diff options
Diffstat (limited to 'fs/f2fs/data.c')
| -rw-r--r-- | fs/f2fs/data.c | 2140 |
1 files changed, 1217 insertions, 923 deletions
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index b27b72107911..a71e818cd67b 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -8,22 +8,24 @@ #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> -#include <linux/backing-dev.h> #include <linux/pagevec.h> #include <linux/blkdev.h> #include <linux/bio.h> +#include <linux/blk-crypto.h> #include <linux/swap.h> #include <linux/prefetch.h> #include <linux/uio.h> -#include <linux/cleancache.h> #include <linux/sched/signal.h> +#include <linux/fiemap.h> +#include <linux/iomap.h> #include "f2fs.h" #include "node.h" #include "segment.h" -#include "trace.h" +#include "iostat.h" #include <trace/events/f2fs.h> #define NUM_PREALLOC_POST_READ_CTXS 128 @@ -48,31 +50,6 @@ void f2fs_destroy_bioset(void) bioset_exit(&f2fs_bioset); } -static inline struct bio *__f2fs_bio_alloc(gfp_t gfp_mask, - unsigned int nr_iovecs) -{ - return bio_alloc_bioset(gfp_mask, nr_iovecs, &f2fs_bioset); -} - -struct bio *f2fs_bio_alloc(struct f2fs_sb_info *sbi, int npages, bool no_fail) -{ - struct bio *bio; - - if (no_fail) { - /* No failure on bio allocation */ - bio = __f2fs_bio_alloc(GFP_NOIO, npages); - if (!bio) - bio = __f2fs_bio_alloc(GFP_NOIO | __GFP_NOFAIL, npages); - return bio; - } - if (time_to_inject(sbi, FAULT_ALLOC_BIO)) { - f2fs_show_injection_info(sbi, FAULT_ALLOC_BIO); - return NULL; - } - - return __f2fs_bio_alloc(GFP_KERNEL, npages); -} - static bool __is_cp_guaranteed(struct page *page) { struct address_space *mapping = page->mapping; @@ -82,18 +59,18 @@ static bool __is_cp_guaranteed(struct page *page) if (!mapping) return false; - if (f2fs_is_compressed_page(page)) - return false; - inode = mapping->host; sbi = F2FS_I_SB(inode); if (inode->i_ino == F2FS_META_INO(sbi) || - inode->i_ino == F2FS_NODE_INO(sbi) || - S_ISDIR(inode->i_mode) || - (S_ISREG(inode->i_mode) && - (f2fs_is_atomic_file(inode) || IS_NOQUOTA(inode))) || - is_cold_data(page)) + inode->i_ino == F2FS_NODE_INO(sbi) || + 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)) return true; return false; } @@ -117,9 +94,21 @@ static enum count_type __read_io_type(struct page *page) /* postprocessing steps for read bios */ enum bio_post_read_step { - STEP_DECRYPT, - STEP_DECOMPRESS, - STEP_VERITY, +#ifdef CONFIG_FS_ENCRYPTION + STEP_DECRYPT = 1 << 0, +#else + STEP_DECRYPT = 0, /* compile out the decryption-related code */ +#endif +#ifdef CONFIG_F2FS_FS_COMPRESSION + STEP_DECOMPRESS = 1 << 1, +#else + STEP_DECOMPRESS = 0, /* compile out the decompression-related code */ +#endif +#ifdef CONFIG_FS_VERITY + STEP_VERITY = 1 << 2, +#else + STEP_VERITY = 0, /* compile out the verity-related code */ +#endif }; struct bio_post_read_ctx { @@ -127,25 +116,30 @@ struct bio_post_read_ctx { struct f2fs_sb_info *sbi; struct work_struct work; unsigned int enabled_steps; + block_t fs_blkaddr; }; -static void __read_end_io(struct bio *bio, bool compr, bool verity) +static void f2fs_finish_read_bio(struct bio *bio, bool in_task) { - struct page *page; struct bio_vec *bv; struct bvec_iter_all iter_all; + /* + * Update and unlock the bio's pagecache pages, and put the + * decompression context for any compressed pages. + */ bio_for_each_segment_all(bv, bio, iter_all) { - page = bv->bv_page; + struct page *page = bv->bv_page; -#ifdef CONFIG_F2FS_FS_COMPRESSION - if (compr && f2fs_is_compressed_page(page)) { - f2fs_decompress_pages(bio, page, verity); + if (f2fs_is_compressed_page(page)) { + if (bio->bi_status) + f2fs_end_read_compressed_page(page, true, 0, + in_task); + f2fs_put_page_dic(page, in_task); continue; } -#endif - /* PG_error was set if any post_read step failed */ + /* PG_error was set if verity failed. */ if (bio->bi_status || PageError(page)) { ClearPageUptodate(page); /* will re-read again later */ @@ -156,163 +150,176 @@ static void __read_end_io(struct bio *bio, bool compr, bool verity) dec_page_count(F2FS_P_SB(page), __read_io_type(page)); unlock_page(page); } -} - -static void f2fs_release_read_bio(struct bio *bio); -static void __f2fs_read_end_io(struct bio *bio, bool compr, bool verity) -{ - if (!compr) - __read_end_io(bio, false, verity); - f2fs_release_read_bio(bio); -} -static void f2fs_decompress_bio(struct bio *bio, bool verity) -{ - __read_end_io(bio, true, verity); -} - -static void bio_post_read_processing(struct bio_post_read_ctx *ctx); - -static void f2fs_decrypt_work(struct bio_post_read_ctx *ctx) -{ - fscrypt_decrypt_bio(ctx->bio); -} - -static void f2fs_decompress_work(struct bio_post_read_ctx *ctx) -{ - f2fs_decompress_bio(ctx->bio, ctx->enabled_steps & (1 << STEP_VERITY)); -} - -#ifdef CONFIG_F2FS_FS_COMPRESSION -static void f2fs_verify_pages(struct page **rpages, unsigned int cluster_size) -{ - f2fs_decompress_end_io(rpages, cluster_size, false, true); -} - -static void f2fs_verify_bio(struct bio *bio) -{ - struct page *page = bio_first_page_all(bio); - struct decompress_io_ctx *dic = - (struct decompress_io_ctx *)page_private(page); - - f2fs_verify_pages(dic->rpages, dic->cluster_size); - f2fs_free_dic(dic); + if (bio->bi_private) + mempool_free(bio->bi_private, bio_post_read_ctx_pool); + bio_put(bio); } -#endif -static void f2fs_verity_work(struct work_struct *work) +static void f2fs_verify_bio(struct work_struct *work) { struct bio_post_read_ctx *ctx = container_of(work, struct bio_post_read_ctx, work); struct bio *bio = ctx->bio; -#ifdef CONFIG_F2FS_FS_COMPRESSION - unsigned int enabled_steps = ctx->enabled_steps; -#endif + bool may_have_compressed_pages = (ctx->enabled_steps & STEP_DECOMPRESS); /* - * fsverity_verify_bio() may call readpages() again, and while verity - * will be disabled for this, decryption may still be needed, resulting - * in another bio_post_read_ctx being allocated. So to prevent - * deadlocks we need to release the current ctx to the mempool first. - * This assumes that verity is the last post-read step. + * fsverity_verify_bio() may call readahead() again, and while verity + * will be disabled for this, decryption and/or decompression may still + * be needed, resulting in another bio_post_read_ctx being allocated. + * So to prevent deadlocks we need to release the current ctx to the + * mempool first. This assumes that verity is the last post-read step. */ mempool_free(ctx, bio_post_read_ctx_pool); bio->bi_private = NULL; -#ifdef CONFIG_F2FS_FS_COMPRESSION - /* previous step is decompression */ - if (enabled_steps & (1 << STEP_DECOMPRESS)) { - f2fs_verify_bio(bio); - f2fs_release_read_bio(bio); - return; + /* + * Verify the bio's pages with fs-verity. Exclude compressed pages, + * 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; + + bio_for_each_segment_all(bv, bio, iter_all) { + struct page *page = bv->bv_page; + + if (!f2fs_is_compressed_page(page) && + !fsverity_verify_page(page)) + SetPageError(page); + } + } else { + fsverity_verify_bio(bio); } -#endif - fsverity_verify_bio(bio); - __f2fs_read_end_io(bio, false, false); + f2fs_finish_read_bio(bio, true); } -static void f2fs_post_read_work(struct work_struct *work) +/* + * If the bio's data needs to be verified with fs-verity, then enqueue the + * verity work for the bio. Otherwise finish the bio now. + * + * Note that to avoid deadlocks, the verity work can't be done on the + * decryption/decompression workqueue. This is because verifying the data pages + * can involve reading verity metadata pages from the file, and these verity + * metadata pages may be encrypted and/or compressed. + */ +static void f2fs_verify_and_finish_bio(struct bio *bio, bool in_task) { - struct bio_post_read_ctx *ctx = - container_of(work, struct bio_post_read_ctx, work); - - if (ctx->enabled_steps & (1 << STEP_DECRYPT)) - f2fs_decrypt_work(ctx); + struct bio_post_read_ctx *ctx = bio->bi_private; - if (ctx->enabled_steps & (1 << STEP_DECOMPRESS)) - f2fs_decompress_work(ctx); - - if (ctx->enabled_steps & (1 << STEP_VERITY)) { - INIT_WORK(&ctx->work, f2fs_verity_work); + if (ctx && (ctx->enabled_steps & STEP_VERITY)) { + INIT_WORK(&ctx->work, f2fs_verify_bio); fsverity_enqueue_verify_work(&ctx->work); - return; + } else { + f2fs_finish_read_bio(bio, in_task); } - - __f2fs_read_end_io(ctx->bio, - ctx->enabled_steps & (1 << STEP_DECOMPRESS), false); } -static void f2fs_enqueue_post_read_work(struct f2fs_sb_info *sbi, - struct work_struct *work) +/* + * Handle STEP_DECOMPRESS by decompressing any compressed clusters whose last + * remaining page was read by @ctx->bio. + * + * Note that a bio may span clusters (even a mix of compressed and uncompressed + * clusters) or be for just part of a cluster. STEP_DECOMPRESS just indicates + * that the bio includes at least one compressed page. The actual decompression + * is done on a per-cluster basis, not a per-bio basis. + */ +static void f2fs_handle_step_decompress(struct bio_post_read_ctx *ctx, + bool in_task) { - queue_work(sbi->post_read_wq, work); -} + struct bio_vec *bv; + struct bvec_iter_all iter_all; + 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; + + if (f2fs_is_compressed_page(page)) + f2fs_end_read_compressed_page(page, false, blkaddr, + in_task); + else + all_compressed = false; + + blkaddr++; + } -static void bio_post_read_processing(struct bio_post_read_ctx *ctx) -{ /* - * We use different work queues for decryption and for verity because - * verity may require reading metadata pages that need decryption, and - * we shouldn't recurse to the same workqueue. + * Optimization: if all the bio's pages are compressed, then scheduling + * the per-bio verity work is unnecessary, as verity will be fully + * handled at the compression cluster level. */ + if (all_compressed) + ctx->enabled_steps &= ~STEP_VERITY; +} - if (ctx->enabled_steps & (1 << STEP_DECRYPT) || - ctx->enabled_steps & (1 << STEP_DECOMPRESS)) { - INIT_WORK(&ctx->work, f2fs_post_read_work); - f2fs_enqueue_post_read_work(ctx->sbi, &ctx->work); - return; - } +static void f2fs_post_read_work(struct work_struct *work) +{ + struct bio_post_read_ctx *ctx = + container_of(work, struct bio_post_read_ctx, work); + struct bio *bio = ctx->bio; - if (ctx->enabled_steps & (1 << STEP_VERITY)) { - INIT_WORK(&ctx->work, f2fs_verity_work); - fsverity_enqueue_verify_work(&ctx->work); + if ((ctx->enabled_steps & STEP_DECRYPT) && !fscrypt_decrypt_bio(bio)) { + f2fs_finish_read_bio(bio, true); return; } - __f2fs_read_end_io(ctx->bio, false, false); -} + if (ctx->enabled_steps & STEP_DECOMPRESS) + f2fs_handle_step_decompress(ctx, true); -static bool f2fs_bio_post_read_required(struct bio *bio) -{ - return bio->bi_private; + f2fs_verify_and_finish_bio(bio, true); } static void f2fs_read_end_io(struct bio *bio) { struct f2fs_sb_info *sbi = F2FS_P_SB(bio_first_page_all(bio)); + struct bio_post_read_ctx *ctx; + bool intask = in_task(); + + iostat_update_and_unbind_ctx(bio, 0); + ctx = bio->bi_private; if (time_to_inject(sbi, FAULT_READ_IO)) { f2fs_show_injection_info(sbi, FAULT_READ_IO); bio->bi_status = BLK_STS_IOERR; } - if (f2fs_bio_post_read_required(bio)) { - struct bio_post_read_ctx *ctx = bio->bi_private; - - bio_post_read_processing(ctx); + if (bio->bi_status) { + f2fs_finish_read_bio(bio, intask); return; } - __f2fs_read_end_io(bio, false, false); + if (ctx) { + unsigned int enabled_steps = ctx->enabled_steps & + (STEP_DECRYPT | STEP_DECOMPRESS); + + /* + * If we have only decompression step between decompression and + * decrypt, we don't need post processing for this. + */ + if (enabled_steps == STEP_DECOMPRESS && + !f2fs_low_mem_mode(sbi)) { + f2fs_handle_step_decompress(ctx, intask); + } else if (enabled_steps) { + INIT_WORK(&ctx->work, f2fs_post_read_work); + queue_work(ctx->sbi->post_read_wq, &ctx->work); + return; + } + } + + f2fs_verify_and_finish_bio(bio, intask); } static void f2fs_write_end_io(struct bio *bio) { - struct f2fs_sb_info *sbi = bio->bi_private; + struct f2fs_sb_info *sbi; struct bio_vec *bvec; struct bvec_iter_all iter_all; + iostat_update_and_unbind_ctx(bio, 1); + sbi = bio->bi_private; + if (time_to_inject(sbi, FAULT_WRITE_IO)) { f2fs_show_injection_info(sbi, FAULT_WRITE_IO); bio->bi_status = BLK_STS_IOERR; @@ -322,14 +329,14 @@ static void f2fs_write_end_io(struct bio *bio) struct page *page = bvec->bv_page; enum count_type type = WB_DATA_TYPE(page); - if (IS_DUMMY_WRITTEN_PAGE(page)) { - set_page_private(page, (unsigned long)NULL); - ClearPagePrivate(page); + if (page_private_dummy(page)) { + clear_page_private_dummy(page); unlock_page(page); mempool_free(page, sbi->write_io_dummy); if (unlikely(bio->bi_status)) - f2fs_stop_checkpoint(sbi, true); + f2fs_stop_checkpoint(sbi, true, + STOP_CP_REASON_WRITE_FAIL); continue; } @@ -345,7 +352,8 @@ static void f2fs_write_end_io(struct bio *bio) if (unlikely(bio->bi_status)) { mapping_set_error(page->mapping, -EIO); if (type == F2FS_WB_CP_DATA) - f2fs_stop_checkpoint(sbi, true); + f2fs_stop_checkpoint(sbi, true, + STOP_CP_REASON_WRITE_FAIL); } f2fs_bug_on(sbi, page->mapping == NODE_MAPPING(sbi) && @@ -354,7 +362,7 @@ static void f2fs_write_end_io(struct bio *bio) dec_page_count(sbi, type); if (f2fs_in_warm_node_list(sbi, page)) f2fs_del_fsync_node_entry(sbi, page); - clear_cold_data(page); + clear_page_private_gcing(page); end_page_writeback(page); } if (!get_pages(sbi, F2FS_WB_CP_DATA) && @@ -364,11 +372,8 @@ static void f2fs_write_end_io(struct bio *bio) bio_put(bio); } -/* - * Return true, if pre_bio's bdev is same as its target device. - */ struct block_device *f2fs_target_device(struct f2fs_sb_info *sbi, - block_t blk_addr, struct bio *bio) + block_t blk_addr, sector_t *sector) { struct block_device *bdev = sbi->sb->s_bdev; int i; @@ -383,10 +388,9 @@ struct block_device *f2fs_target_device(struct f2fs_sb_info *sbi, } } } - if (bio) { - bio_set_dev(bio, bdev); - bio->bi_iter.bi_sector = SECTOR_FROM_BLOCK(blk_addr); - } + + if (sector) + *sector = SECTOR_FROM_BLOCK(blk_addr); return bdev; } @@ -403,39 +407,91 @@ int f2fs_target_device_index(struct f2fs_sb_info *sbi, block_t blkaddr) return 0; } -static bool __same_bdev(struct f2fs_sb_info *sbi, - block_t blk_addr, struct bio *bio) +static blk_opf_t f2fs_io_flags(struct f2fs_io_info *fio) { - struct block_device *b = f2fs_target_device(sbi, blk_addr, NULL); - return bio->bi_disk == b->bd_disk && bio->bi_partno == b->bd_partno; + unsigned int temp_mask = (1 << NR_TEMP_TYPE) - 1; + unsigned int fua_flag, meta_flag, io_flag; + blk_opf_t op_flags = 0; + + if (fio->op != REQ_OP_WRITE) + return 0; + if (fio->type == DATA) + io_flag = fio->sbi->data_io_flag; + else if (fio->type == NODE) + io_flag = fio->sbi->node_io_flag; + else + return 0; + + fua_flag = io_flag & temp_mask; + meta_flag = (io_flag >> NR_TEMP_TYPE) & temp_mask; + + /* + * data/node io flag bits per temp: + * REQ_META | REQ_FUA | + * 5 | 4 | 3 | 2 | 1 | 0 | + * Cold | Warm | Hot | Cold | Warm | Hot | + */ + if ((1 << fio->temp) & meta_flag) + op_flags |= REQ_META; + if ((1 << fio->temp) & fua_flag) + op_flags |= REQ_FUA; + return op_flags; } -/* - * Low-level block read/write IO operations. - */ static struct bio *__bio_alloc(struct f2fs_io_info *fio, int npages) { struct f2fs_sb_info *sbi = fio->sbi; + struct block_device *bdev; + sector_t sector; struct bio *bio; - bio = f2fs_bio_alloc(sbi, npages, true); - - f2fs_target_device(sbi, fio->new_blkaddr, bio); + bdev = f2fs_target_device(sbi, fio->new_blkaddr, §or); + bio = bio_alloc_bioset(bdev, npages, + fio->op | fio->op_flags | f2fs_io_flags(fio), + GFP_NOIO, &f2fs_bioset); + bio->bi_iter.bi_sector = sector; if (is_read_io(fio->op)) { bio->bi_end_io = f2fs_read_end_io; bio->bi_private = NULL; } 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); + if (fio->io_wbc) wbc_init_bio(fio->io_wbc, bio); return bio; } +static void f2fs_set_bio_crypt_ctx(struct bio *bio, const struct inode *inode, + pgoff_t first_idx, + const struct f2fs_io_info *fio, + gfp_t gfp_mask) +{ + /* + * The f2fs garbage collector sets ->encrypted_page when it wants to + * read/write raw data without encryption. + */ + if (!fio || !fio->encrypted_page) + fscrypt_set_bio_crypt_ctx(bio, inode, first_idx, gfp_mask); +} + +static bool f2fs_crypt_mergeable_bio(struct bio *bio, const struct inode *inode, + pgoff_t next_idx, + const struct f2fs_io_info *fio) +{ + /* + * The f2fs garbage collector sets ->encrypted_page when it wants to + * read/write raw data without encryption. + */ + if (fio && fio->encrypted_page) + return !bio_has_crypt_ctx(bio); + + return fscrypt_mergeable_bio(bio, inode, next_idx); +} + static inline void __submit_bio(struct f2fs_sb_info *sbi, struct bio *bio, enum page_type type) { @@ -445,10 +501,10 @@ static inline void __submit_bio(struct f2fs_sb_info *sbi, if (type != DATA && type != NODE) goto submit_io; - if (test_opt(sbi, LFS) && current->plug) + if (f2fs_lfs_mode(sbi) && current->plug) blk_finish_plug(current->plug); - if (F2FS_IO_ALIGNED(sbi)) + if (!F2FS_IO_ALIGNED(sbi)) goto submit_io; start = bio->bi_iter.bi_size >> F2FS_BLKSIZE_BITS; @@ -464,10 +520,11 @@ static inline void __submit_bio(struct f2fs_sb_info *sbi, GFP_NOIO | __GFP_NOFAIL); f2fs_bug_on(sbi, !page); - zero_user_segment(page, 0, PAGE_SIZE); - SetPagePrivate(page); - set_page_private(page, (unsigned long)DUMMY_WRITTEN_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); } @@ -483,6 +540,8 @@ submit_io: trace_f2fs_submit_read_bio(sbi->sb, type, bio); else trace_f2fs_submit_write_bio(sbi->sb, type, bio); + + iostat_update_submit_ctx(bio, type); submit_bio(bio); } @@ -499,8 +558,6 @@ static void __submit_merged_bio(struct f2fs_bio_info *io) if (!io->bio) return; - bio_set_op_attrs(io->bio, fio->op, fio->op_flags); - if (is_read_io(fio->op)) trace_f2fs_prepare_read_bio(io->sbi->sb, fio->type, io->bio); else @@ -547,24 +604,51 @@ static bool __has_merged_page(struct bio *bio, struct inode *inode, return false; } +int f2fs_init_write_merge_io(struct f2fs_sb_info *sbi) +{ + int i; + + for (i = 0; i < NR_PAGE_TYPE; i++) { + int n = (i == META) ? 1 : NR_TEMP_TYPE; + int j; + + sbi->write_io[i] = f2fs_kmalloc(sbi, + array_size(n, sizeof(struct f2fs_bio_info)), + GFP_KERNEL); + if (!sbi->write_io[i]) + 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); + } + } + + return 0; +} + static void __f2fs_submit_merged_write(struct f2fs_sb_info *sbi, enum page_type type, enum temp_type temp) { enum page_type btype = PAGE_TYPE_OF_BIO(type); struct f2fs_bio_info *io = sbi->write_io[btype] + temp; - down_write(&io->io_rwsem); + f2fs_down_write(&io->io_rwsem); /* change META to META_FLUSH in the checkpoint procedure */ if (type >= META_FLUSH) { io->fio.type = META_FLUSH; - io->fio.op = REQ_OP_WRITE; - io->fio.op_flags = REQ_META | REQ_PRIO | REQ_SYNC; + io->bio->bi_opf |= REQ_META | REQ_PRIO | REQ_SYNC; if (!test_opt(sbi, NOBARRIER)) - io->fio.op_flags |= REQ_PREFLUSH | REQ_FUA; + io->bio->bi_opf |= REQ_PREFLUSH | REQ_FUA; } __submit_merged_bio(io); - up_write(&io->io_rwsem); + f2fs_up_write(&io->io_rwsem); } static void __submit_merged_write_cond(struct f2fs_sb_info *sbi, @@ -579,9 +663,9 @@ static void __submit_merged_write_cond(struct f2fs_sb_info *sbi, enum page_type btype = PAGE_TYPE_OF_BIO(type); struct f2fs_bio_info *io = sbi->write_io[btype] + temp; - down_read(&io->io_rwsem); + f2fs_down_read(&io->io_rwsem); ret = __has_merged_page(io->bio, inode, page, ino); - up_read(&io->io_rwsem); + f2fs_up_read(&io->io_rwsem); } if (ret) __f2fs_submit_merged_write(sbi, type, temp); @@ -623,15 +707,19 @@ int f2fs_submit_page_bio(struct f2fs_io_info *fio) if (!f2fs_is_valid_blkaddr(fio->sbi, fio->new_blkaddr, fio->is_por ? META_POR : (__is_meta_io(fio) ? - META_GENERIC : DATA_GENERIC_ENHANCE))) + META_GENERIC : DATA_GENERIC_ENHANCE))) { + f2fs_handle_error(fio->sbi, ERROR_INVALID_BLKADDR); return -EFSCORRUPTED; + } trace_f2fs_submit_page_bio(page, fio); - f2fs_trace_ios(fio, 0); /* 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; @@ -640,10 +728,8 @@ int f2fs_submit_page_bio(struct f2fs_io_info *fio) if (fio->io_wbc && !is_read_io(fio->op)) wbc_account_cgroup_owner(fio->io_wbc, page, PAGE_SIZE); - bio_set_op_attrs(bio, fio->op, fio->op_flags); - inc_page_count(fio->sbi, is_read_io(fio->op) ? - __read_io_type(page): WB_DATA_TYPE(fio->page)); + __read_io_type(page) : WB_DATA_TYPE(fio->page)); __submit_bio(fio->sbi, bio, fio->type); return 0; @@ -652,9 +738,12 @@ int f2fs_submit_page_bio(struct f2fs_io_info *fio) static bool page_is_mergeable(struct f2fs_sb_info *sbi, struct bio *bio, block_t last_blkaddr, block_t cur_blkaddr) { + if (unlikely(sbi->max_io_bytes && + bio->bi_iter.bi_size >= sbi->max_io_bytes)) + return false; if (last_blkaddr + 1 != cur_blkaddr) return false; - return __same_bdev(sbi, cur_blkaddr, bio); + return bio->bi_bdev == f2fs_target_device(sbi, cur_blkaddr, NULL); } static bool io_type_is_mergeable(struct f2fs_bio_info *io, @@ -692,16 +781,16 @@ static void add_bio_entry(struct f2fs_sb_info *sbi, struct bio *bio, struct f2fs_bio_info *io = sbi->write_io[DATA] + temp; struct bio_entry *be; - be = f2fs_kmem_cache_alloc(bio_entry_slab, GFP_NOFS); + be = f2fs_kmem_cache_alloc(bio_entry_slab, GFP_NOFS, true, NULL); be->bio = bio; bio_get(bio); if (bio_add_page(bio, page, PAGE_SIZE, 0) != PAGE_SIZE) f2fs_bug_on(sbi, 1); - down_write(&io->bio_list_lock); + f2fs_down_write(&io->bio_list_lock); list_add_tail(&be->list, &io->bio_list); - up_write(&io->bio_list_lock); + f2fs_up_write(&io->bio_list_lock); } static void del_bio_entry(struct bio_entry *be) @@ -710,9 +799,10 @@ static void del_bio_entry(struct bio_entry *be) kmem_cache_free(bio_entry_slab, be); } -static int add_ipu_page(struct f2fs_sb_info *sbi, struct bio **bio, +static int add_ipu_page(struct f2fs_io_info *fio, struct bio **bio, struct page *page) { + struct f2fs_sb_info *sbi = fio->sbi; enum temp_type temp; bool found = false; int ret = -EAGAIN; @@ -722,25 +812,31 @@ static int add_ipu_page(struct f2fs_sb_info *sbi, struct bio **bio, struct list_head *head = &io->bio_list; struct bio_entry *be; - down_write(&io->bio_list_lock); + f2fs_down_write(&io->bio_list_lock); list_for_each_entry(be, head, list) { if (be->bio != *bio) continue; found = true; - if (bio_add_page(*bio, page, PAGE_SIZE, 0) == - PAGE_SIZE) { + f2fs_bug_on(sbi, !page_is_mergeable(sbi, *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) { ret = 0; break; } - /* bio is full */ + /* page can't be merged into bio; submit the bio */ del_bio_entry(be); __submit_bio(sbi, *bio, DATA); break; } - up_write(&io->bio_list_lock); + f2fs_up_write(&io->bio_list_lock); } if (ret) { @@ -766,7 +862,7 @@ void f2fs_submit_merged_ipu_write(struct f2fs_sb_info *sbi, if (list_empty(head)) continue; - down_read(&io->bio_list_lock); + f2fs_down_read(&io->bio_list_lock); list_for_each_entry(be, head, list) { if (target) found = (target == be->bio); @@ -776,14 +872,14 @@ void f2fs_submit_merged_ipu_write(struct f2fs_sb_info *sbi, if (found) break; } - up_read(&io->bio_list_lock); + f2fs_up_read(&io->bio_list_lock); if (!found) continue; found = false; - down_write(&io->bio_list_lock); + f2fs_down_write(&io->bio_list_lock); list_for_each_entry(be, head, list) { if (target) found = (target == be->bio); @@ -796,7 +892,7 @@ void f2fs_submit_merged_ipu_write(struct f2fs_sb_info *sbi, break; } } - up_write(&io->bio_list_lock); + f2fs_up_write(&io->bio_list_lock); } if (found) @@ -814,23 +910,25 @@ int f2fs_merge_page_bio(struct f2fs_io_info *fio) fio->encrypted_page : fio->page; if (!f2fs_is_valid_blkaddr(fio->sbi, fio->new_blkaddr, - __is_meta_io(fio) ? META_GENERIC : DATA_GENERIC)) + __is_meta_io(fio) ? META_GENERIC : DATA_GENERIC)) { + f2fs_handle_error(fio->sbi, ERROR_INVALID_BLKADDR); return -EFSCORRUPTED; + } trace_f2fs_submit_page_bio(page, fio); - f2fs_trace_ios(fio, 0); if (bio && !page_is_mergeable(fio->sbi, bio, *fio->last_block, fio->new_blkaddr)) f2fs_submit_merged_ipu_write(fio->sbi, &bio, NULL); alloc_new: if (!bio) { - bio = __bio_alloc(fio, BIO_MAX_PAGES); - bio_set_op_attrs(bio, fio->op, fio->op_flags); + bio = __bio_alloc(fio, BIO_MAX_VECS); + f2fs_set_bio_crypt_ctx(bio, fio->page->mapping->host, + fio->page->index, fio, GFP_NOIO); add_bio_entry(fio->sbi, bio, page, fio->temp); } else { - if (add_ipu_page(fio->sbi, &bio, page)) + if (add_ipu_page(fio, &bio, page)) goto alloc_new; } @@ -854,7 +952,7 @@ void f2fs_submit_page_write(struct f2fs_io_info *fio) f2fs_bug_on(sbi, is_read_io(fio->op)); - down_write(&io->io_rwsem); + f2fs_down_write(&io->io_rwsem); next: if (fio->in_list) { spin_lock(&io->io_lock); @@ -882,8 +980,11 @@ next: inc_page_count(sbi, WB_DATA_TYPE(bio_page)); - if (io->bio && !io_is_mergeable(sbi, io->bio, io, fio, - io->last_block_in_bio, fio->new_blkaddr)) + 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))) __submit_merged_bio(io); alloc_new: if (io->bio == NULL) { @@ -894,7 +995,9 @@ alloc_new: fio->retry = true; goto skip; } - io->bio = __bio_alloc(fio, BIO_MAX_PAGES); + 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); io->fio = *fio; } @@ -907,7 +1010,6 @@ alloc_new: wbc_account_cgroup_owner(fio->io_wbc, bio_page, PAGE_SIZE); io->last_block_in_bio = fio->new_blkaddr; - f2fs_trace_ios(fio, 0); trace_f2fs_submit_page_write(fio->page, fio); skip: @@ -917,65 +1019,66 @@ out: if (is_sbi_flag_set(sbi, SBI_IS_SHUTDOWN) || !f2fs_is_checkpoint_ready(sbi)) __submit_merged_bio(io); - up_write(&io->io_rwsem); -} - -static inline bool f2fs_need_verity(const struct inode *inode, pgoff_t idx) -{ - return fsverity_active(inode) && - idx < DIV_ROUND_UP(inode->i_size, PAGE_SIZE); + f2fs_up_write(&io->io_rwsem); } static struct bio *f2fs_grab_read_bio(struct inode *inode, block_t blkaddr, - unsigned nr_pages, unsigned op_flag, - pgoff_t first_idx) + unsigned nr_pages, blk_opf_t op_flag, + pgoff_t first_idx, bool for_write) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct bio *bio; - struct bio_post_read_ctx *ctx; + struct bio_post_read_ctx *ctx = NULL; unsigned int post_read_steps = 0; + sector_t sector; + struct block_device *bdev = f2fs_target_device(sbi, blkaddr, §or); - bio = f2fs_bio_alloc(sbi, min_t(int, nr_pages, BIO_MAX_PAGES), false); + 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); - f2fs_target_device(sbi, blkaddr, bio); + 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; - bio_set_op_attrs(bio, REQ_OP_READ, op_flag); - if (f2fs_encrypted_file(inode)) - post_read_steps |= 1 << STEP_DECRYPT; - if (f2fs_compressed_file(inode)) - post_read_steps |= 1 << STEP_DECOMPRESS; + if (fscrypt_inode_uses_fs_layer_crypto(inode)) + post_read_steps |= STEP_DECRYPT; + if (f2fs_need_verity(inode, first_idx)) - post_read_steps |= 1 << STEP_VERITY; + post_read_steps |= STEP_VERITY; - if (post_read_steps) { + /* + * STEP_DECOMPRESS is handled specially, since a compressed file might + * contain both compressed and uncompressed clusters. We'll allocate a + * bio_post_read_ctx if the file is compressed, but the caller is + * responsible for enabling STEP_DECOMPRESS if it's actually needed. + */ + + if (post_read_steps || f2fs_compressed_file(inode)) { /* Due to the mempool, this never fails. */ ctx = mempool_alloc(bio_post_read_ctx_pool, GFP_NOFS); ctx->bio = bio; ctx->sbi = sbi; ctx->enabled_steps = post_read_steps; + ctx->fs_blkaddr = blkaddr; bio->bi_private = ctx; } + iostat_alloc_and_bind_ctx(sbi, bio, ctx); return bio; } -static void f2fs_release_read_bio(struct bio *bio) -{ - if (bio->bi_private) - mempool_free(bio->bi_private, bio_post_read_ctx_pool); - bio_put(bio); -} - /* This can handle encryption stuffs */ static int f2fs_submit_page_read(struct inode *inode, struct page *page, - block_t blkaddr) + block_t blkaddr, blk_opf_t op_flags, + bool for_write) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct bio *bio; - bio = f2fs_grab_read_bio(inode, blkaddr, 1, 0, page->index); + bio = f2fs_grab_read_bio(inode, blkaddr, 1, op_flags, + page->index, for_write); if (IS_ERR(bio)) return PTR_ERR(bio); @@ -988,6 +1091,7 @@ static int f2fs_submit_page_read(struct inode *inode, struct page *page, } ClearPageError(page); inc_page_count(sbi, F2FS_RD_DATA); + f2fs_update_iostat(sbi, NULL, FS_DATA_READ_IO, F2FS_BLKSIZE); __submit_bio(sbi, bio, DATA); return 0; } @@ -1047,8 +1151,8 @@ int f2fs_reserve_new_blocks(struct dnode_of_data *dn, blkcnt_t count) f2fs_wait_on_page_writeback(dn->node_page, NODE, true, true); for (; count > 0; dn->ofs_in_node++) { - block_t blkaddr = datablock_addr(dn->inode, - dn->node_page, dn->ofs_in_node); + block_t blkaddr = f2fs_data_blkaddr(dn); + if (blkaddr == NULL_ADDR) { dn->data_blkaddr = NEW_ADDR; __set_data_blkaddr(dn); @@ -1090,7 +1194,7 @@ int f2fs_reserve_block(struct dnode_of_data *dn, pgoff_t index) int f2fs_get_block(struct dnode_of_data *dn, pgoff_t index) { - struct extent_info ei = {0,0,0}; + struct extent_info ei = {0, }; struct inode *inode = dn->inode; if (f2fs_lookup_extent_cache(inode, index, &ei)) { @@ -1102,12 +1206,12 @@ int f2fs_get_block(struct dnode_of_data *dn, pgoff_t index) } struct page *f2fs_get_read_data_page(struct inode *inode, pgoff_t index, - int op_flags, bool for_write) + blk_opf_t op_flags, bool for_write) { struct address_space *mapping = inode->i_mapping; struct dnode_of_data dn; struct page *page; - struct extent_info ei = {0,0,0}; + struct extent_info ei = {0, }; int err; page = f2fs_grab_cache_page(mapping, index, for_write); @@ -1119,6 +1223,8 @@ struct page *f2fs_get_read_data_page(struct inode *inode, pgoff_t index, 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; @@ -1139,6 +1245,8 @@ 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: @@ -1162,7 +1270,8 @@ got_it: return page; } - err = f2fs_submit_page_read(inode, page, dn.data_blkaddr); + err = f2fs_submit_page_read(inode, page, dn.data_blkaddr, + op_flags, for_write); if (err) goto put_err; return page; @@ -1296,12 +1405,11 @@ static int __allocate_data_block(struct dnode_of_data *dn, int seg_type) if (unlikely(is_inode_flag_set(dn->inode, FI_NO_ALLOC))) return -EPERM; - err = f2fs_get_node_info(sbi, dn->nid, &ni); + err = f2fs_get_node_info(sbi, dn->nid, &ni, false); if (err) return err; - dn->data_blkaddr = datablock_addr(dn->inode, - dn->node_page, dn->ofs_in_node); + dn->data_blkaddr = f2fs_data_blkaddr(dn); if (dn->data_blkaddr != NULL_ADDR) goto alloc; @@ -1312,73 +1420,23 @@ alloc: 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, false); - if (GET_SEGNO(sbi, old_blkaddr) != NULL_SEGNO) + &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); + } f2fs_update_data_blkaddr(dn, dn->data_blkaddr); - - /* - * i_size will be updated by direct_IO. Otherwise, we'll get stale - * data from unwritten block via dio_read. - */ return 0; } -int f2fs_preallocate_blocks(struct kiocb *iocb, struct iov_iter *from) -{ - struct inode *inode = file_inode(iocb->ki_filp); - struct f2fs_map_blocks map; - int flag; - int err = 0; - bool direct_io = iocb->ki_flags & IOCB_DIRECT; - - map.m_lblk = F2FS_BLK_ALIGN(iocb->ki_pos); - map.m_len = F2FS_BYTES_TO_BLK(iocb->ki_pos + iov_iter_count(from)); - if (map.m_len > map.m_lblk) - map.m_len -= map.m_lblk; - else - map.m_len = 0; - - map.m_next_pgofs = NULL; - map.m_next_extent = NULL; - map.m_seg_type = NO_CHECK_TYPE; - map.m_may_create = true; - - if (direct_io) { - map.m_seg_type = f2fs_rw_hint_to_seg_type(iocb->ki_hint); - flag = f2fs_force_buffered_io(inode, iocb, from) ? - F2FS_GET_BLOCK_PRE_AIO : - F2FS_GET_BLOCK_PRE_DIO; - goto map_blocks; - } - if (iocb->ki_pos + iov_iter_count(from) > MAX_INLINE_DATA(inode)) { - err = f2fs_convert_inline_inode(inode); - if (err) - return err; - } - if (f2fs_has_inline_data(inode)) - return err; - - flag = F2FS_GET_BLOCK_PRE_AIO; - -map_blocks: - err = f2fs_map_blocks(inode, &map, 1, flag); - if (map.m_len > 0 && err == -ENOSPC) { - if (!direct_io) - set_inode_flag(inode, FI_NO_PREALLOC); - err = 0; - } - return err; -} - -void __do_map_lock(struct f2fs_sb_info *sbi, int flag, bool lock) +void f2fs_do_map_lock(struct f2fs_sb_info *sbi, int flag, bool lock) { if (flag == F2FS_GET_BLOCK_PRE_AIO) { if (lock) - down_read(&sbi->node_change); + f2fs_down_read(&sbi->node_change); else - up_read(&sbi->node_change); + f2fs_up_read(&sbi->node_change); } else { if (lock) f2fs_lock_op(sbi); @@ -1388,13 +1446,9 @@ void __do_map_lock(struct f2fs_sb_info *sbi, int flag, bool lock) } /* - * f2fs_map_blocks() now supported readahead/bmap/rw direct_IO with - * f2fs_map_blocks structure. - * If original data blocks are allocated, then give them to blockdev. - * Otherwise, - * a. preallocate requested block addresses - * b. do not use extent cache for better performance - * c. give the block addresses to blockdev + * f2fs_map_blocks() tries to find or build mapping relationship which + * maps continuous logical blocks to physical blocks, and return such + * info via f2fs_map_blocks structure. */ int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map, int create, int flag) @@ -1407,13 +1461,18 @@ int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map, int err = 0, ofs = 1; unsigned int ofs_in_node, last_ofs_in_node; blkcnt_t prealloc; - struct extent_info ei = {0,0,0}; + struct extent_info ei = {0, }; block_t blkaddr; unsigned int start_pgofs; + int bidx = 0; if (!maxblocks) return 0; + map->m_bdev = inode->i_sb->s_bdev; + map->m_multidev_dio = + f2fs_allow_multi_device_dio(F2FS_I_SB(inode), flag); + map->m_len = 0; map->m_flags = 0; @@ -1422,7 +1481,7 @@ int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map, end = pgofs + maxblocks; if (!create && f2fs_lookup_extent_cache(inode, pgofs, &ei)) { - if (test_opt(sbi, LFS) && flag == F2FS_GET_BLOCK_DIO && + if (f2fs_lfs_mode(sbi) && flag == F2FS_GET_BLOCK_DIO && map->m_may_create) goto next_dnode; @@ -1436,12 +1495,27 @@ int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map, if (flag == F2FS_GET_BLOCK_DIO) f2fs_wait_on_block_writeback_range(inode, map->m_pblk, map->m_len); + + if (map->m_multidev_dio) { + block_t blk_addr = map->m_pblk; + + bidx = f2fs_target_device_index(sbi, map->m_pblk); + + map->m_bdev = FDEV(bidx).bdev; + map->m_pblk -= FDEV(bidx).start_blk; + map->m_len = min(map->m_len, + FDEV(bidx).end_blk + 1 - map->m_pblk); + + if (map->m_may_create) + f2fs_update_device_state(sbi, inode->i_ino, + blk_addr, map->m_len); + } goto out; } next_dnode: if (map->m_may_create) - __do_map_lock(sbi, flag, true); + f2fs_do_map_lock(sbi, flag, true); /* When reading holes, we need its node page */ set_new_dnode(&dn, inode, NULL, NULL, 0); @@ -1449,7 +1523,21 @@ next_dnode: if (err) { if (flag == F2FS_GET_BLOCK_BMAP) map->m_pblk = 0; + if (err == -ENOENT) { + /* + * There is one exceptional case that read_node_page() + * may return -ENOENT due to filesystem has been + * shutdown or cp_error, so force to convert error + * number to EIO for such case. + */ + if (map->m_may_create && + (is_sbi_flag_set(sbi, SBI_IS_SHUTDOWN) || + f2fs_cp_error(sbi))) { + err = -EIO; + goto unlock_out; + } + err = 0; if (map->m_next_pgofs) *map->m_next_pgofs = @@ -1467,17 +1555,18 @@ next_dnode: end_offset = ADDRS_PER_PAGE(dn.node_page, inode); next_block: - blkaddr = datablock_addr(dn.inode, dn.node_page, dn.ofs_in_node); + blkaddr = f2fs_data_blkaddr(&dn); if (__is_valid_data_blkaddr(blkaddr) && !f2fs_is_valid_blkaddr(sbi, blkaddr, DATA_GENERIC_ENHANCE)) { err = -EFSCORRUPTED; + f2fs_handle_error(sbi, ERROR_INVALID_BLKADDR); goto sync_out; } if (__is_valid_data_blkaddr(blkaddr)) { /* use out-place-update for driect IO under LFS mode */ - if (test_opt(sbi, LFS) && flag == F2FS_GET_BLOCK_DIO && + if (f2fs_lfs_mode(sbi) && flag == F2FS_GET_BLOCK_DIO && map->m_may_create) { err = __allocate_data_block(&dn, map->m_seg_type); if (err) @@ -1501,14 +1590,26 @@ next_block: flag != F2FS_GET_BLOCK_DIO); err = __allocate_data_block(&dn, map->m_seg_type); - if (!err) + if (!err) { + if (flag == F2FS_GET_BLOCK_PRE_DIO) + file_need_truncate(inode); set_inode_flag(inode, FI_APPEND_WRITE); + } } if (err) goto sync_out; map->m_flags |= F2FS_MAP_NEW; blkaddr = dn.data_blkaddr; } else { + if (f2fs_compressed_file(inode) && + f2fs_sanity_check_cluster(&dn) && + (flag != F2FS_GET_BLOCK_FIEMAP || + IS_ENABLED(CONFIG_F2FS_CHECK_FS))) { + err = -EFSCORRUPTED; + f2fs_handle_error(sbi, + ERROR_CORRUPTED_CLUSTER); + goto sync_out; + } if (flag == F2FS_GET_BLOCK_BMAP) { map->m_pblk = 0; goto sync_out; @@ -1533,6 +1634,9 @@ next_block: if (flag == F2FS_GET_BLOCK_PRE_AIO) goto skip; + if (map->m_multidev_dio) + bidx = f2fs_target_device_index(sbi, blkaddr); + if (map->m_len == 0) { /* preallocated unwritten block should be mapped for fiemap. */ if (blkaddr == NEW_ADDR) @@ -1541,10 +1645,15 @@ next_block: 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; ofs++; map->m_len++; } else { @@ -1590,18 +1699,38 @@ skip: f2fs_put_dnode(&dn); if (map->m_may_create) { - __do_map_lock(sbi, flag, false); + f2fs_do_map_lock(sbi, flag, false); f2fs_balance_fs(sbi, dn.node_changed); } goto next_dnode; sync_out: - /* for hardware encryption, but to avoid potential issue in future */ - if (flag == F2FS_GET_BLOCK_DIO && map->m_flags & F2FS_MAP_MAPPED) + if (flag == F2FS_GET_BLOCK_DIO && map->m_flags & F2FS_MAP_MAPPED) { + /* + * for hardware encryption, but to avoid potential issue + * in future + */ f2fs_wait_on_block_writeback_range(inode, map->m_pblk, map->m_len); + if (map->m_multidev_dio) { + block_t blk_addr = map->m_pblk; + + bidx = f2fs_target_device_index(sbi, map->m_pblk); + + map->m_bdev = FDEV(bidx).bdev; + map->m_pblk -= FDEV(bidx).start_blk; + + if (map->m_may_create) + f2fs_update_device_state(sbi, inode->i_ino, + blk_addr, map->m_len); + + f2fs_bug_on(sbi, blk_addr + map->m_len > + FDEV(bidx).end_blk + 1); + } + } + if (flag == F2FS_GET_BLOCK_PRECACHE) { if (map->m_flags & F2FS_MAP_MAPPED) { unsigned int ofs = start_pgofs - map->m_lblk; @@ -1616,11 +1745,11 @@ sync_out: f2fs_put_dnode(&dn); unlock_out: if (map->m_may_create) { - __do_map_lock(sbi, flag, false); + f2fs_do_map_lock(sbi, flag, false); f2fs_balance_fs(sbi, dn.node_changed); } out: - trace_f2fs_map_blocks(inode, map, err); + trace_f2fs_map_blocks(inode, map, create, flag, err); return err; } @@ -1650,76 +1779,14 @@ bool f2fs_overwrite_io(struct inode *inode, loff_t pos, size_t len) return true; } -static int __get_data_block(struct inode *inode, sector_t iblock, - struct buffer_head *bh, int create, int flag, - pgoff_t *next_pgofs, int seg_type, bool may_write) -{ - struct f2fs_map_blocks map; - int err; - - map.m_lblk = iblock; - map.m_len = bh->b_size >> inode->i_blkbits; - map.m_next_pgofs = next_pgofs; - map.m_next_extent = NULL; - map.m_seg_type = seg_type; - map.m_may_create = may_write; - - err = f2fs_map_blocks(inode, &map, create, flag); - if (!err) { - map_bh(bh, inode->i_sb, map.m_pblk); - bh->b_state = (bh->b_state & ~F2FS_MAP_FLAGS) | map.m_flags; - bh->b_size = (u64)map.m_len << inode->i_blkbits; - } - return err; -} - -static int get_data_block(struct inode *inode, sector_t iblock, - struct buffer_head *bh_result, int create, int flag, - pgoff_t *next_pgofs) -{ - return __get_data_block(inode, iblock, bh_result, create, - flag, next_pgofs, - NO_CHECK_TYPE, create); -} - -static int get_data_block_dio_write(struct inode *inode, sector_t iblock, - struct buffer_head *bh_result, int create) -{ - return __get_data_block(inode, iblock, bh_result, create, - F2FS_GET_BLOCK_DIO, NULL, - f2fs_rw_hint_to_seg_type(inode->i_write_hint), - IS_SWAPFILE(inode) ? false : true); -} - -static int get_data_block_dio(struct inode *inode, sector_t iblock, - struct buffer_head *bh_result, int create) +static inline u64 bytes_to_blks(struct inode *inode, u64 bytes) { - return __get_data_block(inode, iblock, bh_result, create, - F2FS_GET_BLOCK_DIO, NULL, - f2fs_rw_hint_to_seg_type(inode->i_write_hint), - false); -} - -static int get_data_block_bmap(struct inode *inode, sector_t iblock, - struct buffer_head *bh_result, int create) -{ - /* Block number less than F2FS MAX BLOCKS */ - if (unlikely(iblock >= F2FS_I_SB(inode)->max_file_blocks)) - return -EFBIG; - - return __get_data_block(inode, iblock, bh_result, create, - F2FS_GET_BLOCK_BMAP, NULL, - NO_CHECK_TYPE, create); + return (bytes >> inode->i_blkbits); } -static inline sector_t logical_to_blk(struct inode *inode, loff_t offset) +static inline u64 blks_to_bytes(struct inode *inode, u64 blks) { - return (offset >> inode->i_blkbits); -} - -static inline loff_t blk_to_logical(struct inode *inode, sector_t blk) -{ - return (blk << inode->i_blkbits); + return (blks << inode->i_blkbits); } static int f2fs_xattr_fiemap(struct inode *inode, @@ -1741,13 +1808,13 @@ static int f2fs_xattr_fiemap(struct inode *inode, if (!page) return -ENOMEM; - err = f2fs_get_node_info(sbi, inode->i_ino, &ni); + err = f2fs_get_node_info(sbi, inode->i_ino, &ni, false); if (err) { f2fs_put_page(page, 1); return err; } - phys = (__u64)blk_to_logical(inode, ni.blk_addr); + phys = blks_to_bytes(inode, ni.blk_addr); offset = offsetof(struct f2fs_inode, i_addr) + sizeof(__le32) * (DEF_ADDRS_PER_INODE - get_inline_xattr_addrs(inode)); @@ -1763,7 +1830,8 @@ static int f2fs_xattr_fiemap(struct inode *inode, flags |= FIEMAP_EXTENT_LAST; err = fiemap_fill_next_extent(fieinfo, 0, phys, len, flags); - if (err || err == 1) + trace_f2fs_fiemap(inode, 0, phys, len, flags, err); + if (err) return err; } @@ -1772,13 +1840,13 @@ static int f2fs_xattr_fiemap(struct inode *inode, if (!page) return -ENOMEM; - err = f2fs_get_node_info(sbi, xnid, &ni); + err = f2fs_get_node_info(sbi, xnid, &ni, false); if (err) { f2fs_put_page(page, 1); return err; } - phys = (__u64)blk_to_logical(inode, ni.blk_addr); + phys = blks_to_bytes(inode, ni.blk_addr); len = inode->i_sb->s_blocksize; f2fs_put_page(page, 1); @@ -1786,21 +1854,46 @@ static int f2fs_xattr_fiemap(struct inode *inode, flags = FIEMAP_EXTENT_LAST; } - if (phys) + if (phys) { err = fiemap_fill_next_extent(fieinfo, 0, phys, len, flags); + trace_f2fs_fiemap(inode, 0, phys, len, flags, err); + } 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 buffer_head map_bh; + struct f2fs_map_blocks map; sector_t start_blk, last_blk; pgoff_t next_pgofs; u64 logical = 0, phys = 0, size = 0; u32 flags = 0; int ret = 0; + bool compr_cluster = false, compr_appended; + unsigned int cluster_size = F2FS_I(inode)->i_cluster_size; + unsigned int count_in_cluster = 0; + loff_t maxbytes; if (fieinfo->fi_flags & FIEMAP_FLAG_CACHE) { ret = f2fs_precache_extents(inode); @@ -1808,12 +1901,21 @@ int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, return ret; } - ret = fiemap_check_flags(fieinfo, FIEMAP_FLAG_SYNC | FIEMAP_FLAG_XATTR); + ret = fiemap_prep(inode, fieinfo, start, &len, FIEMAP_FLAG_XATTR); if (ret) return ret; inode_lock(inode); + maxbytes = max_file_blocks(inode) << F2FS_BLKSIZE_BITS; + if (start > maxbytes) { + ret = -EFBIG; + goto out; + } + + if (len > maxbytes || (maxbytes - len) < start) + len = maxbytes - start; + if (fieinfo->fi_flags & FIEMAP_FLAG_XATTR) { ret = f2fs_xattr_fiemap(inode, fieinfo); goto out; @@ -1825,51 +1927,93 @@ int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, goto out; } - if (logical_to_blk(inode, len) == 0) - len = blk_to_logical(inode, 1); + if (bytes_to_blks(inode, len) == 0) + len = blks_to_bytes(inode, 1); - start_blk = logical_to_blk(inode, start); - last_blk = logical_to_blk(inode, start + len - 1); + start_blk = bytes_to_blks(inode, start); + last_blk = bytes_to_blks(inode, start + len - 1); next: - memset(&map_bh, 0, sizeof(struct buffer_head)); - map_bh.b_size = len; + memset(&map, 0, sizeof(map)); + map.m_lblk = start_blk; + map.m_len = bytes_to_blks(inode, len); + map.m_next_pgofs = &next_pgofs; + map.m_seg_type = NO_CHECK_TYPE; + + if (compr_cluster) { + map.m_lblk += 1; + map.m_len = cluster_size - count_in_cluster; + } - ret = get_data_block(inode, start_blk, &map_bh, 0, - F2FS_GET_BLOCK_FIEMAP, &next_pgofs); + ret = f2fs_map_blocks(inode, &map, 0, F2FS_GET_BLOCK_FIEMAP); if (ret) goto out; /* HOLE */ - if (!buffer_mapped(&map_bh)) { + if (!compr_cluster && !(map.m_flags & F2FS_MAP_FLAGS)) { start_blk = next_pgofs; - if (blk_to_logical(inode, start_blk) < blk_to_logical(inode, - F2FS_I_SB(inode)->max_file_blocks)) + if (blks_to_bytes(inode, start_blk) < blks_to_bytes(inode, + max_inode_blocks(inode))) goto prep_next; flags |= FIEMAP_EXTENT_LAST; } + compr_appended = false; + /* In a case of compressed cluster, append this to the last extent */ + if (compr_cluster && ((map.m_flags & F2FS_MAP_UNWRITTEN) || + !(map.m_flags & F2FS_MAP_FLAGS))) { + compr_appended = true; + goto skip_fill; + } + if (size) { + flags |= FIEMAP_EXTENT_MERGED; if (IS_ENCRYPTED(inode)) flags |= FIEMAP_EXTENT_DATA_ENCRYPTED; ret = fiemap_fill_next_extent(fieinfo, logical, phys, size, flags); + trace_f2fs_fiemap(inode, logical, phys, size, flags, ret); + if (ret) + goto out; + size = 0; } - if (start_blk > last_blk || ret) + if (start_blk > last_blk) goto out; - logical = blk_to_logical(inode, start_blk); - phys = blk_to_logical(inode, map_bh.b_blocknr); - size = map_bh.b_size; - flags = 0; - if (buffer_unwritten(&map_bh)) - flags = FIEMAP_EXTENT_UNWRITTEN; +skip_fill: + if (map.m_pblk == COMPRESS_ADDR) { + compr_cluster = true; + count_in_cluster = 1; + } else if (compr_appended) { + unsigned int appended_blks = cluster_size - + count_in_cluster + 1; + size += blks_to_bytes(inode, appended_blks); + start_blk += appended_blks; + compr_cluster = false; + } else { + logical = blks_to_bytes(inode, 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); + flags = 0; + + if (compr_cluster) { + flags = FIEMAP_EXTENT_ENCODED; + count_in_cluster += map.m_len; + if (count_in_cluster == cluster_size) { + compr_cluster = false; + size += blks_to_bytes(inode, 1); + } + } else if (map.m_flags & F2FS_MAP_UNWRITTEN) { + flags = FIEMAP_EXTENT_UNWRITTEN; + } - start_blk += logical_to_blk(inode, size); + start_blk += bytes_to_blks(inode, size); + } prep_next: cond_resched(); @@ -1902,8 +2046,7 @@ static int f2fs_read_single_page(struct inode *inode, struct page *page, bool is_readahead) { struct bio *bio = *bio_ret; - const unsigned blkbits = inode->i_blkbits; - const unsigned blocksize = 1 << blkbits; + const unsigned blocksize = blks_to_bytes(inode, 1); sector_t block_in_file; sector_t last_block; sector_t last_block_in_file; @@ -1912,8 +2055,8 @@ static int f2fs_read_single_page(struct inode *inode, struct page *page, block_in_file = (sector_t)page_index(page); last_block = block_in_file + nr_pages; - last_block_in_file = (f2fs_readpage_limit(inode) + blocksize - 1) >> - blkbits; + last_block_in_file = bytes_to_blks(inode, + f2fs_readpage_limit(inode) + blocksize - 1); if (last_block > last_block_in_file) last_block = last_block_in_file; @@ -1943,15 +2086,11 @@ got_it: block_nr = map->m_pblk + block_in_file - map->m_lblk; SetPageMappedToDisk(page); - if (!PageUptodate(page) && (!PageSwapCache(page) && - !cleancache_get_page(page))) { - SetPageUptodate(page); - goto confused; - } - 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 { @@ -1972,15 +2111,17 @@ zero_out: * This page will go to BIO. Do we need to send this * BIO off first? */ - if (bio && !page_is_mergeable(F2FS_I_SB(inode), bio, - *last_block_in_bio, block_nr)) { + 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))) { submit_and_realloc: __submit_bio(F2FS_I_SB(inode), bio, DATA); bio = NULL; } if (bio == NULL) { bio = f2fs_grab_read_bio(inode, block_nr, nr_pages, - is_readahead ? REQ_RAHEAD : 0, page->index); + is_readahead ? REQ_RAHEAD : 0, page->index, + false); if (IS_ERR(bio)) { ret = PTR_ERR(bio); bio = NULL; @@ -1998,15 +2139,11 @@ submit_and_realloc: goto submit_and_realloc; inc_page_count(F2FS_I_SB(inode), F2FS_RD_DATA); + f2fs_update_iostat(F2FS_I_SB(inode), NULL, FS_DATA_READ_IO, + F2FS_BLKSIZE); ClearPageError(page); *last_block_in_bio = block_nr; goto out; -confused: - if (bio) { - __submit_bio(F2FS_I_SB(inode), bio, DATA); - bio = NULL; - } - unlock_page(page); out: *bio_ret = bio; return ret; @@ -2015,7 +2152,7 @@ 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 is_readahead, bool for_write) { struct dnode_of_data dn; struct inode *inode = cc->inode; @@ -2023,15 +2160,17 @@ 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 blkbits = inode->i_blkbits; - const unsigned blocksize = 1 << blkbits; + const unsigned blocksize = blks_to_bytes(inode, 1); struct decompress_io_ctx *dic = NULL; + struct extent_info ei = {0, }; + bool from_dnode = true; int i; int ret = 0; f2fs_bug_on(sbi, f2fs_cluster_is_empty(cc)); - last_block_in_file = (i_size_read(inode) + blocksize - 1) >> blkbits; + last_block_in_file = bytes_to_blks(inode, + f2fs_readpage_limit(inode) + blocksize - 1); /* get rid of pages beyond EOF */ for (i = 0; i < cc->cluster_size; i++) { @@ -2047,6 +2186,8 @@ int f2fs_read_multi_pages(struct compress_ctx *cc, struct bio **bio_ret, continue; } unlock_page(page); + if (for_write) + put_page(page); cc->rpages[i] = NULL; cc->nr_rpages--; } @@ -2055,20 +2196,26 @@ int f2fs_read_multi_pages(struct compress_ctx *cc, struct bio **bio_ret, if (f2fs_cluster_is_empty(cc)) goto out; + if (f2fs_lookup_extent_cache(inode, start_idx, &ei)) + from_dnode = false; + + if (!from_dnode) + goto skip_reading_dnode; + set_new_dnode(&dn, inode, NULL, NULL, 0); ret = f2fs_get_dnode_of_data(&dn, start_idx, LOOKUP_NODE); if (ret) goto out; - /* cluster was overwritten as normal cluster */ - if (dn.data_blkaddr != COMPRESS_ADDR) - goto out; + f2fs_bug_on(sbi, dn.data_blkaddr != COMPRESS_ADDR); +skip_reading_dnode: for (i = 1; i < cc->cluster_size; i++) { block_t blkaddr; - blkaddr = datablock_addr(dn.inode, dn.node_page, - dn.ofs_in_node + i); + blkaddr = from_dnode ? data_blkaddr(dn.inode, dn.node_page, + dn.ofs_in_node + i) : + ei.blk + i - 1; if (!__is_valid_data_blkaddr(blkaddr)) break; @@ -2078,6 +2225,9 @@ int f2fs_read_multi_pages(struct compress_ctx *cc, struct bio **bio_ret, goto out_put_dnode; } cc->nr_cpages++; + + if (!from_dnode && i >= ei.c_len) + break; } /* nothing to decompress */ @@ -2092,15 +2242,26 @@ int f2fs_read_multi_pages(struct compress_ctx *cc, struct bio **bio_ret, goto out_put_dnode; } - for (i = 0; i < dic->nr_cpages; i++) { + for (i = 0; i < cc->nr_cpages; i++) { struct page *page = dic->cpages[i]; block_t blkaddr; + struct bio_post_read_ctx *ctx; - blkaddr = datablock_addr(dn.inode, dn.node_page, - dn.ofs_in_node + i + 1); + blkaddr = from_dnode ? data_blkaddr(dn.inode, dn.node_page, + dn.ofs_in_node + i + 1) : + ei.blk + i; + + f2fs_wait_on_block_writeback(inode, blkaddr); - if (bio && !page_is_mergeable(sbi, bio, - *last_block_in_bio, blkaddr)) { + if (f2fs_load_compressed_page(sbi, page, blkaddr)) { + if (atomic_dec_and_test(&dic->remaining_pages)) + f2fs_decompress_cluster(dic, true); + continue; + } + + if (bio && (!page_is_mergeable(sbi, bio, + *last_block_in_bio, blkaddr) || + !f2fs_crypt_mergeable_bio(bio, inode, page->index, NULL))) { submit_and_realloc: __submit_bio(sbi, bio, DATA); bio = NULL; @@ -2109,42 +2270,46 @@ submit_and_realloc: if (!bio) { bio = f2fs_grab_read_bio(inode, blkaddr, nr_pages, is_readahead ? REQ_RAHEAD : 0, - page->index); + page->index, for_write); if (IS_ERR(bio)) { ret = PTR_ERR(bio); - bio = NULL; - dic->failed = true; - if (refcount_sub_and_test(dic->nr_cpages - i, - &dic->ref)) - f2fs_decompress_end_io(dic->rpages, - cc->cluster_size, true, - false); - f2fs_free_dic(dic); + f2fs_decompress_end_io(dic, ret, true); f2fs_put_dnode(&dn); - *bio_ret = bio; + *bio_ret = NULL; return ret; } } - f2fs_wait_on_block_writeback(inode, blkaddr); - if (bio_add_page(bio, page, blocksize, 0) < blocksize) goto submit_and_realloc; + ctx = get_post_read_ctx(bio); + ctx->enabled_steps |= STEP_DECOMPRESS; + refcount_inc(&dic->refcnt); + inc_page_count(sbi, F2FS_RD_DATA); + f2fs_update_iostat(sbi, inode, FS_DATA_READ_IO, F2FS_BLKSIZE); ClearPageError(page); *last_block_in_bio = blkaddr; } - f2fs_put_dnode(&dn); + if (from_dnode) + f2fs_put_dnode(&dn); *bio_ret = bio; return 0; out_put_dnode: - f2fs_put_dnode(&dn); + if (from_dnode) + f2fs_put_dnode(&dn); out: - f2fs_decompress_end_io(cc->rpages, cc->cluster_size, true, false); + for (i = 0; i < cc->cluster_size; i++) { + if (cc->rpages[i]) { + ClearPageUptodate(cc->rpages[i]); + ClearPageError(cc->rpages[i]); + unlock_page(cc->rpages[i]); + } + } *bio_ret = bio; return ret; } @@ -2153,19 +2318,12 @@ out: /* * This function was originally taken from fs/mpage.c, and customized for f2fs. * Major change was from block_size == page_size in f2fs by default. - * - * Note that the aops->readpages() function is ONLY used for read-ahead. If - * this function ever deviates from doing just read-ahead, it should either - * use ->readpage() or do the necessary surgery to decouple ->readpages() - * from read-ahead. */ -int f2fs_mpage_readpages(struct address_space *mapping, - struct list_head *pages, struct page *page, - unsigned nr_pages, bool is_readahead) +static int f2fs_mpage_readpages(struct inode *inode, + struct readahead_control *rac, struct page *page) { struct bio *bio = NULL; sector_t last_block_in_bio = 0; - struct inode *inode = mapping->host; struct f2fs_map_blocks map; #ifdef CONFIG_F2FS_FS_COMPRESSION struct compress_ctx cc = { @@ -2178,7 +2336,9 @@ int f2fs_mpage_readpages(struct address_space *mapping, .nr_rpages = 0, .nr_cpages = 0, }; + pgoff_t nc_cluster_idx = NULL_CLUSTER; #endif + unsigned nr_pages = rac ? readahead_count(rac) : 1; unsigned max_nr_pages = nr_pages; int ret = 0; @@ -2192,15 +2352,9 @@ int f2fs_mpage_readpages(struct address_space *mapping, map.m_may_create = false; for (; nr_pages; nr_pages--) { - if (pages) { - page = list_last_entry(pages, struct page, lru); - + if (rac) { + page = readahead_page(rac); prefetchw(&page->flags); - list_del(&page->lru); - if (add_to_page_cache_lru(page, mapping, - page_index(page), - readahead_gfp_mask(mapping))) - goto next_page; } #ifdef CONFIG_F2FS_FS_COMPRESSION @@ -2210,17 +2364,28 @@ int f2fs_mpage_readpages(struct address_space *mapping, ret = f2fs_read_multi_pages(&cc, &bio, max_nr_pages, &last_block_in_bio, - is_readahead); - f2fs_destroy_compress_ctx(&cc); + rac != NULL, false); + f2fs_destroy_compress_ctx(&cc, false); if (ret) goto set_error_page; } - ret = f2fs_is_compressed_cluster(inode, page->index); - if (ret < 0) - goto set_error_page; - else if (!ret) - goto read_single_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); if (ret) goto set_error_page; @@ -2233,7 +2398,7 @@ read_single_page: #endif ret = f2fs_read_single_page(inode, page, max_nr_pages, &map, - &bio, &last_block_in_bio, is_readahead); + &bio, &last_block_in_bio, rac); if (ret) { #ifdef CONFIG_F2FS_FS_COMPRESSION set_error_page: @@ -2242,8 +2407,10 @@ set_error_page: zero_user_segment(page, 0, PAGE_SIZE); unlock_page(page); } +#ifdef CONFIG_F2FS_FS_COMPRESSION next_page: - if (pages) +#endif + if (rac) put_page(page); #ifdef CONFIG_F2FS_FS_COMPRESSION @@ -2253,20 +2420,20 @@ next_page: ret = f2fs_read_multi_pages(&cc, &bio, max_nr_pages, &last_block_in_bio, - is_readahead); - f2fs_destroy_compress_ctx(&cc); + rac != NULL, false); + f2fs_destroy_compress_ctx(&cc, false); } } #endif } - BUG_ON(pages && !list_empty(pages)); if (bio) __submit_bio(F2FS_I_SB(inode), bio, DATA); - return pages ? 0 : ret; + return ret; } -static int f2fs_read_data_page(struct file *file, struct page *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; int ret = -EAGAIN; @@ -2281,28 +2448,24 @@ static int f2fs_read_data_page(struct file *file, struct page *page) if (f2fs_has_inline_data(inode)) ret = f2fs_read_inline_data(inode, page); if (ret == -EAGAIN) - ret = f2fs_mpage_readpages(page_file_mapping(page), - NULL, page, 1, false); + ret = f2fs_mpage_readpages(inode, NULL, page); return ret; } -static int f2fs_read_data_pages(struct file *file, - struct address_space *mapping, - struct list_head *pages, unsigned nr_pages) +static void f2fs_readahead(struct readahead_control *rac) { - struct inode *inode = mapping->host; - struct page *page = list_last_entry(pages, struct page, lru); + struct inode *inode = rac->mapping->host; - trace_f2fs_readpages(inode, page, nr_pages); + trace_f2fs_readpages(inode, readahead_index(rac), readahead_count(rac)); if (!f2fs_is_compress_backend_ready(inode)) - return 0; + return; - /* If the file has inline data, skip readpages */ + /* If the file has inline data, skip readahead */ if (f2fs_has_inline_data(inode)) - return 0; + return; - return f2fs_mpage_readpages(mapping, pages, NULL, nr_pages, true); + f2fs_mpage_readpages(inode, rac, NULL); } int f2fs_encrypt_one_page(struct f2fs_io_info *fio) @@ -2319,6 +2482,9 @@ int f2fs_encrypt_one_page(struct f2fs_io_info *fio) /* 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, PAGE_SIZE, 0, gfp_flags); @@ -2326,7 +2492,7 @@ retry_encrypt: /* flush pending IOs and wait for a while in the ENOMEM case */ if (PTR_ERR(fio->encrypted_page) == -ENOMEM) { f2fs_flush_merged_writes(fio->sbi); - congestion_wait(BLK_RW_ASYNC, HZ/50); + memalloc_retry_wait(GFP_NOFS); gfp_flags |= __GFP_NOFAIL; goto retry_encrypt; } @@ -2349,6 +2515,9 @@ static inline bool check_inplace_update_policy(struct inode *inode, struct f2fs_sb_info *sbi = F2FS_I_SB(inode); unsigned int policy = SM_I(sbi)->ipu_policy; + if (policy & (0x1 << F2FS_IPU_HONOR_OPU_WRITE) && + is_inode_flag_set(inode, FI_OPU_WRITE)) + return false; if (policy & (0x1 << F2FS_IPU_FORCE)) return true; if (policy & (0x1 << F2FS_IPU_SSR) && f2fs_need_SSR(sbi)) @@ -2383,11 +2552,15 @@ static inline bool check_inplace_update_policy(struct inode *inode, bool f2fs_should_update_inplace(struct inode *inode, struct f2fs_io_info *fio) { + /* swap file is migrating in aligned write mode */ + if (is_inode_flag_set(inode, FI_ALIGNED_WRITE)) + return false; + if (f2fs_is_pinned_file(inode)) return true; /* if this is cold file, we should overwrite to avoid fragmentation */ - if (file_is_cold(inode)) + if (file_is_cold(inode) && !is_inode_flag_set(inode, FI_OPU_WRITE)) return true; return check_inplace_update_policy(inode, fio); @@ -2397,7 +2570,12 @@ bool f2fs_should_update_outplace(struct inode *inode, struct f2fs_io_info *fio) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); - if (test_opt(sbi, LFS)) + /* The below cases were checked when setting it. */ + if (f2fs_is_pinned_file(inode)) + return false; + if (fio && is_sbi_flag_set(sbi, SBI_NEED_FSCK)) + return true; + if (f2fs_lfs_mode(sbi)) return true; if (S_ISDIR(inode->i_mode)) return true; @@ -2405,10 +2583,18 @@ bool f2fs_should_update_outplace(struct inode *inode, struct f2fs_io_info *fio) return true; if (f2fs_is_atomic_file(inode)) return true; + + /* swap file is migrating in aligned write mode */ + if (is_inode_flag_set(inode, FI_ALIGNED_WRITE)) + return true; + + if (is_inode_flag_set(inode, FI_OPU_WRITE)) + return true; + if (fio) { - if (is_cold_data(fio->page)) + if (page_private_gcing(fio->page)) return true; - if (IS_ATOMIC_WRITTEN_PAGE(fio->page)) + 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))) @@ -2432,19 +2618,27 @@ int f2fs_do_write_data_page(struct f2fs_io_info *fio) struct page *page = fio->page; struct inode *inode = page->mapping->host; struct dnode_of_data dn; - struct extent_info ei = {0,0,0}; + struct extent_info ei = {0, }; struct node_info ni; bool ipu_force = false; int err = 0; - set_new_dnode(&dn, inode, NULL, NULL, 0); + /* Use COW inode to make dnode_of_data for atomic write */ + if (f2fs_is_atomic_file(inode)) + 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_extent_cache(inode, page->index, &ei)) { fio->old_blkaddr = ei.blk + page->index - ei.fofs; if (!f2fs_is_valid_blkaddr(fio->sbi, fio->old_blkaddr, - DATA_GENERIC_ENHANCE)) + DATA_GENERIC_ENHANCE)) { + f2fs_handle_error(fio->sbi, + ERROR_INVALID_BLKADDR); return -EFSCORRUPTED; + } ipu_force = true; fio->need_lock = LOCK_DONE; @@ -2464,7 +2658,7 @@ 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_cold_data(page); + clear_page_private_gcing(page); goto out_writepage; } got_it: @@ -2472,8 +2666,10 @@ 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; } + /* * If current allocation needs SSR, * it had better in-place writes for updated data. @@ -2492,7 +2688,7 @@ got_it: f2fs_unlock_op(fio->sbi); err = f2fs_inplace_write_data(fio); if (err) { - if (f2fs_encrypted_file(inode)) + if (fscrypt_inode_uses_fs_layer_crypto(inode)) fscrypt_finalize_bounce_page(&fio->encrypted_page); if (PageWriteback(page)) end_page_writeback(page); @@ -2511,7 +2707,7 @@ got_it: fio->need_lock = LOCK_REQ; } - err = f2fs_get_node_info(fio->sbi, dn.nid, &ni); + err = f2fs_get_node_info(fio->sbi, dn.nid, &ni, false); if (err) goto out_writepage; @@ -2546,7 +2742,8 @@ int f2fs_write_single_data_page(struct page *page, int *submitted, sector_t *last_block, struct writeback_control *wbc, enum iostat_type io_type, - int compr_blocks) + int compr_blocks, + bool allow_balance) { struct inode *inode = page->mapping->host; struct f2fs_sb_info *sbi = F2FS_I_SB(inode); @@ -2569,6 +2766,7 @@ int f2fs_write_single_data_page(struct page *page, int *submitted, .submitted = false, .compr_blocks = compr_blocks, .need_lock = LOCK_RETRY, + .post_read = f2fs_post_read_required(inode), .io_type = io_type, .io_wbc = wbc, .bio = bio, @@ -2609,16 +2807,23 @@ int f2fs_write_single_data_page(struct page *page, int *submitted, write: if (f2fs_is_drop_cache(inode)) goto out; - /* we should not write 0'th page having journal header */ - if (f2fs_is_volatile_file(inode) && (!page->index || - (!wbc->for_reclaim && - f2fs_available_free_memory(sbi, BASE_CHECK)))) - goto redirty_out; - /* Dentry blocks are controlled by checkpoint */ - if (S_ISDIR(inode->i_mode)) { + /* Dentry/quota blocks are controlled by checkpoint */ + if (S_ISDIR(inode->i_mode) || IS_NOQUOTA(inode)) { + /* + * We need to wait for node_write to avoid block allocation during + * checkpoint. This can only happen to quota writes which can cause + * the below discard race condition. + */ + if (IS_NOQUOTA(inode)) + f2fs_down_read(&sbi->node_write); + fio.need_lock = LOCK_DONE; err = f2fs_do_write_data_page(&fio); + + if (IS_NOQUOTA(inode)) + f2fs_up_read(&sbi->node_write); + goto done; } @@ -2647,10 +2852,10 @@ write: if (err) { file_set_keep_isize(inode); } else { - down_write(&F2FS_I(inode)->i_sem); + spin_lock(&F2FS_I(inode)->i_size_lock); if (F2FS_I(inode)->last_disk_size < psize) F2FS_I(inode)->last_disk_size = psize; - up_write(&F2FS_I(inode)->i_sem); + spin_unlock(&F2FS_I(inode)->i_size_lock); } done: @@ -2661,7 +2866,7 @@ out: inode_dec_dirty_pages(inode); if (err) { ClearPageUptodate(page); - clear_cold_data(page); + clear_page_private_gcing(page); } if (wbc->for_reclaim) { @@ -2672,7 +2877,7 @@ out: } unlock_page(page); if (!S_ISDIR(inode->i_mode) && !IS_NOQUOTA(inode) && - !F2FS_I(inode)->cp_task) + !F2FS_I(inode)->wb_task && allow_balance) f2fs_balance_fs(sbi, need_balance_fs); if (unlikely(f2fs_cp_error(sbi))) { @@ -2719,7 +2924,7 @@ out: #endif return f2fs_write_single_data_page(page, NULL, NULL, NULL, - wbc, FS_DATA_IO, 0); + wbc, FS_DATA_IO, 0, true); } /* @@ -2733,7 +2938,7 @@ static int f2fs_write_cache_pages(struct address_space *mapping, { int ret = 0; int done = 0, retry = 0; - struct pagevec pvec; + struct page *pages[F2FS_ONSTACK_PAGES]; struct f2fs_sb_info *sbi = F2FS_M_SB(mapping); struct bio *bio = NULL; sector_t last_block; @@ -2747,6 +2952,7 @@ static int f2fs_write_cache_pages(struct address_space *mapping, .rpages = NULL, .nr_rpages = 0, .cpages = NULL, + .valid_nr_cpages = 0, .rbuf = NULL, .cbuf = NULL, .rlen = PAGE_SIZE * F2FS_I(inode)->i_cluster_size, @@ -2754,19 +2960,15 @@ static int f2fs_write_cache_pages(struct address_space *mapping, }; #endif int nr_pages; - pgoff_t uninitialized_var(writeback_index); pgoff_t index; pgoff_t end; /* Inclusive */ pgoff_t done_index; - int cycled; int range_whole = 0; xa_mark_t tag; int nwritten = 0; int submitted = 0; int i; - pagevec_init(&pvec); - if (get_dirty_pages(mapping->host) <= SM_I(F2FS_M_SB(mapping))->min_hot_blocks) set_inode_flag(mapping->host, FI_HOT_DATA); @@ -2774,19 +2976,13 @@ static int f2fs_write_cache_pages(struct address_space *mapping, clear_inode_flag(mapping->host, FI_HOT_DATA); if (wbc->range_cyclic) { - writeback_index = mapping->writeback_index; /* prev offset */ - index = writeback_index; - if (index == 0) - cycled = 1; - else - cycled = 0; + index = mapping->writeback_index; /* prev offset */ end = -1; } else { index = wbc->range_start >> PAGE_SHIFT; end = wbc->range_end >> PAGE_SHIFT; if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX) range_whole = 1; - cycled = 1; /* ignore range_cyclic tests */ } if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages) tag = PAGECACHE_TAG_TOWRITE; @@ -2798,18 +2994,22 @@ retry: tag_pages_for_writeback(mapping, index, end); done_index = index; while (!done && !retry && (index <= end)) { - nr_pages = pagevec_lookup_range_tag(&pvec, mapping, &index, end, - tag); + nr_pages = find_get_pages_range_tag(mapping, &index, end, + tag, F2FS_ONSTACK_PAGES, pages); if (nr_pages == 0) break; for (i = 0; i < nr_pages; i++) { - struct page *page = pvec.pages[i]; + struct page *page = pages[i]; bool need_readd; readd: need_readd = false; #ifdef CONFIG_F2FS_FS_COMPRESSION if (f2fs_compressed_file(inode)) { + void *fsdata = NULL; + struct page *pagep; + int ret2; + ret = f2fs_init_compress_ctx(&cc); if (ret) { done = 1; @@ -2828,27 +3028,27 @@ readd: if (unlikely(f2fs_cp_error(sbi))) goto lock_page; - if (f2fs_cluster_is_empty(&cc)) { - void *fsdata = NULL; - struct page *pagep; - int ret2; + if (!f2fs_cluster_is_empty(&cc)) + goto lock_page; - ret2 = f2fs_prepare_compress_overwrite( + if (f2fs_all_cluster_page_ready(&cc, + pages, i, nr_pages, true)) + goto lock_page; + + ret2 = f2fs_prepare_compress_overwrite( inode, &pagep, page->index, &fsdata); - if (ret2 < 0) { - ret = ret2; - done = 1; - break; - } else if (ret2 && - !f2fs_compress_write_end(inode, - fsdata, page->index, - 1)) { - retry = 1; - break; - } - } else { - goto lock_page; + if (ret2 < 0) { + ret = ret2; + done = 1; + break; + } else if (ret2 && + (!f2fs_compress_write_end(inode, + fsdata, page->index, 1) || + !f2fs_all_cluster_page_ready(&cc, + pages, i, nr_pages, false))) { + retry = 1; + break; } } #endif @@ -2895,7 +3095,8 @@ continue_unlock: } #endif ret = f2fs_write_single_data_page(page, &submitted, - &bio, &last_block, wbc, io_type, 0); + &bio, &last_block, wbc, io_type, + 0, true); if (ret == AOP_WRITEPAGE_ACTIVATE) unlock_page(page); #ifdef CONFIG_F2FS_FS_COMPRESSION @@ -2915,9 +3116,8 @@ result: } else if (ret == -EAGAIN) { ret = 0; if (wbc->sync_mode == WB_SYNC_ALL) { - cond_resched(); - congestion_wait(BLK_RW_ASYNC, - HZ/50); + f2fs_io_schedule_timeout( + DEFAULT_IO_TIMEOUT); goto retry_write; } goto next; @@ -2936,7 +3136,7 @@ next: if (need_readd) goto readd; } - pagevec_release(&pvec); + release_pages(pages, nr_pages); cond_resched(); } #ifdef CONFIG_F2FS_FS_COMPRESSION @@ -2950,13 +3150,16 @@ next: retry = 0; } } + if (f2fs_compressed_file(inode)) + f2fs_destroy_compress_ctx(&cc, false); #endif - if ((!cycled && !done) || retry) { - cycled = 1; + if (retry) { index = 0; - end = writeback_index - 1; + end = -1; goto retry; } + if (wbc->range_cyclic && !done) + done_index = 0; if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0)) mapping->writeback_index = done_index; @@ -2973,15 +3176,17 @@ next: static inline bool __should_serialize_io(struct inode *inode, struct writeback_control *wbc) { + /* to avoid deadlock in path of data flush */ + if (F2FS_I(inode)->wb_task) + return false; + if (!S_ISREG(inode->i_mode)) return false; - if (f2fs_compressed_file(inode)) - return true; if (IS_NOQUOTA(inode)) return false; - /* to avoid deadlock in path of data flush */ - if (F2FS_I(inode)->cp_task) - return false; + + if (f2fs_need_compress_data(inode)) + return true; if (wbc->sync_mode != WB_SYNC_ALL) return true; if (get_dirty_pages(inode) >= SM_I(F2FS_I_SB(inode))->min_seq_blocks) @@ -3017,8 +3222,8 @@ static int __f2fs_write_data_pages(struct address_space *mapping, f2fs_available_free_memory(sbi, DIRTY_DENTS)) goto skip_write; - /* skip writing during file defragment */ - if (is_inode_flag_set(inode, FI_DO_DEFRAG)) + /* skip writing in file defragment preparing stage */ + if (is_inode_flag_set(inode, FI_SKIP_WRITES)) goto skip_write; trace_f2fs_writepages(mapping->host, wbc, DATA); @@ -3026,8 +3231,12 @@ static int __f2fs_write_data_pages(struct address_space *mapping, /* to avoid spliting IOs due to mixed WB_SYNC_ALL and WB_SYNC_NONE */ if (wbc->sync_mode == WB_SYNC_ALL) atomic_inc(&sbi->wb_sync_req[DATA]); - else if (atomic_read(&sbi->wb_sync_req[DATA])) + else if (atomic_read(&sbi->wb_sync_req[DATA])) { + /* to avoid potential deadlock */ + if (current->plug) + blk_finish_plug(current->plug); goto skip_write; + } if (__should_serialize_io(inode, wbc)) { mutex_lock(&sbi->writepages); @@ -3067,9 +3276,8 @@ static int f2fs_write_data_pages(struct address_space *mapping, FS_CP_DATA_IO : FS_DATA_IO); } -static void f2fs_write_failed(struct address_space *mapping, loff_t to) +void f2fs_write_failed(struct inode *inode, loff_t to) { - struct inode *inode = mapping->host; loff_t i_size = i_size_read(inode); if (IS_NOQUOTA(inode)) @@ -3077,14 +3285,14 @@ static void f2fs_write_failed(struct address_space *mapping, loff_t to) /* In the fs-verity case, f2fs_end_enable_verity() does the truncate */ if (to > i_size && !f2fs_verity_in_progress(inode)) { - down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); - down_write(&F2FS_I(inode)->i_mmap_sem); + f2fs_down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); + filemap_invalidate_lock(inode->i_mapping); truncate_pagecache(inode, i_size); f2fs_truncate_blocks(inode, i_size, true); - up_write(&F2FS_I(inode)->i_mmap_sem); - up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); + filemap_invalidate_unlock(inode->i_mapping); + f2fs_up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); } } @@ -3097,17 +3305,15 @@ static int prepare_write_begin(struct f2fs_sb_info *sbi, struct dnode_of_data dn; struct page *ipage; bool locked = false; - struct extent_info ei = {0,0,0}; + struct extent_info ei = {0, }; int err = 0; int flag; /* - * we already allocated all the blocks, so we don't need to get - * the block addresses when there is no need to fill the page. + * If a whole page is being written and we already preallocated all the + * blocks, then there is no need to get a block address now. */ - if (!f2fs_has_inline_data(inode) && len == PAGE_SIZE && - !is_inode_flag_set(inode, FI_NO_PREALLOC) && - !f2fs_verity_in_progress(inode)) + if (len == PAGE_SIZE && is_inode_flag_set(inode, FI_PREALLOCATED_ALL)) return 0; /* f2fs_lock_op avoids race between write CP and convert_inline_page */ @@ -3118,7 +3324,7 @@ static int prepare_write_begin(struct f2fs_sb_info *sbi, if (f2fs_has_inline_data(inode) || (pos & PAGE_MASK) >= i_size_read(inode)) { - __do_map_lock(sbi, flag, true); + f2fs_do_map_lock(sbi, flag, true); locked = true; } @@ -3137,7 +3343,7 @@ restart: f2fs_do_read_inline_data(page, ipage); set_inode_flag(inode, FI_DATA_EXIST); if (inode->i_nlink) - set_inline_node(ipage); + set_page_private_inline(ipage); } else { err = f2fs_convert_inline_page(&dn, page); if (err) @@ -3155,7 +3361,7 @@ restart: err = f2fs_get_dnode_of_data(&dn, index, LOOKUP_NODE); if (err || dn.data_blkaddr == NULL_ADDR) { f2fs_put_dnode(&dn); - __do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO, + f2fs_do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO, true); WARN_ON(flag != F2FS_GET_BLOCK_PRE_AIO); locked = true; @@ -3171,37 +3377,123 @@ out: f2fs_put_dnode(&dn); unlock_out: if (locked) - __do_map_lock(sbi, flag, false); + f2fs_do_map_lock(sbi, flag, false); + return err; +} + +static int __find_data_block(struct inode *inode, pgoff_t index, + block_t *blk_addr) +{ + struct dnode_of_data dn; + struct page *ipage; + struct extent_info ei = {0, }; + int err = 0; + + ipage = f2fs_get_node_page(F2FS_I_SB(inode), inode->i_ino); + if (IS_ERR(ipage)) + return PTR_ERR(ipage); + + set_new_dnode(&dn, inode, ipage, ipage, 0); + + if (f2fs_lookup_extent_cache(inode, index, &ei)) { + dn.data_blkaddr = ei.blk + index - ei.fofs; + } else { + /* hole case */ + err = f2fs_get_dnode_of_data(&dn, index, LOOKUP_NODE); + if (err) { + dn.data_blkaddr = NULL_ADDR; + err = 0; + } + } + *blk_addr = dn.data_blkaddr; + f2fs_put_dnode(&dn); + return err; +} + +static int __reserve_data_block(struct inode *inode, pgoff_t index, + block_t *blk_addr, bool *node_changed) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct dnode_of_data dn; + struct page *ipage; + int err = 0; + + f2fs_do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO, true); + + ipage = f2fs_get_node_page(sbi, inode->i_ino); + if (IS_ERR(ipage)) { + err = PTR_ERR(ipage); + goto unlock_out; + } + set_new_dnode(&dn, inode, ipage, ipage, 0); + + err = f2fs_get_block(&dn, index); + + *blk_addr = dn.data_blkaddr; + *node_changed = dn.node_changed; + f2fs_put_dnode(&dn); + +unlock_out: + f2fs_do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO, false); return err; } +static int prepare_atomic_write_begin(struct f2fs_sb_info *sbi, + struct page *page, loff_t pos, unsigned int len, + block_t *blk_addr, bool *node_changed) +{ + struct inode *inode = page->mapping->host; + struct inode *cow_inode = F2FS_I(inode)->cow_inode; + pgoff_t index = page->index; + int err = 0; + block_t ori_blk_addr = NULL_ADDR; + + /* If pos is beyond the end of file, reserve a new block in COW inode */ + if ((pos & PAGE_MASK) >= i_size_read(inode)) + goto reserve_block; + + /* Look for the block in COW inode first */ + err = __find_data_block(cow_inode, index, blk_addr); + if (err) + return err; + else if (*blk_addr != NULL_ADDR) + return 0; + + /* Look for the block in the original inode */ + err = __find_data_block(inode, index, &ori_blk_addr); + if (err) + return err; + +reserve_block: + /* Finally, we should reserve a new block in COW inode for the update */ + err = __reserve_data_block(cow_inode, index, blk_addr, node_changed); + if (err) + return err; + inc_atomic_write_cnt(inode); + + if (ori_blk_addr != NULL_ADDR) + *blk_addr = ori_blk_addr; + return 0; +} + static int f2fs_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, - struct page **pagep, void **fsdata) + loff_t pos, unsigned len, struct page **pagep, 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; - bool need_balance = false, drop_atomic = false; + bool need_balance = false; block_t blkaddr = NULL_ADDR; int err = 0; - trace_f2fs_write_begin(inode, pos, len, flags); + trace_f2fs_write_begin(inode, pos, len); if (!f2fs_is_checkpoint_ready(sbi)) { err = -ENOSPC; goto fail; } - if ((f2fs_is_atomic_file(inode) && - !f2fs_available_free_memory(sbi, INMEM_PAGES)) || - is_inode_flag_set(inode, FI_ATOMIC_REVOKE_REQUEST)) { - err = -ENOMEM; - drop_atomic = true; - goto fail; - } - /* * 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: @@ -3219,6 +3511,9 @@ static int f2fs_write_begin(struct file *file, struct address_space *mapping, *fsdata = NULL; + if (len == PAGE_SIZE && !(f2fs_is_atomic_file(inode))) + goto repeat; + ret = f2fs_prepare_compress_overwrite(inode, pagep, index, fsdata); if (ret < 0) { @@ -3246,7 +3541,11 @@ repeat: *pagep = page; - err = prepare_write_begin(sbi, page, pos, len, + if (f2fs_is_atomic_file(inode)) + err = prepare_atomic_write_begin(sbi, page, pos, len, + &blkaddr, &need_balance); + else + err = prepare_write_begin(sbi, page, pos, len, &blkaddr, &need_balance); if (err) goto fail; @@ -3281,9 +3580,10 @@ repeat: if (!f2fs_is_valid_blkaddr(sbi, blkaddr, DATA_GENERIC_ENHANCE_READ)) { err = -EFSCORRUPTED; + f2fs_handle_error(sbi, ERROR_INVALID_BLKADDR); goto fail; } - err = f2fs_submit_page_read(inode, page, blkaddr); + err = f2fs_submit_page_read(inode, page, blkaddr, 0, true); if (err) goto fail; @@ -3301,9 +3601,7 @@ repeat: fail: f2fs_put_page(page, 1); - f2fs_write_failed(mapping, pos + len); - if (drop_atomic) - f2fs_drop_inmem_pages_all(sbi, false); + f2fs_write_failed(inode, pos + len); return err; } @@ -3333,6 +3631,10 @@ static int f2fs_write_end(struct file *file, if (f2fs_compressed_file(inode) && fsdata) { f2fs_compress_write_end(inode, fsdata, page->index, copied); f2fs_update_time(F2FS_I_SB(inode), REQ_TIME); + + if (pos + copied > i_size_read(inode) && + !f2fs_verity_in_progress(inode)) + f2fs_i_size_write(inode, pos + copied); return copied; } #endif @@ -3343,164 +3645,28 @@ static int f2fs_write_end(struct file *file, set_page_dirty(page); if (pos + copied > i_size_read(inode) && - !f2fs_verity_in_progress(inode)) + !f2fs_verity_in_progress(inode)) { f2fs_i_size_write(inode, pos + copied); + if (f2fs_is_atomic_file(inode)) + f2fs_i_size_write(F2FS_I(inode)->cow_inode, + pos + copied); + } unlock_out: f2fs_put_page(page, 1); f2fs_update_time(F2FS_I_SB(inode), REQ_TIME); return copied; } -static int check_direct_IO(struct inode *inode, struct iov_iter *iter, - loff_t offset) -{ - unsigned i_blkbits = READ_ONCE(inode->i_blkbits); - unsigned blkbits = i_blkbits; - unsigned blocksize_mask = (1 << blkbits) - 1; - unsigned long align = offset | iov_iter_alignment(iter); - struct block_device *bdev = inode->i_sb->s_bdev; - - if (align & blocksize_mask) { - if (bdev) - blkbits = blksize_bits(bdev_logical_block_size(bdev)); - blocksize_mask = (1 << blkbits) - 1; - if (align & blocksize_mask) - return -EINVAL; - return 1; - } - return 0; -} - -static void f2fs_dio_end_io(struct bio *bio) -{ - struct f2fs_private_dio *dio = bio->bi_private; - - dec_page_count(F2FS_I_SB(dio->inode), - dio->write ? F2FS_DIO_WRITE : F2FS_DIO_READ); - - bio->bi_private = dio->orig_private; - bio->bi_end_io = dio->orig_end_io; - - kvfree(dio); - - bio_endio(bio); -} - -static void f2fs_dio_submit_bio(struct bio *bio, struct inode *inode, - loff_t file_offset) -{ - struct f2fs_private_dio *dio; - bool write = (bio_op(bio) == REQ_OP_WRITE); - - dio = f2fs_kzalloc(F2FS_I_SB(inode), - sizeof(struct f2fs_private_dio), GFP_NOFS); - if (!dio) - goto out; - - dio->inode = inode; - dio->orig_end_io = bio->bi_end_io; - dio->orig_private = bio->bi_private; - dio->write = write; - - bio->bi_end_io = f2fs_dio_end_io; - bio->bi_private = dio; - - inc_page_count(F2FS_I_SB(inode), - write ? F2FS_DIO_WRITE : F2FS_DIO_READ); - - submit_bio(bio); - return; -out: - bio->bi_status = BLK_STS_IOERR; - bio_endio(bio); -} - -static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) -{ - struct address_space *mapping = iocb->ki_filp->f_mapping; - struct inode *inode = mapping->host; - struct f2fs_sb_info *sbi = F2FS_I_SB(inode); - struct f2fs_inode_info *fi = F2FS_I(inode); - size_t count = iov_iter_count(iter); - loff_t offset = iocb->ki_pos; - int rw = iov_iter_rw(iter); - int err; - enum rw_hint hint = iocb->ki_hint; - int whint_mode = F2FS_OPTION(sbi).whint_mode; - bool do_opu; - - err = check_direct_IO(inode, iter, offset); - if (err) - return err < 0 ? err : 0; - - if (f2fs_force_buffered_io(inode, iocb, iter)) - return 0; - - do_opu = allow_outplace_dio(inode, iocb, iter); - - trace_f2fs_direct_IO_enter(inode, offset, count, rw); - - if (rw == WRITE && whint_mode == WHINT_MODE_OFF) - iocb->ki_hint = WRITE_LIFE_NOT_SET; - - if (iocb->ki_flags & IOCB_NOWAIT) { - if (!down_read_trylock(&fi->i_gc_rwsem[rw])) { - iocb->ki_hint = hint; - err = -EAGAIN; - goto out; - } - if (do_opu && !down_read_trylock(&fi->i_gc_rwsem[READ])) { - up_read(&fi->i_gc_rwsem[rw]); - iocb->ki_hint = hint; - err = -EAGAIN; - goto out; - } - } else { - down_read(&fi->i_gc_rwsem[rw]); - if (do_opu) - down_read(&fi->i_gc_rwsem[READ]); - } - - err = __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev, - iter, rw == WRITE ? get_data_block_dio_write : - get_data_block_dio, NULL, f2fs_dio_submit_bio, - DIO_LOCKING | DIO_SKIP_HOLES); - - if (do_opu) - up_read(&fi->i_gc_rwsem[READ]); - - up_read(&fi->i_gc_rwsem[rw]); - - if (rw == WRITE) { - if (whint_mode == WHINT_MODE_OFF) - iocb->ki_hint = hint; - if (err > 0) { - f2fs_update_iostat(F2FS_I_SB(inode), APP_DIRECT_IO, - err); - if (!do_opu) - set_inode_flag(inode, FI_UPDATE_WRITE); - } else if (err < 0) { - f2fs_write_failed(mapping, offset + count); - } - } - -out: - trace_f2fs_direct_IO_exit(inode, offset, count, rw, err); - - return err; -} - -void f2fs_invalidate_page(struct page *page, unsigned int offset, - unsigned int length) +void f2fs_invalidate_folio(struct folio *folio, size_t offset, size_t length) { - struct inode *inode = page->mapping->host; + struct inode *inode = folio->mapping->host; struct f2fs_sb_info *sbi = F2FS_I_SB(inode); if (inode->i_ino >= F2FS_ROOT_INO(sbi) && - (offset % PAGE_SIZE || length != PAGE_SIZE)) + (offset || length != folio_size(folio))) return; - if (PageDirty(page)) { + if (folio_test_dirty(folio)) { if (inode->i_ino == F2FS_META_INO(sbi)) { dec_page_count(sbi, F2FS_DIRTY_META); } else if (inode->i_ino == F2FS_NODE_INO(sbi)) { @@ -3511,228 +3677,287 @@ void f2fs_invalidate_page(struct page *page, unsigned int offset, } } - clear_cold_data(page); + clear_page_private_gcing(&folio->page); - if (IS_ATOMIC_WRITTEN_PAGE(page)) - return f2fs_drop_inmem_page(inode, page); + if (test_opt(sbi, COMPRESS_CACHE) && + inode->i_ino == F2FS_COMPRESS_INO(sbi)) + clear_page_private_data(&folio->page); - f2fs_clear_page_private(page); + folio_detach_private(folio); } -int f2fs_release_page(struct page *page, gfp_t wait) +bool f2fs_release_folio(struct folio *folio, gfp_t wait) { - /* If this is dirty page, keep PagePrivate */ - if (PageDirty(page)) - return 0; + struct f2fs_sb_info *sbi; - /* This is atomic written page, keep Private */ - if (IS_ATOMIC_WRITTEN_PAGE(page)) - return 0; + /* If this is dirty folio, keep private data */ + if (folio_test_dirty(folio)) + return false; + + sbi = F2FS_M_SB(folio->mapping); + if (test_opt(sbi, COMPRESS_CACHE)) { + struct inode *inode = folio->mapping->host; + + if (inode->i_ino == F2FS_COMPRESS_INO(sbi)) + clear_page_private_data(&folio->page); + } - clear_cold_data(page); - f2fs_clear_page_private(page); - return 1; + clear_page_private_gcing(&folio->page); + + folio_detach_private(folio); + return true; } -static int f2fs_set_data_page_dirty(struct page *page) +static bool f2fs_dirty_data_folio(struct address_space *mapping, + struct folio *folio) { - struct inode *inode = page_file_mapping(page)->host; + struct inode *inode = mapping->host; - trace_f2fs_set_page_dirty(page, DATA); + trace_f2fs_set_page_dirty(&folio->page, DATA); - if (!PageUptodate(page)) - SetPageUptodate(page); - if (PageSwapCache(page)) - return __set_page_dirty_nobuffers(page); + if (!folio_test_uptodate(folio)) + folio_mark_uptodate(folio); + BUG_ON(folio_test_swapcache(folio)); - if (f2fs_is_atomic_file(inode) && !f2fs_is_commit_atomic_write(inode)) { - if (!IS_ATOMIC_WRITTEN_PAGE(page)) { - f2fs_register_inmem_page(inode, page); - return 1; - } - /* - * Previously, this page has been registered, we just - * return here. - */ - return 0; + if (filemap_dirty_folio(mapping, folio)) { + f2fs_update_dirty_folio(inode, folio); + return true; } + return false; +} + - if (!PageDirty(page)) { - __set_page_dirty_nobuffers(page); - f2fs_update_dirty_page(inode, page); - return 1; +static sector_t f2fs_bmap_compress(struct inode *inode, sector_t block) +{ +#ifdef CONFIG_F2FS_FS_COMPRESSION + struct dnode_of_data dn; + sector_t start_idx, blknr = 0; + int ret; + + start_idx = round_down(block, F2FS_I(inode)->i_cluster_size); + + set_new_dnode(&dn, inode, NULL, NULL, 0); + ret = f2fs_get_dnode_of_data(&dn, start_idx, LOOKUP_NODE); + if (ret) + return 0; + + if (dn.data_blkaddr != COMPRESS_ADDR) { + dn.ofs_in_node += block - start_idx; + blknr = f2fs_data_blkaddr(&dn); + if (!__is_valid_data_blkaddr(blknr)) + blknr = 0; } + + f2fs_put_dnode(&dn); + return blknr; +#else return 0; +#endif } + static sector_t f2fs_bmap(struct address_space *mapping, sector_t block) { struct inode *inode = mapping->host; + sector_t blknr = 0; if (f2fs_has_inline_data(inode)) - return 0; + goto out; /* make sure allocating whole blocks */ if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) filemap_write_and_wait(mapping); - return generic_block_bmap(mapping, block, get_data_block_bmap); -} + /* Block number less than F2FS MAX BLOCKS */ + if (unlikely(block >= max_file_blocks(inode))) + goto out; -#ifdef CONFIG_MIGRATION -#include <linux/migrate.h> + if (f2fs_compressed_file(inode)) { + blknr = f2fs_bmap_compress(inode, block); + } else { + struct f2fs_map_blocks map; + + memset(&map, 0, sizeof(map)); + map.m_lblk = block; + map.m_len = 1; + map.m_next_pgofs = NULL; + map.m_seg_type = NO_CHECK_TYPE; + + if (!f2fs_map_blocks(inode, &map, 0, F2FS_GET_BLOCK_BMAP)) + blknr = map.m_pblk; + } +out: + trace_f2fs_bmap(inode, block, blknr); + return blknr; +} -int f2fs_migrate_page(struct address_space *mapping, - struct page *newpage, struct page *page, enum migrate_mode mode) +#ifdef CONFIG_SWAP +static int f2fs_migrate_blocks(struct inode *inode, block_t start_blk, + unsigned int blkcnt) { - int rc, extra_count; - struct f2fs_inode_info *fi = F2FS_I(mapping->host); - bool atomic_written = IS_ATOMIC_WRITTEN_PAGE(page); + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + unsigned int blkofs; + unsigned int blk_per_sec = BLKS_PER_SEC(sbi); + unsigned int secidx = start_blk / blk_per_sec; + unsigned int end_sec = secidx + blkcnt / blk_per_sec; + int ret = 0; - BUG_ON(PageWriteback(page)); + f2fs_down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); + filemap_invalidate_lock(inode->i_mapping); - /* migrating an atomic written page is safe with the inmem_lock hold */ - if (atomic_written) { - if (mode != MIGRATE_SYNC) - return -EBUSY; - if (!mutex_trylock(&fi->inmem_lock)) - return -EAGAIN; - } + set_inode_flag(inode, FI_ALIGNED_WRITE); + set_inode_flag(inode, FI_OPU_WRITE); - /* one extra reference was held for atomic_write page */ - extra_count = atomic_written ? 1 : 0; - rc = migrate_page_move_mapping(mapping, newpage, - page, extra_count); - if (rc != MIGRATEPAGE_SUCCESS) { - if (atomic_written) - mutex_unlock(&fi->inmem_lock); - return rc; - } + for (; secidx < end_sec; secidx++) { + f2fs_down_write(&sbi->pin_sem); - if (atomic_written) { - struct inmem_pages *cur; - list_for_each_entry(cur, &fi->inmem_pages, list) - if (cur->page == page) { - cur->page = newpage; - break; + f2fs_lock_op(sbi); + f2fs_allocate_new_section(sbi, CURSEG_COLD_DATA_PINNED, false); + f2fs_unlock_op(sbi); + + set_inode_flag(inode, FI_SKIP_WRITES); + + for (blkofs = 0; blkofs < blk_per_sec; blkofs++) { + struct page *page; + unsigned int blkidx = secidx * blk_per_sec + blkofs; + + page = f2fs_get_lock_data_page(inode, blkidx, true); + if (IS_ERR(page)) { + f2fs_up_write(&sbi->pin_sem); + ret = PTR_ERR(page); + goto done; } - mutex_unlock(&fi->inmem_lock); - put_page(page); - get_page(newpage); - } - if (PagePrivate(page)) { - f2fs_set_page_private(newpage, page_private(page)); - f2fs_clear_page_private(page); + set_page_dirty(page); + f2fs_put_page(page, 1); + } + + clear_inode_flag(inode, FI_SKIP_WRITES); + + ret = filemap_fdatawrite(inode->i_mapping); + + f2fs_up_write(&sbi->pin_sem); + + if (ret) + break; } - if (mode != MIGRATE_SYNC_NO_COPY) - migrate_page_copy(newpage, page); - else - migrate_page_states(newpage, page); +done: + clear_inode_flag(inode, FI_SKIP_WRITES); + clear_inode_flag(inode, FI_OPU_WRITE); + clear_inode_flag(inode, FI_ALIGNED_WRITE); + + filemap_invalidate_unlock(inode->i_mapping); + f2fs_up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); - return MIGRATEPAGE_SUCCESS; + return ret; } -#endif -#ifdef CONFIG_SWAP -/* Copied from generic_swapfile_activate() to check any holes */ static int check_swap_activate(struct swap_info_struct *sis, struct file *swap_file, sector_t *span) { struct address_space *mapping = swap_file->f_mapping; struct inode *inode = mapping->host; - unsigned blocks_per_page; - unsigned long page_no; - unsigned blkbits; - sector_t probe_block; - sector_t last_block; - sector_t lowest_block = -1; - sector_t highest_block = 0; + 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; int nr_extents = 0; - int ret; - - blkbits = inode->i_blkbits; - blocks_per_page = PAGE_SIZE >> blkbits; + unsigned long 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; /* * Map all the blocks into the extent list. This code doesn't try * to be very smart. */ - probe_block = 0; - page_no = 0; - last_block = i_size_read(inode) >> blkbits; - while ((probe_block + blocks_per_page) <= last_block && - page_no < sis->max) { - unsigned block_in_page; - sector_t first_block; - sector_t block = 0; - int err = 0; + cur_lblock = 0; + last_lblock = bytes_to_blks(inode, i_size_read(inode)); + while (cur_lblock < last_lblock && cur_lblock < sis->max) { + struct f2fs_map_blocks map; +retry: cond_resched(); - block = probe_block; - err = bmap(inode, &block); - if (err || !block) - goto bad_bmap; - first_block = block; + memset(&map, 0, sizeof(map)); + map.m_lblk = cur_lblock; + map.m_len = last_lblock - cur_lblock; + map.m_next_pgofs = NULL; + map.m_next_extent = NULL; + map.m_seg_type = NO_CHECK_TYPE; + map.m_may_create = false; - /* - * It must be PAGE_SIZE aligned on-disk - */ - if (first_block & (blocks_per_page - 1)) { - probe_block++; - goto reprobe; + ret = f2fs_map_blocks(inode, &map, 0, F2FS_GET_BLOCK_FIEMAP); + if (ret) + goto out; + + /* hole */ + if (!(map.m_flags & F2FS_MAP_FLAGS)) { + f2fs_err(sbi, "Swapfile has holes"); + ret = -EINVAL; + goto out; } - for (block_in_page = 1; block_in_page < blocks_per_page; - block_in_page++) { + pblock = map.m_pblk; + nr_pblocks = map.m_len; - block = probe_block + block_in_page; - err = bmap(inode, &block); + if ((pblock - SM_I(sbi)->main_blkaddr) & sec_blks_mask || + nr_pblocks & sec_blks_mask) { + not_aligned++; - if (err || !block) - goto bad_bmap; + nr_pblocks = roundup(nr_pblocks, blks_per_sec); + if (cur_lblock + nr_pblocks > sis->max) + nr_pblocks -= blks_per_sec; - if (block != first_block + block_in_page) { - /* Discontiguity */ - probe_block++; - goto reprobe; + 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; } - } - first_block >>= (PAGE_SHIFT - blkbits); - if (page_no) { /* exclude the header page */ - if (first_block < lowest_block) - lowest_block = first_block; - if (first_block > highest_block) - highest_block = first_block; + ret = f2fs_migrate_blocks(inode, cur_lblock, + nr_pblocks); + if (ret) + goto out; + goto retry; + } +next: + if (cur_lblock + nr_pblocks >= sis->max) + nr_pblocks = sis->max - cur_lblock; + + if (cur_lblock) { /* exclude the header page */ + if (pblock < lowest_pblock) + lowest_pblock = pblock; + if (pblock + nr_pblocks - 1 > highest_pblock) + highest_pblock = pblock + nr_pblocks - 1; } /* * We found a PAGE_SIZE-length, PAGE_SIZE-aligned run of blocks */ - ret = add_swap_extent(sis, page_no, 1, first_block); + ret = add_swap_extent(sis, cur_lblock, nr_pblocks, pblock); if (ret < 0) goto out; nr_extents += ret; - page_no++; - probe_block += blocks_per_page; -reprobe: - continue; + cur_lblock += nr_pblocks; } ret = nr_extents; - *span = 1 + highest_block - lowest_block; - if (page_no == 0) - page_no = 1; /* force Empty message */ - sis->max = page_no; - sis->pages = page_no - 1; - sis->highest_bit = page_no - 1; + *span = 1 + highest_pblock - lowest_pblock; + if (cur_lblock == 0) + 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)", + not_aligned, blks_per_sec * F2FS_BLKSIZE); return ret; -bad_bmap: - pr_err("swapon: swapfile has holes\n"); - return -EINVAL; } static int f2fs_swap_activate(struct swap_info_struct *sis, struct file *file, @@ -3747,19 +3972,27 @@ static int f2fs_swap_activate(struct swap_info_struct *sis, struct file *file, if (f2fs_readonly(F2FS_I_SB(inode)->sb)) return -EROFS; + if (f2fs_lfs_mode(F2FS_I_SB(inode))) { + f2fs_err(F2FS_I_SB(inode), + "Swapfile not supported in LFS mode"); + return -EINVAL; + } + ret = f2fs_convert_inline_inode(inode); if (ret) return ret; - if (f2fs_disable_compressed_file(inode)) + if (!f2fs_disable_compressed_file(inode)) return -EINVAL; + f2fs_precache_extents(inode); + ret = check_swap_activate(sis, file, span); if (ret < 0) return ret; + stat_inc_swapfile_inode(inode); set_inode_flag(inode, FI_PIN_FILE); - f2fs_precache_extents(inode); f2fs_update_time(F2FS_I_SB(inode), REQ_TIME); return ret; } @@ -3768,6 +4001,7 @@ static void f2fs_swap_deactivate(struct file *file) { struct inode *inode = file_inode(file); + stat_dec_swapfile_inode(inode); clear_inode_flag(inode, FI_PIN_FILE); } #else @@ -3783,22 +4017,20 @@ static void f2fs_swap_deactivate(struct file *file) #endif const struct address_space_operations f2fs_dblock_aops = { - .readpage = f2fs_read_data_page, - .readpages = f2fs_read_data_pages, + .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, - .set_page_dirty = f2fs_set_data_page_dirty, - .invalidatepage = f2fs_invalidate_page, - .releasepage = f2fs_release_page, - .direct_IO = f2fs_direct_IO, + .dirty_folio = f2fs_dirty_data_folio, + .migrate_folio = filemap_migrate_folio, + .invalidate_folio = f2fs_invalidate_folio, + .release_folio = f2fs_release_folio, + .direct_IO = noop_direct_IO, .bmap = f2fs_bmap, .swap_activate = f2fs_swap_activate, .swap_deactivate = f2fs_swap_deactivate, -#ifdef CONFIG_MIGRATION - .migratepage = f2fs_migrate_page, -#endif }; void f2fs_clear_page_cache_dirty_tag(struct page *page) @@ -3861,7 +4093,7 @@ void f2fs_destroy_post_read_wq(struct f2fs_sb_info *sbi) int __init f2fs_init_bio_entry_cache(void) { - bio_entry_slab = f2fs_kmem_cache_create("bio_entry_slab", + bio_entry_slab = f2fs_kmem_cache_create("f2fs_bio_entry_slab", sizeof(struct bio_entry)); if (!bio_entry_slab) return -ENOMEM; @@ -3872,3 +4104,65 @@ void f2fs_destroy_bio_entry_cache(void) { kmem_cache_destroy(bio_entry_slab); } + +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 = {}; + 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_next_pgofs = &next_pgofs; + map.m_seg_type = f2fs_rw_hint_to_seg_type(inode->i_write_hint); + if (flags & IOMAP_WRITE) + map.m_may_create = true; + + err = f2fs_map_blocks(inode, &map, flags & IOMAP_WRITE, + F2FS_GET_BLOCK_DIO); + if (err) + return err; + + iomap->offset = blks_to_bytes(inode, map.m_lblk); + + /* + * When inline encryption is enabled, sometimes I/O to an encrypted file + * has to be broken up to guarantee DUN contiguity. Handle this by + * limiting the length of the mapping returned. + */ + map.m_len = fscrypt_limit_io_blocks(inode, map.m_lblk, map.m_len); + + if (map.m_flags & (F2FS_MAP_MAPPED | F2FS_MAP_UNWRITTEN)) { + iomap->length = blks_to_bytes(inode, map.m_len); + if (map.m_flags & F2FS_MAP_MAPPED) { + iomap->type = IOMAP_MAPPED; + iomap->flags |= IOMAP_F_MERGED; + } else { + iomap->type = IOMAP_UNWRITTEN; + } + if (WARN_ON_ONCE(!__is_valid_data_blkaddr(map.m_pblk))) + return -EINVAL; + + iomap->bdev = map.m_bdev; + iomap->addr = blks_to_bytes(inode, map.m_pblk); + } else { + iomap->length = blks_to_bytes(inode, next_pgofs) - + iomap->offset; + iomap->type = IOMAP_HOLE; + iomap->addr = IOMAP_NULL_ADDR; + } + + if (map.m_flags & F2FS_MAP_NEW) + iomap->flags |= IOMAP_F_NEW; + if ((inode->i_state & I_DIRTY_DATASYNC) || + offset + length > i_size_read(inode)) + iomap->flags |= IOMAP_F_DIRTY; + + return 0; +} + +const struct iomap_ops f2fs_iomap_ops = { + .iomap_begin = f2fs_iomap_begin, +}; |