summaryrefslogtreecommitdiff
path: root/fs/ext4/ext4.h
diff options
context:
space:
mode:
Diffstat (limited to 'fs/ext4/ext4.h')
-rw-r--r--fs/ext4/ext4.h525
1 files changed, 317 insertions, 208 deletions
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 481491e892df..56112f201cac 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -33,7 +33,7 @@
#include <linux/blockgroup_lock.h>
#include <linux/percpu_counter.h>
#include <linux/ratelimit.h>
-#include <crypto/hash.h>
+#include <linux/crc32c.h>
#include <linux/falloc.h>
#include <linux/percpu-rwsem.h>
#include <linux/fiemap.h>
@@ -157,7 +157,7 @@ enum criteria {
/*
* Reads each block group sequentially, performing disk IO if
- * necessary, to find find_suitable block group. Tries to
+ * necessary, to find suitable block group. Tries to
* allocate goal length but might trim the request if nothing
* is found after enough tries.
*/
@@ -176,9 +176,6 @@ enum criteria {
EXT4_MB_NUM_CRS
};
-/* criteria below which we use fast block scanning and avoid unnecessary IO */
-#define CR_FAST CR_GOAL_LEN_SLOW
-
/*
* Flags used in mballoc's allocation_context flags field.
*
@@ -188,14 +185,8 @@ enum criteria {
/* 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) */
@@ -216,12 +207,6 @@ enum criteria {
#define EXT4_MB_USE_RESERVED 0x2000
/* Do strict check for free blocks while retrying block allocation */
#define EXT4_MB_STRICT_CHECK 0x4000
-/* Large fragment size list lookup succeeded at least once for cr = 0 */
-#define EXT4_MB_CR_POWER2_ALIGNED_OPTIMIZED 0x8000
-/* Avg fragment size rb tree lookup succeeded at least once for cr = 1 */
-#define EXT4_MB_CR_GOAL_LEN_FAST_OPTIMIZED 0x00010000
-/* Avg fragment size rb tree lookup succeeded at least once for cr = 1.5 */
-#define EXT4_MB_CR_BEST_AVAIL_LEN_OPTIMIZED 0x00020000
struct ext4_allocation_request {
/* target inode for block we're allocating */
@@ -255,14 +240,27 @@ struct ext4_allocation_request {
#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_UNWRITTEN | EXT4_MAP_BOUNDARY |\
+ 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;
};
/*
@@ -276,7 +274,10 @@ struct ext4_system_blocks {
/*
* Flags for ext4_io_end->flags
*/
-#define EXT4_IO_END_UNWRITTEN 0x0001
+#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 */
@@ -365,7 +366,16 @@ struct ext4_io_submit {
#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 */
@@ -692,16 +702,22 @@ enum {
/* Caller is from the delayed allocation writeout path
* finally doing the actual allocation of delayed blocks */
#define EXT4_GET_BLOCKS_DELALLOC_RESERVE 0x0004
- /* caller is from the direct IO path, request to creation of an
- unwritten extents if not allocated, split the unwritten
- extent if blocks has been preallocated already*/
-#define EXT4_GET_BLOCKS_PRE_IO 0x0008
-#define EXT4_GET_BLOCKS_CONVERT 0x0010
-#define EXT4_GET_BLOCKS_IO_CREATE_EXT (EXT4_GET_BLOCKS_PRE_IO|\
- EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT)
- /* Convert extent to initialized after IO complete */
-#define EXT4_GET_BLOCKS_IO_CONVERT_EXT (EXT4_GET_BLOCKS_CONVERT|\
+ /*
+ * 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
/* 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
@@ -713,11 +729,23 @@ enum {
#define EXT4_GET_BLOCKS_ZERO 0x0200
#define EXT4_GET_BLOCKS_CREATE_ZERO (EXT4_GET_BLOCKS_CREATE |\
EXT4_GET_BLOCKS_ZERO)
- /* Caller will submit data before dropping transaction handle. This
- * allows jbd2 to avoid submitting data before commit. */
+ /* 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
@@ -731,6 +759,13 @@ enum {
#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
@@ -894,10 +929,13 @@ do { \
(raw_inode)->xtime = cpu_to_le32(clamp_t(int32_t, (ts).tv_sec, S32_MIN, S32_MAX)); \
} while (0)
-#define EXT4_INODE_SET_XTIME(xtime, inode, raw_inode) \
- EXT4_INODE_SET_XTIME_VAL(xtime, inode, raw_inode, (inode)->xtime)
+#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) \
+#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) \
@@ -913,9 +951,16 @@ do { \
.tv_sec = (signed)le32_to_cpu((raw_inode)->xtime) \
})
-#define EXT4_INODE_GET_XTIME(xtime, inode, raw_inode) \
+#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_INODE_GET_MTIME(inode, raw_inode) \
do { \
- (inode)->xtime = EXT4_INODE_GET_XTIME_VAL(xtime, inode, raw_inode); \
+ inode_set_mtime_to_ts(inode, \
+ EXT4_INODE_GET_XTIME_VAL(i_mtime, inode, raw_inode)); \
} while (0)
#define EXT4_INODE_GET_CTIME(inode, raw_inode) \
@@ -1044,14 +1089,16 @@ struct ext4_inode_info {
/* End of lblk range that needs to be committed in this fast commit */
ext4_lblk_t i_fc_lblk_len;
- /* Number of ongoing updates on this inode */
- atomic_t i_fc_updates;
+ 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 */
- struct mutex i_fc_lock;
+ /*
+ * 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
@@ -1084,8 +1131,6 @@ struct ext4_inode_info {
struct inode vfs_inode;
struct jbd2_inode *jinode;
- spinlock_t i_raw_lock; /* protects updates to the raw inode */
-
/*
* File creation time. Its function is same as that of
* struct timespec64 i_{a,c,m}time in the generic inode.
@@ -1094,6 +1139,10 @@ struct ext4_inode_info {
/* mballoc */
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;
@@ -1106,14 +1155,12 @@ struct ext4_inode_info {
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, this refer to clusters rather than blocks */
- unsigned int i_reserved_data_blocks;
-
/* pending cluster reservations for bigalloc file systems */
struct ext4_pending_tree i_pending_tree;
@@ -1128,6 +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;
@@ -1137,9 +1185,6 @@ struct ext4_inode_info {
*/
struct list_head i_rsv_conversion_list;
struct work_struct i_rsv_conversion_work;
- atomic_t i_unwritten; /* Nr. of inflight conversions pending */
-
- spinlock_t i_block_reservation_lock;
/*
* Transactions that contain inode's metadata needed to complete
@@ -1149,13 +1194,21 @@ struct ext4_inode_info {
tid_t i_datasync_tid;
#ifdef CONFIG_QUOTA
- struct dquot *i_dquot[MAXQUOTAS];
+ 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
};
/*
@@ -1241,6 +1294,7 @@ struct ext4_inode_info {
#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
@@ -1258,10 +1312,8 @@ 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
@@ -1336,7 +1388,7 @@ 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[EXT4_LABEL_MAX]; /* volume name */
+/*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 */
/*
@@ -1417,7 +1469,9 @@ struct ext4_super_block {
__le16 s_encoding; /* Filename charset encoding */
__le16 s_encoding_flags; /* Filename charset encoding flags */
__le32 s_orphan_file_inum; /* Inode for tracking orphan inodes */
- __le32 s_reserved[94]; /* Padding to the end of the block */
+ __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) */
};
@@ -1498,6 +1552,7 @@ 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 */
+ /* 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;
@@ -1541,7 +1596,7 @@ struct ext4_sb_info {
unsigned long s_commit_interval;
u32 s_max_batch_time;
u32 s_min_batch_time;
- struct block_device *s_journal_bdev;
+ struct file *s_journal_bdev_file;
#ifdef CONFIG_QUOTA
/* Names of quota files with journalled quota */
char __rcu *s_qf_names[EXT4_MAXQUOTAS];
@@ -1567,16 +1622,14 @@ struct ext4_sb_info {
unsigned short *s_mb_offsets;
unsigned int *s_mb_maxs;
unsigned int s_group_info_size;
- unsigned int s_mb_free_pending;
- struct list_head s_freed_data_list; /* List of blocks to be freed
+ 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 list_head *s_mb_avg_fragment_size;
- rwlock_t *s_mb_avg_fragment_size_locks;
- struct list_head *s_mb_largest_free_orders;
- rwlock_t *s_mb_largest_free_orders_locks;
+ struct xarray *s_mb_avg_fragment_size;
+ struct xarray *s_mb_largest_free_orders;
/* tunables */
unsigned long s_stripe;
@@ -1588,12 +1641,15 @@ struct ext4_sb_info {
unsigned int s_mb_order2_reqs;
unsigned int s_mb_group_prealloc;
unsigned int s_max_dir_size_kb;
- /* where last allocation was done - for stream allocation */
- unsigned long s_mb_last_group;
- unsigned long s_mb_last_start;
unsigned int s_mb_prefetch;
unsigned int s_mb_prefetch_limit;
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 */
+ 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 */
@@ -1603,12 +1659,10 @@ struct ext4_sb_info {
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 */
- atomic_t s_bal_p2_aligned_bad_suggestions;
- atomic_t s_bal_goal_fast_bad_suggestions;
- atomic_t s_bal_best_avail_bad_suggestions;
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 */
@@ -1650,14 +1704,16 @@ struct ext4_sb_info {
/* record the last minlen when FITRIM is called. */
unsigned long s_last_trim_minblks;
- /* Reference to checksum algorithm driver via cryptoapi */
- struct crypto_shash *s_chksum_driver;
+ /* 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 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;
@@ -1680,7 +1736,8 @@ struct ext4_sb_info {
/*
* Barrier between writepages ops and changing any inode's JOURNAL_DATA
- * or EXTENTS flag.
+ * 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;
@@ -1708,10 +1765,17 @@ struct ext4_sb_info {
const char *s_last_error_func;
time64_t s_last_error_time;
/*
- * If we are in a context where we cannot update error information in
- * the on-disk superblock, we queue this work to do it.
+ * 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_error_work;
+ 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;
@@ -1732,7 +1796,7 @@ struct ext4_sb_info {
* following fields:
* ei->i_fc_list, s_fc_dentry_q, s_fc_q, s_fc_bytes, s_fc_bh.
*/
- spinlock_t s_fc_lock;
+ struct mutex s_fc_lock;
struct buffer_head *s_fc_bh;
struct ext4_fc_stats s_fc_stats;
tid_t s_fc_ineligible_tid;
@@ -1782,6 +1846,18 @@ static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino)
ino <= le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count));
}
+static inline int ext4_get_resuid(struct ext4_super_block *es)
+{
+ 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
@@ -1804,8 +1880,8 @@ static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino)
*/
enum {
EXT4_MF_MNTDIR_SAMPLED,
- EXT4_MF_FS_ABORTED, /* Fatal error detected */
- EXT4_MF_FC_INELIGIBLE /* Fast commit ineligible */
+ 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)
@@ -1850,14 +1926,6 @@ static inline bool ext4_simulate_fail(struct super_block *sb,
return false;
}
-static inline void ext4_simulate_fail_bh(struct super_block *sb,
- struct buffer_head *bh,
- unsigned long code)
-{
- if (!IS_ERR(bh) && ext4_simulate_fail(sb, code))
- clear_buffer_uptodate(bh);
-}
-
/*
* Error number codes for s_{first,last}_error_errno
*
@@ -1899,6 +1967,7 @@ enum {
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 */
};
@@ -1959,6 +2028,16 @@ static inline bool ext4_verity_in_progress(struct inode *inode)
#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
@@ -2224,13 +2303,30 @@ extern int ext4_feature_set_ok(struct super_block *sb, int readonly);
/*
* Superblock flags
*/
-#define EXT4_FLAGS_RESIZING 0
-#define EXT4_FLAGS_SHUTDOWN 1
-#define EXT4_FLAGS_BDEV_IS_DAX 2
+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_forced_shutdown(struct ext4_sb_info *sbi)
+static inline int ext4_emergency_ro(struct super_block *sb)
{
- return test_bit(EXT4_FLAGS_SHUTDOWN, &sbi->s_ext4_flags);
+ 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;
}
/*
@@ -2264,10 +2360,19 @@ static inline int ext4_forced_shutdown(struct ext4_sb_info *sbi)
#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
@@ -2323,9 +2428,9 @@ struct ext4_dir_entry_2 {
((struct ext4_dir_entry_hash *) \
(((void *)(entry)) + \
((8 + (entry)->name_len + EXT4_DIR_ROUND) & ~EXT4_DIR_ROUND)))
-#define EXT4_DIRENT_HASH(entry) le32_to_cpu(EXT4_DIRENT_HASHES(de)->hash)
+#define EXT4_DIRENT_HASH(entry) le32_to_cpu(EXT4_DIRENT_HASHES(entry)->hash)
#define EXT4_DIRENT_MINOR_HASH(entry) \
- le32_to_cpu(EXT4_DIRENT_HASHES(de)->minor_hash)
+ le32_to_cpu(EXT4_DIRENT_HASHES(entry)->minor_hash)
static inline bool ext4_hash_in_dirent(const struct inode *inode)
{
@@ -2391,28 +2496,19 @@ static inline unsigned int ext4_dir_rec_len(__u8 name_len,
return (rec_len & ~EXT4_DIR_ROUND);
}
-/*
- * If we ever get support for fs block sizes > page_size, we'll need
- * to remove the #if statements in the next two functions...
- */
static inline unsigned int
ext4_rec_len_from_disk(__le16 dlen, unsigned blocksize)
{
unsigned len = le16_to_cpu(dlen);
-#if (PAGE_SIZE >= 65536)
if (len == EXT4_MAX_REC_LEN || len == 0)
return blocksize;
return (len & 65532) | ((len & 3) << 16);
-#else
- return len;
-#endif
}
static inline __le16 ext4_rec_len_to_disk(unsigned len, unsigned blocksize)
{
BUG_ON((len > blocksize) || (blocksize > (1 << 18)) || (len & 3));
-#if (PAGE_SIZE >= 65536)
if (len < 65536)
return cpu_to_le16(len);
if (len == blocksize) {
@@ -2422,9 +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
}
/*
@@ -2447,23 +2540,11 @@ static inline __le16 ext4_rec_len_to_disk(unsigned len, unsigned blocksize)
#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;
-
- BUG_ON(crypto_shash_descsize(sbi->s_chksum_driver)!=sizeof(desc.ctx));
-
- desc.shash.tfm = sbi->s_chksum_driver;
- *(u32 *)desc.ctx = crc;
-
- BUG_ON(crypto_shash_update(&desc.shash, address, length));
-
- return *(u32 *)desc.ctx;
+ return crc32c(crc, address, length);
}
#ifdef __KERNEL__
@@ -2496,7 +2577,7 @@ struct ext4_filename {
struct fscrypt_str crypto_buf;
#endif
#if IS_ENABLED(CONFIG_UNICODE)
- struct fscrypt_str cf_name;
+ struct qstr cf_name;
#endif
};
@@ -2538,6 +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 */
@@ -2678,10 +2761,10 @@ struct mmpd_data {
extern unsigned int ext4_count_free(char *bitmap, unsigned numchars);
void ext4_inode_bitmap_csum_set(struct super_block *sb,
struct ext4_group_desc *gdp,
- struct buffer_head *bh, int sz);
+ 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);
+ struct buffer_head *bh);
void ext4_block_bitmap_csum_set(struct super_block *sb,
struct ext4_group_desc *gdp,
struct buffer_head *bh);
@@ -2708,7 +2791,6 @@ 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);
@@ -2731,8 +2813,25 @@ 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);
+ 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 */
@@ -2755,16 +2854,11 @@ static inline int ext4_fname_setup_filename(struct inode *dir,
int lookup,
struct ext4_filename *fname)
{
- int err = 0;
fname->usr_fname = iname;
fname->disk_name.name = (unsigned char *) iname->name;
fname->disk_name.len = iname->len;
-#if IS_ENABLED(CONFIG_UNICODE)
- err = ext4_fname_setup_ci_filename(dir, iname, fname);
-#endif
-
- return err;
+ return ext4_fname_setup_ci_filename(dir, iname, fname);
}
static inline int ext4_fname_prepare_lookup(struct inode *dir,
@@ -2776,10 +2870,7 @@ static inline int ext4_fname_prepare_lookup(struct inode *dir,
static inline void ext4_fname_free_filename(struct ext4_filename *fname)
{
-#if IS_ENABLED(CONFIG_UNICODE)
- kfree(fname->cf_name.name);
- fname->cf_name.name = NULL;
-#endif
+ ext4_fname_free_ci_filename(fname);
}
static inline int ext4_ioctl_get_encryption_pwsalt(struct file *filp,
@@ -2803,8 +2894,7 @@ extern int ext4_htree_store_dirent(struct file *dir_file, __u32 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,
struct ext4_filename *fname,
struct ext4_dir_entry_2 **dest_de);
@@ -2864,7 +2954,6 @@ 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);
@@ -2887,8 +2976,6 @@ void __ext4_fc_track_create(handle_t *handle, struct inode *inode,
void ext4_fc_track_create(handle_t *handle, struct dentry *dentry);
void ext4_fc_track_inode(handle_t *handle, struct inode *inode);
void ext4_fc_mark_ineligible(struct super_block *sb, int reason, handle_t *handle);
-void ext4_fc_start_update(struct inode *inode);
-void ext4_fc_stop_update(struct inode *inode);
void ext4_fc_del(struct inode *inode);
bool ext4_fc_replay_check_excluded(struct super_block *sb, ext4_fsblk_t block);
void ext4_fc_replay_cleanup(struct super_block *sb);
@@ -2904,11 +2991,10 @@ 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 *, unsigned 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,
@@ -2929,12 +3015,17 @@ extern int ext4_group_add_blocks(handle_t *handle, struct super_block *sb,
extern int ext4_trim_fs(struct super_block *, struct fstrim_range *);
extern void ext4_process_freed_data(struct super_block *sb, tid_t commit_tid);
extern void ext4_mb_mark_bb(struct super_block *sb, ext4_fsblk_t block,
- int len, int state);
+ int len, bool state);
+static inline bool ext4_mb_cr_expensive(enum criteria cr)
+{
+ return cr >= CR_GOAL_LEN_SLOW;
+}
/* inode.c */
void ext4_inode_csum_set(struct inode *inode, struct ext4_inode *raw,
struct ext4_inode_info *ei);
int ext4_inode_is_fast_symlink(struct inode *inode);
+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,
@@ -2955,6 +3046,7 @@ int ext4_walk_page_buffers(handle_t *handle,
struct buffer_head *bh));
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
@@ -2983,7 +3075,6 @@ extern void ext4_evict_inode(struct inode *);
extern void ext4_clear_inode(struct inode *);
extern int ext4_file_getattr(struct mnt_idmap *, const struct path *,
struct kstat *, u32, unsigned int);
-extern int ext4_sync_inode(handle_t *, struct inode *);
extern void ext4_dirty_inode(struct inode *, int);
extern int ext4_change_inode_journal_flag(struct inode *, int);
extern int ext4_get_inode_loc(struct inode *, struct ext4_iloc *);
@@ -2993,13 +3084,17 @@ extern int ext4_inode_attach_jinode(struct inode *inode);
extern int ext4_can_truncate(struct inode *inode);
extern int ext4_truncate(struct inode *);
extern int ext4_break_layouts(struct inode *);
+extern int ext4_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_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 vm_fault_t ext4_page_mkwrite(struct vm_fault *vmf);
@@ -3011,6 +3106,17 @@ extern void ext4_da_update_reserve_space(struct inode *inode,
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);
@@ -3023,8 +3129,8 @@ extern int ext4_ind_remove_space(handle_t *handle, struct inode *inode,
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 fileattr *fa);
-int ext4_fileattr_get(struct dentry *dentry, struct fileattr *fa);
+ 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);
@@ -3072,16 +3178,17 @@ 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);
+ 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);
+ 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 __le32 ext4_superblock_csum(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 int ext4_alloc_flex_bg_array(struct super_block *sb,
ext4_group_t ngroup);
@@ -3090,6 +3197,8 @@ extern const char *ext4_decode_error(struct super_block *sb, int errno,
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(7, 8)
void __ext4_error(struct super_block *, const char *, unsigned int, bool,
@@ -3249,18 +3358,10 @@ extern void ext4_group_desc_csum_set(struct super_block *sb, __u32 group,
extern int ext4_register_li_request(struct super_block *sb,
ext4_group_t first_not_zeroed);
-static inline int ext4_has_metadata_csum(struct super_block *sb)
-{
- WARN_ON_ONCE(ext4_has_feature_metadata_csum(sb) &&
- !EXT4_SB(sb)->s_chksum_driver);
-
- return ext4_has_feature_metadata_csum(sb) &&
- (EXT4_SB(sb)->s_chksum_driver != NULL);
-}
-
static inline int ext4_has_group_desc_csum(struct super_block *sb)
{
- return ext4_has_feature_gdt_csum(sb) || ext4_has_metadata_csum(sb);
+ return ext4_has_feature_gdt_csum(sb) ||
+ ext4_has_feature_metadata_csum(sb);
}
#define ext4_read_incompat_64bit_val(es, name) \
@@ -3345,6 +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)) \
@@ -3409,8 +3517,6 @@ struct ext4_group_info {
void *bb_bitmap;
#endif
struct rw_semaphore alloc_sem;
- struct list_head bb_avg_fragment_size_node;
- struct list_head bb_largest_free_order_node;
ext4_grpblk_t bb_counters[]; /* Nr of free power-of-two-block
* regions, index is order.
* bb_counters[3] = 5 means
@@ -3461,23 +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));
}
}
@@ -3531,22 +3642,21 @@ extern loff_t ext4_llseek(struct file *file, loff_t offset, int origin);
/* inline.c */
extern int ext4_get_max_inline_size(struct inode *inode);
extern int ext4_find_inline_data_nolock(struct inode *inode);
-extern int ext4_init_inline_data(handle_t *handle, struct inode *inode,
- unsigned int len);
extern int ext4_destroy_inline_data(handle_t *handle, struct inode *inode);
+extern void ext4_update_final_de(void *de_buf, int old_size, int new_size);
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,
- struct page **pagep);
+ 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_da_write_inline_data_begin(struct address_space *mapping,
- struct inode *inode,
- loff_t pos, unsigned len,
- struct page **pagep,
- void **fsdata);
+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);
@@ -3593,10 +3703,10 @@ static inline int ext4_has_inline_data(struct inode *inode)
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 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,
@@ -3679,6 +3789,8 @@ 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,
@@ -3686,11 +3798,12 @@ extern int ext4_map_blocks(handle_t *handle, struct inode *inode,
extern int ext4_ext_calc_credits_for_single_extent(struct inode *inode,
int num,
struct ext4_ext_path *path);
-extern int ext4_ext_insert_extent(handle_t *, struct inode *,
- struct ext4_ext_path **,
- struct ext4_extent *, int);
+extern struct ext4_ext_path *ext4_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 **,
+ 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);
@@ -3780,34 +3893,19 @@ static inline void set_bitmap_uptodate(struct buffer_head *bh)
set_bit(BH_BITMAP_UPTODATE, &(bh)->b_state);
}
-/* For ioend & aio unwritten conversion wait queues */
-#define EXT4_WQ_HASH_SZ 37
-#define ext4_ioend_wq(v) (&ext4__ioend_wq[((unsigned long)(v)) %\
- EXT4_WQ_HASH_SZ])
-extern wait_queue_head_t ext4__ioend_wq[EXT4_WQ_HASH_SZ];
-
extern int ext4_resize_begin(struct super_block *sb);
extern int ext4_resize_end(struct super_block *sb, bool update_backups);
-static inline void ext4_set_io_unwritten_flag(struct inode *inode,
- struct ext4_io_end *io_end)
+static inline void ext4_set_io_unwritten_flag(struct ext4_io_end *io_end)
{
- if (!(io_end->flag & EXT4_IO_END_UNWRITTEN)) {
+ if (!(io_end->flag & EXT4_IO_END_UNWRITTEN))
io_end->flag |= EXT4_IO_END_UNWRITTEN;
- atomic_inc(&EXT4_I(inode)->i_unwritten);
- }
}
static inline void ext4_clear_io_unwritten_flag(ext4_io_end_t *io_end)
{
- struct inode *inode = io_end->inode;
-
- if (io_end->flag & EXT4_IO_END_UNWRITTEN) {
+ if (io_end->flag & EXT4_IO_END_UNWRITTEN)
io_end->flag &= ~EXT4_IO_END_UNWRITTEN;
- /* Wake up anyone waiting on unwritten extent conversion */
- if (atomic_dec_and_test(&EXT4_I(inode)->i_unwritten))
- wake_up_all(ext4_ioend_wq(inode));
- }
}
extern const struct iomap_ops ext4_iomap_ops;
@@ -3827,6 +3925,17 @@ static inline int ext4_buffer_uptodate(struct buffer_head *bh)
return buffer_uptodate(bh);
}
+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 */
generated by cgit (git 2.34.1) at 2025-12-24 20:59:30 +0000