diff options
38 files changed, 1075 insertions, 386 deletions
diff --git a/Documentation/ABI/testing/sysfs-fs-f2fs b/Documentation/ABI/testing/sysfs-fs-f2fs index 67b3ed8e8c2f..3dfee94e0618 100644 --- a/Documentation/ABI/testing/sysfs-fs-f2fs +++ b/Documentation/ABI/testing/sysfs-fs-f2fs @@ -370,3 +370,10 @@ Date: April 2020 Contact: "Daeho Jeong" <daehojeong@google.com> Description: Give a way to change iostat_period time. 3secs by default. The new iostat trace gives stats gap given the period. +What: /sys/fs/f2fs/<disk>/max_io_bytes +Date: December 2020 +Contact: "Jaegeuk Kim" <jaegeuk@kernel.org> +Description: This gives a control to limit the bio size in f2fs. + Default is zero, which will follow underlying block layer limit, + whereas, if it has a certain bytes value, f2fs won't submit a + bio larger than that size. diff --git a/Documentation/filesystems/f2fs.rst b/Documentation/filesystems/f2fs.rst index b8ee761c9922..dae15c96e659 100644 --- a/Documentation/filesystems/f2fs.rst +++ b/Documentation/filesystems/f2fs.rst @@ -260,6 +260,14 @@ compress_extension=%s Support adding specified extension, so that f2fs can enab For other files, we can still enable compression via ioctl. Note that, there is one reserved special extension '*', it can be set to enable compression for all files. +compress_chksum Support verifying chksum of raw data in compressed cluster. +compress_mode=%s Control file compression mode. This supports "fs" and "user" + modes. In "fs" mode (default), f2fs does automatic compression + on the compression enabled files. In "user" mode, f2fs disables + the automaic compression and gives the user discretion of + choosing the target file and the timing. The user can do manual + compression/decompression on the compression enabled files using + ioctls. inlinecrypt When possible, encrypt/decrypt the contents of encrypted files using the blk-crypto framework rather than filesystem-layer encryption. This allows the use of @@ -810,6 +818,34 @@ Compress metadata layout:: | data length | data chksum | reserved | compressed data | +-------------+-------------+----------+----------------------------+ +Compression mode +-------------------------- + +f2fs supports "fs" and "user" compression modes with "compression_mode" mount option. +With this option, f2fs provides a choice to select the way how to compress the +compression enabled files (refer to "Compression implementation" section for how to +enable compression on a regular inode). + +1) compress_mode=fs +This is the default option. f2fs does automatic compression in the writeback of the +compression enabled files. + +2) compress_mode=user +This disables the automaic compression and gives the user discretion of choosing the +target file and the timing. The user can do manual compression/decompression on the +compression enabled files using F2FS_IOC_DECOMPRESS_FILE and F2FS_IOC_COMPRESS_FILE +ioctls like the below. + +To decompress a file, + +fd = open(filename, O_WRONLY, 0); +ret = ioctl(fd, F2FS_IOC_DECOMPRESS_FILE); + +To compress a file, + +fd = open(filename, O_WRONLY, 0); +ret = ioctl(fd, F2FS_IOC_COMPRESS_FILE); + NVMe Zoned Namespace devices ---------------------------- diff --git a/MAINTAINERS b/MAINTAINERS index f59ebd1eda3d..b35b04abd08d 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -6746,6 +6746,7 @@ F: Documentation/filesystems/f2fs.rst F: fs/f2fs/ F: include/linux/f2fs_fs.h F: include/trace/events/f2fs.h +F: include/uapi/linux/f2fs.h F71805F HARDWARE MONITORING DRIVER M: Jean Delvare <jdelvare@suse.com> diff --git a/fs/crypto/fname.c b/fs/crypto/fname.c index 3414d35ccbb6..6ca7d16593ff 100644 --- a/fs/crypto/fname.c +++ b/fs/crypto/fname.c @@ -574,7 +574,3 @@ int fscrypt_d_revalidate(struct dentry *dentry, unsigned int flags) return valid; } EXPORT_SYMBOL_GPL(fscrypt_d_revalidate); - -const struct dentry_operations fscrypt_d_ops = { - .d_revalidate = fscrypt_d_revalidate, -}; diff --git a/fs/crypto/fscrypt_private.h b/fs/crypto/fscrypt_private.h index f0bed6b06fa6..3fa965eb3336 100644 --- a/fs/crypto/fscrypt_private.h +++ b/fs/crypto/fscrypt_private.h @@ -297,7 +297,6 @@ int fscrypt_fname_encrypt(const struct inode *inode, const struct qstr *iname, bool fscrypt_fname_encrypted_size(const union fscrypt_policy *policy, u32 orig_len, u32 max_len, u32 *encrypted_len_ret); -extern const struct dentry_operations fscrypt_d_ops; /* hkdf.c */ diff --git a/fs/crypto/hooks.c b/fs/crypto/hooks.c index 79570e0e8e61..a73b0376e6f3 100644 --- a/fs/crypto/hooks.c +++ b/fs/crypto/hooks.c @@ -108,7 +108,6 @@ int __fscrypt_prepare_lookup(struct inode *dir, struct dentry *dentry, spin_lock(&dentry->d_lock); dentry->d_flags |= DCACHE_NOKEY_NAME; spin_unlock(&dentry->d_lock); - d_set_d_op(dentry, &fscrypt_d_ops); } return err; } diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c index c6d16353326a..5ed870614c8d 100644 --- a/fs/ext4/dir.c +++ b/fs/ext4/dir.c @@ -657,10 +657,3 @@ const struct file_operations ext4_dir_operations = { .fsync = ext4_sync_file, .release = ext4_release_dir, }; - -#ifdef CONFIG_UNICODE -const struct dentry_operations ext4_dentry_ops = { - .d_hash = generic_ci_d_hash, - .d_compare = generic_ci_d_compare, -}; -#endif diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 65ecaf96d0a4..c64ea8f59ea7 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -3381,10 +3381,6 @@ static inline void ext4_unlock_group(struct super_block *sb, /* dir.c */ extern const struct file_operations ext4_dir_operations; -#ifdef CONFIG_UNICODE -extern const struct dentry_operations ext4_dentry_ops; -#endif - /* file.c */ extern const struct inode_operations ext4_file_inode_operations; extern const struct file_operations ext4_file_operations; diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 5fa8436cd5fa..326fe402e495 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -1608,6 +1608,7 @@ static struct buffer_head *ext4_lookup_entry(struct inode *dir, struct buffer_head *bh; err = ext4_fname_prepare_lookup(dir, dentry, &fname); + generic_set_encrypted_ci_d_ops(dentry); if (err == -ENOENT) return NULL; if (err) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index a2ec60fa8811..830c196ec069 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -4963,11 +4963,6 @@ no_journal: goto failed_mount4; } -#ifdef CONFIG_UNICODE - if (sb->s_encoding) - sb->s_d_op = &ext4_dentry_ops; -#endif - sb->s_root = d_make_root(root); if (!sb->s_root) { ext4_msg(sb, KERN_ERR, "get root dentry failed"); diff --git a/fs/f2fs/acl.c b/fs/f2fs/acl.c index 306413589827..1e5e9b1136ee 100644 --- a/fs/f2fs/acl.c +++ b/fs/f2fs/acl.c @@ -384,7 +384,7 @@ int f2fs_init_acl(struct inode *inode, struct inode *dir, struct page *ipage, struct page *dpage) { struct posix_acl *default_acl = NULL, *acl = NULL; - int error = 0; + int error; error = f2fs_acl_create(dir, &inode->i_mode, &default_acl, &acl, dpage); if (error) diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c index 54a1905af052..897edb7c951a 100644 --- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -37,7 +37,7 @@ void f2fs_stop_checkpoint(struct f2fs_sb_info *sbi, bool end_io) struct page *f2fs_grab_meta_page(struct f2fs_sb_info *sbi, pgoff_t index) { struct address_space *mapping = META_MAPPING(sbi); - struct page *page = NULL; + struct page *page; repeat: page = f2fs_grab_cache_page(mapping, index, false); if (!page) { @@ -348,13 +348,13 @@ static int f2fs_write_meta_pages(struct address_space *mapping, goto skip_write; /* if locked failed, cp will flush dirty pages instead */ - if (!mutex_trylock(&sbi->cp_mutex)) + if (!down_write_trylock(&sbi->cp_global_sem)) goto skip_write; trace_f2fs_writepages(mapping->host, wbc, META); diff = nr_pages_to_write(sbi, META, wbc); written = f2fs_sync_meta_pages(sbi, META, wbc->nr_to_write, FS_META_IO); - mutex_unlock(&sbi->cp_mutex); + up_write(&sbi->cp_global_sem); wbc->nr_to_write = max((long)0, wbc->nr_to_write - written - diff); return 0; @@ -1385,6 +1385,26 @@ static void commit_checkpoint(struct f2fs_sb_info *sbi, f2fs_submit_merged_write(sbi, META_FLUSH); } +static inline u64 get_sectors_written(struct block_device *bdev) +{ + return (u64)part_stat_read(bdev, sectors[STAT_WRITE]); +} + +u64 f2fs_get_sectors_written(struct f2fs_sb_info *sbi) +{ + if (f2fs_is_multi_device(sbi)) { + u64 sectors = 0; + int i; + + for (i = 0; i < sbi->s_ndevs; i++) + sectors += get_sectors_written(FDEV(i).bdev); + + return sectors; + } + + return get_sectors_written(sbi->sb->s_bdev); +} + static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) { struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi); @@ -1488,8 +1508,9 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) start_blk += data_sum_blocks; /* Record write statistics in the hot node summary */ - kbytes_written = sbi->kbytes_written + BD_PART_WRITTEN(sbi); - + kbytes_written = sbi->kbytes_written; + kbytes_written += (f2fs_get_sectors_written(sbi) - + sbi->sectors_written_start) >> 1; seg_i->journal->info.kbytes_written = cpu_to_le64(kbytes_written); if (__remain_node_summaries(cpc->reason)) { @@ -1569,7 +1590,7 @@ int f2fs_write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) f2fs_warn(sbi, "Start checkpoint disabled!"); } if (cpc->reason != CP_RESIZE) - mutex_lock(&sbi->cp_mutex); + down_write(&sbi->cp_global_sem); if (!is_sbi_flag_set(sbi, SBI_IS_DIRTY) && ((cpc->reason & CP_FASTBOOT) || (cpc->reason & CP_SYNC) || @@ -1597,7 +1618,7 @@ int f2fs_write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) goto out; } - if (NM_I(sbi)->dirty_nat_cnt == 0 && + if (NM_I(sbi)->nat_cnt[DIRTY_NAT] == 0 && SIT_I(sbi)->dirty_sentries == 0 && prefree_segments(sbi) == 0) { f2fs_flush_sit_entries(sbi, cpc); @@ -1644,7 +1665,7 @@ stop: trace_f2fs_write_checkpoint(sbi->sb, cpc->reason, "finish checkpoint"); out: if (cpc->reason != CP_RESIZE) - mutex_unlock(&sbi->cp_mutex); + up_write(&sbi->cp_global_sem); return err; } diff --git a/fs/f2fs/compress.c b/fs/f2fs/compress.c index 14262e0f1cd6..4bcbacfe3325 100644 --- a/fs/f2fs/compress.c +++ b/fs/f2fs/compress.c @@ -602,6 +602,7 @@ static int f2fs_compress_pages(struct compress_ctx *cc) f2fs_cops[fi->i_compress_algorithm]; unsigned int max_len, new_nr_cpages; struct page **new_cpages; + u32 chksum = 0; int i, ret; trace_f2fs_compress_pages_start(cc->inode, cc->cluster_idx, @@ -655,6 +656,11 @@ static int f2fs_compress_pages(struct compress_ctx *cc) cc->cbuf->clen = cpu_to_le32(cc->clen); + if (fi->i_compress_flag & 1 << COMPRESS_CHKSUM) + chksum = f2fs_crc32(F2FS_I_SB(cc->inode), + cc->cbuf->cdata, cc->clen); + cc->cbuf->chksum = cpu_to_le32(chksum); + for (i = 0; i < COMPRESS_DATA_RESERVED_SIZE; i++) cc->cbuf->reserved[i] = cpu_to_le32(0); @@ -790,6 +796,22 @@ void f2fs_decompress_pages(struct bio *bio, struct page *page, bool verity) ret = cops->decompress_pages(dic); + if (!ret && (fi->i_compress_flag & 1 << COMPRESS_CHKSUM)) { + u32 provided = le32_to_cpu(dic->cbuf->chksum); + u32 calculated = f2fs_crc32(sbi, dic->cbuf->cdata, dic->clen); + + if (provided != calculated) { + if (!is_inode_flag_set(dic->inode, FI_COMPRESS_CORRUPT)) { + set_inode_flag(dic->inode, FI_COMPRESS_CORRUPT); + printk_ratelimited( + "%sF2FS-fs (%s): checksum invalid, nid = %lu, %x vs %x", + KERN_INFO, sbi->sb->s_id, dic->inode->i_ino, + provided, calculated); + } + set_sbi_flag(sbi, SBI_NEED_FSCK); + } + } + out_vunmap_cbuf: vm_unmap_ram(dic->cbuf, dic->nr_cpages); out_vunmap_rbuf: @@ -798,8 +820,6 @@ destroy_decompress_ctx: if (cops->destroy_decompress_ctx) cops->destroy_decompress_ctx(dic); out_free_dic: - if (verity) - atomic_set(&dic->pending_pages, dic->nr_cpages); if (!verity) f2fs_decompress_end_io(dic->rpages, dic->cluster_size, ret, false); @@ -921,7 +941,7 @@ int f2fs_is_compressed_cluster(struct inode *inode, pgoff_t index) static bool cluster_may_compress(struct compress_ctx *cc) { - if (!f2fs_compressed_file(cc->inode)) + if (!f2fs_need_compress_data(cc->inode)) return false; if (f2fs_is_atomic_file(cc->inode)) return false; diff --git a/fs/f2fs/compress.h b/fs/f2fs/compress.h new file mode 100644 index 000000000000..e69de29bb2d1 --- /dev/null +++ b/fs/f2fs/compress.h diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index be4da52604ed..aa34d620bec9 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -202,7 +202,7 @@ static void f2fs_verify_bio(struct bio *bio) dic = (struct decompress_io_ctx *)page_private(page); if (dic) { - if (atomic_dec_return(&dic->pending_pages)) + if (atomic_dec_return(&dic->verity_pages)) continue; f2fs_verify_pages(dic->rpages, dic->cluster_size); @@ -736,6 +736,9 @@ 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); @@ -1027,7 +1030,8 @@ static inline bool f2fs_need_verity(const struct inode *inode, pgoff_t idx) static struct bio *f2fs_grab_read_bio(struct inode *inode, block_t blkaddr, unsigned nr_pages, unsigned op_flag, - pgoff_t first_idx, bool for_write) + pgoff_t first_idx, bool for_write, + bool for_verity) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct bio *bio; @@ -1049,7 +1053,7 @@ static struct bio *f2fs_grab_read_bio(struct inode *inode, block_t blkaddr, post_read_steps |= 1 << STEP_DECRYPT; if (f2fs_compressed_file(inode)) post_read_steps |= 1 << STEP_DECOMPRESS_NOWQ; - if (f2fs_need_verity(inode, first_idx)) + if (for_verity && f2fs_need_verity(inode, first_idx)) post_read_steps |= 1 << STEP_VERITY; if (post_read_steps) { @@ -1079,7 +1083,7 @@ static int f2fs_submit_page_read(struct inode *inode, struct page *page, struct bio *bio; bio = f2fs_grab_read_bio(inode, blkaddr, 1, op_flags, - page->index, for_write); + page->index, for_write, true); if (IS_ERR(bio)) return PTR_ERR(bio); @@ -1750,6 +1754,16 @@ bool f2fs_overwrite_io(struct inode *inode, loff_t pos, size_t len) return true; } +static inline u64 bytes_to_blks(struct inode *inode, u64 bytes) +{ + return (bytes >> inode->i_blkbits); +} + +static inline u64 blks_to_bytes(struct inode *inode, u64 blks) +{ + return (blks << inode->i_blkbits); +} + static int __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) @@ -1758,7 +1772,7 @@ static int __get_data_block(struct inode *inode, sector_t iblock, int err; map.m_lblk = iblock; - map.m_len = bh->b_size >> inode->i_blkbits; + map.m_len = bytes_to_blks(inode, bh->b_size); map.m_next_pgofs = next_pgofs; map.m_next_extent = NULL; map.m_seg_type = seg_type; @@ -1768,20 +1782,11 @@ static int __get_data_block(struct inode *inode, sector_t iblock, 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; + bh->b_size = blks_to_bytes(inode, map.m_len); } 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) { @@ -1800,24 +1805,6 @@ static int get_data_block_dio(struct inode *inode, sector_t iblock, false); } -static int get_data_block_bmap(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_BMAP, NULL, - NO_CHECK_TYPE, create); -} - -static inline sector_t logical_to_blk(struct inode *inode, loff_t offset) -{ - return (offset >> inode->i_blkbits); -} - -static inline loff_t blk_to_logical(struct inode *inode, sector_t blk) -{ - return (blk << inode->i_blkbits); -} - static int f2fs_xattr_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo) { @@ -1843,7 +1830,7 @@ static int f2fs_xattr_fiemap(struct inode *inode, 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)); @@ -1875,7 +1862,7 @@ static int f2fs_xattr_fiemap(struct inode *inode, 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); @@ -1913,7 +1900,7 @@ static loff_t max_inode_blocks(struct inode *inode) 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; @@ -1945,29 +1932,31 @@ 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_bh.b_size = blk_to_logical(inode, cluster_size - 1); + map.m_len = cluster_size - 1; - 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 (!(map.m_flags & F2FS_MAP_FLAGS)) { start_blk = next_pgofs; - if (blk_to_logical(inode, start_blk) < blk_to_logical(inode, + if (blks_to_bytes(inode, start_blk) < blks_to_bytes(inode, max_inode_blocks(inode))) goto prep_next; @@ -1993,9 +1982,9 @@ next: compr_cluster = false; - logical = blk_to_logical(inode, start_blk - 1); - phys = blk_to_logical(inode, map_bh.b_blocknr); - size = blk_to_logical(inode, cluster_size); + logical = blks_to_bytes(inode, start_blk - 1); + phys = blks_to_bytes(inode, map.m_pblk); + size = blks_to_bytes(inode, cluster_size); flags |= FIEMAP_EXTENT_ENCODED; @@ -2007,20 +1996,20 @@ next: goto prep_next; } - if (map_bh.b_blocknr == COMPRESS_ADDR) { + if (map.m_pblk == COMPRESS_ADDR) { compr_cluster = true; start_blk++; goto prep_next; } - logical = blk_to_logical(inode, start_blk); - phys = blk_to_logical(inode, map_bh.b_blocknr); - size = map_bh.b_size; + logical = blks_to_bytes(inode, start_blk); + phys = blks_to_bytes(inode, map.m_pblk); + size = blks_to_bytes(inode, map.m_len); flags = 0; - if (buffer_unwritten(&map_bh)) + 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(); @@ -2053,8 +2042,7 @@ 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; @@ -2063,8 +2051,8 @@ 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; @@ -2133,7 +2121,7 @@ submit_and_realloc: if (bio == NULL) { bio = f2fs_grab_read_bio(inode, block_nr, nr_pages, is_readahead ? REQ_RAHEAD : 0, page->index, - false); + false, true); if (IS_ERR(bio)) { ret = PTR_ERR(bio); bio = NULL; @@ -2177,16 +2165,17 @@ 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 bio_post_read_ctx *ctx; + bool for_verity = false; int i; int ret = 0; f2fs_bug_on(sbi, f2fs_cluster_is_empty(cc)); - 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); /* get rid of pages beyond EOF */ for (i = 0; i < cc->cluster_size; i++) { @@ -2245,10 +2234,29 @@ int f2fs_read_multi_pages(struct compress_ctx *cc, struct bio **bio_ret, goto out_put_dnode; } + /* + * It's possible to enable fsverity on the fly when handling a cluster, + * which requires complicated error handling. Instead of adding more + * complexity, let's give a rule where end_io post-processes fsverity + * per cluster. In order to do that, we need to submit bio, if previous + * bio sets a different post-process policy. + */ + if (fsverity_active(cc->inode)) { + atomic_set(&dic->verity_pages, cc->nr_cpages); + for_verity = true; + + if (bio) { + ctx = bio->bi_private; + if (!(ctx->enabled_steps & (1 << STEP_VERITY))) { + __submit_bio(sbi, bio, DATA); + bio = NULL; + } + } + } + for (i = 0; i < dic->nr_cpages; i++) { struct page *page = dic->cpages[i]; block_t blkaddr; - struct bio_post_read_ctx *ctx; blkaddr = data_blkaddr(dn.inode, dn.node_page, dn.ofs_in_node + i + 1); @@ -2264,17 +2272,31 @@ submit_and_realloc: if (!bio) { bio = f2fs_grab_read_bio(inode, blkaddr, nr_pages, is_readahead ? REQ_RAHEAD : 0, - page->index, for_write); + page->index, for_write, for_verity); if (IS_ERR(bio)) { + unsigned int remained = dic->nr_cpages - i; + bool release = false; + ret = PTR_ERR(bio); dic->failed = true; - if (!atomic_sub_return(dic->nr_cpages - i, - &dic->pending_pages)) { + + if (for_verity) { + if (!atomic_sub_return(remained, + &dic->verity_pages)) + release = true; + } else { + if (!atomic_sub_return(remained, + &dic->pending_pages)) + release = true; + } + + if (release) { f2fs_decompress_end_io(dic->rpages, - cc->cluster_size, true, - false); + cc->cluster_size, true, + false); f2fs_free_dic(dic); } + f2fs_put_dnode(&dn); *bio_ret = NULL; return ret; @@ -3164,7 +3186,7 @@ static inline bool __should_serialize_io(struct inode *inode, if (IS_NOQUOTA(inode)) return false; - if (f2fs_compressed_file(inode)) + if (f2fs_need_compress_data(inode)) return true; if (wbc->sync_mode != WB_SYNC_ALL) return true; @@ -3799,9 +3821,6 @@ static sector_t f2fs_bmap_compress(struct inode *inode, sector_t block) static sector_t f2fs_bmap(struct address_space *mapping, sector_t block) { struct inode *inode = mapping->host; - struct buffer_head tmp = { - .b_size = i_blocksize(inode), - }; sector_t blknr = 0; if (f2fs_has_inline_data(inode)) @@ -3818,8 +3837,16 @@ static sector_t f2fs_bmap(struct address_space *mapping, sector_t block) if (f2fs_compressed_file(inode)) { blknr = f2fs_bmap_compress(inode, block); } else { - if (!get_data_block_bmap(inode, block, &tmp, 0)) - blknr = tmp.b_blocknr; + 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); @@ -3895,7 +3922,7 @@ static int check_swap_activate_fast(struct swap_info_struct *sis, sector_t highest_pblock = 0; int nr_extents = 0; unsigned long nr_pblocks; - unsigned long len; + u64 len; int ret; /* @@ -3903,29 +3930,31 @@ static int check_swap_activate_fast(struct swap_info_struct *sis, * to be very smart. */ cur_lblock = 0; - last_lblock = logical_to_blk(inode, i_size_read(inode)); + last_lblock = bytes_to_blks(inode, i_size_read(inode)); len = i_size_read(inode); while (cur_lblock <= last_lblock && cur_lblock < sis->max) { - struct buffer_head map_bh; + struct f2fs_map_blocks map; pgoff_t next_pgofs; cond_resched(); - memset(&map_bh, 0, sizeof(struct buffer_head)); - map_bh.b_size = len - cur_lblock; + memset(&map, 0, sizeof(map)); + map.m_lblk = cur_lblock; + map.m_len = bytes_to_blks(inode, len) - cur_lblock; + map.m_next_pgofs = &next_pgofs; + map.m_seg_type = NO_CHECK_TYPE; - ret = get_data_block(inode, cur_lblock, &map_bh, 0, - F2FS_GET_BLOCK_FIEMAP, &next_pgofs); + ret = f2fs_map_blocks(inode, &map, 0, F2FS_GET_BLOCK_FIEMAP); if (ret) goto err_out; /* hole */ - if (!buffer_mapped(&map_bh)) + if (!(map.m_flags & F2FS_MAP_FLAGS)) goto err_out; - pblock = map_bh.b_blocknr; - nr_pblocks = logical_to_blk(inode, map_bh.b_size); + pblock = map.m_pblk; + nr_pblocks = map.m_len; |