mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-28 20:02:17 +00:00
![Chao Yu](/assets/img/avatar_default.png)
syzbot reports below bug: BUG: KASAN: slab-use-after-free in f2fs_truncate_data_blocks_range+0x122a/0x14c0 fs/f2fs/file.c:574 Read of size 4 at addr ffff88802a25c000 by task syz-executor148/5000 CPU: 1 PID: 5000 Comm: syz-executor148 Not tainted 6.4.0-rc7-syzkaller-00041-ge660abd551f1 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 05/27/2023 Call Trace: <TASK> __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0xd9/0x150 lib/dump_stack.c:106 print_address_description.constprop.0+0x2c/0x3c0 mm/kasan/report.c:351 print_report mm/kasan/report.c:462 [inline] kasan_report+0x11c/0x130 mm/kasan/report.c:572 f2fs_truncate_data_blocks_range+0x122a/0x14c0 fs/f2fs/file.c:574 truncate_dnode+0x229/0x2e0 fs/f2fs/node.c:944 f2fs_truncate_inode_blocks+0x64b/0xde0 fs/f2fs/node.c:1154 f2fs_do_truncate_blocks+0x4ac/0xf30 fs/f2fs/file.c:721 f2fs_truncate_blocks+0x7b/0x300 fs/f2fs/file.c:749 f2fs_truncate.part.0+0x4a5/0x630 fs/f2fs/file.c:799 f2fs_truncate include/linux/fs.h:825 [inline] f2fs_setattr+0x1738/0x2090 fs/f2fs/file.c:1006 notify_change+0xb2c/0x1180 fs/attr.c:483 do_truncate+0x143/0x200 fs/open.c:66 handle_truncate fs/namei.c:3295 [inline] do_open fs/namei.c:3640 [inline] path_openat+0x2083/0x2750 fs/namei.c:3791 do_filp_open+0x1ba/0x410 fs/namei.c:3818 do_sys_openat2+0x16d/0x4c0 fs/open.c:1356 do_sys_open fs/open.c:1372 [inline] __do_sys_creat fs/open.c:1448 [inline] __se_sys_creat fs/open.c:1442 [inline] __x64_sys_creat+0xcd/0x120 fs/open.c:1442 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x39/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd The root cause is, inodeA references inodeB via inodeB's ino, once inodeA is truncated, it calls truncate_dnode() to truncate data blocks in inodeB's node page, it traverse mapping data from node->i.i_addr[0] to node->i.i_addr[ADDRS_PER_BLOCK() - 1], result in out-of-boundary access. This patch fixes to add sanity check on dnode page in truncate_dnode(), so that, it can help to avoid triggering such issue, and once it encounters such issue, it will record newly introduced ERROR_INVALID_NODE_REFERENCE error into superblock, later fsck can detect such issue and try repairing. Also, it removes f2fs_truncate_data_blocks() for cleanup due to the function has only one caller, and uses f2fs_truncate_data_blocks_range() instead. Reported-and-tested-by: syzbot+12cb4425b22169b52036@syzkaller.appspotmail.com Closes: https://lore.kernel.org/linux-f2fs-devel/000000000000f3038a05fef867f8@google.com Signed-off-by: Chao Yu <chao@kernel.org> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
590 lines
20 KiB
C
590 lines
20 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
/**
|
|
* include/linux/f2fs_fs.h
|
|
*
|
|
* Copyright (c) 2012 Samsung Electronics Co., Ltd.
|
|
* http://www.samsung.com/
|
|
*/
|
|
#ifndef _LINUX_F2FS_FS_H
|
|
#define _LINUX_F2FS_FS_H
|
|
|
|
#include <linux/pagemap.h>
|
|
#include <linux/types.h>
|
|
|
|
#define F2FS_SUPER_OFFSET 1024 /* byte-size offset */
|
|
#define F2FS_MIN_LOG_SECTOR_SIZE 9 /* 9 bits for 512 bytes */
|
|
#define F2FS_MAX_LOG_SECTOR_SIZE 12 /* 12 bits for 4096 bytes */
|
|
#define F2FS_LOG_SECTORS_PER_BLOCK 3 /* log number for sector/blk */
|
|
#define F2FS_BLKSIZE 4096 /* support only 4KB block */
|
|
#define F2FS_BLKSIZE_BITS 12 /* bits for F2FS_BLKSIZE */
|
|
#define F2FS_MAX_EXTENSION 64 /* # of extension entries */
|
|
#define F2FS_EXTENSION_LEN 8 /* max size of extension */
|
|
#define F2FS_BLK_ALIGN(x) (((x) + F2FS_BLKSIZE - 1) >> F2FS_BLKSIZE_BITS)
|
|
|
|
#define NULL_ADDR ((block_t)0) /* used as block_t addresses */
|
|
#define NEW_ADDR ((block_t)-1) /* used as block_t addresses */
|
|
#define COMPRESS_ADDR ((block_t)-2) /* used as compressed data flag */
|
|
|
|
#define F2FS_BYTES_TO_BLK(bytes) ((bytes) >> F2FS_BLKSIZE_BITS)
|
|
#define F2FS_BLK_TO_BYTES(blk) ((blk) << F2FS_BLKSIZE_BITS)
|
|
|
|
/* 0, 1(node nid), 2(meta nid) are reserved node id */
|
|
#define F2FS_RESERVED_NODE_NUM 3
|
|
|
|
#define F2FS_ROOT_INO(sbi) ((sbi)->root_ino_num)
|
|
#define F2FS_NODE_INO(sbi) ((sbi)->node_ino_num)
|
|
#define F2FS_META_INO(sbi) ((sbi)->meta_ino_num)
|
|
#define F2FS_COMPRESS_INO(sbi) (NM_I(sbi)->max_nid)
|
|
|
|
#define F2FS_MAX_QUOTAS 3
|
|
|
|
#define F2FS_ENC_UTF8_12_1 1
|
|
|
|
#define F2FS_IO_SIZE(sbi) BIT(F2FS_OPTION(sbi).write_io_size_bits) /* Blocks */
|
|
#define F2FS_IO_SIZE_KB(sbi) BIT(F2FS_OPTION(sbi).write_io_size_bits + 2) /* KB */
|
|
#define F2FS_IO_SIZE_BITS(sbi) (F2FS_OPTION(sbi).write_io_size_bits) /* power of 2 */
|
|
#define F2FS_IO_SIZE_MASK(sbi) (F2FS_IO_SIZE(sbi) - 1)
|
|
#define F2FS_IO_ALIGNED(sbi) (F2FS_IO_SIZE(sbi) > 1)
|
|
|
|
/* This flag is used by node and meta inodes, and by recovery */
|
|
#define GFP_F2FS_ZERO (GFP_NOFS | __GFP_ZERO)
|
|
|
|
/*
|
|
* For further optimization on multi-head logs, on-disk layout supports maximum
|
|
* 16 logs by default. The number, 16, is expected to cover all the cases
|
|
* enoughly. The implementaion currently uses no more than 6 logs.
|
|
* Half the logs are used for nodes, and the other half are used for data.
|
|
*/
|
|
#define MAX_ACTIVE_LOGS 16
|
|
#define MAX_ACTIVE_NODE_LOGS 8
|
|
#define MAX_ACTIVE_DATA_LOGS 8
|
|
|
|
#define VERSION_LEN 256
|
|
#define MAX_VOLUME_NAME 512
|
|
#define MAX_PATH_LEN 64
|
|
#define MAX_DEVICES 8
|
|
|
|
/*
|
|
* For superblock
|
|
*/
|
|
struct f2fs_device {
|
|
__u8 path[MAX_PATH_LEN];
|
|
__le32 total_segments;
|
|
} __packed;
|
|
|
|
/* reason of stop_checkpoint */
|
|
enum stop_cp_reason {
|
|
STOP_CP_REASON_SHUTDOWN,
|
|
STOP_CP_REASON_FAULT_INJECT,
|
|
STOP_CP_REASON_META_PAGE,
|
|
STOP_CP_REASON_WRITE_FAIL,
|
|
STOP_CP_REASON_CORRUPTED_SUMMARY,
|
|
STOP_CP_REASON_UPDATE_INODE,
|
|
STOP_CP_REASON_FLUSH_FAIL,
|
|
STOP_CP_REASON_MAX,
|
|
};
|
|
|
|
#define MAX_STOP_REASON 32
|
|
|
|
/* detail reason for EFSCORRUPTED */
|
|
enum f2fs_error {
|
|
ERROR_CORRUPTED_CLUSTER,
|
|
ERROR_FAIL_DECOMPRESSION,
|
|
ERROR_INVALID_BLKADDR,
|
|
ERROR_CORRUPTED_DIRENT,
|
|
ERROR_CORRUPTED_INODE,
|
|
ERROR_INCONSISTENT_SUMMARY,
|
|
ERROR_INCONSISTENT_FOOTER,
|
|
ERROR_INCONSISTENT_SUM_TYPE,
|
|
ERROR_CORRUPTED_JOURNAL,
|
|
ERROR_INCONSISTENT_NODE_COUNT,
|
|
ERROR_INCONSISTENT_BLOCK_COUNT,
|
|
ERROR_INVALID_CURSEG,
|
|
ERROR_INCONSISTENT_SIT,
|
|
ERROR_CORRUPTED_VERITY_XATTR,
|
|
ERROR_CORRUPTED_XATTR,
|
|
ERROR_INVALID_NODE_REFERENCE,
|
|
ERROR_MAX,
|
|
};
|
|
|
|
#define MAX_F2FS_ERRORS 16
|
|
|
|
struct f2fs_super_block {
|
|
__le32 magic; /* Magic Number */
|
|
__le16 major_ver; /* Major Version */
|
|
__le16 minor_ver; /* Minor Version */
|
|
__le32 log_sectorsize; /* log2 sector size in bytes */
|
|
__le32 log_sectors_per_block; /* log2 # of sectors per block */
|
|
__le32 log_blocksize; /* log2 block size in bytes */
|
|
__le32 log_blocks_per_seg; /* log2 # of blocks per segment */
|
|
__le32 segs_per_sec; /* # of segments per section */
|
|
__le32 secs_per_zone; /* # of sections per zone */
|
|
__le32 checksum_offset; /* checksum offset inside super block */
|
|
__le64 block_count; /* total # of user blocks */
|
|
__le32 section_count; /* total # of sections */
|
|
__le32 segment_count; /* total # of segments */
|
|
__le32 segment_count_ckpt; /* # of segments for checkpoint */
|
|
__le32 segment_count_sit; /* # of segments for SIT */
|
|
__le32 segment_count_nat; /* # of segments for NAT */
|
|
__le32 segment_count_ssa; /* # of segments for SSA */
|
|
__le32 segment_count_main; /* # of segments for main area */
|
|
__le32 segment0_blkaddr; /* start block address of segment 0 */
|
|
__le32 cp_blkaddr; /* start block address of checkpoint */
|
|
__le32 sit_blkaddr; /* start block address of SIT */
|
|
__le32 nat_blkaddr; /* start block address of NAT */
|
|
__le32 ssa_blkaddr; /* start block address of SSA */
|
|
__le32 main_blkaddr; /* start block address of main area */
|
|
__le32 root_ino; /* root inode number */
|
|
__le32 node_ino; /* node inode number */
|
|
__le32 meta_ino; /* meta inode number */
|
|
__u8 uuid[16]; /* 128-bit uuid for volume */
|
|
__le16 volume_name[MAX_VOLUME_NAME]; /* volume name */
|
|
__le32 extension_count; /* # of extensions below */
|
|
__u8 extension_list[F2FS_MAX_EXTENSION][F2FS_EXTENSION_LEN];/* extension array */
|
|
__le32 cp_payload;
|
|
__u8 version[VERSION_LEN]; /* the kernel version */
|
|
__u8 init_version[VERSION_LEN]; /* the initial kernel version */
|
|
__le32 feature; /* defined features */
|
|
__u8 encryption_level; /* versioning level for encryption */
|
|
__u8 encrypt_pw_salt[16]; /* Salt used for string2key algorithm */
|
|
struct f2fs_device devs[MAX_DEVICES]; /* device list */
|
|
__le32 qf_ino[F2FS_MAX_QUOTAS]; /* quota inode numbers */
|
|
__u8 hot_ext_count; /* # of hot file extension */
|
|
__le16 s_encoding; /* Filename charset encoding */
|
|
__le16 s_encoding_flags; /* Filename charset encoding flags */
|
|
__u8 s_stop_reason[MAX_STOP_REASON]; /* stop checkpoint reason */
|
|
__u8 s_errors[MAX_F2FS_ERRORS]; /* reason of image corrupts */
|
|
__u8 reserved[258]; /* valid reserved region */
|
|
__le32 crc; /* checksum of superblock */
|
|
} __packed;
|
|
|
|
/*
|
|
* For checkpoint
|
|
*/
|
|
#define CP_RESIZEFS_FLAG 0x00004000
|
|
#define CP_DISABLED_QUICK_FLAG 0x00002000
|
|
#define CP_DISABLED_FLAG 0x00001000
|
|
#define CP_QUOTA_NEED_FSCK_FLAG 0x00000800
|
|
#define CP_LARGE_NAT_BITMAP_FLAG 0x00000400
|
|
#define CP_NOCRC_RECOVERY_FLAG 0x00000200
|
|
#define CP_TRIMMED_FLAG 0x00000100
|
|
#define CP_NAT_BITS_FLAG 0x00000080
|
|
#define CP_CRC_RECOVERY_FLAG 0x00000040
|
|
#define CP_FASTBOOT_FLAG 0x00000020
|
|
#define CP_FSCK_FLAG 0x00000010
|
|
#define CP_ERROR_FLAG 0x00000008
|
|
#define CP_COMPACT_SUM_FLAG 0x00000004
|
|
#define CP_ORPHAN_PRESENT_FLAG 0x00000002
|
|
#define CP_UMOUNT_FLAG 0x00000001
|
|
|
|
#define F2FS_CP_PACKS 2 /* # of checkpoint packs */
|
|
|
|
struct f2fs_checkpoint {
|
|
__le64 checkpoint_ver; /* checkpoint block version number */
|
|
__le64 user_block_count; /* # of user blocks */
|
|
__le64 valid_block_count; /* # of valid blocks in main area */
|
|
__le32 rsvd_segment_count; /* # of reserved segments for gc */
|
|
__le32 overprov_segment_count; /* # of overprovision segments */
|
|
__le32 free_segment_count; /* # of free segments in main area */
|
|
|
|
/* information of current node segments */
|
|
__le32 cur_node_segno[MAX_ACTIVE_NODE_LOGS];
|
|
__le16 cur_node_blkoff[MAX_ACTIVE_NODE_LOGS];
|
|
/* information of current data segments */
|
|
__le32 cur_data_segno[MAX_ACTIVE_DATA_LOGS];
|
|
__le16 cur_data_blkoff[MAX_ACTIVE_DATA_LOGS];
|
|
__le32 ckpt_flags; /* Flags : umount and journal_present */
|
|
__le32 cp_pack_total_block_count; /* total # of one cp pack */
|
|
__le32 cp_pack_start_sum; /* start block number of data summary */
|
|
__le32 valid_node_count; /* Total number of valid nodes */
|
|
__le32 valid_inode_count; /* Total number of valid inodes */
|
|
__le32 next_free_nid; /* Next free node number */
|
|
__le32 sit_ver_bitmap_bytesize; /* Default value 64 */
|
|
__le32 nat_ver_bitmap_bytesize; /* Default value 256 */
|
|
__le32 checksum_offset; /* checksum offset inside cp block */
|
|
__le64 elapsed_time; /* mounted time */
|
|
/* allocation type of current segment */
|
|
unsigned char alloc_type[MAX_ACTIVE_LOGS];
|
|
|
|
/* SIT and NAT version bitmap */
|
|
unsigned char sit_nat_version_bitmap[];
|
|
} __packed;
|
|
|
|
#define CP_CHKSUM_OFFSET 4092 /* default chksum offset in checkpoint */
|
|
#define CP_MIN_CHKSUM_OFFSET \
|
|
(offsetof(struct f2fs_checkpoint, sit_nat_version_bitmap))
|
|
|
|
/*
|
|
* For orphan inode management
|
|
*/
|
|
#define F2FS_ORPHANS_PER_BLOCK 1020
|
|
|
|
#define GET_ORPHAN_BLOCKS(n) (((n) + F2FS_ORPHANS_PER_BLOCK - 1) / \
|
|
F2FS_ORPHANS_PER_BLOCK)
|
|
|
|
struct f2fs_orphan_block {
|
|
__le32 ino[F2FS_ORPHANS_PER_BLOCK]; /* inode numbers */
|
|
__le32 reserved; /* reserved */
|
|
__le16 blk_addr; /* block index in current CP */
|
|
__le16 blk_count; /* Number of orphan inode blocks in CP */
|
|
__le32 entry_count; /* Total number of orphan nodes in current CP */
|
|
__le32 check_sum; /* CRC32 for orphan inode block */
|
|
} __packed;
|
|
|
|
/*
|
|
* For NODE structure
|
|
*/
|
|
struct f2fs_extent {
|
|
__le32 fofs; /* start file offset of the extent */
|
|
__le32 blk; /* start block address of the extent */
|
|
__le32 len; /* length of the extent */
|
|
} __packed;
|
|
|
|
#define F2FS_NAME_LEN 255
|
|
/* 200 bytes for inline xattrs by default */
|
|
#define DEFAULT_INLINE_XATTR_ADDRS 50
|
|
#define DEF_ADDRS_PER_INODE 923 /* Address Pointers in an Inode */
|
|
#define CUR_ADDRS_PER_INODE(inode) (DEF_ADDRS_PER_INODE - \
|
|
get_extra_isize(inode))
|
|
#define DEF_NIDS_PER_INODE 5 /* Node IDs in an Inode */
|
|
#define ADDRS_PER_INODE(inode) addrs_per_inode(inode)
|
|
#define DEF_ADDRS_PER_BLOCK 1018 /* Address Pointers in a Direct Block */
|
|
#define ADDRS_PER_BLOCK(inode) addrs_per_block(inode)
|
|
#define NIDS_PER_BLOCK 1018 /* Node IDs in an Indirect Block */
|
|
|
|
#define ADDRS_PER_PAGE(page, inode) \
|
|
(IS_INODE(page) ? ADDRS_PER_INODE(inode) : ADDRS_PER_BLOCK(inode))
|
|
|
|
#define NODE_DIR1_BLOCK (DEF_ADDRS_PER_INODE + 1)
|
|
#define NODE_DIR2_BLOCK (DEF_ADDRS_PER_INODE + 2)
|
|
#define NODE_IND1_BLOCK (DEF_ADDRS_PER_INODE + 3)
|
|
#define NODE_IND2_BLOCK (DEF_ADDRS_PER_INODE + 4)
|
|
#define NODE_DIND_BLOCK (DEF_ADDRS_PER_INODE + 5)
|
|
|
|
#define F2FS_INLINE_XATTR 0x01 /* file inline xattr flag */
|
|
#define F2FS_INLINE_DATA 0x02 /* file inline data flag */
|
|
#define F2FS_INLINE_DENTRY 0x04 /* file inline dentry flag */
|
|
#define F2FS_DATA_EXIST 0x08 /* file inline data exist flag */
|
|
#define F2FS_INLINE_DOTS 0x10 /* file having implicit dot dentries */
|
|
#define F2FS_EXTRA_ATTR 0x20 /* file having extra attribute */
|
|
#define F2FS_PIN_FILE 0x40 /* file should not be gced */
|
|
#define F2FS_COMPRESS_RELEASED 0x80 /* file released compressed blocks */
|
|
|
|
struct f2fs_inode {
|
|
__le16 i_mode; /* file mode */
|
|
__u8 i_advise; /* file hints */
|
|
__u8 i_inline; /* file inline flags */
|
|
__le32 i_uid; /* user ID */
|
|
__le32 i_gid; /* group ID */
|
|
__le32 i_links; /* links count */
|
|
__le64 i_size; /* file size in bytes */
|
|
__le64 i_blocks; /* file size in blocks */
|
|
__le64 i_atime; /* access time */
|
|
__le64 i_ctime; /* change time */
|
|
__le64 i_mtime; /* modification time */
|
|
__le32 i_atime_nsec; /* access time in nano scale */
|
|
__le32 i_ctime_nsec; /* change time in nano scale */
|
|
__le32 i_mtime_nsec; /* modification time in nano scale */
|
|
__le32 i_generation; /* file version (for NFS) */
|
|
union {
|
|
__le32 i_current_depth; /* only for directory depth */
|
|
__le16 i_gc_failures; /*
|
|
* # of gc failures on pinned file.
|
|
* only for regular files.
|
|
*/
|
|
};
|
|
__le32 i_xattr_nid; /* nid to save xattr */
|
|
__le32 i_flags; /* file attributes */
|
|
__le32 i_pino; /* parent inode number */
|
|
__le32 i_namelen; /* file name length */
|
|
__u8 i_name[F2FS_NAME_LEN]; /* file name for SPOR */
|
|
__u8 i_dir_level; /* dentry_level for large dir */
|
|
|
|
struct f2fs_extent i_ext; /* caching a largest extent */
|
|
|
|
union {
|
|
struct {
|
|
__le16 i_extra_isize; /* extra inode attribute size */
|
|
__le16 i_inline_xattr_size; /* inline xattr size, unit: 4 bytes */
|
|
__le32 i_projid; /* project id */
|
|
__le32 i_inode_checksum;/* inode meta checksum */
|
|
__le64 i_crtime; /* creation time */
|
|
__le32 i_crtime_nsec; /* creation time in nano scale */
|
|
__le64 i_compr_blocks; /* # of compressed blocks */
|
|
__u8 i_compress_algorithm; /* compress algorithm */
|
|
__u8 i_log_cluster_size; /* log of cluster size */
|
|
__le16 i_compress_flag; /* compress flag */
|
|
/* 0 bit: chksum flag
|
|
* [8,15] bits: compress level
|
|
*/
|
|
__le32 i_extra_end[0]; /* for attribute size calculation */
|
|
} __packed;
|
|
__le32 i_addr[DEF_ADDRS_PER_INODE]; /* Pointers to data blocks */
|
|
};
|
|
__le32 i_nid[DEF_NIDS_PER_INODE]; /* direct(2), indirect(2),
|
|
double_indirect(1) node id */
|
|
} __packed;
|
|
|
|
struct direct_node {
|
|
__le32 addr[DEF_ADDRS_PER_BLOCK]; /* array of data block address */
|
|
} __packed;
|
|
|
|
struct indirect_node {
|
|
__le32 nid[NIDS_PER_BLOCK]; /* array of data block address */
|
|
} __packed;
|
|
|
|
enum {
|
|
COLD_BIT_SHIFT = 0,
|
|
FSYNC_BIT_SHIFT,
|
|
DENT_BIT_SHIFT,
|
|
OFFSET_BIT_SHIFT
|
|
};
|
|
|
|
#define OFFSET_BIT_MASK GENMASK(OFFSET_BIT_SHIFT - 1, 0)
|
|
|
|
struct node_footer {
|
|
__le32 nid; /* node id */
|
|
__le32 ino; /* inode number */
|
|
__le32 flag; /* include cold/fsync/dentry marks and offset */
|
|
__le64 cp_ver; /* checkpoint version */
|
|
__le32 next_blkaddr; /* next node page block address */
|
|
} __packed;
|
|
|
|
struct f2fs_node {
|
|
/* can be one of three types: inode, direct, and indirect types */
|
|
union {
|
|
struct f2fs_inode i;
|
|
struct direct_node dn;
|
|
struct indirect_node in;
|
|
};
|
|
struct node_footer footer;
|
|
} __packed;
|
|
|
|
/*
|
|
* For NAT entries
|
|
*/
|
|
#define NAT_ENTRY_PER_BLOCK (PAGE_SIZE / sizeof(struct f2fs_nat_entry))
|
|
|
|
struct f2fs_nat_entry {
|
|
__u8 version; /* latest version of cached nat entry */
|
|
__le32 ino; /* inode number */
|
|
__le32 block_addr; /* block address */
|
|
} __packed;
|
|
|
|
struct f2fs_nat_block {
|
|
struct f2fs_nat_entry entries[NAT_ENTRY_PER_BLOCK];
|
|
} __packed;
|
|
|
|
/*
|
|
* For SIT entries
|
|
*
|
|
* Each segment is 2MB in size by default so that a bitmap for validity of
|
|
* there-in blocks should occupy 64 bytes, 512 bits.
|
|
* Not allow to change this.
|
|
*/
|
|
#define SIT_VBLOCK_MAP_SIZE 64
|
|
#define SIT_ENTRY_PER_BLOCK (PAGE_SIZE / sizeof(struct f2fs_sit_entry))
|
|
|
|
/*
|
|
* F2FS uses 4 bytes to represent block address. As a result, supported size of
|
|
* disk is 16 TB and it equals to 16 * 1024 * 1024 / 2 segments.
|
|
*/
|
|
#define F2FS_MAX_SEGMENT ((16 * 1024 * 1024) / 2)
|
|
|
|
/*
|
|
* Note that f2fs_sit_entry->vblocks has the following bit-field information.
|
|
* [15:10] : allocation type such as CURSEG_XXXX_TYPE
|
|
* [9:0] : valid block count
|
|
*/
|
|
#define SIT_VBLOCKS_SHIFT 10
|
|
#define SIT_VBLOCKS_MASK ((1 << SIT_VBLOCKS_SHIFT) - 1)
|
|
#define GET_SIT_VBLOCKS(raw_sit) \
|
|
(le16_to_cpu((raw_sit)->vblocks) & SIT_VBLOCKS_MASK)
|
|
#define GET_SIT_TYPE(raw_sit) \
|
|
((le16_to_cpu((raw_sit)->vblocks) & ~SIT_VBLOCKS_MASK) \
|
|
>> SIT_VBLOCKS_SHIFT)
|
|
|
|
struct f2fs_sit_entry {
|
|
__le16 vblocks; /* reference above */
|
|
__u8 valid_map[SIT_VBLOCK_MAP_SIZE]; /* bitmap for valid blocks */
|
|
__le64 mtime; /* segment age for cleaning */
|
|
} __packed;
|
|
|
|
struct f2fs_sit_block {
|
|
struct f2fs_sit_entry entries[SIT_ENTRY_PER_BLOCK];
|
|
} __packed;
|
|
|
|
/*
|
|
* For segment summary
|
|
*
|
|
* One summary block contains exactly 512 summary entries, which represents
|
|
* exactly 2MB segment by default. Not allow to change the basic units.
|
|
*
|
|
* NOTE: For initializing fields, you must use set_summary
|
|
*
|
|
* - If data page, nid represents dnode's nid
|
|
* - If node page, nid represents the node page's nid.
|
|
*
|
|
* The ofs_in_node is used by only data page. It represents offset
|
|
* from node's page's beginning to get a data block address.
|
|
* ex) data_blkaddr = (block_t)(nodepage_start_address + ofs_in_node)
|
|
*/
|
|
#define ENTRIES_IN_SUM 512
|
|
#define SUMMARY_SIZE (7) /* sizeof(struct summary) */
|
|
#define SUM_FOOTER_SIZE (5) /* sizeof(struct summary_footer) */
|
|
#define SUM_ENTRY_SIZE (SUMMARY_SIZE * ENTRIES_IN_SUM)
|
|
|
|
/* a summary entry for a 4KB-sized block in a segment */
|
|
struct f2fs_summary {
|
|
__le32 nid; /* parent node id */
|
|
union {
|
|
__u8 reserved[3];
|
|
struct {
|
|
__u8 version; /* node version number */
|
|
__le16 ofs_in_node; /* block index in parent node */
|
|
} __packed;
|
|
};
|
|
} __packed;
|
|
|
|
/* summary block type, node or data, is stored to the summary_footer */
|
|
#define SUM_TYPE_NODE (1)
|
|
#define SUM_TYPE_DATA (0)
|
|
|
|
struct summary_footer {
|
|
unsigned char entry_type; /* SUM_TYPE_XXX */
|
|
__le32 check_sum; /* summary checksum */
|
|
} __packed;
|
|
|
|
#define SUM_JOURNAL_SIZE (F2FS_BLKSIZE - SUM_FOOTER_SIZE -\
|
|
SUM_ENTRY_SIZE)
|
|
#define NAT_JOURNAL_ENTRIES ((SUM_JOURNAL_SIZE - 2) /\
|
|
sizeof(struct nat_journal_entry))
|
|
#define NAT_JOURNAL_RESERVED ((SUM_JOURNAL_SIZE - 2) %\
|
|
sizeof(struct nat_journal_entry))
|
|
#define SIT_JOURNAL_ENTRIES ((SUM_JOURNAL_SIZE - 2) /\
|
|
sizeof(struct sit_journal_entry))
|
|
#define SIT_JOURNAL_RESERVED ((SUM_JOURNAL_SIZE - 2) %\
|
|
sizeof(struct sit_journal_entry))
|
|
|
|
/* Reserved area should make size of f2fs_extra_info equals to
|
|
* that of nat_journal and sit_journal.
|
|
*/
|
|
#define EXTRA_INFO_RESERVED (SUM_JOURNAL_SIZE - 2 - 8)
|
|
|
|
/*
|
|
* frequently updated NAT/SIT entries can be stored in the spare area in
|
|
* summary blocks
|
|
*/
|
|
enum {
|
|
NAT_JOURNAL = 0,
|
|
SIT_JOURNAL
|
|
};
|
|
|
|
struct nat_journal_entry {
|
|
__le32 nid;
|
|
struct f2fs_nat_entry ne;
|
|
} __packed;
|
|
|
|
struct nat_journal {
|
|
struct nat_journal_entry entries[NAT_JOURNAL_ENTRIES];
|
|
__u8 reserved[NAT_JOURNAL_RESERVED];
|
|
} __packed;
|
|
|
|
struct sit_journal_entry {
|
|
__le32 segno;
|
|
struct f2fs_sit_entry se;
|
|
} __packed;
|
|
|
|
struct sit_journal {
|
|
struct sit_journal_entry entries[SIT_JOURNAL_ENTRIES];
|
|
__u8 reserved[SIT_JOURNAL_RESERVED];
|
|
} __packed;
|
|
|
|
struct f2fs_extra_info {
|
|
__le64 kbytes_written;
|
|
__u8 reserved[EXTRA_INFO_RESERVED];
|
|
} __packed;
|
|
|
|
struct f2fs_journal {
|
|
union {
|
|
__le16 n_nats;
|
|
__le16 n_sits;
|
|
};
|
|
/* spare area is used by NAT or SIT journals or extra info */
|
|
union {
|
|
struct nat_journal nat_j;
|
|
struct sit_journal sit_j;
|
|
struct f2fs_extra_info info;
|
|
};
|
|
} __packed;
|
|
|
|
/* 4KB-sized summary block structure */
|
|
struct f2fs_summary_block {
|
|
struct f2fs_summary entries[ENTRIES_IN_SUM];
|
|
struct f2fs_journal journal;
|
|
struct summary_footer footer;
|
|
} __packed;
|
|
|
|
/*
|
|
* For directory operations
|
|
*/
|
|
#define F2FS_DOT_HASH 0
|
|
#define F2FS_DDOT_HASH F2FS_DOT_HASH
|
|
#define F2FS_MAX_HASH (~((0x3ULL) << 62))
|
|
#define F2FS_HASH_COL_BIT ((0x1ULL) << 63)
|
|
|
|
typedef __le32 f2fs_hash_t;
|
|
|
|
/* One directory entry slot covers 8bytes-long file name */
|
|
#define F2FS_SLOT_LEN 8
|
|
#define F2FS_SLOT_LEN_BITS 3
|
|
|
|
#define GET_DENTRY_SLOTS(x) (((x) + F2FS_SLOT_LEN - 1) >> F2FS_SLOT_LEN_BITS)
|
|
|
|
/* MAX level for dir lookup */
|
|
#define MAX_DIR_HASH_DEPTH 63
|
|
|
|
/* MAX buckets in one level of dir */
|
|
#define MAX_DIR_BUCKETS BIT((MAX_DIR_HASH_DEPTH / 2) - 1)
|
|
|
|
/*
|
|
* space utilization of regular dentry and inline dentry (w/o extra reservation)
|
|
* regular dentry inline dentry (def) inline dentry (min)
|
|
* bitmap 1 * 27 = 27 1 * 23 = 23 1 * 1 = 1
|
|
* reserved 1 * 3 = 3 1 * 7 = 7 1 * 1 = 1
|
|
* dentry 11 * 214 = 2354 11 * 182 = 2002 11 * 2 = 22
|
|
* filename 8 * 214 = 1712 8 * 182 = 1456 8 * 2 = 16
|
|
* total 4096 3488 40
|
|
*
|
|
* Note: there are more reserved space in inline dentry than in regular
|
|
* dentry, when converting inline dentry we should handle this carefully.
|
|
*/
|
|
#define NR_DENTRY_IN_BLOCK 214 /* the number of dentry in a block */
|
|
#define SIZE_OF_DIR_ENTRY 11 /* by byte */
|
|
#define SIZE_OF_DENTRY_BITMAP ((NR_DENTRY_IN_BLOCK + BITS_PER_BYTE - 1) / \
|
|
BITS_PER_BYTE)
|
|
#define SIZE_OF_RESERVED (PAGE_SIZE - ((SIZE_OF_DIR_ENTRY + \
|
|
F2FS_SLOT_LEN) * \
|
|
NR_DENTRY_IN_BLOCK + SIZE_OF_DENTRY_BITMAP))
|
|
#define MIN_INLINE_DENTRY_SIZE 40 /* just include '.' and '..' entries */
|
|
|
|
/* One directory entry slot representing F2FS_SLOT_LEN-sized file name */
|
|
struct f2fs_dir_entry {
|
|
__le32 hash_code; /* hash code of file name */
|
|
__le32 ino; /* inode number */
|
|
__le16 name_len; /* length of file name */
|
|
__u8 file_type; /* file type */
|
|
} __packed;
|
|
|
|
/* 4KB-sized directory entry block */
|
|
struct f2fs_dentry_block {
|
|
/* validity bitmap for directory entries in each block */
|
|
__u8 dentry_bitmap[SIZE_OF_DENTRY_BITMAP];
|
|
__u8 reserved[SIZE_OF_RESERVED];
|
|
struct f2fs_dir_entry dentry[NR_DENTRY_IN_BLOCK];
|
|
__u8 filename[NR_DENTRY_IN_BLOCK][F2FS_SLOT_LEN];
|
|
} __packed;
|
|
|
|
#define F2FS_DEF_PROJID 0 /* default project ID */
|
|
|
|
#endif /* _LINUX_F2FS_FS_H */
|