structures and exits (and can be created later later by another filesystem). We do not disturb regular inode allocations in any way, it just do not care whether the inode table is, or is not zeroed. But when zeroing, we have to skip used inodes, obviously. Also we should prevent new inode allocations from the group, while zeroing is on the way. For that we take write alloc_sem lock in ext4_init_inode_table() and read alloc_sem in the ext4_claim_inode, so when we are unlucky and allocator hits the group which is currently being zeroed, it just has to wait. This can be suppresed using the mount option no_init_itable. Signed-off-by: Lukas Czerner <lczerner@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2010-10-28 09:30:05 +08:00
ext4_clear_request_list();
kfree(ext4_li_info);
ext4_li_info = NULL;
printk(KERN_CRIT "EXT4-fs: error %d creating inode table "
ext4: add support for lazy inode table initialization When the lazy_itable_init extended option is passed to mke2fs, it considerably speeds up filesystem creation because inode tables are not zeroed out. The fact that parts of the inode table are uninitialized is not a problem so long as the block group descriptors, which contain information regarding how much of the inode table has been initialized, has not been corrupted However, if the block group checksums are not valid, e2fsck must scan the entire inode table, and the the old, uninitialized data could potentially cause e2fsck to report false problems. Hence, it is important for the inode tables to be initialized as soon as possble. This commit adds this feature so that mke2fs can safely use the lazy inode table initialization feature to speed up formatting file systems. This is done via a new new kernel thread called ext4lazyinit, which is created on demand and destroyed, when it is no longer needed. There is only one thread for all ext4 filesystems in the system. When the first filesystem with inititable mount option is mounted, ext4lazyinit thread is created, then the filesystem can register its request in the request list. This thread then walks through the list of requests picking up scheduled requests and invoking ext4_init_inode_table(). Next schedule time for the request is computed by multiplying the time it took to zero out last inode table with wait multiplier, which can be set with the (init_itable=n) mount option (default is 10). We are doing this so we do not take the whole I/O bandwidth. When the thread is no longer necessary (request list is empty) it frees the appropriate structures and exits (and can be created later later by another filesystem). We do not disturb regular inode allocations in any way, it just do not care whether the inode table is, or is not zeroed. But when zeroing, we have to skip used inodes, obviously. Also we should prevent new inode allocations from the group, while zeroing is on the way. For that we take write alloc_sem lock in ext4_init_inode_table() and read alloc_sem in the ext4_claim_inode, so when we are unlucky and allocator hits the group which is currently being zeroed, it just has to wait. This can be suppresed using the mount option no_init_itable. Signed-off-by: Lukas Czerner <lczerner@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2010-10-28 09:30:05 +08:00
"initialization thread\n",
err);
return err;
}
ext4_li_info->li_state |= EXT4_LAZYINIT_RUNNING;
return 0;
}
/*
* Check whether it make sense to run itable init. thread or not.
* If there is at least one uninitialized inode table, return
* corresponding group number, else the loop goes through all
* groups and return total number of groups.
*/
static ext4_group_t ext4_has_uninit_itable(struct super_block *sb)
{
ext4_group_t group, ngroups = EXT4_SB(sb)->s_groups_count;
struct ext4_group_desc *gdp = NULL;
for (group = 0; group < ngroups; group++) {
gdp = ext4_get_group_desc(sb, group, NULL);
if (!gdp)
continue;
if (!(gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_ZEROED)))
break;
}
return group;
}
static int ext4_li_info_new(void)
{
struct ext4_lazy_init *eli = NULL;
eli = kzalloc(sizeof(*eli), GFP_KERNEL);
if (!eli)
return -ENOMEM;
INIT_LIST_HEAD(&eli->li_request_list);
mutex_init(&eli->li_list_mtx);
eli->li_state |= EXT4_LAZYINIT_QUIT;
ext4_li_info = eli;
return 0;
}
static struct ext4_li_request *ext4_li_request_new(struct super_block *sb,
ext4_group_t start)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
struct ext4_li_request *elr;
elr = kzalloc(sizeof(*elr), GFP_KERNEL);
if (!elr)
return NULL;
elr->lr_super = sb;
elr->lr_sbi = sbi;
elr->lr_next_group = start;
/*
* Randomize first schedule time of the request to
* spread the inode table initialization requests
* better.
*/
elr->lr_next_sched = jiffies + (prandom_u32() %
(EXT4_DEF_LI_MAX_START_DELAY * HZ));
ext4: add support for lazy inode table initialization When the lazy_itable_init extended option is passed to mke2fs, it considerably speeds up filesystem creation because inode tables are not zeroed out. The fact that parts of the inode table are uninitialized is not a problem so long as the block group descriptors, which contain information regarding how much of the inode table has been initialized, has not been corrupted However, if the block group checksums are not valid, e2fsck must scan the entire inode table, and the the old, uninitialized data could potentially cause e2fsck to report false problems. Hence, it is important for the inode tables to be initialized as soon as possble. This commit adds this feature so that mke2fs can safely use the lazy inode table initialization feature to speed up formatting file systems. This is done via a new new kernel thread called ext4lazyinit, which is created on demand and destroyed, when it is no longer needed. There is only one thread for all ext4 filesystems in the system. When the first filesystem with inititable mount option is mounted, ext4lazyinit thread is created, then the filesystem can register its request in the request list. This thread then walks through the list of requests picking up scheduled requests and invoking ext4_init_inode_table(). Next schedule time for the request is computed by multiplying the time it took to zero out last inode table with wait multiplier, which can be set with the (init_itable=n) mount option (default is 10). We are doing this so we do not take the whole I/O bandwidth. When the thread is no longer necessary (request list is empty) it frees the appropriate structures and exits (and can be created later later by another filesystem). We do not disturb regular inode allocations in any way, it just do not care whether the inode table is, or is not zeroed. But when zeroing, we have to skip used inodes, obviously. Also we should prevent new inode allocations from the group, while zeroing is on the way. For that we take write alloc_sem lock in ext4_init_inode_table() and read alloc_sem in the ext4_claim_inode, so when we are unlucky and allocator hits the group which is currently being zeroed, it just has to wait. This can be suppresed using the mount option no_init_itable. Signed-off-by: Lukas Czerner <lczerner@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2010-10-28 09:30:05 +08:00
return elr;
}
int ext4_register_li_request(struct super_block *sb,
ext4_group_t first_not_zeroed)
ext4: add support for lazy inode table initialization When the lazy_itable_init extended option is passed to mke2fs, it considerably speeds up filesystem creation because inode tables are not zeroed out. The fact that parts of the inode table are uninitialized is not a problem so long as the block group descriptors, which contain information regarding how much of the inode table has been initialized, has not been corrupted However, if the block group checksums are not valid, e2fsck must scan the entire inode table, and the the old, uninitialized data could potentially cause e2fsck to report false problems. Hence, it is important for the inode tables to be initialized as soon as possble. This commit adds this feature so that mke2fs can safely use the lazy inode table initialization feature to speed up formatting file systems. This is done via a new new kernel thread called ext4lazyinit, which is created on demand and destroyed, when it is no longer needed. There is only one thread for all ext4 filesystems in the system. When the first filesystem with inititable mount option is mounted, ext4lazyinit thread is created, then the filesystem can register its request in the request list. This thread then walks through the list of requests picking up scheduled requests and invoking ext4_init_inode_table(). Next schedule time for the request is computed by multiplying the time it took to zero out last inode table with wait multiplier, which can be set with the (init_itable=n) mount option (default is 10). We are doing this so we do not take the whole I/O bandwidth. When the thread is no longer necessary (request list is empty) it frees the appropriate structures and exits (and can be created later later by another filesystem). We do not disturb regular inode allocations in any way, it just do not care whether the inode table is, or is not zeroed. But when zeroing, we have to skip used inodes, obviously. Also we should prevent new inode allocations from the group, while zeroing is on the way. For that we take write alloc_sem lock in ext4_init_inode_table() and read alloc_sem in the ext4_claim_inode, so when we are unlucky and allocator hits the group which is currently being zeroed, it just has to wait. This can be suppresed using the mount option no_init_itable. Signed-off-by: Lukas Czerner <lczerner@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2010-10-28 09:30:05 +08:00
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
struct ext4_li_request *elr = NULL;
ext4: add support for lazy inode table initialization When the lazy_itable_init extended option is passed to mke2fs, it considerably speeds up filesystem creation because inode tables are not zeroed out. The fact that parts of the inode table are uninitialized is not a problem so long as the block group descriptors, which contain information regarding how much of the inode table has been initialized, has not been corrupted However, if the block group checksums are not valid, e2fsck must scan the entire inode table, and the the old, uninitialized data could potentially cause e2fsck to report false problems. Hence, it is important for the inode tables to be initialized as soon as possble. This commit adds this feature so that mke2fs can safely use the lazy inode table initialization feature to speed up formatting file systems. This is done via a new new kernel thread called ext4lazyinit, which is created on demand and destroyed, when it is no longer needed. There is only one thread for all ext4 filesystems in the system. When the first filesystem with inititable mount option is mounted, ext4lazyinit thread is created, then the filesystem can register its request in the request list. This thread then walks through the list of requests picking up scheduled requests and invoking ext4_init_inode_table(). Next schedule time for the request is computed by multiplying the time it took to zero out last inode table with wait multiplier, which can be set with the (init_itable=n) mount option (default is 10). We are doing this so we do not take the whole I/O bandwidth. When the thread is no longer necessary (request list is empty) it frees the appropriate structures and exits (and can be created later later by another filesystem). We do not disturb regular inode allocations in any way, it just do not care whether the inode table is, or is not zeroed. But when zeroing, we have to skip used inodes, obviously. Also we should prevent new inode allocations from the group, while zeroing is on the way. For that we take write alloc_sem lock in ext4_init_inode_table() and read alloc_sem in the ext4_claim_inode, so when we are unlucky and allocator hits the group which is currently being zeroed, it just has to wait. This can be suppresed using the mount option no_init_itable. Signed-off-by: Lukas Czerner <lczerner@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2010-10-28 09:30:05 +08:00
ext4_group_t ngroups = EXT4_SB(sb)->s_groups_count;
int ret = 0;
ext4: add support for lazy inode table initialization When the lazy_itable_init extended option is passed to mke2fs, it considerably speeds up filesystem creation because inode tables are not zeroed out. The fact that parts of the inode table are uninitialized is not a problem so long as the block group descriptors, which contain information regarding how much of the inode table has been initialized, has not been corrupted However, if the block group checksums are not valid, e2fsck must scan the entire inode table, and the the old, uninitialized data could potentially cause e2fsck to report false problems. Hence, it is important for the inode tables to be initialized as soon as possble. This commit adds this feature so that mke2fs can safely use the lazy inode table initialization feature to speed up formatting file systems. This is done via a new new kernel thread called ext4lazyinit, which is created on demand and destroyed, when it is no longer needed. There is only one thread for all ext4 filesystems in the system. When the first filesystem with inititable mount option is mounted, ext4lazyinit thread is created, then the filesystem can register its request in the request list. This thread then walks through the list of requests picking up scheduled requests and invoking ext4_init_inode_table(). Next schedule time for the request is computed by multiplying the time it took to zero out last inode table with wait multiplier, which can be set with the (init_itable=n) mount option (default is 10). We are doing this so we do not take the whole I/O bandwidth. When the thread is no longer necessary (request list is empty) it frees the appropriate structures and exits (and can be created later later by another filesystem). We do not disturb regular inode allocations in any way, it just do not care whether the inode table is, or is not zeroed. But when zeroing, we have to skip used inodes, obviously. Also we should prevent new inode allocations from the group, while zeroing is on the way. For that we take write alloc_sem lock in ext4_init_inode_table() and read alloc_sem in the ext4_claim_inode, so when we are unlucky and allocator hits the group which is currently being zeroed, it just has to wait. This can be suppresed using the mount option no_init_itable. Signed-off-by: Lukas Czerner <lczerner@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2010-10-28 09:30:05 +08:00
mutex_lock(&ext4_li_mtx);
if (sbi->s_li_request != NULL) {
/*
* Reset timeout so it can be computed again, because
* s_li_wait_mult might have changed.
*/
sbi->s_li_request->lr_timeout = 0;
goto out;
}
ext4: add support for lazy inode table initialization When the lazy_itable_init extended option is passed to mke2fs, it considerably speeds up filesystem creation because inode tables are not zeroed out. The fact that parts of the inode table are uninitialized is not a problem so long as the block group descriptors, which contain information regarding how much of the inode table has been initialized, has not been corrupted However, if the block group checksums are not valid, e2fsck must scan the entire inode table, and the the old, uninitialized data could potentially cause e2fsck to report false problems. Hence, it is important for the inode tables to be initialized as soon as possble. This commit adds this feature so that mke2fs can safely use the lazy inode table initialization feature to speed up formatting file systems. This is done via a new new kernel thread called ext4lazyinit, which is created on demand and destroyed, when it is no longer needed. There is only one thread for all ext4 filesystems in the system. When the first filesystem with inititable mount option is mounted, ext4lazyinit thread is created, then the filesystem can register its request in the request list. This thread then walks through the list of requests picking up scheduled requests and invoking ext4_init_inode_table(). Next schedule time for the request is computed by multiplying the time it took to zero out last inode table with wait multiplier, which can be set with the (init_itable=n) mount option (default is 10). We are doing this so we do not take the whole I/O bandwidth. When the thread is no longer necessary (request list is empty) it frees the appropriate structures and exits (and can be created later later by another filesystem). We do not disturb regular inode allocations in any way, it just do not care whether the inode table is, or is not zeroed. But when zeroing, we have to skip used inodes, obviously. Also we should prevent new inode allocations from the group, while zeroing is on the way. For that we take write alloc_sem lock in ext4_init_inode_table() and read alloc_sem in the ext4_claim_inode, so when we are unlucky and allocator hits the group which is currently being zeroed, it just has to wait. This can be suppresed using the mount option no_init_itable. Signed-off-by: Lukas Czerner <lczerner@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2010-10-28 09:30:05 +08:00
if (first_not_zeroed == ngroups ||
(sb->s_flags & MS_RDONLY) ||
!test_opt(sb, INIT_INODE_TABLE))
goto out;
ext4: add support for lazy inode table initialization When the lazy_itable_init extended option is passed to mke2fs, it considerably speeds up filesystem creation because inode tables are not zeroed out. The fact that parts of the inode table are uninitialized is not a problem so long as the block group descriptors, which contain information regarding how much of the inode table has been initialized, has not been corrupted However, if the block group checksums are not valid, e2fsck must scan the entire inode table, and the the old, uninitialized data could potentially cause e2fsck to report false problems. Hence, it is important for the inode tables to be initialized as soon as possble. This commit adds this feature so that mke2fs can safely use the lazy inode table initialization feature to speed up formatting file systems. This is done via a new new kernel thread called ext4lazyinit, which is created on demand and destroyed, when it is no longer needed. There is only one thread for all ext4 filesystems in the system. When the first filesystem with inititable mount option is mounted, ext4lazyinit thread is created, then the filesystem can register its request in the request list. This thread then walks through the list of requests picking up scheduled requests and invoking ext4_init_inode_table(). Next schedule time for the request is computed by multiplying the time it took to zero out last inode table with wait multiplier, which can be set with the (init_itable=n) mount option (default is 10). We are doing this so we do not take the whole I/O bandwidth. When the thread is no longer necessary (request list is empty) it frees the appropriate structures and exits (and can be created later later by another filesystem). We do not disturb regular inode allocations in any way, it just do not care whether the inode table is, or is not zeroed. But when zeroing, we have to skip used inodes, obviously. Also we should prevent new inode allocations from the group, while zeroing is on the way. For that we take write alloc_sem lock in ext4_init_inode_table() and read alloc_sem in the ext4_claim_inode, so when we are unlucky and allocator hits the group which is currently being zeroed, it just has to wait. This can be suppresed using the mount option no_init_itable. Signed-off-by: Lukas Czerner <lczerner@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2010-10-28 09:30:05 +08:00
elr = ext4_li_request_new(sb, first_not_zeroed);
if (!elr) {
ret = -ENOMEM;
goto out;
}
ext4: add support for lazy inode table initialization When the lazy_itable_init extended option is passed to mke2fs, it considerably speeds up filesystem creation because inode tables are not zeroed out. The fact that parts of the inode table are uninitialized is not a problem so long as the block group descriptors, which contain information regarding how much of the inode table has been initialized, has not been corrupted However, if the block group checksums are not valid, e2fsck must scan the entire inode table, and the the old, uninitialized data could potentially cause e2fsck to report false problems. Hence, it is important for the inode tables to be initialized as soon as possble. This commit adds this feature so that mke2fs can safely use the lazy inode table initialization feature to speed up formatting file systems. This is done via a new new kernel thread called ext4lazyinit, which is created on demand and destroyed, when it is no longer needed. There is only one thread for all ext4 filesystems in the system. When the first filesystem with inititable mount option is mounted, ext4lazyinit thread is created, then the filesystem can register its request in the request list. This thread then walks through the list of requests picking up scheduled requests and invoking ext4_init_inode_table(). Next schedule time for the request is computed by multiplying the time it took to zero out last inode table with wait multiplier, which can be set with the (init_itable=n) mount option (default is 10). We are doing this so we do not take the whole I/O bandwidth. When the thread is no longer necessary (request list is empty) it frees the appropriate structures and exits (and can be created later later by another filesystem). We do not disturb regular inode allocations in any way, it just do not care whether the inode table is, or is not zeroed. But when zeroing, we have to skip used inodes, obviously. Also we should prevent new inode allocations from the group, while zeroing is on the way. For that we take write alloc_sem lock in ext4_init_inode_table() and read alloc_sem in the ext4_claim_inode, so when we are unlucky and allocator hits the group which is currently being zeroed, it just has to wait. This can be suppresed using the mount option no_init_itable. Signed-off-by: Lukas Czerner <lczerner@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2010-10-28 09:30:05 +08:00
if (NULL == ext4_li_info) {
ret = ext4_li_info_new();
if (ret)
goto out;
}
mutex_lock(&ext4_li_info->li_list_mtx);
list_add(&elr->lr_request, &ext4_li_info->li_request_list);
mutex_unlock(&ext4_li_info->li_list_mtx);
sbi->s_li_request = elr;
/*
* set elr to NULL here since it has been inserted to
* the request_list and the removal and free of it is
* handled by ext4_clear_request_list from now on.
*/
elr = NULL;
ext4: add support for lazy inode table initialization When the lazy_itable_init extended option is passed to mke2fs, it considerably speeds up filesystem creation because inode tables are not zeroed out. The fact that parts of the inode table are uninitialized is not a problem so long as the block group descriptors, which contain information regarding how much of the inode table has been initialized, has not been corrupted However, if the block group checksums are not valid, e2fsck must scan the entire inode table, and the the old, uninitialized data could potentially cause e2fsck to report false problems. Hence, it is important for the inode tables to be initialized as soon as possble. This commit adds this feature so that mke2fs can safely use the lazy inode table initialization feature to speed up formatting file systems. This is done via a new new kernel thread called ext4lazyinit, which is created on demand and destroyed, when it is no longer needed. There is only one thread for all ext4 filesystems in the system. When the first filesystem with inititable mount option is mounted, ext4lazyinit thread is created, then the filesystem can register its request in the request list. This thread then walks through the list of requests picking up scheduled requests and invoking ext4_init_inode_table(). Next schedule time for the request is computed by multiplying the time it took to zero out last inode table with wait multiplier, which can be set with the (init_itable=n) mount option (default is 10). We are doing this so we do not take the whole I/O bandwidth. When the thread is no longer necessary (request list is empty) it frees the appropriate structures and exits (and can be created later later by another filesystem). We do not disturb regular inode allocations in any way, it just do not care whether the inode table is, or is not zeroed. But when zeroing, we have to skip used inodes, obviously. Also we should prevent new inode allocations from the group, while zeroing is on the way. For that we take write alloc_sem lock in ext4_init_inode_table() and read alloc_sem in the ext4_claim_inode, so when we are unlucky and allocator hits the group which is currently being zeroed, it just has to wait. This can be suppresed using the mount option no_init_itable. Signed-off-by: Lukas Czerner <lczerner@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2010-10-28 09:30:05 +08:00
if (!(ext4_li_info->li_state & EXT4_LAZYINIT_RUNNING)) {
ret = ext4_run_lazyinit_thread();
if (ret)
goto out;
}
out:
mutex_unlock(&ext4_li_mtx);
if (ret)
ext4: add support for lazy inode table initialization When the lazy_itable_init extended option is passed to mke2fs, it considerably speeds up filesystem creation because inode tables are not zeroed out. The fact that parts of the inode table are uninitialized is not a problem so long as the block group descriptors, which contain information regarding how much of the inode table has been initialized, has not been corrupted However, if the block group checksums are not valid, e2fsck must scan the entire inode table, and the the old, uninitialized data could potentially cause e2fsck to report false problems. Hence, it is important for the inode tables to be initialized as soon as possble. This commit adds this feature so that mke2fs can safely use the lazy inode table initialization feature to speed up formatting file systems. This is done via a new new kernel thread called ext4lazyinit, which is created on demand and destroyed, when it is no longer needed. There is only one thread for all ext4 filesystems in the system. When the first filesystem with inititable mount option is mounted, ext4lazyinit thread is created, then the filesystem can register its request in the request list. This thread then walks through the list of requests picking up scheduled requests and invoking ext4_init_inode_table(). Next schedule time for the request is computed by multiplying the time it took to zero out last inode table with wait multiplier, which can be set with the (init_itable=n) mount option (default is 10). We are doing this so we do not take the whole I/O bandwidth. When the thread is no longer necessary (request list is empty) it frees the appropriate structures and exits (and can be created later later by another filesystem). We do not disturb regular inode allocations in any way, it just do not care whether the inode table is, or is not zeroed. But when zeroing, we have to skip used inodes, obviously. Also we should prevent new inode allocations from the group, while zeroing is on the way. For that we take write alloc_sem lock in ext4_init_inode_table() and read alloc_sem in the ext4_claim_inode, so when we are unlucky and allocator hits the group which is currently being zeroed, it just has to wait. This can be suppresed using the mount option no_init_itable. Signed-off-by: Lukas Czerner <lczerner@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2010-10-28 09:30:05 +08:00
kfree(elr);
return ret;
}
/*
* We do not need to lock anything since this is called on
* module unload.
*/
static void ext4_destroy_lazyinit_thread(void)
{
/*
* If thread exited earlier
* there's nothing to be done.
*/
if (!ext4_li_info || !ext4_lazyinit_task)
ext4: add support for lazy inode table initialization When the lazy_itable_init extended option is passed to mke2fs, it considerably speeds up filesystem creation because inode tables are not zeroed out. The fact that parts of the inode table are uninitialized is not a problem so long as the block group descriptors, which contain information regarding how much of the inode table has been initialized, has not been corrupted However, if the block group checksums are not valid, e2fsck must scan the entire inode table, and the the old, uninitialized data could potentially cause e2fsck to report false problems. Hence, it is important for the inode tables to be initialized as soon as possble. This commit adds this feature so that mke2fs can safely use the lazy inode table initialization feature to speed up formatting file systems. This is done via a new new kernel thread called ext4lazyinit, which is created on demand and destroyed, when it is no longer needed. There is only one thread for all ext4 filesystems in the system. When the first filesystem with inititable mount option is mounted, ext4lazyinit thread is created, then the filesystem can register its request in the request list. This thread then walks through the list of requests picking up scheduled requests and invoking ext4_init_inode_table(). Next schedule time for the request is computed by multiplying the time it took to zero out last inode table with wait multiplier, which can be set with the (init_itable=n) mount option (default is 10). We are doing this so we do not take the whole I/O bandwidth. When the thread is no longer necessary (request list is empty) it frees the appropriate structures and exits (and can be created later later by another filesystem). We do not disturb regular inode allocations in any way, it just do not care whether the inode table is, or is not zeroed. But when zeroing, we have to skip used inodes, obviously. Also we should prevent new inode allocations from the group, while zeroing is on the way. For that we take write alloc_sem lock in ext4_init_inode_table() and read alloc_sem in the ext4_claim_inode, so when we are unlucky and allocator hits the group which is currently being zeroed, it just has to wait. This can be suppresed using the mount option no_init_itable. Signed-off-by: Lukas Czerner <lczerner@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2010-10-28 09:30:05 +08:00
return;
kthread_stop(ext4_lazyinit_task);
ext4: add support for lazy inode table initialization When the lazy_itable_init extended option is passed to mke2fs, it considerably speeds up filesystem creation because inode tables are not zeroed out. The fact that parts of the inode table are uninitialized is not a problem so long as the block group descriptors, which contain information regarding how much of the inode table has been initialized, has not been corrupted However, if the block group checksums are not valid, e2fsck must scan the entire inode table, and the the old, uninitialized data could potentially cause e2fsck to report false problems. Hence, it is important for the inode tables to be initialized as soon as possble. This commit adds this feature so that mke2fs can safely use the lazy inode table initialization feature to speed up formatting file systems. This is done via a new new kernel thread called ext4lazyinit, which is created on demand and destroyed, when it is no longer needed. There is only one thread for all ext4 filesystems in the system. When the first filesystem with inititable mount option is mounted, ext4lazyinit thread is created, then the filesystem can register its request in the request list. This thread then walks through the list of requests picking up scheduled requests and invoking ext4_init_inode_table(). Next schedule time for the request is computed by multiplying the time it took to zero out last inode table with wait multiplier, which can be set with the (init_itable=n) mount option (default is 10). We are doing this so we do not take the whole I/O bandwidth. When the thread is no longer necessary (request list is empty) it frees the appropriate structures and exits (and can be created later later by another filesystem). We do not disturb regular inode allocations in any way, it just do not care whether the inode table is, or is not zeroed. But when zeroing, we have to skip used inodes, obviously. Also we should prevent new inode allocations from the group, while zeroing is on the way. For that we take write alloc_sem lock in ext4_init_inode_table() and read alloc_sem in the ext4_claim_inode, so when we are unlucky and allocator hits the group which is currently being zeroed, it just has to wait. This can be suppresed using the mount option no_init_itable. Signed-off-by: Lukas Czerner <lczerner@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2010-10-28 09:30:05 +08:00
}
static int set_journal_csum_feature_set(struct super_block *sb)
{
int ret = 1;
int compat, incompat;
struct ext4_sb_info *sbi = EXT4_SB(sb);
if (ext4_has_metadata_csum(sb)) {
/* journal checksum v3 */
compat = 0;
incompat = JBD2_FEATURE_INCOMPAT_CSUM_V3;
} else {
/* journal checksum v1 */
compat = JBD2_FEATURE_COMPAT_CHECKSUM;
incompat = 0;
}
jbd2_journal_clear_features(sbi->s_journal,
JBD2_FEATURE_COMPAT_CHECKSUM, 0,
JBD2_FEATURE_INCOMPAT_CSUM_V3 |
JBD2_FEATURE_INCOMPAT_CSUM_V2);
if (test_opt(sb, JOURNAL_ASYNC_COMMIT)) {
ret = jbd2_journal_set_features(sbi->s_journal,
compat, 0,
JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT |
incompat);
} else if (test_opt(sb, JOURNAL_CHECKSUM)) {
ret = jbd2_journal_set_features(sbi->s_journal,
compat, 0,
incompat);
jbd2_journal_clear_features(sbi->s_journal, 0, 0,
JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT);
} else {
jbd2_journal_clear_features(sbi->s_journal, 0, 0,
JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT);
}
return ret;
}
/*
* Note: calculating the overhead so we can be compatible with
* historical BSD practice is quite difficult in the face of
* clusters/bigalloc. This is because multiple metadata blocks from
* different block group can end up in the same allocation cluster.
* Calculating the exact overhead in the face of clustered allocation
* requires either O(all block bitmaps) in memory or O(number of block
* groups**2) in time. We will still calculate the superblock for
* older file systems --- and if we come across with a bigalloc file
* system with zero in s_overhead_clusters the estimate will be close to
* correct especially for very large cluster sizes --- but for newer
* file systems, it's better to calculate this figure once at mkfs
* time, and store it in the superblock. If the superblock value is
* present (even for non-bigalloc file systems), we will use it.
*/
static int count_overhead(struct super_block *sb, ext4_group_t grp,
char *buf)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
struct ext4_group_desc *gdp;
ext4_fsblk_t first_block, last_block, b;
ext4_group_t i, ngroups = ext4_get_groups_count(sb);
int s, j, count = 0;
if (!ext4_has_feature_bigalloc(sb))
return (ext4_bg_has_super(sb, grp) + ext4_bg_num_gdb(sb, grp) +
sbi->s_itb_per_group + 2);
first_block = le32_to_cpu(sbi->s_es->s_first_data_block) +
(grp * EXT4_BLOCKS_PER_GROUP(sb));
last_block = first_block + EXT4_BLOCKS_PER_GROUP(sb) - 1;
for (i = 0; i < ngroups; i++) {
gdp = ext4_get_group_desc(sb, i, NULL);
b = ext4_block_bitmap(sb, gdp);
if (b >= first_block && b <= last_block) {
ext4_set_bit(EXT4_B2C(sbi, b - first_block), buf);
count++;
}
b = ext4_inode_bitmap(sb, gdp);
if (b >= first_block && b <= last_block) {
ext4_set_bit(EXT4_B2C(sbi, b - first_block), buf);
count++;
}
b = ext4_inode_table(sb, gdp);
if (b >= first_block && b + sbi->s_itb_per_group <= last_block)
for (j = 0; j < sbi->s_itb_per_group; j++, b++) {
int c = EXT4_B2C(sbi, b - first_block);
ext4_set_bit(c, buf);
count++;
}
if (i != grp)
continue;
s = 0;
if (ext4_bg_has_super(sb, grp)) {
ext4_set_bit(s++, buf);
count++;
}
j = ext4_bg_num_gdb(sb, grp);
if (s + j > EXT4_BLOCKS_PER_GROUP(sb)) {
ext4_error(sb, "Invalid number of block group "
"descriptor blocks: %d", j);
j = EXT4_BLOCKS_PER_GROUP(sb) - s;
}
count += j;
for (; j > 0; j--)
ext4_set_bit(EXT4_B2C(sbi, s++), buf);
}
if (!count)
return 0;
return EXT4_CLUSTERS_PER_GROUP(sb) -
ext4_count_free(buf, EXT4_CLUSTERS_PER_GROUP(sb) / 8);
}
/*
* Compute the overhead and stash it in sbi->s_overhead
*/
int ext4_calculate_overhead(struct super_block *sb)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
struct ext4_super_block *es = sbi->s_es;
struct inode *j_inode;
unsigned int j_blocks, j_inum = le32_to_cpu(es->s_journal_inum);
ext4_group_t i, ngroups = ext4_get_groups_count(sb);
ext4_fsblk_t overhead = 0;
char *buf = (char *) get_zeroed_page(GFP_NOFS);
if (!buf)
return -ENOMEM;
/*
* Compute the overhead (FS structures). This is constant
* for a given filesystem unless the number of block groups
* changes so we cache the previous value until it does.
*/
/*
* All of the blocks before first_data_block are overhead
*/
overhead = EXT4_B2C(sbi, le32_to_cpu(es->s_first_data_block));
/*
* Add the overhead found in each block group
*/
for (i = 0; i < ngroups; i++) {
int blks;
blks = count_overhead(sb, i, buf);
overhead += blks;
if (blks)
memset(buf, 0, PAGE_SIZE);
cond_resched();
}
/*
* Add the internal journal blocks whether the journal has been
* loaded or not
*/
if (sbi->s_journal && !sbi->journal_bdev)
overhead += EXT4_NUM_B2C(sbi, sbi->s_journal->j_maxlen);
else if (ext4_has_feature_journal(sb) && !sbi->s_journal) {
j_inode = ext4_get_journal_inode(sb, j_inum);
if (j_inode) {
j_blocks = j_inode->i_size >> sb->s_blocksize_bits;
overhead += EXT4_NUM_B2C(sbi, j_blocks);
iput(j_inode);
} else {
ext4_msg(sb, KERN_ERR, "can't get journal size");
}
}
sbi->s_overhead = overhead;
smp_wmb();
free_page((unsigned long) buf);
return 0;
}
static void ext4_set_resv_clusters(struct super_block *sb)
ext4: introduce reserved space Currently in ENOSPC condition when writing into unwritten space, or punching a hole, we might need to split the extent and grow extent tree. However since we can not allocate any new metadata blocks we'll have to zero out unwritten part of extent or punched out part of extent, or in the worst case return ENOSPC even though use actually does not allocate any space. Also in delalloc path we do reserve metadata and data blocks for the time we're going to write out, however metadata block reservation is very tricky especially since we expect that logical connectivity implies physical connectivity, however that might not be the case and hence we might end up allocating more metadata blocks than previously reserved. So in future, metadata reservation checks should be removed since we can not assure that we do not under reserve. And this is where reserved space comes into the picture. When mounting the file system we slice off a little bit of the file system space (2% or 4096 clusters, whichever is smaller) which can be then used for the cases mentioned above to prevent costly zeroout, or unexpected ENOSPC. The number of reserved clusters can be set via sysfs, however it can never be bigger than number of free clusters in the file system. Note that this patch fixes the failure of xfstest 274 as expected. Signed-off-by: Lukas Czerner <lczerner@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu> Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
2013-04-10 10:11:22 +08:00
{
ext4_fsblk_t resv_clusters;
struct ext4_sb_info *sbi = EXT4_SB(sb);
ext4: introduce reserved space Currently in ENOSPC condition when writing into unwritten space, or punching a hole, we might need to split the extent and grow extent tree. However since we can not allocate any new metadata blocks we'll have to zero out unwritten part of extent or punched out part of extent, or in the worst case return ENOSPC even though use actually does not allocate any space. Also in delalloc path we do reserve metadata and data blocks for the time we're going to write out, however metadata block reservation is very tricky especially since we expect that logical connectivity implies physical connectivity, however that might not be the case and hence we might end up allocating more metadata blocks than previously reserved. So in future, metadata reservation checks should be removed since we can not assure that we do not under reserve. And this is where reserved space comes into the picture. When mounting the file system we slice off a little bit of the file system space (2% or 4096 clusters, whichever is smaller) which can be then used for the cases mentioned above to prevent costly zeroout, or unexpected ENOSPC. The number of reserved clusters can be set via sysfs, however it can never be bigger than number of free clusters in the file system. Note that this patch fixes the failure of xfstest 274 as expected. Signed-off-by: Lukas Czerner <lczerner@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu> Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
2013-04-10 10:11:22 +08:00
/*
* There's no need to reserve anything when we aren't using extents.
* The space estimates are exact, there are no unwritten extents,
* hole punching doesn't need new metadata... This is needed especially
* to keep ext2/3 backward compatibility.
*/
if (!ext4_has_feature_extents(sb))
return;
ext4: introduce reserved space Currently in ENOSPC condition when writing into unwritten space, or punching a hole, we might need to split the extent and grow extent tree. However since we can not allocate any new metadata blocks we'll have to zero out unwritten part of extent or punched out part of extent, or in the worst case return ENOSPC even though use actually does not allocate any space. Also in delalloc path we do reserve metadata and data blocks for the time we're going to write out, however metadata block reservation is very tricky especially since we expect that logical connectivity implies physical connectivity, however that might not be the case and hence we might end up allocating more metadata blocks than previously reserved. So in future, metadata reservation checks should be removed since we can not assure that we do not under reserve. And this is where reserved space comes into the picture. When mounting the file system we slice off a little bit of the file system space (2% or 4096 clusters, whichever is smaller) which can be then used for the cases mentioned above to prevent costly zeroout, or unexpected ENOSPC. The number of reserved clusters can be set via sysfs, however it can never be bigger than number of free clusters in the file system. Note that this patch fixes the failure of xfstest 274 as expected. Signed-off-by: Lukas Czerner <lczerner@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu> Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
2013-04-10 10:11:22 +08:00
/*
* By default we reserve 2% or 4096 clusters, whichever is smaller.
* This should cover the situations where we can not afford to run
* out of space like for example punch hole, or converting
* unwritten extents in delalloc path. In most cases such
ext4: introduce reserved space Currently in ENOSPC condition when writing into unwritten space, or punching a hole, we might need to split the extent and grow extent tree. However since we can not allocate any new metadata blocks we'll have to zero out unwritten part of extent or punched out part of extent, or in the worst case return ENOSPC even though use actually does not allocate any space. Also in delalloc path we do reserve metadata and data blocks for the time we're going to write out, however metadata block reservation is very tricky especially since we expect that logical connectivity implies physical connectivity, however that might not be the case and hence we might end up allocating more metadata blocks than previously reserved. So in future, metadata reservation checks should be removed since we can not assure that we do not under reserve. And this is where reserved space comes into the picture. When mounting the file system we slice off a little bit of the file system space (2% or 4096 clusters, whichever is smaller) which can be then used for the cases mentioned above to prevent costly zeroout, or unexpected ENOSPC. The number of reserved clusters can be set via sysfs, however it can never be bigger than number of free clusters in the file system. Note that this patch fixes the failure of xfstest 274 as expected. Signed-off-by: Lukas Czerner <lczerner@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu> Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
2013-04-10 10:11:22 +08:00
* allocation would require 1, or 2 blocks, higher numbers are
* very rare.
*/
resv_clusters = (ext4_blocks_count(sbi->s_es) >>
sbi->s_cluster_bits);
ext4: introduce reserved space Currently in ENOSPC condition when writing into unwritten space, or punching a hole, we might need to split the extent and grow extent tree. However since we can not allocate any new metadata blocks we'll have to zero out unwritten part of extent or punched out part of extent, or in the worst case return ENOSPC even though use actually does not allocate any space. Also in delalloc path we do reserve metadata and data blocks for the time we're going to write out, however metadata block reservation is very tricky especially since we expect that logical connectivity implies physical connectivity, however that might not be the case and hence we might end up allocating more metadata blocks than previously reserved. So in future, metadata reservation checks should be removed since we can not assure that we do not under reserve. And this is where reserved space comes into the picture. When mounting the file system we slice off a little bit of the file system space (2% or 4096 clusters, whichever is smaller) which can be then used for the cases mentioned above to prevent costly zeroout, or unexpected ENOSPC. The number of reserved clusters can be set via sysfs, however it can never be bigger than number of free clusters in the file system. Note that this patch fixes the failure of xfstest 274 as expected. Signed-off-by: Lukas Czerner <lczerner@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu> Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
2013-04-10 10:11:22 +08:00
do_div(resv_clusters, 50);
resv_clusters = min_t(ext4_fsblk_t, resv_clusters, 4096);
atomic64_set(&sbi->s_resv_clusters, resv_clusters);
ext4: introduce reserved space Currently in ENOSPC condition when writing into unwritten space, or punching a hole, we might need to split the extent and grow extent tree. However since we can not allocate any new metadata blocks we'll have to zero out unwritten part of extent or punched out part of extent, or in the worst case return ENOSPC even though use actually does not allocate any space. Also in delalloc path we do reserve metadata and data blocks for the time we're going to write out, however metadata block reservation is very tricky especially since we expect that logical connectivity implies physical connectivity, however that might not be the case and hence we might end up allocating more metadata blocks than previously reserved. So in future, metadata reservation checks should be removed since we can not assure that we do not under reserve. And this is where reserved space comes into the picture. When mounting the file system we slice off a little bit of the file system space (2% or 4096 clusters, whichever is smaller) which can be then used for the cases mentioned above to prevent costly zeroout, or unexpected ENOSPC. The number of reserved clusters can be set via sysfs, however it can never be bigger than number of free clusters in the file system. Note that this patch fixes the failure of xfstest 274 as expected. Signed-off-by: Lukas Czerner <lczerner@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu> Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
2013-04-10 10:11:22 +08:00
}
static int ext4_fill_super(struct super_block *sb, void *data, int silent)
{
char *orig_data = kstrdup(data, GFP_KERNEL);
struct buffer_head *bh;
struct ext4_super_block *es = NULL;
struct ext4_sb_info *sbi = kzalloc(sizeof(*sbi), GFP_KERNEL);
ext4_fsblk_t block;
ext4_fsblk_t sb_block = get_sb_block(&data);
ext4_fsblk_t logical_sb_block;
unsigned long offset = 0;
unsigned long journal_devnum = 0;
unsigned long def_mount_opts;
struct inode *root;
const char *descr;
int ret = -ENOMEM;
int blocksize, clustersize;
unsigned int db_count;
unsigned int i;
int needs_recovery, has_huge_files, has_bigalloc;
__u64 blocks_count;
int err = 0;
unsigned int journal_ioprio = DEFAULT_JOURNAL_IOPRIO;
ext4: add support for lazy inode table initialization When the lazy_itable_init extended option is passed to mke2fs, it considerably speeds up filesystem creation because inode tables are not zeroed out. The fact that parts of the inode table are uninitialized is not a problem so long as the block group descriptors, which contain information regarding how much of the inode table has been initialized, has not been corrupted However, if the block group checksums are not valid, e2fsck must scan the entire inode table, and the the old, uninitialized data could potentially cause e2fsck to report false problems. Hence, it is important for the inode tables to be initialized as soon as possble. This commit adds this feature so that mke2fs can safely use the lazy inode table initialization feature to speed up formatting file systems. This is done via a new new kernel thread called ext4lazyinit, which is created on demand and destroyed, when it is no longer needed. There is only one thread for all ext4 filesystems in the system. When the first filesystem with inititable mount option is mounted, ext4lazyinit thread is created, then the filesystem can register its request in the request list. This thread then walks through the list of requests picking up scheduled requests and invoking ext4_init_inode_table(). Next schedule time for the request is computed by multiplying the time it took to zero out last inode table with wait multiplier, which can be set with the (init_itable=n) mount option (default is 10). We are doing this so we do not take the whole I/O bandwidth. When the thread is no longer necessary (request list is empty) it frees the appropriate structures and exits (and can be created later later by another filesystem). We do not disturb regular inode allocations in any way, it just do not care whether the inode table is, or is not zeroed. But when zeroing, we have to skip used inodes, obviously. Also we should prevent new inode allocations from the group, while zeroing is on the way. For that we take write alloc_sem lock in ext4_init_inode_table() and read alloc_sem in the ext4_claim_inode, so when we are unlucky and allocator hits the group which is currently being zeroed, it just has to wait. This can be suppresed using the mount option no_init_itable. Signed-off-by: Lukas Czerner <lczerner@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2010-10-28 09:30:05 +08:00
ext4_group_t first_not_zeroed;
if ((data && !orig_data) || !sbi)
goto out_free_base;
sbi->s_blockgroup_lock =
kzalloc(sizeof(struct blockgroup_lock), GFP_KERNEL);
if (!sbi->s_blockgroup_lock)
goto out_free_base;
sb->s_fs_info = sbi;
sbi->s_sb = sb;
sbi->s_inode_readahead_blks = EXT4_DEF_INODE_READAHEAD_BLKS;
sbi->s_sb_block = sb_block;
if (sb->s_bdev->bd_part)
sbi->s_sectors_written_start =
part_stat_read(sb->s_bdev->bd_part, sectors[1]);
/* Cleanup superblock name */
strreplace(sb->s_id, '/', '!');
/* -EINVAL is default */
ret = -EINVAL;
blocksize = sb_min_blocksize(sb, EXT4_MIN_BLOCK_SIZE);
if (!blocksize) {
ext4_msg(sb, KERN_ERR, "unable to set blocksize");
goto out_fail;
}
/*
* The ext4 superblock will not be buffer aligned for other than 1kB
* block sizes. We need to calculate the offset from buffer start.
*/
if (blocksize != EXT4_MIN_BLOCK_SIZE) {
logical_sb_block = sb_block * EXT4_MIN_BLOCK_SIZE;
offset = do_div(logical_sb_block, blocksize);
} else {
logical_sb_block = sb_block;
}
if (!(bh = sb_bread_unmovable(sb, logical_sb_block))) {
ext4_msg(sb, KERN_ERR, "unable to read superblock");
goto out_fail;
}
/*
* Note: s_es must be initialized as soon as possible because
* some ext4 macro-instructions depend on its value
*/
es = (struct ext4_super_block *) (bh->b_data + offset);
sbi->s_es = es;
sb->s_magic = le16_to_cpu(es->s_magic);
if (sb->s_magic != EXT4_SUPER_MAGIC)
goto cantfind_ext4;
sbi->s_kbytes_written = le64_to_cpu(es->s_kbytes_written);
/* Warn if metadata_csum and gdt_csum are both set. */
if (ext4_has_feature_metadata_csum(sb) &&
ext4_has_feature_gdt_csum(sb))
ext4_warning(sb, "metadata_csum and uninit_bg are "
"redundant flags; please run fsck.");
/* Check for a known checksum algorithm */
if (!ext4_verify_csum_type(sb, es)) {
ext4_msg(sb, KERN_ERR, "VFS: Found ext4 filesystem with "
"unknown checksum algorithm.");
silent = 1;
goto cantfind_ext4;
}
/* Load the checksum driver */
if (ext4_has_feature_metadata_csum(sb)) {
sbi->s_chksum_driver = crypto_alloc_shash("crc32c", 0, 0);
if (IS_ERR(sbi->s_chksum_driver)) {
ext4_msg(sb, KERN_ERR, "Cannot load crc32c driver.");
ret = PTR_ERR(sbi->s_chksum_driver);
sbi->s_chksum_driver = NULL;
goto failed_mount;
}
}
/* Check superblock checksum */
if (!ext4_superblock_csum_verify(sb, es)) {
ext4_msg(sb, KERN_ERR, "VFS: Found ext4 filesystem with "
"invalid superblock checksum. Run e2fsck?");
silent = 1;
ret = -EFSBADCRC;
goto cantfind_ext4;
}
/* Precompute checksum seed for all metadata */
if (ext4_has_feature_csum_seed(sb))
sbi->s_csum_seed = le32_to_cpu(es->s_checksum_seed);
else if (ext4_has_metadata_csum(sb))
sbi->s_csum_seed = ext4_chksum(sbi, ~0, es->s_uuid,
sizeof(es->s_uuid));
/* Set defaults before we parse the mount options */
def_mount_opts = le32_to_cpu(es->s_default_mount_opts);
set_opt(sb, INIT_INODE_TABLE);
if (def_mount_opts & EXT4_DEFM_DEBUG)
set_opt(sb, DEBUG);
if (def_mount_opts & EXT4_DEFM_BSDGROUPS)
set_opt(sb, GRPID);
if (def_mount_opts & EXT4_DEFM_UID16)
set_opt(sb, NO_UID32);
/* xattr user namespace & acls are now defaulted on */
set_opt(sb, XATTR_USER);
#ifdef CONFIG_EXT4_FS_POSIX_ACL
set_opt(sb, POSIX_ACL);
#endif
/* don't forget to enable journal_csum when metadata_csum is enabled. */
if (ext4_has_metadata_csum(sb))
set_opt(sb, JOURNAL_CHECKSUM);
if ((def_mount_opts & EXT4_DEFM_JMODE) == EXT4_DEFM_JMODE_DATA)
set_opt(sb, JOURNAL_DATA);
else if ((def_mount_opts & EXT4_DEFM_JMODE) == EXT4_DEFM_JMODE_ORDERED)
set_opt(sb, ORDERED_DATA);
else if ((def_mount_opts & EXT4_DEFM_JMODE) == EXT4_DEFM_JMODE_WBACK)
set_opt(sb, WRITEBACK_DATA);
if (le16_to_cpu(sbi->s_es->s_errors) == EXT4_ERRORS_PANIC)
set_opt(sb, ERRORS_PANIC);
else if (le16_to_cpu(sbi->s_es->s_errors) == EXT4_ERRORS_CONTINUE)
set_opt(sb, ERRORS_CONT);
else
set_opt(sb, ERRORS_RO);
/* block_validity enabled by default; disable with noblock_validity */
set_opt(sb, BLOCK_VALIDITY);
if (def_mount_opts & EXT4_DEFM_DISCARD)
set_opt(sb, DISCARD);
sbi->s_resuid = make_kuid(&init_user_ns, le16_to_cpu(es->s_def_resuid));
sbi->s_resgid = make_kgid(&init_user_ns, le16_to_cpu(es->s_def_resgid));
sbi->s_commit_interval = JBD2_DEFAULT_MAX_COMMIT_AGE * HZ;
sbi->s_min_batch_time = EXT4_DEF_MIN_BATCH_TIME;
sbi->s_max_batch_time = EXT4_DEF_MAX_BATCH_TIME;
if ((def_mount_opts & EXT4_DEFM_NOBARRIER) == 0)
set_opt(sb, BARRIER);
/*
* enable delayed allocation by default
* Use -o nodelalloc to turn it off
*/
if (!IS_EXT3_SB(sb) && !IS_EXT2_SB(sb) &&
((def_mount_opts & EXT4_DEFM_NODELALLOC) == 0))
set_opt(sb, DELALLOC);
/*
* set default s_li_wait_mult for lazyinit, for the case there is
* no mount option specified.
*/
sbi->s_li_wait_mult = EXT4_DEF_LI_WAIT_MULT;
if (sbi->s_es->s_mount_opts[0]) {
char *s_mount_opts = kstrndup(sbi->s_es->s_mount_opts,
sizeof(sbi->s_es->s_mount_opts),
GFP_KERNEL);
if (!s_mount_opts)
goto failed_mount;
if (!parse_options(s_mount_opts, sb, &journal_devnum,
&journal_ioprio, 0)) {
ext4_msg(sb, KERN_WARNING,
"failed to parse options in superblock: %s",
s_mount_opts);
}
kfree(s_mount_opts);
}
sbi->s_def_mount_opt = sbi->s_mount_opt;
if (!parse_options((char *) data, sb, &journal_devnum,
&journal_ioprio, 0))
goto failed_mount;
if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) {
printk_once(KERN_WARNING "EXT4-fs: Warning: mounting "
"with data=journal disables delayed "
"allocation and O_DIRECT support!\n");
if (test_opt2(sb, EXPLICIT_DELALLOC)) {
ext4_msg(sb, KERN_ERR, "can't mount with "
"both data=journal and delalloc");
goto failed_mount;
}
if (test_opt(sb, DIOREAD_NOLOCK)) {
ext4_msg(sb, KERN_ERR, "can't mount with "
"both data=journal and dioread_nolock");
goto failed_mount;
}
if (test_opt(sb, DAX)) {
ext4_msg(sb, KERN_ERR, "can't mount with "
"both data=journal and dax");
goto failed_mount;
}
ext4: do not perform data journaling when data is encrypted Currently data journalling is incompatible with encryption: enabling both at the same time has never been supported by design, and would result in unpredictable behavior. However, users are not precluded from turning on both features simultaneously. This change programmatically replaces data journaling for encrypted regular files with ordered data journaling mode. Background: Journaling encrypted data has not been supported because it operates on buffer heads of the page in the page cache. Namely, when the commit happens, which could be up to five seconds after caching, the commit thread uses the buffer heads attached to the page to copy the contents of the page to the journal. With encryption, it would have been required to keep the bounce buffer with ciphertext for up to the aforementioned five seconds, since the page cache can only hold plaintext and could not be used for journaling. Alternatively, it would be required to setup the journal to initiate a callback at the commit time to perform deferred encryption - in this case, not only would the data have to be written twice, but it would also have to be encrypted twice. This level of complexity was not justified for a mode that in practice is very rarely used because of the overhead from the data journalling. Solution: If data=journaled has been set as a mount option for a filesystem, or if journaling is enabled on a regular file, do not perform journaling if the file is also encrypted, instead fall back to the data=ordered mode for the file. Rationale: The intent is to allow seamless and proper filesystem operation when journaling and encryption have both been enabled, and have these two conflicting features gracefully resolved by the filesystem. Fixes: 4461471107b7 Signed-off-by: Sergey Karamov <skaramov@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Cc: stable@vger.kernel.org
2016-12-11 06:54:58 +08:00
if (ext4_has_feature_encrypt(sb)) {
ext4_msg(sb, KERN_WARNING,
"encrypted files will use data=ordered "
"instead of data journaling mode");
}
if (test_opt(sb, DELALLOC))
clear_opt(sb, DELALLOC);
} else {
sb->s_iflags |= SB_I_CGROUPWB;
}
sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
(test_opt(sb, POSIX_ACL) ? MS_POSIXACL : 0);
if (le32_to_cpu(es->s_rev_level) == EXT4_GOOD_OLD_REV &&
(ext4_has_compat_features(sb) ||
ext4_has_ro_compat_features(sb) ||
ext4_has_incompat_features(sb)))
ext4_msg(sb, KERN_WARNING,
"feature flags set on rev 0 fs, "
"running e2fsck is recommended");
if (es->s_creator_os == cpu_to_le32(EXT4_OS_HURD)) {
set_opt2(sb, HURD_COMPAT);
if (ext4_has_feature_64bit(sb)) {
ext4_msg(sb, KERN_ERR,
"The Hurd can't support 64-bit file systems");
goto failed_mount;
}
}
if (IS_EXT2_SB(sb)) {
if (ext2_feature_set_ok(sb))
ext4_msg(sb, KERN_INFO, "mounting ext2 file system "
"using the ext4 subsystem");
else {
ext4_msg(sb, KERN_ERR, "couldn't mount as ext2 due "
"to feature incompatibilities");
goto failed_mount;
}
}
if (IS_EXT3_SB(sb)) {
if (ext3_feature_set_ok(sb))
ext4_msg(sb, KERN_INFO, "mounting ext3 file system "
"using the ext4 subsystem");
else {
ext4_msg(sb, KERN_ERR, "couldn't mount as ext3 due "
"to feature incompatibilities");
goto failed_mount;
}
}
/*
* Check feature flags regardless of the revision level, since we
* previously didn't change the revision level when setting the flags,
* so there is a chance incompat flags are set on a rev 0 filesystem.
*/
if (!ext4_feature_set_ok(sb, (sb->s_flags & MS_RDONLY)))
goto failed_mount;
blocksize = BLOCK_SIZE << le32_to_cpu(es->s_log_block_size);
if (blocksize < EXT4_MIN_BLOCK_SIZE ||
blocksize > EXT4_MAX_BLOCK_SIZE) {
ext4_msg(sb, KERN_ERR,
"Unsupported filesystem blocksize %d (%d log_block_size)",
blocksize, le32_to_cpu(es->s_log_block_size));
goto failed_mount;
}
if (le32_to_cpu(es->s_log_block_size) >
(EXT4_MAX_BLOCK_LOG_SIZE - EXT4_MIN_BLOCK_LOG_SIZE)) {
ext4_msg(sb, KERN_ERR,
"Invalid log block size: %u",
le32_to_cpu(es->s_log_block_size));
goto failed_mount;
}
if (le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks) > (blocksize / 4)) {
ext4_msg(sb, KERN_ERR,
"Number of reserved GDT blocks insanely large: %d",
le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks));
goto failed_mount;
}
if (sbi->s_mount_opt & EXT4_MOUNT_DAX) {
err = bdev_dax_supported(sb, blocksize);
if (err)
goto failed_mount;
}
if (ext4_has_feature_encrypt(sb) && es->s_encryption_level) {
ext4_msg(sb, KERN_ERR, "Unsupported encryption level %d",
es->s_encryption_level);
goto failed_mount;
}
if (sb->s_blocksize != blocksize) {
/* Validate the filesystem blocksize */
if (!sb_set_blocksize(sb, blocksize)) {
ext4_msg(sb, KERN_ERR, "bad block size %d",
blocksize);
goto failed_mount;
}
brelse(bh);
logical_sb_block = sb_block * EXT4_MIN_BLOCK_SIZE;
offset = do_div(logical_sb_block, blocksize);
bh = sb_bread_unmovable(sb, logical_sb_block);
if (!bh) {
ext4_msg(sb, KERN_ERR,
"Can't read superblock on 2nd try");
goto failed_mount;
}
es = (struct ext4_super_block *)(bh->b_data + offset);
sbi->s_es = es;
if (es->s_magic != cpu_to_le16(EXT4_SUPER_MAGIC)) {
ext4_msg(sb, KERN_ERR,
"Magic mismatch, very weird!");
goto failed_mount;
}
}
has_huge_files = ext4_has_feature_huge_file(sb);
sbi->s_bitmap_maxbytes = ext4_max_bitmap_size(sb->s_blocksize_bits,
has_huge_files);
sb->s_maxbytes = ext4_max_size(sb->s_blocksize_bits, has_huge_files);
if (le32_to_cpu(es->s_rev_level) == EXT4_GOOD_OLD_REV) {
sbi->s_inode_size = EXT4_GOOD_OLD_INODE_SIZE;
sbi->s_first_ino = EXT4_GOOD_OLD_FIRST_INO;
} else {
sbi->s_inode_size = le16_to_cpu(es->s_inode_size);
sbi->s_first_ino = le32_to_cpu(es->s_first_ino);
if ((sbi->s_inode_size < EXT4_GOOD_OLD_INODE_SIZE) ||
(!is_power_of_2(sbi->s_inode_size)) ||
(sbi->s_inode_size > blocksize)) {
ext4_msg(sb, KERN_ERR,
"unsupported inode size: %d",
sbi->s_inode_size);
goto failed_mount;
}
if (sbi->s_inode_size > EXT4_GOOD_OLD_INODE_SIZE)
sb->s_time_gran = 1 << (EXT4_EPOCH_BITS - 2);
}
sbi->s_desc_size = le16_to_cpu(es->s_desc_size);
if (ext4_has_feature_64bit(sb)) {
if (sbi->s_desc_size < EXT4_MIN_DESC_SIZE_64BIT ||
sbi->s_desc_size > EXT4_MAX_DESC_SIZE ||
!is_power_of_2(sbi->s_desc_size)) {
ext4_msg(sb, KERN_ERR,
"unsupported descriptor size %lu",
sbi->s_desc_size);
goto failed_mount;
}
} else
sbi->s_desc_size = EXT4_MIN_DESC_SIZE;
sbi->s_blocks_per_group = le32_to_cpu(es->s_blocks_per_group);
sbi->s_inodes_per_group = le32_to_cpu(es->s_inodes_per_group);
sbi->s_inodes_per_block = blocksize / EXT4_INODE_SIZE(sb);
if (sbi->s_inodes_per_block == 0)
goto cantfind_ext4;
if (sbi->s_inodes_per_group < sbi->s_inodes_per_block ||
sbi->s_inodes_per_group > blocksize * 8) {
ext4_msg(sb, KERN_ERR, "invalid inodes per group: %lu\n",
sbi->s_blocks_per_group);
goto failed_mount;
}
sbi->s_itb_per_group = sbi->s_inodes_per_group /
sbi->s_inodes_per_block;
sbi->s_desc_per_block = blocksize / EXT4_DESC_SIZE(sb);
sbi->s_sbh = bh;
sbi->s_mount_state = le16_to_cpu(es->s_state);
sbi->s_addr_per_block_bits = ilog2(EXT4_ADDR_PER_BLOCK(sb));
sbi->s_desc_per_block_bits = ilog2(EXT4_DESC_PER_BLOCK(sb));
for (i = 0; i < 4; i++)
sbi->s_hash_seed[i] = le32_to_cpu(es->s_hash_seed[i]);
sbi->s_def_hash_version = es->s_def_hash_version;
if (ext4_has_feature_dir_index(sb)) {
i = le32_to_cpu(es->s_flags);
if (i & EXT2_FLAGS_UNSIGNED_HASH)
sbi->s_hash_unsigned = 3;
else if ((i & EXT2_FLAGS_SIGNED_HASH) == 0) {
#ifdef __CHAR_UNSIGNED__
if (!(sb->s_flags & MS_RDONLY))
es->s_flags |=
cpu_to_le32(EXT2_FLAGS_UNSIGNED_HASH);
sbi->s_hash_unsigned = 3;
#else
if (!(sb->s_flags & MS_RDONLY))
es->s_flags |=
cpu_to_le32(EXT2_FLAGS_SIGNED_HASH);
#endif
}
}
/* Handle clustersize */
clustersize = BLOCK_SIZE << le32_to_cpu(es->s_log_cluster_size);
has_bigalloc = ext4_has_feature_bigalloc(sb);
if (has_bigalloc) {
if (clustersize < blocksize) {
ext4_msg(sb, KERN_ERR,
"cluster size (%d) smaller than "
"block size (%d)", clustersize, blocksize);
goto failed_mount;
}
if (le32_to_cpu(es->s_log_cluster_size) >
(EXT4_MAX_CLUSTER_LOG_SIZE - EXT4_MIN_BLOCK_LOG_SIZE)) {
ext4_msg(sb, KERN_ERR,
"Invalid log cluster size: %u",
le32_to_cpu(es->s_log_cluster_size));
goto failed_mount;
}
sbi->s_cluster_bits = le32_to_cpu(es->s_log_cluster_size) -
le32_to_cpu(es->s_log_block_size);
sbi->s_clusters_per_group =
le32_to_cpu(es->s_clusters_per_group);
if (sbi->s_clusters_per_group > blocksize * 8) {
ext4_msg(sb, KERN_ERR,
"#clusters per group too big: %lu",
sbi->s_clusters_per_group);
goto failed_mount;
}
if (sbi->s_blocks_per_group !=
(sbi->s_clusters_per_group * (clustersize / blocksize))) {
ext4_msg(sb, KERN_ERR, "blocks per group (%lu) and "
"clusters per group (%lu) inconsistent",
sbi->s_blocks_per_group,
sbi->s_clusters_per_group);
goto failed_mount;
}
} else {
if (clustersize != blocksize) {
ext4_warning(sb, "fragment/cluster size (%d) != "
"block size (%d)", clustersize,
blocksize);
clustersize = blocksize;
}
if (sbi->s_blocks_per_group > blocksize * 8) {
ext4_msg(sb, KERN_ERR,
"#blocks per group too big: %lu",
sbi->s_blocks_per_group);
goto failed_mount;
}
sbi->s_clusters_per_group = sbi->s_blocks_per_group;
sbi->s_cluster_bits = 0;
}
sbi->s_cluster_ratio = clustersize / blocksize;
ext4: fix ext4_get_group_number() The function ext4_get_group_number() was introduced as an optimization in commit bd86298e60b8. Unfortunately, this commit incorrectly calculate the group number for file systems with a 1k block size (when s_first_data_block is 1 instead of zero). This could cause the following kernel BUG: [ 568.877799] ------------[ cut here ]------------ [ 568.877833] kernel BUG at fs/ext4/mballoc.c:3728! [ 568.877840] Oops: Exception in kernel mode, sig: 5 [#1] [ 568.877845] SMP NR_CPUS=32 NUMA pSeries [ 568.877852] Modules linked in: binfmt_misc [ 568.877861] CPU: 1 PID: 3516 Comm: fs_mark Not tainted 3.10.0-03216-g7c6809f-dirty #1 [ 568.877867] task: c0000001fb0b8000 ti: c0000001fa954000 task.ti: c0000001fa954000 [ 568.877873] NIP: c0000000002f42a4 LR: c0000000002f4274 CTR: c000000000317ef8 [ 568.877879] REGS: c0000001fa956ed0 TRAP: 0700 Not tainted (3.10.0-03216-g7c6809f-dirty) [ 568.877884] MSR: 8000000000029032 <SF,EE,ME,IR,DR,RI> CR: 24000428 XER: 00000000 [ 568.877902] SOFTE: 1 [ 568.877905] CFAR: c0000000002b5464 [ 568.877908] GPR00: 0000000000000001 c0000001fa957150 c000000000c6a408 c0000001fb588000 GPR04: 0000000000003fff c0000001fa9571c0 c0000001fa9571c4 000138098c50625f GPR08: 1301200000000000 0000000000000002 0000000000000001 0000000000000000 GPR12: 0000000024000422 c00000000f33a300 0000000000008000 c0000001fa9577f0 GPR16: c0000001fb7d0100 c000000000c29190 c0000000007f46e8 c000000000a14672 GPR20: 0000000000000001 0000000000000008 ffffffffffffffff 0000000000000000 GPR24: 0000000000000100 c0000001fa957278 c0000001fdb2bc78 c0000001fa957288 GPR28: 0000000000100100 c0000001fa957288 c0000001fb588000 c0000001fdb2bd10 [ 568.877993] NIP [c0000000002f42a4] .ext4_mb_release_group_pa+0xec/0x1c0 [ 568.877999] LR [c0000000002f4274] .ext4_mb_release_group_pa+0xbc/0x1c0 [ 568.878004] Call Trace: [ 568.878008] [c0000001fa957150] [c0000000002f4274] .ext4_mb_release_group_pa+0xbc/0x1c0 (unreliable) [ 568.878017] [c0000001fa957200] [c0000000002fb070] .ext4_mb_discard_lg_preallocations+0x394/0x444 [ 568.878025] [c0000001fa957340] [c0000000002fb45c] .ext4_mb_release_context+0x33c/0x734 [ 568.878032] [c0000001fa957440] [c0000000002fbcf8] .ext4_mb_new_blocks+0x4a4/0x5f4 [ 568.878039] [c0000001fa957510] [c0000000002ef56c] .ext4_ext_map_blocks+0xc28/0x1178 [ 568.878047] [c0000001fa957640] [c0000000002c1a94] .ext4_map_blocks+0x2c8/0x490 [ 568.878054] [c0000001fa957730] [c0000000002c536c] .ext4_writepages+0x738/0xc60 [ 568.878062] [c0000001fa957950] [c000000000168a78] .do_writepages+0x5c/0x80 [ 568.878069] [c0000001fa9579d0] [c00000000015d1c4] .__filemap_fdatawrite_range+0x88/0xb0 [ 568.878078] [c0000001fa957aa0] [c00000000015d23c] .filemap_write_and_wait_range+0x50/0xfc [ 568.878085] [c0000001fa957b30] [c0000000002b8edc] .ext4_sync_file+0x220/0x3c4 [ 568.878092] [c0000001fa957be0] [c0000000001f849c] .vfs_fsync_range+0x64/0x80 [ 568.878098] [c0000001fa957c70] [c0000000001f84f0] .vfs_fsync+0x38/0x4c [ 568.878105] [c0000001fa957d00] [c0000000001f87f4] .do_fsync+0x54/0x90 [ 568.878111] [c0000001fa957db0] [c0000000001f8894] .SyS_fsync+0x28/0x3c [ 568.878120] [c0000001fa957e30] [c000000000009c88] syscall_exit+0x0/0x7c [ 568.878125] Instruction dump: [ 568.878130] 60000000 813d0034 81610070 38000000 7f8b4800 419e001c 813f007c 7d2bfe70 [ 568.878144] 7d604a78 7c005850 54000ffe 7c0007b4 <0b000000> e8a10076 e87f0090 7fa4eb78 [ 568.878160] ---[ end trace 594d911d9654770b ]--- In addition fix the STD_GROUP optimization so that it works for bigalloc file systems as well. Signed-off-by: "Theodore Ts'o" <tytso@mit.edu> Reported-by: Li Zhong <lizhongfs@gmail.com> Reviewed-by: Lukas Czerner <lczerner@redhat.com> Cc: stable@vger.kernel.org # 3.10
2013-07-06 11:11:16 +08:00
/* Do we have standard group size of clustersize * 8 blocks ? */
if (sbi->s_blocks_per_group == clustersize << 3)
set_opt2(sb, STD_GROUP_SIZE);
/*
* Test whether we have more sectors than will fit in sector_t,
* and whether the max offset is addressable by the page cache.
*/
err = generic_check_addressable(sb->s_blocksize_bits,
ext4_blocks_count(es));
if (err) {
ext4_msg(sb, KERN_ERR, "filesystem"
" too large to mount safely on this system");
if (sizeof(sector_t) < 8)
ext4_msg(sb, KERN_WARNING, "CONFIG_LBDAF not enabled");
goto failed_mount;
}
if (EXT4_BLOCKS_PER_GROUP(sb) == 0)
goto cantfind_ext4;
ext4: fix oops on corrupted ext4 mount When mounting an ext4 filesystem with corrupted s_first_data_block, things can go very wrong and oops. Because blocks_count in ext4_fill_super is a u64, and we must use do_div, the calculation of db_count is done differently than on ext4. If first_data_block is corrupted such that it is larger than ext4_blocks_count, for example, then the intermediate blocks_count value may go negative, but sign-extend to a very large value: blocks_count = (ext4_blocks_count(es) - le32_to_cpu(es->s_first_data_block) + EXT4_BLOCKS_PER_GROUP(sb) - 1); This is then assigned to s_groups_count which is an unsigned long: sbi->s_groups_count = blocks_count; This may result in a value of 0xFFFFFFFF which is then used to compute db_count: db_count = (sbi->s_groups_count + EXT4_DESC_PER_BLOCK(sb) - 1) / EXT4_DESC_PER_BLOCK(sb); and in this case db_count will wind up as 0 because the addition overflows 32 bits. This in turn causes the kmalloc for group_desc to be of 0 size: sbi->s_group_desc = kmalloc(db_count * sizeof (struct buffer_head *), GFP_KERNEL); and eventually in ext4_check_descriptors, dereferencing sbi->s_group_desc[desc_block] will result in a NULL pointer dereference. The simplest test seems to be to sanity check s_first_data_block, EXT4_BLOCKS_PER_GROUP, and ext4_blocks_count values to be sure their combination won't result in a bad intermediate value for blocks_count. We could just check for db_count == 0, but catching it at the root cause seems like it provides more info. Signed-off-by: Eric Sandeen <sandeen@redhat.com> Reviewed-by: Mingming Cao <cmm@us.ibm.com>
2008-01-29 12:58:27 +08:00
/* check blocks count against device size */
blocks_count = sb->s_bdev->bd_inode->i_size >> sb->s_blocksize_bits;
if (blocks_count && ext4_blocks_count(es) > blocks_count) {
ext4_msg(sb, KERN_WARNING, "bad geometry: block count %llu "
"exceeds size of device (%llu blocks)",
ext4_blocks_count(es), blocks_count);
goto failed_mount;
}
/*
* It makes no sense for the first data block to be beyond the end
* of the filesystem.
*/
if (le32_to_cpu(es->s_first_data_block) >= ext4_blocks_count(es)) {
ext4_msg(sb, KERN_WARNING, "bad geometry: first data "
"block %u is beyond end of filesystem (%llu)",
le32_to_cpu(es->s_first_data_block),
ext4_blocks_count(es));
ext4: fix oops on corrupted ext4 mount When mounting an ext4 filesystem with corrupted s_first_data_block, things can go very wrong and oops. Because blocks_count in ext4_fill_super is a u64, and we must use do_div, the calculation of db_count is done differently than on ext4. If first_data_block is corrupted such that it is larger than ext4_blocks_count, for example, then the intermediate blocks_count value may go negative, but sign-extend to a very large value: blocks_count = (ext4_blocks_count(es) - le32_to_cpu(es->s_first_data_block) + EXT4_BLOCKS_PER_GROUP(sb) - 1); This is then assigned to s_groups_count which is an unsigned long: sbi->s_groups_count = blocks_count; This may result in a value of 0xFFFFFFFF which is then used to compute db_count: db_count = (sbi->s_groups_count + EXT4_DESC_PER_BLOCK(sb) - 1) / EXT4_DESC_PER_BLOCK(sb); and in this case db_count will wind up as 0 because the addition overflows 32 bits. This in turn causes the kmalloc for group_desc to be of 0 size: sbi->s_group_desc = kmalloc(db_count * sizeof (struct buffer_head *), GFP_KERNEL); and eventually in ext4_check_descriptors, dereferencing sbi->s_group_desc[desc_block] will result in a NULL pointer dereference. The simplest test seems to be to sanity check s_first_data_block, EXT4_BLOCKS_PER_GROUP, and ext4_blocks_count values to be sure their combination won't result in a bad intermediate value for blocks_count. We could just check for db_count == 0, but catching it at the root cause seems like it provides more info. Signed-off-by: Eric Sandeen <sandeen@redhat.com> Reviewed-by: Mingming Cao <cmm@us.ibm.com>
2008-01-29 12:58:27 +08:00
goto failed_mount;
}
blocks_count = (ext4_blocks_count(es) -
le32_to_cpu(es->s_first_data_block) +
EXT4_BLOCKS_PER_GROUP(sb) - 1);
do_div(blocks_count, EXT4_BLOCKS_PER_GROUP(sb));
if (blocks_count > ((uint64_t)1<<32) - EXT4_DESC_PER_BLOCK(sb)) {
ext4_msg(sb, KERN_WARNING, "groups count too large: %u "
"(block count %llu, first data block %u, "
"blocks per group %lu)", sbi->s_groups_count,
ext4_blocks_count(es),
le32_to_cpu(es->s_first_data_block),
EXT4_BLOCKS_PER_GROUP(sb));
goto failed_mount;
}
sbi->s_groups_count = blocks_count;
sbi->s_blockfile_groups = min_t(ext4_group_t, sbi->s_groups_count,
(EXT4_MAX_BLOCK_FILE_PHYS / EXT4_BLOCKS_PER_GROUP(sb)));
db_count = (sbi->s_groups_count + EXT4_DESC_PER_BLOCK(sb) - 1) /
EXT4_DESC_PER_BLOCK(sb);
if (ext4_has_feature_meta_bg(sb)) {
if (le32_to_cpu(es->s_first_meta_bg) >= db_count) {
ext4_msg(sb, KERN_WARNING,
"first meta block group too large: %u "
"(group descriptor block count %u)",
le32_to_cpu(es->s_first_meta_bg), db_count);
goto failed_mount;
}
}
sbi->s_group_desc = ext4_kvmalloc(db_count *
sizeof(struct buffer_head *),
GFP_KERNEL);
if (sbi->s_group_desc == NULL) {
ext4_msg(sb, KERN_ERR, "not enough memory");
ret = -ENOMEM;
goto failed_mount;
}
bgl_lock_init(sbi->s_blockgroup_lock);
for (i = 0; i < db_count; i++) {
block = descriptor_loc(sb, logical_sb_block, i);
sbi->s_group_desc[i] = sb_bread_unmovable(sb, block);
if (!sbi->s_group_desc[i]) {
ext4_msg(sb, KERN_ERR,
"can't read group descriptor %d", i);
db_count = i;
goto failed_mount2;
}
}
if (!ext4_check_descriptors(sb, logical_sb_block, &first_not_zeroed)) {
ext4_msg(sb, KERN_ERR, "group descriptors corrupted!");
ret = -EFSCORRUPTED;
goto failed_mount2;
}
sbi->s_gdb_count = db_count;
get_random_bytes(&sbi->s_next_generation, sizeof(u32));
spin_lock_init(&sbi->s_next_gen_lock);
setup_timer(&sbi->s_err_report, print_daily_error_info,
(unsigned long) sb);
ext4: unregister es_shrinker if mount failed Otherwise destroyed ext_sb_info will be part of global shinker list and result in the following OOPS: JBD2: corrupted journal superblock JBD2: recovery failed EXT4-fs (dm-2): error loading journal general protection fault: 0000 [#1] SMP Modules linked in: fuse acpi_cpufreq freq_table mperf coretemp kvm_intel kvm crc32c_intel microcode sg button sd_mod crc_t10dif ahci libahci pata_acpi ata_generic dm_mirror dm_region_hash dm_log dm_\ mod CPU 1 Pid: 2758, comm: mount Not tainted 3.8.0-rc3+ #136 /DH55TC RIP: 0010:[<ffffffff811bfb2d>] [<ffffffff811bfb2d>] unregister_shrinker+0xad/0xe0 RSP: 0000:ffff88011d5cbcd8 EFLAGS: 00010207 RAX: 6b6b6b6b6b6b6b6b RBX: 6b6b6b6b6b6b6b53 RCX: 0000000000000006 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000246 RBP: ffff88011d5cbce8 R08: 0000000000000002 R09: 0000000000000001 R10: 0000000000000001 R11: 0000000000000000 R12: ffff88011cd3f848 R13: ffff88011cd3f830 R14: ffff88011cd3f000 R15: 0000000000000000 FS: 00007f7b721dd7e0(0000) GS:ffff880121a00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b CR2: 00007fffa6f75038 CR3: 000000011bc1c000 CR4: 00000000000007e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Process mount (pid: 2758, threadinfo ffff88011d5ca000, task ffff880116aacb80) Stack: ffff88011cd3f000 ffffffff8209b6c0 ffff88011d5cbd18 ffffffff812482f1 00000000000003f3 00000000ffffffea ffff880115f4c200 0000000000000000 ffff88011d5cbda8 ffffffff81249381 ffff8801219d8bf8 ffffffff00000000 Call Trace: [<ffffffff812482f1>] deactivate_locked_super+0x91/0xb0 [<ffffffff81249381>] mount_bdev+0x331/0x340 [<ffffffff81376730>] ? ext4_alloc_flex_bg_array+0x180/0x180 [<ffffffff81362035>] ext4_mount+0x15/0x20 [<ffffffff8124869a>] mount_fs+0x9a/0x2e0 [<ffffffff81277e25>] vfs_kern_mount+0xc5/0x170 [<ffffffff81279c02>] do_new_mount+0x172/0x2e0 [<ffffffff8127aa56>] do_mount+0x376/0x380 [<ffffffff8127ab98>] sys_mount+0x138/0x150 [<ffffffff818ffed9>] system_call_fastpath+0x16/0x1b Code: 8b 05 88 04 eb 00 48 3d 90 ff 06 82 48 8d 58 e8 75 19 4c 89 e7 e8 e4 d7 2c 00 48 c7 c7 00 ff 06 82 e8 58 5f ef ff 5b 41 5c c9 c3 <48> 8b 4b 18 48 8b 73 20 48 89 da 31 c0 48 c7 c7 c5 a0 e4 81 e\ 8 RIP [<ffffffff811bfb2d>] unregister_shrinker+0xad/0xe0 RSP <ffff88011d5cbcd8> Signed-off-by: Dmitry Monakhov <dmonakhov@openvz.org> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu> Cc: stable@vger.kernel.org
2013-04-04 10:10:52 +08:00
/* Register extent status tree shrinker */
ext4: track extent status tree shrinker delay statictics This commit adds some statictics in extent status tree shrinker. The purpose to add these is that we want to collect more details when we encounter a stall caused by extent status tree shrinker. Here we count the following statictics: stats: the number of all objects on all extent status trees the number of reclaimable objects on lru list cache hits/misses the last sorted interval the number of inodes on lru list average: scan time for shrinking some objects the number of shrunk objects maximum: the inode that has max nr. of objects on lru list the maximum scan time for shrinking some objects The output looks like below: $ cat /proc/fs/ext4/sda1/es_shrinker_info stats: 28228 objects 6341 reclaimable objects 5281/631 cache hits/misses 586 ms last sorted interval 250 inodes on lru list average: 153 us scan time 128 shrunk objects maximum: 255 inode (255 objects, 198 reclaimable) 125723 us max scan time If the lru list has never been sorted, the following line will not be printed: 586ms last sorted interval If there is an empty lru list, the following lines also will not be printed: 250 inodes on lru list ... maximum: 255 inode (255 objects, 198 reclaimable) 0 us max scan time Meanwhile in this commit a new trace point is defined to print some details in __ext4_es_shrink(). Cc: Andreas Dilger <adilger.kernel@dilger.ca> Cc: Jan Kara <jack@suse.cz> Reviewed-by: Jan Kara <jack@suse.cz> Signed-off-by: Zheng Liu <wenqing.lz@taobao.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2014-09-02 10:26:49 +08:00
if (ext4_es_register_shrinker(sbi))
goto failed_mount3;
sbi->s_stripe = ext4_get_stripe_size(sbi);
sbi->s_extent_max_zeroout_kb = 32;
/*
* set up enough so that it can read an inode
*/
sb->s_op = &ext4_sops;
sb->s_export_op = &ext4_export_ops;
sb->s_xattr = ext4_xattr_handlers;
sb->s_cop = &ext4_cryptops;
#ifdef CONFIG_QUOTA
sb->dq_op = &ext4_quota_operations;
if (ext4_has_feature_quota(sb))
sb->s_qcop = &dquot_quotactl_sysfile_ops;
else
sb->s_qcop = &ext4_qctl_operations;
sb->s_quota_types = QTYPE_MASK_USR | QTYPE_MASK_GRP | QTYPE_MASK_PRJ;
#endif
memcpy(sb->s_uuid, es->s_uuid, sizeof(es->s_uuid));
INIT_LIST_HEAD(&sbi->s_orphan); /* unlinked but open files */
mutex_init(&sbi->s_orphan_lock);
sb->s_root = NULL;
needs_recovery = (es->s_last_orphan != 0 ||
ext4_has_feature_journal_needs_recovery(sb));
if (ext4_has_feature_mmp(sb) && !(sb->s_flags & MS_RDONLY))
if (ext4_multi_mount_protect(sb, le64_to_cpu(es->s_mmp_block)))
goto failed_mount3a;
/*
* The first inode we look at is the journal inode. Don't try
* root first: it may be modified in the journal!
*/
if (!test_opt(sb, NOLOAD) && ext4_has_feature_journal(sb)) {
if (ext4_load_journal(sb, es, journal_devnum))
goto failed_mount3a;
} else if (test_opt(sb, NOLOAD) && !(sb->s_flags & MS_RDONLY) &&
ext4_has_feature_journal_needs_recovery(sb)) {
ext4_msg(sb, KERN_ERR, "required journal recovery "
"suppressed and not mounted read-only");
goto failed_mount_wq;
} else {
/* Nojournal mode, all journal mount options are illegal */
if (test_opt2(sb, EXPLICIT_JOURNAL_CHECKSUM)) {
ext4_msg(sb, KERN_ERR, "can't mount with "
"journal_checksum, fs mounted w/o journal");
goto failed_mount_wq;
}
if (test_opt(sb, JOURNAL_ASYNC_COMMIT)) {
ext4_msg(sb, KERN_ERR, "can't mount with "
"journal_async_commit, fs mounted w/o journal");
goto failed_mount_wq;
}
if (sbi->s_commit_interval != JBD2_DEFAULT_MAX_COMMIT_AGE*HZ) {
ext4_msg(sb, KERN_ERR, "can't mount with "
"commit=%lu, fs mounted w/o journal",
sbi->s_commit_interval / HZ);
goto failed_mount_wq;
}
if (EXT4_MOUNT_DATA_FLAGS &
(sbi->s_mount_opt ^ sbi->s_def_mount_opt)) {
ext4_msg(sb, KERN_ERR, "can't mount with "
"data=, fs mounted w/o journal");
goto failed_mount_wq;
}
sbi->s_def_mount_opt &= EXT4_MOUNT_JOURNAL_CHECKSUM;
clear_opt(sb, JOURNAL_CHECKSUM);
clear_opt(sb, DATA_FLAGS);
sbi->s_journal = NULL;
needs_recovery = 0;
goto no_journal;
}
if (ext4_has_feature_64bit(sb) &&
!jbd2_journal_set_features(EXT4_SB(sb)->s_journal, 0, 0,
JBD2_FEATURE_INCOMPAT_64BIT)) {
ext4_msg(sb, KERN_ERR, "Failed to set 64-bit journal feature");
goto failed_mount_wq;
}
if (!set_journal_csum_feature_set(sb)) {
ext4_msg(sb, KERN_ERR, "Failed to set journal checksum "
"feature set");
goto failed_mount_wq;
}
/* We have now updated the journal if required, so we can
* validate the data journaling mode. */
switch (test_opt(sb, DATA_FLAGS)) {
case 0:
/* No mode set, assume a default based on the journal
* capabilities: ORDERED_DATA if the journal can
* cope, else JOURNAL_DATA
*/
if (jbd2_journal_check_available_features
(sbi->s_journal, 0, 0, JBD2_FEATURE_INCOMPAT_REVOKE))
set_opt(sb, ORDERED_DATA);
else
set_opt(sb, JOURNAL_DATA);
break;
case EXT4_MOUNT_ORDERED_DATA:
case EXT4_MOUNT_WRITEBACK_DATA:
if (!jbd2_journal_check_available_features
(sbi->s_journal, 0, 0, JBD2_FEATURE_INCOMPAT_REVOKE)) {
ext4_msg(sb, KERN_ERR, "Journal does not support "
"requested data journaling mode");
goto failed_mount_wq;
}
default:
break;
}
if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA &&
test_opt(sb, JOURNAL_ASYNC_COMMIT)) {
ext4_msg(sb, KERN_ERR, "can't mount with "
"journal_async_commit in data=ordered mode");
goto failed_mount_wq;
}
set_task_ioprio(sbi->s_journal->j_task, journal_ioprio);
sbi->s_journal->j_commit_callback = ext4_journal_commit_callback;
no_journal:
sbi->s_mb_cache = ext4_xattr_create_cache();
if (!sbi->s_mb_cache) {
ext4_msg(sb, KERN_ERR, "Failed to create an mb_cache");
goto failed_mount_wq;
}
if ((DUMMY_ENCRYPTION_ENABLED(sbi) || ext4_has_feature_encrypt(sb)) &&
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 20:29:47 +08:00
(blocksize != PAGE_SIZE)) {
ext4_msg(sb, KERN_ERR,
"Unsupported blocksize for fs encryption");
goto failed_mount_wq;
}
if (DUMMY_ENCRYPTION_ENABLED(sbi) && !(sb->s_flags & MS_RDONLY) &&
!ext4_has_feature_encrypt(sb)) {
ext4_set_feature_encrypt(sb);
ext4_commit_super(sb, 1);
}
/*
* Get the # of file system overhead blocks from the
* superblock if present.
*/
if (es->s_overhead_clusters)
sbi->s_overhead = le32_to_cpu(es->s_overhead_clusters);
else {
err = ext4_calculate_overhead(sb);
if (err)
goto failed_mount_wq;
}
/*
* The maximum number of concurrent works can be high and
* concurrency isn't really necessary. Limit it to 1.
*/
EXT4_SB(sb)->rsv_conversion_wq =
alloc_workqueue("ext4-rsv-conversion", WQ_MEM_RECLAIM | WQ_UNBOUND, 1);
if (!EXT4_SB(sb)->rsv_conversion_wq) {
printk(KERN_ERR "EXT4-fs: failed to create workqueue\n");
ret = -ENOMEM;
goto failed_mount4;
}
/*
* The jbd2_journal_load will have done any necessary log recovery,
* so we can safely mount the rest of the filesystem now.
*/
root = ext4_iget(sb, EXT4_ROOT_INO);
if (IS_ERR(root)) {
ext4_msg(sb, KERN_ERR, "get root inode failed");
ret = PTR_ERR(root);
root = NULL;
goto failed_mount4;
}
if (!S_ISDIR(root->i_mode) || !root->i_blocks || !root->i_size) {
ext4_msg(sb, KERN_ERR, "corrupt root inode, run e2fsck");
iput(root);
goto failed_mount4;
}
sb->s_root = d_make_root(root);
if (!sb->s_root) {
ext4_msg(sb, KERN_ERR, "get root dentry failed");
ret = -ENOMEM;
goto failed_mount4;
}
if (ext4_setup_super(sb, es, sb->s_flags & MS_RDONLY))
sb->s_flags |= MS_RDONLY;
/* determine the minimum size of new large inodes, if present */
if (sbi->s_inode_size > EXT4_GOOD_OLD_INODE_SIZE) {
sbi->s_want_extra_isize = sizeof(struct ext4_inode) -
EXT4_GOOD_OLD_INODE_SIZE;
if (ext4_has_feature_extra_isize(sb)) {
if (sbi->s_want_extra_isize <
le16_to_cpu(es->s_want_extra_isize))
sbi->s_want_extra_isize =
le16_to_cpu(es->s_want_extra_isize);
if (sbi->s_want_extra_isize <
le16_to_cpu(es->s_min_extra_isize))
sbi->s_want_extra_isize =
le16_to_cpu(es->s_min_extra_isize);
}
}
/* Check if enough inode space is available */
if (EXT4_GOOD_OLD_INODE_SIZE + sbi->s_want_extra_isize >
sbi->s_inode_size) {
sbi->s_want_extra_isize = sizeof(struct ext4_inode) -
EXT4_GOOD_OLD_INODE_SIZE;
ext4_msg(sb, KERN_INFO, "required extra inode space not"
"available");
}
ext4_set_resv_clusters(sb);
ext4: introduce reserved space Currently in ENOSPC condition when writing into unwritten space, or punching a hole, we might need to split the extent and grow extent tree. However since we can not allocate any new metadata blocks we'll have to zero out unwritten part of extent or punched out part of extent, or in the worst case return ENOSPC even though use actually does not allocate any space. Also in delalloc path we do reserve metadata and data blocks for the time we're going to write out, however metadata block reservation is very tricky especially since we expect that logical connectivity implies physical connectivity, however that might not be the case and hence we might end up allocating more metadata blocks than previously reserved. So in future, metadata reservation checks should be removed since we can not assure that we do not under reserve. And this is where reserved space comes into the picture. When mounting the file system we slice off a little bit of the file system space (2% or 4096 clusters, whichever is smaller) which can be then used for the cases mentioned above to prevent costly zeroout, or unexpected ENOSPC. The number of reserved clusters can be set via sysfs, however it can never be bigger than number of free clusters in the file system. Note that this patch fixes the failure of xfstest 274 as expected. Signed-off-by: Lukas Czerner <lczerner@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu> Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
2013-04-10 10:11:22 +08:00
err = ext4_setup_system_zone(sb);
if (err) {
ext4_msg(sb, KERN_ERR, "failed to initialize system "
"zone (%d)", err);
goto failed_mount4a;
}
ext4_ext_init(sb);
err = ext4_mb_init(sb);
if (err) {
ext4_msg(sb, KERN_ERR, "failed to initialize mballoc (%d)",
err);
goto failed_mount5;
}
block = ext4_count_free_clusters(sb);
ext4_free_blocks_count_set(sbi->s_es,
EXT4_C2B(sbi, block));
err = percpu_counter_init(&sbi->s_freeclusters_counter, block,
GFP_KERNEL);
if (!err) {
unsigned long freei = ext4_count_free_inodes(sb);
sbi->s_es->s_free_inodes_count = cpu_to_le32(freei);
err = percpu_counter_init(&sbi->s_freeinodes_counter, freei,
GFP_KERNEL);
}
if (!err)
err = percpu_counter_init(&sbi->s_dirs_counter,
ext4_count_dirs(sb), GFP_KERNEL);
if (!err)
err = percpu_counter_init(&sbi->s_dirtyclusters_counter, 0,
GFP_KERNEL);
if (!err)
err = percpu_init_rwsem(&sbi->s_journal_flag_rwsem);
if (err) {
ext4_msg(sb, KERN_ERR, "insufficient memory");
goto failed_mount6;
}
if (ext4_has_feature_flex_bg(sb))
if (!ext4_fill_flex_info(sb)) {
ext4_msg(sb, KERN_ERR,
"unable to initialize "
"flex_bg meta info!");
goto failed_mount6;
}
ext4: add support for lazy inode table initialization When the lazy_itable_init extended option is passed to mke2fs, it considerably speeds up filesystem creation because inode tables are not zeroed out. The fact that parts of the inode table are uninitialized is not a problem so long as the block group descriptors, which contain information regarding how much of the inode table has been initialized, has not been corrupted However, if the block group checksums are not valid, e2fsck must scan the entire inode table, and the the old, uninitialized data could potentially cause e2fsck to report false problems. Hence, it is important for the inode tables to be initialized as soon as possble. This commit adds this feature so that mke2fs can safely use the lazy inode table initialization feature to speed up formatting file systems. This is done via a new new kernel thread called ext4lazyinit, which is created on demand and destroyed, when it is no longer needed. There is only one thread for all ext4 filesystems in the system. When the first filesystem with inititable mount option is mounted, ext4lazyinit thread is created, then the filesystem can register its request in the request list. This thread then walks through the list of requests picking up scheduled requests and invoking ext4_init_inode_table(). Next schedule time for the request is computed by multiplying the time it took to zero out last inode table with wait multiplier, which can be set with the (init_itable=n) mount option (default is 10). We are doing this so we do not take the whole I/O bandwidth. When the thread is no longer necessary (request list is empty) it frees the appropriate structures and exits (and can be created later later by another filesystem). We do not disturb regular inode allocations in any way, it just do not care whether the inode table is, or is not zeroed. But when zeroing, we have to skip used inodes, obviously. Also we should prevent new inode allocations from the group, while zeroing is on the way. For that we take write alloc_sem lock in ext4_init_inode_table() and read alloc_sem in the ext4_claim_inode, so when we are unlucky and allocator hits the group which is currently being zeroed, it just has to wait. This can be suppresed using the mount option no_init_itable. Signed-off-by: Lukas Czerner <lczerner@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2010-10-28 09:30:05 +08:00
err = ext4_register_li_request(sb, first_not_zeroed);
if (err)
goto failed_mount6;
ext4: add support for lazy inode table initialization When the lazy_itable_init extended option is passed to mke2fs, it considerably speeds up filesystem creation because inode tables are not zeroed out. The fact that parts of the inode table are uninitialized is not a problem so long as the block group descriptors, which contain information regarding how much of the inode table has been initialized, has not been corrupted However, if the block group checksums are not valid, e2fsck must scan the entire inode table, and the the old, uninitialized data could potentially cause e2fsck to report false problems. Hence, it is important for the inode tables to be initialized as soon as possble. This commit adds this feature so that mke2fs can safely use the lazy inode table initialization feature to speed up formatting file systems. This is done via a new new kernel thread called ext4lazyinit, which is created on demand and destroyed, when it is no longer needed. There is only one thread for all ext4 filesystems in the system. When the first filesystem with inititable mount option is mounted, ext4lazyinit thread is created, then the filesystem can register its request in the request list. This thread then walks through the list of requests picking up scheduled requests and invoking ext4_init_inode_table(). Next schedule time for the request is computed by multiplying the time it took to zero out last inode table with wait multiplier, which can be set with the (init_itable=n) mount option (default is 10). We are doing this so we do not take the whole I/O bandwidth. When the thread is no longer necessary (request list is empty) it frees the appropriate structures and exits (and can be created later later by another filesystem). We do not disturb regular inode allocations in any way, it just do not care whether the inode table is, or is not zeroed. But when zeroing, we have to skip used inodes, obviously. Also we should prevent new inode allocations from the group, while zeroing is on the way. For that we take write alloc_sem lock in ext4_init_inode_table() and read alloc_sem in the ext4_claim_inode, so when we are unlucky and allocator hits the group which is currently being zeroed, it just has to wait. This can be suppresed using the mount option no_init_itable. Signed-off-by: Lukas Czerner <lczerner@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2010-10-28 09:30:05 +08:00
err = ext4_register_sysfs(sb);
if (err)
goto failed_mount7;
#ifdef CONFIG_QUOTA
/* Enable quota usage during mount. */
if (ext4_has_feature_quota(sb) && !(sb->s_flags & MS_RDONLY)) {
err = ext4_enable_quotas(sb);
if (err)
goto failed_mount8;
}
#endif /* CONFIG_QUOTA */
EXT4_SB(sb)->s_mount_state |= EXT4_ORPHAN_FS;
ext4_orphan_cleanup(sb, es);
EXT4_SB(sb)->s_mount_state &= ~EXT4_ORPHAN_FS;
if (needs_recovery) {
ext4_msg(sb, KERN_INFO, "recovery complete");
ext4_mark_recovery_complete(sb, es);
}
if (EXT4_SB(sb)->s_journal) {
if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA)
descr = " journalled data mode";
else if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA)
descr = " ordered data mode";
else
descr = " writeback data mode";
} else
descr = "out journal";
if (test_opt(sb, DISCARD)) {
struct request_queue *q = bdev_get_queue(sb->s_bdev);
if (!blk_queue_discard(q))
ext4_msg(sb, KERN_WARNING,
"mounting with \"discard\" option, but "
"the device does not support discard");
}
if (___ratelimit(&ext4_mount_msg_ratelimit, "EXT4-fs mount"))
ext4_msg(sb, KERN_INFO, "mounted filesystem with%s. "
"Opts: %.*s%s%s", descr,
(int) sizeof(sbi->s_es->s_mount_opts),
sbi->s_es->s_mount_opts,
*sbi->s_es->s_mount_opts ? "; " : "", orig_data);
if (es->s_error_count)
mod_timer(&sbi->s_err_report, jiffies + 300*HZ); /* 5 minutes */
/* Enable message ratelimiting. Default is 10 messages per 5 secs. */
ratelimit_state_init(&sbi->s_err_ratelimit_state, 5 * HZ, 10);
ratelimit_state_init(&sbi->s_warning_ratelimit_state, 5 * HZ, 10);
ratelimit_state_init(&sbi->s_msg_ratelimit_state, 5 * HZ, 10);
kfree(orig_data);
#ifdef CONFIG_EXT4_FS_ENCRYPTION
memcpy(sbi->key_prefix, EXT4_KEY_DESC_PREFIX,
EXT4_KEY_DESC_PREFIX_SIZE);
sbi->key_prefix_size = EXT4_KEY_DESC_PREFIX_SIZE;
#endif
return 0;
cantfind_ext4:
if (!silent)
ext4_msg(sb, KERN_ERR, "VFS: Can't find ext4 filesystem");
goto failed_mount;
#ifdef CONFIG_QUOTA
failed_mount8:
ext4_unregister_sysfs(sb);
#endif
failed_mount7:
ext4_unregister_li_request(sb);
failed_mount6:
ext4_mb_release(sb);
if (sbi->s_flex_groups)
kvfree(sbi->s_flex_groups);
percpu_counter_destroy(&sbi->s_freeclusters_counter);
percpu_counter_destroy(&sbi->s_freeinodes_counter);
percpu_counter_destroy(&sbi->s_dirs_counter);
percpu_counter_destroy(&sbi->s_dirtyclusters_counter);
ext4: initialize multi-block allocator before checking block descriptors With EXT4FS_DEBUG ext4_count_free_clusters() will call ext4_read_block_bitmap() without s_group_info initialized, so we need to initialize multi-block allocator before. And dependencies that must be solved, to allow this: - multi-block allocator needs in group descriptors - need to install s_op before initializing multi-block allocator, because in ext4_mb_init_backend() new inode is created. - initialize number of group desc blocks (s_gdb_count) otherwise number of clusters returned by ext4_free_clusters_after_init() is not correct. (see ext4_bg_num_gdb_nometa()) Here is the stack backtrace: (gdb) bt #0 ext4_get_group_info (group=0, sb=0xffff880079a10000) at ext4.h:2430 #1 ext4_validate_block_bitmap (sb=sb@entry=0xffff880079a10000, desc=desc@entry=0xffff880056510000, block_group=block_group@entry=0, bh=bh@entry=0xffff88007bf2b2d8) at balloc.c:358 #2 0xffffffff81232202 in ext4_wait_block_bitmap (sb=sb@entry=0xffff880079a10000, block_group=block_group@entry=0, bh=bh@entry=0xffff88007bf2b2d8) at balloc.c:476 #3 0xffffffff81232eaf in ext4_read_block_bitmap (sb=sb@entry=0xffff880079a10000, block_group=block_group@entry=0) at balloc.c:489 #4 0xffffffff81232fc0 in ext4_count_free_clusters (sb=sb@entry=0xffff880079a10000) at balloc.c:665 #5 0xffffffff81259ffa in ext4_check_descriptors (first_not_zeroed=<synthetic pointer>, sb=0xffff880079a10000) at super.c:2143 #6 ext4_fill_super (sb=sb@entry=0xffff880079a10000, data=<optimized out>, data@entry=0x0 <irq_stack_union>, silent=silent@entry=0) at super.c:3851 ... Signed-off-by: Azat Khuzhin <a3at.mail@gmail.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2014-04-07 22:54:20 +08:00
failed_mount5:
ext4_ext_release(sb);
ext4_release_system_zone(sb);
failed_mount4a:
dput(sb->s_root);
sb->s_root = NULL;
failed_mount4:
ext4_msg(sb, KERN_ERR, "mount failed");
if (EXT4_SB(sb)->rsv_conversion_wq)
destroy_workqueue(EXT4_SB(sb)->rsv_conversion_wq);
failed_mount_wq:
if (sbi->s_mb_cache) {
ext4_xattr_destroy_cache(sbi->s_mb_cache);
sbi->s_mb_cache = NULL;
}
if (sbi->s_journal) {
jbd2_journal_destroy(sbi->s_journal);
sbi->s_journal = NULL;
}
failed_mount3a:
ext4: improve extent cache shrink mechanism to avoid to burn CPU time Now we maintain an proper in-order LRU list in ext4 to reclaim entries from extent status tree when we are under heavy memory pressure. For keeping this order, a spin lock is used to protect this list. But this lock burns a lot of CPU time. We can use the following steps to trigger it. % cd /dev/shm % dd if=/dev/zero of=ext4-img bs=1M count=2k % mkfs.ext4 ext4-img % mount -t ext4 -o loop ext4-img /mnt % cd /mnt % for ((i=0;i<160;i++)); do truncate -s 64g $i; done % for ((i=0;i<160;i++)); do cp $i /dev/null &; done % perf record -a -g % perf report This commit tries to fix this problem. Now a new member called i_touch_when is added into ext4_inode_info to record the last access time for an inode. Meanwhile we never need to keep a proper in-order LRU list. So this can avoid to burns some CPU time. When we try to reclaim some entries from extent status tree, we use list_sort() to get a proper in-order list. Then we traverse this list to discard some entries. In ext4_sb_info, we use s_es_last_sorted to record the last time of sorting this list. When we traverse the list, we skip the inode that is newer than this time, and move this inode to the tail of LRU list. When the head of the list is newer than s_es_last_sorted, we will sort the LRU list again. In this commit, we break the loop if s_extent_cache_cnt == 0 because that means that all extents in extent status tree have been reclaimed. Meanwhile in this commit, ext4_es_{un}register_shrinker()'s prototype is changed to save a local variable in these functions. Reported-by: Dave Hansen <dave.hansen@intel.com> Signed-off-by: Zheng Liu <wenqing.lz@taobao.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2013-07-01 20:12:37 +08:00
ext4_es_unregister_shrinker(sbi);
ext4: track extent status tree shrinker delay statictics This commit adds some statictics in extent status tree shrinker. The purpose to add these is that we want to collect more details when we encounter a stall caused by extent status tree shrinker. Here we count the following statictics: stats: the number of all objects on all extent status trees the number of reclaimable objects on lru list cache hits/misses the last sorted interval the number of inodes on lru list average: scan time for shrinking some objects the number of shrunk objects maximum: the inode that has max nr. of objects on lru list the maximum scan time for shrinking some objects The output looks like below: $ cat /proc/fs/ext4/sda1/es_shrinker_info stats: 28228 objects 6341 reclaimable objects 5281/631 cache hits/misses 586 ms last sorted interval 250 inodes on lru list average: 153 us scan time 128 shrunk objects maximum: 255 inode (255 objects, 198 reclaimable) 125723 us max scan time If the lru list has never been sorted, the following line will not be printed: 586ms last sorted interval If there is an empty lru list, the following lines also will not be printed: 250 inodes on lru list ... maximum: 255 inode (255 objects, 198 reclaimable) 0 us max scan time Meanwhile in this commit a new trace point is defined to print some details in __ext4_es_shrink(). Cc: Andreas Dilger <adilger.kernel@dilger.ca> Cc: Jan Kara <jack@suse.cz> Reviewed-by: Jan Kara <jack@suse.cz> Signed-off-by: Zheng Liu <wenqing.lz@taobao.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2014-09-02 10:26:49 +08:00
failed_mount3:
del_timer_sync(&sbi->s_err_report);
if (sbi->s_mmp_tsk)
kthread_stop(sbi->s_mmp_tsk);
failed_mount2:
for (i = 0; i < db_count; i++)
brelse(sbi->s_group_desc[i]);
kvfree(sbi->s_group_desc);
failed_mount:
if (sbi->s_chksum_driver)
crypto_free_shash(sbi->s_chksum_driver);
#ifdef CONFIG_QUOTA
for (i = 0; i < EXT4_MAXQUOTAS; i++)
kfree(sbi->s_qf_names[i]);
#endif
ext4_blkdev_remove(sbi);
brelse(bh);
out_fail:
sb->s_fs_info = NULL;
kfree(sbi->s_blockgroup_lock);
out_free_base:
kfree(sbi);
kfree(orig_data);
return err ? err : ret;
}
/*
* Setup any per-fs journal parameters now. We'll do this both on
* initial mount, once the journal has been initialised but before we've
* done any recovery; and again on any subsequent remount.
*/
static void ext4_init_journal_params(struct super_block *sb, journal_t *journal)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
journal->j_commit_interval = sbi->s_commit_interval;
journal->j_min_batch_time = sbi->s_min_batch_time;
journal->j_max_batch_time = sbi->s_max_batch_time;
write_lock(&journal->j_state_lock);
if (test_opt(sb, BARRIER))
journal->j_flags |= JBD2_BARRIER;
else
journal->j_flags &= ~JBD2_BARRIER;
if (test_opt(sb, DATA_ERR_ABORT))
journal->j_flags |= JBD2_ABORT_ON_SYNCDATA_ERR;
else
journal->j_flags &= ~JBD2_ABORT_ON_SYNCDATA_ERR;
write_unlock(&journal->j_state_lock);
}
static struct inode *ext4_get_journal_inode(struct super_block *sb,
unsigned int journal_inum)
{
struct inode *journal_inode;
/*
* Test for the existence of a valid inode on disk. Bad things
* happen if we iget() an unused inode, as the subsequent iput()
* will try to delete it.
*/
journal_inode = ext4_iget(sb, journal_inum);
if (IS_ERR(journal_inode)) {
ext4_msg(sb, KERN_ERR, "no journal found");
return NULL;
}
if (!journal_inode->i_nlink) {
make_bad_inode(journal_inode);
iput(journal_inode);
ext4_msg(sb, KERN_ERR, "journal inode is deleted");
return NULL;
}
jbd_debug(2, "Journal inode found at %p: %lld bytes\n",
journal_inode, journal_inode->i_size);
if (!S_ISREG(journal_inode->i_mode)) {
ext4_msg(sb, KERN_ERR, "invalid journal inode");
iput(journal_inode);
return NULL;
}
return journal_inode;
}
static journal_t *ext4_get_journal(struct super_block *sb,
unsigned int journal_inum)
{
struct inode *journal_inode;
journal_t *journal;
BUG_ON(!ext4_has_feature_journal(sb));
journal_inode = ext4_get_journal_inode(sb, journal_inum);
if (!journal_inode)
return NULL;
journal = jbd2_journal_init_inode(journal_inode);
if (!journal) {
ext4_msg(sb, KERN_ERR, "Could not load journal inode");
iput(journal_inode);
return NULL;
}
journal->j_private = sb;
ext4_init_journal_params(sb, journal);
return journal;
}
static journal_t *ext4_get_dev_journal(struct super_block *sb,
dev_t j_dev)
{
struct buffer_head *bh;
journal_t *journal;
ext4_fsblk_t start;
ext4_fsblk_t len;
int hblock, blocksize;
ext4_fsblk_t sb_block;
unsigned long offset;
struct ext4_super_block *es;
struct block_device *bdev;
BUG_ON(!ext4_has_feature_journal(sb));
bdev = ext4_blkdev_get(j_dev, sb);
if (bdev == NULL)
return NULL;
blocksize = sb->s_blocksize;
hblock = bdev_logical_block_size(bdev);
if (blocksize < hblock) {
ext4_msg(sb, KERN_ERR,
"blocksize too small for journal device");
goto out_bdev;
}
sb_block = EXT4_MIN_BLOCK_SIZE / blocksize;
offset = EXT4_MIN_BLOCK_SIZE % blocksize;
set_blocksize(bdev, blocksize);
if (!(bh = __bread(bdev, sb_block, blocksize))) {
ext4_msg(sb, KERN_ERR, "couldn't read superblock of "
"external journal");
goto out_bdev;
}
es = (struct ext4_super_block *) (bh->b_data + offset);
if ((le16_to_cpu(es->s_magic) != EXT4_SUPER_MAGIC) ||
!(le32_to_cpu(es->s_feature_incompat) &
EXT4_FEATURE_INCOMPAT_JOURNAL_DEV)) {
ext4_msg(sb, KERN_ERR, "external journal has "
"bad superblock");
brelse(bh);
goto out_bdev;
}
if ((le32_to_cpu(es->s_feature_ro_compat) &
EXT4_FEATURE_RO_COMPAT_METADATA_CSUM) &&
es->s_checksum != ext4_superblock_csum(sb, es)) {
ext4_msg(sb, KERN_ERR, "external journal has "
"corrupt superblock");
brelse(bh);
goto out_bdev;
}
if (memcmp(EXT4_SB(sb)->s_es->s_journal_uuid, es->s_uuid, 16)) {
ext4_msg(sb, KERN_ERR, "journal UUID does not match");
brelse(bh);
goto out_bdev;
}
len = ext4_blocks_count(es);
start = sb_block + 1;
brelse(bh); /* we're done with the superblock */
journal = jbd2_journal_init_dev(bdev, sb->s_bdev,
start, len, blocksize);
if (!journal) {
ext4_msg(sb, KERN_ERR, "failed to create device journal");
goto out_bdev;
}
journal->j_private = sb;
ll_rw_block(REQ_OP_READ, REQ_META | REQ_PRIO, 1, &journal->j_sb_buffer);
wait_on_buffer(journal->j_sb_buffer);
if (!buffer_uptodate(journal->j_sb_buffer)) {
ext4_msg(sb, KERN_ERR, "I/O error on journal device");
goto out_journal;
}
if (be32_to_cpu(journal->j_superblock->s_nr_users) != 1) {
ext4_msg(sb, KERN_ERR, "External journal has more than one "
"user (unsupported) - %d",
be32_to_cpu(journal->j_superblock->s_nr_users));
goto out_journal;
}
EXT4_SB(sb)->journal_bdev = bdev;
ext4_init_journal_params(sb, journal);
return journal;
out_journal:
jbd2_journal_destroy(journal);
out_bdev:
ext4_blkdev_put(bdev);
return NULL;
}
static int ext4_load_journal(struct super_block *sb,
struct ext4_super_block *es,
unsigned long journal_devnum)
{
journal_t *journal;
unsigned int journal_inum = le32_to_cpu(es->s_journal_inum);
dev_t journal_dev;
int err = 0;
int really_read_only;
BUG_ON(!ext4_has_feature_journal(sb));
if (journal_devnum &&
journal_devnum != le32_to_cpu(es->s_journal_dev)) {
ext4_msg(sb, KERN_INFO, "external journal device major/minor "
"numbers have changed");
journal_dev = new_decode_dev(journal_devnum);
} else
journal_dev = new_decode_dev(le32_to_cpu(es->s_journal_dev));
really_read_only = bdev_read_only(sb->s_bdev);
/*
* Are we loading a blank journal or performing recovery after a
* crash? For recovery, we need to check in advance whether we
* can get read-write access to the device.
*/
if (ext4_has_feature_journal_needs_recovery(sb)) {
if (sb->s_flags & MS_RDONLY) {
ext4_msg(sb, KERN_INFO, "INFO: recovery "
"required on readonly filesystem");
if (really_read_only) {
ext4_msg(sb, KERN_ERR, "write access "
"unavailable, cannot proceed");
return -EROFS;
}
ext4_msg(sb, KERN_INFO, "write access will "
"be enabled during recovery");
}
}
if (journal_inum && journal_dev) {
ext4_msg(sb, KERN_ERR, "filesystem has both journal "
"and inode journals!");
return -EINVAL;
}
if (journal_inum) {
if (!(journal = ext4_get_journal(sb, journal_inum)))
return -EINVAL;
} else {
if (!(journal = ext4_get_dev_journal(sb, journal_dev)))
return -EINVAL;
}
if (!(journal->j_flags & JBD2_BARRIER))
ext4_msg(sb, KERN_INFO, "barriers disabled");
if (!ext4_has_feature_journal_needs_recovery(sb))
err = jbd2_journal_wipe(journal, !really_read_only);
if (!err) {
char *save = kmalloc(EXT4_S_ERR_LEN, GFP_KERNEL);
if (save)
memcpy(save, ((char *) es) +
EXT4_S_ERR_START, EXT4_S_ERR_LEN);
err = jbd2_journal_load(journal);
if (save)
memcpy(((char *) es) + EXT4_S_ERR_START,
save, EXT4_S_ERR_LEN);
kfree(save);
}
if (err) {
ext4_msg(sb, KERN_ERR, "error loading journal");
jbd2_journal_destroy(journal);
return err;
}
EXT4_SB(sb)->s_journal = journal;
ext4_clear_journal_err(sb, es);
if (!really_read_only && journal_devnum &&
journal_devnum != le32_to_cpu(es->s_journal_dev)) {
es->s_journal_dev = cpu_to_le32(journal_devnum);
/* Make sure we flush the recovery flag to disk. */
ext4_commit_super(sb, 1);
}
return 0;
}
static int ext4_commit_super(struct super_block *sb, int sync)
{
struct ext4_super_block *es = EXT4_SB(sb)->s_es;
struct buffer_head *sbh = EXT4_SB(sb)->s_sbh;
filesystem freeze: add error handling of write_super_lockfs/unlockfs Currently, ext3 in mainline Linux doesn't have the freeze feature which suspends write requests. So, we cannot take a backup which keeps the filesystem's consistency with the storage device's features (snapshot and replication) while it is mounted. In many case, a commercial filesystem (e.g. VxFS) has the freeze feature and it would be used to get the consistent backup. If Linux's standard filesystem ext3 has the freeze feature, we can do it without a commercial filesystem. So I have implemented the ioctls of the freeze feature. I think we can take the consistent backup with the following steps. 1. Freeze the filesystem with the freeze ioctl. 2. Separate the replication volume or create the snapshot with the storage device's feature. 3. Unfreeze the filesystem with the unfreeze ioctl. 4. Take the backup from the separated replication volume or the snapshot. This patch: VFS: Changed the type of write_super_lockfs and unlockfs from "void" to "int" so that they can return an error. Rename write_super_lockfs and unlockfs of the super block operation freeze_fs and unfreeze_fs to avoid a confusion. ext3, ext4, xfs, gfs2, jfs: Changed the type of write_super_lockfs and unlockfs from "void" to "int" so that write_super_lockfs returns an error if needed, and unlockfs always returns 0. reiserfs: Changed the type of write_super_lockfs and unlockfs from "void" to "int" so that they always return 0 (success) to keep a current behavior. Signed-off-by: Takashi Sato <t-sato@yk.jp.nec.com> Signed-off-by: Masayuki Hamaguchi <m-hamaguchi@ys.jp.nec.com> Cc: <xfs-masters@oss.sgi.com> Cc: <linux-ext4@vger.kernel.org> Cc: Christoph Hellwig <hch@lst.de> Cc: Dave Kleikamp <shaggy@austin.ibm.com> Cc: Dave Chinner <david@fromorbit.com> Cc: Alasdair G Kergon <agk@redhat.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-10 08:40:58 +08:00
int error = 0;
Revert "ext4: remove block_device_ejected" This reverts commit 08439fec266c3cc5702953b4f54bdf5649357de0. Unfortunately we still need to test for bdi->dev to avoid a crash when a USB stick is yanked out while a file system is mounted: usb 2-2: USB disconnect, device number 2 Buffer I/O error on dev sdb1, logical block 15237120, lost sync page write JBD2: Error -5 detected when updating journal superblock for sdb1-8. BUG: unable to handle kernel paging request at 34beb000 IP: [<c136ce88>] __percpu_counter_add+0x18/0xc0 *pdpt = 0000000023db9001 *pde = 0000000000000000 Oops: 0000 [#1] SMP CPU: 0 PID: 4083 Comm: umount Tainted: G U OE 4.1.1-040101-generic #201507011435 Hardware name: LENOVO 7675CTO/7675CTO, BIOS 7NETC2WW (2.22 ) 03/22/2011 task: ebf06b50 ti: ebebc000 task.ti: ebebc000 EIP: 0060:[<c136ce88>] EFLAGS: 00010082 CPU: 0 EIP is at __percpu_counter_add+0x18/0xc0 EAX: f21c8e88 EBX: f21c8e88 ECX: 00000000 EDX: 00000001 ESI: 00000001 EDI: 00000000 EBP: ebebde60 ESP: ebebde40 DS: 007b ES: 007b FS: 00d8 GS: 00e0 SS: 0068 CR0: 8005003b CR2: 34beb000 CR3: 33354200 CR4: 000007f0 Stack: c1abe100 edcb0098 edcb00ec ffffffff f21c8e68 ffffffff f21c8e68 f286d160 ebebde84 c1160454 00000010 00000282 f72a77f8 00000984 f72a77f8 f286d160 f286d170 ebebdea0 c11e613f 00000000 00000282 f72a77f8 edd7f4d0 00000000 Call Trace: [<c1160454>] account_page_dirtied+0x74/0x110 [<c11e613f>] __set_page_dirty+0x3f/0xb0 [<c11e6203>] mark_buffer_dirty+0x53/0xc0 [<c124a0cb>] ext4_commit_super+0x17b/0x250 [<c124ac71>] ext4_put_super+0xc1/0x320 [<c11f04ba>] ? fsnotify_unmount_inodes+0x1aa/0x1c0 [<c11cfeda>] ? evict_inodes+0xca/0xe0 [<c11b925a>] generic_shutdown_super+0x6a/0xe0 [<c10a1df0>] ? prepare_to_wait_event+0xd0/0xd0 [<c1165a50>] ? unregister_shrinker+0x40/0x50 [<c11b92f6>] kill_block_super+0x26/0x70 [<c11b94f5>] deactivate_locked_super+0x45/0x80 [<c11ba007>] deactivate_super+0x47/0x60 [<c11d2b39>] cleanup_mnt+0x39/0x80 [<c11d2bc0>] __cleanup_mnt+0x10/0x20 [<c1080b51>] task_work_run+0x91/0xd0 [<c1011e3c>] do_notify_resume+0x7c/0x90 [<c1720da5>] work_notify Code: 8b 55 e8 e9 f4 fe ff ff 90 90 90 90 90 90 90 90 90 90 90 55 89 e5 83 ec 20 89 5d f4 89 c3 89 75 f8 89 d6 89 7d fc 89 cf 8b 48 14 <64> 8b 01 89 45 ec 89 c2 8b 45 08 c1 fa 1f 01 75 ec 89 55 f0 89 EIP: [<c136ce88>] __percpu_counter_add+0x18/0xc0 SS:ESP 0068:ebebde40 CR2: 0000000034beb000 ---[ end trace dd564a7bea834ecd ]--- Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=101011 Signed-off-by: Theodore Ts'o <tytso@mit.edu> Cc: stable@vger.kernel.org
2015-08-16 22:03:57 +08:00
if (!sbh || block_device_ejected(sb))
filesystem freeze: add error handling of write_super_lockfs/unlockfs Currently, ext3 in mainline Linux doesn't have the freeze feature which suspends write requests. So, we cannot take a backup which keeps the filesystem's consistency with the storage device's features (snapshot and replication) while it is mounted. In many case, a commercial filesystem (e.g. VxFS) has the freeze feature and it would be used to get the consistent backup. If Linux's standard filesystem ext3 has the freeze feature, we can do it without a commercial filesystem. So I have implemented the ioctls of the freeze feature. I think we can take the consistent backup with the following steps. 1. Freeze the filesystem with the freeze ioctl. 2. Separate the replication volume or create the snapshot with the storage device's feature. 3. Unfreeze the filesystem with the unfreeze ioctl. 4. Take the backup from the separated replication volume or the snapshot. This patch: VFS: Changed the type of write_super_lockfs and unlockfs from "void" to "int" so that they can return an error. Rename write_super_lockfs and unlockfs of the super block operation freeze_fs and unfreeze_fs to avoid a confusion. ext3, ext4, xfs, gfs2, jfs: Changed the type of write_super_lockfs and unlockfs from "void" to "int" so that write_super_lockfs returns an error if needed, and unlockfs always returns 0. reiserfs: Changed the type of write_super_lockfs and unlockfs from "void" to "int" so that they always return 0 (success) to keep a current behavior. Signed-off-by: Takashi Sato <t-sato@yk.jp.nec.com> Signed-off-by: Masayuki Hamaguchi <m-hamaguchi@ys.jp.nec.com> Cc: <xfs-masters@oss.sgi.com> Cc: <linux-ext4@vger.kernel.org> Cc: Christoph Hellwig <hch@lst.de> Cc: Dave Kleikamp <shaggy@austin.ibm.com> Cc: Dave Chinner <david@fromorbit.com> Cc: Alasdair G Kergon <agk@redhat.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-10 08:40:58 +08:00
return error;
/*
* If the file system is mounted read-only, don't update the
* superblock write time. This avoids updating the superblock
* write time when we are mounting the root file system
* read/only but we need to replay the journal; at that point,
* for people who are east of GMT and who make their clock
* tick in localtime for Windows bug-for-bug compatibility,
* the clock is set in the future, and this will cause e2fsck
* to complain and force a full file system check.
*/
if (!(sb->s_flags & MS_RDONLY))
es->s_wtime = cpu_to_le32(get_seconds());
if (sb->s_bdev->bd_part)
es->s_kbytes_written =
cpu_to_le64(EXT4_SB(sb)->s_kbytes_written +
((part_stat_read(sb->s_bdev->bd_part, sectors[1]) -
EXT4_SB(sb)->s_sectors_written_start) >> 1));
else
es->s_kbytes_written =
cpu_to_le64(EXT4_SB(sb)->s_kbytes_written);
if (percpu_counter_initialized(&EXT4_SB(sb)->s_freeclusters_counter))
ext4_free_blocks_count_set(es,
EXT4_C2B(EXT4_SB(sb), percpu_counter_sum_positive(
&EXT4_SB(sb)->s_freeclusters_counter)));
if (percpu_counter_initialized(&EXT4_SB(sb)->s_freeinodes_counter))
es->s_free_inodes_count =
cpu_to_le32(percpu_counter_sum_positive(
&EXT4_SB(sb)->s_freeinodes_counter));
BUFFER_TRACE(sbh, "marking dirty");
ext4_superblock_csum_set(sb);
ext4: don't lock buffer in ext4_commit_super if holding spinlock If there is an error reported in mballoc via ext4_grp_locked_error(), the code is holding a spinlock, so ext4_commit_super() must not try to lock the buffer head, or else it will trigger a BUG: BUG: sleeping function called from invalid context at ./include/linux/buffer_head.h:358 in_atomic(): 1, irqs_disabled(): 0, pid: 993, name: mount CPU: 0 PID: 993 Comm: mount Not tainted 4.9.0-rc1-clouder1 #62 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.8.1-0-g4adadbd-20150316_085822-nilsson.home.kraxel.org 04/01/2014 ffff880006423548 ffffffff81318c89 ffffffff819ecdd0 0000000000000166 ffff880006423558 ffffffff810810b0 ffff880006423580 ffffffff81081153 ffff880006e5a1a0 ffff88000690e400 0000000000000000 ffff8800064235c0 Call Trace: [<ffffffff81318c89>] dump_stack+0x67/0x9e [<ffffffff810810b0>] ___might_sleep+0xf0/0x140 [<ffffffff81081153>] __might_sleep+0x53/0xb0 [<ffffffff8126c1dc>] ext4_commit_super+0x19c/0x290 [<ffffffff8126e61a>] __ext4_grp_locked_error+0x14a/0x230 [<ffffffff81081153>] ? __might_sleep+0x53/0xb0 [<ffffffff812822be>] ext4_mb_generate_buddy+0x1de/0x320 Since ext4_grp_locked_error() calls ext4_commit_super with sync == 0 (and it is the only caller which does so), avoid locking and unlocking the buffer in this case. This can result in races with ext4_commit_super() if there are other problems (which is what commit 4743f83990614 was trying to address), but a Warning is better than BUG. Fixes: 4743f83990614 Cc: stable@vger.kernel.org # 4.9 Reported-by: Nikolay Borisov <kernel@kyup.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Reviewed-by: Jan Kara <jack@suse.cz>
2016-11-14 11:02:29 +08:00
if (sync)
lock_buffer(sbh);
if (buffer_write_io_error(sbh)) {
/*
* Oh, dear. A previous attempt to write the
* superblock failed. This could happen because the
* USB device was yanked out. Or it could happen to
* be a transient write error and maybe the block will
* be remapped. Nothing we can do but to retry the
* write and hope for the best.
*/
ext4_msg(sb, KERN_ERR, "previous I/O error to "
"superblock detected");
clear_buffer_write_io_error(sbh);
set_buffer_uptodate(sbh);
}
mark_buffer_dirty(sbh);
if (sync) {
ext4: don't lock buffer in ext4_commit_super if holding spinlock If there is an error reported in mballoc via ext4_grp_locked_error(), the code is holding a spinlock, so ext4_commit_super() must not try to lock the buffer head, or else it will trigger a BUG: BUG: sleeping function called from invalid context at ./include/linux/buffer_head.h:358 in_atomic(): 1, irqs_disabled(): 0, pid: 993, name: mount CPU: 0 PID: 993 Comm: mount Not tainted 4.9.0-rc1-clouder1 #62 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.8.1-0-g4adadbd-20150316_085822-nilsson.home.kraxel.org 04/01/2014 ffff880006423548 ffffffff81318c89 ffffffff819ecdd0 0000000000000166 ffff880006423558 ffffffff810810b0 ffff880006423580 ffffffff81081153 ffff880006e5a1a0 ffff88000690e400 0000000000000000 ffff8800064235c0 Call Trace: [<ffffffff81318c89>] dump_stack+0x67/0x9e [<ffffffff810810b0>] ___might_sleep+0xf0/0x140 [<ffffffff81081153>] __might_sleep+0x53/0xb0 [<ffffffff8126c1dc>] ext4_commit_super+0x19c/0x290 [<ffffffff8126e61a>] __ext4_grp_locked_error+0x14a/0x230 [<ffffffff81081153>] ? __might_sleep+0x53/0xb0 [<ffffffff812822be>] ext4_mb_generate_buddy+0x1de/0x320 Since ext4_grp_locked_error() calls ext4_commit_super with sync == 0 (and it is the only caller which does so), avoid locking and unlocking the buffer in this case. This can result in races with ext4_commit_super() if there are other problems (which is what commit 4743f83990614 was trying to address), but a Warning is better than BUG. Fixes: 4743f83990614 Cc: stable@vger.kernel.org # 4.9 Reported-by: Nikolay Borisov <kernel@kyup.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Reviewed-by: Jan Kara <jack@suse.cz>
2016-11-14 11:02:29 +08:00
unlock_buffer(sbh);
error = __sync_dirty_buffer(sbh,
test_opt(sb, BARRIER) ? REQ_FUA : REQ_SYNC);
filesystem freeze: add error handling of write_super_lockfs/unlockfs Currently, ext3 in mainline Linux doesn't have the freeze feature which suspends write requests. So, we cannot take a backup which keeps the filesystem's consistency with the storage device's features (snapshot and replication) while it is mounted. In many case, a commercial filesystem (e.g. VxFS) has the freeze feature and it would be used to get the consistent backup. If Linux's standard filesystem ext3 has the freeze feature, we can do it without a commercial filesystem. So I have implemented the ioctls of the freeze feature. I think we can take the consistent backup with the following steps. 1. Freeze the filesystem with the freeze ioctl. 2. Separate the replication volume or create the snapshot with the storage device's feature. 3. Unfreeze the filesystem with the unfreeze ioctl. 4. Take the backup from the separated replication volume or the snapshot. This patch: VFS: Changed the type of write_super_lockfs and unlockfs from "void" to "int" so that they can return an error. Rename write_super_lockfs and unlockfs of the super block operation freeze_fs and unfreeze_fs to avoid a confusion. ext3, ext4, xfs, gfs2, jfs: Changed the type of write_super_lockfs and unlockfs from "void" to "int" so that write_super_lockfs returns an error if needed, and unlockfs always returns 0. reiserfs: Changed the type of write_super_lockfs and unlockfs from "void" to "int" so that they always return 0 (success) to keep a current behavior. Signed-off-by: Takashi Sato <t-sato@yk.jp.nec.com> Signed-off-by: Masayuki Hamaguchi <m-hamaguchi@ys.jp.nec.com> Cc: <xfs-masters@oss.sgi.com> Cc: <linux-ext4@vger.kernel.org> Cc: Christoph Hellwig <hch@lst.de> Cc: Dave Kleikamp <shaggy@austin.ibm.com> Cc: Dave Chinner <david@fromorbit.com> Cc: Alasdair G Kergon <agk@redhat.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-10 08:40:58 +08:00
if (error)
return error;
error = buffer_write_io_error(sbh);
if (error) {
ext4_msg(sb, KERN_ERR, "I/O error while writing "
"superblock");
clear_buffer_write_io_error(sbh);
set_buffer_uptodate(sbh);
}
}
filesystem freeze: add error handling of write_super_lockfs/unlockfs Currently, ext3 in mainline Linux doesn't have the freeze feature which suspends write requests. So, we cannot take a backup which keeps the filesystem's consistency with the storage device's features (snapshot and replication) while it is mounted. In many case, a commercial filesystem (e.g. VxFS) has the freeze feature and it would be used to get the consistent backup. If Linux's standard filesystem ext3 has the freeze feature, we can do it without a commercial filesystem. So I have implemented the ioctls of the freeze feature. I think we can take the consistent backup with the following steps. 1. Freeze the filesystem with the freeze ioctl. 2. Separate the replication volume or create the snapshot with the storage device's feature. 3. Unfreeze the filesystem with the unfreeze ioctl. 4. Take the backup from the separated replication volume or the snapshot. This patch: VFS: Changed the type of write_super_lockfs and unlockfs from "void" to "int" so that they can return an error. Rename write_super_lockfs and unlockfs of the super block operation freeze_fs and unfreeze_fs to avoid a confusion. ext3, ext4, xfs, gfs2, jfs: Changed the type of write_super_lockfs and unlockfs from "void" to "int" so that write_super_lockfs returns an error if needed, and unlockfs always returns 0. reiserfs: Changed the type of write_super_lockfs and unlockfs from "void" to "int" so that they always return 0 (success) to keep a current behavior. Signed-off-by: Takashi Sato <t-sato@yk.jp.nec.com> Signed-off-by: Masayuki Hamaguchi <m-hamaguchi@ys.jp.nec.com> Cc: <xfs-masters@oss.sgi.com> Cc: <linux-ext4@vger.kernel.org> Cc: Christoph Hellwig <hch@lst.de> Cc: Dave Kleikamp <shaggy@austin.ibm.com> Cc: Dave Chinner <david@fromorbit.com> Cc: Alasdair G Kergon <agk@redhat.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-10 08:40:58 +08:00
return error;
}
/*
* Have we just finished recovery? If so, and if we are mounting (or
* remounting) the filesystem readonly, then we will end up with a
* consistent fs on disk. Record that fact.
*/
static void ext4_mark_recovery_complete(struct super_block *sb,
struct ext4_super_block *es)
{
journal_t *journal = EXT4_SB(sb)->s_journal;
if (!ext4_has_feature_journal(sb)) {
BUG_ON(journal != NULL);
return;
}
jbd2_journal_lock_updates(journal);
if (jbd2_journal_flush(journal) < 0)
goto out;
if (ext4_has_feature_journal_needs_recovery(sb) &&
sb->s_flags & MS_RDONLY) {
ext4_clear_feature_journal_needs_recovery(sb);
ext4_commit_super(sb, 1);
}
out:
jbd2_journal_unlock_updates(journal);
}
/*
* If we are mounting (or read-write remounting) a filesystem whose journal
* has recorded an error from a previous lifetime, move that error to the
* main filesystem now.
*/
static void ext4_clear_journal_err(struct super_block *sb,
struct ext4_super_block *es)
{
journal_t *journal;
int j_errno;
const char *errstr;
BUG_ON(!ext4_has_feature_journal(sb));
journal = EXT4_SB(sb)->s_journal;
/*
* Now check for any error status which may have been recorded in the
* journal by a prior ext4_error() or ext4_abort()
*/
j_errno = jbd2_journal_errno(journal);
if (j_errno) {
char nbuf[16];
errstr = ext4_decode_error(sb, j_errno, nbuf);
ext4_warning(sb, "Filesystem error recorded "
"from previous mount: %s", errstr);
ext4_warning(sb, "Marking fs in need of filesystem check.");
EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
es->s_state |= cpu_to_le16(EXT4_ERROR_FS);
ext4_commit_super(sb, 1);
jbd2_journal_clear_err(journal);
jbd2_journal_update_sb_errno(journal);
}
}
/*
* Force the running and committing transactions to commit,
* and wait on the commit.
*/
int ext4_force_commit(struct super_block *sb)
{
journal_t *journal;
if (sb->s_flags & MS_RDONLY)
return 0;
journal = EXT4_SB(sb)->s_journal;
return ext4_journal_force_commit(journal);
}
static int ext4_sync_fs(struct super_block *sb, int wait)
{
int ret = 0;
tid_t target;
bool needs_barrier = false;
struct ext4_sb_info *sbi = EXT4_SB(sb);
trace_ext4_sync_fs(sb, wait);
flush_workqueue(sbi->rsv_conversion_wq);
/*
* Writeback quota in non-journalled quota case - journalled quota has
* no dirty dquots
*/
dquot_writeback_dquots(sb, -1);
/*
* Data writeback is possible w/o journal transaction, so barrier must
* being sent at the end of the function. But we can skip it if
* transaction_commit will do it for us.
*/
if (sbi->s_journal) {
target = jbd2_get_latest_transaction(sbi->s_journal);
if (wait && sbi->s_journal->j_flags & JBD2_BARRIER &&
!jbd2_trans_will_send_data_barrier(sbi->s_journal, target))
needs_barrier = true;
if (jbd2_journal_start_commit(sbi->s_journal, &target)) {
if (wait)
ret = jbd2_log_wait_commit(sbi->s_journal,
target);
}
} else if (wait && test_opt(sb, BARRIER))
needs_barrier = true;
if (needs_barrier) {
int err;
err = blkdev_issue_flush(sb->s_bdev, GFP_KERNEL, NULL);
if (!ret)
ret = err;
}
return ret;
}
/*
* LVM calls this function before a (read-only) snapshot is created. This
* gives us a chance to flush the journal completely and mark the fs clean.
*
* Note that only this function cannot bring a filesystem to be in a clean
* state independently. It relies on upper layer to stop all data & metadata
* modifications.
*/
filesystem freeze: add error handling of write_super_lockfs/unlockfs Currently, ext3 in mainline Linux doesn't have the freeze feature which suspends write requests. So, we cannot take a backup which keeps the filesystem's consistency with the storage device's features (snapshot and replication) while it is mounted. In many case, a commercial filesystem (e.g. VxFS) has the freeze feature and it would be used to get the consistent backup. If Linux's standard filesystem ext3 has the freeze feature, we can do it without a commercial filesystem. So I have implemented the ioctls of the freeze feature. I think we can take the consistent backup with the following steps. 1. Freeze the filesystem with the freeze ioctl. 2. Separate the replication volume or create the snapshot with the storage device's feature. 3. Unfreeze the filesystem with the unfreeze ioctl. 4. Take the backup from the separated replication volume or the snapshot. This patch: VFS: Changed the type of write_super_lockfs and unlockfs from "void" to "int" so that they can return an error. Rename write_super_lockfs and unlockfs of the super block operation freeze_fs and unfreeze_fs to avoid a confusion. ext3, ext4, xfs, gfs2, jfs: Changed the type of write_super_lockfs and unlockfs from "void" to "int" so that write_super_lockfs returns an error if needed, and unlockfs always returns 0. reiserfs: Changed the type of write_super_lockfs and unlockfs from "void" to "int" so that they always return 0 (success) to keep a current behavior. Signed-off-by: Takashi Sato <t-sato@yk.jp.nec.com> Signed-off-by: Masayuki Hamaguchi <m-hamaguchi@ys.jp.nec.com> Cc: <xfs-masters@oss.sgi.com> Cc: <linux-ext4@vger.kernel.org> Cc: Christoph Hellwig <hch@lst.de> Cc: Dave Kleikamp <shaggy@austin.ibm.com> Cc: Dave Chinner <david@fromorbit.com> Cc: Alasdair G Kergon <agk@redhat.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-10 08:40:58 +08:00
static int ext4_freeze(struct super_block *sb)
{
filesystem freeze: add error handling of write_super_lockfs/unlockfs Currently, ext3 in mainline Linux doesn't have the freeze feature which suspends write requests. So, we cannot take a backup which keeps the filesystem's consistency with the storage device's features (snapshot and replication) while it is mounted. In many case, a commercial filesystem (e.g. VxFS) has the freeze feature and it would be used to get the consistent backup. If Linux's standard filesystem ext3 has the freeze feature, we can do it without a commercial filesystem. So I have implemented the ioctls of the freeze feature. I think we can take the consistent backup with the following steps. 1. Freeze the filesystem with the freeze ioctl. 2. Separate the replication volume or create the snapshot with the storage device's feature. 3. Unfreeze the filesystem with the unfreeze ioctl. 4. Take the backup from the separated replication volume or the snapshot. This patch: VFS: Changed the type of write_super_lockfs and unlockfs from "void" to "int" so that they can return an error. Rename write_super_lockfs and unlockfs of the super block operation freeze_fs and unfreeze_fs to avoid a confusion. ext3, ext4, xfs, gfs2, jfs: Changed the type of write_super_lockfs and unlockfs from "void" to "int" so that write_super_lockfs returns an error if needed, and unlockfs always returns 0. reiserfs: Changed the type of write_super_lockfs and unlockfs from "void" to "int" so that they always return 0 (success) to keep a current behavior. Signed-off-by: Takashi Sato <t-sato@yk.jp.nec.com> Signed-off-by: Masayuki Hamaguchi <m-hamaguchi@ys.jp.nec.com> Cc: <xfs-masters@oss.sgi.com> Cc: <linux-ext4@vger.kernel.org> Cc: Christoph Hellwig <hch@lst.de> Cc: Dave Kleikamp <shaggy@austin.ibm.com> Cc: Dave Chinner <david@fromorbit.com> Cc: Alasdair G Kergon <agk@redhat.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-10 08:40:58 +08:00
int error = 0;
journal_t *journal;
if (sb->s_flags & MS_RDONLY)
return 0;
journal = EXT4_SB(sb)->s_journal;
if (journal) {
/* Now we set up the journal barrier. */
jbd2_journal_lock_updates(journal);
/*
* Don't clear the needs_recovery flag if we failed to
* flush the journal.
*/
error = jbd2_journal_flush(journal);
if (error < 0)
goto out;
/* Journal blocked and flushed, clear needs_recovery flag. */
ext4_clear_feature_journal_needs_recovery(sb);
}
error = ext4_commit_super(sb, 1);
out:
if (journal)
/* we rely on upper layer to stop further updates */
jbd2_journal_unlock_updates(journal);
return error;
}
/*
* Called by LVM after the snapshot is done. We need to reset the RECOVER
* flag here, even though the filesystem is not technically dirty yet.
*/
filesystem freeze: add error handling of write_super_lockfs/unlockfs Currently, ext3 in mainline Linux doesn't have the freeze feature which suspends write requests. So, we cannot take a backup which keeps the filesystem's consistency with the storage device's features (snapshot and replication) while it is mounted. In many case, a commercial filesystem (e.g. VxFS) has the freeze feature and it would be used to get the consistent backup. If Linux's standard filesystem ext3 has the freeze feature, we can do it without a commercial filesystem. So I have implemented the ioctls of the freeze feature. I think we can take the consistent backup with the following steps. 1. Freeze the filesystem with the freeze ioctl. 2. Separate the replication volume or create the snapshot with the storage device's feature. 3. Unfreeze the filesystem with the unfreeze ioctl. 4. Take the backup from the separated replication volume or the snapshot. This patch: VFS: Changed the type of write_super_lockfs and unlockfs from "void" to "int" so that they can return an error. Rename write_super_lockfs and unlockfs of the super block operation freeze_fs and unfreeze_fs to avoid a confusion. ext3, ext4, xfs, gfs2, jfs: Changed the type of write_super_lockfs and unlockfs from "void" to "int" so that write_super_lockfs returns an error if needed, and unlockfs always returns 0. reiserfs: Changed the type of write_super_lockfs and unlockfs from "void" to "int" so that they always return 0 (success) to keep a current behavior. Signed-off-by: Takashi Sato <t-sato@yk.jp.nec.com> Signed-off-by: Masayuki Hamaguchi <m-hamaguchi@ys.jp.nec.com> Cc: <xfs-masters@oss.sgi.com> Cc: <linux-ext4@vger.kernel.org> Cc: Christoph Hellwig <hch@lst.de> Cc: Dave Kleikamp <shaggy@austin.ibm.com> Cc: Dave Chinner <david@fromorbit.com> Cc: Alasdair G Kergon <agk@redhat.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-10 08:40:58 +08:00
static int ext4_unfreeze(struct super_block *sb)
{
if (sb->s_flags & MS_RDONLY)
return 0;
if (EXT4_SB(sb)->s_journal) {
/* Reset the needs_recovery flag before the fs is unlocked. */
ext4_set_feature_journal_needs_recovery(sb);
}
ext4_commit_super(sb, 1);
filesystem freeze: add error handling of write_super_lockfs/unlockfs Currently, ext3 in mainline Linux doesn't have the freeze feature which suspends write requests. So, we cannot take a backup which keeps the filesystem's consistency with the storage device's features (snapshot and replication) while it is mounted. In many case, a commercial filesystem (e.g. VxFS) has the freeze feature and it would be used to get the consistent backup. If Linux's standard filesystem ext3 has the freeze feature, we can do it without a commercial filesystem. So I have implemented the ioctls of the freeze feature. I think we can take the consistent backup with the following steps. 1. Freeze the filesystem with the freeze ioctl. 2. Separate the replication volume or create the snapshot with the storage device's feature. 3. Unfreeze the filesystem with the unfreeze ioctl. 4. Take the backup from the separated replication volume or the snapshot. This patch: VFS: Changed the type of write_super_lockfs and unlockfs from "void" to "int" so that they can return an error. Rename write_super_lockfs and unlockfs of the super block operation freeze_fs and unfreeze_fs to avoid a confusion. ext3, ext4, xfs, gfs2, jfs: Changed the type of write_super_lockfs and unlockfs from "void" to "int" so that write_super_lockfs returns an error if needed, and unlockfs always returns 0. reiserfs: Changed the type of write_super_lockfs and unlockfs from "void" to "int" so that they always return 0 (success) to keep a current behavior. Signed-off-by: Takashi Sato <t-sato@yk.jp.nec.com> Signed-off-by: Masayuki Hamaguchi <m-hamaguchi@ys.jp.nec.com> Cc: <xfs-masters@oss.sgi.com> Cc: <linux-ext4@vger.kernel.org> Cc: Christoph Hellwig <hch@lst.de> Cc: Dave Kleikamp <shaggy@austin.ibm.com> Cc: Dave Chinner <david@fromorbit.com> Cc: Alasdair G Kergon <agk@redhat.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-10 08:40:58 +08:00
return 0;
}
/*
* Structure to save mount options for ext4_remount's benefit
*/
struct ext4_mount_options {
unsigned long s_mount_opt;
unsigned long s_mount_opt2;
kuid_t s_resuid;
kgid_t s_resgid;
unsigned long s_commit_interval;
u32 s_min_batch_time, s_max_batch_time;
#ifdef CONFIG_QUOTA
int s_jquota_fmt;
char *s_qf_names[EXT4_MAXQUOTAS];
#endif
};
static int ext4_remount(struct super_block *sb, int *flags, char *data)
{
struct ext4_super_block *es;
struct ext4_sb_info *sbi = EXT4_SB(sb);
unsigned long old_sb_flags;
struct ext4_mount_options old_opts;
int enable_quota = 0;
ext4_group_t g;
unsigned int journal_ioprio = DEFAULT_JOURNAL_IOPRIO;
int err = 0;
#ifdef CONFIG_QUOTA
int i, j;
#endif
char *orig_data = kstrdup(data, GFP_KERNEL);
/* Store the original options */
old_sb_flags = sb->s_flags;
old_opts.s_mount_opt = sbi->s_mount_opt;
old_opts.s_mount_opt2 = sbi->s_mount_opt2;
old_opts.s_resuid = sbi->s_resuid;
old_opts.s_resgid = sbi->s_resgid;
old_opts.s_commit_interval = sbi->s_commit_interval;
old_opts.s_min_batch_time = sbi->s_min_batch_time;
old_opts.s_max_batch_time = sbi->s_max_batch_time;
#ifdef CONFIG_QUOTA
old_opts.s_jquota_fmt = sbi->s_jquota_fmt;
for (i = 0; i < EXT4_MAXQUOTAS; i++)
if (sbi->s_qf_names[i]) {
old_opts.s_qf_names[i] = kstrdup(sbi->s_qf_names[i],
GFP_KERNEL);
if (!old_opts.s_qf_names[i]) {
for (j = 0; j < i; j++)
kfree(old_opts.s_qf_names[j]);
kfree(orig_data);
return -ENOMEM;
}
} else
old_opts.s_qf_names[i] = NULL;
#endif
if (sbi->s_journal && sbi->s_journal->j_task->io_context)
journal_ioprio = sbi->s_journal->j_task->io_context->ioprio;
if (!parse_options(data, sb, NULL, &journal_ioprio, 1)) {
err = -EINVAL;
goto restore_opts;
}
if ((old_opts.s_mount_opt & EXT4_MOUNT_JOURNAL_CHECKSUM) ^
test_opt(sb, JOURNAL_CHECKSUM)) {
ext4_msg(sb, KERN_ERR, "changing journal_checksum "
"during remount not supported; ignoring");
sbi->s_mount_opt ^= EXT4_MOUNT_JOURNAL_CHECKSUM;
}
if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) {
if (test_opt2(sb, EXPLICIT_DELALLOC)) {
ext4_msg(sb, KERN_ERR, "can't mount with "
"both data=journal and delalloc");
err = -EINVAL;
goto restore_opts;
}
if (test_opt(sb, DIOREAD_NOLOCK)) {
ext4_msg(sb, KERN_ERR, "can't mount with "
"both data=journal and dioread_nolock");
err = -EINVAL;
goto restore_opts;
}
if (test_opt(sb, DAX)) {
ext4_msg(sb, KERN_ERR, "can't mount with "
"both data=journal and dax");
err = -EINVAL;
goto restore_opts;
}
} else if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA) {
if (test_opt(sb, JOURNAL_ASYNC_COMMIT)) {
ext4_msg(sb, KERN_ERR, "can't mount with "
"journal_async_commit in data=ordered mode");
err = -EINVAL;
goto restore_opts;
}
}
if ((sbi->s_mount_opt ^ old_opts.s_mount_opt) & EXT4_MOUNT_DAX) {
ext4_msg(sb, KERN_WARNING, "warning: refusing change of "
"dax flag with busy inodes while remounting");
sbi->s_mount_opt ^= EXT4_MOUNT_DAX;
}
if (sbi->s_mount_flags & EXT4_MF_FS_ABORTED)
ext4_abort(sb, "Abort forced by user");
sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
(test_opt(sb, POSIX_ACL) ? MS_POSIXACL : 0);
es = sbi->s_es;
if (sbi->s_journal) {
ext4_init_journal_params(sb, sbi->s_journal);
set_task_ioprio(sbi->s_journal->j_task, journal_ioprio);
}
if (*flags & MS_LAZYTIME)
sb->s_flags |= MS_LAZYTIME;
if ((*flags & MS_RDONLY) != (sb->s_flags & MS_RDONLY)) {
if (sbi->s_mount_flags & EXT4_MF_FS_ABORTED) {
err = -EROFS;
goto restore_opts;
}
if (*flags & MS_RDONLY) {
err = sync_filesystem(sb);
if (err < 0)
goto restore_opts;
err = dquot_suspend(sb, -1);
if (err < 0)
goto restore_opts;
/*
* First of all, the unconditional stuff we have to do
* to disable replay of the journal when we next remount
*/
sb->s_flags |= MS_RDONLY;
/*
* OK, test if we are remounting a valid rw partition
* readonly, and if so set the rdonly flag and then
* mark the partition as valid again.
*/
if (!(es->s_state & cpu_to_le16(EXT4_VALID_FS)) &&
(sbi->s_mount_state & EXT4_VALID_FS))
es->s_state = cpu_to_le16(sbi->s_mount_state);
if (sbi->s_journal)
ext4_mark_recovery_complete(sb, es);
} else {
/* Make sure we can mount this feature set readwrite */
if (ext4_has_feature_readonly(sb) ||
!ext4_feature_set_ok(sb, 0)) {
err = -EROFS;
goto restore_opts;
}
/*
* Make sure the group descriptor checksums
* are sane. If they aren't, refuse to remount r/w.
*/
for (g = 0; g < sbi->s_groups_count; g++) {
struct ext4_group_desc *gdp =
ext4_get_group_desc(sb, g, NULL);
if (!ext4_group_desc_csum_verify(sb, g, gdp)) {
ext4_msg(sb, KERN_ERR,
"ext4_remount: Checksum for group %u failed (%u!=%u)",
g, le16_to_cpu(ext4_group_desc_csum(sb, g, gdp)),
le16_to_cpu(gdp->bg_checksum));
err = -EFSBADCRC;
goto restore_opts;
}
}
/*
* If we have an unprocessed orphan list hanging
* around from a previously readonly bdev mount,
* require a full umount/remount for now.
*/
if (es->s_last_orphan) {
ext4_msg(sb, KERN_WARNING, "Couldn't "
"remount RDWR because of unprocessed "
"orphan inode list. Please "
"umount/remount instead");
err = -EINVAL;
goto restore_opts;
}
/*
* Mounting a RDONLY partition read-write, so reread
* and store the current valid flag. (It may have
* been changed by e2fsck since we originally mounted
* the partition.)
*/
if (sbi->s_journal)
ext4_clear_journal_err(sb, es);
sbi->s_mount_state = le16_to_cpu(es->s_state);
if (!ext4_setup_super(sb, es, 0))
sb->s_flags &= ~MS_RDONLY;
if (ext4_has_feature_mmp(sb))
if (ext4_multi_mount_protect(sb,
le64_to_cpu(es->s_mmp_block))) {
err = -EROFS;
goto restore_opts;
}
enable_quota = 1;
}
}
ext4: add support for lazy inode table initialization When the lazy_itable_init extended option is passed to mke2fs, it considerably speeds up filesystem creation because inode tables are not zeroed out. The fact that parts of the inode table are uninitialized is not a problem so long as the block group descriptors, which contain information regarding how much of the inode table has been initialized, has not been corrupted However, if the block group checksums are not valid, e2fsck must scan the entire inode table, and the the old, uninitialized data could potentially cause e2fsck to report false problems. Hence, it is important for the inode tables to be initialized as soon as possble. This commit adds this feature so that mke2fs can safely use the lazy inode table initialization feature to speed up formatting file systems. This is done via a new new kernel thread called ext4lazyinit, which is created on demand and destroyed, when it is no longer needed. There is only one thread for all ext4 filesystems in the system. When the first filesystem with inititable mount option is mounted, ext4lazyinit thread is created, then the filesystem can register its request in the request list. This thread then walks through the list of requests picking up scheduled requests and invoking ext4_init_inode_table(). Next schedule time for the request is computed by multiplying the time it took to zero out last inode table with wait multiplier, which can be set with the (init_itable=n) mount option (default is 10). We are doing this so we do not take the whole I/O bandwidth. When the thread is no longer necessary (request list is empty) it frees the appropriate structures and exits (and can be created later later by another filesystem). We do not disturb regular inode allocations in any way, it just do not care whether the inode table is, or is not zeroed. But when zeroing, we have to skip used inodes, obviously. Also we should prevent new inode allocations from the group, while zeroing is on the way. For that we take write alloc_sem lock in ext4_init_inode_table() and read alloc_sem in the ext4_claim_inode, so when we are unlucky and allocator hits the group which is currently being zeroed, it just has to wait. This can be suppresed using the mount option no_init_itable. Signed-off-by: Lukas Czerner <lczerner@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2010-10-28 09:30:05 +08:00
/*
* Reinitialize lazy itable initialization thread based on
* current settings
*/
if ((sb->s_flags & MS_RDONLY) || !test_opt(sb, INIT_INODE_TABLE))
ext4_unregister_li_request(sb);
else {
ext4_group_t first_not_zeroed;
first_not_zeroed = ext4_has_uninit_itable(sb);
ext4_register_li_request(sb, first_not_zeroed);
}
ext4_setup_system_zone(sb);
if (sbi->s_journal == NULL && !(old_sb_flags & MS_RDONLY))
ext4_commit_super(sb, 1);
#ifdef CONFIG_QUOTA
/* Release old quota file names */
for (i = 0; i < EXT4_MAXQUOTAS; i++)
kfree(old_opts.s_qf_names[i]);
ext4: make quota as first class supported feature This patch adds support for quotas as a first class feature in ext4; which is to say, the quota files are stored in hidden inodes as file system metadata, instead of as separate files visible in the file system directory hierarchy. It is based on the proposal at: https://ext4.wiki.kernel.org/index.php/Design_For_1st_Class_Quota_in_Ext4 This patch introduces a new feature - EXT4_FEATURE_RO_COMPAT_QUOTA which, when turned on, enables quota accounting at mount time iteself. Also, the quota inodes are stored in two additional superblock fields. Some changes introduced by this patch that should be pointed out are: 1) Two new ext4-superblock fields - s_usr_quota_inum and s_grp_quota_inum for storing the quota inodes in use. 2) Default quota inodes are: inode#3 for tracking userquota and inode#4 for tracking group quota. The superblock fields can be set to use other inodes as well. 3) If the QUOTA feature and corresponding quota inodes are set in superblock, the quota usage tracking is turned on at mount time. On 'quotaon' ioctl, the quota limits enforcement is turned on. 'quotaoff' ioctl turns off only the limits enforcement in this case. 4) When QUOTA feature is in use, the quota mount options 'quota', 'usrquota', 'grpquota' are ignored by the kernel. 5) mke2fs or tune2fs can be used to set the QUOTA feature and initialize quota inodes. The default reserved inodes will not be visible to user as regular files. 6) The quota-tools will need to be modified to support hidden quota files on ext4. E2fsprogs will also include support for creating and fixing quota files. 7) Support is only for the new V2 quota file format. Tested-by: Jan Kara <jack@suse.cz> Reviewed-by: Jan Kara <jack@suse.cz> Reviewed-by: Johann Lombardi <johann@whamcloud.com> Signed-off-by: Aditya Kali <adityakali@google.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2012-07-23 08:21:31 +08:00
if (enable_quota) {
if (sb_any_quota_suspended(sb))
dquot_resume(sb, -1);
else if (ext4_has_feature_quota(sb)) {
ext4: make quota as first class supported feature This patch adds support for quotas as a first class feature in ext4; which is to say, the quota files are stored in hidden inodes as file system metadata, instead of as separate files visible in the file system directory hierarchy. It is based on the proposal at: https://ext4.wiki.kernel.org/index.php/Design_For_1st_Class_Quota_in_Ext4 This patch introduces a new feature - EXT4_FEATURE_RO_COMPAT_QUOTA which, when turned on, enables quota accounting at mount time iteself. Also, the quota inodes are stored in two additional superblock fields. Some changes introduced by this patch that should be pointed out are: 1) Two new ext4-superblock fields - s_usr_quota_inum and s_grp_quota_inum for storing the quota inodes in use. 2) Default quota inodes are: inode#3 for tracking userquota and inode#4 for tracking group quota. The superblock fields can be set to use other inodes as well. 3) If the QUOTA feature and corresponding quota inodes are set in superblock, the quota usage tracking is turned on at mount time. On 'quotaon' ioctl, the quota limits enforcement is turned on. 'quotaoff' ioctl turns off only the limits enforcement in this case. 4) When QUOTA feature is in use, the quota mount options 'quota', 'usrquota', 'grpquota' are ignored by the kernel. 5) mke2fs or tune2fs can be used to set the QUOTA feature and initialize quota inodes. The default reserved inodes will not be visible to user as regular files. 6) The quota-tools will need to be modified to support hidden quota files on ext4. E2fsprogs will also include support for creating and fixing quota files. 7) Support is only for the new V2 quota file format. Tested-by: Jan Kara <jack@suse.cz> Reviewed-by: Jan Kara <jack@suse.cz> Reviewed-by: Johann Lombardi <johann@whamcloud.com> Signed-off-by: Aditya Kali <adityakali@google.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2012-07-23 08:21:31 +08:00
err = ext4_enable_quotas(sb);
if (err)
ext4: make quota as first class supported feature This patch adds support for quotas as a first class feature in ext4; which is to say, the quota files are stored in hidden inodes as file system metadata, instead of as separate files visible in the file system directory hierarchy. It is based on the proposal at: https://ext4.wiki.kernel.org/index.php/Design_For_1st_Class_Quota_in_Ext4 This patch introduces a new feature - EXT4_FEATURE_RO_COMPAT_QUOTA which, when turned on, enables quota accounting at mount time iteself. Also, the quota inodes are stored in two additional superblock fields. Some changes introduced by this patch that should be pointed out are: 1) Two new ext4-superblock fields - s_usr_quota_inum and s_grp_quota_inum for storing the quota inodes in use. 2) Default quota inodes are: inode#3 for tracking userquota and inode#4 for tracking group quota. The superblock fields can be set to use other inodes as well. 3) If the QUOTA feature and corresponding quota inodes are set in superblock, the quota usage tracking is turned on at mount time. On 'quotaon' ioctl, the quota limits enforcement is turned on. 'quotaoff' ioctl turns off only the limits enforcement in this case. 4) When QUOTA feature is in use, the quota mount options 'quota', 'usrquota', 'grpquota' are ignored by the kernel. 5) mke2fs or tune2fs can be used to set the QUOTA feature and initialize quota inodes. The default reserved inodes will not be visible to user as regular files. 6) The quota-tools will need to be modified to support hidden quota files on ext4. E2fsprogs will also include support for creating and fixing quota files. 7) Support is only for the new V2 quota file format. Tested-by: Jan Kara <jack@suse.cz> Reviewed-by: Jan Kara <jack@suse.cz> Reviewed-by: Johann Lombardi <johann@whamcloud.com> Signed-off-by: Aditya Kali <adityakali@google.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2012-07-23 08:21:31 +08:00
goto restore_opts;
}
}
#endif
*flags = (*flags & ~MS_LAZYTIME) | (sb->s_flags & MS_LAZYTIME);
ext4_msg(sb, KERN_INFO, "re-mounted. Opts: %s", orig_data);
kfree(orig_data);
return 0;
restore_opts:
sb->s_flags = old_sb_flags;
sbi->s_mount_opt = old_opts.s_mount_opt;
sbi->s_mount_opt2 = old_opts.s_mount_opt2;
sbi->s_resuid = old_opts.s_resuid;
sbi->s_resgid = old_opts.s_resgid;
sbi->s_commit_interval = old_opts.s_commit_interval;
sbi->s_min_batch_time = old_opts.s_min_batch_time;
sbi->s_max_batch_time = old_opts.s_max_batch_time;
#ifdef CONFIG_QUOTA
sbi->s_jquota_fmt = old_opts.s_jquota_fmt;
for (i = 0; i < EXT4_MAXQUOTAS; i++) {
kfree(sbi->s_qf_names[i]);
sbi->s_qf_names[i] = old_opts.s_qf_names[i];
}
#endif
kfree(orig_data);
return err;
}
#ifdef CONFIG_QUOTA
static int ext4_statfs_project(struct super_block *sb,
kprojid_t projid, struct kstatfs *buf)
{
struct kqid qid;
struct dquot *dquot;
u64 limit;
u64 curblock;
qid = make_kqid_projid(projid);
dquot = dqget(sb, qid);
if (IS_ERR(dquot))
return PTR_ERR(dquot);
spin_lock(&dq_data_lock);
limit = (dquot->dq_dqb.dqb_bsoftlimit ?
dquot->dq_dqb.dqb_bsoftlimit :
dquot->dq_dqb.dqb_bhardlimit) >> sb->s_blocksize_bits;
if (limit && buf->f_blocks > limit) {
curblock = dquot->dq_dqb.dqb_curspace >> sb->s_blocksize_bits;
buf->f_blocks = limit;
buf->f_bfree = buf->f_bavail =
(buf->f_blocks > curblock) ?
(buf->f_blocks - curblock) : 0;
}
limit = dquot->dq_dqb.dqb_isoftlimit ?
dquot->dq_dqb.dqb_isoftlimit :
dquot->dq_dqb.dqb_ihardlimit;
if (limit && buf->f_files > limit) {
buf->f_files = limit;
buf->f_ffree =
(buf->f_files > dquot->dq_dqb.dqb_curinodes) ?
(buf->f_files - dquot->dq_dqb.dqb_curinodes) : 0;
}
spin_unlock(&dq_data_lock);
dqput(dquot);
return 0;
}
#endif
static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf)
{
struct super_block *sb = dentry->d_sb;
struct ext4_sb_info *sbi = EXT4_SB(sb);
struct ext4_super_block *es = sbi->s_es;
ext4: introduce reserved space Currently in ENOSPC condition when writing into unwritten space, or punching a hole, we might need to split the extent and grow extent tree. However since we can not allocate any new metadata blocks we'll have to zero out unwritten part of extent or punched out part of extent, or in the worst case return ENOSPC even though use actually does not allocate any space. Also in delalloc path we do reserve metadata and data blocks for the time we're going to write out, however metadata block reservation is very tricky especially since we expect that logical connectivity implies physical connectivity, however that might not be the case and hence we might end up allocating more metadata blocks than previously reserved. So in future, metadata reservation checks should be removed since we can not assure that we do not under reserve. And this is where reserved space comes into the picture. When mounting the file system we slice off a little bit of the file system space (2% or 4096 clusters, whichever is smaller) which can be then used for the cases mentioned above to prevent costly zeroout, or unexpected ENOSPC. The number of reserved clusters can be set via sysfs, however it can never be bigger than number of free clusters in the file system. Note that this patch fixes the failure of xfstest 274 as expected. Signed-off-by: Lukas Czerner <lczerner@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu> Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
2013-04-10 10:11:22 +08:00
ext4_fsblk_t overhead = 0, resv_blocks;
u64 fsid;
s64 bfree;
ext4: introduce reserved space Currently in ENOSPC condition when writing into unwritten space, or punching a hole, we might need to split the extent and grow extent tree. However since we can not allocate any new metadata blocks we'll have to zero out unwritten part of extent or punched out part of extent, or in the worst case return ENOSPC even though use actually does not allocate any space. Also in delalloc path we do reserve metadata and data blocks for the time we're going to write out, however metadata block reservation is very tricky especially since we expect that logical connectivity implies physical connectivity, however that might not be the case and hence we might end up allocating more metadata blocks than previously reserved. So in future, metadata reservation checks should be removed since we can not assure that we do not under reserve. And this is where reserved space comes into the picture. When mounting the file system we slice off a little bit of the file system space (2% or 4096 clusters, whichever is smaller) which can be then used for the cases mentioned above to prevent costly zeroout, or unexpected ENOSPC. The number of reserved clusters can be set via sysfs, however it can never be bigger than number of free clusters in the file system. Note that this patch fixes the failure of xfstest 274 as expected. Signed-off-by: Lukas Czerner <lczerner@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu> Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
2013-04-10 10:11:22 +08:00
resv_blocks = EXT4_C2B(sbi, atomic64_read(&sbi->s_resv_clusters));
if (!test_opt(sb, MINIX_DF))
overhead = sbi->s_overhead;
buf->f_type = EXT4_SUPER_MAGIC;
buf->f_bsize = sb->s_blocksize;
buf->f_blocks = ext4_blocks_count(es) - EXT4_C2B(sbi, overhead);
bfree = percpu_counter_sum_positive(&sbi->s_freeclusters_counter) -
percpu_counter_sum_positive(&sbi->s_dirtyclusters_counter);
/* prevent underflow in case that few free space is available */
buf->f_bfree = EXT4_C2B(sbi, max_t(s64, bfree, 0));
ext4: introduce reserved space Currently in ENOSPC condition when writing into unwritten space, or punching a hole, we might need to split the extent and grow extent tree. However since we can not allocate any new metadata blocks we'll have to zero out unwritten part of extent or punched out part of extent, or in the worst case return ENOSPC even though use actually does not allocate any space. Also in delalloc path we do reserve metadata and data blocks for the time we're going to write out, however metadata block reservation is very tricky especially since we expect that logical connectivity implies physical connectivity, however that might not be the case and hence we might end up allocating more metadata blocks than previously reserved. So in future, metadata reservation checks should be removed since we can not assure that we do not under reserve. And this is where reserved space comes into the picture. When mounting the file system we slice off a little bit of the file system space (2% or 4096 clusters, whichever is smaller) which can be then used for the cases mentioned above to prevent costly zeroout, or unexpected ENOSPC. The number of reserved clusters can be set via sysfs, however it can never be bigger than number of free clusters in the file system. Note that this patch fixes the failure of xfstest 274 as expected. Signed-off-by: Lukas Czerner <lczerner@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu> Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
2013-04-10 10:11:22 +08:00
buf->f_bavail = buf->f_bfree -
(ext4_r_blocks_count(es) + resv_blocks);
if (buf->f_bfree < (ext4_r_blocks_count(es) + resv_blocks))
buf->f_bavail = 0;
buf->f_files = le32_to_cpu(es->s_inodes_count);
buf->f_ffree = percpu_counter_sum_positive(&sbi->s_freeinodes_counter);
buf->f_namelen = EXT4_NAME_LEN;
fsid = le64_to_cpup((void *)es->s_uuid) ^
le64_to_cpup((void *)es->s_uuid + sizeof(u64));
buf->f_fsid.val[0] = fsid & 0xFFFFFFFFUL;
buf->f_fsid.val[1] = (fsid >> 32) & 0xFFFFFFFFUL;
#ifdef CONFIG_QUOTA
if (ext4_test_inode_flag(dentry->d_inode, EXT4_INODE_PROJINHERIT) &&
sb_has_quota_limits_enabled(sb, PRJQUOTA))
ext4_statfs_project(sb, EXT4_I(dentry->d_inode)->i_projid, buf);
#endif
return 0;
}
/* Helper function for writing quotas on sync - we need to start transaction
* before quota file is locked for write. Otherwise the are possible deadlocks:
* Process 1 Process 2
* ext4_create() quota_sync()
* jbd2_journal_start() write_dquot()
* dquot_initialize() down(dqio_mutex)
* down(dqio_mutex) jbd2_journal_start()
*
*/
#ifdef CONFIG_QUOTA
static inline struct inode *dquot_to_inode(struct dquot *dquot)
{
return sb_dqopt(dquot->dq_sb)->files[dquot->dq_id.type];
}
static int ext4_write_dquot(struct dquot *dquot)
{
int ret, err;
handle_t *handle;
struct inode *inode;
inode = dquot_to_inode(dquot);
handle = ext4_journal_start(inode, EXT4_HT_QUOTA,
EXT4_QUOTA_TRANS_BLOCKS(dquot->dq_sb));
if (IS_ERR(handle))
return PTR_ERR(handle);
ret = dquot_commit(dquot);
err = ext4_journal_stop(handle);
if (!ret)
ret = err;
return ret;
}
static int ext4_acquire_dquot(struct dquot *dquot)
{
int ret, err;
handle_t *handle;
handle = ext4_journal_start(dquot_to_inode(dquot), EXT4_HT_QUOTA,
EXT4_QUOTA_INIT_BLOCKS(dquot->dq_sb));
if (IS_ERR(handle))
return PTR_ERR(handle);
ret = dquot_acquire(dquot);
err = ext4_journal_stop(handle);
if (!ret)
ret = err;
return ret;
}
static int ext4_release_dquot(struct dquot *dquot)
{
int ret, err;
handle_t *handle;
handle = ext4_journal_start(dquot_to_inode(dquot), EXT4_HT_QUOTA,
EXT4_QUOTA_DEL_BLOCKS(dquot->dq_sb));
if (IS_ERR(handle)) {
/* Release dquot anyway to avoid endless cycle in dqput() */
dquot_release(dquot);
return PTR_ERR(handle);
}
ret = dquot_release(dquot);
err = ext4_journal_stop(handle);
if (!ret)
ret = err;
return ret;
}
static int ext4_mark_dquot_dirty(struct dquot *dquot)
{
struct super_block *sb = dquot->dq_sb;
struct ext4_sb_info *sbi = EXT4_SB(sb);
/* Are we journaling quotas? */
if (ext4_has_feature_quota(sb) ||
sbi->s_qf_names[USRQUOTA] || sbi->s_qf_names[GRPQUOTA]) {
dquot_mark_dquot_dirty(dquot);
return ext4_write_dquot(dquot);
} else {
return dquot_mark_dquot_dirty(dquot);
}
}
static int ext4_write_info(struct super_block *sb, int type)
{
int ret, err;
handle_t *handle;
/* Data block + inode block */
handle = ext4_journal_start(d_inode(sb->s_root), EXT4_HT_QUOTA, 2);
if (IS_ERR(handle))
return PTR_ERR(handle);
ret = dquot_commit_info(sb, type);
err = ext4_journal_stop(handle);
if (!ret)
ret = err;
return ret;
}
/*
* Turn on quotas during mount time - we need to find
* the quota file and such...
*/
static int ext4_quota_on_mount(struct super_block *sb, int type)
{
return dquot_quota_on_mount(sb, EXT4_SB(sb)->s_qf_names[type],
EXT4_SB(sb)->s_jquota_fmt, type);
}
static void lockdep_set_quota_inode(struct inode *inode, int subclass)
{
struct ext4_inode_info *ei = EXT4_I(inode);
/* The first argument of lockdep_set_subclass has to be
* *exactly* the same as the argument to init_rwsem() --- in
* this case, in init_once() --- or lockdep gets unhappy
* because the name of the lock is set using the
* stringification of the argument to init_rwsem().
*/
(void) ei; /* shut up clang warning if !CONFIG_LOCKDEP */
lockdep_set_subclass(&ei->i_data_sem, subclass);
}
/*
* Standard function to be called on quota_on
*/
static int ext4_quota_on(struct super_block *sb, int type, int format_id,
const struct path *path)
{
int err;
if (!test_opt(sb, QUOTA))
return -EINVAL;
/* Quotafile not on the same filesystem? */
if (path->dentry->d_sb != sb)
return -EXDEV;
/* Journaling quota? */
if (EXT4_SB(sb)->s_qf_names[type]) {
/* Quotafile not in fs root? */
if (path->dentry->d_parent != sb->s_root)
ext4_msg(sb, KERN_WARNING,
"Quota file not on filesystem root. "
"Journaled quota will not work");
}
/*
* When we journal data on quota file, we have to flush journal to see
* all updates to the file when we bypass pagecache...
*/
if (EXT4_SB(sb)->s_journal &&
ext4_should_journal_data(d_inode(path->dentry))) {
/*
* We don't need to lock updates but journal_flush() could
* otherwise be livelocked...
*/
jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal);
err = jbd2_journal_flush(EXT4_SB(sb)->s_journal);
jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
if (err)
return err;
}
lockdep_set_quota_inode(path->dentry->d_inode, I_DATA_SEM_QUOTA);
err = dquot_quota_on(sb, type, format_id, path);
if (err)
lockdep_set_quota_inode(path->dentry->d_inode,
I_DATA_SEM_NORMAL);
return err;
}
ext4: make quota as first class supported feature This patch adds support for quotas as a first class feature in ext4; which is to say, the quota files are stored in hidden inodes as file system metadata, instead of as separate files visible in the file system directory hierarchy. It is based on the proposal at: https://ext4.wiki.kernel.org/index.php/Design_For_1st_Class_Quota_in_Ext4 This patch introduces a new feature - EXT4_FEATURE_RO_COMPAT_QUOTA which, when turned on, enables quota accounting at mount time iteself. Also, the quota inodes are stored in two additional superblock fields. Some changes introduced by this patch that should be pointed out are: 1) Two new ext4-superblock fields - s_usr_quota_inum and s_grp_quota_inum for storing the quota inodes in use. 2) Default quota inodes are: inode#3 for tracking userquota and inode#4 for tracking group quota. The superblock fields can be set to use other inodes as well. 3) If the QUOTA feature and corresponding quota inodes are set in superblock, the quota usage tracking is turned on at mount time. On 'quotaon' ioctl, the quota limits enforcement is turned on. 'quotaoff' ioctl turns off only the limits enforcement in this case. 4) When QUOTA feature is in use, the quota mount options 'quota', 'usrquota', 'grpquota' are ignored by the kernel. 5) mke2fs or tune2fs can be used to set the QUOTA feature and initialize quota inodes. The default reserved inodes will not be visible to user as regular files. 6) The quota-tools will need to be modified to support hidden quota files on ext4. E2fsprogs will also include support for creating and fixing quota files. 7) Support is only for the new V2 quota file format. Tested-by: Jan Kara <jack@suse.cz> Reviewed-by: Jan Kara <jack@suse.cz> Reviewed-by: Johann Lombardi <johann@whamcloud.com> Signed-off-by: Aditya Kali <adityakali@google.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2012-07-23 08:21:31 +08:00
static int ext4_quota_enable(struct super_block *sb, int type, int format_id,
unsigned int flags)
{
int err;
struct inode *qf_inode;
unsigned long qf_inums[EXT4_MAXQUOTAS] = {
ext4: make quota as first class supported feature This patch adds support for quotas as a first class feature in ext4; which is to say, the quota files are stored in hidden inodes as file system metadata, instead of as separate files visible in the file system directory hierarchy. It is based on the proposal at: https://ext4.wiki.kernel.org/index.php/Design_For_1st_Class_Quota_in_Ext4 This patch introduces a new feature - EXT4_FEATURE_RO_COMPAT_QUOTA which, when turned on, enables quota accounting at mount time iteself. Also, the quota inodes are stored in two additional superblock fields. Some changes introduced by this patch that should be pointed out are: 1) Two new ext4-superblock fields - s_usr_quota_inum and s_grp_quota_inum for storing the quota inodes in use. 2) Default quota inodes are: inode#3 for tracking userquota and inode#4 for tracking group quota. The superblock fields can be set to use other inodes as well. 3) If the QUOTA feature and corresponding quota inodes are set in superblock, the quota usage tracking is turned on at mount time. On 'quotaon' ioctl, the quota limits enforcement is turned on. 'quotaoff' ioctl turns off only the limits enforcement in this case. 4) When QUOTA feature is in use, the quota mount options 'quota', 'usrquota', 'grpquota' are ignored by the kernel. 5) mke2fs or tune2fs can be used to set the QUOTA feature and initialize quota inodes. The default reserved inodes will not be visible to user as regular files. 6) The quota-tools will need to be modified to support hidden quota files on ext4. E2fsprogs will also include support for creating and fixing quota files. 7) Support is only for the new V2 quota file format. Tested-by: Jan Kara <jack@suse.cz> Reviewed-by: Jan Kara <jack@suse.cz> Reviewed-by: Johann Lombardi <johann@whamcloud.com> Signed-off-by: Aditya Kali <adityakali@google.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2012-07-23 08:21:31 +08:00
le32_to_cpu(EXT4_SB(sb)->s_es->s_usr_quota_inum),
le32_to_cpu(EXT4_SB(sb)->s_es->s_grp_quota_inum),
le32_to_cpu(EXT4_SB(sb)->s_es->s_prj_quota_inum)
ext4: make quota as first class supported feature This patch adds support for quotas as a first class feature in ext4; which is to say, the quota files are stored in hidden inodes as file system metadata, instead of as separate files visible in the file system directory hierarchy. It is based on the proposal at: https://ext4.wiki.kernel.org/index.php/Design_For_1st_Class_Quota_in_Ext4 This patch introduces a new feature - EXT4_FEATURE_RO_COMPAT_QUOTA which, when turned on, enables quota accounting at mount time iteself. Also, the quota inodes are stored in two additional superblock fields. Some changes introduced by this patch that should be pointed out are: 1) Two new ext4-superblock fields - s_usr_quota_inum and s_grp_quota_inum for storing the quota inodes in use. 2) Default quota inodes are: inode#3 for tracking userquota and inode#4 for tracking group quota. The superblock fields can be set to use other inodes as well. 3) If the QUOTA feature and corresponding quota inodes are set in superblock, the quota usage tracking is turned on at mount time. On 'quotaon' ioctl, the quota limits enforcement is turned on. 'quotaoff' ioctl turns off only the limits enforcement in this case. 4) When QUOTA feature is in use, the quota mount options 'quota', 'usrquota', 'grpquota' are ignored by the kernel. 5) mke2fs or tune2fs can be used to set the QUOTA feature and initialize quota inodes. The default reserved inodes will not be visible to user as regular files. 6) The quota-tools will need to be modified to support hidden quota files on ext4. E2fsprogs will also include support for creating and fixing quota files. 7) Support is only for the new V2 quota file format. Tested-by: Jan Kara <jack@suse.cz> Reviewed-by: Jan Kara <jack@suse.cz> Reviewed-by: Johann Lombardi <johann@whamcloud.com> Signed-off-by: Aditya Kali <adityakali@google.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2012-07-23 08:21:31 +08:00
};
BUG_ON(!ext4_has_feature_quota(sb));
ext4: make quota as first class supported feature This patch adds support for quotas as a first class feature in ext4; which is to say, the quota files are stored in hidden inodes as file system metadata, instead of as separate files visible in the file system directory hierarchy. It is based on the proposal at: https://ext4.wiki.kernel.org/index.php/Design_For_1st_Class_Quota_in_Ext4 This patch introduces a new feature - EXT4_FEATURE_RO_COMPAT_QUOTA which, when turned on, enables quota accounting at mount time iteself. Also, the quota inodes are stored in two additional superblock fields. Some changes introduced by this patch that should be pointed out are: 1) Two new ext4-superblock fields - s_usr_quota_inum and s_grp_quota_inum for storing the quota inodes in use. 2) Default quota inodes are: inode#3 for tracking userquota and inode#4 for tracking group quota. The superblock fields can be set to use other inodes as well. 3) If the QUOTA feature and corresponding quota inodes are set in superblock, the quota usage tracking is turned on at mount time. On 'quotaon' ioctl, the quota limits enforcement is turned on. 'quotaoff' ioctl turns off only the limits enforcement in this case. 4) When QUOTA feature is in use, the quota mount options 'quota', 'usrquota', 'grpquota' are ignored by the kernel. 5) mke2fs or tune2fs can be used to set the QUOTA feature and initialize quota inodes. The default reserved inodes will not be visible to user as regular files. 6) The quota-tools will need to be modified to support hidden quota files on ext4. E2fsprogs will also include support for creating and fixing quota files. 7) Support is only for the new V2 quota file format. Tested-by: Jan Kara <jack@suse.cz> Reviewed-by: Jan Kara <jack@suse.cz> Reviewed-by: Johann Lombardi <johann@whamcloud.com> Signed-off-by: Aditya Kali <adityakali@google.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2012-07-23 08:21:31 +08:00
if (!qf_inums[type])
return -EPERM;
qf_inode = ext4_iget(sb, qf_inums[type]);
if (IS_ERR(qf_inode)) {
ext4_error(sb, "Bad quota inode # %lu", qf_inums[type]);
return PTR_ERR(qf_inode);
}
/* Don't account quota for quota files to avoid recursion */
qf_inode->i_flags |= S_NOQUOTA;
lockdep_set_quota_inode(qf_inode, I_DATA_SEM_QUOTA);
ext4: make quota as first class supported feature This patch adds support for quotas as a first class feature in ext4; which is to say, the quota files are stored in hidden inodes as file system metadata, instead of as separate files visible in the file system directory hierarchy. It is based on the proposal at: https://ext4.wiki.kernel.org/index.php/Design_For_1st_Class_Quota_in_Ext4 This patch introduces a new feature - EXT4_FEATURE_RO_COMPAT_QUOTA which, when turned on, enables quota accounting at mount time iteself. Also, the quota inodes are stored in two additional superblock fields. Some changes introduced by this patch that should be pointed out are: 1) Two new ext4-superblock fields - s_usr_quota_inum and s_grp_quota_inum for storing the quota inodes in use. 2) Default quota inodes are: inode#3 for tracking userquota and inode#4 for tracking group quota. The superblock fields can be set to use other inodes as well. 3) If the QUOTA feature and corresponding quota inodes are set in superblock, the quota usage tracking is turned on at mount time. On 'quotaon' ioctl, the quota limits enforcement is turned on. 'quotaoff' ioctl turns off only the limits enforcement in this case. 4) When QUOTA feature is in use, the quota mount options 'quota', 'usrquota', 'grpquota' are ignored by the kernel. 5) mke2fs or tune2fs can be used to set the QUOTA feature and initialize quota inodes. The default reserved inodes will not be visible to user as regular files. 6) The quota-tools will need to be modified to support hidden quota files on ext4. E2fsprogs will also include support for creating and fixing quota files. 7) Support is only for the new V2 quota file format. Tested-by: Jan Kara <jack@suse.cz> Reviewed-by: Jan Kara <jack@suse.cz> Reviewed-by: Johann Lombardi <johann@whamcloud.com> Signed-off-by: Aditya Kali <adityakali@google.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2012-07-23 08:21:31 +08:00
err = dquot_enable(qf_inode, type, format_id, flags);
iput(qf_inode);
if (err)
lockdep_set_quota_inode(qf_inode, I_DATA_SEM_NORMAL);
ext4: make quota as first class supported feature This patch adds support for quotas as a first class feature in ext4; which is to say, the quota files are stored in hidden inodes as file system metadata, instead of as separate files visible in the file system directory hierarchy. It is based on the proposal at: https://ext4.wiki.kernel.org/index.php/Design_For_1st_Class_Quota_in_Ext4 This patch introduces a new feature - EXT4_FEATURE_RO_COMPAT_QUOTA which, when turned on, enables quota accounting at mount time iteself. Also, the quota inodes are stored in two additional superblock fields. Some changes introduced by this patch that should be pointed out are: 1) Two new ext4-superblock fields - s_usr_quota_inum and s_grp_quota_inum for storing the quota inodes in use. 2) Default quota inodes are: inode#3 for tracking userquota and inode#4 for tracking group quota. The superblock fields can be set to use other inodes as well. 3) If the QUOTA feature and corresponding quota inodes are set in superblock, the quota usage tracking is turned on at mount time. On 'quotaon' ioctl, the quota limits enforcement is turned on. 'quotaoff' ioctl turns off only the limits enforcement in this case. 4) When QUOTA feature is in use, the quota mount options 'quota', 'usrquota', 'grpquota' are ignored by the kernel. 5) mke2fs or tune2fs can be used to set the QUOTA feature and initialize quota inodes. The default reserved inodes will not be visible to user as regular files. 6) The quota-tools will need to be modified to support hidden quota files on ext4. E2fsprogs will also include support for creating and fixing quota files. 7) Support is only for the new V2 quota file format. Tested-by: Jan Kara <jack@suse.cz> Reviewed-by: Jan Kara <jack@suse.cz> Reviewed-by: Johann Lombardi <johann@whamcloud.com> Signed-off-by: Aditya Kali <adityakali@google.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2012-07-23 08:21:31 +08:00
return err;
}
/* Enable usage tracking for all quota types. */
static int ext4_enable_quotas(struct super_block *sb)
{
int type, err = 0;
unsigned long qf_inums[EXT4_MAXQUOTAS] = {
ext4: make quota as first class supported feature This patch adds support for quotas as a first class feature in ext4; which is to say, the quota files are stored in hidden inodes as file system metadata, instead of as separate files visible in the file system directory hierarchy. It is based on the proposal at: https://ext4.wiki.kernel.org/index.php/Design_For_1st_Class_Quota_in_Ext4 This patch introduces a new feature - EXT4_FEATURE_RO_COMPAT_QUOTA which, when turned on, enables quota accounting at mount time iteself. Also, the quota inodes are stored in two additional superblock fields. Some changes introduced by this patch that should be pointed out are: 1) Two new ext4-superblock fields - s_usr_quota_inum and s_grp_quota_inum for storing the quota inodes in use. 2) Default quota inodes are: inode#3 for tracking userquota and inode#4 for tracking group quota. The superblock fields can be set to use other inodes as well. 3) If the QUOTA feature and corresponding quota inodes are set in superblock, the quota usage tracking is turned on at mount time. On 'quotaon' ioctl, the quota limits enforcement is turned on. 'quotaoff' ioctl turns off only the limits enforcement in this case. 4) When QUOTA feature is in use, the quota mount options 'quota', 'usrquota', 'grpquota' are ignored by the kernel. 5) mke2fs or tune2fs can be used to set the QUOTA feature and initialize quota inodes. The default reserved inodes will not be visible to user as regular files. 6) The quota-tools will need to be modified to support hidden quota files on ext4. E2fsprogs will also include support for creating and fixing quota files. 7) Support is only for the new V2 quota file format. Tested-by: Jan Kara <jack@suse.cz> Reviewed-by: Jan Kara <jack@suse.cz> Reviewed-by: Johann Lombardi <johann@whamcloud.com> Signed-off-by: Aditya Kali <adityakali@google.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2012-07-23 08:21:31 +08:00
le32_to_cpu(EXT4_SB(sb)->s_es->s_usr_quota_inum),
le32_to_cpu(EXT4_SB(sb)->s_es->s_grp_quota_inum),
le32_to_cpu(EXT4_SB(sb)->s_es->s_prj_quota_inum)
ext4: make quota as first class supported feature This patch adds support for quotas as a first class feature in ext4; which is to say, the quota files are stored in hidden inodes as file system metadata, instead of as separate files visible in the file system directory hierarchy. It is based on the proposal at: https://ext4.wiki.kernel.org/index.php/Design_For_1st_Class_Quota_in_Ext4 This patch introduces a new feature - EXT4_FEATURE_RO_COMPAT_QUOTA which, when turned on, enables quota accounting at mount time iteself. Also, the quota inodes are stored in two additional superblock fields. Some changes introduced by this patch that should be pointed out are: 1) Two new ext4-superblock fields - s_usr_quota_inum and s_grp_quota_inum for storing the quota inodes in use. 2) Default quota inodes are: inode#3 for tracking userquota and inode#4 for tracking group quota. The superblock fields can be set to use other inodes as well. 3) If the QUOTA feature and corresponding quota inodes are set in superblock, the quota usage tracking is turned on at mount time. On 'quotaon' ioctl, the quota limits enforcement is turned on. 'quotaoff' ioctl turns off only the limits enforcement in this case. 4) When QUOTA feature is in use, the quota mount options 'quota', 'usrquota', 'grpquota' are ignored by the kernel. 5) mke2fs or tune2fs can be used to set the QUOTA feature and initialize quota inodes. The default reserved inodes will not be visible to user as regular files. 6) The quota-tools will need to be modified to support hidden quota files on ext4. E2fsprogs will also include support for creating and fixing quota files. 7) Support is only for the new V2 quota file format. Tested-by: Jan Kara <jack@suse.cz> Reviewed-by: Jan Kara <jack@suse.cz> Reviewed-by: Johann Lombardi <johann@whamcloud.com> Signed-off-by: Aditya Kali <adityakali@google.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2012-07-23 08:21:31 +08:00
};
bool quota_mopt[EXT4_MAXQUOTAS] = {
test_opt(sb, USRQUOTA),
test_opt(sb, GRPQUOTA),
test_opt(sb, PRJQUOTA),
};
ext4: make quota as first class supported feature This patch adds support for quotas as a first class feature in ext4; which is to say, the quota files are stored in hidden inodes as file system metadata, instead of as separate files visible in the file system directory hierarchy. It is based on the proposal at: https://ext4.wiki.kernel.org/index.php/Design_For_1st_Class_Quota_in_Ext4 This patch introduces a new feature - EXT4_FEATURE_RO_COMPAT_QUOTA which, when turned on, enables quota accounting at mount time iteself. Also, the quota inodes are stored in two additional superblock fields. Some changes introduced by this patch that should be pointed out are: 1) Two new ext4-superblock fields - s_usr_quota_inum and s_grp_quota_inum for storing the quota inodes in use. 2) Default quota inodes are: inode#3 for tracking userquota and inode#4 for tracking group quota. The superblock fields can be set to use other inodes as well. 3) If the QUOTA feature and corresponding quota inodes are set in superblock, the quota usage tracking is turned on at mount time. On 'quotaon' ioctl, the quota limits enforcement is turned on. 'quotaoff' ioctl turns off only the limits enforcement in this case. 4) When QUOTA feature is in use, the quota mount options 'quota', 'usrquota', 'grpquota' are ignored by the kernel. 5) mke2fs or tune2fs can be used to set the QUOTA feature and initialize quota inodes. The default reserved inodes will not be visible to user as regular files. 6) The quota-tools will need to be modified to support hidden quota files on ext4. E2fsprogs will also include support for creating and fixing quota files. 7) Support is only for the new V2 quota file format. Tested-by: Jan Kara <jack@suse.cz> Reviewed-by: Jan Kara <jack@suse.cz> Reviewed-by: Johann Lombardi <johann@whamcloud.com> Signed-off-by: Aditya Kali <adityakali@google.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2012-07-23 08:21:31 +08:00
sb_dqopt(sb)->flags |= DQUOT_QUOTA_SYS_FILE;
for (type = 0; type < EXT4_MAXQUOTAS; type++) {
ext4: make quota as first class supported feature This patch adds support for quotas as a first class feature in ext4; which is to say, the quota files are stored in hidden inodes as file system metadata, instead of as separate files visible in the file system directory hierarchy. It is based on the proposal at: https://ext4.wiki.kernel.org/index.php/Design_For_1st_Class_Quota_in_Ext4 This patch introduces a new feature - EXT4_FEATURE_RO_COMPAT_QUOTA which, when turned on, enables quota accounting at mount time iteself. Also, the quota inodes are stored in two additional superblock fields. Some changes introduced by this patch that should be pointed out are: 1) Two new ext4-superblock fields - s_usr_quota_inum and s_grp_quota_inum for storing the quota inodes in use. 2) Default quota inodes are: inode#3 for tracking userquota and inode#4 for tracking group quota. The superblock fields can be set to use other inodes as well. 3) If the QUOTA feature and corresponding quota inodes are set in superblock, the quota usage tracking is turned on at mount time. On 'quotaon' ioctl, the quota limits enforcement is turned on. 'quotaoff' ioctl turns off only the limits enforcement in this case. 4) When QUOTA feature is in use, the quota mount options 'quota', 'usrquota', 'grpquota' are ignored by the kernel. 5) mke2fs or tune2fs can be used to set the QUOTA feature and initialize quota inodes. The default reserved inodes will not be visible to user as regular files. 6) The quota-tools will need to be modified to support hidden quota files on ext4. E2fsprogs will also include support for creating and fixing quota files. 7) Support is only for the new V2 quota file format. Tested-by: Jan Kara <jack@suse.cz> Reviewed-by: Jan Kara <jack@suse.cz> Reviewed-by: Johann Lombardi <johann@whamcloud.com> Signed-off-by: Aditya Kali <adityakali@google.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2012-07-23 08:21:31 +08:00
if (qf_inums[type]) {
err = ext4_quota_enable(sb, type, QFMT_VFS_V1,
DQUOT_USAGE_ENABLED |
(quota_mopt[type] ? DQUOT_LIMITS_ENABLED : 0));
ext4: make quota as first class supported feature This patch adds support for quotas as a first class feature in ext4; which is to say, the quota files are stored in hidden inodes as file system metadata, instead of as separate files visible in the file system directory hierarchy. It is based on the proposal at: https://ext4.wiki.kernel.org/index.php/Design_For_1st_Class_Quota_in_Ext4 This patch introduces a new feature - EXT4_FEATURE_RO_COMPAT_QUOTA which, when turned on, enables quota accounting at mount time iteself. Also, the quota inodes are stored in two additional superblock fields. Some changes introduced by this patch that should be pointed out are: 1) Two new ext4-superblock fields - s_usr_quota_inum and s_grp_quota_inum for storing the quota inodes in use. 2) Default quota inodes are: inode#3 for tracking userquota and inode#4 for tracking group quota. The superblock fields can be set to use other inodes as well. 3) If the QUOTA feature and corresponding quota inodes are set in superblock, the quota usage tracking is turned on at mount time. On 'quotaon' ioctl, the quota limits enforcement is turned on. 'quotaoff' ioctl turns off only the limits enforcement in this case. 4) When QUOTA feature is in use, the quota mount options 'quota', 'usrquota', 'grpquota' are ignored by the kernel. 5) mke2fs or tune2fs can be used to set the QUOTA feature and initialize quota inodes. The default reserved inodes will not be visible to user as regular files. 6) The quota-tools will need to be modified to support hidden quota files on ext4. E2fsprogs will also include support for creating and fixing quota files. 7) Support is only for the new V2 quota file format. Tested-by: Jan Kara <jack@suse.cz> Reviewed-by: Jan Kara <jack@suse.cz> Reviewed-by: Johann Lombardi <johann@whamcloud.com> Signed-off-by: Aditya Kali <adityakali@google.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2012-07-23 08:21:31 +08:00
if (err) {
ext4_warning(sb,
"Failed to enable quota tracking "
"(type=%d, err=%d). Please run "
"e2fsck to fix.", type, err);
ext4: make quota as first class supported feature This patch adds support for quotas as a first class feature in ext4; which is to say, the quota files are stored in hidden inodes as file system metadata, instead of as separate files visible in the file system directory hierarchy. It is based on the proposal at: https://ext4.wiki.kernel.org/index.php/Design_For_1st_Class_Quota_in_Ext4 This patch introduces a new feature - EXT4_FEATURE_RO_COMPAT_QUOTA which, when turned on, enables quota accounting at mount time iteself. Also, the quota inodes are stored in two additional superblock fields. Some changes introduced by this patch that should be pointed out are: 1) Two new ext4-superblock fields - s_usr_quota_inum and s_grp_quota_inum for storing the quota inodes in use. 2) Default quota inodes are: inode#3 for tracking userquota and inode#4 for tracking group quota. The superblock fields can be set to use other inodes as well. 3) If the QUOTA feature and corresponding quota inodes are set in superblock, the quota usage tracking is turned on at mount time. On 'quotaon' ioctl, the quota limits enforcement is turned on. 'quotaoff' ioctl turns off only the limits enforcement in this case. 4) When QUOTA feature is in use, the quota mount options 'quota', 'usrquota', 'grpquota' are ignored by the kernel. 5) mke2fs or tune2fs can be used to set the QUOTA feature and initialize quota inodes. The default reserved inodes will not be visible to user as regular files. 6) The quota-tools will need to be modified to support hidden quota files on ext4. E2fsprogs will also include support for creating and fixing quota files. 7) Support is only for the new V2 quota file format. Tested-by: Jan Kara <jack@suse.cz> Reviewed-by: Jan Kara <jack@suse.cz> Reviewed-by: Johann Lombardi <johann@whamcloud.com> Signed-off-by: Aditya Kali <adityakali@google.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2012-07-23 08:21:31 +08:00
return err;
}
}
}
return 0;
}
static int ext4_quota_off(struct super_block *sb, int type)
{
struct inode *inode = sb_dqopt(sb)->files[type];
handle_t *handle;
/* Force all delayed allocation blocks to be allocated.
* Caller already holds s_umount sem */
if (test_opt(sb, DELALLOC))
sync_filesystem(sb);
if (!inode)
goto out;
/* Update modification times of quota files when userspace can
* start looking at them */
handle = ext4_journal_start(inode, EXT4_HT_QUOTA, 1);
if (IS_ERR(handle))
goto out;
inode->i_mtime = inode->i_ctime = current_time(inode);
ext4_mark_inode_dirty(handle, inode);
ext4_journal_stop(handle);
out:
return dquot_quota_off(sb, type);
}
/* Read data from quotafile - avoid pagecache and such because we cannot afford
* acquiring the locks... As quota files are never truncated and quota code
* itself serializes the operations (and no one else should touch the files)
* we don't have to be afraid of races */
static ssize_t ext4_quota_read(struct super_block *sb, int type, char *data,
size_t len, loff_t off)
{
struct inode *inode = sb_dqopt(sb)->files[type];
ext4_lblk_t blk = off >> EXT4_BLOCK_SIZE_BITS(sb);
int offset = off & (sb->s_blocksize - 1);
int tocopy;
size_t toread;
struct buffer_head *bh;
loff_t i_size = i_size_read(inode);
if (off > i_size)
return 0;
if (off+len > i_size)
len = i_size-off;
toread = len;
while (toread > 0) {
tocopy = sb->s_blocksize - offset < toread ?
sb->s_blocksize - offset : toread;
bh = ext4_bread(NULL, inode, blk, 0);
if (IS_ERR(bh))
return PTR_ERR(bh);
if (!bh) /* A hole? */
memset(data, 0, tocopy);
else
memcpy(data, bh->b_data+offset, tocopy);
brelse(bh);
offset = 0;
toread -= tocopy;
data += tocopy;
blk++;
}
return len;
}
/* Write to quotafile (we know the transaction is already started and has
* enough credits) */
static ssize_t ext4_quota_write(struct super_block *sb, int type,
const char *data, size_t len, loff_t off)
{
struct inode *inode = sb_dqopt(sb)->files[type];
ext4_lblk_t blk = off >> EXT4_BLOCK_SIZE_BITS(sb);
int err, offset = off & (sb->s_blocksize - 1);
int retries = 0;
struct buffer_head *bh;
handle_t *handle = journal_current_handle();
if (EXT4_SB(sb)->s_journal && !handle) {
ext4_msg(sb, KERN_WARNING, "Quota write (off=%llu, len=%llu)"
" cancelled because transaction is not started",
(unsigned long long)off, (unsigned long long)len);
return -EIO;
}
/*
* Since we account only one data block in transaction credits,
* then it is impossible to cross a block boundary.
*/
if (sb->s_blocksize - offset < len) {
ext4_msg(sb, KERN_WARNING, "Quota write (off=%llu, len=%llu)"
" cancelled because not block aligned",
(unsigned long long)off, (unsigned long long)len);
return -EIO;
}
do {
bh = ext4_bread(handle, inode, blk,
EXT4_GET_BLOCKS_CREATE |
EXT4_GET_BLOCKS_METADATA_NOFAIL);
} while (IS_ERR(bh) && (PTR_ERR(bh) == -ENOSPC) &&
ext4_should_retry_alloc(inode->i_sb, &retries));
if (IS_ERR(bh))
return PTR_ERR(bh);
if (!bh)
goto out;
BUFFER_TRACE(bh, "get write access");
err = ext4_journal_get_write_access(handle, bh);
if (err) {
brelse(bh);
return err;
}
lock_buffer(bh);
memcpy(bh->b_data+offset, data, len);
flush_dcache_page(bh->b_page);
unlock_buffer(bh);
err = ext4_handle_dirty_metadata(handle, NULL, bh);
brelse(bh);
out:
if (inode->i_size < off + len) {
i_size_write(inode, off + len);
EXT4_I(inode)->i_disksize = inode->i_size;
ext4_mark_inode_dirty(handle, inode);
}
return len;
}
static int ext4_get_next_id(struct super_block *sb, struct kqid *qid)
{
const struct quota_format_ops *ops;
if (!sb_has_quota_loaded(sb, qid->type))
return -ESRCH;
ops = sb_dqopt(sb)->ops[qid->type];
if (!ops || !ops->get_next_id)
return -ENOSYS;
return dquot_get_next_id(sb, qid);
}
#endif
static struct dentry *ext4_mount(struct file_system_type *fs_type, int flags,
const char *dev_name, void *data)
{
return mount_bdev(fs_type, flags, dev_name, data, ext4_fill_super);
}
#if !defined(CONFIG_EXT2_FS) && !defined(CONFIG_EXT2_FS_MODULE) && defined(CONFIG_EXT4_USE_FOR_EXT2)
static inline void register_as_ext2(void)
{
int err = register_filesystem(&ext2_fs_type);
if (err)
printk(KERN_WARNING
"EXT4-fs: Unable to register as ext2 (%d)\n", err);
}
static inline void unregister_as_ext2(void)
{
unregister_filesystem(&ext2_fs_type);
}
static inline int ext2_feature_set_ok(struct super_block *sb)
{
if (ext4_has_unknown_ext2_incompat_features(sb))
return 0;
if (sb->s_flags & MS_RDONLY)
return 1;
if (ext4_has_unknown_ext2_ro_compat_features(sb))
return 0;
return 1;
}
#else
static inline void register_as_ext2(void) { }
static inline void unregister_as_ext2(void) { }
static inline int ext2_feature_set_ok(struct super_block *sb) { return 0; }
#endif
static inline void register_as_ext3(void)
{
int err = register_filesystem(&ext3_fs_type);
if (err)
printk(KERN_WARNING
"EXT4-fs: Unable to register as ext3 (%d)\n", err);
}
static inline void unregister_as_ext3(void)
{
unregister_filesystem(&ext3_fs_type);
}
static inline int ext3_feature_set_ok(struct super_block *sb)
{
if (ext4_has_unknown_ext3_incompat_features(sb))
return 0;
if (!ext4_has_feature_journal(sb))
return 0;
if (sb->s_flags & MS_RDONLY)
return 1;
if (ext4_has_unknown_ext3_ro_compat_features(sb))
return 0;
return 1;
}
static struct file_system_type ext4_fs_type = {
.owner = THIS_MODULE,
.name = "ext4",
.mount = ext4_mount,
.kill_sb = kill_block_super,
.fs_flags = FS_REQUIRES_DEV,
};
fs: Limit sys_mount to only request filesystem modules. Modify the request_module to prefix the file system type with "fs-" and add aliases to all of the filesystems that can be built as modules to match. A common practice is to build all of the kernel code and leave code that is not commonly needed as modules, with the result that many users are exposed to any bug anywhere in the kernel. Looking for filesystems with a fs- prefix limits the pool of possible modules that can be loaded by mount to just filesystems trivially making things safer with no real cost. Using aliases means user space can control the policy of which filesystem modules are auto-loaded by editing /etc/modprobe.d/*.conf with blacklist and alias directives. Allowing simple, safe, well understood work-arounds to known problematic software. This also addresses a rare but unfortunate problem where the filesystem name is not the same as it's module name and module auto-loading would not work. While writing this patch I saw a handful of such cases. The most significant being autofs that lives in the module autofs4. This is relevant to user namespaces because we can reach the request module in get_fs_type() without having any special permissions, and people get uncomfortable when a user specified string (in this case the filesystem type) goes all of the way to request_module. After having looked at this issue I don't think there is any particular reason to perform any filtering or permission checks beyond making it clear in the module request that we want a filesystem module. The common pattern in the kernel is to call request_module() without regards to the users permissions. In general all a filesystem module does once loaded is call register_filesystem() and go to sleep. Which means there is not much attack surface exposed by loading a filesytem module unless the filesystem is mounted. In a user namespace filesystems are not mounted unless .fs_flags = FS_USERNS_MOUNT, which most filesystems do not set today. Acked-by: Serge Hallyn <serge.hallyn@canonical.com> Acked-by: Kees Cook <keescook@chromium.org> Reported-by: Kees Cook <keescook@google.com> Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
2013-03-03 11:39:14 +08:00
MODULE_ALIAS_FS("ext4");
ext4: serialize unaligned asynchronous DIO ext4 has a data corruption case when doing non-block-aligned asynchronous direct IO into a sparse file, as demonstrated by xfstest 240. The root cause is that while ext4 preallocates space in the hole, mappings of that space still look "new" and dio_zero_block() will zero out the unwritten portions. When more than one AIO thread is going, they both find this "new" block and race to zero out their portion; this is uncoordinated and causes data corruption. Dave Chinner fixed this for xfs by simply serializing all unaligned asynchronous direct IO. I've done the same here. The difference is that we only wait on conversions, not all IO. This is a very big hammer, and I'm not very pleased with stuffing this into ext4_file_write(). But since ext4 is DIO_LOCKING, we need to serialize it at this high level. I tried to move this into ext4_ext_direct_IO, but by then we have the i_mutex already, and we will wait on the work queue to do conversions - which must also take the i_mutex. So that won't work. This was originally exposed by qemu-kvm installing to a raw disk image with a normal sector-63 alignment. I've tested a backport of this patch with qemu, and it does avoid the corruption. It is also quite a lot slower (14 min for package installs, vs. 8 min for well-aligned) but I'll take slow correctness over fast corruption any day. Mingming suggested that we can track outstanding conversions, and wait on those so that non-sparse files won't be affected, and I've implemented that here; unaligned AIO to nonsparse files won't take a perf hit. [tytso@mit.edu: Keep the mutex as a hashed array instead of bloating the ext4 inode] [tytso@mit.edu: Fix up namespace issues so that global variables are protected with an "ext4_" prefix.] Signed-off-by: Eric Sandeen <sandeen@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2011-02-12 21:17:34 +08:00
/* Shared across all ext4 file systems */
wait_queue_head_t ext4__ioend_wq[EXT4_WQ_HASH_SZ];
static int __init ext4_init_fs(void)
{
ext4: serialize unaligned asynchronous DIO ext4 has a data corruption case when doing non-block-aligned asynchronous direct IO into a sparse file, as demonstrated by xfstest 240. The root cause is that while ext4 preallocates space in the hole, mappings of that space still look "new" and dio_zero_block() will zero out the unwritten portions. When more than one AIO thread is going, they both find this "new" block and race to zero out their portion; this is uncoordinated and causes data corruption. Dave Chinner fixed this for xfs by simply serializing all unaligned asynchronous direct IO. I've done the same here. The difference is that we only wait on conversions, not all IO. This is a very big hammer, and I'm not very pleased with stuffing this into ext4_file_write(). But since ext4 is DIO_LOCKING, we need to serialize it at this high level. I tried to move this into ext4_ext_direct_IO, but by then we have the i_mutex already, and we will wait on the work queue to do conversions - which must also take the i_mutex. So that won't work. This was originally exposed by qemu-kvm installing to a raw disk image with a normal sector-63 alignment. I've tested a backport of this patch with qemu, and it does avoid the corruption. It is also quite a lot slower (14 min for package installs, vs. 8 min for well-aligned) but I'll take slow correctness over fast corruption any day. Mingming suggested that we can track outstanding conversions, and wait on those so that non-sparse files won't be affected, and I've implemented that here; unaligned AIO to nonsparse files won't take a perf hit. [tytso@mit.edu: Keep the mutex as a hashed array instead of bloating the ext4 inode] [tytso@mit.edu: Fix up namespace issues so that global variables are protected with an "ext4_" prefix.] Signed-off-by: Eric Sandeen <sandeen@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2011-02-12 21:17:34 +08:00
int i, err;
ratelimit_state_init(&ext4_mount_msg_ratelimit, 30 * HZ, 64);
ext4_li_info = NULL;
mutex_init(&ext4_li_mtx);
/* Build-time check for flags consistency */
ext4_check_flag_values();
ext4: serialize unaligned asynchronous DIO ext4 has a data corruption case when doing non-block-aligned asynchronous direct IO into a sparse file, as demonstrated by xfstest 240. The root cause is that while ext4 preallocates space in the hole, mappings of that space still look "new" and dio_zero_block() will zero out the unwritten portions. When more than one AIO thread is going, they both find this "new" block and race to zero out their portion; this is uncoordinated and causes data corruption. Dave Chinner fixed this for xfs by simply serializing all unaligned asynchronous direct IO. I've done the same here. The difference is that we only wait on conversions, not all IO. This is a very big hammer, and I'm not very pleased with stuffing this into ext4_file_write(). But since ext4 is DIO_LOCKING, we need to serialize it at this high level. I tried to move this into ext4_ext_direct_IO, but by then we have the i_mutex already, and we will wait on the work queue to do conversions - which must also take the i_mutex. So that won't work. This was originally exposed by qemu-kvm installing to a raw disk image with a normal sector-63 alignment. I've tested a backport of this patch with qemu, and it does avoid the corruption. It is also quite a lot slower (14 min for package installs, vs. 8 min for well-aligned) but I'll take slow correctness over fast corruption any day. Mingming suggested that we can track outstanding conversions, and wait on those so that non-sparse files won't be affected, and I've implemented that here; unaligned AIO to nonsparse files won't take a perf hit. [tytso@mit.edu: Keep the mutex as a hashed array instead of bloating the ext4 inode] [tytso@mit.edu: Fix up namespace issues so that global variables are protected with an "ext4_" prefix.] Signed-off-by: Eric Sandeen <sandeen@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2011-02-12 21:17:34 +08:00
for (i = 0; i < EXT4_WQ_HASH_SZ; i++)
ext4: serialize unaligned asynchronous DIO ext4 has a data corruption case when doing non-block-aligned asynchronous direct IO into a sparse file, as demonstrated by xfstest 240. The root cause is that while ext4 preallocates space in the hole, mappings of that space still look "new" and dio_zero_block() will zero out the unwritten portions. When more than one AIO thread is going, they both find this "new" block and race to zero out their portion; this is uncoordinated and causes data corruption. Dave Chinner fixed this for xfs by simply serializing all unaligned asynchronous direct IO. I've done the same here. The difference is that we only wait on conversions, not all IO. This is a very big hammer, and I'm not very pleased with stuffing this into ext4_file_write(). But since ext4 is DIO_LOCKING, we need to serialize it at this high level. I tried to move this into ext4_ext_direct_IO, but by then we have the i_mutex already, and we will wait on the work queue to do conversions - which must also take the i_mutex. So that won't work. This was originally exposed by qemu-kvm installing to a raw disk image with a normal sector-63 alignment. I've tested a backport of this patch with qemu, and it does avoid the corruption. It is also quite a lot slower (14 min for package installs, vs. 8 min for well-aligned) but I'll take slow correctness over fast corruption any day. Mingming suggested that we can track outstanding conversions, and wait on those so that non-sparse files won't be affected, and I've implemented that here; unaligned AIO to nonsparse files won't take a perf hit. [tytso@mit.edu: Keep the mutex as a hashed array instead of bloating the ext4 inode] [tytso@mit.edu: Fix up namespace issues so that global variables are protected with an "ext4_" prefix.] Signed-off-by: Eric Sandeen <sandeen@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2011-02-12 21:17:34 +08:00
init_waitqueue_head(&ext4__ioend_wq[i]);
err = ext4_init_es();
if (err)
return err;
err = ext4_init_pageio();
if (err)
goto out5;
err = ext4_init_system_zone();
if (err)
goto out4;
err = ext4_init_sysfs();
if (err)
goto out3;
err = ext4_init_mballoc();
if (err)
goto out2;
err = init_inodecache();
if (err)
goto out1;
register_as_ext3();
register_as_ext2();
err = register_filesystem(&ext4_fs_type);
if (err)
goto out;
ext4: add support for lazy inode table initialization When the lazy_itable_init extended option is passed to mke2fs, it considerably speeds up filesystem creation because inode tables are not zeroed out. The fact that parts of the inode table are uninitialized is not a problem so long as the block group descriptors, which contain information regarding how much of the inode table has been initialized, has not been corrupted However, if the block group checksums are not valid, e2fsck must scan the entire inode table, and the the old, uninitialized data could potentially cause e2fsck to report false problems. Hence, it is important for the inode tables to be initialized as soon as possble. This commit adds this feature so that mke2fs can safely use the lazy inode table initialization feature to speed up formatting file systems. This is done via a new new kernel thread called ext4lazyinit, which is created on demand and destroyed, when it is no longer needed. There is only one thread for all ext4 filesystems in the system. When the first filesystem with inititable mount option is mounted, ext4lazyinit thread is created, then the filesystem can register its request in the request list. This thread then walks through the list of requests picking up scheduled requests and invoking ext4_init_inode_table(). Next schedule time for the request is computed by multiplying the time it took to zero out last inode table with wait multiplier, which can be set with the (init_itable=n) mount option (default is 10). We are doing this so we do not take the whole I/O bandwidth. When the thread is no longer necessary (request list is empty) it frees the appropriate structures and exits (and can be created later later by another filesystem). We do not disturb regular inode allocations in any way, it just do not care whether the inode table is, or is not zeroed. But when zeroing, we have to skip used inodes, obviously. Also we should prevent new inode allocations from the group, while zeroing is on the way. For that we take write alloc_sem lock in ext4_init_inode_table() and read alloc_sem in the ext4_claim_inode, so when we are unlucky and allocator hits the group which is currently being zeroed, it just has to wait. This can be suppresed using the mount option no_init_itable. Signed-off-by: Lukas Czerner <lczerner@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2010-10-28 09:30:05 +08:00
return 0;
out:
unregister_as_ext2();
unregister_as_ext3();
destroy_inodecache();
out1:
ext4_exit_mballoc();
out2:
ext4_exit_sysfs();
out3:
ext4_exit_system_zone();
out4:
ext4_exit_pageio();
out5:
ext4_exit_es();
return err;
}
static void __exit ext4_exit_fs(void)
{
ext4: add support for lazy inode table initialization When the lazy_itable_init extended option is passed to mke2fs, it considerably speeds up filesystem creation because inode tables are not zeroed out. The fact that parts of the inode table are uninitialized is not a problem so long as the block group descriptors, which contain information regarding how much of the inode table has been initialized, has not been corrupted However, if the block group checksums are not valid, e2fsck must scan the entire inode table, and the the old, uninitialized data could potentially cause e2fsck to report false problems. Hence, it is important for the inode tables to be initialized as soon as possble. This commit adds this feature so that mke2fs can safely use the lazy inode table initialization feature to speed up formatting file systems. This is done via a new new kernel thread called ext4lazyinit, which is created on demand and destroyed, when it is no longer needed. There is only one thread for all ext4 filesystems in the system. When the first filesystem with inititable mount option is mounted, ext4lazyinit thread is created, then the filesystem can register its request in the request list. This thread then walks through the list of requests picking up scheduled requests and invoking ext4_init_inode_table(). Next schedule time for the request is computed by multiplying the time it took to zero out last inode table with wait multiplier, which can be set with the (init_itable=n) mount option (default is 10). We are doing this so we do not take the whole I/O bandwidth. When the thread is no longer necessary (request list is empty) it frees the appropriate structures and exits (and can be created later later by another filesystem). We do not disturb regular inode allocations in any way, it just do not care whether the inode table is, or is not zeroed. But when zeroing, we have to skip used inodes, obviously. Also we should prevent new inode allocations from the group, while zeroing is on the way. For that we take write alloc_sem lock in ext4_init_inode_table() and read alloc_sem in the ext4_claim_inode, so when we are unlucky and allocator hits the group which is currently being zeroed, it just has to wait. This can be suppresed using the mount option no_init_itable. Signed-off-by: Lukas Czerner <lczerner@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2010-10-28 09:30:05 +08:00
ext4_destroy_lazyinit_thread();
unregister_as_ext2();
unregister_as_ext3();
unregister_filesystem(&ext4_fs_type);
destroy_inodecache();
ext4_exit_mballoc();
ext4_exit_sysfs();
ext4_exit_system_zone();
ext4_exit_pageio();
ext4_exit_es();
}
MODULE_AUTHOR("Remy Card, Stephen Tweedie, Andrew Morton, Andreas Dilger, Theodore Ts'o and others");
MODULE_DESCRIPTION("Fourth Extended Filesystem");
MODULE_LICENSE("GPL");
module_init(ext4_init_fs)
module_exit(ext4_exit_fs)