diff options
Diffstat (limited to 'fs/f2fs')
-rw-r--r-- | fs/f2fs/compress.c | 23 | ||||
-rw-r--r-- | fs/f2fs/data.c | 6 | ||||
-rw-r--r-- | fs/f2fs/f2fs.h | 50 | ||||
-rw-r--r-- | fs/f2fs/file.c | 41 | ||||
-rw-r--r-- | fs/f2fs/gc.c | 3 | ||||
-rw-r--r-- | fs/f2fs/gc.h | 1 | ||||
-rw-r--r-- | fs/f2fs/inode.c | 17 | ||||
-rw-r--r-- | fs/f2fs/namei.c | 19 | ||||
-rw-r--r-- | fs/f2fs/segment.c | 23 | ||||
-rw-r--r-- | fs/f2fs/segment.h | 64 | ||||
-rw-r--r-- | fs/f2fs/super.c | 88 | ||||
-rw-r--r-- | fs/f2fs/sysfs.c | 74 |
12 files changed, 307 insertions, 102 deletions
diff --git a/fs/f2fs/compress.c b/fs/f2fs/compress.c index 7f26440e8595..b05bb7bfa14c 100644 --- a/fs/f2fs/compress.c +++ b/fs/f2fs/compress.c @@ -178,8 +178,7 @@ void f2fs_compress_ctx_add_page(struct compress_ctx *cc, struct folio *folio) #ifdef CONFIG_F2FS_FS_LZO static int lzo_init_compress_ctx(struct compress_ctx *cc) { - cc->private = f2fs_kvmalloc(F2FS_I_SB(cc->inode), - LZO1X_MEM_COMPRESS, GFP_NOFS); + cc->private = f2fs_vmalloc(LZO1X_MEM_COMPRESS); if (!cc->private) return -ENOMEM; @@ -189,7 +188,7 @@ static int lzo_init_compress_ctx(struct compress_ctx *cc) static void lzo_destroy_compress_ctx(struct compress_ctx *cc) { - kvfree(cc->private); + vfree(cc->private); cc->private = NULL; } @@ -246,7 +245,7 @@ static int lz4_init_compress_ctx(struct compress_ctx *cc) size = LZ4HC_MEM_COMPRESS; #endif - cc->private = f2fs_kvmalloc(F2FS_I_SB(cc->inode), size, GFP_NOFS); + cc->private = f2fs_vmalloc(size); if (!cc->private) return -ENOMEM; @@ -261,7 +260,7 @@ static int lz4_init_compress_ctx(struct compress_ctx *cc) static void lz4_destroy_compress_ctx(struct compress_ctx *cc) { - kvfree(cc->private); + vfree(cc->private); cc->private = NULL; } @@ -342,8 +341,7 @@ static int zstd_init_compress_ctx(struct compress_ctx *cc) params = zstd_get_params(level, cc->rlen); workspace_size = zstd_cstream_workspace_bound(¶ms.cParams); - workspace = f2fs_kvmalloc(F2FS_I_SB(cc->inode), - workspace_size, GFP_NOFS); + workspace = f2fs_vmalloc(workspace_size); if (!workspace) return -ENOMEM; @@ -351,7 +349,7 @@ static int zstd_init_compress_ctx(struct compress_ctx *cc) if (!stream) { f2fs_err_ratelimited(F2FS_I_SB(cc->inode), "%s zstd_init_cstream failed", __func__); - kvfree(workspace); + vfree(workspace); return -EIO; } @@ -364,7 +362,7 @@ static int zstd_init_compress_ctx(struct compress_ctx *cc) static void zstd_destroy_compress_ctx(struct compress_ctx *cc) { - kvfree(cc->private); + vfree(cc->private); cc->private = NULL; cc->private2 = NULL; } @@ -423,8 +421,7 @@ static int zstd_init_decompress_ctx(struct decompress_io_ctx *dic) workspace_size = zstd_dstream_workspace_bound(max_window_size); - workspace = f2fs_kvmalloc(F2FS_I_SB(dic->inode), - workspace_size, GFP_NOFS); + workspace = f2fs_vmalloc(workspace_size); if (!workspace) return -ENOMEM; @@ -432,7 +429,7 @@ static int zstd_init_decompress_ctx(struct decompress_io_ctx *dic) if (!stream) { f2fs_err_ratelimited(F2FS_I_SB(dic->inode), "%s zstd_init_dstream failed", __func__); - kvfree(workspace); + vfree(workspace); return -EIO; } @@ -444,7 +441,7 @@ static int zstd_init_decompress_ctx(struct decompress_io_ctx *dic) static void zstd_destroy_decompress_ctx(struct decompress_io_ctx *dic) { - kvfree(dic->private); + vfree(dic->private); dic->private = NULL; dic->private2 = NULL; } diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 1b0050b8421d..654f672639b3 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -53,8 +53,8 @@ bool f2fs_is_cp_guaranteed(struct page *page) struct inode *inode; struct f2fs_sb_info *sbi; - if (!mapping) - return false; + if (fscrypt_is_bounce_page(page)) + return page_private_gcing(fscrypt_pagecache_page(page)); inode = mapping->host; sbi = F2FS_I_SB(inode); @@ -3986,7 +3986,7 @@ retry: if ((pblock - SM_I(sbi)->main_blkaddr) % blks_per_sec || nr_pblocks % blks_per_sec || - !f2fs_valid_pinned_area(sbi, pblock)) { + f2fs_is_sequential_zone_area(sbi, pblock)) { bool last_extent = false; not_aligned++; diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 1c783c2e4902..a435550b2839 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -1762,6 +1762,7 @@ struct f2fs_sb_info { unsigned int dirty_device; /* for checkpoint data flush */ spinlock_t dev_lock; /* protect dirty_device */ bool aligned_blksize; /* all devices has the same logical blksize */ + unsigned int first_seq_zone_segno; /* first segno in sequential zone */ /* For write statistics */ u64 sectors_written_start; @@ -2508,8 +2509,14 @@ static inline void dec_valid_block_count(struct f2fs_sb_info *sbi, blkcnt_t sectors = count << F2FS_LOG_SECTORS_PER_BLOCK; spin_lock(&sbi->stat_lock); - f2fs_bug_on(sbi, sbi->total_valid_block_count < (block_t) count); - sbi->total_valid_block_count -= (block_t)count; + if (unlikely(sbi->total_valid_block_count < count)) { + f2fs_warn(sbi, "Inconsistent total_valid_block_count:%u, ino:%lu, count:%u", + sbi->total_valid_block_count, inode->i_ino, count); + sbi->total_valid_block_count = 0; + set_sbi_flag(sbi, SBI_NEED_FSCK); + } else { + sbi->total_valid_block_count -= count; + } if (sbi->reserved_blocks && sbi->current_reserved_blocks < sbi->reserved_blocks) sbi->current_reserved_blocks = min(sbi->reserved_blocks, @@ -3488,6 +3495,11 @@ static inline void *f2fs_kvzalloc(struct f2fs_sb_info *sbi, return f2fs_kvmalloc(sbi, size, flags | __GFP_ZERO); } +static inline void *f2fs_vmalloc(size_t size) +{ + return vmalloc(size); +} + static inline int get_extra_isize(struct inode *inode) { return F2FS_I(inode)->i_extra_isize / sizeof(__le32); @@ -4545,12 +4557,16 @@ F2FS_FEATURE_FUNCS(compression, COMPRESSION); F2FS_FEATURE_FUNCS(readonly, RO); #ifdef CONFIG_BLK_DEV_ZONED -static inline bool f2fs_blkz_is_seq(struct f2fs_sb_info *sbi, int devi, - block_t blkaddr) +static inline bool f2fs_zone_is_seq(struct f2fs_sb_info *sbi, int devi, + unsigned int zone) { - unsigned int zno = blkaddr / sbi->blocks_per_blkz; + return test_bit(zone, FDEV(devi).blkz_seq); +} - return test_bit(zno, FDEV(devi).blkz_seq); +static inline bool f2fs_blkz_is_seq(struct f2fs_sb_info *sbi, int devi, + block_t blkaddr) +{ + return f2fs_zone_is_seq(sbi, devi, blkaddr / sbi->blocks_per_blkz); } #endif @@ -4622,15 +4638,31 @@ static inline bool f2fs_lfs_mode(struct f2fs_sb_info *sbi) return F2FS_OPTION(sbi).fs_mode == FS_MODE_LFS; } -static inline bool f2fs_valid_pinned_area(struct f2fs_sb_info *sbi, +static inline bool f2fs_is_sequential_zone_area(struct f2fs_sb_info *sbi, block_t blkaddr) { if (f2fs_sb_has_blkzoned(sbi)) { +#ifdef CONFIG_BLK_DEV_ZONED int devi = f2fs_target_device_index(sbi, blkaddr); - return !bdev_is_zoned(FDEV(devi).bdev); + if (!bdev_is_zoned(FDEV(devi).bdev)) + return false; + + if (f2fs_is_multi_device(sbi)) { + if (blkaddr < FDEV(devi).start_blk || + blkaddr > FDEV(devi).end_blk) { + f2fs_err(sbi, "Invalid block %x", blkaddr); + return false; + } + blkaddr -= FDEV(devi).start_blk; + } + + return f2fs_blkz_is_seq(sbi, devi, blkaddr); +#else + return false; +#endif } - return true; + return false; } static inline bool f2fs_low_mem_mode(struct f2fs_sb_info *sbi) diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 71ddecaf771f..d9037e74631c 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -35,6 +35,17 @@ #include <trace/events/f2fs.h> #include <uapi/linux/f2fs.h> +static void f2fs_zero_post_eof_page(struct inode *inode, loff_t new_size) +{ + loff_t old_size = i_size_read(inode); + + if (old_size >= new_size) + return; + + /* zero or drop pages only in range of [old_size, new_size] */ + truncate_pagecache(inode, old_size); +} + static vm_fault_t f2fs_filemap_fault(struct vm_fault *vmf) { struct inode *inode = file_inode(vmf->vma->vm_file); @@ -103,8 +114,13 @@ static vm_fault_t f2fs_vm_page_mkwrite(struct vm_fault *vmf) f2fs_bug_on(sbi, f2fs_has_inline_data(inode)); + filemap_invalidate_lock(inode->i_mapping); + f2fs_zero_post_eof_page(inode, (folio->index + 1) << PAGE_SHIFT); + filemap_invalidate_unlock(inode->i_mapping); + file_update_time(vmf->vma->vm_file); filemap_invalidate_lock_shared(inode->i_mapping); + folio_lock(folio); if (unlikely(folio->mapping != inode->i_mapping || folio_pos(folio) > i_size_read(inode) || @@ -1064,6 +1080,8 @@ int f2fs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, f2fs_down_write(&fi->i_gc_rwsem[WRITE]); filemap_invalidate_lock(inode->i_mapping); + if (attr->ia_size > old_size) + f2fs_zero_post_eof_page(inode, attr->ia_size); truncate_setsize(inode, attr->ia_size); if (attr->ia_size <= old_size) @@ -1182,6 +1200,10 @@ static int f2fs_punch_hole(struct inode *inode, loff_t offset, loff_t len) if (ret) return ret; + filemap_invalidate_lock(inode->i_mapping); + f2fs_zero_post_eof_page(inode, offset + len); + filemap_invalidate_unlock(inode->i_mapping); + pg_start = ((unsigned long long) offset) >> PAGE_SHIFT; pg_end = ((unsigned long long) offset + len) >> PAGE_SHIFT; @@ -1465,6 +1487,8 @@ static int f2fs_do_collapse(struct inode *inode, loff_t offset, loff_t len) f2fs_down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); filemap_invalidate_lock(inode->i_mapping); + f2fs_zero_post_eof_page(inode, offset + len); + f2fs_lock_op(sbi); f2fs_drop_extent_tree(inode); truncate_pagecache(inode, offset); @@ -1586,6 +1610,10 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len, if (ret) return ret; + filemap_invalidate_lock(mapping); + f2fs_zero_post_eof_page(inode, offset + len); + filemap_invalidate_unlock(mapping); + pg_start = ((unsigned long long) offset) >> PAGE_SHIFT; pg_end = ((unsigned long long) offset + len) >> PAGE_SHIFT; @@ -1717,6 +1745,8 @@ static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len) /* avoid gc operation during block exchange */ f2fs_down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); filemap_invalidate_lock(mapping); + + f2fs_zero_post_eof_page(inode, offset + len); truncate_pagecache(inode, offset); while (!ret && idx > pg_start) { @@ -1774,6 +1804,10 @@ static int f2fs_expand_inode_data(struct inode *inode, loff_t offset, if (err) return err; + filemap_invalidate_lock(inode->i_mapping); + f2fs_zero_post_eof_page(inode, offset + len); + filemap_invalidate_unlock(inode->i_mapping); + f2fs_balance_fs(sbi, true); pg_start = ((unsigned long long)offset) >> PAGE_SHIFT; @@ -1794,7 +1828,8 @@ static int f2fs_expand_inode_data(struct inode *inode, loff_t offset, map.m_len = sec_blks; next_alloc: - if (has_not_enough_free_secs(sbi, 0, + if (has_not_enough_free_secs(sbi, 0, f2fs_sb_has_blkzoned(sbi) ? + ZONED_PIN_SEC_REQUIRED_COUNT : GET_SEC_FROM_SEG(sbi, overprovision_segments(sbi)))) { f2fs_down_write(&sbi->gc_lock); stat_inc_gc_call_count(sbi, FOREGROUND); @@ -4715,6 +4750,10 @@ static ssize_t f2fs_write_checks(struct kiocb *iocb, struct iov_iter *from) err = file_modified(file); if (err) return err; + + filemap_invalidate_lock(inode->i_mapping); + f2fs_zero_post_eof_page(inode, iocb->ki_pos + iov_iter_count(from)); + filemap_invalidate_unlock(inode->i_mapping); return count; } diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index e0469316c7cd..cd56c0e66657 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -2072,6 +2072,9 @@ int f2fs_gc_range(struct f2fs_sb_info *sbi, .iroot = RADIX_TREE_INIT(gc_list.iroot, GFP_NOFS), }; + if (IS_CURSEC(sbi, GET_SEC_FROM_SEG(sbi, segno))) + continue; + do_garbage_collect(sbi, segno, &gc_list, FG_GC, true, false); put_gc_inode(&gc_list); diff --git a/fs/f2fs/gc.h b/fs/f2fs/gc.h index 2914b678bf8f..5c1eaf55e127 100644 --- a/fs/f2fs/gc.h +++ b/fs/f2fs/gc.h @@ -35,6 +35,7 @@ #define LIMIT_BOOST_ZONED_GC 25 /* percentage over total user space of boosted gc for zoned devices */ #define DEF_MIGRATION_WINDOW_GRANULARITY_ZONED 3 #define BOOST_GC_MULTIPLE 5 +#define ZONED_PIN_SEC_REQUIRED_COUNT 1 #define DEF_GC_FAILED_PINNED_FILES 2048 #define MAX_GC_FAILED_PINNED_FILES USHRT_MAX diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c index a60db5e795a4..06688b9957c8 100644 --- a/fs/f2fs/inode.c +++ b/fs/f2fs/inode.c @@ -34,7 +34,9 @@ void f2fs_mark_inode_dirty_sync(struct inode *inode, bool sync) if (f2fs_inode_dirtied(inode, sync)) return; - if (f2fs_is_atomic_file(inode)) + /* only atomic file w/ FI_ATOMIC_COMMITTED can be set vfs dirty */ + if (f2fs_is_atomic_file(inode) && + !is_inode_flag_set(inode, FI_ATOMIC_COMMITTED)) return; mark_inode_dirty_sync(inode); @@ -286,6 +288,12 @@ static bool sanity_check_inode(struct inode *inode, struct page *node_page) return false; } + if (ino_of_node(node_page) == fi->i_xattr_nid) { + f2fs_warn(sbi, "%s: corrupted inode i_ino=%lx, xnid=%x, run fsck to fix.", + __func__, inode->i_ino, fi->i_xattr_nid); + return false; + } + if (f2fs_has_extra_attr(inode)) { if (!f2fs_sb_has_extra_attr(sbi)) { f2fs_warn(sbi, "%s: inode (ino=%lx) is with extra_attr, but extra_attr feature is off", @@ -777,6 +785,13 @@ int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc) !is_inode_flag_set(inode, FI_DIRTY_INODE)) return 0; + /* + * no need to update inode page, ultimately f2fs_evict_inode() will + * clear dirty status of inode. + */ + if (f2fs_cp_error(sbi)) + return -EIO; + if (!f2fs_is_checkpoint_ready(sbi)) { f2fs_mark_inode_dirty_sync(inode, true); return -ENOSPC; diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c index 57d46e1439de..781b872fac8c 100644 --- a/fs/f2fs/namei.c +++ b/fs/f2fs/namei.c @@ -413,7 +413,7 @@ static int f2fs_link(struct dentry *old_dentry, struct inode *dir, if (is_inode_flag_set(dir, FI_PROJ_INHERIT) && (!projid_eq(F2FS_I(dir)->i_projid, - F2FS_I(old_dentry->d_inode)->i_projid))) + F2FS_I(inode)->i_projid))) return -EXDEV; err = f2fs_dquot_initialize(dir); @@ -560,6 +560,15 @@ static int f2fs_unlink(struct inode *dir, struct dentry *dentry) goto fail; } + if (unlikely(inode->i_nlink == 0)) { + f2fs_warn(F2FS_I_SB(inode), "%s: inode (ino=%lx) has zero i_nlink", + __func__, inode->i_ino); + err = -EFSCORRUPTED; + set_sbi_flag(F2FS_I_SB(inode), SBI_NEED_FSCK); + f2fs_put_page(page, 0); + goto fail; + } + f2fs_balance_fs(sbi, true); f2fs_lock_op(sbi); @@ -905,7 +914,7 @@ static int f2fs_rename(struct mnt_idmap *idmap, struct inode *old_dir, if (is_inode_flag_set(new_dir, FI_PROJ_INHERIT) && (!projid_eq(F2FS_I(new_dir)->i_projid, - F2FS_I(old_dentry->d_inode)->i_projid))) + F2FS_I(old_inode)->i_projid))) return -EXDEV; /* @@ -1098,10 +1107,10 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry, if ((is_inode_flag_set(new_dir, FI_PROJ_INHERIT) && !projid_eq(F2FS_I(new_dir)->i_projid, - F2FS_I(old_dentry->d_inode)->i_projid)) || - (is_inode_flag_set(new_dir, FI_PROJ_INHERIT) && + F2FS_I(old_inode)->i_projid)) || + (is_inode_flag_set(old_dir, FI_PROJ_INHERIT) && !projid_eq(F2FS_I(old_dir)->i_projid, - F2FS_I(new_dentry->d_inode)->i_projid))) + F2FS_I(new_inode)->i_projid))) return -EXDEV; err = f2fs_dquot_initialize(old_dir); diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index b9ffb2ee9548..e48b5e2efea2 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -370,7 +370,13 @@ out: } else { sbi->committed_atomic_block += fi->atomic_write_cnt; set_inode_flag(inode, FI_ATOMIC_COMMITTED); + + /* + * inode may has no FI_ATOMIC_DIRTIED flag due to no write + * before commit. + */ if (is_inode_flag_set(inode, FI_ATOMIC_DIRTIED)) { + /* clear atomic dirty status and set vfs dirty status */ clear_inode_flag(inode, FI_ATOMIC_DIRTIED); f2fs_mark_inode_dirty_sync(inode, true); } @@ -2713,7 +2719,7 @@ static int get_new_segment(struct f2fs_sb_info *sbi, if (sbi->blkzone_alloc_policy == BLKZONE_ALLOC_PRIOR_CONV || pinning) segno = 0; else - segno = max(first_zoned_segno(sbi), *newseg); + segno = max(sbi->first_seq_zone_segno, *newseg); hint = GET_SEC_FROM_SEG(sbi, segno); } #endif @@ -2725,7 +2731,7 @@ find_other_zone: if (secno >= MAIN_SECS(sbi) && f2fs_sb_has_blkzoned(sbi)) { /* Write only to sequential zones */ if (sbi->blkzone_alloc_policy == BLKZONE_ALLOC_ONLY_SEQ) { - hint = GET_SEC_FROM_SEG(sbi, first_zoned_segno(sbi)); + hint = GET_SEC_FROM_SEG(sbi, sbi->first_seq_zone_segno); secno = find_next_zero_bit(free_i->free_secmap, MAIN_SECS(sbi), hint); } else secno = find_first_zero_bit(free_i->free_secmap, @@ -2772,11 +2778,15 @@ find_other_zone: } got_it: /* set it as dirty segment in free segmap */ - f2fs_bug_on(sbi, test_bit(segno, free_i->free_segmap)); + if (test_bit(segno, free_i->free_segmap)) { + ret = -EFSCORRUPTED; + f2fs_stop_checkpoint(sbi, false, STOP_CP_REASON_CORRUPTED_FREE_BITMAP); + goto out_unlock; + } - /* no free section in conventional zone */ + /* no free section in conventional device or conventional zone */ if (new_sec && pinning && - !f2fs_valid_pinned_area(sbi, START_BLOCK(sbi, segno))) { + f2fs_is_sequential_zone_area(sbi, START_BLOCK(sbi, segno))) { ret = -EAGAIN; goto out_unlock; } @@ -3240,7 +3250,8 @@ retry: if (f2fs_sb_has_blkzoned(sbi) && err == -EAGAIN && gc_required) { f2fs_down_write(&sbi->gc_lock); - err = f2fs_gc_range(sbi, 0, GET_SEGNO(sbi, FDEV(0).end_blk), true, 1); + err = f2fs_gc_range(sbi, 0, sbi->first_seq_zone_segno - 1, + true, ZONED_PIN_SEC_REQUIRED_COUNT); f2fs_up_write(&sbi->gc_lock); gc_required = false; diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h index 51b2b8c5c749..52bb1a281935 100644 --- a/fs/f2fs/segment.h +++ b/fs/f2fs/segment.h @@ -431,7 +431,6 @@ static inline void __set_free(struct f2fs_sb_info *sbi, unsigned int segno) unsigned int secno = GET_SEC_FROM_SEG(sbi, segno); unsigned int start_segno = GET_SEG_FROM_SEC(sbi, secno); unsigned int next; - unsigned int usable_segs = f2fs_usable_segs_in_sec(sbi); spin_lock(&free_i->segmap_lock); clear_bit(segno, free_i->free_segmap); @@ -439,7 +438,7 @@ static inline void __set_free(struct f2fs_sb_info *sbi, unsigned int segno) next = find_next_bit(free_i->free_segmap, start_segno + SEGS_PER_SEC(sbi), start_segno); - if (next >= start_segno + usable_segs) { + if (next >= start_segno + f2fs_usable_segs_in_sec(sbi)) { clear_bit(secno, free_i->free_secmap); free_i->free_sections++; } @@ -465,22 +464,36 @@ static inline void __set_test_and_free(struct f2fs_sb_info *sbi, unsigned int secno = GET_SEC_FROM_SEG(sbi, segno); unsigned int start_segno = GET_SEG_FROM_SEC(sbi, secno); unsigned int next; - unsigned int usable_segs = f2fs_usable_segs_in_sec(sbi); + bool ret; spin_lock(&free_i->segmap_lock); - if (test_and_clear_bit(segno, free_i->free_segmap)) { - free_i->free_segments++; - - if (!inmem && IS_CURSEC(sbi, secno)) - goto skip_free; - next = find_next_bit(free_i->free_segmap, - start_segno + SEGS_PER_SEC(sbi), start_segno); - if (next >= start_segno + usable_segs) { - if (test_and_clear_bit(secno, free_i->free_secmap)) - free_i->free_sections++; - } - } -skip_free: + ret = test_and_clear_bit(segno, free_i->free_segmap); + if (!ret) + goto unlock_out; + + free_i->free_segments++; + + if (!inmem && IS_CURSEC(sbi, secno)) + goto unlock_out; + + /* check large section */ + next = find_next_bit(free_i->free_segmap, + start_segno + SEGS_PER_SEC(sbi), start_segno); + if (next < start_segno + f2fs_usable_segs_in_sec(sbi)) + goto unlock_out; + + ret = test_and_clear_bit(secno, free_i->free_secmap); + if (!ret) + goto unlock_out; + + free_i->free_sections++; + + if (GET_SEC_FROM_SEG(sbi, sbi->next_victim_seg[BG_GC]) == secno) + sbi->next_victim_seg[BG_GC] = NULL_SEGNO; + if (GET_SEC_FROM_SEG(sbi, sbi->next_victim_seg[FG_GC]) == secno) + sbi->next_victim_seg[FG_GC] = NULL_SEGNO; + +unlock_out: spin_unlock(&free_i->segmap_lock); } @@ -562,13 +575,16 @@ static inline bool has_curseg_enough_space(struct f2fs_sb_info *sbi, unsigned int node_blocks, unsigned int data_blocks, unsigned int dent_blocks) { - unsigned int segno, left_blocks, blocks; int i; /* check current data/node sections in the worst case. */ for (i = CURSEG_HOT_DATA; i < NR_PERSISTENT_LOG; i++) { segno = CURSEG_I(sbi, i)->segno; + + if (unlikely(segno == NULL_SEGNO)) + return false; + left_blocks = CAP_BLKS_PER_SEC(sbi) - get_ckpt_valid_blocks(sbi, segno, true); @@ -579,6 +595,10 @@ static inline bool has_curseg_enough_space(struct f2fs_sb_info *sbi, /* check current data section for dentry blocks. */ segno = CURSEG_I(sbi, CURSEG_HOT_DATA)->segno; + + if (unlikely(segno == NULL_SEGNO)) + return false; + left_blocks = CAP_BLKS_PER_SEC(sbi) - get_ckpt_valid_blocks(sbi, segno, true); if (dent_blocks > left_blocks) @@ -972,13 +992,3 @@ wake_up: dcc->discard_wake = true; wake_up_interruptible_all(&dcc->discard_wait_queue); } - -static inline unsigned int first_zoned_segno(struct f2fs_sb_info *sbi) -{ - int devi; - - for (devi = 0; devi < sbi->s_ndevs; devi++) - if (bdev_is_zoned(FDEV(devi).bdev)) - return GET_SEGNO(sbi, FDEV(devi).start_blk); - return 0; -} diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 573cc4725e2e..3f2c6fa3623b 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -1516,7 +1516,9 @@ int f2fs_inode_dirtied(struct inode *inode, bool sync) } spin_unlock(&sbi->inode_lock[DIRTY_META]); - if (!ret && f2fs_is_atomic_file(inode)) + /* if atomic write is not committed, set inode w/ atomic dirty */ + if (!ret && f2fs_is_atomic_file(inode) && + !is_inode_flag_set(inode, FI_ATOMIC_COMMITTED)) set_inode_flag(inode, FI_ATOMIC_DIRTIED); return ret; @@ -1785,26 +1787,32 @@ static int f2fs_statfs_project(struct super_block *sb, limit = min_not_zero(dquot->dq_dqb.dqb_bsoftlimit, dquot->dq_dqb.dqb_bhardlimit); - if (limit) - limit >>= sb->s_blocksize_bits; + limit >>= sb->s_blocksize_bits; + + if (limit) { + uint64_t remaining = 0; - if (limit && buf->f_blocks > limit) { curblock = (dquot->dq_dqb.dqb_curspace + dquot->dq_dqb.dqb_rsvspace) >> sb->s_blocksize_bits; - buf->f_blocks = limit; - buf->f_bfree = buf->f_bavail = - (buf->f_blocks > curblock) ? - (buf->f_blocks - curblock) : 0; + if (limit > curblock) + remaining = limit - curblock; + + buf->f_blocks = min(buf->f_blocks, limit); + buf->f_bfree = min(buf->f_bfree, remaining); + buf->f_bavail = min(buf->f_bavail, remaining); } limit = min_not_zero(dquot->dq_dqb.dqb_isoftlimit, dquot->dq_dqb.dqb_ihardlimit); - if (limit && buf->f_files > limit) { - buf->f_files = limit; - buf->f_ffree = - (buf->f_files > dquot->dq_dqb.dqb_curinodes) ? - (buf->f_files - dquot->dq_dqb.dqb_curinodes) : 0; + if (limit) { + uint64_t remaining = 0; + + if (limit > dquot->dq_dqb.dqb_curinodes) + remaining = limit - dquot->dq_dqb.dqb_curinodes; + + buf->f_files = min(buf->f_files, limit); + buf->f_ffree = min(buf->f_ffree, remaining); } spin_unlock(&dquot->dq_dqb_lock); @@ -1862,9 +1870,9 @@ static int f2fs_statfs(struct dentry *dentry, struct kstatfs *buf) buf->f_fsid = u64_to_fsid(id); #ifdef CONFIG_QUOTA - if (is_inode_flag_set(dentry->d_inode, FI_PROJ_INHERIT) && + if (is_inode_flag_set(d_inode(dentry), FI_PROJ_INHERIT) && sb_has_quota_limits_enabled(sb, PRJQUOTA)) { - f2fs_statfs_project(sb, F2FS_I(dentry->d_inode)->i_projid, buf); + f2fs_statfs_project(sb, F2FS_I(d_inode(dentry))->i_projid, buf); } #endif return 0; @@ -3659,6 +3667,7 @@ int f2fs_sanity_check_ckpt(struct f2fs_sb_info *sbi) block_t user_block_count, valid_user_blocks; block_t avail_node_count, valid_node_count; unsigned int nat_blocks, nat_bits_bytes, nat_bits_blocks; + unsigned int sit_blk_cnt; int i, j; total = le32_to_cpu(raw_super->segment_count); @@ -3770,6 +3779,13 @@ skip_cross: return 1; } + sit_blk_cnt = DIV_ROUND_UP(main_segs, SIT_ENTRY_PER_BLOCK); + if (sit_bitmap_size * 8 < sit_blk_cnt) { + f2fs_err(sbi, "Wrong bitmap size: sit: %u, sit_blk_cnt:%u", + sit_bitmap_size, sit_blk_cnt); + return 1; + } + cp_pack_start_sum = __start_sum_addr(sbi); cp_payload = __cp_payload(sbi); if (cp_pack_start_sum < cp_payload + 1 || @@ -4244,6 +4260,37 @@ static void f2fs_record_error_work(struct work_struct *work) f2fs_record_stop_reason(sbi); } +static inline unsigned int get_first_seq_zone_segno(struct f2fs_sb_info *sbi) +{ +#ifdef CONFIG_BLK_DEV_ZONED + unsigned int zoneno, total_zones; + int devi; + + if (!f2fs_sb_has_blkzoned(sbi)) + return NULL_SEGNO; + + for (devi = 0; devi < sbi->s_ndevs; devi++) { + if (!bdev_is_zoned(FDEV(devi).bdev)) + continue; + + total_zones = GET_ZONE_FROM_SEG(sbi, FDEV(devi).total_segments); + + for (zoneno = 0; zoneno < total_zones; zoneno++) { + unsigned int segs, blks; + + if (!f2fs_zone_is_seq(sbi, devi, zoneno)) + continue; + + segs = GET_SEG_FROM_SEC(sbi, + zoneno * sbi->secs_per_zone); + blks = SEGS_TO_BLKS(sbi, segs); + return GET_SEGNO(sbi, FDEV(devi).start_blk + blks); + } + } +#endif + return NULL_SEGNO; +} + static int f2fs_scan_devices(struct f2fs_sb_info *sbi) { struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi); @@ -4278,6 +4325,14 @@ static int f2fs_scan_devices(struct f2fs_sb_info *sbi) #endif for (i = 0; i < max_devices; i++) { + if (max_devices == 1) { + FDEV(i).total_segments = + le32_to_cpu(raw_super->segment_count_main); + FDEV(i).start_blk = 0; + FDEV(i).end_blk = FDEV(i).total_segments * + BLKS_PER_SEG(sbi); + } + if (i == 0) FDEV(0).bdev_file = sbi->sb->s_bdev_file; else if (!RDEV(i).path[0]) @@ -4644,6 +4699,9 @@ try_onemore: /* For write statistics */ sbi->sectors_written_start = f2fs_get_sectors_written(sbi); + /* get segno of first zoned block device */ + sbi->first_seq_zone_segno = get_first_seq_zone_segno(sbi); + /* Read accumulated write IO statistics if exists */ seg_i = CURSEG_I(sbi, CURSEG_HOT_NODE); if (__exist_node_summaries(sbi)) diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c index d9a44f03e558..7df638f901a1 100644 --- a/fs/f2fs/sysfs.c +++ b/fs/f2fs/sysfs.c @@ -61,6 +61,12 @@ struct f2fs_attr { int id; }; +struct f2fs_base_attr { + struct attribute attr; + ssize_t (*show)(struct f2fs_base_attr *a, char *buf); + ssize_t (*store)(struct f2fs_base_attr *a, const char *buf, size_t len); +}; + static ssize_t f2fs_sbi_show(struct f2fs_attr *a, struct f2fs_sb_info *sbi, char *buf); @@ -864,6 +870,25 @@ static void f2fs_sb_release(struct kobject *kobj) complete(&sbi->s_kobj_unregister); } +static ssize_t f2fs_base_attr_show(struct kobject *kobj, + struct attribute *attr, char *buf) +{ + struct f2fs_base_attr *a = container_of(attr, + struct f2fs_base_attr, attr); + + return a->show ? a->show(a, buf) : 0; +} + +static ssize_t f2fs_base_attr_store(struct kobject *kobj, + struct attribute *attr, + const char *buf, size_t len) +{ + struct f2fs_base_attr *a = container_of(attr, + struct f2fs_base_attr, attr); + + return a->store ? a->store(a, buf, len) : 0; +} + /* * Note that there are three feature list entries: * 1) /sys/fs/f2fs/features @@ -882,14 +907,13 @@ static void f2fs_sb_release(struct kobject *kobj) * please add new on-disk feature in this list only. * - ref. F2FS_SB_FEATURE_RO_ATTR() */ -static ssize_t f2fs_feature_show(struct f2fs_attr *a, - struct f2fs_sb_info *sbi, char *buf) +static ssize_t f2fs_feature_show(struct f2fs_base_attr *a, char *buf) { return sysfs_emit(buf, "supported\n"); } #define F2FS_FEATURE_RO_ATTR(_name) \ -static struct f2fs_attr f2fs_attr_##_name = { \ +static struct f2fs_base_attr f2fs_base_attr_##_name = { \ .attr = {.name = __stringify(_name), .mode = 0444 }, \ .show = f2fs_feature_show, \ } @@ -1258,37 +1282,38 @@ static struct attribute *f2fs_attrs[] = { }; ATTRIBUTE_GROUPS(f2fs); +#define BASE_ATTR_LIST(name) (&f2fs_base_attr_##name.attr) static struct attribute *f2fs_feat_attrs[] = { #ifdef CONFIG_FS_ENCRYPTION - ATTR_LIST(encryption), - ATTR_LIST(test_dummy_encryption_v2), + BASE_ATTR_LIST(encryption), + BASE_ATTR_LIST(test_dummy_encryption_v2), #if IS_ENABLED(CONFIG_UNICODE) - ATTR_LIST(encrypted_casefold), + BASE_ATTR_LIST(encrypted_casefold), #endif #endif /* CONFIG_FS_ENCRYPTION */ #ifdef CONFIG_BLK_DEV_ZONED - ATTR_LIST(block_zoned), + BASE_ATTR_LIST(block_zoned), #endif - ATTR_LIST(atomic_write), - ATTR_LIST(extra_attr), - ATTR_LIST(project_quota), - ATTR_LIST(inode_checksum), - ATTR_LIST(flexible_inline_xattr), - ATTR_LIST(quota_ino), - ATTR_LIST(inode_crtime), - ATTR_LIST(lost_found), + BASE_ATTR_LIST(atomic_write), + BASE_ATTR_LIST(extra_attr), + BASE_ATTR_LIST(project_quota), + BASE_ATTR_LIST(inode_checksum), + BASE_ATTR_LIST(flexible_inline_xattr), + BASE_ATTR_LIST(quota_ino), + BASE_ATTR_LIST(inode_crtime), + BASE_ATTR_LIST(lost_found), #ifdef CONFIG_FS_VERITY - ATTR_LIST(verity), + BASE_ATTR_LIST(verity), #endif - ATTR_LIST(sb_checksum), + BASE_ATTR_LIST(sb_checksum), #if IS_ENABLED(CONFIG_UNICODE) - ATTR_LIST(casefold), + BASE_ATTR_LIST(casefold), #endif - ATTR_LIST(readonly), + BASE_ATTR_LIST(readonly), #ifdef CONFIG_F2FS_FS_COMPRESSION - ATTR_LIST(compression), + BASE_ATTR_LIST(compression), #endif - ATTR_LIST(pin_file), + BASE_ATTR_LIST(pin_file), NULL, }; ATTRIBUTE_GROUPS(f2fs_feat); @@ -1362,9 +1387,14 @@ static struct kset f2fs_kset = { .kobj = {.ktype = &f2fs_ktype}, }; +static const struct sysfs_ops f2fs_feat_attr_ops = { + .show = f2fs_base_attr_show, + .store = f2fs_base_attr_store, +}; + static const struct kobj_type f2fs_feat_ktype = { .default_groups = f2fs_feat_groups, - .sysfs_ops = &f2fs_attr_ops, + .sysfs_ops = &f2fs_feat_attr_ops, }; static struct kobject f2fs_feat = { |