diff options
Diffstat (limited to 'fs/ext4/ext4.h')
| -rw-r--r-- | fs/ext4/ext4.h | 2391 |
1 files changed, 1772 insertions, 619 deletions
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index b577e45425b0..56112f201cac 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * ext4.h * @@ -16,6 +17,7 @@ #ifndef _EXT4_H #define _EXT4_H +#include <linux/refcount.h> #include <linux/types.h> #include <linux/blkdev.h> #include <linux/magic.h> @@ -27,18 +29,41 @@ #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 <crypto/hash.h> +#include <linux/ratelimit.h> +#include <linux/crc32c.h> +#include <linux/falloc.h> +#include <linux/percpu-rwsem.h> +#include <linux/fiemap.h> #ifdef __KERNEL__ #include <linux/compat.h> #endif +#include <uapi/linux/ext4.h> + +#include <linux/fscrypt.h> +#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 @@ -57,24 +82,33 @@ #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__ + /* - * Turn on EXT_DEBUG to get lots of info about extents operations. + * Dynamic printk for controlled extents debugging. */ -#define EXT_DEBUG__ -#ifdef EXT_DEBUG -#define ext_debug(fmt, ...) printk(fmt, ##__VA_ARGS__) +#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(fmt, ...) no_printk(fmt, ##__VA_ARGS__) +#define ext_debug(ino, fmt, ...) no_printk(fmt, ##__VA_ARGS__) #endif -#define EXT4_ERROR_INODE(inode, fmt, a...) \ - ext4_error_inode((inode), __func__, __LINE__, 0, (fmt), ## a) - -#define EXT4_ERROR_INODE_BLOCK(inode, block, fmt, a...) \ - ext4_error_inode((inode), __func__, __LINE__, (block), (fmt), ## a) - -#define EXT4_ERROR_FILE(file, block, fmt, a...) \ - ext4_error_file((file), __func__, __LINE__, (block), (fmt), ## a) +#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; @@ -88,6 +122,60 @@ 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, +}; + +/* + * For each criteria, mballoc has slightly different way of finding + * the required blocks nad usually, higher the criteria the slower the + * allocation. We start at lower criterias and keep falling back to + * higher ones if we are not able to find any blocks. Lower (earlier) + * criteria are faster. + */ +enum criteria { + /* + * Used when number of blocks needed is a power of 2. This + * doesn't trigger any disk IO except prefetch and is the + * fastest criteria. + */ + CR_POWER2_ALIGNED, + + /* + * Tries to lookup in-memory data structures to find the most + * suitable group that satisfies goal request. No disk IO + * except block prefetch. + */ + CR_GOAL_LEN_FAST, + + /* + * Same as CR_GOAL_LEN_FAST but is allowed to reduce the goal + * length to the best available length for faster allocation. + */ + CR_BEST_AVAIL_LEN, + + /* + * Reads each block group sequentially, performing disk IO if + * necessary, to find suitable block group. Tries to + * allocate goal length but might trim the request if nothing + * is found after enough tries. + */ + CR_GOAL_LEN_SLOW, + + /* + * Finds the first free set of blocks and allocates + * those. This is only used in rare cases when + * CR_GOAL_LEN_SLOW also fails to allocate anything. + */ + CR_ANY_FREE, + + /* + * Number of criterias defined. + */ + EXT4_MB_NUM_CRS +}; + /* * Flags used in mballoc's allocation_context flags field. * @@ -97,14 +185,8 @@ typedef unsigned int ext4_group_t; /* 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) */ @@ -123,6 +205,8 @@ typedef unsigned int ext4_group_t; #define EXT4_MB_USE_ROOT_BLOCKS 0x1000 /* 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 struct ext4_allocation_request { /* target inode for block we're allocating */ @@ -152,38 +236,57 @@ struct ext4_allocation_request { * well as to store the information returned by ext4_map_blocks(). It * takes less room on the stack than a struct buffer_head. */ -#define EXT4_MAP_NEW (1 << BH_New) -#define EXT4_MAP_MAPPED (1 << BH_Mapped) -#define EXT4_MAP_UNWRITTEN (1 << BH_Unwritten) -#define EXT4_MAP_BOUNDARY (1 << BH_Boundary) -#define EXT4_MAP_UNINIT (1 << BH_Uninit) -/* Sometimes (in the bigalloc case, from ext4_da_get_block_prep) the caller of - * ext4_map_blocks wants to know whether or not the underlying cluster has - * already been accounted for. EXT4_MAP_FROM_CLUSTER conveys to the caller that - * the requested mapping was from previously mapped (or delayed allocated) - * cluster. We use BH_AllocFromCluster only for this flag. BH_AllocFromCluster - * should never appear on buffer_head's state flags. - */ -#define EXT4_MAP_FROM_CLUSTER (1 << BH_AllocFromCluster) +#define EXT4_MAP_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_DELAYED BIT(BH_Delay) +/* + * This is for use in ext4_map_query_blocks() for a special case where we can + * have a physically and logically contiguous blocks split across two leaf + * nodes instead of a single extent. This is required in case of atomic writes + * to know whether the returned extent is last in leaf. If yes, then lookup for + * next in leaf block in ext4_map_query_blocks_next_in_leaf(). + * - This is never going to be added to any buffer head state. + * - We use the next available bit after BH_BITMAP_UPTODATE. + */ +#define EXT4_MAP_QUERY_LAST_IN_LEAF BIT(BH_BITMAP_UPTODATE + 1) #define EXT4_MAP_FLAGS (EXT4_MAP_NEW | EXT4_MAP_MAPPED |\ EXT4_MAP_UNWRITTEN | EXT4_MAP_BOUNDARY |\ - EXT4_MAP_UNINIT | EXT4_MAP_FROM_CLUSTER) + EXT4_MAP_DELAYED | EXT4_MAP_QUERY_LAST_IN_LEAF) struct ext4_map_blocks { ext4_fsblk_t m_pblk; ext4_lblk_t m_lblk; unsigned int m_len; unsigned int m_flags; + u64 m_seq; +}; + +/* + * 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 -#define EXT4_IO_END_DIRECT 0x0002 +#define EXT4_IO_END_UNWRITTEN 0x0001 +#define EXT4_IO_END_FAILED 0x0002 + +#define EXT4_IO_END_DEFER_COMPLETION (EXT4_IO_END_UNWRITTEN | EXT4_IO_END_FAILED) + +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 uninitialized extents on a work queue. 'handle' is used for + * For converting unwritten extents on a work queue. 'handle' is used for * buffered writeback. */ typedef struct ext4_io_end { @@ -194,15 +297,12 @@ typedef struct ext4_io_end { struct bio *bio; /* Linked list of completed * bios covering the extent */ unsigned int flag; /* unwritten or not */ - loff_t offset; /* offset in the file */ - ssize_t size; /* size of the extent */ - struct kiocb *iocb; /* iocb struct for AIO */ - int result; /* error value for AIO */ - atomic_t count; /* reference counter */ + refcount_t count; /* reference counter */ + struct list_head list_vec; /* list of ext4_io_end_vec */ } ext4_io_end_t; struct ext4_io_submit { - int io_op; + struct writeback_control *io_wbc; struct bio *io_bio; ext4_io_end_t *io_end; sector_t io_next_block; @@ -235,6 +335,7 @@ struct ext4_io_submit { #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 @@ -262,7 +363,19 @@ struct ext4_io_submit { (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)) +#define EXT4_B_TO_LBLK(inode, offset) \ + (round_up((offset), i_blocksize(inode)) >> (inode)->i_blkbits) +#define EXT4_LBLK_TO_B(inode, lblk) ((loff_t)(lblk) << (inode)->i_blkbits) + +/* Translate a block number to a page index */ +#define EXT4_LBLK_TO_PG(inode, lblk) (EXT4_LBLK_TO_B((inode), (lblk)) >> \ + PAGE_SHIFT) +/* Translate a page index to a block number */ +#define EXT4_PG_TO_LBLK(inode, pnum) (((loff_t)(pnum) << PAGE_SHIFT) >> \ + (inode)->i_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 */ @@ -270,6 +383,19 @@ struct ext4_io_submit { /* 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 @@ -365,7 +491,8 @@ struct flex_groups { #define EXT4_DIRTY_FL 0x00000100 #define EXT4_COMPRBLK_FL 0x00000200 /* One or more compressed clusters */ #define EXT4_NOCOMPR_FL 0x00000400 /* Don't compress */ -#define EXT4_ECOMPR_FL 0x00000800 /* Compression error */ + /* 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 */ @@ -375,26 +502,68 @@ struct flex_groups { #define EXT4_TOPDIR_FL 0x00020000 /* Top of directory hierarchies*/ #define EXT4_HUGE_FILE_FL 0x00040000 /* Set to each huge file */ #define EXT4_EXTENTS_FL 0x00080000 /* Inode uses extents */ +#define EXT4_VERITY_FL 0x00100000 /* Verity protected inode */ #define EXT4_EA_INODE_FL 0x00200000 /* Inode used for large EA */ -#define EXT4_EOFBLOCKS_FL 0x00400000 /* Blocks allocated beyond EOF */ +/* 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 */ -#define EXT4_FL_USER_VISIBLE 0x004BDFFF /* User visible flags */ -#define EXT4_FL_USER_MODIFIABLE 0x004380FF /* User modifiable flags */ +/* 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_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)) +#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) { @@ -422,7 +591,7 @@ enum { EXT4_INODE_DIRTY = 8, EXT4_INODE_COMPRBLK = 9, /* One or more compressed clusters */ EXT4_INODE_NOCOMPR = 10, /* Don't compress */ - EXT4_INODE_ECOMPR = 11, /* Compression error */ + 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 */ @@ -432,9 +601,13 @@ enum { EXT4_INODE_TOPDIR = 17, /* Top of directory hierarchies*/ EXT4_INODE_HUGE_FILE = 18, /* Set to each huge file */ EXT4_INODE_EXTENTS = 19, /* Inode uses extents */ + EXT4_INODE_VERITY = 20, /* Verity protected inode */ EXT4_INODE_EA_INODE = 21, /* Inode used for large EA */ - EXT4_INODE_EOFBLOCKS = 22, /* Blocks allocated beyond EOF */ +/* 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 */ }; @@ -451,7 +624,7 @@ enum { * * 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 TEST_FLAG_VALUE(FLAG) (EXT4_##FLAG##_FL == (1U << EXT4_INODE_##FLAG)) #define CHECK_FLAG_VALUE(FLAG) BUILD_BUG_ON(!TEST_FLAG_VALUE(FLAG)) static inline void ext4_check_flag_values(void) @@ -467,7 +640,7 @@ static inline void ext4_check_flag_values(void) CHECK_FLAG_VALUE(DIRTY); CHECK_FLAG_VALUE(COMPRBLK); CHECK_FLAG_VALUE(NOCOMPR); - CHECK_FLAG_VALUE(ECOMPR); + CHECK_FLAG_VALUE(ENCRYPT); CHECK_FLAG_VALUE(INDEX); CHECK_FLAG_VALUE(IMAGIC); CHECK_FLAG_VALUE(JOURNAL_DATA); @@ -476,23 +649,14 @@ static inline void ext4_check_flag_values(void) CHECK_FLAG_VALUE(TOPDIR); CHECK_FLAG_VALUE(HUGE_FILE); CHECK_FLAG_VALUE(EXTENTS); + CHECK_FLAG_VALUE(VERITY); CHECK_FLAG_VALUE(EA_INODE); - CHECK_FLAG_VALUE(EOFBLOCKS); 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; @@ -513,8 +677,8 @@ struct ext4_new_group_data { __u64 inode_table; __u32 blocks_count; __u16 reserved_blocks; - __u16 unused; - __u32 free_blocks_count; + __u16 mdata_blocks; + __u32 free_clusters_count; }; /* Indexes used to index group tables in ext4_new_group_data */ @@ -528,75 +692,96 @@ enum { /* * Flags used by ext4_map_blocks() */ - /* Allocate any needed blocks and/or convert an unitialized + /* 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 unitialized extent */ -#define EXT4_GET_BLOCKS_UNINIT_EXT 0x0002 -#define EXT4_GET_BLOCKS_CREATE_UNINIT_EXT (EXT4_GET_BLOCKS_UNINIT_EXT|\ + /* 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) /* 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 - unitialized extents if not allocated, split the uninitialized - extent if blocks has been preallocated already*/ -#define EXT4_GET_BLOCKS_PRE_IO 0x0008 + /* + * This means that we cannot merge newly allocated extents, and if we + * found an unwritten extent, we need to split it. + */ +#define EXT4_GET_BLOCKS_SPLIT_NOMERGE 0x0008 + /* + * Caller is from the dio or dioread_nolock buffered IO, reqest to + * create an unwritten extent if it does not exist or split the + * found unwritten extent. Also do not merge the newly created + * unwritten extent, io end will convert unwritten to written, + * and try to merge the written extent. + */ +#define EXT4_GET_BLOCKS_IO_CREATE_EXT (EXT4_GET_BLOCKS_SPLIT_NOMERGE|\ + EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT) + /* Convert unwritten extent to initialized. */ #define EXT4_GET_BLOCKS_CONVERT 0x0010 -#define EXT4_GET_BLOCKS_IO_CREATE_EXT (EXT4_GET_BLOCKS_PRE_IO|\ - EXT4_GET_BLOCKS_CREATE_UNINIT_EXT) - /* Convert extent to initialized after IO complete */ -#define EXT4_GET_BLOCKS_IO_CONVERT_EXT (EXT4_GET_BLOCKS_CONVERT|\ - EXT4_GET_BLOCKS_CREATE_UNINIT_EXT) /* 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 - /* Request will not result in inode size update (user for fallocate) */ -#define EXT4_GET_BLOCKS_KEEP_SIZE 0x0080 - /* Do not take i_data_sem locking in ext4_map_blocks */ -#define EXT4_GET_BLOCKS_NO_LOCK 0x0100 - /* Do not put hole in extent cache */ -#define EXT4_GET_BLOCKS_NO_PUT_HOLE 0x0200 + /* 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 is in the context of data submission, such as writeback, + * fsync, etc. Especially, in the generic writeback path, caller will + * submit data before dropping transaction handle. This allows jbd2 + * to avoid submitting data before commit. */ +#define EXT4_GET_BLOCKS_IO_SUBMIT 0x0400 + /* 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_GET_BLOCKS_IO_SUBMIT) + /* Caller is in the atomic contex, find extent if it has been cached */ +#define EXT4_GET_BLOCKS_CACHED_NOWAIT 0x0800 +/* + * Atomic write caller needs this to query in the slow path of mixed mapping + * case, when a contiguous extent can be split across two adjacent leaf nodes. + * Look EXT4_MAP_QUERY_LAST_IN_LEAF. + */ +#define EXT4_GET_BLOCKS_QUERY_LAST_IN_LEAF 0x1000 + +/* + * 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 +/* + * ext4_map_query_blocks() uses this filter mask to filter the flags needed to + * pass while lookup/querying of on disk extent tree. + */ +#define EXT4_EX_QUERY_FILTER (EXT4_EX_NOCACHE | EXT4_EX_FORCE_CACHE |\ + EXT4_EX_NOFAIL |\ + EXT4_GET_BLOCKS_QUERY_LAST_IN_LEAF) /* * 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_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 - -/* - * ioctl commands - */ -#define EXT4_IOC_GETFLAGS FS_IOC_GETFLAGS -#define EXT4_IOC_SETFLAGS FS_IOC_SETFLAGS -#define EXT4_IOC_GETVERSION _IOR('f', 3, long) -#define EXT4_IOC_SETVERSION _IOW('f', 4, long) -#define EXT4_IOC_GETVERSION_OLD FS_IOC_GETVERSION -#define EXT4_IOC_SETVERSION_OLD FS_IOC_SETVERSION -#define EXT4_IOC_GETRSVSZ _IOR('f', 5, long) -#define EXT4_IOC_SETRSVSZ _IOW('f', 6, long) -#define EXT4_IOC_GROUP_EXTEND _IOW('f', 7, unsigned long) -#define EXT4_IOC_GROUP_ADD _IOW('f', 8, struct ext4_new_group_input) -#define EXT4_IOC_MIGRATE _IO('f', 9) - /* note ioctl 10 reserved for an early version of the FIEMAP ioctl */ - /* note ioctl 11 reserved for filesystem-independent FIEMAP ioctl */ -#define EXT4_IOC_ALLOC_DA_BLKS _IO('f', 12) -#define EXT4_IOC_MOVE_EXT _IOWR('f', 15, struct move_extent) -#define EXT4_IOC_RESIZE_FS _IOW('f', 16, __u64) -#define EXT4_IOC_SWAP_BOOT _IO('f', 17) +#define EXT4_FREE_BLOCKS_RERESERVE_CLUSTER 0x0040 #if defined(__KERNEL__) && defined(CONFIG_COMPAT) /* * ioctl commands in 32 bit emulation */ -#define EXT4_IOC32_GETFLAGS FS_IOC32_GETFLAGS -#define EXT4_IOC32_SETFLAGS FS_IOC32_SETFLAGS #define EXT4_IOC32_GETVERSION _IOR('f', 3, int) #define EXT4_IOC32_SETVERSION _IOW('f', 4, int) #define EXT4_IOC32_GETRSVSZ _IOR('f', 5, int) @@ -610,6 +795,9 @@ enum { /* 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 */ @@ -671,15 +859,7 @@ struct ext4_inode { __le32 i_crtime; /* File Creation time */ __le32 i_crtime_extra; /* extra FileCreationtime (nsec << 2 | epoch) */ __le32 i_version_hi; /* high 32 bits for 64-bit version */ -}; - -struct move_extent { - __u32 reserved; /* should be zero */ - __u32 donor_fd; /* donor file descriptor */ - __u64 orig_start; /* logical start offset in block for orig */ - __u64 donor_start; /* logical start offset in block for donor */ - __u64 len; /* block length to be moved */ - __u64 moved_len; /* moved block length */ + __le32 i_projid; /* Project ID */ }; #define EXT4_EPOCH_BITS 2 @@ -702,58 +882,101 @@ struct move_extent { <= (EXT4_GOOD_OLD_INODE_SIZE + \ (einode)->i_extra_isize)) \ -static inline __le32 ext4_encode_extra_time(struct timespec *time) +/* + * 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 ts) { - return cpu_to_le32((sizeof(time->tv_sec) > 4 ? - (time->tv_sec >> 32) & EXT4_EPOCH_MASK : 0) | - ((time->tv_nsec << EXT4_EPOCH_BITS) & EXT4_NSEC_MASK)); + u32 extra = ((ts.tv_sec - (s32)ts.tv_sec) >> 32) & EXT4_EPOCH_MASK; + return cpu_to_le32(extra | (ts.tv_nsec << EXT4_EPOCH_BITS)); } -static inline void ext4_decode_extra_time(struct timespec *time, __le32 extra) +static inline struct timespec64 ext4_decode_extra_time(__le32 base, + __le32 extra) { - if (sizeof(time->tv_sec) > 4) - time->tv_sec |= (__u64)(le32_to_cpu(extra) & EXT4_EPOCH_MASK) - << 32; - time->tv_nsec = (le32_to_cpu(extra) & EXT4_NSEC_MASK) >> EXT4_EPOCH_BITS; + struct timespec64 ts = { .tv_sec = (signed)le32_to_cpu(base) }; + + if (unlikely(extra & cpu_to_le32(EXT4_EPOCH_MASK))) + ts.tv_sec += (u64)(le32_to_cpu(extra) & EXT4_EPOCH_MASK) << 32; + ts.tv_nsec = (le32_to_cpu(extra) & EXT4_NSEC_MASK) >> EXT4_EPOCH_BITS; + return ts; } -#define EXT4_INODE_SET_XTIME(xtime, inode, raw_inode) \ -do { \ - (raw_inode)->xtime = cpu_to_le32((inode)->xtime.tv_sec); \ - if (EXT4_FITS_IN_INODE(raw_inode, EXT4_I(inode), xtime ## _extra)) \ - (raw_inode)->xtime ## _extra = \ - ext4_encode_extra_time(&(inode)->xtime); \ +#define EXT4_INODE_SET_XTIME_VAL(xtime, inode, raw_inode, ts) \ +do { \ + if (EXT4_FITS_IN_INODE(raw_inode, EXT4_I(inode), xtime ## _extra)) { \ + (raw_inode)->xtime = cpu_to_le32((ts).tv_sec); \ + (raw_inode)->xtime ## _extra = ext4_encode_extra_time(ts); \ + } else \ + (raw_inode)->xtime = cpu_to_le32(clamp_t(int32_t, (ts).tv_sec, S32_MIN, S32_MAX)); \ +} while (0) + +#define EXT4_INODE_SET_ATIME(inode, raw_inode) \ + EXT4_INODE_SET_XTIME_VAL(i_atime, inode, raw_inode, inode_get_atime(inode)) + +#define EXT4_INODE_SET_MTIME(inode, raw_inode) \ + EXT4_INODE_SET_XTIME_VAL(i_mtime, inode, raw_inode, inode_get_mtime(inode)) + +#define EXT4_INODE_SET_CTIME(inode, raw_inode) \ + EXT4_INODE_SET_XTIME_VAL(i_ctime, inode, raw_inode, inode_get_ctime(inode)) + +#define EXT4_EINODE_SET_XTIME(xtime, einode, raw_inode) \ + if (EXT4_FITS_IN_INODE(raw_inode, einode, xtime)) \ + EXT4_INODE_SET_XTIME_VAL(xtime, &((einode)->vfs_inode), \ + raw_inode, (einode)->xtime) + +#define EXT4_INODE_GET_XTIME_VAL(xtime, inode, raw_inode) \ + (EXT4_FITS_IN_INODE(raw_inode, EXT4_I(inode), xtime ## _extra) ? \ + ext4_decode_extra_time((raw_inode)->xtime, \ + (raw_inode)->xtime ## _extra) : \ + (struct timespec64) { \ + .tv_sec = (signed)le32_to_cpu((raw_inode)->xtime) \ + }) + +#define EXT4_INODE_GET_ATIME(inode, raw_inode) \ +do { \ + inode_set_atime_to_ts(inode, \ + EXT4_INODE_GET_XTIME_VAL(i_atime, inode, raw_inode)); \ } 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); \ +#define EXT4_INODE_GET_MTIME(inode, raw_inode) \ +do { \ + inode_set_mtime_to_ts(inode, \ + EXT4_INODE_GET_XTIME_VAL(i_mtime, inode, raw_inode)); \ } while (0) -#define EXT4_INODE_GET_XTIME(xtime, inode, raw_inode) \ -do { \ - (inode)->xtime.tv_sec = (signed)le32_to_cpu((raw_inode)->xtime); \ - if (EXT4_FITS_IN_INODE(raw_inode, EXT4_I(inode), xtime ## _extra)) \ - ext4_decode_extra_time(&(inode)->xtime, \ - raw_inode->xtime ## _extra); \ - else \ - (inode)->xtime.tv_nsec = 0; \ +#define EXT4_INODE_GET_CTIME(inode, raw_inode) \ +do { \ + inode_set_ctime_to_ts(inode, \ + EXT4_INODE_GET_XTIME_VAL(i_ctime, inode, raw_inode)); \ } while (0) -#define EXT4_EINODE_GET_XTIME(xtime, einode, raw_inode) \ -do { \ - if (EXT4_FITS_IN_INODE(raw_inode, einode, xtime)) \ - (einode)->xtime.tv_sec = \ - (signed)le32_to_cpu((raw_inode)->xtime); \ - if (EXT4_FITS_IN_INODE(raw_inode, einode, xtime ## _extra)) \ - ext4_decode_extra_time(&(einode)->xtime, \ - raw_inode->xtime ## _extra); \ - else \ - (einode)->xtime.tv_nsec = 0; \ +#define EXT4_EINODE_GET_XTIME(xtime, einode, raw_inode) \ +do { \ + if (EXT4_FITS_IN_INODE(raw_inode, einode, xtime)) \ + (einode)->xtime = \ + EXT4_INODE_GET_XTIME_VAL(xtime, &(einode->vfs_inode), \ + raw_inode); \ + else \ + (einode)->xtime = (struct timespec64){0, 0}; \ } while (0) #define i_disk_version osd1.linux1.l_i_version @@ -784,6 +1007,32 @@ do { \ #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 + * I_DATA_SEM_EA - Used for ea_inodes only + */ +enum { + I_DATA_SEM_NORMAL = 0, + I_DATA_SEM_OTHER, + I_DATA_SEM_QUOTA, + I_DATA_SEM_EA +}; + /* * fourth extended file system inode data in memory @@ -796,7 +1045,7 @@ struct ext4_inode_info { /* * i_block_group is the number of the block group which contains * this file's inode. Constant across the lifetime of the inode, - * it is ued for making block allocation decisions - we try to + * 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. */ @@ -809,14 +1058,47 @@ struct ext4_inode_info { /* * Extended attributes can be read independently of the main file - * data. Taking i_mutex even when reading would cause contention + * 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; - struct list_head i_orphan; /* unlinked but open inodes */ + /* + * 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 */ + + /* 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; + + spinlock_t i_raw_lock; /* protects updates to the raw inode */ + + /* 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 + * and inode's EXT4_FC_STATE_COMMITTING state bit. + */ + spinlock_t i_fc_lock; /* * i_disksize keeps track of what the inode size is ON DISK, not @@ -851,31 +1133,36 @@ struct ext4_inode_info { /* * File creation time. Its function is same as that of - * struct timespec i_{a,c,m}time in the generic inode. + * struct timespec64 i_{a,c,m}time in the generic inode. */ - struct timespec i_crtime; + struct timespec64 i_crtime; /* mballoc */ - struct list_head i_prealloc_list; - spinlock_t i_prealloc_lock; + atomic_t i_prealloc_active; + + /* allocation reservation info for delalloc */ + /* In case of bigalloc, this refer to clusters rather than blocks */ + unsigned int i_reserved_data_blocks; + struct rb_root i_prealloc_node; + rwlock_t i_prealloc_lock; /* extents status tree */ struct ext4_es_tree i_es_tree; rwlock_t i_es_lock; - struct list_head i_es_lru; - unsigned int i_es_lru_nr; /* protected by i_es_lock */ - unsigned long i_touch_when; /* jiffies of last accessing */ + struct list_head i_es_list; + 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 */ + u64 i_es_seq; /* Change counter for extents. + Protected by i_es_lock */ /* ialloc */ ext4_group_t i_last_alloc_group; - /* allocation reservation info for delalloc */ - /* In case of bigalloc, these refer to clusters rather than blocks */ - unsigned int i_reserved_data_blocks; - unsigned int i_reserved_meta_blocks; - unsigned int i_allocated_meta_blocks; - ext4_lblk_t i_da_metadata_calc_last_lblock; - int i_da_metadata_calc_len; + /* pending cluster reservations for bigalloc file systems */ + struct ext4_pending_tree i_pending_tree; /* on-disk additional length */ __u16 i_extra_isize; @@ -888,6 +1175,7 @@ struct ext4_inode_info { /* quota space reservation, managed internally by quota code */ qsize_t i_reserved_quota; #endif + spinlock_t i_block_reservation_lock; /* Lock protecting lists below */ spinlock_t i_completed_io_lock; @@ -896,17 +1184,7 @@ struct ext4_inode_info { * transaction reserved */ struct list_head i_rsv_conversion_list; - /* - * Completed IOs that need unwritten extents handling and don't have - * transaction reserved - */ - struct list_head i_unrsv_conversion_list; - atomic_t i_ioend_count; /* Number of outstanding io_end structs */ - atomic_t i_unwritten; /* Nr. of inflight conversions pending */ struct work_struct i_rsv_conversion_work; - struct work_struct i_unrsv_conversion_work; - - spinlock_t i_block_reservation_lock; /* * Transactions that contain inode's metadata needed to complete @@ -915,8 +1193,22 @@ struct ext4_inode_info { tid_t i_sync_tid; tid_t i_datasync_tid; +#ifdef CONFIG_QUOTA + struct dquot __rcu *i_dquot[MAXQUOTAS]; +#endif + /* Precomputed uuid+inum+igen checksum for seeding inode checksums */ __u32 i_csum_seed; + + kprojid_t i_projid; + +#ifdef CONFIG_FS_ENCRYPTION + struct fscrypt_inode_info *i_crypt_info; +#endif + +#ifdef CONFIG_FS_VERITY + struct fsverity_info *i_verity_info; +#endif }; /* @@ -925,6 +1217,7 @@ struct ext4_inode_info { #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 @@ -936,6 +1229,7 @@ struct ext4_inode_info { /* * 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 */ @@ -944,6 +1238,11 @@ struct ext4_inode_info { #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 */ @@ -954,12 +1253,20 @@ struct ext4_inode_info { #define EXT4_MOUNT_POSIX_ACL 0x08000 /* POSIX Access Control Lists */ #define EXT4_MOUNT_NO_AUTO_DA_ALLOC 0x10000 /* No auto delalloc mapping */ #define EXT4_MOUNT_BARRIER 0x20000 /* Use block barriers */ -#define EXT4_MOUNT_QUOTA 0x80000 /* Some quota option set */ -#define EXT4_MOUNT_USRQUOTA 0x100000 /* "old" user quota */ -#define EXT4_MOUNT_GRPQUOTA 0x200000 /* "old" group quota */ +#define EXT4_MOUNT_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 */ @@ -976,6 +1283,18 @@ struct ext4_inode_info { #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 */ +#define EXT4_MOUNT2_MB_OPTIMIZE_SCAN 0x00000080 /* Optimize group + * scanning in mballoc + */ +#define EXT4_MOUNT2_ABORT 0x00000100 /* Abort filesystem */ #define clear_opt(sb, opt) EXT4_SB(sb)->s_mount_opt &= \ ~EXT4_MOUNT_##opt @@ -993,15 +1312,13 @@ struct ext4_inode_info { #define ext4_test_and_set_bit __test_and_set_bit_le #define ext4_set_bit __set_bit_le -#define ext4_set_bit_atomic ext2_set_bit_atomic #define ext4_test_and_clear_bit __test_and_clear_bit_le #define ext4_clear_bit __clear_bit_le -#define ext4_clear_bit_atomic ext2_clear_bit_atomic #define ext4_test_bit test_bit_le #define ext4_find_next_zero_bit find_next_zero_bit_le #define ext4_find_next_bit find_next_bit_le -extern void ext4_set_bits(void *bm, int cur, int len); +extern void mb_set_bits(void *bm, int cur, int len); /* * Maximal mount counts between two filesystem checks @@ -1020,6 +1337,8 @@ extern void ext4_set_bits(void *bm, int cur, int len); /* Metadata checksum algorithm codes */ #define EXT4_CRC32C_CHKSUM 1 +#define EXT4_LABEL_MAX 16 + /* * Structure of the super block */ @@ -1069,8 +1388,8 @@ struct ext4_super_block { /*60*/ __le32 s_feature_incompat; /* incompatible feature set */ __le32 s_feature_ro_compat; /* readonly-compatible feature set */ /*68*/ __u8 s_uuid[16]; /* 128-bit uuid for volume */ -/*78*/ char s_volume_name[16]; /* volume name */ -/*88*/ char s_last_mounted[64]; /* directory where last mounted */ +/*78*/ char s_volume_name[EXT4_LABEL_MAX] __nonstring; /* 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 @@ -1094,7 +1413,7 @@ struct ext4_super_block { __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 */ + /* 64bit support valid if EXT4_FEATURE_INCOMPAT_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 */ @@ -1107,7 +1426,8 @@ struct ext4_super_block { __le32 s_raid_stripe_width; /* blocks on all data disks (N*stride)*/ __u8 s_log_groups_per_flex; /* FLEX_BG group size */ __u8 s_checksum_type; /* metadata checksum algorithm used */ - __le16 s_reserved_pad; + __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 */ @@ -1120,19 +1440,38 @@ struct ext4_super_block { __le32 s_first_error_time; /* first time an error happened */ __le32 s_first_error_ino; /* inode involved in first error */ __le64 s_first_error_block; /* block involved of first error */ - __u8 s_first_error_func[32]; /* function where the error happened */ + __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]; /* function where the error happened */ + __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_reserved[108]; /* Padding to the end of the block */ + __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 */ + __le32 s_orphan_file_inum; /* Inode for tracking orphan inodes */ + __le16 s_def_resuid_hi; + __le16 s_def_resgid_hi; + __le32 s_reserved[93]; /* Padding to the end of the block */ __le32 s_checksum; /* crc32c(superblock) */ }; @@ -1140,11 +1479,58 @@ struct ext4_super_block { #ifdef __KERNEL__ +/* 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_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); +} + +#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 { + atomic_t ob_free_entries; /* Number of free orphan entries in block */ + struct buffer_head *ob_bh; /* Buffer for orphan block */ +}; + /* - * run-time mount flags + * Info about orphan file. */ -#define EXT4_MF_MNTDIR_SAMPLED 0x0001 -#define EXT4_MF_FS_ABORTED 0x0002 /* Fatal error detected */ +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 @@ -1166,11 +1552,13 @@ struct ext4_sb_info { loff_t s_bitmap_maxbytes; /* max bytes for bitmap files */ struct buffer_head * s_sbh; /* Buffer containing the super block */ struct ext4_super_block *s_es; /* Pointer to the super block in the buffer */ - struct buffer_head **s_group_desc; + /* Array of bh's for the block group descriptors */ + struct buffer_head * __rcu *s_group_desc; unsigned int s_mount_opt; unsigned int s_mount_opt2; - unsigned int s_mount_flags; + unsigned long s_mount_flags; unsigned int s_def_mount_opt; + unsigned int s_def_mount_opt2; ext4_fsblk_t s_sb_block; atomic64_t s_resv_clusters; kuid_t s_resuid; @@ -1183,37 +1571,39 @@ struct ext4_sb_info { int s_first_ino; unsigned int s_inode_readahead_blks; unsigned int s_inode_goal; - spinlock_t s_next_gen_lock; - u32 s_next_generation; u32 s_hash_seed[4]; int s_def_hash_version; - int s_hash_unsigned; /* 3 if hash should be signed, 0 if not */ + 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; + 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; - struct list_head s_orphan; - struct mutex s_orphan_lock; - unsigned long s_resize_flags; /* Flags indicating if there - is a resizer */ + unsigned long s_ext4_flags; /* Ext4 superblock flags */ + 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 *journal_bdev; + struct file *s_journal_bdev_file; #ifdef CONFIG_QUOTA - char *s_qf_names[MAXQUOTAS]; /* Names of quota files with journalled 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 rb_root system_blks; + struct ext4_system_blocks __rcu *s_system_blks; #ifdef EXTENTS_STATS /* ext4 extents stats */ @@ -1226,15 +1616,24 @@ struct ext4_sb_info { #endif /* for buddy allocator */ - struct ext4_group_info ***s_group_info; + 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; + atomic_t s_mb_free_pending; + struct list_head s_freed_data_list[2]; /* List of blocks to be freed + after commit completed */ + struct list_head s_discard_list; + struct work_struct s_discard_work; + atomic_t s_retry_alloc_pending; + struct xarray *s_mb_avg_fragment_size; + struct xarray *s_mb_largest_free_orders; /* tunables */ unsigned long s_stripe; + 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; @@ -1242,21 +1641,33 @@ struct ext4_sb_info { unsigned int s_mb_order2_reqs; unsigned int s_mb_group_prealloc; unsigned int s_max_dir_size_kb; + unsigned int s_mb_prefetch; + unsigned int s_mb_prefetch_limit; + unsigned int s_mb_best_avail_max_trim_order; + unsigned int s_sb_update_sec; + unsigned int s_sb_update_kb; + /* where last allocation was done - for stream allocation */ - unsigned long s_mb_last_group; - unsigned long s_mb_last_start; + ext4_group_t *s_mb_last_groups; + unsigned int s_mb_nr_global_goals; /* 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_cX_ex_scanned[EXT4_MB_NUM_CRS]; /* total extents scanned */ + atomic_t s_bal_groups_scanned; /* number of groups scanned */ atomic_t s_bal_goals; /* goal hits */ + atomic_t s_bal_stream_goals; /* stream allocation global goal hits */ + atomic_t s_bal_len_goals; /* len goal hits */ atomic_t s_bal_breaks; /* too long searches */ atomic_t s_bal_2orders; /* 2^order hits */ - spinlock_t s_bal_lock; - unsigned long s_mb_buddies_generated; - unsigned long long s_mb_generation_time; + atomic64_t s_bal_cX_groups_considered[EXT4_MB_NUM_CRS]; + atomic64_t s_bal_cX_hits[EXT4_MB_NUM_CRS]; + atomic64_t s_bal_cX_failed[EXT4_MB_NUM_CRS]; /* 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; @@ -1273,11 +1684,9 @@ struct ext4_sb_info { unsigned int s_extent_max_zeroout_kb; unsigned int s_log_groups_per_flex; - struct flex_groups *s_flex_groups; + struct flex_groups * __rcu *s_flex_groups; ext4_group_t s_flex_groups_allocated; - /* workqueue for unreserved extent convertions (dio) */ - struct workqueue_struct *unrsv_conversion_wq; /* workqueue for reserved extent conversions (buffered io) */ struct workqueue_struct *rsv_conversion_wq; @@ -1293,20 +1702,108 @@ struct ext4_sb_info { struct task_struct *s_mmp_tsk; /* record the last minlen when FITRIM is called. */ - atomic_t s_last_trim_minblks; + unsigned long s_last_trim_minblks; - /* Reference to checksum algorithm driver via cryptoapi */ - struct crypto_shash *s_chksum_driver; + /* minimum folio order of a page cache allocation */ + u16 s_min_folio_order; + /* supported maximum folio order, 0 means not supported */ + u16 s_max_folio_order; /* 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_lru; - unsigned long s_es_last_sorted; - struct percpu_counter s_extent_cache_cnt; - spinlock_t s_es_lru_lock ____cacheline_aligned_in_smp; + struct shrinker *s_es_shrinker; + struct list_head s_es_list; /* List of inodes with reclaimable extents */ + long s_es_nr_inode; + 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; + + /* Encryption policy for '-o test_dummy_encryption' */ + struct fscrypt_dummy_policy s_dummy_enc_policy; + + /* + * Barrier between writepages ops and changing any inode's JOURNAL_DATA + * or EXTENTS flag or between writepages ops and changing DELALLOC or + * DIOREAD_NOLOCK mount options on remount. + */ + 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 the on-disk + * superblock, we queue the work here. This is used to update + * the error information in the superblock, and for periodic + * updates of the superblock called from the commit callback + * function. + */ + struct work_struct s_sb_upd_work; + + /* Atomic write unit values in bytes */ + unsigned int s_awu_min; + unsigned int s_awu_max; + + /* 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. + */ + struct mutex 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) @@ -1318,63 +1815,160 @@ static inline struct ext4_inode_info *EXT4_I(struct inode *inode) return container_of(inode, struct ext4_inode_info, vfs_inode); } -static inline struct timespec ext4_current_time(struct inode *inode) +static inline int ext4_writepages_down_read(struct super_block *sb) +{ + percpu_down_read(&EXT4_SB(sb)->s_writepages_rwsem); + return memalloc_nofs_save(); +} + +static inline void ext4_writepages_up_read(struct super_block *sb, int ctx) +{ + memalloc_nofs_restore(ctx); + percpu_up_read(&EXT4_SB(sb)->s_writepages_rwsem); +} + +static inline int ext4_writepages_down_write(struct super_block *sb) { - return (inode->i_sb->s_time_gran < NSEC_PER_SEC) ? - current_fs_time(inode->i_sb) : CURRENT_TIME_SEC; + percpu_down_write(&EXT4_SB(sb)->s_writepages_rwsem); + return memalloc_nofs_save(); +} + +static inline void ext4_writepages_up_write(struct super_block *sb, int ctx) +{ + memalloc_nofs_restore(ctx); + percpu_up_write(&EXT4_SB(sb)->s_writepages_rwsem); } static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino) { return ino == EXT4_ROOT_INO || - ino == EXT4_USR_QUOTA_INO || - ino == EXT4_GRP_QUOTA_INO || - ino == EXT4_BOOT_LOADER_INO || - ino == EXT4_JOURNAL_INO || - ino == EXT4_RESIZE_INO || (ino >= EXT4_FIRST_INO(sb) && ino <= le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count)); } -static inline void ext4_set_io_unwritten_flag(struct inode *inode, - struct ext4_io_end *io_end) +static inline int ext4_get_resuid(struct ext4_super_block *es) { - if (!(io_end->flag & EXT4_IO_END_UNWRITTEN)) { - /* Writeback has to have coversion transaction reserved */ - WARN_ON(EXT4_SB(inode->i_sb)->s_journal && !io_end->handle && - !(io_end->flag & EXT4_IO_END_DIRECT)); - io_end->flag |= EXT4_IO_END_UNWRITTEN; - atomic_inc(&EXT4_I(inode)->i_unwritten); - } + return le16_to_cpu(es->s_def_resuid) | + le16_to_cpu(es->s_def_resuid_hi) << 16; +} + +static inline int ext4_get_resgid(struct ext4_super_block *es) +{ + return le16_to_cpu(es->s_def_resgid) | + le16_to_cpu(es->s_def_resgid_hi) << 16; +} + +/* + * 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_FC_INELIGIBLE, /* Fast commit ineligible */ + EXT4_MF_JOURNAL_DESTROY /* Journal is in process of destroying */ +}; + +static inline void ext4_set_mount_flag(struct super_block *sb, int bit) +{ + set_bit(bit, &EXT4_SB(sb)->s_mount_flags); } -static inline ext4_io_end_t *ext4_inode_aio(struct inode *inode) +static inline void ext4_clear_mount_flag(struct super_block *sb, int bit) { - return inode->i_private; + clear_bit(bit, &EXT4_SB(sb)->s_mount_flags); } -static inline void ext4_inode_aio_set(struct inode *inode, ext4_io_end_t *io) +static inline int ext4_test_mount_flag(struct super_block *sb, int bit) { - inode->i_private = io; + 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; } /* + * 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_DIO_UNWRITTEN, /* need convert on dio done*/ EXT4_STATE_NEWENTRY, /* File just added to dir */ - EXT4_STATE_DELALLOC_RESERVED, /* blks already reserved for delalloc */ - EXT4_STATE_DIOREAD_LOCK, /* Disable support for dio read - nolocking */ EXT4_STATE_MAY_INLINE_DATA, /* may have in-inode data */ - EXT4_STATE_ORDERED_MODE, /* data=ordered mode */ + EXT4_STATE_EXT_PRECACHED, /* extents have been precached */ + EXT4_STATE_LUSTRE_EA_INODE, /* Lustre-style ea_inode */ + EXT4_STATE_VERITY_IN_PROGRESS, /* building fs-verity Merkle tree */ + EXT4_STATE_FC_COMMITTING, /* Fast commit ongoing */ + EXT4_STATE_FC_FLUSHING_DATA, /* Fast commit flushing data */ + EXT4_STATE_ORPHAN_FILE, /* Inode orphaned in orphan file */ }; #define EXT4_INODE_BIT_FNS(name, field, offset) \ @@ -1391,7 +1985,18 @@ 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) @@ -1414,9 +2019,25 @@ static inline void ext4_clear_state_flags(struct ext4_inode_info *ei) #define EXT4_SB(sb) (sb) #endif +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 /* + * Check whether the inode is tracked as orphan (either in orphan file or + * orphan list). + */ +static inline bool ext4_inode_orphan_tracked(struct inode *inode) +{ + return ext4_test_inode_state(inode, EXT4_STATE_ORPHAN_FILE) || + !list_empty(&EXT4_I(inode)->i_orphan); +} + +/* * Codes for operating systems */ #define EXT4_OS_LINUX 0 @@ -1431,40 +2052,35 @@ static inline void ext4_clear_state_flags(struct ext4_inode_info *ei) #define EXT4_GOOD_OLD_REV 0 /* The good old (original) format */ #define EXT4_DYNAMIC_REV 1 /* V2 format w/ dynamic inode sizes */ -#define EXT4_CURRENT_REV EXT4_GOOD_OLD_REV #define EXT4_MAX_SUPP_REV EXT4_DYNAMIC_REV #define EXT4_GOOD_OLD_INODE_SIZE 128 +#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_HAS_COMPAT_FEATURE(sb,mask) \ - ((EXT4_SB(sb)->s_es->s_feature_compat & cpu_to_le32(mask)) != 0) -#define EXT4_HAS_RO_COMPAT_FEATURE(sb,mask) \ - ((EXT4_SB(sb)->s_es->s_feature_ro_compat & cpu_to_le32(mask)) != 0) -#define EXT4_HAS_INCOMPAT_FEATURE(sb,mask) \ - ((EXT4_SB(sb)->s_es->s_feature_incompat & cpu_to_le32(mask)) != 0) -#define EXT4_SET_COMPAT_FEATURE(sb,mask) \ - EXT4_SB(sb)->s_es->s_feature_compat |= cpu_to_le32(mask) -#define EXT4_SET_RO_COMPAT_FEATURE(sb,mask) \ - EXT4_SB(sb)->s_es->s_feature_ro_compat |= cpu_to_le32(mask) -#define EXT4_SET_INCOMPAT_FEATURE(sb,mask) \ - EXT4_SB(sb)->s_es->s_feature_incompat |= cpu_to_le32(mask) -#define EXT4_CLEAR_COMPAT_FEATURE(sb,mask) \ - EXT4_SB(sb)->s_es->s_feature_compat &= ~cpu_to_le32(mask) -#define EXT4_CLEAR_RO_COMPAT_FEATURE(sb,mask) \ - EXT4_SB(sb)->s_es->s_feature_ro_compat &= ~cpu_to_le32(mask) -#define EXT4_CLEAR_INCOMPAT_FEATURE(sb,mask) \ - EXT4_SB(sb)->s_es->s_feature_incompat &= ~cpu_to_le32(mask) - #define EXT4_FEATURE_COMPAT_DIR_PREALLOC 0x0001 #define EXT4_FEATURE_COMPAT_IMAGIC_INODES 0x0002 #define EXT4_FEATURE_COMPAT_HAS_JOURNAL 0x0004 #define EXT4_FEATURE_COMPAT_EXT_ATTR 0x0008 #define EXT4_FEATURE_COMPAT_RESIZE_INODE 0x0010 #define EXT4_FEATURE_COMPAT_DIR_INDEX 0x0020 +#define EXT4_FEATURE_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 +#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 @@ -1482,6 +2098,11 @@ static inline void ext4_clear_state_flags(struct ext4_inode_info *ei) * 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 +#define EXT4_FEATURE_RO_COMPAT_VERITY 0x8000 +#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 @@ -1494,9 +2115,110 @@ static inline void ext4_clear_state_flags(struct ext4_inode_info *ei) #define EXT4_FEATURE_INCOMPAT_FLEX_BG 0x0200 #define EXT4_FEATURE_INCOMPAT_EA_INODE 0x0400 /* EA in inode */ #define EXT4_FEATURE_INCOMPAT_DIRDATA 0x1000 /* data in dirent */ -#define EXT4_FEATURE_INCOMPAT_BG_USE_META_CSUM 0x2000 /* use crc32c for bg */ +#define EXT4_FEATURE_INCOMPAT_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_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_FEATURE_RO_COMPAT_FUNCS(verity, VERITY) +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| \ @@ -1513,15 +2235,21 @@ static inline void ext4_clear_state_flags(struct ext4_inode_info *ei) EXT4_FEATURE_RO_COMPAT_LARGE_FILE| \ EXT4_FEATURE_RO_COMPAT_BTREE_DIR) -#define EXT4_FEATURE_COMPAT_SUPP EXT2_FEATURE_COMPAT_EXT_ATTR +#define EXT4_FEATURE_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_FEATURE_INCOMPAT_MMP | \ - EXT4_FEATURE_INCOMPAT_INLINE_DATA) + 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_FEATURE_RO_COMPAT_GDT_CSUM| \ @@ -1531,7 +2259,75 @@ static inline void ext4_clear_state_flags(struct ext4_inode_info *ei) EXT4_FEATURE_RO_COMPAT_HUGE_FILE |\ EXT4_FEATURE_RO_COMPAT_BIGALLOC |\ EXT4_FEATURE_RO_COMPAT_METADATA_CSUM|\ - EXT4_FEATURE_RO_COMPAT_QUOTA) + EXT4_FEATURE_RO_COMPAT_QUOTA |\ + EXT4_FEATURE_RO_COMPAT_PROJECT |\ + 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 + */ +enum { + EXT4_FLAGS_RESIZING, /* Avoid superblock update and resize race */ + EXT4_FLAGS_SHUTDOWN, /* Prevent access to the file system */ + EXT4_FLAGS_BDEV_IS_DAX, /* Current block device support DAX */ + EXT4_FLAGS_EMERGENCY_RO,/* Emergency read-only due to fs errors */ +}; + +static inline int ext4_forced_shutdown(struct super_block *sb) +{ + return test_bit(EXT4_FLAGS_SHUTDOWN, &EXT4_SB(sb)->s_ext4_flags); +} + +static inline int ext4_emergency_ro(struct super_block *sb) +{ + return test_bit(EXT4_FLAGS_EMERGENCY_RO, &EXT4_SB(sb)->s_ext4_flags); +} + +static inline int ext4_emergency_state(struct super_block *sb) +{ + if (unlikely(ext4_forced_shutdown(sb))) + return -EIO; + if (unlikely(ext4_emergency_ro(sb))) + return -EROFS; + return 0; +} /* * Default values for user and/or group using reserved blocks @@ -1539,6 +2335,11 @@ static inline void ext4_clear_state_flags(struct ext4_inode_info *ei) #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 /* @@ -1559,10 +2360,19 @@ static inline void ext4_clear_state_flags(struct ext4_inode_info *ei) #define EXT4_DEFM_NODELALLOC 0x0800 /* - * Default journal batch times + * Default journal batch times and ioprio. */ #define EXT4_DEF_MIN_BATCH_TIME 0 #define EXT4_DEF_MAX_BATCH_TIME 15000 /* 15ms */ +#define EXT4_DEF_JOURNAL_IOPRIO (IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, 3)) + + +/* + * Default values for superblock update + */ +#define EXT4_DEF_SB_UPDATE_INTERVAL_SEC (3600) /* seconds (1 hour) */ +#define EXT4_DEF_SB_UPDATE_INTERVAL_KB (16384) /* kilobytes (16MB) */ + /* * Minimum number of groups in a flexgroup before we separate out @@ -1574,6 +2384,10 @@ static inline void ext4_clear_state_flags(struct ext4_inode_info *ei) * Structure of a directory entry */ #define EXT4_NAME_LEN 255 +/* + * 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 */ @@ -1582,6 +2396,17 @@ struct ext4_dir_entry { 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 @@ -1592,11 +2417,27 @@ struct ext4_dir_entry_2 { __le32 inode; /* Inode number */ __le16 rec_len; /* Directory entry length */ __u8 name_len; /* Name length */ - __u8 file_type; + __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(entry)->hash) +#define EXT4_DIRENT_MINOR_HASH(entry) \ + le32_to_cpu(EXT4_DIRENT_HASHES(entry)->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. */ @@ -1637,33 +2478,37 @@ struct ext4_dir_entry_tail { */ #define EXT4_DIR_PAD 4 #define EXT4_DIR_ROUND (EXT4_DIR_PAD - 1) -#define EXT4_DIR_REC_LEN(name_len) (((name_len) + 8 + EXT4_DIR_ROUND) & \ - ~EXT4_DIR_ROUND) #define EXT4_MAX_REC_LEN ((1<<16)-1) /* - * If we ever get support for fs block sizes > page_size, we'll need - * to remove the #if statements in the next two functions... + * 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); +} + static inline unsigned int ext4_rec_len_from_disk(__le16 dlen, unsigned blocksize) { unsigned len = le16_to_cpu(dlen); -#if (PAGE_CACHE_SIZE >= 65536) if (len == EXT4_MAX_REC_LEN || len == 0) return blocksize; return (len & 65532) | ((len & 3) << 16); -#else - return len; -#endif } static inline __le16 ext4_rec_len_to_disk(unsigned len, unsigned blocksize) { - if ((len > blocksize) || (blocksize > (1 << 18)) || (len & 3)) - BUG(); -#if (PAGE_CACHE_SIZE >= 65536) + BUG_ON((len > blocksize) || (blocksize > (1 << 18)) || (len & 3)); if (len < 65536) return cpu_to_le16(len); if (len == blocksize) { @@ -1673,9 +2518,6 @@ static inline __le16 ext4_rec_len_to_disk(unsigned len, unsigned blocksize) return cpu_to_le16(0); } return cpu_to_le16((len & 65532) | ((len >> 16) & 3)); -#else - return cpu_to_le16(len); -#endif } /* @@ -1683,40 +2525,26 @@ static inline __le16 ext4_rec_len_to_disk(unsigned len, unsigned blocksize) * (c) Daniel Phillips, 2001 */ -#define is_dx(dir) (EXT4_HAS_COMPAT_FEATURE(dir->i_sb, \ - EXT4_FEATURE_COMPAT_DIR_INDEX) && \ +#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) (!is_dx(dir) && (dir)->i_nlink >= EXT4_LINK_MAX) +#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_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 +#define DX_HASH_LAST DX_HASH_SIPHASH -static inline u32 ext4_chksum(struct ext4_sb_info *sbi, u32 crc, - const void *address, unsigned int length) +static inline u32 ext4_chksum(u32 crc, const void *address, unsigned int length) { - struct { - struct shash_desc shash; - char ctx[4]; - } desc; - int err; - - BUG_ON(crypto_shash_descsize(sbi->s_chksum_driver)!=sizeof(desc.ctx)); - - desc.shash.tfm = sbi->s_chksum_driver; - desc.shash.flags = 0; - *(u32 *)desc.ctx = crc; - - err = crypto_shash_update(&desc.shash, address, length); - BUG_ON(err); - - return *(u32 *)desc.ctx; + return crc32c(crc, address, length); } #ifdef __KERNEL__ @@ -1741,6 +2569,21 @@ struct dx_hash_info */ #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 qstr 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 @@ -1757,6 +2600,12 @@ 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 @@ -1770,6 +2619,8 @@ struct dir_private_info { __u32 curr_hash; __u32 curr_minor_hash; __u32 next_hash; + u64 cookie; + bool initialized; }; /* calculate the first block number of the group */ @@ -1783,7 +2634,17 @@ ext4_group_first_block_no(struct super_block *sb, ext4_group_t group_no) /* * Special error return code only used by dx_probe() and its callers. */ -#define ERR_BAD_DX_DIR -75000 +#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; +} /* * Timeout and state flag for lazy initialization inode thread. @@ -1802,9 +2663,15 @@ struct ext4_lazy_init { struct mutex li_list_mtx; }; +enum ext4_li_mode { + EXT4_LI_MODE_PREFETCH_BBITMAP, + EXT4_LI_MODE_ITABLE, +}; + struct ext4_li_request { struct super_block *lr_super; - struct ext4_sb_info *lr_sbi; + enum ext4_li_mode lr_mode; + ext4_group_t lr_first_not_zeroed; ext4_group_t lr_next_group; struct list_head lr_request; unsigned long lr_next_sched; @@ -1892,16 +2759,16 @@ struct mmpd_data { /* 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, +void ext4_inode_bitmap_csum_set(struct super_block *sb, 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 buffer_head *bh); +int ext4_inode_bitmap_csum_verify(struct super_block *sb, 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 buffer_head *bh); +void ext4_block_bitmap_csum_set(struct super_block *sb, struct ext4_group_desc *gdp, struct buffer_head *bh); -int ext4_block_bitmap_csum_verify(struct super_block *sb, ext4_group_t group, +int ext4_block_bitmap_csum_verify(struct super_block *sb, struct ext4_group_desc *gdp, struct buffer_head *bh); @@ -1913,14 +2780,6 @@ extern void ext4_get_group_no_and_offset(struct super_block *sb, extern ext4_group_t ext4_get_group_number(struct super_block *sb, ext4_fsblk_t block); -extern void ext4_validate_block_bitmap(struct super_block *sb, - struct ext4_group_desc *desc, - unsigned int block_group, - struct buffer_head *bh); -extern unsigned int ext4_block_group(struct super_block *sb, - ext4_fsblk_t blocknr); -extern ext4_grpblk_t ext4_block_group_offset(struct super_block *sb, - ext4_fsblk_t blocknr); extern int ext4_bg_has_super(struct super_block *sb, ext4_group_t group); extern unsigned long ext4_bg_num_gdb(struct super_block *sb, ext4_group_t group); @@ -1932,115 +2791,218 @@ extern ext4_fsblk_t ext4_new_meta_blocks(handle_t *handle, struct inode *inode, 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 struct ext4_group_info *ext4_get_group_info(struct super_block *sb, + ext4_group_t group); 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); + 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 void ext4_init_block_bitmap(struct super_block *sb, - struct buffer_head *bh, - ext4_group_t group, - struct ext4_group_desc *desc); extern unsigned ext4_free_clusters_after_init(struct super_block *sb, ext4_group_t block_group, struct ext4_group_desc *gdp); -extern unsigned ext4_num_overhead_clusters(struct super_block *sb, - ext4_group_t block_group, - struct ext4_group_desc *gdp); ext4_fsblk_t ext4_inode_to_goal_block(struct inode *); +#if IS_ENABLED(CONFIG_UNICODE) +extern int ext4_fname_setup_ci_filename(struct inode *dir, + const struct qstr *iname, + struct ext4_filename *fname); + +static inline void ext4_fname_free_ci_filename(struct ext4_filename *fname) +{ + kfree(fname->cf_name.name); + fname->cf_name.name = NULL; +} +#else +static inline int ext4_fname_setup_ci_filename(struct inode *dir, + const struct qstr *iname, + struct ext4_filename *fname) +{ + return 0; +} + +static inline void ext4_fname_free_ci_filename(struct ext4_filename *fname) +{ +} +#endif + +/* ext4 encryption related stuff goes here crypto.c */ +#ifdef CONFIG_FS_ENCRYPTION +extern const struct fscrypt_operations ext4_cryptops; + +int ext4_fname_setup_filename(struct inode *dir, const struct qstr *iname, + int lookup, struct ext4_filename *fname); + +int ext4_fname_prepare_lookup(struct inode *dir, struct dentry *dentry, + struct ext4_filename *fname); + +void ext4_fname_free_filename(struct ext4_filename *fname); + +int ext4_ioctl_get_encryption_pwsalt(struct file *filp, void __user *arg); + +#else /* !CONFIG_FS_ENCRYPTION */ +static inline int ext4_fname_setup_filename(struct inode *dir, + const struct qstr *iname, + int lookup, + struct ext4_filename *fname) +{ + fname->usr_fname = iname; + fname->disk_name.name = (unsigned char *) iname->name; + fname->disk_name.len = iname->len; + + return ext4_fname_setup_ci_filename(dir, iname, fname); +} + +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) +{ + ext4_fname_free_ci_filename(fname); +} + +static inline int ext4_ioctl_get_encryption_pwsalt(struct file *filp, + void __user *arg) +{ + return -EOPNOTSUPP; +} +#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) \ +#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))) + (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); + __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, +extern int ext4_find_dest_de(struct inode *dir, struct buffer_head *bh, void *buf, int buf_size, - const char *name, int namelen, + struct ext4_filename *fname, struct ext4_dir_entry_2 **dest_de); -void ext4_insert_dentry(struct inode *inode, +void ext4_insert_dentry(struct inode *dir, struct inode *inode, struct ext4_dir_entry_2 *de, int buf_size, - const char *name, int namelen); + struct ext4_filename *fname); static inline void ext4_update_dx_flag(struct inode *inode) { - if (!EXT4_HAS_COMPAT_FEATURE(inode->i_sb, - EXT4_FEATURE_COMPAT_DIR_INDEX)) + if (!ext4_has_feature_dir_index(inode->i_sb) && + ext4_test_inode_flag(inode, EXT4_INODE_INDEX)) { + /* 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); + } } -static unsigned char ext4_filetype_table[] = { +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_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FILETYPE) || - (filetype >= EXT4_FT_MAX)) + 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 */ -extern int ext4fs_dirhash(const char *name, int len, struct - dx_hash_info *hinfo); +extern int ext4fs_dirhash(const struct inode *dir, const char *name, int len, + struct dx_hash_info *hinfo); /* ialloc.c */ -extern struct inode *__ext4_new_inode(handle_t *, struct inode *, umode_t, +extern int ext4_mark_inode_used(struct super_block *sb, int ino); +extern struct inode *__ext4_new_inode(struct mnt_idmap *, handle_t *, + struct inode *, umode_t, const struct qstr *qstr, __u32 goal, - uid_t *owner, int handle_type, - unsigned int line_no, int nblocks); - -#define ext4_new_inode(handle, dir, mode, qstr, goal, owner) \ - __ext4_new_inode((handle), (dir), (mode), (qstr), (goal), (owner), \ - 0, 0, 0) -#define ext4_new_inode_start_handle(dir, mode, qstr, goal, owner, \ + uid_t *owner, __u32 i_flags, + int handle_type, unsigned int line_no, + int nblocks); + +#define ext4_new_inode(handle, dir, mode, qstr, goal, owner, i_flags) \ + __ext4_new_inode(&nop_mnt_idmap, (handle), (dir), (mode), (qstr), \ + (goal), (owner), i_flags, 0, 0, 0) +#define ext4_new_inode_start_handle(idmap, dir, mode, qstr, goal, owner, \ type, nblocks) \ - __ext4_new_inode(NULL, (dir), (mode), (qstr), (goal), (owner), \ - (type), __LINE__, (nblocks)) + __ext4_new_inode((idmap), NULL, (dir), (mode), (qstr), (goal), (owner), \ + 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); 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); +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_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 long ext4_mb_stats; -extern long ext4_mb_max_to_scan; +extern const struct seq_operations ext4_mb_seq_groups_ops; +extern const struct seq_operations ext4_mb_seq_structs_summary_ops; +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 void ext4_mb_release(struct super_block *); extern ext4_fsblk_t ext4_mb_new_blocks(handle_t *, struct ext4_allocation_request *, int *); -extern int ext4_mb_reserve_blocks(struct super_block *, int); extern void ext4_discard_preallocations(struct inode *); extern int __init ext4_init_mballoc(void); extern void ext4_exit_mballoc(void); +extern 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); @@ -2051,142 +3013,210 @@ extern int ext4_mb_add_groupinfo(struct super_block *sb, 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, bool state); +static inline bool ext4_mb_cr_expensive(enum criteria cr) +{ + return cr >= CR_GOAL_LEN_SLOW; +} /* inode.c */ -struct buffer_head *ext4_getblk(handle_t *, struct inode *, - ext4_lblk_t, int, int *); -struct buffer_head *ext4_bread(handle_t *, struct inode *, - ext4_lblk_t, int, int *); -int ext4_get_block_write(struct inode *inode, sector_t iblock, - struct buffer_head *bh_result, int create); +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); +void ext4_check_map_extents_env(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); + 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, + int (*fn)(handle_t *handle, struct inode *inode, struct buffer_head *bh)); -int do_journal_get_write_access(handle_t *handle, +int do_journal_get_write_access(handle_t *handle, struct inode *inode, struct buffer_head *bh); +void ext4_set_inode_mapping_order(struct inode *inode); #define FALL_BACK_TO_NONDELALLOC 1 #define CONVERT_INLINE_DATA 2 -extern struct inode *ext4_iget(struct super_block *, unsigned long); +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_BAD = 0x0004, /* Allow to iget a bad inode */ + EXT4_IGET_EA_INODE = 0x0008 /* Inode should contain an EA value */ +} 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 dentry *, struct iattr *); -extern int ext4_getattr(struct vfsmount *mnt, struct dentry *dentry, - struct kstat *stat); +extern int ext4_setattr(struct mnt_idmap *, struct dentry *, + struct iattr *); +extern u32 ext4_dio_alignment(struct inode *inode); +extern int ext4_getattr(struct mnt_idmap *, 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_sync_inode(handle_t *, struct inode *); +extern int ext4_file_getattr(struct mnt_idmap *, const struct path *, + struct kstat *, u32, unsigned int); 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 void ext4_truncate(struct inode *); -extern int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length); -extern int ext4_truncate_restart_trans(handle_t *, struct inode *, int nblocks); -extern void ext4_set_inode_flags(struct inode *); -extern void ext4_get_inode_flags(struct ext4_inode_info *); +extern int ext4_truncate(struct inode *); +extern int ext4_break_layouts(struct inode *); +extern int ext4_truncate_page_cache_block_range(struct inode *inode, + loff_t start, loff_t end); +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_normal_submit_inode_data_buffers(struct jbd2_inode *jinode); extern int ext4_chunk_trans_blocks(struct inode *, int nrblocks); -extern int ext4_block_truncate_page(handle_t *handle, - struct address_space *mapping, loff_t from); -extern int ext4_block_zero_page_range(handle_t *handle, - struct address_space *mapping, loff_t from, loff_t length); +extern int ext4_chunk_trans_extent(struct inode *inode, int nrblocks); +extern int ext4_meta_trans_blocks(struct inode *inode, int lblocks, + int pextents); extern int ext4_zero_partial_blocks(handle_t *handle, struct inode *inode, loff_t lstart, loff_t lend); -extern int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf); +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); + +static inline bool is_special_ino(struct super_block *sb, unsigned long ino) +{ + struct ext4_super_block *es = EXT4_SB(sb)->s_es; + + return (ino < EXT4_FIRST_INO(sb) && ino != EXT4_ROOT_INO) || + ino == le32_to_cpu(es->s_usr_quota_inum) || + ino == le32_to_cpu(es->s_grp_quota_inum) || + ino == le32_to_cpu(es->s_prj_quota_inum) || + ino == le32_to_cpu(es->s_orphan_file_inum); +} /* indirect.c */ extern int ext4_ind_map_blocks(handle_t *handle, struct inode *inode, struct ext4_map_blocks *map, int flags); -extern ssize_t ext4_ind_direct_IO(int rw, struct kiocb *iocb, - const struct iovec *iov, loff_t offset, - unsigned long nr_segs); -extern int ext4_ind_calc_metadata_amount(struct inode *inode, sector_t lblock); extern int ext4_ind_trans_blocks(struct inode *inode, int nrblocks); extern void ext4_ind_truncate(handle_t *, struct inode *inode); -extern int ext4_free_hole_blocks(handle_t *handle, struct inode *inode, - ext4_lblk_t first, ext4_lblk_t stop); +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 mnt_idmap *idmap, + struct dentry *dentry, struct file_kattr *fa); +int ext4_fileattr_get(struct dentry *dentry, struct file_kattr *fa); +extern void ext4_reset_inode_seed(struct inode *inode); +int ext4_update_overhead(struct super_block *sb, bool force); +int ext4_force_shutdown(struct super_block *sb, u32 flags); /* migrate.c */ extern int ext4_ext_migrate(struct inode *); extern int ext4_ind_migrate(struct inode *inode); /* namei.c */ -extern int ext4_dirent_csum_verify(struct inode *inode, - struct ext4_dir_entry *dirent); -extern int ext4_orphan_add(handle_t *, struct inode *); -extern int ext4_orphan_del(handle_t *, struct inode *); +extern int ext4_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 search_dir(struct buffer_head *bh, - char *search_buf, - int buf_size, - struct inode *dir, - const struct qstr *d_name, - unsigned int offset, - struct ext4_dir_entry_2 **res_dir); -extern int ext4_generic_delete_entry(handle_t *handle, - struct inode *dir, +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, blk_opf_t op_flags); +extern struct buffer_head *ext4_sb_bread_unmovable(struct super_block *sb, + sector_t block); +extern struct buffer_head *ext4_sb_bread_nofail(struct super_block *sb, + sector_t block); +extern void ext4_read_bh_nowait(struct buffer_head *bh, blk_opf_t op_flags, + bh_end_io_t *end_io, bool simu_fail); +extern int ext4_read_bh(struct buffer_head *bh, blk_opf_t op_flags, + bh_end_io_t *end_io, bool simu_fail); +extern int ext4_read_bh_lock(struct buffer_head *bh, blk_opf_t 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 int ext4_superblock_csum_verify(struct super_block *sb, - struct ext4_super_block *es); +extern __le32 ext4_superblock_csum(struct ext4_super_block *es); extern void ext4_superblock_csum_set(struct super_block *sb); -extern void *ext4_kvmalloc(size_t size, gfp_t flags); -extern void *ext4_kvzalloc(size_t size, gfp_t flags); -extern void ext4_kvfree(void *ptr); extern 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 unsigned int ext4_num_base_meta_blocks(struct super_block *sb, + ext4_group_t block_group); -extern __printf(4, 5) -void __ext4_error(struct super_block *, const char *, unsigned int, - const char *, ...); -extern __printf(5, 6) -void __ext4_error_inode(struct inode *, const char *, unsigned int, ext4_fsblk_t, - const char *, ...); +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_abort(struct super_block *, const char *, unsigned int, - const char *, ...); -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, @@ -2197,18 +3227,41 @@ void __ext4_grp_locked_error(const char *, unsigned int, 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, fmt, ##__VA_ARGS__) + __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__, fmt, ##__VA_ARGS__) -#define ext4_abort(sb, fmt, ...) \ - __ext4_abort(sb, __func__, __LINE__, fmt, ##__VA_ARGS__) + __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) \ @@ -2222,7 +3275,12 @@ void __ext4_grp_locked_error(const char *, unsigned int, #define ext4_error_inode(inode, func, line, block, fmt, ...) \ do { \ no_printk(fmt, ##__VA_ARGS__); \ - __ext4_error_inode(inode, "", 0, block, " "); \ + __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 { \ @@ -2232,18 +3290,23 @@ do { \ #define ext4_error(sb, fmt, ...) \ do { \ no_printk(fmt, ##__VA_ARGS__); \ - __ext4_error(sb, "", 0, " "); \ + __ext4_error(sb, "", 0, false, 0, 0, " "); \ } while (0) -#define ext4_abort(sb, fmt, ...) \ +#define ext4_error_err(sb, err, fmt, ...) \ do { \ no_printk(fmt, ##__VA_ARGS__); \ - __ext4_abort(sb, "", 0, " "); \ + __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__); \ @@ -2259,13 +3322,6 @@ do { \ #endif -extern void ext4_update_dynamic_rev(struct super_block *sb); -extern int ext4_update_compat_feature(handle_t *handle, struct super_block *sb, - __u32 compat); -extern int ext4_update_rocompat_feature(handle_t *handle, - struct super_block *sb, __u32 rocompat); -extern int ext4_update_incompat_feature(handle_t *handle, - struct super_block *sb, __u32 incompat); extern ext4_fsblk_t ext4_block_bitmap(struct super_block *sb, struct ext4_group_desc *bg); extern ext4_fsblk_t ext4_inode_bitmap(struct super_block *sb, @@ -2304,27 +3360,28 @@ extern int ext4_register_li_request(struct super_block *sb, static inline int ext4_has_group_desc_csum(struct super_block *sb) { - return EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_GDT_CSUM | - EXT4_FEATURE_RO_COMPAT_METADATA_CSUM); + return ext4_has_feature_gdt_csum(sb) || + ext4_has_feature_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_fsblk_t)le32_to_cpu(es->s_blocks_count_hi) << 32) | - le32_to_cpu(es->s_blocks_count_lo); + 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_fsblk_t)le32_to_cpu(es->s_r_blocks_count_hi) << 32) | - le32_to_cpu(es->s_r_blocks_count_lo); + 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_fsblk_t)le32_to_cpu(es->s_free_blocks_count_hi) << 32) | - le32_to_cpu(es->s_free_blocks_count_lo); + return ext4_read_incompat_64bit_val(es, s_free_blocks_count); } static inline void ext4_blocks_count_set(struct ext4_super_block *es, @@ -2348,13 +3405,15 @@ static inline void ext4_r_blocks_count_set(struct ext4_super_block *es, es->s_r_blocks_count_hi = cpu_to_le32(blk >> 32); } -static inline loff_t ext4_isize(struct ext4_inode *raw_inode) +static inline loff_t ext4_isize(struct super_block *sb, + struct ext4_inode *raw_inode) { - if (S_ISREG(le16_to_cpu(raw_inode->i_mode))) + 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); - else - return (loff_t) 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) @@ -2363,19 +3422,6 @@ static inline void ext4_isize_set(struct ext4_inode *raw_inode, loff_t 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); - grp_info = EXT4_SB(sb)->s_group_info; - indexv = group >> (EXT4_DESC_PER_BLOCK_BITS(sb)); - indexh = group & ((EXT4_DESC_PER_BLOCK(sb)) - 1); - return grp_info[indexv][indexh]; -} - /* * Reading s_groups_count requires using smp_rmb() afterwards. See * the locking protocol documented in the comments of ext4_group_add() @@ -2400,6 +3446,13 @@ static inline unsigned int ext4_flex_bg_size(struct ext4_sb_info *sbi) return 1 << sbi->s_log_groups_per_flex; } +static inline loff_t ext4_get_maxbytes(struct inode *inode) +{ + if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) + return inode->i_sb->s_maxbytes; + return EXT4_SB(inode->i_sb)->s_bitmap_maxbytes; +} + #define ext4_std_error(sb, errno) \ do { \ if ((errno)) \ @@ -2416,25 +3469,49 @@ do { \ #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) { - /* - * XXX: replace with spinlock if seen contended -bzzz - */ + 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_I(inode)->i_disksize = newsize; + WRITE_ONCE(EXT4_I(inode)->i_disksize, newsize); up_write(&EXT4_I(inode)->i_data_sem); - return ; } +/* 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 */ + int bb_avg_fragment_size_order; /* order of average + fragment in BG */ ext4_grpblk_t bb_largest_free_order;/* order of largest frag in BG */ + ext4_group_t bb_group; /* Group number */ struct list_head bb_prealloc_list; #ifdef DOUBLE_CHECK void *bb_bitmap; @@ -2448,9 +3525,20 @@ struct ext4_group_info { #define EXT4_GROUP_INFO_NEED_INIT_BIT 0 #define EXT4_GROUP_INFO_WAS_TRIMMED_BIT 1 +#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))) +#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))) #define EXT4_MB_GRP_WAS_TRIMMED(grp) \ (test_bit(EXT4_GROUP_INFO_WAS_TRIMMED_BIT, &((grp)->bb_state))) @@ -2458,6 +3546,8 @@ struct ext4_group_info { (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))) #define EXT4_MAX_CONTENTION 8 #define EXT4_CONTENTION_THRESHOLD 2 @@ -2477,23 +3567,28 @@ static inline int ext4_fs_is_busy(struct ext4_sb_info *sbi) return (atomic_read(&sbi->s_lock_busy) > EXT4_CONTENTION_THRESHOLD); } +static inline bool ext4_try_lock_group(struct super_block *sb, ext4_group_t group) +{ + if (!spin_trylock(ext4_group_lock_ptr(sb, group))) + return false; + /* + * 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); + return true; +} + 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 { + if (!ext4_try_lock_group(sb, group)) { /* * 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); + spin_lock(ext4_group_lock_ptr(sb, group)); } } @@ -2503,6 +3598,22 @@ static inline void ext4_unlock_group(struct super_block *sb, 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 */ @@ -2527,61 +3638,41 @@ extern const struct file_operations ext4_dir_operations; extern const struct inode_operations ext4_file_inode_operations; extern const struct file_operations ext4_file_operations; extern loff_t ext4_llseek(struct file *file, loff_t offset, int origin); -extern void ext4_unwritten_wait(struct inode *inode); /* inline.c */ -extern int ext4_has_inline_data(struct inode *inode); -extern int ext4_get_inline_size(struct inode *inode); extern int ext4_get_max_inline_size(struct inode *inode); extern int ext4_find_inline_data_nolock(struct inode *inode); -extern void ext4_write_inline_data(struct inode *inode, - struct ext4_iloc *iloc, - void *buffer, loff_t pos, - unsigned int len); -extern int ext4_prepare_inline_data(handle_t *handle, struct inode *inode, - unsigned int len); -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 void ext4_update_final_de(void *de_buf, int old_size, int new_size); -extern int ext4_readpage_inline(struct inode *inode, struct page *page); +int ext4_readpage_inline(struct inode *inode, struct folio *folio); 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_da_write_inline_data_end(struct inode *inode, loff_t pos, - unsigned len, unsigned copied, - struct page *page); -extern int ext4_try_add_inline_entry(handle_t *handle, struct dentry *dentry, - struct inode *inode); + struct folio **foliop); +int ext4_write_inline_data_end(struct inode *inode, loff_t pos, unsigned len, + unsigned copied, struct folio *folio); +extern int ext4_generic_write_inline_data(struct address_space *mapping, + struct inode *inode, + loff_t pos, unsigned len, + struct folio **foliop, + void **fsdata, bool da); +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 htree_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 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, - const struct qstr *d_name, + struct ext4_filename *fname, struct ext4_dir_entry_2 **res_dir, int *has_inline_data); extern int ext4_delete_inline_entry(handle_t *handle, @@ -2589,35 +3680,44 @@ extern int ext4_delete_inline_entry(handle_t *handle, struct ext4_dir_entry_2 *de_del, struct buffer_head *bh, int *has_inline_data); -extern int empty_inline_dir(struct inode *dir, 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); -extern int ext4_try_to_evict_inline_data(handle_t *handle, - struct inode *inode, - int needed); -extern void ext4_inline_data_truncate(struct inode *inode, int *has_inline); +extern void *ext4_read_inline_link(struct inode *inode); + +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); +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 initialize_dirent_tail(struct ext4_dir_entry_tail *t, - unsigned int blocksize); -extern int ext4_handle_dirty_dirent_node(handle_t *handle, - struct inode *inode, - struct buffer_head *bh); +extern int ext4_init_dirblock(handle_t *handle, struct inode *inode, + struct buffer_head *dir_block, + unsigned int parent_ino, void *inline_buf, + int inline_size); +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(struct inode *dir, const struct qstr *d_name, + struct inode *inode, struct dentry *dentry); +extern int __ext4_link(struct inode *dir, struct inode *inode, + struct dentry *dentry); + #define S_SHIFT 12 -static unsigned char ext4_type_by_mode[S_IFMT >> S_SHIFT] = { +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, @@ -2630,36 +3730,57 @@ static unsigned char ext4_type_by_mode[S_IFMT >> S_SHIFT] = { static inline void ext4_set_de_type(struct super_block *sb, struct ext4_dir_entry_2 *de, umode_t mode) { - if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FILETYPE)) + 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 folio *folio); +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); -extern int ext4_data_block_valid(struct ext4_sb_info *sbi, - ext4_fsblk_t start_blk, - unsigned int count); +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; -extern int ext4_ext_tree_init(handle_t *handle, struct inode *); -extern int ext4_ext_writepage_trans_blocks(struct inode *, int); +/* + * 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 void ext4_ext_truncate(handle_t *, struct inode *); +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 *); @@ -2668,30 +3789,44 @@ 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_extents_atomic(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_metadata_amount(struct inode *inode, - ext4_lblk_t lblocks); -extern int ext4_extent_tree_init(handle_t *, struct inode *); extern int ext4_ext_calc_credits_for_single_extent(struct inode *inode, int num, struct ext4_ext_path *path); -extern int ext4_can_extents_be_merged(struct inode *inode, - struct ext4_extent *ex1, - struct ext4_extent *ex2); -extern int ext4_ext_insert_extent(handle_t *, struct inode *, - struct ext4_ext_path *, - struct ext4_extent *, int); -extern struct ext4_ext_path *ext4_ext_find_extent(struct inode *, ext4_lblk_t, - struct ext4_ext_path *); -extern void ext4_ext_drop_refs(struct ext4_ext_path *); +extern struct ext4_ext_path *ext4_ext_insert_extent( + handle_t *handle, struct inode *inode, + struct ext4_ext_path *path, + struct ext4_extent *newext, int gb_flags); +extern struct ext4_ext_path *ext4_find_extent(struct inode *, ext4_lblk_t, + struct ext4_ext_path *, + int flags); +extern void ext4_free_ext_path(struct ext4_ext_path *); extern int ext4_ext_check_inode(struct inode *inode); -extern int ext4_find_delalloc_range(struct inode *inode, - ext4_lblk_t lblk_start, - ext4_lblk_t lblk_end); -extern int ext4_find_delalloc_cluster(struct inode *inode, ext4_lblk_t lblk); +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 */ @@ -2699,8 +3834,6 @@ 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); -void ext4_inode_double_lock(struct inode *inode1, struct inode *inode2); -void ext4_inode_double_unlock(struct inode *inode1, struct inode *inode2); extern int ext4_move_extents(struct file *o_filp, struct file *d_filp, __u64 start_orig, __u64 start_donor, __u64 len, __u64 *moved_len); @@ -2715,29 +3848,33 @@ 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_end_io_unrsv_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, - struct writeback_control *wbc); +int ext4_bio_write_folio(struct ext4_io_submit *io, struct folio *page, + size_t len); +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); -extern void ext4_mmp_csum_set(struct super_block *sb, struct mmp_struct *mmp); -extern int ext4_mmp_csum_verify(struct super_block *sb, - struct mmp_struct *mmp); -/* - * Note that these flags will never ever appear in a buffer_head's state flag. - * See EXT4_MAP_... to see where this is used. - */ -enum ext4_state_bits { - BH_Uninit /* blocks are allocated but uninitialized on disk */ - = BH_JBDPrivateStart, - BH_AllocFromCluster, /* allocated blocks were part of already - * allocated cluster. */ -}; +/* mmp.c */ +extern void ext4_stop_mmpd(struct ext4_sb_info *sbi); + +/* 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); +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 @@ -2756,36 +3893,52 @@ static inline void set_bitmap_uptodate(struct buffer_head *bh) set_bit(BH_BITMAP_UPTODATE, &(bh)->b_state); } -/* - * Disable DIO read nolock optimization, so new dioreaders will be forced - * to grab i_mutex - */ -static inline void ext4_inode_block_unlocked_dio(struct inode *inode) +extern int ext4_resize_begin(struct super_block *sb); +extern int ext4_resize_end(struct super_block *sb, bool update_backups); + +static inline void ext4_set_io_unwritten_flag(struct ext4_io_end *io_end) { - ext4_set_inode_state(inode, EXT4_STATE_DIOREAD_LOCK); - smp_mb(); + if (!(io_end->flag & EXT4_IO_END_UNWRITTEN)) + io_end->flag |= EXT4_IO_END_UNWRITTEN; } -static inline void ext4_inode_resume_unlocked_dio(struct inode *inode) + +static inline void ext4_clear_io_unwritten_flag(ext4_io_end_t *io_end) { - smp_mb(); - ext4_clear_inode_state(inode, EXT4_STATE_DIOREAD_LOCK); + if (io_end->flag & EXT4_IO_END_UNWRITTEN) + io_end->flag &= ~EXT4_IO_END_UNWRITTEN; } -#define in_range(b, first, len) ((b) >= (first) && (b) <= (first) + (len) - 1) +extern const struct iomap_ops ext4_iomap_ops; +extern const struct iomap_ops ext4_iomap_overwrite_ops; +extern const struct iomap_ops ext4_iomap_report_ops; -/* For ioend & aio unwritten conversion wait queues */ -#define EXT4_WQ_HASH_SZ 37 -#define ext4_ioend_wq(v) (&ext4__ioend_wq[((unsigned long)(v)) %\ - EXT4_WQ_HASH_SZ]) -#define ext4_aio_mutex(v) (&ext4__aio_mutex[((unsigned long)(v)) %\ - EXT4_WQ_HASH_SZ]) -extern wait_queue_head_t ext4__ioend_wq[EXT4_WQ_HASH_SZ]; -extern struct mutex ext4__aio_mutex[EXT4_WQ_HASH_SZ]; +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); +} -#define EXT4_RESIZING 0 -extern int ext4_resize_begin(struct super_block *sb); -extern void ext4_resize_end(struct super_block *sb); +static inline bool ext4_inode_can_atomic_write(struct inode *inode) +{ + return S_ISREG(inode->i_mode) && + ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS) && + EXT4_SB(inode->i_sb)->s_awu_min > 0; +} + +extern int ext4_block_write_begin(handle_t *handle, struct folio *folio, + loff_t pos, unsigned len, + get_block_t *get_block); #endif /* __KERNEL__ */ +#define EFSBADCRC EBADMSG /* Bad CRC detected */ +#define EFSCORRUPTED EUCLEAN /* Filesystem is corrupted */ + #endif /* _EXT4_H */ |