linux/fs/ext4/ext4.h

3904 lines
135 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0
/*
* 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/refcount.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/sched/signal.h>
#include <linux/blockgroup_lock.h>
#include <linux/percpu_counter.h>
#include <linux/ratelimit.h>
#include <crypto/hash.h>
#include <linux/falloc.h>
#include <linux/percpu-rwsem.h>
#include <linux/fiemap.h>
#ifdef __KERNEL__
#include <linux/compat.h>
#endif
#include <linux/fscrypt.h>
ext4: add basic fs-verity support Add most of fs-verity support to ext4. fs-verity is a filesystem feature that enables transparent integrity protection and authentication of read-only files. It uses a dm-verity like mechanism at the file level: a Merkle tree is used to verify any block in the file in log(filesize) time. It is implemented mainly by helper functions in fs/verity/. See Documentation/filesystems/fsverity.rst for the full documentation. This commit adds all of ext4 fs-verity support except for the actual data verification, including: - Adding a filesystem feature flag and an inode flag for fs-verity. - Implementing the fsverity_operations to support enabling verity on an inode and reading/writing the verity metadata. - Updating ->write_begin(), ->write_end(), and ->writepages() to support writing verity metadata pages. - Calling the fs-verity hooks for ->open(), ->setattr(), and ->ioctl(). ext4 stores the verity metadata (Merkle tree and fsverity_descriptor) past the end of the file, starting at the first 64K boundary beyond i_size. This approach works because (a) verity files are readonly, and (b) pages fully beyond i_size aren't visible to userspace but can be read/written internally by ext4 with only some relatively small changes to ext4. This approach avoids having to depend on the EA_INODE feature and on rearchitecturing ext4's xattr support to support paging multi-gigabyte xattrs into memory, and to support encrypting xattrs. Note that the verity metadata *must* be encrypted when the file is, since it contains hashes of the plaintext data. This patch incorporates work by Theodore Ts'o and Chandan Rajendra. Reviewed-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Eric Biggers <ebiggers@google.com>
2019-07-23 00:26:24 +08:00
#include <linux/fsverity.h>
#include <linux/compiler.h>
/*
* The fourth extended filesystem constants/structures
*/
/*
* with AGGRESSIVE_CHECK allocator runs consistency checks over
* structures. these checks slow things down a lot
*/
#define AGGRESSIVE_CHECK__
/*
* with DOUBLE_CHECK defined mballoc creates persistent in-core
* bitmaps, maintains and uses them to check for double allocations
*/
#define DOUBLE_CHECK__
/*
* 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
/*
* Turn on EXT_DEBUG to enable ext4_ext_show_path/leaf/move in extents.c
*/
#define EXT_DEBUG__
/*
* Dynamic printk for controlled extents debugging.
*/
#ifdef CONFIG_EXT4_DEBUG
#define ext_debug(ino, fmt, ...) \
pr_debug("[%s/%d] EXT4-fs (%s): ino %lu: (%s, %d): %s:" fmt, \
current->comm, task_pid_nr(current), \
ino->i_sb->s_id, ino->i_ino, __FILE__, __LINE__, \
__func__, ##__VA_ARGS__)
#else
#define ext_debug(ino, fmt, ...) no_printk(fmt, ##__VA_ARGS__)
#endif
#define ASSERT(assert) \
do { \
if (unlikely(!(assert))) { \
printk(KERN_EMERG \
"Assertion failure in %s() at %s:%d: '%s'\n", \
__func__, __FILE__, __LINE__, #assert); \
BUG(); \
} \
} while (0)
/* 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;
enum SHIFT_DIRECTION {
SHIFT_LEFT = 0,
SHIFT_RIGHT,
};
/*
* 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
ext4: introduce reserved space Currently in ENOSPC condition when writing into unwritten space, or punching a hole, we might need to split the extent and grow extent tree. However since we can not allocate any new metadata blocks we'll have to zero out unwritten part of extent or punched out part of extent, or in the worst case return ENOSPC even though use actually does not allocate any space. Also in delalloc path we do reserve metadata and data blocks for the time we're going to write out, however metadata block reservation is very tricky especially since we expect that logical connectivity implies physical connectivity, however that might not be the case and hence we might end up allocating more metadata blocks than previously reserved. So in future, metadata reservation checks should be removed since we can not assure that we do not under reserve. And this is where reserved space comes into the picture. When mounting the file system we slice off a little bit of the file system space (2% or 4096 clusters, whichever is smaller) which can be then used for the cases mentioned above to prevent costly zeroout, or unexpected ENOSPC. The number of reserved clusters can be set via sysfs, however it can never be bigger than number of free clusters in the file system. Note that this patch fixes the failure of xfstest 274 as expected. Signed-off-by: Lukas Czerner <lczerner@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu> Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
2013-04-10 10:11:22 +08:00
/* Use blocks from reserved pool */
#define EXT4_MB_USE_RESERVED 0x2000
/* Do strict check for free blocks while retrying block allocation */
#define EXT4_MB_STRICT_CHECK 0x4000
ext4: improve cr 0 / cr 1 group scanning Instead of traversing through groups linearly, scan groups in specific orders at cr 0 and cr 1. At cr 0, we want to find groups that have the largest free order >= the order of the request. So, with this patch, we maintain lists for each possible order and insert each group into a list based on the largest free order in its buddy bitmap. During cr 0 allocation, we traverse these lists in the increasing order of largest free orders. This allows us to find a group with the best available cr 0 match in constant time. If nothing can be found, we fallback to cr 1 immediately. At CR1, the story is slightly different. We want to traverse in the order of increasing average fragment size. For CR1, we maintain a rb tree of groupinfos which is sorted by average fragment size. Instead of traversing linearly, at CR1, we traverse in the order of increasing average fragment size, starting at the most optimal group. This brings down cr 1 search complexity to log(num groups). For cr >= 2, we just perform the linear search as before. Also, in case of lock contention, we intermittently fallback to linear search even in CR 0 and CR 1 cases. This allows us to proceed during the allocation path even in case of high contention. There is an opportunity to do optimization at CR2 too. That's because at CR2 we only consider groups where bb_free counter (number of free blocks) is greater than the request extent size. That's left as future work. All the changes introduced in this patch are protected under a new mount option "mb_optimize_scan". With this patchset, following experiment was performed: Created a highly fragmented disk of size 65TB. The disk had no contiguous 2M regions. Following command was run consecutively for 3 times: time dd if=/dev/urandom of=file bs=2M count=10 Here are the results with and without cr 0/1 optimizations introduced in this patch: |---------+------------------------------+---------------------------| | | Without CR 0/1 Optimizations | With CR 0/1 Optimizations | |---------+------------------------------+---------------------------| | 1st run | 5m1.871s | 2m47.642s | | 2nd run | 2m28.390s | 0m0.611s | | 3rd run | 2m26.530s | 0m1.255s | |---------+------------------------------+---------------------------| Signed-off-by: Harshad Shirwadkar <harshadshirwadkar@gmail.com> Reported-by: kernel test robot <lkp@intel.com> Reported-by: Dan Carpenter <dan.carpenter@oracle.com> Reviewed-by: Andreas Dilger <adilger@dilger.ca> Link: https://lore.kernel.org/r/20210401172129.189766-6-harshadshirwadkar@gmail.com Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2021-04-02 01:21:27 +08:00
/* Large fragment size list lookup succeeded at least once for cr = 0 */
#define EXT4_MB_CR0_OPTIMIZED 0x8000
/* Avg fragment size rb tree lookup succeeded at least once for cr = 1 */
#define EXT4_MB_CR1_OPTIMIZED 0x00010000
/* Perform linear traversal for one group */
#define EXT4_MB_SEARCH_NEXT_LINEAR 0x00020000
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 BIT(BH_New)
#define EXT4_MAP_MAPPED BIT(BH_Mapped)
#define EXT4_MAP_UNWRITTEN BIT(BH_Unwritten)
#define EXT4_MAP_BOUNDARY BIT(BH_Boundary)
#define EXT4_MAP_FLAGS (EXT4_MAP_NEW | EXT4_MAP_MAPPED |\
EXT4_MAP_UNWRITTEN | EXT4_MAP_BOUNDARY)
struct ext4_map_blocks {
ext4_fsblk_t m_pblk;
ext4_lblk_t m_lblk;
unsigned int m_len;
unsigned int m_flags;
};
/*
* Block validity checking, system zone rbtree.
*/
struct ext4_system_blocks {
struct rb_root root;
struct rcu_head rcu;
};
/*
* Flags for ext4_io_end->flags
*/
#define EXT4_IO_END_UNWRITTEN 0x0001
struct ext4_io_end_vec {
struct list_head list; /* list of io_end_vec */
loff_t offset; /* offset in the file */
ssize_t size; /* size of the extent */
};
/*
* For converting unwritten extents on a work queue. 'handle' is used for
* buffered writeback.
*/
typedef struct ext4_io_end {
struct list_head list; /* per-file finished IO list */
handle_t *handle; /* handle reserved for extent
* conversion */
struct inode *inode; /* file being written to */
struct bio *bio; /* Linked list of completed
* bios covering the extent */
unsigned int flag; /* unwritten or not */
refcount_t count; /* reference counter */
struct list_head list_vec; /* list of ext4_io_end_vec */
} ext4_io_end_t;
struct ext4_io_submit {
struct writeback_control *io_wbc;
struct bio *io_bio;
ext4_io_end_t *io_end;
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
#define EXT4_MAX_CLUSTER_LOG_SIZE 30
#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)))
#define EXT4_MAX_BLOCKS(size, offset, blkbits) \
((EXT4_BLOCK_ALIGN(size + offset, blkbits) >> blkbits) - (offset >> \
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)
/* Mask out the low bits to get the starting block of the cluster */
#define EXT4_PBLK_CMASK(s, pblk) ((pblk) & \
~((ext4_fsblk_t) (s)->s_cluster_ratio - 1))
#define EXT4_LBLK_CMASK(s, lblk) ((lblk) & \
~((ext4_lblk_t) (s)->s_cluster_ratio - 1))
/* Fill in the low bits to get the last block of the cluster */
#define EXT4_LBLK_CFILL(sbi, lblk) ((lblk) | \
((ext4_lblk_t) (sbi)->s_cluster_ratio - 1))
/* Get the cluster offset */
#define EXT4_PBLK_COFF(s, pblk) ((pblk) & \
((ext4_fsblk_t) (s)->s_cluster_ratio - 1))
#define EXT4_LBLK_COFF(s, lblk) ((lblk) & \
((ext4_lblk_t) (s)->s_cluster_ratio - 1))
/*
* 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>
2007-10-17 06:38:25 +08:00
__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>
2007-10-17 06:38:25 +08:00
__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 {
atomic64_t free_clusters;
atomic_t free_inodes;
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>
2007-10-17 06:38:25 +08:00
#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 */
/* nb: was previously EXT2_ECOMPR_FL */
#define EXT4_ENCRYPT_FL 0x00000800 /* encrypted file */
/* 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 */
ext4: add basic fs-verity support Add most of fs-verity support to ext4. fs-verity is a filesystem feature that enables transparent integrity protection and authentication of read-only files. It uses a dm-verity like mechanism at the file level: a Merkle tree is used to verify any block in the file in log(filesize) time. It is implemented mainly by helper functions in fs/verity/. See Documentation/filesystems/fsverity.rst for the full documentation. This commit adds all of ext4 fs-verity support except for the actual data verification, including: - Adding a filesystem feature flag and an inode flag for fs-verity. - Implementing the fsverity_operations to support enabling verity on an inode and reading/writing the verity metadata. - Updating ->write_begin(), ->write_end(), and ->writepages() to support writing verity metadata pages. - Calling the fs-verity hooks for ->open(), ->setattr(), and ->ioctl(). ext4 stores the verity metadata (Merkle tree and fsverity_descriptor) past the end of the file, starting at the first 64K boundary beyond i_size. This approach works because (a) verity files are readonly, and (b) pages fully beyond i_size aren't visible to userspace but can be read/written internally by ext4 with only some relatively small changes to ext4. This approach avoids having to depend on the EA_INODE feature and on rearchitecturing ext4's xattr support to support paging multi-gigabyte xattrs into memory, and to support encrypting xattrs. Note that the verity metadata *must* be encrypted when the file is, since it contains hashes of the plaintext data. This patch incorporates work by Theodore Ts'o and Chandan Rajendra. Reviewed-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Eric Biggers <ebiggers@google.com>
2019-07-23 00:26:24 +08:00
#define EXT4_VERITY_FL 0x00100000 /* Verity protected inode */
#define EXT4_EA_INODE_FL 0x00200000 /* Inode used for large EA */
ext4: remove EXT4_EOFBLOCKS_FL and associated code The EXT4_EOFBLOCKS_FL inode flag is used to indicate whether a file contains unwritten blocks past i_size. It's set when ext4_fallocate is called with the KEEP_SIZE flag to extend a file with an unwritten extent. However, this flag hasn't been useful functionally since March, 2012, when a decision was made to remove it from ext4. All traces of EXT4_EOFBLOCKS_FL were removed from e2fsprogs version 1.42.2 by commit 010dc7b90d97 ("e2fsck: remove EXT4_EOFBLOCKS_FL flag handling") at that time. Now that enough time has passed to make e2fsprogs versions containing this modification common, this patch now removes the code associated with EXT4_EOFBLOCKS_FL from the kernel as well. This change has two implications. First, because pre-1.42.2 e2fsck versions only look for a problem if EXT4_EOFBLOCKS_FL is set, and because that bit will never be set by newer kernels containing this patch, old versions of e2fsck won't have a compatibility problem with files created by newer kernels. Second, newer kernels will not clear EXT4_EOFBLOCKS_FL inode flag bits belonging to a file written by an older kernel. If set, it will remain in that state until the file is deleted. Because e2fsck versions since 1.42.2 don't check the flag at all, no adverse effect is expected. However, pre-1.42.2 e2fsck versions that do check the flag may report that it is set when it ought not to be after a file has been truncated or had its unwritten blocks written. In this case, the old version of e2fsck will offer to clear the flag. No adverse effect would then occur whether the user chooses to clear the flag or not. Signed-off-by: Eric Whitney <enwlinux@gmail.com> Link: https://lore.kernel.org/r/20200211210216.24960-1-enwlinux@gmail.com Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2020-02-12 05:02:16 +08:00
/* 0x00400000 was formerly EXT4_EOFBLOCKS_FL */
#define EXT4_DAX_FL 0x02000000 /* Inode is DAX */
#define EXT4_INLINE_DATA_FL 0x10000000 /* Inode has inline data. */
#define EXT4_PROJINHERIT_FL 0x20000000 /* Create with parents projid */
#define EXT4_CASEFOLD_FL 0x40000000 /* Casefolded directory */
#define EXT4_RESERVED_FL 0x80000000 /* reserved for ext4 lib */
/* User modifiable flags */
#define EXT4_FL_USER_MODIFIABLE (EXT4_SECRM_FL | \
EXT4_UNRM_FL | \
EXT4_COMPR_FL | \
EXT4_SYNC_FL | \
EXT4_IMMUTABLE_FL | \
EXT4_APPEND_FL | \
EXT4_NODUMP_FL | \
EXT4_NOATIME_FL | \
EXT4_JOURNAL_DATA_FL | \
EXT4_NOTAIL_FL | \
EXT4_DIRSYNC_FL | \
EXT4_TOPDIR_FL | \
EXT4_EXTENTS_FL | \
0x00400000 /* EXT4_EOFBLOCKS_FL */ | \
EXT4_DAX_FL | \
EXT4_PROJINHERIT_FL | \
EXT4_CASEFOLD_FL)
/* User visible flags */
#define EXT4_FL_USER_VISIBLE (EXT4_FL_USER_MODIFIABLE | \
EXT4_DIRTY_FL | \
EXT4_COMPRBLK_FL | \
EXT4_NOCOMPR_FL | \
EXT4_ENCRYPT_FL | \
EXT4_INDEX_FL | \
EXT4_VERITY_FL | \
EXT4_INLINE_DATA_FL)
/* 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 |\
EXT4_PROJINHERIT_FL | EXT4_CASEFOLD_FL |\
EXT4_DAX_FL)
/* Flags that are appropriate for regular files (all but dir-specific ones). */
#define EXT4_REG_FLMASK (~(EXT4_DIRSYNC_FL | EXT4_TOPDIR_FL | EXT4_CASEFOLD_FL |\
EXT4_PROJINHERIT_FL))
/* Flags that are appropriate for non-directories/regular files. */
#define EXT4_OTHER_FLMASK (EXT4_NODUMP_FL | EXT4_NOATIME_FL)
/* The only flags that should be swapped */
#define EXT4_FL_SHOULD_SWAP (EXT4_HUGE_FILE_FL | EXT4_EXTENTS_FL)
/* Flags which are mutually exclusive to DAX */
#define EXT4_DAX_MUT_EXCL (EXT4_VERITY_FL | EXT4_ENCRYPT_FL |\
EXT4_JOURNAL_DATA_FL | EXT4_INLINE_DATA_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_ENCRYPT = 11, /* Encrypted file */
/* 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: add basic fs-verity support Add most of fs-verity support to ext4. fs-verity is a filesystem feature that enables transparent integrity protection and authentication of read-only files. It uses a dm-verity like mechanism at the file level: a Merkle tree is used to verify any block in the file in log(filesize) time. It is implemented mainly by helper functions in fs/verity/. See Documentation/filesystems/fsverity.rst for the full documentation. This commit adds all of ext4 fs-verity support except for the actual data verification, including: - Adding a filesystem feature flag and an inode flag for fs-verity. - Implementing the fsverity_operations to support enabling verity on an inode and reading/writing the verity metadata. - Updating ->write_begin(), ->write_end(), and ->writepages() to support writing verity metadata pages. - Calling the fs-verity hooks for ->open(), ->setattr(), and ->ioctl(). ext4 stores the verity metadata (Merkle tree and fsverity_descriptor) past the end of the file, starting at the first 64K boundary beyond i_size. This approach works because (a) verity files are readonly, and (b) pages fully beyond i_size aren't visible to userspace but can be read/written internally by ext4 with only some relatively small changes to ext4. This approach avoids having to depend on the EA_INODE feature and on rearchitecturing ext4's xattr support to support paging multi-gigabyte xattrs into memory, and to support encrypting xattrs. Note that the verity metadata *must* be encrypted when the file is, since it contains hashes of the plaintext data. This patch incorporates work by Theodore Ts'o and Chandan Rajendra. Reviewed-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Eric Biggers <ebiggers@google.com>
2019-07-23 00:26:24 +08:00
EXT4_INODE_VERITY = 20, /* Verity protected inode */
EXT4_INODE_EA_INODE = 21, /* Inode used for large EA */
ext4: remove EXT4_EOFBLOCKS_FL and associated code The EXT4_EOFBLOCKS_FL inode flag is used to indicate whether a file contains unwritten blocks past i_size. It's set when ext4_fallocate is called with the KEEP_SIZE flag to extend a file with an unwritten extent. However, this flag hasn't been useful functionally since March, 2012, when a decision was made to remove it from ext4. All traces of EXT4_EOFBLOCKS_FL were removed from e2fsprogs version 1.42.2 by commit 010dc7b90d97 ("e2fsck: remove EXT4_EOFBLOCKS_FL flag handling") at that time. Now that enough time has passed to make e2fsprogs versions containing this modification common, this patch now removes the code associated with EXT4_EOFBLOCKS_FL from the kernel as well. This change has two implications. First, because pre-1.42.2 e2fsck versions only look for a problem if EXT4_EOFBLOCKS_FL is set, and because that bit will never be set by newer kernels containing this patch, old versions of e2fsck won't have a compatibility problem with files created by newer kernels. Second, newer kernels will not clear EXT4_EOFBLOCKS_FL inode flag bits belonging to a file written by an older kernel. If set, it will remain in that state until the file is deleted. Because e2fsck versions since 1.42.2 don't check the flag at all, no adverse effect is expected. However, pre-1.42.2 e2fsck versions that do check the flag may report that it is set when it ought not to be after a file has been truncated or had its unwritten blocks written. In this case, the old version of e2fsck will offer to clear the flag. No adverse effect would then occur whether the user chooses to clear the flag or not. Signed-off-by: Eric Whitney <enwlinux@gmail.com> Link: https://lore.kernel.org/r/20200211210216.24960-1-enwlinux@gmail.com Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2020-02-12 05:02:16 +08:00
/* 22 was formerly EXT4_INODE_EOFBLOCKS */
EXT4_INODE_DAX = 25, /* Inode is DAX */
EXT4_INODE_INLINE_DATA = 28, /* Data in inode. */
EXT4_INODE_PROJINHERIT = 29, /* Create with parents projid */
EXT4_INODE_CASEFOLD = 30, /* Casefolded directory */
EXT4_INODE_RESERVED = 31, /* reserved for ext4 lib */
};
/*
* Since it's pretty easy to mix up bit numbers and hex values, we use a
* build-time check to make sure that EXT4_XXX_FL is consistent with respect to
* EXT4_INODE_XXX. If all is well, the macros will be dropped, so, it won't cost
* any extra space in the compiled kernel image, otherwise, the build will fail.
* It's important that these values are the same, since we are using
* EXT4_INODE_XXX to test for flag values, but EXT4_XXX_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. :-)
*/
#define TEST_FLAG_VALUE(FLAG) (EXT4_##FLAG##_FL == (1 << EXT4_INODE_##FLAG))
#define CHECK_FLAG_VALUE(FLAG) BUILD_BUG_ON(!TEST_FLAG_VALUE(FLAG))
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(ENCRYPT);
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);
ext4: add basic fs-verity support Add most of fs-verity support to ext4. fs-verity is a filesystem feature that enables transparent integrity protection and authentication of read-only files. It uses a dm-verity like mechanism at the file level: a Merkle tree is used to verify any block in the file in log(filesize) time. It is implemented mainly by helper functions in fs/verity/. See Documentation/filesystems/fsverity.rst for the full documentation. This commit adds all of ext4 fs-verity support except for the actual data verification, including: - Adding a filesystem feature flag and an inode flag for fs-verity. - Implementing the fsverity_operations to support enabling verity on an inode and reading/writing the verity metadata. - Updating ->write_begin(), ->write_end(), and ->writepages() to support writing verity metadata pages. - Calling the fs-verity hooks for ->open(), ->setattr(), and ->ioctl(). ext4 stores the verity metadata (Merkle tree and fsverity_descriptor) past the end of the file, starting at the first 64K boundary beyond i_size. This approach works because (a) verity files are readonly, and (b) pages fully beyond i_size aren't visible to userspace but can be read/written internally by ext4 with only some relatively small changes to ext4. This approach avoids having to depend on the EA_INODE feature and on rearchitecturing ext4's xattr support to support paging multi-gigabyte xattrs into memory, and to support encrypting xattrs. Note that the verity metadata *must* be encrypted when the file is, since it contains hashes of the plaintext data. This patch incorporates work by Theodore Ts'o and Chandan Rajendra. Reviewed-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Eric Biggers <ebiggers@google.com>
2019-07-23 00:26:24 +08:00
CHECK_FLAG_VALUE(VERITY);
CHECK_FLAG_VALUE(EA_INODE);
CHECK_FLAG_VALUE(INLINE_DATA);
CHECK_FLAG_VALUE(PROJINHERIT);
CHECK_FLAG_VALUE(CASEFOLD);
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 mdata_blocks;
__u32 free_clusters_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 unwritten
extent to be an initialized ext4 */
#define EXT4_GET_BLOCKS_CREATE 0x0001
/* Request the creation of an unwritten extent */
#define EXT4_GET_BLOCKS_UNWRIT_EXT 0x0002
#define EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT (EXT4_GET_BLOCKS_UNWRIT_EXT|\
EXT4_GET_BLOCKS_CREATE)
ext4: introduce reserved space Currently in ENOSPC condition when writing into unwritten space, or punching a hole, we might need to split the extent and grow extent tree. However since we can not allocate any new metadata blocks we'll have to zero out unwritten part of extent or punched out part of extent, or in the worst case return ENOSPC even though use actually does not allocate any space. Also in delalloc path we do reserve metadata and data blocks for the time we're going to write out, however metadata block reservation is very tricky especially since we expect that logical connectivity implies physical connectivity, however that might not be the case and hence we might end up allocating more metadata blocks than previously reserved. So in future, metadata reservation checks should be removed since we can not assure that we do not under reserve. And this is where reserved space comes into the picture. When mounting the file system we slice off a little bit of the file system space (2% or 4096 clusters, whichever is smaller) which can be then used for the cases mentioned above to prevent costly zeroout, or unexpected ENOSPC. The number of reserved clusters can be set via sysfs, however it can never be bigger than number of free clusters in the file system. Note that this patch fixes the failure of xfstest 274 as expected. Signed-off-by: Lukas Czerner <lczerner@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu> Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
2013-04-10 10:11:22 +08:00
/* Caller is from the delayed allocation writeout path
* finally doing the actual allocation of delayed blocks */
#define EXT4_GET_BLOCKS_DELALLOC_RESERVE 0x0004
/* caller is from the direct IO path, request to creation of an
unwritten extents if not allocated, split the unwritten
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_UNWRIT_EXT)
/* Convert extent to initialized after IO complete */
#define EXT4_GET_BLOCKS_IO_CONVERT_EXT (EXT4_GET_BLOCKS_CONVERT|\
EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT)
ext4: introduce reserved space Currently in ENOSPC condition when writing into unwritten space, or punching a hole, we might need to split the extent and grow extent tree. However since we can not allocate any new metadata blocks we'll have to zero out unwritten part of extent or punched out part of extent, or in the worst case return ENOSPC even though use actually does not allocate any space. Also in delalloc path we do reserve metadata and data blocks for the time we're going to write out, however metadata block reservation is very tricky especially since we expect that logical connectivity implies physical connectivity, however that might not be the case and hence we might end up allocating more metadata blocks than previously reserved. So in future, metadata reservation checks should be removed since we can not assure that we do not under reserve. And this is where reserved space comes into the picture. When mounting the file system we slice off a little bit of the file system space (2% or 4096 clusters, whichever is smaller) which can be then used for the cases mentioned above to prevent costly zeroout, or unexpected ENOSPC. The number of reserved clusters can be set via sysfs, however it can never be bigger than number of free clusters in the file system. Note that this patch fixes the failure of xfstest 274 as expected. Signed-off-by: Lukas Czerner <lczerner@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu> Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
2013-04-10 10:11:22 +08:00
/* Eventual metadata allocation (due to growing extent tree)
* should not fail, so try to use reserved blocks for that.*/
#define EXT4_GET_BLOCKS_METADATA_NOFAIL 0x0020
/* Don't normalize allocation size (used for fallocate) */
#define EXT4_GET_BLOCKS_NO_NORMALIZE 0x0040
/* Convert written extents to unwritten */
#define EXT4_GET_BLOCKS_CONVERT_UNWRITTEN 0x0100
/* Write zeros to newly created written extents */
#define EXT4_GET_BLOCKS_ZERO 0x0200
#define EXT4_GET_BLOCKS_CREATE_ZERO (EXT4_GET_BLOCKS_CREATE |\
EXT4_GET_BLOCKS_ZERO)
/* Caller will submit data before dropping transaction handle. This
* allows jbd2 to avoid submitting data before commit. */
#define EXT4_GET_BLOCKS_IO_SUBMIT 0x0400
/* Caller is in the atomic contex, find extent if it has been cached */
#define EXT4_GET_BLOCKS_CACHED_NOWAIT 0x0800
/*
* The bit position of these flags must not overlap with any of the
* EXT4_GET_BLOCKS_*. They are used by ext4_find_extent(),
* read_extent_tree_block(), ext4_split_extent_at(),
* ext4_ext_insert_extent(), and ext4_ext_create_new_leaf().
* EXT4_EX_NOCACHE is used to indicate that the we shouldn't be
* caching the extents when reading from the extent tree while a
* truncate or punch hole operation is in progress.
*/
#define EXT4_EX_NOCACHE 0x40000000
#define EXT4_EX_FORCE_CACHE 0x20000000
#define EXT4_EX_NOFAIL 0x10000000
/*
* 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
#define EXT4_FREE_BLOCKS_RERESERVE_CLUSTER 0x0040
/*
* ioctl commands
*/
#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)
#define EXT4_IOC_SWAP_BOOT _IO('f', 17)
#define EXT4_IOC_PRECACHE_EXTENTS _IO('f', 18)
/* ioctl codes 19--39 are reserved for fscrypt */
#define EXT4_IOC_CLEAR_ES_CACHE _IO('f', 40)
#define EXT4_IOC_GETSTATE _IOW('f', 41, __u32)
#define EXT4_IOC_GET_ES_CACHE _IOWR('f', 42, struct fiemap)
ext4: add ioctl EXT4_IOC_CHECKPOINT ioctl EXT4_IOC_CHECKPOINT checkpoints and flushes the journal. This includes forcing all the transactions to the log, checkpointing the transactions, and flushing the log to disk. This ioctl takes u32 "flags" as an argument. Three flags are supported. EXT4_IOC_CHECKPOINT_FLAG_DRY_RUN can be used to verify input to the ioctl. It returns error if there is any invalid input, otherwise it returns success without performing any checkpointing. The other two flags, EXT4_IOC_CHECKPOINT_FLAG_DISCARD and EXT4_IOC_CHECKPOINT_FLAG_ZEROOUT, can be used to issue requests to discard or zeroout the journal logs blocks, respectively. At this point, EXT4_IOC_CHECKPOINT_FLAG_ZEROOUT is primarily added to enable testing of this codepath on devices that don't support discard. EXT4_IOC_CHECKPOINT_FLAG_DISCARD and EXT4_IOC_CHECKPOINT_FLAG_ZEROOUT cannot both be set. Systems that wish to achieve content deletion SLO can set up a daemon that calls this ioctl at a regular interval such that it matches with the SLO requirement. Thus, with this patch, the ext4_dir_entry2 wipeout patch[1], and the Ext4 "-o discard" mount option set, Ext4 can now guarantee that all file contents, file metatdata, and filenames will not be accessible through the filesystem and will have had discard or zeroout requests issued for corresponding device blocks. The __jbd2_journal_erase function could also be used to discard or zero-fill the journal during journal load after recovery. This would provide a potential solution to a journal replay bug reported earlier this year[2]. After a successful journal recovery, e2fsck can call this ioctl to discard the journal as well. [1] https://lore.kernel.org/linux-ext4/YIHknqxngB1sUdie@mit.edu/ [2] https://lore.kernel.org/linux-ext4/YDZoaacIYStFQT8g@mit.edu/ Link: https://lore.kernel.org/r/20210518151327.130198-2-leah.rumancik@gmail.com Signed-off-by: Leah Rumancik <leah.rumancik@gmail.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2021-05-18 23:13:26 +08:00
#define EXT4_IOC_CHECKPOINT _IOW('f', 43, __u32)
#define EXT4_IOC_SHUTDOWN _IOR ('X', 125, __u32)
/*
* Flags for going down operation
*/
#define EXT4_GOING_FLAGS_DEFAULT 0x0 /* going down */
#define EXT4_GOING_FLAGS_LOGFLUSH 0x1 /* flush log but not data */
#define EXT4_GOING_FLAGS_NOLOGFLUSH 0x2 /* don't flush log nor data */
/*
* Flags returned by EXT4_IOC_GETSTATE
*
* We only expose to userspace a subset of the state flags in
* i_state_flags
*/
#define EXT4_STATE_FLAG_EXT_PRECACHED 0x00000001
#define EXT4_STATE_FLAG_NEW 0x00000002
#define EXT4_STATE_FLAG_NEWENTRY 0x00000004
#define EXT4_STATE_FLAG_DA_ALLOC_CLOSE 0x00000008
ext4: add ioctl EXT4_IOC_CHECKPOINT ioctl EXT4_IOC_CHECKPOINT checkpoints and flushes the journal. This includes forcing all the transactions to the log, checkpointing the transactions, and flushing the log to disk. This ioctl takes u32 "flags" as an argument. Three flags are supported. EXT4_IOC_CHECKPOINT_FLAG_DRY_RUN can be used to verify input to the ioctl. It returns error if there is any invalid input, otherwise it returns success without performing any checkpointing. The other two flags, EXT4_IOC_CHECKPOINT_FLAG_DISCARD and EXT4_IOC_CHECKPOINT_FLAG_ZEROOUT, can be used to issue requests to discard or zeroout the journal logs blocks, respectively. At this point, EXT4_IOC_CHECKPOINT_FLAG_ZEROOUT is primarily added to enable testing of this codepath on devices that don't support discard. EXT4_IOC_CHECKPOINT_FLAG_DISCARD and EXT4_IOC_CHECKPOINT_FLAG_ZEROOUT cannot both be set. Systems that wish to achieve content deletion SLO can set up a daemon that calls this ioctl at a regular interval such that it matches with the SLO requirement. Thus, with this patch, the ext4_dir_entry2 wipeout patch[1], and the Ext4 "-o discard" mount option set, Ext4 can now guarantee that all file contents, file metatdata, and filenames will not be accessible through the filesystem and will have had discard or zeroout requests issued for corresponding device blocks. The __jbd2_journal_erase function could also be used to discard or zero-fill the journal during journal load after recovery. This would provide a potential solution to a journal replay bug reported earlier this year[2]. After a successful journal recovery, e2fsck can call this ioctl to discard the journal as well. [1] https://lore.kernel.org/linux-ext4/YIHknqxngB1sUdie@mit.edu/ [2] https://lore.kernel.org/linux-ext4/YDZoaacIYStFQT8g@mit.edu/ Link: https://lore.kernel.org/r/20210518151327.130198-2-leah.rumancik@gmail.com Signed-off-by: Leah Rumancik <leah.rumancik@gmail.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2021-05-18 23:13:26 +08:00
/* flags for ioctl EXT4_IOC_CHECKPOINT */
#define EXT4_IOC_CHECKPOINT_FLAG_DISCARD 0x1
#define EXT4_IOC_CHECKPOINT_FLAG_ZEROOUT 0x2
#define EXT4_IOC_CHECKPOINT_FLAG_DRY_RUN 0x4
#define EXT4_IOC_CHECKPOINT_FLAG_VALID (EXT4_IOC_CHECKPOINT_FLAG_DISCARD | \
EXT4_IOC_CHECKPOINT_FLAG_ZEROOUT | \
EXT4_IOC_CHECKPOINT_FLAG_DRY_RUN)
#if defined(__KERNEL__) && defined(CONFIG_COMPAT)
/*
* ioctl commands in 32 bit emulation
*/
#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
/*
* Returned by EXT4_IOC_GET_ES_CACHE as an additional possible flag.
* It indicates that the entry in extent status cache is for a hole.
*/
#define EXT4_FIEMAP_EXTENT_HOLE 0x08000000
/* Max physical block we can address w/o extents */
#define EXT4_MAX_BLOCK_FILE_PHYS 0xFFFFFFFF
/* Max logical block we can support */
#define EXT4_MAX_LOGICAL_BLOCK 0xFFFFFFFE
/*
* 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 */
__le32 i_projid; /* Project ID */
};
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)) \
/*
* We use an encoding that preserves the times for extra epoch "00":
*
* extra msb of adjust for signed
* epoch 32-bit 32-bit tv_sec to
* bits time decoded 64-bit tv_sec 64-bit tv_sec valid time range
* 0 0 1 -0x80000000..-0x00000001 0x000000000 1901-12-13..1969-12-31
* 0 0 0 0x000000000..0x07fffffff 0x000000000 1970-01-01..2038-01-19
* 0 1 1 0x080000000..0x0ffffffff 0x100000000 2038-01-19..2106-02-07
* 0 1 0 0x100000000..0x17fffffff 0x100000000 2106-02-07..2174-02-25
* 1 0 1 0x180000000..0x1ffffffff 0x200000000 2174-02-25..2242-03-16
* 1 0 0 0x200000000..0x27fffffff 0x200000000 2242-03-16..2310-04-04
* 1 1 1 0x280000000..0x2ffffffff 0x300000000 2310-04-04..2378-04-22
* 1 1 0 0x300000000..0x37fffffff 0x300000000 2378-04-22..2446-05-10
*
* Note that previous versions of the kernel on 64-bit systems would
* incorrectly use extra epoch bits 1,1 for dates between 1901 and
* 1970. e2fsck will correct this, assuming that it is run on the
* affected filesystem before 2242.
*/
static inline __le32 ext4_encode_extra_time(struct timespec64 *time)
{
u32 extra =((time->tv_sec - (s32)time->tv_sec) >> 32) & EXT4_EPOCH_MASK;
return cpu_to_le32(extra | (time->tv_nsec << EXT4_EPOCH_BITS));
}
static inline void ext4_decode_extra_time(struct timespec64 *time,
__le32 extra)
{
if (unlikely(extra & cpu_to_le32(EXT4_EPOCH_MASK)))
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;
}
vfs: change inode times to use struct timespec64 struct timespec is not y2038 safe. Transition vfs to use y2038 safe struct timespec64 instead. The change was made with the help of the following cocinelle script. This catches about 80% of the changes. All the header file and logic changes are included in the first 5 rules. The rest are trivial substitutions. I avoid changing any of the function signatures or any other filesystem specific data structures to keep the patch simple for review. The script can be a little shorter by combining different cases. But, this version was sufficient for my usecase. virtual patch @ depends on patch @ identifier now; @@ - struct timespec + struct timespec64 current_time ( ... ) { - struct timespec now = current_kernel_time(); + struct timespec64 now = current_kernel_time64(); ... - return timespec_trunc( + return timespec64_trunc( ... ); } @ depends on patch @ identifier xtime; @@ struct \( iattr \| inode \| kstat \) { ... - struct timespec xtime; + struct timespec64 xtime; ... } @ depends on patch @ identifier t; @@ struct inode_operations { ... int (*update_time) (..., - struct timespec t, + struct timespec64 t, ...); ... } @ depends on patch @ identifier t; identifier fn_update_time =~ "update_time$"; @@ fn_update_time (..., - struct timespec *t, + struct timespec64 *t, ...) { ... } @ depends on patch @ identifier t; @@ lease_get_mtime( ... , - struct timespec *t + struct timespec64 *t ) { ... } @te depends on patch forall@ identifier ts; local idexpression struct inode *inode_node; identifier i_xtime =~ "^i_[acm]time$"; identifier ia_xtime =~ "^ia_[acm]time$"; identifier fn_update_time =~ "update_time$"; identifier fn; expression e, E3; local idexpression struct inode *node1; local idexpression struct inode *node2; local idexpression struct iattr *attr1; local idexpression struct iattr *attr2; local idexpression struct iattr attr; identifier i_xtime1 =~ "^i_[acm]time$"; identifier i_xtime2 =~ "^i_[acm]time$"; identifier ia_xtime1 =~ "^ia_[acm]time$"; identifier ia_xtime2 =~ "^ia_[acm]time$"; @@ ( ( - struct timespec ts; + struct timespec64 ts; | - struct timespec ts = current_time(inode_node); + struct timespec64 ts = current_time(inode_node); ) <+... when != ts ( - timespec_equal(&inode_node->i_xtime, &ts) + timespec64_equal(&inode_node->i_xtime, &ts) | - timespec_equal(&ts, &inode_node->i_xtime) + timespec64_equal(&ts, &inode_node->i_xtime) | - timespec_compare(&inode_node->i_xtime, &ts) + timespec64_compare(&inode_node->i_xtime, &ts) | - timespec_compare(&ts, &inode_node->i_xtime) + timespec64_compare(&ts, &inode_node->i_xtime) | ts = current_time(e) | fn_update_time(..., &ts,...) | inode_node->i_xtime = ts | node1->i_xtime = ts | ts = inode_node->i_xtime | <+... attr1->ia_xtime ...+> = ts | ts = attr1->ia_xtime | ts.tv_sec | ts.tv_nsec | btrfs_set_stack_timespec_sec(..., ts.tv_sec) | btrfs_set_stack_timespec_nsec(..., ts.tv_nsec) | - ts = timespec64_to_timespec( + ts = ... -) | - ts = ktime_to_timespec( + ts = ktime_to_timespec64( ...) | - ts = E3 + ts = timespec_to_timespec64(E3) | - ktime_get_real_ts(&ts) + ktime_get_real_ts64(&ts) | fn(..., - ts + timespec64_to_timespec(ts) ,...) ) ...+> ( <... when != ts - return ts; + return timespec64_to_timespec(ts); ...> ) | - timespec_equal(&node1->i_xtime1, &node2->i_xtime2) + timespec64_equal(&node1->i_xtime2, &node2->i_xtime2) | - timespec_equal(&node1->i_xtime1, &attr2->ia_xtime2) + timespec64_equal(&node1->i_xtime2, &attr2->ia_xtime2) | - timespec_compare(&node1->i_xtime1, &node2->i_xtime2) + timespec64_compare(&node1->i_xtime1, &node2->i_xtime2) | node1->i_xtime1 = - timespec_trunc(attr1->ia_xtime1, + timespec64_trunc(attr1->ia_xtime1, ...) | - attr1->ia_xtime1 = timespec_trunc(attr2->ia_xtime2, + attr1->ia_xtime1 = timespec64_trunc(attr2->ia_xtime2, ...) | - ktime_get_real_ts(&attr1->ia_xtime1) + ktime_get_real_ts64(&attr1->ia_xtime1) | - ktime_get_real_ts(&attr.ia_xtime1) + ktime_get_real_ts64(&attr.ia_xtime1) ) @ depends on patch @ struct inode *node; struct iattr *attr; identifier fn; identifier i_xtime =~ "^i_[acm]time$"; identifier ia_xtime =~ "^ia_[acm]time$"; expression e; @@ ( - fn(node->i_xtime); + fn(timespec64_to_timespec(node->i_xtime)); | fn(..., - node->i_xtime); + timespec64_to_timespec(node->i_xtime)); | - e = fn(attr->ia_xtime); + e = fn(timespec64_to_timespec(attr->ia_xtime)); ) @ depends on patch forall @ struct inode *node; struct iattr *attr; identifier i_xtime =~ "^i_[acm]time$"; identifier ia_xtime =~ "^ia_[acm]time$"; identifier fn; @@ { + struct timespec ts; <+... ( + ts = timespec64_to_timespec(node->i_xtime); fn (..., - &node->i_xtime, + &ts, ...); | + ts = timespec64_to_timespec(attr->ia_xtime); fn (..., - &attr->ia_xtime, + &ts, ...); ) ...+> } @ depends on patch forall @ struct inode *node; struct iattr *attr; struct kstat *stat; identifier ia_xtime =~ "^ia_[acm]time$"; identifier i_xtime =~ "^i_[acm]time$"; identifier xtime =~ "^[acm]time$"; identifier fn, ret; @@ { + struct timespec ts; <+... ( + ts = timespec64_to_timespec(node->i_xtime); ret = fn (..., - &node->i_xtime, + &ts, ...); | + ts = timespec64_to_timespec(node->i_xtime); ret = fn (..., - &node->i_xtime); + &ts); | + ts = timespec64_to_timespec(attr->ia_xtime); ret = fn (..., - &attr->ia_xtime, + &ts, ...); | + ts = timespec64_to_timespec(attr->ia_xtime); ret = fn (..., - &attr->ia_xtime); + &ts); | + ts = timespec64_to_timespec(stat->xtime); ret = fn (..., - &stat->xtime); + &ts); ) ...+> } @ depends on patch @ struct inode *node; struct inode *node2; identifier i_xtime1 =~ "^i_[acm]time$"; identifier i_xtime2 =~ "^i_[acm]time$"; identifier i_xtime3 =~ "^i_[acm]time$"; struct iattr *attrp; struct iattr *attrp2; struct iattr attr ; identifier ia_xtime1 =~ "^ia_[acm]time$"; identifier ia_xtime2 =~ "^ia_[acm]time$"; struct kstat *stat; struct kstat stat1; struct timespec64 ts; identifier xtime =~ "^[acmb]time$"; expression e; @@ ( ( node->i_xtime2 \| attrp->ia_xtime2 \| attr.ia_xtime2 \) = node->i_xtime1 ; | node->i_xtime2 = \( node2->i_xtime1 \| timespec64_trunc(...) \); | node->i_xtime2 = node->i_xtime1 = node->i_xtime3 = \(ts \| current_time(...) \); | node->i_xtime1 = node->i_xtime3 = \(ts \| current_time(...) \); | stat->xtime = node2->i_xtime1; | stat1.xtime = node2->i_xtime1; | ( node->i_xtime2 \| attrp->ia_xtime2 \) = attrp->ia_xtime1 ; | ( attrp->ia_xtime1 \| attr.ia_xtime1 \) = attrp2->ia_xtime2; | - e = node->i_xtime1; + e = timespec64_to_timespec( node->i_xtime1 ); | - e = attrp->ia_xtime1; + e = timespec64_to_timespec( attrp->ia_xtime1 ); | node->i_xtime1 = current_time(...); | node->i_xtime2 = node->i_xtime1 = node->i_xtime3 = - e; + timespec_to_timespec64(e); | node->i_xtime1 = node->i_xtime3 = - e; + timespec_to_timespec64(e); | - node->i_xtime1 = e; + node->i_xtime1 = timespec_to_timespec64(e); ) Signed-off-by: Deepa Dinamani <deepa.kernel@gmail.com> Cc: <anton@tuxera.com> Cc: <balbi@kernel.org> Cc: <bfields@fieldses.org> Cc: <darrick.wong@oracle.com> Cc: <dhowells@redhat.com> Cc: <dsterba@suse.com> Cc: <dwmw2@infradead.org> Cc: <hch@lst.de> Cc: <hirofumi@mail.parknet.co.jp> Cc: <hubcap@omnibond.com> Cc: <jack@suse.com> Cc: <jaegeuk@kernel.org> Cc: <jaharkes@cs.cmu.edu> Cc: <jslaby@suse.com> Cc: <keescook@chromium.org> Cc: <mark@fasheh.com> Cc: <miklos@szeredi.hu> Cc: <nico@linaro.org> Cc: <reiserfs-devel@vger.kernel.org> Cc: <richard@nod.at> Cc: <sage@redhat.com> Cc: <sfrench@samba.org> Cc: <swhiteho@redhat.com> Cc: <tj@kernel.org> Cc: <trond.myklebust@primarydata.com> Cc: <tytso@mit.edu> Cc: <viro@zeniv.linux.org.uk>
2018-05-09 10:36:02 +08:00
#define EXT4_INODE_SET_XTIME(xtime, inode, raw_inode) \
do { \
if (EXT4_FITS_IN_INODE(raw_inode, EXT4_I(inode), xtime ## _extra)) {\
(raw_inode)->xtime = cpu_to_le32((inode)->xtime.tv_sec); \
vfs: change inode times to use struct timespec64 struct timespec is not y2038 safe. Transition vfs to use y2038 safe struct timespec64 instead. The change was made with the help of the following cocinelle script. This catches about 80% of the changes. All the header file and logic changes are included in the first 5 rules. The rest are trivial substitutions. I avoid changing any of the function signatures or any other filesystem specific data structures to keep the patch simple for review. The script can be a little shorter by combining different cases. But, this version was sufficient for my usecase. virtual patch @ depends on patch @ identifier now; @@ - struct timespec + struct timespec64 current_time ( ... ) { - struct timespec now = current_kernel_time(); + struct timespec64 now = current_kernel_time64(); ... - return timespec_trunc( + return timespec64_trunc( ... ); } @ depends on patch @ identifier xtime; @@ struct \( iattr \| inode \| kstat \) { ... - struct timespec xtime; + struct timespec64 xtime; ... } @ depends on patch @ identifier t; @@ struct inode_operations { ... int (*update_time) (..., - struct timespec t, + struct timespec64 t, ...); ... } @ depends on patch @ identifier t; identifier fn_update_time =~ "update_time$"; @@ fn_update_time (..., - struct timespec *t, + struct timespec64 *t, ...) { ... } @ depends on patch @ identifier t; @@ lease_get_mtime( ... , - struct timespec *t + struct timespec64 *t ) { ... } @te depends on patch forall@ identifier ts; local idexpression struct inode *inode_node; identifier i_xtime =~ "^i_[acm]time$"; identifier ia_xtime =~ "^ia_[acm]time$"; identifier fn_update_time =~ "update_time$"; identifier fn; expression e, E3; local idexpression struct inode *node1; local idexpression struct inode *node2; local idexpression struct iattr *attr1; local idexpression struct iattr *attr2; local idexpression struct iattr attr; identifier i_xtime1 =~ "^i_[acm]time$"; identifier i_xtime2 =~ "^i_[acm]time$"; identifier ia_xtime1 =~ "^ia_[acm]time$"; identifier ia_xtime2 =~ "^ia_[acm]time$"; @@ ( ( - struct timespec ts; + struct timespec64 ts; | - struct timespec ts = current_time(inode_node); + struct timespec64 ts = current_time(inode_node); ) <+... when != ts ( - timespec_equal(&inode_node->i_xtime, &ts) + timespec64_equal(&inode_node->i_xtime, &ts) | - timespec_equal(&ts, &inode_node->i_xtime) + timespec64_equal(&ts, &inode_node->i_xtime) | - timespec_compare(&inode_node->i_xtime, &ts) + timespec64_compare(&inode_node->i_xtime, &ts) | - timespec_compare(&ts, &inode_node->i_xtime) + timespec64_compare(&ts, &inode_node->i_xtime) | ts = current_time(e) | fn_update_time(..., &ts,...) | inode_node->i_xtime = ts | node1->i_xtime = ts | ts = inode_node->i_xtime | <+... attr1->ia_xtime ...+> = ts | ts = attr1->ia_xtime | ts.tv_sec | ts.tv_nsec | btrfs_set_stack_timespec_sec(..., ts.tv_sec) | btrfs_set_stack_timespec_nsec(..., ts.tv_nsec) | - ts = timespec64_to_timespec( + ts = ... -) | - ts = ktime_to_timespec( + ts = ktime_to_timespec64( ...) | - ts = E3 + ts = timespec_to_timespec64(E3) | - ktime_get_real_ts(&ts) + ktime_get_real_ts64(&ts) | fn(..., - ts + timespec64_to_timespec(ts) ,...) ) ...+> ( <... when != ts - return ts; + return timespec64_to_timespec(ts); ...> ) | - timespec_equal(&node1->i_xtime1, &node2->i_xtime2) + timespec64_equal(&node1->i_xtime2, &node2->i_xtime2) | - timespec_equal(&node1->i_xtime1, &attr2->ia_xtime2) + timespec64_equal(&node1->i_xtime2, &attr2->ia_xtime2) | - timespec_compare(&node1->i_xtime1, &node2->i_xtime2) + timespec64_compare(&node1->i_xtime1, &node2->i_xtime2) | node1->i_xtime1 = - timespec_trunc(attr1->ia_xtime1, + timespec64_trunc(attr1->ia_xtime1, ...) | - attr1->ia_xtime1 = timespec_trunc(attr2->ia_xtime2, + attr1->ia_xtime1 = timespec64_trunc(attr2->ia_xtime2, ...) | - ktime_get_real_ts(&attr1->ia_xtime1) + ktime_get_real_ts64(&attr1->ia_xtime1) | - ktime_get_real_ts(&attr.ia_xtime1) + ktime_get_real_ts64(&attr.ia_xtime1) ) @ depends on patch @ struct inode *node; struct iattr *attr; identifier fn; identifier i_xtime =~ "^i_[acm]time$"; identifier ia_xtime =~ "^ia_[acm]time$"; expression e; @@ ( - fn(node->i_xtime); + fn(timespec64_to_timespec(node->i_xtime)); | fn(..., - node->i_xtime); + timespec64_to_timespec(node->i_xtime)); | - e = fn(attr->ia_xtime); + e = fn(timespec64_to_timespec(attr->ia_xtime)); ) @ depends on patch forall @ struct inode *node; struct iattr *attr; identifier i_xtime =~ "^i_[acm]time$"; identifier ia_xtime =~ "^ia_[acm]time$"; identifier fn; @@ { + struct timespec ts; <+... ( + ts = timespec64_to_timespec(node->i_xtime); fn (..., - &node->i_xtime, + &ts, ...); | + ts = timespec64_to_timespec(attr->ia_xtime); fn (..., - &attr->ia_xtime, + &ts, ...); ) ...+> } @ depends on patch forall @ struct inode *node; struct iattr *attr; struct kstat *stat; identifier ia_xtime =~ "^ia_[acm]time$"; identifier i_xtime =~ "^i_[acm]time$"; identifier xtime =~ "^[acm]time$"; identifier fn, ret; @@ { + struct timespec ts; <+... ( + ts = timespec64_to_timespec(node->i_xtime); ret = fn (..., - &node->i_xtime, + &ts, ...); | + ts = timespec64_to_timespec(node->i_xtime); ret = fn (..., - &node->i_xtime); + &ts); | + ts = timespec64_to_timespec(attr->ia_xtime); ret = fn (..., - &attr->ia_xtime, + &ts, ...); | + ts = timespec64_to_timespec(attr->ia_xtime); ret = fn (..., - &attr->ia_xtime); + &ts); | + ts = timespec64_to_timespec(stat->xtime); ret = fn (..., - &stat->xtime); + &ts); ) ...+> } @ depends on patch @ struct inode *node; struct inode *node2; identifier i_xtime1 =~ "^i_[acm]time$"; identifier i_xtime2 =~ "^i_[acm]time$"; identifier i_xtime3 =~ "^i_[acm]time$"; struct iattr *attrp; struct iattr *attrp2; struct iattr attr ; identifier ia_xtime1 =~ "^ia_[acm]time$"; identifier ia_xtime2 =~ "^ia_[acm]time$"; struct kstat *stat; struct kstat stat1; struct timespec64 ts; identifier xtime =~ "^[acmb]time$"; expression e; @@ ( ( node->i_xtime2 \| attrp->ia_xtime2 \| attr.ia_xtime2 \) = node->i_xtime1 ; | node->i_xtime2 = \( node2->i_xtime1 \| timespec64_trunc(...) \); | node->i_xtime2 = node->i_xtime1 = node->i_xtime3 = \(ts \| current_time(...) \); | node->i_xtime1 = node->i_xtime3 = \(ts \| current_time(...) \); | stat->xtime = node2->i_xtime1; | stat1.xtime = node2->i_xtime1; | ( node->i_xtime2 \| attrp->ia_xtime2 \) = attrp->ia_xtime1 ; | ( attrp->ia_xtime1 \| attr.ia_xtime1 \) = attrp2->ia_xtime2; | - e = node->i_xtime1; + e = timespec64_to_timespec( node->i_xtime1 ); | - e = attrp->ia_xtime1; + e = timespec64_to_timespec( attrp->ia_xtime1 ); | node->i_xtime1 = current_time(...); | node->i_xtime2 = node->i_xtime1 = node->i_xtime3 = - e; + timespec_to_timespec64(e); | node->i_xtime1 = node->i_xtime3 = - e; + timespec_to_timespec64(e); | - node->i_xtime1 = e; + node->i_xtime1 = timespec_to_timespec64(e); ) Signed-off-by: Deepa Dinamani <deepa.kernel@gmail.com> Cc: <anton@tuxera.com> Cc: <balbi@kernel.org> Cc: <bfields@fieldses.org> Cc: <darrick.wong@oracle.com> Cc: <dhowells@redhat.com> Cc: <dsterba@suse.com> Cc: <dwmw2@infradead.org> Cc: <hch@lst.de> Cc: <hirofumi@mail.parknet.co.jp> Cc: <hubcap@omnibond.com> Cc: <jack@suse.com> Cc: <jaegeuk@kernel.org> Cc: <jaharkes@cs.cmu.edu> Cc: <jslaby@suse.com> Cc: <keescook@chromium.org> Cc: <mark@fasheh.com> Cc: <miklos@szeredi.hu> Cc: <nico@linaro.org> Cc: <reiserfs-devel@vger.kernel.org> Cc: <richard@nod.at> Cc: <sage@redhat.com> Cc: <sfrench@samba.org> Cc: <swhiteho@redhat.com> Cc: <tj@kernel.org> Cc: <trond.myklebust@primarydata.com> Cc: <tytso@mit.edu> Cc: <viro@zeniv.linux.org.uk>
2018-05-09 10:36:02 +08:00
(raw_inode)->xtime ## _extra = \
ext4_encode_extra_time(&(inode)->xtime); \
vfs: change inode times to use struct timespec64 struct timespec is not y2038 safe. Transition vfs to use y2038 safe struct timespec64 instead. The change was made with the help of the following cocinelle script. This catches about 80% of the changes. All the header file and logic changes are included in the first 5 rules. The rest are trivial substitutions. I avoid changing any of the function signatures or any other filesystem specific data structures to keep the patch simple for review. The script can be a little shorter by combining different cases. But, this version was sufficient for my usecase. virtual patch @ depends on patch @ identifier now; @@ - struct timespec + struct timespec64 current_time ( ... ) { - struct timespec now = current_kernel_time(); + struct timespec64 now = current_kernel_time64(); ... - return timespec_trunc( + return timespec64_trunc( ... ); } @ depends on patch @ identifier xtime; @@ struct \( iattr \| inode \| kstat \) { ... - struct timespec xtime; + struct timespec64 xtime; ... } @ depends on patch @ identifier t; @@ struct inode_operations { ... int (*update_time) (..., - struct timespec t, + struct timespec64 t, ...); ... } @ depends on patch @ identifier t; identifier fn_update_time =~ "update_time$"; @@ fn_update_time (..., - struct timespec *t, + struct timespec64 *t, ...) { ... } @ depends on patch @ identifier t; @@ lease_get_mtime( ... , - struct timespec *t + struct timespec64 *t ) { ... } @te depends on patch forall@ identifier ts; local idexpression struct inode *inode_node; identifier i_xtime =~ "^i_[acm]time$"; identifier ia_xtime =~ "^ia_[acm]time$"; identifier fn_update_time =~ "update_time$"; identifier fn; expression e, E3; local idexpression struct inode *node1; local idexpression struct inode *node2; local idexpression struct iattr *attr1; local idexpression struct iattr *attr2; local idexpression struct iattr attr; identifier i_xtime1 =~ "^i_[acm]time$"; identifier i_xtime2 =~ "^i_[acm]time$"; identifier ia_xtime1 =~ "^ia_[acm]time$"; identifier ia_xtime2 =~ "^ia_[acm]time$"; @@ ( ( - struct timespec ts; + struct timespec64 ts; | - struct timespec ts = current_time(inode_node); + struct timespec64 ts = current_time(inode_node); ) <+... when != ts ( - timespec_equal(&inode_node->i_xtime, &ts) + timespec64_equal(&inode_node->i_xtime, &ts) | - timespec_equal(&ts, &inode_node->i_xtime) + timespec64_equal(&ts, &inode_node->i_xtime) | - timespec_compare(&inode_node->i_xtime, &ts) + timespec64_compare(&inode_node->i_xtime, &ts) | - timespec_compare(&ts, &inode_node->i_xtime) + timespec64_compare(&ts, &inode_node->i_xtime) | ts = current_time(e) | fn_update_time(..., &ts,...) | inode_node->i_xtime = ts | node1->i_xtime = ts | ts = inode_node->i_xtime | <+... attr1->ia_xtime ...+> = ts | ts = attr1->ia_xtime | ts.tv_sec | ts.tv_nsec | btrfs_set_stack_timespec_sec(..., ts.tv_sec) | btrfs_set_stack_timespec_nsec(..., ts.tv_nsec) | - ts = timespec64_to_timespec( + ts = ... -) | - ts = ktime_to_timespec( + ts = ktime_to_timespec64( ...) | - ts = E3 + ts = timespec_to_timespec64(E3) | - ktime_get_real_ts(&ts) + ktime_get_real_ts64(&ts) | fn(..., - ts + timespec64_to_timespec(ts) ,...) ) ...+> ( <... when != ts - return ts; + return timespec64_to_timespec(ts); ...> ) | - timespec_equal(&node1->i_xtime1, &node2->i_xtime2) + timespec64_equal(&node1->i_xtime2, &node2->i_xtime2) | - timespec_equal(&node1->i_xtime1, &attr2->ia_xtime2) + timespec64_equal(&node1->i_xtime2, &attr2->ia_xtime2) | - timespec_compare(&node1->i_xtime1, &node2->i_xtime2) + timespec64_compare(&node1->i_xtime1, &node2->i_xtime2) | node1->i_xtime1 = - timespec_trunc(attr1->ia_xtime1, + timespec64_trunc(attr1->ia_xtime1, ...) | - attr1->ia_xtime1 = timespec_trunc(attr2->ia_xtime2, + attr1->ia_xtime1 = timespec64_trunc(attr2->ia_xtime2, ...) | - ktime_get_real_ts(&attr1->ia_xtime1) + ktime_get_real_ts64(&attr1->ia_xtime1) | - ktime_get_real_ts(&attr.ia_xtime1) + ktime_get_real_ts64(&attr.ia_xtime1) ) @ depends on patch @ struct inode *node; struct iattr *attr; identifier fn; identifier i_xtime =~ "^i_[acm]time$"; identifier ia_xtime =~ "^ia_[acm]time$"; expression e; @@ ( - fn(node->i_xtime); + fn(timespec64_to_timespec(node->i_xtime)); | fn(..., - node->i_xtime); + timespec64_to_timespec(node->i_xtime)); | - e = fn(attr->ia_xtime); + e = fn(timespec64_to_timespec(attr->ia_xtime)); ) @ depends on patch forall @ struct inode *node; struct iattr *attr; identifier i_xtime =~ "^i_[acm]time$"; identifier ia_xtime =~ "^ia_[acm]time$"; identifier fn; @@ { + struct timespec ts; <+... ( + ts = timespec64_to_timespec(node->i_xtime); fn (..., - &node->i_xtime, + &ts, ...); | + ts = timespec64_to_timespec(attr->ia_xtime); fn (..., - &attr->ia_xtime, + &ts, ...); ) ...+> } @ depends on patch forall @ struct inode *node; struct iattr *attr; struct kstat *stat; identifier ia_xtime =~ "^ia_[acm]time$"; identifier i_xtime =~ "^i_[acm]time$"; identifier xtime =~ "^[acm]time$"; identifier fn, ret; @@ { + struct timespec ts; <+... ( + ts = timespec64_to_timespec(node->i_xtime); ret = fn (..., - &node->i_xtime, + &ts, ...); | + ts = timespec64_to_timespec(node->i_xtime); ret = fn (..., - &node->i_xtime); + &ts); | + ts = timespec64_to_timespec(attr->ia_xtime); ret = fn (..., - &attr->ia_xtime, + &ts, ...); | + ts = timespec64_to_timespec(attr->ia_xtime); ret = fn (..., - &attr->ia_xtime); + &ts); | + ts = timespec64_to_timespec(stat->xtime); ret = fn (..., - &stat->xtime); + &ts); ) ...+> } @ depends on patch @ struct inode *node; struct inode *node2; identifier i_xtime1 =~ "^i_[acm]time$"; identifier i_xtime2 =~ "^i_[acm]time$"; identifier i_xtime3 =~ "^i_[acm]time$"; struct iattr *attrp; struct iattr *attrp2; struct iattr attr ; identifier ia_xtime1 =~ "^ia_[acm]time$"; identifier ia_xtime2 =~ "^ia_[acm]time$"; struct kstat *stat; struct kstat stat1; struct timespec64 ts; identifier xtime =~ "^[acmb]time$"; expression e; @@ ( ( node->i_xtime2 \| attrp->ia_xtime2 \| attr.ia_xtime2 \) = node->i_xtime1 ; | node->i_xtime2 = \( node2->i_xtime1 \| timespec64_trunc(...) \); | node->i_xtime2 = node->i_xtime1 = node->i_xtime3 = \(ts \| current_time(...) \); | node->i_xtime1 = node->i_xtime3 = \(ts \| current_time(...) \); | stat->xtime = node2->i_xtime1; | stat1.xtime = node2->i_xtime1; | ( node->i_xtime2 \| attrp->ia_xtime2 \) = attrp->ia_xtime1 ; | ( attrp->ia_xtime1 \| attr.ia_xtime1 \) = attrp2->ia_xtime2; | - e = node->i_xtime1; + e = timespec64_to_timespec( node->i_xtime1 ); | - e = attrp->ia_xtime1; + e = timespec64_to_timespec( attrp->ia_xtime1 ); | node->i_xtime1 = current_time(...); | node->i_xtime2 = node->i_xtime1 = node->i_xtime3 = - e; + timespec_to_timespec64(e); | node->i_xtime1 = node->i_xtime3 = - e; + timespec_to_timespec64(e); | - node->i_xtime1 = e; + node->i_xtime1 = timespec_to_timespec64(e); ) Signed-off-by: Deepa Dinamani <deepa.kernel@gmail.com> Cc: <anton@tuxera.com> Cc: <balbi@kernel.org> Cc: <bfields@fieldses.org> Cc: <darrick.wong@oracle.com> Cc: <dhowells@redhat.com> Cc: <dsterba@suse.com> Cc: <dwmw2@infradead.org> Cc: <hch@lst.de> Cc: <hirofumi@mail.parknet.co.jp> Cc: <hubcap@omnibond.com> Cc: <jack@suse.com> Cc: <jaegeuk@kernel.org> Cc: <jaharkes@cs.cmu.edu> Cc: <jslaby@suse.com> Cc: <keescook@chromium.org> Cc: <mark@fasheh.com> Cc: <miklos@szeredi.hu> Cc: <nico@linaro.org> Cc: <reiserfs-devel@vger.kernel.org> Cc: <richard@nod.at> Cc: <sage@redhat.com> Cc: <sfrench@samba.org> Cc: <swhiteho@redhat.com> Cc: <tj@kernel.org> Cc: <trond.myklebust@primarydata.com> Cc: <tytso@mit.edu> Cc: <viro@zeniv.linux.org.uk>
2018-05-09 10:36:02 +08:00
} \
else \
(raw_inode)->xtime = cpu_to_le32(clamp_t(int32_t, (inode)->xtime.tv_sec, S32_MIN, S32_MAX)); \
} 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)
vfs: change inode times to use struct timespec64 struct timespec is not y2038 safe. Transition vfs to use y2038 safe struct timespec64 instead. The change was made with the help of the following cocinelle script. This catches about 80% of the changes. All the header file and logic changes are included in the first 5 rules. The rest are trivial substitutions. I avoid changing any of the function signatures or any other filesystem specific data structures to keep the patch simple for review. The script can be a little shorter by combining different cases. But, this version was sufficient for my usecase. virtual patch @ depends on patch @ identifier now; @@ - struct timespec + struct timespec64 current_time ( ... ) { - struct timespec now = current_kernel_time(); + struct timespec64 now = current_kernel_time64(); ... - return timespec_trunc( + return timespec64_trunc( ... ); } @ depends on patch @ identifier xtime; @@ struct \( iattr \| inode \| kstat \) { ... - struct timespec xtime; + struct timespec64 xtime; ... } @ depends on patch @ identifier t; @@ struct inode_operations { ... int (*update_time) (..., - struct timespec t, + struct timespec64 t, ...); ... } @ depends on patch @ identifier t; identifier fn_update_time =~ "update_time$"; @@ fn_update_time (..., - struct timespec *t, + struct timespec64 *t, ...) { ... } @ depends on patch @ identifier t; @@ lease_get_mtime( ... , - struct timespec *t + struct timespec64 *t ) { ... } @te depends on patch forall@ identifier ts; local idexpression struct inode *inode_node; identifier i_xtime =~ "^i_[acm]time$"; identifier ia_xtime =~ "^ia_[acm]time$"; identifier fn_update_time =~ "update_time$"; identifier fn; expression e, E3; local idexpression struct inode *node1; local idexpression struct inode *node2; local idexpression struct iattr *attr1; local idexpression struct iattr *attr2; local idexpression struct iattr attr; identifier i_xtime1 =~ "^i_[acm]time$"; identifier i_xtime2 =~ "^i_[acm]time$"; identifier ia_xtime1 =~ "^ia_[acm]time$"; identifier ia_xtime2 =~ "^ia_[acm]time$"; @@ ( ( - struct timespec ts; + struct timespec64 ts; | - struct timespec ts = current_time(inode_node); + struct timespec64 ts = current_time(inode_node); ) <+... when != ts ( - timespec_equal(&inode_node->i_xtime, &ts) + timespec64_equal(&inode_node->i_xtime, &ts) | - timespec_equal(&ts, &inode_node->i_xtime) + timespec64_equal(&ts, &inode_node->i_xtime) | - timespec_compare(&inode_node->i_xtime, &ts) + timespec64_compare(&inode_node->i_xtime, &ts) | - timespec_compare(&ts, &inode_node->i_xtime) + timespec64_compare(&ts, &inode_node->i_xtime) | ts = current_time(e) | fn_update_time(..., &ts,...) | inode_node->i_xtime = ts | node1->i_xtime = ts | ts = inode_node->i_xtime | <+... attr1->ia_xtime ...+> = ts | ts = attr1->ia_xtime | ts.tv_sec | ts.tv_nsec | btrfs_set_stack_timespec_sec(..., ts.tv_sec) | btrfs_set_stack_timespec_nsec(..., ts.tv_nsec) | - ts = timespec64_to_timespec( + ts = ... -) | - ts = ktime_to_timespec( + ts = ktime_to_timespec64( ...) | - ts = E3 + ts = timespec_to_timespec64(E3) | - ktime_get_real_ts(&ts) + ktime_get_real_ts64(&ts) | fn(..., - ts + timespec64_to_timespec(ts) ,...) ) ...+> ( <... when != ts - return ts; + return timespec64_to_timespec(ts); ...> ) | - timespec_equal(&node1->i_xtime1, &node2->i_xtime2) + timespec64_equal(&node1->i_xtime2, &node2->i_xtime2) | - timespec_equal(&node1->i_xtime1, &attr2->ia_xtime2) + timespec64_equal(&node1->i_xtime2, &attr2->ia_xtime2) | - timespec_compare(&node1->i_xtime1, &node2->i_xtime2) + timespec64_compare(&node1->i_xtime1, &node2->i_xtime2) | node1->i_xtime1 = - timespec_trunc(attr1->ia_xtime1, + timespec64_trunc(attr1->ia_xtime1, ...) | - attr1->ia_xtime1 = timespec_trunc(attr2->ia_xtime2, + attr1->ia_xtime1 = timespec64_trunc(attr2->ia_xtime2, ...) | - ktime_get_real_ts(&attr1->ia_xtime1) + ktime_get_real_ts64(&attr1->ia_xtime1) | - ktime_get_real_ts(&attr.ia_xtime1) + ktime_get_real_ts64(&attr.ia_xtime1) ) @ depends on patch @ struct inode *node; struct iattr *attr; identifier fn; identifier i_xtime =~ "^i_[acm]time$"; identifier ia_xtime =~ "^ia_[acm]time$"; expression e; @@ ( - fn(node->i_xtime); + fn(timespec64_to_timespec(node->i_xtime)); | fn(..., - node->i_xtime); + timespec64_to_timespec(node->i_xtime)); | - e = fn(attr->ia_xtime); + e = fn(timespec64_to_timespec(attr->ia_xtime)); ) @ depends on patch forall @ struct inode *node; struct iattr *attr; identifier i_xtime =~ "^i_[acm]time$"; identifier ia_xtime =~ "^ia_[acm]time$"; identifier fn; @@ { + struct timespec ts; <+... ( + ts = timespec64_to_timespec(node->i_xtime); fn (..., - &node->i_xtime, + &ts, ...); | + ts = timespec64_to_timespec(attr->ia_xtime); fn (..., - &attr->ia_xtime, + &ts, ...); ) ...+> } @ depends on patch forall @ struct inode *node; struct iattr *attr; struct kstat *stat; identifier ia_xtime =~ "^ia_[acm]time$"; identifier i_xtime =~ "^i_[acm]time$"; identifier xtime =~ "^[acm]time$"; identifier fn, ret; @@ { + struct timespec ts; <+... ( + ts = timespec64_to_timespec(node->i_xtime); ret = fn (..., - &node->i_xtime, + &ts, ...); | + ts = timespec64_to_timespec(node->i_xtime); ret = fn (..., - &node->i_xtime); + &ts); | + ts = timespec64_to_timespec(attr->ia_xtime); ret = fn (..., - &attr->ia_xtime, + &ts, ...); | + ts = timespec64_to_timespec(attr->ia_xtime); ret = fn (..., - &attr->ia_xtime); + &ts); | + ts = timespec64_to_timespec(stat->xtime); ret = fn (..., - &stat->xtime); + &ts); ) ...+> } @ depends on patch @ struct inode *node; struct inode *node2; identifier i_xtime1 =~ "^i_[acm]time$"; identifier i_xtime2 =~ "^i_[acm]time$"; identifier i_xtime3 =~ "^i_[acm]time$"; struct iattr *attrp; struct iattr *attrp2; struct iattr attr ; identifier ia_xtime1 =~ "^ia_[acm]time$"; identifier ia_xtime2 =~ "^ia_[acm]time$"; struct kstat *stat; struct kstat stat1; struct timespec64 ts; identifier xtime =~ "^[acmb]time$"; expression e; @@ ( ( node->i_xtime2 \| attrp->ia_xtime2 \| attr.ia_xtime2 \) = node->i_xtime1 ; | node->i_xtime2 = \( node2->i_xtime1 \| timespec64_trunc(...) \); | node->i_xtime2 = node->i_xtime1 = node->i_xtime3 = \(ts \| current_time(...) \); | node->i_xtime1 = node->i_xtime3 = \(ts \| current_time(...) \); | stat->xtime = node2->i_xtime1; | stat1.xtime = node2->i_xtime1; | ( node->i_xtime2 \| attrp->ia_xtime2 \) = attrp->ia_xtime1 ; | ( attrp->ia_xtime1 \| attr.ia_xtime1 \) = attrp2->ia_xtime2; | - e = node->i_xtime1; + e = timespec64_to_timespec( node->i_xtime1 ); | - e = attrp->ia_xtime1; + e = timespec64_to_timespec( attrp->ia_xtime1 ); | node->i_xtime1 = current_time(...); | node->i_xtime2 = node->i_xtime1 = node->i_xtime3 = - e; + timespec_to_timespec64(e); | node->i_xtime1 = node->i_xtime3 = - e; + timespec_to_timespec64(e); | - node->i_xtime1 = e; + node->i_xtime1 = timespec_to_timespec64(e); ) Signed-off-by: Deepa Dinamani <deepa.kernel@gmail.com> Cc: <anton@tuxera.com> Cc: <balbi@kernel.org> Cc: <bfields@fieldses.org> Cc: <darrick.wong@oracle.com> Cc: <dhowells@redhat.com> Cc: <dsterba@suse.com> Cc: <dwmw2@infradead.org> Cc: <hch@lst.de> Cc: <hirofumi@mail.parknet.co.jp> Cc: <hubcap@omnibond.com> Cc: <jack@suse.com> Cc: <jaegeuk@kernel.org> Cc: <jaharkes@cs.cmu.edu> Cc: <jslaby@suse.com> Cc: <keescook@chromium.org> Cc: <mark@fasheh.com> Cc: <miklos@szeredi.hu> Cc: <nico@linaro.org> Cc: <reiserfs-devel@vger.kernel.org> Cc: <richard@nod.at> Cc: <sage@redhat.com> Cc: <sfrench@samba.org> Cc: <swhiteho@redhat.com> Cc: <tj@kernel.org> Cc: <trond.myklebust@primarydata.com> Cc: <tytso@mit.edu> Cc: <viro@zeniv.linux.org.uk>
2018-05-09 10:36:02 +08:00
#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, \
vfs: change inode times to use struct timespec64 struct timespec is not y2038 safe. Transition vfs to use y2038 safe struct timespec64 instead. The change was made with the help of the following cocinelle script. This catches about 80% of the changes. All the header file and logic changes are included in the first 5 rules. The rest are trivial substitutions. I avoid changing any of the function signatures or any other filesystem specific data structures to keep the patch simple for review. The script can be a little shorter by combining different cases. But, this version was sufficient for my usecase. virtual patch @ depends on patch @ identifier now; @@ - struct timespec + struct timespec64 current_time ( ... ) { - struct timespec now = current_kernel_time(); + struct timespec64 now = current_kernel_time64(); ... - return timespec_trunc( + return timespec64_trunc( ... ); } @ depends on patch @ identifier xtime; @@ struct \( iattr \| inode \| kstat \) { ... - struct timespec xtime; + struct timespec64 xtime; ... } @ depends on patch @ identifier t; @@ struct inode_operations { ... int (*update_time) (..., - struct timespec t, + struct timespec64 t, ...); ... } @ depends on patch @ identifier t; identifier fn_update_time =~ "update_time$"; @@ fn_update_time (..., - struct timespec *t, + struct timespec64 *t, ...) { ... } @ depends on patch @ identifier t; @@ lease_get_mtime( ... , - struct timespec *t + struct timespec64 *t ) { ... } @te depends on patch forall@ identifier ts; local idexpression struct inode *inode_node; identifier i_xtime =~ "^i_[acm]time$"; identifier ia_xtime =~ "^ia_[acm]time$"; identifier fn_update_time =~ "update_time$"; identifier fn; expression e, E3; local idexpression struct inode *node1; local idexpression struct inode *node2; local idexpression struct iattr *attr1; local idexpression struct iattr *attr2; local idexpression struct iattr attr; identifier i_xtime1 =~ "^i_[acm]time$"; identifier i_xtime2 =~ "^i_[acm]time$"; identifier ia_xtime1 =~ "^ia_[acm]time$"; identifier ia_xtime2 =~ "^ia_[acm]time$"; @@ ( ( - struct timespec ts; + struct timespec64 ts; | - struct timespec ts = current_time(inode_node); + struct timespec64 ts = current_time(inode_node); ) <+... when != ts ( - timespec_equal(&inode_node->i_xtime, &ts) + timespec64_equal(&inode_node->i_xtime, &ts) | - timespec_equal(&ts, &inode_node->i_xtime) + timespec64_equal(&ts, &inode_node->i_xtime) | - timespec_compare(&inode_node->i_xtime, &ts) + timespec64_compare(&inode_node->i_xtime, &ts) | - timespec_compare(&ts, &inode_node->i_xtime) + timespec64_compare(&ts, &inode_node->i_xtime) | ts = current_time(e) | fn_update_time(..., &ts,...) | inode_node->i_xtime = ts | node1->i_xtime = ts | ts = inode_node->i_xtime | <+... attr1->ia_xtime ...+> = ts | ts = attr1->ia_xtime | ts.tv_sec | ts.tv_nsec | btrfs_set_stack_timespec_sec(..., ts.tv_sec) | btrfs_set_stack_timespec_nsec(..., ts.tv_nsec) | - ts = timespec64_to_timespec( + ts = ... -) | - ts = ktime_to_timespec( + ts = ktime_to_timespec64( ...) | - ts = E3 + ts = timespec_to_timespec64(E3) | - ktime_get_real_ts(&ts) + ktime_get_real_ts64(&ts) | fn(..., - ts + timespec64_to_timespec(ts) ,...) ) ...+> ( <... when != ts - return ts; + return timespec64_to_timespec(ts); ...> ) | - timespec_equal(&node1->i_xtime1, &node2->i_xtime2) + timespec64_equal(&node1->i_xtime2, &node2->i_xtime2) | - timespec_equal(&node1->i_xtime1, &attr2->ia_xtime2) + timespec64_equal(&node1->i_xtime2, &attr2->ia_xtime2) | - timespec_compare(&node1->i_xtime1, &node2->i_xtime2) + timespec64_compare(&node1->i_xtime1, &node2->i_xtime2) | node1->i_xtime1 = - timespec_trunc(attr1->ia_xtime1, + timespec64_trunc(attr1->ia_xtime1, ...) | - attr1->ia_xtime1 = timespec_trunc(attr2->ia_xtime2, + attr1->ia_xtime1 = timespec64_trunc(attr2->ia_xtime2, ...) | - ktime_get_real_ts(&attr1->ia_xtime1) + ktime_get_real_ts64(&attr1->ia_xtime1) | - ktime_get_real_ts(&attr.ia_xtime1) + ktime_get_real_ts64(&attr.ia_xtime1) ) @ depends on patch @ struct inode *node; struct iattr *attr; identifier fn; identifier i_xtime =~ "^i_[acm]time$"; identifier ia_xtime =~ "^ia_[acm]time$"; expression e; @@ ( - fn(node->i_xtime); + fn(timespec64_to_timespec(node->i_xtime)); | fn(..., - node->i_xtime); + timespec64_to_timespec(node->i_xtime)); | - e = fn(attr->ia_xtime); + e = fn(timespec64_to_timespec(attr->ia_xtime)); ) @ depends on patch forall @ struct inode *node; struct iattr *attr; identifier i_xtime =~ "^i_[acm]time$"; identifier ia_xtime =~ "^ia_[acm]time$"; identifier fn; @@ { + struct timespec ts; <+... ( + ts = timespec64_to_timespec(node->i_xtime); fn (..., - &node->i_xtime, + &ts, ...); | + ts = timespec64_to_timespec(attr->ia_xtime); fn (..., - &attr->ia_xtime, + &ts, ...); ) ...+> } @ depends on patch forall @ struct inode *node; struct iattr *attr; struct kstat *stat; identifier ia_xtime =~ "^ia_[acm]time$"; identifier i_xtime =~ "^i_[acm]time$"; identifier xtime =~ "^[acm]time$"; identifier fn, ret; @@ { + struct timespec ts; <+... ( + ts = timespec64_to_timespec(node->i_xtime); ret = fn (..., - &node->i_xtime, + &ts, ...); | + ts = timespec64_to_timespec(node->i_xtime); ret = fn (..., - &node->i_xtime); + &ts); | + ts = timespec64_to_timespec(attr->ia_xtime); ret = fn (..., - &attr->ia_xtime, + &ts, ...); | + ts = timespec64_to_timespec(attr->ia_xtime); ret = fn (..., - &attr->ia_xtime); + &ts); | + ts = timespec64_to_timespec(stat->xtime); ret = fn (..., - &stat->xtime); + &ts); ) ...+> } @ depends on patch @ struct inode *node; struct inode *node2; identifier i_xtime1 =~ "^i_[acm]time$"; identifier i_xtime2 =~ "^i_[acm]time$"; identifier i_xtime3 =~ "^i_[acm]time$"; struct iattr *attrp; struct iattr *attrp2; struct iattr attr ; identifier ia_xtime1 =~ "^ia_[acm]time$"; identifier ia_xtime2 =~ "^ia_[acm]time$"; struct kstat *stat; struct kstat stat1; struct timespec64 ts; identifier xtime =~ "^[acmb]time$"; expression e; @@ ( ( node->i_xtime2 \| attrp->ia_xtime2 \| attr.ia_xtime2 \) = node->i_xtime1 ; | node->i_xtime2 = \( node2->i_xtime1 \| timespec64_trunc(...) \); | node->i_xtime2 = node->i_xtime1 = node->i_xtime3 = \(ts \| current_time(...) \); | node->i_xtime1 = node->i_xtime3 = \(ts \| current_time(...) \); | stat->xtime = node2->i_xtime1; | stat1.xtime = node2->i_xtime1; | ( node->i_xtime2 \| attrp->ia_xtime2 \) = attrp->ia_xtime1 ; | ( attrp->ia_xtime1 \| attr.ia_xtime1 \) = attrp2->ia_xtime2; | - e = node->i_xtime1; + e = timespec64_to_timespec( node->i_xtime1 ); | - e = attrp->ia_xtime1; + e = timespec64_to_timespec( attrp->ia_xtime1 ); | node->i_xtime1 = current_time(...); | node->i_xtime2 = node->i_xtime1 = node->i_xtime3 = - e; + timespec_to_timespec64(e); | node->i_xtime1 = node->i_xtime3 = - e; + timespec_to_timespec64(e); | - node->i_xtime1 = e; + node->i_xtime1 = timespec_to_timespec64(e); ) Signed-off-by: Deepa Dinamani <deepa.kernel@gmail.com> Cc: <anton@tuxera.com> Cc: <balbi@kernel.org> Cc: <bfields@fieldses.org> Cc: <darrick.wong@oracle.com> Cc: <dhowells@redhat.com> Cc: <dsterba@suse.com> Cc: <dwmw2@infradead.org> Cc: <hch@lst.de> Cc: <hirofumi@mail.parknet.co.jp> Cc: <hubcap@omnibond.com> Cc: <jack@suse.com> Cc: <jaegeuk@kernel.org> Cc: <jaharkes@cs.cmu.edu> Cc: <jslaby@suse.com> Cc: <keescook@chromium.org> Cc: <mark@fasheh.com> Cc: <miklos@szeredi.hu> Cc: <nico@linaro.org> Cc: <reiserfs-devel@vger.kernel.org> Cc: <richard@nod.at> Cc: <sage@redhat.com> Cc: <sfrench@samba.org> Cc: <swhiteho@redhat.com> Cc: <tj@kernel.org> Cc: <trond.myklebust@primarydata.com> Cc: <tytso@mit.edu> Cc: <viro@zeniv.linux.org.uk>
2018-05-09 10:36:02 +08:00
raw_inode->xtime ## _extra); \
} \
else \
(inode)->xtime.tv_nsec = 0; \
} while (0)
vfs: change inode times to use struct timespec64 struct timespec is not y2038 safe. Transition vfs to use y2038 safe struct timespec64 instead. The change was made with the help of the following cocinelle script. This catches about 80% of the changes. All the header file and logic changes are included in the first 5 rules. The rest are trivial substitutions. I avoid changing any of the function signatures or any other filesystem specific data structures to keep the patch simple for review. The script can be a little shorter by combining different cases. But, this version was sufficient for my usecase. virtual patch @ depends on patch @ identifier now; @@ - struct timespec + struct timespec64 current_time ( ... ) { - struct timespec now = current_kernel_time(); + struct timespec64 now = current_kernel_time64(); ... - return timespec_trunc( + return timespec64_trunc( ... ); } @ depends on patch @ identifier xtime; @@ struct \( iattr \| inode \| kstat \) { ... - struct timespec xtime; + struct timespec64 xtime; ... } @ depends on patch @ identifier t; @@ struct inode_operations { ... int (*update_time) (..., - struct timespec t, + struct timespec64 t, ...); ... } @ depends on patch @ identifier t; identifier fn_update_time =~ "update_time$"; @@ fn_update_time (..., - struct timespec *t, + struct timespec64 *t, ...) { ... } @ depends on patch @ identifier t; @@ lease_get_mtime( ... , - struct timespec *t + struct timespec64 *t ) { ... } @te depends on patch forall@ identifier ts; local idexpression struct inode *inode_node; identifier i_xtime =~ "^i_[acm]time$"; identifier ia_xtime =~ "^ia_[acm]time$"; identifier fn_update_time =~ "update_time$"; identifier fn; expression e, E3; local idexpression struct inode *node1; local idexpression struct inode *node2; local idexpression struct iattr *attr1; local idexpression struct iattr *attr2; local idexpression struct iattr attr; identifier i_xtime1 =~ "^i_[acm]time$"; identifier i_xtime2 =~ "^i_[acm]time$"; identifier ia_xtime1 =~ "^ia_[acm]time$"; identifier ia_xtime2 =~ "^ia_[acm]time$"; @@ ( ( - struct timespec ts; + struct timespec64 ts; | - struct timespec ts = current_time(inode_node); + struct timespec64 ts = current_time(inode_node); ) <+... when != ts ( - timespec_equal(&inode_node->i_xtime, &ts) + timespec64_equal(&inode_node->i_xtime, &ts) | - timespec_equal(&ts, &inode_node->i_xtime) + timespec64_equal(&ts, &inode_node->i_xtime) | - timespec_compare(&inode_node->i_xtime, &ts) + timespec64_compare(&inode_node->i_xtime, &ts) | - timespec_compare(&ts, &inode_node->i_xtime) + timespec64_compare(&ts, &inode_node->i_xtime) | ts = current_time(e) | fn_update_time(..., &ts,...) | inode_node->i_xtime = ts | node1->i_xtime = ts | ts = inode_node->i_xtime | <+... attr1->ia_xtime ...+> = ts | ts = attr1->ia_xtime | ts.tv_sec | ts.tv_nsec | btrfs_set_stack_timespec_sec(..., ts.tv_sec) | btrfs_set_stack_timespec_nsec(..., ts.tv_nsec) | - ts = timespec64_to_timespec( + ts = ... -) | - ts = ktime_to_timespec( + ts = ktime_to_timespec64( ...) | - ts = E3 + ts = timespec_to_timespec64(E3) | - ktime_get_real_ts(&ts) + ktime_get_real_ts64(&ts) | fn(..., - ts + timespec64_to_timespec(ts) ,...) ) ...+> ( <... when != ts - return ts; + return timespec64_to_timespec(ts); ...> ) | - timespec_equal(&node1->i_xtime1, &node2->i_xtime2) + timespec64_equal(&node1->i_xtime2, &node2->i_xtime2) | - timespec_equal(&node1->i_xtime1, &attr2->ia_xtime2) + timespec64_equal(&node1->i_xtime2, &attr2->ia_xtime2) | - timespec_compare(&node1->i_xtime1, &node2->i_xtime2) + timespec64_compare(&node1->i_xtime1, &node2->i_xtime2) | node1->i_xtime1 = - timespec_trunc(attr1->ia_xtime1, + timespec64_trunc(attr1->ia_xtime1, ...) | - attr1->ia_xtime1 = timespec_trunc(attr2->ia_xtime2, + attr1->ia_xtime1 = timespec64_trunc(attr2->ia_xtime2, ...) | - ktime_get_real_ts(&attr1->ia_xtime1) + ktime_get_real_ts64(&attr1->ia_xtime1) | - ktime_get_real_ts(&attr.ia_xtime1) + ktime_get_real_ts64(&attr.ia_xtime1) ) @ depends on patch @ struct inode *node; struct iattr *attr; identifier fn; identifier i_xtime =~ "^i_[acm]time$"; identifier ia_xtime =~ "^ia_[acm]time$"; expression e; @@ ( - fn(node->i_xtime); + fn(timespec64_to_timespec(node->i_xtime)); | fn(..., - node->i_xtime); + timespec64_to_timespec(node->i_xtime)); | - e = fn(attr->ia_xtime); + e = fn(timespec64_to_timespec(attr->ia_xtime)); ) @ depends on patch forall @ struct inode *node; struct iattr *attr; identifier i_xtime =~ "^i_[acm]time$"; identifier ia_xtime =~ "^ia_[acm]time$"; identifier fn; @@ { + struct timespec ts; <+... ( + ts = timespec64_to_timespec(node->i_xtime); fn (..., - &node->i_xtime, + &ts, ...); | + ts = timespec64_to_timespec(attr->ia_xtime); fn (..., - &attr->ia_xtime, + &ts, ...); ) ...+> } @ depends on patch forall @ struct inode *node; struct iattr *attr; struct kstat *stat; identifier ia_xtime =~ "^ia_[acm]time$"; identifier i_xtime =~ "^i_[acm]time$"; identifier xtime =~ "^[acm]time$"; identifier fn, ret; @@ { + struct timespec ts; <+... ( + ts = timespec64_to_timespec(node->i_xtime); ret = fn (..., - &node->i_xtime, + &ts, ...); | + ts = timespec64_to_timespec(node->i_xtime); ret = fn (..., - &node->i_xtime); + &ts); | + ts = timespec64_to_timespec(attr->ia_xtime); ret = fn (..., - &attr->ia_xtime, + &ts, ...); | + ts = timespec64_to_timespec(attr->ia_xtime); ret = fn (..., - &attr->ia_xtime); + &ts); | + ts = timespec64_to_timespec(stat->xtime); ret = fn (..., - &stat->xtime); + &ts); ) ...+> } @ depends on patch @ struct inode *node; struct inode *node2; identifier i_xtime1 =~ "^i_[acm]time$"; identifier i_xtime2 =~ "^i_[acm]time$"; identifier i_xtime3 =~ "^i_[acm]time$"; struct iattr *attrp; struct iattr *attrp2; struct iattr attr ; identifier ia_xtime1 =~ "^ia_[acm]time$"; identifier ia_xtime2 =~ "^ia_[acm]time$"; struct kstat *stat; struct kstat stat1; struct timespec64 ts; identifier xtime =~ "^[acmb]time$"; expression e; @@ ( ( node->i_xtime2 \| attrp->ia_xtime2 \| attr.ia_xtime2 \) = node->i_xtime1 ; | node->i_xtime2 = \( node2->i_xtime1 \| timespec64_trunc(...) \); | node->i_xtime2 = node->i_xtime1 = node->i_xtime3 = \(ts \| current_time(...) \); | node->i_xtime1 = node->i_xtime3 = \(ts \| current_time(...) \); | stat->xtime = node2->i_xtime1; | stat1.xtime = node2->i_xtime1; | ( node->i_xtime2 \| attrp->ia_xtime2 \) = attrp->ia_xtime1 ; | ( attrp->ia_xtime1 \| attr.ia_xtime1 \) = attrp2->ia_xtime2; | - e = node->i_xtime1; + e = timespec64_to_timespec( node->i_xtime1 ); | - e = attrp->ia_xtime1; + e = timespec64_to_timespec( attrp->ia_xtime1 ); | node->i_xtime1 = current_time(...); | node->i_xtime2 = node->i_xtime1 = node->i_xtime3 = - e; + timespec_to_timespec64(e); | node->i_xtime1 = node->i_xtime3 = - e; + timespec_to_timespec64(e); | - node->i_xtime1 = e; + node->i_xtime1 = timespec_to_timespec64(e); ) Signed-off-by: Deepa Dinamani <deepa.kernel@gmail.com> Cc: <anton@tuxera.com> Cc: <balbi@kernel.org> Cc: <bfields@fieldses.org> Cc: <darrick.wong@oracle.com> Cc: <dhowells@redhat.com> Cc: <dsterba@suse.com> Cc: <dwmw2@infradead.org> Cc: <hch@lst.de> Cc: <hirofumi@mail.parknet.co.jp> Cc: <hubcap@omnibond.com> Cc: <jack@suse.com> Cc: <jaegeuk@kernel.org> Cc: <jaharkes@cs.cmu.edu> Cc: <jslaby@suse.com> Cc: <keescook@chromium.org> Cc: <mark@fasheh.com> Cc: <miklos@szeredi.hu> Cc: <nico@linaro.org> Cc: <reiserfs-devel@vger.kernel.org> Cc: <richard@nod.at> Cc: <sage@redhat.com> Cc: <sfrench@samba.org> Cc: <swhiteho@redhat.com> Cc: <tj@kernel.org> Cc: <trond.myklebust@primarydata.com> Cc: <tytso@mit.edu> Cc: <viro@zeniv.linux.org.uk>
2018-05-09 10:36:02 +08:00
#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); \
else \
(einode)->xtime.tv_sec = 0; \
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__) */
#include "extents_status.h"
#include "fast_commit.h"
/*
* Lock subclasses for i_data_sem in the ext4_inode_info structure.
*
* These are needed to avoid lockdep false positives when we need to
* allocate blocks to the quota inode during ext4_map_blocks(), while
* holding i_data_sem for a normal (non-quota) inode. Since we don't
* do quota tracking for the quota inode, this avoids deadlock (as
* well as infinite recursion, since it isn't turtles all the way
* down...)
*
* I_DATA_SEM_NORMAL - Used for most inodes
* I_DATA_SEM_OTHER - Used by move_inode.c for the second normal inode
* where the second inode has larger inode number
* than the first
* I_DATA_SEM_QUOTA - Used for quota inodes only
*/
enum {
I_DATA_SEM_NORMAL = 0,
I_DATA_SEM_OTHER,
I_DATA_SEM_QUOTA,
};
/*
* 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 used 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;
/*
* Extended attributes can be read independently of the main file
* data. Taking i_rwsem 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;
ext4: Speedup ext4 orphan inode handling Ext4 orphan inode handling is a bottleneck for workloads which heavily truncate / unlink small files since it contends on the global s_orphan_mutex lock (and generally it's difficult to improve scalability of the ondisk linked list of orphaned inodes). This patch implements new way of handling orphan inodes. Instead of linking orphaned inode into a linked list, we store it's inode number in a new special file which we call "orphan file". Only if there's no more space in the orphan file (too many inodes are currently orphaned) we fall back to using old style linked list. Currently we protect operations in the orphan file with a spinlock for simplicity but even in this setting we can substantially reduce the length of the critical section and thus speedup some workloads. In the next patch we improve this by making orphan handling lockless. Note that the change is backwards compatible when the filesystem is clean - the existence of the orphan file is a compat feature, we set another ro-compat feature indicating orphan file needs scanning for orphaned inodes when mounting filesystem read-write. This ro-compat feature gets cleared on unmount / remount read-only. Some performance data from 80 CPU Xeon Server with 512 GB of RAM, filesystem located on SSD, average of 5 runs: stress-orphan (microbenchmark truncating files byte-by-byte from N processes in parallel) Threads Time Time Vanilla Patched 1 1.057200 0.945600 2 1.680400 1.331800 4 2.547000 1.995000 8 7.049400 6.424200 16 14.827800 14.937600 32 40.948200 33.038200 64 87.787400 60.823600 128 206.504000 122.941400 So we can see significant wins all over the board. Reviewed-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Jan Kara <jack@suse.cz> Link: https://lore.kernel.org/r/20210816095713.16537-3-jack@suse.cz Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2021-08-16 17:57:06 +08:00
/*
* Inodes with EXT4_STATE_ORPHAN_FILE use i_orphan_idx. Otherwise
* i_orphan is used.
*/
union {
struct list_head i_orphan; /* unlinked but open inodes */
unsigned int i_orphan_idx; /* Index in orphan file */
};
/* Fast commit related info */
ext4: improve fast_commit performance and scalability Currently ext4_fc_commit_dentry_updates() is of quadratic time complexity, which is causing performance bottlenecks with high threads/file/dir count with fs_mark. This patch makes commit dentry updates (and hence ext4_fc_commit()) path to linear time complexity. Hence improves the performance of workloads which does fsync on multiple threads/open files one-by-one. Absolute numbers in avg file creates per sec (from fs_mark in 1K order) ======================================================================= no. Order without-patch(K) with-patch(K) Diff(%) 1 1 16.90 17.51 +3.60 2 2,2 32.08 31.80 -0.87 3 3,3 53.97 55.01 +1.92 4 4,4 78.94 76.90 -2.58 5 5,5 95.82 95.37 -0.46 6 6,6 87.92 103.38 +17.58 7 6,10 0.73 126.13 +17178.08 8 6,14 2.33 143.19 +6045.49 workload type ============== For e.g. 7th row order of 6,10 (2^6 == 64 && 2^10 == 1024) echo /run/riteshh/mnt/{1..64} |sed -E 's/[[:space:]]+/ -d /g' \ | xargs -I {} bash -c "sudo fs_mark -L 100 -D 1024 -n 1024 -s0 -S5 -d {}" Perf profile (w/o patches) ============================= 87.15% [kernel] [k] ext4_fc_commit --> Heavy contention/bottleneck 1.98% [kernel] [k] perf_event_interrupt 0.96% [kernel] [k] power_pmu_enable 0.91% [kernel] [k] update_sd_lb_stats.constprop.0 0.67% [kernel] [k] ktime_get Signed-off-by: Ritesh Harjani <riteshh@linux.ibm.com> Reviewed-by: Harshad Shirwadkar <harshadshirwadkar@gmail.com> Link: https://lore.kernel.org/r/930f35d4fd5f83e2673c868781d9ebf15e91bf4e.1645426817.git.riteshh@linux.ibm.com Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2022-02-21 15:56:15 +08:00
/* For tracking dentry create updates */
struct list_head i_fc_dilist;
struct list_head i_fc_list; /*
* inodes that need fast commit
* protected by sbi->s_fc_lock.
*/
/* Start of lblk range that needs to be committed in this fast commit */
ext4_lblk_t i_fc_lblk_start;
/* End of lblk range that needs to be committed in this fast commit */
ext4_lblk_t i_fc_lblk_len;
/* Number of ongoing updates on this inode */
atomic_t i_fc_updates;
/* Fast commit wait queue for this inode */
wait_queue_head_t i_fc_wait;
/* Protect concurrent accesses on i_fc_lblk_start, i_fc_lblk_len */
struct mutex i_fc_lock;
/*
* 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;
spinlock_t i_raw_lock; /* protects updates to the raw inode */
/*
* File creation time. Its function is same as that of
* struct timespec64 i_{a,c,m}time in the generic inode.
*/
struct timespec64 i_crtime;
/* mballoc */
atomic_t i_prealloc_active;
struct list_head i_prealloc_list;
spinlock_t i_prealloc_lock;
/* extents status tree */
struct ext4_es_tree i_es_tree;
rwlock_t i_es_lock;
struct list_head i_es_list;
ext4: track extent status tree shrinker delay statictics This commit adds some statictics in extent status tree shrinker. The purpose to add these is that we want to collect more details when we encounter a stall caused by extent status tree shrinker. Here we count the following statictics: stats: the number of all objects on all extent status trees the number of reclaimable objects on lru list cache hits/misses the last sorted interval the number of inodes on lru list average: scan time for shrinking some objects the number of shrunk objects maximum: the inode that has max nr. of objects on lru list the maximum scan time for shrinking some objects The output looks like below: $ cat /proc/fs/ext4/sda1/es_shrinker_info stats: 28228 objects 6341 reclaimable objects 5281/631 cache hits/misses 586 ms last sorted interval 250 inodes on lru list average: 153 us scan time 128 shrunk objects maximum: 255 inode (255 objects, 198 reclaimable) 125723 us max scan time If the lru list has never been sorted, the following line will not be printed: 586ms last sorted interval If there is an empty lru list, the following lines also will not be printed: 250 inodes on lru list ... maximum: 255 inode (255 objects, 198 reclaimable) 0 us max scan time Meanwhile in this commit a new trace point is defined to print some details in __ext4_es_shrink(). Cc: Andreas Dilger <adilger.kernel@dilger.ca> Cc: Jan Kara <jack@suse.cz> Reviewed-by: Jan Kara <jack@suse.cz> Signed-off-by: Zheng Liu <wenqing.lz@taobao.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2014-09-02 10:26:49 +08:00
unsigned int i_es_all_nr; /* protected by i_es_lock */
unsigned int i_es_shk_nr; /* protected by i_es_lock */
ext4_lblk_t i_es_shrink_lblk; /* Offset where we start searching for
extents to shrink. Protected by
i_es_lock */
/* ialloc */
ext4_group_t i_last_alloc_group;
/* allocation reservation info for delalloc */
/* In case of bigalloc, this refer to clusters rather than blocks */
unsigned int i_reserved_data_blocks;
/* pending cluster reservations for bigalloc file systems */
struct ext4_pending_tree i_pending_tree;
/* on-disk additional length */
__u16 i_extra_isize;
/* Indicate the inline data space. */
u16 i_inline_off;
u16 i_inline_size;
#ifdef CONFIG_QUOTA
/* quota space reservation, managed internally by quota code */
qsize_t i_reserved_quota;
#endif
/* Lock protecting lists below */
spinlock_t i_completed_io_lock;
/*
* Completed IOs that need unwritten extents handling and have
* transaction reserved
*/
struct list_head i_rsv_conversion_list;
struct work_struct i_rsv_conversion_work;
atomic_t i_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;
#ifdef CONFIG_QUOTA
struct dquot *i_dquot[MAXQUOTAS];
#endif
/* Precomputed uuid+inum+igen checksum for seeding inode checksums */
__u32 i_csum_seed;
kprojid_t i_projid;
};
/*
* 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 */
#define EXT4_FC_REPLAY 0x0020 /* Fast commit replay ongoing */
/*
* 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 set via mount options or defaults
*/
#define EXT4_MOUNT_NO_MBCACHE 0x00001 /* Do not use mbcache */
#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*/
#ifdef CONFIG_FS_DAX
#define EXT4_MOUNT_DAX_ALWAYS 0x00200 /* Direct Access */
#else
#define EXT4_MOUNT_DAX_ALWAYS 0
#endif
#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 0x40000 /* Some quota option set */
#define EXT4_MOUNT_USRQUOTA 0x80000 /* "old" user quota,
* enable enforcement for hidden
* quota files */
#define EXT4_MOUNT_GRPQUOTA 0x100000 /* "old" group quota, enable
* enforcement for hidden quota
* files */
#define EXT4_MOUNT_PRJQUOTA 0x200000 /* Enable project quota
* enforcement */
#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_WARN_ON_ERROR 0x2000000 /* Trigger WARN_ON on error */
#define EXT4_MOUNT_NO_PREFETCH_BLOCK_BITMAPS 0x4000000
#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 09:30:05 +08:00
#define EXT4_MOUNT_INIT_INODE_TABLE 0x80000000 /* Initialize uninitialized itables */
/*
* Mount flags set either automatically (could not be set by mount option)
* based on per file system feature or property or in special cases such as
* distinguishing between explicit mount option definition and default.
*/
#define EXT4_MOUNT2_EXPLICIT_DELALLOC 0x00000001 /* User explicitly
specified delalloc */
#define EXT4_MOUNT2_STD_GROUP_SIZE 0x00000002 /* We have standard group
size of blocksize * 8
blocks */
#define EXT4_MOUNT2_HURD_COMPAT 0x00000004 /* Support HURD-castrated
file systems */
#define EXT4_MOUNT2_EXPLICIT_JOURNAL_CHECKSUM 0x00000008 /* User explicitly
specified journal checksum */
#define EXT4_MOUNT2_JOURNAL_FAST_COMMIT 0x00000010 /* Journal fast commit */
#define EXT4_MOUNT2_DAX_NEVER 0x00000020 /* Do not allow Direct Access */
#define EXT4_MOUNT2_DAX_INODE 0x00000040 /* For printing options only */
ext4: improve cr 0 / cr 1 group scanning Instead of traversing through groups linearly, scan groups in specific orders at cr 0 and cr 1. At cr 0, we want to find groups that have the largest free order >= the order of the request. So, with this patch, we maintain lists for each possible order and insert each group into a list based on the largest free order in its buddy bitmap. During cr 0 allocation, we traverse these lists in the increasing order of largest free orders. This allows us to find a group with the best available cr 0 match in constant time. If nothing can be found, we fallback to cr 1 immediately. At CR1, the story is slightly different. We want to traverse in the order of increasing average fragment size. For CR1, we maintain a rb tree of groupinfos which is sorted by average fragment size. Instead of traversing linearly, at CR1, we traverse in the order of increasing average fragment size, starting at the most optimal group. This brings down cr 1 search complexity to log(num groups). For cr >= 2, we just perform the linear search as before. Also, in case of lock contention, we intermittently fallback to linear search even in CR 0 and CR 1 cases. This allows us to proceed during the allocation path even in case of high contention. There is an opportunity to do optimization at CR2 too. That's because at CR2 we only consider groups where bb_free counter (number of free blocks) is greater than the request extent size. That's left as future work. All the changes introduced in this patch are protected under a new mount option "mb_optimize_scan". With this patchset, following experiment was performed: Created a highly fragmented disk of size 65TB. The disk had no contiguous 2M regions. Following command was run consecutively for 3 times: time dd if=/dev/urandom of=file bs=2M count=10 Here are the results with and without cr 0/1 optimizations introduced in this patch: |---------+------------------------------+---------------------------| | | Without CR 0/1 Optimizations | With CR 0/1 Optimizations | |---------+------------------------------+---------------------------| | 1st run | 5m1.871s | 2m47.642s | | 2nd run | 2m28.390s | 0m0.611s | | 3rd run | 2m26.530s | 0m1.255s | |---------+------------------------------+---------------------------| Signed-off-by: Harshad Shirwadkar <harshadshirwadkar@gmail.com> Reported-by: kernel test robot <lkp@intel.com> Reported-by: Dan Carpenter <dan.carpenter@oracle.com> Reviewed-by: Andreas Dilger <adilger@dilger.ca> Link: https://lore.kernel.org/r/20210401172129.189766-6-harshadshirwadkar@gmail.com Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2021-04-02 01:21:27 +08:00
#define EXT4_MOUNT2_MB_OPTIMIZE_SCAN 0x00000080 /* Optimize group
* scanning in mballoc
*/
#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 mb_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
#define EXT4_LABEL_MAX 16
/*
* 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[EXT4_LABEL_MAX]; /* volume name */
/*88*/ char s_last_mounted[64] __nonstring; /* 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 */
__u8 s_encryption_level; /* versioning level for encryption */
__u8 s_reserved_pad; /* Padding to next 32bits */
__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] __nonstring; /* 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] __nonstring; /* 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_backup_bgs[2]; /* groups with sparse_super2 SBs */
__u8 s_encrypt_algos[4]; /* Encryption algorithms in use */
__u8 s_encrypt_pw_salt[16]; /* Salt used for string2key algorithm */
__le32 s_lpf_ino; /* Location of the lost+found inode */
__le32 s_prj_quota_inum; /* inode for tracking project quota */
__le32 s_checksum_seed; /* crc32c(uuid) if csum_seed set */
__u8 s_wtime_hi;
__u8 s_mtime_hi;
__u8 s_mkfs_time_hi;
__u8 s_lastcheck_hi;
__u8 s_first_error_time_hi;
__u8 s_last_error_time_hi;
__u8 s_first_error_errcode;
__u8 s_last_error_errcode;
__le16 s_encoding; /* Filename charset encoding */
__le16 s_encoding_flags; /* Filename charset encoding flags */
ext4: Speedup ext4 orphan inode handling Ext4 orphan inode handling is a bottleneck for workloads which heavily truncate / unlink small files since it contends on the global s_orphan_mutex lock (and generally it's difficult to improve scalability of the ondisk linked list of orphaned inodes). This patch implements new way of handling orphan inodes. Instead of linking orphaned inode into a linked list, we store it's inode number in a new special file which we call "orphan file". Only if there's no more space in the orphan file (too many inodes are currently orphaned) we fall back to using old style linked list. Currently we protect operations in the orphan file with a spinlock for simplicity but even in this setting we can substantially reduce the length of the critical section and thus speedup some workloads. In the next patch we improve this by making orphan handling lockless. Note that the change is backwards compatible when the filesystem is clean - the existence of the orphan file is a compat feature, we set another ro-compat feature indicating orphan file needs scanning for orphaned inodes when mounting filesystem read-write. This ro-compat feature gets cleared on unmount / remount read-only. Some performance data from 80 CPU Xeon Server with 512 GB of RAM, filesystem located on SSD, average of 5 runs: stress-orphan (microbenchmark truncating files byte-by-byte from N processes in parallel) Threads Time Time Vanilla Patched 1 1.057200 0.945600 2 1.680400 1.331800 4 2.547000 1.995000 8 7.049400 6.424200 16 14.827800 14.937600 32 40.948200 33.038200 64 87.787400 60.823600 128 206.504000 122.941400 So we can see significant wins all over the board. Reviewed-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Jan Kara <jack@suse.cz> Link: https://lore.kernel.org/r/20210816095713.16537-3-jack@suse.cz Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2021-08-16 17:57:06 +08:00
__le32 s_orphan_file_inum; /* Inode for tracking orphan inodes */
__le32 s_reserved[94]; /* 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__
#ifdef CONFIG_FS_ENCRYPTION
fscrypt: handle test_dummy_encryption in more logical way The behavior of the test_dummy_encryption mount option is that when a new file (or directory or symlink) is created in an unencrypted directory, it's automatically encrypted using a dummy encryption policy. That's it; in particular, the encryption (or lack thereof) of existing files (or directories or symlinks) doesn't change. Unfortunately the implementation of test_dummy_encryption is a bit weird and confusing. When test_dummy_encryption is enabled and a file is being created in an unencrypted directory, we set up an encryption key (->i_crypt_info) for the directory. This isn't actually used to do any encryption, however, since the directory is still unencrypted! Instead, ->i_crypt_info is only used for inheriting the encryption policy. One consequence of this is that the filesystem ends up providing a "dummy context" (policy + nonce) instead of a "dummy policy". In commit ed318a6cc0b6 ("fscrypt: support test_dummy_encryption=v2"), I mistakenly thought this was required. However, actually the nonce only ends up being used to derive a key that is never used. Another consequence of this implementation is that it allows for 'inode->i_crypt_info != NULL && !IS_ENCRYPTED(inode)', which is an edge case that can be forgotten about. For example, currently FS_IOC_GET_ENCRYPTION_POLICY on an unencrypted directory may return the dummy encryption policy when the filesystem is mounted with test_dummy_encryption. That seems like the wrong thing to do, since again, the directory itself is not actually encrypted. Therefore, switch to a more logical and maintainable implementation where the dummy encryption policy inheritance is done without setting up keys for unencrypted directories. This involves: - Adding a function fscrypt_policy_to_inherit() which returns the encryption policy to inherit from a directory. This can be a real policy, a dummy policy, or no policy. - Replacing struct fscrypt_dummy_context, ->get_dummy_context(), etc. with struct fscrypt_dummy_policy, ->get_dummy_policy(), etc. - Making fscrypt_fname_encrypted_size() take an fscrypt_policy instead of an inode. Acked-by: Jaegeuk Kim <jaegeuk@kernel.org> Acked-by: Jeff Layton <jlayton@kernel.org> Link: https://lore.kernel.org/r/20200917041136.178600-13-ebiggers@kernel.org Signed-off-by: Eric Biggers <ebiggers@google.com>
2020-09-17 12:11:35 +08:00
#define DUMMY_ENCRYPTION_ENABLED(sbi) ((sbi)->s_dummy_enc_policy.policy != NULL)
#else
#define DUMMY_ENCRYPTION_ENABLED(sbi) (0)
#endif
/* Number of quota types we support */
#define EXT4_MAXQUOTAS 3
#define EXT4_ENC_UTF8_12_1 1
/* Types of ext4 journal triggers */
enum ext4_journal_trigger_type {
ext4: Speedup ext4 orphan inode handling Ext4 orphan inode handling is a bottleneck for workloads which heavily truncate / unlink small files since it contends on the global s_orphan_mutex lock (and generally it's difficult to improve scalability of the ondisk linked list of orphaned inodes). This patch implements new way of handling orphan inodes. Instead of linking orphaned inode into a linked list, we store it's inode number in a new special file which we call "orphan file". Only if there's no more space in the orphan file (too many inodes are currently orphaned) we fall back to using old style linked list. Currently we protect operations in the orphan file with a spinlock for simplicity but even in this setting we can substantially reduce the length of the critical section and thus speedup some workloads. In the next patch we improve this by making orphan handling lockless. Note that the change is backwards compatible when the filesystem is clean - the existence of the orphan file is a compat feature, we set another ro-compat feature indicating orphan file needs scanning for orphaned inodes when mounting filesystem read-write. This ro-compat feature gets cleared on unmount / remount read-only. Some performance data from 80 CPU Xeon Server with 512 GB of RAM, filesystem located on SSD, average of 5 runs: stress-orphan (microbenchmark truncating files byte-by-byte from N processes in parallel) Threads Time Time Vanilla Patched 1 1.057200 0.945600 2 1.680400 1.331800 4 2.547000 1.995000 8 7.049400 6.424200 16 14.827800 14.937600 32 40.948200 33.038200 64 87.787400 60.823600 128 206.504000 122.941400 So we can see significant wins all over the board. Reviewed-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Jan Kara <jack@suse.cz> Link: https://lore.kernel.org/r/20210816095713.16537-3-jack@suse.cz Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2021-08-16 17:57:06 +08:00
EXT4_JTR_ORPHAN_FILE,
EXT4_JTR_NONE /* This must be the last entry for indexing to work! */
};
#define EXT4_JOURNAL_TRIGGER_COUNT EXT4_JTR_NONE
struct ext4_journal_trigger {
struct jbd2_buffer_trigger_type tr_triggers;
struct super_block *sb;
};
static inline struct ext4_journal_trigger *EXT4_TRIGGER(
struct jbd2_buffer_trigger_type *trigger)
{
return container_of(trigger, struct ext4_journal_trigger, tr_triggers);
}
ext4: Speedup ext4 orphan inode handling Ext4 orphan inode handling is a bottleneck for workloads which heavily truncate / unlink small files since it contends on the global s_orphan_mutex lock (and generally it's difficult to improve scalability of the ondisk linked list of orphaned inodes). This patch implements new way of handling orphan inodes. Instead of linking orphaned inode into a linked list, we store it's inode number in a new special file which we call "orphan file". Only if there's no more space in the orphan file (too many inodes are currently orphaned) we fall back to using old style linked list. Currently we protect operations in the orphan file with a spinlock for simplicity but even in this setting we can substantially reduce the length of the critical section and thus speedup some workloads. In the next patch we improve this by making orphan handling lockless. Note that the change is backwards compatible when the filesystem is clean - the existence of the orphan file is a compat feature, we set another ro-compat feature indicating orphan file needs scanning for orphaned inodes when mounting filesystem read-write. This ro-compat feature gets cleared on unmount / remount read-only. Some performance data from 80 CPU Xeon Server with 512 GB of RAM, filesystem located on SSD, average of 5 runs: stress-orphan (microbenchmark truncating files byte-by-byte from N processes in parallel) Threads Time Time Vanilla Patched 1 1.057200 0.945600 2 1.680400 1.331800 4 2.547000 1.995000 8 7.049400 6.424200 16 14.827800 14.937600 32 40.948200 33.038200 64 87.787400 60.823600 128 206.504000 122.941400 So we can see significant wins all over the board. Reviewed-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Jan Kara <jack@suse.cz> Link: https://lore.kernel.org/r/20210816095713.16537-3-jack@suse.cz Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2021-08-16 17:57:06 +08:00
#define EXT4_ORPHAN_BLOCK_MAGIC 0x0b10ca04
/* Structure at the tail of orphan block */
struct ext4_orphan_block_tail {
__le32 ob_magic;
__le32 ob_checksum;
};
static inline int ext4_inodes_per_orphan_block(struct super_block *sb)
{
return (sb->s_blocksize - sizeof(struct ext4_orphan_block_tail)) /
sizeof(u32);
}
struct ext4_orphan_block {
ext4: Improve scalability of ext4 orphan file handling Even though the length of the critical section when adding / removing orphaned inodes was significantly reduced by using orphan file, the contention of lock protecting orphan file still appears high in profiles for truncate / unlink intensive workloads with high number of threads. This patch makes handling of orphan file completely lockless. Also to reduce conflicts between CPUs different CPUs start searching for empty slot in orphan file in different blocks. Performance comparison of locked orphan file handling, lockless orphan file handling, and completely disabled orphan inode handling from 80 CPU Xeon Server with 526 GB of RAM, filesystem located on SAS SSD disk, average of 5 runs: stress-orphan (microbenchmark truncating files byte-by-byte from N processes in parallel) Threads Time Time Time Orphan locked Orphan lockless No orphan 1 0.945600 0.939400 0.891200 2 1.331800 1.246600 1.174400 4 1.995000 1.780600 1.713200 8 6.424200 4.900000 4.106000 16 14.937600 8.516400 8.138000 32 33.038200 24.565600 24.002200 64 60.823600 39.844600 38.440200 128 122.941400 70.950400 69.315000 So we can see that with lockless orphan file handling, addition / deletion of orphaned inodes got almost completely out of picture even for a microbenchmark stressing it. For reaim creat_clo workload on ramdisk there are also noticeable gains (average of 5 runs): Clients Vanilla (ops/s) Patched (ops/s) creat_clo-1 14705.88 ( 0.00%) 14354.07 * -2.39%* creat_clo-3 27108.43 ( 0.00%) 28301.89 ( 4.40%) creat_clo-5 37406.48 ( 0.00%) 45180.73 * 20.78%* creat_clo-7 41338.58 ( 0.00%) 54687.50 * 32.29%* creat_clo-9 45226.13 ( 0.00%) 62937.07 * 39.16%* creat_clo-11 44000.00 ( 0.00%) 65088.76 * 47.93%* creat_clo-13 36516.85 ( 0.00%) 68661.97 * 88.03%* creat_clo-15 30864.20 ( 0.00%) 69551.78 * 125.35%* creat_clo-17 27478.45 ( 0.00%) 67729.08 * 146.48%* creat_clo-19 25000.00 ( 0.00%) 61621.62 * 146.49%* creat_clo-21 18772.35 ( 0.00%) 63829.79 * 240.02%* creat_clo-23 16698.94 ( 0.00%) 61938.96 * 270.92%* creat_clo-25 14973.05 ( 0.00%) 56947.61 * 280.33%* creat_clo-27 16436.69 ( 0.00%) 65008.03 * 295.51%* creat_clo-29 13949.01 ( 0.00%) 69047.62 * 395.00%* creat_clo-31 14283.52 ( 0.00%) 67982.45 * 375.95%* Reviewed-by: Theodore Ts'o <tytso@mit.edu> Reviewed-by: Lukas Czerner <lczerner@redhat.com> Signed-off-by: Jan Kara <jack@suse.cz> Link: https://lore.kernel.org/r/20210816095713.16537-5-jack@suse.cz Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2021-08-16 17:57:08 +08:00
atomic_t ob_free_entries; /* Number of free orphan entries in block */
ext4: Speedup ext4 orphan inode handling Ext4 orphan inode handling is a bottleneck for workloads which heavily truncate / unlink small files since it contends on the global s_orphan_mutex lock (and generally it's difficult to improve scalability of the ondisk linked list of orphaned inodes). This patch implements new way of handling orphan inodes. Instead of linking orphaned inode into a linked list, we store it's inode number in a new special file which we call "orphan file". Only if there's no more space in the orphan file (too many inodes are currently orphaned) we fall back to using old style linked list. Currently we protect operations in the orphan file with a spinlock for simplicity but even in this setting we can substantially reduce the length of the critical section and thus speedup some workloads. In the next patch we improve this by making orphan handling lockless. Note that the change is backwards compatible when the filesystem is clean - the existence of the orphan file is a compat feature, we set another ro-compat feature indicating orphan file needs scanning for orphaned inodes when mounting filesystem read-write. This ro-compat feature gets cleared on unmount / remount read-only. Some performance data from 80 CPU Xeon Server with 512 GB of RAM, filesystem located on SSD, average of 5 runs: stress-orphan (microbenchmark truncating files byte-by-byte from N processes in parallel) Threads Time Time Vanilla Patched 1 1.057200 0.945600 2 1.680400 1.331800 4 2.547000 1.995000 8 7.049400 6.424200 16 14.827800 14.937600 32 40.948200 33.038200 64 87.787400 60.823600 128 206.504000 122.941400 So we can see significant wins all over the board. Reviewed-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Jan Kara <jack@suse.cz> Link: https://lore.kernel.org/r/20210816095713.16537-3-jack@suse.cz Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2021-08-16 17:57:06 +08:00
struct buffer_head *ob_bh; /* Buffer for orphan block */
};
/*
* Info about orphan file.
*/
struct ext4_orphan_info {
int of_blocks; /* Number of orphan blocks in a file */
__u32 of_csum_seed; /* Checksum seed for orphan file */
struct ext4_orphan_block *of_binfo; /* Array with info about orphan
* file blocks */
};
/*
* 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; /* # of fs overhead clusters */
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 * __rcu *s_group_desc;
unsigned int s_mount_opt;
unsigned int s_mount_opt2;
unsigned long s_mount_flags;
unsigned int s_def_mount_opt;
ext4_fsblk_t s_sb_block;
ext4: introduce reserved space Currently in ENOSPC condition when writing into unwritten space, or punching a hole, we might need to split the extent and grow extent tree. However since we can not allocate any new metadata blocks we'll have to zero out unwritten part of extent or punched out part of extent, or in the worst case return ENOSPC even though use actually does not allocate any space. Also in delalloc path we do reserve metadata and data blocks for the time we're going to write out, however metadata block reservation is very tricky especially since we expect that logical connectivity implies physical connectivity, however that might not be the case and hence we might end up allocating more metadata blocks than previously reserved. So in future, metadata reservation checks should be removed since we can not assure that we do not under reserve. And this is where reserved space comes into the picture. When mounting the file system we slice off a little bit of the file system space (2% or 4096 clusters, whichever is smaller) which can be then used for the cases mentioned above to prevent costly zeroout, or unexpected ENOSPC. The number of reserved clusters can be set via sysfs, however it can never be bigger than number of free clusters in the file system. Note that this patch fixes the failure of xfstest 274 as expected. Signed-off-by: Lukas Czerner <lczerner@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu> Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
2013-04-10 10:11:22 +08:00
atomic64_t s_resv_clusters;
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;
u32 s_hash_seed[4];
int s_def_hash_version;
int s_hash_unsigned; /* 3 if hash should be unsigned, 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;
ext4: shrink race window in ext4_should_retry_alloc() When generic/371 is run on kvm-xfstests using 5.10 and 5.11 kernels, it fails at significant rates on the two test scenarios that disable delayed allocation (ext3conv and data_journal) and force actual block allocation for the fallocate and pwrite functions in the test. The failure rate on 5.10 for both ext3conv and data_journal on one test system typically runs about 85%. On 5.11, the failure rate on ext3conv sometimes drops to as low as 1% while the rate on data_journal increases to nearly 100%. The observed failures are largely due to ext4_should_retry_alloc() cutting off block allocation retries when s_mb_free_pending (used to indicate that a transaction in progress will free blocks) is 0. However, free space is usually available when this occurs during runs of generic/371. It appears that a thread attempting to allocate blocks is just missing transaction commits in other threads that increase the free cluster count and reset s_mb_free_pending while the allocating thread isn't running. Explicitly testing for free space availability avoids this race. The current code uses a post-increment operator in the conditional expression that determines whether the retry limit has been exceeded. This means that the conditional expression uses the value of the retry counter before it's increased, resulting in an extra retry cycle. The current code actually retries twice before hitting its retry limit rather than once. Increasing the retry limit to 3 from the current actual maximum retry count of 2 in combination with the change described above reduces the observed failure rate to less that 0.1% on both ext3conv and data_journal with what should be limited impact on users sensitive to the overhead caused by retries. A per filesystem percpu counter exported via sysfs is added to allow users or developers to track the number of times the retry limit is exceeded without resorting to debugging methods. This should provide some insight into worst case retry behavior. Signed-off-by: Eric Whitney <enwlinux@gmail.com> Link: https://lore.kernel.org/r/20210218151132.19678-1-enwlinux@gmail.com Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2021-02-18 23:11:32 +08:00
struct percpu_counter s_sra_exceeded_retry_limit;
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;
struct buffer_head *s_mmp_bh;
/* Journaling */
struct journal_s *s_journal;
unsigned long s_ext4_flags; /* Ext4 superblock flags */
ext4: Speedup ext4 orphan inode handling Ext4 orphan inode handling is a bottleneck for workloads which heavily truncate / unlink small files since it contends on the global s_orphan_mutex lock (and generally it's difficult to improve scalability of the ondisk linked list of orphaned inodes). This patch implements new way of handling orphan inodes. Instead of linking orphaned inode into a linked list, we store it's inode number in a new special file which we call "orphan file". Only if there's no more space in the orphan file (too many inodes are currently orphaned) we fall back to using old style linked list. Currently we protect operations in the orphan file with a spinlock for simplicity but even in this setting we can substantially reduce the length of the critical section and thus speedup some workloads. In the next patch we improve this by making orphan handling lockless. Note that the change is backwards compatible when the filesystem is clean - the existence of the orphan file is a compat feature, we set another ro-compat feature indicating orphan file needs scanning for orphaned inodes when mounting filesystem read-write. This ro-compat feature gets cleared on unmount / remount read-only. Some performance data from 80 CPU Xeon Server with 512 GB of RAM, filesystem located on SSD, average of 5 runs: stress-orphan (microbenchmark truncating files byte-by-byte from N processes in parallel) Threads Time Time Vanilla Patched 1 1.057200 0.945600 2 1.680400 1.331800 4 2.547000 1.995000 8 7.049400 6.424200 16 14.827800 14.937600 32 40.948200 33.038200 64 87.787400 60.823600 128 206.504000 122.941400 So we can see significant wins all over the board. Reviewed-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Jan Kara <jack@suse.cz> Link: https://lore.kernel.org/r/20210816095713.16537-3-jack@suse.cz Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2021-08-16 17:57:06 +08:00
struct mutex s_orphan_lock; /* Protects on disk list changes */
struct list_head s_orphan; /* List of orphaned inodes in on disk
list */
struct ext4_orphan_info s_orphan_info;
unsigned long s_commit_interval;
u32 s_max_batch_time;
u32 s_min_batch_time;
struct block_device *s_journal_bdev;
#ifdef CONFIG_QUOTA
/* Names of quota files with journalled quota */
char __rcu *s_qf_names[EXT4_MAXQUOTAS];
int s_jquota_fmt; /* Format of quota to use */
#endif
unsigned int s_want_extra_isize; /* New inodes should reserve # bytes */
struct ext4_system_blocks __rcu *s_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 ** __rcu *s_group_info;
struct inode *s_buddy_cache;
spinlock_t s_md_lock;
unsigned short *s_mb_offsets;
unsigned int *s_mb_maxs;
unsigned int s_group_info_size;
unsigned int s_mb_free_pending;
struct list_head s_freed_data_list; /* List of blocks to be freed
after commit completed */
2021-07-24 15:41:23 +08:00
struct list_head s_discard_list;
struct work_struct s_discard_work;
atomic_t s_retry_alloc_pending;
ext4: improve cr 0 / cr 1 group scanning Instead of traversing through groups linearly, scan groups in specific orders at cr 0 and cr 1. At cr 0, we want to find groups that have the largest free order >= the order of the request. So, with this patch, we maintain lists for each possible order and insert each group into a list based on the largest free order in its buddy bitmap. During cr 0 allocation, we traverse these lists in the increasing order of largest free orders. This allows us to find a group with the best available cr 0 match in constant time. If nothing can be found, we fallback to cr 1 immediately. At CR1, the story is slightly different. We want to traverse in the order of increasing average fragment size. For CR1, we maintain a rb tree of groupinfos which is sorted by average fragment size. Instead of traversing linearly, at CR1, we traverse in the order of increasing average fragment size, starting at the most optimal group. This brings down cr 1 search complexity to log(num groups). For cr >= 2, we just perform the linear search as before. Also, in case of lock contention, we intermittently fallback to linear search even in CR 0 and CR 1 cases. This allows us to proceed during the allocation path even in case of high contention. There is an opportunity to do optimization at CR2 too. That's because at CR2 we only consider groups where bb_free counter (number of free blocks) is greater than the request extent size. That's left as future work. All the changes introduced in this patch are protected under a new mount option "mb_optimize_scan". With this patchset, following experiment was performed: Created a highly fragmented disk of size 65TB. The disk had no contiguous 2M regions. Following command was run consecutively for 3 times: time dd if=/dev/urandom of=file bs=2M count=10 Here are the results with and without cr 0/1 optimizations introduced in this patch: |---------+------------------------------+---------------------------| | | Without CR 0/1 Optimizations | With CR 0/1 Optimizations | |---------+------------------------------+---------------------------| | 1st run | 5m1.871s | 2m47.642s | | 2nd run | 2m28.390s | 0m0.611s | | 3rd run | 2m26.530s | 0m1.255s | |---------+------------------------------+---------------------------| Signed-off-by: Harshad Shirwadkar <harshadshirwadkar@gmail.com> Reported-by: kernel test robot <lkp@intel.com> Reported-by: Dan Carpenter <dan.carpenter@oracle.com> Reviewed-by: Andreas Dilger <adilger@dilger.ca> Link: https://lore.kernel.org/r/20210401172129.189766-6-harshadshirwadkar@gmail.com Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2021-04-02 01:21:27 +08:00
struct rb_root s_mb_avg_fragment_size_root;
rwlock_t s_mb_rb_lock;
struct list_head *s_mb_largest_free_orders;
rwlock_t *s_mb_largest_free_orders_locks;
/* tunables */
unsigned long s_stripe;
ext4: improve cr 0 / cr 1 group scanning Instead of traversing through groups linearly, scan groups in specific orders at cr 0 and cr 1. At cr 0, we want to find groups that have the largest free order >= the order of the request. So, with this patch, we maintain lists for each possible order and insert each group into a list based on the largest free order in its buddy bitmap. During cr 0 allocation, we traverse these lists in the increasing order of largest free orders. This allows us to find a group with the best available cr 0 match in constant time. If nothing can be found, we fallback to cr 1 immediately. At CR1, the story is slightly different. We want to traverse in the order of increasing average fragment size. For CR1, we maintain a rb tree of groupinfos which is sorted by average fragment size. Instead of traversing linearly, at CR1, we traverse in the order of increasing average fragment size, starting at the most optimal group. This brings down cr 1 search complexity to log(num groups). For cr >= 2, we just perform the linear search as before. Also, in case of lock contention, we intermittently fallback to linear search even in CR 0 and CR 1 cases. This allows us to proceed during the allocation path even in case of high contention. There is an opportunity to do optimization at CR2 too. That's because at CR2 we only consider groups where bb_free counter (number of free blocks) is greater than the request extent size. That's left as future work. All the changes introduced in this patch are protected under a new mount option "mb_optimize_scan". With this patchset, following experiment was performed: Created a highly fragmented disk of size 65TB. The disk had no contiguous 2M regions. Following command was run consecutively for 3 times: time dd if=/dev/urandom of=file bs=2M count=10 Here are the results with and without cr 0/1 optimizations introduced in this patch: |---------+------------------------------+---------------------------| | | Without CR 0/1 Optimizations | With CR 0/1 Optimizations | |---------+------------------------------+---------------------------| | 1st run | 5m1.871s | 2m47.642s | | 2nd run | 2m28.390s | 0m0.611s | | 3rd run | 2m26.530s | 0m1.255s | |---------+------------------------------+---------------------------| Signed-off-by: Harshad Shirwadkar <harshadshirwadkar@gmail.com> Reported-by: kernel test robot <lkp@intel.com> Reported-by: Dan Carpenter <dan.carpenter@oracle.com> Reviewed-by: Andreas Dilger <adilger@dilger.ca> Link: https://lore.kernel.org/r/20210401172129.189766-6-harshadshirwadkar@gmail.com Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2021-04-02 01:21:27 +08:00
unsigned int s_mb_max_linear_groups;
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_mb_max_inode_prealloc;
unsigned int s_max_dir_size_kb;
/* where last allocation was done - for stream allocation */
unsigned long s_mb_last_group;
unsigned long s_mb_last_start;
unsigned int s_mb_prefetch;
unsigned int s_mb_prefetch_limit;
/* 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_groups_scanned; /* number of groups scanned */
atomic_t s_bal_goals; /* goal hits */
atomic_t s_bal_breaks; /* too long searches */
atomic_t s_bal_2orders; /* 2^order hits */
ext4: improve cr 0 / cr 1 group scanning Instead of traversing through groups linearly, scan groups in specific orders at cr 0 and cr 1. At cr 0, we want to find groups that have the largest free order >= the order of the request. So, with this patch, we maintain lists for each possible order and insert each group into a list based on the largest free order in its buddy bitmap. During cr 0 allocation, we traverse these lists in the increasing order of largest free orders. This allows us to find a group with the best available cr 0 match in constant time. If nothing can be found, we fallback to cr 1 immediately. At CR1, the story is slightly different. We want to traverse in the order of increasing average fragment size. For CR1, we maintain a rb tree of groupinfos which is sorted by average fragment size. Instead of traversing linearly, at CR1, we traverse in the order of increasing average fragment size, starting at the most optimal group. This brings down cr 1 search complexity to log(num groups). For cr >= 2, we just perform the linear search as before. Also, in case of lock contention, we intermittently fallback to linear search even in CR 0 and CR 1 cases. This allows us to proceed during the allocation path even in case of high contention. There is an opportunity to do optimization at CR2 too. That's because at CR2 we only consider groups where bb_free counter (number of free blocks) is greater than the request extent size. That's left as future work. All the changes introduced in this patch are protected under a new mount option "mb_optimize_scan". With this patchset, following experiment was performed: Created a highly fragmented disk of size 65TB. The disk had no contiguous 2M regions. Following command was run consecutively for 3 times: time dd if=/dev/urandom of=file bs=2M count=10 Here are the results with and without cr 0/1 optimizations introduced in this patch: |---------+------------------------------+---------------------------| | | Without CR 0/1 Optimizations | With CR 0/1 Optimizations | |---------+------------------------------+---------------------------| | 1st run | 5m1.871s | 2m47.642s | | 2nd run | 2m28.390s | 0m0.611s | | 3rd run | 2m26.530s | 0m1.255s | |---------+------------------------------+---------------------------| Signed-off-by: Harshad Shirwadkar <harshadshirwadkar@gmail.com> Reported-by: kernel test robot <lkp@intel.com> Reported-by: Dan Carpenter <dan.carpenter@oracle.com> Reviewed-by: Andreas Dilger <adilger@dilger.ca> Link: https://lore.kernel.org/r/20210401172129.189766-6-harshadshirwadkar@gmail.com Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2021-04-02 01:21:27 +08:00
atomic_t s_bal_cr0_bad_suggestions;
atomic_t s_bal_cr1_bad_suggestions;
atomic64_t s_bal_cX_groups_considered[4];
atomic64_t s_bal_cX_hits[4];
atomic64_t s_bal_cX_failed[4]; /* cX loop didn't find blocks */
atomic_t s_mb_buddies_generated; /* number of buddies generated */
atomic64_t 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;
/* the size of zero-out chunk */
unsigned int s_extent_max_zeroout_kb;
unsigned int s_log_groups_per_flex;
struct flex_groups * __rcu *s_flex_groups;
ext4_group_t s_flex_groups_allocated;
/* workqueue for reserved extent conversions (buffered io) */
struct workqueue_struct *rsv_conversion_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 09:30:05 +08:00
/* 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 12:03:38 +08:00
/* record the last minlen when FITRIM is called. */
unsigned long 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;
/* Reclaim extents from extent status tree */
struct shrinker s_es_shrinker;
struct list_head s_es_list; /* List of inodes with reclaimable extents */
long s_es_nr_inode;
ext4: track extent status tree shrinker delay statictics This commit adds some statictics in extent status tree shrinker. The purpose to add these is that we want to collect more details when we encounter a stall caused by extent status tree shrinker. Here we count the following statictics: stats: the number of all objects on all extent status trees the number of reclaimable objects on lru list cache hits/misses the last sorted interval the number of inodes on lru list average: scan time for shrinking some objects the number of shrunk objects maximum: the inode that has max nr. of objects on lru list the maximum scan time for shrinking some objects The output looks like below: $ cat /proc/fs/ext4/sda1/es_shrinker_info stats: 28228 objects 6341 reclaimable objects 5281/631 cache hits/misses 586 ms last sorted interval 250 inodes on lru list average: 153 us scan time 128 shrunk objects maximum: 255 inode (255 objects, 198 reclaimable) 125723 us max scan time If the lru list has never been sorted, the following line will not be printed: 586ms last sorted interval If there is an empty lru list, the following lines also will not be printed: 250 inodes on lru list ... maximum: 255 inode (255 objects, 198 reclaimable) 0 us max scan time Meanwhile in this commit a new trace point is defined to print some details in __ext4_es_shrink(). Cc: Andreas Dilger <adilger.kernel@dilger.ca> Cc: Jan Kara <jack@suse.cz> Reviewed-by: Jan Kara <jack@suse.cz> Signed-off-by: Zheng Liu <wenqing.lz@taobao.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2014-09-02 10:26:49 +08:00
struct ext4_es_stats s_es_stats;
struct mb_cache *s_ea_block_cache;
struct mb_cache *s_ea_inode_cache;
spinlock_t s_es_lock ____cacheline_aligned_in_smp;
/* Journal triggers for checksum computation */
struct ext4_journal_trigger s_journal_triggers[EXT4_JOURNAL_TRIGGER_COUNT];
/* Ratelimit ext4 messages. */
struct ratelimit_state s_err_ratelimit_state;
struct ratelimit_state s_warning_ratelimit_state;
struct ratelimit_state s_msg_ratelimit_state;
atomic_t s_warning_count;
atomic_t s_msg_count;
fscrypt: handle test_dummy_encryption in more logical way The behavior of the test_dummy_encryption mount option is that when a new file (or directory or symlink) is created in an unencrypted directory, it's automatically encrypted using a dummy encryption policy. That's it; in particular, the encryption (or lack thereof) of existing files (or directories or symlinks) doesn't change. Unfortunately the implementation of test_dummy_encryption is a bit weird and confusing. When test_dummy_encryption is enabled and a file is being created in an unencrypted directory, we set up an encryption key (->i_crypt_info) for the directory. This isn't actually used to do any encryption, however, since the directory is still unencrypted! Instead, ->i_crypt_info is only used for inheriting the encryption policy. One consequence of this is that the filesystem ends up providing a "dummy context" (policy + nonce) instead of a "dummy policy". In commit ed318a6cc0b6 ("fscrypt: support test_dummy_encryption=v2"), I mistakenly thought this was required. However, actually the nonce only ends up being used to derive a key that is never used. Another consequence of this implementation is that it allows for 'inode->i_crypt_info != NULL && !IS_ENCRYPTED(inode)', which is an edge case that can be forgotten about. For example, currently FS_IOC_GET_ENCRYPTION_POLICY on an unencrypted directory may return the dummy encryption policy when the filesystem is mounted with test_dummy_encryption. That seems like the wrong thing to do, since again, the directory itself is not actually encrypted. Therefore, switch to a more logical and maintainable implementation where the dummy encryption policy inheritance is done without setting up keys for unencrypted directories. This involves: - Adding a function fscrypt_policy_to_inherit() which returns the encryption policy to inherit from a directory. This can be a real policy, a dummy policy, or no policy. - Replacing struct fscrypt_dummy_context, ->get_dummy_context(), etc. with struct fscrypt_dummy_policy, ->get_dummy_policy(), etc. - Making fscrypt_fname_encrypted_size() take an fscrypt_policy instead of an inode. Acked-by: Jaegeuk Kim <jaegeuk@kernel.org> Acked-by: Jeff Layton <jlayton@kernel.org> Link: https://lore.kernel.org/r/20200917041136.178600-13-ebiggers@kernel.org Signed-off-by: Eric Biggers <ebiggers@google.com>
2020-09-17 12:11:35 +08:00
/* Encryption policy for '-o test_dummy_encryption' */
struct fscrypt_dummy_policy s_dummy_enc_policy;
fscrypt: support test_dummy_encryption=v2 v1 encryption policies are deprecated in favor of v2, and some new features (e.g. encryption+casefolding) are only being added for v2. Therefore, the "test_dummy_encryption" mount option (which is used for encryption I/O testing with xfstests) needs to support v2 policies. To do this, extend its syntax to be "test_dummy_encryption=v1" or "test_dummy_encryption=v2". The existing "test_dummy_encryption" (no argument) also continues to be accepted, to specify the default setting -- currently v1, but the next patch changes it to v2. To cleanly support both v1 and v2 while also making it easy to support specifying other encryption settings in the future (say, accepting "$contents_mode:$filenames_mode:v2"), make ext4 and f2fs maintain a pointer to the dummy fscrypt_context rather than using mount flags. To avoid concurrency issues, don't allow test_dummy_encryption to be set or changed during a remount. (The former restriction is new, but xfstests doesn't run into it, so no one should notice.) Tested with 'gce-xfstests -c {ext4,f2fs}/encrypt -g auto'. On ext4, there are two regressions, both of which are test bugs: ext4/023 and ext4/028 fail because they set an xattr and expect it to be stored inline, but the increase in size of the fscrypt_context from 24 to 40 bytes causes this xattr to be spilled into an external block. Link: https://lore.kernel.org/r/20200512233251.118314-4-ebiggers@kernel.org Acked-by: Jaegeuk Kim <jaegeuk@kernel.org> Reviewed-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Eric Biggers <ebiggers@google.com>
2020-05-13 07:32:50 +08:00
ext4: fix race between writepages and enabling EXT4_EXTENTS_FL If EXT4_EXTENTS_FL is set on an inode while ext4_writepages() is running on it, the following warning in ext4_add_complete_io() can be hit: WARNING: CPU: 1 PID: 0 at fs/ext4/page-io.c:234 ext4_put_io_end_defer+0xf0/0x120 Here's a minimal reproducer (not 100% reliable) (root isn't required): while true; do sync done & while true; do rm -f file touch file chattr -e file echo X >> file chattr +e file done The problem is that in ext4_writepages(), ext4_should_dioread_nolock() (which only returns true on extent-based files) is checked once to set the number of reserved journal credits, and also again later to select the flags for ext4_map_blocks() and copy the reserved journal handle to ext4_io_end::handle. But if EXT4_EXTENTS_FL is being concurrently set, the first check can see dioread_nolock disabled while the later one can see it enabled, causing the reserved handle to unexpectedly be NULL. Since changing EXT4_EXTENTS_FL is uncommon, and there may be other races related to doing so as well, fix this by synchronizing changing EXT4_EXTENTS_FL with ext4_writepages() via the existing s_writepages_rwsem (previously called s_journal_flag_rwsem). This was originally reported by syzbot without a reproducer at https://syzkaller.appspot.com/bug?extid=2202a584a00fffd19fbf, but now that dioread_nolock is the default I also started seeing this when running syzkaller locally. Link: https://lore.kernel.org/r/20200219183047.47417-3-ebiggers@kernel.org Reported-by: syzbot+2202a584a00fffd19fbf@syzkaller.appspotmail.com Fixes: 6b523df4fb5a ("ext4: use transaction reservation for extent conversion in ext4_end_io") Signed-off-by: Eric Biggers <ebiggers@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Reviewed-by: Jan Kara <jack@suse.cz> Cc: stable@kernel.org
2020-02-20 02:30:47 +08:00
/*
* Barrier between writepages ops and changing any inode's JOURNAL_DATA
* or EXTENTS flag.
*/
struct percpu_rw_semaphore s_writepages_rwsem;
struct dax_device *s_daxdev;
u64 s_dax_part_off;
#ifdef CONFIG_EXT4_DEBUG
unsigned long s_simulate_fail;
#endif
/* Record the errseq of the backing block device */
errseq_t s_bdev_wb_err;
spinlock_t s_bdev_wb_lock;
/* Information about errors that happened during this mount */
spinlock_t s_error_lock;
int s_add_error_count;
int s_first_error_code;
__u32 s_first_error_line;
__u32 s_first_error_ino;
__u64 s_first_error_block;
const char *s_first_error_func;
time64_t s_first_error_time;
int s_last_error_code;
__u32 s_last_error_line;
__u32 s_last_error_ino;
__u64 s_last_error_block;
const char *s_last_error_func;
time64_t s_last_error_time;
/*
* If we are in a context where we cannot update error information in
* the on-disk superblock, we queue this work to do it.
*/
struct work_struct s_error_work;
/* Ext4 fast commit sub transaction ID */
atomic_t s_fc_subtid;
/*
* After commit starts, the main queue gets locked, and the further
* updates get added in the staging queue.
*/
#define FC_Q_MAIN 0
#define FC_Q_STAGING 1
struct list_head s_fc_q[2]; /* Inodes staged for fast commit
* that have data changes in them.
*/
struct list_head s_fc_dentry_q[2]; /* directory entry updates */
unsigned int s_fc_bytes;
/*
* Main fast commit lock. This lock protects accesses to the
* following fields:
* ei->i_fc_list, s_fc_dentry_q, s_fc_q, s_fc_bytes, s_fc_bh.
*/
spinlock_t s_fc_lock;
struct buffer_head *s_fc_bh;
struct ext4_fc_stats s_fc_stats;
tid_t s_fc_ineligible_tid;
#ifdef CONFIG_EXT4_DEBUG
int s_fc_debug_max_replay;
#endif
struct ext4_fc_replay_state s_fc_replay_state;
};
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 int ext4_valid_inum(struct super_block *sb, unsigned long ino)
{
return ino == EXT4_ROOT_INO ||
(ino >= EXT4_FIRST_INO(sb) &&
ino <= le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count));
}
/*
* Returns: sbi->field[index]
* Used to access an array element from the following sbi fields which require
* rcu protection to avoid dereferencing an invalid pointer due to reassignment
* - s_group_desc
* - s_group_info
* - s_flex_group
*/
#define sbi_array_rcu_deref(sbi, field, index) \
({ \
typeof(*((sbi)->field)) _v; \
rcu_read_lock(); \
_v = ((typeof(_v)*)rcu_dereference((sbi)->field))[index]; \
rcu_read_unlock(); \
_v; \
})
/*
* run-time mount flags
*/
enum {
EXT4_MF_MNTDIR_SAMPLED,
EXT4_MF_FS_ABORTED, /* Fatal error detected */
EXT4_MF_FC_INELIGIBLE /* Fast commit ineligible */
};
static inline void ext4_set_mount_flag(struct super_block *sb, int bit)
{
set_bit(bit, &EXT4_SB(sb)->s_mount_flags);
}
static inline void ext4_clear_mount_flag(struct super_block *sb, int bit)
{
clear_bit(bit, &EXT4_SB(sb)->s_mount_flags);
}
static inline int ext4_test_mount_flag(struct super_block *sb, int bit)
{
return test_bit(bit, &EXT4_SB(sb)->s_mount_flags);
}
/*
* Simulate_fail codes
*/
#define EXT4_SIM_BBITMAP_EIO 1
#define EXT4_SIM_BBITMAP_CRC 2
#define EXT4_SIM_IBITMAP_EIO 3
#define EXT4_SIM_IBITMAP_CRC 4
#define EXT4_SIM_INODE_EIO 5
#define EXT4_SIM_INODE_CRC 6
#define EXT4_SIM_DIRBLOCK_EIO 7
#define EXT4_SIM_DIRBLOCK_CRC 8
static inline bool ext4_simulate_fail(struct super_block *sb,
unsigned long code)
{
#ifdef CONFIG_EXT4_DEBUG
struct ext4_sb_info *sbi = EXT4_SB(sb);
if (unlikely(sbi->s_simulate_fail == code)) {
sbi->s_simulate_fail = 0;
return true;
}
#endif
return false;
}
static inline void ext4_simulate_fail_bh(struct super_block *sb,
struct buffer_head *bh,
unsigned long code)
{
if (!IS_ERR(bh) && ext4_simulate_fail(sb, code))
clear_buffer_uptodate(bh);
}
/*
* Error number codes for s_{first,last}_error_errno
*
* Linux errno numbers are architecture specific, so we need to translate
* them into something which is architecture independent. We don't define
* codes for all errno's; just the ones which are most likely to be the cause
* of an ext4_error() call.
*/
#define EXT4_ERR_UNKNOWN 1
#define EXT4_ERR_EIO 2
#define EXT4_ERR_ENOMEM 3
#define EXT4_ERR_EFSBADCRC 4
#define EXT4_ERR_EFSCORRUPTED 5
#define EXT4_ERR_ENOSPC 6
#define EXT4_ERR_ENOKEY 7
#define EXT4_ERR_EROFS 8
#define EXT4_ERR_EFBIG 9
#define EXT4_ERR_EEXIST 10
#define EXT4_ERR_ERANGE 11
#define EXT4_ERR_EOVERFLOW 12
#define EXT4_ERR_EBUSY 13
#define EXT4_ERR_ENOTDIR 14
#define EXT4_ERR_ENOTEMPTY 15
#define EXT4_ERR_ESHUTDOWN 16
#define EXT4_ERR_EFAULT 17
/*
* 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_NEWENTRY, /* File just added to dir */
EXT4_STATE_MAY_INLINE_DATA, /* may have in-inode data */
EXT4_STATE_EXT_PRECACHED, /* extents have been precached */
EXT4_STATE_LUSTRE_EA_INODE, /* Lustre-style ea_inode */
ext4: add basic fs-verity support Add most of fs-verity support to ext4. fs-verity is a filesystem feature that enables transparent integrity protection and authentication of read-only files. It uses a dm-verity like mechanism at the file level: a Merkle tree is used to verify any block in the file in log(filesize) time. It is implemented mainly by helper functions in fs/verity/. See Documentation/filesystems/fsverity.rst for the full documentation. This commit adds all of ext4 fs-verity support except for the actual data verification, including: - Adding a filesystem feature flag and an inode flag for fs-verity. - Implementing the fsverity_operations to support enabling verity on an inode and reading/writing the verity metadata. - Updating ->write_begin(), ->write_end(), and ->writepages() to support writing verity metadata pages. - Calling the fs-verity hooks for ->open(), ->setattr(), and ->ioctl(). ext4 stores the verity metadata (Merkle tree and fsverity_descriptor) past the end of the file, starting at the first 64K boundary beyond i_size. This approach works because (a) verity files are readonly, and (b) pages fully beyond i_size aren't visible to userspace but can be read/written internally by ext4 with only some relatively small changes to ext4. This approach avoids having to depend on the EA_INODE feature and on rearchitecturing ext4's xattr support to support paging multi-gigabyte xattrs into memory, and to support encrypting xattrs. Note that the verity metadata *must* be encrypted when the file is, since it contains hashes of the plaintext data. This patch incorporates work by Theodore Ts'o and Chandan Rajendra. Reviewed-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Eric Biggers <ebiggers@google.com>
2019-07-23 00:26:24 +08:00
EXT4_STATE_VERITY_IN_PROGRESS, /* building fs-verity Merkle tree */
EXT4_STATE_FC_COMMITTING, /* Fast commit ongoing */
ext4: Speedup ext4 orphan inode handling Ext4 orphan inode handling is a bottleneck for workloads which heavily truncate / unlink small files since it contends on the global s_orphan_mutex lock (and generally it's difficult to improve scalability of the ondisk linked list of orphaned inodes). This patch implements new way of handling orphan inodes. Instead of linking orphaned inode into a linked list, we store it's inode number in a new special file which we call "orphan file". Only if there's no more space in the orphan file (too many inodes are currently orphaned) we fall back to using old style linked list. Currently we protect operations in the orphan file with a spinlock for simplicity but even in this setting we can substantially reduce the length of the critical section and thus speedup some workloads. In the next patch we improve this by making orphan handling lockless. Note that the change is backwards compatible when the filesystem is clean - the existence of the orphan file is a compat feature, we set another ro-compat feature indicating orphan file needs scanning for orphaned inodes when mounting filesystem read-write. This ro-compat feature gets cleared on unmount / remount read-only. Some performance data from 80 CPU Xeon Server with 512 GB of RAM, filesystem located on SSD, average of 5 runs: stress-orphan (microbenchmark truncating files byte-by-byte from N processes in parallel) Threads Time Time Vanilla Patched 1 1.057200 0.945600 2 1.680400 1.331800 4 2.547000 1.995000 8 7.049400 6.424200 16 14.827800 14.937600 32 40.948200 33.038200 64 87.787400 60.823600 128 206.504000 122.941400 So we can see significant wins all over the board. Reviewed-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Jan Kara <jack@suse.cz> Link: https://lore.kernel.org/r/20210816095713.16537-3-jack@suse.cz Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2021-08-16 17:57:06 +08:00
EXT4_STATE_ORPHAN_FILE, /* Inode orphaned in orphan file */
};
#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); \
}
/* Add these declarations here only so that these functions can be
* found by name. Otherwise, they are very hard to locate. */
static inline int ext4_test_inode_flag(struct inode *inode, int bit);
static inline void ext4_set_inode_flag(struct inode *inode, int bit);
static inline void ext4_clear_inode_flag(struct inode *inode, int bit);
EXT4_INODE_BIT_FNS(flag, flags, 0)
/* Add these declarations here only so that these functions can be
* found by name. Otherwise, they are very hard to locate. */
static inline int ext4_test_inode_state(struct inode *inode, int bit);
static inline void ext4_set_inode_state(struct inode *inode, int bit);
static inline void ext4_clear_inode_state(struct inode *inode, int bit);
#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
ext4: add basic fs-verity support Add most of fs-verity support to ext4. fs-verity is a filesystem feature that enables transparent integrity protection and authentication of read-only files. It uses a dm-verity like mechanism at the file level: a Merkle tree is used to verify any block in the file in log(filesize) time. It is implemented mainly by helper functions in fs/verity/. See Documentation/filesystems/fsverity.rst for the full documentation. This commit adds all of ext4 fs-verity support except for the actual data verification, including: - Adding a filesystem feature flag and an inode flag for fs-verity. - Implementing the fsverity_operations to support enabling verity on an inode and reading/writing the verity metadata. - Updating ->write_begin(), ->write_end(), and ->writepages() to support writing verity metadata pages. - Calling the fs-verity hooks for ->open(), ->setattr(), and ->ioctl(). ext4 stores the verity metadata (Merkle tree and fsverity_descriptor) past the end of the file, starting at the first 64K boundary beyond i_size. This approach works because (a) verity files are readonly, and (b) pages fully beyond i_size aren't visible to userspace but can be read/written internally by ext4 with only some relatively small changes to ext4. This approach avoids having to depend on the EA_INODE feature and on rearchitecturing ext4's xattr support to support paging multi-gigabyte xattrs into memory, and to support encrypting xattrs. Note that the verity metadata *must* be encrypted when the file is, since it contains hashes of the plaintext data. This patch incorporates work by Theodore Ts'o and Chandan Rajendra. Reviewed-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Eric Biggers <ebiggers@google.com>
2019-07-23 00:26:24 +08:00
static inline bool ext4_verity_in_progress(struct inode *inode)
{
return IS_ENABLED(CONFIG_FS_VERITY) &&
ext4_test_inode_state(inode, EXT4_STATE_VERITY_IN_PROGRESS);
}
#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_MAX_SUPP_REV EXT4_DYNAMIC_REV
#define EXT4_GOOD_OLD_INODE_SIZE 128
#define EXT4_EXTRA_TIMESTAMP_MAX (((s64)1 << 34) - 1 + S32_MIN)
#define EXT4_NON_EXTRA_TIMESTAMP_MAX S32_MAX
#define EXT4_TIMESTAMP_MIN S32_MIN
/*
* Feature set definitions
*/
#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_COMPAT_SPARSE_SUPER2 0x0200
/*
* The reason why "FAST_COMMIT" is a compat feature is that, FS becomes
* incompatible only if fast commit blocks are present in the FS. Since we
* clear the journal (and thus the fast commit blocks), we don't mark FS as
* incompatible. We also have a JBD2 incompat feature, which gets set when
* there are fast commit blocks present in the journal.
*/
#define EXT4_FEATURE_COMPAT_FAST_COMMIT 0x0400
#define EXT4_FEATURE_COMPAT_STABLE_INODES 0x0800
ext4: Speedup ext4 orphan inode handling Ext4 orphan inode handling is a bottleneck for workloads which heavily truncate / unlink small files since it contends on the global s_orphan_mutex lock (and generally it's difficult to improve scalability of the ondisk linked list of orphaned inodes). This patch implements new way of handling orphan inodes. Instead of linking orphaned inode into a linked list, we store it's inode number in a new special file which we call "orphan file". Only if there's no more space in the orphan file (too many inodes are currently orphaned) we fall back to using old style linked list. Currently we protect operations in the orphan file with a spinlock for simplicity but even in this setting we can substantially reduce the length of the critical section and thus speedup some workloads. In the next patch we improve this by making orphan handling lockless. Note that the change is backwards compatible when the filesystem is clean - the existence of the orphan file is a compat feature, we set another ro-compat feature indicating orphan file needs scanning for orphaned inodes when mounting filesystem read-write. This ro-compat feature gets cleared on unmount / remount read-only. Some performance data from 80 CPU Xeon Server with 512 GB of RAM, filesystem located on SSD, average of 5 runs: stress-orphan (microbenchmark truncating files byte-by-byte from N processes in parallel) Threads Time Time Vanilla Patched 1 1.057200 0.945600 2 1.680400 1.331800 4 2.547000 1.995000 8 7.049400 6.424200 16 14.827800 14.937600 32 40.948200 33.038200 64 87.787400 60.823600 128 206.504000 122.941400 So we can see significant wins all over the board. Reviewed-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Jan Kara <jack@suse.cz> Link: https://lore.kernel.org/r/20210816095713.16537-3-jack@suse.cz Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2021-08-16 17:57:06 +08:00
#define EXT4_FEATURE_COMPAT_ORPHAN_FILE 0x1000 /* Orphan file exists */
#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>
2007-10-17 06:38:25 +08:00
#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_RO_COMPAT_READONLY 0x1000
#define EXT4_FEATURE_RO_COMPAT_PROJECT 0x2000
ext4: add basic fs-verity support Add most of fs-verity support to ext4. fs-verity is a filesystem feature that enables transparent integrity protection and authentication of read-only files. It uses a dm-verity like mechanism at the file level: a Merkle tree is used to verify any block in the file in log(filesize) time. It is implemented mainly by helper functions in fs/verity/. See Documentation/filesystems/fsverity.rst for the full documentation. This commit adds all of ext4 fs-verity support except for the actual data verification, including: - Adding a filesystem feature flag and an inode flag for fs-verity. - Implementing the fsverity_operations to support enabling verity on an inode and reading/writing the verity metadata. - Updating ->write_begin(), ->write_end(), and ->writepages() to support writing verity metadata pages. - Calling the fs-verity hooks for ->open(), ->setattr(), and ->ioctl(). ext4 stores the verity metadata (Merkle tree and fsverity_descriptor) past the end of the file, starting at the first 64K boundary beyond i_size. This approach works because (a) verity files are readonly, and (b) pages fully beyond i_size aren't visible to userspace but can be read/written internally by ext4 with only some relatively small changes to ext4. This approach avoids having to depend on the EA_INODE feature and on rearchitecturing ext4's xattr support to support paging multi-gigabyte xattrs into memory, and to support encrypting xattrs. Note that the verity metadata *must* be encrypted when the file is, since it contains hashes of the plaintext data. This patch incorporates work by Theodore Ts'o and Chandan Rajendra. Reviewed-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Eric Biggers <ebiggers@google.com>
2019-07-23 00:26:24 +08:00
#define EXT4_FEATURE_RO_COMPAT_VERITY 0x8000
ext4: Speedup ext4 orphan inode handling Ext4 orphan inode handling is a bottleneck for workloads which heavily truncate / unlink small files since it contends on the global s_orphan_mutex lock (and generally it's difficult to improve scalability of the ondisk linked list of orphaned inodes). This patch implements new way of handling orphan inodes. Instead of linking orphaned inode into a linked list, we store it's inode number in a new special file which we call "orphan file". Only if there's no more space in the orphan file (too many inodes are currently orphaned) we fall back to using old style linked list. Currently we protect operations in the orphan file with a spinlock for simplicity but even in this setting we can substantially reduce the length of the critical section and thus speedup some workloads. In the next patch we improve this by making orphan handling lockless. Note that the change is backwards compatible when the filesystem is clean - the existence of the orphan file is a compat feature, we set another ro-compat feature indicating orphan file needs scanning for orphaned inodes when mounting filesystem read-write. This ro-compat feature gets cleared on unmount / remount read-only. Some performance data from 80 CPU Xeon Server with 512 GB of RAM, filesystem located on SSD, average of 5 runs: stress-orphan (microbenchmark truncating files byte-by-byte from N processes in parallel) Threads Time Time Vanilla Patched 1 1.057200 0.945600 2 1.680400 1.331800 4 2.547000 1.995000 8 7.049400 6.424200 16 14.827800 14.937600 32 40.948200 33.038200 64 87.787400 60.823600 128 206.504000 122.941400 So we can see significant wins all over the board. Reviewed-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Jan Kara <jack@suse.cz> Link: https://lore.kernel.org/r/20210816095713.16537-3-jack@suse.cz Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2021-08-16 17:57:06 +08:00
#define EXT4_FEATURE_RO_COMPAT_ORPHAN_PRESENT 0x10000 /* Orphan file may be
non-empty */
#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_CSUM_SEED 0x2000
#define EXT4_FEATURE_INCOMPAT_LARGEDIR 0x4000 /* >2GB or 3-lvl htree */
#define EXT4_FEATURE_INCOMPAT_INLINE_DATA 0x8000 /* data in inode */
#define EXT4_FEATURE_INCOMPAT_ENCRYPT 0x10000
#define EXT4_FEATURE_INCOMPAT_CASEFOLD 0x20000
extern void ext4_update_dynamic_rev(struct super_block *sb);
#define EXT4_FEATURE_COMPAT_FUNCS(name, flagname) \
static inline bool ext4_has_feature_##name(struct super_block *sb) \
{ \
return ((EXT4_SB(sb)->s_es->s_feature_compat & \
cpu_to_le32(EXT4_FEATURE_COMPAT_##flagname)) != 0); \
} \
static inline void ext4_set_feature_##name(struct super_block *sb) \
{ \
ext4_update_dynamic_rev(sb); \
EXT4_SB(sb)->s_es->s_feature_compat |= \
cpu_to_le32(EXT4_FEATURE_COMPAT_##flagname); \
} \
static inline void ext4_clear_feature_##name(struct super_block *sb) \
{ \
EXT4_SB(sb)->s_es->s_feature_compat &= \
~cpu_to_le32(EXT4_FEATURE_COMPAT_##flagname); \
}
#define EXT4_FEATURE_RO_COMPAT_FUNCS(name, flagname) \
static inline bool ext4_has_feature_##name(struct super_block *sb) \
{ \
return ((EXT4_SB(sb)->s_es->s_feature_ro_compat & \
cpu_to_le32(EXT4_FEATURE_RO_COMPAT_##flagname)) != 0); \
} \
static inline void ext4_set_feature_##name(struct super_block *sb) \
{ \
ext4_update_dynamic_rev(sb); \
EXT4_SB(sb)->s_es->s_feature_ro_compat |= \
cpu_to_le32(EXT4_FEATURE_RO_COMPAT_##flagname); \
} \
static inline void ext4_clear_feature_##name(struct super_block *sb) \
{ \
EXT4_SB(sb)->s_es->s_feature_ro_compat &= \
~cpu_to_le32(EXT4_FEATURE_RO_COMPAT_##flagname); \
}
#define EXT4_FEATURE_INCOMPAT_FUNCS(name, flagname) \
static inline bool ext4_has_feature_##name(struct super_block *sb) \
{ \
return ((EXT4_SB(sb)->s_es->s_feature_incompat & \
cpu_to_le32(EXT4_FEATURE_INCOMPAT_##flagname)) != 0); \
} \
static inline void ext4_set_feature_##name(struct super_block *sb) \
{ \
ext4_update_dynamic_rev(sb); \
EXT4_SB(sb)->s_es->s_feature_incompat |= \
cpu_to_le32(EXT4_FEATURE_INCOMPAT_##flagname); \
} \
static inline void ext4_clear_feature_##name(struct super_block *sb) \
{ \
EXT4_SB(sb)->s_es->s_feature_incompat &= \
~cpu_to_le32(EXT4_FEATURE_INCOMPAT_##flagname); \
}
EXT4_FEATURE_COMPAT_FUNCS(dir_prealloc, DIR_PREALLOC)
EXT4_FEATURE_COMPAT_FUNCS(imagic_inodes, IMAGIC_INODES)
EXT4_FEATURE_COMPAT_FUNCS(journal, HAS_JOURNAL)
EXT4_FEATURE_COMPAT_FUNCS(xattr, EXT_ATTR)
EXT4_FEATURE_COMPAT_FUNCS(resize_inode, RESIZE_INODE)
EXT4_FEATURE_COMPAT_FUNCS(dir_index, DIR_INDEX)
EXT4_FEATURE_COMPAT_FUNCS(sparse_super2, SPARSE_SUPER2)
EXT4_FEATURE_COMPAT_FUNCS(fast_commit, FAST_COMMIT)
EXT4_FEATURE_COMPAT_FUNCS(stable_inodes, STABLE_INODES)
ext4: Speedup ext4 orphan inode handling Ext4 orphan inode handling is a bottleneck for workloads which heavily truncate / unlink small files since it contends on the global s_orphan_mutex lock (and generally it's difficult to improve scalability of the ondisk linked list of orphaned inodes). This patch implements new way of handling orphan inodes. Instead of linking orphaned inode into a linked list, we store it's inode number in a new special file which we call "orphan file". Only if there's no more space in the orphan file (too many inodes are currently orphaned) we fall back to using old style linked list. Currently we protect operations in the orphan file with a spinlock for simplicity but even in this setting we can substantially reduce the length of the critical section and thus speedup some workloads. In the next patch we improve this by making orphan handling lockless. Note that the change is backwards compatible when the filesystem is clean - the existence of the orphan file is a compat feature, we set another ro-compat feature indicating orphan file needs scanning for orphaned inodes when mounting filesystem read-write. This ro-compat feature gets cleared on unmount / remount read-only. Some performance data from 80 CPU Xeon Server with 512 GB of RAM, filesystem located on SSD, average of 5 runs: stress-orphan (microbenchmark truncating files byte-by-byte from N processes in parallel) Threads Time Time Vanilla Patched 1 1.057200 0.945600 2 1.680400 1.331800 4 2.547000 1.995000 8 7.049400 6.424200 16 14.827800 14.937600 32 40.948200 33.038200 64 87.787400 60.823600 128 206.504000 122.941400 So we can see significant wins all over the board. Reviewed-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Jan Kara <jack@suse.cz> Link: https://lore.kernel.org/r/20210816095713.16537-3-jack@suse.cz Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2021-08-16 17:57:06 +08:00
EXT4_FEATURE_COMPAT_FUNCS(orphan_file, ORPHAN_FILE)
EXT4_FEATURE_RO_COMPAT_FUNCS(sparse_super, SPARSE_SUPER)
EXT4_FEATURE_RO_COMPAT_FUNCS(large_file, LARGE_FILE)
EXT4_FEATURE_RO_COMPAT_FUNCS(btree_dir, BTREE_DIR)
EXT4_FEATURE_RO_COMPAT_FUNCS(huge_file, HUGE_FILE)
EXT4_FEATURE_RO_COMPAT_FUNCS(gdt_csum, GDT_CSUM)
EXT4_FEATURE_RO_COMPAT_FUNCS(dir_nlink, DIR_NLINK)
EXT4_FEATURE_RO_COMPAT_FUNCS(extra_isize, EXTRA_ISIZE)
EXT4_FEATURE_RO_COMPAT_FUNCS(quota, QUOTA)
EXT4_FEATURE_RO_COMPAT_FUNCS(bigalloc, BIGALLOC)
EXT4_FEATURE_RO_COMPAT_FUNCS(metadata_csum, METADATA_CSUM)
EXT4_FEATURE_RO_COMPAT_FUNCS(readonly, READONLY)
EXT4_FEATURE_RO_COMPAT_FUNCS(project, PROJECT)
ext4: add basic fs-verity support Add most of fs-verity support to ext4. fs-verity is a filesystem feature that enables transparent integrity protection and authentication of read-only files. It uses a dm-verity like mechanism at the file level: a Merkle tree is used to verify any block in the file in log(filesize) time. It is implemented mainly by helper functions in fs/verity/. See Documentation/filesystems/fsverity.rst for the full documentation. This commit adds all of ext4 fs-verity support except for the actual data verification, including: - Adding a filesystem feature flag and an inode flag for fs-verity. - Implementing the fsverity_operations to support enabling verity on an inode and reading/writing the verity metadata. - Updating ->write_begin(), ->write_end(), and ->writepages() to support writing verity metadata pages. - Calling the fs-verity hooks for ->open(), ->setattr(), and ->ioctl(). ext4 stores the verity metadata (Merkle tree and fsverity_descriptor) past the end of the file, starting at the first 64K boundary beyond i_size. This approach works because (a) verity files are readonly, and (b) pages fully beyond i_size aren't visible to userspace but can be read/written internally by ext4 with only some relatively small changes to ext4. This approach avoids having to depend on the EA_INODE feature and on rearchitecturing ext4's xattr support to support paging multi-gigabyte xattrs into memory, and to support encrypting xattrs. Note that the verity metadata *must* be encrypted when the file is, since it contains hashes of the plaintext data. This patch incorporates work by Theodore Ts'o and Chandan Rajendra. Reviewed-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Eric Biggers <ebiggers@google.com>
2019-07-23 00:26:24 +08:00
EXT4_FEATURE_RO_COMPAT_FUNCS(verity, VERITY)
ext4: Speedup ext4 orphan inode handling Ext4 orphan inode handling is a bottleneck for workloads which heavily truncate / unlink small files since it contends on the global s_orphan_mutex lock (and generally it's difficult to improve scalability of the ondisk linked list of orphaned inodes). This patch implements new way of handling orphan inodes. Instead of linking orphaned inode into a linked list, we store it's inode number in a new special file which we call "orphan file". Only if there's no more space in the orphan file (too many inodes are currently orphaned) we fall back to using old style linked list. Currently we protect operations in the orphan file with a spinlock for simplicity but even in this setting we can substantially reduce the length of the critical section and thus speedup some workloads. In the next patch we improve this by making orphan handling lockless. Note that the change is backwards compatible when the filesystem is clean - the existence of the orphan file is a compat feature, we set another ro-compat feature indicating orphan file needs scanning for orphaned inodes when mounting filesystem read-write. This ro-compat feature gets cleared on unmount / remount read-only. Some performance data from 80 CPU Xeon Server with 512 GB of RAM, filesystem located on SSD, average of 5 runs: stress-orphan (microbenchmark truncating files byte-by-byte from N processes in parallel) Threads Time Time Vanilla Patched 1 1.057200 0.945600 2 1.680400 1.331800 4 2.547000 1.995000 8 7.049400 6.424200 16 14.827800 14.937600 32 40.948200 33.038200 64 87.787400 60.823600 128 206.504000 122.941400 So we can see significant wins all over the board. Reviewed-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Jan Kara <jack@suse.cz> Link: https://lore.kernel.org/r/20210816095713.16537-3-jack@suse.cz Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2021-08-16 17:57:06 +08:00
EXT4_FEATURE_RO_COMPAT_FUNCS(orphan_present, ORPHAN_PRESENT)
EXT4_FEATURE_INCOMPAT_FUNCS(compression, COMPRESSION)
EXT4_FEATURE_INCOMPAT_FUNCS(filetype, FILETYPE)
EXT4_FEATURE_INCOMPAT_FUNCS(journal_needs_recovery, RECOVER)
EXT4_FEATURE_INCOMPAT_FUNCS(journal_dev, JOURNAL_DEV)
EXT4_FEATURE_INCOMPAT_FUNCS(meta_bg, META_BG)
EXT4_FEATURE_INCOMPAT_FUNCS(extents, EXTENTS)
EXT4_FEATURE_INCOMPAT_FUNCS(64bit, 64BIT)
EXT4_FEATURE_INCOMPAT_FUNCS(mmp, MMP)
EXT4_FEATURE_INCOMPAT_FUNCS(flex_bg, FLEX_BG)
EXT4_FEATURE_INCOMPAT_FUNCS(ea_inode, EA_INODE)
EXT4_FEATURE_INCOMPAT_FUNCS(dirdata, DIRDATA)
EXT4_FEATURE_INCOMPAT_FUNCS(csum_seed, CSUM_SEED)
EXT4_FEATURE_INCOMPAT_FUNCS(largedir, LARGEDIR)
EXT4_FEATURE_INCOMPAT_FUNCS(inline_data, INLINE_DATA)
EXT4_FEATURE_INCOMPAT_FUNCS(encrypt, ENCRYPT)
EXT4_FEATURE_INCOMPAT_FUNCS(casefold, CASEFOLD)
#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)
ext4: Speedup ext4 orphan inode handling Ext4 orphan inode handling is a bottleneck for workloads which heavily truncate / unlink small files since it contends on the global s_orphan_mutex lock (and generally it's difficult to improve scalability of the ondisk linked list of orphaned inodes). This patch implements new way of handling orphan inodes. Instead of linking orphaned inode into a linked list, we store it's inode number in a new special file which we call "orphan file". Only if there's no more space in the orphan file (too many inodes are currently orphaned) we fall back to using old style linked list. Currently we protect operations in the orphan file with a spinlock for simplicity but even in this setting we can substantially reduce the length of the critical section and thus speedup some workloads. In the next patch we improve this by making orphan handling lockless. Note that the change is backwards compatible when the filesystem is clean - the existence of the orphan file is a compat feature, we set another ro-compat feature indicating orphan file needs scanning for orphaned inodes when mounting filesystem read-write. This ro-compat feature gets cleared on unmount / remount read-only. Some performance data from 80 CPU Xeon Server with 512 GB of RAM, filesystem located on SSD, average of 5 runs: stress-orphan (microbenchmark truncating files byte-by-byte from N processes in parallel) Threads Time Time Vanilla Patched 1 1.057200 0.945600 2 1.680400 1.331800 4 2.547000 1.995000 8 7.049400 6.424200 16 14.827800 14.937600 32 40.948200 33.038200 64 87.787400 60.823600 128 206.504000 122.941400 So we can see significant wins all over the board. Reviewed-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Jan Kara <jack@suse.cz> Link: https://lore.kernel.org/r/20210816095713.16537-3-jack@suse.cz Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2021-08-16 17:57:06 +08:00
#define EXT4_FEATURE_COMPAT_SUPP (EXT4_FEATURE_COMPAT_EXT_ATTR| \
EXT4_FEATURE_COMPAT_ORPHAN_FILE)
#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: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
EXT4_FEATURE_INCOMPAT_EA_INODE| \
EXT4_FEATURE_INCOMPAT_MMP | \
EXT4_FEATURE_INCOMPAT_INLINE_DATA | \
EXT4_FEATURE_INCOMPAT_ENCRYPT | \
EXT4_FEATURE_INCOMPAT_CASEFOLD | \
EXT4_FEATURE_INCOMPAT_CSUM_SEED | \
EXT4_FEATURE_INCOMPAT_LARGEDIR)
#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>
2007-10-17 06:38:25 +08:00
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: make quota as first class supported feature This patch adds support for quotas as a first class feature in ext4; which is to say, the quota files are stored in hidden inodes as file system metadata, instead of as separate files visible in the file system directory hierarchy. It is based on the proposal at: https://ext4.wiki.kernel.org/index.php/Design_For_1st_Class_Quota_in_Ext4 This patch introduces a new feature - EXT4_FEATURE_RO_COMPAT_QUOTA which, when turned on, enables quota accounting at mount time iteself. Also, the quota inodes are stored in two additional superblock fields. Some changes introduced by this patch that should be pointed out are: 1) Two new ext4-superblock fields - s_usr_quota_inum and s_grp_quota_inum for storing the quota inodes in use. 2) Default quota inodes are: inode#3 for tracking userquota and inode#4 for tracking group quota. The superblock fields can be set to use other inodes as well. 3) If the QUOTA feature and corresponding quota inodes are set in superblock, the quota usage tracking is turned on at mount time. On 'quotaon' ioctl, the quota limits enforcement is turned on. 'quotaoff' ioctl turns off only the limits enforcement in this case. 4) When QUOTA feature is in use, the quota mount options 'quota', 'usrquota', 'grpquota' are ignored by the kernel. 5) mke2fs or tune2fs can be used to set the QUOTA feature and initialize quota inodes. The default reserved inodes will not be visible to user as regular files. 6) The quota-tools will need to be modified to support hidden quota files on ext4. E2fsprogs will also include support for creating and fixing quota files. 7) Support is only for the new V2 quota file format. Tested-by: Jan Kara <jack@suse.cz> Reviewed-by: Jan Kara <jack@suse.cz> Reviewed-by: Johann Lombardi <johann@whamcloud.com> Signed-off-by: Aditya Kali <adityakali@google.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2012-07-23 08:21:31 +08:00
EXT4_FEATURE_RO_COMPAT_METADATA_CSUM|\
EXT4_FEATURE_RO_COMPAT_QUOTA |\
ext4: add basic fs-verity support Add most of fs-verity support to ext4. fs-verity is a filesystem feature that enables transparent integrity protection and authentication of read-only files. It uses a dm-verity like mechanism at the file level: a Merkle tree is used to verify any block in the file in log(filesize) time. It is implemented mainly by helper functions in fs/verity/. See Documentation/filesystems/fsverity.rst for the full documentation. This commit adds all of ext4 fs-verity support except for the actual data verification, including: - Adding a filesystem feature flag and an inode flag for fs-verity. - Implementing the fsverity_operations to support enabling verity on an inode and reading/writing the verity metadata. - Updating ->write_begin(), ->write_end(), and ->writepages() to support writing verity metadata pages. - Calling the fs-verity hooks for ->open(), ->setattr(), and ->ioctl(). ext4 stores the verity metadata (Merkle tree and fsverity_descriptor) past the end of the file, starting at the first 64K boundary beyond i_size. This approach works because (a) verity files are readonly, and (b) pages fully beyond i_size aren't visible to userspace but can be read/written internally by ext4 with only some relatively small changes to ext4. This approach avoids having to depend on the EA_INODE feature and on rearchitecturing ext4's xattr support to support paging multi-gigabyte xattrs into memory, and to support encrypting xattrs. Note that the verity metadata *must* be encrypted when the file is, since it contains hashes of the plaintext data. This patch incorporates work by Theodore Ts'o and Chandan Rajendra. Reviewed-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Eric Biggers <ebiggers@google.com>
2019-07-23 00:26:24 +08:00
EXT4_FEATURE_RO_COMPAT_PROJECT |\
ext4: Speedup ext4 orphan inode handling Ext4 orphan inode handling is a bottleneck for workloads which heavily truncate / unlink small files since it contends on the global s_orphan_mutex lock (and generally it's difficult to improve scalability of the ondisk linked list of orphaned inodes). This patch implements new way of handling orphan inodes. Instead of linking orphaned inode into a linked list, we store it's inode number in a new special file which we call "orphan file". Only if there's no more space in the orphan file (too many inodes are currently orphaned) we fall back to using old style linked list. Currently we protect operations in the orphan file with a spinlock for simplicity but even in this setting we can substantially reduce the length of the critical section and thus speedup some workloads. In the next patch we improve this by making orphan handling lockless. Note that the change is backwards compatible when the filesystem is clean - the existence of the orphan file is a compat feature, we set another ro-compat feature indicating orphan file needs scanning for orphaned inodes when mounting filesystem read-write. This ro-compat feature gets cleared on unmount / remount read-only. Some performance data from 80 CPU Xeon Server with 512 GB of RAM, filesystem located on SSD, average of 5 runs: stress-orphan (microbenchmark truncating files byte-by-byte from N processes in parallel) Threads Time Time Vanilla Patched 1 1.057200 0.945600 2 1.680400 1.331800 4 2.547000 1.995000 8 7.049400 6.424200 16 14.827800 14.937600 32 40.948200 33.038200 64 87.787400 60.823600 128 206.504000 122.941400 So we can see significant wins all over the board. Reviewed-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Jan Kara <jack@suse.cz> Link: https://lore.kernel.org/r/20210816095713.16537-3-jack@suse.cz Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2021-08-16 17:57:06 +08:00
EXT4_FEATURE_RO_COMPAT_VERITY |\
EXT4_FEATURE_RO_COMPAT_ORPHAN_PRESENT)
#define EXTN_FEATURE_FUNCS(ver) \
static inline bool ext4_has_unknown_ext##ver##_compat_features(struct super_block *sb) \
{ \
return ((EXT4_SB(sb)->s_es->s_feature_compat & \
cpu_to_le32(~EXT##ver##_FEATURE_COMPAT_SUPP)) != 0); \
} \
static inline bool ext4_has_unknown_ext##ver##_ro_compat_features(struct super_block *sb) \
{ \
return ((EXT4_SB(sb)->s_es->s_feature_ro_compat & \
cpu_to_le32(~EXT##ver##_FEATURE_RO_COMPAT_SUPP)) != 0); \
} \
static inline bool ext4_has_unknown_ext##ver##_incompat_features(struct super_block *sb) \
{ \
return ((EXT4_SB(sb)->s_es->s_feature_incompat & \
cpu_to_le32(~EXT##ver##_FEATURE_INCOMPAT_SUPP)) != 0); \
}
EXTN_FEATURE_FUNCS(2)
EXTN_FEATURE_FUNCS(3)
EXTN_FEATURE_FUNCS(4)
static inline bool ext4_has_compat_features(struct super_block *sb)
{
return (EXT4_SB(sb)->s_es->s_feature_compat != 0);
}
static inline bool ext4_has_ro_compat_features(struct super_block *sb)
{
return (EXT4_SB(sb)->s_es->s_feature_ro_compat != 0);
}
static inline bool ext4_has_incompat_features(struct super_block *sb)
{
return (EXT4_SB(sb)->s_es->s_feature_incompat != 0);
}
extern int ext4_feature_set_ok(struct super_block *sb, int readonly);
/*
* Superblock flags
*/
#define EXT4_FLAGS_RESIZING 0
#define EXT4_FLAGS_SHUTDOWN 1
#define EXT4_FLAGS_BDEV_IS_DAX 2
static inline int ext4_forced_shutdown(struct ext4_sb_info *sbi)
{
return test_bit(EXT4_FLAGS_SHUTDOWN, &sbi->s_ext4_flags);
}
/*
* Default values for user and/or group using reserved blocks
*/
#define EXT4_DEF_RESUID 0
#define EXT4_DEF_RESGID 0
/*
* Default project ID
*/
#define EXT4_DEF_PROJID 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
ext4: fix use-after-free in ext4_search_dir We got issue as follows: EXT4-fs (loop0): mounted filesystem without journal. Opts: ,errors=continue ================================================================== BUG: KASAN: use-after-free in ext4_search_dir fs/ext4/namei.c:1394 [inline] BUG: KASAN: use-after-free in search_dirblock fs/ext4/namei.c:1199 [inline] BUG: KASAN: use-after-free in __ext4_find_entry+0xdca/0x1210 fs/ext4/namei.c:1553 Read of size 1 at addr ffff8881317c3005 by task syz-executor117/2331 CPU: 1 PID: 2331 Comm: syz-executor117 Not tainted 5.10.0+ #1 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.14.0-0-g155821a1990b-prebuilt.qemu.org 04/01/2014 Call Trace: __dump_stack lib/dump_stack.c:83 [inline] dump_stack+0x144/0x187 lib/dump_stack.c:124 print_address_description+0x7d/0x630 mm/kasan/report.c:387 __kasan_report+0x132/0x190 mm/kasan/report.c:547 kasan_report+0x47/0x60 mm/kasan/report.c:564 ext4_search_dir fs/ext4/namei.c:1394 [inline] search_dirblock fs/ext4/namei.c:1199 [inline] __ext4_find_entry+0xdca/0x1210 fs/ext4/namei.c:1553 ext4_lookup_entry fs/ext4/namei.c:1622 [inline] ext4_lookup+0xb8/0x3a0 fs/ext4/namei.c:1690 __lookup_hash+0xc5/0x190 fs/namei.c:1451 do_rmdir+0x19e/0x310 fs/namei.c:3760 do_syscall_64+0x33/0x40 arch/x86/entry/common.c:46 entry_SYSCALL_64_after_hwframe+0x44/0xa9 RIP: 0033:0x445e59 Code: 4d c7 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 1b c7 fb ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007fff2277fac8 EFLAGS: 00000246 ORIG_RAX: 0000000000000054 RAX: ffffffffffffffda RBX: 0000000000400280 RCX: 0000000000445e59 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 00000000200000c0 RBP: 0000000000000000 R08: 0000000000000000 R09: 0000000000000002 R10: 00007fff2277f990 R11: 0000000000000246 R12: 0000000000000000 R13: 431bde82d7b634db R14: 0000000000000000 R15: 0000000000000000 The buggy address belongs to the page: page:0000000048cd3304 refcount:0 mapcount:0 mapping:0000000000000000 index:0x1 pfn:0x1317c3 flags: 0x200000000000000() raw: 0200000000000000 ffffea0004526588 ffffea0004528088 0000000000000000 raw: 0000000000000001 0000000000000000 00000000ffffffff 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff8881317c2f00: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ffff8881317c2f80: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 >ffff8881317c3000: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ^ ffff8881317c3080: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ffff8881317c3100: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ================================================================== ext4_search_dir: ... de = (struct ext4_dir_entry_2 *)search_buf; dlimit = search_buf + buf_size; while ((char *) de < dlimit) { ... if ((char *) de + de->name_len <= dlimit && ext4_match(dir, fname, de)) { ... } ... de_len = ext4_rec_len_from_disk(de->rec_len, dir->i_sb->s_blocksize); if (de_len <= 0) return -1; offset += de_len; de = (struct ext4_dir_entry_2 *) ((char *) de + de_len); } Assume: de=0xffff8881317c2fff dlimit=0x0xffff8881317c3000 If read 'de->name_len' which address is 0xffff8881317c3005, obviously is out of range, then will trigger use-after-free. To solve this issue, 'dlimit' must reserve 8 bytes, as we will read 'de->name_len' to judge if '(char *) de + de->name_len' out of range. Signed-off-by: Ye Bin <yebin10@huawei.com> Reviewed-by: Jan Kara <jack@suse.cz> Link: https://lore.kernel.org/r/20220324064816.1209985-1-yebin10@huawei.com Signed-off-by: Theodore Ts'o <tytso@mit.edu> Cc: stable@kernel.org
2022-03-24 14:48:16 +08:00
/*
* Base length of the ext4 directory entry excluding the name length
*/
#define EXT4_BASE_DIR_LEN (sizeof(struct ext4_dir_entry_2) - EXT4_NAME_LEN)
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 */
};
/*
* Encrypted Casefolded entries require saving the hash on disk. This structure
* followed ext4_dir_entry_2's name[name_len] at the next 4 byte aligned
* boundary.
*/
struct ext4_dir_entry_hash {
__le32 hash;
__le32 minor_hash;
};
/*
* 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; /* See file type macros EXT4_FT_* below */
char name[EXT4_NAME_LEN]; /* File name */
};
/*
* Access the hashes at the end of ext4_dir_entry_2
*/
#define EXT4_DIRENT_HASHES(entry) \
((struct ext4_dir_entry_hash *) \
(((void *)(entry)) + \
((8 + (entry)->name_len + EXT4_DIR_ROUND) & ~EXT4_DIR_ROUND)))
#define EXT4_DIRENT_HASH(entry) le32_to_cpu(EXT4_DIRENT_HASHES(de)->hash)
#define EXT4_DIRENT_MINOR_HASH(entry) \
le32_to_cpu(EXT4_DIRENT_HASHES(de)->minor_hash)
static inline bool ext4_hash_in_dirent(const struct inode *inode)
{
return IS_CASEFOLDED(inode) && IS_ENCRYPTED(inode);
}
/*
* 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) */
};
#define EXT4_DIRENT_TAIL(block, blocksize) \
((struct ext4_dir_entry_tail *)(((void *)(block)) + \
((blocksize) - \
sizeof(struct ext4_dir_entry_tail))))
/*
* 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_MAX_REC_LEN ((1<<16)-1)
/*
* The rec_len is dependent on the type of directory. Directories that are
* casefolded and encrypted need to store the hash as well, so we add room for
* ext4_extended_dir_entry_2. For all entries related to '.' or '..' you should
* pass NULL for dir, as those entries do not use the extra fields.
*/
static inline unsigned int ext4_dir_rec_len(__u8 name_len,
const struct inode *dir)
{
int rec_len = (name_len + 8 + EXT4_DIR_ROUND);
if (dir && ext4_hash_in_dirent(dir))
rec_len += sizeof(struct ext4_dir_entry_hash);
return (rec_len & ~EXT4_DIR_ROUND);
}
/*
* 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_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)
{
BUG_ON((len > blocksize) || (blocksize > (1 << 18)) || (len & 3));
#if (PAGE_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_feature_dir_index((dir)->i_sb) && \
ext4_test_inode_flag((dir), EXT4_INODE_INDEX))
#define EXT4_DIR_LINK_MAX(dir) unlikely((dir)->i_nlink >= EXT4_LINK_MAX && \
!(ext4_has_feature_dir_nlink((dir)->i_sb) && is_dx(dir)))
#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
#define DX_HASH_SIPHASH 6
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[4];
} desc;
BUG_ON(crypto_shash_descsize(sbi->s_chksum_driver)!=sizeof(desc.ctx));
desc.shash.tfm = sbi->s_chksum_driver;
*(u32 *)desc.ctx = crc;
BUG_ON(crypto_shash_update(&desc.shash, address, length));
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
struct ext4_filename {
const struct qstr *usr_fname;
struct fscrypt_str disk_name;
struct dx_hash_info hinfo;
#ifdef CONFIG_FS_ENCRYPTION
struct fscrypt_str crypto_buf;
#endif
#if IS_ENABLED(CONFIG_UNICODE)
struct fscrypt_str cf_name;
#endif
};
#define fname_name(p) ((p)->disk_name.name)
#define fname_usr_name(p) ((p)->usr_fname->name)
#define fname_len(p) ((p)->disk_name.len)
/*
* 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);
}
static inline bool ext4_is_quota_file(struct inode *inode)
{
return IS_NOQUOTA(inode) &&
!(EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL);
}
/*
* 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 (-(MAX_ERRNO - 1))
/* htree levels for ext4 */
#define EXT4_HTREE_LEVEL_COMPAT 2
#define EXT4_HTREE_LEVEL 3
static inline int ext4_dir_htree_level(struct super_block *sb)
{
return ext4_has_feature_largedir(sb) ?
EXT4_HTREE_LEVEL : EXT4_HTREE_LEVEL_COMPAT;
}
ext4: add support for lazy inode table initialization When the lazy_itable_init extended option is passed to mke2fs, it considerably speeds up filesystem creation because inode tables are not zeroed out. The fact that parts of the inode table are uninitialized is not a problem so long as the block group descriptors, which contain information regarding how much of the inode table has been initialized, has not been corrupted However, if the block group checksums are not valid, e2fsck must scan the entire inode table, and the the old, uninitialized data could potentially cause e2fsck to report false problems. Hence, it is important for the inode tables to be initialized as soon as possble. This commit adds this feature so that mke2fs can safely use the lazy inode table initialization feature to speed up formatting file systems. This is done via a new new kernel thread called ext4lazyinit, which is created on demand and destroyed, when it is no longer needed. There is only one thread for all ext4 filesystems in the system. When the first filesystem with inititable mount option is mounted, ext4lazyinit thread is created, then the filesystem can register its request in the request list. This thread then walks through the list of requests picking up scheduled requests and invoking ext4_init_inode_table(). Next schedule time for the request is computed by multiplying the time it took to zero out last inode table with wait multiplier, which can be set with the (init_itable=n) mount option (default is 10). We are doing this so we do not take the whole I/O bandwidth. When the thread is no longer necessary (request list is empty) it frees the appropriate structures and exits (and can be created later later by another filesystem). We do not disturb regular inode allocations in any way, it just do not care whether the inode table is, or is not zeroed. But when zeroing, we have to skip used inodes, obviously. Also we should prevent new inode allocations from the group, while zeroing is on the way. For that we take write alloc_sem lock in ext4_init_inode_table() and read alloc_sem in the ext4_claim_inode, so when we are unlucky and allocator hits the group which is currently being zeroed, it just has to wait. This can be suppresed using the mount option no_init_itable. Signed-off-by: Lukas Czerner <lczerner@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2010-10-28 09:30:05 +08:00
/*
* 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;
};
enum ext4_li_mode {
EXT4_LI_MODE_PREFETCH_BBITMAP,
EXT4_LI_MODE_ITABLE,
};
ext4: add support for lazy inode table initialization When the lazy_itable_init extended option is passed to mke2fs, it considerably speeds up filesystem creation because inode tables are not zeroed out. The fact that parts of the inode table are uninitialized is not a problem so long as the block group descriptors, which contain information regarding how much of the inode table has been initialized, has not been corrupted However, if the block group checksums are not valid, e2fsck must scan the entire inode table, and the the old, uninitialized data could potentially cause e2fsck to report false problems. Hence, it is important for the inode tables to be initialized as soon as possble. This commit adds this feature so that mke2fs can safely use the lazy inode table initialization feature to speed up formatting file systems. This is done via a new new kernel thread called ext4lazyinit, which is created on demand and destroyed, when it is no longer needed. There is only one thread for all ext4 filesystems in the system. When the first filesystem with inititable mount option is mounted, ext4lazyinit thread is created, then the filesystem can register its request in the request list. This thread then walks through the list of requests picking up scheduled requests and invoking ext4_init_inode_table(). Next schedule time for the request is computed by multiplying the time it took to zero out last inode table with wait multiplier, which can be set with the (init_itable=n) mount option (default is 10). We are doing this so we do not take the whole I/O bandwidth. When the thread is no longer necessary (request list is empty) it frees the appropriate structures and exits (and can be created later later by another filesystem). We do not disturb regular inode allocations in any way, it just do not care whether the inode table is, or is not zeroed. But when zeroing, we have to skip used inodes, obviously. Also we should prevent new inode allocations from the group, while zeroing is on the way. For that we take write alloc_sem lock in ext4_init_inode_table() and read alloc_sem in the ext4_claim_inode, so when we are unlucky and allocator hits the group which is currently being zeroed, it just has to wait. This can be suppresed using the mount option no_init_itable. Signed-off-by: Lukas Czerner <lczerner@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2010-10-28 09:30:05 +08:00
struct ext4_li_request {
struct super_block *lr_super;
enum ext4_li_mode lr_mode;
ext4_group_t lr_first_not_zeroed;
ext4: add support for lazy inode table initialization When the lazy_itable_init extended option is passed to mke2fs, it considerably speeds up filesystem creation because inode tables are not zeroed out. The fact that parts of the inode table are uninitialized is not a problem so long as the block group descriptors, which contain information regarding how much of the inode table has been initialized, has not been corrupted However, if the block group checksums are not valid, e2fsck must scan the entire inode table, and the the old, uninitialized data could potentially cause e2fsck to report false problems. Hence, it is important for the inode tables to be initialized as soon as possble. This commit adds this feature so that mke2fs can safely use the lazy inode table initialization feature to speed up formatting file systems. This is done via a new new kernel thread called ext4lazyinit, which is created on demand and destroyed, when it is no longer needed. There is only one thread for all ext4 filesystems in the system. When the first filesystem with inititable mount option is mounted, ext4lazyinit thread is created, then the filesystem can register its request in the request list. This thread then walks through the list of requests picking up scheduled requests and invoking ext4_init_inode_table(). Next schedule time for the request is computed by multiplying the time it took to zero out last inode table with wait multiplier, which can be set with the (init_itable=n) mount option (default is 10). We are doing this so we do not take the whole I/O bandwidth. When the thread is no longer necessary (request list is empty) it frees the appropriate structures and exits (and can be created later later by another filesystem). We do not disturb regular inode allocations in any way, it just do not care whether the inode table is, or is not zeroed. But when zeroing, we have to skip used inodes, obviously. Also we should prevent new inode allocations from the group, while zeroing is on the way. For that we take write alloc_sem lock in ext4_init_inode_table() and read alloc_sem in the ext4_claim_inode, so when we are unlucky and allocator hits the group which is currently being zeroed, it just has to wait. This can be suppresed using the mount option no_init_itable. Signed-off-by: Lukas Czerner <lczerner@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2010-10-28 09:30:05 +08:00
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(char *bitmap, unsigned numchars);
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 ext4_block_bitmap_csum_verify(struct super_block *sb, ext4_group_t group,
struct ext4_group_desc *gdp,
struct buffer_head *bh);
/* balloc.c */
extern void ext4_get_group_no_and_offset(struct super_block *sb,
ext4_fsblk_t blocknr,
ext4_group_t *blockgrpp,
ext4_grpblk_t *offsetp);
extern ext4_group_t ext4_get_group_number(struct super_block *sb,
ext4_fsblk_t block);
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,
bool ignore_locked);
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 unsigned ext4_free_clusters_after_init(struct super_block *sb,
ext4_group_t block_group,
struct ext4_group_desc *gdp);
ext4_fsblk_t ext4_inode_to_goal_block(struct inode *);
#if IS_ENABLED(CONFIG_UNICODE)
extern int ext4_fname_setup_ci_filename(struct inode *dir,
const struct qstr *iname,
struct ext4_filename *fname);
#endif
#ifdef CONFIG_FS_ENCRYPTION
fscrypt: fix race where ->lookup() marks plaintext dentry as ciphertext ->lookup() in an encrypted directory begins as follows: 1. fscrypt_prepare_lookup(): a. Try to load the directory's encryption key. b. If the key is unavailable, mark the dentry as a ciphertext name via d_flags. 2. fscrypt_setup_filename(): a. Try to load the directory's encryption key. b. If the key is available, encrypt the name (treated as a plaintext name) to get the on-disk name. Otherwise decode the name (treated as a ciphertext name) to get the on-disk name. But if the key is concurrently added, it may be found at (2a) but not at (1a). In this case, the dentry will be wrongly marked as a ciphertext name even though it was actually treated as plaintext. This will cause the dentry to be wrongly invalidated on the next lookup, potentially causing problems. For example, if the racy ->lookup() was part of sys_mount(), then the new mount will be detached when anything tries to access it. This is despite the mountpoint having a plaintext path, which should remain valid now that the key was added. Of course, this is only possible if there's a userspace race. Still, the additional kernel-side race is confusing and unexpected. Close the kernel-side race by changing fscrypt_prepare_lookup() to also set the on-disk filename (step 2b), consistent with the d_flags update. Fixes: 28b4c263961c ("ext4 crypto: revalidate dentry after adding or removing the key") Signed-off-by: Eric Biggers <ebiggers@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2019-03-21 02:39:13 +08:00
static inline void ext4_fname_from_fscrypt_name(struct ext4_filename *dst,
const struct fscrypt_name *src)
{
memset(dst, 0, sizeof(*dst));
dst->usr_fname = src->usr_fname;
dst->disk_name = src->disk_name;
dst->hinfo.hash = src->hash;
dst->hinfo.minor_hash = src->minor_hash;
dst->crypto_buf = src->crypto_buf;
}
static inline int ext4_fname_setup_filename(struct inode *dir,
fscrypt: fix race where ->lookup() marks plaintext dentry as ciphertext ->lookup() in an encrypted directory begins as follows: 1. fscrypt_prepare_lookup(): a. Try to load the directory's encryption key. b. If the key is unavailable, mark the dentry as a ciphertext name via d_flags. 2. fscrypt_setup_filename(): a. Try to load the directory's encryption key. b. If the key is available, encrypt the name (treated as a plaintext name) to get the on-disk name. Otherwise decode the name (treated as a ciphertext name) to get the on-disk name. But if the key is concurrently added, it may be found at (2a) but not at (1a). In this case, the dentry will be wrongly marked as a ciphertext name even though it was actually treated as plaintext. This will cause the dentry to be wrongly invalidated on the next lookup, potentially causing problems. For example, if the racy ->lookup() was part of sys_mount(), then the new mount will be detached when anything tries to access it. This is despite the mountpoint having a plaintext path, which should remain valid now that the key was added. Of course, this is only possible if there's a userspace race. Still, the additional kernel-side race is confusing and unexpected. Close the kernel-side race by changing fscrypt_prepare_lookup() to also set the on-disk filename (step 2b), consistent with the d_flags update. Fixes: 28b4c263961c ("ext4 crypto: revalidate dentry after adding or removing the key") Signed-off-by: Eric Biggers <ebiggers@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2019-03-21 02:39:13 +08:00
const struct qstr *iname,
int lookup,
struct ext4_filename *fname)
{
struct fscrypt_name name;
int err;
err = fscrypt_setup_filename(dir, iname, lookup, &name);
fscrypt: fix race where ->lookup() marks plaintext dentry as ciphertext ->lookup() in an encrypted directory begins as follows: 1. fscrypt_prepare_lookup(): a. Try to load the directory's encryption key. b. If the key is unavailable, mark the dentry as a ciphertext name via d_flags. 2. fscrypt_setup_filename(): a. Try to load the directory's encryption key. b. If the key is available, encrypt the name (treated as a plaintext name) to get the on-disk name. Otherwise decode the name (treated as a ciphertext name) to get the on-disk name. But if the key is concurrently added, it may be found at (2a) but not at (1a). In this case, the dentry will be wrongly marked as a ciphertext name even though it was actually treated as plaintext. This will cause the dentry to be wrongly invalidated on the next lookup, potentially causing problems. For example, if the racy ->lookup() was part of sys_mount(), then the new mount will be detached when anything tries to access it. This is despite the mountpoint having a plaintext path, which should remain valid now that the key was added. Of course, this is only possible if there's a userspace race. Still, the additional kernel-side race is confusing and unexpected. Close the kernel-side race by changing fscrypt_prepare_lookup() to also set the on-disk filename (step 2b), consistent with the d_flags update. Fixes: 28b4c263961c ("ext4 crypto: revalidate dentry after adding or removing the key") Signed-off-by: Eric Biggers <ebiggers@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2019-03-21 02:39:13 +08:00
if (err)
return err;
ext4 crypto: reorganize how we store keys in the inode This is a pretty massive patch which does a number of different things: 1) The per-inode encryption information is now stored in an allocated data structure, ext4_crypt_info, instead of directly in the node. This reduces the size usage of an in-memory inode when it is not using encryption. 2) We drop the ext4_fname_crypto_ctx entirely, and use the per-inode encryption structure instead. This remove an unnecessary memory allocation and free for the fname_crypto_ctx as well as allowing us to reuse the ctfm in a directory for multiple lookups and file creations. 3) We also cache the inode's policy information in the ext4_crypt_info structure so we don't have to continually read it out of the extended attributes. 4) We now keep the keyring key in the inode's encryption structure instead of releasing it after we are done using it to derive the per-inode key. This allows us to test to see if the key has been revoked; if it has, we prevent the use of the derived key and free it. 5) When an inode is released (or when the derived key is freed), we will use memset_explicit() to zero out the derived key, so it's not left hanging around in memory. This implies that when a user logs out, it is important to first revoke the key, and then unlink it, and then finally, to use "echo 3 > /proc/sys/vm/drop_caches" to release any decrypted pages and dcache entries from the system caches. 6) All this, and we also shrink the number of lines of code by around 100. :-) Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2015-05-19 01:17:47 +08:00
fscrypt: fix race where ->lookup() marks plaintext dentry as ciphertext ->lookup() in an encrypted directory begins as follows: 1. fscrypt_prepare_lookup(): a. Try to load the directory's encryption key. b. If the key is unavailable, mark the dentry as a ciphertext name via d_flags. 2. fscrypt_setup_filename(): a. Try to load the directory's encryption key. b. If the key is available, encrypt the name (treated as a plaintext name) to get the on-disk name. Otherwise decode the name (treated as a ciphertext name) to get the on-disk name. But if the key is concurrently added, it may be found at (2a) but not at (1a). In this case, the dentry will be wrongly marked as a ciphertext name even though it was actually treated as plaintext. This will cause the dentry to be wrongly invalidated on the next lookup, potentially causing problems. For example, if the racy ->lookup() was part of sys_mount(), then the new mount will be detached when anything tries to access it. This is despite the mountpoint having a plaintext path, which should remain valid now that the key was added. Of course, this is only possible if there's a userspace race. Still, the additional kernel-side race is confusing and unexpected. Close the kernel-side race by changing fscrypt_prepare_lookup() to also set the on-disk filename (step 2b), consistent with the d_flags update. Fixes: 28b4c263961c ("ext4 crypto: revalidate dentry after adding or removing the key") Signed-off-by: Eric Biggers <ebiggers@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2019-03-21 02:39:13 +08:00
ext4_fname_from_fscrypt_name(fname, &name);
#if IS_ENABLED(CONFIG_UNICODE)
err = ext4_fname_setup_ci_filename(dir, iname, fname);
#endif
return err;
fscrypt: fix race where ->lookup() marks plaintext dentry as ciphertext ->lookup() in an encrypted directory begins as follows: 1. fscrypt_prepare_lookup(): a. Try to load the directory's encryption key. b. If the key is unavailable, mark the dentry as a ciphertext name via d_flags. 2. fscrypt_setup_filename(): a. Try to load the directory's encryption key. b. If the key is available, encrypt the name (treated as a plaintext name) to get the on-disk name. Otherwise decode the name (treated as a ciphertext name) to get the on-disk name. But if the key is concurrently added, it may be found at (2a) but not at (1a). In this case, the dentry will be wrongly marked as a ciphertext name even though it was actually treated as plaintext. This will cause the dentry to be wrongly invalidated on the next lookup, potentially causing problems. For example, if the racy ->lookup() was part of sys_mount(), then the new mount will be detached when anything tries to access it. This is despite the mountpoint having a plaintext path, which should remain valid now that the key was added. Of course, this is only possible if there's a userspace race. Still, the additional kernel-side race is confusing and unexpected. Close the kernel-side race by changing fscrypt_prepare_lookup() to also set the on-disk filename (step 2b), consistent with the d_flags update. Fixes: 28b4c263961c ("ext4 crypto: revalidate dentry after adding or removing the key") Signed-off-by: Eric Biggers <ebiggers@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2019-03-21 02:39:13 +08:00
}
static inline int ext4_fname_prepare_lookup(struct inode *dir,
struct dentry *dentry,
struct ext4_filename *fname)
{
struct fscrypt_name name;
int err;
err = fscrypt_prepare_lookup(dir, dentry, &name);
if (err)
return err;
ext4_fname_from_fscrypt_name(fname, &name);
#if IS_ENABLED(CONFIG_UNICODE)
err = ext4_fname_setup_ci_filename(dir, &dentry->d_name, fname);
#endif
return err;
ext4 crypto: reorganize how we store keys in the inode This is a pretty massive patch which does a number of different things: 1) The per-inode encryption information is now stored in an allocated data structure, ext4_crypt_info, instead of directly in the node. This reduces the size usage of an in-memory inode when it is not using encryption. 2) We drop the ext4_fname_crypto_ctx entirely, and use the per-inode encryption structure instead. This remove an unnecessary memory allocation and free for the fname_crypto_ctx as well as allowing us to reuse the ctfm in a directory for multiple lookups and file creations. 3) We also cache the inode's policy information in the ext4_crypt_info structure so we don't have to continually read it out of the extended attributes. 4) We now keep the keyring key in the inode's encryption structure instead of releasing it after we are done using it to derive the per-inode key. This allows us to test to see if the key has been revoked; if it has, we prevent the use of the derived key and free it. 5) When an inode is released (or when the derived key is freed), we will use memset_explicit() to zero out the derived key, so it's not left hanging around in memory. This implies that when a user logs out, it is important to first revoke the key, and then unlink it, and then finally, to use "echo 3 > /proc/sys/vm/drop_caches" to release any decrypted pages and dcache entries from the system caches. 6) All this, and we also shrink the number of lines of code by around 100. :-) Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2015-05-19 01:17:47 +08:00
}
static inline void ext4_fname_free_filename(struct ext4_filename *fname)
{
struct fscrypt_name name;
name.crypto_buf = fname->crypto_buf;
fscrypt_free_filename(&name);
fname->crypto_buf.name = NULL;
fname->usr_fname = NULL;
fname->disk_name.name = NULL;
#if IS_ENABLED(CONFIG_UNICODE)
kfree(fname->cf_name.name);
fname->cf_name.name = NULL;
#endif
}
fscrypt: fix race where ->lookup() marks plaintext dentry as ciphertext ->lookup() in an encrypted directory begins as follows: 1. fscrypt_prepare_lookup(): a. Try to load the directory's encryption key. b. If the key is unavailable, mark the dentry as a ciphertext name via d_flags. 2. fscrypt_setup_filename(): a. Try to load the directory's encryption key. b. If the key is available, encrypt the name (treated as a plaintext name) to get the on-disk name. Otherwise decode the name (treated as a ciphertext name) to get the on-disk name. But if the key is concurrently added, it may be found at (2a) but not at (1a). In this case, the dentry will be wrongly marked as a ciphertext name even though it was actually treated as plaintext. This will cause the dentry to be wrongly invalidated on the next lookup, potentially causing problems. For example, if the racy ->lookup() was part of sys_mount(), then the new mount will be detached when anything tries to access it. This is despite the mountpoint having a plaintext path, which should remain valid now that the key was added. Of course, this is only possible if there's a userspace race. Still, the additional kernel-side race is confusing and unexpected. Close the kernel-side race by changing fscrypt_prepare_lookup() to also set the on-disk filename (step 2b), consistent with the d_flags update. Fixes: 28b4c263961c ("ext4 crypto: revalidate dentry after adding or removing the key") Signed-off-by: Eric Biggers <ebiggers@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2019-03-21 02:39:13 +08:00
#else /* !CONFIG_FS_ENCRYPTION */
static inline int ext4_fname_setup_filename(struct inode *dir,
fscrypt: fix race where ->lookup() marks plaintext dentry as ciphertext ->lookup() in an encrypted directory begins as follows: 1. fscrypt_prepare_lookup(): a. Try to load the directory's encryption key. b. If the key is unavailable, mark the dentry as a ciphertext name via d_flags. 2. fscrypt_setup_filename(): a. Try to load the directory's encryption key. b. If the key is available, encrypt the name (treated as a plaintext name) to get the on-disk name. Otherwise decode the name (treated as a ciphertext name) to get the on-disk name. But if the key is concurrently added, it may be found at (2a) but not at (1a). In this case, the dentry will be wrongly marked as a ciphertext name even though it was actually treated as plaintext. This will cause the dentry to be wrongly invalidated on the next lookup, potentially causing problems. For example, if the racy ->lookup() was part of sys_mount(), then the new mount will be detached when anything tries to access it. This is despite the mountpoint having a plaintext path, which should remain valid now that the key was added. Of course, this is only possible if there's a userspace race. Still, the additional kernel-side race is confusing and unexpected. Close the kernel-side race by changing fscrypt_prepare_lookup() to also set the on-disk filename (step 2b), consistent with the d_flags update. Fixes: 28b4c263961c ("ext4 crypto: revalidate dentry after adding or removing the key") Signed-off-by: Eric Biggers <ebiggers@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2019-03-21 02:39:13 +08:00
const struct qstr *iname,
int lookup,
struct ext4_filename *fname)
ext4 crypto: reorganize how we store keys in the inode This is a pretty massive patch which does a number of different things: 1) The per-inode encryption information is now stored in an allocated data structure, ext4_crypt_info, instead of directly in the node. This reduces the size usage of an in-memory inode when it is not using encryption. 2) We drop the ext4_fname_crypto_ctx entirely, and use the per-inode encryption structure instead. This remove an unnecessary memory allocation and free for the fname_crypto_ctx as well as allowing us to reuse the ctfm in a directory for multiple lookups and file creations. 3) We also cache the inode's policy information in the ext4_crypt_info structure so we don't have to continually read it out of the extended attributes. 4) We now keep the keyring key in the inode's encryption structure instead of releasing it after we are done using it to derive the per-inode key. This allows us to test to see if the key has been revoked; if it has, we prevent the use of the derived key and free it. 5) When an inode is released (or when the derived key is freed), we will use memset_explicit() to zero out the derived key, so it's not left hanging around in memory. This implies that when a user logs out, it is important to first revoke the key, and then unlink it, and then finally, to use "echo 3 > /proc/sys/vm/drop_caches" to release any decrypted pages and dcache entries from the system caches. 6) All this, and we also shrink the number of lines of code by around 100. :-) Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2015-05-19 01:17:47 +08:00
{
int err = 0;
fname->usr_fname = iname;
fname->disk_name.name = (unsigned char *) iname->name;
fname->disk_name.len = iname->len;
#if IS_ENABLED(CONFIG_UNICODE)
err = ext4_fname_setup_ci_filename(dir, iname, fname);
#endif
return err;
ext4 crypto: reorganize how we store keys in the inode This is a pretty massive patch which does a number of different things: 1) The per-inode encryption information is now stored in an allocated data structure, ext4_crypt_info, instead of directly in the node. This reduces the size usage of an in-memory inode when it is not using encryption. 2) We drop the ext4_fname_crypto_ctx entirely, and use the per-inode encryption structure instead. This remove an unnecessary memory allocation and free for the fname_crypto_ctx as well as allowing us to reuse the ctfm in a directory for multiple lookups and file creations. 3) We also cache the inode's policy information in the ext4_crypt_info structure so we don't have to continually read it out of the extended attributes. 4) We now keep the keyring key in the inode's encryption structure instead of releasing it after we are done using it to derive the per-inode key. This allows us to test to see if the key has been revoked; if it has, we prevent the use of the derived key and free it. 5) When an inode is released (or when the derived key is freed), we will use memset_explicit() to zero out the derived key, so it's not left hanging around in memory. This implies that when a user logs out, it is important to first revoke the key, and then unlink it, and then finally, to use "echo 3 > /proc/sys/vm/drop_caches" to release any decrypted pages and dcache entries from the system caches. 6) All this, and we also shrink the number of lines of code by around 100. :-) Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2015-05-19 01:17:47 +08:00
}
fscrypt: fix race where ->lookup() marks plaintext dentry as ciphertext ->lookup() in an encrypted directory begins as follows: 1. fscrypt_prepare_lookup(): a. Try to load the directory's encryption key. b. If the key is unavailable, mark the dentry as a ciphertext name via d_flags. 2. fscrypt_setup_filename(): a. Try to load the directory's encryption key. b. If the key is available, encrypt the name (treated as a plaintext name) to get the on-disk name. Otherwise decode the name (treated as a ciphertext name) to get the on-disk name. But if the key is concurrently added, it may be found at (2a) but not at (1a). In this case, the dentry will be wrongly marked as a ciphertext name even though it was actually treated as plaintext. This will cause the dentry to be wrongly invalidated on the next lookup, potentially causing problems. For example, if the racy ->lookup() was part of sys_mount(), then the new mount will be detached when anything tries to access it. This is despite the mountpoint having a plaintext path, which should remain valid now that the key was added. Of course, this is only possible if there's a userspace race. Still, the additional kernel-side race is confusing and unexpected. Close the kernel-side race by changing fscrypt_prepare_lookup() to also set the on-disk filename (step 2b), consistent with the d_flags update. Fixes: 28b4c263961c ("ext4 crypto: revalidate dentry after adding or removing the key") Signed-off-by: Eric Biggers <ebiggers@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2019-03-21 02:39:13 +08:00
static inline int ext4_fname_prepare_lookup(struct inode *dir,
struct dentry *dentry,
struct ext4_filename *fname)
{
return ext4_fname_setup_filename(dir, &dentry->d_name, 1, fname);
}
static inline void ext4_fname_free_filename(struct ext4_filename *fname)
{
#if IS_ENABLED(CONFIG_UNICODE)
kfree(fname->cf_name.name);
fname->cf_name.name = NULL;
#endif
}
fscrypt: fix race where ->lookup() marks plaintext dentry as ciphertext ->lookup() in an encrypted directory begins as follows: 1. fscrypt_prepare_lookup(): a. Try to load the directory's encryption key. b. If the key is unavailable, mark the dentry as a ciphertext name via d_flags. 2. fscrypt_setup_filename(): a. Try to load the directory's encryption key. b. If the key is available, encrypt the name (treated as a plaintext name) to get the on-disk name. Otherwise decode the name (treated as a ciphertext name) to get the on-disk name. But if the key is concurrently added, it may be found at (2a) but not at (1a). In this case, the dentry will be wrongly marked as a ciphertext name even though it was actually treated as plaintext. This will cause the dentry to be wrongly invalidated on the next lookup, potentially causing problems. For example, if the racy ->lookup() was part of sys_mount(), then the new mount will be detached when anything tries to access it. This is despite the mountpoint having a plaintext path, which should remain valid now that the key was added. Of course, this is only possible if there's a userspace race. Still, the additional kernel-side race is confusing and unexpected. Close the kernel-side race by changing fscrypt_prepare_lookup() to also set the on-disk filename (step 2b), consistent with the d_flags update. Fixes: 28b4c263961c ("ext4 crypto: revalidate dentry after adding or removing the key") Signed-off-by: Eric Biggers <ebiggers@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2019-03-21 02:39:13 +08:00
#endif /* !CONFIG_FS_ENCRYPTION */
/* dir.c */
extern int __ext4_check_dir_entry(const char *, unsigned int, struct inode *,
struct file *,
struct ext4_dir_entry_2 *,
struct buffer_head *, char *, int,
unsigned int);
#define ext4_check_dir_entry(dir, filp, de, bh, buf, size, offset) \
unlikely(__ext4_check_dir_entry(__func__, __LINE__, (dir), (filp), \
(de), (bh), (buf), (size), (offset)))
extern int ext4_htree_store_dirent(struct file *dir_file, __u32 hash,
__u32 minor_hash,
struct ext4_dir_entry_2 *dirent,
struct fscrypt_str *ent_name);
extern void ext4_htree_free_dir_info(struct dir_private_info *p);
extern int ext4_find_dest_de(struct inode *dir, struct inode *inode,
struct buffer_head *bh,
void *buf, int buf_size,
struct ext4_filename *fname,
struct ext4_dir_entry_2 **dest_de);
void ext4_insert_dentry(struct inode *dir, struct inode *inode,
struct ext4_dir_entry_2 *de,
int buf_size,
struct ext4_filename *fname);
static inline void ext4_update_dx_flag(struct inode *inode)
{
if (!ext4_has_feature_dir_index(inode->i_sb) &&
ext4_test_inode_flag(inode, EXT4_INODE_INDEX)) {
ext4: fix checksum errors with indexed dirs DIR_INDEX has been introduced as a compat ext4 feature. That means that even kernels / tools that don't understand the feature may modify the filesystem. This works because for kernels not understanding indexed dir format, internal htree nodes appear just as empty directory entries. Index dir aware kernels then check the htree structure is still consistent before using the data. This all worked reasonably well until metadata checksums were introduced. The problem is that these effectively made DIR_INDEX only ro-compatible because internal htree nodes store checksums in a different place than normal directory blocks. Thus any modification ignorant to DIR_INDEX (or just clearing EXT4_INDEX_FL from the inode) will effectively cause checksum mismatch and trigger kernel errors. So we have to be more careful when dealing with indexed directories on filesystems with checksumming enabled. 1) We just disallow loading any directory inodes with EXT4_INDEX_FL when DIR_INDEX is not enabled. This is harsh but it should be very rare (it means someone disabled DIR_INDEX on existing filesystem and didn't run e2fsck), e2fsck can fix the problem, and we don't want to answer the difficult question: "Should we rather corrupt the directory more or should we ignore that DIR_INDEX feature is not set?" 2) When we find out htree structure is corrupted (but the filesystem and the directory should in support htrees), we continue just ignoring htree information for reading but we refuse to add new entries to the directory to avoid corrupting it more. Link: https://lore.kernel.org/r/20200210144316.22081-1-jack@suse.cz Fixes: dbe89444042a ("ext4: Calculate and verify checksums for htree nodes") Reviewed-by: Andreas Dilger <adilger@dilger.ca> Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Cc: stable@kernel.org
2020-02-10 22:43:16 +08:00
/* ext4_iget() should have caught this... */
WARN_ON_ONCE(ext4_has_feature_metadata_csum(inode->i_sb));
ext4_clear_inode_flag(inode, EXT4_INODE_INDEX);
ext4: fix checksum errors with indexed dirs DIR_INDEX has been introduced as a compat ext4 feature. That means that even kernels / tools that don't understand the feature may modify the filesystem. This works because for kernels not understanding indexed dir format, internal htree nodes appear just as empty directory entries. Index dir aware kernels then check the htree structure is still consistent before using the data. This all worked reasonably well until metadata checksums were introduced. The problem is that these effectively made DIR_INDEX only ro-compatible because internal htree nodes store checksums in a different place than normal directory blocks. Thus any modification ignorant to DIR_INDEX (or just clearing EXT4_INDEX_FL from the inode) will effectively cause checksum mismatch and trigger kernel errors. So we have to be more careful when dealing with indexed directories on filesystems with checksumming enabled. 1) We just disallow loading any directory inodes with EXT4_INDEX_FL when DIR_INDEX is not enabled. This is harsh but it should be very rare (it means someone disabled DIR_INDEX on existing filesystem and didn't run e2fsck), e2fsck can fix the problem, and we don't want to answer the difficult question: "Should we rather corrupt the directory more or should we ignore that DIR_INDEX feature is not set?" 2) When we find out htree structure is corrupted (but the filesystem and the directory should in support htrees), we continue just ignoring htree information for reading but we refuse to add new entries to the directory to avoid corrupting it more. Link: https://lore.kernel.org/r/20200210144316.22081-1-jack@suse.cz Fixes: dbe89444042a ("ext4: Calculate and verify checksums for htree nodes") Reviewed-by: Andreas Dilger <adilger@dilger.ca> Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Cc: stable@kernel.org
2020-02-10 22:43:16 +08:00
}
}
static const unsigned char ext4_filetype_table[] = {
DT_UNKNOWN, DT_REG, DT_DIR, DT_CHR, DT_BLK, DT_FIFO, DT_SOCK, DT_LNK
};
static inline unsigned char get_dtype(struct super_block *sb, int filetype)
{
if (!ext4_has_feature_filetype(sb) || filetype >= EXT4_FT_MAX)
return DT_UNKNOWN;
return ext4_filetype_table[filetype];
}
extern int ext4_check_all_de(struct inode *dir, struct buffer_head *bh,
void *buf, int buf_size);
/* fsync.c */
extern int ext4_sync_file(struct file *, loff_t, loff_t, int);
/* hash.c */
ext4: Support case-insensitive file name lookups This patch implements the actual support for case-insensitive file name lookups in ext4, based on the feature bit and the encoding stored in the superblock. A filesystem that has the casefold feature set is able to configure directories with the +F (EXT4_CASEFOLD_FL) attribute, enabling lookups to succeed in that directory in a case-insensitive fashion, i.e: match a directory entry even if the name used by userspace is not a byte per byte match with the disk name, but is an equivalent case-insensitive version of the Unicode string. This operation is called a case-insensitive file name lookup. The feature is configured as an inode attribute applied to directories and inherited by its children. This attribute can only be enabled on empty directories for filesystems that support the encoding feature, thus preventing collision of file names that only differ by case. * dcache handling: For a +F directory, Ext4 only stores the first equivalent name dentry used in the dcache. This is done to prevent unintentional duplication of dentries in the dcache, while also allowing the VFS code to quickly find the right entry in the cache despite which equivalent string was used in a previous lookup, without having to resort to ->lookup(). d_hash() of casefolded directories is implemented as the hash of the casefolded string, such that we always have a well-known bucket for all the equivalencies of the same string. d_compare() uses the utf8_strncasecmp() infrastructure, which handles the comparison of equivalent, same case, names as well. For now, negative lookups are not inserted in the dcache, since they would need to be invalidated anyway, because we can't trust missing file dentries. This is bad for performance but requires some leveraging of the vfs layer to fix. We can live without that for now, and so does everyone else. * on-disk data: Despite using a specific version of the name as the internal representation within the dcache, the name stored and fetched from the disk is a byte-per-byte match with what the user requested, making this implementation 'name-preserving'. i.e. no actual information is lost when writing to storage. DX is supported by modifying the hashes used in +F directories to make them case/encoding-aware. The new disk hashes are calculated as the hash of the full casefolded string, instead of the string directly. This allows us to efficiently search for file names in the htree without requiring the user to provide an exact name. * Dealing with invalid sequences: By default, when a invalid UTF-8 sequence is identified, ext4 will treat it as an opaque byte sequence, ignoring the encoding and reverting to the old behavior for that unique file. This means that case-insensitive file name lookup will not work only for that file. An optional bit can be set in the superblock telling the filesystem code and userspace tools to enforce the encoding. When that optional bit is set, any attempt to create a file name using an invalid UTF-8 sequence will fail and return an error to userspace. * Normalization algorithm: The UTF-8 algorithms used to compare strings in ext4 is implemented lives in fs/unicode, and is based on a previous version developed by SGI. It implements the Canonical decomposition (NFD) algorithm described by the Unicode specification 12.1, or higher, combined with the elimination of ignorable code points (NFDi) and full case-folding (CF) as documented in fs/unicode/utf8_norm.c. NFD seems to be the best normalization method for EXT4 because: - It has a lower cost than NFC/NFKC (which requires decomposing to NFD as an intermediary step) - It doesn't eliminate important semantic meaning like compatibility decompositions. Although: - This implementation is not completely linguistic accurate, because different languages have conflicting rules, which would require the specialization of the filesystem to a given locale, which brings all sorts of problems for removable media and for users who use more than one language. Signed-off-by: Gabriel Krisman Bertazi <krisman@collabora.co.uk> Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2019-04-26 02:12:08 +08:00
extern int ext4fs_dirhash(const struct inode *dir, const char *name, int len,
struct dx_hash_info *hinfo);
/* ialloc.c */
extern int ext4_mark_inode_used(struct super_block *sb, int ino);
ext4: support idmapped mounts Enable idmapped mounts for ext4. All dedicated helpers we need for this exist. So this basically just means we're passing down the user_namespace argument from the VFS methods to the relevant helpers. Let's create simple example where we idmap an ext4 filesystem: root@f2-vm:~# truncate -s 5G ext4.img root@f2-vm:~# mkfs.ext4 ./ext4.img mke2fs 1.45.5 (07-Jan-2020) Discarding device blocks: done Creating filesystem with 1310720 4k blocks and 327680 inodes Filesystem UUID: 3fd91794-c6ca-4b0f-9964-289a000919cf Superblock backups stored on blocks: 32768, 98304, 163840, 229376, 294912, 819200, 884736 Allocating group tables: done Writing inode tables: done Creating journal (16384 blocks): done Writing superblocks and filesystem accounting information: done root@f2-vm:~# losetup -f --show ./ext4.img /dev/loop0 root@f2-vm:~# mount /dev/loop0 /mnt root@f2-vm:~# ls -al /mnt/ total 24 drwxr-xr-x 3 root root 4096 Oct 28 13:34 . drwxr-xr-x 30 root root 4096 Oct 28 13:22 .. drwx------ 2 root root 16384 Oct 28 13:34 lost+found # Let's create an idmapped mount at /idmapped1 where we map uid and gid # 0 to uid and gid 1000 root@f2-vm:/# ./mount-idmapped --map-mount b:0:1000:1 /mnt/ /idmapped1/ root@f2-vm:/# ls -al /idmapped1/ total 24 drwxr-xr-x 3 ubuntu ubuntu 4096 Oct 28 13:34 . drwxr-xr-x 30 root root 4096 Oct 28 13:22 .. drwx------ 2 ubuntu ubuntu 16384 Oct 28 13:34 lost+found # Let's create an idmapped mount at /idmapped2 where we map uid and gid # 0 to uid and gid 2000 root@f2-vm:/# ./mount-idmapped --map-mount b:0:2000:1 /mnt/ /idmapped2/ root@f2-vm:/# ls -al /idmapped2/ total 24 drwxr-xr-x 3 2000 2000 4096 Oct 28 13:34 . drwxr-xr-x 31 root root 4096 Oct 28 13:39 .. drwx------ 2 2000 2000 16384 Oct 28 13:34 lost+found Let's create another example where we idmap the rootfs filesystem without a mapping for uid 0 and gid 0: # Create an idmapped mount of for a full POSIX range of rootfs under # /mnt but without a mapping for uid 0 to reduce attack surface root@f2-vm:/# ./mount-idmapped --map-mount b:1:1:65536 / /mnt/ # Since we don't have a mapping for uid and gid 0 all files owned by # uid and gid 0 should show up as uid and gid 65534: root@f2-vm:/# ls -al /mnt/ total 664 drwxr-xr-x 31 nobody nogroup 4096 Oct 28 13:39 . drwxr-xr-x 31 root root 4096 Oct 28 13:39 .. lrwxrwxrwx 1 nobody nogroup 7 Aug 25 07:44 bin -> usr/bin drwxr-xr-x 4 nobody nogroup 4096 Oct 28 13:17 boot drwxr-xr-x 2 nobody nogroup 4096 Aug 25 07:48 dev drwxr-xr-x 81 nobody nogroup 4096 Oct 28 04:00 etc drwxr-xr-x 4 nobody nogroup 4096 Oct 28 04:00 home lrwxrwxrwx 1 nobody nogroup 7 Aug 25 07:44 lib -> usr/lib lrwxrwxrwx 1 nobody nogroup 9 Aug 25 07:44 lib32 -> usr/lib32 lrwxrwxrwx 1 nobody nogroup 9 Aug 25 07:44 lib64 -> usr/lib64 lrwxrwxrwx 1 nobody nogroup 10 Aug 25 07:44 libx32 -> usr/libx32 drwx------ 2 nobody nogroup 16384 Aug 25 07:47 lost+found drwxr-xr-x 2 nobody nogroup 4096 Aug 25 07:44 media drwxr-xr-x 31 nobody nogroup 4096 Oct 28 13:39 mnt drwxr-xr-x 2 nobody nogroup 4096 Aug 25 07:44 opt drwxr-xr-x 2 nobody nogroup 4096 Apr 15 2020 proc drwx--x--x 6 nobody nogroup 4096 Oct 28 13:34 root drwxr-xr-x 2 nobody nogroup 4096 Aug 25 07:46 run lrwxrwxrwx 1 nobody nogroup 8 Aug 25 07:44 sbin -> usr/sbin drwxr-xr-x 2 nobody nogroup 4096 Aug 25 07:44 srv drwxr-xr-x 2 nobody nogroup 4096 Apr 15 2020 sys drwxrwxrwt 10 nobody nogroup 4096 Oct 28 13:19 tmp drwxr-xr-x 14 nobody nogroup 4096 Oct 20 13:00 usr drwxr-xr-x 12 nobody nogroup 4096 Aug 25 07:45 var # Since we do have a mapping for uid and gid 1000 all files owned by # uid and gid 1000 should simply show up as uid and gid 1000: root@f2-vm:/# ls -al /mnt/home/ubuntu/ total 40 drwxr-xr-x 3 ubuntu ubuntu 4096 Oct 28 00:43 . drwxr-xr-x 4 nobody nogroup 4096 Oct 28 04:00 .. -rw------- 1 ubuntu ubuntu 2936 Oct 28 12:26 .bash_history -rw-r--r-- 1 ubuntu ubuntu 220 Feb 25 2020 .bash_logout -rw-r--r-- 1 ubuntu ubuntu 3771 Feb 25 2020 .bashrc -rw-r--r-- 1 ubuntu ubuntu 807 Feb 25 2020 .profile -rw-r--r-- 1 ubuntu ubuntu 0 Oct 16 16:11 .sudo_as_admin_successful -rw------- 1 ubuntu ubuntu 1144 Oct 28 00:43 .viminfo Link: https://lore.kernel.org/r/20210121131959.646623-39-christian.brauner@ubuntu.com Cc: Christoph Hellwig <hch@lst.de> Cc: David Howells <dhowells@redhat.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: linux-ext4@vger.kernel.org Cc: linux-fsdevel@vger.kernel.org Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
2021-01-21 21:19:57 +08:00
extern struct inode *__ext4_new_inode(struct user_namespace *, handle_t *,
struct inode *, umode_t,
const struct qstr *qstr, __u32 goal,
ext4: do not set posix acls on xattr inodes We don't need acls on xattr inodes because they are not directly accessible from user mode. Besides lockdep complains about recursive locking of xattr_sem as seen below. ============================================= [ INFO: possible recursive locking detected ] 4.11.0-rc8+ #402 Not tainted --------------------------------------------- python/1894 is trying to acquire lock: (&ei->xattr_sem){++++..}, at: [<ffffffff804878a6>] ext4_xattr_get+0x66/0x270 but task is already holding lock: (&ei->xattr_sem){++++..}, at: [<ffffffff80489500>] ext4_xattr_set_handle+0xa0/0x5d0 other info that might help us debug this: Possible unsafe locking scenario: CPU0 ---- lock(&ei->xattr_sem); lock(&ei->xattr_sem); *** DEADLOCK *** May be due to missing lock nesting notation 3 locks held by python/1894: #0: (sb_writers#10){.+.+.+}, at: [<ffffffff803d829f>] mnt_want_write+0x1f/0x50 #1: (&sb->s_type->i_mutex_key#15){+.+...}, at: [<ffffffff803dda27>] vfs_setxattr+0x57/0xb0 #2: (&ei->xattr_sem){++++..}, at: [<ffffffff80489500>] ext4_xattr_set_handle+0xa0/0x5d0 stack backtrace: CPU: 0 PID: 1894 Comm: python Not tainted 4.11.0-rc8+ #402 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011 Call Trace: dump_stack+0x67/0x99 __lock_acquire+0x5f3/0x1830 lock_acquire+0xb5/0x1d0 down_read+0x2f/0x60 ext4_xattr_get+0x66/0x270 ext4_get_acl+0x43/0x1e0 get_acl+0x72/0xf0 posix_acl_create+0x5e/0x170 ext4_init_acl+0x21/0xc0 __ext4_new_inode+0xffd/0x16b0 ext4_xattr_set_entry+0x5ea/0xb70 ext4_xattr_block_set+0x1b5/0x970 ext4_xattr_set_handle+0x351/0x5d0 ext4_xattr_set+0x124/0x180 ext4_xattr_user_set+0x34/0x40 __vfs_setxattr+0x66/0x80 __vfs_setxattr_noperm+0x69/0x1c0 vfs_setxattr+0xa2/0xb0 setxattr+0x129/0x160 path_setxattr+0x87/0xb0 SyS_setxattr+0xf/0x20 entry_SYSCALL_64_fastpath+0x18/0xad Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2017-06-22 09:21:39 +08:00
uid_t *owner, __u32 i_flags,
int handle_type, unsigned int line_no,
int nblocks);
ext4: support idmapped mounts Enable idmapped mounts for ext4. All dedicated helpers we need for this exist. So this basically just means we're passing down the user_namespace argument from the VFS methods to the relevant helpers. Let's create simple example where we idmap an ext4 filesystem: root@f2-vm:~# truncate -s 5G ext4.img root@f2-vm:~# mkfs.ext4 ./ext4.img mke2fs 1.45.5 (07-Jan-2020) Discarding device blocks: done Creating filesystem with 1310720 4k blocks and 327680 inodes Filesystem UUID: 3fd91794-c6ca-4b0f-9964-289a000919cf Superblock backups stored on blocks: 32768, 98304, 163840, 229376, 294912, 819200, 884736 Allocating group tables: done Writing inode tables: done Creating journal (16384 blocks): done Writing superblocks and filesystem accounting information: done root@f2-vm:~# losetup -f --show ./ext4.img /dev/loop0 root@f2-vm:~# mount /dev/loop0 /mnt root@f2-vm:~# ls -al /mnt/ total 24 drwxr-xr-x 3 root root 4096 Oct 28 13:34 . drwxr-xr-x 30 root root 4096 Oct 28 13:22 .. drwx------ 2 root root 16384 Oct 28 13:34 lost+found # Let's create an idmapped mount at /idmapped1 where we map uid and gid # 0 to uid and gid 1000 root@f2-vm:/# ./mount-idmapped --map-mount b:0:1000:1 /mnt/ /idmapped1/ root@f2-vm:/# ls -al /idmapped1/ total 24 drwxr-xr-x 3 ubuntu ubuntu 4096 Oct 28 13:34 . drwxr-xr-x 30 root root 4096 Oct 28 13:22 .. drwx------ 2 ubuntu ubuntu 16384 Oct 28 13:34 lost+found # Let's create an idmapped mount at /idmapped2 where we map uid and gid # 0 to uid and gid 2000 root@f2-vm:/# ./mount-idmapped --map-mount b:0:2000:1 /mnt/ /idmapped2/ root@f2-vm:/# ls -al /idmapped2/ total 24 drwxr-xr-x 3 2000 2000 4096 Oct 28 13:34 . drwxr-xr-x 31 root root 4096 Oct 28 13:39 .. drwx------ 2 2000 2000 16384 Oct 28 13:34 lost+found Let's create another example where we idmap the rootfs filesystem without a mapping for uid 0 and gid 0: # Create an idmapped mount of for a full POSIX range of rootfs under # /mnt but without a mapping for uid 0 to reduce attack surface root@f2-vm:/# ./mount-idmapped --map-mount b:1:1:65536 / /mnt/ # Since we don't have a mapping for uid and gid 0 all files owned by # uid and gid 0 should show up as uid and gid 65534: root@f2-vm:/# ls -al /mnt/ total 664 drwxr-xr-x 31 nobody nogroup 4096 Oct 28 13:39 . drwxr-xr-x 31 root root 4096 Oct 28 13:39 .. lrwxrwxrwx 1 nobody nogroup 7 Aug 25 07:44 bin -> usr/bin drwxr-xr-x 4 nobody nogroup 4096 Oct 28 13:17 boot drwxr-xr-x 2 nobody nogroup 4096 Aug 25 07:48 dev drwxr-xr-x 81 nobody nogroup 4096 Oct 28 04:00 etc drwxr-xr-x 4 nobody nogroup 4096 Oct 28 04:00 home lrwxrwxrwx 1 nobody nogroup 7 Aug 25 07:44 lib -> usr/lib lrwxrwxrwx 1 nobody nogroup 9 Aug 25 07:44 lib32 -> usr/lib32 lrwxrwxrwx 1 nobody nogroup 9 Aug 25 07:44 lib64 -> usr/lib64 lrwxrwxrwx 1 nobody nogroup 10 Aug 25 07:44 libx32 -> usr/libx32 drwx------ 2 nobody nogroup 16384 Aug 25 07:47 lost+found drwxr-xr-x 2 nobody nogroup 4096 Aug 25 07:44 media drwxr-xr-x 31 nobody nogroup 4096 Oct 28 13:39 mnt drwxr-xr-x 2 nobody nogroup 4096 Aug 25 07:44 opt drwxr-xr-x 2 nobody nogroup 4096 Apr 15 2020 proc drwx--x--x 6 nobody nogroup 4096 Oct 28 13:34 root drwxr-xr-x 2 nobody nogroup 4096 Aug 25 07:46 run lrwxrwxrwx 1 nobody nogroup 8 Aug 25 07:44 sbin -> usr/sbin drwxr-xr-x 2 nobody nogroup 4096 Aug 25 07:44 srv drwxr-xr-x 2 nobody nogroup 4096 Apr 15 2020 sys drwxrwxrwt 10 nobody nogroup 4096 Oct 28 13:19 tmp drwxr-xr-x 14 nobody nogroup 4096 Oct 20 13:00 usr drwxr-xr-x 12 nobody nogroup 4096 Aug 25 07:45 var # Since we do have a mapping for uid and gid 1000 all files owned by # uid and gid 1000 should simply show up as uid and gid 1000: root@f2-vm:/# ls -al /mnt/home/ubuntu/ total 40 drwxr-xr-x 3 ubuntu ubuntu 4096 Oct 28 00:43 . drwxr-xr-x 4 nobody nogroup 4096 Oct 28 04:00 .. -rw------- 1 ubuntu ubuntu 2936 Oct 28 12:26 .bash_history -rw-r--r-- 1 ubuntu ubuntu 220 Feb 25 2020 .bash_logout -rw-r--r-- 1 ubuntu ubuntu 3771 Feb 25 2020 .bashrc -rw-r--r-- 1 ubuntu ubuntu 807 Feb 25 2020 .profile -rw-r--r-- 1 ubuntu ubuntu 0 Oct 16 16:11 .sudo_as_admin_successful -rw------- 1 ubuntu ubuntu 1144 Oct 28 00:43 .viminfo Link: https://lore.kernel.org/r/20210121131959.646623-39-christian.brauner@ubuntu.com Cc: Christoph Hellwig <hch@lst.de> Cc: David Howells <dhowells@redhat.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: linux-ext4@vger.kernel.org Cc: linux-fsdevel@vger.kernel.org Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
2021-01-21 21:19:57 +08:00
#define ext4_new_inode(handle, dir, mode, qstr, goal, owner, i_flags) \
__ext4_new_inode(&init_user_ns, (handle), (dir), (mode), (qstr), \
(goal), (owner), i_flags, 0, 0, 0)
#define ext4_new_inode_start_handle(mnt_userns, dir, mode, qstr, goal, owner, \
type, nblocks) \
ext4: support idmapped mounts Enable idmapped mounts for ext4. All dedicated helpers we need for this exist. So this basically just means we're passing down the user_namespace argument from the VFS methods to the relevant helpers. Let's create simple example where we idmap an ext4 filesystem: root@f2-vm:~# truncate -s 5G ext4.img root@f2-vm:~# mkfs.ext4 ./ext4.img mke2fs 1.45.5 (07-Jan-2020) Discarding device blocks: done Creating filesystem with 1310720 4k blocks and 327680 inodes Filesystem UUID: 3fd91794-c6ca-4b0f-9964-289a000919cf Superblock backups stored on blocks: 32768, 98304, 163840, 229376, 294912, 819200, 884736 Allocating group tables: done Writing inode tables: done Creating journal (16384 blocks): done Writing superblocks and filesystem accounting information: done root@f2-vm:~# losetup -f --show ./ext4.img /dev/loop0 root@f2-vm:~# mount /dev/loop0 /mnt root@f2-vm:~# ls -al /mnt/ total 24 drwxr-xr-x 3 root root 4096 Oct 28 13:34 . drwxr-xr-x 30 root root 4096 Oct 28 13:22 .. drwx------ 2 root root 16384 Oct 28 13:34 lost+found # Let's create an idmapped mount at /idmapped1 where we map uid and gid # 0 to uid and gid 1000 root@f2-vm:/# ./mount-idmapped --map-mount b:0:1000:1 /mnt/ /idmapped1/ root@f2-vm:/# ls -al /idmapped1/ total 24 drwxr-xr-x 3 ubuntu ubuntu 4096 Oct 28 13:34 . drwxr-xr-x 30 root root 4096 Oct 28 13:22 .. drwx------ 2 ubuntu ubuntu 16384 Oct 28 13:34 lost+found # Let's create an idmapped mount at /idmapped2 where we map uid and gid # 0 to uid and gid 2000 root@f2-vm:/# ./mount-idmapped --map-mount b:0:2000:1 /mnt/ /idmapped2/ root@f2-vm:/# ls -al /idmapped2/ total 24 drwxr-xr-x 3 2000 2000 4096 Oct 28 13:34 . drwxr-xr-x 31 root root 4096 Oct 28 13:39 .. drwx------ 2 2000 2000 16384 Oct 28 13:34 lost+found Let's create another example where we idmap the rootfs filesystem without a mapping for uid 0 and gid 0: # Create an idmapped mount of for a full POSIX range of rootfs under # /mnt but without a mapping for uid 0 to reduce attack surface root@f2-vm:/# ./mount-idmapped --map-mount b:1:1:65536 / /mnt/ # Since we don't have a mapping for uid and gid 0 all files owned by # uid and gid 0 should show up as uid and gid 65534: root@f2-vm:/# ls -al /mnt/ total 664 drwxr-xr-x 31 nobody nogroup 4096 Oct 28 13:39 . drwxr-xr-x 31 root root 4096 Oct 28 13:39 .. lrwxrwxrwx 1 nobody nogroup 7 Aug 25 07:44 bin -> usr/bin drwxr-xr-x 4 nobody nogroup 4096 Oct 28 13:17 boot drwxr-xr-x 2 nobody nogroup 4096 Aug 25 07:48 dev drwxr-xr-x 81 nobody nogroup 4096 Oct 28 04:00 etc drwxr-xr-x 4 nobody nogroup 4096 Oct 28 04:00 home lrwxrwxrwx 1 nobody nogroup 7 Aug 25 07:44 lib -> usr/lib lrwxrwxrwx 1 nobody nogroup 9 Aug 25 07:44 lib32 -> usr/lib32 lrwxrwxrwx 1 nobody nogroup 9 Aug 25 07:44 lib64 -> usr/lib64 lrwxrwxrwx 1 nobody nogroup 10 Aug 25 07:44 libx32 -> usr/libx32 drwx------ 2 nobody nogroup 16384 Aug 25 07:47 lost+found drwxr-xr-x 2 nobody nogroup 4096 Aug 25 07:44 media drwxr-xr-x 31 nobody nogroup 4096 Oct 28 13:39 mnt drwxr-xr-x 2 nobody nogroup 4096 Aug 25 07:44 opt drwxr-xr-x 2 nobody nogroup 4096 Apr 15 2020 proc drwx--x--x 6 nobody nogroup 4096 Oct 28 13:34 root drwxr-xr-x 2 nobody nogroup 4096 Aug 25 07:46 run lrwxrwxrwx 1 nobody nogroup 8 Aug 25 07:44 sbin -> usr/sbin drwxr-xr-x 2 nobody nogroup 4096 Aug 25 07:44 srv drwxr-xr-x 2 nobody nogroup 4096 Apr 15 2020 sys drwxrwxrwt 10 nobody nogroup 4096 Oct 28 13:19 tmp drwxr-xr-x 14 nobody nogroup 4096 Oct 20 13:00 usr drwxr-xr-x 12 nobody nogroup 4096 Aug 25 07:45 var # Since we do have a mapping for uid and gid 1000 all files owned by # uid and gid 1000 should simply show up as uid and gid 1000: root@f2-vm:/# ls -al /mnt/home/ubuntu/ total 40 drwxr-xr-x 3 ubuntu ubuntu 4096 Oct 28 00:43 . drwxr-xr-x 4 nobody nogroup 4096 Oct 28 04:00 .. -rw------- 1 ubuntu ubuntu 2936 Oct 28 12:26 .bash_history -rw-r--r-- 1 ubuntu ubuntu 220 Feb 25 2020 .bash_logout -rw-r--r-- 1 ubuntu ubuntu 3771 Feb 25 2020 .bashrc -rw-r--r-- 1 ubuntu ubuntu 807 Feb 25 2020 .profile -rw-r--r-- 1 ubuntu ubuntu 0 Oct 16 16:11 .sudo_as_admin_successful -rw------- 1 ubuntu ubuntu 1144 Oct 28 00:43 .viminfo Link: https://lore.kernel.org/r/20210121131959.646623-39-christian.brauner@ubuntu.com Cc: Christoph Hellwig <hch@lst.de> Cc: David Howells <dhowells@redhat.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: linux-ext4@vger.kernel.org Cc: linux-fsdevel@vger.kernel.org Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
2021-01-21 21:19:57 +08:00
__ext4_new_inode((mnt_userns), NULL, (dir), (mode), (qstr), (goal), (owner), \
ext4: do not set posix acls on xattr inodes We don't need acls on xattr inodes because they are not directly accessible from user mode. Besides lockdep complains about recursive locking of xattr_sem as seen below. ============================================= [ INFO: possible recursive locking detected ] 4.11.0-rc8+ #402 Not tainted --------------------------------------------- python/1894 is trying to acquire lock: (&ei->xattr_sem){++++..}, at: [<ffffffff804878a6>] ext4_xattr_get+0x66/0x270 but task is already holding lock: (&ei->xattr_sem){++++..}, at: [<ffffffff80489500>] ext4_xattr_set_handle+0xa0/0x5d0 other info that might help us debug this: Possible unsafe locking scenario: CPU0 ---- lock(&ei->xattr_sem); lock(&ei->xattr_sem); *** DEADLOCK *** May be due to missing lock nesting notation 3 locks held by python/1894: #0: (sb_writers#10){.+.+.+}, at: [<ffffffff803d829f>] mnt_want_write+0x1f/0x50 #1: (&sb->s_type->i_mutex_key#15){+.+...}, at: [<ffffffff803dda27>] vfs_setxattr+0x57/0xb0 #2: (&ei->xattr_sem){++++..}, at: [<ffffffff80489500>] ext4_xattr_set_handle+0xa0/0x5d0 stack backtrace: CPU: 0 PID: 1894 Comm: python Not tainted 4.11.0-rc8+ #402 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011 Call Trace: dump_stack+0x67/0x99 __lock_acquire+0x5f3/0x1830 lock_acquire+0xb5/0x1d0 down_read+0x2f/0x60 ext4_xattr_get+0x66/0x270 ext4_get_acl+0x43/0x1e0 get_acl+0x72/0xf0 posix_acl_create+0x5e/0x170 ext4_init_acl+0x21/0xc0 __ext4_new_inode+0xffd/0x16b0 ext4_xattr_set_entry+0x5ea/0xb70 ext4_xattr_block_set+0x1b5/0x970 ext4_xattr_set_handle+0x351/0x5d0 ext4_xattr_set+0x124/0x180 ext4_xattr_user_set+0x34/0x40 __vfs_setxattr+0x66/0x80 __vfs_setxattr_noperm+0x69/0x1c0 vfs_setxattr+0xa2/0xb0 setxattr+0x129/0x160 path_setxattr+0x87/0xb0 SyS_setxattr+0xf/0x20 entry_SYSCALL_64_fastpath+0x18/0xad Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2017-06-22 09:21:39 +08:00
0, (type), __LINE__, (nblocks))
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 09:30:05 +08:00
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);
/* fast_commit.c */
int ext4_fc_info_show(struct seq_file *seq, void *v);
void ext4_fc_init(struct super_block *sb, journal_t *journal);
void ext4_fc_init_inode(struct inode *inode);
void ext4_fc_track_range(handle_t *handle, struct inode *inode, ext4_lblk_t start,
ext4_lblk_t end);
void __ext4_fc_track_unlink(handle_t *handle, struct inode *inode,
struct dentry *dentry);
void __ext4_fc_track_link(handle_t *handle, struct inode *inode,
struct dentry *dentry);
void ext4_fc_track_unlink(handle_t *handle, struct dentry *dentry);
void ext4_fc_track_link(handle_t *handle, struct dentry *dentry);
ext4: fix rename whiteout with fast commit This patch adds rename whiteout support in fast commits. Note that the whiteout object that gets created is actually char device. Which imples, the function ext4_inode_journal_mode(struct inode *inode) would return "JOURNAL_DATA" for this inode. This has a consequence in fast commit code that it will make creation of the whiteout object a fast-commit ineligible behavior and thus will fall back to full commits. With this patch, this can be observed by running fast commits with rename whiteout and seeing the stats generated by ext4_fc_stats tracepoint as follows: ext4_fc_stats: dev 254:32 fc ineligible reasons: XATTR:0, CROSS_RENAME:0, JOURNAL_FLAG_CHANGE:0, NO_MEM:0, SWAP_BOOT:0, RESIZE:0, RENAME_DIR:0, FALLOC_RANGE:0, INODE_JOURNAL_DATA:16; num_commits:6, ineligible: 6, numblks: 3 So in short, this patch guarantees that in case of rename whiteout, we fall back to full commits. Amir mentioned that instead of creating a new whiteout object for every rename, we can create a static whiteout object with irrelevant nlink. That will make fast commits to not fall back to full commit. But until this happens, this patch will ensure correctness by falling back to full commits. Fixes: 8016e29f4362 ("ext4: fast commit recovery path") Cc: stable@kernel.org Signed-off-by: Harshad Shirwadkar <harshadshirwadkar@gmail.com> Link: https://lore.kernel.org/r/20210316221921.1124955-1-harshadshirwadkar@gmail.com Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2021-03-17 06:19:21 +08:00
void __ext4_fc_track_create(handle_t *handle, struct inode *inode,
struct dentry *dentry);
void ext4_fc_track_create(handle_t *handle, struct dentry *dentry);
void ext4_fc_track_inode(handle_t *handle, struct inode *inode);
void ext4_fc_mark_ineligible(struct super_block *sb, int reason, handle_t *handle);
void ext4_fc_start_update(struct inode *inode);
void ext4_fc_stop_update(struct inode *inode);
void ext4_fc_del(struct inode *inode);
bool ext4_fc_replay_check_excluded(struct super_block *sb, ext4_fsblk_t block);
void ext4_fc_replay_cleanup(struct super_block *sb);
int ext4_fc_commit(journal_t *journal, tid_t commit_tid);
int __init ext4_fc_init_dentry_cache(void);
void ext4_fc_destroy_dentry_cache(void);
int ext4_fc_record_regions(struct super_block *sb, int ino,
ext4_lblk_t lblk, ext4_fsblk_t pblk,
int len, int replay);
/* mballoc.c */
extern const struct seq_operations ext4_mb_seq_groups_ops;
extern const struct seq_operations ext4_mb_seq_structs_summary_ops;
extern long ext4_mb_stats;
extern long ext4_mb_max_to_scan;
extern int ext4_seq_mb_stats_show(struct seq_file *seq, void *offset);
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 *, unsigned int);
extern int __init ext4_init_mballoc(void);
extern void ext4_exit_mballoc(void);
extern ext4_group_t ext4_mb_prefetch(struct super_block *sb,
ext4_group_t group,
unsigned int nr, int *cnt);
extern void ext4_mb_prefetch_fini(struct super_block *sb, ext4_group_t group,
unsigned int nr);
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_alloc_groupinfo(struct super_block *sb,
ext4_group_t ngroups);
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 *);
extern void ext4_process_freed_data(struct super_block *sb, tid_t commit_tid);
extern void ext4_mb_mark_bb(struct super_block *sb, ext4_fsblk_t block,
int len, int state);
/* inode.c */
void ext4_inode_csum_set(struct inode *inode, struct ext4_inode *raw,
struct ext4_inode_info *ei);
int ext4_inode_is_fast_symlink(struct inode *inode);
struct buffer_head *ext4_getblk(handle_t *, struct inode *, ext4_lblk_t, int);
struct buffer_head *ext4_bread(handle_t *, struct inode *, ext4_lblk_t, int);
int ext4_bread_batch(struct inode *inode, ext4_lblk_t block, int bh_count,
bool wait, struct buffer_head **bhs);
int ext4_get_block_unwritten(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create);
int ext4_get_block(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create);
int ext4_da_get_block_prep(struct inode *inode, sector_t iblock,
struct buffer_head *bh, int create);
int ext4_walk_page_buffers(handle_t *handle,
struct inode *inode,
struct buffer_head *head,
unsigned from,
unsigned to,
int *partial,
int (*fn)(handle_t *handle, struct inode *inode,
struct buffer_head *bh));
int do_journal_get_write_access(handle_t *handle, struct inode *inode,
struct buffer_head *bh);
#define FALL_BACK_TO_NONDELALLOC 1
#define CONVERT_INLINE_DATA 2
typedef enum {
EXT4_IGET_NORMAL = 0,
EXT4_IGET_SPECIAL = 0x0001, /* OK to iget a system inode */
EXT4_IGET_HANDLE = 0x0002 /* Inode # is from a handle */
} ext4_iget_flags;
extern struct inode *__ext4_iget(struct super_block *sb, unsigned long ino,
ext4_iget_flags flags, const char *function,
unsigned int line);
#define ext4_iget(sb, ino, flags) \
__ext4_iget((sb), (ino), (flags), __func__, __LINE__)
extern int ext4_write_inode(struct inode *, struct writeback_control *);
extern int ext4_setattr(struct user_namespace *, struct dentry *,
struct iattr *);
extern int ext4_getattr(struct user_namespace *, const struct path *,
struct kstat *, u32, unsigned int);
extern void ext4_evict_inode(struct inode *);
extern void ext4_clear_inode(struct inode *);
extern int ext4_file_getattr(struct user_namespace *, const struct path *,
struct kstat *, u32, unsigned int);
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_get_fc_inode_loc(struct super_block *sb, unsigned long ino,
struct ext4_iloc *iloc);
extern int ext4_inode_attach_jinode(struct inode *inode);
extern int ext4_can_truncate(struct inode *inode);
extern int ext4_truncate(struct inode *);
extern int ext4_break_layouts(struct inode *);
extern int ext4_punch_hole(struct file *file, loff_t offset, loff_t length);
extern void ext4_set_inode_flags(struct inode *, bool init);
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);
extern int ext4_zero_partial_blocks(handle_t *handle, struct inode *inode,
loff_t lstart, loff_t lend);
extern vm_fault_t ext4_page_mkwrite(struct vm_fault *vmf);
extern qsize_t *ext4_get_reserved_space(struct inode *inode);
extern int ext4_get_projid(struct inode *inode, kprojid_t *projid);
extern void ext4_da_release_space(struct inode *inode, int to_free);
extern void ext4_da_update_reserve_space(struct inode *inode,
int used, int quota_claim);
extern int ext4_issue_zeroout(struct inode *inode, ext4_lblk_t lblk,
ext4_fsblk_t pblk, ext4_lblk_t len);
/* indirect.c */
extern int ext4_ind_map_blocks(handle_t *handle, struct inode *inode,
struct ext4_map_blocks *map, int flags);
extern int ext4_ind_trans_blocks(struct inode *inode, int nrblocks);
extern void ext4_ind_truncate(handle_t *, struct inode *inode);
extern int ext4_ind_remove_space(handle_t *handle, struct inode *inode,
ext4_lblk_t start, ext4_lblk_t end);
/* ioctl.c */
extern long ext4_ioctl(struct file *, unsigned int, unsigned long);
extern long ext4_compat_ioctl(struct file *, unsigned int, unsigned long);
int ext4_fileattr_set(struct user_namespace *mnt_userns,
struct dentry *dentry, struct fileattr *fa);
int ext4_fileattr_get(struct dentry *dentry, struct fileattr *fa);
extern void ext4_reset_inode_seed(struct inode *inode);
int ext4_update_overhead(struct super_block *sb);
/* migrate.c */
extern int ext4_ext_migrate(struct inode *);
extern int ext4_ind_migrate(struct inode *inode);
/* namei.c */
extern int ext4_init_new_dir(handle_t *handle, struct inode *dir,
struct inode *inode);
extern int ext4_dirblock_csum_verify(struct inode *inode,
struct buffer_head *bh);
extern int ext4_htree_fill_tree(struct file *dir_file, __u32 start_hash,
__u32 start_minor_hash, __u32 *next_hash);
extern int ext4_search_dir(struct buffer_head *bh,
char *search_buf,
int buf_size,
struct inode *dir,
struct ext4_filename *fname,
unsigned int offset,
struct ext4_dir_entry_2 **res_dir);
extern int ext4_generic_delete_entry(struct inode *dir,
struct ext4_dir_entry_2 *de_del,
struct buffer_head *bh,
void *entry_buf,
int buf_size,
int csum_size);
extern bool ext4_empty_dir(struct inode *inode);
/* resize.c */
extern void ext4_kvfree_array_rcu(void *to_free);
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);
extern unsigned int ext4_list_backups(struct super_block *sb,
unsigned int *three, unsigned int *five,
unsigned int *seven);
/* super.c */
extern struct buffer_head *ext4_sb_bread(struct super_block *sb,
sector_t block, int op_flags);
extern struct buffer_head *ext4_sb_bread_unmovable(struct super_block *sb,
sector_t block);
extern void ext4_read_bh_nowait(struct buffer_head *bh, int op_flags,
bh_end_io_t *end_io);
extern int ext4_read_bh(struct buffer_head *bh, int op_flags,
bh_end_io_t *end_io);
extern int ext4_read_bh_lock(struct buffer_head *bh, int op_flags, bool wait);
extern void ext4_sb_breadahead_unmovable(struct super_block *sb, sector_t block);
extern int ext4_seq_options_show(struct seq_file *seq, void *offset);
extern int ext4_calculate_overhead(struct super_block *sb);
extern __le32 ext4_superblock_csum(struct super_block *sb,
struct ext4_super_block *es);
extern void ext4_superblock_csum_set(struct super_block *sb);
extern int ext4_alloc_flex_bg_array(struct super_block *sb,
ext4_group_t ngroup);
extern const char *ext4_decode_error(struct super_block *sb, int errno,
char nbuf[16]);
extern void ext4_mark_group_bitmap_corrupted(struct super_block *sb,
ext4_group_t block_group,
unsigned int flags);
extern __printf(7, 8)
void __ext4_error(struct super_block *, const char *, unsigned int, bool,
int, __u64, const char *, ...);
extern __printf(6, 7)
void __ext4_error_inode(struct inode *, const char *, unsigned int,
ext4_fsblk_t, int, 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_warning(struct super_block *, const char *, unsigned int,
const char *, ...);
extern __printf(4, 5)
void __ext4_warning_inode(const struct inode *inode, const char *function,
unsigned int line, const char *fmt, ...);
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 *);
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_ERROR_INODE(inode, fmt, a...) \
ext4_error_inode((inode), __func__, __LINE__, 0, (fmt), ## a)
#define EXT4_ERROR_INODE_ERR(inode, err, fmt, a...) \
__ext4_error_inode((inode), __func__, __LINE__, 0, (err), (fmt), ## a)
#define ext4_error_inode_block(inode, block, err, fmt, a...) \
__ext4_error_inode((inode), __func__, __LINE__, (block), (err), \
(fmt), ## a)
#define EXT4_ERROR_FILE(file, block, fmt, a...) \
ext4_error_file((file), __func__, __LINE__, (block), (fmt), ## a)
#define ext4_abort(sb, err, fmt, a...) \
__ext4_error((sb), __func__, __LINE__, true, (err), 0, (fmt), ## a)
#ifdef CONFIG_PRINTK
#define ext4_error_inode(inode, func, line, block, fmt, ...) \
__ext4_error_inode(inode, func, line, block, 0, fmt, ##__VA_ARGS__)
#define ext4_error_inode_err(inode, func, line, block, err, fmt, ...) \
__ext4_error_inode((inode), (func), (line), (block), \
(err), (fmt), ##__VA_ARGS__)
#define ext4_error_file(file, func, line, block, fmt, ...) \
__ext4_error_file(file, func, line, block, fmt, ##__VA_ARGS__)
#define ext4_error(sb, fmt, ...) \
__ext4_error((sb), __func__, __LINE__, false, 0, 0, (fmt), \
##__VA_ARGS__)
#define ext4_error_err(sb, err, fmt, ...) \
__ext4_error((sb), __func__, __LINE__, false, (err), 0, (fmt), \
##__VA_ARGS__)
#define ext4_warning(sb, fmt, ...) \
__ext4_warning(sb, __func__, __LINE__, fmt, ##__VA_ARGS__)
#define ext4_warning_inode(inode, fmt, ...) \
__ext4_warning_inode(inode, __func__, __LINE__, fmt, ##__VA_ARGS__)
#define ext4_msg(sb, level, fmt, ...) \
__ext4_msg(sb, level, fmt, ##__VA_ARGS__)
#define dump_mmp_msg(sb, mmp, msg) \
__dump_mmp_msg(sb, mmp, __func__, __LINE__, msg)
#define ext4_grp_locked_error(sb, grp, ino, block, fmt, ...) \
__ext4_grp_locked_error(__func__, __LINE__, sb, grp, ino, block, \
fmt, ##__VA_ARGS__)
#else
#define ext4_error_inode(inode, func, line, block, fmt, ...) \
do { \
no_printk(fmt, ##__VA_ARGS__); \
__ext4_error_inode(inode, "", 0, block, 0, " "); \
} while (0)
#define ext4_error_inode_err(inode, func, line, block, err, fmt, ...) \
do { \
no_printk(fmt, ##__VA_ARGS__); \
__ext4_error_inode(inode, "", 0, block, err, " "); \
} while (0)
#define ext4_error_file(file, func, line, block, fmt, ...) \
do { \
no_printk(fmt, ##__VA_ARGS__); \
__ext4_error_file(file, "", 0, block, " "); \
} while (0)
#define ext4_error(sb, fmt, ...) \
do { \
no_printk(fmt, ##__VA_ARGS__); \
__ext4_error(sb, "", 0, false, 0, 0, " "); \
} while (0)
#define ext4_error_err(sb, err, fmt, ...) \
do { \
no_printk(fmt, ##__VA_ARGS__); \
__ext4_error(sb, "", 0, false, err, 0, " "); \
} while (0)
#define ext4_warning(sb, fmt, ...) \
do { \
no_printk(fmt, ##__VA_ARGS__); \
__ext4_warning(sb, "", 0, " "); \
} while (0)
#define ext4_warning_inode(inode, fmt, ...) \
do { \
no_printk(fmt, ##__VA_ARGS__); \
__ext4_warning_inode(inode, "", 0, " "); \
} while (0)
#define ext4_msg(sb, level, fmt, ...) \
do { \
no_printk(fmt, ##__VA_ARGS__); \
__ext4_msg(sb, "", " "); \
} while (0)
#define dump_mmp_msg(sb, mmp, msg) \
__dump_mmp_msg(sb, mmp, "", 0, "")
#define ext4_grp_locked_error(sb, grp, ino, block, fmt, ...) \
do { \
no_printk(fmt, ##__VA_ARGS__); \
__ext4_grp_locked_error("", 0, sb, grp, ino, block, " "); \
} while (0)
#endif
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);
extern int ext4_register_li_request(struct super_block *sb,
ext4_group_t first_not_zeroed);
static inline int ext4_has_metadata_csum(struct super_block *sb)
{
WARN_ON_ONCE(ext4_has_feature_metadata_csum(sb) &&
!EXT4_SB(sb)->s_chksum_driver);
return ext4_has_feature_metadata_csum(sb) &&
(EXT4_SB(sb)->s_chksum_driver != NULL);
}
static inline int ext4_has_group_desc_csum(struct super_block *sb)
{
return ext4_has_feature_gdt_csum(sb) || ext4_has_metadata_csum(sb);
}
#define ext4_read_incompat_64bit_val(es, name) \
(((es)->s_feature_incompat & cpu_to_le32(EXT4_FEATURE_INCOMPAT_64BIT) \
? (ext4_fsblk_t)le32_to_cpu(es->name##_hi) << 32 : 0) | \
le32_to_cpu(es->name##_lo))
static inline ext4_fsblk_t ext4_blocks_count(struct ext4_super_block *es)
{
return ext4_read_incompat_64bit_val(es, s_blocks_count);
}
static inline ext4_fsblk_t ext4_r_blocks_count(struct ext4_super_block *es)
{
return ext4_read_incompat_64bit_val(es, s_r_blocks_count);
}
static inline ext4_fsblk_t ext4_free_blocks_count(struct ext4_super_block *es)
{
return ext4_read_incompat_64bit_val(es, s_free_blocks_count);
}
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 super_block *sb,
struct ext4_inode *raw_inode)
{
if (ext4_has_feature_largedir(sb) ||
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);
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;
BUG_ON(group >= EXT4_SB(sb)->s_groups_count);
indexv = group >> (EXT4_DESC_PER_BLOCK_BITS(sb));
indexh = group & ((EXT4_DESC_PER_BLOCK(sb)) - 1);
grp_info = sbi_array_rcu_deref(EXT4_SB(sb), s_group_info, indexv);
return grp_info[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
/* Update i_disksize. Requires i_rwsem to avoid races with truncate */
static inline void ext4_update_i_disksize(struct inode *inode, loff_t newsize)
{
WARN_ON_ONCE(S_ISREG(inode->i_mode) &&
!inode_is_locked(inode));
down_write(&EXT4_I(inode)->i_data_sem);
if (newsize > EXT4_I(inode)->i_disksize)
ext4: fix a data race in EXT4_I(inode)->i_disksize EXT4_I(inode)->i_disksize could be accessed concurrently as noticed by KCSAN, BUG: KCSAN: data-race in ext4_write_end [ext4] / ext4_writepages [ext4] write to 0xffff91c6713b00f8 of 8 bytes by task 49268 on cpu 127: ext4_write_end+0x4e3/0x750 [ext4] ext4_update_i_disksize at fs/ext4/ext4.h:3032 (inlined by) ext4_update_inode_size at fs/ext4/ext4.h:3046 (inlined by) ext4_write_end at fs/ext4/inode.c:1287 generic_perform_write+0x208/0x2a0 ext4_buffered_write_iter+0x11f/0x210 [ext4] ext4_file_write_iter+0xce/0x9e0 [ext4] new_sync_write+0x29c/0x3b0 __vfs_write+0x92/0xa0 vfs_write+0x103/0x260 ksys_write+0x9d/0x130 __x64_sys_write+0x4c/0x60 do_syscall_64+0x91/0xb47 entry_SYSCALL_64_after_hwframe+0x49/0xbe read to 0xffff91c6713b00f8 of 8 bytes by task 24872 on cpu 37: ext4_writepages+0x10ac/0x1d00 [ext4] mpage_map_and_submit_extent at fs/ext4/inode.c:2468 (inlined by) ext4_writepages at fs/ext4/inode.c:2772 do_writepages+0x5e/0x130 __writeback_single_inode+0xeb/0xb20 writeback_sb_inodes+0x429/0x900 __writeback_inodes_wb+0xc4/0x150 wb_writeback+0x4bd/0x870 wb_workfn+0x6b4/0x960 process_one_work+0x54c/0xbe0 worker_thread+0x80/0x650 kthread+0x1e0/0x200 ret_from_fork+0x27/0x50 Reported by Kernel Concurrency Sanitizer on: CPU: 37 PID: 24872 Comm: kworker/u261:2 Tainted: G W O L 5.5.0-next-20200204+ #5 Hardware name: HPE ProLiant DL385 Gen10/ProLiant DL385 Gen10, BIOS A40 07/10/2019 Workqueue: writeback wb_workfn (flush-7:0) Since only the read is operating as lockless (outside of the "i_data_sem"), load tearing could introduce a logic bug. Fix it by adding READ_ONCE() for the read and WRITE_ONCE() for the write. Signed-off-by: Qian Cai <cai@lca.pw> Link: https://lore.kernel.org/r/1581085751-31793-1-git-send-email-cai@lca.pw Signed-off-by: Theodore Ts'o <tytso@mit.edu> Cc: stable@kernel.org
2020-02-07 22:29:11 +08:00
WRITE_ONCE(EXT4_I(inode)->i_disksize, newsize);
up_write(&EXT4_I(inode)->i_data_sem);
}
/* Update i_size, i_disksize. Requires i_rwsem to avoid races with truncate */
static inline int ext4_update_inode_size(struct inode *inode, loff_t newsize)
{
int changed = 0;
if (newsize > inode->i_size) {
i_size_write(inode, newsize);
changed = 1;
}
if (newsize > EXT4_I(inode)->i_disksize) {
ext4_update_i_disksize(inode, newsize);
changed |= 2;
}
return changed;
}
int ext4_update_disksize_before_punch(struct inode *inode, loff_t offset,
loff_t len);
struct ext4_group_info {
unsigned long bb_state;
#ifdef AGGRESSIVE_CHECK
unsigned long bb_check_counter;
#endif
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 */
ext4: improve cr 0 / cr 1 group scanning Instead of traversing through groups linearly, scan groups in specific orders at cr 0 and cr 1. At cr 0, we want to find groups that have the largest free order >= the order of the request. So, with this patch, we maintain lists for each possible order and insert each group into a list based on the largest free order in its buddy bitmap. During cr 0 allocation, we traverse these lists in the increasing order of largest free orders. This allows us to find a group with the best available cr 0 match in constant time. If nothing can be found, we fallback to cr 1 immediately. At CR1, the story is slightly different. We want to traverse in the order of increasing average fragment size. For CR1, we maintain a rb tree of groupinfos which is sorted by average fragment size. Instead of traversing linearly, at CR1, we traverse in the order of increasing average fragment size, starting at the most optimal group. This brings down cr 1 search complexity to log(num groups). For cr >= 2, we just perform the linear search as before. Also, in case of lock contention, we intermittently fallback to linear search even in CR 0 and CR 1 cases. This allows us to proceed during the allocation path even in case of high contention. There is an opportunity to do optimization at CR2 too. That's because at CR2 we only consider groups where bb_free counter (number of free blocks) is greater than the request extent size. That's left as future work. All the changes introduced in this patch are protected under a new mount option "mb_optimize_scan". With this patchset, following experiment was performed: Created a highly fragmented disk of size 65TB. The disk had no contiguous 2M regions. Following command was run consecutively for 3 times: time dd if=/dev/urandom of=file bs=2M count=10 Here are the results with and without cr 0/1 optimizations introduced in this patch: |---------+------------------------------+---------------------------| | | Without CR 0/1 Optimizations | With CR 0/1 Optimizations | |---------+------------------------------+---------------------------| | 1st run | 5m1.871s | 2m47.642s | | 2nd run | 2m28.390s | 0m0.611s | | 3rd run | 2m26.530s | 0m1.255s | |---------+------------------------------+---------------------------| Signed-off-by: Harshad Shirwadkar <harshadshirwadkar@gmail.com> Reported-by: kernel test robot <lkp@intel.com> Reported-by: Dan Carpenter <dan.carpenter@oracle.com> Reviewed-by: Andreas Dilger <adilger@dilger.ca> Link: https://lore.kernel.org/r/20210401172129.189766-6-harshadshirwadkar@gmail.com Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2021-04-02 01:21:27 +08:00
ext4_group_t bb_group; /* Group number */
struct list_head bb_prealloc_list;
#ifdef DOUBLE_CHECK
void *bb_bitmap;
#endif
struct rw_semaphore alloc_sem;
ext4: improve cr 0 / cr 1 group scanning Instead of traversing through groups linearly, scan groups in specific orders at cr 0 and cr 1. At cr 0, we want to find groups that have the largest free order >= the order of the request. So, with this patch, we maintain lists for each possible order and insert each group into a list based on the largest free order in its buddy bitmap. During cr 0 allocation, we traverse these lists in the increasing order of largest free orders. This allows us to find a group with the best available cr 0 match in constant time. If nothing can be found, we fallback to cr 1 immediately. At CR1, the story is slightly different. We want to traverse in the order of increasing average fragment size. For CR1, we maintain a rb tree of groupinfos which is sorted by average fragment size. Instead of traversing linearly, at CR1, we traverse in the order of increasing average fragment size, starting at the most optimal group. This brings down cr 1 search complexity to log(num groups). For cr >= 2, we just perform the linear search as before. Also, in case of lock contention, we intermittently fallback to linear search even in CR 0 and CR 1 cases. This allows us to proceed during the allocation path even in case of high contention. There is an opportunity to do optimization at CR2 too. That's because at CR2 we only consider groups where bb_free counter (number of free blocks) is greater than the request extent size. That's left as future work. All the changes introduced in this patch are protected under a new mount option "mb_optimize_scan". With this patchset, following experiment was performed: Created a highly fragmented disk of size 65TB. The disk had no contiguous 2M regions. Following command was run consecutively for 3 times: time dd if=/dev/urandom of=file bs=2M count=10 Here are the results with and without cr 0/1 optimizations introduced in this patch: |---------+------------------------------+---------------------------| | | Without CR 0/1 Optimizations | With CR 0/1 Optimizations | |---------+------------------------------+---------------------------| | 1st run | 5m1.871s | 2m47.642s | | 2nd run | 2m28.390s | 0m0.611s | | 3rd run | 2m26.530s | 0m1.255s | |---------+------------------------------+---------------------------| Signed-off-by: Harshad Shirwadkar <harshadshirwadkar@gmail.com> Reported-by: kernel test robot <lkp@intel.com> Reported-by: Dan Carpenter <dan.carpenter@oracle.com> Reviewed-by: Andreas Dilger <adilger@dilger.ca> Link: https://lore.kernel.org/r/20210401172129.189766-6-harshadshirwadkar@gmail.com Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2021-04-02 01:21:27 +08:00
struct rb_node bb_avg_fragment_size_rb;
struct list_head bb_largest_free_order_node;
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 12:03:38 +08:00
#define EXT4_GROUP_INFO_NEED_INIT_BIT 0
#define EXT4_GROUP_INFO_WAS_TRIMMED_BIT 1
ext4: mark block group as corrupt on block bitmap error When we notice a block-bitmap corruption (because of device failure or something else), we should mark this group as corrupt and prevent further block allocations/deallocations from it. Currently, we end up generating one error message for every block in the bitmap. This potentially could make the system unstable as noticed in some bugs. With this patch, the error will be printed only the first time and mark the entire block group as corrupted. This prevents future access allocations/deallocations from it. Also tested by corrupting the block bitmap and forcefully introducing the mb_free_blocks error: (1) create a largefile (2Gb) $ dd if=/dev/zero of=largefile oflag=direct bs=10485760 count=200 (2) umount filesystem. use dumpe2fs to see which block-bitmaps are in use by largefile and note their block numbers (3) use dd to zero-out the used block bitmaps $ dd if=/dev/zero of=/dev/hdc4 bs=4096 seek=14 count=8 oflag=direct (4) mount the FS and delete the largefile. (5) recreate the largefile. verify that the new largefile does not get any blocks from the groups marked as bad. Without the patch, we will see mb_free_blocks error for each bit in each zero'ed out bitmap at (4). With the patch, we only see the error once per blockgroup: [ 309.706803] EXT4-fs error (device sdb4): ext4_mb_generate_buddy:735: group 15: 32768 clusters in bitmap, 0 in gd. blk grp corrupted. [ 309.720824] EXT4-fs error (device sdb4): ext4_mb_generate_buddy:735: group 14: 32768 clusters in bitmap, 0 in gd. blk grp corrupted. [ 309.732858] EXT4-fs error (device sdb4) in ext4_free_blocks:4802: IO failure [ 309.748321] EXT4-fs error (device sdb4): ext4_mb_generate_buddy:735: group 13: 32768 clusters in bitmap, 0 in gd. blk grp corrupted. [ 309.760331] EXT4-fs error (device sdb4) in ext4_free_blocks:4802: IO failure [ 309.769695] EXT4-fs error (device sdb4): ext4_mb_generate_buddy:735: group 12: 32768 clusters in bitmap, 0 in gd. blk grp corrupted. [ 309.781721] EXT4-fs error (device sdb4) in ext4_free_blocks:4802: IO failure [ 309.798166] EXT4-fs error (device sdb4): ext4_mb_generate_buddy:735: group 11: 32768 clusters in bitmap, 0 in gd. blk grp corrupted. [ 309.810184] EXT4-fs error (device sdb4) in ext4_free_blocks:4802: IO failure [ 309.819532] EXT4-fs error (device sdb4): ext4_mb_generate_buddy:735: group 10: 32768 clusters in bitmap, 0 in gd. blk grp corrupted. Google-Bug-Id: 7258357 [darrick.wong@oracle.com] Further modifications (by Darrick) to make more obvious that this corruption bit applies to blocks only. Set the corruption flag if the block group bitmap verification fails. Original-author: Aditya Kali <adityakali@google.com> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2013-08-29 05:35:51 +08:00
#define EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT 2
#define EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT 3
#define EXT4_GROUP_INFO_BBITMAP_CORRUPT \
(1 << EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT)
#define EXT4_GROUP_INFO_IBITMAP_CORRUPT \
(1 << EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT)
#define EXT4_GROUP_INFO_BBITMAP_READ_BIT 4
#define EXT4_MB_GRP_NEED_INIT(grp) \
(test_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &((grp)->bb_state)))
ext4: mark block group as corrupt on block bitmap error When we notice a block-bitmap corruption (because of device failure or something else), we should mark this group as corrupt and prevent further block allocations/deallocations from it. Currently, we end up generating one error message for every block in the bitmap. This potentially could make the system unstable as noticed in some bugs. With this patch, the error will be printed only the first time and mark the entire block group as corrupted. This prevents future access allocations/deallocations from it. Also tested by corrupting the block bitmap and forcefully introducing the mb_free_blocks error: (1) create a largefile (2Gb) $ dd if=/dev/zero of=largefile oflag=direct bs=10485760 count=200 (2) umount filesystem. use dumpe2fs to see which block-bitmaps are in use by largefile and note their block numbers (3) use dd to zero-out the used block bitmaps $ dd if=/dev/zero of=/dev/hdc4 bs=4096 seek=14 count=8 oflag=direct (4) mount the FS and delete the largefile. (5) recreate the largefile. verify that the new largefile does not get any blocks from the groups marked as bad. Without the patch, we will see mb_free_blocks error for each bit in each zero'ed out bitmap at (4). With the patch, we only see the error once per blockgroup: [ 309.706803] EXT4-fs error (device sdb4): ext4_mb_generate_buddy:735: group 15: 32768 clusters in bitmap, 0 in gd. blk grp corrupted. [ 309.720824] EXT4-fs error (device sdb4): ext4_mb_generate_buddy:735: group 14: 32768 clusters in bitmap, 0 in gd. blk grp corrupted. [ 309.732858] EXT4-fs error (device sdb4) in ext4_free_blocks:4802: IO failure [ 309.748321] EXT4-fs error (device sdb4): ext4_mb_generate_buddy:735: group 13: 32768 clusters in bitmap, 0 in gd. blk grp corrupted. [ 309.760331] EXT4-fs error (device sdb4) in ext4_free_blocks:4802: IO failure [ 309.769695] EXT4-fs error (device sdb4): ext4_mb_generate_buddy:735: group 12: 32768 clusters in bitmap, 0 in gd. blk grp corrupted. [ 309.781721] EXT4-fs error (device sdb4) in ext4_free_blocks:4802: IO failure [ 309.798166] EXT4-fs error (device sdb4): ext4_mb_generate_buddy:735: group 11: 32768 clusters in bitmap, 0 in gd. blk grp corrupted. [ 309.810184] EXT4-fs error (device sdb4) in ext4_free_blocks:4802: IO failure [ 309.819532] EXT4-fs error (device sdb4): ext4_mb_generate_buddy:735: group 10: 32768 clusters in bitmap, 0 in gd. blk grp corrupted. Google-Bug-Id: 7258357 [darrick.wong@oracle.com] Further modifications (by Darrick) to make more obvious that this corruption bit applies to blocks only. Set the corruption flag if the block group bitmap verification fails. Original-author: Aditya Kali <adityakali@google.com> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2013-08-29 05:35:51 +08:00
#define EXT4_MB_GRP_BBITMAP_CORRUPT(grp) \
(test_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &((grp)->bb_state)))
#define EXT4_MB_GRP_IBITMAP_CORRUPT(grp) \
(test_bit(EXT4_GROUP_INFO_IBITMAP_CORRUPT_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 12:03:38 +08:00
#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_MB_GRP_TEST_AND_SET_READ(grp) \
(test_and_set_bit(EXT4_GROUP_INFO_BBITMAP_READ_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 12:03:38 +08:00
#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));
}
#ifdef CONFIG_QUOTA
static inline bool ext4_quota_capable(struct super_block *sb)
{
return (test_opt(sb, QUOTA) || ext4_has_feature_quota(sb));
}
static inline bool ext4_is_quota_journalled(struct super_block *sb)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
return (ext4_has_feature_quota(sb) ||
sbi->s_qf_names[USRQUOTA] || sbi->s_qf_names[GRPQUOTA]);
}
int ext4_enable_quotas(struct super_block *sb);
#endif
/*
* 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 09:30:06 +08:00
extern loff_t ext4_llseek(struct file *file, loff_t offset, int origin);
/* inline.c */
extern int ext4_get_max_inline_size(struct inode *inode);
extern int ext4_find_inline_data_nolock(struct inode *inode);
extern int ext4_init_inline_data(handle_t *handle, struct inode *inode,
unsigned int len);
extern int ext4_destroy_inline_data(handle_t *handle, struct inode *inode);
extern int ext4_readpage_inline(struct inode *inode, struct page *page);
extern int ext4_try_to_write_inline_data(struct address_space *mapping,
struct inode *inode,
loff_t pos, unsigned len,
unsigned flags,
struct page **pagep);
extern int ext4_write_inline_data_end(struct inode *inode,
loff_t pos, unsigned len,
unsigned copied,
struct page *page);
extern struct buffer_head *
ext4_journalled_write_inline_data(struct inode *inode,
unsigned len,
struct page *page);
extern int ext4_da_write_inline_data_begin(struct address_space *mapping,
struct inode *inode,
loff_t pos, unsigned len,
unsigned flags,
struct page **pagep,
void **fsdata);
extern int ext4_try_add_inline_entry(handle_t *handle,
struct ext4_filename *fname,
struct inode *dir, struct inode *inode);
extern int ext4_try_create_inline_dir(handle_t *handle,
struct inode *parent,
struct inode *inode);
extern int ext4_read_inline_dir(struct file *filp,
struct dir_context *ctx,
int *has_inline_data);
extern int ext4_inlinedir_to_tree(struct file *dir_file,
struct inode *dir, ext4_lblk_t block,
struct dx_hash_info *hinfo,
__u32 start_hash, __u32 start_minor_hash,
int *has_inline_data);
extern struct buffer_head *ext4_find_inline_entry(struct inode *dir,
struct ext4_filename *fname,
struct ext4_dir_entry_2 **res_dir,
int *has_inline_data);
extern int ext4_delete_inline_entry(handle_t *handle,
struct inode *dir,
struct ext4_dir_entry_2 *de_del,
struct buffer_head *bh,
int *has_inline_data);
extern bool empty_inline_dir(struct inode *dir, int *has_inline_data);
extern struct buffer_head *ext4_get_first_inline_block(struct inode *inode,
struct ext4_dir_entry_2 **parent_de,
int *retval);
extern int ext4_inline_data_fiemap(struct inode *inode,
struct fiemap_extent_info *fieinfo,
int *has_inline, __u64 start, __u64 len);
struct iomap;
extern int ext4_inline_data_iomap(struct inode *inode, struct iomap *iomap);
extern int ext4_inline_data_truncate(struct inode *inode, int *has_inline);
extern int ext4_convert_inline_data(struct inode *inode);
ext4: make ext4_has_inline_data() as a inline function Now ext4_has_inline_data() is used in wide spread codepaths. So we need to make it as a inline function to avoid burning some CPU cycles. Change in text size: text data bss dec hex filename before: 326110 19258 5528 350896 55ab0 fs/ext4/ext4.o after: 326227 19258 5528 351013 55b25 fs/ext4/ext4.o I use the following script to measure the CPU usage. #!/bin/bash shm_base='/dev/shm' img=${shm_base}/ext4-img mnt=/mnt/loop e2fsprgs_base=$HOME/e2fsprogs mkfs=${e2fsprgs_base}/misc/mke2fs fsck=${e2fsprgs_base}/e2fsck/e2fsck sudo umount $mnt dd if=/dev/zero of=$img bs=4k count=3145728 ${mkfs} -t ext4 -O inline_data -F $img sudo mount -t ext4 -o loop $img $mnt # start testing... testdir="${mnt}/testdir" mkdir $testdir cd $testdir echo "start testing..." for ((cnt=0;cnt<100;cnt++)); do for ((i=0;i<5;i++)); do for ((j=0;j<5;j++)); do for ((k=0;k<5;k++)); do for ((l=0;l<5;l++)); do mkdir -p $i/$j/$k/$l echo "$i-$j-$k-$l" > $i/$j/$k/$l/testfile done done done done ls -R $testdir > /dev/null rm -rf $testdir/* done The result of `perf top -G -U` is as below. vanilla: 13.92% [ext4] [k] ext4_do_update_inode 9.36% [ext4] [k] __ext4_get_inode_loc 4.07% [ext4] [k] ftrace_define_fields_ext4_writepages 3.83% [ext4] [k] __ext4_handle_dirty_metadata 3.42% [ext4] [k] ext4_get_inode_flags 2.71% [ext4] [k] ext4_mark_iloc_dirty 2.46% [ext4] [k] ftrace_define_fields_ext4_direct_IO_enter 2.26% [ext4] [k] ext4_get_inode_loc 2.22% [ext4] [k] ext4_has_inline_data [...] After applied the patch, we don't see ext4_has_inline_data() because it has been inlined and perf couldn't sample it. Although it doesn't mean that the CPU cycles can be saved but at least the overhead of function calls can be eliminated. So IMHO we'd better inline this function. Cc: Andreas Dilger <adilger.kernel@dilger.ca> Signed-off-by: Zheng Liu <wenqing.lz@taobao.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2014-07-15 22:10:04 +08:00
static inline int ext4_has_inline_data(struct inode *inode)
{
return ext4_test_inode_flag(inode, EXT4_INODE_INLINE_DATA) &&
EXT4_I(inode)->i_inline_off;
}
/* 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);
extern struct ext4_dir_entry_2 *ext4_init_dot_dotdot(struct inode *inode,
struct ext4_dir_entry_2 *de,
int blocksize, int csum_size,
unsigned int parent_ino, int dotdot_real_len);
extern void ext4_initialize_dirent_tail(struct buffer_head *bh,
unsigned int blocksize);
extern int ext4_handle_dirty_dirblock(handle_t *handle, struct inode *inode,
struct buffer_head *bh);
extern int __ext4_unlink(handle_t *handle, struct inode *dir, const struct qstr *d_name,
struct inode *inode);
extern int __ext4_link(struct inode *dir, struct inode *inode,
struct dentry *dentry);
ext4: Support case-insensitive file name lookups This patch implements the actual support for case-insensitive file name lookups in ext4, based on the feature bit and the encoding stored in the superblock. A filesystem that has the casefold feature set is able to configure directories with the +F (EXT4_CASEFOLD_FL) attribute, enabling lookups to succeed in that directory in a case-insensitive fashion, i.e: match a directory entry even if the name used by userspace is not a byte per byte match with the disk name, but is an equivalent case-insensitive version of the Unicode string. This operation is called a case-insensitive file name lookup. The feature is configured as an inode attribute applied to directories and inherited by its children. This attribute can only be enabled on empty directories for filesystems that support the encoding feature, thus preventing collision of file names that only differ by case. * dcache handling: For a +F directory, Ext4 only stores the first equivalent name dentry used in the dcache. This is done to prevent unintentional duplication of dentries in the dcache, while also allowing the VFS code to quickly find the right entry in the cache despite which equivalent string was used in a previous lookup, without having to resort to ->lookup(). d_hash() of casefolded directories is implemented as the hash of the casefolded string, such that we always have a well-known bucket for all the equivalencies of the same string. d_compare() uses the utf8_strncasecmp() infrastructure, which handles the comparison of equivalent, same case, names as well. For now, negative lookups are not inserted in the dcache, since they would need to be invalidated anyway, because we can't trust missing file dentries. This is bad for performance but requires some leveraging of the vfs layer to fix. We can live without that for now, and so does everyone else. * on-disk data: Despite using a specific version of the name as the internal representation within the dcache, the name stored and fetched from the disk is a byte-per-byte match with what the user requested, making this implementation 'name-preserving'. i.e. no actual information is lost when writing to storage. DX is supported by modifying the hashes used in +F directories to make them case/encoding-aware. The new disk hashes are calculated as the hash of the full casefolded string, instead of the string directly. This allows us to efficiently search for file names in the htree without requiring the user to provide an exact name. * Dealing with invalid sequences: By default, when a invalid UTF-8 sequence is identified, ext4 will treat it as an opaque byte sequence, ignoring the encoding and reverting to the old behavior for that unique file. This means that case-insensitive file name lookup will not work only for that file. An optional bit can be set in the superblock telling the filesystem code and userspace tools to enforce the encoding. When that optional bit is set, any attempt to create a file name using an invalid UTF-8 sequence will fail and return an error to userspace. * Normalization algorithm: The UTF-8 algorithms used to compare strings in ext4 is implemented lives in fs/unicode, and is based on a previous version developed by SGI. It implements the Canonical decomposition (NFD) algorithm described by the Unicode specification 12.1, or higher, combined with the elimination of ignorable code points (NFDi) and full case-folding (CF) as documented in fs/unicode/utf8_norm.c. NFD seems to be the best normalization method for EXT4 because: - It has a lower cost than NFC/NFKC (which requires decomposing to NFD as an intermediary step) - It doesn't eliminate important semantic meaning like compatibility decompositions. Although: - This implementation is not completely linguistic accurate, because different languages have conflicting rules, which would require the specialization of the filesystem to a given locale, which brings all sorts of problems for removable media and for users who use more than one language. Signed-off-by: Gabriel Krisman Bertazi <krisman@collabora.co.uk> Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2019-04-26 02:12:08 +08:00
#define S_SHIFT 12
static const unsigned char ext4_type_by_mode[(S_IFMT >> S_SHIFT) + 1] = {
[S_IFREG >> S_SHIFT] = EXT4_FT_REG_FILE,
[S_IFDIR >> S_SHIFT] = EXT4_FT_DIR,
[S_IFCHR >> S_SHIFT] = EXT4_FT_CHRDEV,
[S_IFBLK >> S_SHIFT] = EXT4_FT_BLKDEV,
[S_IFIFO >> S_SHIFT] = EXT4_FT_FIFO,
[S_IFSOCK >> S_SHIFT] = EXT4_FT_SOCK,
[S_IFLNK >> S_SHIFT] = EXT4_FT_SYMLINK,
};
static inline void ext4_set_de_type(struct super_block *sb,
struct ext4_dir_entry_2 *de,
umode_t mode) {
if (ext4_has_feature_filetype(sb))
de->file_type = ext4_type_by_mode[(mode & S_IFMT)>>S_SHIFT];
}
/* readpages.c */
extern int ext4_mpage_readpages(struct inode *inode,
struct readahead_control *rac, struct page *page);
extern int __init ext4_init_post_read_processing(void);
extern void ext4_exit_post_read_processing(void);
/* symlink.c */
extern const struct inode_operations ext4_encrypted_symlink_inode_operations;
extern const struct inode_operations ext4_symlink_inode_operations;
extern const struct inode_operations ext4_fast_symlink_inode_operations;
/* sysfs.c */
extern void ext4_notify_error_sysfs(struct ext4_sb_info *sbi);
extern int ext4_register_sysfs(struct super_block *sb);
extern void ext4_unregister_sysfs(struct super_block *sb);
extern int __init ext4_init_sysfs(void);
extern void ext4_exit_sysfs(void);
/* 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);
2020-07-28 21:04:34 +08:00
extern int ext4_inode_block_valid(struct inode *inode,
ext4_fsblk_t start_blk,
unsigned int count);
extern int ext4_check_blockref(const char *, unsigned int,
struct inode *, __le32 *, unsigned int);
extern int ext4_sb_block_valid(struct super_block *sb, struct inode *inode,
ext4_fsblk_t start_blk, unsigned int count);
/* extents.c */
struct ext4_ext_path;
struct ext4_extent;
/*
* Maximum number of logical blocks in a file; ext4_extent's ee_block is
* __le32.
*/
#define EXT_MAX_BLOCKS 0xffffffff
extern void ext4_ext_tree_init(handle_t *handle, struct inode *inode);
extern int ext4_ext_index_trans_blocks(struct inode *inode, int extents);
extern int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
struct ext4_map_blocks *map, int flags);
extern int ext4_ext_truncate(handle_t *, struct inode *);
extern int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start,
ext4_lblk_t end);
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(handle_t *handle, struct inode *inode,
loff_t offset, ssize_t len);
extern int ext4_convert_unwritten_io_end_vec(handle_t *handle,
ext4_io_end_t *io_end);
extern int ext4_map_blocks(handle_t *handle, struct inode *inode,
struct ext4_map_blocks *map, int flags);
extern int ext4_ext_calc_credits_for_single_extent(struct inode *inode,
int num,
struct ext4_ext_path *path);
extern int ext4_ext_insert_extent(handle_t *, struct inode *,
struct ext4_ext_path **,
struct ext4_extent *, int);
extern struct ext4_ext_path *ext4_find_extent(struct inode *, ext4_lblk_t,
struct ext4_ext_path **,
int flags);
extern void ext4_ext_drop_refs(struct ext4_ext_path *);
extern int ext4_ext_check_inode(struct inode *inode);
extern ext4_lblk_t ext4_ext_next_allocated_block(struct ext4_ext_path *path);
extern int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
__u64 start, __u64 len);
extern int ext4_get_es_cache(struct inode *inode,
struct fiemap_extent_info *fieinfo,
__u64 start, __u64 len);
extern int ext4_ext_precache(struct inode *inode);
extern int ext4_swap_extents(handle_t *handle, struct inode *inode1,
struct inode *inode2, ext4_lblk_t lblk1,
ext4_lblk_t lblk2, ext4_lblk_t count,
int mark_unwritten,int *err);
extern int ext4_clu_mapped(struct inode *inode, ext4_lblk_t lclu);
extern int ext4_datasem_ensure_credits(handle_t *handle, struct inode *inode,
int check_cred, int restart_cred,
int revoke_cred);
extern void ext4_ext_replay_shrink_inode(struct inode *inode, ext4_lblk_t end);
extern int ext4_ext_replay_set_iblocks(struct inode *inode);
extern int ext4_ext_replay_update_ex(struct inode *inode, ext4_lblk_t start,
int len, int unwritten, ext4_fsblk_t pblk);
extern int ext4_ext_clear_bb(struct inode *inode);
/* move_extent.c */
extern void ext4_double_down_write_data_sem(struct inode *first,
struct inode *second);
extern void ext4_double_up_write_data_sem(struct inode *orig_inode,
struct inode *donor_inode);
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);
extern ext4_io_end_t *ext4_init_io_end(struct inode *inode, gfp_t flags);
extern ext4_io_end_t *ext4_get_io_end(ext4_io_end_t *io_end);
extern int ext4_put_io_end(ext4_io_end_t *io_end);
extern void ext4_put_io_end_defer(ext4_io_end_t *io_end);
extern void ext4_io_submit_init(struct ext4_io_submit *io,
struct writeback_control *wbc);
extern void ext4_end_io_rsv_work(struct work_struct *work);
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,
ext4: fix data integrity sync in ordered mode When we perform a data integrity sync we tag all the dirty pages with PAGECACHE_TAG_TOWRITE at start of ext4_da_writepages. Later we check for this tag in write_cache_pages_da and creates a struct mpage_da_data containing contiguously indexed pages tagged with this tag and sync these pages with a call to mpage_da_map_and_submit. This process is done in while loop until all the PAGECACHE_TAG_TOWRITE pages are synced. We also do journal start and stop in each iteration. journal_stop could initiate journal commit which would call ext4_writepage which in turn will call ext4_bio_write_page even for delayed OR unwritten buffers. When ext4_bio_write_page is called for such buffers, even though it does not sync them but it clears the PAGECACHE_TAG_TOWRITE of the corresponding page and hence these pages are also not synced by the currently running data integrity sync. We will end up with dirty pages although sync is completed. This could cause a potential data loss when the sync call is followed by a truncate_pagecache call, which is exactly the case in collapse_range. (It will cause generic/127 failure in xfstests) To avoid this issue, we can use set_page_writeback_keepwrite instead of set_page_writeback, which doesn't clear TOWRITE tag. Cc: stable@vger.kernel.org Signed-off-by: Namjae Jeon <namjae.jeon@samsung.com> Signed-off-by: Ashish Sangwan <a.sangwan@samsung.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu> Reviewed-by: Jan Kara <jack@suse.cz>
2014-05-12 20:12:25 +08:00
bool keep_towrite);
extern struct ext4_io_end_vec *ext4_alloc_io_end_vec(ext4_io_end_t *io_end);
extern struct ext4_io_end_vec *ext4_last_io_end_vec(ext4_io_end_t *io_end);
/* mmp.c */
extern int ext4_multi_mount_protect(struct super_block *, ext4_fsblk_t);
/* mmp.c */
extern void ext4_stop_mmpd(struct ext4_sb_info *sbi);
ext4: add basic fs-verity support Add most of fs-verity support to ext4. fs-verity is a filesystem feature that enables transparent integrity protection and authentication of read-only files. It uses a dm-verity like mechanism at the file level: a Merkle tree is used to verify any block in the file in log(filesize) time. It is implemented mainly by helper functions in fs/verity/. See Documentation/filesystems/fsverity.rst for the full documentation. This commit adds all of ext4 fs-verity support except for the actual data verification, including: - Adding a filesystem feature flag and an inode flag for fs-verity. - Implementing the fsverity_operations to support enabling verity on an inode and reading/writing the verity metadata. - Updating ->write_begin(), ->write_end(), and ->writepages() to support writing verity metadata pages. - Calling the fs-verity hooks for ->open(), ->setattr(), and ->ioctl(). ext4 stores the verity metadata (Merkle tree and fsverity_descriptor) past the end of the file, starting at the first 64K boundary beyond i_size. This approach works because (a) verity files are readonly, and (b) pages fully beyond i_size aren't visible to userspace but can be read/written internally by ext4 with only some relatively small changes to ext4. This approach avoids having to depend on the EA_INODE feature and on rearchitecturing ext4's xattr support to support paging multi-gigabyte xattrs into memory, and to support encrypting xattrs. Note that the verity metadata *must* be encrypted when the file is, since it contains hashes of the plaintext data. This patch incorporates work by Theodore Ts'o and Chandan Rajendra. Reviewed-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Eric Biggers <ebiggers@google.com>
2019-07-23 00:26:24 +08:00
/* verity.c */
extern const struct fsverity_operations ext4_verityops;
/* orphan.c */
extern int ext4_orphan_add(handle_t *, struct inode *);
extern int ext4_orphan_del(handle_t *, struct inode *);
extern void ext4_orphan_cleanup(struct super_block *sb,
struct ext4_super_block *es);
ext4: Speedup ext4 orphan inode handling Ext4 orphan inode handling is a bottleneck for workloads which heavily truncate / unlink small files since it contends on the global s_orphan_mutex lock (and generally it's difficult to improve scalability of the ondisk linked list of orphaned inodes). This patch implements new way of handling orphan inodes. Instead of linking orphaned inode into a linked list, we store it's inode number in a new special file which we call "orphan file". Only if there's no more space in the orphan file (too many inodes are currently orphaned) we fall back to using old style linked list. Currently we protect operations in the orphan file with a spinlock for simplicity but even in this setting we can substantially reduce the length of the critical section and thus speedup some workloads. In the next patch we improve this by making orphan handling lockless. Note that the change is backwards compatible when the filesystem is clean - the existence of the orphan file is a compat feature, we set another ro-compat feature indicating orphan file needs scanning for orphaned inodes when mounting filesystem read-write. This ro-compat feature gets cleared on unmount / remount read-only. Some performance data from 80 CPU Xeon Server with 512 GB of RAM, filesystem located on SSD, average of 5 runs: stress-orphan (microbenchmark truncating files byte-by-byte from N processes in parallel) Threads Time Time Vanilla Patched 1 1.057200 0.945600 2 1.680400 1.331800 4 2.547000 1.995000 8 7.049400 6.424200 16 14.827800 14.937600 32 40.948200 33.038200 64 87.787400 60.823600 128 206.504000 122.941400 So we can see significant wins all over the board. Reviewed-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Jan Kara <jack@suse.cz> Link: https://lore.kernel.org/r/20210816095713.16537-3-jack@suse.cz Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2021-08-16 17:57:06 +08:00
extern void ext4_release_orphan_info(struct super_block *sb);
extern int ext4_init_orphan_info(struct super_block *sb);
extern int ext4_orphan_file_empty(struct super_block *sb);
extern void ext4_orphan_file_block_trigger(
struct jbd2_buffer_trigger_type *triggers,
struct buffer_head *bh,
void *data, size_t size);
/*
* Add new method to test whether 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 21:17:34 +08:00
/* 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])
extern wait_queue_head_t ext4__ioend_wq[EXT4_WQ_HASH_SZ];
extern int ext4_resize_begin(struct super_block *sb);
extern void ext4_resize_end(struct super_block *sb);
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_unwritten);
}
}
static inline void ext4_clear_io_unwritten_flag(ext4_io_end_t *io_end)
{
struct inode *inode = io_end->inode;
if (io_end->flag & EXT4_IO_END_UNWRITTEN) {
io_end->flag &= ~EXT4_IO_END_UNWRITTEN;
/* Wake up anyone waiting on unwritten extent conversion */
if (atomic_dec_and_test(&EXT4_I(inode)->i_unwritten))
wake_up_all(ext4_ioend_wq(inode));
}
}
extern const struct iomap_ops ext4_iomap_ops;
ext4: Optimize ext4 DIO overwrites Currently we start transaction for mapping every extent for writing using direct IO. This is unnecessary when we know we are overwriting already allocated blocks and the overhead of starting a transaction can be significant especially for multithreaded workloads doing small writes. Use iomap operations that avoid starting a transaction for direct IO overwrites. This improves throughput of 4k random writes - fio jobfile: [global] rw=randrw norandommap=1 invalidate=0 bs=4k numjobs=16 time_based=1 ramp_time=30 runtime=120 group_reporting=1 ioengine=psync direct=1 size=16G filename=file1.0.0:file1.0.1:file1.0.2:file1.0.3:file1.0.4:file1.0.5:file1.0.6:file1.0.7:file1.0.8:file1.0.9:file1.0.10:file1.0.11:file1.0.12:file1.0.13:file1.0.14:file1.0.15:file1.0.16:file1.0.17:file1.0.18:file1.0.19:file1.0.20:file1.0.21:file1.0.22:file1.0.23:file1.0.24:file1.0.25:file1.0.26:file1.0.27:file1.0.28:file1.0.29:file1.0.30:file1.0.31 file_service_type=random nrfiles=32 from 3018MB/s to 4059MB/s in my test VM running test against simulated pmem device (note that before iomap conversion, this workload was able to achieve 3708MB/s because old direct IO path avoided transaction start for overwrites as well). For dax, the win is even larger improving throughput from 3042MB/s to 4311MB/s. Reported-by: Dan Williams <dan.j.williams@intel.com> Signed-off-by: Jan Kara <jack@suse.cz> Link: https://lore.kernel.org/r/20191218174433.19380-1-jack@suse.cz Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2019-12-19 01:44:33 +08:00
extern const struct iomap_ops ext4_iomap_overwrite_ops;
extern const struct iomap_ops ext4_iomap_report_ops;
static inline int ext4_buffer_uptodate(struct buffer_head *bh)
{
/*
* If the buffer has the write error flag, we have failed
* to write out data in the block. In this case, we don't
* have to read the block because we may read the old data
* successfully.
*/
if (buffer_write_io_error(bh))
set_buffer_uptodate(bh);
return buffer_uptodate(bh);
}
#endif /* __KERNEL__ */
#define EFSBADCRC EBADMSG /* Bad CRC detected */
#define EFSCORRUPTED EUCLEAN /* Filesystem is corrupted */
#endif /* _EXT4_H */