diff options
Diffstat (limited to 'fs/f2fs/segment.c')
| -rw-r--r-- | fs/f2fs/segment.c | 1998 |
1 files changed, 1441 insertions, 557 deletions
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index 2cd0d126ef8f..fa32ce92ed65 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/segment.c * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/fs.h> #include <linux/f2fs_fs.h> @@ -169,7 +166,7 @@ found: return result - size + __reverse_ffz(tmp); } -bool need_SSR(struct f2fs_sb_info *sbi) +bool f2fs_need_SSR(struct f2fs_sb_info *sbi) { int node_secs = get_blocktype_secs(sbi, F2FS_DIRTY_NODES); int dent_secs = get_blocktype_secs(sbi, F2FS_DIRTY_DENTS); @@ -177,22 +174,22 @@ bool need_SSR(struct f2fs_sb_info *sbi) if (test_opt(sbi, LFS)) return false; - if (sbi->gc_thread && sbi->gc_thread->gc_urgent) + if (sbi->gc_mode == GC_URGENT) + return true; + if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) return true; return free_sections(sbi) <= (node_secs + 2 * dent_secs + imeta_secs + - 2 * reserved_sections(sbi)); + SM_I(sbi)->min_ssr_sections + reserved_sections(sbi)); } -void register_inmem_page(struct inode *inode, struct page *page) +void f2fs_register_inmem_page(struct inode *inode, struct page *page) { - struct f2fs_inode_info *fi = F2FS_I(inode); struct inmem_pages *new; f2fs_trace_pid(page); - set_page_private(page, (unsigned long)ATOMIC_WRITTEN_PAGE); - SetPagePrivate(page); + f2fs_set_page_private(page, (unsigned long)ATOMIC_WRITTEN_PAGE); new = f2fs_kmem_cache_alloc(inmem_entry_slab, GFP_NOFS); @@ -201,17 +198,18 @@ void register_inmem_page(struct inode *inode, struct page *page) INIT_LIST_HEAD(&new->list); /* increase reference count with clean state */ - mutex_lock(&fi->inmem_lock); get_page(page); - list_add_tail(&new->list, &fi->inmem_pages); + mutex_lock(&F2FS_I(inode)->inmem_lock); + list_add_tail(&new->list, &F2FS_I(inode)->inmem_pages); inc_page_count(F2FS_I_SB(inode), F2FS_INMEM_PAGES); - mutex_unlock(&fi->inmem_lock); + mutex_unlock(&F2FS_I(inode)->inmem_lock); trace_f2fs_register_inmem_page(page, INMEM); } static int __revoke_inmem_pages(struct inode *inode, - struct list_head *head, bool drop, bool recover) + struct list_head *head, bool drop, bool recover, + bool trylock) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct inmem_pages *cur, *tmp; @@ -223,9 +221,18 @@ static int __revoke_inmem_pages(struct inode *inode, if (drop) trace_f2fs_commit_inmem_page(page, INMEM_DROP); - lock_page(page); + if (trylock) { + /* + * to avoid deadlock in between page lock and + * inmem_lock. + */ + if (!trylock_page(page)) + continue; + } else { + lock_page(page); + } - f2fs_wait_on_page_writeback(page, DATA, true); + f2fs_wait_on_page_writeback(page, DATA, true, true); if (recover) { struct dnode_of_data dn; @@ -234,7 +241,8 @@ static int __revoke_inmem_pages(struct inode *inode, trace_f2fs_commit_inmem_page(page, INMEM_REVOKE); retry: set_new_dnode(&dn, inode, NULL, NULL, 0); - err = get_dnode_of_data(&dn, page->index, LOOKUP_NODE); + err = f2fs_get_dnode_of_data(&dn, page->index, + LOOKUP_NODE); if (err) { if (err == -ENOMEM) { congestion_wait(BLK_RW_ASYNC, HZ/50); @@ -244,8 +252,18 @@ retry: err = -EAGAIN; goto next; } - get_node_info(sbi, dn.nid, &ni); - f2fs_replace_block(sbi, &dn, dn.data_blkaddr, + + err = f2fs_get_node_info(sbi, dn.nid, &ni); + if (err) { + f2fs_put_dnode(&dn); + return err; + } + + if (cur->old_addr == NEW_ADDR) { + f2fs_invalidate_blocks(sbi, dn.data_blkaddr); + f2fs_update_data_blkaddr(&dn, NEW_ADDR); + } else + f2fs_replace_block(sbi, &dn, dn.data_blkaddr, cur->old_addr, ni.version, true, true); f2fs_put_dnode(&dn); } @@ -255,8 +273,7 @@ next: ClearPageUptodate(page); clear_cold_data(page); } - set_page_private(page, 0); - ClearPagePrivate(page); + f2fs_clear_page_private(page); f2fs_put_page(page, 1); list_del(&cur->list); @@ -266,20 +283,70 @@ next: return err; } -void drop_inmem_pages(struct inode *inode) +void f2fs_drop_inmem_pages_all(struct f2fs_sb_info *sbi, bool gc_failure) +{ + struct list_head *head = &sbi->inode_list[ATOMIC_FILE]; + struct inode *inode; + struct f2fs_inode_info *fi; + unsigned int count = sbi->atomic_files; + unsigned int looped = 0; +next: + spin_lock(&sbi->inode_lock[ATOMIC_FILE]); + if (list_empty(head)) { + spin_unlock(&sbi->inode_lock[ATOMIC_FILE]); + return; + } + fi = list_first_entry(head, struct f2fs_inode_info, inmem_ilist); + inode = igrab(&fi->vfs_inode); + if (inode) + list_move_tail(&fi->inmem_ilist, head); + spin_unlock(&sbi->inode_lock[ATOMIC_FILE]); + + if (inode) { + if (gc_failure) { + if (!fi->i_gc_failures[GC_FAILURE_ATOMIC]) + goto skip; + } + set_inode_flag(inode, FI_ATOMIC_REVOKE_REQUEST); + f2fs_drop_inmem_pages(inode); +skip: + iput(inode); + } + congestion_wait(BLK_RW_ASYNC, HZ/50); + cond_resched(); + if (gc_failure) { + if (++looped >= count) + return; + } + goto next; +} + +void f2fs_drop_inmem_pages(struct inode *inode) { + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct f2fs_inode_info *fi = F2FS_I(inode); - mutex_lock(&fi->inmem_lock); - __revoke_inmem_pages(inode, &fi->inmem_pages, true, false); - mutex_unlock(&fi->inmem_lock); + while (!list_empty(&fi->inmem_pages)) { + mutex_lock(&fi->inmem_lock); + __revoke_inmem_pages(inode, &fi->inmem_pages, + true, false, true); + mutex_unlock(&fi->inmem_lock); + } - clear_inode_flag(inode, FI_ATOMIC_FILE); - clear_inode_flag(inode, FI_HOT_DATA); + fi->i_gc_failures[GC_FAILURE_ATOMIC] = 0; stat_dec_atomic_write(inode); + + spin_lock(&sbi->inode_lock[ATOMIC_FILE]); + if (!list_empty(&fi->inmem_ilist)) + list_del_init(&fi->inmem_ilist); + if (f2fs_is_atomic_file(inode)) { + clear_inode_flag(inode, FI_ATOMIC_FILE); + sbi->atomic_files--; + } + spin_unlock(&sbi->inode_lock[ATOMIC_FILE]); } -void drop_inmem_page(struct inode *inode, struct page *page) +void f2fs_drop_inmem_page(struct inode *inode, struct page *page) { struct f2fs_inode_info *fi = F2FS_I(inode); struct f2fs_sb_info *sbi = F2FS_I_SB(inode); @@ -294,7 +361,7 @@ void drop_inmem_page(struct inode *inode, struct page *page) break; } - f2fs_bug_on(sbi, !cur || cur->page != page); + f2fs_bug_on(sbi, list_empty(head) || cur->page != page); list_del(&cur->list); mutex_unlock(&fi->inmem_lock); @@ -302,29 +369,31 @@ void drop_inmem_page(struct inode *inode, struct page *page) kmem_cache_free(inmem_entry_slab, cur); ClearPageUptodate(page); - set_page_private(page, 0); - ClearPagePrivate(page); + f2fs_clear_page_private(page); f2fs_put_page(page, 0); trace_f2fs_commit_inmem_page(page, INMEM_INVALIDATE); } -static int __commit_inmem_pages(struct inode *inode, - struct list_head *revoke_list) +static int __f2fs_commit_inmem_pages(struct inode *inode) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct f2fs_inode_info *fi = F2FS_I(inode); struct inmem_pages *cur, *tmp; struct f2fs_io_info fio = { .sbi = sbi, + .ino = inode->i_ino, .type = DATA, .op = REQ_OP_WRITE, .op_flags = REQ_SYNC | REQ_PRIO, .io_type = FS_DATA_IO, }; - pgoff_t last_idx = ULONG_MAX; + struct list_head revoke_list; + bool submit_bio = false; int err = 0; + INIT_LIST_HEAD(&revoke_list); + list_for_each_entry_safe(cur, tmp, &fi->inmem_pages, list) { struct page *page = cur->page; @@ -332,18 +401,19 @@ static int __commit_inmem_pages(struct inode *inode, if (page->mapping == inode->i_mapping) { trace_f2fs_commit_inmem_page(page, INMEM); + f2fs_wait_on_page_writeback(page, DATA, true, true); + set_page_dirty(page); - f2fs_wait_on_page_writeback(page, DATA, true); if (clear_page_dirty_for_io(page)) { inode_dec_dirty_pages(inode); - remove_dirty_inode(inode); + f2fs_remove_dirty_inode(inode); } retry: fio.page = page; fio.old_blkaddr = NULL_ADDR; fio.encrypted_page = NULL; fio.need_lock = LOCK_DONE; - err = do_write_data_page(&fio); + err = f2fs_do_write_data_page(&fio); if (err) { if (err == -ENOMEM) { congestion_wait(BLK_RW_ASYNC, HZ/50); @@ -355,58 +425,60 @@ retry: } /* record old blkaddr for revoking */ cur->old_addr = fio.old_blkaddr; - last_idx = page->index; + submit_bio = true; } unlock_page(page); - list_move_tail(&cur->list, revoke_list); + list_move_tail(&cur->list, &revoke_list); } - if (last_idx != ULONG_MAX) - f2fs_submit_merged_write_cond(sbi, inode, 0, last_idx, DATA); + if (submit_bio) + f2fs_submit_merged_write_cond(sbi, inode, NULL, 0, DATA); - if (!err) - __revoke_inmem_pages(inode, revoke_list, false, false); + if (err) { + /* + * try to revoke all committed pages, but still we could fail + * due to no memory or other reason, if that happened, EAGAIN + * will be returned, which means in such case, transaction is + * already not integrity, caller should use journal to do the + * recovery or rewrite & commit last transaction. For other + * error number, revoking was done by filesystem itself. + */ + err = __revoke_inmem_pages(inode, &revoke_list, + false, true, false); + + /* drop all uncommitted pages */ + __revoke_inmem_pages(inode, &fi->inmem_pages, + true, false, false); + } else { + __revoke_inmem_pages(inode, &revoke_list, + false, false, false); + } return err; } -int commit_inmem_pages(struct inode *inode) +int f2fs_commit_inmem_pages(struct inode *inode) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct f2fs_inode_info *fi = F2FS_I(inode); - struct list_head revoke_list; int err; - INIT_LIST_HEAD(&revoke_list); f2fs_balance_fs(sbi, true); - f2fs_lock_op(sbi); + down_write(&fi->i_gc_rwsem[WRITE]); + + f2fs_lock_op(sbi); set_inode_flag(inode, FI_ATOMIC_COMMIT); mutex_lock(&fi->inmem_lock); - err = __commit_inmem_pages(inode, &revoke_list); - if (err) { - int ret; - /* - * try to revoke all committed pages, but still we could fail - * due to no memory or other reason, if that happened, EAGAIN - * will be returned, which means in such case, transaction is - * already not integrity, caller should use journal to do the - * recovery or rewrite & commit last transaction. For other - * error number, revoking was done by filesystem itself. - */ - ret = __revoke_inmem_pages(inode, &revoke_list, false, true); - if (ret) - err = ret; - - /* drop all uncommitted pages */ - __revoke_inmem_pages(inode, &fi->inmem_pages, true, false); - } + err = __f2fs_commit_inmem_pages(inode); mutex_unlock(&fi->inmem_lock); clear_inode_flag(inode, FI_ATOMIC_COMMIT); f2fs_unlock_op(sbi); + up_write(&fi->i_gc_rwsem[WRITE]); + return err; } @@ -416,17 +488,18 @@ int commit_inmem_pages(struct inode *inode) */ void f2fs_balance_fs(struct f2fs_sb_info *sbi, bool need) { -#ifdef CONFIG_F2FS_FAULT_INJECTION if (time_to_inject(sbi, FAULT_CHECKPOINT)) { - f2fs_show_injection_info(FAULT_CHECKPOINT); + f2fs_show_injection_info(sbi, FAULT_CHECKPOINT); f2fs_stop_checkpoint(sbi, false); } -#endif /* balance_fs_bg is able to be pending */ if (need && excess_cached_nats(sbi)) f2fs_balance_fs_bg(sbi); + if (!f2fs_is_checkpoint_ready(sbi)) + return; + /* * We should do GC or end up with checkpoint, if there are so many dirty * dir/node pages without enough free segments. @@ -443,33 +516,39 @@ void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi) return; /* try to shrink extent cache when there is no enough memory */ - if (!available_free_memory(sbi, EXTENT_CACHE)) + if (!f2fs_available_free_memory(sbi, EXTENT_CACHE)) f2fs_shrink_extent_tree(sbi, EXTENT_CACHE_SHRINK_NUMBER); /* check the # of cached NAT entries */ - if (!available_free_memory(sbi, NAT_ENTRIES)) - try_to_free_nats(sbi, NAT_ENTRY_PER_BLOCK); + if (!f2fs_available_free_memory(sbi, NAT_ENTRIES)) + f2fs_try_to_free_nats(sbi, NAT_ENTRY_PER_BLOCK); - if (!available_free_memory(sbi, FREE_NIDS)) - try_to_free_nids(sbi, MAX_FREE_NIDS); + if (!f2fs_available_free_memory(sbi, FREE_NIDS)) + f2fs_try_to_free_nids(sbi, MAX_FREE_NIDS); else - build_free_nids(sbi, false, false); + f2fs_build_free_nids(sbi, false, false); - if (!is_idle(sbi) && !excess_dirty_nats(sbi)) + if (!is_idle(sbi, REQ_TIME) && + (!excess_dirty_nats(sbi) && !excess_dirty_nodes(sbi))) return; /* checkpoint is the only way to shrink partial cached entries */ - if (!available_free_memory(sbi, NAT_ENTRIES) || - !available_free_memory(sbi, INO_ENTRIES) || + if (!f2fs_available_free_memory(sbi, NAT_ENTRIES) || + !f2fs_available_free_memory(sbi, INO_ENTRIES) || excess_prefree_segs(sbi) || excess_dirty_nats(sbi) || + excess_dirty_nodes(sbi) || f2fs_time_over(sbi, CP_TIME)) { if (test_opt(sbi, DATA_FLUSH)) { struct blk_plug plug; + mutex_lock(&sbi->flush_lock); + blk_start_plug(&plug); - sync_dirty_inodes(sbi, FILE_INODE); + f2fs_sync_dirty_inodes(sbi, FILE_INODE); blk_finish_plug(&plug); + + mutex_unlock(&sbi->flush_lock); } f2fs_sync_fs(sbi->sb, true); stat_inc_bg_cp_count(sbi->stat_info); @@ -479,9 +558,13 @@ void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi) static int __submit_flush_wait(struct f2fs_sb_info *sbi, struct block_device *bdev) { - struct bio *bio = f2fs_bio_alloc(0); + struct bio *bio; int ret; + bio = f2fs_bio_alloc(sbi, 0, false); + if (!bio) + return -ENOMEM; + bio->bi_opf = REQ_OP_WRITE | REQ_SYNC | REQ_PREFLUSH; bio_set_dev(bio, bdev); ret = submit_bio_wait(bio); @@ -492,15 +575,17 @@ static int __submit_flush_wait(struct f2fs_sb_info *sbi, return ret; } -static int submit_flush_wait(struct f2fs_sb_info *sbi) +static int submit_flush_wait(struct f2fs_sb_info *sbi, nid_t ino) { - int ret = __submit_flush_wait(sbi, sbi->sb->s_bdev); + int ret = 0; int i; - if (!f2fs_is_multi_device(sbi) || ret) - return ret; + if (!f2fs_is_multi_device(sbi)) + return __submit_flush_wait(sbi, sbi->sb->s_bdev); - for (i = 1; i < sbi->s_ndevs; i++) { + for (i = 0; i < sbi->s_ndevs; i++) { + if (!f2fs_is_dirty_device(sbi, ino, i, FLUSH_INO)) + continue; ret = __submit_flush_wait(sbi, FDEV(i).bdev); if (ret) break; @@ -526,7 +611,9 @@ repeat: fcc->dispatch_list = llist_del_all(&fcc->issue_list); fcc->dispatch_list = llist_reverse_order(fcc->dispatch_list); - ret = submit_flush_wait(sbi); + cmd = llist_entry(fcc->dispatch_list, struct flush_cmd, llnode); + + ret = submit_flush_wait(sbi, cmd->ino); atomic_inc(&fcc->issued_flush); llist_for_each_entry_safe(cmd, next, @@ -544,7 +631,7 @@ repeat: goto repeat; } -int f2fs_issue_flush(struct f2fs_sb_info *sbi) +int f2fs_issue_flush(struct f2fs_sb_info *sbi, nid_t ino) { struct flush_cmd_control *fcc = SM_I(sbi)->fcc_info; struct flush_cmd cmd; @@ -554,19 +641,23 @@ int f2fs_issue_flush(struct f2fs_sb_info *sbi) return 0; if (!test_opt(sbi, FLUSH_MERGE)) { - ret = submit_flush_wait(sbi); + atomic_inc(&fcc->queued_flush); + ret = submit_flush_wait(sbi, ino); + atomic_dec(&fcc->queued_flush); atomic_inc(&fcc->issued_flush); return ret; } - if (atomic_inc_return(&fcc->issing_flush) == 1) { - ret = submit_flush_wait(sbi); - atomic_dec(&fcc->issing_flush); + if (atomic_inc_return(&fcc->queued_flush) == 1 || + f2fs_is_multi_device(sbi)) { + ret = submit_flush_wait(sbi, ino); + atomic_dec(&fcc->queued_flush); atomic_inc(&fcc->issued_flush); return ret; } + cmd.ino = ino; init_completion(&cmd.wait); llist_add(&cmd.llnode, &fcc->issue_list); @@ -579,23 +670,23 @@ int f2fs_issue_flush(struct f2fs_sb_info *sbi) if (fcc->f2fs_issue_flush) { wait_for_completion(&cmd.wait); - atomic_dec(&fcc->issing_flush); + atomic_dec(&fcc->queued_flush); } else { struct llist_node *list; list = llist_del_all(&fcc->issue_list); if (!list) { wait_for_completion(&cmd.wait); - atomic_dec(&fcc->issing_flush); + atomic_dec(&fcc->queued_flush); } else { struct flush_cmd *tmp, *next; - ret = submit_flush_wait(sbi); + ret = submit_flush_wait(sbi, ino); llist_for_each_entry_safe(tmp, next, list, llnode) { if (tmp == &cmd) { cmd.ret = ret; - atomic_dec(&fcc->issing_flush); + atomic_dec(&fcc->queued_flush); continue; } tmp->ret = ret; @@ -607,7 +698,7 @@ int f2fs_issue_flush(struct f2fs_sb_info *sbi) return cmd.ret; } -int create_flush_cmd_control(struct f2fs_sb_info *sbi) +int f2fs_create_flush_cmd_control(struct f2fs_sb_info *sbi) { dev_t dev = sbi->sb->s_bdev->bd_dev; struct flush_cmd_control *fcc; @@ -620,11 +711,11 @@ int create_flush_cmd_control(struct f2fs_sb_info *sbi) goto init_thread; } - fcc = kzalloc(sizeof(struct flush_cmd_control), GFP_KERNEL); + fcc = f2fs_kzalloc(sbi, sizeof(struct flush_cmd_control), GFP_KERNEL); if (!fcc) return -ENOMEM; atomic_set(&fcc->issued_flush, 0); - atomic_set(&fcc->issing_flush, 0); + atomic_set(&fcc->queued_flush, 0); init_waitqueue_head(&fcc->flush_wait_queue); init_llist_head(&fcc->issue_list); SM_I(sbi)->fcc_info = fcc; @@ -636,7 +727,7 @@ init_thread: "f2fs_flush-%u:%u", MAJOR(dev), MINOR(dev)); if (IS_ERR(fcc->f2fs_issue_flush)) { err = PTR_ERR(fcc->f2fs_issue_flush); - kfree(fcc); + kvfree(fcc); SM_I(sbi)->fcc_info = NULL; return err; } @@ -644,7 +735,7 @@ init_thread: return err; } -void destroy_flush_cmd_control(struct f2fs_sb_info *sbi, bool free) +void f2fs_destroy_flush_cmd_control(struct f2fs_sb_info *sbi, bool free) { struct flush_cmd_control *fcc = SM_I(sbi)->fcc_info; @@ -655,11 +746,33 @@ void destroy_flush_cmd_control(struct f2fs_sb_info *sbi, bool free) kthread_stop(flush_thread); } if (free) { - kfree(fcc); + kvfree(fcc); SM_I(sbi)->fcc_info = NULL; } } +int f2fs_flush_device_cache(struct f2fs_sb_info *sbi) +{ + int ret = 0, i; + + if (!f2fs_is_multi_device(sbi)) + return 0; + + for (i = 1; i < sbi->s_ndevs; i++) { + if (!f2fs_test_bit(i, (char *)&sbi->dirty_device)) + continue; + ret = __submit_flush_wait(sbi, FDEV(i).bdev); + if (ret) + break; + + spin_lock(&sbi->dev_lock); + f2fs_clear_bit(i, (char *)&sbi->dirty_device); + spin_unlock(&sbi->dev_lock); + } + + return ret; +} + static void __locate_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno, enum dirty_type dirty_type) { @@ -700,9 +813,13 @@ static void __remove_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno, if (test_and_clear_bit(segno, dirty_i->dirty_segmap[t])) dirty_i->nr_dirty[t]--; - if (get_valid_blocks(sbi, segno, true) == 0) + if (get_valid_blocks(sbi, segno, true) == 0) { clear_bit(GET_SEC_FROM_SEG(sbi, segno), dirty_i->victim_secmap); +#ifdef CONFIG_F2FS_CHECK_FS + clear_bit(segno, SIT_I(sbi)->invalid_segmap); +#endif + } } } @@ -714,7 +831,7 @@ static void __remove_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno, static void locate_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno) { struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); - unsigned short valid_blocks; + unsigned short valid_blocks, ckpt_valid_blocks; if (segno == NULL_SEGNO || IS_CURSEG(sbi, segno)) return; @@ -722,8 +839,10 @@ static void locate_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno) mutex_lock(&dirty_i->seglist_lock); valid_blocks = get_valid_blocks(sbi, segno, false); + ckpt_valid_blocks = get_ckpt_valid_blocks(sbi, segno); - if (valid_blocks == 0) { + if (valid_blocks == 0 && (!is_sbi_flag_set(sbi, SBI_CP_DISABLED) || + ckpt_valid_blocks == sbi->blocks_per_seg)) { __locate_dirty_segment(sbi, segno, PRE); __remove_dirty_segment(sbi, segno, DIRTY); } else if (valid_blocks < sbi->blocks_per_seg) { @@ -736,6 +855,82 @@ static void locate_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno) mutex_unlock(&dirty_i->seglist_lock); } +/* This moves currently empty dirty blocks to prefree. Must hold seglist_lock */ +void f2fs_dirty_to_prefree(struct f2fs_sb_info *sbi) +{ + struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); + unsigned int segno; + + mutex_lock(&dirty_i->seglist_lock); + for_each_set_bit(segno, dirty_i->dirty_segmap[DIRTY], MAIN_SEGS(sbi)) { + if (get_valid_blocks(sbi, segno, false)) + continue; + if (IS_CURSEG(sbi, segno)) + continue; + __locate_dirty_segment(sbi, segno, PRE); + __remove_dirty_segment(sbi, segno, DIRTY); + } + mutex_unlock(&dirty_i->seglist_lock); +} + +block_t f2fs_get_unusable_blocks(struct f2fs_sb_info *sbi) +{ + int ovp_hole_segs = + (overprovision_segments(sbi) - reserved_segments(sbi)); + block_t ovp_holes = ovp_hole_segs << sbi->log_blocks_per_seg; + struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); + block_t holes[2] = {0, 0}; /* DATA and NODE */ + block_t unusable; + struct seg_entry *se; + unsigned int segno; + + mutex_lock(&dirty_i->seglist_lock); + for_each_set_bit(segno, dirty_i->dirty_segmap[DIRTY], MAIN_SEGS(sbi)) { + se = get_seg_entry(sbi, segno); + if (IS_NODESEG(se->type)) + holes[NODE] += sbi->blocks_per_seg - se->valid_blocks; + else + holes[DATA] += sbi->blocks_per_seg - se->valid_blocks; + } + mutex_unlock(&dirty_i->seglist_lock); + + unusable = holes[DATA] > holes[NODE] ? holes[DATA] : holes[NODE]; + if (unusable > ovp_holes) + return unusable - ovp_holes; + return 0; +} + +int f2fs_disable_cp_again(struct f2fs_sb_info *sbi, block_t unusable) +{ + int ovp_hole_segs = + (overprovision_segments(sbi) - reserved_segments(sbi)); + if (unusable > F2FS_OPTION(sbi).unusable_cap) + return -EAGAIN; + if (is_sbi_flag_set(sbi, SBI_CP_DISABLED_QUICK) && + dirty_segments(sbi) > ovp_hole_segs) + return -EAGAIN; + return 0; +} + +/* This is only used by SBI_CP_DISABLED */ +static unsigned int get_free_segment(struct f2fs_sb_info *sbi) +{ + struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); + unsigned int segno = 0; + + mutex_lock(&dirty_i->seglist_lock); + for_each_set_bit(segno, dirty_i->dirty_segmap[DIRTY], MAIN_SEGS(sbi)) { + if (get_valid_blocks(sbi, segno, false)) + continue; + if (get_ckpt_valid_blocks(sbi, segno)) + continue; + mutex_unlock(&dirty_i->seglist_lock); + return segno; + } + mutex_unlock(&dirty_i->seglist_lock); + return NULL_SEGNO; +} + static struct discard_cmd *__create_discard_cmd(struct f2fs_sb_info *sbi, struct block_device *bdev, block_t lstart, block_t start, block_t len) @@ -756,9 +951,12 @@ static struct discard_cmd *__create_discard_cmd(struct f2fs_sb_info *sbi, dc->len = len; dc->ref = 0; dc->state = D_PREP; + dc->queued = 0; dc->error = 0; init_completion(&dc->wait); list_add_tail(&dc->list, pend_list); + spin_lock_init(&dc->lock); + dc->bio_ref = 0; atomic_inc(&dcc->discard_cmd_cnt); dcc->undiscard_blks += len; @@ -768,7 +966,8 @@ static struct discard_cmd *__create_discard_cmd(struct f2fs_sb_info *sbi, static struct discard_cmd *__attach_discard_cmd(struct f2fs_sb_info *sbi, struct block_device *bdev, block_t lstart, block_t start, block_t len, - struct rb_node *parent, struct rb_node **p) + struct rb_node *parent, struct rb_node **p, + bool leftmost) { struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info; struct discard_cmd *dc; @@ -776,7 +975,7 @@ static struct discard_cmd *__attach_discard_cmd(struct f2fs_sb_info *sbi, dc = __create_discard_cmd(sbi, bdev, lstart, start, len); rb_link_node(&dc->rb_node, parent, p); - rb_insert_color(&dc->rb_node, &dcc->root); + rb_insert_color_cached(&dc->rb_node, &dcc->root, leftmost); return dc; } @@ -785,10 +984,10 @@ static void __detach_discard_cmd(struct discard_cmd_control *dcc, struct discard_cmd *dc) { if (dc->state == D_DONE) - atomic_dec(&dcc->issing_discard); + atomic_sub(dc->queued, &dcc->queued_discard); list_del(&dc->list); - rb_erase(&dc->rb_node, &dcc->root); + rb_erase_cached(&dc->rb_node, &dcc->root); dcc->undiscard_blks -= dc->len; kmem_cache_free(discard_cmd_slab, dc); @@ -800,6 +999,16 @@ static void __remove_discard_cmd(struct f2fs_sb_info *sbi, struct discard_cmd *dc) { struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info; + unsigned long flags; + + trace_f2fs_remove_discard(dc->bdev, dc->start, dc->len); + + spin_lock_irqsave(&dc->lock, flags); + if (dc->bio_ref) { + spin_unlock_irqrestore(&dc->lock, flags); + return; + } + spin_unlock_irqrestore(&dc->lock, flags); f2fs_bug_on(sbi, dc->ref); @@ -807,8 +1016,9 @@ static void __remove_discard_cmd(struct f2fs_sb_info *sbi, dc->error = 0; if (dc->error) - f2fs_msg(sbi->sb, KERN_INFO, - "Issue discard(%u, %u, %u) failed, ret: %d", + printk_ratelimited( + "%sF2FS-fs (%s): Issue discard(%u, %u, %u) failed, ret: %d", + KERN_INFO, sbi->sb->s_id, dc->lstart, dc->start, dc->len, dc->error); __detach_discard_cmd(dcc, dc); } @@ -816,14 +1026,21 @@ static void __remove_discard_cmd(struct f2fs_sb_info *sbi, static void f2fs_submit_discard_endio(struct bio *bio) { struct discard_cmd *dc = (struct discard_cmd *)bio->bi_private; + unsigned long flags; dc->error = blk_status_to_errno(bio->bi_status); - dc->state = D_DONE; - complete_all(&dc->wait); + + spin_lock_irqsave(&dc->lock, flags); + dc->bio_ref--; + if (!dc->bio_ref && dc->state == D_SUBMIT) { + dc->state = D_DONE; + complete_all(&dc->wait); + } + spin_unlock_irqrestore(&dc->lock, flags); bio_put(bio); } -void __check_sit_bitmap(struct f2fs_sb_info *sbi, +static void __check_sit_bitmap(struct f2fs_sb_info *sbi, block_t start, block_t end) { #ifdef CONFIG_F2FS_CHECK_FS @@ -850,40 +1067,155 @@ void __check_sit_bitmap(struct f2fs_sb_info *sbi, #endif } +static void __init_discard_policy(struct f2fs_sb_info *sbi, + struct discard_policy *dpolicy, + int discard_type, unsigned int granularity) +{ + /* common policy */ + dpolicy->type = discard_type; + dpolicy->sync = true; + dpolicy->ordered = false; + dpolicy->granularity = granularity; + + dpolicy->max_requests = DEF_MAX_DISCARD_REQUEST; + dpolicy->io_aware_gran = MAX_PLIST_NUM; + dpolicy->timeout = 0; + + if (discard_type == DPOLICY_BG) { + dpolicy->min_interval = DEF_MIN_DISCARD_ISSUE_TIME; + dpolicy->mid_interval = DEF_MID_DISCARD_ISSUE_TIME; + dpolicy->max_interval = DEF_MAX_DISCARD_ISSUE_TIME; + dpolicy->io_aware = true; + dpolicy->sync = false; + dpolicy->ordered = true; + if (utilization(sbi) > DEF_DISCARD_URGENT_UTIL) { + dpolicy->granularity = 1; + dpolicy->max_interval = DEF_MIN_DISCARD_ISSUE_TIME; + } + } else if (discard_type == DPOLICY_FORCE) { + dpolicy->min_interval = DEF_MIN_DISCARD_ISSUE_TIME; + dpolicy->mid_interval = DEF_MID_DISCARD_ISSUE_TIME; + dpolicy->max_interval = DEF_MAX_DISCARD_ISSUE_TIME; + dpolicy->io_aware = false; + } else if (discard_type == DPOLICY_FSTRIM) { + dpolicy->io_aware = false; + } else if (discard_type == DPOLICY_UMOUNT) { + dpolicy->max_requests = UINT_MAX; + dpolicy->io_aware = false; + /* we need to issue all to keep CP_TRIMMED_FLAG */ + dpolicy->granularity = 1; + } +} + +static void __update_discard_tree_range(struct f2fs_sb_info *sbi, + struct block_device *bdev, block_t lstart, + block_t start, block_t len); /* this function is copied from blkdev_issue_discard from block/blk-lib.c */ -static void __submit_discard_cmd(struct f2fs_sb_info *sbi, - struct discard_cmd *dc) -{ +static int __submit_discard_cmd(struct f2fs_sb_info *sbi, + struct discard_policy *dpolicy, + struct discard_cmd *dc, + unsigned int *issued) +{ + struct block_device *bdev = dc->bdev; + struct request_queue *q = bdev_get_queue(bdev); + unsigned int max_discard_blocks = + SECTOR_TO_BLOCK(q->limits.max_discard_sectors); struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info; - struct bio *bio = NULL; + struct list_head *wait_list = (dpolicy->type == DPOLICY_FSTRIM) ? + &(dcc->fstrim_list) : &(dcc->wait_list); + int flag = dpolicy->sync ? REQ_SYNC : 0; + block_t lstart, start, len, total_len; + int err = 0; if (dc->state != D_PREP) - return; + return 0; - trace_f2fs_issue_discard(dc->bdev, dc->start, dc->len); + if (is_sbi_flag_set(sbi, SBI_NEED_FSCK)) + return 0; - dc->error = __blkdev_issue_discard(dc->bdev, - SECTOR_FROM_BLOCK(dc->start), - SECTOR_FROM_BLOCK(dc->len), - GFP_NOFS, 0, &bio); - if (!dc->error) { - /* should keep before submission to avoid D_DONE right away */ - dc->state = D_SUBMIT; - atomic_inc(&dcc->issued_discard); - atomic_inc(&dcc->issing_discard); - if (bio) { - bio->bi_private = dc; - bio->bi_end_io = f2fs_submit_discard_endio; - bio->bi_opf |= REQ_SYNC; - submit_bio(bio); - list_move_tail(&dc->list, &dcc->wait_list); - __check_sit_bitmap(sbi, dc->start, dc->start + dc->len); + trace_f2fs_issue_discard(bdev, dc->start, dc->len); - f2fs_update_iostat(sbi, FS_DISCARD, 1); + lstart = dc->lstart; + start = dc->start; + len = dc->len; + total_len = len; + + dc->len = 0; + + while (total_len && *issued < dpolicy->max_requests && !err) { + struct bio *bio = NULL; + unsigned long flags; + bool last = true; + + if (len > max_discard_blocks) { + len = max_discard_blocks; + last = false; } - } else { - __remove_discard_cmd(sbi, dc); + + (*issued)++; + if (*issued == dpolicy->max_requests) + last = true; + + dc->len += len; + + if (time_to_inject(sbi, FAULT_DISCARD)) { + f2fs_show_injection_info(sbi, FAULT_DISCARD); + err = -EIO; + goto submit; + } + err = __blkdev_issue_discard(bdev, + SECTOR_FROM_BLOCK(start), + SECTOR_FROM_BLOCK(len), + GFP_NOFS, 0, &bio); +submit: + if (err) { + spin_lock_irqsave(&dc->lock, flags); + if (dc->state == D_PARTIAL) + dc->state = D_SUBMIT; + spin_unlock_irqrestore(&dc->lock, flags); + + break; + } + + f2fs_bug_on(sbi, !bio); + + /* + * should keep before submission to avoid D_DONE + * right away + */ + spin_lock_irqsave(&dc->lock, flags); + if (last) + dc->state = D_SUBMIT; + else + dc->state = D_PARTIAL; + dc->bio_ref++; + spin_unlock_irqrestore(&dc->lock, flags); + + atomic_inc(&dcc->queued_discard); + dc->queued++; + list_move_tail(&dc->list, wait_list); + + /* sanity check on discard range */ + __check_sit_bitmap(sbi, lstart, lstart + len); + + bio->bi_private = dc; + bio->bi_end_io = f2fs_submit_discard_endio; + bio->bi_opf |= flag; + submit_bio(bio); + + atomic_inc(&dcc->issued_discard); + + f2fs_update_iostat(sbi, FS_DISCARD, 1); + + lstart += len; + start += len; + total_len -= len; + len = total_len; } + + if (!err && len) + __update_discard_tree_range(sbi, bdev, lstart, start, len); + return err; } static struct discard_cmd *__insert_discard_tree(struct f2fs_sb_info *sbi, @@ -893,9 +1225,10 @@ static struct discard_cmd *__insert_discard_tree(struct f2fs_sb_info *sbi, struct rb_node *insert_parent) { struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info; - struct rb_node **p = &dcc->root.rb_node; + struct rb_node **p; struct rb_node *parent = NULL; struct discard_cmd *dc = NULL; + bool leftmost = true; if (insert_p && insert_parent) { parent = insert_parent; @@ -903,9 +1236,11 @@ static struct discard_cmd *__insert_discard_tree(struct f2fs_sb_info *sbi, goto do_insert; } - p = __lookup_rb_tree_for_insert(sbi, &dcc->root, &parent, lstart); + p = f2fs_lookup_rb_tree_for_insert(sbi, &dcc->root, &parent, + lstart, &leftmost); do_insert: - dc = __attach_discard_cmd(sbi, bdev, lstart, start, len, parent, p); + dc = __attach_discard_cmd(sbi, bdev, lstart, start, len, parent, + p, leftmost); if (!dc) return NULL; @@ -964,15 +1299,16 @@ static void __update_discard_tree_range(struct f2fs_sb_info *sbi, struct discard_cmd *dc; struct discard_info di = {0}; struct rb_node **insert_p = NULL, *insert_parent = NULL; + struct request_queue *q = bdev_get_queue(bdev); + unsigned int max_discard_blocks = + SECTOR_TO_BLOCK(q->limits.max_discard_sectors); block_t end = lstart + len; - mutex_lock(&dcc->cmd_lock); - - dc = (struct discard_cmd *)__lookup_rb_tree_ret(&dcc->root, + dc = (struct discard_cmd *)f2fs_lookup_rb_tree_ret(&dcc->root, NULL, lstart, (struct rb_entry **)&prev_dc, (struct rb_entry **)&next_dc, - &insert_p, &insert_parent, true); + &insert_p, &insert_parent, true, NULL); if (dc) prev_dc = dc; @@ -1007,7 +1343,8 @@ static void __update_discard_tree_range(struct f2fs_sb_info *sbi, if (prev_dc && prev_dc->state == D_PREP && prev_dc->bdev == bdev && - __is_discard_back_mergeable(&di, &prev_dc->di)) { + __is_discard_back_mergeable(&di, &prev_dc->di, + max_discard_blocks)) { prev_dc->di.len += di.len; dcc->undiscard_blks += di.len; __relocate_discard_cmd(dcc, prev_dc); @@ -1018,7 +1355,8 @@ static void __update_discard_tree_range(struct f2fs_sb_info *sbi, if (next_dc && next_dc->state == D_PREP && next_dc->bdev == bdev && - __is_discard_front_mergeable(&di, &next_dc->di)) { + __is_discard_front_mergeable(&di, &next_dc->di, + max_discard_blocks)) { next_dc->di.lstart = di.lstart; next_dc->di.len += di.len; next_dc->di.start = di.start; @@ -1041,8 +1379,6 @@ static void __update_discard_tree_range(struct f2fs_sb_info *sbi, node = rb_next(&prev_dc->rb_node); next_dc = rb_entry_safe(node, struct discard_cmd, rb_node); } - - mutex_unlock(&dcc->cmd_lock); } static int __queue_discard_cmd(struct f2fs_sb_info *sbi, @@ -1050,6 +1386,9 @@ static int __queue_discard_cmd(struct f2fs_sb_info *sbi, { block_t lblkstart = blkstart; + if (!f2fs_bdev_support_discard(bdev)) + return 0; + trace_f2fs_queue_discard(bdev, blkstart, blklen); if (f2fs_is_multi_device(sbi)) { @@ -1057,62 +1396,130 @@ static int __queue_discard_cmd(struct f2fs_sb_info *sbi, blkstart -= FDEV(devi).start_blk; } + mutex_lock(&SM_I(sbi)->dcc_info->cmd_lock); __update_discard_tree_range(sbi, bdev, lblkstart, blkstart, blklen); + mutex_unlock(&SM_I(sbi)->dcc_info->cmd_lock); return 0; } -static int __issue_discard_cmd(struct f2fs_sb_info *sbi, bool issue_cond) +static unsigned int __issue_discard_cmd_orderly(struct f2fs_sb_info *sbi, + struct discard_policy *dpolicy) { struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info; - struct list_head *pend_list; - struct discard_cmd *dc, *tmp; + struct discard_cmd *prev_dc = NULL, *next_dc = NULL; + struct rb_node **insert_p = NULL, *insert_parent = NULL; + struct discard_cmd *dc; struct blk_plug plug; - int iter = 0, issued = 0; - int i; + unsigned int pos = dcc->next_pos; + unsigned int issued = 0; bool io_interrupted = false; mutex_lock(&dcc->cmd_lock); - f2fs_bug_on(sbi, - !__check_rb_tree_consistence(sbi, &dcc->root)); + dc = (struct discard_cmd *)f2fs_lookup_rb_tree_ret(&dcc->root, + NULL, pos, + (struct rb_entry **)&prev_dc, + (struct rb_entry **)&next_dc, + &insert_p, &insert_parent, true, NULL); + if (!dc) + dc = next_dc; + blk_start_plug(&plug); - for (i = MAX_PLIST_NUM - 1; - i >= 0 && plist_issue(dcc->pend_list_tag[i]); i--) { + + while (dc) { + struct rb_node *node; + int err = 0; + + if (dc->state != D_PREP) + goto next; + + if (dpolicy->io_aware && !is_idle(sbi, DISCARD_TIME)) { + io_interrupted = true; + break; + } + + dcc->next_pos = dc->lstart + dc->len; + err = __submit_discard_cmd(sbi, dpolicy, dc, &issued); + + if (issued >= dpolicy->max_requests) + break; +next: + node = rb_next(&dc->rb_node); + if (err) + __remove_discard_cmd(sbi, dc); + dc = rb_entry_safe(node, struct discard_cmd, rb_node); + } + + blk_finish_plug(&plug); + + if (!dc) + dcc->next_pos = 0; + + mutex_unlock(&dcc->cmd_lock); + + if (!issued && io_interrupted) + issued = -1; + + return issued; +} + +static int __issue_discard_cmd(struct f2fs_sb_info *sbi, + struct discard_policy *dpolicy) +{ + struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info; + struct list_head *pend_list; + struct discard_cmd *dc, *tmp; + struct blk_plug plug; + int i, issued = 0; + bool io_interrupted = false; + + if (dpolicy->timeout != 0) + f2fs_update_time(sbi, dpolicy->timeout); + + for (i = MAX_PLIST_NUM - 1; i >= 0; i--) { + if (dpolicy->timeout != 0 && + f2fs_time_over(sbi, dpolicy->timeout)) + break; + + if (i + 1 < dpolicy->granularity) + break; + + if (i < DEFAULT_DISCARD_GRANULARITY && dpolicy->ordered) + return __issue_discard_cmd_orderly(sbi, dpolicy); + pend_list = &dcc->pend_list[i]; + + mutex_lock(&dcc->cmd_lock); + if (list_empty(pend_list)) + goto next; + if (unlikely(dcc->rbtree_check)) + f2fs_bug_on(sbi, !f2fs_check_rb_tree_consistence(sbi, + &dcc->root)); + blk_start_plug(&plug); list_for_each_entry_safe(dc, tmp, pend_list, list) { f2fs_bug_on(sbi, dc->state != D_PREP); - /* Hurry up to finish fstrim */ - if (dcc->pend_list_tag[i] & P_TRIM) { - __submit_discard_cmd(sbi, dc); - issued++; - - if (fatal_signal_pending(current)) - break; - continue; - } - - if (!issue_cond) { - __submit_discard_cmd(sbi, dc); - issued++; - continue; - } + if (dpolicy->timeout != 0 && + f2fs_time_over(sbi, dpolicy->timeout)) + break; - if (is_idle(sbi)) { - __submit_discard_cmd(sbi, dc); - issued++; - } else { + if (dpolicy->io_aware && i < dpolicy->io_aware_gran && + !is_idle(sbi, DISCARD_TIME)) { io_interrupted = true; + break; } - if (++iter >= DISCARD_ISSUE_RATE) - goto out; + __submit_discard_cmd(sbi, dpolicy, dc, &issued); + + if (issued >= dpolicy->max_requests) + break; } - if (list_empty(pend_list) && dcc->pend_list_tag[i] & P_TRIM) - dcc->pend_list_tag[i] &= (~P_TRIM); + blk_finish_plug(&plug); +next: + mutex_unlock(&dcc->cmd_lock); + + if (issued >= dpolicy->max_requests || io_interrupted) + break; } -out: - blk_finish_plug(&plug); - mutex_unlock(&dcc->cmd_lock); if (!issued && io_interrupted) issued = -1; @@ -1120,12 +1527,13 @@ out: return issued; } -static void __drop_discard_cmd(struct f2fs_sb_info *sbi) +static bool __drop_discard_cmd(struct f2fs_sb_info *sbi) { struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info; struct list_head *pend_list; struct discard_cmd *dc, *tmp; int i; + bool dropped = false; mutex_lock(&dcc->cmd_lock); for (i = MAX_PLIST_NUM - 1; i >= 0; i--) { @@ -1133,39 +1541,63 @@ static void __drop_discard_cmd(struct f2fs_sb_info *sbi) list_for_each_entry_safe(dc, tmp, pend_list, list) { f2fs_bug_on(sbi, dc->state != D_PREP); __remove_discard_cmd(sbi, dc); + dropped = true; } } mutex_unlock(&dcc->cmd_lock); + + return dropped; +} + +void f2fs_drop_discard_cmd(struct f2fs_sb_info *sbi) +{ + __drop_discard_cmd(sbi); } -static void __wait_one_discard_bio(struct f2fs_sb_info *sbi, +static unsigned int __wait_one_discard_bio(struct f2fs_sb_info *sbi, struct discard_cmd *dc) { struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info; + unsigned int len = 0; wait_for_completion_io(&dc->wait); mutex_lock(&dcc->cmd_lock); f2fs_bug_on(sbi, dc->state != D_DONE); dc->ref--; - if (!dc->ref) + if (!dc->ref) { + if (!dc->error) + len = dc->len; __remove_discard_cmd(sbi, dc); + } mutex_unlock(&dcc->cmd_lock); + + return len; } -static void __wait_discard_cmd(struct f2fs_sb_info *sbi, bool wait_cond) +static unsigned int __wait_discard_cmd_range(struct f2fs_sb_info *sbi, + struct discard_policy *dpolicy, + block_t start, block_t end) { struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info; - struct list_head *wait_list = &(dcc->wait_list); + struct list_head *wait_list = (dpolicy->type == DPOLICY_FSTRIM) ? + &(dcc->fstrim_list) : &(dcc->wait_list); struct discard_cmd *dc, *tmp; bool need_wait; + unsigned int trimmed = 0; next: need_wait = false; mutex_lock(&dcc->cmd_lock); list_for_each_entry_safe(dc, tmp, wait_list, list) { - if (!wait_cond || (dc->state == D_DONE && !dc->ref)) { + if (dc->lstart + dc->len <= start || end <= dc->lstart) + continue; + if (dc->len < dpolicy->granularity) + continue; + if (dc->state == D_DONE && !dc->ref) { wait_for_completion_io(&dc->wait); + if (!dc->error) + trimmed += dc->len; __remove_discard_cmd(sbi, dc); } else { dc->ref++; @@ -1176,20 +1608,41 @@ next: mutex_unlock(&dcc->cmd_lock); if (need_wait) { - __wait_one_discard_bio(sbi, dc); + trimmed += __wait_one_discard_bio(sbi, dc); goto next; } + + return trimmed; +} + +static unsigned int __wait_all_discard_cmd(struct f2fs_sb_info *sbi, + struct discard_policy *dpolicy) +{ + struct discard_policy dp; + unsigned int discard_blks; + + if (dpolicy) + return __wait_discard_cmd_range(sbi, dpolicy, 0, UINT_MAX); + + /* wait all */ + __init_discard_policy(sbi, &dp, DPOLICY_FSTRIM, 1); + discard_blks = __wait_discard_cmd_range(sbi, &dp, 0, UINT_MAX); + __init_discard_policy(sbi, &dp, DPOLICY_UMOUNT, 1); + discard_blks += __wait_discard_cmd_range(sbi, &dp, 0, UINT_MAX); + + return discard_blks; } /* This should be covered by global mutex, &sit_i->sentry_lock */ -void f2fs_wait_discard_bio(struct f2fs_sb_info *sbi, block_t blkaddr) +static void f2fs_wait_discard_bio(struct f2fs_sb_info *sbi, block_t blkaddr) { struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info; struct discard_cmd *dc; bool need_wait = false; mutex_lock(&dcc->cmd_lock); - dc = (struct discard_cmd *)__lookup_rb_tree(&dcc->root, NULL, blkaddr); + dc = (struct discard_cmd *)f2fs_lookup_rb_tree(&dcc->root, + NULL, blkaddr); if (dc) { if (dc->state == D_PREP) { __punch_discard_cmd(sbi, dc, blkaddr); @@ -1204,7 +1657,7 @@ void f2fs_wait_discard_bio(struct f2fs_sb_info *sbi, block_t blkaddr) __wait_one_discard_bio(sbi, dc); } -void stop_discard_thread(struct f2fs_sb_info *sbi) +void f2fs_stop_discard_thread(struct f2fs_sb_info *sbi) { struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info; @@ -1216,23 +1669,24 @@ void stop_discard_thread(struct f2fs_sb_info *sbi) } } -/* This comes from f2fs_put_super and f2fs_trim_fs */ -void f2fs_wait_discard_bios(struct f2fs_sb_info *sbi, bool umount) -{ - __issue_discard_cmd(sbi, false); - __drop_discard_cmd(sbi); - __wait_discard_cmd(sbi, !umount); -} - -static void mark_discard_range_all(struct f2fs_sb_info *sbi) +/* This comes from f2fs_put_super */ +bool f2fs_issue_discard_timeout(struct f2fs_sb_info *sbi) { struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info; - int i; + struct discard_policy dpolicy; + bool dropped; - mutex_lock(&dcc->cmd_lock); - for (i = 0; i < MAX_PLIST_NUM; i++) - dcc->pend_list_tag[i] |= P_TRIM; - mutex_unlock(&dcc->cmd_lock); + __init_discard_policy(sbi, &dpolicy, DPOLICY_UMOUNT, + dcc->discard_granularity); + dpolicy.timeout = UMOUNT_DISCARD_TIMEOUT; + __issue_discard_cmd(sbi, &dpolicy); + dropped = __drop_discard_cmd(sbi); + + /* just to make sure there is no pending discard commands */ + __wait_all_discard_cmd(sbi, NULL); + + f2fs_bug_on(sbi, atomic_read(&dcc->discard_cmd_cnt)); + return dropped; } static int issue_discard_thread(void *data) @@ -1240,35 +1694,54 @@ static int issue_discard_thread(void *data) struct f2fs_sb_info *sbi = data; struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info; wait_queue_head_t *q = &dcc->discard_wait_queue; + struct discard_policy dpolicy; unsigned int wait_ms = DEF_MIN_DISCARD_ISSUE_TIME; int issued; set_freezable(); do { + __init_discard_policy(sbi, &dpolicy, DPOLICY_BG, + dcc->discard_granularity); + wait_event_interruptible_timeout(*q, kthread_should_stop() || freezing(current) || dcc->discard_wake, msecs_to_jiffies(wait_ms)); + + if (dcc->discard_wake) + dcc->discard_wake = 0; + + /* clean up pending candidates before going to sleep */ + if (atomic_read(&dcc->queued_discard)) + __wait_all_discard_cmd(sbi, NULL); + if (try_to_freeze()) continue; + if (f2fs_readonly(sbi->sb)) + continue; if (kthread_should_stop()) return 0; - - if (dcc->discard_wake) { - dcc->discard_wake = 0; - if (sbi->gc_thread && sbi->gc_thread->gc_urgent) - mark_discard_range_all(sbi); + if (is_sbi_flag_set(sbi, SBI_NEED_FSCK)) { + wait_ms = dpolicy.max_interval; + continue; } + if (sbi->gc_mode == GC_URGENT) + __init_discard_policy(sbi, &dpolicy, DPOLICY_FORCE, 1); + sb_start_intwrite(sbi->sb); - issued = __issue_discard_cmd(sbi, true); - if (issued) { - __wait_discard_cmd(sbi, true); - wait_ms = DEF_MIN_DISCARD_ISSUE_TIME; + issued = __issue_discard_cmd(sbi, &dpolicy); + if (issued > 0) { + __wait_all_discard_cmd(sbi, &dpolicy); + wait_ms = dpolicy.min_interval; + } else if (issued == -1){ + wait_ms = f2fs_time_to_wait(sbi, DISCARD_TIME); + if (!wait_ms) + wait_ms = dpolicy.mid_interval; } else { - wait_ms = DEF_MAX_DISCARD_ISSUE_TIME; + wait_ms = dpolicy.max_interval; } sb_end_intwrite(sbi->sb); @@ -1287,40 +1760,32 @@ static int __f2fs_issue_discard_zone(struct f2fs_sb_info *sbi, if (f2fs_is_multi_device(sbi)) { devi = f2fs_target_device_index(sbi, blkstart); + if (blkstart < FDEV(devi).start_blk || + blkstart > FDEV(devi).end_blk) { + f2fs_err(sbi, "Invalid block %x", blkstart); + return -EIO; + } blkstart -= FDEV(devi).start_blk; } - /* - * We need to know the type of the zone: for conventional zones, - * use regular discard if the drive supports it. For sequential - * zones, reset the zone write pointer. - */ - switch (get_blkz_type(sbi, bdev, blkstart)) { - - case BLK_ZONE_TYPE_CONVENTIONAL: - if (!blk_queue_discard(bdev_get_queue(bdev))) - return 0; - return __queue_discard_cmd(sbi, bdev, lblkstart, blklen); - case BLK_ZONE_TYPE_SEQWRITE_REQ: - case BLK_ZONE_TYPE_SEQWRITE_PREF: + /* For sequential zones, reset the zone write pointer */ + if (f2fs_blkz_is_seq(sbi, devi, blkstart)) { sector = SECTOR_FROM_BLOCK(blkstart); nr_sects = SECTOR_FROM_BLOCK(blklen); if (sector & (bdev_zone_sectors(bdev) - 1) || nr_sects != bdev_zone_sectors(bdev)) { - f2fs_msg(sbi->sb, KERN_INFO, - "(%d) %s: Unaligned discard attempted (block %x + %x)", - devi, sbi->s_ndevs ? FDEV(devi).path: "", - blkstart, blklen); + f2fs_err(sbi, "(%d) %s: Unaligned zone reset attempted (block %x + %x)", + devi, sbi->s_ndevs ? FDEV(devi).path : "", + blkstart, blklen); return -EIO; } trace_f2fs_issue_reset_zone(bdev, blkstart); - return blkdev_reset_zones(bdev, sector, - nr_sects, GFP_NOFS); - default: - /* Unknown zone type: broken device ? */ - return -EIO; + return blkdev_reset_zones(bdev, sector, nr_sects, GFP_NOFS); } + + /* For conventional zones, use regular discard if supported */ + return __queue_discard_cmd(sbi, bdev, lblkstart, blklen); } #endif @@ -1328,8 +1793,7 @@ static int __issue_discard_async(struct f2fs_sb_info *sbi, struct block_device *bdev, block_t blkstart, block_t blklen) { #ifdef CONFIG_BLK_DEV_ZONED - if (f2fs_sb_mounted_blkzoned(sbi->sb) && - bdev_zoned_model(bdev) != BLK_ZONED_NONE) + if (f2fs_sb_has_blkzoned(sbi) && bdev_is_zoned(bdev)) return __f2fs_issue_discard_zone(sbi, bdev, blkstart, blklen); #endif return __queue_discard_cmd(sbi, bdev, blkstart, blklen); @@ -1391,11 +1855,11 @@ static bool add_discard_addrs(struct f2fs_sb_info *sbi, struct cp_control *cpc, struct list_head *head = &SM_I(sbi)->dcc_info->entry_list; int i; - if (se->valid_blocks == max_blocks || !f2fs_discard_en(sbi)) + if (se->valid_blocks == max_blocks || !f2fs_hw_support_discard(sbi)) return false; if (!force) { - if (!test_opt(sbi, DISCARD) || !se->valid_blocks || + if (!f2fs_realtime_discard_enable(sbi) || !se->valid_blocks || SM_I(sbi)->dcc_info->nr_discards >= SM_I(sbi)->dcc_info->max_discards) return false; @@ -1435,20 +1899,24 @@ static bool add_discard_addrs(struct f2fs_sb_info *sbi, struct cp_control *cpc, return false; } -void release_discard_addrs(struct f2fs_sb_info *sbi) +static void release_discard_addr(struct discard_entry *entry) +{ + list_del(&entry->list); + kmem_cache_free(discard_entry_slab, entry); +} + +void f2fs_release_discard_addrs(struct f2fs_sb_info *sbi) { struct list_head *head = &(SM_I(sbi)->dcc_info->entry_list); struct discard_entry *entry, *this; /* drop caches */ - list_for_each_entry_safe(entry, this, head, list) { - list_del(&entry->list); - kmem_cache_free(discard_entry_slab, entry); - } + list_for_each_entry_safe(entry, this, head, list) + release_discard_addr(entry); } /* - * Should call clear_prefree_segments after checkpoint is done. + * Should call f2fs_clear_prefree_segments after checkpoint is done. */ static void set_prefree_as_free_segments(struct f2fs_sb_info *sbi) { @@ -1461,7 +1929,8 @@ static void set_prefree_as_free_segments(struct f2fs_sb_info *sbi) mutex_unlock(&dirty_i->seglist_lock); } -void clear_prefree_segments(struct f2fs_sb_info *sbi, struct cp_control *cpc) +void f2fs_clear_prefree_segments(struct f2fs_sb_info *sbi, + struct cp_control *cpc) { struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info; struct list_head *head = &dcc->entry_list; @@ -1471,30 +1940,39 @@ void clear_prefree_segments(struct f2fs_sb_info *sbi, struct cp_control *cpc) unsigned int start = 0, end = -1; unsigned int secno, start_segno; bool force = (cpc->reason & CP_DISCARD); + bool need_align = test_opt(sbi, LFS) && __is_large_section(sbi); mutex_lock(&dirty_i->seglist_lock); while (1) { int i; + + if (need_align && end != -1) + end--; start = find_next_bit(prefree_map, MAIN_SEGS(sbi), end + 1); if (start >= MAIN_SEGS(sbi)) break; end = find_next_zero_bit(prefree_map, MAIN_SEGS(sbi), start + 1); - for (i = start; i < end; i++) - clear_bit(i, prefree_map); + if (need_align) { + start = rounddown(start, sbi->segs_per_sec); + end = roundup(end, sbi->segs_per_sec); + } - dirty_i->nr_dirty[PRE] -= end - start; + for (i = start; i < end; i++) { + if (test_and_clear_bit(i, prefree_map)) + dirty_i->nr_dirty[PRE]--; + } - if (!test_opt(sbi, DISCARD)) + if (!f2fs_realtime_discard_enable(sbi)) continue; if (force && start >= cpc->trim_start && (end - 1) <= cpc->trim_end) continue; - if (!test_opt(sbi, LFS) || sbi->segs_per_sec == 1) { + if (!test_opt(sbi, LFS) || !__is_large_section(sbi)) { f2fs_issue_discard(sbi, START_BLOCK(sbi, start), (end - start) << sbi->log_blocks_per_seg); continue; @@ -1526,13 +2004,12 @@ find_next: sbi->blocks_per_seg, cur_pos); len = next_pos - cur_pos; - if (f2fs_sb_mounted_blkzoned(sbi->sb) || + if (f2fs_sb_has_blkzoned(sbi) || (force && len < cpc->trim_minlen)) goto skip; f2fs_issue_discard(sbi, entry->start_blkaddr + cur_pos, len); - cpc->trimmed += len; total_len += len; } else { next_pos = find_next_bit_le(entry->discard_map, @@ -1545,9 +2022,8 @@ skip: if (cur_pos < sbi->blocks_per_seg) goto find_next; - list_del(&entry->list); + release_discard_addr(entry); dcc->nr_discards -= total_len; - kmem_cache_free(discard_entry_slab, entry); } wake_up_discard_thread(sbi, false); @@ -1564,26 +2040,26 @@ static int create_discard_cmd_control(struct f2fs_sb_info *sbi) goto init_thread; } - dcc = kzalloc(sizeof(struct discard_cmd_control), GFP_KERNEL); + dcc = f2fs_kzalloc(sbi, sizeof(struct discard_cmd_control), GFP_KERNEL); if (!dcc) return -ENOMEM; dcc->discard_granularity = DEFAULT_DISCARD_GRANULARITY; INIT_LIST_HEAD(&dcc->entry_list); - for (i = 0; i < MAX_PLIST_NUM; i++) { + for (i = 0; i < MAX_PLIST_NUM; i++) INIT_LIST_HEAD(&dcc->pend_list[i]); - if (i >= dcc->discard_granularity - 1) - dcc->pend_list_tag[i] |= P_ACTIVE; - } INIT_LIST_HEAD(&dcc->wait_list); + INIT_LIST_HEAD(&dcc->fstrim_list); mutex_init(&dcc->cmd_lock); atomic_set(&dcc->issued_discard, 0); - atomic_set(&dcc->issing_discard, 0); + atomic_set(&dcc->queued_discard, 0); atomic_set(&dcc->discard_cmd_cnt, 0); dcc->nr_discards = 0; dcc->max_discards = MAIN_SEGS(sbi) << sbi->log_blocks_per_seg; dcc->undiscard_blks = 0; - dcc->root = RB_ROOT; + dcc->next_pos = 0; + dcc->root = RB_ROOT_CACHED; + dcc->rbtree_check = false; init_waitqueue_head(&dcc->discard_wait_queue); SM_I(sbi)->dcc_info = dcc; @@ -1592,7 +2068,7 @@ init_thread: "f2fs_discard-%u:%u", MAJOR(dev), MINOR(dev)); if (IS_ERR(dcc->f2fs_issue_discard)) { err = PTR_ERR(dcc->f2fs_issue_discard); - kfree(dcc); + kvfree(dcc); SM_I(sbi)->dcc_info = NULL; return err; } @@ -1607,9 +2083,16 @@ static void destroy_discard_cmd_control(struct f2fs_sb_info *sbi) if (!dcc) return; - stop_discard_thread(sbi); + f2fs_stop_discard_thread(sbi); + + /* + * Recovery can cache discard commands, so in error path of + * fill_super(), it needs to give a chance to handle them. + */ + if (unlikely(atomic_read(&dcc->discard_cmd_cnt))) + f2fs_issue_discard_timeout(sbi); - kfree(dcc); + kvfree(dcc); SM_I(sbi)->dcc_info = NULL; } @@ -1654,8 +2137,9 @@ static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del) (new_vblocks > sbi->blocks_per_seg))); se->valid_blocks = new_vblocks; - se->mtime = get_mtime(sbi); - SIT_I(sbi)->max_mtime = se->mtime; + se->mtime = get_mtime(sbi, false); + if (se->mtime > SIT_I(sbi)->max_mtime) + SIT_I(sbi)->max_mtime = se->mtime; /* Update valid block bitmap */ if (del > 0) { @@ -1664,26 +2148,27 @@ static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del) mir_exist = f2fs_test_and_set_bit(offset, se->cur_valid_map_mir); if (unlikely(exist != mir_exist)) { - f2fs_msg(sbi->sb, KERN_ERR, "Inconsistent error " - "when setting bitmap, blk:%u, old bit:%d", - blkaddr, exist); + f2fs_err(sbi, "Inconsistent error when setting bitmap, blk:%u, old bit:%d", + blkaddr, exist); f2fs_bug_on(sbi, 1); } #endif if (unlikely(exist)) { - f2fs_msg(sbi->sb, KERN_ERR, - "Bitmap was wrongly set, blk:%u", blkaddr); + f2fs_err(sbi, "Bitmap was wrongly set, blk:%u", + blkaddr); f2fs_bug_on(sbi, 1); se->valid_blocks--; del = 0; } - if (f2fs_discard_en(sbi) && - !f2fs_test_and_set_bit(offset, se->discard_map)) + if (!f2fs_test_and_set_bit(offset, se->discard_map)) sbi->discard_blks--; - /* don't overwrite by SSR to keep node chain */ - if (se->type == CURSEG_WARM_NODE) { + /* + * SSR should never reuse block which is checkpointed + * or newly invalidated. + */ + if (!is_sbi_flag_set(sbi, SBI_CP_DISABLED)) { if (!f2fs_test_and_set_bit(offset, se->ckpt_valid_map)) se->ckpt_valid_blocks++; } @@ -1693,22 +2178,32 @@ static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del) mir_exist = f2fs_test_and_clear_bit(offset, se->cur_valid_map_mir); if (unlikely(exist != mir_exist)) { - f2fs_msg(sbi->sb, KERN_ERR, "Inconsistent error " - "when clearing bitmap, blk:%u, old bit:%d", - blkaddr, exist); + f2fs_err(sbi, "Inconsistent error when clearing bitmap, blk:%u, old bit:%d", + blkaddr, exist); f2fs_bug_on(sbi, 1); } #endif if (unlikely(!exist)) { - f2fs_msg(sbi->sb, KERN_ERR, - "Bitmap was wrongly cleared, blk:%u", blkaddr); + f2fs_err(sbi, "Bitmap was wrongly cleared, blk:%u", + blkaddr); f2fs_bug_on(sbi, 1); se->valid_blocks++; del = 0; + } else if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) { + /* + * If checkpoints are off, we must not reuse data that + * was used in the previous checkpoint. If it was used + * before, we must track that to know how much space we + * really have. + */ + if (f2fs_test_bit(offset, se->ckpt_valid_map)) { + spin_lock(&sbi->stat_lock); + sbi->unusable_block_count++; + spin_unlock(&sbi->stat_lock); + } } - if (f2fs_discard_en(sbi) && - f2fs_test_and_clear_bit(offset, se->discard_map)) + if (f2fs_test_and_clear_bit(offset, se->discard_map)) sbi->discard_blks++; } if (!f2fs_test_bit(offset, se->ckpt_valid_map)) @@ -1719,21 +2214,11 @@ static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del) /* update total number of valid blocks to be written in ckpt area */ SIT_I(sbi)->written_valid_blocks += del; - if (sbi->segs_per_sec > 1) + if (__is_large_section(sbi)) get_sec_entry(sbi, segno)->valid_blocks += del; } -void refresh_sit_entry(struct f2fs_sb_info *sbi, block_t old, block_t new) -{ - update_sit_entry(sbi, new, 1); - if (GET_SEGNO(sbi, old) != NULL_SEGNO) - update_sit_entry(sbi, old, -1); - - locate_dirty_segment(sbi, GET_SEGNO(sbi, old)); - locate_dirty_segment(sbi, GET_SEGNO(sbi, new)); -} - -void invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr) +void f2fs_invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr) { unsigned int segno = GET_SEGNO(sbi, addr); struct sit_info *sit_i = SIT_I(sbi); @@ -1742,28 +2227,30 @@ void invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr) if (addr == NEW_ADDR) return; + invalidate_mapping_pages(META_MAPPING(sbi), addr, addr); + /* add it into sit main buffer */ - mutex_lock(&sit_i->sentry_lock); + down_write(&sit_i->sentry_lock); update_sit_entry(sbi, addr, -1); /* add it into dirty seglist */ locate_dirty_segment(sbi, segno); - mutex_unlock(&sit_i->sentry_lock); + up_write(&sit_i->sentry_lock); } -bool is_checkpointed_data(struct f2fs_sb_info *sbi, block_t blkaddr) +bool f2fs_is_checkpointed_data(struct f2fs_sb_info *sbi, block_t blkaddr) { struct sit_info *sit_i = SIT_I(sbi); unsigned int segno, offset; struct seg_entry *se; bool is_cp = false; - if (!is_valid_data_blkaddr(sbi, blkaddr)) + if (!__is_valid_data_blkaddr(blkaddr)) return true; - mutex_lock(&sit_i->sentry_lock); + down_read(&sit_i->sentry_lock); segno = GET_SEGNO(sbi, blkaddr); se = get_seg_entry(sbi, segno); @@ -1772,7 +2259,7 @@ bool is_checkpointed_data(struct f2fs_sb_info *sbi, block_t blkaddr) if (f2fs_test_bit(offset, se->ckpt_valid_map)) is_cp = true; - mutex_unlock(&sit_i->sentry_lock); + up_read(&sit_i->sentry_lock); return is_cp; } @@ -1792,7 +2279,7 @@ static void __add_sum_entry(struct f2fs_sb_info *sbi, int type, /* * Calculate the number of current summary pages for writing */ -int npages_for_summary_flush(struct f2fs_sb_info *sbi, bool for_ra) +int f2fs_npages_for_summary_flush(struct f2fs_sb_info *sbi, bool for_ra) { int valid_sum_count = 0; int i, sum_in_page; @@ -1822,20 +2309,17 @@ int npages_for_summary_flush(struct f2fs_sb_info *sbi, bool for_ra) /* * Caller should put this summary page */ -struct page *get_sum_page(struct f2fs_sb_info *sbi, unsigned int segno) +struct page *f2fs_get_sum_page(struct f2fs_sb_info *sbi, unsigned int segno) { - return get_meta_page(sbi, GET_SUM_BLOCK(sbi, segno)); + return f2fs_get_meta_page_nofail(sbi, GET_SUM_BLOCK(sbi, segno)); } -void update_meta_page(struct f2fs_sb_info *sbi, void *src, block_t blk_addr) +void f2fs_update_meta_page(struct f2fs_sb_info *sbi, + void *src, block_t blk_addr) { - struct page *page = grab_meta_page(sbi, blk_addr); - void *dst = page_address(page); + struct page *page = f2fs_grab_meta_page(sbi, blk_addr); - if (src) - memcpy(dst, src, PAGE_SIZE); - else - memset(dst, 0, PAGE_SIZE); + memcpy(page_address(page), src, PAGE_SIZE); set_page_dirty(page); f2fs_put_page(page, 1); } @@ -1843,18 +2327,19 @@ void update_meta_page(struct f2fs_sb_info *sbi, void *src, block_t blk_addr) static void write_sum_page(struct f2fs_sb_info *sbi, struct f2fs_summary_block *sum_blk, block_t blk_addr) { - update_meta_page(sbi, (void *)sum_blk, blk_addr); + f2fs_update_meta_page(sbi, (void *)sum_blk, blk_addr); } static void write_current_sum_page(struct f2fs_sb_info *sbi, int type, block_t blk_addr) { struct curseg_info *curseg = CURSEG_I(sbi, type); - struct page *page = grab_meta_page(sbi, blk_addr); + struct page *page = f2fs_grab_meta_page(sbi, blk_addr); struct f2fs_summary_block *src = curseg->sum_blk; struct f2fs_summary_block *dst; dst = (struct f2fs_summary_block *)page_address(page); + memset(dst, 0, PAGE_SIZE); mutex_lock(&curseg->curseg_mutex); @@ -1934,7 +2419,6 @@ find_other_zone: } secno = left_start; skip_left: - hint = secno; segno = GET_SEG_FROM_SEC(sbi, secno); zoneno = GET_ZONE_FROM_SEC(sbi, secno); @@ -1996,15 +2480,23 @@ static void reset_curseg(struct f2fs_sb_info *sbi, int type, int modified) static unsigned int __get_next_segno(struct f2fs_sb_info *sbi, int type) { /* if segs_per_sec is large than 1, we need to keep original policy. */ - if (sbi->segs_per_sec != 1) + if (__is_large_section(sbi)) return CURSEG_I(sbi, type)->segno; + if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) + return 0; + if (test_opt(sbi, NOHEAP) && (type == CURSEG_HOT_DATA || IS_NODESEG(type))) return 0; if (SIT_I(sbi)->last_victim[ALLOC_NEXT]) return SIT_I(sbi)->last_victim[ALLOC_NEXT]; + + /* find segments from 0 to reuse freed segments */ + if (F2FS_OPTION(sbi).alloc_mode == ALLOC_MODE_REUSE) + return 0; + return CURSEG_I(sbi, type)->segno; } @@ -2090,7 +2582,8 @@ static void change_curseg(struct f2fs_sb_info *sbi, int type) curseg->alloc_type = SSR; __next_free_blkoff(sbi, curseg, 0); - sum_page = get_sum_page(sbi, new_segno); + sum_page = f2fs_get_sum_page(sbi, new_segno); + f2fs_bug_on(sbi, IS_ERR(sum_page)); sum_node = (struct f2fs_summary_block *)page_address(sum_page); memcpy(curseg->sum_blk, sum_node, SUM_ENTRY_SIZE); f2fs_put_page(sum_page, 1); @@ -2104,7 +2597,7 @@ static int get_ssr_segment(struct f2fs_sb_info *sbi, int type) int i, cnt; bool reversed = false; - /* need_SSR() already forces to do this */ + /* f2fs_need_SSR() already forces to do this */ if (v_ops->get_victim(sbi, &segno, BG_GC, type, SSR)) { curseg->next_segno = segno; return 1; @@ -2137,6 +2630,15 @@ static int get_ssr_segment(struct f2fs_sb_info *sbi, int type) return 1; } } + + /* find valid_blocks=0 in dirty list */ + if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) { + segno = get_free_segment(sbi); + if (segno != NULL_SEGNO) { + curseg->next_segno = segno; + return 1; + } + } return 0; } @@ -2154,9 +2656,10 @@ static void allocate_segment_by_default(struct f2fs_sb_info *sbi, else if (!is_set_ckpt_flags(sbi, CP_CRC_RECOVERY_FLAG) && type == CURSEG_WARM_NODE) new_curseg(sbi, type, false); - else if (curseg->alloc_type == LFS && is_next_segment_free(sbi, type)) + else if (curseg->alloc_type == LFS && is_next_segment_free(sbi, type) && + likely(!is_sbi_flag_set(sbi, SBI_CP_DISABLED))) new_curseg(sbi, type, false); - else if (need_SSR(sbi) && get_ssr_segment(sbi, type)) + else if (f2fs_need_SSR(sbi) && get_ssr_segment(sbi, type)) change_curseg(sbi, type); else new_curseg(sbi, type, false); @@ -2164,98 +2667,226 @@ static void allocate_segment_by_default(struct f2fs_sb_info *sbi, stat_inc_seg_type(sbi, curseg); } -void allocate_new_segments(struct f2fs_sb_info *sbi) +void allocate_segment_for_resize(struct f2fs_sb_info *sbi, int type, + unsigned int start, unsigned int end) +{ + struct curseg_info *curseg = CURSEG_I(sbi, type); + unsigned int segno; + + down_read(&SM_I(sbi)->curseg_lock); + mutex_lock(&curseg->curseg_mutex); + down_write(&SIT_I(sbi)->sentry_lock); + + segno = CURSEG_I(sbi, type)->segno; + if (segno < start || segno > end) + goto unlock; + + if (f2fs_need_SSR(sbi) && get_ssr_segment(sbi, type)) + change_curseg(sbi, type); + else + new_curseg(sbi, type, true); + + stat_inc_seg_type(sbi, curseg); + + locate_dirty_segment(sbi, segno); +unlock: + up_write(&SIT_I(sbi)->sentry_lock); + + if (segno != curseg->segno) + f2fs_notice(sbi, "For resize: curseg of type %d: %u ==> %u", + type, segno, curseg->segno); + + mutex_unlock(&curseg->curseg_mutex); + up_read(&SM_I(sbi)->curseg_lock); +} + +void f2fs_allocate_new_segments(struct f2fs_sb_info *sbi, int type) { struct curseg_info *curseg; unsigned int old_segno; int i; + down_write(&SIT_I(sbi)->sentry_lock); + for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++) { + if (type != NO_CHECK_TYPE && i != type) + continue; + curseg = CURSEG_I(sbi, i); - old_segno = curseg->segno; - SIT_I(sbi)->s_ops->allocate_segment(sbi, i, true); - locate_dirty_segment(sbi, old_segno); + if (type == NO_CHECK_TYPE || curseg->next_blkoff || + get_valid_blocks(sbi, curseg->segno, false) || + get_ckpt_valid_blocks(sbi, curseg->segno)) { + old_segno = curseg->segno; + SIT_I(sbi)->s_ops->allocate_segment(sbi, i, true); + locate_dirty_segment(sbi, old_segno); + } } + + up_write(&SIT_I(sbi)->sentry_lock); } static const struct segment_allocation default_salloc_ops = { .allocate_segment = allocate_segment_by_default, }; -bool exist_trim_candidates(struct f2fs_sb_info *sbi, struct cp_control *cpc) +bool f2fs_exist_trim_candidates(struct f2fs_sb_info *sbi, + struct cp_control *cpc) { __u64 trim_start = cpc->trim_start; bool has_candidate = false; - mutex_lock(&SIT_I(sbi)->sentry_lock); + down_write(&SIT_I(sbi)->sentry_lock); for (; cpc->trim_start <= cpc->trim_end; cpc->trim_start++) { if (add_discard_addrs(sbi, cpc, true)) { has_candidate = true; break; } } - mutex_unlock(&SIT_I(sbi)->sentry_lock); + up_write(&SIT_I(sbi)->sentry_lock); cpc->trim_start = trim_start; return has_candidate; } +static unsigned int __issue_discard_cmd_range(struct f2fs_sb_info *sbi, + struct discard_policy *dpolicy, + unsigned int start, unsigned int end) +{ + struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info; + struct discard_cmd *prev_dc = NULL, *next_dc = NULL; + struct rb_node **insert_p = NULL, *insert_parent = NULL; + struct discard_cmd *dc; + struct blk_plug plug; + int issued; + unsigned int trimmed = 0; + +next: + issued = 0; + + mutex_lock(&dcc->cmd_lock); + if (unlikely(dcc->rbtree_check)) + f2fs_bug_on(sbi, !f2fs_check_rb_tree_consistence(sbi, + &dcc->root)); + + dc = (struct discard_cmd *)f2fs_lookup_rb_tree_ret(&dcc->root, + NULL, start, + (struct rb_entry **)&prev_dc, + (struct rb_entry **)&next_dc, + &insert_p, &insert_parent, true, NULL); + if (!dc) + dc = next_dc; + + blk_start_plug(&plug); + + while (dc && dc->lstart <= end) { + struct rb_node *node; + int err = 0; + + if (dc->len < dpolicy->granularity) + goto skip; + + if (dc->state != D_PREP) { + list_move_tail(&dc->list, &dcc->fstrim_list); + goto skip; + } + + err = __submit_discard_cmd(sbi, dpolicy, dc, &issued); + + if (issued >= dpolicy->max_requests) { + start = dc->lstart + dc->len; + + if (err) + __remove_discard_cmd(sbi, dc); + + blk_finish_plug(&plug); + mutex_unlock(&dcc->cmd_lock); + trimmed += __wait_all_discard_cmd(sbi, NULL); + congestion_wait(BLK_RW_ASYNC, HZ/50); + goto next; + } +skip: + node = rb_next(&dc->rb_node); + if (err) + __remove_discard_cmd(sbi, dc); + dc = rb_entry_safe(node, struct discard_cmd, rb_node); + + if (fatal_signal_pending(current)) + break; + } + + blk_finish_plug(&plug); + mutex_unlock(&dcc->cmd_lock); + + return trimmed; +} + int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range) { __u64 start = F2FS_BYTES_TO_BLK(range->start); __u64 end = start + F2FS_BYTES_TO_BLK(range->len) - 1; unsigned int start_segno, end_segno; + block_t start_block, end_block; struct cp_control cpc; + struct discard_policy dpolicy; + unsigned long long trimmed = 0; int err = 0; + bool need_align = test_opt(sbi, LFS) && __is_large_section(sbi); if (start >= MAX_BLKADDR(sbi) || range->len < sbi->blocksize) return -EINVAL; - cpc.trimmed = 0; - if (end <= MAIN_BLKADDR(sbi)) + if (end < MAIN_BLKADDR(sbi)) goto out; if (is_sbi_flag_set(sbi, SBI_NEED_FSCK)) { - f2fs_msg(sbi->sb, KERN_WARNING, - "Found FS corruption, run fsck to fix."); - err = -EFSCORRUPTED; - goto out; + f2fs_warn(sbi, "Found FS corruption, run fsck to fix."); + return -EFSCORRUPTED; } /* start/end segment number in main_area */ start_segno = (start <= MAIN_BLKADDR(sbi)) ? 0 : GET_SEGNO(sbi, start); end_segno = (end >= MAX_BLKADDR(sbi)) ? MAIN_SEGS(sbi) - 1 : GET_SEGNO(sbi, end); + if (need_align) { + start_segno = rounddown(start_segno, sbi->segs_per_sec); + end_segno = roundup(end_segno + 1, sbi->segs_per_sec) - 1; + } + cpc.reason = CP_DISCARD; cpc.trim_minlen = max_t(__u64, 1, F2FS_BYTES_TO_BLK(range->minlen)); + cpc.trim_start = start_segno; + cpc.trim_end = end_segno; - /* do checkpoint to issue discard commands safely */ - for (; start_segno <= end_segno; start_segno = cpc.trim_end + 1) { - cpc.trim_start = start_segno; + if (sbi->discard_blks == 0) + goto out; - if (sbi->discard_blks == 0) - break; - else if (sbi->discard_blks < BATCHED_TRIM_BLOCKS(sbi)) - cpc.trim_end = end_segno; - else - cpc.trim_end = min_t(unsigned int, - rounddown(start_segno + - BATCHED_TRIM_SEGMENTS(sbi), - sbi->segs_per_sec) - 1, end_segno); + mutex_lock(&sbi->gc_mutex); + err = f2fs_write_checkpoint(sbi, &cpc); + mutex_unlock(&sbi->gc_mutex); + if (err) + goto out; - mutex_lock(&sbi->gc_mutex); - err = write_checkpoint(sbi, &cpc); - mutex_unlock(&sbi->gc_mutex); - if (err) - break; + /* + * We filed discard candidates, but actually we don't need to wait for + * all of them, since they'll be issued in idle time along with runtime + * discard option. User configuration looks like using runtime discard + * or periodic fstrim instead of it. + */ + if (f2fs_realtime_discard_enable(sbi)) + goto out; - schedule(); - } - /* It's time to issue all the filed discards */ - mark_discard_range_all(sbi); - f2fs_wait_discard_bios(sbi, false); + start_block = START_BLOCK(sbi, start_segno); + end_block = START_BLOCK(sbi, end_segno + 1); + + __init_discard_policy(sbi, &dpolicy, DPOLICY_FSTRIM, cpc.trim_minlen); + trimmed = __issue_discard_cmd_range(sbi, &dpolicy, + start_block, end_block); + + trimmed += __wait_discard_cmd_range(sbi, &dpolicy, + start_block, end_block); out: - range->len = F2FS_BLK_TO_BYTES(cpc.trimmed); + if (!err) + range->len = F2FS_BLK_TO_BYTES(trimmed); return err; } @@ -2267,6 +2898,113 @@ static bool __has_curseg_space(struct f2fs_sb_info *sbi, int type) return false; } +int f2fs_rw_hint_to_seg_type(enum rw_hint hint) +{ + switch (hint) { + case WRITE_LIFE_SHORT: + return CURSEG_HOT_DATA; + case WRITE_LIFE_EXTREME: + return CURSEG_COLD_DATA; + default: + return CURSEG_WARM_DATA; + } +} + +/* This returns write hints for each segment type. This hints will be + * passed down to block layer. There are mapping tables which depend on + * the mount option 'whint_mode'. + * + * 1) whint_mode=off. F2FS only passes down WRITE_LIFE_NOT_SET. + * + * 2) whint_mode=user-based. F2FS tries to pass down hints given by users. + * + * User F2FS Block + * ---- ---- ----- + * META WRITE_LIFE_NOT_SET + * HOT_NODE " + * WARM_NODE " + * COLD_NODE " + * ioctl(COLD) COLD_DATA WRITE_LIFE_EXTREME + * extension list " " + * + * -- buffered io + * WRITE_LIFE_EXTREME COLD_DATA WRITE_LIFE_EXTREME + * WRITE_LIFE_SHORT HOT_DATA WRITE_LIFE_SHORT + * WRITE_LIFE_NOT_SET WARM_DATA WRITE_LIFE_NOT_SET + * WRITE_LIFE_NONE " " + * WRITE_LIFE_MEDIUM " " + * WRITE_LIFE_LONG " " + * + * -- direct io + * WRITE_LIFE_EXTREME COLD_DATA WRITE_LIFE_EXTREME + * WRITE_LIFE_SHORT HOT_DATA WRITE_LIFE_SHORT + * WRITE_LIFE_NOT_SET WARM_DATA WRITE_LIFE_NOT_SET + * WRITE_LIFE_NONE " WRITE_LIFE_NONE + * WRITE_LIFE_MEDIUM " WRITE_LIFE_MEDIUM + * WRITE_LIFE_LONG " WRITE_LIFE_LONG + * + * 3) whint_mode=fs-based. F2FS passes down hints with its policy. + * + * User F2FS Block + * ---- ---- ----- + * META WRITE_LIFE_MEDIUM; + * HOT_NODE WRITE_LIFE_NOT_SET + * WARM_NODE " + * COLD_NODE WRITE_LIFE_NONE + * ioctl(COLD) COLD_DATA WRITE_LIFE_EXTREME + * extension list " " + * + * -- buffered io + * WRITE_LIFE_EXTREME COLD_DATA WRITE_LIFE_EXTREME + * WRITE_LIFE_SHORT HOT_DATA WRITE_LIFE_SHORT + * WRITE_LIFE_NOT_SET WARM_DATA WRITE_LIFE_LONG + * WRITE_LIFE_NONE " " + * WRITE_LIFE_MEDIUM " " + * WRITE_LIFE_LONG " " + * + * -- direct io + * WRITE_LIFE_EXTREME COLD_DATA WRITE_LIFE_EXTREME + * WRITE_LIFE_SHORT HOT_DATA WRITE_LIFE_SHORT + * WRITE_LIFE_NOT_SET WARM_DATA WRITE_LIFE_NOT_SET + * WRITE_LIFE_NONE " WRITE_LIFE_NONE + * WRITE_LIFE_MEDIUM " WRITE_LIFE_MEDIUM + * WRITE_LIFE_LONG " WRITE_LIFE_LONG + */ + +enum rw_hint f2fs_io_type_to_rw_hint(struct f2fs_sb_info *sbi, + enum page_type type, enum temp_type temp) +{ + if (F2FS_OPTION(sbi).whint_mode == WHINT_MODE_USER) { + if (type == DATA) { + if (temp == WARM) + return WRITE_LIFE_NOT_SET; + else if (temp == HOT) + return WRITE_LIFE_SHORT; + else if (temp == COLD) + return WRITE_LIFE_EXTREME; + } else { + return WRITE_LIFE_NOT_SET; + } + } else if (F2FS_OPTION(sbi).whint_mode == WHINT_MODE_FS) { + if (type == DATA) { + if (temp == WARM) + return WRITE_LIFE_LONG; + else if (temp == HOT) + return WRITE_LIFE_SHORT; + else if (temp == COLD) + return WRITE_LIFE_EXTREME; + } else if (type == NODE) { + if (temp == WARM || temp == HOT) + return WRITE_LIFE_NOT_SET; + else if (temp == COLD) + return WRITE_LIFE_NONE; + } else if (type == META) { + return WRITE_LIFE_MEDIUM; + } + } + return WRITE_LIFE_NOT_SET; +} + static int __get_segment_type_2(struct f2fs_io_info *fio) { if (fio->type == DATA) @@ -2299,9 +3037,12 @@ static int __get_segment_type_6(struct f2fs_io_info *fio) if (is_cold_data(fio->page) || file_is_cold(inode)) return CURSEG_COLD_DATA; - if (is_inode_flag_set(inode, FI_HOT_DATA)) + if (file_is_hot(inode) || + is_inode_flag_set(inode, FI_HOT_DATA) || + f2fs_is_atomic_file(inode) || + f2fs_is_volatile_file(inode)) return CURSEG_HOT_DATA; - return CURSEG_WARM_DATA; + return f2fs_rw_hint_to_seg_type(inode->i_write_hint); } else { if (IS_DNODE(fio->page)) return is_cold_node(fio->page) ? CURSEG_WARM_NODE : @@ -2314,7 +3055,7 @@ static int __get_segment_type(struct f2fs_io_info *fio) { int type = 0; - switch (fio->sbi->active_logs) { + switch (F2FS_OPTION(fio->sbi).active_logs) { case 2: type = __get_segment_type_2(fio); break; @@ -2337,16 +3078,31 @@ static int __get_segment_type(struct f2fs_io_info *fio) return type; } -void allocate_data_block(struct f2fs_sb_info *sbi, struct page *page, +void f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct page *page, block_t old_blkaddr, block_t *new_blkaddr, struct f2fs_summary *sum, int type, struct f2fs_io_info *fio, bool add_list) { struct sit_info *sit_i = SIT_I(sbi); struct curseg_info *curseg = CURSEG_I(sbi, type); + bool put_pin_sem = false; + + if (type == CURSEG_COLD_DATA) { + /* GC during CURSEG_COLD_DATA_PINNED allocation */ + if (down_read_trylock(&sbi->pin_sem)) { + put_pin_sem = true; + } else { + type = CURSEG_WARM_DATA; + curseg = CURSEG_I(sbi, type); + } + } else if (type == CURSEG_COLD_DATA_PINNED) { + type = CURSEG_COLD_DATA; + } + + down_read(&SM_I(sbi)->curseg_lock); mutex_lock(&curseg->curseg_mutex); - mutex_lock(&sit_i->sentry_lock); + down_write(&sit_i->sentry_lock); *new_blkaddr = NEXT_FREE_BLKADDR(sbi, curseg); @@ -2363,15 +3119,26 @@ void allocate_data_block(struct f2fs_sb_info *sbi, struct page *page, stat_inc_block_count(sbi, curseg); + /* + * SIT information should be updated before segment allocation, + * since SSR needs latest valid block information. + */ + update_sit_entry(sbi, *new_blkaddr, 1); + if (GET_SEGNO(sbi, old_blkaddr) != NULL_SEGNO) + update_sit_entry(sbi, old_blkaddr, -1); + if (!__has_curseg_space(sbi, type)) sit_i->s_ops->allocate_segment(sbi, type, false); + /* - * SIT information should be updated after segment allocation, - * since we need to keep dirty segments precisely under SSR. + * segment dirty status should be updated after segment allocation, + * so we just need to update status only one time after previous + * segment being closed. */ - refresh_sit_entry(sbi, old_blkaddr, *new_blkaddr); + locate_dirty_segment(sbi, GET_SEGNO(sbi, old_blkaddr)); + locate_dirty_segment(sbi, GET_SEGNO(sbi, *new_blkaddr)); - mutex_unlock(&sit_i->sentry_lock); + up_write(&sit_i->sentry_lock); if (page && IS_NODESEG(type)) { fill_node_footer_blkaddr(page, NEXT_FREE_BLKADDR(sbi, curseg)); @@ -2379,6 +3146,9 @@ void allocate_data_block(struct f2fs_sb_info *sbi, struct page *page, f2fs_inode_chksum_set(sbi, page); } + if (F2FS_IO_ALIGNED(sbi)) + fio->retry = false; + if (add_list) { struct f2fs_bio_info *io; @@ -2391,31 +3161,68 @@ void allocate_data_block(struct f2fs_sb_info *sbi, struct page *page, } mutex_unlock(&curseg->curseg_mutex); + + up_read(&SM_I(sbi)->curseg_lock); + + if (put_pin_sem) + up_read(&sbi->pin_sem); +} + +static void update_device_state(struct f2fs_io_info *fio) +{ + struct f2fs_sb_info *sbi = fio->sbi; + unsigned int devidx; + + if (!f2fs_is_multi_device(sbi)) + return; + + devidx = f2fs_target_device_index(sbi, fio->new_blkaddr); + + /* update device state for fsync */ + f2fs_set_dirty_device(sbi, fio->ino, devidx, FLUSH_INO); + + /* update device state for checkpoint */ + if (!f2fs_test_bit(devidx, (char *)&sbi->dirty_device)) { + spin_lock(&sbi->dev_lock); + f2fs_set_bit(devidx, (char *)&sbi->dirty_device); + spin_unlock(&sbi->dev_lock); + } } static void do_write_page(struct f2fs_summary *sum, struct f2fs_io_info *fio) { int type = __get_segment_type(fio); - int err; + bool keep_order = (test_opt(fio->sbi, LFS) && type == CURSEG_COLD_DATA); + if (keep_order) + down_read(&fio->sbi->io_order_lock); reallocate: - allocate_data_block(fio->sbi, fio->page, fio->old_blkaddr, + f2fs_allocate_data_block(fio->sbi, fio->page, fio->old_blkaddr, &fio->new_blkaddr, sum, type, fio, true); + if (GET_SEGNO(fio->sbi, fio->old_blkaddr) != NULL_SEGNO) + invalidate_mapping_pages(META_MAPPING(fio->sbi), + fio->old_blkaddr, fio->old_blkaddr); /* writeout dirty page into bdev */ - err = f2fs_submit_page_write(fio); - if (err == -EAGAIN) { + f2fs_submit_page_write(fio); + if (fio->retry) { fio->old_blkaddr = fio->new_blkaddr; goto reallocate; } + + update_device_state(fio); + + if (keep_order) + up_read(&fio->sbi->io_order_lock); } -void write_meta_page(struct f2fs_sb_info *sbi, struct page *page, +void f2fs_do_write_meta_page(struct f2fs_sb_info *sbi, struct page *page, enum iostat_type io_type) { struct f2fs_io_info fio = { .sbi = sbi, .type = META, + .temp = HOT, .op = REQ_OP_WRITE, .op_flags = REQ_SYNC | REQ_META | REQ_PRIO, .old_blkaddr = page->index, @@ -2429,12 +3236,14 @@ void write_meta_page(struct f2fs_sb_info *sbi, struct page *page, fio.op_flags &= ~REQ_META; set_page_writeback(page); + ClearPageError(page); f2fs_submit_page_write(&fio); + stat_inc_meta_count(sbi, page->index); f2fs_update_iostat(sbi, io_type, F2FS_BLKSIZE); } -void write_node_page(unsigned int nid, struct f2fs_io_info *fio) +void f2fs_do_write_node_page(unsigned int nid, struct f2fs_io_info *fio) { struct f2fs_summary sum; @@ -2444,36 +3253,66 @@ void write_node_page(unsigned int nid, struct f2fs_io_info *fio) f2fs_update_iostat(fio->sbi, fio->io_type, F2FS_BLKSIZE); } -void write_data_page(struct dnode_of_data *dn, struct f2fs_io_info *fio) +void f2fs_outplace_write_data(struct dnode_of_data *dn, + struct f2fs_io_info *fio) { struct f2fs_sb_info *sbi = fio->sbi; struct f2fs_summary sum; - struct node_info ni; f2fs_bug_on(sbi, dn->data_blkaddr == NULL_ADDR); - get_node_info(sbi, dn->nid, &ni); - set_summary(&sum, dn->nid, dn->ofs_in_node, ni.version); + set_summary(&sum, dn->nid, dn->ofs_in_node, fio->version); do_write_page(&sum, fio); f2fs_update_data_blkaddr(dn, fio->new_blkaddr); f2fs_update_iostat(sbi, fio->io_type, F2FS_BLKSIZE); } -int rewrite_data_page(struct f2fs_io_info *fio) +int f2fs_inplace_write_data(struct f2fs_io_info *fio) { int err; + struct f2fs_sb_info *sbi = fio->sbi; + unsigned int segno; fio->new_blkaddr = fio->old_blkaddr; - stat_inc_inplace_blocks(fio->sbi); + /* i/o temperature is needed for passing down write hints */ + __get_segment_type(fio); - err = f2fs_submit_page_bio(fio); + segno = GET_SEGNO(sbi, fio->new_blkaddr); - f2fs_update_iostat(fio->sbi, fio->io_type, F2FS_BLKSIZE); + if (!IS_DATASEG(get_seg_entry(sbi, segno)->type)) { + set_sbi_flag(sbi, SBI_NEED_FSCK); + f2fs_warn(sbi, "%s: incorrect segment(%u) type, run fsck to fix.", + __func__, segno); + return -EFSCORRUPTED; + } + + stat_inc_inplace_blocks(fio->sbi); + + if (fio->bio) + err = f2fs_merge_page_bio(fio); + else + err = f2fs_submit_page_bio(fio); + if (!err) { + update_device_state(fio); + f2fs_update_iostat(fio->sbi, fio->io_type, F2FS_BLKSIZE); + } return err; } -void __f2fs_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, +static inline int __f2fs_get_curseg(struct f2fs_sb_info *sbi, + unsigned int segno) +{ + int i; + + for (i = CURSEG_HOT_DATA; i < NO_CHECK_TYPE; i++) { + if (CURSEG_I(sbi, i)->segno == segno) + break; + } + return i; +} + +void f2fs_do_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, block_t old_blkaddr, block_t new_blkaddr, bool recover_curseg, bool recover_newaddr) { @@ -2488,6 +3327,8 @@ void __f2fs_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, se = get_seg_entry(sbi, segno); type = se->type; + down_write(&SM_I(sbi)->curseg_lock); + if (!recover_curseg) { /* for recovery flow */ if (se->valid_blocks == 0 && !IS_CURSEG(sbi, segno)) { @@ -2497,14 +3338,20 @@ void __f2fs_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, type = CURSEG_WARM_DATA; } } else { - if (!IS_CURSEG(sbi, segno)) + if (IS_CURSEG(sbi, segno)) { + /* se->type is volatile as SSR allocation */ + type = __f2fs_get_curseg(sbi, segno); + f2fs_bug_on(sbi, type == NO_CHECK_TYPE); + } else { type = CURSEG_WARM_DATA; + } } + f2fs_bug_on(sbi, !IS_DATASEG(type)); curseg = CURSEG_I(sbi, type); mutex_lock(&curseg->curseg_mutex); - mutex_lock(&sit_i->sentry_lock); + down_write(&sit_i->sentry_lock); old_cursegno = curseg->segno; old_blkoff = curseg->next_blkoff; @@ -2520,8 +3367,11 @@ void __f2fs_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, if (!recover_curseg || recover_newaddr) update_sit_entry(sbi, new_blkaddr, 1); - if (GET_SEGNO(sbi, old_blkaddr) != NULL_SEGNO) + if (GET_SEGNO(sbi, old_blkaddr) != NULL_SEGNO) { + invalidate_mapping_pages(META_MAPPING(sbi), + old_blkaddr, old_blkaddr); update_sit_entry(sbi, old_blkaddr, -1); + } locate_dirty_segment(sbi, GET_SEGNO(sbi, old_blkaddr)); locate_dirty_segment(sbi, GET_SEGNO(sbi, new_blkaddr)); @@ -2536,8 +3386,9 @@ void __f2fs_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, curseg->next_blkoff = old_blkoff; } - mutex_unlock(&sit_i->sentry_lock); + up_write(&sit_i->sentry_lock); mutex_unlock(&curseg->curseg_mutex); + up_write(&SM_I(sbi)->curseg_lock); } void f2fs_replace_block(struct f2fs_sb_info *sbi, struct dnode_of_data *dn, @@ -2549,41 +3400,58 @@ void f2fs_replace_block(struct f2fs_sb_info *sbi, struct dnode_of_data *dn, set_summary(&sum, dn->nid, dn->ofs_in_node, version); - __f2fs_replace_block(sbi, &sum, old_addr, new_addr, + f2fs_do_replace_block(sbi, &sum, old_addr, new_addr, recover_curseg, recover_newaddr); f2fs_update_data_blkaddr(dn, new_addr); } void f2fs_wait_on_page_writeback(struct page *page, - enum page_type type, bool ordered) + enum page_type type, bool ordered, bool locked) { if (PageWriteback(page)) { struct f2fs_sb_info *sbi = F2FS_P_SB(page); - f2fs_submit_merged_write_cond(sbi, page->mapping->host, - 0, page->index, type); - if (ordered) + /* submit cached LFS IO */ + f2fs_submit_merged_write_cond(sbi, NULL, page, 0, type); + /* sbumit cached IPU IO */ + f2fs_submit_merged_ipu_write(sbi, NULL, page); + if (ordered) { wait_on_page_writeback(page); - else + f2fs_bug_on(sbi, locked && PageWriteback(page)); + } else { wait_for_stable_page(page); + } } } -void f2fs_wait_on_block_writeback(struct f2fs_sb_info *sbi, block_t blkaddr) +void f2fs_wait_on_block_writeback(struct inode *inode, block_t blkaddr) { + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct page *cpage; - if (!is_valid_data_blkaddr(sbi, blkaddr)) + if (!f2fs_post_read_required(inode)) + return; + + if (!__is_valid_data_blkaddr(blkaddr)) return; cpage = find_lock_page(META_MAPPING(sbi), blkaddr); if (cpage) { - f2fs_wait_on_page_writeback(cpage, DATA, true); + f2fs_wait_on_page_writeback(cpage, DATA, true, true); f2fs_put_page(cpage, 1); } } +void f2fs_wait_on_block_writeback_range(struct inode *inode, block_t blkaddr, + block_t len) +{ + block_t i; + + for (i = 0; i < len; i++) + f2fs_wait_on_block_writeback(inode, blkaddr + i); +} + static int read_compacted_summaries(struct f2fs_sb_info *sbi) { struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi); @@ -2595,7 +3463,9 @@ static int read_compacted_summaries(struct f2fs_sb_info *sbi) start = start_sum_block(sbi); - page = get_meta_page(sbi, start++); + page = f2fs_get_meta_page(sbi, start++); + if (IS_ERR(page)) + return PTR_ERR(page); kaddr = (unsigned char *)page_address(page); /* Step 1: restore nat cache */ @@ -2635,7 +3505,9 @@ static int read_compacted_summaries(struct f2fs_sb_info *sbi) f2fs_put_page(page, 1); page = NULL; - page = get_meta_page(sbi, start++); + page = f2fs_get_meta_page(sbi, start++); + if (IS_ERR(page)) + return PTR_ERR(page); kaddr = (unsigned char *)page_address(page); offset = 0; } @@ -2653,6 +3525,7 @@ static int read_normal_summaries(struct f2fs_sb_info *sbi, int type) unsigned short blk_off; unsigned int segno = 0; block_t blk_addr = 0; + int err = 0; /* get segment number and block addr */ if (IS_DATASEG(type)) { @@ -2675,7 +3548,9 @@ static int read_normal_summaries(struct f2fs_sb_info *sbi, int type) blk_addr = GET_SUM_BLOCK(sbi, segno); } - new = get_meta_page(sbi, blk_addr); + new = f2fs_get_meta_page(sbi, blk_addr); + if (IS_ERR(new)) + return PTR_ERR(new); sum = (struct f2fs_summary_block *)page_address(new); if (IS_NODESEG(type)) { @@ -2687,13 +3562,9 @@ static int read_normal_summaries(struct f2fs_sb_info *sbi, int type) ns->ofs_in_node = 0; } } else { - int err; - - err = restore_node_summary(sbi, segno, sum); - if (err) { - f2fs_put_page(new, 1); - return err; - } + err = f2fs_restore_node_summary(sbi, segno, sum); + if (err) + goto out; } } @@ -2713,8 +3584,9 @@ static int read_normal_summaries(struct f2fs_sb_info *sbi, int type) curseg->alloc_type = ckpt->alloc_type[type]; curseg->next_blkoff = blk_off; mutex_unlock(&curseg->curseg_mutex); +out: f2fs_put_page(new, 1); - return 0; + return err; } static int restore_curseg_summaries(struct f2fs_sb_info *sbi) @@ -2725,20 +3597,21 @@ static int restore_curseg_summaries(struct f2fs_sb_info *sbi) int err; if (is_set_ckpt_flags(sbi, CP_COMPACT_SUM_FLAG)) { - int npages = npages_for_summary_flush(sbi, true); + int npages = f2fs_npages_for_summary_flush(sbi, true); if (npages >= 2) - ra_meta_pages(sbi, start_sum_block(sbi), npages, + f2fs_ra_meta_pages(sbi, start_sum_block(sbi), npages, META_CP, true); /* restore for compacted data summary */ - if (read_compacted_summaries(sbi)) - return -EINVAL; + err = read_compacted_summaries(sbi); + if (err) + return err; type = CURSEG_HOT_NODE; } if (__exist_node_summaries(sbi)) - ra_meta_pages(sbi, sum_blk_addr(sbi, NR_CURSEG_TYPE, type), + f2fs_ra_meta_pages(sbi, sum_blk_addr(sbi, NR_CURSEG_TYPE, type), NR_CURSEG_TYPE - type, META_CP, true); for (; type <= CURSEG_COLD_NODE; type++) { @@ -2749,8 +3622,11 @@ static int restore_curseg_summaries(struct f2fs_sb_info *sbi) /* sanity check for summary blocks */ if (nats_in_cursum(nat_j) > NAT_JOURNAL_ENTRIES || - sits_in_cursum(sit_j) > SIT_JOURNAL_ENTRIES) + sits_in_cursum(sit_j) > SIT_JOURNAL_ENTRIES) { + f2fs_err(sbi, "invalid journal entries nats %u sits %u\n", + nats_in_cursum(nat_j), sits_in_cursum(sit_j)); return -EINVAL; + } return 0; } @@ -2764,8 +3640,9 @@ static void write_compacted_summaries(struct f2fs_sb_info *sbi, block_t blkaddr) int written_size = 0; int i, j; - page = grab_meta_page(sbi, blkaddr++); + page = f2fs_grab_meta_page(sbi, blkaddr++); kaddr = (unsigned char *)page_address(page); + memset(kaddr, 0, PAGE_SIZE); /* Step 1: write nat cache */ seg_i = CURSEG_I(sbi, CURSEG_HOT_DATA); @@ -2788,8 +3665,9 @@ static void write_compacted_summaries(struct f2fs_sb_info *sbi, block_t blkaddr) for (j = 0; j < blkoff; j++) { if (!page) { - page = grab_meta_page(sbi, blkaddr++); + page = f2fs_grab_meta_page(sbi, blkaddr++); kaddr = (unsigned char *)page_address(page); + memset(kaddr, 0, PAGE_SIZE); written_size = 0; } summary = (struct f2fs_summary *)(kaddr + written_size); @@ -2824,7 +3702,7 @@ static void write_normal_summaries(struct f2fs_sb_info *sbi, write_current_sum_page(sbi, i, blkaddr + (i - type)); } -void write_data_summaries(struct f2fs_sb_info *sbi, block_t start_blk) +void f2fs_write_data_summaries(struct f2fs_sb_info *sbi, block_t start_blk) { if (is_set_ckpt_flags(sbi, CP_COMPACT_SUM_FLAG)) write_compacted_summaries(sbi, start_blk); @@ -2832,12 +3710,12 @@ void write_data_summaries(struct f2fs_sb_info *sbi, block_t start_blk) write_normal_summaries(sbi, start_blk, CURSEG_HOT_DATA); } -void write_node_summaries(struct f2fs_sb_info *sbi, block_t start_blk) +void f2fs_write_node_summaries(struct f2fs_sb_info *sbi, block_t start_blk) { write_normal_summaries(sbi, start_blk, CURSEG_HOT_NODE); } -int lookup_journal_in_cursum(struct f2fs_journal *journal, int type, +int f2fs_lookup_journal_in_cursum(struct f2fs_journal *journal, int type, unsigned int val, int alloc) { int i; @@ -2862,35 +3740,26 @@ int lookup_journal_in_cursum(struct f2fs_journal *journal, int type, static struct page *get_current_sit_page(struct f2fs_sb_info *sbi, unsigned int segno) { - return get_meta_page(sbi, current_sit_addr(sbi, segno)); + return f2fs_get_meta_page_nofail(sbi, current_sit_addr(sbi, segno)); } static struct page *get_next_sit_page(struct f2fs_sb_info *sbi, unsigned int start) { struct sit_info *sit_i = SIT_I(sbi); - struct page *src_page, *dst_page; + struct page *page; pgoff_t src_off, dst_off; - void *src_addr, *dst_addr; src_off = current_sit_addr(sbi, start); dst_off = next_sit_addr(sbi, src_off); - /* get current sit block page without lock */ - src_page = get_meta_page(sbi, src_off); - dst_page = grab_meta_page(sbi, dst_off); - f2fs_bug_on(sbi, PageDirty(src_page)); - - src_addr = page_address(src_page); - dst_addr = page_address(dst_page); - memcpy(dst_addr, src_addr, PAGE_SIZE); - - set_page_dirty(dst_page); - f2fs_put_page(src_page, 1); + page = f2fs_grab_meta_page(sbi, dst_off); + seg_info_to_sit_page(sbi, page, start); + set_page_dirty(page); set_to_next_sit(sit_i, start); - return dst_page; + return page; } static struct sit_entry_set *grab_sit_entry_set(void) @@ -2980,7 +3849,7 @@ static void remove_sits_in_journal(struct f2fs_sb_info *sbi) * CP calls this function, which flushes SIT entries including sit_journal, * and moves prefree segs to free segs. */ -void flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc) +void f2fs_flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc) { struct sit_info *sit_i = SIT_I(sbi); unsigned long *bitmap = sit_i->dirty_sentries_bitmap; @@ -2988,10 +3857,10 @@ void flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc) struct f2fs_journal *journal = curseg->journal; struct sit_entry_set *ses, *tmp; struct list_head *head = &SM_I(sbi)->sit_entry_set; - bool to_journal = true; + bool to_journal = !is_sbi_flag_set(sbi, SBI_IS_RESIZEFS); struct seg_entry *se; - mutex_lock(&sit_i->sentry_lock); + down_write(&sit_i->sentry_lock); if (!sit_i->dirty_sentries) goto out; @@ -3007,7 +3876,8 @@ void flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc) * entries, remove all entries from journal and add and account * them in sit entry set. */ - if (!__has_cursum_space(journal, sit_i->dirty_sentries, SIT_JOURNAL)) + if (!__has_cursum_space(journal, sit_i->dirty_sentries, SIT_JOURNAL) || + !to_journal) remove_sits_in_journal(sbi); /* @@ -3039,6 +3909,11 @@ void flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc) int offset, sit_offset; se = get_seg_entry(sbi, segno); +#ifdef CONFIG_F2FS_CHECK_FS + if (memcmp(se->cur_valid_map, se->cur_valid_map_mir, + SIT_VBLOCK_MAP_SIZE)) + f2fs_bug_on(sbi, 1); +#endif /* add discard candidates */ if (!(cpc->reason & CP_DISCARD)) { @@ -3047,17 +3922,21 @@ void flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc) } if (to_journal) { - offset = lookup_journal_in_cursum(journal, + offset = f2fs_lookup_journal_in_cursum(journal, SIT_JOURNAL, segno, 1); f2fs_bug_on(sbi, offset < 0); segno_in_journal(journal, offset) = cpu_to_le32(segno); seg_info_to_raw_sit(se, &sit_in_journal(journal, offset)); + check_block_count(sbi, segno, + &sit_in_journal(journal, offset)); } else { sit_offset = SIT_ENTRY_OFFSET(sit_i, segno); seg_info_to_raw_sit(se, &raw_sit->entries[sit_offset]); + check_block_count(sbi, segno, + &raw_sit->entries[sit_offset]); } __clear_bit(segno, bitmap); @@ -3085,7 +3964,7 @@ out: cpc->trim_start = trim_start; } - mutex_unlock(&sit_i->sentry_lock); + up_write(&sit_i->sentry_lock); set_prefree_as_free_segments(sbi); } @@ -3095,57 +3974,65 @@ static int build_sit_info(struct f2fs_sb_info *sbi) struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi); struct sit_info *sit_i; unsigned int sit_segs, start; - char *src_bitmap; - unsigned int bitmap_size; + char *src_bitmap, *bitmap; + unsigned int bitmap_size, main_bitmap_size, sit_bitmap_size; /* allocate memory for SIT information */ - sit_i = kzalloc(sizeof(struct sit_info), GFP_KERNEL); + sit_i = f2fs_kzalloc(sbi, sizeof(struct sit_info), GFP_KERNEL); if (!sit_i) return -ENOMEM; SM_I(sbi)->sit_info = sit_i; - sit_i->sentries = kvzalloc(MAIN_SEGS(sbi) * - sizeof(struct seg_entry), GFP_KERNEL); + sit_i->sentries = + f2fs_kvzalloc(sbi, array_size(sizeof(struct seg_entry), + MAIN_SEGS(sbi)), + GFP_KERNEL); if (!sit_i->sentries) return -ENOMEM; - bitmap_size = f2fs_bitmap_size(MAIN_SEGS(sbi)); - sit_i->dirty_sentries_bitmap = kvzalloc(bitmap_size, GFP_KERNEL); + main_bitmap_size = f2fs_bitmap_size(MAIN_SEGS(sbi)); + sit_i->dirty_sentries_bitmap = f2fs_kvzalloc(sbi, main_bitmap_size, + GFP_KERNEL); if (!sit_i->dirty_sentries_bitmap) return -ENOMEM; +#ifdef CONFIG_F2FS_CHECK_FS + bitmap_size = MAIN_SEGS(sbi) * SIT_VBLOCK_MAP_SIZE * 4; +#else + bitmap_size = MAIN_SEGS(sbi) * SIT_VBLOCK_MAP_SIZE * 3; +#endif + sit_i->bitmap = f2fs_kvzalloc(sbi, bitmap_size, GFP_KERNEL); + if (!sit_i->bitmap) + return -ENOMEM; + + bitmap = sit_i->bitmap; + for (start = 0; start < MAIN_SEGS(sbi); start++) { - sit_i->sentries[start].cur_valid_map - = kzalloc(SIT_VBLOCK_MAP_SIZE, GFP_KERNEL); - sit_i->sentries[start].ckpt_valid_map - = kzalloc(SIT_VBLOCK_MAP_SIZE, GFP_KERNEL); - if (!sit_i->sentries[start].cur_valid_map || - !sit_i->sentries[start].ckpt_valid_map) - return -ENOMEM; + sit_i->sentries[start].cur_valid_map = bitmap; + bitmap += SIT_VBLOCK_MAP_SIZE; + + sit_i->sentries[start].ckpt_valid_map = bitmap; + bitmap += SIT_VBLOCK_MAP_SIZE; #ifdef CONFIG_F2FS_CHECK_FS - sit_i->sentries[start].cur_valid_map_mir - = kzalloc(SIT_VBLOCK_MAP_SIZE, GFP_KERNEL); - if (!sit_i->sentries[start].cur_valid_map_mir) - return -ENOMEM; + sit_i->sentries[start].cur_valid_map_mir = bitmap; + bitmap += SIT_VBLOCK_MAP_SIZE; #endif - if (f2fs_discard_en(sbi)) { - sit_i->sentries[start].discard_map - = kzalloc(SIT_VBLOCK_MAP_SIZE, GFP_KERNEL); - if (!sit_i->sentries[start].discard_map) - return -ENOMEM; - } + sit_i->sentries[start].discard_map = bitmap; + bitmap += SIT_VBLOCK_MAP_SIZE; } - sit_i->tmp_map = kzalloc(SIT_VBLOCK_MAP_SIZE, GFP_KERNEL); + sit_i->tmp_map = f2fs_kzalloc(sbi, SIT_VBLOCK_MAP_SIZE, GFP_KERNEL); if (!sit_i->tmp_map) return -ENOMEM; - if (sbi->segs_per_sec > 1) { - sit_i->sec_entries = kvzalloc(MAIN_SECS(sbi) * - sizeof(struct sec_entry), GFP_KERNEL); + if (__is_large_section(sbi)) { + sit_i->sec_entries = + f2fs_kvzalloc(sbi, array_size(sizeof(struct sec_entry), + MAIN_SECS(sbi)), + GFP_KERNEL); if (!sit_i->sec_entries) return -ENOMEM; } @@ -3154,17 +4041,23 @@ static int build_sit_info(struct f2fs_sb_info *sbi) sit_segs = le32_to_cpu(raw_super->segment_count_sit) >> 1; /* setup SIT bitmap from ckeckpoint pack */ - bitmap_size = __bitmap_size(sbi, SIT_BITMAP); + sit_bitmap_size = __bitmap_size(sbi, SIT_BITMAP); src_bitmap = __bitmap_ptr(sbi, SIT_BITMAP); - sit_i->sit_bitmap = kmemdup(src_bitmap, bitmap_size, GFP_KERNEL); + sit_i->sit_bitmap = kmemdup(src_bitmap, sit_bitmap_size, GFP_KERNEL); if (!sit_i->sit_bitmap) return -ENOMEM; #ifdef CONFIG_F2FS_CHECK_FS - sit_i->sit_bitmap_mir = kmemdup(src_bitmap, bitmap_size, GFP_KERNEL); + sit_i->sit_bitmap_mir = kmemdup(src_bitmap, + sit_bitmap_size, GFP_KERNEL); if (!sit_i->sit_bitmap_mir) return -ENOMEM; + + sit_i->invalid_segmap = f2fs_kvzalloc(sbi, + main_bitmap_size, GFP_KERNEL); + if (!sit_i->invalid_segmap) + return -ENOMEM; #endif /* init SIT information */ @@ -3173,12 +4066,12 @@ static int build_sit_info(struct f2fs_sb_info *sbi) sit_i->sit_base_addr = le32_to_cpu(raw_super->sit_blkaddr); sit_i->sit_blocks = sit_segs << sbi->log_blocks_per_seg; sit_i->written_valid_blocks = 0; - sit_i->bitmap_size = bitmap_size; + sit_i->bitmap_size = sit_bitmap_size; sit_i->dirty_sentries = 0; sit_i->sents_per_block = SIT_ENTRY_PER_BLOCK; sit_i->elapsed_time = le64_to_cpu(sbi->ckpt->elapsed_time); sit_i->mounted_time = ktime_get_real_seconds(); - mutex_init(&sit_i->sentry_lock); + init_rwsem(&sit_i->sentry_lock); return 0; } @@ -3188,19 +4081,19 @@ static int build_free_segmap(struct f2fs_sb_info *sbi) unsigned int bitmap_size, sec_bitmap_size; /* allocate memory for free segmap information */ - free_i = kzalloc(sizeof(struct free_segmap_info), GFP_KERNEL); + free_i = f2fs_kzalloc(sbi, sizeof(struct free_segmap_info), GFP_KERNEL); if (!free_i) return -ENOMEM; SM_I(sbi)->free_info = free_i; bitmap_size = f2fs_bitmap_size(MAIN_SEGS(sbi)); - free_i->free_segmap = kvmalloc(bitmap_size, GFP_KERNEL); + free_i->free_segmap = f2fs_kvmalloc(sbi, bitmap_size, GFP_KERNEL); if (!free_i->free_segmap) return -ENOMEM; sec_bitmap_size = f2fs_bitmap_size(MAIN_SECS(sbi)); - free_i->free_secmap = kvmalloc(sec_bitmap_size, GFP_KERNEL); + free_i->free_secmap = f2fs_kvmalloc(sbi, sec_bitmap_size, GFP_KERNEL); if (!free_i->free_secmap) return -ENOMEM; @@ -3221,7 +4114,8 @@ static int build_curseg(struct f2fs_sb_info *sbi) struct curseg_info *array; int i; - array = kcalloc(NR_CURSEG_TYPE, sizeof(*array), GFP_KERNEL); + array = f2fs_kzalloc(sbi, array_size(NR_CURSEG_TYPE, sizeof(*array)), + GFP_KERNEL); if (!array) return -ENOMEM; @@ -3229,12 +4123,12 @@ static int build_curseg(struct f2fs_sb_info *sbi) for (i = 0; i < NR_CURSEG_TYPE; i++) { mutex_init(&array[i].curseg_mutex); - array[i].sum_blk = kzalloc(PAGE_SIZE, GFP_KERNEL); + array[i].sum_blk = f2fs_kzalloc(sbi, PAGE_SIZE, GFP_KERNEL); if (!array[i].sum_blk) return -ENOMEM; init_rwsem(&array[i].journal_rwsem); - array[i].journal = kzalloc(sizeof(struct f2fs_journal), - GFP_KERNEL); + array[i].journal = f2fs_kzalloc(sbi, + sizeof(struct f2fs_journal), GFP_KERNEL); if (!array[i].journal) return -ENOMEM; array[i].segno = NULL_SEGNO; @@ -3257,7 +4151,7 @@ static int build_sit_entries(struct f2fs_sb_info *sbi) block_t total_node_blocks = 0; do { - readed = ra_meta_pages(sbi, start_blk, BIO_MAX_PAGES, + readed = f2fs_ra_meta_pages(sbi, start_blk, BIO_MAX_PAGES, META_SIT, true); start = start_blk * sit_i->sents_per_block; @@ -3269,6 +4163,8 @@ static int build_sit_entries(struct f2fs_sb_info *sbi) se = &sit_i->sentries[start]; page = get_current_sit_page(sbi, start); + if (IS_ERR(page)) + return PTR_ERR(page); sit_blk = (struct f2fs_sit_block *)page_address(page); sit = sit_blk->entries[SIT_ENTRY_OFFSET(sit_i, start)]; f2fs_put_page(page, 1); @@ -3281,21 +4177,19 @@ static int build_sit_entries(struct f2fs_sb_info *sbi) total_node_blocks += se->valid_blocks; /* build discard map only one time */ - if (f2fs_discard_en(sbi)) { - if (is_set_ckpt_flags(sbi, CP_TRIMMED_FLAG)) { - memset(se->discard_map, 0xff, - SIT_VBLOCK_MAP_SIZE); - } else { - memcpy(se->discard_map, - se->cur_valid_map, - SIT_VBLOCK_MAP_SIZE); - sbi->discard_blks += - sbi->blocks_per_seg - - se->valid_blocks; - } + if (is_set_ckpt_flags(sbi, CP_TRIMMED_FLAG)) { + memset(se->discard_map, 0xff, + SIT_VBLOCK_MAP_SIZE); + } else { + memcpy(se->discard_map, + se->cur_valid_map, + SIT_VBLOCK_MAP_SIZE); + sbi->discard_blks += + sbi->blocks_per_seg - + se->valid_blocks; } - if (sbi->segs_per_sec > 1) + if (__is_large_section(sbi)) get_sec_entry(sbi, start)->valid_blocks += se->valid_blocks; } @@ -3308,10 +4202,8 @@ static int build_sit_entries(struct f2fs_sb_info *sbi) start = le32_to_cpu(segno_in_journal(journal, i)); if (start >= MAIN_SEGS(sbi)) { - f2fs_msg(sbi->sb, KERN_ERR, - "Wrong journal entry on segno %u", - start); - set_sbi_flag(sbi, SBI_NEED_FSCK); + f2fs_err(sbi, "Wrong journal entry on segno %u", + start); err = -EFSCORRUPTED; break; } @@ -3330,29 +4222,27 @@ static int build_sit_entries(struct f2fs_sb_info *sbi) if (IS_NODESEG(se->type)) total_node_blocks += se->valid_blocks; - if (f2fs_discard_en(sbi)) { - if (is_set_ckpt_flags(sbi, CP_TRIMMED_FLAG)) { - memset(se->discard_map, 0xff, - SIT_VBLOCK_MAP_SIZE); - } else { - memcpy(se->discard_map, se->cur_valid_map, - SIT_VBLOCK_MAP_SIZE); - sbi->discard_blks += old_valid_blocks - - se->valid_blocks; - } + if (is_set_ckpt_flags(sbi, CP_TRIMMED_FLAG)) { + memset(se->discard_map, 0xff, SIT_VBLOCK_MAP_SIZE); + } else { + memcpy(se->discard_map, se->cur_valid_map, + SIT_VBLOCK_MAP_SIZE); + sbi->discard_blks += old_valid_blocks; + sbi->discard_blks -= se->valid_blocks; } - if (sbi->segs_per_sec > 1) + if (__is_large_section(sbi)) { get_sec_entry(sbi, start)->valid_blocks += - se->valid_blocks - old_valid_blocks; + se->valid_blocks; + get_sec_entry(sbi, start)->valid_blocks -= + old_valid_blocks; + } } up_read(&curseg->journal_rwsem); if (!err && total_node_blocks != valid_node_count(sbi)) { - f2fs_msg(sbi->sb, KERN_ERR, - "SIT is corrupted node# %u vs %u", - total_node_blocks, valid_node_count(sbi)); - set_sbi_flag(sbi, SBI_NEED_FSCK); + f2fs_err(sbi, "SIT is corrupted node# %u vs %u", + total_node_blocks, valid_node_count(sbi)); err = -EFSCORRUPTED; } @@ -3411,7 +4301,7 @@ static int init_victim_secmap(struct f2fs_sb_info *sbi) struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); unsigned int bitmap_size = f2fs_bitmap_size(MAIN_SECS(sbi)); - dirty_i->victim_secmap = kvzalloc(bitmap_size, GFP_KERNEL); + dirty_i->victim_secmap = f2fs_kvzalloc(sbi, bitmap_size, GFP_KERNEL); if (!dirty_i->victim_secmap) return -ENOMEM; return 0; @@ -3423,7 +4313,8 @@ static int build_dirty_segmap(struct f2fs_sb_info *sbi) unsigned int bitmap_size, i; /* allocate memory for dirty segments list information */ - dirty_i = kzalloc(sizeof(struct dirty_seglist_info), GFP_KERNEL); + dirty_i = f2fs_kzalloc(sbi, sizeof(struct dirty_seglist_info), + GFP_KERNEL); if (!dirty_i) return -ENOMEM; @@ -3433,7 +4324,8 @@ static int build_dirty_segmap(struct f2fs_sb_info *sbi) bitmap_size = f2fs_bitmap_size(MAIN_SEGS(sbi)); for (i = 0; i < NR_DIRTY_TYPE; i++) { - dirty_i->dirty_segmap[i] = kvzalloc(bitmap_size, GFP_KERNEL); + dirty_i->dirty_segmap[i] = f2fs_kvzalloc(sbi, bitmap_size, + GFP_KERNEL); if (!dirty_i->dirty_segmap[i]) return -ENOMEM; } @@ -3465,12 +4357,10 @@ static int sanity_check_curseg(struct f2fs_sb_info *sbi) if (!f2fs_test_bit(blkofs, se->cur_valid_map)) continue; out: - f2fs_msg(sbi->sb, KERN_ERR, - "Current segment's next free block offset is " - "inconsistent with bitmap, logtype:%u, " - "segno:%u, type:%u, next_blkoff:%u, blkofs:%u", - i, curseg->segno, curseg->alloc_type, - curseg->next_blkoff, blkofs); + f2fs_err(sbi, + "Current segment's next free block offset is inconsistent with bitmap, logtype:%u, segno:%u, type:%u, next_blkoff:%u, blkofs:%u", + i, curseg->segno, curseg->alloc_type, + curseg->next_blkoff, blkofs); return -EFSCORRUPTED; } } @@ -3485,9 +4375,9 @@ static void init_min_max_mtime(struct f2fs_sb_info *sbi) struct sit_info *sit_i = SIT_I(sbi); unsigned int segno; - mutex_lock(&sit_i->sentry_lock); + down_write(&sit_i->sentry_lock); - sit_i->min_mtime = LLONG_MAX; + sit_i->min_mtime = ULLONG_MAX; for (segno = 0; segno < MAIN_SEGS(sbi); segno += sbi->segs_per_sec) { unsigned int i; @@ -3501,18 +4391,18 @@ static void init_min_max_mtime(struct f2fs_sb_info *sbi) if (sit_i->min_mtime > mtime) sit_i->min_mtime = mtime; } - sit_i->max_mtime = get_mtime(sbi); - mutex_unlock(&sit_i->sentry_lock); + sit_i->max_mtime = get_mtime(sbi, false); + up_write(&sit_i->sentry_lock); } -int build_segment_manager(struct f2fs_sb_info *sbi) +int f2fs_build_segment_manager(struct f2fs_sb_info *sbi) { struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi); struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi); struct f2fs_sm_info *sm_info; int err; - sm_info = kzalloc(sizeof(struct f2fs_sm_info), GFP_KERNEL); + sm_info = f2fs_kzalloc(sbi, sizeof(struct f2fs_sm_info), GFP_KERNEL); if (!sm_info) return -ENOMEM; @@ -3534,14 +4424,16 @@ int build_segment_manager(struct f2fs_sb_info *sbi) sm_info->ipu_policy = 1 << F2FS_IPU_FSYNC; sm_info->min_ipu_util = DEF_MIN_IPU_UTIL; sm_info->min_fsync_blocks = DEF_MIN_FSYNC_BLOCKS; + sm_info->min_seq_blocks = sbi->blocks_per_seg * sbi->segs_per_sec; sm_info->min_hot_blocks = DEF_MIN_HOT_BLOCKS; - - sm_info->trim_sections = DEF_BATCHED_TRIM_SECTIONS; + sm_info->min_ssr_sections = reserved_sections(sbi); INIT_LIST_HEAD(&sm_info->sit_entry_set); + init_rwsem(&sm_info->curseg_lock); + if (!f2fs_readonly(sbi->sb)) { - err = create_flush_cmd_control(sbi); + err = f2fs_create_flush_cmd_control(sbi); if (err) return err; } @@ -3609,7 +4501,7 @@ static void destroy_dirty_segmap(struct f2fs_sb_info *sbi) destroy_victim_secmap(sbi); SM_I(sbi)->dirty_info = NULL; - kfree(dirty_i); + kvfree(dirty_i); } static void destroy_curseg(struct f2fs_sb_info *sbi) @@ -3621,10 +4513,10 @@ static void destroy_curseg(struct f2fs_sb_info *sbi) return; SM_I(sbi)->curseg_array = NULL; for (i = 0; i < NR_CURSEG_TYPE; i++) { - kfree(array[i].sum_blk); - kfree(array[i].journal); + kvfree(array[i].sum_blk); + kvfree(array[i].journal); } - kfree(array); + kvfree(array); } static void destroy_free_segmap(struct f2fs_sb_info *sbi) @@ -3635,58 +4527,50 @@ static void destroy_free_segmap(struct f2fs_sb_info *sbi) SM_I(sbi)->free_info = NULL; kvfree(free_i->free_segmap); kvfree(free_i->free_secmap); - kfree(free_i); + kvfree(free_i); } static void destroy_sit_info(struct f2fs_sb_info *sbi) { struct sit_info *sit_i = SIT_I(sbi); - unsigned int start; if (!sit_i) return; - if (sit_i->sentries) { - for (start = 0; start < MAIN_SEGS(sbi); start++) { - kfree(sit_i->sentries[start].cur_valid_map); -#ifdef CONFIG_F2FS_CHECK_FS - kfree(sit_i->sentries[start].cur_valid_map_mir); -#endif - kfree(sit_i->sentries[start].ckpt_valid_map); - kfree(sit_i->sentries[start].discard_map); - } - } - kfree(sit_i->tmp_map); + if (sit_i->sentries) + kvfree(sit_i->bitmap); + kvfree(sit_i->tmp_map); kvfree(sit_i->sentries); kvfree(sit_i->sec_entries); kvfree(sit_i->dirty_sentries_bitmap); SM_I(sbi)->sit_info = NULL; - kfree(sit_i->sit_bitmap); + kvfree(sit_i->sit_bitmap); #ifdef CONFIG_F2FS_CHECK_FS - kfree(sit_i->sit_bitmap_mir); + kvfree(sit_i->sit_bitmap_mir); + kvfree(sit_i->invalid_segmap); #endif - kfree(sit_i); + kvfree(sit_i); } -void destroy_segment_manager(struct f2fs_sb_info *sbi) +void f2fs_destroy_segment_manager(struct f2fs_sb_info *sbi) { struct f2fs_sm_info *sm_info = SM_I(sbi); if (!sm_info) return; - destroy_flush_cmd_control(sbi, true); + f2fs_destroy_flush_cmd_control(sbi, true); destroy_discard_cmd_control(sbi); destroy_dirty_segmap(sbi); destroy_curseg(sbi); destroy_free_segmap(sbi); destroy_sit_info(sbi); sbi->sm_info = NULL; - kfree(sm_info); + kvfree(sm_info); } -int __init create_segment_manager_caches(void) +int __init f2fs_create_segment_manager_caches(void) { discard_entry_slab = f2fs_kmem_cache_create("discard_entry", sizeof(struct discard_entry)); @@ -3719,7 +4603,7 @@ fail: return -ENOMEM; } -void destroy_segment_manager_caches(void) +void f2fs_destroy_segment_manager_caches(void) { kmem_cache_destroy(sit_entry_set_slab); kmem_cache_destroy(discard_cmd_slab); |