linux/fs/ext4/ext4.h

2477 lines
87 KiB
C
Raw Normal View History

/*
* ext4.h
*
* 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/include/linux/minix_fs.h
*
* Copyright (C) 1991, 1992 Linus Torvalds
*/
#ifndef _EXT4_H
#define _EXT4_H
#include <linux/types.h>
#include <linux/blkdev.h>
#include <linux/magic.h>
#include <linux/jbd2.h>
#include <linux/quota.h>
#include <linux/rwsem.h>
#include <linux/rbtree.h>
#include <linux/seqlock.h>
#include <linux/mutex.h>
#include <linux/timer.h>
#include <linux/wait.h>
#include <linux/blockgroup_lock.h>
#include <linux/percpu_counter.h>
#include <crypto/hash.h>
#ifdef __KERNEL__
#include <linux/compat.h>
#endif
/*
* The fourth extended filesystem constants/structures
*/
/*
* Define EXT4FS_DEBUG to produce debug messages
*/
#undef EXT4FS_DEBUG
/*
* Debug code
*/
#ifdef EXT4FS_DEBUG
#define ext4_debug(f, a...) \
do { \
printk(KERN_DEBUG "EXT4-fs DEBUG (%s, %d): %s:", \
__FILE__, __LINE__, __func__); \
printk(KERN_DEBUG f, ## a); \
} while (0)
#else
#define ext4_debug(fmt, ...) no_printk(fmt, ##__VA_ARGS__)
#endif
#define EXT4_ERROR_INODE(inode, fmt, a...) \
ext4_error_inode((inode), __func__, __LINE__, 0, (fmt), ## a)
#define EXT4_ERROR_INODE_BLOCK(inode, block, fmt, a...) \
ext4_error_inode((inode), __func__, __LINE__, (block), (fmt), ## a)
#define EXT4_ERROR_FILE(file, block, fmt, a...) \
ext4_error_file((file), __func__, __LINE__, (block), (fmt), ## a)
/* data type for block offset of block group */
typedef int ext4_grpblk_t;
/* data type for filesystem-wide blocks number */
typedef unsigned long long ext4_fsblk_t;
/* data type for file logical block number */
typedef __u32 ext4_lblk_t;
/* data type for block group number */
typedef unsigned int ext4_group_t;
/*
* Flags used in mballoc's allocation_context flags field.
*
* Also used to show what's going on for debugging purposes when the
* flag field is exported via the traceport interface
*/
/* prefer goal again. length */
#define EXT4_MB_HINT_MERGE 0x0001
/* blocks already reserved */
#define EXT4_MB_HINT_RESERVED 0x0002
/* metadata is being allocated */
#define EXT4_MB_HINT_METADATA 0x0004
/* first blocks in the file */
#define EXT4_MB_HINT_FIRST 0x0008
/* search for the best chunk */
#define EXT4_MB_HINT_BEST 0x0010
/* data is being allocated */
#define EXT4_MB_HINT_DATA 0x0020
/* don't preallocate (for tails) */
#define EXT4_MB_HINT_NOPREALLOC 0x0040
/* allocate for locality group */
#define EXT4_MB_HINT_GROUP_ALLOC 0x0080
/* allocate goal blocks or none */
#define EXT4_MB_HINT_GOAL_ONLY 0x0100
/* goal is meaningful */
#define EXT4_MB_HINT_TRY_GOAL 0x0200
/* blocks already pre-reserved by delayed allocation */
#define EXT4_MB_DELALLOC_RESERVED 0x0400
/* We are doing stream allocation */
#define EXT4_MB_STREAM_ALLOC 0x0800
/* Use reserved root blocks if needed */
#define EXT4_MB_USE_ROOT_BLOCKS 0x1000
struct ext4_allocation_request {
/* target inode for block we're allocating */
struct inode *inode;
/* how many blocks we want to allocate */
unsigned int len;
/* logical block in target inode */
ext4_lblk_t logical;
/* the closest logical allocated block to the left */
ext4_lblk_t lleft;
/* the closest logical allocated block to the right */
ext4_lblk_t lright;
/* phys. target (a hint) */
ext4_fsblk_t goal;
/* phys. block for the closest logical allocated block to the left */
ext4_fsblk_t pleft;
/* phys. block for the closest logical allocated block to the right */
ext4_fsblk_t pright;
/* flags. see above EXT4_MB_HINT_* */
unsigned int flags;
};
/*
* Logical to physical block mapping, used by ext4_map_blocks()
*
* This structure is used to pass requests into ext4_map_blocks() as
* well as to store the information returned by ext4_map_blocks(). It
* takes less room on the stack than a struct buffer_head.
*/
#define EXT4_MAP_NEW (1 << BH_New)
#define EXT4_MAP_MAPPED (1 << BH_Mapped)
#define EXT4_MAP_UNWRITTEN (1 << BH_Unwritten)
#define EXT4_MAP_BOUNDARY (1 << BH_Boundary)
#define EXT4_MAP_UNINIT (1 << BH_Uninit)
/* Sometimes (in the bigalloc case, from ext4_da_get_block_prep) the caller of
* ext4_map_blocks wants to know whether or not the underlying cluster has
* already been accounted for. EXT4_MAP_FROM_CLUSTER conveys to the caller that
* the requested mapping was from previously mapped (or delayed allocated)
* cluster. We use BH_AllocFromCluster only for this flag. BH_AllocFromCluster
* should never appear on buffer_head's state flags.
*/
#define EXT4_MAP_FROM_CLUSTER (1 << BH_AllocFromCluster)
#define EXT4_MAP_FLAGS (EXT4_MAP_NEW | EXT4_MAP_MAPPED |\
EXT4_MAP_UNWRITTEN | EXT4_MAP_BOUNDARY |\
EXT4_MAP_UNINIT | EXT4_MAP_FROM_CLUSTER)
struct ext4_map_blocks {
ext4_fsblk_t m_pblk;
ext4_lblk_t m_lblk;
unsigned int m_len;
unsigned int m_flags;
};
/*
* For delayed allocation tracking
*/
struct mpage_da_data {
struct inode *inode;
sector_t b_blocknr; /* start block number of extent */
size_t b_size; /* size of extent */
unsigned long b_state; /* state of the extent */
unsigned long first_page, next_page; /* extent of pages */
struct writeback_control *wbc;
int io_done;
int pages_written;
int retval;
};
/*
* Flags for ext4_io_end->flags
*/
#define EXT4_IO_END_UNWRITTEN 0x0001
#define EXT4_IO_END_ERROR 0x0002
ext4: remove i_mutex lock in ext4_evict_inode to fix lockdep complaining The i_mutex lock and flush_completed_IO() added by commit 2581fdc810 in ext4_evict_inode() causes lockdep complaining about potential deadlock in several places. In most/all of these LOCKDEP complaints it looks like it's a false positive, since many of the potential circular locking cases can't take place by the time the ext4_evict_inode() is called; but since at the very least it may mask real problems, we need to address this. This change removes the flush_completed_IO() and i_mutex lock in ext4_evict_inode(). Instead, we take a different approach to resolve the software lockup that commit 2581fdc810 intends to fix. Rather than having ext4-dio-unwritten thread wait for grabing the i_mutex lock of an inode, we use mutex_trylock() instead, and simply requeue the work item if we fail to grab the inode's i_mutex lock. This should speed up work queue processing in general and also prevents the following deadlock scenario: During page fault, shrink_icache_memory is called that in turn evicts another inode B. Inode B has some pending io_end work so it calls ext4_ioend_wait() that waits for inode B's i_ioend_count to become zero. However, inode B's ioend work was queued behind some of inode A's ioend work on the same cpu's ext4-dio-unwritten workqueue. As the ext4-dio-unwritten thread on that cpu is processing inode A's ioend work, it tries to grab inode A's i_mutex lock. Since the i_mutex lock of inode A is still hold before the page fault happened, we enter a deadlock. Signed-off-by: Jiaying Zhang <jiayingz@google.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2011-08-31 15:50:51 +00:00
#define EXT4_IO_END_QUEUED 0x0004
#define EXT4_IO_END_DIRECT 0x0008
ext4: fix race between sync and completed io work The following command line will leave the aio-stress process unkillable on an ext4 file system (in my case, mounted on /mnt/test): aio-stress -t 20 -s 10 -O -S -o 2 -I 1000 /mnt/test/aiostress.3561.4 /mnt/test/aiostress.3561.4.20 /mnt/test/aiostress.3561.4.19 /mnt/test/aiostress.3561.4.18 /mnt/test/aiostress.3561.4.17 /mnt/test/aiostress.3561.4.16 /mnt/test/aiostress.3561.4.15 /mnt/test/aiostress.3561.4.14 /mnt/test/aiostress.3561.4.13 /mnt/test/aiostress.3561.4.12 /mnt/test/aiostress.3561.4.11 /mnt/test/aiostress.3561.4.10 /mnt/test/aiostress.3561.4.9 /mnt/test/aiostress.3561.4.8 /mnt/test/aiostress.3561.4.7 /mnt/test/aiostress.3561.4.6 /mnt/test/aiostress.3561.4.5 /mnt/test/aiostress.3561.4.4 /mnt/test/aiostress.3561.4.3 /mnt/test/aiostress.3561.4.2 This is using the aio-stress program from the xfstests test suite. That particular command line tells aio-stress to do random writes to 20 files from 20 threads (one thread per file). The files are NOT preallocated, so you will get writes to random offsets within the file, thus creating holes and extending i_size. It also opens the file with O_DIRECT and O_SYNC. On to the problem. When an I/O requires unwritten extent conversion, it is queued onto the completed_io_list for the ext4 inode. Two code paths will pull work items from this list. The first is the ext4_end_io_work routine, and the second is ext4_flush_completed_IO, which is called via the fsync path (and O_SYNC handling, as well). There are two issues I've found in these code paths. First, if the fsync path beats the work routine to a particular I/O, the work routine will free the io_end structure! It does not take into account the fact that the io_end may still be in use by the fsync path. I've fixed this issue by adding yet another IO_END flag, indicating that the io_end is being processed by the fsync path. The second problem is that the work routine will make an assignment to io->flag outside of the lock. I have witnessed this result in a hang at umount. Moving the flag setting inside the lock resolved that problem. The problem was introduced by commit b82e384c7b ("ext4: optimize locking for end_io extent conversion"), which first appeared in 3.2. As such, the fix should be backported to that release (probably along with the unwritten extent conversion race fix). Signed-off-by: Jeff Moyer <jmoyer@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu> CC: stable@kernel.org
2012-03-05 15:29:52 +00:00
#define EXT4_IO_END_IN_FSYNC 0x0010
struct ext4_io_page {
struct page *p_page;
atomic_t p_count;
};
#define MAX_IO_PAGES 128
/*
* For converting uninitialized extents on a work queue.
*
* 'page' is only used from the writepage() path; 'pages' is only used for
* buffered writes; they are used to keep page references until conversion
* takes place. For AIO/DIO, neither field is filled in.
*/
typedef struct ext4_io_end {
struct list_head list; /* per-file finished IO list */
struct inode *inode; /* file being written to */
unsigned int flag; /* unwritten or not */
struct page *page; /* for writepage() path */
loff_t offset; /* offset in the file */
ssize_t size; /* size of the extent */
struct work_struct work; /* data work queue */
struct kiocb *iocb; /* iocb struct for AIO */
int result; /* error value for AIO */
int num_io_pages; /* for writepages() */
struct ext4_io_page *pages[MAX_IO_PAGES]; /* for writepages() */
} ext4_io_end_t;
struct ext4_io_submit {
int io_op;
struct bio *io_bio;
ext4_io_end_t *io_end;
struct ext4_io_page *io_page;
sector_t io_next_block;
};
/*
* Special inodes numbers
*/
#define EXT4_BAD_INO 1 /* Bad blocks inode */
#define EXT4_ROOT_INO 2 /* Root inode */
#define EXT4_USR_QUOTA_INO 3 /* User quota inode */
#define EXT4_GRP_QUOTA_INO 4 /* Group quota inode */
#define EXT4_BOOT_LOADER_INO 5 /* Boot loader inode */
#define EXT4_UNDEL_DIR_INO 6 /* Undelete directory inode */
#define EXT4_RESIZE_INO 7 /* Reserved group descriptors inode */
#define EXT4_JOURNAL_INO 8 /* Journal inode */
/* First non-reserved inode for old ext4 filesystems */
#define EXT4_GOOD_OLD_FIRST_INO 11
/*
* Maximal count of links to a file
*/
#define EXT4_LINK_MAX 65000
/*
* Macro-instructions used to manage several block sizes
*/
#define EXT4_MIN_BLOCK_SIZE 1024
#define EXT4_MAX_BLOCK_SIZE 65536
#define EXT4_MIN_BLOCK_LOG_SIZE 10
#define EXT4_MAX_BLOCK_LOG_SIZE 16
#ifdef __KERNEL__
# define EXT4_BLOCK_SIZE(s) ((s)->s_blocksize)
#else
# define EXT4_BLOCK_SIZE(s) (EXT4_MIN_BLOCK_SIZE << (s)->s_log_block_size)
#endif
#define EXT4_ADDR_PER_BLOCK(s) (EXT4_BLOCK_SIZE(s) / sizeof(__u32))
#define EXT4_CLUSTER_SIZE(s) (EXT4_BLOCK_SIZE(s) << \
EXT4_SB(s)->s_cluster_bits)
#ifdef __KERNEL__
# define EXT4_BLOCK_SIZE_BITS(s) ((s)->s_blocksize_bits)
# define EXT4_CLUSTER_BITS(s) (EXT4_SB(s)->s_cluster_bits)
#else
# define EXT4_BLOCK_SIZE_BITS(s) ((s)->s_log_block_size + 10)
#endif
#ifdef __KERNEL__
#define EXT4_ADDR_PER_BLOCK_BITS(s) (EXT4_SB(s)->s_addr_per_block_bits)
#define EXT4_INODE_SIZE(s) (EXT4_SB(s)->s_inode_size)
#define EXT4_FIRST_INO(s) (EXT4_SB(s)->s_first_ino)
#else
#define EXT4_INODE_SIZE(s) (((s)->s_rev_level == EXT4_GOOD_OLD_REV) ? \
EXT4_GOOD_OLD_INODE_SIZE : \
(s)->s_inode_size)
#define EXT4_FIRST_INO(s) (((s)->s_rev_level == EXT4_GOOD_OLD_REV) ? \
EXT4_GOOD_OLD_FIRST_INO : \
(s)->s_first_ino)
#endif
#define EXT4_BLOCK_ALIGN(size, blkbits) ALIGN((size), (1 << (blkbits)))
/* Translate a block number to a cluster number */
#define EXT4_B2C(sbi, blk) ((blk) >> (sbi)->s_cluster_bits)
/* Translate a cluster number to a block number */
#define EXT4_C2B(sbi, cluster) ((cluster) << (sbi)->s_cluster_bits)
/* Translate # of blks to # of clusters */
#define EXT4_NUM_B2C(sbi, blks) (((blks) + (sbi)->s_cluster_ratio - 1) >> \
(sbi)->s_cluster_bits)
/*
* Structure of a blocks group descriptor
*/
struct ext4_group_desc
{
__le32 bg_block_bitmap_lo; /* Blocks bitmap block */
__le32 bg_inode_bitmap_lo; /* Inodes bitmap block */
__le32 bg_inode_table_lo; /* Inodes table block */
__le16 bg_free_blocks_count_lo;/* Free blocks count */
__le16 bg_free_inodes_count_lo;/* Free inodes count */
__le16 bg_used_dirs_count_lo; /* Directories count */
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>
2007-10-16 22:38:25 +00:00
__le16 bg_flags; /* EXT4_BG_flags (INODE_UNINIT, etc) */
__le32 bg_exclude_bitmap_lo; /* Exclude bitmap for snapshots */
__le16 bg_block_bitmap_csum_lo;/* crc32c(s_uuid+grp_num+bbitmap) LE */
__le16 bg_inode_bitmap_csum_lo;/* crc32c(s_uuid+grp_num+ibitmap) LE */
__le16 bg_itable_unused_lo; /* Unused inodes count */
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>
2007-10-16 22:38:25 +00:00
__le16 bg_checksum; /* crc16(sb_uuid+group+desc) */
__le32 bg_block_bitmap_hi; /* Blocks bitmap block MSB */
__le32 bg_inode_bitmap_hi; /* Inodes bitmap block MSB */
__le32 bg_inode_table_hi; /* Inodes table block MSB */
__le16 bg_free_blocks_count_hi;/* Free blocks count MSB */
__le16 bg_free_inodes_count_hi;/* Free inodes count MSB */
__le16 bg_used_dirs_count_hi; /* Directories count MSB */
__le16 bg_itable_unused_hi; /* Unused inodes count MSB */
__le32 bg_exclude_bitmap_hi; /* Exclude bitmap block MSB */
__le16 bg_block_bitmap_csum_hi;/* crc32c(s_uuid+grp_num+bbitmap) BE */
__le16 bg_inode_bitmap_csum_hi;/* crc32c(s_uuid+grp_num+ibitmap) BE */
__u32 bg_reserved;
};
#define EXT4_BG_INODE_BITMAP_CSUM_HI_END \
(offsetof(struct ext4_group_desc, bg_inode_bitmap_csum_hi) + \
sizeof(__le16))
#define EXT4_BG_BLOCK_BITMAP_CSUM_HI_END \
(offsetof(struct ext4_group_desc, bg_block_bitmap_csum_hi) + \
sizeof(__le16))
/*
* Structure of a flex block group info
*/
struct flex_groups {
atomic_t free_inodes;
atomic_t free_clusters;
atomic_t used_dirs;
};
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>
2007-10-16 22:38:25 +00:00
#define EXT4_BG_INODE_UNINIT 0x0001 /* Inode table/bitmap not in use */
#define EXT4_BG_BLOCK_UNINIT 0x0002 /* Block bitmap not in use */
#define EXT4_BG_INODE_ZEROED 0x0004 /* On-disk itable initialized to zero */
/*
* Macro-instructions used to manage group descriptors
*/
#define EXT4_MIN_DESC_SIZE 32
#define EXT4_MIN_DESC_SIZE_64BIT 64
#define EXT4_MAX_DESC_SIZE EXT4_MIN_BLOCK_SIZE
#define EXT4_DESC_SIZE(s) (EXT4_SB(s)->s_desc_size)
#ifdef __KERNEL__
# define EXT4_BLOCKS_PER_GROUP(s) (EXT4_SB(s)->s_blocks_per_group)
# define EXT4_CLUSTERS_PER_GROUP(s) (EXT4_SB(s)->s_clusters_per_group)
# define EXT4_DESC_PER_BLOCK(s) (EXT4_SB(s)->s_desc_per_block)
# define EXT4_INODES_PER_GROUP(s) (EXT4_SB(s)->s_inodes_per_group)
# define EXT4_DESC_PER_BLOCK_BITS(s) (EXT4_SB(s)->s_desc_per_block_bits)
#else
# define EXT4_BLOCKS_PER_GROUP(s) ((s)->s_blocks_per_group)
# define EXT4_DESC_PER_BLOCK(s) (EXT4_BLOCK_SIZE(s) / EXT4_DESC_SIZE(s))
# define EXT4_INODES_PER_GROUP(s) ((s)->s_inodes_per_group)
#endif
/*
* Constants relative to the data blocks
*/
#define EXT4_NDIR_BLOCKS 12
#define EXT4_IND_BLOCK EXT4_NDIR_BLOCKS
#define EXT4_DIND_BLOCK (EXT4_IND_BLOCK + 1)
#define EXT4_TIND_BLOCK (EXT4_DIND_BLOCK + 1)
#define EXT4_N_BLOCKS (EXT4_TIND_BLOCK + 1)
/*
* Inode flags
*/
#define EXT4_SECRM_FL 0x00000001 /* Secure deletion */
#define EXT4_UNRM_FL 0x00000002 /* Undelete */
#define EXT4_COMPR_FL 0x00000004 /* Compress file */
#define EXT4_SYNC_FL 0x00000008 /* Synchronous updates */
#define EXT4_IMMUTABLE_FL 0x00000010 /* Immutable file */
#define EXT4_APPEND_FL 0x00000020 /* writes to file may only append */
#define EXT4_NODUMP_FL 0x00000040 /* do not dump file */
#define EXT4_NOATIME_FL 0x00000080 /* do not update atime */
/* Reserved for compression usage... */
#define EXT4_DIRTY_FL 0x00000100
#define EXT4_COMPRBLK_FL 0x00000200 /* One or more compressed clusters */
#define EXT4_NOCOMPR_FL 0x00000400 /* Don't compress */
#define EXT4_ECOMPR_FL 0x00000800 /* Compression error */
/* End compression flags --- maybe not all used */
#define EXT4_INDEX_FL 0x00001000 /* hash-indexed directory */
#define EXT4_IMAGIC_FL 0x00002000 /* AFS directory */
#define EXT4_JOURNAL_DATA_FL 0x00004000 /* file data should be journaled */
#define EXT4_NOTAIL_FL 0x00008000 /* file tail should not be merged */
#define EXT4_DIRSYNC_FL 0x00010000 /* dirsync behaviour (directories only) */
#define EXT4_TOPDIR_FL 0x00020000 /* Top of directory hierarchies*/
#define EXT4_HUGE_FILE_FL 0x00040000 /* Set to each huge file */
#define EXT4_EXTENTS_FL 0x00080000 /* Inode uses extents */
#define EXT4_EA_INODE_FL 0x00200000 /* Inode used for large EA */
#define EXT4_EOFBLOCKS_FL 0x00400000 /* Blocks allocated beyond EOF */
#define EXT4_RESERVED_FL 0x80000000 /* reserved for ext4 lib */
#define EXT4_FL_USER_VISIBLE 0x004BDFFF /* User visible flags */
#define EXT4_FL_USER_MODIFIABLE 0x004B80FF /* User modifiable flags */
/* Flags that should be inherited by new inodes from their parent. */
#define EXT4_FL_INHERITED (EXT4_SECRM_FL | EXT4_UNRM_FL | EXT4_COMPR_FL |\
EXT4_SYNC_FL | EXT4_NODUMP_FL | EXT4_NOATIME_FL |\
EXT4_NOCOMPR_FL | EXT4_JOURNAL_DATA_FL |\
EXT4_NOTAIL_FL | EXT4_DIRSYNC_FL)
/* Flags that are appropriate for regular files (all but dir-specific ones). */
#define EXT4_REG_FLMASK (~(EXT4_DIRSYNC_FL | EXT4_TOPDIR_FL))
/* Flags that are appropriate for non-directories/regular files. */
#define EXT4_OTHER_FLMASK (EXT4_NODUMP_FL | EXT4_NOATIME_FL)
/* Mask out flags that are inappropriate for the given type of inode. */
static inline __u32 ext4_mask_flags(umode_t mode, __u32 flags)
{
if (S_ISDIR(mode))
return flags;
else if (S_ISREG(mode))
return flags & EXT4_REG_FLMASK;
else
return flags & EXT4_OTHER_FLMASK;
}
/*
* Inode flags used for atomic set/get
*/
enum {
EXT4_INODE_SECRM = 0, /* Secure deletion */
EXT4_INODE_UNRM = 1, /* Undelete */
EXT4_INODE_COMPR = 2, /* Compress file */
EXT4_INODE_SYNC = 3, /* Synchronous updates */
EXT4_INODE_IMMUTABLE = 4, /* Immutable file */
EXT4_INODE_APPEND = 5, /* writes to file may only append */
EXT4_INODE_NODUMP = 6, /* do not dump file */
EXT4_INODE_NOATIME = 7, /* do not update atime */
/* Reserved for compression usage... */
EXT4_INODE_DIRTY = 8,
EXT4_INODE_COMPRBLK = 9, /* One or more compressed clusters */
EXT4_INODE_NOCOMPR = 10, /* Don't compress */
EXT4_INODE_ECOMPR = 11, /* Compression error */
/* End compression flags --- maybe not all used */
EXT4_INODE_INDEX = 12, /* hash-indexed directory */
EXT4_INODE_IMAGIC = 13, /* AFS directory */
EXT4_INODE_JOURNAL_DATA = 14, /* file data should be journaled */
EXT4_INODE_NOTAIL = 15, /* file tail should not be merged */
EXT4_INODE_DIRSYNC = 16, /* dirsync behaviour (directories only) */
EXT4_INODE_TOPDIR = 17, /* Top of directory hierarchies*/
EXT4_INODE_HUGE_FILE = 18, /* Set to each huge file */
EXT4_INODE_EXTENTS = 19, /* Inode uses extents */
EXT4_INODE_EA_INODE = 21, /* Inode used for large EA */
EXT4_INODE_EOFBLOCKS = 22, /* Blocks allocated beyond EOF */
EXT4_INODE_RESERVED = 31, /* reserved for ext4 lib */
};
#define TEST_FLAG_VALUE(FLAG) (EXT4_##FLAG##_FL == (1 << EXT4_INODE_##FLAG))
#define CHECK_FLAG_VALUE(FLAG) if (!TEST_FLAG_VALUE(FLAG)) { \
printk(KERN_EMERG "EXT4 flag fail: " #FLAG ": %d %d\n", \
EXT4_##FLAG##_FL, EXT4_INODE_##FLAG); BUG_ON(1); }
/*
* Since it's pretty easy to mix up bit numbers and hex values, and we
* can't do a compile-time test for ENUM values, we use a run-time
* test to make sure that EXT4_XXX_FL is consistent with respect to
* EXT4_INODE_XXX. If all is well the printk and BUG_ON will all drop
* out so it won't cost any extra space in the compiled kernel image.
* But it's important that these values are the same, since we are
* using EXT4_INODE_XXX to test for the flag values, but EXT4_XX_FL
* must be consistent with the values of FS_XXX_FL defined in
* include/linux/fs.h and the on-disk values found in ext2, ext3, and
* ext4 filesystems, and of course the values defined in e2fsprogs.
*
* It's not paranoia if the Murphy's Law really *is* out to get you. :-)
*/
static inline void ext4_check_flag_values(void)
{
CHECK_FLAG_VALUE(SECRM);
CHECK_FLAG_VALUE(UNRM);
CHECK_FLAG_VALUE(COMPR);
CHECK_FLAG_VALUE(SYNC);
CHECK_FLAG_VALUE(IMMUTABLE);
CHECK_FLAG_VALUE(APPEND);
CHECK_FLAG_VALUE(NODUMP);
CHECK_FLAG_VALUE(NOATIME);
CHECK_FLAG_VALUE(DIRTY);
CHECK_FLAG_VALUE(COMPRBLK);
CHECK_FLAG_VALUE(NOCOMPR);
CHECK_FLAG_VALUE(ECOMPR);
CHECK_FLAG_VALUE(INDEX);
CHECK_FLAG_VALUE(IMAGIC);
CHECK_FLAG_VALUE(JOURNAL_DATA);
CHECK_FLAG_VALUE(NOTAIL);
CHECK_FLAG_VALUE(DIRSYNC);
CHECK_FLAG_VALUE(TOPDIR);
CHECK_FLAG_VALUE(HUGE_FILE);
CHECK_FLAG_VALUE(EXTENTS);
CHECK_FLAG_VALUE(EA_INODE);
CHECK_FLAG_VALUE(EOFBLOCKS);
CHECK_FLAG_VALUE(RESERVED);
}
/* Used to pass group descriptor data when online resize is done */
struct ext4_new_group_input {
__u32 group; /* Group number for this data */
__u64 block_bitmap; /* Absolute block number of block bitmap */
__u64 inode_bitmap; /* Absolute block number of inode bitmap */
__u64 inode_table; /* Absolute block number of inode table start */
__u32 blocks_count; /* Total number of blocks in this group */
__u16 reserved_blocks; /* Number of reserved blocks in this group */
__u16 unused;
};
#if defined(__KERNEL__) && defined(CONFIG_COMPAT)
struct compat_ext4_new_group_input {
u32 group;
compat_u64 block_bitmap;
compat_u64 inode_bitmap;
compat_u64 inode_table;
u32 blocks_count;
u16 reserved_blocks;
u16 unused;
};
#endif
/* The struct ext4_new_group_input in kernel space, with free_blocks_count */
struct ext4_new_group_data {
__u32 group;
__u64 block_bitmap;
__u64 inode_bitmap;
__u64 inode_table;
__u32 blocks_count;
__u16 reserved_blocks;
__u16 unused;
__u32 free_blocks_count;
};
/* Indexes used to index group tables in ext4_new_group_data */
enum {
BLOCK_BITMAP = 0, /* block bitmap */
INODE_BITMAP, /* inode bitmap */
INODE_TABLE, /* inode tables */
GROUP_TABLE_COUNT,
};
/*
* Flags used by ext4_map_blocks()
*/
/* Allocate any needed blocks and/or convert an unitialized
extent to be an initialized ext4 */
#define EXT4_GET_BLOCKS_CREATE 0x0001
/* Request the creation of an unitialized extent */
#define EXT4_GET_BLOCKS_UNINIT_EXT 0x0002
#define EXT4_GET_BLOCKS_CREATE_UNINIT_EXT (EXT4_GET_BLOCKS_UNINIT_EXT|\
EXT4_GET_BLOCKS_CREATE)
/* Caller is from the delayed allocation writeout path,
so set the magic i_delalloc_reserve_flag after taking the
inode allocation semaphore for */
#define EXT4_GET_BLOCKS_DELALLOC_RESERVE 0x0004
/* caller is from the direct IO path, request to creation of an
unitialized extents if not allocated, split the uninitialized
extent if blocks has been preallocated already*/
#define EXT4_GET_BLOCKS_PRE_IO 0x0008
#define EXT4_GET_BLOCKS_CONVERT 0x0010
#define EXT4_GET_BLOCKS_IO_CREATE_EXT (EXT4_GET_BLOCKS_PRE_IO|\
EXT4_GET_BLOCKS_CREATE_UNINIT_EXT)
/* Convert extent to initialized after IO complete */
#define EXT4_GET_BLOCKS_IO_CONVERT_EXT (EXT4_GET_BLOCKS_CONVERT|\
EXT4_GET_BLOCKS_CREATE_UNINIT_EXT)
/* Punch out blocks of an extent */
#define EXT4_GET_BLOCKS_PUNCH_OUT_EXT 0x0020
/* Don't normalize allocation size (used for fallocate) */
#define EXT4_GET_BLOCKS_NO_NORMALIZE 0x0040
/* Request will not result in inode size update (user for fallocate) */
#define EXT4_GET_BLOCKS_KEEP_SIZE 0x0080
/*
* Flags used by ext4_free_blocks
*/
#define EXT4_FREE_BLOCKS_METADATA 0x0001
#define EXT4_FREE_BLOCKS_FORGET 0x0002
#define EXT4_FREE_BLOCKS_VALIDATED 0x0004
#define EXT4_FREE_BLOCKS_NO_QUOT_UPDATE 0x0008
#define EXT4_FREE_BLOCKS_NOFREE_FIRST_CLUSTER 0x0010
#define EXT4_FREE_BLOCKS_NOFREE_LAST_CLUSTER 0x0020
ext4: Add new ext4_discard_partial_page_buffers routines This patch adds two new routines: ext4_discard_partial_page_buffers and ext4_discard_partial_page_buffers_no_lock. The ext4_discard_partial_page_buffers routine is a wrapper function to ext4_discard_partial_page_buffers_no_lock. The wrapper function locks the page and passes it to ext4_discard_partial_page_buffers_no_lock. Calling functions that already have the page locked can call ext4_discard_partial_page_buffers_no_lock directly. The ext4_discard_partial_page_buffers_no_lock function zeros a specified range in a page, and unmaps the corresponding buffer heads. Only block aligned regions of the page will have their buffer heads unmapped. Unblock aligned regions will be mapped if needed so that they can be updated with the partial zero out. This function is meant to be used to update a page and its buffer heads to be zeroed and unmapped when the corresponding blocks have been released or will be released. This routine is used in the following scenarios: * A hole is punched and the non page aligned regions of the head and tail of the hole need to be discarded * The file is truncated and the partial page beyond EOF needs to be discarded * The end of a hole is in the same page as EOF. After the page is flushed, the partial page beyond EOF needs to be discarded. * A write operation begins or ends inside a hole and the partial page appearing before or after the write needs to be discarded * A write operation extends EOF and the partial page beyond EOF needs to be discarded This function takes a flag EXT4_DISCARD_PARTIAL_PG_ZERO_UNMAPPED which is used when a write operation begins or ends in a hole. When the EXT4_DISCARD_PARTIAL_PG_ZERO_UNMAPPED flag is used, only buffer heads that are already unmapped will have the corresponding regions of the page zeroed. Signed-off-by: Allison Henderson <achender@linux.vnet.ibm.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2011-09-03 15:51:09 +00:00
/*
* Flags used by ext4_discard_partial_page_buffers
*/
#define EXT4_DISCARD_PARTIAL_PG_ZERO_UNMAPPED 0x0001
/*
* ioctl commands
*/
#define EXT4_IOC_GETFLAGS FS_IOC_GETFLAGS
#define EXT4_IOC_SETFLAGS FS_IOC_SETFLAGS
#define EXT4_IOC_GETVERSION _IOR('f', 3, long)
#define EXT4_IOC_SETVERSION _IOW('f', 4, long)
#define EXT4_IOC_GETVERSION_OLD FS_IOC_GETVERSION
#define EXT4_IOC_SETVERSION_OLD FS_IOC_SETVERSION
#define EXT4_IOC_GETRSVSZ _IOR('f', 5, long)
#define EXT4_IOC_SETRSVSZ _IOW('f', 6, long)
#define EXT4_IOC_GROUP_EXTEND _IOW('f', 7, unsigned long)
#define EXT4_IOC_GROUP_ADD _IOW('f', 8, struct ext4_new_group_input)
#define EXT4_IOC_MIGRATE _IO('f', 9)
/* note ioctl 10 reserved for an early version of the FIEMAP ioctl */
/* note ioctl 11 reserved for filesystem-independent FIEMAP ioctl */
#define EXT4_IOC_ALLOC_DA_BLKS _IO('f', 12)
#define EXT4_IOC_MOVE_EXT _IOWR('f', 15, struct move_extent)
#define EXT4_IOC_RESIZE_FS _IOW('f', 16, __u64)
#if defined(__KERNEL__) && defined(CONFIG_COMPAT)
/*
* ioctl commands in 32 bit emulation
*/
#define EXT4_IOC32_GETFLAGS FS_IOC32_GETFLAGS
#define EXT4_IOC32_SETFLAGS FS_IOC32_SETFLAGS
#define EXT4_IOC32_GETVERSION _IOR('f', 3, int)
#define EXT4_IOC32_SETVERSION _IOW('f', 4, int)
#define EXT4_IOC32_GETRSVSZ _IOR('f', 5, int)
#define EXT4_IOC32_SETRSVSZ _IOW('f', 6, int)
#define EXT4_IOC32_GROUP_EXTEND _IOW('f', 7, unsigned int)
#define EXT4_IOC32_GROUP_ADD _IOW('f', 8, struct compat_ext4_new_group_input)
#define EXT4_IOC32_GETVERSION_OLD FS_IOC32_GETVERSION
#define EXT4_IOC32_SETVERSION_OLD FS_IOC32_SETVERSION
#endif
/* Max physical block we can address w/o extents */
#define EXT4_MAX_BLOCK_FILE_PHYS 0xFFFFFFFF
/*
* Structure of an inode on the disk
*/
struct ext4_inode {
__le16 i_mode; /* File mode */
__le16 i_uid; /* Low 16 bits of Owner Uid */
__le32 i_size_lo; /* Size in bytes */
__le32 i_atime; /* Access time */
__le32 i_ctime; /* Inode Change time */
__le32 i_mtime; /* Modification time */
__le32 i_dtime; /* Deletion Time */
__le16 i_gid; /* Low 16 bits of Group Id */
__le16 i_links_count; /* Links count */
__le32 i_blocks_lo; /* Blocks count */
__le32 i_flags; /* File flags */
union {
struct {
__le32 l_i_version;
} linux1;
struct {
__u32 h_i_translator;
} hurd1;
struct {
__u32 m_i_reserved1;
} masix1;
} osd1; /* OS dependent 1 */
__le32 i_block[EXT4_N_BLOCKS];/* Pointers to blocks */
__le32 i_generation; /* File version (for NFS) */
__le32 i_file_acl_lo; /* File ACL */
__le32 i_size_high;
__le32 i_obso_faddr; /* Obsoleted fragment address */
union {
struct {
__le16 l_i_blocks_high; /* were l_i_reserved1 */
__le16 l_i_file_acl_high;
__le16 l_i_uid_high; /* these 2 fields */
__le16 l_i_gid_high; /* were reserved2[0] */
__le16 l_i_checksum_lo;/* crc32c(uuid+inum+inode) LE */
__le16 l_i_reserved;
} linux2;
struct {
__le16 h_i_reserved1; /* Obsoleted fragment number/size which are removed in ext4 */
__u16 h_i_mode_high;
__u16 h_i_uid_high;
__u16 h_i_gid_high;
__u32 h_i_author;
} hurd2;
struct {
__le16 h_i_reserved1; /* Obsoleted fragment number/size which are removed in ext4 */
__le16 m_i_file_acl_high;
__u32 m_i_reserved2[2];
} masix2;
} osd2; /* OS dependent 2 */
__le16 i_extra_isize;
__le16 i_checksum_hi; /* crc32c(uuid+inum+inode) BE */
__le32 i_ctime_extra; /* extra Change time (nsec << 2 | epoch) */
__le32 i_mtime_extra; /* extra Modification time(nsec << 2 | epoch) */
__le32 i_atime_extra; /* extra Access time (nsec << 2 | epoch) */
__le32 i_crtime; /* File Creation time */
__le32 i_crtime_extra; /* extra FileCreationtime (nsec << 2 | epoch) */
__le32 i_version_hi; /* high 32 bits for 64-bit version */
};
struct move_extent {
__u32 reserved; /* should be zero */
__u32 donor_fd; /* donor file descriptor */
__u64 orig_start; /* logical start offset in block for orig */
__u64 donor_start; /* logical start offset in block for donor */
__u64 len; /* block length to be moved */
__u64 moved_len; /* moved block length */
};
#define EXT4_EPOCH_BITS 2
#define EXT4_EPOCH_MASK ((1 << EXT4_EPOCH_BITS) - 1)
#define EXT4_NSEC_MASK (~0UL << EXT4_EPOCH_BITS)
/*
* Extended fields will fit into an inode if the filesystem was formatted
* with large inodes (-I 256 or larger) and there are not currently any EAs
* consuming all of the available space. For new inodes we always reserve
* enough space for the kernel's known extended fields, but for inodes
* created with an old kernel this might not have been the case. None of
* the extended inode fields is critical for correct filesystem operation.
* This macro checks if a certain field fits in the inode. Note that
* inode-size = GOOD_OLD_INODE_SIZE + i_extra_isize
*/
#define EXT4_FITS_IN_INODE(ext4_inode, einode, field) \
((offsetof(typeof(*ext4_inode), field) + \
sizeof((ext4_inode)->field)) \
<= (EXT4_GOOD_OLD_INODE_SIZE + \
(einode)->i_extra_isize)) \
static inline __le32 ext4_encode_extra_time(struct timespec *time)
{
return cpu_to_le32((sizeof(time->tv_sec) > 4 ?
(time->tv_sec >> 32) & EXT4_EPOCH_MASK : 0) |
((time->tv_nsec << EXT4_EPOCH_BITS) & EXT4_NSEC_MASK));
}
static inline void ext4_decode_extra_time(struct timespec *time, __le32 extra)
{
if (sizeof(time->tv_sec) > 4)
time->tv_sec |= (__u64)(le32_to_cpu(extra) & EXT4_EPOCH_MASK)
<< 32;
time->tv_nsec = (le32_to_cpu(extra) & EXT4_NSEC_MASK) >> EXT4_EPOCH_BITS;
}
#define EXT4_INODE_SET_XTIME(xtime, inode, raw_inode) \
do { \
(raw_inode)->xtime = cpu_to_le32((inode)->xtime.tv_sec); \
if (EXT4_FITS_IN_INODE(raw_inode, EXT4_I(inode), xtime ## _extra)) \
(raw_inode)->xtime ## _extra = \
ext4_encode_extra_time(&(inode)->xtime); \
} while (0)
#define EXT4_EINODE_SET_XTIME(xtime, einode, raw_inode) \
do { \
if (EXT4_FITS_IN_INODE(raw_inode, einode, xtime)) \
(raw_inode)->xtime = cpu_to_le32((einode)->xtime.tv_sec); \
if (EXT4_FITS_IN_INODE(raw_inode, einode, xtime ## _extra)) \
(raw_inode)->xtime ## _extra = \
ext4_encode_extra_time(&(einode)->xtime); \
} while (0)
#define EXT4_INODE_GET_XTIME(xtime, inode, raw_inode) \
do { \
(inode)->xtime.tv_sec = (signed)le32_to_cpu((raw_inode)->xtime); \
if (EXT4_FITS_IN_INODE(raw_inode, EXT4_I(inode), xtime ## _extra)) \
ext4_decode_extra_time(&(inode)->xtime, \
raw_inode->xtime ## _extra); \
else \
(inode)->xtime.tv_nsec = 0; \
} while (0)
#define EXT4_EINODE_GET_XTIME(xtime, einode, raw_inode) \
do { \
if (EXT4_FITS_IN_INODE(raw_inode, einode, xtime)) \
(einode)->xtime.tv_sec = \
(signed)le32_to_cpu((raw_inode)->xtime); \
if (EXT4_FITS_IN_INODE(raw_inode, einode, xtime ## _extra)) \
ext4_decode_extra_time(&(einode)->xtime, \
raw_inode->xtime ## _extra); \
else \
(einode)->xtime.tv_nsec = 0; \
} while (0)
#define i_disk_version osd1.linux1.l_i_version
#if defined(__KERNEL__) || defined(__linux__)
#define i_reserved1 osd1.linux1.l_i_reserved1
#define i_file_acl_high osd2.linux2.l_i_file_acl_high
#define i_blocks_high osd2.linux2.l_i_blocks_high
#define i_uid_low i_uid
#define i_gid_low i_gid
#define i_uid_high osd2.linux2.l_i_uid_high
#define i_gid_high osd2.linux2.l_i_gid_high
#define i_checksum_lo osd2.linux2.l_i_checksum_lo
#elif defined(__GNU__)
#define i_translator osd1.hurd1.h_i_translator
#define i_uid_high osd2.hurd2.h_i_uid_high
#define i_gid_high osd2.hurd2.h_i_gid_high
#define i_author osd2.hurd2.h_i_author
#elif defined(__masix__)
#define i_reserved1 osd1.masix1.m_i_reserved1
#define i_file_acl_high osd2.masix2.m_i_file_acl_high
#define i_reserved2 osd2.masix2.m_i_reserved2
#endif /* defined(__KERNEL__) || defined(__linux__) */
/*
* storage for cached extent
* If ec_len == 0, then the cache is invalid.
* If ec_start == 0, then the cache represents a gap (null mapping)
*/
struct ext4_ext_cache {
ext4_fsblk_t ec_start;
ext4_lblk_t ec_block;
__u32 ec_len; /* must be 32bit to return holes */
};
/*
* fourth extended file system inode data in memory
*/
struct ext4_inode_info {
__le32 i_data[15]; /* unconverted */
__u32 i_dtime;
ext4_fsblk_t i_file_acl;
/*
* i_block_group is the number of the block group which contains
* this file's inode. Constant across the lifetime of the inode,
* it is ued for making block allocation decisions - we try to
* place a file's data blocks near its inode block, and new inodes
* near to their parent directory's inode.
*/
ext4_group_t i_block_group;
ext4_lblk_t i_dir_start_lookup;
#if (BITS_PER_LONG < 64)
unsigned long i_state_flags; /* Dynamic state flags */
#endif
unsigned long i_flags;
#ifdef CONFIG_EXT4_FS_XATTR
/*
* Extended attributes can be read independently of the main file
* data. Taking i_mutex even when reading would cause contention
* between readers of EAs and writers of regular file data, so
* instead we synchronize on xattr_sem when reading or changing
* EAs.
*/
struct rw_semaphore xattr_sem;
#endif
struct list_head i_orphan; /* unlinked but open inodes */
/*
* i_disksize keeps track of what the inode size is ON DISK, not
* in memory. During truncate, i_size is set to the new size by
* the VFS prior to calling ext4_truncate(), but the filesystem won't
* set i_disksize to 0 until the truncate is actually under way.
*
* The intent is that i_disksize always represents the blocks which
* are used by this file. This allows recovery to restart truncate
* on orphans if we crash during truncate. We actually write i_disksize
* into the on-disk inode when writing inodes out, instead of i_size.
*
* The only time when i_disksize and i_size may be different is when
* a truncate is in progress. The only things which change i_disksize
* are ext4_get_block (growth) and ext4_truncate (shrinkth).
*/
loff_t i_disksize;
/*
* i_data_sem is for serialising ext4_truncate() against
* ext4_getblock(). In the 2.4 ext2 design, great chunks of inode's
* data tree are chopped off during truncate. We can't do that in
* ext4 because whenever we perform intermediate commits during
* truncate, the inode and all the metadata blocks *must* be in a
* consistent state which allows truncation of the orphans to restart
* during recovery. Hence we must fix the get_block-vs-truncate race
* by other means, so we have i_data_sem.
*/
struct rw_semaphore i_data_sem;
struct inode vfs_inode;
struct jbd2_inode *jinode;
struct ext4_ext_cache i_cached_extent;
/*
* File creation time. Its function is same as that of
* struct timespec i_{a,c,m}time in the generic inode.
*/
struct timespec i_crtime;
/* mballoc */
struct list_head i_prealloc_list;
spinlock_t i_prealloc_lock;
/* ialloc */
ext4_group_t i_last_alloc_group;
/* allocation reservation info for delalloc */
/* In case of bigalloc, these refer to clusters rather than blocks */
unsigned int i_reserved_data_blocks;
unsigned int i_reserved_meta_blocks;
unsigned int i_allocated_meta_blocks;
ext4_lblk_t i_da_metadata_calc_last_lblock;
int i_da_metadata_calc_len;
/* on-disk additional length */
__u16 i_extra_isize;
#ifdef CONFIG_QUOTA
/* quota space reservation, managed internally by quota code */
qsize_t i_reserved_quota;
#endif
/* completed IOs that might need unwritten extents handling */
struct list_head i_completed_io_list;
spinlock_t i_completed_io_lock;
atomic_t i_ioend_count; /* Number of outstanding io_end structs */
/* current io_end structure for async DIO write*/
ext4_io_end_t *cur_aio_dio;
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 13:17:34 +00:00
atomic_t i_aiodio_unwritten; /* Nr. of inflight conversions pending */
spinlock_t i_block_reservation_lock;
/*
* Transactions that contain inode's metadata needed to complete
* fsync and fdatasync, respectively.
*/
tid_t i_sync_tid;
tid_t i_datasync_tid;
/* Precomputed uuid+inum+igen checksum for seeding inode checksums */
__u32 i_csum_seed;
};
/*
* File system states
*/
#define EXT4_VALID_FS 0x0001 /* Unmounted cleanly */
#define EXT4_ERROR_FS 0x0002 /* Errors detected */
#define EXT4_ORPHAN_FS 0x0004 /* Orphans being recovered */
/*
* Misc. filesystem flags
*/
#define EXT2_FLAGS_SIGNED_HASH 0x0001 /* Signed dirhash in use */
#define EXT2_FLAGS_UNSIGNED_HASH 0x0002 /* Unsigned dirhash in use */
#define EXT2_FLAGS_TEST_FILESYS 0x0004 /* to test development code */
/*
* Mount flags
*/
#define EXT4_MOUNT_GRPID 0x00004 /* Create files with directory's group */
#define EXT4_MOUNT_DEBUG 0x00008 /* Some debugging messages */
#define EXT4_MOUNT_ERRORS_CONT 0x00010 /* Continue on errors */
#define EXT4_MOUNT_ERRORS_RO 0x00020 /* Remount fs ro on errors */
#define EXT4_MOUNT_ERRORS_PANIC 0x00040 /* Panic on errors */
#define EXT4_MOUNT_ERRORS_MASK 0x00070
#define EXT4_MOUNT_MINIX_DF 0x00080 /* Mimics the Minix statfs */
#define EXT4_MOUNT_NOLOAD 0x00100 /* Don't use existing journal*/
#define EXT4_MOUNT_DATA_FLAGS 0x00C00 /* Mode for data writes: */
#define EXT4_MOUNT_JOURNAL_DATA 0x00400 /* Write data to journal */
#define EXT4_MOUNT_ORDERED_DATA 0x00800 /* Flush data before commit */
#define EXT4_MOUNT_WRITEBACK_DATA 0x00C00 /* No data ordering */
#define EXT4_MOUNT_UPDATE_JOURNAL 0x01000 /* Update the journal format */
#define EXT4_MOUNT_NO_UID32 0x02000 /* Disable 32-bit UIDs */
#define EXT4_MOUNT_XATTR_USER 0x04000 /* Extended user attributes */
#define EXT4_MOUNT_POSIX_ACL 0x08000 /* POSIX Access Control Lists */
#define EXT4_MOUNT_NO_AUTO_DA_ALLOC 0x10000 /* No auto delalloc mapping */
#define EXT4_MOUNT_BARRIER 0x20000 /* Use block barriers */
#define EXT4_MOUNT_QUOTA 0x80000 /* Some quota option set */
#define EXT4_MOUNT_USRQUOTA 0x100000 /* "old" user quota */
#define EXT4_MOUNT_GRPQUOTA 0x200000 /* "old" group quota */
#define EXT4_MOUNT_DIOREAD_NOLOCK 0x400000 /* Enable support for dio read nolocking */
#define EXT4_MOUNT_JOURNAL_CHECKSUM 0x800000 /* Journal checksums */
#define EXT4_MOUNT_JOURNAL_ASYNC_COMMIT 0x1000000 /* Journal Async Commit */
#define EXT4_MOUNT_MBLK_IO_SUBMIT 0x4000000 /* multi-block io submits */
#define EXT4_MOUNT_DELALLOC 0x8000000 /* Delalloc support */
#define EXT4_MOUNT_DATA_ERR_ABORT 0x10000000 /* Abort on file data write */
#define EXT4_MOUNT_BLOCK_VALIDITY 0x20000000 /* Block validity checking */
#define EXT4_MOUNT_DISCARD 0x40000000 /* Issue DISCARD requests */
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 01:30:05 +00:00
#define EXT4_MOUNT_INIT_INODE_TABLE 0x80000000 /* Initialize uninitialized itables */
#define EXT4_MOUNT2_EXPLICIT_DELALLOC 0x00000001 /* User explicitly
specified delalloc */
#define clear_opt(sb, opt) EXT4_SB(sb)->s_mount_opt &= \
~EXT4_MOUNT_##opt
#define set_opt(sb, opt) EXT4_SB(sb)->s_mount_opt |= \
EXT4_MOUNT_##opt
#define test_opt(sb, opt) (EXT4_SB(sb)->s_mount_opt & \
EXT4_MOUNT_##opt)
#define clear_opt2(sb, opt) EXT4_SB(sb)->s_mount_opt2 &= \
~EXT4_MOUNT2_##opt
#define set_opt2(sb, opt) EXT4_SB(sb)->s_mount_opt2 |= \
EXT4_MOUNT2_##opt
#define test_opt2(sb, opt) (EXT4_SB(sb)->s_mount_opt2 & \
EXT4_MOUNT2_##opt)
#define ext4_test_and_set_bit __test_and_set_bit_le
#define ext4_set_bit __set_bit_le
#define ext4_set_bit_atomic ext2_set_bit_atomic
#define ext4_test_and_clear_bit __test_and_clear_bit_le
#define ext4_clear_bit __clear_bit_le
#define ext4_clear_bit_atomic ext2_clear_bit_atomic
#define ext4_test_bit test_bit_le
#define ext4_find_next_zero_bit find_next_zero_bit_le
#define ext4_find_next_bit find_next_bit_le
extern void ext4_set_bits(void *bm, int cur, int len);
/*
* Maximal mount counts between two filesystem checks
*/
#define EXT4_DFL_MAX_MNT_COUNT 20 /* Allow 20 mounts */
#define EXT4_DFL_CHECKINTERVAL 0 /* Don't use interval check */
/*
* Behaviour when detecting errors
*/
#define EXT4_ERRORS_CONTINUE 1 /* Continue execution */
#define EXT4_ERRORS_RO 2 /* Remount fs read-only */
#define EXT4_ERRORS_PANIC 3 /* Panic */
#define EXT4_ERRORS_DEFAULT EXT4_ERRORS_CONTINUE
/* Metadata checksum algorithm codes */
#define EXT4_CRC32C_CHKSUM 1
/*
* Structure of the super block
*/
struct ext4_super_block {
/*00*/ __le32 s_inodes_count; /* Inodes count */
__le32 s_blocks_count_lo; /* Blocks count */
__le32 s_r_blocks_count_lo; /* Reserved blocks count */
__le32 s_free_blocks_count_lo; /* Free blocks count */
/*10*/ __le32 s_free_inodes_count; /* Free inodes count */
__le32 s_first_data_block; /* First Data Block */
__le32 s_log_block_size; /* Block size */
__le32 s_log_cluster_size; /* Allocation cluster size */
/*20*/ __le32 s_blocks_per_group; /* # Blocks per group */
__le32 s_clusters_per_group; /* # Clusters per group */
__le32 s_inodes_per_group; /* # Inodes per group */
__le32 s_mtime; /* Mount time */
/*30*/ __le32 s_wtime; /* Write time */
__le16 s_mnt_count; /* Mount count */
__le16 s_max_mnt_count; /* Maximal mount count */
__le16 s_magic; /* Magic signature */
__le16 s_state; /* File system state */
__le16 s_errors; /* Behaviour when detecting errors */
__le16 s_minor_rev_level; /* minor revision level */
/*40*/ __le32 s_lastcheck; /* time of last check */
__le32 s_checkinterval; /* max. time between checks */
__le32 s_creator_os; /* OS */
__le32 s_rev_level; /* Revision level */
/*50*/ __le16 s_def_resuid; /* Default uid for reserved blocks */
__le16 s_def_resgid; /* Default gid for reserved blocks */
/*
* These fields are for EXT4_DYNAMIC_REV superblocks only.
*
* Note: the difference between the compatible feature set and
* the incompatible feature set is that if there is a bit set
* in the incompatible feature set that the kernel doesn't
* know about, it should refuse to mount the filesystem.
*
* e2fsck's requirements are more strict; if it doesn't know
* about a feature in either the compatible or incompatible
* feature set, it must abort and not try to meddle with
* things it doesn't understand...
*/
__le32 s_first_ino; /* First non-reserved inode */
__le16 s_inode_size; /* size of inode structure */
__le16 s_block_group_nr; /* block group # of this superblock */
__le32 s_feature_compat; /* compatible feature set */
/*60*/ __le32 s_feature_incompat; /* incompatible feature set */
__le32 s_feature_ro_compat; /* readonly-compatible feature set */
/*68*/ __u8 s_uuid[16]; /* 128-bit uuid for volume */
/*78*/ char s_volume_name[16]; /* volume name */
/*88*/ char s_last_mounted[64]; /* directory where last mounted */
/*C8*/ __le32 s_algorithm_usage_bitmap; /* For compression */
/*
* Performance hints. Directory preallocation should only
* happen if the EXT4_FEATURE_COMPAT_DIR_PREALLOC flag is on.
*/
__u8 s_prealloc_blocks; /* Nr of blocks to try to preallocate*/
__u8 s_prealloc_dir_blocks; /* Nr to preallocate for dirs */
__le16 s_reserved_gdt_blocks; /* Per group desc for online growth */
/*
* Journaling support valid if EXT4_FEATURE_COMPAT_HAS_JOURNAL set.
*/
/*D0*/ __u8 s_journal_uuid[16]; /* uuid of journal superblock */
/*E0*/ __le32 s_journal_inum; /* inode number of journal file */
__le32 s_journal_dev; /* device number of journal file */
__le32 s_last_orphan; /* start of list of inodes to delete */
__le32 s_hash_seed[4]; /* HTREE hash seed */
__u8 s_def_hash_version; /* Default hash version to use */
__u8 s_jnl_backup_type;
__le16 s_desc_size; /* size of group descriptor */
/*100*/ __le32 s_default_mount_opts;
__le32 s_first_meta_bg; /* First metablock block group */
__le32 s_mkfs_time; /* When the filesystem was created */
__le32 s_jnl_blocks[17]; /* Backup of the journal inode */
/* 64bit support valid if EXT4_FEATURE_COMPAT_64BIT */
/*150*/ __le32 s_blocks_count_hi; /* Blocks count */
__le32 s_r_blocks_count_hi; /* Reserved blocks count */
__le32 s_free_blocks_count_hi; /* Free blocks count */
__le16 s_min_extra_isize; /* All inodes have at least # bytes */
__le16 s_want_extra_isize; /* New inodes should reserve # bytes */
__le32 s_flags; /* Miscellaneous flags */
__le16 s_raid_stride; /* RAID stride */
__le16 s_mmp_update_interval; /* # seconds to wait in MMP checking */
__le64 s_mmp_block; /* Block for multi-mount protection */
__le32 s_raid_stripe_width; /* blocks on all data disks (N*stride)*/
__u8 s_log_groups_per_flex; /* FLEX_BG group size */
__u8 s_checksum_type; /* metadata checksum algorithm used */
__le16 s_reserved_pad;
__le64 s_kbytes_written; /* nr of lifetime kilobytes written */
__le32 s_snapshot_inum; /* Inode number of active snapshot */
__le32 s_snapshot_id; /* sequential ID of active snapshot */
__le64 s_snapshot_r_blocks_count; /* reserved blocks for active
snapshot's future use */
__le32 s_snapshot_list; /* inode number of the head of the
on-disk snapshot list */
#define EXT4_S_ERR_START offsetof(struct ext4_super_block, s_error_count)
__le32 s_error_count; /* number of fs errors */
__le32 s_first_error_time; /* first time an error happened */
__le32 s_first_error_ino; /* inode involved in first error */
__le64 s_first_error_block; /* block involved of first error */
__u8 s_first_error_func[32]; /* function where the error happened */
__le32 s_first_error_line; /* line number where error happened */
__le32 s_last_error_time; /* most recent time of an error */
__le32 s_last_error_ino; /* inode involved in last error */
__le32 s_last_error_line; /* line number where error happened */
__le64 s_last_error_block; /* block involved of last error */
__u8 s_last_error_func[32]; /* function where the error happened */
#define EXT4_S_ERR_END offsetof(struct ext4_super_block, s_mount_opts)
__u8 s_mount_opts[64];
__le32 s_usr_quota_inum; /* inode for tracking user quota */
__le32 s_grp_quota_inum; /* inode for tracking group quota */
__le32 s_overhead_clusters; /* overhead blocks/clusters in fs */
__le32 s_reserved[108]; /* Padding to the end of the block */
__le32 s_checksum; /* crc32c(superblock) */
};
#define EXT4_S_ERR_LEN (EXT4_S_ERR_END - EXT4_S_ERR_START)
#ifdef __KERNEL__
/*
* run-time mount flags
*/
#define EXT4_MF_MNTDIR_SAMPLED 0x0001
#define EXT4_MF_FS_ABORTED 0x0002 /* Fatal error detected */
/*
* fourth extended-fs super-block data in memory
*/
struct ext4_sb_info {
unsigned long s_desc_size; /* Size of a group descriptor in bytes */
unsigned long s_inodes_per_block;/* Number of inodes per block */
unsigned long s_blocks_per_group;/* Number of blocks in a group */
unsigned long s_clusters_per_group; /* Number of clusters in a group */
unsigned long s_inodes_per_group;/* Number of inodes in a group */
unsigned long s_itb_per_group; /* Number of inode table blocks per group */
unsigned long s_gdb_count; /* Number of group descriptor blocks */
unsigned long s_desc_per_block; /* Number of group descriptors per block */
ext4_group_t s_groups_count; /* Number of groups in the fs */
ext4_group_t s_blockfile_groups;/* Groups acceptable for non-extent files */
unsigned long s_overhead_last; /* Last calculated overhead */
unsigned long s_blocks_last; /* Last seen block count */
unsigned int s_cluster_ratio; /* Number of blocks per cluster */
unsigned int s_cluster_bits; /* log2 of s_cluster_ratio */
loff_t s_bitmap_maxbytes; /* max bytes for bitmap files */
struct buffer_head * s_sbh; /* Buffer containing the super block */
struct ext4_super_block *s_es; /* Pointer to the super block in the buffer */
struct buffer_head **s_group_desc;
unsigned int s_mount_opt;
unsigned int s_mount_opt2;
unsigned int s_mount_flags;
unsigned int s_def_mount_opt;
ext4_fsblk_t s_sb_block;
kuid_t s_resuid;
kgid_t s_resgid;
unsigned short s_mount_state;
unsigned short s_pad;
int s_addr_per_block_bits;
int s_desc_per_block_bits;
int s_inode_size;
int s_first_ino;
unsigned int s_inode_readahead_blks;
unsigned int s_inode_goal;
spinlock_t s_next_gen_lock;
u32 s_next_generation;
u32 s_hash_seed[4];
int s_def_hash_version;
int s_hash_unsigned; /* 3 if hash should be signed, 0 if not */
struct percpu_counter s_freeclusters_counter;
struct percpu_counter s_freeinodes_counter;
struct percpu_counter s_dirs_counter;
struct percpu_counter s_dirtyclusters_counter;
struct blockgroup_lock *s_blockgroup_lock;
struct proc_dir_entry *s_proc;
struct kobject s_kobj;
struct completion s_kobj_unregister;
struct super_block *s_sb;
/* Journaling */
struct journal_s *s_journal;
struct list_head s_orphan;
struct mutex s_orphan_lock;
unsigned long s_resize_flags; /* Flags indicating if there
is a resizer */
unsigned long s_commit_interval;
u32 s_max_batch_time;
u32 s_min_batch_time;
struct block_device *journal_bdev;
#ifdef CONFIG_QUOTA
char *s_qf_names[MAXQUOTAS]; /* Names of quota files with journalled quota */
int s_jquota_fmt; /* Format of quota to use */
#endif
unsigned int s_want_extra_isize; /* New inodes should reserve # bytes */
struct rb_root system_blks;
#ifdef EXTENTS_STATS
/* ext4 extents stats */
unsigned long s_ext_min;
unsigned long s_ext_max;
unsigned long s_depth_max;
spinlock_t s_ext_stats_lock;
unsigned long s_ext_blocks;
unsigned long s_ext_extents;
#endif
/* for buddy allocator */
struct ext4_group_info ***s_group_info;
struct inode *s_buddy_cache;
spinlock_t s_md_lock;
unsigned short *s_mb_offsets;
unsigned int *s_mb_maxs;
/* tunables */
unsigned long s_stripe;
unsigned int s_mb_stream_request;
unsigned int s_mb_max_to_scan;
unsigned int s_mb_min_to_scan;
unsigned int s_mb_stats;
unsigned int s_mb_order2_reqs;
unsigned int s_mb_group_prealloc;
unsigned int s_max_writeback_mb_bump;
/* where last allocation was done - for stream allocation */
unsigned long s_mb_last_group;
unsigned long s_mb_last_start;
/* stats for buddy allocator */
atomic_t s_bal_reqs; /* number of reqs with len > 1 */
atomic_t s_bal_success; /* we found long enough chunks */
atomic_t s_bal_allocated; /* in blocks */
atomic_t s_bal_ex_scanned; /* total extents scanned */
atomic_t s_bal_goals; /* goal hits */
atomic_t s_bal_breaks; /* too long searches */
atomic_t s_bal_2orders; /* 2^order hits */
spinlock_t s_bal_lock;
unsigned long s_mb_buddies_generated;
unsigned long long s_mb_generation_time;
atomic_t s_mb_lost_chunks;
atomic_t s_mb_preallocated;
atomic_t s_mb_discarded;
atomic_t s_lock_busy;
/* locality groups */
struct ext4_locality_group __percpu *s_locality_groups;
/* for write statistics */
unsigned long s_sectors_written_start;
u64 s_kbytes_written;
unsigned int s_log_groups_per_flex;
struct flex_groups *s_flex_groups;
/* workqueue for dio unwritten */
struct workqueue_struct *dio_unwritten_wq;
/* timer for periodic error stats printing */
struct timer_list s_err_report;
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 01:30:05 +00:00
/* Lazy inode table initialization info */
struct ext4_li_request *s_li_request;
/* Wait multiplier for lazy initialization thread */
unsigned int s_li_wait_mult;
/* Kernel thread for multiple mount protection */
struct task_struct *s_mmp_tsk;
ext4: Speed up FITRIM by recording flags in ext4_group_info In ext4, when FITRIM is called every time, we iterate all the groups and do trim one by one. It is a bit time wasting if the group has been trimmed and there is no change since the last trim. So this patch adds a new flag in ext4_group_info->bb_state to indicate that the group has been trimmed, and it will be cleared if some blocks is freed(in release_blocks_on_commit). Another trim_minlen is added in ext4_sb_info to record the last minlen we use to trim the volume, so that if the caller provide a small one, we will go on the trim regardless of the bb_state. A simple test with my intel x25m ssd: df -h shows: /dev/sdb1 40G 21G 17G 56% /mnt/ext4 Block size: 4096 run the FITRIM with the following parameter: range.start = 0; range.len = UINT64_MAX; range.minlen = 1048576; without the patch: [root@boyu-tm linux-2.6]# time ./ftrim /mnt/ext4/a real 0m5.505s user 0m0.000s sys 0m1.224s [root@boyu-tm linux-2.6]# time ./ftrim /mnt/ext4/a real 0m5.359s user 0m0.000s sys 0m1.178s [root@boyu-tm linux-2.6]# time ./ftrim /mnt/ext4/a real 0m5.228s user 0m0.000s sys 0m1.151s with the patch: [root@boyu-tm linux-2.6]# time ./ftrim /mnt/ext4/a real 0m5.625s user 0m0.000s sys 0m1.269s [root@boyu-tm linux-2.6]# time ./ftrim /mnt/ext4/a real 0m0.002s user 0m0.000s sys 0m0.001s [root@boyu-tm linux-2.6]# time ./ftrim /mnt/ext4/a real 0m0.002s user 0m0.000s sys 0m0.001s A big improvement for the 2nd and 3rd run. Even after I delete some big image files, it is still much faster than iterating the whole disk. [root@boyu-tm test]# time ./ftrim /mnt/ext4/a real 0m1.217s user 0m0.000s sys 0m0.196s Cc: Lukas Czerner <lczerner@redhat.com> Reviewed-by: Andreas Dilger <adilger.kernel@dilger.ca> Signed-off-by: Tao Ma <boyu.mt@taobao.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2011-07-11 04:03:38 +00:00
/* record the last minlen when FITRIM is called. */
atomic_t s_last_trim_minblks;
/* Reference to checksum algorithm driver via cryptoapi */
struct crypto_shash *s_chksum_driver;
/* Precomputed FS UUID checksum for seeding other checksums */
__u32 s_csum_seed;
};
static inline struct ext4_sb_info *EXT4_SB(struct super_block *sb)
{
return sb->s_fs_info;
}
static inline struct ext4_inode_info *EXT4_I(struct inode *inode)
{
return container_of(inode, struct ext4_inode_info, vfs_inode);
}
static inline struct timespec ext4_current_time(struct inode *inode)
{
return (inode->i_sb->s_time_gran < NSEC_PER_SEC) ?
current_fs_time(inode->i_sb) : CURRENT_TIME_SEC;
}
static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino)
{
return ino == EXT4_ROOT_INO ||
ino == EXT4_JOURNAL_INO ||
ino == EXT4_RESIZE_INO ||
(ino >= EXT4_FIRST_INO(sb) &&
ino <= le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count));
}
static inline void ext4_set_io_unwritten_flag(struct inode *inode,
struct ext4_io_end *io_end)
{
if (!(io_end->flag & EXT4_IO_END_UNWRITTEN)) {
io_end->flag |= EXT4_IO_END_UNWRITTEN;
atomic_inc(&EXT4_I(inode)->i_aiodio_unwritten);
}
}
/*
* Inode dynamic state flags
*/
enum {
EXT4_STATE_JDATA, /* journaled data exists */
EXT4_STATE_NEW, /* inode is newly created */
EXT4_STATE_XATTR, /* has in-inode xattrs */
EXT4_STATE_NO_EXPAND, /* No space for expansion */
EXT4_STATE_DA_ALLOC_CLOSE, /* Alloc DA blks on close */
EXT4_STATE_EXT_MIGRATE, /* Inode is migrating */
EXT4_STATE_DIO_UNWRITTEN, /* need convert on dio done*/
EXT4_STATE_NEWENTRY, /* File just added to dir */
EXT4_STATE_DELALLOC_RESERVED, /* blks already reserved for delalloc */
};
#define EXT4_INODE_BIT_FNS(name, field, offset) \
static inline int ext4_test_inode_##name(struct inode *inode, int bit) \
{ \
return test_bit(bit + (offset), &EXT4_I(inode)->i_##field); \
} \
static inline void ext4_set_inode_##name(struct inode *inode, int bit) \
{ \
set_bit(bit + (offset), &EXT4_I(inode)->i_##field); \
} \
static inline void ext4_clear_inode_##name(struct inode *inode, int bit) \
{ \
clear_bit(bit + (offset), &EXT4_I(inode)->i_##field); \
}
EXT4_INODE_BIT_FNS(flag, flags, 0)
#if (BITS_PER_LONG < 64)
EXT4_INODE_BIT_FNS(state, state_flags, 0)
static inline void ext4_clear_state_flags(struct ext4_inode_info *ei)
{
(ei)->i_state_flags = 0;
}
#else
EXT4_INODE_BIT_FNS(state, flags, 32)
static inline void ext4_clear_state_flags(struct ext4_inode_info *ei)
{
/* We depend on the fact that callers will set i_flags */
}
#endif
#else
/* Assume that user mode programs are passing in an ext4fs superblock, not
* a kernel struct super_block. This will allow us to call the feature-test
* macros from user land. */
#define EXT4_SB(sb) (sb)
#endif
#define NEXT_ORPHAN(inode) EXT4_I(inode)->i_dtime
/*
* Codes for operating systems
*/
#define EXT4_OS_LINUX 0
#define EXT4_OS_HURD 1
#define EXT4_OS_MASIX 2
#define EXT4_OS_FREEBSD 3
#define EXT4_OS_LITES 4
/*
* Revision levels
*/
#define EXT4_GOOD_OLD_REV 0 /* The good old (original) format */
#define EXT4_DYNAMIC_REV 1 /* V2 format w/ dynamic inode sizes */
#define EXT4_CURRENT_REV EXT4_GOOD_OLD_REV
#define EXT4_MAX_SUPP_REV EXT4_DYNAMIC_REV
#define EXT4_GOOD_OLD_INODE_SIZE 128
/*
* Feature set definitions
*/
#define EXT4_HAS_COMPAT_FEATURE(sb,mask) \
((EXT4_SB(sb)->s_es->s_feature_compat & cpu_to_le32(mask)) != 0)
#define EXT4_HAS_RO_COMPAT_FEATURE(sb,mask) \
((EXT4_SB(sb)->s_es->s_feature_ro_compat & cpu_to_le32(mask)) != 0)
#define EXT4_HAS_INCOMPAT_FEATURE(sb,mask) \
((EXT4_SB(sb)->s_es->s_feature_incompat & cpu_to_le32(mask)) != 0)
#define EXT4_SET_COMPAT_FEATURE(sb,mask) \
EXT4_SB(sb)->s_es->s_feature_compat |= cpu_to_le32(mask)
#define EXT4_SET_RO_COMPAT_FEATURE(sb,mask) \
EXT4_SB(sb)->s_es->s_feature_ro_compat |= cpu_to_le32(mask)
#define EXT4_SET_INCOMPAT_FEATURE(sb,mask) \
EXT4_SB(sb)->s_es->s_feature_incompat |= cpu_to_le32(mask)
#define EXT4_CLEAR_COMPAT_FEATURE(sb,mask) \
EXT4_SB(sb)->s_es->s_feature_compat &= ~cpu_to_le32(mask)
#define EXT4_CLEAR_RO_COMPAT_FEATURE(sb,mask) \
EXT4_SB(sb)->s_es->s_feature_ro_compat &= ~cpu_to_le32(mask)
#define EXT4_CLEAR_INCOMPAT_FEATURE(sb,mask) \
EXT4_SB(sb)->s_es->s_feature_incompat &= ~cpu_to_le32(mask)
#define EXT4_FEATURE_COMPAT_DIR_PREALLOC 0x0001
#define EXT4_FEATURE_COMPAT_IMAGIC_INODES 0x0002
#define EXT4_FEATURE_COMPAT_HAS_JOURNAL 0x0004
#define EXT4_FEATURE_COMPAT_EXT_ATTR 0x0008
#define EXT4_FEATURE_COMPAT_RESIZE_INODE 0x0010
#define EXT4_FEATURE_COMPAT_DIR_INDEX 0x0020
#define EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER 0x0001
#define EXT4_FEATURE_RO_COMPAT_LARGE_FILE 0x0002
#define EXT4_FEATURE_RO_COMPAT_BTREE_DIR 0x0004
#define EXT4_FEATURE_RO_COMPAT_HUGE_FILE 0x0008
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>
2007-10-16 22:38:25 +00:00
#define EXT4_FEATURE_RO_COMPAT_GDT_CSUM 0x0010
#define EXT4_FEATURE_RO_COMPAT_DIR_NLINK 0x0020
#define EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE 0x0040
#define EXT4_FEATURE_RO_COMPAT_QUOTA 0x0100
#define EXT4_FEATURE_RO_COMPAT_BIGALLOC 0x0200
/*
* METADATA_CSUM also enables group descriptor checksums (GDT_CSUM). When
* METADATA_CSUM is set, group descriptor checksums use the same algorithm as
* all other data structures' checksums. However, the METADATA_CSUM and
* GDT_CSUM bits are mutually exclusive.
*/
#define EXT4_FEATURE_RO_COMPAT_METADATA_CSUM 0x0400
#define EXT4_FEATURE_INCOMPAT_COMPRESSION 0x0001
#define EXT4_FEATURE_INCOMPAT_FILETYPE 0x0002
#define EXT4_FEATURE_INCOMPAT_RECOVER 0x0004 /* Needs recovery */
#define EXT4_FEATURE_INCOMPAT_JOURNAL_DEV 0x0008 /* Journal device */
#define EXT4_FEATURE_INCOMPAT_META_BG 0x0010
#define EXT4_FEATURE_INCOMPAT_EXTENTS 0x0040 /* extents support */
#define EXT4_FEATURE_INCOMPAT_64BIT 0x0080
#define EXT4_FEATURE_INCOMPAT_MMP 0x0100
#define EXT4_FEATURE_INCOMPAT_FLEX_BG 0x0200
#define EXT4_FEATURE_INCOMPAT_EA_INODE 0x0400 /* EA in inode */
#define EXT4_FEATURE_INCOMPAT_DIRDATA 0x1000 /* data in dirent */
#define EXT4_FEATURE_INCOMPAT_BG_USE_META_CSUM 0x2000 /* use crc32c for bg */
#define EXT4_FEATURE_INCOMPAT_LARGEDIR 0x4000 /* >2GB or 3-lvl htree */
#define EXT4_FEATURE_INCOMPAT_INLINEDATA 0x8000 /* data in inode */
#define EXT2_FEATURE_COMPAT_SUPP EXT4_FEATURE_COMPAT_EXT_ATTR
#define EXT2_FEATURE_INCOMPAT_SUPP (EXT4_FEATURE_INCOMPAT_FILETYPE| \
EXT4_FEATURE_INCOMPAT_META_BG)
#define EXT2_FEATURE_RO_COMPAT_SUPP (EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER| \
EXT4_FEATURE_RO_COMPAT_LARGE_FILE| \
EXT4_FEATURE_RO_COMPAT_BTREE_DIR)
#define EXT3_FEATURE_COMPAT_SUPP EXT4_FEATURE_COMPAT_EXT_ATTR
#define EXT3_FEATURE_INCOMPAT_SUPP (EXT4_FEATURE_INCOMPAT_FILETYPE| \
EXT4_FEATURE_INCOMPAT_RECOVER| \
EXT4_FEATURE_INCOMPAT_META_BG)
#define EXT3_FEATURE_RO_COMPAT_SUPP (EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER| \
EXT4_FEATURE_RO_COMPAT_LARGE_FILE| \
EXT4_FEATURE_RO_COMPAT_BTREE_DIR)
#define EXT4_FEATURE_COMPAT_SUPP EXT2_FEATURE_COMPAT_EXT_ATTR
#define EXT4_FEATURE_INCOMPAT_SUPP (EXT4_FEATURE_INCOMPAT_FILETYPE| \
EXT4_FEATURE_INCOMPAT_RECOVER| \
EXT4_FEATURE_INCOMPAT_META_BG| \
EXT4_FEATURE_INCOMPAT_EXTENTS| \
EXT4_FEATURE_INCOMPAT_64BIT| \
EXT4_FEATURE_INCOMPAT_FLEX_BG| \
EXT4_FEATURE_INCOMPAT_MMP)
#define EXT4_FEATURE_RO_COMPAT_SUPP (EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER| \
EXT4_FEATURE_RO_COMPAT_LARGE_FILE| \
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>
2007-10-16 22:38:25 +00:00
EXT4_FEATURE_RO_COMPAT_GDT_CSUM| \
EXT4_FEATURE_RO_COMPAT_DIR_NLINK | \
EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE | \
EXT4_FEATURE_RO_COMPAT_BTREE_DIR |\
EXT4_FEATURE_RO_COMPAT_HUGE_FILE |\
EXT4_FEATURE_RO_COMPAT_BIGALLOC |\
EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)
/*
* Default values for user and/or group using reserved blocks
*/
#define EXT4_DEF_RESUID 0
#define EXT4_DEF_RESGID 0
#define EXT4_DEF_INODE_READAHEAD_BLKS 32
/*
* Default mount options
*/
#define EXT4_DEFM_DEBUG 0x0001
#define EXT4_DEFM_BSDGROUPS 0x0002
#define EXT4_DEFM_XATTR_USER 0x0004
#define EXT4_DEFM_ACL 0x0008
#define EXT4_DEFM_UID16 0x0010
#define EXT4_DEFM_JMODE 0x0060
#define EXT4_DEFM_JMODE_DATA 0x0020
#define EXT4_DEFM_JMODE_ORDERED 0x0040
#define EXT4_DEFM_JMODE_WBACK 0x0060
#define EXT4_DEFM_NOBARRIER 0x0100
#define EXT4_DEFM_BLOCK_VALIDITY 0x0200
#define EXT4_DEFM_DISCARD 0x0400
#define EXT4_DEFM_NODELALLOC 0x0800
/*
* Default journal batch times
*/
#define EXT4_DEF_MIN_BATCH_TIME 0
#define EXT4_DEF_MAX_BATCH_TIME 15000 /* 15ms */
/*
* Minimum number of groups in a flexgroup before we separate out
* directories into the first block group of a flexgroup
*/
#define EXT4_FLEX_SIZE_DIR_ALLOC_SCHEME 4
/*
* Structure of a directory entry
*/
#define EXT4_NAME_LEN 255
struct ext4_dir_entry {
__le32 inode; /* Inode number */
__le16 rec_len; /* Directory entry length */
__le16 name_len; /* Name length */
char name[EXT4_NAME_LEN]; /* File name */
};
/*
* The new version of the directory entry. Since EXT4 structures are
* stored in intel byte order, and the name_len field could never be
* bigger than 255 chars, it's safe to reclaim the extra byte for the
* file_type field.
*/
struct ext4_dir_entry_2 {
__le32 inode; /* Inode number */
__le16 rec_len; /* Directory entry length */
__u8 name_len; /* Name length */
__u8 file_type;
char name[EXT4_NAME_LEN]; /* File name */
};
/*
* This is a bogus directory entry at the end of each leaf block that
* records checksums.
*/
struct ext4_dir_entry_tail {
__le32 det_reserved_zero1; /* Pretend to be unused */
__le16 det_rec_len; /* 12 */
__u8 det_reserved_zero2; /* Zero name length */
__u8 det_reserved_ft; /* 0xDE, fake file type */
__le32 det_checksum; /* crc32c(uuid+inum+dirblock) */
};
/*
* Ext4 directory file types. Only the low 3 bits are used. The
* other bits are reserved for now.
*/
#define EXT4_FT_UNKNOWN 0
#define EXT4_FT_REG_FILE 1
#define EXT4_FT_DIR 2
#define EXT4_FT_CHRDEV 3
#define EXT4_FT_BLKDEV 4
#define EXT4_FT_FIFO 5
#define EXT4_FT_SOCK 6
#define EXT4_FT_SYMLINK 7
#define EXT4_FT_MAX 8
#define EXT4_FT_DIR_CSUM 0xDE
/*
* EXT4_DIR_PAD defines the directory entries boundaries
*
* NOTE: It must be a multiple of 4
*/
#define EXT4_DIR_PAD 4
#define EXT4_DIR_ROUND (EXT4_DIR_PAD - 1)
#define EXT4_DIR_REC_LEN(name_len) (((name_len) + 8 + EXT4_DIR_ROUND) & \
~EXT4_DIR_ROUND)
#define EXT4_MAX_REC_LEN ((1<<16)-1)
/*
* If we ever get support for fs block sizes > page_size, we'll need
* to remove the #if statements in the next two functions...
*/
static inline unsigned int
ext4_rec_len_from_disk(__le16 dlen, unsigned blocksize)
{
unsigned len = le16_to_cpu(dlen);
#if (PAGE_CACHE_SIZE >= 65536)
if (len == EXT4_MAX_REC_LEN || len == 0)
return blocksize;
return (len & 65532) | ((len & 3) << 16);
#else
return len;
#endif
}
static inline __le16 ext4_rec_len_to_disk(unsigned len, unsigned blocksize)
{
if ((len > blocksize) || (blocksize > (1 << 18)) || (len & 3))
BUG();
#if (PAGE_CACHE_SIZE >= 65536)
if (len < 65536)
return cpu_to_le16(len);
if (len == blocksize) {
if (blocksize == 65536)
return cpu_to_le16(EXT4_MAX_REC_LEN);
else
return cpu_to_le16(0);
}
return cpu_to_le16((len & 65532) | ((len >> 16) & 3));
#else
return cpu_to_le16(len);
#endif
}
/*
* Hash Tree Directory indexing
* (c) Daniel Phillips, 2001
*/
#define is_dx(dir) (EXT4_HAS_COMPAT_FEATURE(dir->i_sb, \
EXT4_FEATURE_COMPAT_DIR_INDEX) && \
ext4_test_inode_flag((dir), EXT4_INODE_INDEX))
#define EXT4_DIR_LINK_MAX(dir) (!is_dx(dir) && (dir)->i_nlink >= EXT4_LINK_MAX)
#define EXT4_DIR_LINK_EMPTY(dir) ((dir)->i_nlink == 2 || (dir)->i_nlink == 1)
/* Legal values for the dx_root hash_version field: */
#define DX_HASH_LEGACY 0
#define DX_HASH_HALF_MD4 1
#define DX_HASH_TEA 2
#define DX_HASH_LEGACY_UNSIGNED 3
#define DX_HASH_HALF_MD4_UNSIGNED 4
#define DX_HASH_TEA_UNSIGNED 5
static inline u32 ext4_chksum(struct ext4_sb_info *sbi, u32 crc,
const void *address, unsigned int length)
{
struct {
struct shash_desc shash;
char ctx[crypto_shash_descsize(sbi->s_chksum_driver)];
} desc;
int err;
desc.shash.tfm = sbi->s_chksum_driver;
desc.shash.flags = 0;
*(u32 *)desc.ctx = crc;
err = crypto_shash_update(&desc.shash, address, length);
BUG_ON(err);
return *(u32 *)desc.ctx;
}
#ifdef __KERNEL__
/* hash info structure used by the directory hash */
struct dx_hash_info
{
u32 hash;
u32 minor_hash;
int hash_version;
u32 *seed;
};
/* 32 and 64 bit signed EOF for dx directories */
#define EXT4_HTREE_EOF_32BIT ((1UL << (32 - 1)) - 1)
#define EXT4_HTREE_EOF_64BIT ((1ULL << (64 - 1)) - 1)
/*
* Control parameters used by ext4_htree_next_block
*/
#define HASH_NB_ALWAYS 1
/*
* Describe an inode's exact location on disk and in memory
*/
struct ext4_iloc
{
struct buffer_head *bh;
unsigned long offset;
ext4_group_t block_group;
};
static inline struct ext4_inode *ext4_raw_inode(struct ext4_iloc *iloc)
{
return (struct ext4_inode *) (iloc->bh->b_data + iloc->offset);
}
/*
* This structure is stuffed into the struct file's private_data field
* for directories. It is where we put information so that we can do
* readdir operations in hash tree order.
*/
struct dir_private_info {
struct rb_root root;
struct rb_node *curr_node;
struct fname *extra_fname;
loff_t last_pos;
__u32 curr_hash;
__u32 curr_minor_hash;
__u32 next_hash;
};
/* calculate the first block number of the group */
static inline ext4_fsblk_t
ext4_group_first_block_no(struct super_block *sb, ext4_group_t group_no)
{
return group_no * (ext4_fsblk_t)EXT4_BLOCKS_PER_GROUP(sb) +
le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block);
}
/*
* Special error return code only used by dx_probe() and its callers.
*/
#define ERR_BAD_DX_DIR -75000
void ext4_get_group_no_and_offset(struct super_block *sb, ext4_fsblk_t blocknr,
ext4_group_t *blockgrpp, ext4_grpblk_t *offsetp);
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 01:30:05 +00:00
/*
* Timeout and state flag for lazy initialization inode thread.
*/
#define EXT4_DEF_LI_WAIT_MULT 10
#define EXT4_DEF_LI_MAX_START_DELAY 5
#define EXT4_LAZYINIT_QUIT 0x0001
#define EXT4_LAZYINIT_RUNNING 0x0002
/*
* Lazy inode table initialization info
*/
struct ext4_lazy_init {
unsigned long li_state;
struct list_head li_request_list;
struct mutex li_list_mtx;
};
struct ext4_li_request {
struct super_block *lr_super;
struct ext4_sb_info *lr_sbi;
ext4_group_t lr_next_group;
struct list_head lr_request;
unsigned long lr_next_sched;
unsigned long lr_timeout;
};
struct ext4_features {
struct kobject f_kobj;
struct completion f_kobj_unregister;
};
/*
* This structure will be used for multiple mount protection. It will be
* written into the block number saved in the s_mmp_block field in the
* superblock. Programs that check MMP should assume that if
* SEQ_FSCK (or any unknown code above SEQ_MAX) is present then it is NOT safe
* to use the filesystem, regardless of how old the timestamp is.
*/
#define EXT4_MMP_MAGIC 0x004D4D50U /* ASCII for MMP */
#define EXT4_MMP_SEQ_CLEAN 0xFF4D4D50U /* mmp_seq value for clean unmount */
#define EXT4_MMP_SEQ_FSCK 0xE24D4D50U /* mmp_seq value when being fscked */
#define EXT4_MMP_SEQ_MAX 0xE24D4D4FU /* maximum valid mmp_seq value */
struct mmp_struct {
__le32 mmp_magic; /* Magic number for MMP */
__le32 mmp_seq; /* Sequence no. updated periodically */
/*
* mmp_time, mmp_nodename & mmp_bdevname are only used for information
* purposes and do not affect the correctness of the algorithm
*/
__le64 mmp_time; /* Time last updated */
char mmp_nodename[64]; /* Node which last updated MMP block */
char mmp_bdevname[32]; /* Bdev which last updated MMP block */
/*
* mmp_check_interval is used to verify if the MMP block has been
* updated on the block device. The value is updated based on the
* maximum time to write the MMP block during an update cycle.
*/
__le16 mmp_check_interval;
__le16 mmp_pad1;
__le32 mmp_pad2[226];
__le32 mmp_checksum; /* crc32c(uuid+mmp_block) */
};
/* arguments passed to the mmp thread */
struct mmpd_data {
struct buffer_head *bh; /* bh from initial read_mmp_block() */
struct super_block *sb; /* super block of the fs */
};
/*
* Check interval multiplier
* The MMP block is written every update interval and initially checked every
* update interval x the multiplier (the value is then adapted based on the
* write latency). The reason is that writes can be delayed under load and we
* don't want readers to incorrectly assume that the filesystem is no longer
* in use.
*/
#define EXT4_MMP_CHECK_MULT 2UL
/*
* Minimum interval for MMP checking in seconds.
*/
#define EXT4_MMP_MIN_CHECK_INTERVAL 5UL
/*
* Maximum interval for MMP checking in seconds.
*/
#define EXT4_MMP_MAX_CHECK_INTERVAL 300UL
/*
* Function prototypes
*/
/*
* Ok, these declarations are also in <linux/kernel.h> but none of the
* ext4 source programs needs to include it so they are duplicated here.
*/
# define NORET_TYPE /**/
# define ATTRIB_NORET __attribute__((noreturn))
# define NORET_AND noreturn,
/* bitmap.c */
extern unsigned int ext4_count_free(struct buffer_head *, unsigned);
void ext4_inode_bitmap_csum_set(struct super_block *sb, ext4_group_t group,
struct ext4_group_desc *gdp,
struct buffer_head *bh, int sz);
int ext4_inode_bitmap_csum_verify(struct super_block *sb, ext4_group_t group,
struct ext4_group_desc *gdp,
struct buffer_head *bh, int sz);
void ext4_block_bitmap_csum_set(struct super_block *sb, ext4_group_t group,
struct ext4_group_desc *gdp,
struct buffer_head *bh, int sz);
int ext4_block_bitmap_csum_verify(struct super_block *sb, ext4_group_t group,
struct ext4_group_desc *gdp,
struct buffer_head *bh, int sz);
/* balloc.c */
extern void ext4_validate_block_bitmap(struct super_block *sb,
struct ext4_group_desc *desc,
unsigned int block_group,
struct buffer_head *bh);
extern unsigned int ext4_block_group(struct super_block *sb,
ext4_fsblk_t blocknr);
extern ext4_grpblk_t ext4_block_group_offset(struct super_block *sb,
ext4_fsblk_t blocknr);
extern int ext4_bg_has_super(struct super_block *sb, ext4_group_t group);
extern unsigned long ext4_bg_num_gdb(struct super_block *sb,
ext4_group_t group);
extern ext4_fsblk_t ext4_new_meta_blocks(handle_t *handle, struct inode *inode,
ext4_fsblk_t goal,
unsigned int flags,
unsigned long *count,
int *errp);
extern int ext4_claim_free_clusters(struct ext4_sb_info *sbi,
s64 nclusters, unsigned int flags);
extern ext4_fsblk_t ext4_count_free_clusters(struct super_block *);
extern void ext4_check_blocks_bitmap(struct super_block *);
extern struct ext4_group_desc * ext4_get_group_desc(struct super_block * sb,
ext4_group_t block_group,
struct buffer_head ** bh);
extern int ext4_should_retry_alloc(struct super_block *sb, int *retries);
extern struct buffer_head *ext4_read_block_bitmap_nowait(struct super_block *sb,
ext4_group_t block_group);
extern int ext4_wait_block_bitmap(struct super_block *sb,
ext4_group_t block_group,
struct buffer_head *bh);
extern struct buffer_head *ext4_read_block_bitmap(struct super_block *sb,
ext4_group_t block_group);
extern void ext4_init_block_bitmap(struct super_block *sb,
struct buffer_head *bh,
ext4_group_t group,
struct ext4_group_desc *desc);
extern unsigned ext4_free_clusters_after_init(struct super_block *sb,
ext4_group_t block_group,
struct ext4_group_desc *gdp);
extern unsigned ext4_num_overhead_clusters(struct super_block *sb,
ext4_group_t block_group,
struct ext4_group_desc *gdp);
ext4_fsblk_t ext4_inode_to_goal_block(struct inode *);
/* dir.c */
extern int __ext4_check_dir_entry(const char *, unsigned int, struct inode *,
struct file *,
struct ext4_dir_entry_2 *,
struct buffer_head *, unsigned int);
#define ext4_check_dir_entry(dir, filp, de, bh, offset) \
unlikely(__ext4_check_dir_entry(__func__, __LINE__, (dir), (filp), \
(de), (bh), (offset)))
extern int ext4_htree_store_dirent(struct file *dir_file, __u32 hash,
__u32 minor_hash,
struct ext4_dir_entry_2 *dirent);
extern void ext4_htree_free_dir_info(struct dir_private_info *p);
/* fsync.c */
extern int ext4_sync_file(struct file *, loff_t, loff_t, int);
ext4: flush the i_completed_io_list during ext4_truncate Ted first found the bug when running 2.6.36 kernel with dioread_nolock mount option that xfstests #13 complained about wrong file size during fsck. However, the bug exists in the older kernels as well although it is somehow harder to trigger. The problem is that ext4_end_io_work() can happen after we have truncated an inode to a smaller size. Then when ext4_end_io_work() calls ext4_convert_unwritten_extents(), we may reallocate some blocks that have been truncated, so the inode size becomes inconsistent with the allocated blocks. The following patch flushes the i_completed_io_list during truncate to reduce the risk that some pending end_io requests are executed later and convert already truncated blocks to initialized. Note that although the fix helps reduce the problem a lot there may still be a race window between vmtruncate() and ext4_end_io_work(). The fundamental problem is that if vmtruncate() is called without either i_mutex or i_alloc_sem held, it can race with an ongoing write request so that the io_end request is processed later when the corresponding blocks have been truncated. Ted and I have discussed the problem offline and we saw a few ways to fix the race completely: a) We guarantee that i_mutex lock and i_alloc_sem write lock are both hold whenever vmtruncate() is called. The i_mutex lock prevents any new write requests from entering writeback and the i_alloc_sem prevents the race from ext4_page_mkwrite(). Currently we hold both locks if vmtruncate() is called from do_truncate(), which is probably the most common case. However, there are places where we may call vmtruncate() without holding either i_mutex or i_alloc_sem. I would like to ask for other people's opinions on what locks are expected to be held before calling vmtruncate(). There seems a disagreement among the callers of that function. b) We change the ext4 write path so that we change the extent tree to contain the newly allocated blocks and update i_size both at the same time --- when the write of the data blocks is completed. c) We add some additional locking to synchronize vmtruncate() and ext4_end_io_work(). This approach may have performance implications so we need to be careful. All of the above proposals may require more substantial changes, so we may consider to take the following patch as a bandaid. Signed-off-by: Jiaying Zhang <jiayingz@google.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2011-01-10 17:47:05 +00:00
extern int ext4_flush_completed_IO(struct inode *);
/* hash.c */
extern int ext4fs_dirhash(const char *name, int len, struct
dx_hash_info *hinfo);
/* ialloc.c */
extern struct inode *ext4_new_inode(handle_t *, struct inode *, umode_t,
const struct qstr *qstr, __u32 goal,
uid_t *owner);
extern void ext4_free_inode(handle_t *, struct inode *);
extern struct inode * ext4_orphan_get(struct super_block *, unsigned long);
extern unsigned long ext4_count_free_inodes(struct super_block *);
extern unsigned long ext4_count_dirs(struct super_block *);
extern void ext4_check_inodes_bitmap(struct super_block *);
extern void ext4_mark_bitmap_end(int start_bit, int end_bit, char *bitmap);
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 01:30:05 +00:00
extern int ext4_init_inode_table(struct super_block *sb,
ext4_group_t group, int barrier);
extern void ext4_end_bitmap_read(struct buffer_head *bh, int uptodate);
/* mballoc.c */
extern long ext4_mb_stats;
extern long ext4_mb_max_to_scan;
extern int ext4_mb_init(struct super_block *);
extern int ext4_mb_release(struct super_block *);
extern ext4_fsblk_t ext4_mb_new_blocks(handle_t *,
struct ext4_allocation_request *, int *);
extern int ext4_mb_reserve_blocks(struct super_block *, int);
extern void ext4_discard_preallocations(struct inode *);
extern int __init ext4_init_mballoc(void);
extern void ext4_exit_mballoc(void);
extern void ext4_free_blocks(handle_t *handle, struct inode *inode,
struct buffer_head *bh, ext4_fsblk_t block,
unsigned long count, int flags);
extern int ext4_mb_add_groupinfo(struct super_block *sb,
ext4_group_t i, struct ext4_group_desc *desc);
extern int ext4_group_add_blocks(handle_t *handle, struct super_block *sb,
ext4_fsblk_t block, unsigned long count);
extern int ext4_trim_fs(struct super_block *, struct fstrim_range *);
/* inode.c */
struct buffer_head *ext4_getblk(handle_t *, struct inode *,
ext4_lblk_t, int, int *);
struct buffer_head *ext4_bread(handle_t *, struct inode *,
ext4_lblk_t, int, int *);
int ext4_get_block(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create);
extern struct inode *ext4_iget(struct super_block *, unsigned long);
extern int ext4_write_inode(struct inode *, struct writeback_control *);
extern int ext4_setattr(struct dentry *, struct iattr *);
extern int ext4_getattr(struct vfsmount *mnt, struct dentry *dentry,
struct kstat *stat);
extern void ext4_evict_inode(struct inode *);
extern void ext4_clear_inode(struct inode *);
extern int ext4_sync_inode(handle_t *, struct inode *);
extern void ext4_dirty_inode(struct inode *, int);
extern int ext4_change_inode_journal_flag(struct inode *, int);
extern int ext4_get_inode_loc(struct inode *, struct ext4_iloc *);
extern int ext4_can_truncate(struct inode *inode);
extern void ext4_truncate(struct inode *);
extern int ext4_punch_hole(struct file *file, loff_t offset, loff_t length);
extern int ext4_truncate_restart_trans(handle_t *, struct inode *, int nblocks);
extern void ext4_set_inode_flags(struct inode *);
extern void ext4_get_inode_flags(struct ext4_inode_info *);
extern int ext4_alloc_da_blocks(struct inode *inode);
extern void ext4_set_aops(struct inode *inode);
extern int ext4_writepage_trans_blocks(struct inode *);
extern int ext4_chunk_trans_blocks(struct inode *, int nrblocks);
ext4: Add new ext4_discard_partial_page_buffers routines This patch adds two new routines: ext4_discard_partial_page_buffers and ext4_discard_partial_page_buffers_no_lock. The ext4_discard_partial_page_buffers routine is a wrapper function to ext4_discard_partial_page_buffers_no_lock. The wrapper function locks the page and passes it to ext4_discard_partial_page_buffers_no_lock. Calling functions that already have the page locked can call ext4_discard_partial_page_buffers_no_lock directly. The ext4_discard_partial_page_buffers_no_lock function zeros a specified range in a page, and unmaps the corresponding buffer heads. Only block aligned regions of the page will have their buffer heads unmapped. Unblock aligned regions will be mapped if needed so that they can be updated with the partial zero out. This function is meant to be used to update a page and its buffer heads to be zeroed and unmapped when the corresponding blocks have been released or will be released. This routine is used in the following scenarios: * A hole is punched and the non page aligned regions of the head and tail of the hole need to be discarded * The file is truncated and the partial page beyond EOF needs to be discarded * The end of a hole is in the same page as EOF. After the page is flushed, the partial page beyond EOF needs to be discarded. * A write operation begins or ends inside a hole and the partial page appearing before or after the write needs to be discarded * A write operation extends EOF and the partial page beyond EOF needs to be discarded This function takes a flag EXT4_DISCARD_PARTIAL_PG_ZERO_UNMAPPED which is used when a write operation begins or ends in a hole. When the EXT4_DISCARD_PARTIAL_PG_ZERO_UNMAPPED flag is used, only buffer heads that are already unmapped will have the corresponding regions of the page zeroed. Signed-off-by: Allison Henderson <achender@linux.vnet.ibm.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2011-09-03 15:51:09 +00:00
extern int ext4_discard_partial_page_buffers(handle_t *handle,
struct address_space *mapping, loff_t from,
loff_t length, int flags);
extern int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf);
extern qsize_t *ext4_get_reserved_space(struct inode *inode);
extern void ext4_da_update_reserve_space(struct inode *inode,
int used, int quota_claim);
/* indirect.c */
extern int ext4_ind_map_blocks(handle_t *handle, struct inode *inode,
struct ext4_map_blocks *map, int flags);
extern ssize_t ext4_ind_direct_IO(int rw, struct kiocb *iocb,
const struct iovec *iov, loff_t offset,
unsigned long nr_segs);
extern int ext4_ind_calc_metadata_amount(struct inode *inode, sector_t lblock);
extern int ext4_ind_trans_blocks(struct inode *inode, int nrblocks, int chunk);
extern void ext4_ind_truncate(struct inode *inode);
/* ioctl.c */
extern long ext4_ioctl(struct file *, unsigned int, unsigned long);
extern long ext4_compat_ioctl(struct file *, unsigned int, unsigned long);
/* migrate.c */
extern int ext4_ext_migrate(struct inode *);
/* namei.c */
extern int ext4_dirent_csum_verify(struct inode *inode,
struct ext4_dir_entry *dirent);
extern int ext4_orphan_add(handle_t *, struct inode *);
extern int ext4_orphan_del(handle_t *, struct inode *);
extern int ext4_htree_fill_tree(struct file *dir_file, __u32 start_hash,
__u32 start_minor_hash, __u32 *next_hash);
/* resize.c */
extern int ext4_group_add(struct super_block *sb,
struct ext4_new_group_data *input);
extern int ext4_group_extend(struct super_block *sb,
struct ext4_super_block *es,
ext4_fsblk_t n_blocks_count);
extern int ext4_resize_fs(struct super_block *sb, ext4_fsblk_t n_blocks_count);
/* super.c */
extern int ext4_superblock_csum_verify(struct super_block *sb,
struct ext4_super_block *es);
extern void ext4_superblock_csum_set(struct super_block *sb,
struct ext4_super_block *es);
extern void *ext4_kvmalloc(size_t size, gfp_t flags);
extern void *ext4_kvzalloc(size_t size, gfp_t flags);
extern void ext4_kvfree(void *ptr);
extern __printf(4, 5)
void __ext4_error(struct super_block *, const char *, unsigned int,
const char *, ...);
#define ext4_error(sb, message...) __ext4_error(sb, __func__, \
__LINE__, ## message)
extern __printf(5, 6)
void ext4_error_inode(struct inode *, const char *, unsigned int, ext4_fsblk_t,
const char *, ...);
extern __printf(5, 6)
void ext4_error_file(struct file *, const char *, unsigned int, ext4_fsblk_t,
const char *, ...);
extern void __ext4_std_error(struct super_block *, const char *,
unsigned int, int);
extern __printf(4, 5)
void __ext4_abort(struct super_block *, const char *, unsigned int,
const char *, ...);
#define ext4_abort(sb, message...) __ext4_abort(sb, __func__, \
__LINE__, ## message)
extern __printf(4, 5)
void __ext4_warning(struct super_block *, const char *, unsigned int,
const char *, ...);
#define ext4_warning(sb, message...) __ext4_warning(sb, __func__, \
__LINE__, ## message)
extern __printf(3, 4)
void ext4_msg(struct super_block *, const char *, const char *, ...);
extern void __dump_mmp_msg(struct super_block *, struct mmp_struct *mmp,
const char *, unsigned int, const char *);
#define dump_mmp_msg(sb, mmp, msg) __dump_mmp_msg(sb, mmp, __func__, \
__LINE__, msg)
extern __printf(7, 8)
void __ext4_grp_locked_error(const char *, unsigned int,
struct super_block *, ext4_group_t,
unsigned long, ext4_fsblk_t,
const char *, ...);
#define ext4_grp_locked_error(sb, grp, message...) \
__ext4_grp_locked_error(__func__, __LINE__, (sb), (grp), ## message)
extern void ext4_update_dynamic_rev(struct super_block *sb);
extern int ext4_update_compat_feature(handle_t *handle, struct super_block *sb,
__u32 compat);
extern int ext4_update_rocompat_feature(handle_t *handle,
struct super_block *sb, __u32 rocompat);
extern int ext4_update_incompat_feature(handle_t *handle,
struct super_block *sb, __u32 incompat);
extern ext4_fsblk_t ext4_block_bitmap(struct super_block *sb,
struct ext4_group_desc *bg);
extern ext4_fsblk_t ext4_inode_bitmap(struct super_block *sb,
struct ext4_group_desc *bg);
extern ext4_fsblk_t ext4_inode_table(struct super_block *sb,
struct ext4_group_desc *bg);
extern __u32 ext4_free_group_clusters(struct super_block *sb,
struct ext4_group_desc *bg);
extern __u32 ext4_free_inodes_count(struct super_block *sb,
struct ext4_group_desc *bg);
extern __u32 ext4_used_dirs_count(struct super_block *sb,
struct ext4_group_desc *bg);
extern __u32 ext4_itable_unused_count(struct super_block *sb,
struct ext4_group_desc *bg);
extern void ext4_block_bitmap_set(struct super_block *sb,
struct ext4_group_desc *bg, ext4_fsblk_t blk);
extern void ext4_inode_bitmap_set(struct super_block *sb,
struct ext4_group_desc *bg, ext4_fsblk_t blk);
extern void ext4_inode_table_set(struct super_block *sb,
struct ext4_group_desc *bg, ext4_fsblk_t blk);
extern void ext4_free_group_clusters_set(struct super_block *sb,
struct ext4_group_desc *bg,
__u32 count);
extern void ext4_free_inodes_set(struct super_block *sb,
struct ext4_group_desc *bg, __u32 count);
extern void ext4_used_dirs_set(struct super_block *sb,
struct ext4_group_desc *bg, __u32 count);
extern void ext4_itable_unused_set(struct super_block *sb,
struct ext4_group_desc *bg, __u32 count);
extern int ext4_group_desc_csum_verify(struct super_block *sb, __u32 group,
struct ext4_group_desc *gdp);
extern void ext4_group_desc_csum_set(struct super_block *sb, __u32 group,
struct ext4_group_desc *gdp);
static inline int ext4_has_group_desc_csum(struct super_block *sb)
{
return EXT4_HAS_RO_COMPAT_FEATURE(sb,
EXT4_FEATURE_RO_COMPAT_GDT_CSUM |
EXT4_FEATURE_RO_COMPAT_METADATA_CSUM);
}
static inline ext4_fsblk_t ext4_blocks_count(struct ext4_super_block *es)
{
return ((ext4_fsblk_t)le32_to_cpu(es->s_blocks_count_hi) << 32) |
le32_to_cpu(es->s_blocks_count_lo);
}
static inline ext4_fsblk_t ext4_r_blocks_count(struct ext4_super_block *es)
{
return ((ext4_fsblk_t)le32_to_cpu(es->s_r_blocks_count_hi) << 32) |
le32_to_cpu(es->s_r_blocks_count_lo);
}
static inline ext4_fsblk_t ext4_free_blocks_count(struct ext4_super_block *es)
{
return ((ext4_fsblk_t)le32_to_cpu(es->s_free_blocks_count_hi) << 32) |
le32_to_cpu(es->s_free_blocks_count_lo);
}
static inline void ext4_blocks_count_set(struct ext4_super_block *es,
ext4_fsblk_t blk)
{
es->s_blocks_count_lo = cpu_to_le32((u32)blk);
es->s_blocks_count_hi = cpu_to_le32(blk >> 32);
}
static inline void ext4_free_blocks_count_set(struct ext4_super_block *es,
ext4_fsblk_t blk)
{
es->s_free_blocks_count_lo = cpu_to_le32((u32)blk);
es->s_free_blocks_count_hi = cpu_to_le32(blk >> 32);
}
static inline void ext4_r_blocks_count_set(struct ext4_super_block *es,
ext4_fsblk_t blk)
{
es->s_r_blocks_count_lo = cpu_to_le32((u32)blk);
es->s_r_blocks_count_hi = cpu_to_le32(blk >> 32);
}
static inline loff_t ext4_isize(struct ext4_inode *raw_inode)
{
if (S_ISREG(le16_to_cpu(raw_inode->i_mode)))
return ((loff_t)le32_to_cpu(raw_inode->i_size_high) << 32) |
le32_to_cpu(raw_inode->i_size_lo);
else
return (loff_t) le32_to_cpu(raw_inode->i_size_lo);
}
static inline void ext4_isize_set(struct ext4_inode *raw_inode, loff_t i_size)
{
raw_inode->i_size_lo = cpu_to_le32(i_size);
raw_inode->i_size_high = cpu_to_le32(i_size >> 32);
}
static inline
struct ext4_group_info *ext4_get_group_info(struct super_block *sb,
ext4_group_t group)
{
struct ext4_group_info ***grp_info;
long indexv, indexh;
grp_info = EXT4_SB(sb)->s_group_info;
indexv = group >> (EXT4_DESC_PER_BLOCK_BITS(sb));
indexh = group & ((EXT4_DESC_PER_BLOCK(sb)) - 1);
return grp_info[indexv][indexh];
}
/*
* Reading s_groups_count requires using smp_rmb() afterwards. See
* the locking protocol documented in the comments of ext4_group_add()
* in resize.c
*/
static inline ext4_group_t ext4_get_groups_count(struct super_block *sb)
{
ext4_group_t ngroups = EXT4_SB(sb)->s_groups_count;
smp_rmb();
return ngroups;
}
static inline ext4_group_t ext4_flex_group(struct ext4_sb_info *sbi,
ext4_group_t block_group)
{
return block_group >> sbi->s_log_groups_per_flex;
}
static inline unsigned int ext4_flex_bg_size(struct ext4_sb_info *sbi)
{
return 1 << sbi->s_log_groups_per_flex;
}
#define ext4_std_error(sb, errno) \
do { \
if ((errno)) \
__ext4_std_error((sb), __func__, __LINE__, (errno)); \
} while (0)
#ifdef CONFIG_SMP
/* Each CPU can accumulate percpu_counter_batch clusters in their local
* counters. So we need to make sure we have free clusters more
* than percpu_counter_batch * nr_cpu_ids. Also add a window of 4 times.
*/
#define EXT4_FREECLUSTERS_WATERMARK (4 * (percpu_counter_batch * nr_cpu_ids))
#else
#define EXT4_FREECLUSTERS_WATERMARK 0
#endif
static inline void ext4_update_i_disksize(struct inode *inode, loff_t newsize)
{
/*
* XXX: replace with spinlock if seen contended -bzzz
*/
down_write(&EXT4_I(inode)->i_data_sem);
if (newsize > EXT4_I(inode)->i_disksize)
EXT4_I(inode)->i_disksize = newsize;
up_write(&EXT4_I(inode)->i_data_sem);
return ;
}
struct ext4_group_info {
unsigned long bb_state;
struct rb_root bb_free_root;
ext4_grpblk_t bb_first_free; /* first free block */
ext4_grpblk_t bb_free; /* total free blocks */
ext4_grpblk_t bb_fragments; /* nr of freespace fragments */
ext4_grpblk_t bb_largest_free_order;/* order of largest frag in BG */
struct list_head bb_prealloc_list;
#ifdef DOUBLE_CHECK
void *bb_bitmap;
#endif
struct rw_semaphore alloc_sem;
ext4_grpblk_t bb_counters[]; /* Nr of free power-of-two-block
* regions, index is order.
* bb_counters[3] = 5 means
* 5 free 8-block regions. */
};
ext4: Speed up FITRIM by recording flags in ext4_group_info In ext4, when FITRIM is called every time, we iterate all the groups and do trim one by one. It is a bit time wasting if the group has been trimmed and there is no change since the last trim. So this patch adds a new flag in ext4_group_info->bb_state to indicate that the group has been trimmed, and it will be cleared if some blocks is freed(in release_blocks_on_commit). Another trim_minlen is added in ext4_sb_info to record the last minlen we use to trim the volume, so that if the caller provide a small one, we will go on the trim regardless of the bb_state. A simple test with my intel x25m ssd: df -h shows: /dev/sdb1 40G 21G 17G 56% /mnt/ext4 Block size: 4096 run the FITRIM with the following parameter: range.start = 0; range.len = UINT64_MAX; range.minlen = 1048576; without the patch: [root@boyu-tm linux-2.6]# time ./ftrim /mnt/ext4/a real 0m5.505s user 0m0.000s sys 0m1.224s [root@boyu-tm linux-2.6]# time ./ftrim /mnt/ext4/a real 0m5.359s user 0m0.000s sys 0m1.178s [root@boyu-tm linux-2.6]# time ./ftrim /mnt/ext4/a real 0m5.228s user 0m0.000s sys 0m1.151s with the patch: [root@boyu-tm linux-2.6]# time ./ftrim /mnt/ext4/a real 0m5.625s user 0m0.000s sys 0m1.269s [root@boyu-tm linux-2.6]# time ./ftrim /mnt/ext4/a real 0m0.002s user 0m0.000s sys 0m0.001s [root@boyu-tm linux-2.6]# time ./ftrim /mnt/ext4/a real 0m0.002s user 0m0.000s sys 0m0.001s A big improvement for the 2nd and 3rd run. Even after I delete some big image files, it is still much faster than iterating the whole disk. [root@boyu-tm test]# time ./ftrim /mnt/ext4/a real 0m1.217s user 0m0.000s sys 0m0.196s Cc: Lukas Czerner <lczerner@redhat.com> Reviewed-by: Andreas Dilger <adilger.kernel@dilger.ca> Signed-off-by: Tao Ma <boyu.mt@taobao.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2011-07-11 04:03:38 +00:00
#define EXT4_GROUP_INFO_NEED_INIT_BIT 0
#define EXT4_GROUP_INFO_WAS_TRIMMED_BIT 1
#define EXT4_MB_GRP_NEED_INIT(grp) \
(test_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &((grp)->bb_state)))
ext4: Speed up FITRIM by recording flags in ext4_group_info In ext4, when FITRIM is called every time, we iterate all the groups and do trim one by one. It is a bit time wasting if the group has been trimmed and there is no change since the last trim. So this patch adds a new flag in ext4_group_info->bb_state to indicate that the group has been trimmed, and it will be cleared if some blocks is freed(in release_blocks_on_commit). Another trim_minlen is added in ext4_sb_info to record the last minlen we use to trim the volume, so that if the caller provide a small one, we will go on the trim regardless of the bb_state. A simple test with my intel x25m ssd: df -h shows: /dev/sdb1 40G 21G 17G 56% /mnt/ext4 Block size: 4096 run the FITRIM with the following parameter: range.start = 0; range.len = UINT64_MAX; range.minlen = 1048576; without the patch: [root@boyu-tm linux-2.6]# time ./ftrim /mnt/ext4/a real 0m5.505s user 0m0.000s sys 0m1.224s [root@boyu-tm linux-2.6]# time ./ftrim /mnt/ext4/a real 0m5.359s user 0m0.000s sys 0m1.178s [root@boyu-tm linux-2.6]# time ./ftrim /mnt/ext4/a real 0m5.228s user 0m0.000s sys 0m1.151s with the patch: [root@boyu-tm linux-2.6]# time ./ftrim /mnt/ext4/a real 0m5.625s user 0m0.000s sys 0m1.269s [root@boyu-tm linux-2.6]# time ./ftrim /mnt/ext4/a real 0m0.002s user 0m0.000s sys 0m0.001s [root@boyu-tm linux-2.6]# time ./ftrim /mnt/ext4/a real 0m0.002s user 0m0.000s sys 0m0.001s A big improvement for the 2nd and 3rd run. Even after I delete some big image files, it is still much faster than iterating the whole disk. [root@boyu-tm test]# time ./ftrim /mnt/ext4/a real 0m1.217s user 0m0.000s sys 0m0.196s Cc: Lukas Czerner <lczerner@redhat.com> Reviewed-by: Andreas Dilger <adilger.kernel@dilger.ca> Signed-off-by: Tao Ma <boyu.mt@taobao.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2011-07-11 04:03:38 +00:00
#define EXT4_MB_GRP_WAS_TRIMMED(grp) \
(test_bit(EXT4_GROUP_INFO_WAS_TRIMMED_BIT, &((grp)->bb_state)))
#define EXT4_MB_GRP_SET_TRIMMED(grp) \
(set_bit(EXT4_GROUP_INFO_WAS_TRIMMED_BIT, &((grp)->bb_state)))
#define EXT4_MB_GRP_CLEAR_TRIMMED(grp) \
(clear_bit(EXT4_GROUP_INFO_WAS_TRIMMED_BIT, &((grp)->bb_state)))
#define EXT4_MAX_CONTENTION 8
#define EXT4_CONTENTION_THRESHOLD 2
static inline spinlock_t *ext4_group_lock_ptr(struct super_block *sb,
ext4_group_t group)
{
return bgl_lock_ptr(EXT4_SB(sb)->s_blockgroup_lock, group);
}
/*
* Returns true if the filesystem is busy enough that attempts to
* access the block group locks has run into contention.
*/
static inline int ext4_fs_is_busy(struct ext4_sb_info *sbi)
{
return (atomic_read(&sbi->s_lock_busy) > EXT4_CONTENTION_THRESHOLD);
}
static inline void ext4_lock_group(struct super_block *sb, ext4_group_t group)
{
spinlock_t *lock = ext4_group_lock_ptr(sb, group);
if (spin_trylock(lock))
/*
* We're able to grab the lock right away, so drop the
* lock contention counter.
*/
atomic_add_unless(&EXT4_SB(sb)->s_lock_busy, -1, 0);
else {
/*
* The lock is busy, so bump the contention counter,
* and then wait on the spin lock.
*/
atomic_add_unless(&EXT4_SB(sb)->s_lock_busy, 1,
EXT4_MAX_CONTENTION);
spin_lock(lock);
}
}
static inline void ext4_unlock_group(struct super_block *sb,
ext4_group_t group)
{
spin_unlock(ext4_group_lock_ptr(sb, group));
}
static inline void ext4_mark_super_dirty(struct super_block *sb)
{
struct ext4_super_block *es = EXT4_SB(sb)->s_es;
ext4_superblock_csum_set(sb, es);
if (EXT4_SB(sb)->s_journal == NULL)
sb->s_dirt =1;
}
/*
* Block validity checking
*/
#define ext4_check_indirect_blockref(inode, bh) \
ext4_check_blockref(__func__, __LINE__, inode, \
(__le32 *)(bh)->b_data, \
EXT4_ADDR_PER_BLOCK((inode)->i_sb))
#define ext4_ind_check_inode(inode) \
ext4_check_blockref(__func__, __LINE__, inode, \
EXT4_I(inode)->i_data, \
EXT4_NDIR_BLOCKS)
/*
* Inodes and files operations
*/
/* dir.c */
extern const struct file_operations ext4_dir_operations;
/* file.c */
extern const struct inode_operations ext4_file_inode_operations;
extern const struct file_operations ext4_file_operations;
ext4: improve llseek error handling for overly large seek offsets The llseek system call should return EINVAL if passed a seek offset which results in a write error. What this maximum offset should be depends on whether or not the huge_file file system feature is set, and whether or not the file is extent based or not. If the file has no "EXT4_EXTENTS_FL" flag, the maximum size which can be written (write systemcall) is different from the maximum size which can be sought (lseek systemcall). For example, the following 2 cases demonstrates the differences between the maximum size which can be written, versus the seek offset allowed by the llseek system call: #1: mkfs.ext3 <dev>; mount -t ext4 <dev> #2: mkfs.ext3 <dev>; tune2fs -Oextent,huge_file <dev>; mount -t ext4 <dev> Table. the max file size which we can write or seek at each filesystem feature tuning and file flag setting +============+===============================+===============================+ | \ File flag| | | | \ | !EXT4_EXTENTS_FL | EXT4_EXTETNS_FL | |case \| | | +------------+-------------------------------+-------------------------------+ | #1 | write: 2194719883264 | write: -------------- | | | seek: 2199023251456 | seek: -------------- | +------------+-------------------------------+-------------------------------+ | #2 | write: 4402345721856 | write: 17592186044415 | | | seek: 17592186044415 | seek: 17592186044415 | +------------+-------------------------------+-------------------------------+ The differences exist because ext4 has 2 maxbytes which are sb->s_maxbytes (= extent-mapped maxbytes) and EXT4_SB(sb)->s_bitmap_maxbytes (= block-mapped maxbytes). Although generic_file_llseek uses only extent-mapped maxbytes. (llseek of ext4_file_operations is generic_file_llseek which uses sb->s_maxbytes.) Therefore we create ext4 llseek function which uses 2 maxbytes. The new own function originates from generic_file_llseek(). If the file flag, "EXT4_EXTENTS_FL" is not set, the function alters inode->i_sb->s_maxbytes into EXT4_SB(inode->i_sb)->s_bitmap_maxbytes. Signed-off-by: Toshiyuki Okajima <toshi.okajima@jp.fujitsu.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu> Cc: Andreas Dilger <adilger.kernel@dilger.ca>
2010-10-28 01:30:06 +00:00
extern loff_t ext4_llseek(struct file *file, loff_t offset, int origin);
/* namei.c */
extern const struct inode_operations ext4_dir_inode_operations;
extern const struct inode_operations ext4_special_inode_operations;
extern struct dentry *ext4_get_parent(struct dentry *child);
/* symlink.c */
extern const struct inode_operations ext4_symlink_inode_operations;
extern const struct inode_operations ext4_fast_symlink_inode_operations;
/* block_validity */
extern void ext4_release_system_zone(struct super_block *sb);
extern int ext4_setup_system_zone(struct super_block *sb);
extern int __init ext4_init_system_zone(void);
extern void ext4_exit_system_zone(void);
extern int ext4_data_block_valid(struct ext4_sb_info *sbi,
ext4_fsblk_t start_blk,
unsigned int count);
extern int ext4_check_blockref(const char *, unsigned int,
struct inode *, __le32 *, unsigned int);
/* extents.c */
extern int ext4_ext_tree_init(handle_t *handle, struct inode *);
extern int ext4_ext_writepage_trans_blocks(struct inode *, int);
extern int ext4_ext_index_trans_blocks(struct inode *inode, int nrblocks,
int chunk);
extern int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
struct ext4_map_blocks *map, int flags);
extern void ext4_ext_truncate(struct inode *);
extern int ext4_ext_punch_hole(struct file *file, loff_t offset,
loff_t length);
extern void ext4_ext_init(struct super_block *);
extern void ext4_ext_release(struct super_block *);
extern long ext4_fallocate(struct file *file, int mode, loff_t offset,
loff_t len);
extern int ext4_convert_unwritten_extents(struct inode *inode, loff_t offset,
ssize_t len);
extern int ext4_map_blocks(handle_t *handle, struct inode *inode,
struct ext4_map_blocks *map, int flags);
extern int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
__u64 start, __u64 len);
/* move_extent.c */
extern int ext4_move_extents(struct file *o_filp, struct file *d_filp,
__u64 start_orig, __u64 start_donor,
__u64 len, __u64 *moved_len);
/* page-io.c */
extern int __init ext4_init_pageio(void);
extern void ext4_exit_pageio(void);
ext4: handle writeback of inodes which are being freed The following BUG can occur when an inode which is getting freed when it still has dirty pages outstanding, and it gets deleted (in this because it was the target of a rename). In ordered mode, we need to make sure the data pages are written just in case we crash before the rename (or unlink) is committed. If the inode is being freed then when we try to igrab the inode, we end up tripping the BUG_ON at fs/ext4/page-io.c:146. To solve this problem, we need to keep track of the number of io callbacks which are pending, and avoid destroying the inode until they have all been completed. That way we don't have to bump the inode count to keep the inode from being destroyed; an approach which doesn't work because the count could have already been dropped down to zero before the inode writeback has started (at which point we're not allowed to bump the count back up to 1, since it's already started getting freed). Thanks to Dave Chinner for suggesting this approach, which is also used by XFS. kernel BUG at /scratch_space/linux-2.6/fs/ext4/page-io.c:146! Call Trace: [<ffffffff811075b1>] ext4_bio_write_page+0x172/0x307 [<ffffffff811033a7>] mpage_da_submit_io+0x2f9/0x37b [<ffffffff811068d7>] mpage_da_map_and_submit+0x2cc/0x2e2 [<ffffffff811069b3>] mpage_add_bh_to_extent+0xc6/0xd5 [<ffffffff81106c66>] write_cache_pages_da+0x2a4/0x3ac [<ffffffff81107044>] ext4_da_writepages+0x2d6/0x44d [<ffffffff81087910>] do_writepages+0x1c/0x25 [<ffffffff810810a4>] __filemap_fdatawrite_range+0x4b/0x4d [<ffffffff810815f5>] filemap_fdatawrite_range+0xe/0x10 [<ffffffff81122a2e>] jbd2_journal_begin_ordered_truncate+0x7b/0xa2 [<ffffffff8110615d>] ext4_evict_inode+0x57/0x24c [<ffffffff810c14a3>] evict+0x22/0x92 [<ffffffff810c1a3d>] iput+0x212/0x249 [<ffffffff810bdf16>] dentry_iput+0xa1/0xb9 [<ffffffff810bdf6b>] d_kill+0x3d/0x5d [<ffffffff810be613>] dput+0x13a/0x147 [<ffffffff810b990d>] sys_renameat+0x1b5/0x258 [<ffffffff81145f71>] ? _atomic_dec_and_lock+0x2d/0x4c [<ffffffff810b2950>] ? cp_new_stat+0xde/0xea [<ffffffff810b29c1>] ? sys_newlstat+0x2d/0x38 [<ffffffff810b99c6>] sys_rename+0x16/0x18 [<ffffffff81002a2b>] system_call_fastpath+0x16/0x1b Reported-by: Nick Bowler <nbowler@elliptictech.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu> Tested-by: Nick Bowler <nbowler@elliptictech.com>
2010-11-08 18:43:33 +00:00
extern void ext4_ioend_wait(struct inode *);
extern void ext4_free_io_end(ext4_io_end_t *io);
extern ext4_io_end_t *ext4_init_io_end(struct inode *inode, gfp_t flags);
extern int ext4_end_io_nolock(ext4_io_end_t *io);
extern void ext4_io_submit(struct ext4_io_submit *io);
extern int ext4_bio_write_page(struct ext4_io_submit *io,
struct page *page,
int len,
struct writeback_control *wbc);
/* mmp.c */
extern int ext4_multi_mount_protect(struct super_block *, ext4_fsblk_t);
extern void ext4_mmp_csum_set(struct super_block *sb, struct mmp_struct *mmp);
extern int ext4_mmp_csum_verify(struct super_block *sb,
struct mmp_struct *mmp);
/* BH_Uninit flag: blocks are allocated but uninitialized on disk */
enum ext4_state_bits {
BH_Uninit /* blocks are allocated but uninitialized on disk */
= BH_JBDPrivateStart,
BH_AllocFromCluster, /* allocated blocks were part of already
* allocated cluster. Note that this flag will
* never, ever appear in a buffer_head's state
* flag. See EXT4_MAP_FROM_CLUSTER to see where
* this is used. */
ext4: attempt to fix race in bigalloc code path Currently, there exists a race between delayed allocated writes and the writeback when bigalloc feature is in use. The race was because we wanted to determine what blocks in a cluster are under delayed allocation and we were using buffer_delayed(bh) check for it. But, the writeback codepath clears this bit without any synchronization which resulted in a race and an ext4 warning similar to: EXT4-fs (ram1): ext4_da_update_reserve_space: ino 13, used 1 with only 0 reserved data blocks The race existed in two places. (1) between ext4_find_delalloc_range() and ext4_map_blocks() when called from writeback code path. (2) between ext4_find_delalloc_range() and ext4_da_get_block_prep() (where buffer_delayed(bh) is set. To fix (1), this patch introduces a new buffer_head state bit - BH_Da_Mapped. This bit is set under the protection of EXT4_I(inode)->i_data_sem when we have actually mapped the delayed allocated blocks during the writeout time. We can now reliably check for this bit inside ext4_find_delalloc_range() to determine whether the reservation for the blocks have already been claimed or not. To fix (2), it was necessary to set buffer_delay(bh) under the protection of i_data_sem. So, I extracted the very beginning of ext4_map_blocks into a new function - ext4_da_map_blocks() - and performed the required setting of bh_delay bit and the quota reservation under the protection of i_data_sem. These two fixes makes the checking of buffer_delay(bh) and buffer_da_mapped(bh) consistent, thus removing the race. Tested: I was able to reproduce the problem by running 'dd' and 'fsync' in parallel. Also, xfstests sometimes used to reproduce this race. After the fix both my test and xfstests were successful and no race (warning message) was observed. Google-Bug-Id: 4997027 Signed-off-by: Aditya Kali <adityakali@google.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2011-09-09 23:20:51 +00:00
BH_Da_Mapped, /* Delayed allocated block that now has a mapping. This
* flag is set when ext4_map_blocks is called on a
* delayed allocated block to get its real mapping. */
};
BUFFER_FNS(Uninit, uninit)
TAS_BUFFER_FNS(Uninit, uninit)
ext4: attempt to fix race in bigalloc code path Currently, there exists a race between delayed allocated writes and the writeback when bigalloc feature is in use. The race was because we wanted to determine what blocks in a cluster are under delayed allocation and we were using buffer_delayed(bh) check for it. But, the writeback codepath clears this bit without any synchronization which resulted in a race and an ext4 warning similar to: EXT4-fs (ram1): ext4_da_update_reserve_space: ino 13, used 1 with only 0 reserved data blocks The race existed in two places. (1) between ext4_find_delalloc_range() and ext4_map_blocks() when called from writeback code path. (2) between ext4_find_delalloc_range() and ext4_da_get_block_prep() (where buffer_delayed(bh) is set. To fix (1), this patch introduces a new buffer_head state bit - BH_Da_Mapped. This bit is set under the protection of EXT4_I(inode)->i_data_sem when we have actually mapped the delayed allocated blocks during the writeout time. We can now reliably check for this bit inside ext4_find_delalloc_range() to determine whether the reservation for the blocks have already been claimed or not. To fix (2), it was necessary to set buffer_delay(bh) under the protection of i_data_sem. So, I extracted the very beginning of ext4_map_blocks into a new function - ext4_da_map_blocks() - and performed the required setting of bh_delay bit and the quota reservation under the protection of i_data_sem. These two fixes makes the checking of buffer_delay(bh) and buffer_da_mapped(bh) consistent, thus removing the race. Tested: I was able to reproduce the problem by running 'dd' and 'fsync' in parallel. Also, xfstests sometimes used to reproduce this race. After the fix both my test and xfstests were successful and no race (warning message) was observed. Google-Bug-Id: 4997027 Signed-off-by: Aditya Kali <adityakali@google.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2011-09-09 23:20:51 +00:00
BUFFER_FNS(Da_Mapped, da_mapped)
/*
* Add new method to test wether block and inode bitmaps are properly
* initialized. With uninit_bg reading the block from disk is not enough
* to mark the bitmap uptodate. We need to also zero-out the bitmap
*/
#define BH_BITMAP_UPTODATE BH_JBDPrivateStart
static inline int bitmap_uptodate(struct buffer_head *bh)
{
return (buffer_uptodate(bh) &&
test_bit(BH_BITMAP_UPTODATE, &(bh)->b_state));
}
static inline void set_bitmap_uptodate(struct buffer_head *bh)
{
set_bit(BH_BITMAP_UPTODATE, &(bh)->b_state);
}
#define in_range(b, first, len) ((b) >= (first) && (b) <= (first) + (len) - 1)
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 13:17:34 +00:00
/* For ioend & aio unwritten conversion wait queues */
#define EXT4_WQ_HASH_SZ 37
#define ext4_ioend_wq(v) (&ext4__ioend_wq[((unsigned long)(v)) %\
EXT4_WQ_HASH_SZ])
#define ext4_aio_mutex(v) (&ext4__aio_mutex[((unsigned long)(v)) %\
EXT4_WQ_HASH_SZ])
extern wait_queue_head_t ext4__ioend_wq[EXT4_WQ_HASH_SZ];
extern struct mutex ext4__aio_mutex[EXT4_WQ_HASH_SZ];
#define EXT4_RESIZING 0
extern int ext4_resize_begin(struct super_block *sb);
extern void ext4_resize_end(struct super_block *sb);
#endif /* __KERNEL__ */
#include "ext4_extents.h"
#endif /* _EXT4_H */