diff options
Diffstat (limited to 'fs/f2fs/data.c')
| -rw-r--r-- | fs/f2fs/data.c | 1493 |
1 files changed, 736 insertions, 757 deletions
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 5882afe71d82..c30e69392a62 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -7,7 +7,6 @@ */ #include <linux/fs.h> #include <linux/f2fs_fs.h> -#include <linux/buffer_head.h> #include <linux/sched/mm.h> #include <linux/mpage.h> #include <linux/writeback.h> @@ -48,14 +47,14 @@ void f2fs_destroy_bioset(void) bioset_exit(&f2fs_bioset); } -static bool __is_cp_guaranteed(struct page *page) +bool f2fs_is_cp_guaranteed(const struct folio *folio) { - struct address_space *mapping = page->mapping; + struct address_space *mapping = folio->mapping; struct inode *inode; struct f2fs_sb_info *sbi; - if (!mapping) - return false; + if (fscrypt_is_bounce_folio(folio)) + return folio_test_f2fs_gcing(fscrypt_pagecache_folio(folio)); inode = mapping->host; sbi = F2FS_I_SB(inode); @@ -65,17 +64,15 @@ static bool __is_cp_guaranteed(struct page *page) S_ISDIR(inode->i_mode)) return true; - if (f2fs_is_compressed_page(page)) - return false; if ((S_ISREG(inode->i_mode) && IS_NOQUOTA(inode)) || - page_private_gcing(page)) + folio_test_f2fs_gcing(folio)) return true; return false; } -static enum count_type __read_io_type(struct page *page) +static enum count_type __read_io_type(struct folio *folio) { - struct address_space *mapping = page_file_mapping(page); + struct address_space *mapping = folio->mapping; if (mapping) { struct inode *inode = mapping->host; @@ -139,27 +136,22 @@ struct bio_post_read_ctx { */ static void f2fs_finish_read_bio(struct bio *bio, bool in_task) { - struct bio_vec *bv; - struct bvec_iter_all iter_all; + struct folio_iter fi; struct bio_post_read_ctx *ctx = bio->bi_private; - bio_for_each_segment_all(bv, bio, iter_all) { - struct page *page = bv->bv_page; + bio_for_each_folio_all(fi, bio) { + struct folio *folio = fi.folio; - if (f2fs_is_compressed_page(page)) { + if (f2fs_is_compressed_page(folio)) { if (ctx && !ctx->decompression_attempted) - f2fs_end_read_compressed_page(page, true, 0, + f2fs_end_read_compressed_page(folio, true, 0, in_task); - f2fs_put_page_dic(page, in_task); + f2fs_put_folio_dic(folio, in_task); continue; } - if (bio->bi_status) - ClearPageUptodate(page); - else - SetPageUptodate(page); - dec_page_count(F2FS_P_SB(page), __read_io_type(page)); - unlock_page(page); + dec_page_count(F2FS_F_SB(folio), __read_io_type(folio)); + folio_end_read(folio, bio->bi_status == BLK_STS_OK); } if (ctx) @@ -189,14 +181,13 @@ static void f2fs_verify_bio(struct work_struct *work) * as those were handled separately by f2fs_end_read_compressed_page(). */ if (may_have_compressed_pages) { - struct bio_vec *bv; - struct bvec_iter_all iter_all; + struct folio_iter fi; - bio_for_each_segment_all(bv, bio, iter_all) { - struct page *page = bv->bv_page; + bio_for_each_folio_all(fi, bio) { + struct folio *folio = fi.folio; - if (!f2fs_is_compressed_page(page) && - !fsverity_verify_page(page)) { + if (!f2fs_is_compressed_page(folio) && + !fsverity_verify_page(&folio->page)) { bio->bi_status = BLK_STS_IOERR; break; } @@ -241,16 +232,15 @@ static void f2fs_verify_and_finish_bio(struct bio *bio, bool in_task) static void f2fs_handle_step_decompress(struct bio_post_read_ctx *ctx, bool in_task) { - struct bio_vec *bv; - struct bvec_iter_all iter_all; + struct folio_iter fi; bool all_compressed = true; block_t blkaddr = ctx->fs_blkaddr; - bio_for_each_segment_all(bv, ctx->bio, iter_all) { - struct page *page = bv->bv_page; + bio_for_each_folio_all(fi, ctx->bio) { + struct folio *folio = fi.folio; - if (f2fs_is_compressed_page(page)) - f2fs_end_read_compressed_page(page, false, blkaddr, + if (f2fs_is_compressed_page(folio)) + f2fs_end_read_compressed_page(folio, false, blkaddr, in_task); else all_compressed = false; @@ -288,9 +278,9 @@ static void f2fs_post_read_work(struct work_struct *work) static void f2fs_read_end_io(struct bio *bio) { - struct f2fs_sb_info *sbi = F2FS_P_SB(bio_first_page_all(bio)); + struct f2fs_sb_info *sbi = F2FS_F_SB(bio_first_folio_all(bio)); struct bio_post_read_ctx *ctx; - bool intask = in_task(); + bool intask = in_task() && !irqs_disabled(); iostat_update_and_unbind_ctx(bio); ctx = bio->bi_private; @@ -298,7 +288,7 @@ static void f2fs_read_end_io(struct bio *bio) if (time_to_inject(sbi, FAULT_READ_IO)) bio->bi_status = BLK_STS_IOERR; - if (bio->bi_status) { + if (bio->bi_status != BLK_STS_OK) { f2fs_finish_read_bio(bio, intask); return; } @@ -327,8 +317,7 @@ static void f2fs_read_end_io(struct bio *bio) static void f2fs_write_end_io(struct bio *bio) { struct f2fs_sb_info *sbi; - struct bio_vec *bvec; - struct bvec_iter_all iter_all; + struct folio_iter fi; iostat_update_and_unbind_ctx(bio); sbi = bio->bi_private; @@ -336,45 +325,41 @@ static void f2fs_write_end_io(struct bio *bio) if (time_to_inject(sbi, FAULT_WRITE_IO)) bio->bi_status = BLK_STS_IOERR; - bio_for_each_segment_all(bvec, bio, iter_all) { - struct page *page = bvec->bv_page; - enum count_type type = WB_DATA_TYPE(page); + bio_for_each_folio_all(fi, bio) { + struct folio *folio = fi.folio; + enum count_type type; - if (page_private_dummy(page)) { - clear_page_private_dummy(page); - unlock_page(page); - mempool_free(page, sbi->write_io_dummy); + if (fscrypt_is_bounce_folio(folio)) { + struct folio *io_folio = folio; - if (unlikely(bio->bi_status)) - f2fs_stop_checkpoint(sbi, true, - STOP_CP_REASON_WRITE_FAIL); - continue; + folio = fscrypt_pagecache_folio(io_folio); + fscrypt_free_bounce_page(&io_folio->page); } - fscrypt_finalize_bounce_page(&page); - #ifdef CONFIG_F2FS_FS_COMPRESSION - if (f2fs_is_compressed_page(page)) { - f2fs_compress_write_end_io(bio, page); + if (f2fs_is_compressed_page(folio)) { + f2fs_compress_write_end_io(bio, folio); continue; } #endif - if (unlikely(bio->bi_status)) { - mapping_set_error(page->mapping, -EIO); + type = WB_DATA_TYPE(folio, false); + + if (unlikely(bio->bi_status != BLK_STS_OK)) { + mapping_set_error(folio->mapping, -EIO); if (type == F2FS_WB_CP_DATA) f2fs_stop_checkpoint(sbi, true, STOP_CP_REASON_WRITE_FAIL); } - f2fs_bug_on(sbi, page->mapping == NODE_MAPPING(sbi) && - page->index != nid_of_node(page)); + f2fs_bug_on(sbi, is_node_folio(folio) && + folio->index != nid_of_node(folio)); dec_page_count(sbi, type); - if (f2fs_in_warm_node_list(sbi, page)) - f2fs_del_fsync_node_entry(sbi, page); - clear_page_private_gcing(page); - end_page_writeback(page); + if (f2fs_in_warm_node_list(sbi, folio)) + f2fs_del_fsync_node_entry(sbi, folio); + folio_clear_f2fs_gcing(folio); + folio_end_writeback(folio); } if (!get_pages(sbi, F2FS_WB_CP_DATA) && wq_has_sleeper(&sbi->cp_wait)) @@ -457,6 +442,11 @@ static blk_opf_t f2fs_io_flags(struct f2fs_io_info *fio) op_flags |= REQ_META; if (BIT(fio->temp) & fua_flag) op_flags |= REQ_FUA; + + if (fio->type == DATA && + F2FS_I(fio->folio->mapping->host)->ioprio_hint == F2FS_IOPRIO_WRITE) + op_flags |= REQ_PRIO; + return op_flags; } @@ -478,6 +468,8 @@ static struct bio *__bio_alloc(struct f2fs_io_info *fio, int npages) } else { bio->bi_end_io = f2fs_write_end_io; bio->bi_private = sbi; + bio->bi_write_hint = f2fs_io_type_to_rw_hint(sbi, + fio->type, fio->temp); } iostat_alloc_and_bind_ctx(sbi, bio, NULL); @@ -524,51 +516,10 @@ void f2fs_submit_read_bio(struct f2fs_sb_info *sbi, struct bio *bio, submit_bio(bio); } -static void f2fs_align_write_bio(struct f2fs_sb_info *sbi, struct bio *bio) -{ - unsigned int start = - (bio->bi_iter.bi_size >> F2FS_BLKSIZE_BITS) % F2FS_IO_SIZE(sbi); - - if (start == 0) - return; - - /* fill dummy pages */ - for (; start < F2FS_IO_SIZE(sbi); start++) { - struct page *page = - mempool_alloc(sbi->write_io_dummy, - GFP_NOIO | __GFP_NOFAIL); - f2fs_bug_on(sbi, !page); - - lock_page(page); - - zero_user_segment(page, 0, PAGE_SIZE); - set_page_private_dummy(page); - - if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE) - f2fs_bug_on(sbi, 1); - } -} - static void f2fs_submit_write_bio(struct f2fs_sb_info *sbi, struct bio *bio, enum page_type type) { WARN_ON_ONCE(is_read_io(bio_op(bio))); - - if (type == DATA || type == NODE) { - if (f2fs_lfs_mode(sbi) && current->plug) - blk_finish_plug(current->plug); - - if (F2FS_IO_ALIGNED(sbi)) { - f2fs_align_write_bio(sbi, bio); - /* - * In the NODE case, we lose next block address chain. - * So, we need to do checkpoint in f2fs_sync_file. - */ - if (type == NODE) - set_sbi_flag(sbi, SBI_NEED_CP); - } - } - trace_f2fs_submit_write_bio(sbi->sb, type, bio); iostat_update_submit_ctx(bio, type); submit_bio(bio); @@ -592,34 +543,33 @@ static void __submit_merged_bio(struct f2fs_bio_info *io) } static bool __has_merged_page(struct bio *bio, struct inode *inode, - struct page *page, nid_t ino) + struct folio *folio, nid_t ino) { - struct bio_vec *bvec; - struct bvec_iter_all iter_all; + struct folio_iter fi; if (!bio) return false; - if (!inode && !page && !ino) + if (!inode && !folio && !ino) return true; - bio_for_each_segment_all(bvec, bio, iter_all) { - struct page *target = bvec->bv_page; + bio_for_each_folio_all(fi, bio) { + struct folio *target = fi.folio; - if (fscrypt_is_bounce_page(target)) { - target = fscrypt_pagecache_page(target); + if (fscrypt_is_bounce_folio(target)) { + target = fscrypt_pagecache_folio(target); if (IS_ERR(target)) continue; } if (f2fs_is_compressed_page(target)) { - target = f2fs_compress_control_page(target); + target = f2fs_compress_control_folio(target); if (IS_ERR(target)) continue; } if (inode && inode == target->mapping->host) return true; - if (page && page == target) + if (folio && folio == target) return true; if (ino && ino == ino_of_node(target)) return true; @@ -643,17 +593,20 @@ int f2fs_init_write_merge_io(struct f2fs_sb_info *sbi) return -ENOMEM; for (j = HOT; j < n; j++) { - init_f2fs_rwsem(&sbi->write_io[i][j].io_rwsem); - sbi->write_io[i][j].sbi = sbi; - sbi->write_io[i][j].bio = NULL; - spin_lock_init(&sbi->write_io[i][j].io_lock); - INIT_LIST_HEAD(&sbi->write_io[i][j].io_list); - INIT_LIST_HEAD(&sbi->write_io[i][j].bio_list); - init_f2fs_rwsem(&sbi->write_io[i][j].bio_list_lock); + struct f2fs_bio_info *io = &sbi->write_io[i][j]; + + init_f2fs_rwsem(&io->io_rwsem); + io->sbi = sbi; + io->bio = NULL; + io->last_block_in_bio = 0; + spin_lock_init(&io->io_lock); + INIT_LIST_HEAD(&io->io_list); + INIT_LIST_HEAD(&io->bio_list); + init_f2fs_rwsem(&io->bio_list_lock); #ifdef CONFIG_BLK_DEV_ZONED - init_completion(&sbi->write_io[i][j].zone_wait); - sbi->write_io[i][j].zone_pending_bio = NULL; - sbi->write_io[i][j].bi_private = NULL; + init_completion(&io->zone_wait); + io->zone_pending_bio = NULL; + io->bi_private = NULL; #endif } } @@ -685,7 +638,7 @@ unlock_out: } static void __submit_merged_write_cond(struct f2fs_sb_info *sbi, - struct inode *inode, struct page *page, + struct inode *inode, struct folio *folio, nid_t ino, enum page_type type, bool force) { enum temp_type temp; @@ -697,7 +650,7 @@ static void __submit_merged_write_cond(struct f2fs_sb_info *sbi, struct f2fs_bio_info *io = sbi->write_io[btype] + temp; f2fs_down_read(&io->io_rwsem); - ret = __has_merged_page(io->bio, inode, page, ino); + ret = __has_merged_page(io->bio, inode, folio, ino); f2fs_up_read(&io->io_rwsem); } if (ret) @@ -715,10 +668,10 @@ void f2fs_submit_merged_write(struct f2fs_sb_info *sbi, enum page_type type) } void f2fs_submit_merged_write_cond(struct f2fs_sb_info *sbi, - struct inode *inode, struct page *page, + struct inode *inode, struct folio *folio, nid_t ino, enum page_type type) { - __submit_merged_write_cond(sbi, inode, page, ino, type, false); + __submit_merged_write_cond(sbi, inode, folio, ino, type, false); } void f2fs_flush_merged_writes(struct f2fs_sb_info *sbi) @@ -735,34 +688,29 @@ void f2fs_flush_merged_writes(struct f2fs_sb_info *sbi) int f2fs_submit_page_bio(struct f2fs_io_info *fio) { struct bio *bio; - struct page *page = fio->encrypted_page ? - fio->encrypted_page : fio->page; + struct folio *fio_folio = fio->folio; + struct folio *data_folio = fio->encrypted_page ? + page_folio(fio->encrypted_page) : fio_folio; if (!f2fs_is_valid_blkaddr(fio->sbi, fio->new_blkaddr, fio->is_por ? META_POR : (__is_meta_io(fio) ? - META_GENERIC : DATA_GENERIC_ENHANCE))) { - f2fs_handle_error(fio->sbi, ERROR_INVALID_BLKADDR); + META_GENERIC : DATA_GENERIC_ENHANCE))) return -EFSCORRUPTED; - } - trace_f2fs_submit_page_bio(page, fio); + trace_f2fs_submit_folio_bio(data_folio, fio); /* Allocate a new bio */ bio = __bio_alloc(fio, 1); - f2fs_set_bio_crypt_ctx(bio, fio->page->mapping->host, - fio->page->index, fio, GFP_NOIO); - - if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE) { - bio_put(bio); - return -EFAULT; - } + f2fs_set_bio_crypt_ctx(bio, fio_folio->mapping->host, + fio_folio->index, fio, GFP_NOIO); + bio_add_folio_nofail(bio, data_folio, folio_size(data_folio), 0); if (fio->io_wbc && !is_read_io(fio->op)) - wbc_account_cgroup_owner(fio->io_wbc, fio->page, PAGE_SIZE); + wbc_account_cgroup_owner(fio->io_wbc, fio_folio, PAGE_SIZE); inc_page_count(fio->sbi, is_read_io(fio->op) ? - __read_io_type(page) : WB_DATA_TYPE(fio->page)); + __read_io_type(data_folio) : WB_DATA_TYPE(fio->folio, false)); if (is_read_io(bio_op(bio))) f2fs_submit_read_bio(fio->sbi, bio, fio->type); @@ -785,9 +733,11 @@ static bool page_is_mergeable(struct f2fs_sb_info *sbi, struct bio *bio, static bool io_type_is_mergeable(struct f2fs_bio_info *io, struct f2fs_io_info *fio) { + blk_opf_t mask = ~(REQ_PREFLUSH | REQ_FUA); + if (io->fio.op != fio->op) return false; - return io->fio.op_flags == fio->op_flags; + return (io->fio.op_flags & mask) == (fio->op_flags & mask); } static bool io_is_mergeable(struct f2fs_sb_info *sbi, struct bio *bio, @@ -796,23 +746,13 @@ static bool io_is_mergeable(struct f2fs_sb_info *sbi, struct bio *bio, block_t last_blkaddr, block_t cur_blkaddr) { - if (F2FS_IO_ALIGNED(sbi) && (fio->type == DATA || fio->type == NODE)) { - unsigned int filled_blocks = - F2FS_BYTES_TO_BLK(bio->bi_iter.bi_size); - unsigned int io_size = F2FS_IO_SIZE(sbi); - unsigned int left_vecs = bio->bi_max_vecs - bio->bi_vcnt; - - /* IOs in bio is aligned and left space of vectors is not enough */ - if (!(filled_blocks % io_size) && left_vecs < io_size) - return false; - } if (!page_is_mergeable(sbi, bio, last_blkaddr, cur_blkaddr)) return false; return io_type_is_mergeable(io, fio); } static void add_bio_entry(struct f2fs_sb_info *sbi, struct bio *bio, - struct page *page, enum temp_type temp) + struct folio *folio, enum temp_type temp) { struct f2fs_bio_info *io = sbi->write_io[DATA] + temp; struct bio_entry *be; @@ -821,8 +761,7 @@ static void add_bio_entry(struct f2fs_sb_info *sbi, struct bio *bio, be->bio = bio; bio_get(bio); - if (bio_add_page(bio, page, PAGE_SIZE, 0) != PAGE_SIZE) - f2fs_bug_on(sbi, 1); + bio_add_folio_nofail(bio, folio, folio_size(folio), 0); f2fs_down_write(&io->bio_list_lock); list_add_tail(&be->list, &io->bio_list); @@ -836,8 +775,9 @@ static void del_bio_entry(struct bio_entry *be) } static int add_ipu_page(struct f2fs_io_info *fio, struct bio **bio, - struct page *page) + struct folio *folio) { + struct folio *fio_folio = fio->folio; struct f2fs_sb_info *sbi = fio->sbi; enum temp_type temp; bool found = false; @@ -859,10 +799,9 @@ static int add_ipu_page(struct f2fs_io_info *fio, struct bio **bio, *fio->last_block, fio->new_blkaddr)); if (f2fs_crypt_mergeable_bio(*bio, - fio->page->mapping->host, - fio->page->index, fio) && - bio_add_page(*bio, page, PAGE_SIZE, 0) == - PAGE_SIZE) { + fio_folio->mapping->host, + fio_folio->index, fio) && + bio_add_folio(*bio, folio, folio_size(folio), 0)) { ret = 0; break; } @@ -884,13 +823,13 @@ static int add_ipu_page(struct f2fs_io_info *fio, struct bio **bio, } void f2fs_submit_merged_ipu_write(struct f2fs_sb_info *sbi, - struct bio **bio, struct page *page) + struct bio **bio, struct folio *folio) { enum temp_type temp; bool found = false; struct bio *target = bio ? *bio : NULL; - f2fs_bug_on(sbi, !target && !page); + f2fs_bug_on(sbi, !target && !folio); for (temp = HOT; temp < NR_TEMP_TYPE && !found; temp++) { struct f2fs_bio_info *io = sbi->write_io[DATA] + temp; @@ -906,7 +845,7 @@ void f2fs_submit_merged_ipu_write(struct f2fs_sb_info *sbi, found = (target == be->bio); else found = __has_merged_page(be->bio, NULL, - page, 0); + folio, 0); if (found) break; } @@ -923,7 +862,7 @@ void f2fs_submit_merged_ipu_write(struct f2fs_sb_info *sbi, found = (target == be->bio); else found = __has_merged_page(be->bio, NULL, - page, 0); + folio, 0); if (found) { target = be->bio; del_bio_entry(be); @@ -944,16 +883,15 @@ void f2fs_submit_merged_ipu_write(struct f2fs_sb_info *sbi, int f2fs_merge_page_bio(struct f2fs_io_info *fio) { struct bio *bio = *fio->bio; - struct page *page = fio->encrypted_page ? - fio->encrypted_page : fio->page; + struct folio *data_folio = fio->encrypted_page ? + page_folio(fio->encrypted_page) : fio->folio; + struct folio *folio = fio->folio; if (!f2fs_is_valid_blkaddr(fio->sbi, fio->new_blkaddr, - __is_meta_io(fio) ? META_GENERIC : DATA_GENERIC)) { - f2fs_handle_error(fio->sbi, ERROR_INVALID_BLKADDR); + __is_meta_io(fio) ? META_GENERIC : DATA_GENERIC)) return -EFSCORRUPTED; - } - trace_f2fs_submit_page_bio(page, fio); + trace_f2fs_submit_folio_bio(data_folio, fio); if (bio && !page_is_mergeable(fio->sbi, bio, *fio->last_block, fio->new_blkaddr)) @@ -961,19 +899,19 @@ int f2fs_merge_page_bio(struct f2fs_io_info *fio) alloc_new: if (!bio) { bio = __bio_alloc(fio, BIO_MAX_VECS); - f2fs_set_bio_crypt_ctx(bio, fio->page->mapping->host, - fio->page->index, fio, GFP_NOIO); + f2fs_set_bio_crypt_ctx(bio, folio->mapping->host, + folio->index, fio, GFP_NOIO); - add_bio_entry(fio->sbi, bio, page, fio->temp); + add_bio_entry(fio->sbi, bio, data_folio, fio->temp); } else { - if (add_ipu_page(fio, &bio, page)) + if (add_ipu_page(fio, &bio, data_folio)) goto alloc_new; } if (fio->io_wbc) - wbc_account_cgroup_owner(fio->io_wbc, fio->page, PAGE_SIZE); + wbc_account_cgroup_owner(fio->io_wbc, folio, folio_size(folio)); - inc_page_count(fio->sbi, WB_DATA_TYPE(page)); + inc_page_count(fio->sbi, WB_DATA_TYPE(folio, false)); *fio->last_block = fio->new_blkaddr; *fio->bio = bio; @@ -984,6 +922,7 @@ alloc_new: #ifdef CONFIG_BLK_DEV_ZONED static bool is_end_zone_blkaddr(struct f2fs_sb_info *sbi, block_t blkaddr) { + struct block_device *bdev = sbi->sb->s_bdev; int devi = 0; if (f2fs_is_multi_device(sbi)) { @@ -994,8 +933,9 @@ static bool is_end_zone_blkaddr(struct f2fs_sb_info *sbi, block_t blkaddr) return false; } blkaddr -= FDEV(devi).start_blk; + bdev = FDEV(devi).bdev; } - return bdev_zoned_model(FDEV(devi).bdev) == BLK_ZONED_HM && + return bdev_is_zoned(bdev) && f2fs_blkz_is_seq(sbi, devi, blkaddr) && (blkaddr % sbi->blocks_per_blkz == sbi->blocks_per_blkz - 1); } @@ -1006,12 +946,13 @@ void f2fs_submit_page_write(struct f2fs_io_info *fio) struct f2fs_sb_info *sbi = fio->sbi; enum page_type btype = PAGE_TYPE_OF_BIO(fio->type); struct f2fs_bio_info *io = sbi->write_io[btype] + fio->temp; - struct page *bio_page; + struct folio *bio_folio; + enum count_type type; f2fs_bug_on(sbi, is_read_io(fio->op)); f2fs_down_write(&io->io_rwsem); - +next: #ifdef CONFIG_BLK_DEV_ZONED if (f2fs_sb_has_blkzoned(sbi) && btype < META && io->zone_pending_bio) { wait_for_completion_io(&io->zone_wait); @@ -1021,7 +962,6 @@ void f2fs_submit_page_write(struct f2fs_io_info *fio) } #endif -next: if (fio->in_list) { spin_lock(&io->io_lock); if (list_empty(&io->io_list)) { @@ -1037,53 +977,44 @@ next: verify_fio_blkaddr(fio); if (fio->encrypted_page) - bio_page = fio->encrypted_page; + bio_folio = page_folio(fio->encrypted_page); else if (fio->compressed_page) - bio_page = fio->compressed_page; + bio_folio = page_folio(fio->compressed_page); else - bio_page = fio->page; + bio_folio = fio->folio; /* set submitted = true as a return value */ fio->submitted = 1; - inc_page_count(sbi, WB_DATA_TYPE(bio_page)); + type = WB_DATA_TYPE(bio_folio, fio->compressed_page); + inc_page_count(sbi, type); if (io->bio && (!io_is_mergeable(sbi, io->bio, io, fio, io->last_block_in_bio, fio->new_blkaddr) || - !f2fs_crypt_mergeable_bio(io->bio, fio->page->mapping->host, - bio_page->index, fio))) + !f2fs_crypt_mergeable_bio(io->bio, fio_inode(fio), + bio_folio->index, fio))) __submit_merged_bio(io); alloc_new: if (io->bio == NULL) { - if (F2FS_IO_ALIGNED(sbi) && - (fio->type == DATA || fio->type == NODE) && - fio->new_blkaddr & F2FS_IO_SIZE_MASK(sbi)) { - dec_page_count(sbi, WB_DATA_TYPE(bio_page)); - fio->retry = 1; - goto skip; - } io->bio = __bio_alloc(fio, BIO_MAX_VECS); - f2fs_set_bio_crypt_ctx(io->bio, fio->page->mapping->host, - bio_page->index, fio, GFP_NOIO); + f2fs_set_bio_crypt_ctx(io->bio, fio_inode(fio), + bio_folio->index, fio, GFP_NOIO); io->fio = *fio; } - if (bio_add_page(io->bio, bio_page, PAGE_SIZE, 0) < PAGE_SIZE) { + if (!bio_add_folio(io->bio, bio_folio, folio_size(bio_folio), 0)) { __submit_merged_bio(io); goto alloc_new; } if (fio->io_wbc) - wbc_account_cgroup_owner(fio->io_wbc, fio->page, PAGE_SIZE); + wbc_account_cgroup_owner(fio->io_wbc, fio->folio, + folio_size(fio->folio)); io->last_block_in_bio = fio->new_blkaddr; - trace_f2fs_submit_page_write(fio->page, fio); -skip: - if (fio->in_list) - goto next; -out: + trace_f2fs_submit_folio_write(fio->folio, fio); #ifdef CONFIG_BLK_DEV_ZONED if (f2fs_sb_has_blkzoned(sbi) && btype < META && is_end_zone_blkaddr(sbi, fio->new_blkaddr)) { @@ -1096,6 +1027,9 @@ out: __submit_merged_bio(io); } #endif + if (fio->in_list) + goto next; +out: if (is_sbi_flag_set(sbi, SBI_IS_SHUTDOWN) || !f2fs_is_checkpoint_ready(sbi)) __submit_merged_bio(io); @@ -1116,8 +1050,6 @@ static struct bio *f2fs_grab_read_bio(struct inode *inode, block_t blkaddr, bio = bio_alloc_bioset(bdev, bio_max_segs(nr_pages), REQ_OP_READ | op_flag, for_write ? GFP_NOIO : GFP_KERNEL, &f2fs_bioset); - if (!bio) - return ERR_PTR(-ENOMEM); bio->bi_iter.bi_sector = sector; f2fs_set_bio_crypt_ctx(bio, inode, first_idx, NULL, GFP_NOFS); bio->bi_end_io = f2fs_read_end_io; @@ -1151,7 +1083,7 @@ static struct bio *f2fs_grab_read_bio(struct inode *inode, block_t blkaddr, } /* This can handle encryption stuffs */ -static int f2fs_submit_page_read(struct inode *inode, struct page *page, +static void f2fs_submit_page_read(struct inode *inode, struct folio *folio, block_t blkaddr, blk_opf_t op_flags, bool for_write) { @@ -1159,55 +1091,44 @@ static int f2fs_submit_page_read(struct inode *inode, struct page *page, struct bio *bio; bio = f2fs_grab_read_bio(inode, blkaddr, 1, op_flags, - page->index, for_write); - if (IS_ERR(bio)) - return PTR_ERR(bio); + folio->index, for_write); /* wait for GCed page writeback via META_MAPPING */ f2fs_wait_on_block_writeback(inode, blkaddr); - if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE) { - bio_put(bio); - return -EFAULT; - } + if (!bio_add_folio(bio, folio, PAGE_SIZE, 0)) + f2fs_bug_on(sbi, 1); + inc_page_count(sbi, F2FS_RD_DATA); f2fs_update_iostat(sbi, NULL, FS_DATA_READ_IO, F2FS_BLKSIZE); f2fs_submit_read_bio(sbi, bio, DATA); - return 0; } -static void __set_data_blkaddr(struct dnode_of_data *dn) +static void __set_data_blkaddr(struct dnode_of_data *dn, block_t blkaddr) { - struct f2fs_node *rn = F2FS_NODE(dn->node_page); - __le32 *addr_array; - int base = 0; - - if (IS_INODE(dn->node_page) && f2fs_has_extra_attr(dn->inode)) - base = get_extra_isize(dn->inode); + __le32 *addr = get_dnode_addr(dn->inode, dn->node_folio); - /* Get physical address of data block */ - addr_array = blkaddr_in_node(rn); - addr_array[base + dn->ofs_in_node] = cpu_to_le32(dn->data_blkaddr); + dn->data_blkaddr = blkaddr; + addr[dn->ofs_in_node] = cpu_to_le32(dn->data_blkaddr); } /* * Lock ordering for the change of data block address: * ->data_page - * ->node_page + * ->node_folio * update block addresses in the node page */ -void f2fs_set_data_blkaddr(struct dnode_of_data *dn) +void f2fs_set_data_blkaddr(struct dnode_of_data *dn, block_t blkaddr) { - f2fs_wait_on_page_writeback(dn->node_page, NODE, true, true); - __set_data_blkaddr(dn); - if (set_page_dirty(dn->node_page)) + f2fs_folio_wait_writeback(dn->node_folio, NODE, true, true); + __set_data_blkaddr(dn, blkaddr); + if (folio_mark_dirty(dn->node_folio)) dn->node_changed = true; } void f2fs_update_data_blkaddr(struct dnode_of_data *dn, block_t blkaddr) { - dn->data_blkaddr = blkaddr; - f2fs_set_data_blkaddr(dn); + f2fs_set_data_blkaddr(dn, blkaddr); f2fs_update_read_extent_cache(dn); } @@ -1222,25 +1143,25 @@ int f2fs_reserve_new_blocks(struct dnode_of_data *dn, blkcnt_t count) if (unlikely(is_inode_flag_set(dn->inode, FI_NO_ALLOC))) return -EPERM; - if (unlikely((err = inc_valid_block_count(sbi, dn->inode, &count)))) + err = inc_valid_block_count(sbi, dn->inode, &count, true); + if (unlikely(err)) return err; trace_f2fs_reserve_new_blocks(dn->inode, dn->nid, dn->ofs_in_node, count); - f2fs_wait_on_page_writeback(dn->node_page, NODE, true, true); + f2fs_folio_wait_writeback(dn->node_folio, NODE, true, true); for (; count > 0; dn->ofs_in_node++) { block_t blkaddr = f2fs_data_blkaddr(dn); if (blkaddr == NULL_ADDR) { - dn->data_blkaddr = NEW_ADDR; - __set_data_blkaddr(dn); + __set_data_blkaddr(dn, NEW_ADDR); count--; } } - if (set_page_dirty(dn->node_page)) + if (folio_mark_dirty(dn->node_folio)) dn->node_changed = true; return 0; } @@ -1258,7 +1179,7 @@ int f2fs_reserve_new_block(struct dnode_of_data *dn) int f2fs_reserve_block(struct dnode_of_data *dn, pgoff_t index) { - bool need_put = dn->inode_page ? false : true; + bool need_put = dn->inode_folio ? false : true; int err; err = f2fs_get_dnode_of_data(dn, index, ALLOC_NODE); @@ -1272,26 +1193,23 @@ int f2fs_reserve_block(struct dnode_of_data *dn, pgoff_t index) return err; } -struct page *f2fs_get_read_data_page(struct inode *inode, pgoff_t index, - blk_opf_t op_flags, bool for_write, - pgoff_t *next_pgofs) +struct folio *f2fs_get_read_data_folio(struct inode *inode, pgoff_t index, + blk_opf_t op_flags, bool for_write, pgoff_t *next_pgofs) { struct address_space *mapping = inode->i_mapping; struct dnode_of_data dn; - struct page *page; + struct folio *folio; int err; - page = f2fs_grab_cache_page(mapping, index, for_write); - if (!page) - return ERR_PTR(-ENOMEM); + folio = f2fs_grab_cache_folio(mapping, index, for_write); + if (IS_ERR(folio)) + return folio; if (f2fs_lookup_read_extent_cache_block(inode, index, &dn.data_blkaddr)) { if (!f2fs_is_valid_blkaddr(F2FS_I_SB(inode), dn.data_blkaddr, DATA_GENERIC_ENHANCE_READ)) { err = -EFSCORRUPTED; - f2fs_handle_error(F2FS_I_SB(inode), - ERROR_INVALID_BLKADDR); goto put_err; } goto got_it; @@ -1317,66 +1235,65 @@ struct page *f2fs_get_read_data_page(struct inode *inode, pgoff_t index, dn.data_blkaddr, DATA_GENERIC_ENHANCE)) { err = -EFSCORRUPTED; - f2fs_handle_error(F2FS_I_SB(inode), - ERROR_INVALID_BLKADDR); goto put_err; } got_it: - if (PageUptodate(page)) { - unlock_page(page); - return page; + if (folio_test_uptodate(folio)) { + folio_unlock(folio); + return folio; } /* * A new dentry page is allocated but not able to be written, since its * new inode page couldn't be allocated due to -ENOSPC. * In such the case, its blkaddr can be remained as NEW_ADDR. - * see, f2fs_add_link -> f2fs_get_new_data_page -> + * see, f2fs_add_link -> f2fs_get_new_data_folio -> * f2fs_init_inode_metadata. */ if (dn.data_blkaddr == NEW_ADDR) { - zero_user_segment(page, 0, PAGE_SIZE); - if (!PageUptodate(page)) - SetPageUptodate(page); - unlock_page(page); - return page; + folio_zero_segment(folio, 0, folio_size(folio)); + if (!folio_test_uptodate(folio)) + folio_mark_uptodate(folio); + folio_unlock(folio); + return folio; } - err = f2fs_submit_page_read(inode, page, dn.data_blkaddr, + f2fs_submit_page_read(inode, folio, dn.data_blkaddr, op_flags, for_write); - if (err) - goto put_err; - return page; + return folio; put_err: - f2fs_put_page(page, 1); + f2fs_folio_put(folio, true); return ERR_PTR(err); } -struct page *f2fs_find_data_page(struct inode *inode, pgoff_t index, +struct folio *f2fs_find_data_folio(struct inode *inode, pgoff_t index, pgoff_t *next_pgofs) { struct address_space *mapping = inode->i_mapping; - struct page *page; - - page = find_get_page(mapping, index); - if (page && PageUptodate(page)) - return page; - f2fs_put_page(page, 0); - - page = f2fs_get_read_data_page(inode, index, 0, false, next_pgofs); - if (IS_ERR(page)) - return page; - - if (PageUptodate(page)) - return page; - - wait_on_page_locked(page); - if (unlikely(!PageUptodate(page))) { - f2fs_put_page(page, 0); + struct folio *folio; + + folio = f2fs_filemap_get_folio(mapping, index, FGP_ACCESSED, 0); + if (IS_ERR(folio)) + goto read; + if (folio_test_uptodate(folio)) + return folio; + f2fs_folio_put(folio, false); + +read: + folio = f2fs_get_read_data_folio(inode, index, 0, false, next_pgofs); + if (IS_ERR(folio)) + return folio; + + if (folio_test_uptodate(folio)) + return folio; + + folio_wait_locked(folio); + if (unlikely(!folio_test_uptodate(folio))) { + f2fs_folio_put(folio, false); return ERR_PTR(-EIO); } - return page; + return folio; } /* @@ -1384,27 +1301,23 @@ struct page *f2fs_find_data_page(struct inode *inode, pgoff_t index, * Because, the callers, functions in dir.c and GC, should be able to know * whether this page exists or not. */ -struct page *f2fs_get_lock_data_page(struct inode *inode, pgoff_t index, +struct folio *f2fs_get_lock_data_folio(struct inode *inode, pgoff_t index, bool for_write) { struct address_space *mapping = inode->i_mapping; - struct page *page; -repeat: - page = f2fs_get_read_data_page(inode, index, 0, for_write, NULL); - if (IS_ERR(page)) - return page; + struct folio *folio; + + folio = f2fs_get_read_data_folio(inode, index, 0, for_write, NULL); + if (IS_ERR(folio)) + return folio; /* wait for read completion */ - lock_page(page); - if (unlikely(page->mapping != mapping)) { - f2fs_put_page(page, 1); - goto repeat; - } - if (unlikely(!PageUptodate(page))) { - f2fs_put_page(page, 1); + folio_lock(folio); + if (unlikely(folio->mapping != mapping || !folio_test_uptodate(folio))) { + f2fs_folio_put(folio, true); return ERR_PTR(-EIO); } - return page; + return folio; } /* @@ -1413,57 +1326,57 @@ repeat: * * Also, caller should grab and release a rwsem by calling f2fs_lock_op() and * f2fs_unlock_op(). - * Note that, ipage is set only by make_empty_dir, and if any error occur, - * ipage should be released by this function. + * Note that, ifolio is set only by make_empty_dir, and if any error occur, + * ifolio should be released by this function. */ -struct page *f2fs_get_new_data_page(struct inode *inode, - struct page *ipage, pgoff_t index, bool new_i_size) +struct folio *f2fs_get_new_data_folio(struct inode *inode, + struct folio *ifolio, pgoff_t index, bool new_i_size) { struct address_space *mapping = inode->i_mapping; - struct page *page; + struct folio *folio; struct dnode_of_data dn; int err; - page = f2fs_grab_cache_page(mapping, index, true); - if (!page) { + folio = f2fs_grab_cache_folio(mapping, index, true); + if (IS_ERR(folio)) { /* - * before exiting, we should make sure ipage will be released + * before exiting, we should make sure ifolio will be released * if any error occur. */ - f2fs_put_page(ipage, 1); + f2fs_folio_put(ifolio, true); return ERR_PTR(-ENOMEM); } - set_new_dnode(&dn, inode, ipage, NULL, 0); + set_new_dnode(&dn, inode, ifolio, NULL, 0); err = f2fs_reserve_block(&dn, index); if (err) { - f2fs_put_page(page, 1); + f2fs_folio_put(folio, true); return ERR_PTR(err); } - if (!ipage) + if (!ifolio) f2fs_put_dnode(&dn); - if (PageUptodate(page)) + if (folio_test_uptodate(folio)) goto got_it; if (dn.data_blkaddr == NEW_ADDR) { - zero_user_segment(page, 0, PAGE_SIZE); - if (!PageUptodate(page)) - SetPageUptodate(page); + folio_zero_segment(folio, 0, folio_size(folio)); + if (!folio_test_uptodate(folio)) + folio_mark_uptodate(folio); } else { - f2fs_put_page(page, 1); + f2fs_folio_put(folio, true); - /* if ipage exists, blkaddr should be NEW_ADDR */ - f2fs_bug_on(F2FS_I_SB(inode), ipage); - page = f2fs_get_lock_data_page(inode, index, true); - if (IS_ERR(page)) - return page; + /* if ifolio exists, blkaddr should be NEW_ADDR */ + f2fs_bug_on(F2FS_I_SB(inode), ifolio); + folio = f2fs_get_lock_data_folio(inode, index, true); + if (IS_ERR(folio)) + return folio; } got_it: if (new_i_size && i_size_read(inode) < ((loff_t)(index + 1) << PAGE_SHIFT)) f2fs_i_size_write(inode, ((loff_t)(index + 1) << PAGE_SHIFT)); - return page; + return folio; } static int __allocate_data_block(struct dnode_of_data *dn, int seg_type) @@ -1484,26 +1397,28 @@ static int __allocate_data_block(struct dnode_of_data *dn, int seg_type) dn->data_blkaddr = f2fs_data_blkaddr(dn); if (dn->data_blkaddr == NULL_ADDR) { - err = inc_valid_block_count(sbi, dn->inode, &count); + err = inc_valid_block_count(sbi, dn->inode, &count, true); if (unlikely(err)) return err; } set_summary(&sum, dn->nid, dn->ofs_in_node, ni.version); old_blkaddr = dn->data_blkaddr; - f2fs_allocate_data_block(sbi, NULL, old_blkaddr, &dn->data_blkaddr, - &sum, seg_type, NULL); - if (GET_SEGNO(sbi, old_blkaddr) != NULL_SEGNO) { - invalidate_mapping_pages(META_MAPPING(sbi), - old_blkaddr, old_blkaddr); - f2fs_invalidate_compress_page(sbi, old_blkaddr); - } + err = f2fs_allocate_data_block(sbi, NULL, old_blkaddr, + &dn->data_blkaddr, &sum, seg_type, NULL); + if (err) + return err; + + if (GET_SEGNO(sbi, old_blkaddr) != NULL_SEGNO) + f2fs_invalidate_internal_cache(sbi, old_blkaddr, 1); + f2fs_update_data_blkaddr(dn, dn->data_blkaddr); return 0; } static void f2fs_map_lock(struct f2fs_sb_info *sbi, int flag) { + f2fs_down_read(&sbi->cp_enable_rwsem); if (flag == F2FS_GET_BLOCK_PRE_AIO) f2fs_down_read(&sbi->node_change); else @@ -1516,6 +1431,7 @@ static void f2fs_map_unlock(struct f2fs_sb_info *sbi, int flag) f2fs_up_read(&sbi->node_change); else f2fs_unlock_op(sbi); + f2fs_up_read(&sbi->cp_enable_rwsem); } int f2fs_get_block_locked(struct dnode_of_data *dn, pgoff_t index) @@ -1581,14 +1497,33 @@ static bool f2fs_map_blocks_cached(struct inode *inode, struct f2fs_dev_info *dev = &sbi->devs[bidx]; map->m_bdev = dev->bdev; - map->m_pblk -= dev->start_blk; map->m_len = min(map->m_len, dev->end_blk + 1 - map->m_pblk); + map->m_pblk -= dev->start_blk; } else { map->m_bdev = inode->i_sb->s_bdev; } return true; } +static bool map_is_mergeable(struct f2fs_sb_info *sbi, + struct f2fs_map_blocks *map, + block_t blkaddr, int flag, int bidx, + int ofs) +{ + if (map->m_multidev_dio && map->m_bdev != FDEV(bidx).bdev) + return false; + if (map->m_pblk != NEW_ADDR && blkaddr == (map->m_pblk + ofs)) + return true; + if (map->m_pblk == NEW_ADDR && blkaddr == NEW_ADDR) + return true; + if (flag == F2FS_GET_BLOCK_PRE_DIO) + return true; + if (flag == F2FS_GET_BLOCK_DIO && + map->m_pblk == NULL_ADDR && blkaddr == NULL_ADDR) + return true; + return false; +} + /* * f2fs_map_blocks() tries to find or build mapping relationship which * maps continuous logical blocks to physical blocks, and return such @@ -1608,10 +1543,14 @@ int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map, int flag) unsigned int start_pgofs; int bidx = 0; bool is_hole; + bool lfs_dio_write; if (!maxblocks) return 0; + lfs_dio_write = (flag == F2FS_GET_BLOCK_DIO && f2fs_lfs_mode(sbi) && + map->m_may_create); + if (!map->m_may_create && f2fs_map_blocks_cached(inode, map, flag)) goto out; @@ -1626,9 +1565,15 @@ int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map, int flag) pgofs = (pgoff_t)map->m_lblk; end = pgofs + maxblocks; + if (flag == F2FS_GET_BLOCK_PRECACHE) + mode = LOOKUP_NODE_RA; + next_dnode: - if (map->m_may_create) + if (map->m_may_create) { + if (f2fs_lfs_mode(sbi)) + f2fs_balance_fs(sbi, true); f2fs_map_lock(sbi, flag); + } /* When reading holes, we need its node page */ set_new_dnode(&dn, inode, NULL, NULL, 0); @@ -1644,7 +1589,7 @@ next_dnode: start_pgofs = pgofs; prealloc = 0; last_ofs_in_node = ofs_in_node = dn.ofs_in_node; - end_offset = ADDRS_PER_PAGE(dn.node_page, inode); + end_offset = ADDRS_PER_PAGE(dn.node_folio, inode); next_block: blkaddr = f2fs_data_blkaddr(&dn); @@ -1652,13 +1597,13 @@ next_block: if (!is_hole && !f2fs_is_valid_blkaddr(sbi, blkaddr, DATA_GENERIC_ENHANCE)) { err = -EFSCORRUPTED; - f2fs_handle_error(sbi, ERROR_INVALID_BLKADDR); goto sync_out; } /* use out-place-update for direct IO under LFS mode */ - if (map->m_may_create && - (is_hole || (f2fs_lfs_mode(sbi) && flag == F2FS_GET_BLOCK_DIO))) { + if (map->m_may_create && (is_hole || + (flag == F2FS_GET_BLOCK_DIO && f2fs_lfs_mode(sbi) && + !f2fs_is_pinned_file(inode) && map->m_last_pblk != blkaddr))) { if (unlikely(f2fs_cp_error(sbi))) { err = -EIO; goto sync_out; @@ -1691,9 +1636,7 @@ next_block: map->m_flags |= F2FS_MAP_NEW; } else if (is_hole) { if (f2fs_compressed_file(inode) && - f2fs_sanity_check_cluster(&dn) && - (flag != F2FS_GET_BLOCK_FIEMAP || - IS_ENABLED(CONFIG_F2FS_CHECK_FS))) { + f2fs_sanity_check_cluster(&dn)) { err = -EFSCORRUPTED; f2fs_handle_error(sbi, ERROR_CORRUPTED_CLUSTER); @@ -1713,6 +1656,10 @@ next_block: goto sync_out; } break; + case F2FS_GET_BLOCK_DIO: + if (map->m_next_pgofs) + *map->m_next_pgofs = pgofs + 1; + break; default: /* for defragment case */ if (map->m_next_pgofs) @@ -1731,22 +1678,24 @@ next_block: /* reserved delalloc block should be mapped for fiemap. */ if (blkaddr == NEW_ADDR) map->m_flags |= F2FS_MAP_DELALLOC; - map->m_flags |= F2FS_MAP_MAPPED; + /* DIO READ and hole case, should not map the blocks. */ + if (!(flag == F2FS_GET_BLOCK_DIO && is_hole && !map->m_may_create)) + map->m_flags |= F2FS_MAP_MAPPED; map->m_pblk = blkaddr; map->m_len = 1; if (map->m_multidev_dio) map->m_bdev = FDEV(bidx).bdev; - } else if ((map->m_pblk != NEW_ADDR && - blkaddr == (map->m_pblk + ofs)) || - (map->m_pblk == NEW_ADDR && blkaddr == NEW_ADDR) || - flag == F2FS_GET_BLOCK_PRE_DIO) { - if (map->m_multidev_dio && map->m_bdev != FDEV(bidx).bdev) - goto sync_out; + + if (lfs_dio_write) + map->m_last_pblk = NULL_ADDR; + } else if (map_is_mergeable(sbi, map, blkaddr, flag, bidx, ofs)) { ofs++; map->m_len++; } else { + if (lfs_dio_write && !f2fs_is_pinned_file(inode)) + map->m_last_pblk = blkaddr; goto sync_out; } @@ -1825,12 +1774,13 @@ sync_out: if (map->m_flags & F2FS_MAP_MAPPED) { unsigned int ofs = start_pgofs - map->m_lblk; - f2fs_update_read_extent_cache_range(&dn, - start_pgofs, map->m_pblk + ofs, - map->m_len - ofs); + if (map->m_len > ofs) + f2fs_update_read_extent_cache_range(&dn, + start_pgofs, map->m_pblk + ofs, + map->m_len - ofs); } if (map->m_next_extent) - *map->m_next_extent = pgofs + 1; + *map->m_next_extent = is_hole ? pgofs + 1 : pgofs; } f2fs_put_dnode(&dn); unlock_out: @@ -1869,21 +1819,10 @@ bool f2fs_overwrite_io(struct inode *inode, loff_t pos, size_t len) return true; } -static inline u64 bytes_to_blks(struct inode *inode, u64 bytes) -{ - return (bytes >> inode->i_blkbits); -} - -static inline u64 blks_to_bytes(struct inode *inode, u64 blks) -{ - return (blks << inode->i_blkbits); -} - static int f2fs_xattr_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); - struct page *page; struct node_info ni; __u64 phys = 0, len; __u32 flags; @@ -1892,19 +1831,19 @@ static int f2fs_xattr_fiemap(struct inode *inode, if (f2fs_has_inline_xattr(inode)) { int offset; + struct folio *folio = f2fs_grab_cache_folio(NODE_MAPPING(sbi), + inode->i_ino, false); - page = f2fs_grab_cache_page(NODE_MAPPING(sbi), - inode->i_ino, false); - if (!page) - return -ENOMEM; + if (IS_ERR(folio)) + return PTR_ERR(folio); err = f2fs_get_node_info(sbi, inode->i_ino, &ni, false); if (err) { - f2fs_put_page(page, 1); + f2fs_folio_put(folio, true); return err; } - phys = blks_to_bytes(inode, ni.blk_addr); + phys = F2FS_BLK_TO_BYTES(ni.blk_addr); offset = offsetof(struct f2fs_inode, i_addr) + sizeof(__le32) * (DEF_ADDRS_PER_INODE - get_inline_xattr_addrs(inode)); @@ -1912,7 +1851,7 @@ static int f2fs_xattr_fiemap(struct inode *inode, phys += offset; len = inline_xattr_size(inode); - f2fs_put_page(page, 1); + f2fs_folio_put(folio, true); flags = FIEMAP_EXTENT_DATA_INLINE | FIEMAP_EXTENT_NOT_ALIGNED; @@ -1926,20 +1865,22 @@ static int f2fs_xattr_fiemap(struct inode *inode, } if (xnid) { - page = f2fs_grab_cache_page(NODE_MAPPING(sbi), xnid, false); - if (!page) - return -ENOMEM; + struct folio *folio = f2fs_grab_cache_folio(NODE_MAPPING(sbi), + xnid, false); + + if (IS_ERR(folio)) + return PTR_ERR(folio); err = f2fs_get_node_info(sbi, xnid, &ni, false); if (err) { - f2fs_put_page(page, 1); + f2fs_folio_put(folio, true); return err; } - phys = blks_to_bytes(inode, ni.blk_addr); + phys = F2FS_BLK_TO_BYTES(ni.blk_addr); len = inode->i_sb->s_blocksize; - f2fs_put_page(page, 1); + f2fs_folio_put(folio, true); flags = FIEMAP_EXTENT_LAST; } @@ -1952,30 +1893,11 @@ static int f2fs_xattr_fiemap(struct inode *inode, return (err < 0 ? err : 0); } -static loff_t max_inode_blocks(struct inode *inode) -{ - loff_t result = ADDRS_PER_INODE(inode); - loff_t leaf_count = ADDRS_PER_BLOCK(inode); - - /* two direct node blocks */ - result += (leaf_count * 2); - - /* two indirect node blocks */ - leaf_count *= NIDS_PER_BLOCK; - result += (leaf_count * 2); - - /* one double indirect node block */ - leaf_count *= NIDS_PER_BLOCK; - result += leaf_count; - - return result; -} - int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, u64 start, u64 len) { struct f2fs_map_blocks map; - sector_t start_blk, last_blk; + sector_t start_blk, last_blk, blk_len, max_len; pgoff_t next_pgofs; u64 logical = 0, phys = 0, size = 0; u32 flags = 0; @@ -1995,9 +1917,9 @@ int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, if (ret) return ret; - inode_lock(inode); + inode_lock_shared(inode); - maxbytes = max_file_blocks(inode) << F2FS_BLKSIZE_BITS; + maxbytes = F2FS_BLK_TO_BYTES(max_file_blocks(inode)); if (start > maxbytes) { ret = -EFBIG; goto out; @@ -2017,16 +1939,15 @@ int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, goto out; } - if (bytes_to_blks(inode, len) == 0) - len = blks_to_bytes(inode, 1); - - start_blk = bytes_to_blks(inode, start); - last_blk = bytes_to_blks(inode, start + len - 1); + start_blk = F2FS_BYTES_TO_BLK(start); + last_blk = F2FS_BYTES_TO_BLK(start + len - 1); + blk_len = last_blk - start_blk + 1; + max_len = F2FS_BYTES_TO_BLK(maxbytes) - start_blk; next: memset(&map, 0, sizeof(map)); map.m_lblk = start_blk; - map.m_len = bytes_to_blks(inode, len); + map.m_len = blk_len; map.m_next_pgofs = &next_pgofs; map.m_seg_type = NO_CHECK_TYPE; @@ -2043,13 +1964,23 @@ next: if (!compr_cluster && !(map.m_flags & F2FS_MAP_FLAGS)) { start_blk = next_pgofs; - if (blks_to_bytes(inode, start_blk) < blks_to_bytes(inode, - max_inode_blocks(inode))) + if (F2FS_BLK_TO_BYTES(start_blk) < maxbytes) goto prep_next; flags |= FIEMAP_EXTENT_LAST; } + /* + * current extent may cross boundary of inquiry, increase len to + * requery. + */ + if (!compr_cluster && (map.m_flags & F2FS_MAP_MAPPED) && + map.m_lblk + map.m_len - 1 == last_blk && + blk_len != max_len) { + blk_len = max_len; + goto next; + } + compr_appended = false; /* In a case of compressed cluster, append this to the last extent */ if (compr_cluster && ((map.m_flags & F2FS_MAP_DELALLOC) || @@ -2081,14 +2012,14 @@ skip_fill: } else if (compr_appended) { unsigned int appended_blks = cluster_size - count_in_cluster + 1; - size += blks_to_bytes(inode, appended_blks); + size += F2FS_BLK_TO_BYTES(appended_blks); start_blk += appended_blks; compr_cluster = false; } else { - logical = blks_to_bytes(inode, start_blk); + logical = F2FS_BLK_TO_BYTES(start_blk); phys = __is_valid_data_blkaddr(map.m_pblk) ? - blks_to_bytes(inode, map.m_pblk) : 0; - size = blks_to_bytes(inode, map.m_len); + F2FS_BLK_TO_BYTES(map.m_pblk) : 0; + size = F2FS_BLK_TO_BYTES(map.m_len); flags = 0; if (compr_cluster) { @@ -2096,13 +2027,13 @@ skip_fill: count_in_cluster += map.m_len; if (count_in_cluster == cluster_size) { compr_cluster = false; - size += blks_to_bytes(inode, 1); + size += F2FS_BLKSIZE; } } else if (map.m_flags & F2FS_MAP_DELALLOC) { flags = FIEMAP_EXTENT_UNWRITTEN; } - start_blk += bytes_to_blks(inode, size); + start_blk += F2FS_BYTES_TO_BLK(size); } prep_next: @@ -2115,37 +2046,43 @@ out: if (ret == 1) ret = 0; - inode_unlock(inode); + inode_unlock_shared(inode); return ret; } static inline loff_t f2fs_readpage_limit(struct inode *inode) { if (IS_ENABLED(CONFIG_FS_VERITY) && IS_VERITY(inode)) - return inode->i_sb->s_maxbytes; + return F2FS_BLK_TO_BYTES(max_file_blocks(inode)); return i_size_read(inode); } -static int f2fs_read_single_page(struct inode *inode, struct page *page, +static inline blk_opf_t f2fs_ra_op_flags(struct readahead_control *rac) +{ + return rac ? REQ_RAHEAD : 0; +} + +static int f2fs_read_single_page(struct inode *inode, struct folio *folio, unsigned nr_pages, struct f2fs_map_blocks *map, struct bio **bio_ret, sector_t *last_block_in_bio, - bool is_readahead) + struct readahead_control *rac) { struct bio *bio = *bio_ret; - const unsigned blocksize = blks_to_bytes(inode, 1); + const unsigned int blocksize = F2FS_BLKSIZE; sector_t block_in_file; sector_t last_block; sector_t last_block_in_file; sector_t block_nr; + pgoff_t index = folio->index; int ret = 0; - block_in_file = (sector_t)page_index(page); + block_in_file = (sector_t)index; last_block = block_in_file + nr_pages; - last_block_in_file = bytes_to_blks(inode, - f2fs_readpage_limit(inode) + blocksize - 1); + last_block_in_file = F2FS_BYTES_TO_BLK(f2fs_readpage_limit(inode) + + blocksize - 1); if (last_block > last_block_in_file) last_block = last_block_in_file; @@ -2173,26 +2110,24 @@ static int f2fs_read_single_page(struct inode *inode, struct page *page, got_it: if ((map->m_flags & F2FS_MAP_MAPPED)) { block_nr = map->m_pblk + block_in_file - map->m_lblk; - SetPageMappedToDisk(page); + folio_set_mappedtodisk(folio); if (!f2fs_is_valid_blkaddr(F2FS_I_SB(inode), block_nr, DATA_GENERIC_ENHANCE_READ)) { ret = -EFSCORRUPTED; - f2fs_handle_error(F2FS_I_SB(inode), - ERROR_INVALID_BLKADDR); goto out; } } else { zero_out: - zero_user_segment(page, 0, PAGE_SIZE); - if (f2fs_need_verity(inode, page->index) && - !fsverity_verify_page(page)) { + folio_zero_segment(folio, 0, folio_size(folio)); + if (f2fs_need_verity(inode, index) && + !fsverity_verify_folio(folio)) { ret = -EIO; goto out; } - if (!PageUptodate(page)) - SetPageUptodate(page); - unlock_page(page); + if (!folio_test_uptodate(folio)) + folio_mark_uptodate(folio); + folio_unlock(folio); goto out; } @@ -2202,21 +2137,15 @@ zero_out: */ if (bio && (!page_is_mergeable(F2FS_I_SB(inode), bio, *last_block_in_bio, block_nr) || - !f2fs_crypt_mergeable_bio(bio, inode, page->index, NULL))) { + !f2fs_crypt_mergeable_bio(bio, inode, index, NULL))) { submit_and_realloc: f2fs_submit_read_bio(F2FS_I_SB(inode), bio, DATA); bio = NULL; } - if (bio == NULL) { + if (bio == NULL) bio = f2fs_grab_read_bio(inode, block_nr, nr_pages, - is_readahead ? REQ_RAHEAD : 0, page->index, + f2fs_ra_op_flags(rac), index, false); - if (IS_ERR(bio)) { - ret = PTR_ERR(bio); - bio = NULL; - goto out; - } - } /* * If the page is under writeback, we need to wait for @@ -2224,7 +2153,7 @@ submit_and_realloc: */ f2fs_wait_on_block_writeback(inode, block_nr); - if (bio_add_page(bio, page, blocksize, 0) < blocksize) + if (!bio_add_folio(bio, folio, blocksize, 0)) goto submit_and_realloc; inc_page_count(F2FS_I_SB(inode), F2FS_RD_DATA); @@ -2239,7 +2168,7 @@ out: #ifdef CONFIG_F2FS_FS_COMPRESSION int f2fs_read_multi_pages(struct compress_ctx *cc, struct bio **bio_ret, unsigned nr_pages, sector_t *last_block_in_bio, - bool is_readahead, bool for_write) + struct readahead_control *rac, bool for_write) { struct dnode_of_data dn; struct inode *inode = cc->inode; @@ -2247,34 +2176,43 @@ int f2fs_read_multi_pages(struct compress_ctx *cc, struct bio **bio_ret, struct bio *bio = *bio_ret; unsigned int start_idx = cc->cluster_idx << cc->log_cluster_size; sector_t last_block_in_file; - const unsigned blocksize = blks_to_bytes(inode, 1); + const unsigned int blocksize = F2FS_BLKSIZE; struct decompress_io_ctx *dic = NULL; struct extent_info ei = {}; bool from_dnode = true; int i; int ret = 0; + if (unlikely(f2fs_cp_error(sbi))) { + ret = -EIO; + from_dnode = false; + goto out_put_dnode; + } + f2fs_bug_on(sbi, f2fs_cluster_is_empty(cc)); - last_block_in_file = bytes_to_blks(inode, - f2fs_readpage_limit(inode) + blocksize - 1); + last_block_in_file = F2FS_BYTES_TO_BLK(f2fs_readpage_limit(inode) + + blocksize - 1); /* get rid of pages beyond EOF */ for (i = 0; i < cc->cluster_size; i++) { struct page *page = cc->rpages[i]; + struct folio *folio; if (!page) continue; - if ((sector_t)page->index >= last_block_in_file) { - zero_user_segment(page, 0, PAGE_SIZE); - if (!PageUptodate(page)) - SetPageUptodate(page); - } else if (!PageUptodate(page)) { + + folio = page_folio(page); + if ((sector_t)folio->index >= last_block_in_file) { + folio_zero_segment(folio, 0, folio_size(folio)); + if (!folio_test_uptodate(folio)) + folio_mark_uptodate(folio); + } else if (!folio_test_uptodate(folio)) { continue; } - unlock_page(page); + folio_unlock(folio); if (for_write) - put_page(page); + folio_put(folio); cc->rpages[i] = NULL; cc->nr_rpages--; } @@ -2294,17 +2232,13 @@ int f2fs_read_multi_pages(struct compress_ctx *cc, struct bio **bio_ret, if (ret) goto out; - if (unlikely(f2fs_cp_error(sbi))) { - ret = -EIO; - goto out_put_dnode; - } f2fs_bug_on(sbi, dn.data_blkaddr != COMPRESS_ADDR); skip_reading_dnode: for (i = 1; i < cc->cluster_size; i++) { block_t blkaddr; - blkaddr = from_dnode ? data_blkaddr(dn.inode, dn.node_page, + blkaddr = from_dnode ? data_blkaddr(dn.inode, dn.node_folio, dn.ofs_in_node + i) : ei.blk + i - 1; @@ -2334,44 +2268,38 @@ skip_reading_dnode: } for (i = 0; i < cc->nr_cpages; i++) { - struct page *page = dic->cpages[i]; + struct folio *folio = page_folio(dic->cpages[i]); block_t blkaddr; struct bio_post_read_ctx *ctx; - blkaddr = from_dnode ? data_blkaddr(dn.inode, dn.node_page, + blkaddr = from_dnode ? data_blkaddr(dn.inode, dn.node_folio, dn.ofs_in_node + i + 1) : ei.blk + i; f2fs_wait_on_block_writeback(inode, blkaddr); - if (f2fs_load_compressed_page(sbi, page, blkaddr)) { - if (atomic_dec_and_test(&dic->remaining_pages)) + if (f2fs_load_compressed_folio(sbi, folio, blkaddr)) { + if (atomic_dec_and_test(&dic->remaining_pages)) { f2fs_decompress_cluster(dic, true); + break; + } continue; } if (bio && (!page_is_mergeable(sbi, bio, *last_block_in_bio, blkaddr) || - !f2fs_crypt_mergeable_bio(bio, inode, page->index, NULL))) { + !f2fs_crypt_mergeable_bio(bio, inode, folio->index, NULL))) { submit_and_realloc: f2fs_submit_read_bio(sbi, bio, DATA); bio = NULL; } - if (!bio) { - bio = f2fs_grab_read_bio(inode, blkaddr, nr_pages, - is_readahead ? REQ_RAHEAD : 0, - page->index, for_write); - if (IS_ERR(bio)) { - ret = PTR_ERR(bio); - f2fs_decompress_end_io(dic, ret, true); - f2fs_put_dnode(&dn); - *bio_ret = NULL; - return ret; - } - } + if (!bio) + bio = f2fs_grab_read_bio(inode, blkaddr, nr_pages - i, + f2fs_ra_op_flags(rac), + folio->index, for_write); - if (bio_add_page(bio, page, blocksize, 0) < blocksize) + if (!bio_add_folio(bio, folio, blocksize, 0)) goto submit_and_realloc; ctx = get_post_read_ctx(bio); @@ -2409,7 +2337,7 @@ out: * Major change was from block_size == page_size in f2fs by default. */ static int f2fs_mpage_readpages(struct inode *inode, - struct readahead_control *rac, struct page *page) + struct readahead_control *rac, struct folio *folio) { struct bio *bio = NULL; sector_t last_block_in_bio = 0; @@ -2426,11 +2354,20 @@ static int f2fs_mpage_readpages(struct inode *inode, .nr_cpages = 0, }; pgoff_t nc_cluster_idx = NULL_CLUSTER; + pgoff_t index; #endif unsigned nr_pages = rac ? readahead_count(rac) : 1; unsigned max_nr_pages = nr_pages; int ret = 0; +#ifdef CONFIG_F2FS_FS_COMPRESSION + if (f2fs_compressed_file(inode)) { + index = rac ? readahead_index(rac) : folio->index; + max_nr_pages = round_up(index + nr_pages, cc.cluster_size) - + round_down(index, cc.cluster_size); + } +#endif + map.m_pblk = 0; map.m_lblk = 0; map.m_len = 0; @@ -2442,64 +2379,63 @@ static int f2fs_mpage_readpages(struct inode *inode, for (; nr_pages; nr_pages--) { if (rac) { - page = readahead_page(rac); - prefetchw(&page->flags); + folio = readahead_folio(rac); + prefetchw(&folio->flags); } #ifdef CONFIG_F2FS_FS_COMPRESSION - if (f2fs_compressed_file(inode)) { - /* there are remained compressed pages, submit them */ - if (!f2fs_cluster_can_merge_page(&cc, page->index)) { - ret = f2fs_read_multi_pages(&cc, &bio, - max_nr_pages, - &last_block_in_bio, - rac != NULL, false); - f2fs_destroy_compress_ctx(&cc, false); - if (ret) - goto set_error_page; - } - if (cc.cluster_idx == NULL_CLUSTER) { - if (nc_cluster_idx == - page->index >> cc.log_cluster_size) { - goto read_single_page; - } - - ret = f2fs_is_compressed_cluster(inode, page->index); - if (ret < 0) - goto set_error_page; - else if (!ret) { - nc_cluster_idx = - page->index >> cc.log_cluster_size; - goto read_single_page; - } - - nc_cluster_idx = NULL_CLUSTER; - } - ret = f2fs_init_compress_ctx(&cc); + index = folio->index; + + if (!f2fs_compressed_file(inode)) + goto read_single_page; + + /* there are remained compressed pages, submit them */ + if (!f2fs_cluster_can_merge_page(&cc, index)) { + ret = f2fs_read_multi_pages(&cc, &bio, + max_nr_pages, + &last_block_in_bio, + rac, false); + f2fs_destroy_compress_ctx(&cc, false); if (ret) goto set_error_page; + } + if (cc.cluster_idx == NULL_CLUSTER) { + if (nc_cluster_idx == index >> cc.log_cluster_size) + goto read_single_page; - f2fs_compress_ctx_add_page(&cc, page); + ret = f2fs_is_compressed_cluster(inode, index); + if (ret < 0) + goto set_error_page; + else if (!ret) { + nc_cluster_idx = + index >> cc.log_cluster_size; + goto read_single_page; + } - goto next_page; + nc_cluster_idx = NULL_CLUSTER; } + ret = f2fs_init_compress_ctx(&cc); + if (ret) + goto set_error_page; + + f2fs_compress_ctx_add_page(&cc, folio); + + goto next_page; read_single_page: #endif - ret = f2fs_read_single_page(inode, page, max_nr_pages, &map, + ret = f2fs_read_single_page(inode, folio, max_nr_pages, &map, &bio, &last_block_in_bio, rac); if (ret) { #ifdef CONFIG_F2FS_FS_COMPRESSION set_error_page: #endif - zero_user_segment(page, 0, PAGE_SIZE); - unlock_page(page); + folio_zero_segment(folio, 0, folio_size(folio)); + folio_unlock(folio); } #ifdef CONFIG_F2FS_FS_COMPRESSION next_page: #endif - if (rac) - put_page(page); #ifdef CONFIG_F2FS_FS_COMPRESSION if (f2fs_compressed_file(inode)) { @@ -2508,7 +2444,7 @@ next_page: ret = f2fs_read_multi_pages(&cc, &bio, max_nr_pages, &last_block_in_bio, - rac != NULL, false); + rac, false); f2fs_destroy_compress_ctx(&cc, false); } } @@ -2521,22 +2457,21 @@ next_page: static int f2fs_read_data_folio(struct file *file, struct folio *folio) { - struct page *page = &folio->page; - struct inode *inode = page_file_mapping(page)->host; + struct inode *inode = folio->mapping->host; int ret = -EAGAIN; - trace_f2fs_readpage(page, DATA); + trace_f2fs_readpage(folio, DATA); if (!f2fs_is_compress_backend_ready(inode)) { - unlock_page(page); + folio_unlock(folio); return -EOPNOTSUPP; } /* If the file has inline data, try to read it directly */ if (f2fs_has_inline_data(inode)) - ret = f2fs_read_inline_data(inode, page); + ret = f2fs_read_inline_data(inode, folio); if (ret == -EAGAIN) - ret = f2fs_mpage_readpages(inode, NULL, page); + ret = f2fs_mpage_readpages(inode, NULL, folio); return ret; } @@ -2558,8 +2493,9 @@ static void f2fs_readahead(struct readahead_control *rac) int f2fs_encrypt_one_page(struct f2fs_io_info *fio) { - struct inode *inode = fio->page->mapping->host; - struct page *mpage, *page; + struct inode *inode = fio_inode(fio); + struct folio *mfolio; + struct page *page; gfp_t gfp_flags = GFP_NOFS; if (!f2fs_encrypted_file(inode)) @@ -2567,14 +2503,11 @@ int f2fs_encrypt_one_page(struct f2fs_io_info *fio) page = fio->compressed_page ? fio->compressed_page : fio->page; - /* wait for GCed page writeback via META_MAPPING */ - f2fs_wait_on_block_writeback(inode, fio->old_blkaddr); - if (fscrypt_inode_uses_inline_crypto(inode)) return 0; retry_encrypt: - fio->encrypted_page = fscrypt_encrypt_pagecache_blocks(page, + fio->encrypted_page = fscrypt_encrypt_pagecache_blocks(page_folio(page), PAGE_SIZE, 0, gfp_flags); if (IS_ERR(fio->encrypted_page)) { /* flush pending IOs and wait for a while in the ENOMEM case */ @@ -2587,12 +2520,12 @@ retry_encrypt: return PTR_ERR(fio->encrypted_page); } - mpage = find_lock_page(META_MAPPING(fio->sbi), fio->old_blkaddr); - if (mpage) { - if (PageUptodate(mpage)) - memcpy(page_address(mpage), + mfolio = filemap_lock_folio(META_MAPPING(fio->sbi), fio->old_blkaddr); + if (!IS_ERR(mfolio)) { + if (folio_test_uptodate(mfolio)) + memcpy(folio_address(mfolio), page_address(fio->encrypted_page), PAGE_SIZE); - f2fs_put_page(mpage, 1); + f2fs_folio_put(mfolio, true); } return 0; } @@ -2664,7 +2597,12 @@ bool f2fs_should_update_outplace(struct inode *inode, struct f2fs_io_info *fio) return true; if (IS_NOQUOTA(inode)) return true; - if (f2fs_is_atomic_file(inode)) + if (f2fs_used_in_atomic_write(inode)) + return true; + /* rewrite low ratio compress data w/ OPU mode to avoid fragmentation */ + if (f2fs_compressed_file(inode) && + F2FS_OPTION(sbi).compress_mode == COMPR_MODE_USER && + is_inode_flag_set(inode, FI_ENABLE_COMPRESS)) return true; /* swap file is migrating in aligned write mode */ @@ -2677,8 +2615,6 @@ bool f2fs_should_update_outplace(struct inode *inode, struct f2fs_io_info *fio) if (fio) { if (page_private_gcing(fio->page)) return true; - if (page_private_dummy(fio->page)) - return true; if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED) && f2fs_is_checkpointed_data(sbi, fio->old_blkaddr))) return true; @@ -2688,7 +2624,7 @@ bool f2fs_should_update_outplace(struct inode *inode, struct f2fs_io_info *fio) static inline bool need_inplace_update(struct f2fs_io_info *fio) { - struct inode *inode = fio->page->mapping->host; + struct inode *inode = fio_inode(fio); if (f2fs_should_update_outplace(inode, fio)) return false; @@ -2698,28 +2634,28 @@ static inline bool need_inplace_update(struct f2fs_io_info *fio) int f2fs_do_write_data_page(struct f2fs_io_info *fio) { - struct page *page = fio->page; - struct inode *inode = page->mapping->host; + struct folio *folio = fio->folio; + struct inode *inode = folio->mapping->host; struct dnode_of_data dn; struct node_info ni; bool ipu_force = false; + bool atomic_commit; int err = 0; /* Use COW inode to make dnode_of_data for atomic write */ - if (f2fs_is_atomic_file(inode)) + atomic_commit = f2fs_is_atomic_file(inode) && + folio_test_f2fs_atomic(folio); + if (atomic_commit) set_new_dnode(&dn, F2FS_I(inode)->cow_inode, NULL, NULL, 0); else set_new_dnode(&dn, inode, NULL, NULL, 0); if (need_inplace_update(fio) && - f2fs_lookup_read_extent_cache_block(inode, page->index, + f2fs_lookup_read_extent_cache_block(inode, folio->index, &fio->old_blkaddr)) { if (!f2fs_is_valid_blkaddr(fio->sbi, fio->old_blkaddr, - DATA_GENERIC_ENHANCE)) { - f2fs_handle_error(fio->sbi, - ERROR_INVALID_BLKADDR); + DATA_GENERIC_ENHANCE)) return -EFSCORRUPTED; - } ipu_force = true; fio->need_lock = LOCK_DONE; @@ -2730,7 +2666,7 @@ int f2fs_do_write_data_page(struct f2fs_io_info *fio) if (fio->need_lock == LOCK_REQ && !f2fs_trylock_op(fio->sbi)) return -EAGAIN; - err = f2fs_get_dnode_of_data(&dn, page->index, LOOKUP_NODE); + err = f2fs_get_dnode_of_data(&dn, folio->index, LOOKUP_NODE); if (err) goto out; @@ -2738,8 +2674,8 @@ int f2fs_do_write_data_page(struct f2fs_io_info *fio) /* This page is already truncated */ if (fio->old_blkaddr == NULL_ADDR) { - ClearPageUptodate(page); - clear_page_private_gcing(page); + folio_clear_uptodate(folio); + folio_clear_f2fs_gcing(folio); goto out_writepage; } got_it: @@ -2747,10 +2683,13 @@ got_it: !f2fs_is_valid_blkaddr(fio->sbi, fio->old_blkaddr, DATA_GENERIC_ENHANCE)) { err = -EFSCORRUPTED; - f2fs_handle_error(fio->sbi, ERROR_INVALID_BLKADDR); goto out_writepage; } + /* wait for GCed page writeback via META_MAPPING */ + if (fio->meta_gc) + f2fs_wait_on_block_writeback(inode, fio->old_blkaddr); + /* * If current allocation needs SSR, * it had better in-place writes for updated data. @@ -2762,7 +2701,7 @@ got_it: if (err) goto out_writepage; - set_page_writeback(page); + folio_start_writeback(folio); f2fs_put_dnode(&dn); if (fio->need_lock == LOCK_REQ) f2fs_unlock_op(fio->sbi); @@ -2770,12 +2709,11 @@ got_it: if (err) { if (fscrypt_inode_uses_fs_layer_crypto(inode)) fscrypt_finalize_bounce_page(&fio->encrypted_page); - if (PageWriteback(page)) - end_page_writeback(page); + folio_end_writeback(folio); } else { set_inode_flag(inode, FI_UPDATE_WRITE); } - trace_f2fs_do_write_data_page(fio->page, IPU); + trace_f2fs_do_write_data_page(folio, IPU); return err; } @@ -2797,17 +2735,17 @@ got_it: if (err) goto out_writepage; - set_page_writeback(page); + folio_start_writeback(folio); if (fio->compr_blocks && fio->old_blkaddr == COMPRESS_ADDR) f2fs_i_compr_blocks_update(inode, fio->compr_blocks - 1, false); /* LFS mode write path */ f2fs_outplace_write_data(&dn, fio); - trace_f2fs_do_write_data_page(page, OPU); + trace_f2fs_do_write_data_page(folio, OPU); set_inode_flag(inode, FI_APPEND_WRITE); - if (page->index == 0) - set_inode_flag(inode, FI_FIRST_BLOCK_WRITTEN); + if (atomic_commit) + folio_clear_f2fs_atomic(folio); out_writepage: f2fs_put_dnode(&dn); out: @@ -2816,7 +2754,7 @@ out: return err; } -int f2fs_write_single_data_page(struct page *page, int *submitted, +int f2fs_write_single_data_page(struct folio *folio, int *submitted, struct bio **bio, sector_t *last_block, struct writeback_control *wbc, @@ -2824,12 +2762,12 @@ int f2fs_write_single_data_page(struct page *page, int *submitted, int compr_blocks, bool allow_balance) { - struct inode *inode = page->mapping->host; + struct inode *inode = folio->mapping->host; struct f2fs_sb_info *sbi = F2FS_I_SB(inode); loff_t i_size = i_size_read(inode); const pgoff_t end_index = ((unsigned long long)i_size) >> PAGE_SHIFT; - loff_t psize = (loff_t)(page->index + 1) << PAGE_SHIFT; + loff_t psize = (loff_t)(folio->index + 1) << PAGE_SHIFT; unsigned offset = 0; bool need_balance_fs = false; bool quota_inode = IS_NOQUOTA(inode); @@ -2841,23 +2779,23 @@ int f2fs_write_single_data_page(struct page *page, int *submitted, .op = REQ_OP_WRITE, .op_flags = wbc_to_write_flags(wbc), .old_blkaddr = NULL_ADDR, - .page = page, + .folio = folio, .encrypted_page = NULL, .submitted = 0, .compr_blocks = compr_blocks, - .need_lock = LOCK_RETRY, - .post_read = f2fs_post_read_required(inode) ? 1 : 0, + .need_lock = compr_blocks ? LOCK_DONE : LOCK_RETRY, + .meta_gc = f2fs_meta_inode_gc_required(inode) ? 1 : 0, .io_type = io_type, .io_wbc = wbc, .bio = bio, .last_block = last_block, }; - trace_f2fs_writepage(page, DATA); + trace_f2fs_writepage(folio, DATA); /* we should bypass data pages to proceed the kworker jobs */ if (unlikely(f2fs_cp_error(sbi))) { - mapping_set_error(page->mapping, -EIO); + mapping_set_error(folio->mapping, -EIO); /* * don't drop any dirty dentry pages for keeping lastest * directory structure. @@ -2875,7 +2813,7 @@ int f2fs_write_single_data_page(struct page *page, int *submitted, if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING))) goto redirty_out; - if (page->index < end_index || + if (folio->index < end_index || f2fs_verity_in_progress(inode) || compr_blocks) goto write; @@ -2885,14 +2823,11 @@ int f2fs_write_single_data_page(struct page *page, int *submitted, * this page does not have to be written to disk. */ offset = i_size & (PAGE_SIZE - 1); - if ((page->index >= end_index + 1) || !offset) + if ((folio->index >= end_index + 1) || !offset) goto out; - zero_user_segment(page, offset, PAGE_SIZE); + folio_zero_segment(folio, offset, folio_size(folio)); write: - if (f2fs_is_drop_cache(inode)) - goto out; - /* Dentry/quota blocks are controlled by checkpoint */ if (S_ISDIR(inode->i_mode) || quota_inode) { /* @@ -2912,16 +2847,10 @@ write: goto done; } - if (!wbc->for_reclaim) - need_balance_fs = true; - else if (has_not_enough_free_secs(sbi, 0, 0)) - goto redirty_out; - else - set_inode_flag(inode, FI_HOT_DATA); - + need_balance_fs = true; err = -EAGAIN; if (f2fs_has_inline_data(inode)) { - err = f2fs_write_inline_data(inode, page); + err = f2fs_write_inline_data(inode, folio); if (!err) goto out; } @@ -2929,6 +2858,7 @@ write: if (err == -EAGAIN) { err = f2fs_do_write_data_page(&fio); if (err == -EAGAIN) { + f2fs_bug_on(sbi, compr_blocks); fio.need_lock = LOCK_REQ; err = f2fs_do_write_data_page(&fio); } @@ -2950,17 +2880,10 @@ done: out: inode_dec_dirty_pages(inode); if (err) { - ClearPageUptodate(page); - clear_page_private_gcing(page); - } - - if (wbc->for_reclaim) { - f2fs_submit_merged_write_cond(sbi, NULL, page, 0, DATA); - clear_inode_flag(inode, FI_HOT_DATA); - f2fs_remove_dirty_inode(inode); - submitted = NULL; + folio_clear_uptodate(folio); + folio_clear_f2fs_gcing(folio); } - unlock_page(page); + folio_unlock(folio); if (!S_ISDIR(inode->i_mode) && !IS_NOQUOTA(inode) && !F2FS_I(inode)->wb_task && allow_balance) f2fs_balance_fs(sbi, need_balance_fs); @@ -2978,41 +2901,19 @@ out: return 0; redirty_out: - redirty_page_for_writepage(wbc, page); + folio_redirty_for_writepage(wbc, folio); /* * pageout() in MM translates EAGAIN, so calls handle_write_error() * -> mapping_set_error() -> set_bit(AS_EIO, ...). * file_write_and_wait_range() will see EIO error, which is critical * to return value of fsync() followed by atomic_write failure to user. */ - if (!err || wbc->for_reclaim) - return AOP_WRITEPAGE_ACTIVATE; - unlock_page(page); + folio_unlock(folio); + if (!err) + return 1; return err; } -static int f2fs_write_data_page(struct page *page, - struct writeback_control *wbc) -{ -#ifdef CONFIG_F2FS_FS_COMPRESSION - struct inode *inode = page->mapping->host; - - if (unlikely(f2fs_cp_error(F2FS_I_SB(inode)))) - goto out; - - if (f2fs_compressed_file(inode)) { - if (f2fs_is_compressed_cluster(inode, page->index)) { - redirty_page_for_writepage(wbc, page); - return AOP_WRITEPAGE_ACTIVATE; - } - } -out: -#endif - - return f2fs_write_single_data_page(page, NULL, NULL, NULL, - wbc, FS_DATA_IO, 0, true); -} - /* * This function was copied from write_cache_pages from mm/page-writeback.c. * The major change is making write step of cold data page separately from @@ -3024,7 +2925,8 @@ static int f2fs_write_cache_pages(struct address_space *mapping, { int ret = 0; int done = 0, retry = 0; - struct page *pages[F2FS_ONSTACK_PAGES]; + struct page *pages_local[F2FS_ONSTACK_PAGES]; + struct page **pages = pages_local; struct folio_batch fbatch; struct f2fs_sb_info *sbi = F2FS_M_SB(mapping); struct bio *bio = NULL; @@ -3048,6 +2950,7 @@ static int f2fs_write_cache_pages(struct address_space *mapping, #endif int nr_folios, p, idx; int nr_pages; + unsigned int max_pages = F2FS_ONSTACK_PAGES; pgoff_t index; pgoff_t end; /* Inclusive */ pgoff_t done_index; @@ -3057,6 +2960,15 @@ static int f2fs_write_cache_pages(struct address_space *mapping, int submitted = 0; int i; +#ifdef CONFIG_F2FS_FS_COMPRESSION + if (f2fs_compressed_file(inode) && + 1 << cc.log_cluster_size > F2FS_ONSTACK_PAGES) { + pages = f2fs_kzalloc(sbi, sizeof(struct page *) << + cc.log_cluster_size, GFP_NOFS | __GFP_NOFAIL); + max_pages = 1 << cc.log_cluster_size; + } +#endif + folio_batch_init(&fbatch); if (get_dirty_pages(mapping->host) <= @@ -3074,10 +2986,7 @@ static int f2fs_write_cache_pages(struct address_space *mapping, if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX) range_whole = 1; } - if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages) - tag = PAGECACHE_TAG_TOWRITE; - else - tag = PAGECACHE_TAG_DIRTY; + tag = wbc_to_tag(wbc); retry: retry = 0; if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages) @@ -3102,7 +3011,7 @@ again: add_more: pages[nr_pages] = folio_page(folio, idx); folio_get(folio); - if (++nr_pages == F2FS_ONSTACK_PAGES) { + if (++nr_pages == max_pages) { index = folio->index + idx + 1; folio_batch_release(&fbatch); goto write; @@ -3195,7 +3104,7 @@ continue_unlock: if (folio_test_writeback(folio)) { if (wbc->sync_mode == WB_SYNC_NONE) goto continue_unlock; - f2fs_wait_on_page_writeback(&folio->page, DATA, true, true); + f2fs_folio_wait_writeback(folio, DATA, true, true); } if (!folio_clear_dirty_for_io(folio)) @@ -3204,15 +3113,14 @@ continue_unlock: #ifdef CONFIG_F2FS_FS_COMPRESSION if (f2fs_compressed_file(inode)) { folio_get(folio); - f2fs_compress_ctx_add_page(&cc, &folio->page); + f2fs_compress_ctx_add_page(&cc, folio); continue; } #endif - ret = f2fs_write_single_data_page(&folio->page, + submitted = 0; + ret = f2fs_write_single_data_page(folio, &submitted, &bio, &last_block, wbc, io_type, 0, true); - if (ret == AOP_WRITEPAGE_ACTIVATE) - folio_unlock(folio); #ifdef CONFIG_F2FS_FS_COMPRESSION result: #endif @@ -3224,20 +3132,19 @@ result: * keep nr_to_write, since vfs uses this to * get # of written pages. */ - if (ret == AOP_WRITEPAGE_ACTIVATE) { + if (ret == 1) { ret = 0; goto next; } else if (ret == -EAGAIN) { ret = 0; if (wbc->sync_mode == WB_SYNC_ALL) { - f2fs_io_schedule_timeout( - DEFAULT_IO_TIMEOUT); + f2fs_schedule_timeout( + DEFAULT_SCHEDULE_TIMEOUT); goto retry_write; } goto next; } - done_index = folio->index + - folio_nr_pages(folio); + done_index = folio_next_index(folio); done = 1; break; } @@ -3285,6 +3192,11 @@ next: if (bio) f2fs_submit_merged_ipu_write(sbi, &bio, NULL); +#ifdef CONFIG_F2FS_FS_COMPRESSION + if (pages != pages_local) + kfree(pages); +#endif + return ret; } @@ -3309,6 +3221,19 @@ static inline bool __should_serialize_io(struct inode *inode, return false; } +static inline void account_writeback(struct inode *inode, bool inc) +{ + if (!f2fs_sb_has_compression(F2FS_I_SB(inode))) + return; + + f2fs_down_read(&F2FS_I(inode)->i_sem); + if (inc) + atomic_inc(&F2FS_I(inode)->writeback); + else + atomic_dec(&F2FS_I(inode)->writeback); + f2fs_up_read(&F2FS_I(inode)->i_sem); +} + static int __f2fs_write_data_pages(struct address_space *mapping, struct writeback_control *wbc, enum iostat_type io_type) @@ -3319,10 +3244,6 @@ static int __f2fs_write_data_pages(struct address_space *mapping, int ret; bool locked = false; - /* deal with chardevs and other special file */ - if (!mapping->a_ops->writepage) - return 0; - /* skip writing if there is no dirty page in this inode */ if (!get_dirty_pages(inode) && wbc->sync_mode == WB_SYNC_NONE) return 0; @@ -3358,10 +3279,14 @@ static int __f2fs_write_data_pages(struct address_space *mapping, locked = true; } + account_writeback(inode, true); + blk_start_plug(&plug); ret = f2fs_write_cache_pages(mapping, wbc, io_type); blk_finish_plug(&plug); + account_writeback(inode, false); + if (locked) mutex_unlock(&sbi->writepages); @@ -3412,13 +3337,13 @@ void f2fs_write_failed(struct inode *inode, loff_t to) } static int prepare_write_begin(struct f2fs_sb_info *sbi, - struct page *page, loff_t pos, unsigned len, + struct folio *folio, loff_t pos, unsigned int len, block_t *blk_addr, bool *node_changed) { - struct inode *inode = page->mapping->host; - pgoff_t index = page->index; + struct inode *inode = folio->mapping->host; + pgoff_t index = folio->index; struct dnode_of_data dn; - struct page *ipage; + struct folio *ifolio; bool locked = false; int flag = F2FS_GET_BLOCK_PRE_AIO; int err = 0; @@ -3443,29 +3368,34 @@ static int prepare_write_begin(struct f2fs_sb_info *sbi, restart: /* check inline_data */ - ipage = f2fs_get_node_page(sbi, inode->i_ino); - if (IS_ERR(ipage)) { - err = PTR_ERR(ipage); + ifolio = f2fs_get_inode_folio(sbi, inode->i_ino); + if (IS_ERR(ifolio)) { + err = PTR_ERR(ifolio); goto unlock_out; } - set_new_dnode(&dn, inode, ipage, ipage, 0); + set_new_dnode(&dn, inode, ifolio, ifolio, 0); if (f2fs_has_inline_data(inode)) { if (pos + len <= MAX_INLINE_DATA(inode)) { - f2fs_do_read_inline_data(page, ipage); + f2fs_do_read_inline_data(folio, ifolio); set_inode_flag(inode, FI_DATA_EXIST); if (inode->i_nlink) - set_page_private_inline(ipage); + folio_set_f2fs_inline(ifolio); goto out; } - err = f2fs_convert_inline_page(&dn, page); + err = f2fs_convert_inline_folio(&dn, folio); if (err || dn.data_blkaddr != NULL_ADDR) goto out; } if (!f2fs_lookup_read_extent_cache_block(inode, index, &dn.data_blkaddr)) { + if (IS_DEVICE_ALIASING(inode)) { + err = -ENODATA; + goto out; + } + if (locked) { err = f2fs_reserve_block(&dn, index); goto out; @@ -3498,14 +3428,14 @@ static int __find_data_block(struct inode *inode, pgoff_t index, block_t *blk_addr) { struct dnode_of_data dn; - struct page *ipage; + struct folio *ifolio; int err = 0; - ipage = f2fs_get_node_page(F2FS_I_SB(inode), inode->i_ino); - if (IS_ERR(ipage)) - return PTR_ERR(ipage); + ifolio = f2fs_get_inode_folio(F2FS_I_SB(inode), inode->i_ino); + if (IS_ERR(ifolio)) + return PTR_ERR(ifolio); - set_new_dnode(&dn, inode, ipage, ipage, 0); + set_new_dnode(&dn, inode, ifolio, ifolio, 0); if (!f2fs_lookup_read_extent_cache_block(inode, index, &dn.data_blkaddr)) { @@ -3526,17 +3456,17 @@ static int __reserve_data_block(struct inode *inode, pgoff_t index, { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct dnode_of_data dn; - struct page *ipage; + struct folio *ifolio; int err = 0; f2fs_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO); - ipage = f2fs_get_node_page(sbi, inode->i_ino); - if (IS_ERR(ipage)) { - err = PTR_ERR(ipage); + ifolio = f2fs_get_inode_folio(sbi, inode->i_ino); + if (IS_ERR(ifolio)) { + err = PTR_ERR(ifolio); goto unlock_out; } - set_new_dnode(&dn, inode, ipage, ipage, 0); + set_new_dnode(&dn, inode, ifolio, ifolio, 0); if (!f2fs_lookup_read_extent_cache_block(dn.inode, index, &dn.data_blkaddr)) @@ -3552,12 +3482,12 @@ unlock_out: } static int prepare_atomic_write_begin(struct f2fs_sb_info *sbi, - struct page *page, loff_t pos, unsigned int len, + struct folio *folio, loff_t pos, unsigned int len, block_t *blk_addr, bool *node_changed, bool *use_cow) { - struct inode *inode = page->mapping->host; + struct inode *inode = folio->mapping->host; struct inode *cow_inode = F2FS_I(inode)->cow_inode; - pgoff_t index = page->index; + pgoff_t index = folio->index; int err = 0; block_t ori_blk_addr = NULL_ADDR; @@ -3594,13 +3524,15 @@ reserve_block: return 0; } -static int f2fs_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, struct page **pagep, void **fsdata) +static int f2fs_write_begin(const struct kiocb *iocb, + struct address_space *mapping, + loff_t pos, unsigned len, struct folio **foliop, + void **fsdata) { struct inode *inode = mapping->host; struct f2fs_sb_info *sbi = F2FS_I_SB(inode); - struct page *page = NULL; - pgoff_t index = ((unsigned long long) pos) >> PAGE_SHIFT; + struct folio *folio; + pgoff_t index = pos >> PAGE_SHIFT; bool need_balance = false; bool use_cow = false; block_t blkaddr = NULL_ADDR; @@ -3616,7 +3548,7 @@ static int f2fs_write_begin(struct file *file, struct address_space *mapping, /* * We should check this at this moment to avoid deadlock on inode page * and #0 page. The locking rule for inline_data conversion should be: - * lock_page(page #0) -> lock_page(inode_page) + * folio_lock(folio #0) -> folio_lock(inode_page) */ if (index != 0) { err = f2fs_convert_inline_inode(inode); @@ -3627,18 +3559,20 @@ static int f2fs_write_begin(struct file *file, struct address_space *mapping, #ifdef CONFIG_F2FS_FS_COMPRESSION if (f2fs_compressed_file(inode)) { int ret; + struct page *page; *fsdata = NULL; if (len == PAGE_SIZE && !(f2fs_is_atomic_file(inode))) goto repeat; - ret = f2fs_prepare_compress_overwrite(inode, pagep, + ret = f2fs_prepare_compress_overwrite(inode, &page, index, fsdata); if (ret < 0) { err = ret; goto fail; } else if (ret) { + *foliop = page_folio(page); return 0; } } @@ -3646,92 +3580,93 @@ static int f2fs_write_begin(struct file *file, struct address_space *mapping, repeat: /* - * Do not use grab_cache_page_write_begin() to avoid deadlock due to - * wait_for_stable_page. Will wait that below with our IO control. + * Do not use FGP_STABLE to avoid deadlock. + * Will wait that below with our IO control. */ - page = f2fs_pagecache_get_page(mapping, index, - FGP_LOCK | FGP_WRITE | FGP_CREAT, GFP_NOFS); - if (!page) { - err = -ENOMEM; + folio = f2fs_filemap_get_folio(mapping, index, + FGP_LOCK | FGP_WRITE | FGP_CREAT | FGP_NOFS, + mapping_gfp_mask(mapping)); + if (IS_ERR(folio)) { + err = PTR_ERR(folio); goto fail; } /* TODO: cluster can be compressed due to race with .writepage */ - *pagep = page; + *foliop = folio; if (f2fs_is_atomic_file(inode)) - err = prepare_atomic_write_begin(sbi, page, pos, len, + err = prepare_atomic_write_begin(sbi, folio, pos, len, &blkaddr, &need_balance, &use_cow); else - err = prepare_write_begin(sbi, page, pos, len, + err = prepare_write_begin(sbi, folio, pos, len, &blkaddr, &need_balance); if (err) - goto fail; + goto put_folio; if (need_balance && !IS_NOQUOTA(inode) && has_not_enough_free_secs(sbi, 0, 0)) { - unlock_page(page); + folio_unlock(folio); f2fs_balance_fs(sbi, true); - lock_page(page); - if (page->mapping != mapping) { - /* The page got truncated from under us */ - f2fs_put_page(page, 1); + folio_lock(folio); + if (folio->mapping != mapping) { + /* The folio got truncated from under us */ + folio_unlock(folio); + folio_put(folio); goto repeat; } } - f2fs_wait_on_page_writeback(page, DATA, false, true); + f2fs_folio_wait_writeback(folio, DATA, false, true); - if (len == PAGE_SIZE || PageUptodate(page)) + if (len == folio_size(folio) || folio_test_uptodate(folio)) return 0; if (!(pos & (PAGE_SIZE - 1)) && (pos + len) >= i_size_read(inode) && !f2fs_verity_in_progress(inode)) { - zero_user_segment(page, len, PAGE_SIZE); + folio_zero_segment(folio, len, folio_size(folio)); return 0; } if (blkaddr == NEW_ADDR) { - zero_user_segment(page, 0, PAGE_SIZE); - SetPageUptodate(page); + folio_zero_segment(folio, 0, folio_size(folio)); + folio_mark_uptodate(folio); } else { if (!f2fs_is_valid_blkaddr(sbi, blkaddr, DATA_GENERIC_ENHANCE_READ)) { err = -EFSCORRUPTED; - f2fs_handle_error(sbi, ERROR_INVALID_BLKADDR); - goto fail; + goto put_folio; } - err = f2fs_submit_page_read(use_cow ? - F2FS_I(inode)->cow_inode : inode, page, - blkaddr, 0, true); - if (err) - goto fail; - - lock_page(page); - if (unlikely(page->mapping != mapping)) { - f2fs_put_page(page, 1); + f2fs_submit_page_read(use_cow ? + F2FS_I(inode)->cow_inode : inode, + folio, blkaddr, 0, true); + + folio_lock(folio); + if (unlikely(folio->mapping != mapping)) { + folio_unlock(folio); + folio_put(folio); goto repeat; } - if (unlikely(!PageUptodate(page))) { + if (unlikely(!folio_test_uptodate(folio))) { err = -EIO; - goto fail; + goto put_folio; } } return 0; +put_folio: + f2fs_folio_put(folio, true); fail: - f2fs_put_page(page, 1); f2fs_write_failed(inode, pos + len); return err; } -static int f2fs_write_end(struct file *file, +static int f2fs_write_end(const struct kiocb *iocb, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata) + struct folio *folio, void *fsdata) { - struct inode *inode = page->mapping->host; + struct inode *inode = folio->mapping->host; trace_f2fs_write_end(inode, pos, len, copied); @@ -3740,17 +3675,17 @@ static int f2fs_write_end(struct file *file, * should be PAGE_SIZE. Otherwise, we treat it with zero copied and * let generic_perform_write() try to copy data again through copied=0. */ - if (!PageUptodate(page)) { + if (!folio_test_uptodate(folio)) { if (unlikely(copied != len)) copied = 0; else - SetPageUptodate(page); + folio_mark_uptodate(folio); } #ifdef CONFIG_F2FS_FS_COMPRESSION /* overwrite compressed file */ if (f2fs_compressed_file(inode) && fsdata) { - f2fs_compress_write_end(inode, fsdata, page->index, copied); + f2fs_compress_write_end(inode, fsdata, folio->index, copied); f2fs_update_time(F2FS_I_SB(inode), REQ_TIME); if (pos + copied > i_size_read(inode) && @@ -3763,7 +3698,10 @@ static int f2fs_write_end(struct file *file, if (!copied) goto unlock_out; - set_page_dirty(page); + folio_mark_dirty(folio); + + if (f2fs_is_atomic_file(inode)) + folio_set_f2fs_atomic(folio); if (pos + copied > i_size_read(inode) && !f2fs_verity_in_progress(inode)) { @@ -3773,7 +3711,7 @@ static int f2fs_write_end(struct file *file, pos + copied); } unlock_out: - f2fs_put_page(page, 1); + f2fs_folio_put(folio, true); f2fs_update_time(F2FS_I_SB(inode), REQ_TIME); return copied; } @@ -3797,7 +3735,7 @@ void f2fs_invalidate_folio(struct folio *folio, size_t offset, size_t length) f2fs_remove_dirty_inode(inode); } } - clear_page_private_all(&folio->page); + folio_detach_private(folio); } bool f2fs_release_folio(struct folio *folio, gfp_t wait) @@ -3806,7 +3744,7 @@ bool f2fs_release_folio(struct folio *folio, gfp_t wait) if (folio_test_dirty(folio)) return false; - clear_page_private_all(&folio->page); + folio_detach_private(folio); return true; } @@ -3815,7 +3753,7 @@ static bool f2fs_dirty_data_folio(struct address_space *mapping, { struct inode *inode = mapping->host; - trace_f2fs_set_page_dirty(&folio->page, DATA); + trace_f2fs_set_page_dirty(folio, DATA); if (!folio_test_uptodate(folio)) folio_mark_uptodate(folio); @@ -3900,38 +3838,48 @@ static int f2fs_migrate_blocks(struct inode *inode, block_t start_blk, struct f2fs_sb_info *sbi = F2FS_I_SB(inode); unsigned int blkofs; unsigned int blk_per_sec = BLKS_PER_SEC(sbi); + unsigned int end_blk = start_blk + blkcnt - 1; unsigned int secidx = start_blk / blk_per_sec; - unsigned int end_sec = secidx + blkcnt / blk_per_sec; + unsigned int end_sec; int ret = 0; + if (!blkcnt) + return 0; + end_sec = end_blk / blk_per_sec; + f2fs_down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); filemap_invalidate_lock(inode->i_mapping); set_inode_flag(inode, FI_ALIGNED_WRITE); set_inode_flag(inode, FI_OPU_WRITE); - for (; secidx < end_sec; secidx++) { + for (; secidx <= end_sec; secidx++) { + unsigned int blkofs_end = secidx == end_sec ? + end_blk % blk_per_sec : blk_per_sec - 1; + f2fs_down_write(&sbi->pin_sem); - f2fs_lock_op(sbi); - f2fs_allocate_new_section(sbi, CURSEG_COLD_DATA_PINNED, false); - f2fs_unlock_op(sbi); + ret = f2fs_allocate_pinning_section(sbi); + if (ret) { + f2fs_up_write(&sbi->pin_sem); + break; + } set_inode_flag(inode, FI_SKIP_WRITES); - for (blkofs = 0; blkofs < blk_per_sec; blkofs++) { - struct page *page; + for (blkofs = 0; blkofs <= blkofs_end; blkofs++) { + struct folio *folio; unsigned int blkidx = secidx * blk_per_sec + blkofs; - page = f2fs_get_lock_data_page(inode, blkidx, true); - if (IS_ERR(page)) { + folio = f2fs_get_lock_data_folio(inode, blkidx, true); + if (IS_ERR(folio)) { f2fs_up_write(&sbi->pin_sem); - ret = PTR_ERR(page); + ret = PTR_ERR(folio); goto done; } - set_page_dirty(page); - f2fs_put_page(page, 1); + folio_mark_dirty(folio); + f2fs_folio_put(folio, true); } clear_inode_flag(inode, FI_SKIP_WRITES); @@ -3961,15 +3909,14 @@ static int check_swap_activate(struct swap_info_struct *sis, struct address_space *mapping = swap_file->f_mapping; struct inode *inode = mapping->host; struct f2fs_sb_info *sbi = F2FS_I_SB(inode); - sector_t cur_lblock; - sector_t last_lblock; - sector_t pblock; - sector_t lowest_pblock = -1; - sector_t highest_pblock = 0; + block_t cur_lblock; + block_t last_lblock; + block_t pblock; + block_t lowest_pblock = -1; + block_t highest_pblock = 0; int nr_extents = 0; - unsigned long nr_pblocks; + unsigned int nr_pblocks; unsigned int blks_per_sec = BLKS_PER_SEC(sbi); - unsigned int sec_blks_mask = BLKS_PER_SEC(sbi) - 1; unsigned int not_aligned = 0; int ret = 0; @@ -3978,7 +3925,7 @@ static int check_swap_activate(struct swap_info_struct *sis, * to be very smart. */ cur_lblock = 0; - last_lblock = bytes_to_blks(inode, i_size_read(inode)); + last_lblock = F2FS_BYTES_TO_BLK(i_size_read(inode)); while (cur_lblock < last_lblock && cur_lblock < sis->max) { struct f2fs_map_blocks map; @@ -4007,28 +3954,35 @@ retry: pblock = map.m_pblk; nr_pblocks = map.m_len; - if ((pblock - SM_I(sbi)->main_blkaddr) & sec_blks_mask || - nr_pblocks & sec_blks_mask) { + if ((pblock - SM_I(sbi)->main_blkaddr) % blks_per_sec || + nr_pblocks % blks_per_sec || + f2fs_is_sequential_zone_area(sbi, pblock)) { + bool last_extent = false; + not_aligned++; nr_pblocks = roundup(nr_pblocks, blks_per_sec); if (cur_lblock + nr_pblocks > sis->max) nr_pblocks -= blks_per_sec; + /* this extent is last one */ if (!nr_pblocks) { - /* this extent is last one */ - nr_pblocks = map.m_len; - f2fs_warn(sbi, "Swapfile: last extent is not aligned to section"); - goto next; + nr_pblocks = last_lblock - cur_lblock; + last_extent = true; } ret = f2fs_migrate_blocks(inode, cur_lblock, nr_pblocks); - if (ret) + if (ret) { + if (ret == -ENOENT) + ret = -EINVAL; goto out; - goto retry; + } + + if (!last_extent) + goto retry; } -next: + if (cur_lblock + nr_pblocks >= sis->max) nr_pblocks = sis->max - cur_lblock; @@ -4054,10 +4008,9 @@ next: cur_lblock = 1; /* force Empty message */ sis->max = cur_lblock; sis->pages = cur_lblock - 1; - sis->highest_bit = cur_lblock - 1; out: if (not_aligned) - f2fs_warn(sbi, "Swapfile (%u) is not align to section: 1) creat(), 2) ioctl(F2FS_IOC_SET_PIN_FILE), 3) fallocate(%u * N)", + f2fs_warn(sbi, "Swapfile (%u) is not align to section: 1) creat(), 2) ioctl(F2FS_IOC_SET_PIN_FILE), 3) fallocate(%lu * N)", not_aligned, blks_per_sec * F2FS_BLKSIZE); return ret; } @@ -4066,17 +4019,17 @@ static int f2fs_swap_activate(struct swap_info_struct *sis, struct file *file, sector_t *span) { struct inode *inode = file_inode(file); + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); int ret; if (!S_ISREG(inode->i_mode)) return -EINVAL; - if (f2fs_readonly(F2FS_I_SB(inode)->sb)) + if (f2fs_readonly(sbi->sb)) return -EROFS; - if (f2fs_lfs_mode(F2FS_I_SB(inode))) { - f2fs_err(F2FS_I_SB(inode), - "Swapfile not supported in LFS mode"); + if (f2fs_lfs_mode(sbi) && !f2fs_sb_has_blkzoned(sbi)) { + f2fs_err(sbi, "Swapfile not supported in LFS mode"); return -EINVAL; } @@ -4087,6 +4040,10 @@ static int f2fs_swap_activate(struct swap_info_struct *sis, struct file *file, if (!f2fs_disable_compressed_file(inode)) return -EINVAL; + ret = filemap_fdatawrite(inode->i_mapping); + if (ret < 0) + return ret; + f2fs_precache_extents(inode); ret = check_swap_activate(sis, file, span); @@ -4095,7 +4052,7 @@ static int f2fs_swap_activate(struct swap_info_struct *sis, struct file *file, stat_inc_swapfile_inode(inode); set_inode_flag(inode, FI_PIN_FILE); - f2fs_update_time(F2FS_I_SB(inode), REQ_TIME); + f2fs_update_time(sbi, REQ_TIME); return ret; } @@ -4121,7 +4078,6 @@ static void f2fs_swap_deactivate(struct file *file) const struct address_space_operations f2fs_dblock_aops = { .read_folio = f2fs_read_data_folio, .readahead = f2fs_readahead, - .writepage = f2fs_write_data_page, .writepages = f2fs_write_data_pages, .write_begin = f2fs_write_begin, .write_end = f2fs_write_end, @@ -4134,13 +4090,13 @@ const struct address_space_operations f2fs_dblock_aops = { .swap_deactivate = f2fs_swap_deactivate, }; -void f2fs_clear_page_cache_dirty_tag(struct page *page) +void f2fs_clear_page_cache_dirty_tag(struct folio *folio) { - struct address_space *mapping = page_mapping(page); + struct address_space *mapping = folio->mapping; unsigned long flags; xa_lock_irqsave(&mapping->i_pages, flags); - __xa_clear_mark(&mapping->i_pages, page_index(page), + __xa_clear_mark(&mapping->i_pages, folio->index, PAGECACHE_TAG_DIRTY); xa_unlock_irqrestore(&mapping->i_pages, flags); } @@ -4206,22 +4162,33 @@ static int f2fs_iomap_begin(struct inode *inode, loff_t offset, loff_t length, unsigned int flags, struct iomap *iomap, struct iomap *srcmap) { - struct f2fs_map_blocks map = {}; + struct f2fs_map_blocks map = { NULL, }; pgoff_t next_pgofs = 0; int err; - map.m_lblk = bytes_to_blks(inode, offset); - map.m_len = bytes_to_blks(inode, offset + length - 1) - map.m_lblk + 1; + map.m_lblk = F2FS_BYTES_TO_BLK(offset); + map.m_len = F2FS_BYTES_TO_BLK(offset + length - 1) - map.m_lblk + 1; map.m_next_pgofs = &next_pgofs; - map.m_seg_type = f2fs_rw_hint_to_seg_type(inode->i_write_hint); - if (flags & IOMAP_WRITE) + map.m_seg_type = f2fs_rw_hint_to_seg_type(F2FS_I_SB(inode), + inode->i_write_hint); + if (flags & IOMAP_WRITE && iomap->private) { + map.m_last_pblk = (unsigned long)iomap->private; + iomap->private = NULL; + } + + /* + * If the blocks being overwritten are already allocated, + * f2fs_map_lock and f2fs_balance_fs are not necessary. + */ + if ((flags & IOMAP_WRITE) && + !f2fs_overwrite_io(inode, offset, length)) map.m_may_create = true; err = f2fs_map_blocks(inode, &map, F2FS_GET_BLOCK_DIO); if (err) return err; - iomap->offset = blks_to_bytes(inode, map.m_lblk); + iomap->offset = F2FS_BLK_TO_BYTES(map.m_lblk); /* * When inline encryption is enabled, sometimes I/O to an encrypted file @@ -4234,29 +4201,41 @@ static int f2fs_iomap_begin(struct inode *inode, loff_t offset, loff_t length, * We should never see delalloc or compressed extents here based on * prior flushing and checks. */ - if (WARN_ON_ONCE(map.m_pblk == NEW_ADDR)) - return -EINVAL; if (WARN_ON_ONCE(map.m_pblk == COMPRESS_ADDR)) return -EINVAL; - if (map.m_pblk != NULL_ADDR) { - iomap->length = blks_to_bytes(inode, map.m_len); + if (map.m_flags & F2FS_MAP_MAPPED) { + if (WARN_ON_ONCE(map.m_pblk == NEW_ADDR)) + return -EINVAL; + + iomap->length = F2FS_BLK_TO_BYTES(map.m_len); iomap->type = IOMAP_MAPPED; iomap->flags |= IOMAP_F_MERGED; iomap->bdev = map.m_bdev; - iomap->addr = blks_to_bytes(inode, map.m_pblk); + iomap->addr = F2FS_BLK_TO_BYTES(map.m_pblk); + + if (flags & IOMAP_WRITE && map.m_last_pblk) + iomap->private = (void *)map.m_last_pblk; } else { if (flags & IOMAP_WRITE) return -ENOTBLK; - iomap->length = blks_to_bytes(inode, next_pgofs) - - iomap->offset; - iomap->type = IOMAP_HOLE; + + if (map.m_pblk == NULL_ADDR) { + iomap->length = F2FS_BLK_TO_BYTES(next_pgofs) - + iomap->offset; + iomap->type = IOMAP_HOLE; + } else if (map.m_pblk == NEW_ADDR) { + iomap->length = F2FS_BLK_TO_BYTES(map.m_len); + iomap->type = IOMAP_UNWRITTEN; + } else { + f2fs_bug_on(F2FS_I_SB(inode), 1); + } iomap->addr = IOMAP_NULL_ADDR; } if (map.m_flags & F2FS_MAP_NEW) iomap->flags |= IOMAP_F_NEW; - if ((inode->i_state & I_DIRTY_DATASYNC) || + if ((inode_state_read_once(inode) & I_DIRTY_DATASYNC) || offset + length > i_size_read(inode)) iomap->flags |= IOMAP_F_DIRTY; |