diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2012-06-01 10:12:15 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2012-06-01 10:12:15 -0700 |
commit | 4edebed86690eb8db9af3ab85baf4a34e73266cc (patch) | |
tree | 8ab144b08f490f239fa62be52470860c9311664d /fs/ext4 | |
parent | 51eab603f5c86dd1eae4c525df3e7f7eeab401d6 (diff) | |
parent | 5e44f8c374dc4f8eadf61cd18b2c0d46bc87c1b7 (diff) |
Merge tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4
Pull Ext4 updates from Theodore Ts'o:
"The major new feature added in this update is Darrick J Wong's
metadata checksum feature, which adds crc32 checksums to ext4's
metadata fields.
There is also the usual set of cleanups and bug fixes."
* tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (44 commits)
ext4: hole-punch use truncate_pagecache_range
jbd2: use kmem_cache_zalloc wrapper instead of flag
ext4: remove mb_groups before tearing down the buddy_cache
ext4: add ext4_mb_unload_buddy in the error path
ext4: don't trash state flags in EXT4_IOC_SETFLAGS
ext4: let getattr report the right blocks in delalloc+bigalloc
ext4: add missing save_error_info() to ext4_error()
ext4: add debugging trigger for ext4_error()
ext4: protect group inode free counting with group lock
ext4: use consistent ssize_t type in ext4_file_write()
ext4: fix format flag in ext4_ext_binsearch_idx()
ext4: cleanup in ext4_discard_allocated_blocks()
ext4: return ENOMEM when mounts fail due to lack of memory
ext4: remove redundundant "(char *) bh->b_data" casts
ext4: disallow hard-linked directory in ext4_lookup
ext4: fix potential integer overflow in alloc_flex_gd()
ext4: remove needs_recovery in ext4_mb_init()
ext4: force ro mount if ext4_setup_super() fails
ext4: fix potential NULL dereference in ext4_free_inodes_counts()
ext4/jbd2: add metadata checksumming to the list of supported features
...
Diffstat (limited to 'fs/ext4')
-rw-r--r-- | fs/ext4/Kconfig | 2 | ||||
-rw-r--r-- | fs/ext4/balloc.c | 41 | ||||
-rw-r--r-- | fs/ext4/bitmap.c | 83 | ||||
-rw-r--r-- | fs/ext4/dir.c | 12 | ||||
-rw-r--r-- | fs/ext4/ext4.h | 130 | ||||
-rw-r--r-- | fs/ext4/ext4_extents.h | 24 | ||||
-rw-r--r-- | fs/ext4/ext4_jbd2.c | 9 | ||||
-rw-r--r-- | fs/ext4/ext4_jbd2.h | 7 | ||||
-rw-r--r-- | fs/ext4/extents.c | 91 | ||||
-rw-r--r-- | fs/ext4/file.c | 2 | ||||
-rw-r--r-- | fs/ext4/ialloc.c | 81 | ||||
-rw-r--r-- | fs/ext4/inode.c | 119 | ||||
-rw-r--r-- | fs/ext4/ioctl.c | 19 | ||||
-rw-r--r-- | fs/ext4/mballoc.c | 30 | ||||
-rw-r--r-- | fs/ext4/mmp.c | 44 | ||||
-rw-r--r-- | fs/ext4/namei.c | 445 | ||||
-rw-r--r-- | fs/ext4/resize.c | 71 | ||||
-rw-r--r-- | fs/ext4/super.c | 253 | ||||
-rw-r--r-- | fs/ext4/xattr.c | 92 | ||||
-rw-r--r-- | fs/ext4/xattr.h | 4 |
20 files changed, 1377 insertions, 182 deletions
diff --git a/fs/ext4/Kconfig b/fs/ext4/Kconfig index 9ed1bb1f319f..c22f17021b6e 100644 --- a/fs/ext4/Kconfig +++ b/fs/ext4/Kconfig @@ -2,6 +2,8 @@ config EXT4_FS tristate "The Extended 4 (ext4) filesystem" select JBD2 select CRC16 + select CRYPTO + select CRYPTO_CRC32C help This is the next generation of the ext3 filesystem. diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index c45c41129a35..99b6324290db 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -168,12 +168,14 @@ void ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh, /* If checksum is bad mark all blocks used to prevent allocation * essentially implementing a per-group read-only flag. */ - if (!ext4_group_desc_csum_verify(sbi, block_group, gdp)) { + if (!ext4_group_desc_csum_verify(sb, block_group, gdp)) { ext4_error(sb, "Checksum bad for group %u", block_group); ext4_free_group_clusters_set(sb, gdp, 0); ext4_free_inodes_set(sb, gdp, 0); ext4_itable_unused_set(sb, gdp, 0); memset(bh->b_data, 0xff, sb->s_blocksize); + ext4_block_bitmap_csum_set(sb, block_group, gdp, bh, + EXT4_BLOCKS_PER_GROUP(sb) / 8); return; } memset(bh->b_data, 0, sb->s_blocksize); @@ -210,6 +212,9 @@ void ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh, */ ext4_mark_bitmap_end(num_clusters_in_group(sb, block_group), sb->s_blocksize * 8, bh->b_data); + ext4_block_bitmap_csum_set(sb, block_group, gdp, bh, + EXT4_BLOCKS_PER_GROUP(sb) / 8); + ext4_group_desc_csum_set(sb, block_group, gdp); } /* Return the number of free blocks in a block group. It is used when @@ -276,9 +281,9 @@ struct ext4_group_desc * ext4_get_group_desc(struct super_block *sb, } static int ext4_valid_block_bitmap(struct super_block *sb, - struct ext4_group_desc *desc, - unsigned int block_group, - struct buffer_head *bh) + struct ext4_group_desc *desc, + unsigned int block_group, + struct buffer_head *bh) { ext4_grpblk_t offset; ext4_grpblk_t next_zero_bit; @@ -325,6 +330,23 @@ err_out: block_group, bitmap_blk); return 0; } + +void ext4_validate_block_bitmap(struct super_block *sb, + struct ext4_group_desc *desc, + unsigned int block_group, + struct buffer_head *bh) +{ + if (buffer_verified(bh)) + return; + + ext4_lock_group(sb, block_group); + if (ext4_valid_block_bitmap(sb, desc, block_group, bh) && + ext4_block_bitmap_csum_verify(sb, block_group, desc, bh, + EXT4_BLOCKS_PER_GROUP(sb) / 8)) + set_buffer_verified(bh); + ext4_unlock_group(sb, block_group); +} + /** * ext4_read_block_bitmap() * @sb: super block @@ -355,12 +377,12 @@ ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group) } if (bitmap_uptodate(bh)) - return bh; + goto verify; lock_buffer(bh); if (bitmap_uptodate(bh)) { unlock_buffer(bh); - return bh; + goto verify; } ext4_lock_group(sb, block_group); if (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) { @@ -379,7 +401,7 @@ ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group) */ set_bitmap_uptodate(bh); unlock_buffer(bh); - return bh; + goto verify; } /* * submit the buffer_head for reading @@ -390,6 +412,9 @@ ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group) get_bh(bh); submit_bh(READ, bh); return bh; +verify: + ext4_validate_block_bitmap(sb, desc, block_group, bh); + return bh; } /* Returns 0 on success, 1 on error */ @@ -412,7 +437,7 @@ int ext4_wait_block_bitmap(struct super_block *sb, ext4_group_t block_group, } clear_buffer_new(bh); /* Panic or remount fs read-only if block bitmap is invalid */ - ext4_valid_block_bitmap(sb, desc, block_group, bh); + ext4_validate_block_bitmap(sb, desc, block_group, bh); return 0; } diff --git a/fs/ext4/bitmap.c b/fs/ext4/bitmap.c index fa3af81ac565..b319721da26a 100644 --- a/fs/ext4/bitmap.c +++ b/fs/ext4/bitmap.c @@ -29,3 +29,86 @@ unsigned int ext4_count_free(struct buffer_head *map, unsigned int numchars) #endif /* EXT4FS_DEBUG */ +int ext4_inode_bitmap_csum_verify(struct super_block *sb, ext4_group_t group, + struct ext4_group_desc *gdp, + struct buffer_head *bh, int sz) +{ + __u32 hi; + __u32 provided, calculated; + struct ext4_sb_info *sbi = EXT4_SB(sb); + + if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, + EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + return 1; + + provided = le16_to_cpu(gdp->bg_inode_bitmap_csum_lo); + calculated = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)bh->b_data, sz); + if (sbi->s_desc_size >= EXT4_BG_INODE_BITMAP_CSUM_HI_END) { + hi = le16_to_cpu(gdp->bg_inode_bitmap_csum_hi); + provided |= (hi << 16); + } else + calculated &= 0xFFFF; + + return provided == calculated; +} + +void ext4_inode_bitmap_csum_set(struct super_block *sb, ext4_group_t group, + struct ext4_group_desc *gdp, + struct buffer_head *bh, int sz) +{ + __u32 csum; + struct ext4_sb_info *sbi = EXT4_SB(sb); + + if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, + EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + return; + + csum = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)bh->b_data, sz); + gdp->bg_inode_bitmap_csum_lo = cpu_to_le16(csum & 0xFFFF); + if (sbi->s_desc_size >= EXT4_BG_INODE_BITMAP_CSUM_HI_END) + gdp->bg_inode_bitmap_csum_hi = cpu_to_le16(csum >> 16); +} + +int ext4_block_bitmap_csum_verify(struct super_block *sb, ext4_group_t group, + struct ext4_group_desc *gdp, + struct buffer_head *bh, int sz) +{ + __u32 hi; + __u32 provided, calculated; + struct ext4_sb_info *sbi = EXT4_SB(sb); + + if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, + EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + return 1; + + provided = le16_to_cpu(gdp->bg_block_bitmap_csum_lo); + calculated = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)bh->b_data, sz); + if (sbi->s_desc_size >= EXT4_BG_BLOCK_BITMAP_CSUM_HI_END) { + hi = le16_to_cpu(gdp->bg_block_bitmap_csum_hi); + provided |= (hi << 16); + } else + calculated &= 0xFFFF; + + if (provided == calculated) + return 1; + + ext4_error(sb, "Bad block bitmap checksum: block_group = %u", group); + return 0; +} + +void ext4_block_bitmap_csum_set(struct super_block *sb, ext4_group_t group, + struct ext4_group_desc *gdp, + struct buffer_head *bh, int sz) +{ + __u32 csum; + struct ext4_sb_info *sbi = EXT4_SB(sb); + + if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, + EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + return; + + csum = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)bh->b_data, sz); + gdp->bg_block_bitmap_csum_lo = cpu_to_le16(csum & 0xFFFF); + if (sbi->s_desc_size >= EXT4_BG_BLOCK_BITMAP_CSUM_HI_END) + gdp->bg_block_bitmap_csum_hi = cpu_to_le16(csum >> 16); +} diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c index b86786202643..aa39e600d159 100644 --- a/fs/ext4/dir.c +++ b/fs/ext4/dir.c @@ -179,6 +179,18 @@ static int ext4_readdir(struct file *filp, continue; } + /* Check the checksum */ + if (!buffer_verified(bh) && + !ext4_dirent_csum_verify(inode, + (struct ext4_dir_entry *)bh->b_data)) { + EXT4_ERROR_FILE(filp, 0, "directory fails checksum " + "at offset %llu", + (unsigned long long)filp->f_pos); + filp->f_pos += sb->s_blocksize - offset; + continue; + } + set_buffer_verified(bh); + revalidate: /* If the dir block has changed since the last call to * readdir(2), then we might be pointing to an invalid diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index c21b1de51afb..cfc4e01b3c83 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -29,6 +29,7 @@ #include <linux/wait.h> #include <linux/blockgroup_lock.h> #include <linux/percpu_counter.h> +#include <crypto/hash.h> #ifdef __KERNEL__ #include <linux/compat.h> #endif @@ -298,7 +299,9 @@ struct ext4_group_desc __le16 bg_free_inodes_count_lo;/* Free inodes count */ __le16 bg_used_dirs_count_lo; /* Directories count */ __le16 bg_flags; /* EXT4_BG_flags (INODE_UNINIT, etc) */ - __u32 bg_reserved[2]; /* Likely block/inode bitmap checksum */ + __le32 bg_exclude_bitmap_lo; /* Exclude bitmap for snapshots */ + __le16 bg_block_bitmap_csum_lo;/* crc32c(s_uuid+grp_num+bbitmap) LE */ + __le16 bg_inode_bitmap_csum_lo;/* crc32c(s_uuid+grp_num+ibitmap) LE */ __le16 bg_itable_unused_lo; /* Unused inodes count */ __le16 bg_checksum; /* crc16(sb_uuid+group+desc) */ __le32 bg_block_bitmap_hi; /* Blocks bitmap block MSB */ @@ -308,9 +311,19 @@ struct ext4_group_desc __le16 bg_free_inodes_count_hi;/* Free inodes count MSB */ __le16 bg_used_dirs_count_hi; /* Directories count MSB */ __le16 bg_itable_unused_hi; /* Unused inodes count MSB */ - __u32 bg_reserved2[3]; + __le32 bg_exclude_bitmap_hi; /* Exclude bitmap block MSB */ + __le16 bg_block_bitmap_csum_hi;/* crc32c(s_uuid+grp_num+bbitmap) BE */ + __le16 bg_inode_bitmap_csum_hi;/* crc32c(s_uuid+grp_num+ibitmap) BE */ + __u32 bg_reserved; }; +#define EXT4_BG_INODE_BITMAP_CSUM_HI_END \ + (offsetof(struct ext4_group_desc, bg_inode_bitmap_csum_hi) + \ + sizeof(__le16)) +#define EXT4_BG_BLOCK_BITMAP_CSUM_HI_END \ + (offsetof(struct ext4_group_desc, bg_block_bitmap_csum_hi) + \ + sizeof(__le16)) + /* * Structure of a flex block group info */ @@ -650,7 +663,8 @@ struct ext4_inode { __le16 l_i_file_acl_high; __le16 l_i_uid_high; /* these 2 fields */ __le16 l_i_gid_high; /* were reserved2[0] */ - __u32 l_i_reserved2; + __le16 l_i_checksum_lo;/* crc32c(uuid+inum+inode) LE */ + __le16 l_i_reserved; } linux2; struct { __le16 h_i_reserved1; /* Obsoleted fragment number/size which are removed in ext4 */ @@ -666,7 +680,7 @@ struct ext4_inode { } masix2; } osd2; /* OS dependent 2 */ __le16 i_extra_isize; - __le16 i_pad1; + __le16 i_checksum_hi; /* crc32c(uuid+inum+inode) BE */ __le32 i_ctime_extra; /* extra Change time (nsec << 2 | epoch) */ __le32 i_mtime_extra; /* extra Modification time(nsec << 2 | epoch) */ __le32 i_atime_extra; /* extra Access time (nsec << 2 | epoch) */ @@ -768,7 +782,7 @@ do { \ #define i_gid_low i_gid #define i_uid_high osd2.linux2.l_i_uid_high #define i_gid_high osd2.linux2.l_i_gid_high -#define i_reserved2 osd2.linux2.l_i_reserved2 +#define i_checksum_lo osd2.linux2.l_i_checksum_lo #elif defined(__GNU__) @@ -908,6 +922,9 @@ struct ext4_inode_info { */ tid_t i_sync_tid; tid_t i_datasync_tid; + + /* Precomputed uuid+inum+igen checksum for seeding inode checksums */ + __u32 i_csum_seed; }; /* @@ -1001,6 +1018,9 @@ extern void ext4_set_bits(void *bm, int cur, int len); #define EXT4_ERRORS_PANIC 3 /* Panic */ #define EXT4_ERRORS_DEFAULT EXT4_ERRORS_CONTINUE +/* Metadata checksum algorithm codes */ +#define EXT4_CRC32C_CHKSUM 1 + /* * Structure of the super block */ @@ -1087,7 +1107,7 @@ struct ext4_super_block { __le64 s_mmp_block; /* Block for multi-mount protection */ __le32 s_raid_stripe_width; /* blocks on all data disks (N*stride)*/ __u8 s_log_groups_per_flex; /* FLEX_BG group size */ - __u8 s_reserved_char_pad; + __u8 s_checksum_type; /* metadata checksum algorithm used */ __le16 s_reserved_pad; __le64 s_kbytes_written; /* nr of lifetime kilobytes written */ __le32 s_snapshot_inum; /* Inode number of active snapshot */ @@ -1113,7 +1133,8 @@ struct ext4_super_block { __le32 s_usr_quota_inum; /* inode for tracking user quota */ __le32 s_grp_quota_inum; /* inode for tracking group quota */ __le32 s_overhead_clusters; /* overhead blocks/clusters in fs */ - __le32 s_reserved[109]; /* Padding to the end of the block */ + __le32 s_reserved[108]; /* Padding to the end of the block */ + __le32 s_checksum; /* crc32c(superblock) */ }; #define EXT4_S_ERR_LEN (EXT4_S_ERR_END - EXT4_S_ERR_START) @@ -1176,6 +1197,7 @@ struct ext4_sb_info { struct proc_dir_entry *s_proc; struct kobject s_kobj; struct completion s_kobj_unregister; + struct super_block *s_sb; /* Journaling */ struct journal_s *s_journal; @@ -1266,6 +1288,12 @@ struct ext4_sb_info { /* record the last minlen when FITRIM is called. */ atomic_t s_last_trim_minblks; + + /* Reference to checksum algorithm driver via cryptoapi */ + struct crypto_shash *s_chksum_driver; + + /* Precomputed FS UUID checksum for seeding other checksums */ + __u32 s_csum_seed; }; static inline struct ext4_sb_info *EXT4_SB(struct super_block *sb) @@ -1414,6 +1442,12 @@ static inline void ext4_clear_state_flags(struct ext4_inode_info *ei) #define EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE 0x0040 #define EXT4_FEATURE_RO_COMPAT_QUOTA 0x0100 #define EXT4_FEATURE_RO_COMPAT_BIGALLOC 0x0200 +/* + * METADATA_CSUM also enables group descriptor checksums (GDT_CSUM). When + * METADATA_CSUM is set, group descriptor checksums use the same algorithm as + * all other data structures' checksums. However, the METADATA_CSUM and + * GDT_CSUM bits are mutually exclusive. + */ #define EXT4_FEATURE_RO_COMPAT_METADATA_CSUM 0x0400 #define EXT4_FEATURE_INCOMPAT_COMPRESSION 0x0001 @@ -1461,7 +1495,8 @@ static inline void ext4_clear_state_flags(struct ext4_inode_info *ei) EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE | \ EXT4_FEATURE_RO_COMPAT_BTREE_DIR |\ EXT4_FEATURE_RO_COMPAT_HUGE_FILE |\ - EXT4_FEATURE_RO_COMPAT_BIGALLOC) + EXT4_FEATURE_RO_COMPAT_BIGALLOC |\ + EXT4_FEATURE_RO_COMPAT_METADATA_CSUM) /* * Default values for user and/or group using reserved blocks @@ -1527,6 +1562,18 @@ struct ext4_dir_entry_2 { }; /* + * This is a bogus directory entry at the end of each leaf block that + * records checksums. + */ +struct ext4_dir_entry_tail { + __le32 det_reserved_zero1; /* Pretend to be unused */ + __le16 det_rec_len; /* 12 */ + __u8 det_reserved_zero2; /* Zero name length */ + __u8 det_reserved_ft; /* 0xDE, fake file type */ + __le32 det_checksum; /* crc32c(uuid+inum+dirblock) */ +}; + +/* * Ext4 directory file types. Only the low 3 bits are used. The * other bits are reserved for now. */ @@ -1541,6 +1588,8 @@ struct ext4_dir_entry_2 { #define EXT4_FT_MAX 8 +#define EXT4_FT_DIR_CSUM 0xDE + /* * EXT4_DIR_PAD defines the directory entries boundaries * @@ -1609,6 +1658,25 @@ static inline __le16 ext4_rec_len_to_disk(unsigned len, unsigned blocksize) #define DX_HASH_HALF_MD4_UNSIGNED 4 #define DX_HASH_TEA_UNSIGNED 5 +static inline u32 ext4_chksum(struct ext4_sb_info *sbi, u32 crc, + const void *address, unsigned int length) +{ + struct { + struct shash_desc shash; + char ctx[crypto_shash_descsize(sbi->s_chksum_driver)]; + } desc; + int err; + + desc.shash.tfm = sbi->s_chksum_driver; + desc.shash.flags = 0; + *(u32 *)desc.ctx = crc; + + err = crypto_shash_update(&desc.shash, address, length); + BUG_ON(err); + + return *(u32 *)desc.ctx; +} + #ifdef __KERNEL__ /* hash info structure used by the directory hash */ @@ -1741,7 +1809,8 @@ struct mmp_struct { __le16 mmp_check_interval; __le16 mmp_pad1; - __le32 mmp_pad2[227]; + __le32 mmp_pad2[226]; + __le32 mmp_checksum; /* crc32c(uuid+mmp_block) */ }; /* arguments passed to the mmp thread */ @@ -1784,8 +1853,24 @@ struct mmpd_data { /* bitmap.c */ extern unsigned int ext4_count_free(struct buffer_head *, unsigned); +void ext4_inode_bitmap_csum_set(struct super_block *sb, ext4_group_t group, + struct ext4_group_desc *gdp, + struct buffer_head *bh, int sz); +int ext4_inode_bitmap_csum_verify(struct super_block *sb, ext4_group_t group, + struct ext4_group_desc *gdp, + struct buffer_head *bh, int sz); +void ext4_block_bitmap_csum_set(struct super_block *sb, ext4_group_t group, + struct ext4_group_desc *gdp, + struct buffer_head *bh, int sz); +int ext4_block_bitmap_csum_verify(struct super_block *sb, ext4_group_t group, + struct ext4_group_desc *gdp, + struct buffer_head *bh, int sz); /* balloc.c */ +extern void ext4_validate_block_bitmap(struct super_block *sb, + struct ext4_group_desc *desc, + unsigned int block_group, + struct buffer_head *bh); extern unsigned int ext4_block_group(struct super_block *sb, ext4_fsblk_t blocknr); extern ext4_grpblk_t ext4_block_group_offset(struct super_block *sb, @@ -1864,7 +1949,7 @@ extern void ext4_end_bitmap_read(struct buffer_head *bh, int uptodate); /* mballoc.c */ extern long ext4_mb_stats; extern long ext4_mb_max_to_scan; -extern int ext4_mb_init(struct super_block *, int); +extern int ext4_mb_init(struct super_block *); extern int ext4_mb_release(struct super_block *); extern ext4_fsblk_t ext4_mb_new_blocks(handle_t *, struct ext4_allocation_request *, int *); @@ -1936,6 +2021,8 @@ extern long ext4_compat_ioctl(struct file *, unsigned int, unsigned long); extern int ext4_ext_migrate(struct inode *); /* namei.c */ +extern int ext4_dirent_csum_verify(struct inode *inode, + struct ext4_dir_entry *dirent); extern int ext4_orphan_add(handle_t *, struct inode *); extern int ext4_orphan_del(handle_t *, struct inode *); extern int ext4_htree_fill_tree(struct file *dir_file, __u32 start_hash, @@ -1950,6 +2037,10 @@ extern int ext4_group_extend(struct super_block *sb, extern int ext4_resize_fs(struct super_block *sb, ext4_fsblk_t n_blocks_count); /* super.c */ +extern int ext4_superblock_csum_verify(struct super_block *sb, + struct ext4_super_block *es); +extern void ext4_superblock_csum_set(struct super_block *sb, + struct ext4_super_block *es); extern void *ext4_kvmalloc(size_t size, gfp_t flags); extern void *ext4_kvzalloc(size_t size, gfp_t flags); extern void ext4_kvfree(void *ptr); @@ -2025,10 +2116,17 @@ extern void ext4_used_dirs_set(struct super_block *sb, struct ext4_group_desc *bg, __u32 count); extern void ext4_itable_unused_set(struct super_block *sb, struct ext4_group_desc *bg, __u32 count); -extern __le16 ext4_group_desc_csum(struct ext4_sb_info *sbi, __u32 group, - struct ext4_group_desc *gdp); -extern int ext4_group_desc_csum_verify(struct ext4_sb_info *sbi, __u32 group, +extern int ext4_group_desc_csum_verify(struct super_block *sb, __u32 group, struct ext4_group_desc *gdp); +extern void ext4_group_desc_csum_set(struct super_block *sb, __u32 group, + struct ext4_group_desc *gdp); + +static inline int ext4_has_group_desc_csum(struct super_block *sb) +{ + return EXT4_HAS_RO_COMPAT_FEATURE(sb, + EXT4_FEATURE_RO_COMPAT_GDT_CSUM | + EXT4_FEATURE_RO_COMPAT_METADATA_CSUM); +} static inline ext4_fsblk_t ext4_blocks_count(struct ext4_super_block *es) { @@ -2225,6 +2323,9 @@ static inline void ext4_unlock_group(struct super_block *sb, static inline void ext4_mark_super_dirty(struct super_block *sb) { + struct ext4_super_block *es = EXT4_SB(sb)->s_es; + + ext4_superblock_csum_set(sb, es); if (EXT4_SB(sb)->s_journal == NULL) sb->s_dirt =1; } @@ -2314,6 +2415,9 @@ extern int ext4_bio_write_page(struct ext4_io_submit *io, /* mmp.c */ extern int ext4_multi_mount_protect(struct super_block *, ext4_fsblk_t); +extern void ext4_mmp_csum_set(struct super_block *sb, struct mmp_struct *mmp); +extern int ext4_mmp_csum_verify(struct super_block *sb, + struct mmp_struct *mmp); /* BH_Uninit flag: blocks are allocated but uninitialized on disk */ enum ext4_state_bits { diff --git a/fs/ext4/ext4_extents.h b/fs/ext4/ext4_extents.h index 0f58b86e3a02..cb1b2c919963 100644 --- a/fs/ext4/ext4_extents.h +++ b/fs/ext4/ext4_extents.h @@ -63,9 +63,22 @@ * ext4_inode has i_block array (60 bytes total). * The first 12 bytes store ext4_extent_header; * the remainder stores an array of ext4_extent. + * For non-inode extent blocks, ext4_extent_tail + * follows the array. */ /* + * This is the extent tail on-disk structure. + * All other extent structures are 12 bytes long. It turns out that + * block_size % 12 >= 4 for at least all powers of 2 greater than 512, which + * covers all valid ext4 block sizes. Therefore, this tail structure can be + * crammed into the end of the block without having to rebalance the tree. + */ +struct ext4_extent_tail { + __le32 et_checksum; /* crc32c(uuid+inum+extent_block) */ +}; + +/* * This is the extent on-disk structure. * It's used at the bottom of the tree. */ @@ -101,6 +114,17 @@ struct ext4_extent_header { #define EXT4_EXT_MAGIC cpu_to_le16(0xf30a) +#define EXT4_EXTENT_TAIL_OFFSET(hdr) \ + (sizeof(struct ext4_extent_header) + \ + (sizeof(struct ext4_extent) * le16_to_cpu((hdr)->eh_max))) + +static inline struct ext4_extent_tail * +find_ext4_extent_tail(struct ext4_extent_header *eh) +{ + return (struct ext4_extent_tail *)(((void *)eh) + + EXT4_EXTENT_TAIL_OFFSET(eh)); +} + /* * Array of ext4_ext_path contains path to some extent. * Creation/lookup routines use it for traversal/splitting/etc. diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c index aca179017582..90f7c2e84db1 100644 --- a/fs/ext4/ext4_jbd2.c +++ b/fs/ext4/ext4_jbd2.c @@ -138,16 +138,23 @@ int __ext4_handle_dirty_metadata(const char *where, unsigned int line, } int __ext4_handle_dirty_super(const char *where, unsigned int line, - handle_t *handle, struct super_block *sb) + handle_t *handle, struct super_block *sb, + int now) { struct buffer_head *bh = EXT4_SB(sb)->s_sbh; int err = 0; if (ext4_handle_valid(handle)) { + ext4_superblock_csum_set(sb, + (struct ext4_super_block *)bh->b_data); err = jbd2_journal_dirty_metadata(handle, bh); if (err) ext4_journal_abort_handle(where, line, __func__, bh, handle, err); + } else if (now) { + ext4_superblock_csum_set(sb, + (struct ext4_super_block *)bh->b_data); + mark_buffer_dirty(bh); } else sb->s_dirt = 1; return err; diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h index 83b20fcf9400..f440e8f1841f 100644 --- a/fs/ext4/ext4_jbd2.h +++ b/fs/ext4/ext4_jbd2.h @@ -213,7 +213,8 @@ int __ext4_handle_dirty_metadata(const char *where, unsigned int line, struct buffer_head *bh); int __ext4_handle_dirty_super(const char *where, unsigned int line, - handle_t *handle, struct super_block *sb); + handle_t *handle, struct super_block *sb, + int now); #define ext4_journal_get_write_access(handle, bh) \ __ext4_journal_get_write_access(__func__, __LINE__, (handle), (bh)) @@ -225,8 +226,10 @@ int __ext4_handle_dirty_super(const char *where, unsigned int line, #define ext4_handle_dirty_metadata(handle, inode, bh) \ __ext4_handle_dirty_metadata(__func__, __LINE__, (handle), (inode), \ (bh)) +#define ext4_handle_dirty_super_now(handle, sb) \ + __ext4_handle_dirty_super(__func__, __LINE__, (handle), (sb), 1) #define ext4_handle_dirty_super(handle, sb) \ - __ext4_handle_dirty_super(__func__, __LINE__, (handle), (sb)) + __ext4_handle_dirty_super(__func__, __LINE__, (handle), (sb), 0) handle_t *ext4_journal_start_sb(struct super_block *sb, int nblocks); int __ext4_journal_stop(const char *where, unsigned int line, handle_t *handle); diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index abcdeab67f52..91341ec6e06a 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -52,6 +52,46 @@ #define EXT4_EXT_MARK_UNINIT1 0x2 /* mark first half uninitialized */ #define EXT4_EXT_MARK_UNINIT2 0x4 /* mark second half uninitialized */ +static __le32 ext4_extent_block_csum(struct inode *inode, + struct ext4_extent_header *eh) +{ + struct ext4_inode_info *ei = EXT4_I(inode); + struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); + __u32 csum; + + csum = ext4_chksum(sbi, ei->i_csum_seed, (__u8 *)eh, + EXT4_EXTENT_TAIL_OFFSET(eh)); + return cpu_to_le32(csum); +} + +static int ext4_extent_block_csum_verify(struct inode *inode, + struct ext4_extent_header *eh) +{ + struct ext4_extent_tail *et; + + if (!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, + EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + return 1; + + et = find_ext4_extent_tail(eh); + if (et->et_checksum != ext4_extent_block_csum(inode, eh)) + return 0; + return 1; +} + +static void ext4_extent_block_csum_set(struct inode *inode, + struct ext4_extent_header *eh) +{ + struct ext4_extent_tail *et; + + if (!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, + EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + return; + + et = find_ext4_extent_tail(eh); + et->et_checksum = ext4_extent_block_csum(inode, eh); +} + static int ext4_split_extent(handle_t *handle, struct inode *inode, struct ext4_ext_path *path, @@ -117,6 +157,7 @@ static int __ext4_ext_dirty(const char *where, unsigned int line, { int err; if (path->p_bh) { + ext4_extent_block_csum_set(inode, ext_block_hdr(path->p_bh)); /* path points to block */ err = __ext4_handle_dirty_metadata(where, line, handle, inode, path->p_bh); @@ -391,6 +432,12 @@ static int __ext4_ext_check(const char *function, unsigned int line, error_msg = "invalid extent entries"; goto corrupted; } + /* Verify checksum on non-root extent tree nodes */ + if (ext_depth(inode) != depth && + !ext4_extent_block_csum_verify(inode, eh)) { + error_msg = "extent tree corrupted"; + goto corrupted; + } return 0; corrupted: @@ -412,6 +459,26 @@ int ext4_ext_check_inode(struct inode *inode) return ext4_ext_check(inode, ext_inode_hdr(inode), ext_depth(inode)); } +static int __ext4_ext_check_block(const char *function, unsigned int line, + struct inode *inode, + struct ext4_extent_header *eh, + int depth, + struct buffer_head *bh) +{ + int ret; + + if (buffer_verified(bh)) + return 0; + ret = ext4_ext_check(inode, eh, depth); + if (ret) + return ret; + set_buffer_verified(bh); + return ret; +} + +#define ext4_ext_check_block(inode, eh, depth, bh) \ + __ext4_ext_check_block(__func__, __LINE__, inode, eh, depth, bh) + #ifdef EXT_DEBUG static void ext4_ext_show_path(struct inode *inode, struct ext4_ext_path *path) { @@ -536,7 +603,7 @@ ext4_ext_binsearch_idx(struct inode *inode, } path->p_idx = l - 1; - ext_debug(" -> %d->%lld ", le32_to_cpu(path->p_idx->ei_block), + ext_debug(" -> %u->%lld ", le32_to_cpu(path->p_idx->ei_block), ext4_idx_pblock(path->p_idx)); #ifdef CHECK_BINSEARCH @@ -668,8 +735,6 @@ ext4_ext_find_extent(struct inode *inode, ext4_lblk_t block, i = depth; /* walk through the tree */ while (i) { - int need_to_validate = 0; - ext_debug("depth %d: num %d, max %d\n", ppos, le16_to_cpu(eh->eh_entries), le16_to_cpu(eh->eh_max)); @@ -688,8 +753,6 @@ ext4_ext_find_extent(struct inode *inode, ext4_lblk_t block, put_bh(bh); goto err; } - /* validate the extent entries */ - need_to_validate = 1; } eh = ext_block_hdr(bh); ppos++; @@ -703,7 +766,7 @@ ext4_ext_find_extent(struct inode *inode, ext4_lblk_t block, path[ppos].p_hdr = eh; i--; - if (need_to_validate && ext4_ext_check(inode, eh, i)) + if (ext4_ext_check_block(inode, eh, i, bh)) goto err; } @@ -914,6 +977,7 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode, le16_add_cpu(&neh->eh_entries, m); } + ext4_extent_block_csum_set(inode, neh); set_buffer_uptodate(bh); unlock_buffer(bh); @@ -992,6 +1056,7 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode, sizeof(struct ext4_extent_idx) * m); le16_add_cpu(&neh->eh_entries, m); } + ext4_extent_block_csum_set(inode, neh); set_buffer_uptodate(bh); unlock_buffer(bh); @@ -1089,6 +1154,7 @@ static int ext4_ext_grow_indepth(handle_t *handle, struct inode *inode, else neh->eh_max = cpu_to_le16(ext4_ext_space_block(inode, 0)); neh->eh_magic = EXT4_EXT_MAGIC; + ext4_extent_block_csum_set(inode, neh); set_buffer_uptodate(bh); unlock_buffer(bh); @@ -1344,7 +1410,8 @@ got_index: return -EIO; eh = ext_block_hdr(bh); /* subtract from p_depth to get proper eh_depth */ - if (ext4_ext_check(inode, eh, path->p_depth - depth)) { + if (ext4_ext_check_block(inode, eh, + path->p_depth - depth, bh)) { put_bh(bh); return -EIO; } @@ -1357,7 +1424,7 @@ got_index: if (bh == NULL) return -EIO; eh = ext_block_hdr(bh); - if (ext4_ext_check(inode, eh, path->p_depth - depth)) { + if (ext4_ext_check_block(inode, eh, path->p_depth - depth, bh)) { put_bh(bh); return -EIO; } @@ -2644,8 +2711,8 @@ cont: err = -EIO; break; } - if (ext4_ext_check(inode, ext_block_hdr(bh), - depth - i - 1)) { + if (ext4_ext_check_block(inode, ext_block_hdr(bh), + depth - i - 1, bh)) { err = -EIO; break; } @@ -4722,8 +4789,8 @@ int ext4_ext_punch_hole(struct file *file, loff_t offset, loff_t length) /* Now release the pages */ if (last_page_offset > first_page_offset) { - truncate_inode_pages_range(mapping, first_page_offset, - last_page_offset-1); + truncate_pagecache_range(inode, first_page_offset, + last_page_offset - 1); } /* finish any pending end_io work */ diff --git a/fs/ext4/file.c b/fs/ext4/file.c index cb70f1812a70..8c7642a00054 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -95,7 +95,7 @@ ext4_file_write(struct kiocb *iocb, const struct iovec *iov, { struct inode *inode = iocb->ki_filp->f_path.dentry->d_inode; int unaligned_aio = 0; - int ret; + ssize_t ret; /* * If we have encountered a bitmap-format file, the size limit |