diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2021-05-01 01:35:30 +0300 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2021-05-01 01:35:30 +0300 |
commit | 9f67672a817ec046f7554a885f0fe0d60e1bf99f (patch) | |
tree | 9d238a2cbfabc479bdb31c5879b8f24415dc3aa2 /fs | |
parent | 6bab076a3d2ff4298483c1a3b77162811b451863 (diff) | |
parent | 6c0912739699d8e4b6a87086401bf3ad3c59502d (diff) | |
download | linux-9f67672a817ec046f7554a885f0fe0d60e1bf99f.tar.xz |
Merge tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4
Pull ext4 updates from Ted Ts'o:
"New features for ext4 this cycle include support for encrypted
casefold, ensure that deleted file names are cleared in directory
blocks by zeroing directory entries when they are unlinked or moved as
part of a hash tree node split. We also improve the block allocator's
performance on a freshly mounted file system by prefetching block
bitmaps.
There are also the usual cleanups and bug fixes, including fixing a
page cache invalidation race when there is mixed buffered and direct
I/O and the block size is less than page size, and allow the dax flag
to be set and cleared on inline directories"
* tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (32 commits)
ext4: wipe ext4_dir_entry2 upon file deletion
ext4: Fix occasional generic/418 failure
fs: fix reporting supported extra file attributes for statx()
ext4: allow the dax flag to be set and cleared on inline directories
ext4: fix debug format string warning
ext4: fix trailing whitespace
ext4: fix various seppling typos
ext4: fix error return code in ext4_fc_perform_commit()
ext4: annotate data race in jbd2_journal_dirty_metadata()
ext4: annotate data race in start_this_handle()
ext4: fix ext4_error_err save negative errno into superblock
ext4: fix error code in ext4_commit_super
ext4: always panic when errors=panic is specified
ext4: delete redundant uptodate check for buffer
ext4: do not set SB_ACTIVE in ext4_orphan_cleanup()
ext4: make prefetch_block_bitmaps default
ext4: add proc files to monitor new structures
ext4: improve cr 0 / cr 1 group scanning
ext4: add MB_NUM_ORDERS macro
ext4: add mballoc stats proc file
...
Diffstat (limited to 'fs')
-rw-r--r-- | fs/ext4/balloc.c | 2 | ||||
-rw-r--r-- | fs/ext4/dir.c | 41 | ||||
-rw-r--r-- | fs/ext4/ext4.h | 107 | ||||
-rw-r--r-- | fs/ext4/fast_commit.c | 8 | ||||
-rw-r--r-- | fs/ext4/file.c | 25 | ||||
-rw-r--r-- | fs/ext4/hash.c | 25 | ||||
-rw-r--r-- | fs/ext4/ialloc.c | 51 | ||||
-rw-r--r-- | fs/ext4/indirect.c | 2 | ||||
-rw-r--r-- | fs/ext4/inline.c | 27 | ||||
-rw-r--r-- | fs/ext4/inode.c | 8 | ||||
-rw-r--r-- | fs/ext4/ioctl.c | 6 | ||||
-rw-r--r-- | fs/ext4/mballoc.c | 592 | ||||
-rw-r--r-- | fs/ext4/mballoc.h | 24 | ||||
-rw-r--r-- | fs/ext4/migrate.c | 6 | ||||
-rw-r--r-- | fs/ext4/mmp.c | 2 | ||||
-rw-r--r-- | fs/ext4/namei.c | 245 | ||||
-rw-r--r-- | fs/ext4/super.c | 116 | ||||
-rw-r--r-- | fs/ext4/sysfs.c | 8 | ||||
-rw-r--r-- | fs/ext4/verity.c | 10 | ||||
-rw-r--r-- | fs/ext4/xattr.c | 2 | ||||
-rw-r--r-- | fs/jbd2/recovery.c | 5 | ||||
-rw-r--r-- | fs/jbd2/transaction.c | 15 | ||||
-rw-r--r-- | fs/stat.c | 8 |
23 files changed, 1096 insertions, 239 deletions
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index 74a5172c2d83..9dc6e74b265c 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -239,7 +239,7 @@ unsigned ext4_free_clusters_after_init(struct super_block *sb, ext4_group_t block_group, struct ext4_group_desc *gdp) { - return num_clusters_in_group(sb, block_group) - + return num_clusters_in_group(sb, block_group) - ext4_num_overhead_clusters(sb, block_group, gdp); } diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c index 5ed870614c8d..ffb295aa891c 100644 --- a/fs/ext4/dir.c +++ b/fs/ext4/dir.c @@ -55,6 +55,18 @@ static int is_dx_dir(struct inode *inode) return 0; } +static bool is_fake_dir_entry(struct ext4_dir_entry_2 *de) +{ + /* Check if . or .. , or skip if namelen is 0 */ + if ((de->name_len > 0) && (de->name_len <= 2) && (de->name[0] == '.') && + (de->name[1] == '.' || de->name[1] == '\0')) + return true; + /* Check if this is a csum entry */ + if (de->file_type == EXT4_FT_DIR_CSUM) + return true; + return false; +} + /* * Return 0 if the directory entry is OK, and 1 if there is a problem * @@ -73,16 +85,20 @@ int __ext4_check_dir_entry(const char *function, unsigned int line, const int rlen = ext4_rec_len_from_disk(de->rec_len, dir->i_sb->s_blocksize); const int next_offset = ((char *) de - buf) + rlen; + bool fake = is_fake_dir_entry(de); + bool has_csum = ext4_has_metadata_csum(dir->i_sb); - if (unlikely(rlen < EXT4_DIR_REC_LEN(1))) + if (unlikely(rlen < ext4_dir_rec_len(1, fake ? NULL : dir))) error_msg = "rec_len is smaller than minimal"; else if (unlikely(rlen % 4 != 0)) error_msg = "rec_len % 4 != 0"; - else if (unlikely(rlen < EXT4_DIR_REC_LEN(de->name_len))) + else if (unlikely(rlen < ext4_dir_rec_len(de->name_len, + fake ? NULL : dir))) error_msg = "rec_len is too small for name_len"; else if (unlikely(next_offset > size)) error_msg = "directory entry overrun"; - else if (unlikely(next_offset > size - EXT4_DIR_REC_LEN(1) && + else if (unlikely(next_offset > size - ext4_dir_rec_len(1, + has_csum ? NULL : dir) && next_offset != size)) error_msg = "directory entry too close to block end"; else if (unlikely(le32_to_cpu(de->inode) > @@ -94,15 +110,15 @@ int __ext4_check_dir_entry(const char *function, unsigned int line, if (filp) ext4_error_file(filp, function, line, bh->b_blocknr, "bad entry in directory: %s - offset=%u, " - "inode=%u, rec_len=%d, name_len=%d, size=%d", + "inode=%u, rec_len=%d, size=%d fake=%d", error_msg, offset, le32_to_cpu(de->inode), - rlen, de->name_len, size); + rlen, size, fake); else ext4_error_inode(dir, function, line, bh->b_blocknr, "bad entry in directory: %s - offset=%u, " - "inode=%u, rec_len=%d, name_len=%d, size=%d", + "inode=%u, rec_len=%d, size=%d fake=%d", error_msg, offset, le32_to_cpu(de->inode), - rlen, de->name_len, size); + rlen, size, fake); return 1; } @@ -124,9 +140,9 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx) if (is_dx_dir(inode)) { err = ext4_dx_readdir(file, ctx); - if (err != ERR_BAD_DX_DIR) { + if (err != ERR_BAD_DX_DIR) return err; - } + /* Can we just clear INDEX flag to ignore htree information? */ if (!ext4_has_metadata_csum(sb)) { /* @@ -224,7 +240,8 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx) * failure will be detected in the * dirent test below. */ if (ext4_rec_len_from_disk(de->rec_len, - sb->s_blocksize) < EXT4_DIR_REC_LEN(1)) + sb->s_blocksize) < ext4_dir_rec_len(1, + inode)) break; i += ext4_rec_len_from_disk(de->rec_len, sb->s_blocksize); @@ -265,7 +282,9 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx) /* Directory is encrypted */ err = fscrypt_fname_disk_to_usr(inode, - 0, 0, &de_name, &fstr); + EXT4_DIRENT_HASH(de), + EXT4_DIRENT_MINOR_HASH(de), + &de_name, &fstr); de_name = fstr; fstr.len = save_len; if (err) diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 18f021c988a1..37002663d521 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -162,7 +162,12 @@ enum SHIFT_DIRECTION { #define EXT4_MB_USE_RESERVED 0x2000 /* Do strict check for free blocks while retrying block allocation */ #define EXT4_MB_STRICT_CHECK 0x4000 - +/* Large fragment size list lookup succeeded at least once for cr = 0 */ +#define EXT4_MB_CR0_OPTIMIZED 0x8000 +/* Avg fragment size rb tree lookup succeeded at least once for cr = 1 */ +#define EXT4_MB_CR1_OPTIMIZED 0x00010000 +/* Perform linear traversal for one group */ +#define EXT4_MB_SEARCH_NEXT_LINEAR 0x00020000 struct ext4_allocation_request { /* target inode for block we're allocating */ struct inode *inode; @@ -1213,7 +1218,7 @@ struct ext4_inode_info { #define EXT4_MOUNT_JOURNAL_CHECKSUM 0x800000 /* Journal checksums */ #define EXT4_MOUNT_JOURNAL_ASYNC_COMMIT 0x1000000 /* Journal Async Commit */ #define EXT4_MOUNT_WARN_ON_ERROR 0x2000000 /* Trigger WARN_ON on error */ -#define EXT4_MOUNT_PREFETCH_BLOCK_BITMAPS 0x4000000 +#define EXT4_MOUNT_NO_PREFETCH_BLOCK_BITMAPS 0x4000000 #define EXT4_MOUNT_DELALLOC 0x8000000 /* Delalloc support */ #define EXT4_MOUNT_DATA_ERR_ABORT 0x10000000 /* Abort on file data write */ #define EXT4_MOUNT_BLOCK_VALIDITY 0x20000000 /* Block validity checking */ @@ -1238,7 +1243,9 @@ struct ext4_inode_info { #define EXT4_MOUNT2_JOURNAL_FAST_COMMIT 0x00000010 /* Journal fast commit */ #define EXT4_MOUNT2_DAX_NEVER 0x00000020 /* Do not allow Direct Access */ #define EXT4_MOUNT2_DAX_INODE 0x00000040 /* For printing options only */ - +#define EXT4_MOUNT2_MB_OPTIMIZE_SCAN 0x00000080 /* Optimize group + * scanning in mballoc + */ #define clear_opt(sb, opt) EXT4_SB(sb)->s_mount_opt &= \ ~EXT4_MOUNT_##opt @@ -1519,9 +1526,14 @@ struct ext4_sb_info { unsigned int s_mb_free_pending; struct list_head s_freed_data_list; /* List of blocks to be freed after commit completed */ + struct rb_root s_mb_avg_fragment_size_root; + rwlock_t s_mb_rb_lock; + struct list_head *s_mb_largest_free_orders; + rwlock_t *s_mb_largest_free_orders_locks; /* tunables */ unsigned long s_stripe; + unsigned int s_mb_max_linear_groups; unsigned int s_mb_stream_request; unsigned int s_mb_max_to_scan; unsigned int s_mb_min_to_scan; @@ -1541,12 +1553,17 @@ struct ext4_sb_info { atomic_t s_bal_success; /* we found long enough chunks */ atomic_t s_bal_allocated; /* in blocks */ atomic_t s_bal_ex_scanned; /* total extents scanned */ + atomic_t s_bal_groups_scanned; /* number of groups scanned */ atomic_t s_bal_goals; /* goal hits */ atomic_t s_bal_breaks; /* too long searches */ atomic_t s_bal_2orders; /* 2^order hits */ - spinlock_t s_bal_lock; - unsigned long s_mb_buddies_generated; - unsigned long long s_mb_generation_time; + atomic_t s_bal_cr0_bad_suggestions; + atomic_t s_bal_cr1_bad_suggestions; + atomic64_t s_bal_cX_groups_considered[4]; + atomic64_t s_bal_cX_hits[4]; + atomic64_t s_bal_cX_failed[4]; /* cX loop didn't find blocks */ + atomic_t s_mb_buddies_generated; /* number of buddies generated */ + atomic64_t s_mb_generation_time; atomic_t s_mb_lost_chunks; atomic_t s_mb_preallocated; atomic_t s_mb_discarded; @@ -2187,6 +2204,17 @@ struct ext4_dir_entry { char name[EXT4_NAME_LEN]; /* File name */ }; + +/* + * Encrypted Casefolded entries require saving the hash on disk. This structure + * followed ext4_dir_entry_2's name[name_len] at the next 4 byte aligned + * boundary. + */ +struct ext4_dir_entry_hash { + __le32 hash; + __le32 minor_hash; +}; + /* * The new version of the directory entry. Since EXT4 structures are * stored in intel byte order, and the name_len field could never be @@ -2202,6 +2230,22 @@ struct ext4_dir_entry_2 { }; /* + * Access the hashes at the end of ext4_dir_entry_2 + */ +#define EXT4_DIRENT_HASHES(entry) \ + ((struct ext4_dir_entry_hash *) \ + (((void *)(entry)) + \ + ((8 + (entry)->name_len + EXT4_DIR_ROUND) & ~EXT4_DIR_ROUND))) +#define EXT4_DIRENT_HASH(entry) le32_to_cpu(EXT4_DIRENT_HASHES(de)->hash) +#define EXT4_DIRENT_MINOR_HASH(entry) \ + le32_to_cpu(EXT4_DIRENT_HASHES(de)->minor_hash) + +static inline bool ext4_hash_in_dirent(const struct inode *inode) +{ + return IS_CASEFOLDED(inode) && IS_ENCRYPTED(inode); +} + +/* * This is a bogus directory entry at the end of each leaf block that * records checksums. */ @@ -2242,11 +2286,25 @@ struct ext4_dir_entry_tail { */ #define EXT4_DIR_PAD 4 #define EXT4_DIR_ROUND (EXT4_DIR_PAD - 1) -#define EXT4_DIR_REC_LEN(name_len) (((name_len) + 8 + EXT4_DIR_ROUND) & \ - ~EXT4_DIR_ROUND) #define EXT4_MAX_REC_LEN ((1<<16)-1) /* + * The rec_len is dependent on the type of directory. Directories that are + * casefolded and encrypted need to store the hash as well, so we add room for + * ext4_extended_dir_entry_2. For all entries related to '.' or '..' you should + * pass NULL for dir, as those entries do not use the extra fields. + */ +static inline unsigned int ext4_dir_rec_len(__u8 name_len, + const struct inode *dir) +{ + int rec_len = (name_len + 8 + EXT4_DIR_ROUND); + + if (dir && ext4_hash_in_dirent(dir)) + rec_len += sizeof(struct ext4_dir_entry_hash); + return (rec_len & ~EXT4_DIR_ROUND); +} + +/* * If we ever get support for fs block sizes > page_size, we'll need * to remove the #if statements in the next two functions... */ @@ -2302,6 +2360,7 @@ static inline __le16 ext4_rec_len_to_disk(unsigned len, unsigned blocksize) #define DX_HASH_LEGACY_UNSIGNED 3 #define DX_HASH_HALF_MD4_UNSIGNED 4 #define DX_HASH_TEA_UNSIGNED 5 +#define DX_HASH_SIPHASH 6 static inline u32 ext4_chksum(struct ext4_sb_info *sbi, u32 crc, const void *address, unsigned int length) @@ -2356,6 +2415,7 @@ struct ext4_filename { }; #define fname_name(p) ((p)->disk_name.name) +#define fname_usr_name(p) ((p)->usr_fname->name) #define fname_len(p) ((p)->disk_name.len) /* @@ -2586,9 +2646,9 @@ extern unsigned ext4_free_clusters_after_init(struct super_block *sb, ext4_fsblk_t ext4_inode_to_goal_block(struct inode *); #ifdef CONFIG_UNICODE -extern void ext4_fname_setup_ci_filename(struct inode *dir, +extern int ext4_fname_setup_ci_filename(struct inode *dir, const struct qstr *iname, - struct fscrypt_str *fname); + struct ext4_filename *fname); #endif #ifdef CONFIG_FS_ENCRYPTION @@ -2619,9 +2679,9 @@ static inline int ext4_fname_setup_filename(struct inode *dir, ext4_fname_from_fscrypt_name(fname, &name); #ifdef CONFIG_UNICODE - ext4_fname_setup_ci_filename(dir, iname, &fname->cf_name); + err = ext4_fname_setup_ci_filename(dir, iname, fname); #endif - return 0; + return err; } static inline int ext4_fname_prepare_lookup(struct inode *dir, @@ -2638,9 +2698,9 @@ static inline int ext4_fname_prepare_lookup(struct inode *dir, ext4_fname_from_fscrypt_name(fname, &name); #ifdef CONFIG_UNICODE - ext4_fname_setup_ci_filename(dir, &dentry->d_name, &fname->cf_name); + err = ext4_fname_setup_ci_filename(dir, &dentry->d_name, fname); #endif - return 0; + return err; } static inline void ext4_fname_free_filename(struct ext4_filename *fname) @@ -2665,15 +2725,16 @@ static inline int ext4_fname_setup_filename(struct inode *dir, int lookup, struct ext4_filename *fname) { + int err = 0; fname->usr_fname = iname; fname->disk_name.name = (unsigned char *) iname->name; fname->disk_name.len = iname->len; #ifdef CONFIG_UNICODE - ext4_fname_setup_ci_filename(dir, iname, &fname->cf_name); + err = ext4_fname_setup_ci_filename(dir, iname, fname); #endif - return 0; + return err; } static inline int ext4_fname_prepare_lookup(struct inode *dir, @@ -2698,9 +2759,9 @@ extern int __ext4_check_dir_entry(const char *, unsigned int, struct inode *, struct ext4_dir_entry_2 *, struct buffer_head *, char *, int, unsigned int); -#define ext4_check_dir_entry(dir, filp, de, bh, buf, size, offset) \ +#define ext4_check_dir_entry(dir, filp, de, bh, buf, size, offset) \ unlikely(__ext4_check_dir_entry(__func__, __LINE__, (dir), (filp), \ - (de), (bh), (buf), (size), (offset))) + (de), (bh), (buf), (size), (offset))) extern int ext4_htree_store_dirent(struct file *dir_file, __u32 hash, __u32 minor_hash, struct ext4_dir_entry_2 *dirent, @@ -2711,7 +2772,7 @@ extern int ext4_find_dest_de(struct inode *dir, struct inode *inode, void *buf, int buf_size, struct ext4_filename *fname, struct ext4_dir_entry_2 **dest_de); -void ext4_insert_dentry(struct inode *inode, +void ext4_insert_dentry(struct inode *dir, struct inode *inode, struct ext4_dir_entry_2 *de, int buf_size, struct ext4_filename *fname); @@ -2802,8 +2863,10 @@ int __init ext4_fc_init_dentry_cache(void); /* mballoc.c */ extern const struct seq_operations ext4_mb_seq_groups_ops; +extern const struct seq_operations ext4_mb_seq_structs_summary_ops; extern long ext4_mb_stats; extern long ext4_mb_max_to_scan; +extern int ext4_seq_mb_stats_show(struct seq_file *seq, void *offset); 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 *, @@ -3306,11 +3369,14 @@ struct ext4_group_info { ext4_grpblk_t bb_free; /* total free blocks */ ext4_grpblk_t bb_fragments; /* nr of freespace fragments */ ext4_grpblk_t bb_largest_free_order;/* order of largest frag in BG */ + ext4_group_t bb_group; /* Group number */ struct list_head bb_prealloc_list; #ifdef DOUBLE_CHECK void *bb_bitmap; #endif struct rw_semaphore alloc_sem; + struct rb_node bb_avg_fragment_size_rb; + struct list_head bb_largest_free_order_node; ext4_grpblk_t bb_counters[]; /* Nr of free power-of-two-block * regions, index is order. * bb_counters[3] = 5 means @@ -3513,9 +3579,6 @@ extern void ext4_initialize_dirent_tail(struct buffer_head *bh, unsigned int blocksize); extern int ext4_handle_dirty_dirblock(handle_t *handle, struct inode *inode, struct buffer_head *bh); -extern int ext4_ci_compare(const struct inode *parent, - const struct qstr *fname, - const struct qstr *entry, bool quick); extern int __ext4_unlink(handle_t *handle, struct inode *dir, const struct qstr *d_name, struct inode *inode); extern int __ext4_link(struct inode *dir, struct inode *inode, diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c index 7541d0b5d706..f98ca4f37ef6 100644 --- a/fs/ext4/fast_commit.c +++ b/fs/ext4/fast_commit.c @@ -66,7 +66,7 @@ * Fast Commit Ineligibility * ------------------------- * Not all operations are supported by fast commits today (e.g extended - * attributes). Fast commit ineligiblity is marked by calling one of the + * attributes). Fast commit ineligibility is marked by calling one of the * two following functions: * * - ext4_fc_mark_ineligible(): This makes next fast commit operation to fall @@ -1088,8 +1088,10 @@ static int ext4_fc_perform_commit(journal_t *journal) head.fc_tid = cpu_to_le32( sbi->s_journal->j_running_transaction->t_tid); if (!ext4_fc_add_tlv(sb, EXT4_FC_TAG_HEAD, sizeof(head), - (u8 *)&head, &crc)) + (u8 *)&head, &crc)) { + ret = -ENOSPC; goto out; + } } spin_lock(&sbi->s_fc_lock); @@ -1734,7 +1736,7 @@ static int ext4_fc_replay_add_range(struct super_block *sb, } /* Range is mapped and needs a state change */ - jbd_debug(1, "Converting from %d to %d %lld", + jbd_debug(1, "Converting from %ld to %d %lld", map.m_flags & EXT4_MAP_UNWRITTEN, ext4_ext_is_unwritten(ex), map.m_pblk); ret = ext4_ext_replay_update_ex(inode, cur, map.m_len, diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 5332dd3ea7e2..816dedcbd541 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -371,15 +371,32 @@ truncate: static int ext4_dio_write_end_io(struct kiocb *iocb, ssize_t size, int error, unsigned int flags) { - loff_t offset = iocb->ki_pos; + loff_t pos = iocb->ki_pos; struct inode *inode = file_inode(iocb->ki_filp); if (error) return error; - if (size && flags & IOMAP_DIO_UNWRITTEN) - return ext4_convert_unwritten_extents(NULL, inode, - offset, size); + if (size && flags & IOMAP_DIO_UNWRITTEN) { + error = ext4_convert_unwritten_extents(NULL, inode, pos, size); + if (error < 0) + return error; + } + /* + * If we are extending the file, we have to update i_size here before + * page cache gets invalidated in iomap_dio_rw(). Otherwise racing + * buffered reads could zero out too much from page cache pages. Update + * of on-disk size will happen later in ext4_dio_write_iter() where + * we have enough information to also perform orphan list handling etc. + * Note that we perform all extending writes synchronously under + * i_rwsem held exclusively so i_size update is safe here in that case. + * If the write was not extending, we cannot see pos > i_size here + * because operations reducing i_size like truncate wait for all + * outstanding DIO before updating i_size. + */ + pos += size; + if (pos > i_size_read(inode)) + i_size_write(inode, pos); return 0; } diff --git a/fs/ext4/hash.c b/fs/ext4/hash.c index a92eb79de0cc..f34f4176c1e7 100644 --- a/fs/ext4/hash.c +++ b/fs/ext4/hash.c @@ -197,7 +197,7 @@ static void str2hashbuf_unsigned(const char *msg, int len, __u32 *buf, int num) * represented, and whether or not the returned hash is 32 bits or 64 * bits. 32 bit hashes will return 0 for the minor hash. */ -static int __ext4fs_dirhash(const char *name, int len, +static int __ext4fs_dirhash(const struct inode *dir, const char *name, int len, struct dx_hash_info *hinfo) { __u32 hash; @@ -259,6 +259,22 @@ static int __ext4fs_dirhash(const char *name, int len, hash = buf[0]; minor_hash = buf[1]; break; + case DX_HASH_SIPHASH: + { + struct qstr qname = QSTR_INIT(name, len); + __u64 combined_hash; + + if (fscrypt_has_encryption_key(dir)) { + combined_hash = fscrypt_fname_siphash(dir, &qname); + } else { + ext4_warning_inode(dir, "Siphash requires key"); + return -1; + } + + hash = (__u32)(combined_hash >> 32); + minor_hash = (__u32)combined_hash; + break; + } default: hinfo->hash = 0; return -1; @@ -280,7 +296,8 @@ int ext4fs_dirhash(const struct inode *dir, const char *name, int len, unsigned char *buff; struct qstr qstr = {.name = name, .len = len }; - if (len && IS_CASEFOLDED(dir) && um) { + if (len && IS_CASEFOLDED(dir) && um && + (!IS_ENCRYPTED(dir) || fscrypt_has_encryption_key(dir))) { buff = kzalloc(sizeof(char) * PATH_MAX, GFP_KERNEL); if (!buff) return -ENOMEM; @@ -291,12 +308,12 @@ int ext4fs_dirhash(const struct inode *dir, const char *name, int len, goto opaque_seq; } - r = __ext4fs_dirhash(buff, dlen, hinfo); + r = __ext4fs_dirhash(dir, buff, dlen, hinfo); kfree(buff); return r; } opaque_seq: #endif - return __ext4fs_dirhash(name, len, hinfo); + return __ext4fs_dirhash(dir, name, len, hinfo); } diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index 755a68bb7e22..81a17a3cd80e 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -1292,7 +1292,8 @@ got: ei->i_extra_isize = sbi->s_want_extra_isize; ei->i_inline_off = 0; - if (ext4_has_feature_inline_data(sb)) + if (ext4_has_feature_inline_data(sb) && + (!(ei->i_flags & EXT4_DAX_FL) || S_ISDIR(mode))) ext4_set_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA); ret = inode; err = dquot_alloc_inode(inode); @@ -1513,6 +1514,7 @@ int ext4_init_inode_table(struct super_block *sb, ext4_group_t group, handle_t *handle; ext4_fsblk_t blk; int num, ret = 0, used_blks = 0; + unsigned long used_inos = 0; /* This should not happen, but just to be sure check this */ if (sb_rdonly(sb)) { @@ -1543,22 +1545,37 @@ int ext4_init_inode_table(struct super_block *sb, ext4_group_t group, * used inodes so we need to skip blocks with used inodes in * inode table. */ - if (!(gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT))) - used_blks = DIV_ROUND_UP((EXT4_INODES_PER_GROUP(sb) - - ext4_itable_unused_count(sb, gdp)), - sbi->s_inodes_per_block); - - if ((used_blks < 0) || (used_blks > sbi->s_itb_per_group) || - ((group == 0) && ((EXT4_INODES_PER_GROUP(sb) - - ext4_itable_unused_count(sb, gdp)) < - EXT4_FIRST_INO(sb)))) { - ext4_error(sb, "Something is wrong with group %u: " - "used itable blocks: %d; " - "itable unused count: %u", - group, used_blks, - ext4_itable_unused_count(sb, gdp)); - ret = 1; - goto err_out; + if (!(gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT))) { + used_inos = EXT4_INODES_PER_GROUP(sb) - + ext4_itable_unused_count(sb, gdp); + used_blks = DIV_ROUND_UP(used_inos, sbi->s_inodes_per_block); + + /* Bogus inode unused count? */ + if (used_blks < 0 || used_blks > sbi->s_itb_per_group) { + ext4_error(sb, "Something is wrong with group %u: " + "used itable blocks: %d; " + "itable unused count: %u", + group, used_blks, + ext4_itable_unused_count(sb, gdp)); + ret = 1; + goto err_out; + } + + used_inos += group * EXT4_INODES_PER_GROUP(sb); + /* + * Are there some uninitialized inodes in the inode table + * before the first normal inode? + */ + if ((used_blks != sbi->s_itb_per_group) && + (used_inos < EXT4_FIRST_INO(sb))) { + ext4_error(sb, "Something is wrong with group %u: " + "itable unused count: %u; " + "itables initialized count: %ld", + group, ext4_itable_unused_count(sb, gdp), + used_inos); + ret = 1; + goto err_out; + } } blk = ext4_inode_table(sb, gdp) + used_blks; diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c index 1223a18c3ff9..a7bc6ad656a9 100644 --- a/fs/ext4/indirect.c +++ b/fs/ext4/indirect.c @@ -705,7 +705,7 @@ static int ext4_ind_trunc_restart_fn(handle_t *handle, struct inode *inode, /* * Truncate transactions can be complex and absolutely huge. So we need to - * be able to restart the transaction at a conventient checkpoint to make + * be able to restart the transaction at a convenient checkpoint to make * sure we don't overflow the journal. * * Try to extend this transaction for the purposes of truncation. If diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index b41512d1badc..3cf01629010d 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -795,7 +795,7 @@ ext4_journalled_write_inline_data(struct inode *inode, * clear the inode state safely. * 2. The inode has inline data, then we need to read the data, make it * update and dirty so that ext4_da_writepages can handle it. We don't - * need to start the journal since the file's metatdata isn't changed now. + * need to start the journal since the file's metadata isn't changed now. */ static int ext4_da_convert_inline_data_to_extent(struct address_space *mapping, struct inode *inode, @@ -1031,7 +1031,7 @@ static int ext4_add_dirent_to_inline(handle_t *handle, err = ext4_journal_get_write_access(handle, iloc->bh); if (err) return err; - ext4_insert_dentry(inode, de, inline_size, fname); + ext4_insert_dentry(dir, inode, de, inline_size, fname); ext4_show_inline_dir(dir, iloc->bh, inline_start, inline_size); @@ -1100,7 +1100,7 @@ static int ext4_update_inline_dir(handle_t *handle, struct inode *dir, int old_size = EXT4_I(dir)->i_inline_size - EXT4_MIN_INLINE_DATA_SIZE; int new_size = get_max_inline_xattr_value_size(dir, iloc); - if (new_size - old_size <= EXT4_DIR_REC_LEN(1)) + if (new_size - old_size <= ext4_dir_rec_len(1, NULL)) return -ENOSPC; ret = ext4_update_inline_data(handle, dir, @@ -1380,8 +1380,8 @@ int ext4_inlinedir_to_tree(struct file *dir_file, fake.name_len = 1; strcpy(fake.name, "."); fake.rec_len = ext4_rec_len_to_disk( - EXT4_DIR_REC_LEN(fake.name_len), - inline_size); + ext4_dir_rec_len(fake.name_len, NULL), + inline_size); ext4_set_de_type(inode->i_sb, &fake, S_IFDIR); de = &fake; pos = EXT4_INLINE_DOTDOT_OFFSET; @@ -1390,8 +1390,8 @@ int ext4_inlinedir_to_tree(struct file *dir_file, fake.name_len = 2; strcpy(fake.name, ".."); fake.rec_len = ext4_rec_len_to_disk( - EXT4_DIR_REC_LEN(fake.name_len), - inline_size); + ext4_dir_rec_len(fake.name_len, NULL), + inline_size); ext4_set_de_type(inode->i_sb, &fake, S_IFDIR); de = &fake; pos = EXT4_INLINE_DOTDOT_SIZE; @@ -1406,7 +1406,12 @@ int ext4_inlinedir_to_tree(struct file *dir_file, } } - ext4fs_dirhash(dir, de->name, de->name_len, hinfo); + if (ext4_hash_in_dirent(dir)) { + hinfo->hash = EXT4_DIRENT_HASH(de); + hinfo->minor_hash = EXT4_DIRENT_MINOR_HASH(de); + } else { + ext4fs_dirhash(dir, de->name, de->name_len, hinfo); + } if ((hinfo->hash < start_hash) || ((hinfo->hash == start_hash) && (hinfo->minor_hash < start_minor_hash))) @@ -1488,8 +1493,8 @@ int ext4_read_inline_dir(struct file *file, * So we will use extra_offset and extra_size to indicate them * during the inline dir iteration. */ - dotdot_offset = EXT4_DIR_REC_LEN(1); - dotdot_size = dotdot_offset + EXT4_DIR_REC_LEN(2); + dotdot_offset = ext4_dir_rec_len(1, NULL); + dotdot_size = dotdot_offset + ext4_dir_rec_len(2, NULL); extra_offset = dotdot_size - EXT4_INLINE_DOTDOT_SIZE; extra_size = extra_offset + inline_size; @@ -1524,7 +1529,7 @@ int ext4_read_inline_dir(struct file *file, * failure will be detected in the * dirent test below. */ if (ext4_rec_len_from_disk(de->rec_len, extra_size) - < EXT4_DIR_REC_LEN(1)) + < ext4_dir_rec_len(1, NULL)) break; i += ext4_rec_len_from_disk(de->rec_len, extra_size); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 0948a43f1b3d..fe6045a46599 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1066,8 +1066,7 @@ static int ext4_block_write_begin(struct page *page, loff_t pos, unsigned len, block_end = block_start + blocksize; if (block_end <= from || block_start >= to) { if (PageUptodate(page)) { - if (!buffer_uptodate(bh)) - set_buffer_uptodate(bh); + set_buffer_uptodate(bh); } continue; } @@ -1092,8 +1091,7 @@ static int ext4_block_write_begin(struct page *page, loff_t pos, unsigned len, } } if (PageUptodate(page)) { - if (!buffer_uptodate(bh)) - set_buffer_uptodate(bh); + set_buffer_uptodate(bh); continue; } if (!buffer_uptodate(bh) && !buffer_delay(bh) && @@ -3824,7 +3822,7 @@ unlock: * starting from file offset 'from'. The range to be zero'd must * be contained with in one block. If the specified range exceeds * the end of the block it will be shortened to end of the block - * that cooresponds to 'from' + * that corresponds to 'from' */ static int ext4_block_zero_page_range(handle_t *handle, struct address_space *mapping, loff_t from, loff_t length) diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index e9b0a1fa2ba8..31627f7dc5cd 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -316,6 +316,12 @@ static void ext4_dax_dontcache(struct inode *inode, unsigned int flags) static bool dax_compatible(struct inode *inode, unsigned int oldflags, unsigned int flags) { + /* Allow the DAX flag to be changed on inline directories */ + if (S_ISDIR(inode->i_mode)) { + flags &= ~EXT4_INLINE_DATA_FL; + oldflags &= ~EXT4_INLINE_DATA_FL; + } + if (flags & EXT4_DAX_FL) { if ((oldflags & EXT4_DAX_MUT_EXCL) || ext4_test_inode_state(inode, diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index a02fadf4fc84..3239e6669e84 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -127,11 +127,50 @@ * smallest multiple of the stripe value (sbi->s_stripe) which is * greater than the default mb_group_prealloc. * + * If "mb_optimize_scan" mount option is set, we maintain in memory group info + * structures in two data structures: + * + * 1) Array of largest free order lists (sbi->s_mb_largest_free_orders) + * + * Locking: sbi->s_mb_largest_free_orders_locks(array of rw locks) + * + * This is an array of lists where the index in the array represents the + * largest free order in the buddy bitmap of the participating group infos of + * that list. So, there are exactly MB_NUM_ORDERS(sb) (which means total + * number of buddy bitmap orders possible) number of lists. Group-infos are + * placed in appropriate lists. + * + * 2) Average fragment size rb tree (sbi->s_mb_avg_fragment_size_root) + * + * Locking: sbi->s_mb_rb_lock (rwlock) + * + * This is a red black tree consisting of group infos and the tree is sorted + * by average fragment sizes (which is calculated as ext4_group_info->bb_free + * / ext4_group_info->bb_fragments). + * + * When "mb_optimize_scan" mount option is set, mballoc consults the above data + * structures to decide the order in which groups are to be traversed for + * fulfilling an allocation request. + * + * At CR = 0, we look for groups which have the largest_free_order >= the order + * of the request. We directly look at the largest free order list in the data + * structure (1) above where largest_free_order = order of the request. If that + * list is empty, we look at remaining list in the increasing order of + * largest_free_order. This allows us to perform CR = 0 lookup in O(1) time. + * + * At CR = 1, we only consider groups where average fragment size > request + * size. So, we lookup a group which has average fragment size just above or + * equal to request size using our rb tree (data structure 2) in O(log N) time. + * + * If "mb_optimize_scan" mount option is not set, mballoc traverses groups in + * linear order which requires O(N) search time for each CR 0 and CR 1 phase. + * * The regular allocator (using the buddy cache) supports a few tunables. * * /sys/fs/ext4/<partition>/mb_min_to_scan * /sys/fs/ext4/<partition>/mb_max_to_scan * /sys/fs/ext4/<partition>/mb_order2_req + * /sys/fs/ext4/<partition>/mb_linear_limit * * The regular allocator uses buddy scan only if the request len is power of * 2 blocks and the order of allocation is >= sbi->s_mb_order2_reqs. The @@ -149,6 +188,16 @@ * can be used for allocation. ext4_mb_good_group explains how the groups are * checked. * + * When "mb_optimize_scan" is turned on, as mentioned above, the groups may not + * get traversed linearly. That may result in subsequent allocations being not + * close to each other. And so, the underlying device may get filled up in a + * non-linear fashion. While that may not matter on non-rotational devices, for + * rotational devices that may result in higher seek times. "mb_linear_limit" + * tells mballoc how many groups mballoc should search linearly before + * performing consulting above data structures for more efficient lookups. For + * non rotational devices, this value defaults to 0 and for rotational devices + * this is set to MB_DEFAULT_LINEAR_LIMIT. + * * Both the prealloc space are getting populated as above. So for the first * request we will hit the buddy cache which will result in this prealloc * space getting filled. The prealloc space is then later used for the @@ -299,6 +348,8 @@ * - bitlock on a group (group) * - object (inode/locality) (object) * - per-pa lock (pa) + * - cr0 lists lock (cr0) + * - cr1 tree lock (cr1) * * Paths: * - new pa @@ -328,6 +379,9 @@ * group * object * + * - allocation path (ext4_mb_regular_allocator) + * group + * cr0/cr1 */ static struct kmem_cache *ext4_pspace_cachep; static struct kmem_cache *ext4_ac_cachep; @@ -351,6 +405,9 @@ static void ext4_mb_generate_from_freelist(struct super_block *sb, void *bitmap, ext4_group_t group); static void ext4_mb_new_preallocation(struct ext4_allocation_context *ac); +static bool ext4_mb_good_group(struct ext4_allocation_context *ac, + ext4_group_t group, int cr); + /* * The algorithm using this percpu seq counter goes below: * 1. We sample the percpu discard_pa_seq counter before trying for block @@ -744,6 +801,269 @@ static void ext4_mb_mark_free_simple(struct super_block *sb, } } +static void ext4_mb_rb_insert(struct rb_root *root, struct rb_node *new, + int (*cmp)(struct rb_node *, struct rb_node *)) +{ + struct rb_node **iter = &root->rb_node, *parent = NULL; + + while (*iter) { + parent = *iter; + if (cmp(new, *iter) > 0) + iter = &((*iter)->rb_left); + else + iter = &((*iter)->rb_right); + } + + rb_link_node(new, parent, iter); + rb_insert_color(new, root); +} + +static int +ext4_mb_avg_fragment_size_cmp(struct rb_node *rb1, struct rb_node *rb2) +{ + struct ext4_group_info *grp1 = rb_entry(rb1, + struct ext4_group_info, + bb_avg_fragment_size_rb); + struct ext4_group_info *grp2 = rb_entry(rb2, + struct ext4_group_info, + bb_avg_fragment_size_rb); + int num_frags_1, num_frags_2; + + num_frags_1 = grp1->bb_fragments ? + grp1->bb_free / grp1->bb_fragments : 0; + num_frags_2 = grp2->bb_fragments ? + grp2->bb_free / grp2->bb_fragments : 0; + + return (num_frags_2 - num_frags_1); +} + +/* + * Reinsert grpinfo into the avg_fragment_size tree with new average + * fragment size. + */ +static void +mb_update_avg_fragment_size(struct super_block *sb, struct ext4_group_info *grp) +{ + struct ext4_sb_info *sbi = EXT4_SB(sb); + + if (!test_opt2(sb, MB_OPTIMIZE_SCAN) || grp->bb_free == 0) + return; + + write_lock(&sbi->s_mb_rb_lock); + if (!RB_EMPTY_NODE(&grp->bb_avg_fragment_size_rb)) { + rb_erase(&grp->bb_avg_fragment_size_rb, + &sbi->s_mb_avg_fragment_size_root); + RB_CLEAR_NODE(&grp->bb_avg_fragment_size_rb); + } + + ext4_mb_rb_insert(&sbi->s_mb_avg_fragment_size_root, + &grp->bb_avg_fragment_size_rb, + ext4_mb_avg_fragment_size_cmp); + write_unlock(&sbi->s_mb_rb_lock); +} + +/* + * Choose next group by traversing largest_free_order lists. Updates *new_cr if + * cr level needs an update. + */ +static void ext4_mb_choose_next_group_cr0(struct ext4_allocation_context *ac, + int *new_cr, ext4_group_t *group, ext4_group_t ngroups) +{ + struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); + struct ext4_group_info *iter, *grp; + int i; + + if (ac->ac_status == AC_STATUS_FOUND) + return; + + if (unlikely(sbi->s_mb_stats && ac->ac_flags & EXT4_MB_CR0_OPTIMIZED)) + atomic_inc(&sbi->s_bal_cr0_bad_suggestions); + + grp = NULL; + for (i = ac->ac_2order; i < MB_NUM_ORDERS(ac->ac_sb); i++) { + if (list_empty(&sbi->s_mb_largest_free_orders[i])) + continue; + read_lock(&sbi->s_mb_largest_free_orders_locks[i]); + if (list_empty(&sbi->s_mb_largest_free_orders[i])) { + read_unlock(&sbi->s_mb_largest_free_orders_locks[i]); + continue; + } + grp = NULL; + list_for_each_entry(iter, &sbi->s_mb_largest_free_orders[i], + bb_largest_free_order_node) { + if (sbi->s_mb_stats) + atomic64_inc(&sbi->s_bal_cX_groups_considered[0]); + if (likely(ext4_mb_good_group(ac, iter->bb_group, 0))) { + grp = iter; + break; + } + } + read_unlock(&sbi->s_mb_largest_free_orders_locks[i]); + if (grp) + break; + } + + if (!grp) { + /* Increment cr and search again */ + *new_cr = 1; + } else { + *group = grp->bb_group; + ac->ac_last_optimal_group = *group; + ac->ac_flags |= EXT4_MB_CR0_OPTIMIZED; + } +} + +/* + * Choose next group by traversing average fragment size tree. Updates *new_cr + * if cr lvel needs an update. Sets EXT4_MB_SEARCH_NEXT_LINEAR to indicate that + * the linear search should continue for one iteration since there's lock + * contention on the rb tree lock. + */ +static void ext4_mb_choose_next_group_cr1(struct ext4_allocation_context *ac, + int *new_cr, ext4_group_t *group, ext4_group_t ngroups) +{ + struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); + int avg_fragment_size, best_so_far; + struct rb_node *node, *found; + struct ext4_group_info *grp; + + /* + * If there is contention on the lock, instead of waiting for the lock + * to become available, just continue searching lineraly. We'll resume + * our rb tree search later starting at ac->ac_last_optimal_group. + */ + if (!read_trylock(&sbi->s_mb_rb_lock)) { + ac->ac_flags |= EXT4_MB_SEARCH_NEXT_LINEAR; + return; + } + + if (unlikely(ac->ac_flags & EXT4_MB_CR1_OPTIMIZED)) { + if (sbi->s_mb_stats) + atomic_inc(&sbi->s_bal_cr1_bad_suggestions); + /* We have found something at CR 1 in the past */ + grp = ext4_get_group_info(ac->ac_sb, ac->ac_last_optimal_group); + for (found = rb_next(&grp->bb_avg_fragment_size_rb); found != NULL; + found = rb_next(found)) { + grp = rb_entry(found, struct ext4_group_info, + bb_avg_fragment_size_rb); + if (sbi->s_mb_stats) + atomic64_inc(&sbi->s_bal_cX_groups_considered[1]); + if (likely(ext4_mb_good_group(ac, grp->bb_group, 1))) + break; + } + goto done; + } + + node = sbi->s_mb_avg_fragment_size_root.rb_node; + best_so_far = 0; + found = NULL; + + while (node) { + grp = rb_entry(node, struct ext4_group_info, + bb_avg_fragment_size_rb); + avg_fragment_size = 0; + if (ext4_mb_good_group(ac, grp->bb_group, 1)) { + avg_fragment_size = grp->bb_fragments ? + grp->bb_free / grp->bb_fragments : 0; + if (!best_so_far || avg_fragment_size < best_so_far) { + best_so_far = avg_fragment_size; + found = node; + } + } + if (avg_fragment_size > ac->ac_g_ex.fe_len) + node = node->rb_right; + else + node = node->rb_left; + } + +done: + if (found) { + grp = rb_entry(found, struct ext4_group_info, + bb_avg_fragment_size_rb); + *group = grp->bb_group; + ac->ac_flags |= EXT4_MB_CR1_OPTIMIZED; + } else { + *new_cr = 2; + } + + read_unlock(&sbi->s_mb_rb_lock); + ac->ac_last_optimal_group = *group; +} + +static inline int should_optimize_scan(struct ext4_allocation_context *ac) +{ + if (unlikely(!test_opt2(ac->ac_sb, MB_OPTIMIZE_SCAN))) + return 0; + if (ac->ac_criteria >= 2) + return 0; + if (ext4_test_inode_flag(ac->ac_inode, EXT4_INODE_EXTENTS)) + return 0; + return 1; +} + +/* + * Return next linear group for allocation. If linear traversal should not be + * performed, this function just returns the same group + */ +static int +next_linear_group(struct ext4_allocation_context *ac, int group, int ngroups) +{ + if (!should_optimize_scan(ac)) + goto inc_and_return; + + if (ac->ac_groups_linear_remaining) { + ac->ac_groups_linear_remaining--; + goto inc_and_return; + } + + if (ac->ac_flags & EXT4_MB_SEARCH_NEXT_LINEAR) { + ac->ac_flags &= ~EXT4_MB_SEARCH_NEXT_LINEAR; + goto inc_and_return; + } + + return group; +inc_and_return: + /* + * Artificially restricted ngroups for non-extent + * files makes group > ngroups possible on first loop. + */ + return group + 1 >= ngroups ? 0 : group + 1; +} + +/* + * ext4_mb_choose_next_group: choose next group for allocation. + * + * @ac Allocation Context + * @new_cr This is an output parameter. If the there is no good group + * available at current CR level, this field is updated to indicate + * the new cr level that should be used. + * @group This is an input / output parameter. As an input it indicates the + * next group that the allocator intends to use for allocation. As + * output, this field indicates the next group that should be used as + * determined by the optimization functions. + * @ngroups Total number of groups + */ +static void ext4_mb_choose_next_group(struct ext4_allocation_context *ac, + int *new_cr, ext4_group_t *group, ext4_group_t ngroups) +{ + *new_cr = ac->ac_criteria; + + if (!should_optimize_scan(ac) || ac->ac_groups_linear_remaining) + return; + + if (*new_cr == 0) { + ext4_mb_choose_next_group_cr0(ac, new_cr, group, ngroups); + } else if (*new_cr == 1) { + ext4_mb_choose_next_group_cr1(ac, new_cr, group, ngroups); + } else { + /* + * TODO: For CR=2, we can arrange groups in an rb tree sorted by + * bb_free. But until that happens, we should never come here. + */ + WARN_ON(1); + } +} + /* * Cache the order of the largest free extent we have available in this block * group. @@ -751,18 +1071,33 @@ static void ext4_mb_mark_free_simple(struct super_block *sb, static void mb_set_largest_free_order(struct super_block *sb, struct ext4_group_info *grp) { + struct ext4_sb_info *sbi = EXT4_SB(sb); int i; - int bits; + if (test_opt2(sb, MB_OPTIMIZE_SCAN) && grp->bb_largest_free_order >= 0) { + write_lock(&sbi->s_mb_largest_free_orders_locks[ + grp->bb_largest_free_order]); + list_del_init(&grp->bb_largest_free_order_node); + write_unlock(&sbi->s_mb_largest_free_orders_locks[ + grp->bb_largest_free_order]); + } grp->bb_largest_free_order = -1; /* uninit */ - bits = sb->s_blocksize_bits + 1; - for (i = bits; i >= 0; i--) { + for (i = MB_NUM_ORDERS(sb) - 1; i >= 0; i--) { if (grp->bb_counters[i] > 0) { grp->bb_largest_free_order = i; break; } } + if (test_opt2(sb, MB_OPTIMIZE_SCAN) && + grp->bb_largest_free_order >= 0 && grp->bb_free) { + write_lock(&sbi->s_mb_largest_free_orders_locks[ + grp->bb_largest_free_order]); + list_add_tail(&grp->bb_largest_free_order_node, + &sbi->s_mb_largest_free_orders[grp->bb_largest_free_order]); + write_unlock(&sbi->s_mb_largest_free_orders_locks[ + grp->bb_largest_free_order]); + } } static noinline_for_stack @@ -816,10 +1151,9 @@ void ext4_mb_generate_buddy(struct super_block *sb, clear_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &(grp->bb_state)); period = get_cycles() - period; - spin_lock(&sbi->s_bal_lock); - sbi->s_mb_buddies_generated++; - sbi->s_mb_generation_time += period; - spin_unlock(&sbi->s_bal_lock); + atomic_inc(&sbi->s_mb_buddies_generated); + atomic64_add(period, &sbi->s_mb_generation_time); + mb_update_avg_fragment_size(sb, grp); } /* The buddy information is attached the buddy cache inode @@ -959,7 +1293,7 @@ static int ext4_mb_init_cache(struct page *page, char *incore, gfp_t gfp) grinfo->bb_fragments = 0; memset(grinfo->bb_counters, 0, sizeof(*grinfo->bb_counters) * - (sb->s_blocksize_bits+2)); + (MB_NUM_ORDERS(sb))); /* * incore got set to the group block bitmap below */ @@ -1519,6 +1853,7 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b, done: mb_set_largest_free_order(sb, e4b->bd_info); + mb_update_avg_fragment_size(sb, e4b->bd_info); mb_check_buddy(e4b); } @@ -1655,6 +1990,7 @@ static int mb_mark_used(struct ext4_buddy *e4b, struct ext4_free_extent *ex) } mb_set_largest_free_order(e4b->bd_sb, e4b->bd_info); + mb_update_avg_fragment_size(e4b->bd_sb, e4b->bd_info); ext4_set_bits(e4b->bd_bitmap, ex->fe_start, len0); mb_check_buddy(e4b); @@ -1930,7 +2266,7 @@ void ext4_mb_simple_scan_group(struct ext4_allocation_context *ac, int max; BUG_ON(ac->ac_2order <= 0); - for (i = ac->ac_2order; i <= sb->s_blocksize_bits + 1; i++) { + for (i = ac->ac_2order; i < MB_NUM_ORDERS(sb); i++) { if (grp->bb_counters[i] == 0) continue; @@ -2109,7 +2445,7 @@ static bool ext4_mb_good_group(struct ext4_allocation_context *ac, if (free < ac->ac_g_ex.fe_len) return false; - if (ac->ac_2order > ac->ac_sb->s_blocksize_bits+1) + if (ac->ac_2order >= MB_NUM_ORDERS(ac->ac_sb)) return true; if (grp->bb_largest_free_order < ac->ac_2order) @@ -2148,6 +2484,8 @@ static int ext4_mb_good_group_nolock(struct ext4_allocation_context *ac, ext4_grpblk_t free; int ret = 0; + if (sbi->s_mb_stats) + atomic64_inc(&sbi->s_bal_cX_groups_considered[ac->ac_criteria]); if (should_lock) ext4_lock_group(sb, group); free = grp->bb_free; @@ -2315,13 +2653,13 @@ ext4_mb_regular_allocator(struct ext4_allocation_context *ac) * We also support searching for power-of-two requests only for * requests upto maximum buddy size we have constructed. */ - if (i >= sbi->s_mb_order2_reqs && i <= sb->s_blocksize_bits + 2) { + if (i >= sbi->s_mb_order2_reqs && i <= MB_NUM_ORDERS(sb)) { /* * This should tell if fe_len is exactly power of 2 */ if ((ac->ac_g_ex.fe_len & (~(1 << (i - 1)))) == 0) ac->ac_2order = array_index_nospec(i - 1, - sb->s_blocksize_bits + 2); + MB_NUM_ORDERS(sb)); } /* if stream allocation is enabled, use global goal */ @@ -2347,17 +2685,21 @@ repeat: * from the goal value specified */ group = ac->ac_g_ex.fe_group; + ac->ac_last_optimal_group = group; + ac->ac_groups_linear_remaining = sbi->s_mb_max_linear_groups; prefetch_grp = group; - for (i = 0; i < ngroups; group++, i++) { - int ret = 0; + for (i = 0; i < ngroups; group = next_linear_group(ac, group, ngroups), + i++) { + int ret = 0, new_cr; + cond_resched(); - /* - * Artificially restricted ngroups for non-extent - * files makes group > ngroups possible on first loop. - */ - if (group >= ngroups) - group = 0; + + ext4_mb_choose_next_group(ac, &new_cr, &group, ngroups); + if (new_cr != cr) { + cr = new_cr; + goto repeat; + } /* * Batch reads of the block allocation bitmaps @@ -2422,6 +2764,9 @@ repeat: if (ac->ac_status != AC_STATUS_CONTINUE) break; } + /* Processed all groups and haven't found blocks */ + if (sbi->s_mb_stats && i == ngroups) + atomic64_inc(&sbi->s_bal_cX_failed[cr]); } if (ac->ac_b_ex.fe_len > 0 && ac->ac_status != AC_STATUS_FOUND && @@ -2451,6 +2796,9 @@ repeat: goto repeat; } } + + if (sbi->s_mb_stats && ac->ac_status == AC_STATUS_FOUND) + atomic64_inc(&sbi->s_bal_cX_hits[ac->ac_criteria]); out: if (!err && ac->ac_status != AC_STATUS_FOUND && first_err) err = first_err; @@ -2550,6 +2898,157 @@ const struct seq_operations ext4_mb_seq_groups_ops = { .show = ext4_mb_seq_groups_show, }; +int ext4_seq_mb_stats_show(struct seq_file *seq, void *offset) +{ + struct super_block *sb = (struct super_block *)seq->private; + struct ext4_sb_info *sbi = EXT4_SB(sb); + + seq_puts(seq, "mballoc:\n"); + if (!sbi->s_mb_stats) { + seq_puts(seq, "\tmb stats collection turned off.\n"); + seq_puts(seq, "\tTo enable, please write \"1\" to sysfs file mb_stats.\n"); + return 0; + } + seq_printf(seq, "\treqs: %u\n", atomic_read(&sbi->s_bal_reqs)); + seq_printf(seq, "\tsuccess: %u\n", atomic_read(&sbi->s_bal_success)); + + seq_printf(seq, "\tgroups_scanned: %u\n", atomic_read(&sbi->s_bal_groups_scanned)); + + seq_puts(seq, "\tcr0_stats:\n"); + seq_printf(seq, "\t\thits: %llu\n", atomic64_read(&sbi->s_bal_cX_hits[0])); + seq_printf(seq, "\t\tgroups_considered: %llu\n", + atomic64_read(&sbi->s_bal_cX_groups_considered[0])); + seq_printf(seq, "\t\tuseless_loops: %llu\n", + atomic64_read(&sbi->s_bal_cX_failed[0])); + seq_printf(seq, "\t\tbad_suggestions: %u\n", + atomic_read(&sbi->s_bal_cr0_bad_suggestions)); + + seq_puts(seq, "\tcr1_stats:\n"); + seq_printf(seq, "\t\thits: %llu\n", atomic64_read(&sbi->s_bal_cX_hits[1])); + seq_printf(seq, "\t\tgroups_considered: %llu\n", + atomic64_read(&sbi->s_bal_cX_groups_considered[1])); + seq_printf(seq, "\t\tuseless_loops: %llu\n", + atomic64_read(&sbi->s_bal_cX_failed[1])); + seq_printf(seq, "\t\tbad_suggestions: %u\n", + atomic_read(&sbi->s_bal_cr1_bad_suggestions)); + + seq_puts(seq, "\tcr2_stats:\n"); + seq_printf(seq, "\t\thits: %llu\n", atomic64_read(&sbi->s_bal_cX_hits[2])); + seq_printf(seq, "\t\tgroups_considered: %llu\n", + atomic64_read(&sbi->s_bal_cX_groups_considered[2])); + seq_printf(seq, "\t\tuseless_loops: %llu\n", + atomic64_read(&sbi->s_bal_cX_failed[2])); + + seq_puts(seq, "\tcr3_stats:\n"); + seq_printf(seq, "\t\thits: %llu\n", atomic64_read(&sbi->s_bal_cX_hits[3])); + seq_printf(seq, "\t\tgroups_considered: %llu\n", + atomic64_read(&sbi->s_bal_cX_groups_considered[3])); + seq_printf(seq, "\t\tuseless_loops: %llu\n", + atomic64_read(&sbi->s_bal_cX_failed[3])); + seq_printf(seq, "\textents_scanned: %u\n", atomic_read(&sbi->s_bal_ex_scanned)); + seq_printf(seq, "\t\tgoal_hits: %u\n", atomic_read(&sbi->s_bal_goals)); + seq_printf(seq, "\t\t2^n_hits: %u\n", atomic_read(&sbi->s_bal_2orders)); + seq_printf(seq, "\t\tbreaks: %u\n", atomic_read(&sbi->s_bal_breaks)); + seq_printf(seq, "\t\tlost: %u\n", atomic_read(&sbi->s_mb_lost_chunks)); + + seq_printf(seq, "\tbuddies_generated: %u/%u\n", + atomic_read(&sbi->s_mb_buddies_generated), + ext4_get_groups_count(sb)); + seq_printf(seq, "\tbuddies_time_used: %llu\n", + atomic64_read(&sbi->s_mb_generation_time)); + seq_printf(seq, "\tpreallocated: %u\n", + atomic_read(&sbi->s_mb_preallocated)); + seq_printf(seq, "\tdiscarded: %u\n", + atomic_read(&sbi->s_mb_discarded)); + return 0; +} + +static void *ext4_mb_seq_structs_summary_start(struct seq_file *seq, loff_t *pos) +{ + struct super_block *sb = PDE_DATA(file_inode(seq->file)); + unsigned long position; + + read_lock(&EXT4_SB(sb)->s_mb_rb_lock); + + if (*pos < 0 || *pos >= MB_NUM_ORDERS(sb) + 1) + return NULL; + position = *pos + 1; + return (void *) ((unsigned long) position); +} + +static void *ext4_mb_seq_structs_summary_next(struct seq_file *seq, void *v, loff_t *pos) +{ + struct super_block *sb = PDE_DATA(file_inode(seq->file)); + unsigned long position; + + ++*pos; + if (*pos < 0 || *pos >= MB_NUM_ORDERS(sb) + 1) + return NULL; + position = *pos + 1; + return (void *) ((unsigned long) position); +} + +static int ext4_mb_seq_structs_summary_show(struct seq_file *seq, void *v) +{ + struct super_block *sb = PDE_DATA(file_inode(seq->file)); + struct ext4_sb_info *sbi = EXT4_SB(sb); + unsigned long position = ((unsigned long) v); + struct ext4_group_info *grp; + struct rb_node *n; + unsigned int count, min, max; + + position--; + if (position >= MB_NUM_ORDERS(sb)) { + seq_puts(seq, "fragment_size_tree:\n"); + n = rb_first(&sbi->s_mb_avg_fragment_size_root); + if (!n) { + seq_puts(seq, "\ttree_min: 0\n\ttree_max: 0\n\ttree_nodes: 0\n"); + return 0; + } + grp = rb_entry(n, struct ext4_group_info, bb_avg_fragment_size_rb); + min = grp->bb_fragments ? grp->bb_free / grp->bb_fragments : 0; + count = 1; + while (rb_next(n)) { + count++; + n = rb_next(n); + } + grp = rb_entry(n, struct ext4_group_info, bb_avg_fragment_size_rb); + max = grp->bb_fragments ? grp->bb_free / grp->bb_fragments : 0; + + seq_printf(seq, "\ttree_min: %u\n\ttree_max: %u\n\ttree_nodes: %u\n", + min, max, count); + return 0; + } + + if (position == 0) { + seq_printf(seq, "optimize_scan: %d\n", + test_opt2(sb, MB_OPTIMIZE_SCAN) ? 1 : 0); + seq_puts(seq, "max_free_order_lists:\n"); + } + count = 0; + list_for_each_entry(grp, &sbi->s_mb_largest_free_orders[position], + bb_largest_free_order_node) + count++; + seq_printf(seq, "\tlist_order_%u_groups: %u\n", + (unsigned int)position, count); + + return 0; +} + +static void ext4_mb_seq_structs_summary_stop(struct seq_file *seq, void *v) +{ + struct super_block *sb = PDE_DATA(file_inode(seq->file)); + + read_unlock(&EXT4_SB(sb)->s_mb_rb_lock); +} + +const struct seq_operations ext4_mb_seq_structs_summary_ops = { + .start = ext4_mb_seq_structs_summary_start, + .next = ext4_mb_seq_structs_summary_next, + .stop = ext4_mb_seq_structs_summary_stop, + .show = ext4_mb_seq_structs_summary_show, +}; + static struct kmem_cache *get_groupinfo_cache(int blocksize_bits) { int cache_index = blocksize_bits - EXT4_MIN_BLOCK_LOG_SIZE; @@ -2590,7 +3089,7 @@ int ext4_mb_alloc_groupinfo(struct super_block *sb, ext4_group_t ngroups) sbi->s_group_info_size = size / sizeof(*sbi->s_group_info); if (old_groupinfo) ext4_kvfree_array_rcu(old_groupinfo); - ext4_debug("allocated s_groupinfo array for %d meta_bg's\n", + ext4_debug("allocated s_groupinfo array for %d meta_bg's\n", sbi->s_group_info_size); return 0; } @@ -2652,7 +3151,10 @@ int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t group, INIT_LIST_HEAD(&meta_group_info[i]->bb_prealloc_list); init_rwsem(&meta_group_info[i]->alloc_sem); meta_group_info[i]->bb_free_root = RB_ROOT; + INIT_LIST_HEAD(&meta_group_info[i]->bb_largest_free_order_node); + RB_CLEAR_NODE(&meta_group_info[i]->bb_avg_fragment_size_rb); meta_group_info[i]->bb_largest_free_order = -1; /* uninit */ + meta_group_info[i]->bb_group = group; mb_group_bb_bitmap_alloc(sb, meta_group_info[i], group); return 0; @@ -2813,7 +3315,7 @@ int ext4_mb_init(struct super_block *sb) unsigned max; int ret; - i = (sb->s_blocksize_bits + 2) * sizeof(*sbi->s_mb_offsets); + i = MB_NUM_ORDERS(sb) * sizeof(*sbi->s_mb_offsets); sbi->s_mb_offsets = kmalloc(i, GFP_KERNEL); if (sbi->s_mb_offsets == NULL) { @@ -2821,7 +3323,7 @@ int ext4_mb_init(struct super_block *sb) goto out; } - i = (sb->s_blocksize_bits + 2) * sizeof(*sbi->s_mb_maxs); + i = MB_NUM_ORDERS(sb) * sizeof(*sbi->s_mb_maxs); sbi->s_mb_maxs = kmalloc(i, GFP_KERNEL); if (sbi->s_mb_maxs == NULL) { ret = -ENOMEM; @@ -2847,10 +3349,30 @@ int ext4_mb_init(struct super_block *sb) offset_incr = offset_incr >> 1; max = max >> 1; i++; - } while (i <= sb->s_blocksize_bits + 1); + } while (i < MB_NUM_ORDERS(sb)); + + sbi->s_mb_avg_fragment_size_root = RB_ROOT; + sbi->s_mb_largest_free_orders = + kmalloc_array(MB_NUM_ORDERS(sb), sizeof(struct list_head), + GFP_KERNEL); + if (!sbi->s_mb_largest_free_orders) { + ret = -ENOMEM; + goto out; + } + sbi->s_mb_largest_free_orders_locks = + kmalloc_array(MB_NUM_ORDERS(sb), sizeof(rwlock_t), + GFP_KERNEL); + if (!sbi->s_mb_largest_free_orders_locks) { + ret = -ENOMEM; + goto out; + } + for (i = 0; i < MB_NUM_ORDERS(sb); i++) { + INIT_LIST_HEAD(&sbi->s_mb_largest_free_orders[i]); + rwlock_init(&sbi->s_mb_largest_free_orders_locks[i]); + } + rwlock_init(&sbi->s_mb_rb_lock); spin_lock_init(&sbi->s_md_lock); - spin_lock_init(&sbi->s_bal_lock); sbi->s_mb_free_pending = 0; INIT_LIST_HEAD(&sbi->s_freed_data_list); @@ -2901,6 +3423,10 @@ int ext4_mb_init(struct super_block *sb) spin_lock_init(&lg->lg_prealloc_lock); } + if (blk_queue_nonrot(bdev_get_queue(sb->s_bdev))) + sbi->s_mb_max_linear_groups = 0; + else + sbi->s_mb_max_linear_groups = MB_DEFAULT_LINEAR_LIMIT; /* init file for buddy data */ ret = ext4_mb_init_backend(sb); if (ret != 0) @@ -2912,6 +3438,8 @@ out_free_locality_groups: free_percpu(sbi->s_locality_groups); sbi->s_locality_groups = NULL; out: + kfree(sbi->s_mb_largest_free_orders); + kfree(sbi->s_mb_largest_free_orders_locks); kfree(sbi->s_mb_offsets); sbi->s_mb_offsets = NULL; kfree(sbi->s_mb_maxs); @@ -2968,6 +3496,8 @@ int ext4_mb_release(struct super_block *sb) kvfree(group_info); rcu_read_unlock(); } + kfree(sbi->s_mb_largest_free_orders); + kfree(sbi->s_mb_largest_free_orders_locks); kfree(sbi->s_mb_offsets); kfree(sbi->s_mb_maxs); iput(sbi->s_buddy_cache); @@ -2978,17 +3508,18 @@ int ext4_mb_release(struct super_block *sb) atomic_read(&sbi->s_bal_reqs), atomic_read(&sbi->s_bal_success)); ext4_msg(sb, KERN_INFO, - "mballoc: %u extents scanned, %u goal hits, " + "mballoc: %u extents scanned, %u groups scanned, %u goal hits, " "%u 2^N hits, %u breaks, %u lost", atomic_read(&sbi->s_bal_ex_scanned), + atomic_read(&sbi->s_bal_groups_scanned), atomic_read(&sbi->s_bal_goals), atomic_read(&sbi->s_bal_2orders), atomic_read(&sbi->s_bal_breaks), atomic_read(&sbi->s_mb_lost_chunks)); ext4_msg(sb, KERN_INFO, - "mballoc: %lu generated and it took %Lu", - sbi->s_mb_buddies_generated, - sbi->s_mb_generation_time); + "mballoc: %u generated and it took %llu", + atomic_read(&sbi->s_mb_buddies_generated), + atomic64_read(&sbi->s_mb_generation_time)); ext4_msg(sb, KERN_INFO, "mballoc: %u preallocated, %u discarded", atomic_read(&sbi->s_mb_preallocated), @@ -3583,12 +4114,13 @@ static void ext4_mb_collect_stats(struct ext4_allocation_context *ac) { struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); - if (sbi->s_mb_stats && ac->ac_g_ex.fe_len > 1) { + if (sbi->s_mb_stats && ac->ac_g_ex.fe_len >= 1) { atomic_inc(&sbi->s_bal_reqs); atomic_add(ac->ac_b_ex.fe_len, &sbi->s_bal_allocated); if (ac->ac_b_ex.fe_len >= ac->ac_o_ex.fe_len) atomic_inc(&sbi->s_bal_success); atomic_add(ac->ac_found, &sbi->s_bal_ex_scanned); + atomic_add(ac->ac_groups_scanned, &sbi->s_bal_groups_scanned); if (ac->ac_g_ex.fe_start == ac->ac_b_ex.fe_start && ac->ac_g_ex.fe_group == ac->ac_b_ex.fe_group) atomic_inc(&sbi->s_bal_goals); diff --git a/fs/ext4/mballoc.h b/fs/ext4/mballoc.h index e75b4749aa1c..39da92ceabf8 100644 --- a/fs/ext4/mballoc.h +++ b/fs/ext4/mballoc.h @@ -59,7 +59,7 @@ * by the stream allocator, which purpose is to pack requests * as close each to other as possible to produce smooth I/O traffic * We use locality group prealloc space for stream request. - * We can tune the same via /proc/fs/ext4/<parition>/stream_req + * We can tune the same via /proc/fs/ext4/<partition>/stream_req */ #define MB_DEFAULT_STREAM_THRESHOLD 16 /* 64K */ @@ -78,6 +78,23 @@ */ #define MB_DEFAULT_MAX_INODE_PREALLOC 512 +/* + * Number of groups to search linearly before performing group scanning + * optimization. + */ +#define MB_DEFAULT_LINEAR_LIMIT 4 + +/* + * Minimum number of groups that should be present in the file system to perform + * group scanning optimizations. + */ +#define MB_DEFAULT_LINEAR_SCAN_THRESHOLD 16 + +/* + * Number of valid buddy orders + */ +#define MB_NUM_ORDERS(sb) ((sb)->s_blocksize_bits + 2) + struct ext4_free_data { /* this links the free block information from sb_info */ struct list_head efd_list; @@ -161,11 +178,14 @@ struct ext4_allocation_context { /* copy of the best found extent taken before preallocation efforts */ struct ext4_free_extent ac_f_ex; + ext4_group_t ac_last_optimal_group; + __u32 ac_groups_considered; + __u32 ac_flags; /* allocation hints */ __u16 ac_groups_scanned; + __u16 ac_groups_linear_remaining; __u16 ac_found; __u16 ac_tail; __u16 ac_buddy; - __u16 ac_flags; /* allocation hints */ __u8 ac_status; __u8 ac_criteria; __u8 ac_2order; /* if request is to allocate 2^N blocks and diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c index c5e3fc998211..7e0b4f81c6c0 100644 --- a/fs/ext4/migrate.c +++ b/fs/ext4/migrate.c @@ -32,7 +32,7 @@ static int finish_range(handle_t *handle, struct inode *inode, newext.ee_block = cpu_to_le32(lb->first_block); newext.ee_len = cpu_to_le16(lb->last_block - lb->first_block + 1); ext4_ext_store_pblock(&newext, lb->first_pblock); - /* Locking only for convinience since we are operating on temp inode */ + /* Locking only for convenience since we are operating on temp inode */ down_write(&EXT4_I(inode)->i_data_sem); path = ext4_find_extent(inode, lb->first_block, NULL, 0); if (IS_ERR(path)) { @@ -43,8 +43,8 @@ static int finish_range(handle_t *handle, struct inode *inode, /* * Calculate the credit needed to inserting this extent - * Since we are doing this in loop we may accumalate extra - * credit. But below we try to not accumalate too much + * Since we are doing this in loop we may accumulate extra + * credit. But below we try to not accumulate too much * of them by restarting the journal. */ needed = ext4_ext_calc_credits_for_single_extent(inode, diff --git a/fs/ext4/mmp.c b/fs/ext4/mmp.c index 795c3ff2907c..68fbeedd627b 100644 --- a/fs/ext4/mmp.c +++ b/fs/ext4/mmp.c @@ -56,7 +56,7 @@ static int write_mmp_block(struct super_block *sb, struct buffer_head *bh) wait_on_buffer(bh); sb_end_write(sb); if (unlikely(!buffer_uptodate(bh))) - return 1; + return -EIO; return 0; } diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index a37a19fabee4..e8100a9a22fe 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -280,9 +280,11 @@ static int dx_make_map(struct inode *dir, struct ext4_dir_entry_2 *de, unsigned blocksize, struct dx_hash_info *hinfo, struct dx_map_entry map[]); static void dx_sort_map(struct dx_map_entry *map, unsigned count); -static struct ext4_dir_entry_2 *dx_move_dirents(char *from, char *to, - struct dx_map_entry *offsets, int count, unsigned blocksize); -static struct ext4_dir_entry_2* dx_pack_dirents(char *base, unsigned blocksize); +static struct ext4_dir_entry_2 *dx_move_dirents(struct inode *dir, char *from, + char *to, struct dx_map_entry *offsets, + int count, unsigned int blocksize); +static struct ext4_dir_entry_2 *dx_pack_dirents(struct inode *dir, char *base, + unsigned int blocksize); static void dx_insert_block(struct dx_frame *frame, u32 hash, ext4_lblk_t block); static int ext4_htree_next_block(struct inode *dir, __u32 hash, @@ -574,8 +576,9 @@ static inline void dx_set_limit(struct dx_entry *entries, unsigned value) static inline unsigned dx_root_limit(struct inode *dir, unsigned infosize) { - unsigned entry_space = dir->i_sb->s_blocksize - EXT4_DIR_REC_LEN(1) - - EXT4_DIR_REC_LEN(2) - infosize; + unsigned int entry_space = dir->i_sb->s_blocksize - + ext4_dir_rec_len(1, NULL) - + ext4_dir_rec_len(2, NULL) - infosize; if (ext4_has_metadata_csum(dir->i_sb)) entry_space -= sizeof(struct dx_tail); @@ -584,7 +587,8 @@ static inline unsigned dx_root_limit(struct inode *dir, unsigned infosize) static inline unsigned dx_node_limit(struct inode *dir) { - unsigned entry_space = dir->i_sb->s_blocksize - EXT4_DIR_REC_LEN(0); + unsigned int entry_space = dir->i_sb->s_blocksize - + ext4_dir_rec_len(0, dir); if (ext4_has_metadata_csum(dir->i_sb)) entry_space -= sizeof(struct dx_tail); @@ -673,7 +677,10 @@ static struct stats dx_show_leaf(struct inode *dir, name = fname_crypto_str.name; len = fname_crypto_str.len; } - ext4fs_dirhash(dir, de->name, + if (IS_CASEFOLDED(dir)) + h.hash = EXT4_DIRENT_HASH(de); + else + ext4fs_dirhash(dir, de->name, de->name_len, &h); printk("%*.s:(E)%x.%u ", len, name, h.hash, (unsigned) ((char *) de @@ -689,7 +696,7 @@ static struct stats dx_show_leaf(struct inode *dir, (unsigned) ((char *) de - base)); #endif } - space += EXT4_DIR_REC_LEN(de->name_len); + space += ext4_dir_rec_len(de->name_len, dir); names++; } de = ext4_next_entry(de, size); @@ -784,18 +791,34 @@ dx_probe(struct ext4_filename *fname, struct inode *dir, root = (struct dx_root *) frame->bh->b_data; if (root->info.hash_version != DX_HASH_TEA && root->info.hash_version != DX_HASH_HALF_MD4 && - root->info.hash_version != DX_HASH_LEGACY) { + root->info.hash_version != DX_HASH_LEGACY && + root->info.hash_version != DX_HASH_SIPHASH) { ext4_warning_inode(dir, "Unrecognised inode hash code %u", root->info.hash_version); goto fail; } + if (ext4_hash_in_dirent(dir)) { + if (root->info.hash_version != DX_HASH_SIPHASH) { + ext4_warning_inode(dir, + "Hash in dirent, but hash is not SIPHASH"); + goto fail; + } + } else { + if (root->info.hash_version == DX_HASH_SIPHASH) { + ext4_warning_inode(dir, + "Hash code is SIPHASH, but hash not in dirent"); + goto fail; + } + } if (fname) hinfo = &fname->hinfo; hinfo->hash_version = root->info.hash_version; if (hinfo->hash_version <= DX_HASH_TEA) hinfo->hash_version += EXT4_SB(dir->i_sb)->s_hash_unsigned; hinfo->seed = EXT4_SB(dir->i_sb)->s_hash_seed; - if (fname && fname_name(fname)) + /* hash is already computed for encrypted casefolded directory */ + if (fname && fname_name(fname) && + !(IS_ENCRYPTED(dir) && IS_CASEFOLDED(dir))) ext4fs_dirhash(dir, fname_name(fname), fname_len(fname), hinfo); hash = hinfo->hash; @@ -956,7 +979,7 @@ static int ext4_htree_next_block(struct inode *dir, __u32 hash, * If the hash is 1, then continue only if the next page has a * continuation hash of any value. This is used for readdir * handling. Otherwise, check to see if the hash matches the - * desired contiuation hash. If it doesn't, return since + * desired continuation hash. If it doesn't, return since * there's no point to read in the successive index pages. */ bhash = dx_get_hash(p->at); @@ -997,6 +1020,7 @@ static int htree_dirblock_to_tree(struct file *dir_file, struct ext4_dir_entry_2 *de, *top; int err = 0, count = 0; struct fscrypt_str fname_crypto_str = FSTR_INIT(NULL, 0), tmp_str; + int csum = ext4_has_metadata_csum(dir->i_sb); dxtrace(printk(KERN_INFO "In htree dirblock_to_tree: block %lu\n", (unsigned long)block)); @@ -1005,9 +1029,11 @@ static int htree_dirblock_to_tree(struct file *dir_file, return PTR_ERR(bh); de = (struct ext4_dir_entry_2 *) bh->b_data; + /* csum entries are not larger in the casefolded encrypted case */ top = (struct ext4_dir_entry_2 *) ((char *) de + dir->i_sb->s_blocksize - - EXT4_DIR_REC_LEN(0)); + ext4_dir_rec_len(0, + csum ? NULL : dir)); /* Check if the directory is encrypted */ if (IS_ENCRYPTED(dir)) { err = fscrypt_prepare_readdir(dir); @@ -1031,7 +1057,17 @@ static int htree_dirblock_to_tree(struct file *dir_file, /* silently ignore the rest of the block */ break; } - ext4fs_dirhash(dir, de->name, de->name_len, hinfo); + if (ext4_hash_in_dirent(dir)) { + if (de->name_len && de->inode) { + hinfo->hash = EXT4_DIRENT_HASH(de); + hinfo->minor_hash = EXT4_DIRENT_MINOR_HASH(de); + } else { + hinfo->hash = 0; + hinfo->minor_hash = 0; + } + } else { + ext4fs_dirhash(dir, de->name, de->name_len, hinfo); + } if ((hinfo->hash < start_hash) || ((hinfo->hash == start_hash) && (hinfo->minor_hash < start_minor_hash))) @@ -1100,7 +1136,11 @@ int ext4_htree_fill_tree(struct file *dir_file, __u32 start_hash, start_hash, start_minor_hash)); dir = file_inode(dir_file); if (!(ext4_test_inode_flag(dir, EXT4_INODE_INDEX))) { - hinfo.hash_version = EXT4_SB(dir->i_sb)->s_def_hash_version; + if (ext4_hash_in_dirent(dir)) + hinfo.hash_version = DX_HASH_SIPHASH; + else + hinfo.hash_version = + EXT4_SB(dir->i_sb)->s_def_hash_version; if (hinfo.hash_version <= DX_HASH_TEA) hinfo.hash_version += EXT4_SB(dir->i_sb)->s_hash_unsigned; @@ -1218,7 +1258,10 @@ static int dx_make_map(struct inode *dir, struct ext4_dir_entry_2 *de, while ((char *) de < base + blocksize) { if (de->name_len && de->inode) { - ext4fs_dirhash(dir, de->name, de->name_len, &h); + if (ext4_hash_in_dirent(dir)) + h.hash = EXT4_DIRENT_HASH(de); + else + ext4fs_dirhash(dir, de->name, de->name_len, &h); map_tail--; map_tail->hash = h.hash; map_tail->offs = ((char *) de - base)>>2; @@ -1282,47 +1325,65 @@ static void dx_insert_block(struct dx_frame *frame, u32 hash, ext4_lblk_t block) * Returns: 0 if the directory entry matches, more than 0 if it * doesn't match or less than zero on error. */ -int ext4_ci_compare(const struct inode *parent, const struct qstr *name, - const struct qstr *entry, bool quick) +static int ext4_ci_compare(const struct inode *parent, const struct qstr *name, + u8 *de_name, size_t de_name_len, bool quick) { const struct super_block *sb = parent->i_sb; const struct unicode_map *um = sb->s_encoding; + struct fscrypt_str decrypted_name = FSTR_INIT(NULL, de_name_len); + struct qstr entry = QSTR_INIT(de_name, de_name_len); int ret; + if (IS_ENCRYPTED(parent)) { + const struct fscrypt_str encrypted_name = + FSTR_INIT(de_name, de_name_len); + + decrypted_name.name = kmalloc(de_name_len, GFP_KERNEL); + if (!decrypted_name.name) + return -ENOMEM; + ret = fscrypt_fname_disk_to_usr(parent, 0, 0, &encrypted_name, + &decrypted_name); + if (ret < 0) + goto out; + entry.name = decrypted_name.name; + entry.len = decrypted_name.len; + } + if (quick) - ret = utf8_strncasecmp_folded(um, name, entry); + ret = utf8_strncasecmp_folded(um, name, &entry); else - ret = utf8_strncasecmp(um, name, entry); - + ret = utf8_strncasecmp(um, name, &entry); if (ret < 0) { /* Handle invalid character sequence as either an error * or as an opaque byte sequence. */ if (sb_has_strict_encoding(sb)) - return -EINVAL; - - if (name->len != entry->len) - return 1; - - return !!memcmp(name->name, entry->name, name->len); + ret = -EINVAL; + else if (name->len != entry.len) + ret = 1; + else + ret = !!memcmp(name->name, entry.name, entry.len); } - +out: + kfree(decrypted_name.name); return ret; } -void ext4_fname_setup_ci_filename(struct inode *dir, const struct qstr *iname, - struct fscrypt_str *cf_name) +int ext4_fname_setup_ci_filename(struct inode *dir, const struct qstr *iname, + struct ext4_filename *name) { + struct fscrypt_str *cf_name = &name->cf_name; + struct dx_hash_info *hinfo = &name->hinfo; int len; if (!IS_CASEFOLDED(dir) || !dir->i_sb->s_encoding) { cf_name->name = NULL; - return; + return 0; } cf_name->name = kmalloc(EXT4_NAME_LEN, GFP_NOFS); if (!cf_name->name) - return; + return -ENOMEM; len = utf8_casefold(dir->i_sb->s_encoding, iname, cf_name->name, @@ -1330,10 +1391,18 @@ void ext4_fname_setup_ci_filename(struct inode *dir, const struct qstr *iname, if (len <= 0) { kfree(cf_name->name); cf_name->name = NULL; - return; } cf_name->len = (unsigned) len; + if (!IS_ENCRYPTED(dir)) + return 0; + hinfo->hash_version = DX_HASH_SIPHASH; + hinfo->seed = NULL; + if (cf_name->name) + ext4fs_dirhash(dir, cf_name->name, cf_name->len, hinfo); + else + ext4fs_dirhash(dir, iname->name, iname->len, hinfo); + return 0; } #endif @@ -1342,14 +1411,11 @@ void ext4_fname_setup_ci_filename(struct inode *dir, const struct qstr *iname, * * Return: %true if the directory entry matches, otherwise %false. */ -static inline bool ext4_match(const struct inode *parent, +static bool ext4_match(struct inode *parent, const struct ext4_filename *fname, - const struct ext4_dir_entry_2 *de) + struct ext4_dir_entry_2 *de) { struct fscrypt_name f; -#ifdef CONFIG_UNICODE - const struct qstr entry = {.name = de->name, .len = de->name_len}; -#endif if (!de->inode) return false; @@ -1365,10 +1431,19 @@ static inline bool ext4_match(const struct inode *parent, if (fname->cf_name.name) { struct qstr cf = {.name = fname->cf_name.name, .len = fname->cf_name.len}; - return !ext4_ci_compare(parent, &cf, &entry, true); + if (IS_ENCRYPTED(parent)) { + if (fname->hinfo.hash != EXT4_DIRENT_HASH(de) || + fname->hinfo.minor_hash != + EXT4_DIRENT_MINOR_HASH(de)) { + + return 0; + } + } + return !ext4_ci_compare(parent, &cf, de->name, + de->name_len, true); } - return !ext4_ci_compare(parent, fname->usr_fname, &entry, - false); + return !ext4_ci_compare(parent, fname->usr_fname, de->name, + de->name_len, false); } #endif @@ -1765,7 +1840,8 @@ struct dentry *ext4_get_parent(struct dentry *child) * Returns pointer to last entry moved. */ static struct ext4_dir_entry_2 * -dx_move_dirents(char *from, char *to, struct dx_map_entry *map, int count, +dx_move_dirents(struct inode *dir, char *from, char *to, + struct dx_map_entry *map, int count, unsigned blocksize) { unsigned rec_len = 0; @@ -1773,11 +1849,19 @@ dx_move_dirents(char *from, char *to, struct dx_map_entry *map, int count, while (count--) { struct ext4_dir_entry_2 *de = (struct ext4_dir_entry_2 *) (from + (map->offs<<2)); - rec_len = EXT4_DIR_REC_LEN(de->name_len); + rec_len = ext4_dir_rec_len(de->name_len, dir); + memcpy (to, de, rec_len); ((struct ext4_dir_entry_2 *) to)->rec_len = ext4_rec_len_to_disk(rec_len, blocksize); + + /* wipe dir_entry excluding the rec_len field */ de->inode = 0; + memset(&de->name_len, 0, ext4_rec_len_from_disk(de->rec_len, + blocksize) - + offsetof(struct ext4_dir_entry_2, + name_len)); + map++; to += rec_len; } @@ -1788,7 +1872,8 @@ dx_move_dirents(char *from, char *to, struct dx_map_entry *map, int count, * Compact each dir entry in the range to the minimal rec_len. * Returns pointer to last entry in range. */ -static struct ext4_dir_entry_2* dx_pack_dirents(char *base, unsigned blocksize) +static struct ext4_dir_entry_2 *dx_pack_dirents(struct inode *dir, char *base, + unsigned int blocksize) { struct ext4_dir_entry_2 *next, *to, *prev, *de = (struct ext4_dir_entry_2 *) base; unsigned rec_len = 0; @@ -1797,7 +1882,7 @@ static struct ext4_dir_entry_2* dx_pack_dirents(char *base, unsigned blocksize) while ((char*)de < base + blocksize) { next = ext4_next_entry(de, blocksize); if (de->inode && de->name_len) { - rec_len = EXT4_DIR_REC_LEN(de->name_len); + rec_len = ext4_dir_rec_len(de->name_len, dir); if (de > to) memmove(to, de, rec_len); to->rec_len = ext4_rec_len_to_disk(rec_len, blocksize); @@ -1887,9 +1972,9 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir, hash2, split, count-split)); /* Fancy dance to stay within two buffers */ - de2 = dx_move_dirents(data1, data2, map + split, count - split, + de2 = dx_move_dirents(dir, data1, data2, map + split, count - split, blocksize); - de = dx_pack_dirents(data1, blocksize); + de = dx_pack_dirents(dir, data1, blocksize); de->rec_len = ext4_rec_len_to_disk(data1 + (blocksize - csum_size) - (char *) de, blocksize); @@ -1937,7 +2022,7 @@ int ext4_find_dest_de(struct inode *dir, struct inode *inode, struct ext4_dir_entry_2 **dest_de) { struct ext4_dir_entry_2 *de; - unsigned short reclen = EXT4_DIR_REC_LEN(fname_len(fname)); + unsigned short reclen = ext4_dir_rec_len(fname_len(fname), dir); int nlen, rlen; unsigned int offset = 0; char *top; @@ -1950,7 +2035,7 @@ int ext4_find_dest_de(struct inode *dir, struct inode *inode, return -EFSCORRUPTED; if (ext4_match(dir, fname, de)) return -EEXIST; - nlen = EXT4_DIR_REC_LEN(de->name_len); + nlen = ext4_dir_rec_len(de->name_len, dir); rlen = ext4_rec_len_from_disk(de->rec_len, buf_size); if ((de->inode ? rlen - nlen : rlen) >= reclen) break; @@ -1964,7 +2049,8 @@ int ext4_find_dest_de(struct inode *dir, struct inode *inode, return 0; } -void ext4_insert_dentry(struct inode *inode, +void ext4_insert_dentry(struct inode *dir, + struct inode *inode, struct ext4_dir_entry_2 *de, int buf_size, struct ext4_filename *fname) @@ -1972,7 +2058,7 @@ void ext4_insert_dentry(struct inode *inode, int nlen, rlen; - nlen = EXT4_DIR_REC_LEN(de->name_len); + nlen = ext4_dir_rec_len(de->name_len, dir); rlen = ext4_rec_len_from_disk(de->rec_len, buf_size); if (de->inode) { struct ext4_dir_entry_2 *de1 = @@ -1986,6 +2072,13 @@ void ext4_insert_dentry(struct inode *inode, ext4_set_de_type(inode->i_sb, de, inode->i_mode); de->name_len = fname_len(fname); memcpy(de->name, fname_name(fname), fname_len(fname)); + if (ext4_hash_in_dirent(dir)) { + struct dx_hash_info *hinfo = &fname->hinfo; + + EXT4_DIRENT_HASHES(de)->hash = cpu_to_le32(hinfo->hash); + EXT4_DIRENT_HASHES(de)->minor_hash = + cpu_to_le32(hinfo->minor_hash); + } } /* @@ -2022,7 +2115,7 @@ static int add_dirent_to_buf(handle_t *handle, struct ext4_filename *fname, } /* By now the buffer is marked for journaling */ - ext4_insert_dentry(inode, de, blocksize, fname); + ext4_insert_dentry(dir, inode, de, blocksize, fname); /* * XXX shouldn't update any times until successful @@ -2102,6 +2195,7 @@ static int make_indexed_dir(handle_t *handle, struct ext4_filename *fname, data2 = bh2->b_data; memcpy(data2, de, len); + memset(de, 0, len); /* wipe old data */ de = (struct ext4_dir_entry_2 *) data2; top = data2 + len; while ((char *)(de2 = ext4_next_entry(de, blocksize)) < top) @@ -2114,11 +2208,16 @@ static int make_indexed_dir(handle_t *handle, struct ext4_filename *fname, /* Initialize the root; the dot dirents already exist */ de = (struct ext4_dir_entry_2 *) (&root->dotdot); - de->rec_len = ext4_rec_len_to_disk(blocksize - EXT4_DIR_REC_LEN(2), - blocksize); + de->rec_len = ext4_rec_len_to_disk( + blocksize - ext4_dir_rec_len(2, NULL), blocksize); memset (&root->info, 0, sizeof(root->info)); root->info.info_length = sizeof(root->info); - root->info.hash_version = EXT4_SB(dir->i_sb)->s_def_hash_version; + if (ext4_hash_in_dirent(dir)) + root->info.hash_version = DX_HASH_SIPHASH; + else + root->info.hash_version = + EXT4_SB(dir->i_sb)->s_def_hash_version; + entries = root->entries; dx_set_block(entries, 1); dx_set_count(entries, 1); @@ -2129,7 +2228,11 @@ static int make_indexed_dir(handle_t *handle, struct ext4_filename *fname, if (fname->hinfo.hash_version <= DX_HASH_TEA) fname->hinfo.hash_version += EXT4_SB(dir->i_sb)->s_hash_unsigned; fname->hinfo.seed = EXT4_SB(dir->i_sb)->s_hash_seed; - ext4fs_dirhash(dir, fname_name(fname), fname_len(fname), &fname->hinfo); + + /* casefolded encrypted hashes are computed on fname setup */ + if (!ext4_hash_in_dirent(dir)) + ext4fs_dirhash(dir, fname_name(fname), + fname_len(fname), &fname->hinfo); memset(frames, 0, sizeof(frames)); frame = frames; @@ -2139,10 +2242,10 @@ static int make_indexed_dir(handle_t *handle, struct ext4_filename *fname, retval = ext4_handle_dirty_dx_node(handle, dir, frame->bh); if (retval) - goto out_frames; + goto out_frames; retval = ext4_handle_dirty_dirblock(handle, dir, bh2); if (retval) - goto out_frames; + goto out_frames; de = do_split(handle,dir, &bh2, frame, &fname->hinfo); if (IS_ERR(de)) { @@ -2482,15 +2585,27 @@ int ext4_generic_delete_entry(struct inode *dir, entry_buf, buf_size, i)) return -EFSCORRUPTED; if (de == de_del) { - if (pde) + if (pde) { pde->rec_len = ext4_rec_len_to_disk( ext4_rec_len_from_disk(pde->rec_len, blocksize) + ext4_rec_len_from_disk(de->rec_len, blocksize), blocksize); - else + + /* wipe entire dir_entry */ + memset(de, 0, ext4_rec_len_from_disk(de->rec_len, + blocksize)); + } else { + /* wipe dir_entry excluding the rec_len field */ de->inode = 0; + memset(&de->name_len, 0, + ext4_rec_len_from_disk(de->rec_len, + blocksize) - + offsetof(struct ext4_dir_entry_2, + name_len)); + } + inode_inc_iversion(dir); return 0; } @@ -2722,7 +2837,7 @@ struct ext4_dir_entry_2 *ext4_init_dot_dotdot(struct inode *inode, { de->inode = cpu_to_le32(inode->i_ino); de->name_len = 1; - de->rec_len = ext4_rec_len_to_disk(EXT4_DIR_REC_LEN(de->name_len), + de->rec_len = ext4_rec_len_to_disk(ext4_dir_rec_len(de->name_len, NULL), blocksize); strcpy(de->name, "."); ext4_set_de_type(inode->i_sb, de, S_IFDIR); @@ -2732,11 +2847,12 @@ struct ext4_dir_entry_2 *ext4_init_dot_dotdot(struct inode *inode, de->name_len = 2; if (!dotdot_real_len) de->rec_len = ext4_rec_len_to_disk(blocksize - - (csum_size + EXT4_DIR_REC_LEN(1)), + (csum_size + ext4_dir_rec_len(1, NULL)), blocksize); else de->rec_len = ext4_rec_len_to_disk( - EXT4_DIR_REC_LEN(de->name_len), blocksize); + ext4_dir_rec_len(de->name_len, NULL), + blocksize); strcpy(de->name, ".."); ext4_set_de_type(inode->i_sb, de, S_IFDIR); @@ -2869,7 +2985,8 @@ bool ext4_empty_dir(struct inode *inode) } sb = inode->i_sb; - if (inode->i_size < EXT4_DIR_REC_LEN(1) + EXT4_DIR_REC_LEN(2)) { + if (inode->i_size < ext4_dir_rec_len(1, NULL) + + ext4_dir_rec_len(2, NULL)) { EXT4_ERROR_INODE(inode, "invalid size"); return true; } @@ -3372,7 +3489,7 @@ static int ext4_symlink(struct user_namespace *mnt_userns, struct inode *dir, * for transaction commit if we are running out of space * and thus we deadlock. So we have to stop transaction now * and restart it when symlink contents is written. - * + * * To keep fs consistent in case of crash, we have to put inode * to orphan list in the mean time. */ diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 3868377dec2d..7dc94f3e18e6 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -667,9 +667,6 @@ static void ext4_handle_error(struct super_block *sb, bool force_ro, int error, ext4_commit_super(sb); } - if (sb_rdonly(sb) || continue_fs) - return; - /* * We force ERRORS_RO behavior when system is rebooting. Otherwise we * could panic during 'reboot -f' as the underlying device got already @@ -679,6 +676,10 @@ static void ext4_handle_error(struct super_block *sb, bool force_ro, int error, panic("EXT4-fs (device %s): panic forced after error\n", sb->s_id); } + + if (sb_rdonly(sb) || continue_fs) + return; + ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only"); /* * Make sure updated value of ->s_mount_flags will be visible before @@ -1688,7 +1689,7 @@ enum { Opt_dioread_nolock, Opt_dioread_lock, Opt_discard, Opt_nodiscard, Opt_init_itable, Opt_noinit_itable, Opt_max_dir_size_kb, Opt_nojournal_checksum, Opt_nombcache, - Opt_prefetch_block_bitmaps, + Opt_no_prefetch_block_bitmaps, Opt_mb_optimize_scan, #ifdef CONFIG_EXT4_DEBUG Opt_fc_debug_max_replay, Opt_fc_debug_force #endif @@ -1788,7 +1789,9 @@ static const match_table_t tokens = { {Opt_inlinecrypt, "inlinecrypt"}, {Opt_nombcache, "nombcache"}, {Opt_nombcache, "no_mbcache"}, /* for backward compatibility */ - {Opt_prefetch_block_bitmaps, "prefetch_block_bitmaps"}, + {Opt_removed, "prefetch_block_bitmaps"}, + {Opt_no_prefetch_block_bitmaps, "no_prefetch_block_bitmaps"}, + {Opt_mb_optimize_scan, "mb_optimize_scan=%d"}, {Opt_removed, "check=none"}, /* mount option from ext2/3 */ {Opt_removed, "nocheck"}, /* mount option from ext2/3 */ {Opt_removed, "reservation"}, /* mount option from ext2/3 */ @@ -1821,6 +1824,8 @@ static ext4_fsblk_t get_sb_block(void **data) } #define DEFAULT_JOURNAL_IOPRIO (IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, 3)) +#define DEFAULT_MB_OPTIMIZE_SCAN (-1) + static const char deprecated_msg[] = "Mount option \"%s\" will be removed by %s\n" "Contact linux-ext4@vger.kernel.org if you think we should keep it.\n"; @@ -2007,8 +2012,9 @@ static const struct mount_opts { {Opt_max_dir_size_kb, 0, MOPT_GTE0}, {Opt_test_dummy_encryption, 0, MOPT_STRING}, {Opt_nombcache, EXT4_MOUNT_NO_MBCACHE, MOPT_SET}, - {Opt_prefetch_block_bitmaps, EXT4_MOUNT_PREFETCH_BLOCK_BITMAPS, + {Opt_no_prefetch_block_bitmaps, EXT4_MOUNT_NO_PREFETCH_BLOCK_BITMAPS, MOPT_SET}, + {Opt_mb_optimize_scan, EXT4_MOUNT2_MB_OPTIMIZE_SCAN, MOPT_GTE0}, #ifdef CONFIG_EXT4_DEBUG {Opt_fc_debug_force, EXT4_MOUNT2_JOURNAL_FAST_COMMIT, MOPT_SET | MOPT_2 | MOPT_EXT4_ONLY}, @@ -2090,9 +2096,15 @@ static int ext4_set_test_dummy_encryption(struct super_block *sb, return 1; } +struct ext4_parsed_options { + unsigned long journal_devnum; + unsigned int journal_ioprio; + int mb_optimize_scan; +}; + static int handle_mount_opt(struct super_block *sb, char *opt, int token, - substring_t *args, unsigned long *journal_devnum, - unsigned int *journal_ioprio, int is_remount) + substring_t *args, struct ext4_parsed_options *parsed_opts, + int is_remount) { struct ext4_sb_info *sbi = EXT4_SB(sb); const struct mount_opts *m; @@ -2249,7 +2261,7 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token, "Cannot specify journal on remount"); return -1; } - *journal_devnum = arg; + parsed_opts->journal_devnum = arg; } else if (token == Opt_journal_path) { char *journal_path; struct inode *journal_inode; @@ -2285,7 +2297,7 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token, return -1; } - *journal_devnum = new_encode_dev(journal_inode->i_rdev); + parsed_opts->journal_devnum = new_encode_dev(journal_inode->i_rdev); path_put(&path); kfree(journal_path); } else if (token == Opt_journal_ioprio) { @@ -2294,7 +2306,7 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token, " (must be 0-7)"); return -1; } - *journal_ioprio = + parsed_opts->journal_ioprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, arg); } else if (token == Opt_test_dummy_encryption) { return ext4_set_test_dummy_encryption(sb, opt, &args[0], @@ -2384,6 +2396,13 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token, sbi->s_mount_opt |= m->mount_opt; } else if (token == Opt_data_err_ignore) { sbi->s_mount_opt &= ~m->mount_opt; + } else if (token == Opt_mb_optimize_scan) { + if (arg != 0 && arg != 1) { + ext4_msg(sb, KERN_WARNING, + "mb_optimize_scan should be set to 0 or 1."); + return -1; + } + parsed_opts->mb_optimize_scan = arg; } else { if (!args->from) arg = 1; @@ -2411,8 +2430,7 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token, } static int parse_options(char *options, struct super_block *sb, - unsigned long *journal_devnum, - unsigned int *journal_ioprio, + struct ext4_parsed_options *ret_opts, int is_remount) { struct ext4_sb_info __maybe_unused *sbi = EXT4_SB(sb); @@ -2432,8 +2450,8 @@ static int parse_options(char *options, struct super_block *sb, */ args[0].to = args[0].from = NULL; token = match_token(p, tokens, args); - if (handle_mount_opt(sb, p, token, args, journal_devnum, - journal_ioprio, is_remount) < 0) + if (handle_mount_opt(sb, p, token, args, ret_opts, + is_remount) < 0) return 0; } #ifdef CONFIG_QUOTA @@ -3023,9 +3041,6 @@ static void ext4_orphan_cleanup(struct super_block *sb, sb->s_flags &= ~SB_RDONLY; } #ifdef CONFIG_QUOTA - /* Needed for iput() to work correctly and not trash data */ - sb->s_flags |= SB_ACTIVE; - /* * Turn on quotas which were not enabled for read-only mounts if * filesystem has quota feature, so that they are updated correctly. @@ -3691,11 +3706,11 @@ static struct ext4_li_request *ext4_li_request_new(struct super_block *sb, elr->lr_super = sb; elr->lr_first_not_zeroed = start; - if (test_opt(sb, PREFETCH_BLOCK_BITMAPS)) - elr->lr_mode = EXT4_LI_MODE_PREFETCH_BBITMAP; - else { + if (test_opt(sb, NO_PREFETCH_BLOCK_BITMAPS)) { elr->lr_mode = EXT4_LI_MODE_ITABLE; elr->lr_next_group = start; + } else { + elr->lr_mode = EXT4_LI_MODE_PREFETCH_BBITMAP; } /* @@ -3726,7 +3741,7 @@ int ext4_register_li_request(struct super_block *sb, goto out; } - if (!test_opt(sb, PREFETCH_BLOCK_BITMAPS) && + if (test_opt(sb, NO_PREFETCH_BLOCK_BITMAPS) && (first_not_zeroed == ngroups || sb_rdonly(sb) || !test_opt(sb, INIT_INODE_TABLE))) goto out; @@ -4015,7 +4030,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) ext4_fsblk_t sb_block = get_sb_block(&data); ext4_fsblk_t logical_sb_block; unsigned long offset = 0; - unsigned long journal_devnum = 0; unsigned long def_mount_opts; struct inode *root; const char *descr; @@ -4026,8 +4040,13 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) int needs_recovery, has_huge_files; __u64 blocks_count; int err = 0; - unsigned int journal_ioprio = DEFAULT_JOURNAL_IOPRIO; ext4_group_t first_not_zeroed; + struct ext4_parsed_options parsed_opts; + + /* Set defaults for the variables that will be set during parsing */ + parsed_opts.journal_ioprio = DEFAULT_JOURNAL_IOPRIO; + parsed_opts.journal_devnum = 0; + parsed_opts.mb_optimize_scan = DEFAULT_MB_OPTIMIZE_SCAN; if ((data && !orig_data) || !sbi) goto out_free_base; @@ -4273,8 +4292,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) GFP_KERNEL); if (!s_mount_opts) goto failed_mount; - if (!parse_options(s_mount_opts, sb, &journal_devnum, - &journal_ioprio, 0)) { + if (!parse_options(s_mount_opts, sb, &parsed_opts, 0)) { ext4_msg(sb, KERN_WARNING, "failed to parse options in superblock: %s", s_mount_opts); @@ -4282,8 +4300,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) kfree(s_mount_opts); } sbi->s_def_mount_opt = sbi->s_mount_opt; - if (!parse_options((char *) data, sb, &journal_devnum, - &journal_ioprio, 0)) + if (!parse_options((char *) data, sb, &parsed_opts, 0)) goto failed_mount; #ifdef CONFIG_UNICODE @@ -4292,12 +4309,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) struct unicode_map *encoding; __u16 encoding_flags; - if (ext4_has_feature_encrypt(sb)) { - ext4_msg(sb, KERN_ERR, - "Can't mount with encoding and encryption"); - goto failed_mount; - } - if (ext4_sb_read_encoding(es, &encoding_info, &encoding_flags)) { ext4_msg(sb, KERN_ERR, @@ -4774,7 +4785,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) * root first: it may be modified in the journal! */ if (!test_opt(sb, NOLOAD) && ext4_has_feature_journal(sb)) { - err = ext4_load_journal(sb, es, journal_devnum); + err = ext4_load_journal(sb, es, parsed_opts.journal_devnum); if (err) goto failed_mount3a; } else if (test_opt(sb, NOLOAD) && !sb_rdonly(sb) && @@ -4874,7 +4885,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) goto failed_mount_wq; } - set_task_ioprio(sbi->s_journal->j_task, journal_ioprio); + set_task_ioprio(sbi->s_journal->j_task, parsed_opts.journal_ioprio); sbi->s_journal->j_submit_inode_data_buffers = ext4_journal_submit_inode_data_buffers; @@ -4980,6 +4991,19 @@ no_journal: ext4_fc_replay_cleanup(sb); ext4_ext_init(sb); + + /* + * Enable optimize_scan if number of groups is > threshold. This can be + * turned off by passing "mb_optimize_scan=0". This can also be + * turned on forcefully by passing "mb_optimize_scan=1". + */ + if (parsed_opts.mb_optimize_scan == 1) + set_opt2(sb, MB_OPTIMIZE_SCAN); + else if (parsed_opts.mb_optimize_scan == 0) + clear_opt2(sb, MB_OPTIMIZE_SCAN); + else if (sbi->s_groups_count >= MB_DEFAULT_LINEAR_SCAN_THRESHOLD) + set_opt2(sb, MB_OPTIMIZE_SCAN); + err = ext4_mb_init(sb); if (err) { ext4_msg(sb, KERN_ERR, "failed to initialize mballoc (%d)", @@ -4996,7 +5020,7 @@ no_journal: ext4_journal_commit_callback; block = ext4_count_free_clusters(sb); - ext4_free_blocks_count_set(sbi->s_es, + ext4_free_blocks_count_set(sbi->s_es, EXT4_C2B(sbi, block)); err = percpu_counter_init(&sbi->s_freeclusters_counter, block, GFP_KERNEL); @@ -5561,8 +5585,10 @@ static int ext4_commit_super(struct super_block *sb) struct buffer_head *sbh = EXT4_SB(sb)->s_sbh; int error = 0; - if (!sbh || block_device_ejected(sb)) - return error; + if (!sbh) + return -EINVAL; + if (block_device_ejected(sb)) + return -ENODEV; ext4_update_super(sb); @@ -5813,13 +5839,16 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) struct ext4_mount_options old_opts; int enable_quota = 0; ext4_group_t g; - unsigned int journal_ioprio = DEFAULT_JOURNAL_IOPRIO; int err = 0; #ifdef CONFIG_QUOTA int i, j; char *to_free[EXT4_MAXQUOTAS]; #endif char *orig_data = kstrdup(data, GFP_KERNEL); + struct ext4_parsed_options parsed_opts; + + parsed_opts.journal_ioprio = DEFAULT_JOURNAL_IOPRIO; + parsed_opts.journal_devnum = 0; if (data && !orig_data) return -ENOMEM; @@ -5850,7 +5879,8 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) old_opts.s_qf_names[i] = NULL; #endif if (sbi->s_journal && sbi->s_journal->j_task->io_context) - journal_ioprio = sbi->s_journal->j_task->io_context->ioprio; + parsed_opts.journal_ioprio = + sbi->s_journal->j_task->io_context->ioprio; /* * Some options can be enabled by ext4 and/or by VFS mount flag @@ -5860,7 +5890,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) vfs_flags = SB_LAZYTIME | SB_I_VERSION; sb->s_flags = (sb->s_flags & ~vfs_flags) | (*flags & vfs_flags); - if (!parse_options(data, sb, NULL, &journal_ioprio, 1)) { + if (!parse_options(data, sb, &parsed_opts, 1)) { err = -EINVAL; goto restore_opts; } @@ -5910,7 +5940,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) if (sbi->s_journal) { ext4_init_journal_params(sb, sbi->s_journal); - set_task_ioprio(sbi->s_journal->j_task, journal_ioprio); + set_task_ioprio(sbi->s_journal->j_task, parsed_opts.journal_ioprio); } /* Flush outstanding errors before changing fs state */ diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c index a3d08276d441..6f825dedc3d4 100644 --- a/fs/ext4/sysfs.c +++ b/fs/ext4/sysfs.c @@ -215,6 +215,7 @@ EXT4_RW_ATTR_SBI_UI(mb_order2_req, s_mb_order2_reqs); EXT4_RW_ATTR_SBI_UI(mb_stream_req, s_mb_stream_request); EXT4_RW_ATTR_SBI_UI(mb_group_prealloc, s_mb_group_prealloc); EXT4_RW_ATTR_SBI_UI(mb_max_inode_prealloc, s_mb_max_inode_prealloc); +EXT4_RW_ATTR_SBI_UI(mb_max_linear_groups, s_mb_max_linear_groups); EXT4_RW_ATTR_SBI_UI(extent_max_zeroout_kb, s_extent_max_zeroout_kb); EXT4_ATTR(trigger_fs_error, 0200, trigger_test_error); EXT4_RW_ATTR_SBI_UI(err_ratelimit_interval_ms, s_err_ratelimit_state.interval); @@ -263,6 +264,7 @@ static struct attribute *ext4_attrs[] = { ATTR_LIST(mb_stream_req), ATTR_LIST(mb_group_prealloc), ATTR_LIST(mb_max_inode_prealloc), + ATTR_LIST(mb_max_linear_groups), ATTR_LIST(max_writeback_mb_bump), ATTR_LIST(extent_max_zeroout_kb), ATTR_LIST(trigger_fs_error), @@ -313,6 +315,7 @@ EXT4_ATTR_FEATURE(verity); #endif EXT4_ATTR_FEATURE(metadata_csum_seed); EXT4_ATTR_FEATURE(fast_commit); +EXT4_ATTR_FEATURE(encrypted_casefold); static struct attribute *ext4_feat_attrs[] = { ATTR_LIST(lazy_itable_init), @@ -330,6 +333,7 @@ static struct attribute *ext4_feat_attrs[] = { #endif ATTR_LIST(metadata_csum_seed), ATTR_LIST(fast_commit), + ATTR_LIST(encrypted_casefold), NULL, }; ATTRIBUTE_GROUPS(ext4_feat); @@ -528,6 +532,10 @@ int ext4_register_sysfs(struct super_block *sb) ext4_fc_info_show, sb); proc_create_seq_data("mb_groups", S_IRUGO, sbi->s_proc, &ext4_mb_seq_groups_ops, sb); + proc_create_single_data("mb_stats", 0444, sbi->s_proc, + ext4_seq_mb_stats_show, sb); + proc_create_seq_data("mb_structs_summary", 0444, sbi->s_proc, + &ext4_mb_seq_structs_summary_ops, sb); } return 0; } diff --git a/fs/ext4/verity.c b/fs/ext4/verity.c index 07438f46b558..eacbd489e3bf 100644 --- a/fs/ext4/verity.c +++ b/fs/ext4/verity.c @@ -45,16 +45,13 @@ static int pagecache_read(struct inode *inode, void *buf, size_t count, size_t n = min_t(size_t, count, PAGE_SIZE - offset_in_page(pos)); struct page *page; - void *addr; page = read_mapping_page(inode->i_mapping, pos >> PAGE_SHIFT, NULL); if (IS_ERR(page)) return PTR_ERR(page); - addr = kmap_atomic(page); - memcpy(buf, addr + offset_in_page(pos), n); - kunmap_atomic(addr); + memcpy_from_page(buf, page, offset_in_page(pos), n); put_page(page); @@ -80,7 +77,6 @@ static int pagecache_write(struct inode *inode, const void *buf, size_t count, PAGE_SIZE - offset_in_page(pos)); struct page *page; void *fsdata; - void *addr; int res; res = pagecache_write_begin(NULL, inode->i_mapping, pos, n, 0, @@ -88,9 +84,7 @@ static int pagecache_write(struct inode *inode, const void *buf, size_t count, if (res) return res; - addr = kmap_atomic(page); - memcpy(addr + offset_in_page(pos), buf, n); - kunmap_atomic(addr); + memcpy_to_page(page, offset_in_page(pos), buf, n); res = pagecache_write_end(NULL, inode->i_mapping, pos, n, n, page, fsdata); diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 6c1018223c54..10ba4b24a0aa 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -1617,7 +1617,7 @@ static int ext4_xattr_set_entry(struct ext4_xattr_info *i, * If storing the value in an external inode is an option, * reserve space for xattr entries/names in the external * attribute block so that a long value does not occupy the - * whole space and prevent futher entries being added. + * whole space and prevent further entries being added. */ if (ext4_has_feature_ea_inode(inode->i_sb) && new_size && is_block && diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c index 69f18fe20923..d47a0d96bf30 100644 --- a/fs/jbd2/recovery.c +++ b/fs/jbd2/recovery.c @@ -245,15 +245,14 @@ static int fc_do_one_pass(journal_t *journal, return 0; while (next_fc_block <= journal->j_fc_last) { - jbd_debug(3, "Fast commit replay: next block %ld", + jbd_debug(3, "Fast commit replay: next block %ld\n", next_fc_block); err = jread(&bh, journal, next_fc_block); if (err) { - jbd_debug(3, "Fast commit replay: read error"); + jbd_debug(3, "Fast commit replay: read error\n"); break; } - jbd_debug(3, "Processing fast commit blk with seq %d"); err = journal->j_fc_replay_callback(journal, bh, pass, next_fc_block - journal->j_fc_first, expected_commit_id); diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index 9396666b7314..e8fc45fd751f 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -349,7 +349,12 @@ static int start_this_handle(journal_t *journal, handle_t *handle, } alloc_transaction: - if (!journal->j_running_transaction) { + /* + * This check is racy but it is just an optimization of allocating new + * transaction early if there are high chances we'll need it. If we + * guess wrong, we'll retry or free unused transaction. + */ + if (!data_race(journal->j_running_transaction)) { /* * If __GFP_FS is not present, then we may be being called from * inside the fs writeback layer, so we MUST NOT fail. @@ -1474,8 +1479,8 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh) * crucial to catch bugs so let's do a reliable check until the * lockless handling is fully proven. */ - if (jh->b_transaction != transaction && - jh->b_next_transaction != transaction) { + if (data_race(jh->b_transaction != transaction && + jh->b_next_transaction != transaction)) { spin_lock(&jh->b_state_lock); J_ASSERT_JH(jh, jh->b_transaction == transaction || jh->b_next_transaction == transaction); @@ -1483,8 +1488,8 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh) } if (jh->b_modified == 1) { /* If it's in our transaction it must be in BJ_Metadata list. */ - if (jh->b_transaction == transaction && - jh->b_jlist != BJ_Metadata) { + if (data_race(jh->b_transaction == transaction && + jh->b_jlist != BJ_Metadata)) { spin_lock(&jh->b_state_lock); if (jh->b_transaction == transaction && jh->b_jlist != BJ_Metadata) diff --git a/fs/stat.c b/fs/stat.c index fbc171d038aa..1fa38bdec1a6 100644 --- a/fs/stat.c +++ b/fs/stat.c @@ -86,12 +86,20 @@ int vfs_getattr_nosec(const struct path *path, struct kstat *stat, /* SB_NOATIME means filesystem supplies dummy atime value */ if (inode->i_sb->s_flags & SB_NOATIME) stat->result_mask &= ~STATX_ATIME; + + /* + * Note: If you add another clause to set an attribute flag, please + * update attributes_mask below. + */ if (IS_AUTOMOUNT(inode)) stat->attributes |= STATX_ATTR_AUTOMOUNT; if (IS_DAX(inode)) stat->attributes |= STATX_ATTR_DAX; + stat->attributes_mask |= (STATX_ATTR_AUTOMOUNT | + STATX_ATTR_DAX); + mnt_userns = mnt_user_ns(path->mnt); if (inode->i_op->getattr) return inode->i_op->getattr(mnt_userns, path, stat, |