diff options
Diffstat (limited to 'fs/ext4/mballoc.c')
| -rw-r--r-- | fs/ext4/mballoc.c | 780 |
1 files changed, 428 insertions, 352 deletions
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index cf2fd9fc7d98..9dad93059945 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -140,13 +140,15 @@ * number of buddy bitmap orders possible) number of lists. Group-infos are * placed in appropriate lists. * - * 2) Average fragment size rb tree (sbi->s_mb_avg_fragment_size_root) + * 2) Average fragment size lists (sbi->s_mb_avg_fragment_size) * - * Locking: sbi->s_mb_rb_lock (rwlock) + * Locking: sbi->s_mb_avg_fragment_size_locks(array of rw locks) * - * This is a red black tree consisting of group infos and the tree is sorted - * by average fragment sizes (which is calculated as ext4_group_info->bb_free - * / ext4_group_info->bb_fragments). + * This is an array of lists where in the i-th list there are groups with + * average fragment size >= 2^i and < 2^(i+1). The average fragment size + * is computed as ext4_group_info->bb_free / ext4_group_info->bb_fragments. + * Note that we don't bother with a special list for completely empty groups + * so we only have MB_NUM_ORDERS(sb) lists. * * When "mb_optimize_scan" mount option is set, mballoc consults the above data * structures to decide the order in which groups are to be traversed for @@ -160,7 +162,8 @@ * * At CR = 1, we only consider groups where average fragment size > request * size. So, we lookup a group which has average fragment size just above or - * equal to request size using our rb tree (data structure 2) in O(log N) time. + * equal to request size using our average fragment size group lists (data + * structure 2) in O(1) time. * * If "mb_optimize_scan" mount option is not set, mballoc traverses groups in * linear order which requires O(N) search time for each CR 0 and CR 1 phase. @@ -695,13 +698,10 @@ static int __mb_check_buddy(struct ext4_buddy *e4b, char *file, for (i = 0; i < max; i++) { if (mb_test_bit(i, buddy)) { - /* only single bit in buddy2 may be 1 */ + /* only single bit in buddy2 may be 0 */ if (!mb_test_bit(i << 1, buddy2)) { MB_CHECK_ASSERT( mb_test_bit((i<<1)+1, buddy2)); - } else if (!mb_test_bit((i << 1) + 1, buddy2)) { - MB_CHECK_ASSERT( - mb_test_bit(i << 1, buddy2)); } continue; } @@ -805,65 +805,51 @@ static void ext4_mb_mark_free_simple(struct super_block *sb, } } -static void ext4_mb_rb_insert(struct rb_root *root, struct rb_node *new, - int (*cmp)(struct rb_node *, struct rb_node *)) +static int mb_avg_fragment_size_order(struct super_block *sb, ext4_grpblk_t len) { - struct rb_node **iter = &root->rb_node, *parent = NULL; - - while (*iter) { - parent = *iter; - if (cmp(new, *iter) > 0) - iter = &((*iter)->rb_left); - else - iter = &((*iter)->rb_right); - } - - rb_link_node(new, parent, iter); - rb_insert_color(new, root); -} + int order; -static int -ext4_mb_avg_fragment_size_cmp(struct rb_node *rb1, struct rb_node *rb2) -{ - struct ext4_group_info *grp1 = rb_entry(rb1, - struct ext4_group_info, - bb_avg_fragment_size_rb); - struct ext4_group_info *grp2 = rb_entry(rb2, - struct ext4_group_info, - bb_avg_fragment_size_rb); - int num_frags_1, num_frags_2; - - num_frags_1 = grp1->bb_fragments ? - grp1->bb_free / grp1->bb_fragments : 0; - num_frags_2 = grp2->bb_fragments ? - grp2->bb_free / grp2->bb_fragments : 0; - - return (num_frags_2 - num_frags_1); + /* + * We don't bother with a special lists groups with only 1 block free + * extents and for completely empty groups. + */ + order = fls(len) - 2; + if (order < 0) + return 0; + if (order == MB_NUM_ORDERS(sb)) + order--; + return order; } -/* - * Reinsert grpinfo into the avg_fragment_size tree with new average - * fragment size. - */ +/* Move group to appropriate avg_fragment_size list */ static void mb_update_avg_fragment_size(struct super_block *sb, struct ext4_group_info *grp) { struct ext4_sb_info *sbi = EXT4_SB(sb); + int new_order; if (!test_opt2(sb, MB_OPTIMIZE_SCAN) || grp->bb_free == 0) return; - write_lock(&sbi->s_mb_rb_lock); - if (!RB_EMPTY_NODE(&grp->bb_avg_fragment_size_rb)) { - rb_erase(&grp->bb_avg_fragment_size_rb, - &sbi->s_mb_avg_fragment_size_root); - RB_CLEAR_NODE(&grp->bb_avg_fragment_size_rb); - } + new_order = mb_avg_fragment_size_order(sb, + grp->bb_free / grp->bb_fragments); + if (new_order == grp->bb_avg_fragment_size_order) + return; - ext4_mb_rb_insert(&sbi->s_mb_avg_fragment_size_root, - &grp->bb_avg_fragment_size_rb, - ext4_mb_avg_fragment_size_cmp); - write_unlock(&sbi->s_mb_rb_lock); + if (grp->bb_avg_fragment_size_order != -1) { + write_lock(&sbi->s_mb_avg_fragment_size_locks[ + grp->bb_avg_fragment_size_order]); + list_del(&grp->bb_avg_fragment_size_node); + write_unlock(&sbi->s_mb_avg_fragment_size_locks[ + grp->bb_avg_fragment_size_order]); + } + grp->bb_avg_fragment_size_order = new_order; + write_lock(&sbi->s_mb_avg_fragment_size_locks[ + grp->bb_avg_fragment_size_order]); + list_add_tail(&grp->bb_avg_fragment_size_node, + &sbi->s_mb_avg_fragment_size[grp->bb_avg_fragment_size_order]); + write_unlock(&sbi->s_mb_avg_fragment_size_locks[ + grp->bb_avg_fragment_size_order]); } /* @@ -912,86 +898,55 @@ static void ext4_mb_choose_next_group_cr0(struct ext4_allocation_context *ac, *new_cr = 1; } else { *group = grp->bb_group; - ac->ac_last_optimal_group = *group; ac->ac_flags |= EXT4_MB_CR0_OPTIMIZED; } } /* - * Choose next group by traversing average fragment size tree. Updates *new_cr - * if cr lvel needs an update. Sets EXT4_MB_SEARCH_NEXT_LINEAR to indicate that - * the linear search should continue for one iteration since there's lock - * contention on the rb tree lock. + * Choose next group by traversing average fragment size list of suitable + * order. Updates *new_cr if cr level needs an update. */ static void ext4_mb_choose_next_group_cr1(struct ext4_allocation_context *ac, int *new_cr, ext4_group_t *group, ext4_group_t ngroups) { struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); - int avg_fragment_size, best_so_far; - struct rb_node *node, *found; - struct ext4_group_info *grp; - - /* - * If there is contention on the lock, instead of waiting for the lock - * to become available, just continue searching lineraly. We'll resume - * our rb tree search later starting at ac->ac_last_optimal_group. - */ - if (!read_trylock(&sbi->s_mb_rb_lock)) { - ac->ac_flags |= EXT4_MB_SEARCH_NEXT_LINEAR; - return; - } + struct ext4_group_info *grp = NULL, *iter; + int i; if (unlikely(ac->ac_flags & EXT4_MB_CR1_OPTIMIZED)) { if (sbi->s_mb_stats) atomic_inc(&sbi->s_bal_cr1_bad_suggestions); - /* We have found something at CR 1 in the past */ - grp = ext4_get_group_info(ac->ac_sb, ac->ac_last_optimal_group); - for (found = rb_next(&grp->bb_avg_fragment_size_rb); found != NULL; - found = rb_next(found)) { - grp = rb_entry(found, struct ext4_group_info, - bb_avg_fragment_size_rb); + } + + for (i = mb_avg_fragment_size_order(ac->ac_sb, ac->ac_g_ex.fe_len); + i < MB_NUM_ORDERS(ac->ac_sb); i++) { + if (list_empty(&sbi->s_mb_avg_fragment_size[i])) + continue; + read_lock(&sbi->s_mb_avg_fragment_size_locks[i]); + if (list_empty(&sbi->s_mb_avg_fragment_size[i])) { + read_unlock(&sbi->s_mb_avg_fragment_size_locks[i]); + continue; + } + list_for_each_entry(iter, &sbi->s_mb_avg_fragment_size[i], + bb_avg_fragment_size_node) { if (sbi->s_mb_stats) atomic64_inc(&sbi->s_bal_cX_groups_considered[1]); - if (likely(ext4_mb_good_group(ac, grp->bb_group, 1))) + if (likely(ext4_mb_good_group(ac, iter->bb_group, 1))) { + grp = iter; break; - } - goto done; - } - - node = sbi->s_mb_avg_fragment_size_root.rb_node; - best_so_far = 0; - found = NULL; - - while (node) { - grp = rb_entry(node, struct ext4_group_info, - bb_avg_fragment_size_rb); - avg_fragment_size = 0; - if (ext4_mb_good_group(ac, grp->bb_group, 1)) { - avg_fragment_size = grp->bb_fragments ? - grp->bb_free / grp->bb_fragments : 0; - if (!best_so_far || avg_fragment_size < best_so_far) { - best_so_far = avg_fragment_size; - found = node; } } - if (avg_fragment_size > ac->ac_g_ex.fe_len) - node = node->rb_right; - else - node = node->rb_left; + read_unlock(&sbi->s_mb_avg_fragment_size_locks[i]); + if (grp) + break; } -done: - if (found) { - grp = rb_entry(found, struct ext4_group_info, - bb_avg_fragment_size_rb); + if (grp) { *group = grp->bb_group; ac->ac_flags |= EXT4_MB_CR1_OPTIMIZED; } else { *new_cr = 2; } - - read_unlock(&sbi->s_mb_rb_lock); - ac->ac_last_optimal_group = *group; } static inline int should_optimize_scan(struct ext4_allocation_context *ac) @@ -1000,7 +955,7 @@ static inline int should_optimize_scan(struct ext4_allocation_context *ac) return 0; if (ac->ac_criteria >= 2) return 0; - if (ext4_test_inode_flag(ac->ac_inode, EXT4_INODE_EXTENTS)) + if (!ext4_test_inode_flag(ac->ac_inode, EXT4_INODE_EXTENTS)) return 0; return 1; } @@ -1020,11 +975,6 @@ next_linear_group(struct ext4_allocation_context *ac, int group, int ngroups) goto inc_and_return; } - if (ac->ac_flags & EXT4_MB_SEARCH_NEXT_LINEAR) { - ac->ac_flags &= ~EXT4_MB_SEARCH_NEXT_LINEAR; - goto inc_and_return; - } - return group; inc_and_return: /* @@ -1052,8 +1002,10 @@ static void ext4_mb_choose_next_group(struct ext4_allocation_context *ac, { *new_cr = ac->ac_criteria; - if (!should_optimize_scan(ac) || ac->ac_groups_linear_remaining) + if (!should_optimize_scan(ac) || ac->ac_groups_linear_remaining) { + *group = next_linear_group(ac, *group, ngroups); return; + } if (*new_cr == 0) { ext4_mb_choose_next_group_cr0(ac, new_cr, group, ngroups); @@ -1078,23 +1030,25 @@ mb_set_largest_free_order(struct super_block *sb, struct ext4_group_info *grp) struct ext4_sb_info *sbi = EXT4_SB(sb); int i; - if (test_opt2(sb, MB_OPTIMIZE_SCAN) && grp->bb_largest_free_order >= 0) { + for (i = MB_NUM_ORDERS(sb) - 1; i >= 0; i--) + if (grp->bb_counters[i] > 0) + break; + /* No need to move between order lists? */ + if (!test_opt2(sb, MB_OPTIMIZE_SCAN) || + i == grp->bb_largest_free_order) { + grp->bb_largest_free_order = i; + return; + } + + if (grp->bb_largest_free_order >= 0) { write_lock(&sbi->s_mb_largest_free_orders_locks[ grp->bb_largest_free_order]); list_del_init(&grp->bb_largest_free_order_node); write_unlock(&sbi->s_mb_largest_free_orders_locks[ grp->bb_largest_free_order]); } - grp->bb_largest_free_order = -1; /* uninit */ - - for (i = MB_NUM_ORDERS(sb) - 1; i >= 0; i--) { - if (grp->bb_counters[i] > 0) { - grp->bb_largest_free_order = i; - break; - } - } - if (test_opt2(sb, MB_OPTIMIZE_SCAN) && - grp->bb_largest_free_order >= 0 && grp->bb_free) { + grp->bb_largest_free_order = i; + if (grp->bb_largest_free_order >= 0 && grp->bb_free) { write_lock(&sbi->s_mb_largest_free_orders_locks[ grp->bb_largest_free_order]); list_add_tail(&grp->bb_largest_free_order_node, @@ -1151,13 +1105,13 @@ void ext4_mb_generate_buddy(struct super_block *sb, EXT4_GROUP_INFO_BBITMAP_CORRUPT); } mb_set_largest_free_order(sb, grp); + mb_update_avg_fragment_size(sb, grp); clear_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &(grp->bb_state)); period = get_cycles() - period; atomic_inc(&sbi->s_mb_buddies_generated); atomic64_add(period, &sbi->s_mb_generation_time); - mb_update_avg_fragment_size(sb, grp); } /* The buddy information is attached the buddy cache inode @@ -1689,7 +1643,7 @@ static int mb_test_and_clear_bits(void *bm, int cur, int len) return zero_bit; } -void ext4_set_bits(void *bm, int cur, int len) +void mb_set_bits(void *bm, int cur, int len) { __u32 *addr; @@ -1936,6 +1890,7 @@ static int mb_mark_used(struct ext4_buddy *e4b, struct ext4_free_extent *ex) unsigned ret = 0; int len0 = len; void *buddy; + bool split = false; BUG_ON(start + len > (e4b->bd_sb->s_blocksize << 3)); BUG_ON(e4b->bd_group != ex->fe_group); @@ -1960,12 +1915,16 @@ static int mb_mark_used(struct ext4_buddy *e4b, struct ext4_free_extent *ex) /* let's maintain buddy itself */ while (len) { - ord = mb_find_order_for_block(e4b, start); + if (!split) + ord = mb_find_order_for_block(e4b, start); if (((start >> ord) << ord) == start && len >= (1 << ord)) { /* the whole chunk may be allocated at once! */ mlen = 1 << ord; - buddy = mb_find_buddy(e4b, ord, &max); + if (!split) + buddy = mb_find_buddy(e4b, ord, &max); + else + split = false; BUG_ON((start >> ord) >= max); mb_set_bit(start >> ord, buddy); e4b->bd_info->bb_counters[ord]--; @@ -1992,11 +1951,12 @@ static int mb_mark_used(struct ext4_buddy *e4b, struct ext4_free_extent *ex) mb_clear_bit(cur + 1, buddy); e4b->bd_info->bb_counters[ord]++; e4b->bd_info->bb_counters[ord]++; + split = true; } mb_set_largest_free_order(e4b->bd_sb, e4b->bd_info); mb_update_avg_fragment_size(e4b->bd_sb, e4b->bd_info); - ext4_set_bits(e4b->bd_bitmap, ex->fe_start, len0); + mb_set_bits(e4b->bd_bitmap, ex->fe_start, len0); mb_check_buddy(e4b); return ret; @@ -2633,7 +2593,7 @@ static noinline_for_stack int ext4_mb_regular_allocator(struct ext4_allocation_context *ac) { ext4_group_t prefetch_grp = 0, ngroups, group, i; - int cr = -1; + int cr = -1, new_cr; int err = 0, first_err = 0; unsigned int nr = 0, prefetch_ios = 0; struct ext4_sb_info *sbi; @@ -2704,17 +2664,14 @@ repeat: * from the goal value specified */ group = ac->ac_g_ex.fe_group; - ac->ac_last_optimal_group = group; ac->ac_groups_linear_remaining = sbi->s_mb_max_linear_groups; prefetch_grp = group; - for (i = 0; i < ngroups; group = next_linear_group(ac, group, ngroups), - i++) { - int ret = 0, new_cr; + for (i = 0, new_cr = cr; i < ngroups; i++, + ext4_mb_choose_next_group(ac, &new_cr, &group, ngroups)) { + int ret = 0; cond_resched(); - - ext4_mb_choose_next_group(ac, &new_cr, &group, ngroups); if (new_cr != cr) { cr = new_cr; goto repeat; @@ -2834,7 +2791,7 @@ out: static void *ext4_mb_seq_groups_start(struct seq_file *seq, loff_t *pos) { - struct super_block *sb = PDE_DATA(file_inode(seq->file)); + struct super_block *sb = pde_data(file_inode(seq->file)); ext4_group_t group; if (*pos < 0 || *pos >= ext4_get_groups_count(sb)) @@ -2845,7 +2802,7 @@ static void *ext4_mb_seq_groups_start(struct seq_file *seq, loff_t *pos) static void *ext4_mb_seq_groups_next(struct seq_file *seq, void *v, loff_t *pos) { - struct super_block *sb = PDE_DATA(file_inode(seq->file)); + struct super_block *sb = pde_data(file_inode(seq->file)); ext4_group_t group; ++*pos; @@ -2857,7 +2814,7 @@ static void *ext4_mb_seq_groups_next(struct seq_file *seq, void *v, loff_t *pos) static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v) { - struct super_block *sb = PDE_DATA(file_inode(seq->file)); + struct super_block *sb = pde_data(file_inode(seq->file)); ext4_group_t group = (ext4_group_t) ((unsigned long) v); int i; int err, buddy_loaded = 0; @@ -2919,7 +2876,7 @@ const struct seq_operations ext4_mb_seq_groups_ops = { int ext4_seq_mb_stats_show(struct seq_file *seq, void *offset) { - struct super_block *sb = (struct super_block *)seq->private; + struct super_block *sb = seq->private; struct ext4_sb_info *sbi = EXT4_SB(sb); seq_puts(seq, "mballoc:\n"); @@ -2985,12 +2942,10 @@ int ext4_seq_mb_stats_show(struct seq_file *seq, void *offset) static void *ext4_mb_seq_structs_summary_start(struct seq_file *seq, loff_t *pos) __acquires(&EXT4_SB(sb)->s_mb_rb_lock) { - struct super_block *sb = PDE_DATA(file_inode(seq->file)); + struct super_block *sb = pde_data(file_inode(seq->file)); unsigned long position; - read_lock(&EXT4_SB(sb)->s_mb_rb_lock); - - if (*pos < 0 || *pos >= MB_NUM_ORDERS(sb) + 1) + if (*pos < 0 || *pos >= 2*MB_NUM_ORDERS(sb)) return NULL; position = *pos + 1; return (void *) ((unsigned long) position); @@ -2998,11 +2953,11 @@ __acquires(&EXT4_SB(sb)->s_mb_rb_lock) static void *ext4_mb_seq_structs_summary_next(struct seq_file *seq, void *v, loff_t *pos) { - struct super_block *sb = PDE_DATA(file_inode(seq->file)); + struct super_block *sb = pde_data(file_inode(seq->file)); unsigned long position; ++*pos; - if (*pos < 0 || *pos >= MB_NUM_ORDERS(sb) + 1) + if (*pos < 0 || *pos >= 2*MB_NUM_ORDERS(sb)) return NULL; position = *pos + 1; return (void *) ((unsigned long) position); @@ -3010,33 +2965,26 @@ static void *ext4_mb_seq_structs_summary_next(struct seq_file *seq, void *v, lof static int ext4_mb_seq_structs_summary_show(struct seq_file *seq, void *v) { - struct super_block *sb = PDE_DATA(file_inode(seq->file)); + struct super_block *sb = pde_data(file_inode(seq->file)); struct ext4_sb_info *sbi = EXT4_SB(sb); unsigned long position = ((unsigned long) v); struct ext4_group_info *grp; - struct rb_node *n; - unsigned int count, min, max; + unsigned int count; position--; if (position >= MB_NUM_ORDERS(sb)) { - seq_puts(seq, "fragment_size_tree:\n"); - n = rb_first(&sbi->s_mb_avg_fragment_size_root); - if (!n) { - seq_puts(seq, "\ttree_min: 0\n\ttree_max: 0\n\ttree_nodes: 0\n"); - return 0; - } - grp = rb_entry(n, struct ext4_group_info, bb_avg_fragment_size_rb); - min = grp->bb_fragments ? grp->bb_free / grp->bb_fragments : 0; - count = 1; - while (rb_next(n)) { - count++; - n = rb_next(n); - } - grp = rb_entry(n, struct ext4_group_info, bb_avg_fragment_size_rb); - max = grp->bb_fragments ? grp->bb_free / grp->bb_fragments : 0; + position -= MB_NUM_ORDERS(sb); + if (position == 0) + seq_puts(seq, "avg_fragment_size_lists:\n"); - seq_printf(seq, "\ttree_min: %u\n\ttree_max: %u\n\ttree_nodes: %u\n", - min, max, count); + count = 0; + read_lock(&sbi->s_mb_avg_fragment_size_locks[position]); + list_for_each_entry(grp, &sbi->s_mb_avg_fragment_size[position], + bb_avg_fragment_size_node) + count++; + read_unlock(&sbi->s_mb_avg_fragment_size_locks[position]); + seq_printf(seq, "\tlist_order_%u_groups: %u\n", + (unsigned int)position, count); return 0; } @@ -3046,9 +2994,11 @@ static int ext4_mb_seq_structs_summary_show(struct seq_file *seq, void *v) seq_puts(seq, "max_free_order_lists:\n"); } count = 0; + read_lock(&sbi->s_mb_largest_free_orders_locks[position]); list_for_each_entry(grp, &sbi->s_mb_largest_free_orders[position], bb_largest_free_order_node) count++; + read_unlock(&sbi->s_mb_largest_free_orders_locks[position]); seq_printf(seq, "\tlist_order_%u_groups: %u\n", (unsigned int)position, count); @@ -3056,11 +3006,7 @@ static int ext4_mb_seq_structs_summary_show(struct seq_file *seq, void *v) } static void ext4_mb_seq_structs_summary_stop(struct seq_file *seq, void *v) -__releases(&EXT4_SB(sb)->s_mb_rb_lock) { - struct super_block *sb = PDE_DATA(file_inode(seq->file)); - - read_unlock(&EXT4_SB(sb)->s_mb_rb_lock); } const struct seq_operations ext4_mb_seq_structs_summary_ops = { @@ -3173,8 +3119,9 @@ int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t group, init_rwsem(&meta_group_info[i]->alloc_sem); meta_group_info[i]->bb_free_root = RB_ROOT; INIT_LIST_HEAD(&meta_group_info[i]->bb_largest_free_order_node); - RB_CLEAR_NODE(&meta_group_info[i]->bb_avg_fragment_size_rb); + INIT_LIST_HEAD(&meta_group_info[i]->bb_avg_fragment_size_node); meta_group_info[i]->bb_largest_free_order = -1; /* uninit */ + meta_group_info[i]->bb_avg_fragment_size_order = -1; /* uninit */ meta_group_info[i]->bb_group = group; mb_group_bb_bitmap_alloc(sb, meta_group_info[i], group); @@ -3423,7 +3370,24 @@ int ext4_mb_init(struct super_block *sb) i++; } while (i < MB_NUM_ORDERS(sb)); - sbi->s_mb_avg_fragment_size_root = RB_ROOT; + sbi->s_mb_avg_fragment_size = + kmalloc_array(MB_NUM_ORDERS(sb), sizeof(struct list_head), + GFP_KERNEL); + if (!sbi->s_mb_avg_fragment_size) { + ret = -ENOMEM; + goto out; + } + sbi->s_mb_avg_fragment_size_locks = + kmalloc_array(MB_NUM_ORDERS(sb), sizeof(rwlock_t), + GFP_KERNEL); + if (!sbi->s_mb_avg_fragment_size_locks) { + ret = -ENOMEM; + goto out; + } + for (i = 0; i < MB_NUM_ORDERS(sb); i++) { + INIT_LIST_HEAD(&sbi->s_mb_avg_fragment_size[i]); + rwlock_init(&sbi->s_mb_avg_fragment_size_locks[i]); + } sbi->s_mb_largest_free_orders = kmalloc_array(MB_NUM_ORDERS(sb), sizeof(struct list_head), GFP_KERNEL); @@ -3442,7 +3406,6 @@ int ext4_mb_init(struct super_block *sb) INIT_LIST_HEAD(&sbi->s_mb_largest_free_orders[i]); rwlock_init(&sbi->s_mb_largest_free_orders_locks[i]); } - rwlock_init(&sbi->s_mb_rb_lock); spin_lock_init(&sbi->s_md_lock); sbi->s_mb_free_pending = 0; @@ -3498,7 +3461,7 @@ int ext4_mb_init(struct super_block *sb) spin_lock_init(&lg->lg_prealloc_lock); } - if (blk_queue_nonrot(bdev_get_queue(sb->s_bdev))) + if (bdev_nonrot(sb->s_bdev)) sbi->s_mb_max_linear_groups = 0; else sbi->s_mb_max_linear_groups = MB_DEFAULT_LINEAR_LIMIT; @@ -3513,6 +3476,8 @@ out_free_locality_groups: free_percpu(sbi->s_locality_groups); sbi->s_locality_groups = NULL; out: + kfree(sbi->s_mb_avg_fragment_size); + kfree(sbi->s_mb_avg_fragment_size_locks); kfree(sbi->s_mb_largest_free_orders); kfree(sbi->s_mb_largest_free_orders_locks); kfree(sbi->s_mb_offsets); @@ -3579,6 +3544,8 @@ int ext4_mb_release(struct super_block *sb) kvfree(group_info); rcu_read_unlock(); } + kfree(sbi->s_mb_avg_fragment_size); + kfree(sbi->s_mb_avg_fragment_size_locks); kfree(sbi->s_mb_largest_free_orders); kfree(sbi->s_mb_largest_free_orders_locks); kfree(sbi->s_mb_offsets); @@ -3629,7 +3596,7 @@ static inline int ext4_issue_discard(struct super_block *sb, return __blkdev_issue_discard(sb->s_bdev, (sector_t)discard_block << (sb->s_blocksize_bits - 9), (sector_t)count << (sb->s_blocksize_bits - 9), - GFP_NOFS, 0, biop); + GFP_NOFS, biop); } else return sb_issue_discard(sb, discard_block, count, GFP_NOFS, 0); } @@ -3825,7 +3792,7 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac, * We leak some of the blocks here. */ ext4_lock_group(sb, ac->ac_b_ex.fe_group); - ext4_set_bits(bitmap_bh->b_data, ac->ac_b_ex.fe_start, + 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); @@ -3844,7 +3811,7 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac, } } #endif - ext4_set_bits(bitmap_bh->b_data, ac->ac_b_ex.fe_start, + 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))) { @@ -3899,69 +3866,103 @@ void ext4_mb_mark_bb(struct super_block *sb, ext4_fsblk_t block, struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_group_t group; ext4_grpblk_t blkoff; - int i, clen, err; + int i, err; int already; + unsigned int clen, clen_changed, thisgrp_len; - clen = EXT4_B2C(sbi, len); + while (len > 0) { + ext4_get_group_no_and_offset(sb, block, &group, &blkoff); - ext4_get_group_no_and_offset(sb, block, &group, &blkoff); - bitmap_bh = ext4_read_block_bitmap(sb, group); - if (IS_ERR(bitmap_bh)) { - err = PTR_ERR(bitmap_bh); - bitmap_bh = NULL; - goto out_err; - } + /* + * Check to see if we are freeing blocks across a group + * boundary. + * In case of flex_bg, this can happen that (block, len) may + * span across more than one group. In that case we need to + * get the corresponding group metadata to work with. + * For this we have goto again loop. + */ + thisgrp_len = min_t(unsigned int, (unsigned int)len, + EXT4_BLOCKS_PER_GROUP(sb) - EXT4_C2B(sbi, blkoff)); + clen = EXT4_NUM_B2C(sbi, thisgrp_len); + + if (!ext4_sb_block_valid(sb, NULL, block, thisgrp_len)) { + ext4_error(sb, "Marking blocks in system zone - " + "Block = %llu, len = %u", + block, thisgrp_len); + bitmap_bh = NULL; + break; + } - err = -EIO; - gdp = ext4_get_group_desc(sb, group, &gdp_bh); - if (!gdp) - goto out_err; + bitmap_bh = ext4_read_block_bitmap(sb, group); + if (IS_ERR(bitmap_bh)) { + err = PTR_ERR(bitmap_bh); + bitmap_bh = NULL; + 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++; + err = -EIO; + gdp = ext4_get_group_desc(sb, group, &gdp_bh); + if (!gdp) + break; - if (state) - ext4_set_bits(bitmap_bh->b_data, blkoff, clen); - else - mb_test_and_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 + already; - else - clen = ext4_free_group_clusters(sb, gdp) + clen - already; + 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, group, gdp, bitmap_bh); - ext4_group_desc_csum_set(sb, group, gdp); + ext4_free_group_clusters_set(sb, gdp, clen); + ext4_block_bitmap_csum_set(sb, group, gdp, bitmap_bh); + ext4_group_desc_csum_set(sb, group, gdp); - ext4_unlock_group(sb, group); + ext4_unlock_group(sb, group); - if (sbi->s_log_groups_per_flex) { - ext4_group_t flex_group = ext4_flex_group(sbi, 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); - atomic64_sub(len, - &sbi_array_rcu_deref(sbi, s_flex_groups, - flex_group)->free_clusters); + 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); + if (err) + break; + + block += thisgrp_len; + len -= thisgrp_len; + brelse(bitmap_bh); + BUG_ON(len < 0); } - err = ext4_handle_dirty_metadata(NULL, NULL, bitmap_bh); if (err) - goto out_err; - sync_dirty_buffer(bitmap_bh); - err = ext4_handle_dirty_metadata(NULL, NULL, gdp_bh); - sync_dirty_buffer(gdp_bh); - -out_err: - brelse(bitmap_bh); + brelse(bitmap_bh); } /* @@ -4073,6 +4074,15 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac, size = size >> bsbits; start = start_off >> bsbits; + /* + * For tiny groups (smaller than 8MB) the chosen allocation + * alignment may be larger than group size. Make sure the + * alignment does not move allocation to a different group which + * makes mballoc fail assertions later. + */ + start = max(start, rounddown(ac->ac_o_ex.fe_logical, + (ext4_lblk_t)EXT4_BLOCKS_PER_GROUP(ac->ac_sb))); + /* don't cover already allocated blocks in selected range */ if (ar->pleft && start <= ar->lleft) { size -= ar->lleft + 1 - start; @@ -4145,7 +4155,22 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac, } rcu_read_unlock(); - if (start + size <= ac->ac_o_ex.fe_logical && + /* + * In this function "start" and "size" are normalized for better + * alignment and length such that we could preallocate more blocks. + * This normalization is done such that original request of + * ac->ac_o_ex.fe_logical & fe_len should always lie within "start" and + * "size" boundaries. + * (Note fe_len can be relaxed since FS block allocation API does not + * provide gurantee on number of contiguous blocks allocation since that + * depends upon free space left, etc). + * In case of inode pa, later we use the allocated blocks + * [pa_start + fe_logical - pa_lstart, fe_len/size] from the preallocated + * range of goal/best blocks [start, size] to put it at the + * ac_o_ex.fe_logical extent of this inode. + * (See ext4_mb_use_inode_pa() for more details) + */ + if (start + size <= ac->ac_o_ex.fe_logical || start > ac->ac_o_ex.fe_logical) { ext4_msg(ac->ac_sb, KERN_ERR, "start %lu, size %lu, fe_logical %lu", @@ -4433,7 +4458,7 @@ static void ext4_mb_generate_from_freelist(struct super_block *sb, void *bitmap, while (n) { entry = rb_entry(n, struct ext4_free_data, efd_node); - ext4_set_bits(bitmap, entry->efd_start_cluster, entry->efd_count); + mb_set_bits(bitmap, entry->efd_start_cluster, entry->efd_count); n = rb_next(n); } return; @@ -4474,7 +4499,7 @@ void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap, if (unlikely(len == 0)) continue; BUG_ON(groupnr != group); - ext4_set_bits(bitmap, start, len); + mb_set_bits(bitmap, start, len); preallocated += len; } mb_debug(sb, "preallocated %d for group %u\n", preallocated, group); @@ -5132,6 +5157,7 @@ static void ext4_mb_group_or_file(struct ext4_allocation_context *ac) struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); int bsbits = ac->ac_sb->s_blocksize_bits; loff_t size, isize; + bool inode_pa_eligible, group_pa_eligible; if (!(ac->ac_flags & EXT4_MB_HINT_DATA)) return; @@ -5139,25 +5165,27 @@ static void ext4_mb_group_or_file(struct ext4_allocation_context *ac) if (unlikely(ac->ac_flags & EXT4_MB_HINT_GOAL_ONLY)) return; + 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); isize = (i_size_read(ac->ac_inode) + ac->ac_sb->s_blocksize - 1) >> bsbits; + /* No point in using inode preallocation for closed files */ if ((size == isize) && !ext4_fs_is_busy(sbi) && - !inode_is_open_for_write(ac->ac_inode)) { - ac->ac_flags |= EXT4_MB_HINT_NOPREALLOC; - return; - } + !inode_is_open_for_write(ac->ac_inode)) + inode_pa_eligible = false; - if (sbi->s_mb_group_prealloc <= 0) { - ac->ac_flags |= EXT4_MB_STREAM_ALLOC; - return; - } - - /* don't use group allocation for large files */ size = max(size, isize); - if (size > sbi->s_mb_stream_request) { - ac->ac_flags |= EXT4_MB_STREAM_ALLOC; + /* Don't use group allocation for large files */ + if (size > sbi->s_mb_stream_request) + group_pa_eligible = false; + + if (!group_pa_eligible) { + if (inode_pa_eligible) + ac->ac_flags |= EXT4_MB_STREAM_ALLOC; + else + ac->ac_flags |= EXT4_MB_HINT_NOPREALLOC; return; } @@ -5504,6 +5532,7 @@ ext4_fsblk_t ext4_mb_new_blocks(handle_t *handle, ext4_fsblk_t block = 0; unsigned int inquota = 0; unsigned int reserv_clstrs = 0; + int retries = 0; u64 seq; might_sleep(); @@ -5606,7 +5635,8 @@ repeat: ar->len = ac->ac_b_ex.fe_len; } } else { - if (ext4_mb_discard_preallocations_should_retry(sb, ac, &seq)) + if (++retries < 3 && + ext4_mb_discard_preallocations_should_retry(sb, ac, &seq)) goto repeat; /* * If block allocation fails then the pa allocated above @@ -5753,7 +5783,8 @@ static ext4_fsblk_t ext4_mb_new_blocks_simple(handle_t *handle, struct super_block *sb = ar->inode->i_sb; ext4_group_t group; ext4_grpblk_t blkoff; - int i = sb->s_blocksize; + ext4_grpblk_t max = EXT4_CLUSTERS_PER_GROUP(sb); + ext4_grpblk_t i = 0; ext4_fsblk_t goal, block; struct ext4_super_block *es = EXT4_SB(sb)->s_es; @@ -5775,19 +5806,26 @@ static ext4_fsblk_t ext4_mb_new_blocks_simple(handle_t *handle, ext4_get_group_no_and_offset(sb, max(ext4_group_first_block_no(sb, group), goal), NULL, &blkoff); - i = mb_find_next_zero_bit(bitmap_bh->b_data, sb->s_blocksize, + while (1) { + i = mb_find_next_zero_bit(bitmap_bh->b_data, max, blkoff); + if (i >= max) + break; + if (ext4_fc_replay_check_excluded(sb, + ext4_group_first_block_no(sb, group) + i)) { + blkoff = i + 1; + } else + break; + } brelse(bitmap_bh); - if (i >= sb->s_blocksize) - continue; - if (ext4_fc_replay_check_excluded(sb, - ext4_group_first_block_no(sb, group) + i)) - continue; - break; + if (i < max) + break; } - if (group >= ext4_get_groups_count(sb) && i >= sb->s_blocksize) + if (group >= ext4_get_groups_count(sb) || i >= max) { + *errp = -ENOSPC; return 0; + } block = ext4_group_first_block_no(sb, group) + i; ext4_mb_mark_bb(sb, block, 1, 1); @@ -5838,17 +5876,17 @@ static void ext4_free_blocks_simple(struct inode *inode, ext4_fsblk_t block, } /** - * ext4_free_blocks() -- Free given blocks and update quota + * ext4_mb_clear_bb() -- helper function for freeing blocks. + * Used by ext4_free_blocks() * @handle: handle for this transaction * @inode: inode - * @bh: optional buffer of the block to be freed * @block: starting physical block to be freed * @count: number of blocks to be freed * @flags: flags used by ext4_free_blocks */ -void ext4_free_blocks(handle_t *handle, struct inode *inode, - struct buffer_head *bh, ext4_fsblk_t block, - unsigned long count, int flags) +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; @@ -5865,79 +5903,14 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode, sbi = EXT4_SB(sb); - if (sbi->s_mount_state & EXT4_FC_REPLAY) { - ext4_free_blocks_simple(inode, block, count); - return; - } - - might_sleep(); - if (bh) { - if (block) - BUG_ON(block != bh->b_blocknr); - else - block = bh->b_blocknr; - } - if (!(flags & EXT4_FREE_BLOCKS_VALIDATED) && !ext4_inode_block_valid(inode, block, count)) { - ext4_error(sb, "Freeing blocks not in datazone - " - "block = %llu, count = %lu", 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; } - - ext4_debug("freeing block %llu\n", block); - trace_ext4_free_blocks(inode, block, count, flags); - - if (bh && (flags & EXT4_FREE_BLOCKS_FORGET)) { - BUG_ON(count > 1); - - ext4_forget(handle, flags & EXT4_FREE_BLOCKS_METADATA, - inode, bh, block); - } - - /* - * If the extent to be freed does not begin on a cluster - * boundary, we need to deal with partial clusters at the - * beginning and end of the extent. Normally we will free - * blocks at the beginning or the end unless we are explicitly - * requested to avoid doing so. - */ - overflow = EXT4_PBLK_COFF(sbi, block); - if (overflow) { - if (flags & EXT4_FREE_BLOCKS_NOFREE_FIRST_CLUSTER) { - overflow = sbi->s_cluster_ratio - overflow; - block += overflow; - if (count > overflow) - count -= overflow; - else - return; - } else { - block -= overflow; - count += overflow; - } - } - overflow = EXT4_LBLK_COFF(sbi, count); - if (overflow) { - if (flags & EXT4_FREE_BLOCKS_NOFREE_LAST_CLUSTER) { - if (count > overflow) - count -= overflow; - else - return; - } else - count += sbi->s_cluster_ratio - overflow; - } - - if (!bh && (flags & EXT4_FREE_BLOCKS_FORGET)) { - int i; - int is_metadata = flags & EXT4_FREE_BLOCKS_METADATA; - - for (i = 0; i < count; i++) { - cond_resched(); - if (is_metadata) - bh = sb_find_get_block(inode->i_sb, block + i); - ext4_forget(handle, is_metadata, inode, bh, block + i); - } - } + flags |= EXT4_FREE_BLOCKS_VALIDATED; do_more: overflow = 0; @@ -5955,6 +5928,8 @@ do_more: overflow = EXT4_C2B(sbi, bit) + count - EXT4_BLOCKS_PER_GROUP(sb); count -= overflow; + /* The range changed so it's no longer validated */ + flags &= ~EXT4_FREE_BLOCKS_VALIDATED; } count_clusters = EXT4_NUM_B2C(sbi, count); bitmap_bh = ext4_read_block_bitmap(sb, block_group); @@ -5969,13 +5944,8 @@ do_more: goto error_return; } - if (in_range(ext4_block_bitmap(sb, gdp), block, count) || - in_range(ext4_inode_bitmap(sb, gdp), block, count) || - in_range(block, ext4_inode_table(sb, gdp), - sbi->s_itb_per_group) || - in_range(block + count - 1, ext4_inode_table(sb, gdp), - sbi->s_itb_per_group)) { - + 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 */ @@ -6046,7 +6016,7 @@ do_more: NULL); if (err && err != -EOPNOTSUPP) ext4_msg(sb, KERN_WARNING, "discard request in" - " group:%d block:%d count:%lu failed" + " group:%u block:%d count:%lu failed" " with %d", block_group, bit, count, err); } else @@ -6098,6 +6068,8 @@ do_more: block += count; count = overflow; put_bh(bitmap_bh); + /* The range changed so it's no longer validated */ + flags &= ~EXT4_FREE_BLOCKS_VALIDATED; goto do_more; } error_return: @@ -6107,6 +6079,108 @@ error_return: } /** + * ext4_free_blocks() -- Free given blocks and update quota + * @handle: handle for this transaction + * @inode: inode + * @bh: optional buffer of the block to be freed + * @block: starting physical block to be freed + * @count: number of blocks to be freed + * @flags: flags used by ext4_free_blocks + */ +void ext4_free_blocks(handle_t *handle, struct inode *inode, + struct buffer_head *bh, ext4_fsblk_t block, + unsigned long count, int flags) +{ + struct super_block *sb = inode->i_sb; + unsigned int overflow; + struct ext4_sb_info *sbi; + + sbi = EXT4_SB(sb); + + if (sbi->s_mount_state & EXT4_FC_REPLAY) { + ext4_free_blocks_simple(inode, block, count); + return; + } + + might_sleep(); + if (bh) { + if (block) + BUG_ON(block != bh->b_blocknr); + else + block = bh->b_blocknr; + } + + if (!(flags & EXT4_FREE_BLOCKS_VALIDATED) && + !ext4_inode_block_valid(inode, block, count)) { + ext4_error(sb, "Freeing blocks not in datazone - " + "block = %llu, count = %lu", block, count); + return; + } + flags |= EXT4_FREE_BLOCKS_VALIDATED; + + ext4_debug("freeing block %llu\n", block); + trace_ext4_free_blocks(inode, block, count, flags); + + if (bh && (flags & EXT4_FREE_BLOCKS_FORGET)) { + BUG_ON(count > 1); + + ext4_forget(handle, flags & EXT4_FREE_BLOCKS_METADATA, + inode, bh, block); + } + + /* + * If the extent to be freed does not begin on a cluster + * boundary, we need to deal with partial clusters at the + * beginning and end of the extent. Normally we will free + * blocks at the beginning or the end unless we are explicitly + * requested to avoid doing so. + */ + overflow = EXT4_PBLK_COFF(sbi, block); + if (overflow) { + if (flags & EXT4_FREE_BLOCKS_NOFREE_FIRST_CLUSTER) { + overflow = sbi->s_cluster_ratio - overflow; + block += overflow; + if (count > overflow) + count -= overflow; + else + return; + } else { + block -= overflow; + count += overflow; + } + /* The range changed so it's no longer validated */ + flags &= ~EXT4_FREE_BLOCKS_VALIDATED; + } + overflow = EXT4_LBLK_COFF(sbi, count); + if (overflow) { + if (flags & EXT4_FREE_BLOCKS_NOFREE_LAST_CLUSTER) { + if (count > overflow) + count -= overflow; + else + return; + } else + count += sbi->s_cluster_ratio - overflow; + /* The range changed so it's no longer validated */ + flags &= ~EXT4_FREE_BLOCKS_VALIDATED; + } + + if (!bh && (flags & EXT4_FREE_BLOCKS_FORGET)) { + int i; + int is_metadata = flags & EXT4_FREE_BLOCKS_METADATA; + + for (i = 0; i < count; i++) { + cond_resched(); + if (is_metadata) + bh = sb_find_get_block(inode->i_sb, block + i); + ext4_forget(handle, is_metadata, inode, bh, block + i); + } + } + + ext4_mb_clear_bb(handle, inode, block, count, flags); + return; +} + +/** * ext4_group_add_blocks() -- Add given blocks to an existing group * @handle: handle to this transaction * @sb: super block @@ -6162,11 +6236,7 @@ int ext4_group_add_blocks(handle_t *handle, struct super_block *sb, goto error_return; } - if (in_range(ext4_block_bitmap(sb, desc), block, count) || - in_range(ext4_inode_bitmap(sb, desc), block, count) || - in_range(block, ext4_inode_table(sb, desc), sbi->s_itb_per_group) || - in_range(block + count - 1, ext4_inode_table(sb, desc), - sbi->s_itb_per_group)) { + if (!ext4_sb_block_valid(sb, NULL, block, count)) { ext4_error(sb, "Adding blocks in system zones - " "Block = %llu, count = %lu", block, count); @@ -6343,6 +6413,7 @@ __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 @@ -6352,7 +6423,7 @@ __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) + ext4_grpblk_t minblocks, bool set_trimmed) { struct ext4_buddy e4b; int ret; @@ -6371,7 +6442,7 @@ ext4_trim_all_free(struct super_block *sb, ext4_group_t group, if (!EXT4_MB_GRP_WAS_TRIMMED(e4b.bd_info) || minblocks < EXT4_SB(sb)->s_last_trim_minblks) { ret = ext4_try_to_trim_range(sb, &e4b, start, max, minblocks); - if (ret >= 0) + if (ret >= 0 && set_trimmed) EXT4_MB_GRP_SET_TRIMMED(e4b.bd_info); } else { ret = 0; @@ -6400,7 +6471,7 @@ ext4_trim_all_free(struct super_block *sb, ext4_group_t group, */ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range) { - struct request_queue *q = bdev_get_queue(sb->s_bdev); + unsigned int discard_granularity = bdev_discard_granularity(sb->s_bdev); struct ext4_group_info *grp; ext4_group_t group, first_group, last_group; ext4_grpblk_t cnt = 0, first_cluster, last_cluster; @@ -6408,6 +6479,7 @@ 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; @@ -6420,14 +6492,16 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range) range->len < sb->s_blocksize) return -EINVAL; /* No point to try to trim less than discard granularity */ - if (range->minlen < q->limits.discard_granularity) { + if (range->minlen < discard_granularity) { minlen = EXT4_NUM_B2C(EXT4_SB(sb), - q->limits.discard_granularity >> sb->s_blocksize_bits); + discard_granularity >> sb->s_blocksize_bits); if (minlen > EXT4_CLUSTERS_PER_GROUP(sb)) goto out; } - if (end >= max_blks) + if (end >= max_blks - 1) { end = max_blks - 1; + eof = true; + } if (end <= first_data_blk) goto out; if (start < first_data_blk) @@ -6441,6 +6515,7 @@ 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++) { grp = ext4_get_group_info(sb, group); @@ -6457,12 +6532,13 @@ 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); + end, minlen, whole_group); if (cnt < 0) { ret = cnt; break; |