diff options
Diffstat (limited to 'fs/ext4/mballoc.c')
-rw-r--r-- | fs/ext4/mballoc.c | 129 |
1 files changed, 68 insertions, 61 deletions
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 47c28e3582fd..e44c28ceb9cd 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -16,6 +16,7 @@ #include <linux/slab.h> #include <linux/nospec.h> #include <linux/backing-dev.h> +#include <linux/freezer.h> #include <trace/events/ext4.h> /* @@ -1011,8 +1012,9 @@ static inline int should_optimize_scan(struct ext4_allocation_context *ac) * Return next linear group for allocation. If linear traversal should not be * performed, this function just returns the same group */ -static int -next_linear_group(struct ext4_allocation_context *ac, int group, int ngroups) +static ext4_group_t +next_linear_group(struct ext4_allocation_context *ac, ext4_group_t group, + ext4_group_t ngroups) { if (!should_optimize_scan(ac)) goto inc_and_return; @@ -2445,7 +2447,7 @@ static bool ext4_mb_good_group(struct ext4_allocation_context *ac, BUG_ON(cr < 0 || cr >= 4); - if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(grp) || !grp)) + if (unlikely(!grp || EXT4_MB_GRP_BBITMAP_CORRUPT(grp))) return false; free = grp->bb_free; @@ -4047,8 +4049,7 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac, struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); struct ext4_super_block *es = sbi->s_es; int bsbits, max; - ext4_lblk_t end; - loff_t size, start_off; + loff_t size, start_off, end; loff_t orig_size __maybe_unused; ext4_lblk_t start; struct ext4_inode_info *ei = EXT4_I(ac->ac_inode); @@ -4077,7 +4078,7 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac, /* first, let's learn actual file size * given current request is allocated */ - size = ac->ac_o_ex.fe_logical + EXT4_C2B(sbi, ac->ac_o_ex.fe_len); + size = extent_logical_end(sbi, &ac->ac_o_ex); size = size << bsbits; if (size < i_size_read(ac->ac_inode)) size = i_size_read(ac->ac_inode); @@ -4136,6 +4137,10 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac, start = max(start, rounddown(ac->ac_o_ex.fe_logical, (ext4_lblk_t)EXT4_BLOCKS_PER_GROUP(ac->ac_sb))); + /* avoid unnecessary preallocation that may trigger assertions */ + if (start + size > EXT_MAX_BLOCKS) + size = EXT_MAX_BLOCKS - start; + /* don't cover already allocated blocks in selected range */ if (ar->pleft && start <= ar->lleft) { size -= ar->lleft + 1 - start; @@ -4156,7 +4161,7 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac, /* check we don't cross already preallocated blocks */ rcu_read_lock(); list_for_each_entry_rcu(pa, &ei->i_prealloc_list, pa_inode_list) { - ext4_lblk_t pa_end; + loff_t pa_end; if (pa->pa_deleted) continue; @@ -4166,8 +4171,7 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac, continue; } - pa_end = pa->pa_lstart + EXT4_C2B(EXT4_SB(ac->ac_sb), - pa->pa_len); + pa_end = pa_logical_end(EXT4_SB(ac->ac_sb), pa); /* PA must not overlap original request */ BUG_ON(!(ac->ac_o_ex.fe_logical >= pa_end || @@ -4196,12 +4200,11 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac, /* XXX: extra loop to check we really don't overlap preallocations */ rcu_read_lock(); list_for_each_entry_rcu(pa, &ei->i_prealloc_list, pa_inode_list) { - ext4_lblk_t pa_end; + loff_t pa_end; spin_lock(&pa->pa_lock); if (pa->pa_deleted == 0) { - pa_end = pa->pa_lstart + EXT4_C2B(EXT4_SB(ac->ac_sb), - pa->pa_len); + pa_end = pa_logical_end(EXT4_SB(ac->ac_sb), pa); BUG_ON(!(start >= pa_end || end <= pa->pa_lstart)); } spin_unlock(&pa->pa_lock); @@ -4417,8 +4420,7 @@ ext4_mb_use_preallocated(struct ext4_allocation_context *ac) /* all fields in this condition don't change, * so we can skip locking for them */ if (ac->ac_o_ex.fe_logical < pa->pa_lstart || - ac->ac_o_ex.fe_logical >= (pa->pa_lstart + - EXT4_C2B(sbi, pa->pa_len))) + ac->ac_o_ex.fe_logical >= pa_logical_end(sbi, pa)) continue; /* non-extent files can't have physical blocks past 2^32 */ @@ -4663,8 +4665,11 @@ ext4_mb_new_inode_pa(struct ext4_allocation_context *ac) pa = ac->ac_pa; if (ac->ac_b_ex.fe_len < ac->ac_g_ex.fe_len) { - int new_bex_start; - int new_bex_end; + struct ext4_free_extent ex = { + .fe_logical = ac->ac_g_ex.fe_logical, + .fe_len = ac->ac_g_ex.fe_len, + }; + loff_t orig_goal_end = extent_logical_end(sbi, &ex); /* we can't allocate as much as normalizer wants. * so, found space must get proper lstart @@ -4683,29 +4688,23 @@ ext4_mb_new_inode_pa(struct ext4_allocation_context *ac) * still cover original start * 3. Else, keep the best ex at start of original request. */ - new_bex_end = ac->ac_g_ex.fe_logical + - EXT4_C2B(sbi, ac->ac_g_ex.fe_len); - new_bex_start = new_bex_end - EXT4_C2B(sbi, ac->ac_b_ex.fe_len); - if (ac->ac_o_ex.fe_logical >= new_bex_start) - goto adjust_bex; + ex.fe_len = ac->ac_b_ex.fe_len; - new_bex_start = ac->ac_g_ex.fe_logical; - new_bex_end = - new_bex_start + EXT4_C2B(sbi, ac->ac_b_ex.fe_len); - if (ac->ac_o_ex.fe_logical < new_bex_end) + ex.fe_logical = orig_goal_end - EXT4_C2B(sbi, ex.fe_len); + if (ac->ac_o_ex.fe_logical >= ex.fe_logical) goto adjust_bex; - new_bex_start = ac->ac_o_ex.fe_logical; - new_bex_end = - new_bex_start + EXT4_C2B(sbi, ac->ac_b_ex.fe_len); + ex.fe_logical = ac->ac_g_ex.fe_logical; + if (ac->ac_o_ex.fe_logical < extent_logical_end(sbi, &ex)) + goto adjust_bex; + ex.fe_logical = ac->ac_o_ex.fe_logical; adjust_bex: - ac->ac_b_ex.fe_logical = new_bex_start; + ac->ac_b_ex.fe_logical = ex.fe_logical; BUG_ON(ac->ac_o_ex.fe_logical < ac->ac_b_ex.fe_logical); BUG_ON(ac->ac_o_ex.fe_len > ac->ac_b_ex.fe_len); - BUG_ON(new_bex_end > (ac->ac_g_ex.fe_logical + - EXT4_C2B(sbi, ac->ac_g_ex.fe_len))); + BUG_ON(extent_logical_end(sbi, &ex) > orig_goal_end); } /* preallocation can change ac_b_ex, thus we store actually @@ -5239,7 +5238,7 @@ static void ext4_mb_group_or_file(struct ext4_allocation_context *ac) group_pa_eligible = sbi->s_mb_group_prealloc > 0; inode_pa_eligible = true; - size = ac->ac_o_ex.fe_logical + EXT4_C2B(sbi, ac->ac_o_ex.fe_len); + size = extent_logical_end(sbi, &ac->ac_o_ex); isize = (i_size_read(ac->ac_inode) + ac->ac_sb->s_blocksize - 1) >> bsbits; @@ -6432,6 +6431,21 @@ __acquires(bitlock) return ret; } +static ext4_grpblk_t ext4_last_grp_cluster(struct super_block *sb, + ext4_group_t grp) +{ + if (grp < ext4_get_groups_count(sb)) + return EXT4_CLUSTERS_PER_GROUP(sb) - 1; + return (ext4_blocks_count(EXT4_SB(sb)->s_es) - + ext4_group_first_block_no(sb, grp) - 1) >> + EXT4_CLUSTER_BITS(sb); +} + +static bool ext4_trim_interrupted(void) +{ + return fatal_signal_pending(current) || freezing(current); +} + static int ext4_try_to_trim_range(struct super_block *sb, struct ext4_buddy *e4b, ext4_grpblk_t start, ext4_grpblk_t max, ext4_grpblk_t minblocks) @@ -6439,12 +6453,13 @@ __acquires(ext4_group_lock_ptr(sb, e4b->bd_group)) __releases(ext4_group_lock_ptr(sb, e4b->bd_group)) { ext4_grpblk_t next, count, free_count; + bool set_trimmed = false; void *bitmap; - int ret = 0; bitmap = e4b->bd_bitmap; - start = (e4b->bd_info->bb_first_free > start) ? - e4b->bd_info->bb_first_free : start; + if (start == 0 && max >= ext4_last_grp_cluster(sb, e4b->bd_group)) + set_trimmed = true; + start = max(e4b->bd_info->bb_first_free, start); count = 0; free_count = 0; @@ -6455,19 +6470,17 @@ __releases(ext4_group_lock_ptr(sb, e4b->bd_group)) next = mb_find_next_bit(bitmap, max + 1, start); if ((next - start) >= minblocks) { - ret = ext4_trim_extent(sb, start, next - start, e4b); + int ret = ext4_trim_extent(sb, start, next - start, e4b); + if (ret && ret != -EOPNOTSUPP) - break; - ret = 0; + return count; count += next - start; } free_count += next - start; start = next + 1; - if (fatal_signal_pending(current)) { - count = -ERESTARTSYS; - break; - } + if (ext4_trim_interrupted()) + return count; if (need_resched()) { ext4_unlock_group(sb, e4b->bd_group); @@ -6479,6 +6492,9 @@ __releases(ext4_group_lock_ptr(sb, e4b->bd_group)) break; } + if (set_trimmed) + EXT4_MB_GRP_SET_TRIMMED(e4b->bd_info); + return count; } @@ -6489,7 +6505,6 @@ __releases(ext4_group_lock_ptr(sb, e4b->bd_group)) * @start: first group block to examine * @max: last group block to examine * @minblocks: minimum extent block count - * @set_trimmed: set the trimmed flag if at least one block is trimmed * * ext4_trim_all_free walks through group's block bitmap searching for free * extents. When the free extent is found, mark it as used in group buddy @@ -6499,7 +6514,7 @@ __releases(ext4_group_lock_ptr(sb, e4b->bd_group)) static ext4_grpblk_t ext4_trim_all_free(struct super_block *sb, ext4_group_t group, ext4_grpblk_t start, ext4_grpblk_t max, - ext4_grpblk_t minblocks, bool set_trimmed) + ext4_grpblk_t minblocks) { struct ext4_buddy e4b; int ret; @@ -6516,13 +6531,10 @@ ext4_trim_all_free(struct super_block *sb, ext4_group_t group, ext4_lock_group(sb, group); if (!EXT4_MB_GRP_WAS_TRIMMED(e4b.bd_info) || - minblocks < atomic_read(&EXT4_SB(sb)->s_last_trim_minblks)) { + minblocks < EXT4_SB(sb)->s_last_trim_minblks) ret = ext4_try_to_trim_range(sb, &e4b, start, max, minblocks); - if (ret >= 0 && set_trimmed) - EXT4_MB_GRP_SET_TRIMMED(e4b.bd_info); - } else { + else ret = 0; - } ext4_unlock_group(sb, group); ext4_mb_unload_buddy(&e4b); @@ -6555,7 +6567,6 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range) ext4_fsblk_t first_data_blk = le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block); ext4_fsblk_t max_blks = ext4_blocks_count(EXT4_SB(sb)->s_es); - bool whole_group, eof = false; int ret = 0; start = range->start >> sb->s_blocksize_bits; @@ -6574,10 +6585,8 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range) if (minlen > EXT4_CLUSTERS_PER_GROUP(sb)) goto out; } - if (end >= max_blks - 1) { + if (end >= max_blks - 1) end = max_blks - 1; - eof = true; - } if (end <= first_data_blk) goto out; if (start < first_data_blk) @@ -6591,9 +6600,10 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range) /* end now represents the last cluster to discard in this group */ end = EXT4_CLUSTERS_PER_GROUP(sb) - 1; - whole_group = true; for (group = first_group; group <= last_group; group++) { + if (ext4_trim_interrupted()) + break; grp = ext4_get_group_info(sb, group); if (!grp) continue; @@ -6610,13 +6620,11 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range) * change it for the last group, note that last_cluster is * already computed earlier by ext4_get_group_no_and_offset() */ - if (group == last_group) { + if (group == last_group) end = last_cluster; - whole_group = eof ? true : end == EXT4_CLUSTERS_PER_GROUP(sb) - 1; - } if (grp->bb_free >= minlen) { cnt = ext4_trim_all_free(sb, group, first_cluster, - end, minlen, whole_group); + end, minlen); if (cnt < 0) { ret = cnt; break; @@ -6632,7 +6640,7 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range) } if (!ret) - atomic_set(&EXT4_SB(sb)->s_last_trim_minblks, minlen); + EXT4_SB(sb)->s_last_trim_minblks = minlen; out: range->len = EXT4_C2B(EXT4_SB(sb), trimmed) << sb->s_blocksize_bits; @@ -6661,8 +6669,7 @@ ext4_mballoc_query_range( ext4_lock_group(sb, group); - start = (e4b.bd_info->bb_first_free > start) ? - e4b.bd_info->bb_first_free : start; + start = max(e4b.bd_info->bb_first_free, start); if (end >= EXT4_CLUSTERS_PER_GROUP(sb)) end = EXT4_CLUSTERS_PER_GROUP(sb) - 1; |