diff options
Diffstat (limited to 'fs/ext4')
-rw-r--r-- | fs/ext4/acl.h | 5 | ||||
-rw-r--r-- | fs/ext4/balloc.c | 16 | ||||
-rw-r--r-- | fs/ext4/crypto.c | 13 | ||||
-rw-r--r-- | fs/ext4/ext4.h | 32 | ||||
-rw-r--r-- | fs/ext4/extents.c | 25 | ||||
-rw-r--r-- | fs/ext4/extents_status.c | 150 | ||||
-rw-r--r-- | fs/ext4/fast_commit.c | 8 | ||||
-rw-r--r-- | fs/ext4/file.c | 169 | ||||
-rw-r--r-- | fs/ext4/fsmap.c | 9 | ||||
-rw-r--r-- | fs/ext4/ialloc.c | 4 | ||||
-rw-r--r-- | fs/ext4/inline.c | 4 | ||||
-rw-r--r-- | fs/ext4/inode.c | 47 | ||||
-rw-r--r-- | fs/ext4/ioctl.c | 13 | ||||
-rw-r--r-- | fs/ext4/mballoc-test.c | 349 | ||||
-rw-r--r-- | fs/ext4/mballoc.c | 571 | ||||
-rw-r--r-- | fs/ext4/move_extent.c | 11 | ||||
-rw-r--r-- | fs/ext4/namei.c | 13 | ||||
-rw-r--r-- | fs/ext4/readpage.c | 14 | ||||
-rw-r--r-- | fs/ext4/resize.c | 94 | ||||
-rw-r--r-- | fs/ext4/super.c | 84 | ||||
-rw-r--r-- | fs/ext4/xattr.c | 10 | ||||
-rw-r--r-- | fs/ext4/xattr.h | 2 |
22 files changed, 944 insertions, 699 deletions
diff --git a/fs/ext4/acl.h b/fs/ext4/acl.h index 0c5a79c3b5d4..ef4c19e5f570 100644 --- a/fs/ext4/acl.h +++ b/fs/ext4/acl.h @@ -68,6 +68,11 @@ extern int ext4_init_acl(handle_t *, struct inode *, struct inode *); static inline int ext4_init_acl(handle_t *handle, struct inode *inode, struct inode *dir) { + /* usually, the umask is applied by posix_acl_create(), but if + ext4 ACL support is disabled at compile time, we need to do + it here, because posix_acl_create() will never be called */ + inode->i_mode &= ~current_umask(); + return 0; } #endif /* CONFIG_EXT4_FS_POSIX_ACL */ diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index 79b20d6ae39e..591fb3f710be 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -22,6 +22,7 @@ #include "mballoc.h" #include <trace/events/ext4.h> +#include <kunit/static_stub.h> static unsigned ext4_num_base_meta_clusters(struct super_block *sb, ext4_group_t block_group); @@ -111,10 +112,8 @@ static unsigned ext4_num_overhead_clusters(struct super_block *sb, itbl_blk_start = ext4_inode_table(sb, gdp); itbl_blk_end = itbl_blk_start + sbi->s_itb_per_group - 1; if (itbl_blk_start <= end && itbl_blk_end >= start) { - itbl_blk_start = itbl_blk_start >= start ? - itbl_blk_start : start; - itbl_blk_end = itbl_blk_end <= end ? - itbl_blk_end : end; + itbl_blk_start = max(itbl_blk_start, start); + itbl_blk_end = min(itbl_blk_end, end); itbl_cluster_start = EXT4_B2C(sbi, itbl_blk_start - start); itbl_cluster_end = EXT4_B2C(sbi, itbl_blk_end - start); @@ -274,6 +273,9 @@ struct ext4_group_desc * ext4_get_group_desc(struct super_block *sb, struct ext4_sb_info *sbi = EXT4_SB(sb); struct buffer_head *bh_p; + KUNIT_STATIC_STUB_REDIRECT(ext4_get_group_desc, + sb, block_group, bh); + if (block_group >= ngroups) { ext4_error(sb, "block_group >= groups_count - block_group = %u," " groups_count = %u", block_group, ngroups); @@ -468,6 +470,9 @@ ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group, ext4_fsblk_t bitmap_blk; int err; + KUNIT_STATIC_STUB_REDIRECT(ext4_read_block_bitmap_nowait, + sb, block_group, ignore_locked); + desc = ext4_get_group_desc(sb, block_group, NULL); if (!desc) return ERR_PTR(-EFSCORRUPTED); @@ -563,6 +568,9 @@ int ext4_wait_block_bitmap(struct super_block *sb, ext4_group_t block_group, { struct ext4_group_desc *desc; + KUNIT_STATIC_STUB_REDIRECT(ext4_wait_block_bitmap, + sb, block_group, bh); + if (!buffer_new(bh)) return 0; desc = ext4_get_group_desc(sb, block_group, NULL); diff --git a/fs/ext4/crypto.c b/fs/ext4/crypto.c index 453d4da5de52..7ae0b61258a7 100644 --- a/fs/ext4/crypto.c +++ b/fs/ext4/crypto.c @@ -232,19 +232,14 @@ static bool ext4_has_stable_inodes(struct super_block *sb) return ext4_has_feature_stable_inodes(sb); } -static void ext4_get_ino_and_lblk_bits(struct super_block *sb, - int *ino_bits_ret, int *lblk_bits_ret) -{ - *ino_bits_ret = 8 * sizeof(EXT4_SB(sb)->s_es->s_inodes_count); - *lblk_bits_ret = 8 * sizeof(ext4_lblk_t); -} - const struct fscrypt_operations ext4_cryptops = { - .key_prefix = "ext4:", + .needs_bounce_pages = 1, + .has_32bit_inodes = 1, + .supports_subblock_data_units = 1, + .legacy_key_prefix = "ext4:", .get_context = ext4_get_context, .set_context = ext4_set_context, .get_dummy_policy = ext4_get_dummy_policy, .empty_dir = ext4_empty_dir, .has_stable_inodes = ext4_has_stable_inodes, - .get_ino_and_lblk_bits = ext4_get_ino_and_lblk_bits, }; diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 9418359b1d9d..a5d784872303 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -891,10 +891,13 @@ 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_CTIME(inode, raw_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) \ @@ -910,9 +913,16 @@ 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) \ @@ -1494,6 +1504,7 @@ 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; @@ -1537,7 +1548,7 @@ 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 bdev_handle *s_journal_bdev_handle; #ifdef CONFIG_QUOTA /* Names of quota files with journalled quota */ char __rcu *s_qf_names[EXT4_MAXQUOTAS]; @@ -1564,7 +1575,7 @@ struct ext4_sb_info { 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 + 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; @@ -1653,7 +1664,7 @@ struct ext4_sb_info { __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; @@ -1676,7 +1687,8 @@ 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; @@ -2924,7 +2936,7 @@ 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; diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 202c76996b62..d5efe076d3d3 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -1010,6 +1010,11 @@ static int ext4_ext_insert_index(handle_t *handle, struct inode *inode, ix = curp->p_idx; } + if (unlikely(ix > EXT_MAX_INDEX(curp->p_hdr))) { + EXT4_ERROR_INODE(inode, "ix > EXT_MAX_INDEX!"); + return -EFSCORRUPTED; + } + len = EXT_LAST_INDEX(curp->p_hdr) - ix + 1; BUG_ON(len < 0); if (len > 0) { @@ -1019,11 +1024,6 @@ static int ext4_ext_insert_index(handle_t *handle, struct inode *inode, memmove(ix + 1, ix, len * sizeof(struct ext4_extent_idx)); } - if (unlikely(ix > EXT_MAX_INDEX(curp->p_hdr))) { - EXT4_ERROR_INODE(inode, "ix > EXT_MAX_INDEX!"); - return -EFSCORRUPTED; - } - ix->ei_block = cpu_to_le32(logical); ext4_idx_store_pblock(ix, ptr); le16_add_cpu(&curp->p_hdr->eh_entries, 1); @@ -4481,7 +4481,8 @@ retry: if (epos > new_size) epos = new_size; if (ext4_update_inode_size(inode, epos) & 0x1) - inode->i_mtime = inode_get_ctime(inode); + inode_set_mtime_to_ts(inode, + inode_get_ctime(inode)); } ret2 = ext4_mark_inode_dirty(handle, inode); ext4_update_inode_fsync_trans(handle, inode, 1); @@ -4617,7 +4618,7 @@ static long ext4_zero_range(struct file *file, loff_t offset, /* Now release the pages and zero block aligned part of pages */ truncate_pagecache_range(inode, start, end - 1); - inode->i_mtime = inode_set_ctime_current(inode); + inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); ret = ext4_alloc_file_blocks(file, lblk, max_blocks, new_size, flags); @@ -4642,7 +4643,7 @@ static long ext4_zero_range(struct file *file, loff_t offset, goto out_mutex; } - inode->i_mtime = inode_set_ctime_current(inode); + inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); if (new_size) ext4_update_inode_size(inode, new_size); ret = ext4_mark_inode_dirty(handle, inode); @@ -5378,7 +5379,7 @@ static int ext4_collapse_range(struct file *file, loff_t offset, loff_t len) up_write(&EXT4_I(inode)->i_data_sem); if (IS_SYNC(inode)) ext4_handle_sync(handle); - inode->i_mtime = inode_set_ctime_current(inode); + inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); ret = ext4_mark_inode_dirty(handle, inode); ext4_update_inode_fsync_trans(handle, inode, 1); @@ -5488,7 +5489,7 @@ static int ext4_insert_range(struct file *file, loff_t offset, loff_t len) /* Expand file to avoid data loss if there is error while shifting */ inode->i_size += len; EXT4_I(inode)->i_disksize += len; - inode->i_mtime = inode_set_ctime_current(inode); + inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); ret = ext4_mark_inode_dirty(handle, inode); if (ret) goto out_stop; @@ -6080,13 +6081,13 @@ int ext4_ext_clear_bb(struct inode *inode) for (j = 0; j < path->p_depth; j++) { ext4_mb_mark_bb(inode->i_sb, - path[j].p_block, 1, 0); + path[j].p_block, 1, false); ext4_fc_record_regions(inode->i_sb, inode->i_ino, 0, path[j].p_block, 1, 1); } ext4_free_ext_path(path); } - ext4_mb_mark_bb(inode->i_sb, map.m_pblk, map.m_len, 0); + ext4_mb_mark_bb(inode->i_sb, map.m_pblk, map.m_len, false); ext4_fc_record_regions(inode->i_sb, inode->i_ino, map.m_lblk, map.m_pblk, map.m_len, 1); } diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c index 6f7de14c0fa8..4a00e2f019d9 100644 --- a/fs/ext4/extents_status.c +++ b/fs/ext4/extents_status.c @@ -152,8 +152,9 @@ static int __es_remove_extent(struct inode *inode, ext4_lblk_t lblk, static int es_reclaim_extents(struct ext4_inode_info *ei, int *nr_to_scan); static int __es_shrink(struct ext4_sb_info *sbi, int nr_to_scan, struct ext4_inode_info *locked_ei); -static void __revise_pending(struct inode *inode, ext4_lblk_t lblk, - ext4_lblk_t len); +static int __revise_pending(struct inode *inode, ext4_lblk_t lblk, + ext4_lblk_t len, + struct pending_reservation **prealloc); int __init ext4_init_es(void) { @@ -448,6 +449,19 @@ static void ext4_es_list_del(struct inode *inode) spin_unlock(&sbi->s_es_lock); } +static inline struct pending_reservation *__alloc_pending(bool nofail) +{ + if (!nofail) + return kmem_cache_alloc(ext4_pending_cachep, GFP_ATOMIC); + + return kmem_cache_zalloc(ext4_pending_cachep, GFP_KERNEL | __GFP_NOFAIL); +} + +static inline void __free_pending(struct pending_reservation *pr) +{ + kmem_cache_free(ext4_pending_cachep, pr); +} + /* * Returns true if we cannot fail to allocate memory for this extent_status * entry and cannot reclaim it until its status changes. @@ -836,11 +850,12 @@ void ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk, { struct extent_status newes; ext4_lblk_t end = lblk + len - 1; - int err1 = 0; - int err2 = 0; + int err1 = 0, err2 = 0, err3 = 0; struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct extent_status *es1 = NULL; struct extent_status *es2 = NULL; + struct pending_reservation *pr = NULL; + bool revise_pending = false; if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY) return; @@ -868,11 +883,17 @@ void ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk, ext4_es_insert_extent_check(inode, &newes); + revise_pending = sbi->s_cluster_ratio > 1 && + test_opt(inode->i_sb, DELALLOC) && + (status & (EXTENT_STATUS_WRITTEN | + EXTENT_STATUS_UNWRITTEN)); retry: if (err1 && !es1) es1 = __es_alloc_extent(true); if ((err1 || err2) && !es2) es2 = __es_alloc_extent(true); + if ((err1 || err2 || err3) && revise_pending && !pr) + pr = __alloc_pending(true); write_lock(&EXT4_I(inode)->i_es_lock); err1 = __es_remove_extent(inode, lblk, end, NULL, es1); @@ -897,13 +918,18 @@ retry: es2 = NULL; } - if (sbi->s_cluster_ratio > 1 && test_opt(inode->i_sb, DELALLOC) && - (status & EXTENT_STATUS_WRITTEN || - status & EXTENT_STATUS_UNWRITTEN)) - __revise_pending(inode, lblk, len); + if (revise_pending) { + err3 = __revise_pending(inode, lblk, len, &pr); + if (err3 != 0) + goto error; + if (pr) { + __free_pending(pr); + pr = NULL; + } + } error: write_unlock(&EXT4_I(inode)->i_es_lock); - if (err1 || err2) + if (err1 || err2 || err3) goto retry; ext4_es_print_tree(inode); @@ -1311,7 +1337,7 @@ static unsigned int get_rsvd(struct inode *inode, ext4_lblk_t end, rc->ndelonly--; node = rb_next(&pr->rb_node); rb_erase(&pr->rb_node, &tree->root); - kmem_cache_free(ext4_pending_cachep, pr); + __free_pending(pr); if (!node) break; pr = rb_entry(node, struct pending_reservation, @@ -1405,8 +1431,8 @@ static int __es_remove_extent(struct inode *inode, ext4_lblk_t lblk, } } if (count_reserved) - count_rsvd(inode, lblk, orig_es.es_len - len1 - len2, - &orig_es, &rc); + count_rsvd(inode, orig_es.es_lblk + len1, + orig_es.es_len - len1 - len2, &orig_es, &rc); goto out_get_reserved; } @@ -1606,7 +1632,7 @@ static unsigned long ext4_es_count(struct shrinker *shrink, unsigned long nr; struct ext4_sb_info *sbi; - sbi = container_of(shrink, struct ext4_sb_info, s_es_shrinker); + sbi = shrink->private_data; nr = percpu_counter_read_positive(&sbi->s_es_stats.es_stats_shk_cnt); trace_ext4_es_shrink_count(sbi->s_sb, sc->nr_to_scan, nr); return nr; @@ -1615,8 +1641,7 @@ static unsigned long ext4_es_count(struct shrinker *shrink, static unsigned long ext4_es_scan(struct shrinker *shrink, struct shrink_control *sc) { - struct ext4_sb_info *sbi = container_of(shrink, - struct ext4_sb_info, s_es_shrinker); + struct ext4_sb_info *sbi = shrink->private_data; int nr_to_scan = sc->nr_to_scan; int ret, nr_shrunk; @@ -1700,13 +1725,17 @@ int ext4_es_register_shrinker(struct ext4_sb_info *sbi) if (err) goto err3; - sbi->s_es_shrinker.scan_objects = ext4_es_scan; - sbi->s_es_shrinker.count_objects = ext4_es_count; - sbi->s_es_shrinker.seeks = DEFAULT_SEEKS; - err = register_shrinker(&sbi->s_es_shrinker, "ext4-es:%s", - sbi->s_sb->s_id); - if (err) + sbi->s_es_shrinker = shrinker_alloc(0, "ext4-es:%s", sbi->s_sb->s_id); + if (!sbi->s_es_shrinker) { + err = -ENOMEM; goto err4; + } + + sbi->s_es_shrinker->scan_objects = ext4_es_scan; + sbi->s_es_shrinker->count_objects = ext4_es_count; + sbi->s_es_shrinker->private_data = sbi; + + shrinker_register(sbi->s_es_shrinker); return 0; err4: @@ -1726,7 +1755,7 @@ void ext4_es_unregister_shrinker(struct ext4_sb_info *sbi) percpu_counter_destroy(&sbi->s_es_stats.es_stats_cache_misses); percpu_counter_destroy(&sbi->s_es_stats.es_stats_all_cnt); percpu_counter_destroy(&sbi->s_es_stats.es_stats_shk_cnt); - unregister_shrinker(&sbi->s_es_shrinker); + shrinker_free(sbi->s_es_shrinker); } /* @@ -1907,11 +1936,13 @@ static struct pending_reservation *__get_pending(struct inode *inode, * * @inode - file containing the cluster * @lblk - logical block in the cluster to be added + * @prealloc - preallocated pending entry * * Returns 0 on successful insertion and -ENOMEM on failure. If the * pending reservation is already in the set, returns successfully. */ -static int __insert_pending(struct inode *inode, ext4_lblk_t lblk) +static int __insert_pending(struct inode *inode, ext4_lblk_t lblk, + struct pending_reservation **prealloc) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct ext4_pending_tree *tree = &EXT4_I(inode)->i_pending_tree; @@ -1937,10 +1968,15 @@ static int __insert_pending(struct inode *inode, ext4_lblk_t lblk) } } - pr = kmem_cache_alloc(ext4_pending_cachep, GFP_ATOMIC); - if (pr == NULL) { - ret = -ENOMEM; - goto out; + if (likely(*prealloc == NULL)) { + pr = __alloc_pending(false); + if (!pr) { + ret = -ENOMEM; + goto out; + } + } else { + pr = *prealloc; + *prealloc = NULL; } pr->lclu = lclu; @@ -1970,7 +2006,7 @@ static void __remove_pending(struct inode *inode, ext4_lblk_t lblk) if (pr != NULL) { tree = &EXT4_I(inode)->i_pending_tree; rb_erase(&pr->rb_node, &tree->root); - kmem_cache_free(ext4_pending_cachep, pr); + __free_pending(pr); } } @@ -2029,10 +2065,10 @@ void ext4_es_insert_delayed_block(struct inode *inode, ext4_lblk_t lblk, bool allocated) { struct extent_status newes; - int err1 = 0; - int err2 = 0; + int err1 = 0, err2 = 0, err3 = 0; struct extent_status *es1 = NULL; struct extent_status *es2 = NULL; + struct pending_reservation *pr = NULL; if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY) return; @@ -2052,6 +2088,8 @@ retry: es1 = __es_alloc_extent(true); if ((err1 || err2) && !es2) es2 = __es_alloc_extent(true); + if ((err1 || err2 || err3) && allocated && !pr) + pr = __alloc_pending(true); write_lock(&EXT4_I(inode)->i_es_lock); err1 = __es_remove_extent(inode, lblk, lblk, NULL, es1); @@ -2074,11 +2112,18 @@ retry: es2 = NULL; } - if (allocated) - __insert_pending(inode, lblk); + if (allocated) { + err3 = __insert_pending(inode, lblk, &pr); + if (err3 != 0) + goto error; + if (pr) { + __free_pending(pr); + pr = NULL; + } + } error: write_unlock(&EXT4_I(inode)->i_es_lock); - if (err1 || err2) + if (err1 || err2 || err3) goto retry; ext4_es_print_tree(inode); @@ -2184,21 +2229,24 @@ unsigned int ext4_es_delayed_clu(struct inode *inode, ext4_lblk_t lblk, * @inode - file containing the range * @lblk - logical block defining the start of range * @len - length of range in blocks + * @prealloc - preallocated pending entry * * Used after a newly allocated extent is added to the extents status tree. * Requires that the extents in the range have either written or unwritten * status. Must be called while holding i_es_lock. */ -static void __revise_pending(struct inode *inode, ext4_lblk_t lblk, - ext4_lblk_t len) +static int __revise_pending(struct inode *inode, ext4_lblk_t lblk, + ext4_lblk_t len, + struct pending_reservation **prealloc) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); ext4_lblk_t end = lblk + len - 1; ext4_lblk_t first, last; bool f_del = false, l_del = false; + int ret = 0; if (len == 0) - return; + return 0; /* * Two cases - block range within single cluster and block range @@ -2219,7 +2267,9 @@ static void __revise_pending(struct inode *inode, ext4_lblk_t lblk, f_del = __es_scan_range(inode, &ext4_es_is_delonly, first, lblk - 1); if (f_del) { - __insert_pending(inode, first); + ret = __insert_pending(inode, first, prealloc); + if (ret < 0) + goto out; } else { last = EXT4_LBLK_CMASK(sbi, end) + sbi->s_cluster_ratio - 1; @@ -2227,9 +2277,11 @@ static void __revise_pending(struct inode *inode, ext4_lblk_t lblk, l_del = __es_scan_range(inode, &ext4_es_is_delonly, end + 1, last); - if (l_del) - __insert_pending(inode, last); - else + if (l_del) { + ret = __insert_pending(inode, last, prealloc); + if (ret < 0) + goto out; + } else __remove_pending(inode, last); } } else { @@ -2237,18 +2289,24 @@ static void __revise_pending(struct inode *inode, ext4_lblk_t lblk, if (first != lblk) f_del = __es_scan_range(inode, &ext4_es_is_delonly, first, lblk - 1); - if (f_del) - __insert_pending(inode, first); - else + if (f_del) { + ret = __insert_pending(inode, first, prealloc); + if (ret < 0) + goto out; + } else __remove_pending(inode, first); last = EXT4_LBLK_CMASK(sbi, end) + sbi->s_cluster_ratio - 1; if (last != end) l_del = __es_scan_range(inode, &ext4_es_is_delonly, end + 1, last); - if (l_del) - __insert_pending(inode, last); - else + if (l_del) { + ret = __insert_pending(inode, last, prealloc); + if (ret < 0) + goto out; + } else __remove_pending(inode, last); } +out: + return ret; } diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c index b06de728b3b6..87c009e0c59a 100644 --- a/fs/ext4/fast_commit.c +++ b/fs/ext4/fast_commit.c @@ -1806,7 +1806,7 @@ static int ext4_fc_replay_add_range(struct super_block *sb, * at the end of the FC replay using our array of * modified inodes. */ - ext4_mb_mark_bb(inode->i_sb, map.m_pblk, map.m_len, 0); + ext4_mb_mark_bb(inode->i_sb, map.m_pblk, map.m_len, false); goto next; } @@ -1875,7 +1875,7 @@ ext4_fc_replay_del_range(struct super_block *sb, if (ret > 0) { remaining -= ret; cur += ret; - ext4_mb_mark_bb(inode->i_sb, map.m_pblk, map.m_len, 0); + ext4_mb_mark_bb(inode->i_sb, map.m_pblk, map.m_len, false); } else { remaining -= map.m_len; cur += map.m_len; @@ -1934,12 +1934,12 @@ static void ext4_fc_set_bitmaps_and_counters(struct super_block *sb) if (!IS_ERR(path)) { for (j = 0; j < path->p_depth; j++) ext4_mb_mark_bb(inode->i_sb, - path[j].p_block, 1, 1); + path[j].p_block, 1, true); ext4_free_ext_path(path); } cur += ret; ext4_mb_mark_bb(inode->i_sb, map.m_pblk, - map.m_len, 1); + map.m_len, true); } else { cur = cur + (map.m_len ? map.m_len : 1); } diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 6830ea3a6c59..0166bb9ca160 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -306,80 +306,38 @@ out: } static ssize_t ext4_handle_inode_extension(struct inode *inode, loff_t offset, - ssize_t written, size_t count) + ssize_t count) { handle_t *handle; - bool truncate = false; - u8 blkbits = inode->i_blkbits; - ext4_lblk_t written_blk, end_blk; - int ret; - - /* - * Note that EXT4_I(inode)->i_disksize can get extended up to - * inode->i_size while the I/O was running due to writeback of delalloc - * blocks. But, the code in ext4_iomap_alloc() is careful to use - * zeroed/unwritten extents if this is possible; thus we won't leave - * uninitialized blocks in a file even if we didn't succeed in writing - * as much as we intended. - */ - WARN_ON_ONCE(i_size_read(inode) < EXT4_I(inode)->i_disksize); - if (offset + count <= EXT4_I(inode)->i_disksize) { - /* - * We need to ensure that the inode is removed from the orphan - * list if it has been added prematurely, due to writeback of - * delalloc blocks. - */ - if (!list_empty(&EXT4_I(inode)->i_orphan) && inode->i_nlink) { - handle = ext4_journal_start(inode, EXT4_HT_INODE, 2); - - if (IS_ERR(handle)) { - ext4_orphan_del(NULL, inode); - return PTR_ERR(handle); - } - - ext4_orphan_del(handle, inode); - ext4_journal_stop(handle); - } - - return written; - } - - if (written < 0) - goto truncate; + lockdep_assert_held_write(&inode->i_rwsem); handle = ext4_journal_start(inode, EXT4_HT_INODE, 2); - if (IS_ERR(handle)) { - written = PTR_ERR(handle); - goto truncate; - } + if (IS_ERR(handle)) + return PTR_ERR(handle); - if (ext4_update_inode_size(inode, offset + written)) { - ret = ext4_mark_inode_dirty(handle, inode); + if (ext4_update_inode_size(inode, offset + count)) { + int ret = ext4_mark_inode_dirty(handle, inode); if (unlikely(ret)) { - written = ret; ext4_journal_stop(handle); - goto truncate; + return ret; } } - /* - * We may need to truncate allocated but not written blocks beyond EOF. - */ - written_blk = ALIGN(offset + written, 1 << blkbits); - end_blk = ALIGN(offset + count, 1 << blkbits); - if (written_blk < end_blk && ext4_can_truncate(inode)) - truncate = true; - - /* - * Remove the inode from the orphan list if it has been extended and - * everything went OK. - */ - if (!truncate && inode->i_nlink) + if (inode->i_nlink) ext4_orphan_del(handle, inode); ext4_journal_stop(handle); - if (truncate) { -truncate: + return count; +} + +/* + * Clean up the inode after DIO or DAX extending write has completed and the + * inode size has been updated using ext4_handle_inode_extension(). + */ +static void ext4_inode_extension_cleanup(struct inode *inode, ssize_t count) +{ + lockdep_assert_held_write(&inode->i_rwsem); + if (count < 0) { ext4_truncate_failed_write(inode); /* * If the truncate operation failed early, then the inode may @@ -388,9 +346,28 @@ truncate: */ if (inode->i_nlink) ext4_orphan_del(NULL, inode); + return; } + /* + * If i_disksize got extended due to writeback of delalloc blocks while + * the DIO was running we could fail to cleanup the orphan list in + * ext4_handle_inode_extension(). Do it now. + */ + if (!list_empty(&EXT4_I(inode)->i_orphan) && inode->i_nlink) { + handle_t *handle = ext4_journal_start(inode, EXT4_HT_INODE, 2); - return written; + if (IS_ERR(handle)) { + /* + * The write has successfully completed. Not much to + * do with the error here so just cleanup the orphan + * list and hope for the best. + */ + ext4_orphan_del(NULL, inode); + return; + } + ext4_orphan_del(handle, inode); + ext4_journal_stop(handle); + } } static int ext4_dio_write_end_io(struct kiocb *iocb, ssize_t size, @@ -399,31 +376,22 @@ static int ext4_dio_write_end_io(struct kiocb *iocb, ssize_t size, loff_t pos = iocb->ki_pos; struct inode *inode = file_inode(iocb->ki_filp); + if (!error && size && flags & IOMAP_DIO_UNWRITTEN) + error = ext4_convert_unwritten_extents(NULL, inode, pos, size); if (error) return error; - - if (size && flags & IOMAP_DIO_UNWRITTEN) { - error = ext4_convert_unwritten_extents(NULL, inode, pos, size); - if (error < 0) - return error; - } /* - * If we are extending the file, we have to update i_size here before - * page cache gets invalidated in iomap_dio_rw(). Otherwise racing - * buffered reads could zero out too much from page cache pages. Update - * of on-disk size will happen later in ext4_dio_write_iter() where - * we have enough information to also perform orphan list handling etc. - * Note that we perform all extending writes synchronously under - * i_rwsem held exclusively so i_size update is safe here in that case. - * If the write was not extending, we cannot see pos > i_size here - * because operations reducing i_size like truncate wait for all - * outstanding DIO before updating i_size. + * Note that EXT4_I(inode)->i_disksize can get extended up to + * inode->i_size while the I/O was running due to writeback of delalloc + * blocks. But the code in ext4_iomap_alloc() is careful to use + * zeroed/unwritten extents if this is possible; thus we won't leave + * uninitialized blocks in a file even if we didn't succeed in writing + * as much as we intended. */ - pos += size; - if (pos > i_size_read(inode)) - i_size_write(inode, pos); - - return 0; + WARN_ON_ONCE(i_size_read(inode) < READ_ONCE(EXT4_I(inode)->i_disksize)); + if (pos + size <= READ_ONCE(EXT4_I(inode)->i_disksize)) + return size; + return ext4_handle_inode_extension(inode, pos, size); } static const struct iomap_dio_ops ext4_dio_write_ops = { @@ -569,18 +537,20 @@ static ssize_t ext4_dio_write_iter(struct kiocb *iocb, struct iov_iter *from) return ext4_buffered_write_iter(iocb, from); } + /* + * Prevent inline data from being created since we are going to allocate + * blocks for DIO. We know the inode does not currently have inline data + * because ext4_should_use_dio() checked for it, but we have to clear + * the state flag before the write checks because a lock cycle could + * introduce races with other writers. + */ + ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA); + ret = ext4_dio_write_checks(iocb, from, &ilock_shared, &extend, &unwritten, &dio_flags); if (ret <= 0) return ret; - /* - * Make sure inline data cannot be created anymore since we are going - * to allocate blocks for DIO. We know the inode does not have any - * inline data now because ext4_dio_supported() checked for that. - */ - ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA); - offset = iocb->ki_pos; count = ret; @@ -606,9 +576,16 @@ static ssize_t ext4_dio_write_iter(struct kiocb *iocb, struct iov_iter *from) dio_flags, NULL, 0); if (ret == -ENOTBLK) ret = 0; - - if (extend) - ret = ext4_handle_inode_extension(inode, offset, ret, count); + if (extend) { + /* + * We always perform extending DIO write synchronously so by + * now the IO is completed and ext4_handle_inode_extension() + * was called. Cleanup the inode in case of error or race with + * writeback of delalloc blocks. + */ + WARN_ON_ONCE(ret == -EIOCBQUEUED); + ext4_inode_extension_cleanup(inode, ret); + } out: if (ilock_shared) @@ -689,8 +666,10 @@ ext4_dax_write_iter(struct kiocb *iocb, struct iov_iter *from) ret = dax_iomap_rw(iocb, from, &ext4_iomap_ops); - if (extend) - ret = ext4_handle_inode_extension(inode, offset, ret, count); + if (extend) { + ret = ext4_handle_inode_extension(inode, offset, ret); + ext4_inode_extension_cleanup(inode, ret); + } out: inode_unlock(inode); if (ret > 0) diff --git a/fs/ext4/fsmap.c b/fs/ext4/fsmap.c index cdf9bfe10137..11e6f33677a2 100644 --- a/fs/ext4/fsmap.c +++ b/fs/ext4/fsmap.c @@ -576,8 +576,9 @@ static bool ext4_getfsmap_is_valid_device(struct super_block *sb, if (fm->fmr_device == 0 || fm->fmr_device == UINT_MAX || fm->fmr_device == new_encode_dev(sb->s_bdev->bd_dev)) return true; - if (EXT4_SB(sb)->s_journal_bdev && - fm->fmr_device == new_encode_dev(EXT4_SB(sb)->s_journal_bdev->bd_dev)) + if (EXT4_SB(sb)->s_journal_bdev_handle && + fm->fmr_device == + new_encode_dev(EXT4_SB(sb)->s_journal_bdev_handle->bdev->bd_dev)) return true; return false; } @@ -647,9 +648,9 @@ int ext4_getfsmap(struct super_block *sb, struct ext4_fsmap_head *head, memset(handlers, 0, sizeof(handlers)); handlers[0].gfd_dev = new_encode_dev(sb->s_bdev->bd_dev); handlers[0].gfd_fn = ext4_getfsmap_datadev; - if (EXT4_SB(sb)->s_journal_bdev) { + if (EXT4_SB(sb)->s_journal_bdev_handle) { handlers[1].gfd_dev = new_encode_dev( - EXT4_SB(sb)->s_journal_bdev->bd_dev); + EXT4_SB(sb)->s_journal_bdev_handle->bdev->bd_dev); handlers[1].gfd_fn = ext4_getfsmap_logdev; } diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index b65058d972f9..e9bbb1da2d0a 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -1250,8 +1250,8 @@ got: inode->i_ino = ino + group * EXT4_INODES_PER_GROUP(sb); /* This is the optimal IO size (for stat), not the fs block size */ inode->i_blocks = 0; - inode->i_mtime = inode->i_atime = inode_set_ctime_current(inode); - ei->i_crtime = inode->i_mtime; + simple_inode_init_ts(inode); + ei->i_crtime = inode_get_mtime(inode); memset(ei->i_data, 0, sizeof(ei->i_data)); ei->i_dir_start_lookup = 0; diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index 012d9259ff53..9a84a5f9fef4 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -1037,7 +1037,7 @@ static int ext4_add_dirent_to_inline(handle_t *handle, * happen is that the times are slightly out of date * and/or different from the directory change time. */ - dir->i_mtime = inode_set_ctime_current(dir); + inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); ext4_update_dx_flag(dir); inode_inc_iversion(dir); return 1; @@ -1991,7 +1991,7 @@ out: ext4_orphan_del(handle, inode); if (err == 0) { - inode->i_mtime = inode_set_ctime_current(inode); + inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); err = ext4_mark_inode_dirty(handle, inode); if (IS_SYNC(inode)) ext4_handle_sync(handle); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 4ce35f1c8b0a..61277f7f8722 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -789,10 +789,22 @@ int ext4_get_block(struct inode *inode, sector_t iblock, int ext4_get_block_unwritten(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create) { + int ret = 0; + ext4_debug("ext4_get_block_unwritten: inode %lu, create flag %d\n", inode->i_ino, create); - return _ext4_get_block(inode, iblock, bh_result, + ret = _ext4_get_block(inode, iblock, bh_result, EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT); + + /* + * If the buffer is marked unwritten, mark it as new to make sure it is + * zeroed out correctly in case of partial writes. Otherwise, there is + * a chance of stale data getting exposed. + */ + if (ret == 0 && buffer_unwritten(bh_result)) + set_buffer_new(bh_result); + + return ret; } /* Maximum number of blocks we map for direct IO at once. */ @@ -1020,10 +1032,8 @@ static int ext4_block_write_begin(struct folio *folio, loff_t pos, unsigned len, BUG_ON(from > to); head = folio_buffers(folio); - if (!head) { - create_empty_buffers(&folio->page, blocksize, 0); - head = folio_buffers(folio); - } + if (!head) + head = create_empty_buffers(folio, blocksize, 0); bbits = ilog2(blocksize); block = (sector_t)folio->index << (PAGE_SHIFT - bbits); @@ -1153,7 +1163,7 @@ retry_grab: * starting the handle. */ if (!folio_buffers(folio)) - create_empty_buffers(&folio->page, inode->i_sb->s_blocksize, 0); + create_empty_buffers(folio, inode->i_sb->s_blocksize, 0); folio_unlock(folio); @@ -3643,10 +3653,8 @@ static int __ext4_block_zero_page_range(handle_t *handle, iblock = index << (PAGE_SHIFT - inode->i_sb->s_blocksize_bits); bh = folio_buffers(folio); - if (!bh) { - create_empty_buffers(&folio->page, blocksize, 0); - bh = folio_buffers(folio); - } + if (!bh) + bh = create_empty_buffers(folio, blocksize, 0); /* Find the buffer that contains "offset" */ pos = blocksize; @@ -4020,7 +4028,7 @@ int ext4_punch_hole(struct file *file, loff_t offset, loff_t length) if (IS_SYNC(inode)) ext4_handle_sync(handle); - inode->i_mtime = inode_set_ctime_current(inode); + inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); ret2 = ext4_mark_inode_dirty(handle, inode); if (unlikely(ret2)) ret = ret2; @@ -4180,7 +4188,7 @@ out_stop: if (inode->i_nlink) ext4_orphan_del(handle, inode); - inode->i_mtime = inode_set_ctime_current(inode); + inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); err2 = ext4_mark_inode_dirty(handle, inode); if (unlikely(err2 && !err)) err = err2; @@ -4284,8 +4292,8 @@ static int ext4_fill_raw_inode(struct inode *inode, struct ext4_inode *raw_inode raw_inode->i_links_count = cpu_to_le16(inode->i_nlink); EXT4_INODE_SET_CTIME(inode, raw_inode); - EXT4_INODE_SET_XTIME(i_mtime, inode, raw_inode); - EXT4_INODE_SET_XTIME(i_atime, inode, raw_inode); + EXT4_INODE_SET_MTIME(inode, raw_inode); + EXT4_INODE_SET_ATIME(inode, raw_inode); EXT4_EINODE_SET_XTIME(i_crtime, ei, raw_inode); raw_inode->i_dtime = cpu_to_le32(ei->i_dtime); @@ -4893,8 +4901,8 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino, } EXT4_INODE_GET_CTIME(inode, raw_inode); - EXT4_INODE_GET_XTIME(i_mtime, inode, raw_inode); - EXT4_INODE_GET_XTIME(i_atime, inode, raw_inode); + EXT4_INODE_GET_ATIME(inode, raw_inode); + EXT4_INODE_GET_MTIME(inode, raw_inode); EXT4_EINODE_GET_XTIME(i_crtime, ei, raw_inode); if (likely(!test_opt2(inode->i_sb, HURD_COMPAT))) { @@ -5019,8 +5027,8 @@ static void __ext4_update_other_inode_time(struct super_block *sb, spin_lock(&ei->i_raw_lock); EXT4_INODE_SET_CTIME(inode, raw_inode); - EXT4_INODE_SET_XTIME(i_mtime, inode, raw_inode); - EXT4_INODE_SET_XTIME(i_atime, inode, raw_inode); + EXT4_INODE_SET_MTIME(inode, raw_inode); + EXT4_INODE_SET_ATIME(inode, raw_inode); ext4_inode_csum_set(inode, raw_inode, ei); spin_unlock(&ei->i_raw_lock); trace_ext4_other_inode_update_time(inode, orig_ino); @@ -5413,7 +5421,8 @@ int ext4_setattr(struct mnt_idmap *idmap, struct dentry *dentry, * update c/mtime in shrink case below */ if (!shrink) - inode->i_mtime = inode_set_ctime_current(inode); + inode_set_mtime_to_ts(inode, + inode_set_ctime_current(inode)); if (shrink) ext4_fc_track_range(handle, inode, diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index 0bfe2ce589e2..4f931f80cb34 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -312,13 +312,22 @@ static void swap_inode_data(struct inode *inode1, struct inode *inode2) struct ext4_inode_info *ei1; struct ext4_inode_info *ei2; unsigned long tmp; + struct timespec64 ts1, ts2; ei1 = EXT4_I(inode1); ei2 = EXT4_I(inode2); swap(inode1->i_version, inode2->i_version); - swap(inode1->i_atime, inode2->i_atime); - swap(inode1->i_mtime, inode2->i_mtime); + + ts1 = inode_get_atime(inode1); + ts2 = inode_get_atime(inode2); + inode_set_atime_to_ts(inode1, ts2); + inode_set_atime_to_ts(inode2, ts1); + + ts1 = inode_get_mtime(inode1); + ts2 = inode_get_mtime(inode2); + inode_set_mtime_to_ts(inode1, ts2); + inode_set_mtime_to_ts(inode2, ts1); memswap(ei1->i_data, ei2->i_data, sizeof(ei1->i_data)); tmp = ei1->i_flags & EXT4_FL_SHOULD_SWAP; diff --git a/fs/ext4/mballoc-test.c b/fs/ext4/mballoc-test.c new file mode 100644 index 000000000000..f94901fd3835 --- /dev/null +++ b/fs/ext4/mballoc-test.c @@ -0,0 +1,349 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * KUnit test of ext4 multiblocks allocation. + */ + +#include <kunit/test.h> +#include <kunit/static_stub.h> + +#include "ext4.h" + +struct mbt_grp_ctx { + struct buffer_head bitmap_bh; + /* desc and gd_bh are just the place holders for now */ + struct ext4_group_desc desc; + struct buffer_head gd_bh; +}; + +struct mbt_ctx { + struct mbt_grp_ctx *grp_ctx; +}; + +struct mbt_ext4_super_block { + struct super_block sb; + struct mbt_ctx mbt_ctx; +}; + +#define MBT_CTX(_sb) (&(container_of((_sb), struct mbt_ext4_super_block, sb)->mbt_ctx)) +#define MBT_GRP_CTX(_sb, _group) (&MBT_CTX(_sb)->grp_ctx[_group]) + +static struct super_block *mbt_ext4_alloc_super_block(void) +{ + struct ext4_super_block *es = kzalloc(sizeof(*es), GFP_KERNEL); + struct ext4_sb_info *sbi = kzalloc(sizeof(*sbi), GFP_KERNEL); + struct mbt_ext4_super_block *fsb = kzalloc(sizeof(*fsb), GFP_KERNEL); + + if (fsb == NULL || sbi == NULL || es == NULL) + goto out; + + sbi->s_es = es; + fsb->sb.s_fs_info = sbi; + return &fsb->sb; + +out: + kfree(fsb); + kfree(sbi); + kfree(es); + return NULL; +} + +static void mbt_ext4_free_super_block(struct super_block *sb) +{ + struct mbt_ext4_super_block *fsb = + container_of(sb, struct mbt_ext4_super_block, sb); + struct ext4_sb_info *sbi = EXT4_SB(sb); + + kfree(sbi->s_es); + kfree(sbi); + kfree(fsb); +} + +struct mbt_ext4_block_layout { + unsigned char blocksize_bits; + unsigned int cluster_bits; + uint32_t blocks_per_group; + ext4_group_t group_count; + uint16_t desc_size; +}; + +static void mbt_init_sb_layout(struct super_block *sb, + struct mbt_ext4_block_layout *layout) +{ + struct ext4_sb_info *sbi = EXT4_SB(sb); + struct ext4_super_block *es = sbi->s_es; + + sb->s_blocksize = 1UL << layout->blocksize_bits; + sb->s_blocksize_bits = layout->blocksize_bits; + + sbi->s_groups_count = layout->group_count; + sbi->s_blocks_per_group = layout->blocks_per_group; + sbi->s_cluster_bits = layout->cluster_bits; + sbi->s_cluster_ratio = 1U << layout->cluster_bits; + sbi->s_clusters_per_group = layout->blocks_per_group >> + layout->cluster_bits; + sbi->s_desc_size = layout->desc_size; + + es->s_first_data_block = cpu_to_le32(0); + es->s_blocks_count_lo = cpu_to_le32(layout->blocks_per_group * + layout->group_count); +} + +static int mbt_grp_ctx_init(struct super_block *sb, + struct mbt_grp_ctx *grp_ctx) +{ + grp_ctx->bitmap_bh.b_data = kzalloc(EXT4_BLOCK_SIZE(sb), GFP_KERNEL); + if (grp_ctx->bitmap_bh.b_data == NULL) + return -ENOMEM; + + return 0; +} + +static void mbt_grp_ctx_release(struct mbt_grp_ctx *grp_ctx) +{ + kfree(grp_ctx->bitmap_bh.b_data); + grp_ctx->bitmap_bh.b_data = NULL; +} + +static void mbt_ctx_mark_used(struct super_block *sb, ext4_group_t group, + unsigned int start, unsigned int len) +{ + struct mbt_grp_ctx *grp_ctx = MBT_GRP_CTX(sb, group); + + mb_set_bits(grp_ctx->bitmap_bh.b_data, start, len); +} + +/* called after mbt_init_sb_layout */ +static int mbt_ctx_init(struct super_block *sb) +{ + struct mbt_ctx *ctx = MBT_CTX(sb); + ext4_group_t i, ngroups = ext4_get_groups_count(sb); + + ctx->grp_ctx = kcalloc(ngroups, sizeof(struct mbt_grp_ctx), + GFP_KERNEL); + if (ctx->grp_ctx == NULL) + return -ENOMEM; + + for (i = 0; i < ngroups; i++) + if (mbt_grp_ctx_init(sb, &ctx->grp_ctx[i])) + goto out; + + /* + * first data block(first cluster in first group) is used by + * metadata, mark it used to avoid to alloc data block at first + * block which will fail ext4_sb_block_valid check. + */ + mb_set_bits(ctx->grp_ctx[0].bitmap_bh.b_data, 0, 1); + + return 0; +out: + while (i-- > 0) + mbt_grp_ctx_release(&ctx->grp_ctx[i]); + kfree(ctx->grp_ctx); + return -ENOMEM; +} + +static void mbt_ctx_release(struct super_block *sb) +{ + struct mbt_ctx *ctx = MBT_CTX(sb); + ext4_group_t i, ngroups = ext4_get_groups_count(sb); + + for (i = 0; i < ngroups; i++) + mbt_grp_ctx_release(&ctx->grp_ctx[i]); + kfree(ctx->grp_ctx); +} + +static struct buffer_head * +ext4_read_block_bitmap_nowait_stub(struct super_block *sb, ext4_group_t block_group, + bool ignore_locked) +{ + struct mbt_grp_ctx *grp_ctx = MBT_GRP_CTX(sb, block_group); + + /* paired with brelse from caller of ext4_read_block_bitmap_nowait */ + get_bh(&grp_ctx->bitmap_bh); + return &grp_ctx->bitmap_bh; +} + +static int ext4_wait_block_bitmap_stub(struct super_block *sb, + ext4_group_t block_group, + struct buffer_head *bh) +{ + return 0; +} + +static struct ext4_group_desc * +ext4_get_group_desc_stub(struct super_block *sb, ext4_group_t block_group, + struct buffer_head **bh) +{ + struct mbt_grp_ctx *grp_ctx = MBT_GRP_CTX(sb, block_group); + + if (bh != NULL) + *bh = &grp_ctx->gd_bh; + + return &grp_ctx->desc; +} + +static int +ext4_mb_mark_context_stub(handle_t *handle, struct super_block *sb, bool state, + ext4_group_t group, ext4_grpblk_t blkoff, + ext4_grpblk_t len, int flags, + ext4_grpblk_t *ret_changed) +{ + struct mbt_grp_ctx *grp_ctx = MBT_GRP_CTX(sb, group); + struct buffer_head *bitmap_bh = &grp_ctx->bitmap_bh; + + if (state) + mb_set_bits(bitmap_bh->b_data, blkoff, len); + else + mb_clear_bits(bitmap_bh->b_data, blkoff, len); + + return 0; +} + +#define TEST_GOAL_GROUP 1 +static int mbt_kunit_init(struct kunit *test) +{ + struct mbt_ext4_block_layout *layout = + (struct mbt_ext4_block_layout *)(test->param_value); + struct super_block *sb; + int ret; + + sb = mbt_ext4_alloc_super_block(); + if (sb == NULL) + return -ENOMEM; + + mbt_init_sb_layout(sb, layout); + + ret = mbt_ctx_init(sb); + if (ret != 0) { + mbt_ext4_free_super_block(sb); + return ret; + } + + test->priv = sb; + kunit_activate_static_stub(test, + ext4_read_block_bitmap_nowait, + ext4_read_block_bitmap_nowait_stub); + kunit_activate_static_stub(test, + ext4_wait_block_bitmap, + ext4_wait_block_bitmap_stub); + kunit_activate_static_stub(test, + ext4_get_group_desc, + ext4_get_group_desc_stub); + kunit_activate_static_stub(test, + ext4_mb_mark_context, + ext4_mb_mark_context_stub); + return 0; +} + +static void mbt_kunit_exit(struct kunit *test) +{ + struct super_block *sb = (struct super_block *)test->priv; + + mbt_ctx_release(sb); + mbt_ext4_free_super_block(sb); +} + +static void test_new_blocks_simple(struct kunit *test) +{ + struct super_block *sb = (struct super_block *)test->priv; + struct inode inode = { .i_sb = sb, }; + struct ext4_allocation_request ar; + ext4_group_t i, goal_group = TEST_GOAL_GROUP; + int err = 0; + ext4_fsblk_t found; + struct ext4_sb_info *sbi = EXT4_SB(sb); + + ar.inode = &inode; + + /* get block at goal */ + ar.goal = ext4_group_first_block_no(sb, goal_group); + found = ext4_mb_new_blocks_simple(&ar, &err); + KUNIT_ASSERT_EQ_MSG(test, ar.goal, found, + "failed to alloc block at goal, expected %llu found %llu", + ar.goal, found); + + /* get block after goal in goal group */ + ar.goal = ext4_group_first_block_no(sb, goal_group); + found = ext4_mb_new_blocks_simple(&ar, &err); + KUNIT_ASSERT_EQ_MSG(test, ar.goal + EXT4_C2B(sbi, 1), found, + "failed to alloc block after goal in goal group, expected %llu found %llu", + ar.goal + 1, found); + + /* get block after goal group */ + mbt_ctx_mark_used(sb, goal_group, 0, EXT4_CLUSTERS_PER_GROUP(sb)); + ar.goal = ext4_group_first_block_no(sb, goal_group); + found = ext4_mb_new_blocks_simple(&ar, &err); + KUNIT_ASSERT_EQ_MSG(test, + ext4_group_first_block_no(sb, goal_group + 1), found, + "failed to alloc block after goal group, expected %llu found %llu", + ext4_group_first_block_no(sb, goal_group + 1), found); + + /* get block before goal group */ + for (i = goal_group; i < ext4_get_groups_count(sb); i++) + mbt_ctx_mark_used(sb, i, 0, EXT4_CLUSTERS_PER_GROUP(sb)); + ar.goal = ext4_group_first_block_no(sb, goal_group); + found = ext4_mb_new_blocks_simple(&ar, &err); + KUNIT_ASSERT_EQ_MSG(test, + ext4_group_first_block_no(sb, 0) + EXT4_C2B(sbi, 1), found, + "failed to alloc block before goal group, expected %llu found %llu", + ext4_group_first_block_no(sb, 0 + EXT4_C2B(sbi, 1)), found); + + /* no block available, fail to allocate block */ + for (i = 0; i < ext4_get_groups_count(sb); i++) + mbt_ctx_mark_used(sb, i, 0, EXT4_CLUSTERS_PER_GROUP(sb)); + ar.goal = ext4_group_first_block_no(sb, goal_group); + found = ext4_mb_new_blocks_simple(&ar, &err); + KUNIT_ASSERT_NE_MSG(test, err, 0, + "unexpectedly get block when no block is available"); +} + +static const struct mbt_ext4_block_layout mbt_test_layouts[] = { + { + .blocksize_bits = 10, + .cluster_bits = 3, + .blocks_per_group = 8192, + .group_count = 4, + .desc_size = 64, + }, + { + .blocksize_bits = 12, + .cluster_bits = 3, + .blocks_per_group = 8192, + .group_count = 4, + .desc_size = 64, + }, + { + .blocksize_bits = 16, + .cluster_bits = 3, + .blocks_per_group = 8192, + .group_count = 4, + .desc_size = 64, + }, +}; + +static void mbt_show_layout(const struct mbt_ext4_block_layout *layout, + char *desc) +{ + snprintf(desc, KUNIT_PARAM_DESC_SIZE, "block_bits=%d cluster_bits=%d " + "blocks_per_group=%d group_count=%d desc_size=%d\n", + layout->blocksize_bits, layout->cluster_bits, + layout->blocks_per_group, layout->group_count, + layout->desc_size); +} +KUNIT_ARRAY_PARAM(mbt_layouts, mbt_test_layouts, mbt_show_layout); + +static struct kunit_case mbt_test_cases[] = { + KUNIT_CASE_PARAM(test_new_blocks_simple, mbt_layouts_gen_params), + {} +}; + +static struct kunit_suite mbt_test_suite = { + .name = "ext4_mballoc_test", + .init = mbt_kunit_init, + .exit = mbt_kunit_exit, + .test_cases = mbt_test_cases, +}; + +kunit_test_suites(&mbt_test_suite); + +MODULE_LICENSE("GPL"); diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 1e599305d85f..454d5612641e 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -18,6 +18,7 @@ #include <linux/backing-dev.h> #include <linux/freezer.h> #include <trace/events/ext4.h> +#include <kunit/static_stub.h> /* * MUSTDO: @@ -417,8 +418,6 @@ static const char * const ext4_groupinfo_slab_names[NR_GRPINFO_CACHES] = { static void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap, ext4_group_t group); -static void ext4_mb_generate_from_freelist(struct super_block *sb, void *bitmap, - ext4_group_t group); static void ext4_mb_new_preallocation(struct ext4_allocation_context *ac); static bool ext4_mb_good_group(struct ext4_allocation_context *ac, @@ -1361,17 +1360,17 @@ static int ext4_mb_init_cache(struct page *page, char *incore, gfp_t gfp) * We place the buddy block and bitmap block * close together */ + grinfo = ext4_get_group_info(sb, group); + if (!grinfo) { + err = -EFSCORRUPTED; + goto out; + } if ((first_block + i) & 1) { /* this is block of buddy */ BUG_ON(incore == NULL); mb_debug(sb, "put buddy for group %u in page %lu/%x\n", group, page->index, i * blocksize); trace_ext4_mb_buddy_bitmap_load(sb, group); - grinfo = ext4_get_group_info(sb, group); - if (!grinfo) { - err = -EFSCORRUPTED; - goto out; - } grinfo->bb_fragments = 0; memset(grinfo->bb_counters, 0, sizeof(*grinfo->bb_counters) * @@ -1398,7 +1397,7 @@ static int ext4_mb_init_cache(struct page *page, char *incore, gfp_t gfp) /* mark all preallocated blks used in in-core bitmap */ ext4_mb_generate_from_pa(sb, data, group); - ext4_mb_generate_from_freelist(sb, data, group); + WARN_ON_ONCE(!RB_EMPTY_ROOT(&grinfo->bb_free_root)); ext4_unlock_group(sb, group); /* set incore so that the buddy information can be @@ -3631,7 +3630,8 @@ int ext4_mb_init(struct super_block *sb) spin_lock_init(&sbi->s_md_lock); sbi->s_mb_free_pending = 0; - INIT_LIST_HEAD(&sbi->s_freed_data_list); + INIT_LIST_HEAD(&sbi->s_freed_data_list[0]); + INIT_LIST_HEAD(&sbi->s_freed_data_list[1]); INIT_LIST_HEAD(&sbi->s_discard_list); INIT_WORK(&sbi->s_discard_work, ext4_discard_work); atomic_set(&sbi->s_retry_alloc_pending, 0); @@ -3883,19 +3883,10 @@ void ext4_process_freed_data(struct super_block *sb, tid_t commit_tid) struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_free_data *entry, *tmp; LIST_HEAD(freed_data_list); - struct list_head *cut_pos = NULL; + struct list_head *s_freed_head = &sbi->s_freed_data_list[commit_tid & 1]; bool wake; - spin_lock(&sbi->s_md_lock); - list_for_each_entry(entry, &sbi->s_freed_data_list, efd_list) { - if (entry->efd_tid != commit_tid) - break; - cut_pos = &entry->efd_list; - } - if (cut_pos) - list_cut_position(&freed_data_list, &sbi->s_freed_data_list, - cut_pos); - spin_unlock(&sbi->s_md_lock); + list_replace_init(s_freed_head, &freed_data_list); list_for_each_entry(entry, &freed_data_list, efd_list) ext4_free_data_in_buddy(sb, entry); @@ -3953,6 +3944,111 @@ void ext4_exit_mballoc(void) ext4_groupinfo_destroy_slabs(); } +#define EXT4_MB_BITMAP_MARKED_CHECK 0x0001 +#define EXT4_MB_SYNC_UPDATE 0x0002 +static int +ext4_mb_mark_context(handle_t *handle, struct super_block *sb, bool state, + ext4_group_t group, ext4_grpblk_t blkoff, + ext4_grpblk_t len, int flags, ext4_grpblk_t *ret_changed) +{ + struct ext4_sb_info *sbi = EXT4_SB(sb); + struct buffer_head *bitmap_bh = NULL; + struct ext4_group_desc *gdp; + struct buffer_head *gdp_bh; + int err; + unsigned int i, already, changed = len; + + KUNIT_STATIC_STUB_REDIRECT(ext4_mb_mark_context, + handle, sb, state, group, blkoff, len, + flags, ret_changed); + + if (ret_changed) + *ret_changed = 0; + bitmap_bh = ext4_read_block_bitmap(sb, group); + if (IS_ERR(bitmap_bh)) + return PTR_ERR(bitmap_bh); + + if (handle) { + BUFFER_TRACE(bitmap_bh, "getting write access"); + err = ext4_journal_get_write_access(handle, sb, bitmap_bh, + EXT4_JTR_NONE); + if (err) + goto out_err; + } + + err = -EIO; + gdp = ext4_get_group_desc(sb, group, &gdp_bh); + if (!gdp) + goto out_err; + + if (handle) { + BUFFER_TRACE(gdp_bh, "get_write_access"); + err = ext4_journal_get_write_access(handle, sb, gdp_bh, + EXT4_JTR_NONE); + if (err) + goto out_err; + } + + ext4_lock_group(sb, group); + if (ext4_has_group_desc_csum(sb) && + (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT))) { + gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT); + ext4_free_group_clusters_set(sb, gdp, + ext4_free_clusters_after_init(sb, group, gdp)); + } + + if (flags & EXT4_MB_BITMAP_MARKED_CHECK) { + already = 0; + for (i = 0; i < len; i++) + if (mb_test_bit(blkoff + i, bitmap_bh->b_data) == + state) + already++; + changed = len - already; + } + + if (state) { + mb_set_bits(bitmap_bh->b_data, blkoff, len); + ext4_free_group_clusters_set(sb, gdp, + ext4_free_group_clusters(sb, gdp) - changed); + } else { + mb_clear_bits(bitmap_bh->b_data, blkoff, len); + ext4_free_group_clusters_set(sb, gdp, + ext4_free_group_clusters(sb, gdp) + changed); + } + + ext4_block_bitmap_csum_set(sb, gdp, bitmap_bh); + ext4_group_desc_csum_set(sb, group, gdp); + ext4_unlock_group(sb, group); + if (ret_changed) + *ret_changed = changed; + + if (sbi->s_log_groups_per_flex) { + ext4_group_t flex_group = ext4_flex_group(sbi, group); + struct flex_groups *fg = sbi_array_rcu_deref(sbi, + s_flex_groups, flex_group); + + if (state) + atomic64_sub(changed, &fg->free_clusters); + else + atomic64_add(changed, &fg->free_clusters); + } + + err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh); + if (err) + goto out_err; + err = ext4_handle_dirty_metadata(handle, NULL, gdp_bh); + if (err) + goto out_err; + + if (flags & EXT4_MB_SYNC_UPDATE) { + sync_dirty_buffer(bitmap_bh); + sync_dirty_buffer(gdp_bh); + } + +out_err: + brelse(bitmap_bh); + return err; +} /* * Check quota and mark chosen space (ac->ac_b_ex) non-free in bitmaps @@ -3962,13 +4058,13 @@ static noinline_for_stack int ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac, handle_t *handle, unsigned int reserv_clstrs) { - struct buffer_head *bitmap_bh = NULL; struct ext4_group_desc *gdp; - struct buffer_head *gdp_bh; struct ext4_sb_info *sbi; struct super_block *sb; ext4_fsblk_t block; int err, len; + int flags = 0; + ext4_grpblk_t changed; BUG_ON(ac->ac_status != AC_STATUS_FOUND); BUG_ON(ac->ac_b_ex.fe_len <= 0); @@ -3976,32 +4072,13 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac, sb = ac->ac_sb; sbi = EXT4_SB(sb); - bitmap_bh = ext4_read_block_bitmap(sb, ac->ac_b_ex.fe_group); - if (IS_ERR(bitmap_bh)) { - return PTR_ERR(bitmap_bh); - } - - BUFFER_TRACE(bitmap_bh, "getting write access"); - err = ext4_journal_get_write_access(handle, sb, bitmap_bh, - EXT4_JTR_NONE); - if (err) - goto out_err; - - err = -EIO; - gdp = ext4_get_group_desc(sb, ac->ac_b_ex.fe_group, &gdp_bh); + gdp = ext4_get_group_desc(sb, ac->ac_b_ex.fe_group, NULL); if (!gdp) - goto out_err; - + return -EIO; ext4_debug("using block group %u(%d)\n", ac->ac_b_ex.fe_group, ext4_free_group_clusters(sb, gdp)); - BUFFER_TRACE(gdp_bh, "get_write_access"); - err = ext4_journal_get_write_access(handle, sb, gdp_bh, EXT4_JTR_NONE); - if (err) - goto out_err; - block = ext4_grp_offs_to_block(sb, &ac->ac_b_ex); - len = EXT4_C2B(sbi, ac->ac_b_ex.fe_len); if (!ext4_inode_block_valid(ac->ac_inode, block, len)) { ext4_error(sb, "Allocating blocks %llu-%llu which overlap " @@ -4010,41 +4087,29 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac, * Fix the bitmap and return EFSCORRUPTED * We leak some of the blocks here. */ - ext4_lock_group(sb, ac->ac_b_ex.fe_group); - mb_set_bits(bitmap_bh->b_data, ac->ac_b_ex.fe_start, - ac->ac_b_ex.fe_len); - ext4_unlock_group(sb, ac->ac_b_ex.fe_group); - err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh); + err = ext4_mb_mark_context(handle, sb, true, + ac->ac_b_ex.fe_group, + ac->ac_b_ex.fe_start, + ac->ac_b_ex.fe_len, + 0, NULL); if (!err) err = -EFSCORRUPTED; - goto out_err; + return err; } - ext4_lock_group(sb, ac->ac_b_ex.fe_group); #ifdef AGGRESSIVE_CHECK - { - int i; - for (i = 0; i < ac->ac_b_ex.fe_len; i++) { - BUG_ON(mb_test_bit(ac->ac_b_ex.fe_start + i, - bitmap_bh->b_data)); - } - } + flags |= EXT4_MB_BITMAP_MARKED_CHECK; #endif - mb_set_bits(bitmap_bh->b_data, ac->ac_b_ex.fe_start, - ac->ac_b_ex.fe_len); - if (ext4_has_group_desc_csum(sb) && - (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT))) { - gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT); - ext4_free_group_clusters_set(sb, gdp, - ext4_free_clusters_after_init(sb, - ac->ac_b_ex.fe_group, gdp)); - } - len = ext4_free_group_clusters(sb, gdp) - ac->ac_b_ex.fe_len; - ext4_free_group_clusters_set(sb, gdp, len); - ext4_block_bitmap_csum_set(sb, gdp, bitmap_bh); - ext4_group_desc_csum_set(sb, ac->ac_b_ex.fe_group, gdp); + err = ext4_mb_mark_context(handle, sb, true, ac->ac_b_ex.fe_group, + ac->ac_b_ex.fe_start, ac->ac_b_ex.fe_len, + flags, &changed); + + if (err && changed == 0) + return err; - ext4_unlock_group(sb, ac->ac_b_ex.fe_group); +#ifdef AGGRESSIVE_CHECK + BUG_ON(changed != ac->ac_b_ex.fe_len); +#endif percpu_counter_sub(&sbi->s_freeclusters_counter, ac->ac_b_ex.fe_len); /* * Now reduce the dirty block count also. Should not go negative @@ -4054,21 +4119,6 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac, percpu_counter_sub(&sbi->s_dirtyclusters_counter, reserv_clstrs); - if (sbi->s_log_groups_per_flex) { - ext4_group_t flex_group = ext4_flex_group(sbi, - ac->ac_b_ex.fe_group); - atomic64_sub(ac->ac_b_ex.fe_len, - &sbi_array_rcu_deref(sbi, s_flex_groups, - flex_group)->free_clusters); - } - - err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh); - if (err) - goto out_err; - err = ext4_handle_dirty_metadata(handle, NULL, gdp_bh); - -out_err: - brelse(bitmap_bh); return err; } @@ -4077,17 +4127,13 @@ out_err: * blocks in bitmaps and update counters. */ void ext4_mb_mark_bb(struct super_block *sb, ext4_fsblk_t block, - int len, int state) + int len, bool state) { - struct buffer_head *bitmap_bh = NULL; - struct ext4_group_desc *gdp; - struct buffer_head *gdp_bh; struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_group_t group; ext4_grpblk_t blkoff; - int i, err = 0; - int already; - unsigned int clen, clen_changed, thisgrp_len; + int err = 0; + unsigned int clen, thisgrp_len; while (len > 0) { ext4_get_group_no_and_offset(sb, block, &group, &blkoff); @@ -4108,80 +4154,21 @@ void ext4_mb_mark_bb(struct super_block *sb, ext4_fsblk_t block, ext4_error(sb, "Marking blocks in system zone - " "Block = %llu, len = %u", block, thisgrp_len); - bitmap_bh = NULL; - break; - } - - bitmap_bh = ext4_read_block_bitmap(sb, group); - if (IS_ERR(bitmap_bh)) { - err = PTR_ERR(bitmap_bh); - bitmap_bh = NULL; break; } - err = -EIO; - gdp = ext4_get_group_desc(sb, group, &gdp_bh); - if (!gdp) - break; - - ext4_lock_group(sb, group); - already = 0; - for (i = 0; i < clen; i++) - if (!mb_test_bit(blkoff + i, bitmap_bh->b_data) == - !state) - already++; - - clen_changed = clen - already; - if (state) - mb_set_bits(bitmap_bh->b_data, blkoff, clen); - else - mb_clear_bits(bitmap_bh->b_data, blkoff, clen); - if (ext4_has_group_desc_csum(sb) && - (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT))) { - gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT); - ext4_free_group_clusters_set(sb, gdp, - ext4_free_clusters_after_init(sb, group, gdp)); - } - if (state) - clen = ext4_free_group_clusters(sb, gdp) - clen_changed; - else - clen = ext4_free_group_clusters(sb, gdp) + clen_changed; - - ext4_free_group_clusters_set(sb, gdp, clen); - ext4_block_bitmap_csum_set(sb, gdp, bitmap_bh); - ext4_group_desc_csum_set(sb, group, gdp); - - ext4_unlock_group(sb, group); - - if (sbi->s_log_groups_per_flex) { - ext4_group_t flex_group = ext4_flex_group(sbi, group); - struct flex_groups *fg = sbi_array_rcu_deref(sbi, - s_flex_groups, flex_group); - - if (state) - atomic64_sub(clen_changed, &fg->free_clusters); - else - atomic64_add(clen_changed, &fg->free_clusters); - - } - - err = ext4_handle_dirty_metadata(NULL, NULL, bitmap_bh); - if (err) - break; - sync_dirty_buffer(bitmap_bh); - err = ext4_handle_dirty_metadata(NULL, NULL, gdp_bh); - sync_dirty_buffer(gdp_bh); + err = ext4_mb_mark_context(NULL, sb, state, + group, blkoff, clen, + EXT4_MB_BITMAP_MARKED_CHECK | + EXT4_MB_SYNC_UPDATE, + NULL); if (err) break; block += thisgrp_len; len -= thisgrp_len; - brelse(bitmap_bh); BUG_ON(len < 0); } - - if (err) - brelse(bitmap_bh); } /* @@ -4959,31 +4946,6 @@ try_group_pa: } /* - * the function goes through all block freed in the group - * but not yet committed and marks them used in in-core bitmap. - * buddy must be generated from this bitmap - * Need to be called with the ext4 group lock held - */ -static void ext4_mb_generate_from_freelist(struct super_block *sb, void *bitmap, - ext4_group_t group) -{ - struct rb_node *n; - struct ext4_group_info *grp; - struct ext4_free_data *entry; - - grp = ext4_get_group_info(sb, group); - if (!grp) - return; - n = rb_first(&(grp->bb_free_root)); - - while (n) { - entry = rb_entry(n, struct ext4_free_data, efd_node); - mb_set_bits(bitmap, entry->efd_start_cluster, entry->efd_count); - n = rb_next(n); - } -} - -/* * the function goes through all preallocation in this group and marks them * used in in-core bitmap. buddy must be generated from this bitmap * Need to be called with ext4 group lock held @@ -6130,7 +6092,7 @@ ext4_mb_new_blocks_simple(struct ext4_allocation_request *ar, int *errp) } block = ext4_group_first_block_no(sb, group) + EXT4_C2B(sbi, i); - ext4_mb_mark_bb(sb, block, 1, 1); + ext4_mb_mark_bb(sb, block, 1, true); ar->len = 1; return block; @@ -6378,7 +6340,7 @@ ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b, } spin_lock(&sbi->s_md_lock); - list_add_tail(&new_entry->efd_list, &sbi->s_freed_data_list); + list_add_tail(&new_entry->efd_list, &sbi->s_freed_data_list[new_entry->efd_tid & 1]); sbi->s_mb_free_pending += clusters; spin_unlock(&sbi->s_md_lock); } @@ -6386,43 +6348,15 @@ ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b, static void ext4_free_blocks_simple(struct inode *inode, ext4_fsblk_t block, unsigned long count) { - struct buffer_head *bitmap_bh; struct super_block *sb = inode->i_sb; - struct ext4_group_desc *gdp; - struct buffer_head *gdp_bh; ext4_group_t group; ext4_grpblk_t blkoff; - int already_freed = 0, err, i; ext4_get_group_no_and_offset(sb, block, &group, &blkoff); - bitmap_bh = ext4_read_block_bitmap(sb, group); - if (IS_ERR(bitmap_bh)) { - pr_warn("Failed to read block bitmap\n"); - return; - } - gdp = ext4_get_group_desc(sb, group, &gdp_bh); - if (!gdp) - goto err_out; - - for (i = 0; i < count; i++) { - if (!mb_test_bit(blkoff + i, bitmap_bh->b_data)) - already_freed++; - } - mb_clear_bits(bitmap_bh->b_data, blkoff, count); - err = ext4_handle_dirty_metadata(NULL, NULL, bitmap_bh); - if (err) - goto err_out; - ext4_free_group_clusters_set( - sb, gdp, ext4_free_group_clusters(sb, gdp) + - count - already_freed); - ext4_block_bitmap_csum_set(sb, gdp, bitmap_bh); - ext4_group_desc_csum_set(sb, group, gdp); - ext4_handle_dirty_metadata(NULL, NULL, gdp_bh); - sync_dirty_buffer(bitmap_bh); - sync_dirty_buffer(gdp_bh); - -err_out: - brelse(bitmap_bh); + ext4_mb_mark_context(NULL, sb, false, group, blkoff, count, + EXT4_MB_BITMAP_MARKED_CHECK | + EXT4_MB_SYNC_UPDATE, + NULL); } /** @@ -6438,19 +6372,17 @@ static void ext4_mb_clear_bb(handle_t *handle, struct inode *inode, ext4_fsblk_t block, unsigned long count, int flags) { - struct buffer_head *bitmap_bh = NULL; struct super_block *sb = inode->i_sb; - struct ext4_group_desc *gdp; struct ext4_group_info *grp; unsigned int overflow; ext4_grpblk_t bit; - struct buffer_head *gd_bh; ext4_group_t block_group; struct ext4_sb_info *sbi; struct ext4_buddy e4b; unsigned int count_clusters; int err = 0; - int ret; + int mark_flags = 0; + ext4_grpblk_t changed; sbi = EXT4_SB(sb); @@ -6459,7 +6391,7 @@ static void ext4_mb_clear_bb(handle_t *handle, struct inode *inode, ext4_error(sb, "Freeing blocks in system zone - " "Block = %llu, count = %lu", block, count); /* err = 0. ext4_std_error should be a no op */ - goto error_return; + goto error_out; } flags |= EXT4_FREE_BLOCKS_VALIDATED; @@ -6483,55 +6415,35 @@ do_more: flags &= ~EXT4_FREE_BLOCKS_VALIDATED; } count_clusters = EXT4_NUM_B2C(sbi, count); - bitmap_bh = ext4_read_block_bitmap(sb, block_group); - if (IS_ERR(bitmap_bh)) { - err = PTR_ERR(bitmap_bh); - bitmap_bh = NULL; - goto error_return; - } - gdp = ext4_get_group_desc(sb, block_group, &gd_bh); - if (!gdp) { - err = -EIO; - goto error_return; - } + trace_ext4_mballoc_free(sb, inode, block_group, bit, count_clusters); + + /* __GFP_NOFAIL: retry infinitely, ignore TIF_MEMDIE and memcg limit. */ + err = ext4_mb_load_buddy_gfp(sb, block_group, &e4b, + GFP_NOFS|__GFP_NOFAIL); + if (err) + goto error_out; if (!(flags & EXT4_FREE_BLOCKS_VALIDATED) && !ext4_inode_block_valid(inode, block, count)) { ext4_error(sb, "Freeing blocks in system zone - " "Block = %llu, count = %lu", block, count); /* err = 0. ext4_std_error should be a no op */ - goto error_return; + goto error_clean; } - BUFFER_TRACE(bitmap_bh, "getting write access"); - err = ext4_journal_get_write_access(handle, sb, bitmap_bh, - EXT4_JTR_NONE); - if (err) - goto error_return; - - /* - * We are about to modify some metadata. Call the journal APIs - * to unshare ->b_data if a currently-committing transaction is - * using it - */ - BUFFER_TRACE(gd_bh, "get_write_access"); - err = ext4_journal_get_write_access(handle, sb, gd_bh, EXT4_JTR_NONE); - if (err) - goto error_return; #ifdef AGGRESSIVE_CHECK - { - int i; - for (i = 0; i < count_clusters; i++) - BUG_ON(!mb_test_bit(bit + i, bitmap_bh->b_data)); - } + mark_flags |= EXT4_MB_BITMAP_MARKED_CHECK; #endif - trace_ext4_mballoc_free(sb, inode, block_group, bit, count_clusters); + err = ext4_mb_mark_context(handle, sb, false, block_group, bit, + count_clusters, mark_flags, &changed); - /* __GFP_NOFAIL: retry infinitely, ignore TIF_MEMDIE and memcg limit. */ - err = ext4_mb_load_buddy_gfp(sb, block_group, &e4b, - GFP_NOFS|__GFP_NOFAIL); - if (err) - goto error_return; + + if (err && changed == 0) + goto error_clean; + +#ifdef AGGRESSIVE_CHECK + BUG_ON(changed != count_clusters); +#endif /* * We need to make sure we don't reuse the freed block until after the @@ -6555,13 +6467,8 @@ do_more: new_entry->efd_tid = handle->h_transaction->t_tid; ext4_lock_group(sb, block_group); - mb_clear_bits(bitmap_bh->b_data, bit, count_clusters); ext4_mb_free_metadata(handle, &e4b, new_entry); } else { - /* need to update group_info->bb_free and bitmap - * with group lock held. generate_buddy look at - * them with group lock_held - */ if (test_opt(sb, DISCARD)) { err = ext4_issue_discard(sb, block_group, bit, count_clusters, NULL); @@ -6574,23 +6481,11 @@ do_more: EXT4_MB_GRP_CLEAR_TRIMMED(e4b.bd_info); ext4_lock_group(sb, block_group); - mb_clear_bits(bitmap_bh->b_data, bit, count_clusters); mb_free_blocks(inode, &e4b, bit, count_clusters); } - ret = ext4_free_group_clusters(sb, gdp) + count_clusters; - ext4_free_group_clusters_set(sb, gdp, ret); - ext4_block_bitmap_csum_set(sb, gdp, bitmap_bh); - ext4_group_desc_csum_set(sb, block_group, gdp); ext4_unlock_group(sb, block_group); - if (sbi->s_log_groups_per_flex) { - ext4_group_t flex_group = ext4_flex_group(sbi, block_group); - atomic64_add(count_clusters, - &sbi_array_rcu_deref(sbi, s_flex_groups, - flex_group)->free_clusters); - } - /* * on a bigalloc file system, defer the s_freeclusters_counter * update to the caller (ext4_remove_space and friends) so they @@ -6603,28 +6498,18 @@ do_more: count_clusters); } - ext4_mb_unload_buddy(&e4b); - - /* We dirtied the bitmap block */ - BUFFER_TRACE(bitmap_bh, "dirtied bitmap block"); - err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh); - - /* And the group descriptor block */ - BUFFER_TRACE(gd_bh, "dirtied group descriptor block"); - ret = ext4_handle_dirty_metadata(handle, NULL, gd_bh); - if (!err) - err = ret; - if (overflow && !err) { block += count; count = overflow; - put_bh(bitmap_bh); + ext4_mb_unload_buddy(&e4b); /* The range changed so it's no longer validated */ flags &= ~EXT4_FREE_BLOCKS_VALIDATED; goto do_more; } -error_return: - brelse(bitmap_bh); + +error_clean: + ext4_mb_unload_buddy(&e4b); +error_out: ext4_std_error(sb, err); } @@ -6742,23 +6627,19 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode, int ext4_group_add_blocks(handle_t *handle, struct super_block *sb, ext4_fsblk_t block, unsigned long count) { - struct buffer_head *bitmap_bh = NULL; - struct buffer_head *gd_bh; ext4_group_t block_group; ext4_grpblk_t bit; - unsigned int i; - struct ext4_group_desc *desc; struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_buddy e4b; - int err = 0, ret, free_clusters_count; - ext4_grpblk_t clusters_freed; + int err = 0; ext4_fsblk_t first_cluster = EXT4_B2C(sbi, block); ext4_fsblk_t last_cluster = EXT4_B2C(sbi, block + count - 1); unsigned long cluster_count = last_cluster - first_cluster + 1; + ext4_grpblk_t changed; ext4_debug("Adding block(s) %llu-%llu\n", block, block + count - 1); - if (count == 0) + if (cluster_count == 0) return 0; ext4_get_group_no_and_offset(sb, block, &block_group, &bit); @@ -6770,99 +6651,39 @@ int ext4_group_add_blocks(handle_t *handle, struct super_block *sb, ext4_warning(sb, "too many blocks added to group %u", block_group); err = -EINVAL; - goto error_return; - } - - bitmap_bh = ext4_read_block_bitmap(sb, block_group); - if (IS_ERR(bitmap_bh)) { - err = PTR_ERR(bitmap_bh); - bitmap_bh = NULL; - goto error_return; + goto error_out; } - desc = ext4_get_group_desc(sb, block_group, &gd_bh); - if (!desc) { - err = -EIO; - goto error_return; - } + err = ext4_mb_load_buddy(sb, block_group, &e4b); + if (err) + goto error_out; if (!ext4_sb_block_valid(sb, NULL, block, count)) { ext4_error(sb, "Adding blocks in system zones - " "Block = %llu, count = %lu", block, count); err = -EINVAL; - goto error_return; + goto error_clean; } - BUFFER_TRACE(bitmap_bh, "getting write access"); - err = ext4_journal_get_write_access(handle, sb, bitmap_bh, - EXT4_JTR_NONE); - if (err) - goto error_return; - - /* - * We are about to modify some metadata. Call the journal APIs - * to unshare ->b_data if a currently-committing transaction is - * using it - */ - BUFFER_TRACE(gd_bh, "get_write_access"); - err = ext4_journal_get_write_access(handle, sb, gd_bh, EXT4_JTR_NONE); - if (err) - goto error_return; - - for (i = 0, clusters_freed = 0; i < cluster_count; i++) { - BUFFER_TRACE(bitmap_bh, "clear bit"); - if (!mb_test_bit(bit + i, bitmap_bh->b_data)) { - ext4_error(sb, "bit already cleared for block %llu", - (ext4_fsblk_t)(block + i)); - BUFFER_TRACE(bitmap_bh, "bit already cleared"); - } else { - clusters_freed++; - } - } + err = ext4_mb_mark_context(handle, sb, false, block_group, bit, + cluster_count, EXT4_MB_BITMAP_MARKED_CHECK, + &changed); + if (err && changed == 0) + goto error_clean; - err = ext4_mb_load_buddy(sb, block_group, &e4b); - if (err) - goto error_return; + if (changed != cluster_count) + ext4_error(sb, "bit already cleared in group %u", block_group); - /* - * need to update group_info->bb_free and bitmap - * with group lock held. generate_buddy look at - * them with group lock_held - */ ext4_lock_group(sb, block_group); - mb_clear_bits(bitmap_bh->b_data, bit, cluster_count); mb_free_blocks(NULL, &e4b, bit, cluster_count); - free_clusters_count = clusters_freed + - ext4_free_group_clusters(sb, desc); - ext4_free_group_clusters_set(sb, desc, free_clusters_count); - ext4_block_bitmap_csum_set(sb, desc, bitmap_bh); - ext4_group_desc_csum_set(sb, block_group, desc); ext4_unlock_group(sb, block_group); percpu_counter_add(&sbi->s_freeclusters_counter, - clusters_freed); - - if (sbi->s_log_groups_per_flex) { - ext4_group_t flex_group = ext4_flex_group(sbi, block_group); - atomic64_add(clusters_freed, - &sbi_array_rcu_deref(sbi, s_flex_groups, - flex_group)->free_clusters); - } + changed); +error_clean: ext4_mb_unload_buddy(&e4b); - - /* We dirtied the bitmap block */ - BUFFER_TRACE(bitmap_bh, "dirtied bitmap block"); - err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh); - - /* And the group descriptor block */ - BUFFER_TRACE(gd_bh, "dirtied group descriptor block"); - ret = ext4_handle_dirty_metadata(handle, NULL, gd_bh); - if (!err) - err = ret; - -error_return: - brelse(bitmap_bh); +error_out: ext4_std_error(sb, err); return err; } @@ -7170,3 +6991,7 @@ out_unload: return error; } + +#ifdef CONFIG_EXT4_KUNIT_TESTS +#include "mballoc-test.c" +#endif diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c index 18a9e7c47975..3aa57376d9c2 100644 --- a/fs/ext4/move_extent.c +++ b/fs/ext4/move_extent.c @@ -183,10 +183,8 @@ mext_page_mkuptodate(struct folio *folio, unsigned from, unsigned to) blocksize = i_blocksize(inode); head = folio_buffers(folio); - if (!head) { - create_empty_buffers(&folio->page, blocksize, 0); - head = folio_buffers(folio); - } + if (!head) + head = create_empty_buffers(folio, blocksize, 0); block = (sector_t)folio->index << (PAGE_SHIFT - inode->i_blkbits); for (bh = head, block_start = 0; bh != head || !block_start; @@ -380,9 +378,10 @@ data_copy: } /* Perform all necessary steps similar write_begin()/write_end() * but keeping in mind that i_size will not change */ - if (!folio_buffers(folio[0])) - create_empty_buffers(&folio[0]->page, 1 << orig_inode->i_blkbits, 0); bh = folio_buffers(folio[0]); + if (!bh) + bh = create_empty_buffers(folio[0], + 1 << orig_inode->i_blkbits, 0); for (i = 0; i < data_offset_in_page; i++) bh = bh->b_this_page; for (i = 0; i < block_len_in_page; i++) { diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index bbda587f76b8..d252935f9c8a 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -2207,7 +2207,7 @@ static int add_dirent_to_buf(handle_t *handle, struct ext4_filename *fname, * happen is that the times are slightly out of date * and/or different from the directory change time. */ - dir->i_mtime = inode_set_ctime_current(dir); + inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); ext4_update_dx_flag(dir); inode_inc_iversion(dir); err2 = ext4_mark_inode_dirty(handle, dir); @@ -2280,8 +2280,7 @@ static int make_indexed_dir(handle_t *handle, struct ext4_filename *fname, top = data2 + len; while ((char *)(de2 = ext4_next_entry(de, blocksize)) < top) { if (ext4_check_dir_entry(dir, NULL, de, bh2, data2, len, - (data2 + (blocksize - csum_size) - - (char *) de))) { + (char *)de - data2)) { brelse(bh2); brelse(bh); return -EFSCORRUPTED; @@ -3202,7 +3201,7 @@ static int ext4_rmdir(struct inode *dir, struct dentry *dentry) * recovery. */ inode->i_size = 0; ext4_orphan_add(handle, inode); - dir->i_mtime = inode_set_ctime_current(dir); + inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); inode_set_ctime_current(inode); retval = ext4_mark_inode_dirty(handle, inode); if (retval) @@ -3277,7 +3276,7 @@ int __ext4_unlink(struct inode *dir, const struct qstr *d_name, retval = ext4_delete_entry(handle, dir, de, bh); if (retval) goto out_handle; - dir->i_mtime = inode_set_ctime_current(dir); + inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); ext4_update_dx_flag(dir); retval = ext4_mark_inode_dirty(handle, dir); if (retval) @@ -3648,7 +3647,7 @@ static int ext4_setent(handle_t *handle, struct ext4_renament *ent, if (ext4_has_feature_filetype(ent->dir->i_sb)) ent->de->file_type = file_type; inode_inc_iversion(ent->dir); - ent->dir->i_mtime = inode_set_ctime_current(ent->dir); + inode_set_mtime_to_ts(ent->dir, inode_set_ctime_current(ent->dir)); retval = ext4_mark_inode_dirty(handle, ent->dir); BUFFER_TRACE(ent->bh, "call ext4_handle_dirty_metadata"); if (!ent->inlined) { @@ -3963,7 +3962,7 @@ static int ext4_rename(struct mnt_idmap *idmap, struct inode *old_dir, ext4_dec_count(new.inode); inode_set_ctime_current(new.inode); } - old.dir->i_mtime = inode_set_ctime_current(old.dir); + inode_set_mtime_to_ts(old.dir, inode_set_ctime_current(old.dir)); ext4_update_dx_flag(old.dir); if (old.dir_bh) { retval = ext4_rename_dir_finish(handle, &old, new.dir->i_ino); diff --git a/fs/ext4/readpage.c b/fs/ext4/readpage.c index 3e7d160f543f..21e8f0aebb3c 100644 --- a/fs/ext4/readpage.c +++ b/fs/ext4/readpage.c @@ -70,15 +70,8 @@ static void __read_end_io(struct bio *bio) { struct folio_iter fi; - bio_for_each_folio_all(fi, bio) { - struct folio *folio = fi.folio; - - if (bio->bi_status) - folio_clear_uptodate(folio); - else - folio_mark_uptodate(folio); - folio_unlock(folio); - } + bio_for_each_folio_all(fi, bio) + folio_end_read(fi.folio, bio->bi_status == 0); if (bio->bi_private) mempool_free(bio->bi_private, bio_post_read_ctx_pool); bio_put(bio); @@ -336,8 +329,7 @@ int ext4_mpage_readpages(struct inode *inode, if (ext4_need_verity(inode, folio->index) && !fsverity_verify_folio(folio)) goto set_error_page; - folio_mark_uptodate(folio); - folio_unlock(folio); + folio_end_read(folio, true); continue; } } else if (fully_mapped) { diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index 0361c20910de..4fe061edefdd 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -10,8 +10,6 @@ */ -#define EXT4FS_DEBUG - #include <linux/errno.h> #include <linux/slab.h> #include <linux/jiffies.h> @@ -57,7 +55,7 @@ int ext4_resize_begin(struct super_block *sb) * If the reserved GDT blocks is non-zero, the resize_inode feature * should always be set. */ - if (EXT4_SB(sb)->s_es->s_reserved_gdt_blocks && + if (sbi->s_es->s_reserved_gdt_blocks && !ext4_has_feature_resize_inode(sb)) { ext4_error(sb, "resize_inode disabled but reserved GDT blocks non-zero"); return -EFSCORRUPTED; @@ -69,9 +67,9 @@ int ext4_resize_begin(struct super_block *sb) * bad time to do it anyways. */ if (EXT4_B2C(sbi, sbi->s_sbh->b_blocknr) != - le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block)) { + le32_to_cpu(sbi->s_es->s_first_data_block)) { ext4_warning(sb, "won't resize using backup superblock at %llu", - (unsigned long long)EXT4_SB(sb)->s_sbh->b_blocknr); + (unsigned long long)sbi->s_sbh->b_blocknr); return -EPERM; } @@ -79,7 +77,7 @@ int ext4_resize_begin(struct super_block *sb) * We are not allowed to do online-resizing on a filesystem mounted * with error, because it can destroy the filesystem easily. */ - if (EXT4_SB(sb)->s_mount_state & EXT4_ERROR_FS) { + if (sbi->s_mount_state & EXT4_ERROR_FS) { ext4_warning(sb, "There are errors in the filesystem, " "so online resizing is not allowed"); return -EPERM; @@ -91,7 +89,7 @@ int ext4_resize_begin(struct super_block *sb) } if (test_and_set_bit_lock(EXT4_FLAGS_RESIZING, - &EXT4_SB(sb)->s_ext4_flags)) + &sbi->s_ext4_flags)) ret = -EBUSY; return ret; @@ -106,18 +104,6 @@ int ext4_resize_end(struct super_block *sb, bool update_backups) return 0; } -static ext4_group_t ext4_meta_bg_first_group(struct super_block *sb, - ext4_group_t group) { - return (group >> EXT4_DESC_PER_BLOCK_BITS(sb)) << - EXT4_DESC_PER_BLOCK_BITS(sb); -} - -static ext4_fsblk_t ext4_meta_bg_first_block_no(struct super_block *sb, - ext4_group_t group) { - group = ext4_meta_bg_first_group(sb, group); - return ext4_group_first_block_no(sb, group); -} - static ext4_grpblk_t ext4_group_overhead_blocks(struct super_block *sb, ext4_group_t group) { ext4_grpblk_t overhead; @@ -154,8 +140,9 @@ static int verify_group_input(struct super_block *sb, overhead = ext4_group_overhead_blocks(sb, group); metaend = start + overhead; - input->free_clusters_count = free_blocks_count = - input->blocks_count - 2 - overhead - sbi->s_itb_per_group; + free_blocks_count = input->blocks_count - 2 - overhead - + sbi->s_itb_per_group; + input->free_clusters_count = EXT4_B2C(sbi, free_blocks_count); if (test_opt(sb, DEBUG)) printk(KERN_DEBUG "EXT4-fs: adding %s group %u: %u blocks " @@ -460,8 +447,7 @@ static int set_flexbg_block_bitmap(struct super_block *sb, handle_t *handle, ext4_debug("mark clusters [%llu-%llu] used\n", first_cluster, last_cluster); - for (count2 = count; count > 0; - count -= count2, first_cluster += count2) { + for (; count > 0; count -= count2, first_cluster += count2) { ext4_fsblk_t start; struct buffer_head *bh; ext4_group_t group; @@ -560,13 +546,8 @@ static int setup_new_flex_group_blocks(struct super_block *sb, if (meta_bg == 0 && !ext4_bg_has_super(sb, group)) goto handle_itb; - if (meta_bg == 1) { - ext4_group_t first_group; - first_group = ext4_meta_bg_first_group(sb, group); - if (first_group != group + 1 && - first_group != group + EXT4_DESC_PER_BLOCK(sb) - 1) - goto handle_itb; - } + if (meta_bg == 1) + goto handle_itb; block = start + ext4_bg_has_super(sb, group); /* Copy all of the GDT blocks into the backup in this group */ @@ -614,7 +595,7 @@ static int setup_new_flex_group_blocks(struct super_block *sb, } handle_itb: - /* Initialize group tables of the grop @group */ + /* Initialize group tables of the group @group */ if (!(bg_flags[i] & EXT4_BG_INODE_ZEROED)) goto handle_bb; @@ -704,16 +685,14 @@ handle_ib: block = start; } - if (count) { - err = set_flexbg_block_bitmap(sb, handle, - flex_gd, - EXT4_B2C(sbi, start), - EXT4_B2C(sbi, - start + count - - 1)); - if (err) - goto out; - } + err = set_flexbg_block_bitmap(sb, handle, + flex_gd, + EXT4_B2C(sbi, start), + EXT4_B2C(sbi, + start + count + - 1)); + if (err) + goto out; } out: @@ -952,7 +931,13 @@ errout: } /* - * add_new_gdb_meta_bg is the sister of add_new_gdb. + * If there is no available space in the existing block group descriptors for + * the new block group and there are no reserved block group descriptors, then + * the meta_bg feature will get enabled, and es->s_first_meta_bg will get set + * to the first block group that is managed using meta_bg and s_first_meta_bg + * must be a multiple of EXT4_DESC_PER_BLOCK(sb). + * This function will be called when first group of meta_bg is added to bring + * new group descriptors block of new added meta_bg. */ static int add_new_gdb_meta_bg(struct super_block *sb, handle_t *handle, ext4_group_t group) { @@ -962,8 +947,8 @@ static int add_new_gdb_meta_bg(struct super_block *sb, unsigned long gdb_num = group / EXT4_DESC_PER_BLOCK(sb); int err; - gdblock = ext4_meta_bg_first_block_no(sb, group) + - ext4_bg_has_super(sb, group); + gdblock = ext4_group_first_block_no(sb, group) + + ext4_bg_has_super(sb, group); gdb_bh = ext4_sb_bread(sb, gdblock, 0); if (IS_ERR(gdb_bh)) return PTR_ERR(gdb_bh); @@ -1087,9 +1072,6 @@ static int reserve_backup_gdb(handle_t *handle, struct inode *inode, for (i = 0; i < reserved_gdb; i++) { int err2; data = (__le32 *)primary[i]->b_data; - /* printk("reserving backup %lu[%u] = %lu\n", - primary[i]->b_blocknr, gdbackups, - blk + primary[i]->b_blocknr); */ data[gdbackups] = cpu_to_le32(blk + primary[i]->b_blocknr); err2 = ext4_handle_dirty_metadata(handle, NULL, primary[i]); if (!err) @@ -1191,8 +1173,10 @@ static void update_backups(struct super_block *sb, sector_t blk_off, char *data, ext4_group_first_block_no(sb, group)); BUFFER_TRACE(bh, "get_write_access"); if ((err = ext4_journal_get_write_access(handle, sb, bh, - EXT4_JTR_NONE))) + EXT4_JTR_NONE))) { + brelse(bh); break; + } lock_buffer(bh); memcpy(bh->b_data, data, size); if (rest) @@ -1601,7 +1585,8 @@ exit_journal: int gdb_num_end = ((group + flex_gd->count - 1) / EXT4_DESC_PER_BLOCK(sb)); int meta_bg = ext4_has_feature_meta_bg(sb); - sector_t old_gdb = 0; + sector_t padding_blocks = meta_bg ? 0 : sbi->s_sbh->b_blocknr - + ext4_group_first_block_no(sb, 0); update_backups(sb, ext4_group_first_block_no(sb, 0), (char *)es, sizeof(struct ext4_super_block), 0); @@ -1610,11 +1595,8 @@ exit_journal: gdb_bh = sbi_array_rcu_deref(sbi, s_group_desc, gdb_num); - if (old_gdb == gdb_bh->b_blocknr) - continue; - update_backups(sb, gdb_bh->b_blocknr, gdb_bh->b_data, - gdb_bh->b_size, meta_bg); - old_gdb = gdb_bh->b_blocknr; + update_backups(sb, gdb_bh->b_blocknr - padding_blocks, + gdb_bh->b_data, gdb_bh->b_size, meta_bg); } } exit: @@ -1980,9 +1962,7 @@ static int ext4_convert_meta_bg(struct super_block *sb, struct inode *inode) errout: ret = ext4_journal_stop(handle); - if (!err) - err = ret; - return ret; + return err ? err : ret; invalid_resize_inode: ext4_error(sb, "corrupted/inconsistent resize inode"); diff --git a/fs/ext4/super.c b/fs/ext4/super.c index c44db1915437..c5fcf377ab1f 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -244,18 +244,25 @@ static struct buffer_head *__ext4_sb_bread_gfp(struct super_block *sb, struct buffer_head *ext4_sb_bread(struct super_block *sb, sector_t block, blk_opf_t op_flags) { - return __ext4_sb_bread_gfp(sb, block, op_flags, __GFP_MOVABLE); + gfp_t gfp = mapping_gfp_constraint(sb->s_bdev->bd_inode->i_mapping, + ~__GFP_FS) | __GFP_MOVABLE; + + return __ext4_sb_bread_gfp(sb, block, op_flags, gfp); } struct buffer_head *ext4_sb_bread_unmovable(struct super_block *sb, sector_t block) { - return __ext4_sb_bread_gfp(sb, block, 0, 0); + gfp_t gfp = mapping_gfp_constraint(sb->s_bdev->bd_inode->i_mapping, + ~__GFP_FS); + + return __ext4_sb_bread_gfp(sb, block, 0, gfp); } void ext4_sb_breadahead_unmovable(struct super_block *sb, sector_t block) { - struct buffer_head *bh = sb_getblk_gfp(sb, block, 0); + struct buffer_head *bh = bdev_getblk(sb->s_bdev, block, + sb->s_blocksize, GFP_NOWAIT | __GFP_NOWARN); if (likely(bh)) { if (trylock_buffer(bh)) @@ -768,7 +775,8 @@ static void update_super_work(struct work_struct *work) */ if (!sb_rdonly(sbi->s_sb) && journal) { struct buffer_head *sbh = sbi->s_sbh; - bool call_notify_err; + bool call_notify_err = false; + handle = jbd2_journal_start(journal, 1); if (IS_ERR(handle)) goto write_directly; @@ -1351,14 +1359,14 @@ static void ext4_put_super(struct super_block *sb) sync_blockdev(sb->s_bdev); invalidate_bdev(sb->s_bdev); - if (sbi->s_journal_bdev) { + if (sbi->s_journal_bdev_handle) { /* * Invalidate the journal device's buffers. We don't want them * floating about in memory - the physical journal device may * hotswapped, and it breaks the `ro-after' testing code. */ - sync_blockdev(sbi->s_journal_bdev); - invalidate_bdev(sbi->s_journal_bdev); + sync_blockdev(sbi->s_journal_bdev_handle->bdev); + invalidate_bdev(sbi->s_journal_bdev_handle->bdev); } ext4_xattr_destroy_cache(sbi->s_ea_inode_cache); @@ -4234,7 +4242,7 @@ int ext4_calculate_overhead(struct super_block *sb) * Add the internal journal blocks whether the journal has been * loaded or not */ - if (sbi->s_journal && !sbi->s_journal_bdev) + if (sbi->s_journal && !sbi->s_journal_bdev_handle) overhead += EXT4_NUM_B2C(sbi, sbi->s_journal->j_total_len); else if (ext4_has_feature_journal(sb) && !sbi->s_journal && j_inum) { /* j_inum for internal journal is non-zero */ @@ -5671,9 +5679,9 @@ failed_mount: #endif fscrypt_free_dummy_policy(&sbi->s_dummy_enc_policy); brelse(sbi->s_sbh); - if (sbi->s_journal_bdev) { - invalidate_bdev(sbi->s_journal_bdev); - blkdev_put(sbi->s_journal_bdev, sb); + if (sbi->s_journal_bdev_handle) { + invalidate_bdev(sbi->s_journal_bdev_handle->bdev); + bdev_release(sbi->s_journal_bdev_handle); } out_fail: invalidate_bdev(sb->s_bdev); @@ -5843,12 +5851,13 @@ static journal_t *ext4_open_inode_journal(struct super_block *sb, return journal; } -static struct block_device *ext4_get_journal_blkdev(struct super_block *sb, +static struct bdev_handle *ext4_get_journal_blkdev(struct super_block *sb, dev_t j_dev, ext4_fsblk_t *j_start, ext4_fsblk_t *j_len) { struct buffer_head *bh; struct block_device *bdev; + struct bdev_handle *bdev_handle; int hblock, blocksize; ext4_fsblk_t sb_block; unsigned long offset; @@ -5857,16 +5866,17 @@ static struct block_device *ext4_get_journal_blkdev(struct super_block *sb, /* see get_tree_bdev why this is needed and safe */ up_write(&sb->s_umount); - bdev = blkdev_get_by_dev(j_dev, BLK_OPEN_READ | BLK_OPEN_WRITE, sb, - &fs_holder_ops); + bdev_handle = bdev_open_by_dev(j_dev, BLK_OPEN_READ | BLK_OPEN_WRITE, + sb, &fs_holder_ops); down_write(&sb->s_umount); - if (IS_ERR(bdev)) { + if (IS_ERR(bdev_handle)) { ext4_msg(sb, KERN_ERR, "failed to open journal device unknown-block(%u,%u) %ld", - MAJOR(j_dev), MINOR(j_dev), PTR_ERR(bdev)); - return ERR_CAST(bdev); + MAJOR(j_dev), MINOR(j_dev), PTR_ERR(bdev_handle)); + return bdev_handle; } + bdev = bdev_handle->bdev; blocksize = sb->s_blocksize; hblock = bdev_logical_block_size(bdev); if (blocksize < hblock) { @@ -5913,12 +5923,12 @@ static struct block_device *ext4_get_journal_blkdev(struct super_block *sb, *j_start = sb_block + 1; *j_len = ext4_blocks_count(es); brelse(bh); - return bdev; + return bdev_handle; out_bh: brelse(bh); out_bdev: - blkdev_put(bdev, sb); + bdev_release(bdev_handle); return ERR_PTR(errno); } @@ -5928,14 +5938,14 @@ static journal_t *ext4_open_dev_journal(struct super_block *sb, journal_t *journal; ext4_fsblk_t j_start; ext4_fsblk_t j_len; - struct block_device *journal_bdev; + struct bdev_handle *bdev_handle; int errno = 0; - journal_bdev = ext4_get_journal_blkdev(sb, j_dev, &j_start, &j_len); - if (IS_ERR(journal_bdev)) - return ERR_CAST(journal_bdev); + bdev_handle = ext4_get_journal_blkdev(sb, j_dev, &j_start, &j_len); + if (IS_ERR(bdev_handle)) + return ERR_CAST(bdev_handle); - journal = jbd2_journal_init_dev(journal_bdev, sb->s_bdev, j_start, + journal = jbd2_journal_init_dev(bdev_handle->bdev, sb->s_bdev, j_start, j_len, sb->s_blocksize); if (IS_ERR(journal)) { ext4_msg(sb, KERN_ERR, "failed to create device journal"); @@ -5950,14 +5960,14 @@ static journal_t *ext4_open_dev_journal(struct super_block *sb, goto out_journal; } journal->j_private = sb; - EXT4_SB(sb)->s_journal_bdev = journal_bdev; + EXT4_SB(sb)->s_journal_bdev_handle = bdev_handle; ext4_init_journal_params(sb, journal); return journal; out_journal: jbd2_journal_destroy(journal); out_bdev: - blkdev_put(journal_bdev, sb); + bdev_release(bdev_handle); return ERR_PTR(errno); } @@ -6443,6 +6453,7 @@ static int __ext4_remount(struct fs_context *fc, struct super_block *sb) struct ext4_mount_options old_opts; ext4_group_t g; int err = 0; + int alloc_ctx; #ifdef CONFIG_QUOTA int enable_quota = 0; int i, j; @@ -6483,7 +6494,16 @@ static int __ext4_remount(struct fs_context *fc, struct super_block *sb) } + /* + * Changing the DIOREAD_NOLOCK or DELALLOC mount options may cause + * two calls to ext4_should_dioread_nolock() to return inconsistent + * values, triggering WARN_ON in ext4_add_complete_io(). we grab + * here s_writepages_rwsem to avoid race between writepages ops and + * remount. + */ + alloc_ctx = ext4_writepages_down_write(sb); ext4_apply_options(fc, sb); + ext4_writepages_up_write(sb, alloc_ctx); if ((old_opts.s_mount_opt & EXT4_MOUNT_JOURNAL_CHECKSUM) ^ test_opt(sb, JOURNAL_CHECKSUM)) { @@ -6701,6 +6721,8 @@ restore_opts: if (sb_rdonly(sb) && !(old_sb_flags & SB_RDONLY) && sb_any_quota_suspended(sb)) dquot_resume(sb, -1); + + alloc_ctx = ext4_writepages_down_write(sb); sb->s_flags = old_sb_flags; sbi->s_mount_opt = old_opts.s_mount_opt; sbi->s_mount_opt2 = old_opts.s_mount_opt2; @@ -6709,6 +6731,8 @@ restore_opts: sbi->s_commit_interval = old_opts.s_commit_interval; sbi->s_min_batch_time = old_opts.s_min_batch_time; sbi->s_max_batch_time = old_opts.s_max_batch_time; + ext4_writepages_up_write(sb, alloc_ctx); + if (!test_opt(sb, BLOCK_VALIDITY) && sbi->s_system_blks) ext4_release_system_zone(sb); #ifdef CONFIG_QUOTA @@ -7128,7 +7152,7 @@ static int ext4_quota_off(struct super_block *sb, int type) } EXT4_I(inode)->i_flags &= ~(EXT4_NOATIME_FL | EXT4_IMMUTABLE_FL); inode_set_flags(inode, 0, S_NOATIME | S_IMMUTABLE); - inode->i_mtime = inode_set_ctime_current(inode); + inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); err = ext4_mark_inode_dirty(handle, inode); ext4_journal_stop(handle); out_unlock: @@ -7301,12 +7325,12 @@ static inline int ext3_feature_set_ok(struct super_block *sb) static void ext4_kill_sb(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); - struct block_device *journal_bdev = sbi ? sbi->s_journal_bdev : NULL; + struct bdev_handle *handle = sbi ? sbi->s_journal_bdev_handle : NULL; kill_block_super(sb); - if (journal_bdev) - blkdev_put(journal_bdev, sb); + if (handle) + bdev_release(handle); } static struct file_system_type ext4_fs_type = { diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 92ba28cebac6..82dc5e673d5c 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -98,7 +98,7 @@ static const struct xattr_handler * const ext4_xattr_handler_map[] = { [EXT4_XATTR_INDEX_HURD] = &ext4_xattr_hurd_handler, }; -const struct xattr_handler *ext4_xattr_handlers[] = { +const struct xattr_handler * const ext4_xattr_handlers[] = { &ext4_xattr_user_handler, &ext4_xattr_trusted_handler, #ifdef CONFIG_EXT4_FS_SECURITY @@ -356,7 +356,7 @@ ext4_xattr_inode_hash(struct ext4_sb_info *sbi, const void *buffer, size_t size) static u64 ext4_xattr_inode_get_ref(struct inode *ea_inode) { - return ((u64) inode_get_ctime(ea_inode).tv_sec << 32) | + return ((u64) inode_get_ctime_sec(ea_inode) << 32) | (u32) inode_peek_iversion_raw(ea_inode); } @@ -368,12 +368,12 @@ static void ext4_xattr_inode_set_ref(struct inode *ea_inode, u64 ref_count) static u32 ext4_xattr_inode_get_hash(struct inode *ea_inode) { - return (u32)ea_inode->i_atime.tv_sec; + return (u32) inode_get_atime_sec(ea_inode); } static void ext4_xattr_inode_set_hash(struct inode *ea_inode, u32 hash) { - ea_inode->i_atime.tv_sec = hash; + inode_set_atime(ea_inode, hash, 0); } /* @@ -418,7 +418,7 @@ free_bhs: return ret; } -#define EXT4_XATTR_INODE_GET_PARENT(inode) ((__u32)(inode)->i_mtime.tv_sec) +#define EXT4_XATTR_INODE_GET_PARENT(inode) ((__u32)(inode_get_mtime_sec(inode))) static int ext4_xattr_inode_iget(struct inode *parent, unsigned long ea_ino, u32 ea_inode_hash, struct inode **ea_inode) diff --git a/fs/ext4/xattr.h b/fs/ext4/xattr.h index 824faf0b15a8..bd97c4aa8177 100644 --- a/fs/ext4/xattr.h +++ b/fs/ext4/xattr.h @@ -193,7 +193,7 @@ extern int ext4_expand_extra_isize_ea(struct inode *inode, int new_extra_isize, struct ext4_inode *raw_inode, handle_t *handle); extern void ext4_evict_ea_inode(struct inode *inode); -extern const struct xattr_handler *ext4_xattr_handlers[]; +extern const struct xattr_handler * const ext4_xattr_handlers[]; extern int ext4_xattr_ibody_find(struct inode *inode, struct ext4_xattr_info *i, struct ext4_xattr_ibody_find *is); |