diff options
Diffstat (limited to 'fs/ext4')
36 files changed, 4789 insertions, 3075 deletions
diff --git a/fs/ext4/Makefile b/fs/ext4/Makefile index 7d89142e1421..72206a292676 100644 --- a/fs/ext4/Makefile +++ b/fs/ext4/Makefile @@ -17,3 +17,4 @@ ext4-$(CONFIG_EXT4_FS_SECURITY) += xattr_security.o ext4-inode-test-objs += inode-test.o obj-$(CONFIG_EXT4_KUNIT_TESTS) += ext4-inode-test.o ext4-$(CONFIG_FS_VERITY) += verity.o +ext4-$(CONFIG_FS_ENCRYPTION) += crypto.o diff --git a/fs/ext4/acl.c b/fs/ext4/acl.c index 0613dfcbfd4a..57e82e25f8e2 100644 --- a/fs/ext4/acl.c +++ b/fs/ext4/acl.c @@ -139,7 +139,7 @@ fail: /* * Inode operation get_posix_acl(). * - * inode->i_mutex: don't care + * inode->i_rwsem: don't care */ struct posix_acl * ext4_get_acl(struct inode *inode, int type, bool rcu) @@ -183,7 +183,7 @@ ext4_get_acl(struct inode *inode, int type, bool rcu) /* * Set the access or default ACL of an inode. * - * inode->i_mutex: down unless called from ext4_new_inode + * inode->i_rwsem: down unless called from ext4_new_inode */ static int __ext4_set_acl(handle_t *handle, struct inode *inode, int type, @@ -246,7 +246,6 @@ retry: handle = ext4_journal_start(inode, EXT4_HT_XATTR, credits); if (IS_ERR(handle)) return PTR_ERR(handle); - ext4_fc_start_update(inode); if ((type == ACL_TYPE_ACCESS) && acl) { error = posix_acl_update_mode(mnt_userns, inode, &mode, &acl); @@ -264,7 +263,6 @@ retry: } out_stop: ext4_journal_stop(handle); - ext4_fc_stop_update(inode); if (error == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)) goto retry; return error; @@ -273,8 +271,8 @@ out_stop: /* * Initialize the ACLs of a new inode. Called from ext4_new_inode. * - * dir->i_mutex: down - * inode->i_mutex: up (access to inode is still exclusive) + * dir->i_rwsem: down + * inode->i_rwsem: up (access to inode is still exclusive) */ int ext4_init_acl(handle_t *handle, struct inode *inode, struct inode *dir) diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index a0fb0c4bdc7c..8ff4b9192a9f 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -411,6 +411,7 @@ verified: * ext4_read_block_bitmap_nowait() * @sb: super block * @block_group: given block group + * @ignore_locked: ignore locked buffers * * Read the bitmap for a given block_group,and validate the * bits for block/inode/inode tables are set in the bitmaps @@ -665,7 +666,7 @@ int ext4_should_retry_alloc(struct super_block *sb, int *retries) * it's possible we've just missed a transaction commit here, * so ignore the returned status */ - jbd_debug(1, "%s: retrying operation after ENOSPC\n", sb->s_id); + ext4_debug("%s: retrying operation after ENOSPC\n", sb->s_id); (void) jbd2_journal_force_commit_nested(sbi->s_journal); return 1; } diff --git a/fs/ext4/block_validity.c b/fs/ext4/block_validity.c index 4666b55b736e..5504f72bbbbe 100644 --- a/fs/ext4/block_validity.c +++ b/fs/ext4/block_validity.c @@ -292,15 +292,10 @@ void ext4_release_system_zone(struct super_block *sb) call_rcu(&system_blks->rcu, ext4_destroy_system_zone); } -/* - * Returns 1 if the passed-in block region (start_blk, - * start_blk+count) is valid; 0 if some part of the block region - * overlaps with some other filesystem metadata blocks. - */ -int ext4_inode_block_valid(struct inode *inode, ext4_fsblk_t start_blk, - unsigned int count) +int ext4_sb_block_valid(struct super_block *sb, struct inode *inode, + ext4_fsblk_t start_blk, unsigned int count) { - struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); + struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_system_blocks *system_blks; struct ext4_system_zone *entry; struct rb_node *n; @@ -329,7 +324,9 @@ int ext4_inode_block_valid(struct inode *inode, ext4_fsblk_t start_blk, else if (start_blk >= (entry->start_blk + entry->count)) n = n->rb_right; else { - ret = (entry->ino == inode->i_ino); + ret = 0; + if (inode) + ret = (entry->ino == inode->i_ino); break; } } @@ -338,6 +335,17 @@ out_rcu: return ret; } +/* + * Returns 1 if the passed-in block region (start_blk, + * start_blk+count) is valid; 0 if some part of the block region + * overlaps with some other filesystem metadata blocks. + */ +int ext4_inode_block_valid(struct inode *inode, ext4_fsblk_t start_blk, + unsigned int count) +{ + return ext4_sb_block_valid(inode->i_sb, inode, start_blk, count); +} + int ext4_check_blockref(const char *function, unsigned int line, struct inode *inode, __le32 *p, unsigned int max) { diff --git a/fs/ext4/crypto.c b/fs/ext4/crypto.c new file mode 100644 index 000000000000..e20ac0654b3f --- /dev/null +++ b/fs/ext4/crypto.c @@ -0,0 +1,246 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/quotaops.h> +#include <linux/uuid.h> + +#include "ext4.h" +#include "xattr.h" +#include "ext4_jbd2.h" + +static void ext4_fname_from_fscrypt_name(struct ext4_filename *dst, + const struct fscrypt_name *src) +{ + memset(dst, 0, sizeof(*dst)); + + dst->usr_fname = src->usr_fname; + dst->disk_name = src->disk_name; + dst->hinfo.hash = src->hash; + dst->hinfo.minor_hash = src->minor_hash; + dst->crypto_buf = src->crypto_buf; +} + +int ext4_fname_setup_filename(struct inode *dir, const struct qstr *iname, + int lookup, struct ext4_filename *fname) +{ + struct fscrypt_name name; + int err; + + err = fscrypt_setup_filename(dir, iname, lookup, &name); + if (err) + return err; + + ext4_fname_from_fscrypt_name(fname, &name); + +#if IS_ENABLED(CONFIG_UNICODE) + err = ext4_fname_setup_ci_filename(dir, iname, fname); +#endif + return err; +} + +int ext4_fname_prepare_lookup(struct inode *dir, struct dentry *dentry, + struct ext4_filename *fname) +{ + struct fscrypt_name name; + int err; + + err = fscrypt_prepare_lookup(dir, dentry, &name); + if (err) + return err; + + ext4_fname_from_fscrypt_name(fname, &name); + +#if IS_ENABLED(CONFIG_UNICODE) + err = ext4_fname_setup_ci_filename(dir, &dentry->d_name, fname); +#endif + return err; +} + +void ext4_fname_free_filename(struct ext4_filename *fname) +{ + struct fscrypt_name name; + + name.crypto_buf = fname->crypto_buf; + fscrypt_free_filename(&name); + + fname->crypto_buf.name = NULL; + fname->usr_fname = NULL; + fname->disk_name.name = NULL; + +#if IS_ENABLED(CONFIG_UNICODE) + kfree(fname->cf_name.name); + fname->cf_name.name = NULL; +#endif +} + +static bool uuid_is_zero(__u8 u[16]) +{ + int i; + + for (i = 0; i < 16; i++) + if (u[i]) + return false; + return true; +} + +int ext4_ioctl_get_encryption_pwsalt(struct file *filp, void __user *arg) +{ + struct super_block *sb = file_inode(filp)->i_sb; + struct ext4_sb_info *sbi = EXT4_SB(sb); + int err, err2; + handle_t *handle; + + if (!ext4_has_feature_encrypt(sb)) + return -EOPNOTSUPP; + + if (uuid_is_zero(sbi->s_es->s_encrypt_pw_salt)) { + err = mnt_want_write_file(filp); + if (err) + return err; + handle = ext4_journal_start_sb(sb, EXT4_HT_MISC, 1); + if (IS_ERR(handle)) { + err = PTR_ERR(handle); + goto pwsalt_err_exit; + } + err = ext4_journal_get_write_access(handle, sb, sbi->s_sbh, + EXT4_JTR_NONE); + if (err) + goto pwsalt_err_journal; + lock_buffer(sbi->s_sbh); + generate_random_uuid(sbi->s_es->s_encrypt_pw_salt); + ext4_superblock_csum_set(sb); + unlock_buffer(sbi->s_sbh); + err = ext4_handle_dirty_metadata(handle, NULL, sbi->s_sbh); +pwsalt_err_journal: + err2 = ext4_journal_stop(handle); + if (err2 && !err) + err = err2; +pwsalt_err_exit: + mnt_drop_write_file(filp); + if (err) + return err; + } + + if (copy_to_user(arg, sbi->s_es->s_encrypt_pw_salt, 16)) + return -EFAULT; + return 0; +} + +static int ext4_get_context(struct inode *inode, void *ctx, size_t len) +{ + return ext4_xattr_get(inode, EXT4_XATTR_INDEX_ENCRYPTION, + EXT4_XATTR_NAME_ENCRYPTION_CONTEXT, ctx, len); +} + +static int ext4_set_context(struct inode *inode, const void *ctx, size_t len, + void *fs_data) +{ + handle_t *handle = fs_data; + int res, res2, credits, retries = 0; + + /* + * Encrypting the root directory is not allowed because e2fsck expects + * lost+found to exist and be unencrypted, and encrypting the root + * directory would imply encrypting the lost+found directory as well as + * the filename "lost+found" itself. + */ + if (inode->i_ino == EXT4_ROOT_INO) + return -EPERM; + + if (WARN_ON_ONCE(IS_DAX(inode) && i_size_read(inode))) + return -EINVAL; + + if (ext4_test_inode_flag(inode, EXT4_INODE_DAX)) + return -EOPNOTSUPP; + + res = ext4_convert_inline_data(inode); + if (res) + return res; + + /* + * If a journal handle was specified, then the encryption context is + * being set on a new inode via inheritance and is part of a larger + * transaction to create the inode. Otherwise the encryption context is + * being set on an existing inode in its own transaction. Only in the + * latter case should the "retry on ENOSPC" logic be used. + */ + + if (handle) { + res = ext4_xattr_set_handle(handle, inode, + EXT4_XATTR_INDEX_ENCRYPTION, + EXT4_XATTR_NAME_ENCRYPTION_CONTEXT, + ctx, len, 0); + if (!res) { + ext4_set_inode_flag(inode, EXT4_INODE_ENCRYPT); + ext4_clear_inode_state(inode, + EXT4_STATE_MAY_INLINE_DATA); + /* + * Update inode->i_flags - S_ENCRYPTED will be enabled, + * S_DAX may be disabled + */ + ext4_set_inode_flags(inode, false); + } + return res; + } + + res = dquot_initialize(inode); + if (res) + return res; +retry: + res = ext4_xattr_set_credits(inode, len, false /* is_create */, + &credits); + if (res) + return res; + + handle = ext4_journal_start(inode, EXT4_HT_MISC, credits); + if (IS_ERR(handle)) + return PTR_ERR(handle); + + res = ext4_xattr_set_handle(handle, inode, EXT4_XATTR_INDEX_ENCRYPTION, + EXT4_XATTR_NAME_ENCRYPTION_CONTEXT, + ctx, len, 0); + if (!res) { + ext4_set_inode_flag(inode, EXT4_INODE_ENCRYPT); + /* + * Update inode->i_flags - S_ENCRYPTED will be enabled, + * S_DAX may be disabled + */ + ext4_set_inode_flags(inode, false); + res = ext4_mark_inode_dirty(handle, inode); + if (res) + EXT4_ERROR_INODE(inode, "Failed to mark inode dirty"); + } + res2 = ext4_journal_stop(handle); + + if (res == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)) + goto retry; + if (!res) + res = res2; + return res; +} + +static const union fscrypt_policy *ext4_get_dummy_policy(struct super_block *sb) +{ + return EXT4_SB(sb)->s_dummy_enc_policy.policy; +} + +static bool ext4_has_stable_inodes(struct super_block *sb) +{ + return ext4_has_feature_stable_inodes(sb); +} + +static void ext4_get_ino_and_lblk_bits(struct super_block *sb, + int *ino_bits_ret, int *lblk_bits_ret) +{ + *ino_bits_ret = 8 * sizeof(EXT4_SB(sb)->s_es->s_inodes_count); + *lblk_bits_ret = 8 * sizeof(ext4_lblk_t); +} + +const struct fscrypt_operations ext4_cryptops = { + .key_prefix = "ext4:", + .get_context = ext4_get_context, + .set_context = ext4_set_context, + .get_dummy_policy = ext4_get_dummy_policy, + .empty_dir = ext4_empty_dir, + .has_stable_inodes = ext4_has_stable_inodes, + .get_ino_and_lblk_bits = ext4_get_ino_and_lblk_bits, +}; diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c index 74b172a4adda..3985f8c33f95 100644 --- a/fs/ext4/dir.c +++ b/fs/ext4/dir.c @@ -303,7 +303,6 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx) goto done; brelse(bh); bh = NULL; - offset = 0; } done: err = 0; @@ -413,7 +412,7 @@ struct fname { }; /* - * This functoin implements a non-recursive way of freeing all of the + * This function implements a non-recursive way of freeing all of the * nodes in the red-black tree. */ static void free_rb_tree_fname(struct rb_root *root) @@ -516,7 +515,7 @@ int ext4_htree_store_dirent(struct file *dir_file, __u32 hash, /* * This is a helper function for ext4_dx_readdir. It calls filldir - * for all entres on the fname linked list. (Normally there is only + * for all entries on the fname linked list. (Normally there is only * one entry on the linked list, unless there are 62 bit hash collisions.) */ static int call_filldir(struct file *file, struct dir_context *ctx, @@ -649,7 +648,7 @@ int ext4_check_all_de(struct inode *dir, struct buffer_head *bh, void *buf, unsigned int offset = 0; char *top; - de = (struct ext4_dir_entry_2 *)buf; + de = buf; top = buf + buf_size; while ((char *) de < top) { if (ext4_check_dir_entry(dir, NULL, de, bh, diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 404dd50856e5..8d5453852f98 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -167,8 +167,6 @@ enum SHIFT_DIRECTION { #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; @@ -673,6 +671,8 @@ enum { /* Caller will submit data before dropping transaction handle. This * allows jbd2 to avoid submitting data before commit. */ #define EXT4_GET_BLOCKS_IO_SUBMIT 0x0400 + /* Caller is in the atomic contex, find extent if it has been cached */ +#define EXT4_GET_BLOCKS_CACHED_NOWAIT 0x0800 /* * The bit position of these flags must not overlap with any of the @@ -722,6 +722,8 @@ enum { #define EXT4_IOC_GETSTATE _IOW('f', 41, __u32) #define EXT4_IOC_GET_ES_CACHE _IOWR('f', 42, struct fiemap) #define EXT4_IOC_CHECKPOINT _IOW('f', 43, __u32) +#define EXT4_IOC_GETFSUUID _IOR('f', 44, struct fsuuid) +#define EXT4_IOC_SETFSUUID _IOW('f', 44, struct fsuuid) #define EXT4_IOC_SHUTDOWN _IOR ('X', 125, __u32) @@ -751,6 +753,15 @@ enum { EXT4_IOC_CHECKPOINT_FLAG_ZEROOUT | \ EXT4_IOC_CHECKPOINT_FLAG_DRY_RUN) +/* + * Structure for EXT4_IOC_GETFSUUID/EXT4_IOC_SETFSUUID + */ +struct fsuuid { + __u32 fsu_len; + __u32 fsu_flags; + __u8 fsu_uuid[]; +}; + #if defined(__KERNEL__) && defined(CONFIG_COMPAT) /* * ioctl commands in 32 bit emulation @@ -1028,7 +1039,7 @@ struct ext4_inode_info { /* * Extended attributes can be read independently of the main file - * data. Taking i_mutex even when reading would cause contention + * data. Taking i_rwsem even when reading would cause contention * between readers of EAs and writers of regular file data, so * instead we synchronize on xattr_sem when reading or changing * EAs. @@ -1046,6 +1057,8 @@ struct ext4_inode_info { /* Fast commit related info */ + /* For tracking dentry create updates */ + struct list_head i_fc_dilist; struct list_head i_fc_list; /* * inodes that need fast commit * protected by sbi->s_fc_lock. @@ -1279,7 +1292,7 @@ struct ext4_inode_info { #define ext4_find_next_zero_bit find_next_zero_bit_le #define ext4_find_next_bit find_next_bit_le -extern void ext4_set_bits(void *bm, int cur, int len); +extern void mb_set_bits(void *bm, int cur, int len); /* * Maximal mount counts between two filesystem checks @@ -1298,6 +1311,8 @@ extern void ext4_set_bits(void *bm, int cur, int len); /* Metadata checksum algorithm codes */ #define EXT4_CRC32C_CHKSUM 1 +#define EXT4_LABEL_MAX 16 + /* * Structure of the super block */ @@ -1347,7 +1362,7 @@ struct ext4_super_block { /*60*/ __le32 s_feature_incompat; /* incompatible feature set */ __le32 s_feature_ro_compat; /* readonly-compatible feature set */ /*68*/ __u8 s_uuid[16]; /* 128-bit uuid for volume */ -/*78*/ char s_volume_name[16]; /* volume name */ +/*78*/ char s_volume_name[EXT4_LABEL_MAX]; /* volume name */ /*88*/ char s_last_mounted[64] __nonstring; /* directory where last mounted */ /*C8*/ __le32 s_algorithm_usage_bitmap; /* For compression */ /* @@ -1436,12 +1451,6 @@ struct ext4_super_block { #ifdef __KERNEL__ -#ifdef CONFIG_FS_ENCRYPTION -#define DUMMY_ENCRYPTION_ENABLED(sbi) ((sbi)->s_dummy_enc_policy.policy != NULL) -#else -#define DUMMY_ENCRYPTION_ENABLED(sbi) (0) -#endif - /* Number of quota types we support */ #define EXT4_MAXQUOTAS 3 @@ -1589,8 +1598,8 @@ struct ext4_sb_info { struct list_head s_discard_list; struct work_struct s_discard_work; atomic_t s_retry_alloc_pending; - struct rb_root s_mb_avg_fragment_size_root; - rwlock_t s_mb_rb_lock; + struct list_head *s_mb_avg_fragment_size; + rwlock_t *s_mb_avg_fragment_size_locks; struct list_head *s_mb_largest_free_orders; rwlock_t *s_mb_largest_free_orders_locks; @@ -1661,7 +1670,7 @@ struct ext4_sb_info { struct task_struct *s_mmp_tsk; /* record the last minlen when FITRIM is called. */ - atomic_t s_last_trim_minblks; + unsigned long s_last_trim_minblks; /* Reference to checksum algorithm driver via cryptoapi */ struct crypto_shash *s_chksum_driver; @@ -1697,6 +1706,7 @@ struct ext4_sb_info { */ struct percpu_rw_semaphore s_writepages_rwsem; struct dax_device *s_daxdev; + u64 s_dax_part_off; #ifdef CONFIG_EXT4_DEBUG unsigned long s_simulate_fail; #endif @@ -1725,9 +1735,9 @@ struct ext4_sb_info { */ struct work_struct s_error_work; - /* Ext4 fast commit stuff */ + /* Ext4 fast commit sub transaction ID */ atomic_t s_fc_subtid; - atomic_t s_fc_ineligible_updates; + /* * After commit starts, the main queue gets locked, and the further * updates get added in the staging queue. @@ -1747,7 +1757,7 @@ struct ext4_sb_info { spinlock_t s_fc_lock; struct buffer_head *s_fc_bh; struct ext4_fc_stats s_fc_stats; - u64 s_fc_avg_commit_time; + tid_t s_fc_ineligible_tid; #ifdef CONFIG_EXT4_DEBUG int s_fc_debug_max_replay; #endif @@ -1793,10 +1803,7 @@ static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino) enum { EXT4_MF_MNTDIR_SAMPLED, EXT4_MF_FS_ABORTED, /* Fatal error detected */ - EXT4_MF_FC_INELIGIBLE, /* Fast commit ineligible */ - EXT4_MF_FC_COMMITTING /* File system underoing a fast - * commit. - */ + EXT4_MF_FC_INELIGIBLE /* Fast commit ineligible */ }; static inline void ext4_set_mount_flag(struct super_block *sb, int bit) @@ -2271,6 +2278,10 @@ static inline int ext4_forced_shutdown(struct ext4_sb_info *sbi) * Structure of a directory entry */ #define EXT4_NAME_LEN 255 +/* + * Base length of the ext4 directory entry excluding the name length + */ +#define EXT4_BASE_DIR_LEN (sizeof(struct ext4_dir_entry_2) - EXT4_NAME_LEN) struct ext4_dir_entry { __le32 inode; /* Inode number */ @@ -2399,8 +2410,7 @@ ext4_rec_len_from_disk(__le16 dlen, unsigned blocksize) static inline __le16 ext4_rec_len_to_disk(unsigned len, unsigned blocksize) { - if ((len > blocksize) || (blocksize > (1 << 18)) || (len & 3)) - BUG(); + BUG_ON((len > blocksize) || (blocksize > (1 << 18)) || (len & 3)); #if (PAGE_SIZE >= 65536) if (len < 65536) return cpu_to_le16(len); @@ -2484,7 +2494,7 @@ struct ext4_filename { #ifdef CONFIG_FS_ENCRYPTION struct fscrypt_str crypto_buf; #endif -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) struct fscrypt_str cf_name; #endif }; @@ -2720,80 +2730,26 @@ extern unsigned ext4_free_clusters_after_init(struct super_block *sb, struct ext4_group_desc *gdp); ext4_fsblk_t ext4_inode_to_goal_block(struct inode *); -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) extern int ext4_fname_setup_ci_filename(struct inode *dir, const struct qstr *iname, struct ext4_filename *fname); #endif +/* ext4 encryption related stuff goes here crypto.c */ #ifdef CONFIG_FS_ENCRYPTION -static inline void ext4_fname_from_fscrypt_name(struct ext4_filename *dst, - const struct fscrypt_name *src) -{ - memset(dst, 0, sizeof(*dst)); - - dst->usr_fname = src->usr_fname; - dst->disk_name = src->disk_name; - dst->hinfo.hash = src->hash; - dst->hinfo.minor_hash = src->minor_hash; - dst->crypto_buf = src->crypto_buf; -} - -static inline int ext4_fname_setup_filename(struct inode *dir, - const struct qstr *iname, - int lookup, - struct ext4_filename *fname) -{ - struct fscrypt_name name; - int err; - - err = fscrypt_setup_filename(dir, iname, lookup, &name); - if (err) - return err; - - ext4_fname_from_fscrypt_name(fname, &name); - -#ifdef CONFIG_UNICODE - err = ext4_fname_setup_ci_filename(dir, iname, fname); -#endif - return err; -} - -static inline int ext4_fname_prepare_lookup(struct inode *dir, - struct dentry *dentry, - struct ext4_filename *fname) -{ - struct fscrypt_name name; - int err; +extern const struct fscrypt_operations ext4_cryptops; - err = fscrypt_prepare_lookup(dir, dentry, &name); - if (err) - return err; - - ext4_fname_from_fscrypt_name(fname, &name); - -#ifdef CONFIG_UNICODE - err = ext4_fname_setup_ci_filename(dir, &dentry->d_name, fname); -#endif - return err; -} +int ext4_fname_setup_filename(struct inode *dir, const struct qstr *iname, + int lookup, struct ext4_filename *fname); -static inline void ext4_fname_free_filename(struct ext4_filename *fname) -{ - struct fscrypt_name name; +int ext4_fname_prepare_lookup(struct inode *dir, struct dentry *dentry, + struct ext4_filename *fname); - name.crypto_buf = fname->crypto_buf; - fscrypt_free_filename(&name); +void ext4_fname_free_filename(struct ext4_filename *fname); - fname->crypto_buf.name = NULL; - fname->usr_fname = NULL; - fname->disk_name.name = NULL; +int ext4_ioctl_get_encryption_pwsalt(struct file *filp, void __user *arg); -#ifdef CONFIG_UNICODE - kfree(fname->cf_name.name); - fname->cf_name.name = NULL; -#endif -} #else /* !CONFIG_FS_ENCRYPTION */ static inline int ext4_fname_setup_filename(struct inode *dir, const struct qstr *iname, @@ -2805,7 +2761,7 @@ static inline int ext4_fname_setup_filename(struct inode *dir, fname->disk_name.name = (unsigned char *) iname->name; fname->disk_name.len = iname->len; -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) err = ext4_fname_setup_ci_filename(dir, iname, fname); #endif @@ -2821,11 +2777,17 @@ static inline int ext4_fname_prepare_lookup(struct inode *dir, static inline void ext4_fname_free_filename(struct ext4_filename *fname) { -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) kfree(fname->cf_name.name); fname->cf_name.name = NULL; #endif } + +static inline int ext4_ioctl_get_encryption_pwsalt(struct file *filp, + void __user *arg) +{ + return -EOPNOTSUPP; +} #endif /* !CONFIG_FS_ENCRYPTION */ /* dir.c */ @@ -2925,9 +2887,7 @@ void __ext4_fc_track_create(handle_t *handle, struct inode *inode, struct dentry *dentry); void ext4_fc_track_create(handle_t *handle, struct dentry *dentry); void ext4_fc_track_inode(handle_t *handle, struct inode *inode); -void ext4_fc_mark_ineligible(struct super_block *sb, int reason); -void ext4_fc_start_ineligible(struct super_block *sb, int reason); -void ext4_fc_stop_ineligible(struct super_block *sb); +void ext4_fc_mark_ineligible(struct super_block *sb, int reason, handle_t *handle); void ext4_fc_start_update(struct inode *inode); void ext4_fc_stop_update(struct inode *inode); void ext4_fc_del(struct inode *inode); @@ -2935,6 +2895,10 @@ bool ext4_fc_replay_check_excluded(struct super_block *sb, ext4_fsblk_t block); void ext4_fc_replay_cleanup(struct super_block *sb); int ext4_fc_commit(journal_t *journal, tid_t commit_tid); int __init ext4_fc_init_dentry_cache(void); +void ext4_fc_destroy_dentry_cache(void); +int ext4_fc_record_regions(struct super_block *sb, int ino, + ext4_lblk_t lblk, ext4_fsblk_t pblk, + int len, int replay); /* mballoc.c */ extern const struct seq_operations ext4_mb_seq_groups_ops; @@ -3013,6 +2977,7 @@ extern struct inode *__ext4_iget(struct super_block *sb, unsigned long ino, extern int ext4_write_inode(struct inode *, struct writeback_control *); extern int ext4_setattr(struct user_namespace *, struct dentry *, struct iattr *); +extern u32 ext4_dio_alignment(struct inode *inode); extern int ext4_getattr(struct user_namespace *, const struct path *, struct kstat *, u32, unsigned int); extern void ext4_evict_inode(struct inode *); @@ -3029,7 +2994,7 @@ extern int ext4_inode_attach_jinode(struct inode *inode); extern int ext4_can_truncate(struct inode *inode); extern int ext4_truncate(struct inode *); extern int ext4_break_layouts(struct inode *); -extern int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length); +extern int ext4_punch_hole(struct file *file, loff_t offset, loff_t length); extern void ext4_set_inode_flags(struct inode *, bool init); extern int ext4_alloc_da_blocks(struct inode *inode); extern void ext4_set_aops(struct inode *inode); @@ -3061,6 +3026,7 @@ int ext4_fileattr_set(struct user_namespace *mnt_userns, struct dentry *dentry, struct fileattr *fa); int ext4_fileattr_get(struct dentry *dentry, struct fileattr *fa); extern void ext4_reset_inode_seed(struct inode *inode); +int ext4_update_overhead(struct super_block *sb, bool force); /* migrate.c */ extern int ext4_ext_migrate(struct inode *); @@ -3096,20 +3062,25 @@ extern int ext4_group_extend(struct super_block *sb, struct ext4_super_block *es, ext4_fsblk_t n_blocks_count); extern int ext4_resize_fs(struct super_block *sb, ext4_fsblk_t n_blocks_count); +extern unsigned int ext4_list_backups(struct super_block *sb, + unsigned int *three, unsigned int *five, + unsigned int *seven); /* super.c */ extern struct buffer_head *ext4_sb_bread(struct super_block *sb, - sector_t block, int op_flags); + sector_t block, blk_opf_t op_flags); extern struct buffer_head *ext4_sb_bread_unmovable(struct super_block *sb, sector_t block); -extern void ext4_read_bh_nowait(struct buffer_head *bh, int op_flags, +extern void ext4_read_bh_nowait(struct buffer_head *bh, blk_opf_t op_flags, bh_end_io_t *end_io); -extern int ext4_read_bh(struct buffer_head *bh, int op_flags, +extern int ext4_read_bh(struct buffer_head *bh, blk_opf_t op_flags, bh_end_io_t *end_io); -extern int ext4_read_bh_lock(struct buffer_head *bh, int op_flags, bool wait); +extern int ext4_read_bh_lock(struct buffer_head *bh, blk_opf_t op_flags, bool wait); extern void ext4_sb_breadahead_unmovable(struct super_block *sb, sector_t block); extern int ext4_seq_options_show(struct seq_file *seq, void *offset); extern int ext4_calculate_overhead(struct super_block *sb); +extern __le32 ext4_superblock_csum(struct super_block *sb, + struct ext4_super_block *es); extern void ext4_superblock_csum_set(struct super_block *sb); extern int ext4_alloc_flex_bg_array(struct super_block *sb, ext4_group_t ngroup); @@ -3402,7 +3373,7 @@ do { \ #define EXT4_FREECLUSTERS_WATERMARK 0 #endif -/* Update i_disksize. Requires i_mutex to avoid races with truncate */ +/* Update i_disksize. Requires i_rwsem to avoid races with truncate */ static inline void ext4_update_i_disksize(struct inode *inode, loff_t newsize) { WARN_ON_ONCE(S_ISREG(inode->i_mode) && @@ -3413,7 +3384,7 @@ static inline void ext4_update_i_disksize(struct inode *inode, loff_t newsize) up_write(&EXT4_I(inode)->i_data_sem); } -/* Update i_size, i_disksize. Requires i_mutex to avoid races with truncate */ +/* Update i_size, i_disksize. Requires i_rwsem to avoid races with truncate */ static inline int ext4_update_inode_size(struct inode *inode, loff_t newsize) { int changed = 0; @@ -3441,6 +3412,8 @@ struct ext4_group_info { ext4_grpblk_t bb_first_free; /* first free block */ ext4_grpblk_t bb_free; /* total free blocks */ ext4_grpblk_t bb_fragments; /* nr of freespace fragments */ + int bb_avg_fragment_size_order; /* order of average + fragment in BG */ 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; @@ -3448,7 +3421,7 @@ struct ext4_group_info { void *bb_bitmap; #endif struct rw_semaphore alloc_sem; - struct rb_node bb_avg_fragment_size_rb; + struct list_head bb_avg_fragment_size_node; struct list_head bb_largest_free_order_node; ext4_grpblk_t bb_counters[]; /* Nr of free power-of-two-block * regions, index is order. @@ -3578,7 +3551,6 @@ extern int ext4_readpage_inline(struct inode *inode, struct page *page); extern int ext4_try_to_write_inline_data(struct address_space *mapping, struct inode *inode, loff_t pos, unsigned len, - unsigned flags, struct page **pagep); extern int ext4_write_inline_data_end(struct inode *inode, loff_t pos, unsigned len, @@ -3591,7 +3563,6 @@ ext4_journalled_write_inline_data(struct inode *inode, extern int ext4_da_write_inline_data_begin(struct address_space *mapping, struct inode *inode, loff_t pos, unsigned len, - unsigned flags, struct page **pagep, void **fsdata); extern int ext4_try_add_inline_entry(handle_t *handle, @@ -3621,9 +3592,7 @@ extern bool empty_inline_dir(struct inode *dir, int *has_inline_data); extern struct buffer_head *ext4_get_first_inline_block(struct inode *inode, struct ext4_dir_entry_2 **parent_de, int *retval); -extern int ext4_inline_data_fiemap(struct inode *inode, - struct fiemap_extent_info *fieinfo, - int *has_inline, __u64 start, __u64 len); +extern void *ext4_read_inline_link(struct inode *inode); struct iomap; extern int ext4_inline_data_iomap(struct inode *inode, struct iomap *iomap); @@ -3701,6 +3670,9 @@ extern int ext4_inode_block_valid(struct inode *inode, unsigned int count); extern int ext4_check_blockref(const char *, unsigned int, struct inode *, __le32 *, unsigned int); +extern int ext4_sb_block_valid(struct super_block *sb, struct inode *inode, + ext4_fsblk_t start_blk, unsigned int count); + /* extents.c */ struct ext4_ext_path; @@ -3738,7 +3710,7 @@ extern int ext4_ext_insert_extent(handle_t *, struct inode *, extern struct ext4_ext_path *ext4_find_extent(struct inode *, ext4_lblk_t, struct ext4_ext_path **, int flags); -extern void ext4_ext_drop_refs(struct ext4_ext_path *); +extern void ext4_free_ext_path(struct ext4_ext_path *); extern int ext4_ext_check_inode(struct inode *inode); extern ext4_lblk_t ext4_ext_next_allocated_block(struct ext4_ext_path *path); extern int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, @@ -3837,7 +3809,7 @@ static inline void set_bitmap_uptodate(struct buffer_head *bh) extern wait_queue_head_t ext4__ioend_wq[EXT4_WQ_HASH_SZ]; extern int ext4_resize_begin(struct super_block *sb); -extern void ext4_resize_end(struct super_block *sb); +extern int ext4_resize_end(struct super_block *sb, bool update_backups); static inline void ext4_set_io_unwritten_flag(struct inode *inode, struct ext4_io_end *io_end) diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c index 6def7339056d..8e1fb18f465e 100644 --- a/fs/ext4/ext4_jbd2.c +++ b/fs/ext4/ext4_jbd2.c @@ -162,6 +162,8 @@ int __ext4_journal_ensure_credits(handle_t *handle, int check_cred, { if (!ext4_handle_valid(handle)) return 0; + if (is_handle_aborted(handle)) + return -EROFS; if (jbd2_handle_buffer_credits(handle) >= check_cred && handle->h_revoke_credits >= revoke_cred) return 0; @@ -265,8 +267,7 @@ int __ext4_forget(const char *where, unsigned int line, handle_t *handle, trace_ext4_forget(inode, is_metadata, blocknr); BUFFER_TRACE(bh, "enter"); - jbd_debug(4, "forgetting bh %p: is_metadata = %d, mode %o, " - "data mode %x\n", + ext4_debug("forgetting bh %p: is_metadata=%d, mode %o, data mode %x\n", bh, is_metadata, inode->i_mode, test_opt(inode->i_sb, DATA_FLAGS)); diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h index 0e4fa644df01..db2ae4a2b38d 100644 --- a/fs/ext4/ext4_jbd2.h +++ b/fs/ext4/ext4_jbd2.h @@ -491,7 +491,7 @@ static inline int ext4_free_data_revoke_credits(struct inode *inode, int blocks) /* * This function controls whether or not we should try to go down the * dioread_nolock code paths, which makes it safe to avoid taking - * i_mutex for direct I/O reads. This only works for extent-based + * i_rwsem for direct I/O reads. This only works for extent-based * files, and it doesn't work if data journaling is enabled, since the * dioread_nolock code uses b_private to pass information back to the * I/O completion handler, and this conflicts with the jbd's use of diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 0ecf819bf189..f1956288307f 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -27,8 +27,8 @@ #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/fiemap.h> -#include <linux/backing-dev.h> #include <linux/iomap.h> +#include <linux/sched/mm.h> #include "ext4_jbd2.h" #include "ext4_extents.h" #include "xattr.h" @@ -97,7 +97,7 @@ static int ext4_ext_trunc_restart_fn(struct inode *inode, int *dropped) * Drop i_data_sem to avoid deadlock with ext4_map_blocks. At this * moment, get_block can be called only for blocks inside i_size since * page cache has been already dropped and writes are blocked by - * i_mutex. So we can safely drop the i_data_sem here. + * i_rwsem. So we can safely drop the i_data_sem here. */ BUG_ON(EXT4_JOURNAL(inode) == NULL); ext4_discard_preallocations(inode, 0); @@ -106,6 +106,25 @@ static int ext4_ext_trunc_restart_fn(struct inode *inode, int *dropped) return 0; } +static void ext4_ext_drop_refs(struct ext4_ext_path *path) +{ + int depth, i; + + if (!path) + return; + depth = path->p_depth; + for (i = 0; i <= depth; i++, path++) { + brelse(path->p_bh); + path->p_bh = NULL; + } +} + +void ext4_free_ext_path(struct ext4_ext_path *path) +{ + ext4_ext_drop_refs(path); + kfree(path); +} + /* * Make sure 'handle' has at least 'check_cred' credits. If not, restart * transaction with 'restart_cred' credits. The function drops i_data_sem @@ -372,7 +391,7 @@ static int ext4_valid_extent_entries(struct inode *inode, { unsigned short entries; ext4_lblk_t lblock = 0; - ext4_lblk_t prev = 0; + ext4_lblk_t cur = 0; if (eh->eh_entries == 0) return 1; @@ -396,11 +415,11 @@ static int ext4_valid_extent_entries(struct inode *inode, /* Check for overlapping extents */ lblock = le32_to_cpu(ext->ee_block); - if ((lblock <= prev) && prev) { + if (lblock < cur) { *pblk = ext4_ext_pblock(ext); return 0; } - prev = lblock + ext4_ext_get_actual_len(ext) - 1; + cur = lblock + ext4_ext_get_actual_len(ext); ext++; entries--; } @@ -420,13 +439,13 @@ static int ext4_valid_extent_entries(struct inode *inode, /* Check for overlapping index extents */ lblock = le32_to_cpu(ext_idx->ei_block); - if ((lblock <= prev) && prev) { + if (lblock < cur) { *pblk = ext4_idx_pblock(ext_idx); return 0; } ext_idx++; entries--; - prev = lblock; + cur = lblock + 1; } } return 1; @@ -460,6 +479,10 @@ static int __ext4_ext_check(const char *function, unsigned int line, error_msg = "invalid eh_entries"; goto corrupted; } + if (unlikely((eh->eh_entries == 0) && (depth > 0))) { + error_msg = "eh_entries is 0 but eh_depth is > 0"; + goto corrupted; + } if (!ext4_valid_extent_entries(inode, eh, lblk, &pblk, depth)) { error_msg = "invalid extent entries"; goto corrupted; @@ -632,8 +655,7 @@ int ext4_ext_precache(struct inode *inode) ext4_set_inode_state(inode, EXT4_STATE_EXT_PRECACHED); out: up_read(&ei->i_data_sem); - ext4_ext_drop_refs(path); - kfree(path); + ext4_free_ext_path(path); return ret; } @@ -720,19 +742,6 @@ static void ext4_ext_show_move(struct inode *inode, struct ext4_ext_path *path, #define ext4_ext_show_move(inode, path, newblock, level) #endif -void ext4_ext_drop_refs(struct ext4_ext_path *path) -{ - int depth, i; - - if (!path) - return; - depth = path->p_depth; - for (i = 0; i <= depth; i++, path++) { - brelse(path->p_bh); - path->p_bh = NULL; - } -} - /* * ext4_ext_binsearch_idx: * binary search for the closest index of the given block @@ -951,8 +960,7 @@ ext4_find_extent(struct inode *inode, ext4_lblk_t block, return path; err: - ext4_ext_drop_refs(path); - kfree(path); + ext4_free_ext_path(path); if (orig_path) *orig_path = NULL; return ERR_PTR(ret); @@ -1496,8 +1504,7 @@ static int ext4_ext_search_left(struct inode *inode, EXT4_ERROR_INODE(inode, "ix (%d) != EXT_FIRST_INDEX (%d) (depth %d)!", ix != NULL ? le32_to_cpu(ix->ei_block) : 0, - EXT_FIRST_INDEX(path[depth].p_hdr) != NULL ? - le32_to_cpu(EXT_FIRST_INDEX(path[depth].p_hdr)->ei_block) : 0, + le32_to_cpu(EXT_FIRST_INDEX(path[depth].p_hdr)->ei_block), depth); return -EFSCORRUPTED; } @@ -2025,7 +2032,6 @@ int ext4_ext_insert_extent(handle_t *handle, struct inode *inode, + ext4_ext_get_actual_len(newext)); if (unwritten) ext4_ext_mark_unwritten(ex); - eh = path[depth].p_hdr; nearex = ex; goto merge; } @@ -2054,7 +2060,6 @@ prepend: + ext4_ext_get_actual_len(newext)); if (unwritten) ext4_ext_mark_unwritten(ex); - eh = path[depth].p_hdr; nearex = ex; goto merge; } @@ -2173,8 +2178,7 @@ merge: err = ext4_ext_dirty(handle, inode, path + path->p_depth); cleanup: - ext4_ext_drop_refs(npath); - kfree(npath); + ext4_free_ext_path(npath); return err; } @@ -3060,8 +3064,7 @@ again: } } out: - ext4_ext_drop_refs(path); - kfree(path); + ext4_free_ext_path(path); path = NULL; if (err == -EAGAIN) goto again; @@ -3371,7 +3374,6 @@ static int ext4_split_extent(handle_t *handle, return -EFSCORRUPTED; } unwritten = ext4_ext_is_unwritten(ex); - split_flag1 = 0; if (map->m_lblk >= ee_block) { split_flag1 = split_flag & EXT4_EXT_DATA_VALID2; @@ -4375,8 +4377,7 @@ got_allocated_blocks: allocated = map->m_len; ext4_ext_show_leaf(inode, path); out: - ext4_ext_drop_refs(path); - kfree(path); + ext4_free_ext_path(path); trace_ext4_ext_map_blocks_exit(inode, flags, map, err ? err : allocated); @@ -4407,8 +4408,7 @@ retry: err = ext4_es_remove_extent(inode, last_block, EXT_MAX_BLOCKS - last_block); if (err == -ENOMEM) { - cond_resched(); - congestion_wait(BLK_RW_ASYNC, HZ/50); + memalloc_retry_wait(GFP_ATOMIC); goto retry; } if (err) @@ -4416,8 +4416,7 @@ retry: retry_remove_space: err = ext4_ext_remove_space(inode, last_block, EXT_MAX_BLOCKS - 1); if (err == -ENOMEM) { - cond_resched(); - congestion_wait(BLK_RW_ASYNC, HZ/50); + memalloc_retry_wait(GFP_ATOMIC); goto retry_remove_space; } return err; @@ -4506,9 +4505,9 @@ retry: return ret > 0 ? ret2 : ret; } -static int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len); +static int ext4_collapse_range(struct file *file, loff_t offset, loff_t len); -static int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len); +static int ext4_insert_range(struct file *file, loff_t offset, loff_t len); static long ext4_zero_range(struct file *file, loff_t offset, loff_t len, int mode) @@ -4577,9 +4576,13 @@ static long ext4_zero_range(struct file *file, loff_t offset, flags = EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT; - /* Wait all existing dio workers, newcomers will block on i_mutex */ + /* Wait all existing dio workers, newcomers will block on i_rwsem */ inode_dio_wait(inode); + ret = file_modified(file); + if (ret) + goto out_mutex; + /* Preallocate the range including the unaligned edges */ if (partial_begin || partial_end) { ret = ext4_alloc_file_blocks(file, @@ -4647,8 +4650,6 @@ static long ext4_zero_range(struct file *file, loff_t offset, ret = ext4_mark_inode_dirty(handle, inode); if (unlikely(ret)) goto out_handle; - ext4_fc_track_range(handle, inode, offset >> inode->i_sb->s_blocksize_bits, - (offset + len - 1) >> inode->i_sb->s_blocksize_bits); /* Zero out partial block at the edges of the range */ ret = ext4_zero_partial_blocks(handle, inode, offset, len); if (ret >= 0) @@ -4697,24 +4698,24 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len) FALLOC_FL_INSERT_RANGE)) return -EOPNOTSUPP; - ext4_fc_start_update(inode); + inode_lock(inode); + ret = ext4_convert_inline_data(inode); + inode_unlock(inode); + if (ret) + goto exit; if (mode & FALLOC_FL_PUNCH_HOLE) { - ret = ext4_punch_hole(inode, offset, len); + ret = ext4_punch_hole(file, offset, len); goto exit; } - ret = ext4_convert_inline_data(inode); - if (ret) - goto exit; - if (mode & FALLOC_FL_COLLAPSE_RANGE) { - ret = ext4_collapse_range(inode, offset, len); + ret = ext4_collapse_range(file, offset, len); goto exit; } if (mode & FALLOC_FL_INSERT_RANGE) { - ret = ext4_insert_range(inode, offset, len); + ret = ext4_insert_range(file, offset, len); goto exit; } @@ -4747,9 +4748,13 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len) goto out; } - /* Wait all existing dio workers, newcomers will block on i_mutex */ + /* Wait all existing dio workers, newcomers will block on i_rwsem */ inode_dio_wait(inode); + ret = file_modified(file); + if (ret) + goto out; + ret = ext4_alloc_file_blocks(file, lblk, max_blocks, new_size, flags); if (ret) goto out; @@ -4762,7 +4767,6 @@ out: inode_unlock(inode); trace_ext4_fallocate_exit(inode, offset, max_blocks, ret); exit: - ext4_fc_stop_update(inode); return ret; } @@ -5242,8 +5246,7 @@ again: break; } out: - ext4_ext_drop_refs(path); - kfree(path); + ext4_free_ext_path(path); return ret; } @@ -5252,8 +5255,9 @@ out: * This implements the fallocate's collapse range functionality for ext4 * Returns: 0 and non-zero on error. */ -static int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len) +static int ext4_collapse_range(struct file *file, loff_t offset, loff_t len) { + struct inode *inode = file_inode(file); struct super_block *sb = inode->i_sb; struct address_space *mapping = inode->i_mapping; ext4_lblk_t punch_start, punch_stop; @@ -5305,6 +5309,10 @@ static int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len) /* Wait for existing dio to complete */ inode_dio_wait(inode); + ret = file_modified(file); + if (ret) + goto out_mutex; + /* * Prevent page faults from reinstantiating pages we have released from * page cache. @@ -5344,7 +5352,7 @@ static int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len) ret = PTR_ERR(handle); goto out_mmap; } - ext4_fc_start_ineligible(sb, EXT4_FC_REASON_FALLOC_RANGE); + ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_FALLOC_RANGE, handle); down_write(&EXT4_I(inode)->i_data_sem); ext4_discard_preallocations(inode, 0); @@ -5383,7 +5391,6 @@ static int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len) out_stop: ext4_journal_stop(handle); - ext4_fc_stop_ineligible(sb); out_mmap: filemap_invalidate_unlock(mapping); out_mutex: @@ -5399,8 +5406,9 @@ out_mutex: * by len bytes. * Returns 0 on success, error otherwise. */ -static int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len) +static int ext4_insert_range(struct file *file, loff_t offset, loff_t len) { + struct inode *inode = file_inode(file); struct super_block *sb = inode->i_sb; struct address_space *mapping = inode->i_mapping; handle_t *handle; @@ -5457,6 +5465,10 @@ static int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len) /* Wait for existing dio to complete */ inode_dio_wait(inode); + ret = file_modified(file); + if (ret) + goto out_mutex; + /* * Prevent page faults from reinstantiating pages we have released from * page cache. @@ -5485,7 +5497,7 @@ static int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len) ret = PTR_ERR(handle); goto out_mmap; } - ext4_fc_start_ineligible(sb, EXT4_FC_REASON_FALLOC_RANGE); + ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_FALLOC_RANGE, handle); /* Expand file to avoid data loss if there is error while shifting */ inode->i_size += len; @@ -5526,15 +5538,13 @@ static int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len) EXT4_GET_BLOCKS_METADATA_NOFAIL); } - ext4_ext_drop_refs(path); - kfree(path); + ext4_free_ext_path(path); if (ret < 0) { up_write(&EXT4_I(inode)->i_data_sem); goto out_stop; } } else { - ext4_ext_drop_refs(path); - kfree(path); + ext4_free_ext_path(path); } ret = ext4_es_remove_extent(inode, offset_lblk, @@ -5560,7 +5570,6 @@ static int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len) out_stop: ext4_journal_stop(handle); - ext4_fc_stop_ineligible(sb); out_mmap: filemap_invalidate_unlock(mapping); out_mutex: @@ -5583,7 +5592,7 @@ out_mutex: * stuff such as page-cache locking consistency, bh mapping consistency or * extent's data copying must be performed by caller. * Locking: - * i_mutex is held for both inodes + * i_rwsem is held for both inodes * i_data_sem is locked for write for both inodes * Assumptions: * All pages from requested range are locked for both inodes @@ -5755,10 +5764,8 @@ ext4_swap_extents(handle_t *handle, struct inode *inode1, count -= len; repeat: - ext4_ext_drop_refs(path1); - kfree(path1); - ext4_ext_drop_refs(path2); - kfree(path2); + ext4_free_ext_path(path1); + ext4_free_ext_path(path2); path1 = path2 = NULL; } return replaced_count; @@ -5837,8 +5844,7 @@ int ext4_clu_mapped(struct inode *inode, ext4_lblk_t lclu) } out: - ext4_ext_drop_refs(path); - kfree(path); + ext4_free_ext_path(path); return err ? err : mapped; } @@ -5905,8 +5911,7 @@ int ext4_ext_replay_update_ex(struct inode *inode, ext4_lblk_t start, ret = ext4_ext_dirty(NULL, inode, &path[path->p_depth]); up_write(&EXT4_I(inode)->i_data_sem); out: - ext4_ext_drop_refs(path); - kfree(path); + ext4_free_ext_path(path); ext4_mark_inode_dirty(NULL, inode); return ret; } @@ -5924,8 +5929,7 @@ void ext4_ext_replay_shrink_inode(struct inode *inode, ext4_lblk_t end) return; ex = path[path->p_depth].p_ext; if (!ex) { - ext4_ext_drop_refs(path); - kfree(path); + ext4_free_ext_path(path); ext4_mark_inode_dirty(NULL, inode); return; } @@ -5938,8 +5942,7 @@ void ext4_ext_replay_shrink_inode(struct inode *inode, ext4_lblk_t end) ext4_ext_dirty(NULL, inode, &path[path->p_depth]); up_write(&EXT4_I(inode)->i_data_sem); ext4_mark_inode_dirty(NULL, inode); - ext4_ext_drop_refs(path); - kfree(path); + ext4_free_ext_path(path); } } @@ -5978,13 +5981,11 @@ int ext4_ext_replay_set_iblocks(struct inode *inode) return PTR_ERR(path); ex = path[path->p_depth].p_ext; if (!ex) { - ext4_ext_drop_refs(path); - kfree(path); + ext4_free_ext_path(path); goto out; } end = le32_to_cpu(ex->ee_block) + ext4_ext_get_actual_len(ex); - ext4_ext_drop_refs(path); - kfree(path); + ext4_free_ext_path(path); /* Count the number of data blocks */ cur = 0; @@ -6014,30 +6015,26 @@ int ext4_ext_replay_set_iblocks(struct inode *inode) if (IS_ERR(path)) goto out; numblks += path->p_depth; - ext4_ext_drop_refs(path); - kfree(path); + ext4_free_ext_path(path); while (cur < end) { path = ext4_find_extent(inode, cur, NULL, 0); if (IS_ERR(path)) break; ex = path[path->p_depth].p_ext; if (!ex) { - ext4_ext_drop_refs(path); - kfree(path); + ext4_free_ext_path(path); return 0; } cur = max(cur + 1, le32_to_cpu(ex->ee_block) + ext4_ext_get_actual_len(ex)); ret = skip_hole(inode, &cur); if (ret < 0) { - ext4_ext_drop_refs(path); - kfree(path); + ext4_free_ext_path(path); break; } path2 = ext4_find_extent(inode, cur, NULL, 0); if (IS_ERR(path2)) { - ext4_ext_drop_refs(path); - kfree(path); + ext4_free_ext_path(path); break; } for (i = 0; i <= max(path->p_depth, path2->p_depth); i++) { @@ -6051,10 +6048,8 @@ int ext4_ext_replay_set_iblocks(struct inode *inode) if (cmp1 != cmp2 && cmp2 != 0) numblks++; } - ext4_ext_drop_refs(path); - ext4_ext_drop_refs(path2); - kfree(path); - kfree(path2); + ext4_free_ext_path(path); + ext4_free_ext_path(path2); } out: @@ -6081,13 +6076,11 @@ int ext4_ext_clear_bb(struct inode *inode) return PTR_ERR(path); ex = path[path->p_depth].p_ext; if (!ex) { - ext4_ext_drop_refs(path); - kfree(path); + ext4_free_ext_path(path); return 0; } end = le32_to_cpu(ex->ee_block) + ext4_ext_get_actual_len(ex); - ext4_ext_drop_refs(path); - kfree(path); + ext4_free_ext_path(path); cur = 0; while (cur < end) { @@ -6103,11 +6096,14 @@ int ext4_ext_clear_bb(struct inode *inode) ext4_mb_mark_bb(inode->i_sb, path[j].p_block, 1, 0); + ext4_fc_record_regions(inode->i_sb, inode->i_ino, + 0, path[j].p_block, 1, 1); } - ext4_ext_drop_refs(path); - kfree(path); + ext4_free_ext_path(path); } ext4_mb_mark_bb(inode->i_sb, map.m_pblk, map.m_len, 0); + ext4_fc_record_regions(inode->i_sb, inode->i_ino, + map.m_lblk, map.m_pblk, map.m_len, 1); } cur = cur + map.m_len; } diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c index 9a3a8996aacf..cd0a861853e3 100644 --- a/fs/ext4/extents_status.c +++ b/fs/ext4/extents_status.c @@ -667,8 +667,7 @@ static void ext4_es_insert_extent_ext_check(struct inode *inode, } } out: - ext4_ext_drop_refs(path); - kfree(path); + ext4_free_ext_path(path); } static void ext4_es_insert_extent_ind_check(struct inode *inode, @@ -1654,7 +1653,8 @@ int ext4_es_register_shrinker(struct ext4_sb_info *sbi) sbi->s_es_shrinker.scan_objects = ext4_es_scan; sbi->s_es_shrinker.count_objects = ext4_es_count; sbi->s_es_shrinker.seeks = DEFAULT_SEEKS; - err = register_shrinker(&sbi->s_es_shrinker); + err = register_shrinker(&sbi->s_es_shrinker, "ext4-es:%s", + sbi->s_sb->s_id); if (err) goto err4; diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c index 0f32b445582a..0f6d0a80467d 100644 --- a/fs/ext4/fast_commit.c +++ b/fs/ext4/fast_commit.c @@ -65,21 +65,11 @@ * * Fast Commit Ineligibility * ------------------------- - * Not all operations are supported by fast commits today (e.g extended - * 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 - * back to full commit. This is useful in case of transient errors. * - * - ext4_fc_start_ineligible() and ext4_fc_stop_ineligible() - This makes all - * the fast commits happening between ext4_fc_start_ineligible() and - * ext4_fc_stop_ineligible() and one fast commit after the call to - * ext4_fc_stop_ineligible() to fall back to full commits. It is important to - * make one more fast commit to fall back to full commit after stop call so - * that it guaranteed that the fast commit ineligible operation contained - * within ext4_fc_start_ineligible() and ext4_fc_stop_ineligible() is - * followed by at least 1 full commit. + * Not all operations are supported by fast commits today (e.g extended + * attributes). Fast commit ineligibility is marked by calling + * ext4_fc_mark_ineligible(): This makes next fast commit operation to fall back + * to full commit. * * Atomicity of commits * -------------------- @@ -166,15 +156,13 @@ * fast commit recovery even if that area is invalidated by later full * commits. * - * 1) Make fast commit atomic updates more fine grained. Today, a fast commit - * eligible update must be protected within ext4_fc_start_update() and - * ext4_fc_stop_update(). These routines are called at much higher - * routines. This can be made more fine grained by combining with - * ext4_journal_start(). + * 1) Fast commit's commit path locks the entire file system during fast + * commit. This has significant performance penalty. Instead of that, we + * should use ext4_fc_start/stop_update functions to start inode level + * updates from ext4_journal_start/stop. Once we do that we can drop file + * system locking during commit path. * - * 2) Same above for ext4_fc_start_ineligible() and ext4_fc_stop_ineligible() - * - * 3) Handle more ineligible cases. + * 2) Handle more ineligible cases. */ #include <trace/events/ext4.h> @@ -211,6 +199,7 @@ void ext4_fc_init_inode(struct inode *inode) ext4_fc_reset_inode(inode); ext4_clear_inode_state(inode, EXT4_STATE_FC_COMMITTING); INIT_LIST_HEAD(&ei->i_fc_list); + INIT_LIST_HEAD(&ei->i_fc_dilist); init_waitqueue_head(&ei->i_fc_wait); atomic_set(&ei->i_fc_updates, 0); } @@ -240,6 +229,12 @@ __releases(&EXT4_SB(inode->i_sb)->s_fc_lock) finish_wait(wq, &wait.wq_entry); } +static bool ext4_fc_disabled(struct super_block *sb) +{ + return (!test_opt2(sb, JOURNAL_FAST_COMMIT) || + (EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY)); +} + /* * Inform Ext4's fast about start of an inode update * @@ -251,8 +246,7 @@ void ext4_fc_start_update(struct inode *inode) { struct ext4_inode_info *ei = EXT4_I(inode); - if (!test_opt2(inode->i_sb, JOURNAL_FAST_COMMIT) || - (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY)) + if (ext4_fc_disabled(inode->i_sb)) return; restart: @@ -276,8 +270,7 @@ void ext4_fc_stop_update(struct inode *inode) { struct ext4_inode_info *ei = EXT4_I(inode); - if (!test_opt2(inode->i_sb, JOURNAL_FAST_COMMIT) || - (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY)) + if (ext4_fc_disabled(inode->i_sb)) return; if (atomic_dec_and_test(&ei->i_fc_updates)) @@ -291,14 +284,15 @@ void ext4_fc_stop_update(struct inode *inode) void ext4_fc_del(struct inode *inode) { struct ext4_inode_info *ei = EXT4_I(inode); + struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); + struct ext4_fc_dentry_update *fc_dentry; - if (!test_opt2(inode->i_sb, JOURNAL_FAST_COMMIT) || - (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY)) + if (ext4_fc_disabled(inode->i_sb)) return; restart: spin_lock(&EXT4_SB(inode->i_sb)->s_fc_lock); - if (list_empty(&ei->i_fc_list)) { + if (list_empty(&ei->i_fc_list) && list_empty(&ei->i_fc_dilist)) { spin_unlock(&EXT4_SB(inode->i_sb)->s_fc_lock); return; } @@ -307,63 +301,63 @@ restart: ext4_fc_wait_committing_inode(inode); goto restart; } - list_del_init(&ei->i_fc_list); - spin_unlock(&EXT4_SB(inode->i_sb)->s_fc_lock); -} -/* - * Mark file system as fast commit ineligible. This means that next commit - * operation would result in a full jbd2 commit. - */ -void ext4_fc_mark_ineligible(struct super_block *sb, int reason) -{ - struct ext4_sb_info *sbi = EXT4_SB(sb); + if (!list_empty(&ei->i_fc_list)) + list_del_init(&ei->i_fc_list); - if (!test_opt2(sb, JOURNAL_FAST_COMMIT) || - (EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY)) + /* + * Since this inode is getting removed, let's also remove all FC + * dentry create references, since it is not needed to log it anyways. + */ + if (list_empty(&ei->i_fc_dilist)) { + spin_unlock(&sbi->s_fc_lock); return; + } - ext4_set_mount_flag(sb, EXT4_MF_FC_INELIGIBLE); - WARN_ON(reason >= EXT4_FC_REASON_MAX); - sbi->s_fc_stats.fc_ineligible_reason_count[reason]++; -} + fc_dentry = list_first_entry(&ei->i_fc_dilist, struct ext4_fc_dentry_update, fcd_dilist); + WARN_ON(fc_dentry->fcd_op != EXT4_FC_TAG_CREAT); + list_del_init(&fc_dentry->fcd_list); + list_del_init(&fc_dentry->fcd_dilist); -/* - * Start a fast commit ineligible update. Any commits that happen while - * such an operation is in progress fall back to full commits. - */ -void ext4_fc_start_ineligible(struct super_block *sb, int reason) -{ - struct ext4_sb_info *sbi = EXT4_SB(sb); + WARN_ON(!list_empty(&ei->i_fc_dilist)); + spin_unlock(&sbi->s_fc_lock); - if (!test_opt2(sb, JOURNAL_FAST_COMMIT) || - (EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY)) - return; + if (fc_dentry->fcd_name.name && + fc_dentry->fcd_name.len > DNAME_INLINE_LEN) + kfree(fc_dentry->fcd_name.name); + kmem_cache_free(ext4_fc_dentry_cachep, fc_dentry); - WARN_ON(reason >= EXT4_FC_REASON_MAX); - sbi->s_fc_stats.fc_ineligible_reason_count[reason]++; - atomic_inc(&sbi->s_fc_ineligible_updates); + return; } /* - * Stop a fast commit ineligible update. We set EXT4_MF_FC_INELIGIBLE flag here - * to ensure that after stopping the ineligible update, at least one full - * commit takes place. + * Mark file system as fast commit ineligible, and record latest + * ineligible transaction tid. This means until the recorded + * transaction, commit operation would result in a full jbd2 commit. */ -void ext4_fc_stop_ineligible(struct super_block *sb) +void ext4_fc_mark_ineligible(struct super_block *sb, int reason, handle_t *handle) { - if (!test_opt2(sb, JOURNAL_FAST_COMMIT) || - (EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY)) + struct ext4_sb_info *sbi = EXT4_SB(sb); + tid_t tid; + + if (ext4_fc_disabled(sb)) return; ext4_set_mount_flag(sb, EXT4_MF_FC_INELIGIBLE); - atomic_dec(&EXT4_SB(sb)->s_fc_ineligible_updates); -} - -static inline int ext4_fc_is_ineligible(struct super_block *sb) -{ - return (ext4_test_mount_flag(sb, EXT4_MF_FC_INELIGIBLE) || - atomic_read(&EXT4_SB(sb)->s_fc_ineligible_updates)); + if (handle && !IS_ERR(handle)) + tid = handle->h_transaction->t_tid; + else { + read_lock(&sbi->s_journal->j_state_lock); + tid = sbi->s_journal->j_running_transaction ? + sbi->s_journal->j_running_transaction->t_tid : 0; + read_unlock(&sbi->s_journal->j_state_lock); + } + spin_lock(&sbi->s_fc_lock); + if (sbi->s_fc_ineligible_tid < tid) + sbi->s_fc_ineligible_tid = tid; + spin_unlock(&sbi->s_fc_lock); + WARN_ON(reason >= EXT4_FC_REASON_MAX); + sbi->s_fc_stats.fc_ineligible_reason_count[reason]++; } /* @@ -387,13 +381,6 @@ static int ext4_fc_track_template( tid_t tid = 0; int ret; - if (!test_opt2(inode->i_sb, JOURNAL_FAST_COMMIT) || - (sbi->s_mount_state & EXT4_FC_REPLAY)) - return -EOPNOTSUPP; - - if (ext4_fc_is_ineligible(inode->i_sb)) - return -EINVAL; - tid = handle->h_transaction->t_tid; mutex_lock(&ei->i_fc_lock); if (tid == ei->i_sync_tid) { @@ -411,7 +398,8 @@ static int ext4_fc_track_template( spin_lock(&sbi->s_fc_lock); if (list_empty(&EXT4_I(inode)->i_fc_list)) list_add_tail(&EXT4_I(inode)->i_fc_list, - (ext4_test_mount_flag(inode->i_sb, EXT4_MF_FC_COMMITTING)) ? + (sbi->s_journal->j_flags & JBD2_FULL_COMMIT_ONGOING || + sbi->s_journal->j_flags & JBD2_FAST_COMMIT_ONGOING) ? &sbi->s_fc_q[FC_Q_STAGING] : &sbi->s_fc_q[FC_Q_MAIN]); spin_unlock(&sbi->s_fc_lock); @@ -437,7 +425,7 @@ static int __track_dentry_update(struct inode *inode, void *arg, bool update) mutex_unlock(&ei->i_fc_lock); node = kmem_cache_alloc(ext4_fc_dentry_cachep, GFP_NOFS); if (!node) { - ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_NOMEM); + ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_NOMEM, NULL); mutex_lock(&ei->i_fc_lock); return -ENOMEM; } @@ -450,7 +438,7 @@ static int __track_dentry_update(struct inode *inode, void *arg, bool update) if (!node->fcd_name.name) { kmem_cache_free(ext4_fc_dentry_cachep, node); ext4_fc_mark_ineligible(inode->i_sb, - EXT4_FC_REASON_NOMEM); + EXT4_FC_REASON_NOMEM, NULL); mutex_lock(&ei->i_fc_lock); return -ENOMEM; } @@ -462,13 +450,28 @@ static int __track_dentry_update(struct inode *inode, void *arg, bool update) node->fcd_name.name = node->fcd_iname; } node->fcd_name.len = dentry->d_name.len; - + INIT_LIST_HEAD(&node->fcd_dilist); spin_lock(&sbi->s_fc_lock); - if (ext4_test_mount_flag(inode->i_sb, EXT4_MF_FC_COMMITTING)) + if (sbi->s_journal->j_flags & JBD2_FULL_COMMIT_ONGOING || + sbi->s_journal->j_flags & JBD2_FAST_COMMIT_ONGOING) list_add_tail(&node->fcd_list, &sbi->s_fc_dentry_q[FC_Q_STAGING]); else list_add_tail(&node->fcd_list, &sbi->s_fc_dentry_q[FC_Q_MAIN]); + + /* + * This helps us keep a track of all fc_dentry updates which is part of + * this ext4 inode. So in case the inode is getting unlinked, before + * even we get a chance to fsync, we could remove all fc_dentry + * references while evicting the inode in ext4_fc_del(). + * Also with this, we don't need to loop over all the inodes in + * sbi->s_fc_q to get the corresponding inode in + * ext4_fc_commit_dentry_updates(). + */ + if (dentry_update->op == EXT4_FC_TAG_CREAT) { + WARN_ON(!list_empty(&ei->i_fc_dilist)); + list_add_tail(&node->fcd_dilist, &ei->i_fc_dilist); + } spin_unlock(&sbi->s_fc_lock); mutex_lock(&ei->i_fc_lock); @@ -486,12 +489,20 @@ void __ext4_fc_track_unlink(handle_t *handle, ret = ext4_fc_track_template(handle, inode, __track_dentry_update, (void *)&args, 0); - trace_ext4_fc_track_unlink(inode, dentry, ret); + trace_ext4_fc_track_unlink(handle, inode, dentry, ret); } void ext4_fc_track_unlink(handle_t *handle, struct dentry *dentry) { - __ext4_fc_track_unlink(handle, d_inode(dentry), dentry); + struct inode *inode = d_inode(dentry); + + if (ext4_fc_disabled(inode->i_sb)) + return; + + if (ext4_test_mount_flag(inode->i_sb, EXT4_MF_FC_INELIGIBLE)) + return; + + __ext4_fc_track_unlink(handle, inode, dentry); } void __ext4_fc_track_link(handle_t *handle, @@ -505,12 +516,20 @@ void __ext4_fc_track_link(handle_t *handle, ret = ext4_fc_track_template(handle, inode, __track_dentry_update, (void *)&args, 0); - trace_ext4_fc_track_link(inode, dentry, ret); + trace_ext4_fc_track_link(handle, inode, dentry, ret); } void ext4_fc_track_link(handle_t *handle, struct dentry *dentry) { - __ext4_fc_track_link(handle, d_inode(dentry), dentry); + struct inode *inode = d_inode(dentry); + + if (ext4_fc_disabled(inode->i_sb)) + return; + + if (ext4_test_mount_flag(inode->i_sb, EXT4_MF_FC_INELIGIBLE)) + return; + + __ext4_fc_track_link(handle, inode, dentry); } void __ext4_fc_track_create(handle_t *handle, struct inode *inode, @@ -524,12 +543,20 @@ void __ext4_fc_track_create(handle_t *handle, struct inode *inode, ret = ext4_fc_track_template(handle, inode, __track_dentry_update, (void *)&args, 0); - trace_ext4_fc_track_create(inode, dentry, ret); + trace_ext4_fc_track_create(handle, inode, dentry, ret); } void ext4_fc_track_create(handle_t *handle, struct dentry *dentry) { - __ext4_fc_track_create(handle, d_inode(dentry), dentry); + struct inode *inode = d_inode(dentry); + + if (ext4_fc_disabled(inode->i_sb)) + return; + + if (ext4_test_mount_flag(inode->i_sb, EXT4_MF_FC_INELIGIBLE)) + return; + + __ext4_fc_track_create(handle, inode, dentry); } /* __track_fn for inode tracking */ @@ -550,14 +577,20 @@ void ext4_fc_track_inode(handle_t *handle, struct inode *inode) if (S_ISDIR(inode->i_mode)) return; + if (ext4_fc_disabled(inode->i_sb)) + return; + if (ext4_should_journal_data(inode)) { ext4_fc_mark_ineligible(inode->i_sb, - EXT4_FC_REASON_INODE_JOURNAL_DATA); + EXT4_FC_REASON_INODE_JOURNAL_DATA, handle); return; } + if (ext4_test_mount_flag(inode->i_sb, EXT4_MF_FC_INELIGIBLE)) + return; + ret = ext4_fc_track_template(handle, inode, __track_inode, NULL, 1); - trace_ext4_fc_track_inode(inode, ret); + trace_ext4_fc_track_inode(handle, inode, ret); } struct __track_range_args { @@ -601,17 +634,23 @@ void ext4_fc_track_range(handle_t *handle, struct inode *inode, ext4_lblk_t star if (S_ISDIR(inode->i_mode)) return; + if (ext4_fc_disabled(inode->i_sb)) + return; + + if (ext4_test_mount_flag(inode->i_sb, EXT4_MF_FC_INELIGIBLE)) + return; + args.start = start; args.end = end; ret = ext4_fc_track_template(handle, inode, __track_range, &args, 1); - trace_ext4_fc_track_range(inode, start, end, ret); + trace_ext4_fc_track_range(handle, inode, start, end, ret); } static void ext4_fc_submit_bh(struct super_block *sb, bool is_tail) { - int write_flags = REQ_SYNC; + blk_opf_t write_flags = REQ_SYNC; struct buffer_head *bh = EXT4_SB(sb)->s_fc_bh; /* Add REQ_FUA | REQ_PREFLUSH only its tail */ @@ -621,7 +660,7 @@ static void ext4_fc_submit_bh(struct super_block *sb, bool is_tail) set_buffer_dirty(bh); set_buffer_uptodate(bh); bh->b_end_io = ext4_end_buffer_io_sync; - submit_bh(REQ_OP_WRITE, write_flags, bh); + submit_bh(REQ_OP_WRITE | write_flags, bh); EXT4_SB(sb)->s_fc_bh = NULL; } @@ -663,10 +702,10 @@ static u8 *ext4_fc_reserve_space(struct super_block *sb, int len, u32 *crc) * After allocating len, we should have space at least for a 0 byte * padding. */ - if (len + sizeof(struct ext4_fc_tl) > bsize) + if (len + EXT4_FC_TAG_BASE_LEN > bsize) return NULL; - if (bsize - off - 1 > len + sizeof(struct ext4_fc_tl)) { + if (bsize - off - 1 > len + EXT4_FC_TAG_BASE_LEN) { /* * Only allocate from current buffer if we have enough space for * this request AND we have space to add a zero byte padding. @@ -683,10 +722,10 @@ static u8 *ext4_fc_reserve_space(struct super_block *sb, int len, u32 *crc) /* Need to add PAD tag */ tl = (struct ext4_fc_tl *)(sbi->s_fc_bh->b_data + off); tl->fc_tag = cpu_to_le16(EXT4_FC_TAG_PAD); - pad_len = bsize - off - 1 - sizeof(struct ext4_fc_tl); + pad_len = bsize - off - 1 - EXT4_FC_TAG_BASE_LEN; tl->fc_len = cpu_to_le16(pad_len); if (crc) - *crc = ext4_chksum(sbi, *crc, tl, sizeof(*tl)); + *crc = ext4_chksum(sbi, *crc, tl, EXT4_FC_TAG_BASE_LEN); if (pad_len > 0) ext4_fc_memzero(sb, tl + 1, pad_len, crc); ext4_fc_submit_bh(sb, false); @@ -728,7 +767,7 @@ static int ext4_fc_write_tail(struct super_block *sb, u32 crc) * ext4_fc_reserve_space takes care of allocating an extra block if * there's no enough space on this block for accommodating this tail. */ - dst = ext4_fc_reserve_space(sb, sizeof(tl) + sizeof(tail), &crc); + dst = ext4_fc_reserve_space(sb, EXT4_FC_TAG_BASE_LEN + sizeof(tail), &crc); if (!dst) return -ENOSPC; @@ -738,8 +777,8 @@ static int ext4_fc_write_tail(struct super_block *sb, u32 crc) tl.fc_len = cpu_to_le16(bsize - off - 1 + sizeof(struct ext4_fc_tail)); sbi->s_fc_bytes = round_up(sbi->s_fc_bytes, bsize); - ext4_fc_memcpy(sb, dst, &tl, sizeof(tl), &crc); - dst += sizeof(tl); + ext4_fc_memcpy(sb, dst, &tl, EXT4_FC_TAG_BASE_LEN, &crc); + dst += EXT4_FC_TAG_BASE_LEN; tail.fc_tid = cpu_to_le32(sbi->s_journal->j_running_transaction->t_tid); ext4_fc_memcpy(sb, dst, &tail.fc_tid, sizeof(tail.fc_tid), &crc); dst += sizeof(tail.fc_tid); @@ -761,15 +800,15 @@ static bool ext4_fc_add_tlv(struct super_block *sb, u16 tag, u16 len, u8 *val, struct ext4_fc_tl tl; u8 *dst; - dst = ext4_fc_reserve_space(sb, sizeof(tl) + len, crc); + dst = ext4_fc_reserve_space(sb, EXT4_FC_TAG_BASE_LEN + len, crc); if (!dst) return false; tl.fc_tag = cpu_to_le16(tag); tl.fc_len = cpu_to_le16(len); - ext4_fc_memcpy(sb, dst, &tl, sizeof(tl), crc); - ext4_fc_memcpy(sb, dst + sizeof(tl), val, len, crc); + ext4_fc_memcpy(sb, dst, &tl, EXT4_FC_TAG_BASE_LEN, crc); + ext4_fc_memcpy(sb, dst + EXT4_FC_TAG_BASE_LEN, val, len, crc); return true; } @@ -781,8 +820,8 @@ static bool ext4_fc_add_dentry_tlv(struct super_block *sb, u32 *crc, struct ext4_fc_dentry_info fcd; struct ext4_fc_tl tl; int dlen = fc_dentry->fcd_name.len; - u8 *dst = ext4_fc_reserve_space(sb, sizeof(tl) + sizeof(fcd) + dlen, - crc); + u8 *dst = ext4_fc_reserve_space(sb, + EXT4_FC_TAG_BASE_LEN + sizeof(fcd) + dlen, crc); if (!dst) return false; @@ -791,12 +830,11 @@ static bool ext4_fc_add_dentry_tlv(struct super_block *sb, u32 *crc, fcd.fc_ino = cpu_to_le32(fc_dentry->fcd_ino); tl.fc_tag = cpu_to_le16(fc_dentry->fcd_op); tl.fc_len = cpu_to_le16(sizeof(fcd) + dlen); - ext4_fc_memcpy(sb, dst, &tl, sizeof(tl), crc); - dst += sizeof(tl); + ext4_fc_memcpy(sb, dst, &tl, EXT4_FC_TAG_BASE_LEN, crc); + dst += EXT4_FC_TAG_BASE_LEN; ext4_fc_memcpy(sb, dst, &fcd, sizeof(fcd), crc); dst += sizeof(fcd); ext4_fc_memcpy(sb, dst, fc_dentry->fcd_name.name, dlen, crc); - dst += dlen; return true; } @@ -828,22 +866,25 @@ static int ext4_fc_write_inode(struct inode *inode, u32 *crc) tl.fc_tag = cpu_to_le16(EXT4_FC_TAG_INODE); tl.fc_len = cpu_to_le16(inode_len + sizeof(fc_inode.fc_ino)); + ret = -ECANCELED; dst = ext4_fc_reserve_space(inode->i_sb, - sizeof(tl) + inode_len + sizeof(fc_inode.fc_ino), crc); + EXT4_FC_TAG_BASE_LEN + inode_len + sizeof(fc_inode.fc_ino), crc); if (!dst) - return -ECANCELED; + goto err; - if (!ext4_fc_memcpy(inode->i_sb, dst, &tl, sizeof(tl), crc)) - return -ECANCELED; - dst += sizeof(tl); + if (!ext4_fc_memcpy(inode->i_sb, dst, &tl, EXT4_FC_TAG_BASE_LEN, crc)) + goto err; + dst += EXT4_FC_TAG_BASE_LEN; if (!ext4_fc_memcpy(inode->i_sb, dst, &fc_inode, sizeof(fc_inode), crc)) - return -ECANCELED; + goto err; dst += sizeof(fc_inode); if (!ext4_fc_memcpy(inode->i_sb, dst, (u8 *)ext4_raw_inode(&iloc), inode_len, crc)) - return -ECANCELED; - - return 0; + goto err; + ret = 0; +err: + brelse(iloc.bh); + return ret; } /* @@ -871,8 +912,8 @@ static int ext4_fc_write_inode_data(struct inode *inode, u32 *crc) mutex_unlock(&ei->i_fc_lock); cur_lblk_off = old_blk_size; - jbd_debug(1, "%s: will try writing %d to %d for inode %ld\n", - __func__, cur_lblk_off, new_blk_size, inode->i_ino); + ext4_debug("will try writing %d to %d for inode %ld\n", + cur_lblk_off, new_blk_size, inode->i_ino); while (cur_lblk_off <= new_blk_size) { map.m_lblk = cur_lblk_off; @@ -924,13 +965,12 @@ static int ext4_fc_write_inode_data(struct inode *inode, u32 *crc) /* Submit data for all the fast commit inodes */ static int ext4_fc_submit_inode_data_all(journal_t *journal) { - struct super_block *sb = (struct super_block *)(journal->j_private); + struct super_block *sb = journal->j_private; struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_inode_info *ei; int ret = 0; spin_lock(&sbi->s_fc_lock); - ext4_set_mount_flag(sb, EXT4_MF_FC_COMMITTING); list_for_each_entry(ei, &sbi->s_fc_q[FC_Q_MAIN], i_fc_list) { ext4_set_inode_state(&ei->vfs_inode, EXT4_STATE_FC_COMMITTING); while (atomic_read(&ei->i_fc_updates)) { @@ -959,7 +999,7 @@ static int ext4_fc_submit_inode_data_all(journal_t *journal) /* Wait for completion of data for all the fast commit inodes */ static int ext4_fc_wait_inode_data_all(journal_t *journal) { - struct super_block *sb = (struct super_block *)(journal->j_private); + struct super_block *sb = journal->j_private; struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_inode_info *pos, *n; int ret = 0; @@ -986,11 +1026,11 @@ static int ext4_fc_commit_dentry_updates(journal_t *journal, u32 *crc) __acquires(&sbi->s_fc_lock) __releases(&sbi->s_fc_lock) { - struct super_block *sb = (struct super_block *)(journal->j_private); + struct super_block *sb = journal->j_private; struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_fc_dentry_update *fc_dentry, *fc_dentry_n; struct inode *inode; - struct ext4_inode_info *ei, *ei_n; + struct ext4_inode_info *ei; int ret; if (list_empty(&sbi->s_fc_dentry_q[FC_Q_MAIN])) @@ -1006,21 +1046,16 @@ __releases(&sbi->s_fc_lock) spin_lock(&sbi->s_fc_lock); continue; } - - inode = NULL; - list_for_each_entry_safe(ei, ei_n, &sbi->s_fc_q[FC_Q_MAIN], - i_fc_list) { - if (ei->vfs_inode.i_ino == fc_dentry->fcd_ino) { - inode = &ei->vfs_inode; - break; - } - } /* - * If we don't find inode in our list, then it was deleted, - * in which case, we don't need to record it's create tag. + * With fcd_dilist we need not loop in sbi->s_fc_q to get the + * corresponding inode pointer */ - if (!inode) - continue; + WARN_ON(list_empty(&fc_dentry->fcd_dilist)); + ei = list_first_entry(&fc_dentry->fcd_dilist, + struct ext4_inode_info, i_fc_dilist); + inode = &ei->vfs_inode; + WARN_ON(inode->i_ino != fc_dentry->fcd_ino); + spin_unlock(&sbi->s_fc_lock); /* @@ -1053,7 +1088,7 @@ lock_and_exit: static int ext4_fc_perform_commit(journal_t *journal) { - struct super_block *sb = (struct super_block *)(journal->j_private); + struct super_block *sb = journal->j_private; struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_inode_info *iter; struct ext4_fc_head head; @@ -1123,6 +1158,33 @@ out: return ret; } +static void ext4_fc_update_stats(struct super_block *sb, int status, + u64 commit_time, int nblks, tid_t commit_tid) +{ + struct ext4_fc_stats *stats = &EXT4_SB(sb)->s_fc_stats; + + ext4_debug("Fast commit ended with status = %d for tid %u", + status, commit_tid); + if (status == EXT4_FC_STATUS_OK) { + stats->fc_num_commits++; + stats->fc_numblks += nblks; + if (likely(stats->s_fc_avg_commit_time)) + stats->s_fc_avg_commit_time = + (commit_time + + stats->s_fc_avg_commit_time * 3) / 4; + else + stats->s_fc_avg_commit_time = commit_time; + } else if (status == EXT4_FC_STATUS_FAILED || + status == EXT4_FC_STATUS_INELIGIBLE) { + if (status == EXT4_FC_STATUS_FAILED) + stats->fc_failed_commits++; + stats->fc_ineligible_commits++; + } else { + stats->fc_skipped_commits++; + } + trace_ext4_fc_commit_stop(sb, nblks, status, commit_tid); +} + /* * The main commit entry point. Performs a fast commit for transaction * commit_tid if needed. If it's not possible to perform a fast commit @@ -1131,22 +1193,19 @@ out: */ int ext4_fc_commit(journal_t *journal, tid_t commit_tid) { - struct super_block *sb = (struct super_block *)(journal->j_private); + struct super_block *sb = journal->j_private; struct ext4_sb_info *sbi = EXT4_SB(sb); int nblks = 0, ret, bsize = journal->j_blocksize; int subtid = atomic_read(&sbi->s_fc_subtid); - int reason = EXT4_FC_REASON_OK, fc_bufs_before = 0; + int status = EXT4_FC_STATUS_OK, fc_bufs_before = 0; ktime_t start_time, commit_time; - trace_ext4_fc_commit_start(sb); + if (!test_opt2(sb, JOURNAL_FAST_COMMIT)) + return jbd2_complete_transaction(journal, commit_tid); - start_time = ktime_get(); + trace_ext4_fc_commit_start(sb, commit_tid); - if (!test_opt2(sb, JOURNAL_FAST_COMMIT) || - (ext4_fc_is_ineligible(sb))) { - reason = EXT4_FC_REASON_INELIGIBLE; - goto out; - } + start_time = ktime_get(); restart_fc: ret = jbd2_fc_begin_commit(journal, commit_tid); @@ -1155,74 +1214,61 @@ restart_fc: if (atomic_read(&sbi->s_fc_subtid) <= subtid && commit_tid > journal->j_commit_sequence) goto restart_fc; - reason = EXT4_FC_REASON_ALREADY_COMMITTED; - goto out; + ext4_fc_update_stats(sb, EXT4_FC_STATUS_SKIPPED, 0, 0, + commit_tid); + return 0; } else if (ret) { - sbi->s_fc_stats.fc_ineligible_reason_count[EXT4_FC_COMMIT_FAILED]++; - reason = EXT4_FC_REASON_FC_START_FAILED; - goto out; + /* + * Commit couldn't start. Just update stats and perform a + * full commit. + */ + ext4_fc_update_stats(sb, EXT4_FC_STATUS_FAILED, 0, 0, + commit_tid); + return jbd2_complete_transaction(journal, commit_tid); + } + + /* + * After establishing journal barrier via jbd2_fc_begin_commit(), check + * if we are fast commit ineligible. + */ + if (ext4_test_mount_flag(sb, EXT4_MF_FC_INELIGIBLE)) { + status = EXT4_FC_STATUS_INELIGIBLE; + goto fallback; } fc_bufs_before = (sbi->s_fc_bytes + bsize - 1) / bsize; ret = ext4_fc_perform_commit(journal); if (ret < 0) { - sbi->s_fc_stats.fc_ineligible_reason_count[EXT4_FC_COMMIT_FAILED]++; - reason = EXT4_FC_REASON_FC_FAILED; - goto out; + status = EXT4_FC_STATUS_FAILED; + goto fallback; } nblks = (sbi->s_fc_bytes + bsize - 1) / bsize - fc_bufs_before; ret = jbd2_fc_wait_bufs(journal, nblks); if (ret < 0) { - sbi->s_fc_stats.fc_ineligible_reason_count[EXT4_FC_COMMIT_FAILED]++; - reason = EXT4_FC_REASON_FC_FAILED; - goto out; + status = EXT4_FC_STATUS_FAILED; + goto fallback; } atomic_inc(&sbi->s_fc_subtid); - jbd2_fc_end_commit(journal); -out: - /* Has any ineligible update happened since we started? */ - if (reason == EXT4_FC_REASON_OK && ext4_fc_is_ineligible(sb)) { - sbi->s_fc_stats.fc_ineligible_reason_count[EXT4_FC_COMMIT_FAILED]++; - reason = EXT4_FC_REASON_INELIGIBLE; - } - - spin_lock(&sbi->s_fc_lock); - if (reason != EXT4_FC_REASON_OK && - reason != EXT4_FC_REASON_ALREADY_COMMITTED) { - sbi->s_fc_stats.fc_ineligible_commits++; - } else { - sbi->s_fc_stats.fc_num_commits++; - sbi->s_fc_stats.fc_numblks += nblks; - } - spin_unlock(&sbi->s_fc_lock); - nblks = (reason == EXT4_FC_REASON_OK) ? nblks : 0; - trace_ext4_fc_commit_stop(sb, nblks, reason); - commit_time = ktime_to_ns(ktime_sub(ktime_get(), start_time)); + ret = jbd2_fc_end_commit(journal); /* - * weight the commit time higher than the average time so we don't - * react too strongly to vast changes in the commit time + * weight the commit time higher than the average time so we + * don't react too strongly to vast changes in the commit time */ - if (likely(sbi->s_fc_avg_commit_time)) - sbi->s_fc_avg_commit_time = (commit_time + - sbi->s_fc_avg_commit_time * 3) / 4; - else - sbi->s_fc_avg_commit_time = commit_time; - jbd_debug(1, - "Fast commit ended with blks = %d, reason = %d, subtid - %d", - nblks, reason, subtid); - if (reason == EXT4_FC_REASON_FC_FAILED) - return jbd2_fc_end_commit_fallback(journal); - if (reason == EXT4_FC_REASON_FC_START_FAILED || - reason == EXT4_FC_REASON_INELIGIBLE) - return jbd2_complete_transaction(journal, commit_tid); - return 0; + commit_time = ktime_to_ns(ktime_sub(ktime_get(), start_time)); + ext4_fc_update_stats(sb, status, commit_time, nblks, commit_tid); + return ret; + +fallback: + ret = jbd2_fc_end_commit_fallback(journal); + ext4_fc_update_stats(sb, status, 0, 0, commit_tid); + return ret; } /* * Fast commit cleanup routine. This is called after every fast commit and * full commit. full is true if we are called after a full commit. */ -static void ext4_fc_cleanup(journal_t *journal, int full) +static void ext4_fc_cleanup(journal_t *journal, int full, tid_t tid) { struct super_block *sb = journal->j_private; struct ext4_sb_info *sbi = EXT4_SB(sb); @@ -1232,6 +1278,7 @@ static void ext4_fc_cleanup(journal_t *journal, int full) if (full && sbi->s_fc_bh) sbi->s_fc_bh = NULL; + trace_ext4_fc_cleanup(journal, full, tid); jbd2_fc_release_bufs(journal); spin_lock(&sbi->s_fc_lock); @@ -1240,7 +1287,8 @@ static void ext4_fc_cleanup(journal_t *journal, int full) list_del_init(&iter->i_fc_list); ext4_clear_inode_state(&iter->vfs_inode, EXT4_STATE_FC_COMMITTING); - ext4_fc_reset_inode(&iter->vfs_inode); + if (iter->i_sync_tid <= tid) + ext4_fc_reset_inode(&iter->vfs_inode); /* Make sure EXT4_STATE_FC_COMMITTING bit is clear */ smp_mb(); #if (BITS_PER_LONG < 64) @@ -1255,6 +1303,7 @@ static void ext4_fc_cleanup(journal_t *journal, int full) struct ext4_fc_dentry_update, fcd_list); list_del_init(&fc_dentry->fcd_list); + list_del_init(&fc_dentry->fcd_dilist); spin_unlock(&sbi->s_fc_lock); if (fc_dentry->fcd_name.name && @@ -1269,8 +1318,10 @@ static void ext4_fc_cleanup(journal_t *journal, int full) list_splice_init(&sbi->s_fc_q[FC_Q_STAGING], &sbi->s_fc_q[FC_Q_MAIN]); - ext4_clear_mount_flag(sb, EXT4_MF_FC_COMMITTING); - ext4_clear_mount_flag(sb, EXT4_MF_FC_INELIGIBLE); + if (tid >= sbi->s_fc_ineligible_tid) { + sbi->s_fc_ineligible_tid = 0; + ext4_clear_mount_flag(sb, EXT4_MF_FC_INELIGIBLE); + } if (full) sbi->s_fc_bytes = 0; @@ -1287,7 +1338,7 @@ struct dentry_info_args { }; static inline void tl_to_darg(struct dentry_info_args *darg, - struct ext4_fc_tl *tl, u8 *val) + struct ext4_fc_tl *tl, u8 *val) { struct ext4_fc_dentry_info fcd; @@ -1296,8 +1347,14 @@ static inline void tl_to_darg(struct dentry_info_args *darg, darg->parent_ino = le32_to_cpu(fcd.fc_parent_ino); darg->ino = le32_to_cpu(fcd.fc_ino); darg->dname = val + offsetof(struct ext4_fc_dentry_info, fc_dname); - darg->dname_len = le16_to_cpu(tl->fc_len) - - sizeof(struct ext4_fc_dentry_info); + darg->dname_len = tl->fc_len - sizeof(struct ext4_fc_dentry_info); +} + +static inline void ext4_fc_get_tl(struct ext4_fc_tl *tl, u8 *val) +{ + memcpy(tl, val, EXT4_FC_TAG_BASE_LEN); + tl->fc_len = le16_to_cpu(tl->fc_len); + tl->fc_tag = le16_to_cpu(tl->fc_tag); } /* Unlink replay function */ @@ -1319,14 +1376,14 @@ static int ext4_fc_replay_unlink(struct super_block *sb, struct ext4_fc_tl *tl, inode = ext4_iget(sb, darg.ino, EXT4_IGET_NORMAL); if (IS_ERR(inode)) { - jbd_debug(1, "Inode %d not found", darg.ino); + ext4_debug("Inode %d not found", darg.ino); return 0; } old_parent = ext4_iget(sb, darg.parent_ino, EXT4_IGET_NORMAL); if (IS_ERR(old_parent)) { - jbd_debug(1, "Dir with inode %d not found", darg.parent_ino); + ext4_debug("Dir with inode %d not found", darg.parent_ino); iput(inode); return 0; } @@ -1351,21 +1408,21 @@ static int ext4_fc_replay_link_internal(struct super_block *sb, dir = ext4_iget(sb, darg->parent_ino, EXT4_IGET_NORMAL); if (IS_ERR(dir)) { - jbd_debug(1, "Dir with inode %d not found.", darg->parent_ino); + ext4_debug("Dir with inode %d not found.", darg->parent_ino); dir = NULL; goto out; } dentry_dir = d_obtain_alias(dir); if (IS_ERR(dentry_dir)) { - jbd_debug(1, "Failed to obtain dentry"); + ext4_debug("Failed to obtain dentry"); dentry_dir = NULL; goto out; } dentry_inode = d_alloc(dentry_dir, &qstr_dname); if (!dentry_inode) { - jbd_debug(1, "Inode dentry not created."); + ext4_debug("Inode dentry not created."); ret = -ENOMEM; goto out; } @@ -1378,7 +1435,7 @@ static int ext4_fc_replay_link_internal(struct super_block *sb, * could complete. */ if (ret && ret != -EEXIST) { - jbd_debug(1, "Failed to link\n"); + ext4_debug("Failed to link\n"); goto out; } @@ -1412,7 +1469,7 @@ static int ext4_fc_replay_link(struct super_block *sb, struct ext4_fc_tl *tl, inode = ext4_iget(sb, darg.ino, EXT4_IGET_NORMAL); if (IS_ERR(inode)) { - jbd_debug(1, "Inode not found."); + ext4_debug("Inode not found."); return 0; } @@ -1435,14 +1492,17 @@ static int ext4_fc_record_modified_inode(struct super_block *sb, int ino) if (state->fc_modified_inodes[i] == ino) return 0; if (state->fc_modified_inodes_used == state->fc_modified_inodes_size) { + int *fc_modified_inodes; + + fc_modified_inodes = krealloc(state->fc_modified_inodes, + sizeof(int) * (state->fc_modified_inodes_size + + EXT4_FC_REPLAY_REALLOC_INCREMENT), + GFP_KERNEL); + if (!fc_modified_inodes) + return -ENOMEM; + state->fc_modified_inodes = fc_modified_inodes; state->fc_modified_inodes_size += EXT4_FC_REPLAY_REALLOC_INCREMENT; - state->fc_modified_inodes = krealloc( - state->fc_modified_inodes, sizeof(int) * - state->fc_modified_inodes_size, - GFP_KERNEL); - if (!state->fc_modified_inodes) - return -ENOMEM; } state->fc_modified_inodes[state->fc_modified_inodes_used++] = ino; return 0; @@ -1459,8 +1519,9 @@ static int ext4_fc_replay_inode(struct super_block *sb, struct ext4_fc_tl *tl, struct ext4_inode *raw_fc_inode; struct inode *inode = NULL; struct ext4_iloc iloc; - int inode_len, ino, ret, tag = le16_to_cpu(tl->fc_tag); + int inode_len, ino, ret, tag = tl->fc_tag; struct ext4_extent_header *eh; + size_t off_gen = offsetof(struct ext4_inode, i_generation); memcpy(&fc_inode, val, sizeof(fc_inode)); @@ -1474,7 +1535,9 @@ static int ext4_fc_replay_inode(struct super_block *sb, struct ext4_fc_tl *tl, } inode = NULL; - ext4_fc_record_modified_inode(sb, ino); + ret = ext4_fc_record_modified_inode(sb, ino); + if (ret) + goto out; raw_fc_inode = (struct ext4_inode *) (val + offsetof(struct ext4_fc_inode, fc_raw_inode)); @@ -1482,12 +1545,12 @@ static int ext4_fc_replay_inode(struct super_block *sb, struct ext4_fc_tl *tl, if (ret) goto out; - inode_len = le16_to_cpu(tl->fc_len) - sizeof(struct ext4_fc_inode); + inode_len = tl->fc_len - sizeof(struct ext4_fc_inode); raw_inode = ext4_raw_inode(&iloc); memcpy(raw_inode, raw_fc_inode, offsetof(struct ext4_inode, i_block)); - memcpy(&raw_inode->i_generation, &raw_fc_inode->i_generation, - inode_len - offsetof(struct ext4_inode, i_generation)); + memcpy((u8 *)raw_inode + off_gen, (u8 *)raw_fc_inode + off_gen, + inode_len - off_gen); if (le32_to_cpu(raw_inode->i_flags) & EXT4_EXTENTS_FL) { eh = (struct ext4_extent_header *)(&raw_inode->i_block[0]); if (eh->eh_magic != EXT4_EXT_MAGIC) { @@ -1517,7 +1580,7 @@ static int ext4_fc_replay_inode(struct super_block *sb, struct ext4_fc_tl *tl, /* Given that we just wrote the inode on disk, this SHOULD succeed. */ inode = ext4_iget(sb, ino, EXT4_IGET_NORMAL); if (IS_ERR(inode)) { - jbd_debug(1, "Inode not found."); + ext4_debug("Inode not found."); return -EFSCORRUPTED; } @@ -1571,7 +1634,7 @@ static int ext4_fc_replay_create(struct super_block *sb, struct ext4_fc_tl *tl, inode = ext4_iget(sb, darg.ino, EXT4_IGET_NORMAL); if (IS_ERR(inode)) { - jbd_debug(1, "inode %d not found.", darg.ino); + ext4_debug("inode %d not found.", darg.ino); inode = NULL; ret = -EINVAL; goto out; @@ -1584,7 +1647,7 @@ static int ext4_fc_replay_create(struct super_block *sb, struct ext4_fc_tl *tl, */ dir = ext4_iget(sb, darg.parent_ino, EXT4_IGET_NORMAL); if (IS_ERR(dir)) { - jbd_debug(1, "Dir %d not found.", darg.ino); + ext4_debug("Dir %d not found.", darg.ino); goto out; } ret = ext4_init_new_dir(NULL, dir, inode); @@ -1600,32 +1663,41 @@ static int ext4_fc_replay_create(struct super_block *sb, struct ext4_fc_tl *tl, set_nlink(inode, 1); ext4_mark_inode_dirty(NULL, inode); out: - if (inode) - iput(inode); + iput(inode); return ret; } /* - * Record physical disk regions which are in use as per fast commit area. Our - * simple replay phase allocator excludes these regions from allocation. + * Record physical disk regions which are in use as per fast commit area, + * and used by inodes during replay phase. Our simple replay phase + * allocator excludes these regions from allocation. */ -static int ext4_fc_record_regions(struct super_block *sb, int ino, - ext4_lblk_t lblk, ext4_fsblk_t pblk, int len) +int ext4_fc_record_regions(struct super_block *sb, int ino, + ext4_lblk_t lblk, ext4_fsblk_t pblk, int len, int replay) { struct ext4_fc_replay_state *state; struct ext4_fc_alloc_region *region; state = &EXT4_SB(sb)->s_fc_replay_state; + /* + * during replay phase, the fc_regions_valid may not same as + * fc_regions_used, update it when do new additions. + */ + if (replay && state->fc_regions_used != state->fc_regions_valid) + state->fc_regions_used = state->fc_regions_valid; if (state->fc_regions_used == state->fc_regions_size) { + struct ext4_fc_alloc_region *fc_regions; + + fc_regions = krealloc(state->fc_regions, + sizeof(struct ext4_fc_alloc_region) * + (state->fc_regions_size + + EXT4_FC_REPLAY_REALLOC_INCREMENT), + GFP_KERNEL); + if (!fc_regions) + return -ENOMEM; state->fc_regions_size += EXT4_FC_REPLAY_REALLOC_INCREMENT; - state->fc_regions = krealloc( - state->fc_regions, - state->fc_regions_size * - sizeof(struct ext4_fc_alloc_region), - GFP_KERNEL); - if (!state->fc_regions) - return -ENOMEM; + state->fc_regions = fc_regions; } region = &state->fc_regions[state->fc_regions_used++]; region->ino = ino; @@ -1633,6 +1705,9 @@ static int ext4_fc_record_regions(struct super_block *sb, int ino, region->pblk = pblk; region->len = len; + if (replay) + state->fc_regions_valid++; + return 0; } @@ -1659,11 +1734,13 @@ static int ext4_fc_replay_add_range(struct super_block *sb, inode = ext4_iget(sb, le32_to_cpu(fc_add_ex.fc_ino), EXT4_IGET_NORMAL); if (IS_ERR(inode)) { - jbd_debug(1, "Inode not found."); + ext4_debug("Inode not found."); return 0; } ret = ext4_fc_record_modified_inode(sb, inode->i_ino); + if (ret) + goto out; start = le32_to_cpu(ex->ee_block); start_pblk = ext4_ext_pblock(ex); @@ -1671,7 +1748,7 @@ static int ext4_fc_replay_add_range(struct super_block *sb, cur = start; remaining = len; - jbd_debug(1, "ADD_RANGE, lblk %d, pblk %lld, len %d, unwritten %d, inode %ld\n", + ext4_debug("ADD_RANGE, lblk %d, pblk %lld, len %d, unwritten %d, inode %ld\n", start, start_pblk, len, ext4_ext_is_unwritten(ex), inode->i_ino); @@ -1681,18 +1758,14 @@ static int ext4_fc_replay_add_range(struct super_block *sb, map.m_pblk = 0; ret = ext4_map_blocks(NULL, inode, &map, 0); - if (ret < 0) { - iput(inode); - return 0; - } + if (ret < 0) + goto out; if (ret == 0) { /* Range is not mapped */ path = ext4_find_extent(inode, cur, NULL, 0); - if (IS_ERR(path)) { - iput(inode); - return 0; - } + if (IS_ERR(path)) + goto out; memset(&newex, 0, sizeof(newex)); newex.ee_block = cpu_to_le32(cur); ext4_ext_store_pblock( @@ -1704,12 +1777,9 @@ static int ext4_fc_replay_add_range(struct super_block *sb, ret = ext4_ext_insert_extent( NULL, inode, &path, &newex, 0); up_write((&EXT4_I(inode)->i_data_sem)); - ext4_ext_drop_refs(path); - kfree(path); - if (ret) { - iput(inode); - return 0; - } + ext4_free_ext_path(path); + if (ret) + goto out; goto next; } @@ -1722,10 +1792,8 @@ static int ext4_fc_replay_add_range(struct super_block *sb, ret = ext4_ext_replay_update_ex(inode, cur, map.m_len, ext4_ext_is_unwritten(ex), start_pblk + cur - start); - if (ret) { - iput(inode); - return 0; - } + if (ret) + goto out; /* * Mark the old blocks as free since they aren't used * anymore. We maintain an array of all the modified @@ -1740,15 +1808,13 @@ static int ext4_fc_replay_add_range(struct super_block *sb, } /* Range is mapped and needs a state change */ - jbd_debug(1, "Converting from %ld to %d %lld", + ext4_debug("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, ext4_ext_is_unwritten(ex), map.m_pblk); - if (ret) { - iput(inode); - return 0; - } + if (ret) + goto out; /* * We may have split the extent tree while toggling the state. * Try to shrink the extent tree now. @@ -1760,6 +1826,7 @@ next: } ext4_ext_replay_shrink_inode(inode, i_size_read(inode) >> sb->s_blocksize_bits); +out: iput(inode); return 0; } @@ -1784,13 +1851,15 @@ ext4_fc_replay_del_range(struct super_block *sb, struct ext4_fc_tl *tl, inode = ext4_iget(sb, le32_to_cpu(lrange.fc_ino), EXT4_IGET_NORMAL); if (IS_ERR(inode)) { - jbd_debug(1, "Inode %d not found", le32_to_cpu(lrange.fc_ino)); + ext4_debug("Inode %d not found", le32_to_cpu(lrange.fc_ino)); return 0; } ret = ext4_fc_record_modified_inode(sb, inode->i_ino); + if (ret) + goto out; - jbd_debug(1, "DEL_RANGE, inode %ld, lblk %d, len %d\n", + ext4_debug("DEL_RANGE, inode %ld, lblk %d, len %d\n", inode->i_ino, le32_to_cpu(lrange.fc_lblk), le32_to_cpu(lrange.fc_len)); while (remaining > 0) { @@ -1798,10 +1867,8 @@ ext4_fc_replay_del_range(struct super_block *sb, struct ext4_fc_tl *tl, map.m_len = remaining; ret = ext4_map_blocks(NULL, inode, &map, 0); - if (ret < 0) { - iput(inode); - return 0; - } + if (ret < 0) + goto out; if (ret > 0) { remaining -= ret; cur += ret; @@ -1812,16 +1879,18 @@ ext4_fc_replay_del_range(struct super_block *sb, struct ext4_fc_tl *tl, } } - ret = ext4_punch_hole(inode, - le32_to_cpu(lrange.fc_lblk) << sb->s_blocksize_bits, - le32_to_cpu(lrange.fc_len) << sb->s_blocksize_bits); + down_write(&EXT4_I(inode)->i_data_sem); + ret = ext4_ext_remove_space(inode, le32_to_cpu(lrange.fc_lblk), + le32_to_cpu(lrange.fc_lblk) + + le32_to_cpu(lrange.fc_len) - 1); + up_write(&EXT4_I(inode)->i_data_sem); if (ret) - jbd_debug(1, "ext4_punch_hole returned %d", ret); + goto out; ext4_ext_replay_shrink_inode(inode, i_size_read(inode) >> sb->s_blocksize_bits); ext4_mark_inode_dirty(NULL, inode); +out: iput(inode); - return 0; } @@ -1839,7 +1908,7 @@ static void ext4_fc_set_bitmaps_and_counters(struct super_block *sb) inode = ext4_iget(sb, state->fc_modified_inodes[i], EXT4_IGET_NORMAL); if (IS_ERR(inode)) { - jbd_debug(1, "Inode %d not found.", + ext4_debug("Inode %d not found.", state->fc_modified_inodes[i]); continue; } @@ -1863,8 +1932,7 @@ static void ext4_fc_set_bitmaps_and_counters(struct super_block *sb) for (j = 0; j < path->p_depth; j++) ext4_mb_mark_bb(inode->i_sb, path[j].p_block, 1, 1); - ext4_ext_drop_refs(path); - kfree(path); + ext4_free_ext_path(path); } cur += ret; ext4_mb_mark_bb(inode->i_sb, map.m_pblk, @@ -1892,8 +1960,8 @@ bool ext4_fc_replay_check_excluded(struct super_block *sb, ext4_fsblk_t blk) if (state->fc_regions[i].ino == 0 || state->fc_regions[i].len == 0) continue; - if (blk >= state->fc_regions[i].pblk && - blk < state->fc_regions[i].pblk + state->fc_regions[i].len) + if (in_range(blk, state->fc_regions[i].pblk, + state->fc_regions[i].len)) return true; } return false; @@ -1909,6 +1977,34 @@ void ext4_fc_replay_cleanup(struct super_block *sb) kfree(sbi->s_fc_replay_state.fc_modified_inodes); } +static inline bool ext4_fc_tag_len_isvalid(struct ext4_fc_tl *tl, + u8 *val, u8 *end) +{ + if (val + tl->fc_len > end) + return false; + + /* Here only check ADD_RANGE/TAIL/HEAD which will read data when do + * journal rescan before do CRC check. Other tags length check will + * rely on CRC check. + */ + switch (tl->fc_tag) { + case EXT4_FC_TAG_ADD_RANGE: + return (sizeof(struct ext4_fc_add_range) == tl->fc_len); + case EXT4_FC_TAG_TAIL: + return (sizeof(struct ext4_fc_tail) <= tl->fc_len); + case EXT4_FC_TAG_HEAD: + return (sizeof(struct ext4_fc_head) == tl->fc_len); + case EXT4_FC_TAG_DEL_RANGE: + case EXT4_FC_TAG_LINK: + case EXT4_FC_TAG_UNLINK: + case EXT4_FC_TAG_CREAT: + case EXT4_FC_TAG_INODE: + case EXT4_FC_TAG_PAD: + default: + return true; + } +} + /* * Recovery Scan phase handler * @@ -1965,19 +2061,25 @@ static int ext4_fc_replay_scan(journal_t *journal, } state->fc_replay_expected_off++; - for (cur = start; cur < end; cur = cur + sizeof(tl) + le16_to_cpu(tl.fc_len)) { - memcpy(&tl, cur, sizeof(tl)); - val = cur + sizeof(tl); - jbd_debug(3, "Scan phase, tag:%s, blk %lld\n", - tag2str(le16_to_cpu(tl.fc_tag)), bh->b_blocknr); - switch (le16_to_cpu(tl.fc_tag)) { + for (cur = start; cur < end - EXT4_FC_TAG_BASE_LEN; + cur = cur + EXT4_FC_TAG_BASE_LEN + tl.fc_len) { + ext4_fc_get_tl(&tl, cur); + val = cur + EXT4_FC_TAG_BASE_LEN; + if (!ext4_fc_tag_len_isvalid(&tl, val, end)) { + ret = state->fc_replay_num_tags ? + JBD2_FC_REPLAY_STOP : -ECANCELED; + goto out_err; + } + ext4_debug("Scan phase, tag:%s, blk %lld\n", + tag2str(tl.fc_tag), bh->b_blocknr); + switch (tl.fc_tag) { case EXT4_FC_TAG_ADD_RANGE: memcpy(&ext, val, sizeof(ext)); ex = (struct ext4_extent *)&ext.fc_ex; ret = ext4_fc_record_regions(sb, le32_to_cpu(ext.fc_ino), le32_to_cpu(ex->ee_block), ext4_ext_pblock(ex), - ext4_ext_get_actual_len(ex)); + ext4_ext_get_actual_len(ex), 0); if (ret < 0) break; ret = JBD2_FC_REPLAY_CONTINUE; @@ -1990,13 +2092,13 @@ static int ext4_fc_replay_scan(journal_t *journal, case EXT4_FC_TAG_PAD: state->fc_cur_tag++; state->fc_crc = ext4_chksum(sbi, state->fc_crc, cur, - sizeof(tl) + le16_to_cpu(tl.fc_len)); + EXT4_FC_TAG_BASE_LEN + tl.fc_len); break; case EXT4_FC_TAG_TAIL: state->fc_cur_tag++; memcpy(&tail, val, sizeof(tail)); state->fc_crc = ext4_chksum(sbi, state->fc_crc, cur, - sizeof(tl) + + EXT4_FC_TAG_BASE_LEN + offsetof(struct ext4_fc_tail, fc_crc)); if (le32_to_cpu(tail.fc_tid) == expected_tid && @@ -2023,7 +2125,7 @@ static int ext4_fc_replay_scan(journal_t *journal, } state->fc_cur_tag++; state->fc_crc = ext4_chksum(sbi, state->fc_crc, cur, - sizeof(tl) + le16_to_cpu(tl.fc_len)); + EXT4_FC_TAG_BASE_LEN + tl.fc_len); break; default: ret = state->fc_replay_num_tags ? @@ -2063,7 +2165,7 @@ static int ext4_fc_replay(journal_t *journal, struct buffer_head *bh, sbi->s_mount_state |= EXT4_FC_REPLAY; } if (!sbi->s_fc_replay_state.fc_replay_num_tags) { - jbd_debug(1, "Replay stops\n"); + ext4_debug("Replay stops\n"); ext4_fc_set_bitmaps_and_counters(sb); return 0; } @@ -2078,19 +2180,20 @@ static int ext4_fc_replay(journal_t *journal, struct buffer_head *bh, start = (u8 *)bh->b_data; end = (__u8 *)bh->b_data + journal->j_blocksize - 1; - for (cur = start; cur < end; cur = cur + sizeof(tl) + le16_to_cpu(tl.fc_len)) { - memcpy(&tl, cur, sizeof(tl)); - val = cur + sizeof(tl); + for (cur = start; cur < end - EXT4_FC_TAG_BASE_LEN; + cur = cur + EXT4_FC_TAG_BASE_LEN + tl.fc_len) { + ext4_fc_get_tl(&tl, cur); + val = cur + EXT4_FC_TAG_BASE_LEN; if (state->fc_replay_num_tags == 0) { ret = JBD2_FC_REPLAY_STOP; ext4_fc_set_bitmaps_and_counters(sb); break; } - jbd_debug(3, "Replay phase, tag:%s\n", - tag2str(le16_to_cpu(tl.fc_tag))); + + ext4_debug("Replay phase, tag:%s\n", tag2str(tl.fc_tag)); state->fc_replay_num_tags--; - switch (le16_to_cpu(tl.fc_tag)) { + switch (tl.fc_tag) { case EXT4_FC_TAG_LINK: ret = ext4_fc_replay_link(sb, &tl, val); break; @@ -2111,19 +2214,18 @@ static int ext4_fc_replay(journal_t *journal, struct buffer_head *bh, break; case EXT4_FC_TAG_PAD: trace_ext4_fc_replay(sb, EXT4_FC_TAG_PAD, 0, - le16_to_cpu(tl.fc_len), 0); + tl.fc_len, 0); break; case EXT4_FC_TAG_TAIL: - trace_ext4_fc_replay(sb, EXT4_FC_TAG_TAIL, 0, - le16_to_cpu(tl.fc_len), 0); + trace_ext4_fc_replay(sb, EXT4_FC_TAG_TAIL, + 0, tl.fc_len, 0); memcpy(&tail, val, sizeof(tail)); WARN_ON(le32_to_cpu(tail.fc_tid) != expected_tid); break; case EXT4_FC_TAG_HEAD: break; default: - trace_ext4_fc_replay(sb, le16_to_cpu(tl.fc_tag), 0, - le16_to_cpu(tl.fc_len), 0); + trace_ext4_fc_replay(sb, tl.fc_tag, 0, tl.fc_len, 0); ret = -ECANCELED; break; } @@ -2173,7 +2275,7 @@ int ext4_fc_info_show(struct seq_file *seq, void *v) "fc stats:\n%ld commits\n%ld ineligible\n%ld numblks\n%lluus avg_commit_time\n", stats->fc_num_commits, stats->fc_ineligible_commits, stats->fc_numblks, - div_u64(sbi->s_fc_avg_commit_time, 1000)); + div_u64(stats->s_fc_avg_commit_time, 1000)); seq_puts(seq, "Ineligible reasons:\n"); for (i = 0; i < EXT4_FC_REASON_MAX; i++) seq_printf(seq, "\"%s\":\t%d\n", fc_ineligible_reasons[i], @@ -2192,3 +2294,8 @@ int __init ext4_fc_init_dentry_cache(void) return 0; } + +void ext4_fc_destroy_dentry_cache(void) +{ + kmem_cache_destroy(ext4_fc_dentry_cachep); +} diff --git a/fs/ext4/fast_commit.h b/fs/ext4/fast_commit.h index 937c381b4c85..a6154c3ed135 100644 --- a/fs/ext4/fast_commit.h +++ b/fs/ext4/fast_commit.h @@ -55,13 +55,13 @@ struct ext4_fc_del_range { struct ext4_fc_dentry_info { __le32 fc_parent_ino; __le32 fc_ino; - __u8 fc_dname[0]; + __u8 fc_dname[]; }; /* Value structure for EXT4_FC_TAG_INODE and EXT4_FC_TAG_INODE_PARTIAL. */ struct ext4_fc_inode { __le32 fc_ino; - __u8 fc_raw_inode[0]; + __u8 fc_raw_inode[]; }; /* Value structure for tag EXT4_FC_TAG_TAIL. */ @@ -70,22 +70,23 @@ struct ext4_fc_tail { __le32 fc_crc; }; +/* Tag base length */ +#define EXT4_FC_TAG_BASE_LEN (sizeof(struct ext4_fc_tl)) + +/* + * Fast commit status codes + */ +enum { + EXT4_FC_STATUS_OK = 0, + EXT4_FC_STATUS_INELIGIBLE, + EXT4_FC_STATUS_SKIPPED, + EXT4_FC_STATUS_FAILED, +}; + /* - * Fast commit reason codes + * Fast commit ineligiblity reasons: */ enum { - /* - * Commit status codes: - */ - EXT4_FC_REASON_OK = 0, - EXT4_FC_REASON_INELIGIBLE, - EXT4_FC_REASON_ALREADY_COMMITTED, - EXT4_FC_REASON_FC_START_FAILED, - EXT4_FC_REASON_FC_FAILED, - - /* - * Fast commit ineligiblity reasons: - */ EXT4_FC_REASON_XATTR = 0, EXT4_FC_REASON_CROSS_RENAME, EXT4_FC_REASON_JOURNAL_FLAG_CHANGE, @@ -95,7 +96,6 @@ enum { EXT4_FC_REASON_RENAME_DIR, EXT4_FC_REASON_FALLOC_RANGE, EXT4_FC_REASON_INODE_JOURNAL_DATA, - EXT4_FC_COMMIT_FAILED, EXT4_FC_REASON_MAX }; @@ -111,13 +111,17 @@ struct ext4_fc_dentry_update { struct qstr fcd_name; /* Dirent name */ unsigned char fcd_iname[DNAME_INLINE_LEN]; /* Dirent name string */ struct list_head fcd_list; + struct list_head fcd_dilist; }; struct ext4_fc_stats { unsigned int fc_ineligible_reason_count[EXT4_FC_REASON_MAX]; unsigned long fc_num_commits; unsigned long fc_ineligible_commits; + unsigned long fc_failed_commits; + unsigned long fc_skipped_commits; unsigned long fc_numblks; + u64 s_fc_avg_commit_time; }; #define EXT4_FC_REPLAY_REALLOC_INCREMENT 4 diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 4c5f41052351..a7a597c727e6 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -36,17 +36,34 @@ #include "acl.h" #include "truncate.h" -static bool ext4_dio_supported(struct inode *inode) +/* + * Returns %true if the given DIO request should be attempted with DIO, or + * %false if it should fall back to buffered I/O. + * + * DIO isn't well specified; when it's unsupported (either due to the request + * being misaligned, or due to the file not supporting DIO at all), filesystems + * either fall back to buffered I/O or return EINVAL. For files that don't use + * any special features like encryption or verity, ext4 has traditionally + * returned EINVAL for misaligned DIO. iomap_dio_rw() uses this convention too. + * In this case, we should attempt the DIO, *not* fall back to buffered I/O. + * + * In contrast, in cases where DIO is unsupported due to ext4 features, ext4 + * traditionally falls back to buffered I/O. + * + * This function implements the traditional ext4 behavior in all these cases. + */ +static bool ext4_should_use_dio(struct kiocb *iocb, struct iov_iter *iter) { - if (IS_ENABLED(CONFIG_FS_ENCRYPTION) && IS_ENCRYPTED(inode)) - return false; - if (fsverity_active(inode)) - return false; - if (ext4_should_journal_data(inode)) - return false; - if (ext4_has_inline_data(inode)) + struct inode *inode = file_inode(iocb->ki_filp); + u32 dio_align = ext4_dio_alignment(inode); + + if (dio_align == 0) return false; - return true; + + if (dio_align == 1) + return true; + + return IS_ALIGNED(iocb->ki_pos | iov_iter_alignment(iter), dio_align); } static ssize_t ext4_dio_read_iter(struct kiocb *iocb, struct iov_iter *to) @@ -61,7 +78,7 @@ static ssize_t ext4_dio_read_iter(struct kiocb *iocb, struct iov_iter *to) inode_lock_shared(inode); } - if (!ext4_dio_supported(inode)) { + if (!ext4_should_use_dio(iocb, to)) { inode_unlock_shared(inode); /* * Fallback to buffered I/O if the operation being performed on @@ -74,7 +91,7 @@ static ssize_t ext4_dio_read_iter(struct kiocb *iocb, struct iov_iter *to) return generic_file_read_iter(iocb, to); } - ret = iomap_dio_rw(iocb, to, &ext4_iomap_ops, NULL, 0, 0); + ret = iomap_dio_rw(iocb, to, &ext4_iomap_ops, NULL, 0, NULL, 0); inode_unlock_shared(inode); file_accessed(iocb->ki_filp); @@ -259,19 +276,17 @@ static ssize_t ext4_buffered_write_iter(struct kiocb *iocb, if (iocb->ki_flags & IOCB_NOWAIT) return -EOPNOTSUPP; - ext4_fc_start_update(inode); inode_lock(inode); ret = ext4_write_checks(iocb, from); if (ret <= 0) goto out; current->backing_dev_info = inode_to_bdi(inode); - ret = generic_perform_write(iocb->ki_filp, from, iocb->ki_pos); + ret = generic_perform_write(iocb, from); current->backing_dev_info = NULL; out: inode_unlock(inode); - ext4_fc_stop_update(inode); if (likely(ret > 0)) { iocb->ki_pos += ret; ret = generic_write_sync(iocb, ret); @@ -511,7 +526,7 @@ static ssize_t ext4_dio_write_iter(struct kiocb *iocb, struct iov_iter *from) } /* Fallback to buffered I/O if the inode does not support direct I/O. */ - if (!ext4_dio_supported(inode)) { + if (!ext4_should_use_dio(iocb, from)) { if (ilock_shared) inode_unlock_shared(inode); else @@ -528,6 +543,12 @@ static ssize_t ext4_dio_write_iter(struct kiocb *iocb, struct iov_iter *from) ret = -EAGAIN; goto out; } + /* + * Make sure inline data cannot be created anymore since we are going + * to allocate blocks for DIO. We know the inode does not have any + * inline data now because ext4_dio_supported() checked for that. + */ + ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA); offset = iocb->ki_pos; count = ret; @@ -552,9 +573,7 @@ static ssize_t ext4_dio_write_iter(struct kiocb *iocb, struct iov_iter *from) goto out; } - ext4_fc_start_update(inode); ret = ext4_orphan_add(handle, inode); - ext4_fc_stop_update(inode); if (ret) { ext4_journal_stop(handle); goto out; @@ -567,7 +586,7 @@ static ssize_t ext4_dio_write_iter(struct kiocb *iocb, struct iov_iter *from) iomap_ops = &ext4_iomap_overwrite_ops; ret = iomap_dio_rw(iocb, from, iomap_ops, &ext4_dio_write_ops, (unaligned_io || extend) ? IOMAP_DIO_FORCE_WAIT : 0, - 0); + NULL, 0); if (ret == -ENOTBLK) ret = 0; diff --git a/fs/ext4/hash.c b/fs/ext4/hash.c index f34f4176c1e7..147b5241dd94 100644 --- a/fs/ext4/hash.c +++ b/fs/ext4/hash.c @@ -290,7 +290,7 @@ static int __ext4fs_dirhash(const struct inode *dir, const char *name, int len, int ext4fs_dirhash(const struct inode *dir, const char *name, int len, struct dx_hash_info *hinfo) { -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) const struct unicode_map *um = dir->i_sb->s_encoding; int r, dlen; unsigned char *buff; diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index f73e5eb43eae..e9bc46684106 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -463,10 +463,9 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent, hinfo.hash_version = DX_HASH_HALF_MD4; hinfo.seed = sbi->s_hash_seed; ext4fs_dirhash(parent, qstr->name, qstr->len, &hinfo); - grp = hinfo.hash; + parent_group = hinfo.hash % ngroups; } else - grp = prandom_u32(); - parent_group = (unsigned)grp % ngroups; + parent_group = prandom_u32_max(ngroups); for (i = 0; i < ngroups; i++) { g = (parent_group + i) % ngroups; get_orlov_stats(sb, g, flex_size, &stats); @@ -510,7 +509,7 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent, goto fallback; } - max_dirs = ndirs / ngroups + inodes_per_group / 16; + max_dirs = ndirs / ngroups + inodes_per_group*flex_size / 16; min_inodes = avefreei - inodes_per_group*flex_size / 4; if (min_inodes < 1) min_inodes = 1; @@ -1280,7 +1279,7 @@ got: EXT4_GROUP_INFO_IBITMAP_CORRUPT); goto out; } - inode->i_generation = prandom_u32(); + inode->i_generation = get_random_u32(); /* Precompute checksum seed for inode metadata */ if (ext4_has_metadata_csum(sb)) { diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c index 89efa78ed4b2..860fc5119009 100644 --- a/fs/ext4/indirect.c +++ b/fs/ext4/indirect.c @@ -460,7 +460,7 @@ static int ext4_splice_branch(handle_t *handle, * the new i_size. But that is not done here - it is done in * generic_commit_write->__mark_inode_dirty->ext4_dirty_inode. */ - jbd_debug(5, "splicing indirect only\n"); + ext4_debug("splicing indirect only\n"); BUFFER_TRACE(where->bh, "call ext4_handle_dirty_metadata"); err = ext4_handle_dirty_metadata(handle, ar->inode, where->bh); if (err) @@ -472,7 +472,7 @@ static int ext4_splice_branch(handle_t *handle, err = ext4_mark_inode_dirty(handle, ar->inode); if (unlikely(err)) goto err_out; - jbd_debug(5, "splicing direct\n"); + ext4_debug("splicing direct\n"); } return err; @@ -696,7 +696,7 @@ static int ext4_ind_trunc_restart_fn(handle_t *handle, struct inode *inode, * Drop i_data_sem to avoid deadlock with ext4_map_blocks. At this * moment, get_block can be called only for blocks inside i_size since * page cache has been already dropped and writes are blocked by - * i_mutex. So we can safely drop the i_data_sem here. + * i_rwsem. So we can safely drop the i_data_sem here. */ BUG_ON(EXT4_JOURNAL(inode) == NULL); ext4_discard_preallocations(inode, 0); diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index 39a1ab129fdc..a4fbe825694b 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -6,8 +6,9 @@ #include <linux/iomap.h> #include <linux/fiemap.h> +#include <linux/namei.h> #include <linux/iversion.h> -#include <linux/backing-dev.h> +#include <linux/sched/mm.h> #include "ext4_jbd2.h" #include "ext4.h" @@ -35,6 +36,9 @@ static int get_max_inline_xattr_value_size(struct inode *inode, struct ext4_inode *raw_inode; int free, min_offs; + if (!EXT4_INODE_HAS_XATTR_SPACE(inode)) + return 0; + min_offs = EXT4_SB(inode->i_sb)->s_inode_size - EXT4_GOOD_OLD_INODE_SIZE - EXT4_I(inode)->i_extra_isize - @@ -527,13 +531,13 @@ int ext4_readpage_inline(struct inode *inode, struct page *page) } static int ext4_convert_inline_data_to_extent(struct address_space *mapping, - struct inode *inode, - unsigned flags) + struct inode *inode) { int ret, needed_blocks, no_expand; handle_t *handle = NULL; int retries = 0, sem_held = 0; struct page *page = NULL; + unsigned int flags; unsigned from, to; struct ext4_iloc iloc; @@ -562,9 +566,9 @@ retry: /* We cannot recurse into the filesystem as the transaction is already * started */ - flags |= AOP_FLAG_NOFS; - - page = grab_cache_page_write_begin(mapping, 0, flags); + flags = memalloc_nofs_save(); + page = grab_cache_page_write_begin(mapping, 0); + memalloc_nofs_restore(flags); if (!page) { ret = -ENOMEM; goto out; @@ -649,11 +653,11 @@ out: int ext4_try_to_write_inline_data(struct address_space *mapping, struct inode *inode, loff_t pos, unsigned len, - unsigned flags, struct page **pagep) { int ret; handle_t *handle; + unsigned int flags; struct page *page; struct ext4_iloc iloc; @@ -691,9 +695,9 @@ int ext4_try_to_write_inline_data(struct address_space *mapping, if (ret) goto out; - flags |= AOP_FLAG_NOFS; - - page = grab_cache_page_write_begin(mapping, 0, flags); + flags = memalloc_nofs_save(); + page = grab_cache_page_write_begin(mapping, 0); + memalloc_nofs_restore(flags); if (!page) { ret = -ENOMEM; goto out; @@ -727,8 +731,7 @@ out: brelse(iloc.bh); return ret; convert: - return ext4_convert_inline_data_to_extent(mapping, - inode, flags); + return ext4_convert_inline_data_to_extent(mapping, inode); } int ext4_write_inline_data_end(struct inode *inode, loff_t pos, unsigned len, @@ -848,13 +851,12 @@ ext4_journalled_write_inline_data(struct inode *inode, */ static int ext4_da_convert_inline_data_to_extent(struct address_space *mapping, struct inode *inode, - unsigned flags, void **fsdata) { int ret = 0, inline_size; struct page *page; - page = grab_cache_page_write_begin(mapping, 0, flags); + page = grab_cache_page_write_begin(mapping, 0); if (!page) return -ENOMEM; @@ -907,15 +909,15 @@ out: int ext4_da_write_inline_data_begin(struct address_space *mapping, struct inode *inode, loff_t pos, unsigned len, - unsigned flags, struct page **pagep, void **fsdata) { - int ret, inline_size; + int ret; handle_t *handle; struct page *page; struct ext4_iloc iloc; int retries = 0; + unsigned int flags; ret = ext4_get_inode_loc(inode, &iloc); if (ret) @@ -928,26 +930,14 @@ retry_journal: goto out; } - inline_size = ext4_get_max_inline_size(inode); - - ret = -ENOSPC; - if (inline_size >= pos + len) { - ret = ext4_prepare_inline_data(handle, inode, pos + len); - if (ret && ret != -ENOSPC) - goto out_journal; - } - - /* - * We cannot recurse into the filesystem as the transaction - * is already started. - */ - flags |= AOP_FLAG_NOFS; + ret = ext4_prepare_inline_data(handle, inode, pos + len); + if (ret && ret != -ENOSPC) + goto out_journal; if (ret == -ENOSPC) { ext4_journal_stop(handle); ret = ext4_da_convert_inline_data_to_extent(mapping, inode, - flags, fsdata); if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)) @@ -955,7 +945,13 @@ retry_journal: goto out; } - page = grab_cache_page_write_begin(mapping, 0, flags); + /* + * We cannot recurse into the filesystem as the transaction + * is already started. + */ + flags = memalloc_nofs_save(); + page = grab_cache_page_write_begin(mapping, 0); + memalloc_nofs_restore(flags); if (!page) { ret = -ENOMEM; goto out_journal; @@ -1088,14 +1084,14 @@ static void ext4_update_final_de(void *de_buf, int old_size, int new_size) void *limit; int de_len; - de = (struct ext4_dir_entry_2 *)de_buf; + de = de_buf; if (old_size) { limit = de_buf + old_size; do { prev_de = de; de_len = ext4_rec_len_from_disk(de->rec_len, old_size); de_buf += de_len; - de = (struct ext4_dir_entry_2 *)de_buf; + de = de_buf; } while (de_buf < limit); prev_de->rec_len = ext4_rec_len_to_disk(de_len + new_size - @@ -1133,7 +1129,15 @@ static void ext4_restore_inline_data(handle_t *handle, struct inode *inode, struct ext4_iloc *iloc, void *buf, int inline_size) { - ext4_create_inline_data(handle, inode, inline_size); + int ret; + + ret = ext4_create_inline_data(handle, inode, inline_size); + if (ret) { + ext4_msg(inode->i_sb, KERN_EMERG, + "error restoring inline_data for inode -- potential data loss! (inode %lu, error %d)", + inode->i_ino, ret); + return; + } ext4_write_inline_data(inode, iloc, buf, 0, inline_size); ext4_set_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA); } @@ -1152,7 +1156,7 @@ static int ext4_finish_convert_inline_dir(handle_t *handle, * First create "." and ".." and then copy the dir information * back to the block. */ - de = (struct ext4_dir_entry_2 *)target; + de = target; de = ext4_init_dot_dotdot(inode, de, inode->i_sb->s_blocksize, csum_size, le32_to_cpu(((struct ext4_dir_entry_2 *)buf)->inode), 1); @@ -1588,6 +1592,35 @@ out: return ret; } +void *ext4_read_inline_link(struct inode *inode) +{ + struct ext4_iloc iloc; + int ret, inline_size; + void *link; + + ret = ext4_get_inode_loc(inode, &iloc); + if (ret) + return ERR_PTR(ret); + + ret = -ENOMEM; + inline_size = ext4_get_inline_size(inode); + link = kmalloc(inline_size + 1, GFP_NOFS); + if (!link) + goto out; + + ret = ext4_read_inline_data(inode, link, inline_size, &iloc); + if (ret < 0) { + kfree(link); + goto out; + } + nd_terminate_link(link, inode->i_size, ret); +out: + if (ret < 0) + link = ERR_PTR(ret); + brelse(iloc.bh); + return link; +} + struct buffer_head *ext4_get_first_inline_block(struct inode *inode, struct ext4_dir_entry_2 **parent_de, int *retval) @@ -1780,19 +1813,20 @@ bool empty_inline_dir(struct inode *dir, int *has_inline_data) void *inline_pos; unsigned int offset; struct ext4_dir_entry_2 *de; - bool ret = true; + bool ret = false; err = ext4_get_inode_loc(dir, &iloc); if (err) { EXT4_ERROR_INODE_ERR(dir, -err, "error %d getting inode %lu block", err, dir->i_ino); - return true; + return false; } down_read(&EXT4_I(dir)->xattr_sem); if (!ext4_has_inline_data(dir)) { *has_inline_data = 0; + ret = true; goto out; } @@ -1801,7 +1835,6 @@ bool empty_inline_dir(struct inode *dir, int *has_inline_data) ext4_warning(dir->i_sb, "bad inline directory (dir #%lu) - no `..'", dir->i_ino); - ret = true; goto out; } @@ -1820,16 +1853,15 @@ bool empty_inline_dir(struct inode *dir, int *has_inline_data) dir->i_ino, le32_to_cpu(de->inode), le16_to_cpu(de->rec_len), de->name_len, inline_size); - ret = true; goto out; } if (le32_to_cpu(de->inode)) { - ret = false; goto out; } offset += ext4_rec_len_from_disk(de->rec_len, inline_size); } + ret = true; out: up_read(&EXT4_I(dir)->xattr_sem); brelse(iloc.bh); @@ -1929,8 +1961,7 @@ int ext4_inline_data_truncate(struct inode *inode, int *has_inline) retry: err = ext4_es_remove_extent(inode, 0, EXT_MAX_BLOCKS); if (err == -ENOMEM) { - cond_resched(); - congestion_wait(BLK_RW_ASYNC, HZ/50); + memalloc_retry_wait(GFP_ATOMIC); goto retry; } if (err) @@ -2004,6 +2035,18 @@ int ext4_convert_inline_data(struct inode *inode) if (!ext4_has_inline_data(inode)) { ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA); return 0; + } else if (!ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)) { + /* + * Inode has inline data but EXT4_STATE_MAY_INLINE_DATA is + * cleared. This means we are in the middle of moving of + * inline data to delay allocated block. Just force writeout + * here to finish conversion. + */ + error = filemap_flush(inode->i_mapping); + if (error) + return error; + if (!ext4_has_inline_data(inode)) + return 0; } needed_blocks = ext4_writepage_trans_blocks(inode); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index bfd3545f1e5d..2b5ef1b64249 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -136,8 +136,6 @@ static inline int ext4_begin_ordered_truncate(struct inode *inode, new_size); } -static void ext4_invalidatepage(struct page *page, unsigned int offset, - unsigned int length); static int __ext4_journalled_writepage(struct page *page, unsigned int len); static int ext4_meta_trans_blocks(struct inode *inode, int lblocks, int pextents); @@ -179,13 +177,15 @@ void ext4_evict_inode(struct inode *inode) trace_ext4_evict_inode(inode); + if (EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL) + ext4_evict_ea_inode(inode); if (inode->i_nlink) { /* * When journalling data dirty buffers are tracked only in the * journal. So although mm thinks everything is clean and * ready for reaping the inode might still have some pages to * write in the running transaction or waiting to be - * checkpointed. Thus calling jbd2_journal_invalidatepage() + * checkpointed. Thus calling jbd2_journal_invalidate_folio() * (via truncate_inode_pages()) to discard these buffers can * cause data loss. Also even if we did not discard these * buffers, we would have no way to find them after the inode @@ -200,8 +200,7 @@ void ext4_evict_inode(struct inode *inode) */ if (inode->i_ino != EXT4_JOURNAL_INO && ext4_should_journal_data(inode) && - (S_ISLNK(inode->i_mode) || S_ISREG(inode->i_mode)) && - inode->i_data.nrpages) { + S_ISREG(inode->i_mode) && inode->i_data.nrpages) { journal_t *journal = EXT4_SB(inode->i_sb)->s_journal; tid_t commit_tid = EXT4_I(inode)->i_datasync_tid; @@ -337,7 +336,7 @@ stop_handle: return; no_delete: if (!list_empty(&EXT4_I(inode)->i_fc_list)) - ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_NOMEM); + ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_NOMEM, NULL); ext4_clear_inode(inode); /* We must guarantee clearing of inode... */ } @@ -546,12 +545,21 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode, } else { BUG(); } + + if (flags & EXT4_GET_BLOCKS_CACHED_NOWAIT) + return retval; #ifdef ES_AGGRESSIVE_TEST ext4_map_blocks_es_recheck(handle, inode, map, &orig_map, flags); #endif goto found; } + /* + * In the query cache no-wait mode, nothing we can do more if we + * cannot find extent in the cache. + */ + if (flags & EXT4_GET_BLOCKS_CACHED_NOWAIT) + return 0; /* * Try to see if we can get the block without requesting a new @@ -741,10 +749,11 @@ out_sem: if (ret) return ret; } - ext4_fc_track_range(handle, inode, map->m_lblk, - map->m_lblk + map->m_len - 1); } - + if (retval > 0 && (map->m_flags & EXT4_MAP_UNWRITTEN || + map->m_flags & EXT4_MAP_MAPPED)) + ext4_fc_track_range(handle, inode, map->m_lblk, + map->m_lblk + map->m_len - 1); if (retval < 0) ext_debug(inode, "failed with err %d\n", retval); return retval; @@ -822,7 +831,7 @@ int ext4_get_block_unwritten(struct inode *inode, sector_t iblock, ext4_debug("ext4_get_block_unwritten: inode %lu, create flag %d\n", inode->i_ino, create); return _ext4_get_block(inode, iblock, bh_result, - EXT4_GET_BLOCKS_IO_CREATE_EXT); + EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT); } /* Maximum number of blocks we map for direct IO at once. */ @@ -837,10 +846,12 @@ struct buffer_head *ext4_getblk(handle_t *handle, struct inode *inode, struct ext4_map_blocks map; struct buffer_head *bh; int create = map_flags & EXT4_GET_BLOCKS_CREATE; + bool nowait = map_flags & EXT4_GET_BLOCKS_CACHED_NOWAIT; int err; ASSERT((EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY) || handle != NULL || create == 0); + ASSERT(create == 0 || !nowait); map.m_lblk = block; map.m_len = 1; @@ -851,6 +862,9 @@ struct buffer_head *ext4_getblk(handle_t *handle, struct inode *inode, if (err < 0) return ERR_PTR(err); + if (nowait) + return sb_find_get_block(inode->i_sb, map.m_pblk); + bh = sb_getblk(inode->i_sb, map.m_pblk); if (unlikely(!bh)) return ERR_PTR(-ENOMEM); @@ -1130,7 +1144,7 @@ static int ext4_block_write_begin(struct page *page, loff_t pos, unsigned len, #endif static int ext4_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, + loff_t pos, unsigned len, struct page **pagep, void **fsdata) { struct inode *inode = mapping->host; @@ -1144,7 +1158,7 @@ static int ext4_write_begin(struct file *file, struct address_space *mapping, if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb)))) return -EIO; - trace_ext4_write_begin(inode, pos, len, flags); + trace_ext4_write_begin(inode, pos, len); /* * Reserve one block more for addition to orphan list in case * we allocate blocks but write fails for some reason @@ -1156,7 +1170,7 @@ static int ext4_write_begin(struct file *file, struct address_space *mapping, if (ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)) { ret = ext4_try_to_write_inline_data(mapping, inode, pos, len, - flags, pagep); + pagep); if (ret < 0) return ret; if (ret == 1) @@ -1171,9 +1185,16 @@ static int ext4_write_begin(struct file *file, struct address_space *mapping, * the page (if needed) without using GFP_NOFS. */ retry_grab: - page = grab_cache_page_write_begin(mapping, index, flags); + page = grab_cache_page_write_begin(mapping, index); if (!page) return -ENOMEM; + /* + * The same as page allocation, we prealloc buffer heads before + * starting the handle. + */ + if (!page_has_buffers(page)) + create_empty_buffers(page, inode->i_sb->s_blocksize, 0); + unlock_page(page); retry_journal: @@ -1222,7 +1243,7 @@ retry_journal: /* * __block_write_begin may have instantiated a few blocks * outside i_size. Trim these off again. Don't need - * i_size_read because we hold i_mutex. + * i_size_read because we hold i_rwsem. * * Add inode to orphan list in case we crash before * truncate finishes @@ -1542,9 +1563,9 @@ struct mpage_da_data { static void mpage_release_unused_pages(struct mpage_da_data *mpd, bool invalidate) { - int nr_pages, i; + unsigned nr, i; pgoff_t index, end; - struct pagevec pvec; + struct folio_batch fbatch; struct inode *inode = mpd->inode; struct address_space *mapping = inode->i_mapping; @@ -1559,28 +1580,40 @@ static void mpage_release_unused_pages(struct mpage_da_data *mpd, ext4_lblk_t start, last; start = index << (PAGE_SHIFT - inode->i_blkbits); last = end << (PAGE_SHIFT - inode->i_blkbits); + + /* + * avoid racing with extent status tree scans made by + * ext4_insert_delayed_block() + */ + down_write(&EXT4_I(inode)->i_data_sem); ext4_es_remove_extent(inode, start, last - start + 1); + up_write(&EXT4_I(inode)->i_data_sem); } - pagevec_init(&pvec); + folio_batch_init(&fbatch); while (index <= end) { - nr_pages = pagevec_lookup_range(&pvec, mapping, &index, end); - if (nr_pages == 0) + nr = filemap_get_folios(mapping, &index, end, &fbatch); + if (nr == 0) break; - for (i = 0; i < nr_pages; i++) { - struct page *page = pvec.pages[i]; + for (i = 0; i < nr; i++) { + struct folio *folio = fbatch.folios[i]; - BUG_ON(!PageLocked(page)); - BUG_ON(PageWriteback(page)); + if (folio->index < mpd->first_page) + continue; + if (folio->index + folio_nr_pages(folio) - 1 > end) + continue; + BUG_ON(!folio_test_locked(folio)); + BUG_ON(folio_test_writeback(folio)); if (invalidate) { - if (page_mapped(page)) - clear_page_dirty_for_io(page); - block_invalidatepage(page, 0, PAGE_SIZE); - ClearPageUptodate(page); + if (folio_mapped(folio)) + folio_clear_dirty_for_io(folio); + block_invalidate_folio(folio, 0, + folio_size(folio)); + folio_clear_uptodate(folio); } - unlock_page(page); + folio_unlock(folio); } - pagevec_release(&pvec); + folio_batch_release(&fbatch); } } @@ -1844,30 +1877,16 @@ int ext4_da_get_block_prep(struct inode *inode, sector_t iblock, return 0; } -static int bget_one(handle_t *handle, struct inode *inode, - struct buffer_head *bh) -{ - get_bh(bh); - return 0; -} - -static int bput_one(handle_t *handle, struct inode *inode, - struct buffer_head *bh) -{ - put_bh(bh); - return 0; -} - static int __ext4_journalled_writepage(struct page *page, unsigned int len) { struct address_space *mapping = page->mapping; struct inode *inode = mapping->host; - struct buffer_head *page_bufs = NULL; handle_t *handle = NULL; int ret = 0, err = 0; int inline_data = ext4_has_inline_data(inode); struct buffer_head *inode_bh = NULL; + loff_t size; ClearPageChecked(page); @@ -1877,14 +1896,6 @@ static int __ext4_journalled_writepage(struct page *page, inode_bh = ext4_journalled_write_inline_data(inode, len, page); if (inode_bh == NULL) goto out; - } else { - page_bufs = page_buffers(page); - if (!page_bufs) { - BUG(); - goto out; - } - ext4_walk_page_buffers(handle, inode, page_bufs, 0, len, - NULL, bget_one); } /* * We need to release the page lock before we start the @@ -1905,7 +1916,8 @@ static int __ext4_journalled_writepage(struct page *page, lock_page(page); put_page(page); - if (page->mapping != mapping) { + size = i_size_read(inode); + if (page->mapping != mapping || page_offset(page) > size) { /* The page got truncated from under us */ ext4_journal_stop(handle); ret = 0; @@ -1915,6 +1927,13 @@ static int __ext4_journalled_writepage(struct page *page, if (inline_data) { ret = ext4_mark_inode_dirty(handle, inode); } else { + struct buffer_head *page_bufs = page_buffers(page); + + if (page->index == size >> PAGE_SHIFT) + len = size & ~PAGE_MASK; + else + len = PAGE_SIZE; + ret = ext4_walk_page_buffers(handle, inode, page_bufs, 0, len, NULL, do_journal_get_write_access); @@ -1935,9 +1954,6 @@ static int __ext4_journalled_writepage(struct page *page, out: unlock_page(page); out_no_pagelock: - if (!inline_data && page_bufs) - ext4_walk_page_buffers(NULL, inode, page_bufs, 0, len, - NULL, bput_one); brelse(inode_bh); return ret; } @@ -1986,6 +2002,7 @@ out_no_pagelock: static int ext4_writepage(struct page *page, struct writeback_control *wbc) { + struct folio *folio = page_folio(page); int ret = 0; loff_t size; unsigned int len; @@ -1995,8 +2012,8 @@ static int ext4_writepage(struct page *page, bool keep_towrite = false; if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb)))) { - inode->i_mapping->a_ops->invalidatepage(page, 0, PAGE_SIZE); - unlock_page(page); + folio_invalidate(folio, 0, folio_size(folio)); + folio_unlock(folio); return -EIO; } @@ -2008,6 +2025,15 @@ static int ext4_writepage(struct page *page, else len = PAGE_SIZE; + /* Should never happen but for bugs in other kernel subsystems */ + if (!page_has_buffers(page)) { + ext4_warning_inode(inode, + "page %lu does not have buffers attached", page->index); + ClearPageDirty(page); + unlock_page(page); + return 0; + } + page_bufs = page_buffers(page); /* * We cannot do block allocation or other extent handling in this @@ -2257,7 +2283,6 @@ static int mpage_process_page(struct mpage_da_data *mpd, struct page *page, mpd->map.m_len = 0; mpd->map.m_flags = 0; io_end_vec->size += io_end_size; - io_end_size = 0; err = mpage_process_page_bufs(mpd, head, bh, lblk); if (err > 0) @@ -2282,7 +2307,6 @@ static int mpage_process_page(struct mpage_da_data *mpd, struct page *page, } while (lblk++, (bh = bh->b_this_page) != head); io_end_vec->size += io_end_size; - io_end_size = 0; *map_bh = false; out: *m_lblk = lblk; @@ -2306,8 +2330,8 @@ out: */ static int mpage_map_and_submit_buffers(struct mpage_da_data *mpd) { - struct pagevec pvec; - int nr_pages, i; + struct folio_batch fbatch; + unsigned nr, i; struct inode *inode = mpd->inode; int bpp_bits = PAGE_SHIFT - inode->i_blkbits; pgoff_t start, end; @@ -2321,14 +2345,13 @@ static int mpage_map_and_submit_buffers(struct mpage_da_data *mpd) lblk = start << bpp_bits; pblock = mpd->map.m_pblk; - pagevec_init(&pvec); + folio_batch_init(&fbatch); while (start <= end) { - nr_pages = pagevec_lookup_range(&pvec, inode->i_mapping, - &start, end); - if (nr_pages == 0) + nr = filemap_get_folios(inode->i_mapping, &start, end, &fbatch); + if (nr == 0) break; - for (i = 0; i < nr_pages; i++) { - struct page *page = pvec.pages[i]; + for (i = 0; i < nr; i++) { + struct page *page = &fbatch.folios[i]->page; err = mpage_process_page(mpd, page, &lblk, &pblock, &map_bh); @@ -2344,14 +2367,14 @@ static int mpage_map_and_submit_buffers(struct mpage_da_data *mpd) if (err < 0) goto out; } - pagevec_release(&pvec); + folio_batch_release(&fbatch); } /* Extent fully mapped and matches with page boundary. We are done. */ mpd->map.m_len = 0; mpd->map.m_flags = 0; return 0; out: - pagevec_release(&pvec); + folio_batch_release(&fbatch); return err; } @@ -2611,6 +2634,22 @@ static int mpage_prepare_extent_to_map(struct mpage_da_data *mpd) wait_on_page_writeback(page); BUG_ON(PageWriteback(page)); + /* + * Should never happen but for buggy code in + * other subsystems that call + * set_page_dirty() without properly warning + * the file system first. See [1] for more + * information. + * + * [1] https://lore.kernel.org/linux-mm/20180103100430.GE4911@quack2.suse.cz + */ + if (!page_has_buffers(page)) { + ext4_warning_inode(mpd->inode, "page %lu does not have buffers attached", page->index); + ClearPageDirty(page); + unlock_page(page); + continue; + } + if (mpd->map.m_len == 0) mpd->first_page = page->index; mpd->next_page = page->index + 1; @@ -2922,7 +2961,7 @@ static int ext4_nonda_switch(struct super_block *sb) } static int ext4_da_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, + loff_t pos, unsigned len, struct page **pagep, void **fsdata) { int ret, retries = 0; @@ -2935,18 +2974,16 @@ static int ext4_da_write_begin(struct file *file, struct address_space *mapping, index = pos >> PAGE_SHIFT; - if (ext4_nonda_switch(inode->i_sb) || S_ISLNK(inode->i_mode) || - ext4_verity_in_progress(inode)) { + if (ext4_nonda_switch(inode->i_sb) || ext4_verity_in_progress(inode)) { *fsdata = (void *)FALL_BACK_TO_NONDELALLOC; return ext4_write_begin(file, mapping, pos, - len, flags, pagep, fsdata); + len, pagep, fsdata); } *fsdata = (void *)0; - trace_ext4_da_write_begin(inode, pos, len, flags); + trace_ext4_da_write_begin(inode, pos, len); if (ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)) { - ret = ext4_da_write_inline_data_begin(mapping, inode, - pos, len, flags, + ret = ext4_da_write_inline_data_begin(mapping, inode, pos, len, pagep, fsdata); if (ret < 0) return ret; @@ -2955,7 +2992,7 @@ static int ext4_da_write_begin(struct file *file, struct address_space *mapping, } retry: - page = grab_cache_page_write_begin(mapping, index, flags); + page = grab_cache_page_write_begin(mapping, index); if (!page) return -ENOMEM; @@ -3121,13 +3158,15 @@ static sector_t ext4_bmap(struct address_space *mapping, sector_t block) { struct inode *inode = mapping->host; journal_t *journal; + sector_t ret = 0; int err; + inode_lock_shared(inode); /* * We can get here for an inline file via the FIBMAP ioctl */ if (ext4_has_inline_data(inode)) - return 0; + goto out; if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY) && test_opt(inode->i_sb, DELALLOC)) { @@ -3166,14 +3205,19 @@ static sector_t ext4_bmap(struct address_space *mapping, sector_t block) jbd2_journal_unlock_updates(journal); if (err) - return 0; + goto out; } - return iomap_bmap(mapping, block, &ext4_iomap_ops); + ret = iomap_bmap(mapping, block, &ext4_iomap_ops); + +out: + inode_unlock_shared(inode); + return ret; } -static int ext4_readpage(struct file *file, struct page *page) +static int ext4_read_folio(struct file *file, struct folio *folio) { + struct page *page = &folio->page; int ret = -EAGAIN; struct inode *inode = page->mapping->host; @@ -3199,55 +3243,54 @@ static void ext4_readahead(struct readahead_control *rac) ext4_mpage_readpages(inode, rac, NULL); } -static void ext4_invalidatepage(struct page *page, unsigned int offset, - unsigned int length) +static void ext4_invalidate_folio(struct folio *folio, size_t offset, + size_t length) { - trace_ext4_invalidatepage(page, offset, length); + trace_ext4_invalidate_folio(folio, offset, length); /* No journalling happens on data buffers when this function is used */ - WARN_ON(page_has_buffers(page) && buffer_jbd(page_buffers(page))); + WARN_ON(folio_buffers(folio) && buffer_jbd(folio_buffers(folio))); - block_invalidatepage(page, offset, length); + block_invalidate_folio(folio, offset, length); } -static int __ext4_journalled_invalidatepage(struct page *page, - unsigned int offset, - unsigned int length) +static int __ext4_journalled_invalidate_folio(struct folio *folio, + size_t offset, size_t length) { - journal_t *journal = EXT4_JOURNAL(page->mapping->host); + journal_t *journal = EXT4_JOURNAL(folio->mapping->host); - trace_ext4_journalled_invalidatepage(page, offset, length); + trace_ext4_journalled_invalidate_folio(folio, offset, length); /* * If it's a full truncate we just forget about the pending dirtying */ - if (offset == 0 && length == PAGE_SIZE) - ClearPageChecked(page); + if (offset == 0 && length == folio_size(folio)) + folio_clear_checked(folio); - return jbd2_journal_invalidatepage(journal, page, offset, length); + return jbd2_journal_invalidate_folio(journal, folio, offset, length); } /* Wrapper for aops... */ -static void ext4_journalled_invalidatepage(struct page *page, - unsigned int offset, - unsigned int length) +static void ext4_journalled_invalidate_folio(struct folio *folio, + size_t offset, + size_t length) { - WARN_ON(__ext4_journalled_invalidatepage(page, offset, length) < 0); + WARN_ON(__ext4_journalled_invalidate_folio(folio, offset, length) < 0); } -static int ext4_releasepage(struct page *page, gfp_t wait) +static bool ext4_release_folio(struct folio *folio, gfp_t wait) { - journal_t *journal = EXT4_JOURNAL(page->mapping->host); + journal_t *journal = EXT4_JOURNAL(folio->mapping->host); - trace_ext4_releasepage(page); + trace_ext4_releasepage(&folio->page); /* Page has dirty journalled data -> cannot release */ - if (PageChecked(page)) - return 0; + if (folio_test_checked(folio)) + return false; if (journal) - return jbd2_journal_try_to_free_buffers(journal, page); + return jbd2_journal_try_to_free_buffers(journal, folio); else - return try_to_free_buffers(page); + return try_to_free_buffers(folio); } static bool ext4_inode_datasync_dirty(struct inode *inode) @@ -3271,7 +3314,7 @@ static bool ext4_inode_datasync_dirty(struct inode *inode) static void ext4_set_iomap(struct inode *inode, struct iomap *iomap, struct ext4_map_blocks *map, loff_t offset, - loff_t length) + loff_t length, unsigned int flags) { u8 blkbits = inode->i_blkbits; @@ -3288,8 +3331,10 @@ static void ext4_set_iomap(struct inode *inode, struct iomap *iomap, if (map->m_flags & EXT4_MAP_NEW) iomap->flags |= IOMAP_F_NEW; - iomap->bdev = inode->i_sb->s_bdev; - iomap->dax_dev = EXT4_SB(inode->i_sb)->s_daxdev; + if (flags & IOMAP_DAX) + iomap->dax_dev = EXT4_SB(inode->i_sb)->s_daxdev; + else + iomap->bdev = inode->i_sb->s_bdev; iomap->offset = (u64) map->m_lblk << blkbits; iomap->length = (u64) map->m_len << blkbits; @@ -3309,9 +3354,13 @@ static void ext4_set_iomap(struct inode *inode, struct iomap *iomap, if (map->m_flags & EXT4_MAP_UNWRITTEN) { iomap->type = IOMAP_UNWRITTEN; iomap->addr = (u64) map->m_pblk << blkbits; + if (flags & IOMAP_DAX) + iomap->addr += EXT4_SB(inode->i_sb)->s_dax_part_off; } else if (map->m_flags & EXT4_MAP_MAPPED) { iomap->type = IOMAP_MAPPED; iomap->addr = (u64) map->m_pblk << blkbits; + if (flags & IOMAP_DAX) + iomap->addr += EXT4_SB(inode->i_sb)->s_dax_part_off; } else { iomap->type = IOMAP_HOLE; iomap->addr = IOMAP_NULL_ADDR; @@ -3348,8 +3397,8 @@ retry: * DAX and direct I/O are the only two operations that are currently * supported with IOMAP_WRITE. */ - WARN_ON(!IS_DAX(inode) && !(flags & IOMAP_DIRECT)); - if (IS_DAX(inode)) + WARN_ON(!(flags & (IOMAP_DAX | IOMAP_DIRECT))); + if (flags & IOMAP_DAX) m_flags = EXT4_GET_BLOCKS_CREATE_ZERO; /* * We use i_size instead of i_disksize here because delalloc writeback @@ -3420,7 +3469,14 @@ static int ext4_iomap_begin(struct inode *inode, loff_t offset, loff_t length, if (ret < 0) return ret; out: - ext4_set_iomap(inode, iomap, &map, offset, length); + /* + * When inline encryption is enabled, sometimes I/O to an encrypted file + * has to be broken up to guarantee DUN contiguity. Handle this by + * limiting the length of the mapping returned. + */ + map.m_len = fscrypt_limit_io_blocks(inode, map.m_lblk, map.m_len); + + ext4_set_iomap(inode, iomap, &map, offset, length, flags); return 0; } @@ -3540,7 +3596,7 @@ static int ext4_iomap_begin_report(struct inode *inode, loff_t offset, delalloc = ext4_iomap_is_delalloc(inode, &map); set_iomap: - ext4_set_iomap(inode, iomap, &map, offset, length); + ext4_set_iomap(inode, iomap, &map, offset, length, flags); if (delalloc && iomap->type == IOMAP_HOLE) iomap->type = IOMAP_DELALLOC; @@ -3552,29 +3608,32 @@ const struct iomap_ops ext4_iomap_report_ops = { }; /* - * Pages can be marked dirty completely asynchronously from ext4's journalling - * activity. By filemap_sync_pte(), try_to_unmap_one(), etc. We cannot do - * much here because ->set_page_dirty is called under VFS locks. The page is - * not necessarily locked. + * Whenever the folio is being dirtied, corresponding buffers should already + * be attached to the transaction (we take care of this in ext4_page_mkwrite() + * and ext4_write_begin()). However we cannot move buffers to dirty transaction + * lists here because ->dirty_folio is called under VFS locks and the folio + * is not necessarily locked. * - * We cannot just dirty the page and leave attached buffers clean, because the + * We cannot just dirty the folio and leave attached buffers clean, because the * buffers' dirty state is "definitive". We cannot just set the buffers dirty * or jbddirty because all the journalling code will explode. * - * So what we do is to mark the page "pending dirty" and next time writepage + * So what we do is to mark the folio "pending dirty" and next time writepage * is called, propagate that into the buffers appropriately. */ -static int ext4_journalled_set_page_dirty(struct page *page) +static bool ext4_journalled_dirty_folio(struct address_space *mapping, + struct folio *folio) { - SetPageChecked(page); - return __set_page_dirty_nobuffers(page); + WARN_ON_ONCE(!folio_buffers(folio)); + folio_set_checked(folio); + return filemap_dirty_folio(mapping, folio); } -static int ext4_set_page_dirty(struct page *page) +static bool ext4_dirty_folio(struct address_space *mapping, struct folio *folio) { - WARN_ON_ONCE(!PageLocked(page) && !PageDirty(page)); - WARN_ON_ONCE(!page_has_buffers(page)); - return __set_page_dirty_buffers(page); + WARN_ON_ONCE(!folio_test_locked(folio) && !folio_test_dirty(folio)); + WARN_ON_ONCE(!folio_buffers(folio)); + return block_dirty_folio(mapping, folio); } static int ext4_iomap_swap_activate(struct swap_info_struct *sis, @@ -3585,34 +3644,34 @@ static int ext4_iomap_swap_activate(struct swap_info_struct *sis, } static const struct address_space_operations ext4_aops = { - .readpage = ext4_readpage, + .read_folio = ext4_read_folio, .readahead = ext4_readahead, .writepage = ext4_writepage, .writepages = ext4_writepages, .write_begin = ext4_write_begin, .write_end = ext4_write_end, - .set_page_dirty = ext4_set_page_dirty, + .dirty_folio = ext4_dirty_folio, .bmap = ext4_bmap, - .invalidatepage = ext4_invalidatepage, - .releasepage = ext4_releasepage, + .invalidate_folio = ext4_invalidate_folio, + .release_folio = ext4_release_folio, .direct_IO = noop_direct_IO, - .migratepage = buffer_migrate_page, + .migrate_folio = buffer_migrate_folio, .is_partially_uptodate = block_is_partially_uptodate, .error_remove_page = generic_error_remove_page, .swap_activate = ext4_iomap_swap_activate, }; static const struct address_space_operations ext4_journalled_aops = { - .readpage = ext4_readpage, + .read_folio = ext4_read_folio, .readahead = ext4_readahead, .writepage = ext4_writepage, .writepages = ext4_writepages, .write_begin = ext4_write_begin, .write_end = ext4_journalled_write_end, - .set_page_dirty = ext4_journalled_set_page_dirty, + .dirty_folio = ext4_journalled_dirty_folio, .bmap = ext4_bmap, - .invalidatepage = ext4_journalled_invalidatepage, - .releasepage = ext4_releasepage, + .invalidate_folio = ext4_journalled_invalidate_folio, + .release_folio = ext4_release_folio, .direct_IO = noop_direct_IO, .is_partially_uptodate = block_is_partially_uptodate, .error_remove_page = generic_error_remove_page, @@ -3620,18 +3679,18 @@ static const struct address_space_operations ext4_journalled_aops = { }; static const struct address_space_operations ext4_da_aops = { - .readpage = ext4_readpage, + .read_folio = ext4_read_folio, .readahead = ext4_readahead, .writepage = ext4_writepage, .writepages = ext4_writepages, .write_begin = ext4_da_write_begin, .write_end = ext4_da_write_end, - .set_page_dirty = ext4_set_page_dirty, + .dirty_folio = ext4_dirty_folio, .bmap = ext4_bmap, - .invalidatepage = ext4_invalidatepage, - .releasepage = ext4_releasepage, + .invalidate_folio = ext4_invalidate_folio, + .release_folio = ext4_release_folio, .direct_IO = noop_direct_IO, - .migratepage = buffer_migrate_page, + .migrate_folio = buffer_migrate_folio, .is_partially_uptodate = block_is_partially_uptodate, .error_remove_page = generic_error_remove_page, .swap_activate = ext4_iomap_swap_activate, @@ -3640,9 +3699,8 @@ static const struct address_space_operations ext4_da_aops = { static const struct address_space_operations ext4_dax_aops = { .writepages = ext4_dax_writepages, .direct_IO = noop_direct_IO, - .set_page_dirty = __set_page_dirty_no_writeback, + .dirty_folio = noop_dirty_folio, .bmap = ext4_bmap, - .invalidatepage = noop_invalidatepage, .swap_activate = ext4_iomap_swap_activate, }; @@ -3780,8 +3838,8 @@ static int ext4_block_zero_page_range(handle_t *handle, length = max; if (IS_DAX(inode)) { - return iomap_zero_range(inode, from, length, NULL, - &ext4_iomap_ops); + return dax_zero_range(inode, from, length, NULL, + &ext4_iomap_ops); } return __ext4_block_zero_page_range(handle, mapping, from, length); } @@ -3930,27 +3988,20 @@ int ext4_break_layouts(struct inode *inode) * Returns: 0 on success or negative on failure */ -int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length) +int ext4_punch_hole(struct file *file, loff_t offset, loff_t length) { + struct inode *inode = file_inode(file); struct super_block *sb = inode->i_sb; ext4_lblk_t first_block, stop_block; struct address_space *mapping = inode->i_mapping; - loff_t first_block_offset, last_block_offset; + loff_t first_block_offset, last_block_offset, max_length; + struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); handle_t *handle; unsigned int credits; int ret = 0, ret2 = 0; trace_ext4_punch_hole(inode, offset, length, 0); - ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA); - if (ext4_has_inline_data(inode)) { - filemap_invalidate_lock(mapping); - ret = ext4_convert_inline_data(inode); - filemap_invalidate_unlock(mapping); - if (ret) - return ret; - } - /* * Write out all dirty pages to avoid race conditions * Then release them. @@ -3978,6 +4029,14 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length) offset; } + /* + * For punch hole the length + offset needs to be within one block + * before last range. Adjust the length if it goes beyond that limit. + */ + max_length = sbi->s_bitmap_maxbytes - inode->i_sb->s_blocksize; + if (offset + length > max_length) + length = max_length - offset; + if (offset & (sb->s_blocksize - 1) || (offset + length) & (sb->s_blocksize - 1)) { /* @@ -3990,9 +4049,13 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length) } - /* Wait all existing dio workers, newcomers will block on i_mutex */ + /* Wait all existing dio workers, newcomers will block on i_rwsem */ inode_dio_wait(inode); + ret = file_modified(file); + if (ret) + goto out_mutex; + /* * Prevent page faults from reinstantiating pages we have released from * page cache. @@ -4140,7 +4203,7 @@ int ext4_truncate(struct inode *inode) /* * There is a possibility that we're either freeing the inode * or it's a completely new inode. In those cases we might not - * have i_mutex locked because it's not necessary. + * have i_rwsem locked because it's not necessary. */ if (!(inode->i_state & (I_NEW|I_FREEING))) WARN_ON(!inode_is_locked(inode)); @@ -4523,7 +4586,7 @@ has_buffer: static int __ext4_get_inode_loc_noinmem(struct inode *inode, struct ext4_iloc *iloc) { - ext4_fsblk_t err_blk; + ext4_fsblk_t err_blk = 0; int ret; ret = __ext4_get_inode_loc(inode->i_sb, inode->i_ino, NULL, iloc, @@ -4538,7 +4601,7 @@ static int __ext4_get_inode_loc_noinmem(struct inode *inode, int ext4_get_inode_loc(struct inode *inode, struct ext4_iloc *iloc) { - ext4_fsblk_t err_blk; + ext4_fsblk_t err_blk = 0; int ret; ret = __ext4_get_inode_loc(inode->i_sb, inode->i_ino, inode, iloc, @@ -4646,8 +4709,7 @@ static inline int ext4_iget_extra_inode(struct inode *inode, __le32 *magic = (void *)raw_inode + EXT4_GOOD_OLD_INODE_SIZE + ei->i_extra_isize; - if (EXT4_GOOD_OLD_INODE_SIZE + ei->i_extra_isize + sizeof(__le32) <= - EXT4_INODE_SIZE(inode->i_sb) && + if (EXT4_INODE_HAS_XATTR_SPACE(inode) && *magic == cpu_to_le32(EXT4_XATTR_MAGIC)) { ext4_set_inode_state(inode, EXT4_STATE_XATTR); return ext4_find_inline_data_nolock(inode); @@ -4954,7 +5016,6 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino, } if (IS_ENCRYPTED(inode)) { inode->i_op = &ext4_encrypted_symlink_inode_operations; - ext4_set_aops(inode); } else if (ext4_inode_is_fast_symlink(inode)) { inode->i_link = (char *)ei->i_data; inode->i_op = &ext4_fast_symlink_inode_operations; @@ -4962,9 +5023,7 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino, sizeof(ei->i_data) - 1); } else { inode->i_op = &ext4_symlink_inode_operations; - ext4_set_aops(inode); } - inode_nohighmem(inode); } else if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode) || S_ISFIFO(inode->i_mode) || S_ISSOCK(inode->i_mode)) { inode->i_op = &ext4_special_inode_operations; @@ -5177,7 +5236,7 @@ int ext4_write_inode(struct inode *inode, struct writeback_control *wbc) if (EXT4_SB(inode->i_sb)->s_journal) { if (ext4_journal_current_handle()) { - jbd_debug(1, "called recursively, non-PF_MEMALLOC!\n"); + ext4_debug("called recursively, non-PF_MEMALLOC!\n"); dump_stack(); return -EIO; } @@ -5215,13 +5274,12 @@ int ext4_write_inode(struct inode *inode, struct writeback_control *wbc) } /* - * In data=journal mode ext4_journalled_invalidatepage() may fail to invalidate - * buffers that are attached to a page stradding i_size and are undergoing + * In data=journal mode ext4_journalled_invalidate_folio() may fail to invalidate + * buffers that are attached to a folio straddling i_size and are undergoing * commit. In that case we have to wait for commit to finish and try again. */ static void ext4_wait_for_tail_page_commit(struct inode *inode) { - struct page *page; unsigned offset; journal_t *journal = EXT4_SB(inode->i_sb)->s_journal; tid_t commit_tid = 0; @@ -5229,25 +5287,25 @@ static void ext4_wait_for_tail_page_commit(struct inode *inode) offset = inode->i_size & (PAGE_SIZE - 1); /* - * If the page is fully truncated, we don't need to wait for any commit - * (and we even should not as __ext4_journalled_invalidatepage() may - * strip all buffers from the page but keep the page dirty which can then - * confuse e.g. concurrent ext4_writepage() seeing dirty page without + * If the folio is fully truncated, we don't need to wait for any commit + * (and we even should not as __ext4_journalled_invalidate_folio() may + * strip all buffers from the folio but keep the folio dirty which can then + * confuse e.g. concurrent ext4_writepage() seeing dirty folio without * buffers). Also we don't need to wait for any commit if all buffers in - * the page remain valid. This is most beneficial for the common case of + * the folio remain valid. This is most beneficial for the common case of * blocksize == PAGESIZE. */ if (!offset || offset > (PAGE_SIZE - i_blocksize(inode))) return; while (1) { - page = find_lock_page(inode->i_mapping, + struct folio *folio = filemap_lock_folio(inode->i_mapping, inode->i_size >> PAGE_SHIFT); - if (!page) + if (!folio) return; - ret = __ext4_journalled_invalidatepage(page, offset, - PAGE_SIZE - offset); - unlock_page(page); - put_page(page); + ret = __ext4_journalled_invalidate_folio(folio, offset, + folio_size(folio) - offset); + folio_unlock(folio); + folio_put(folio); if (ret != -EBUSY) return; commit_tid = 0; @@ -5282,7 +5340,7 @@ static void ext4_wait_for_tail_page_commit(struct inode *inode) * transaction are already on disk (truncate waits for pages under * writeback). * - * Called with inode->i_mutex down. + * Called with inode->i_rwsem down. */ int ext4_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, struct iattr *attr) @@ -5291,6 +5349,7 @@ int ext4_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, int error, rc = 0; int orphan = 0; const unsigned int ia_valid = attr->ia_valid; + bool inc_ivers = true; if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb)))) return -EIO; @@ -5315,14 +5374,14 @@ int ext4_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, if (error) return error; - if (is_quota_modification(inode, attr)) { + if (is_quota_modification(mnt_userns, inode, attr)) { error = dquot_initialize(inode); if (error) return error; } - ext4_fc_start_update(inode); - if ((ia_valid & ATTR_UID && !uid_eq(attr->ia_uid, inode->i_uid)) || - (ia_valid & ATTR_GID && !gid_eq(attr->ia_gid, inode->i_gid))) { + + if (i_uid_needs_update(mnt_userns, attr, inode) || + i_gid_needs_update(mnt_userns, attr, inode)) { handle_t *handle; /* (user+group)*(old+new) structure, inode write (sb, @@ -5339,24 +5398,20 @@ int ext4_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, * counts xattr inode references. */ down_read(&EXT4_I(inode)->xattr_sem); - error = dquot_transfer(inode, attr); + error = dquot_transfer(mnt_userns, inode, attr); up_read(&EXT4_I(inode)->xattr_sem); if (error) { ext4_journal_stop(handle); - ext4_fc_stop_update(inode); return error; } /* Update corresponding info in inode so that everything is in * one transaction */ - if (attr->ia_valid & ATTR_UID) - inode->i_uid = attr->ia_uid; - if (attr->ia_valid & ATTR_GID) - inode->i_gid = attr->ia_gid; + i_uid_update(mnt_userns, attr, inode); + i_gid_update(mnt_userns, attr, inode); error = ext4_mark_inode_dirty(handle, inode); ext4_journal_stop(handle); if (unlikely(error)) { - ext4_fc_stop_update(inode); return error; } } @@ -5364,23 +5419,22 @@ int ext4_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, if (attr->ia_valid & ATTR_SIZE) { handle_t *handle; loff_t oldsize = inode->i_size; + loff_t old_disksize; int shrink = (attr->ia_size < inode->i_size); if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); if (attr->ia_size > sbi->s_bitmap_maxbytes) { - ext4_fc_stop_update(inode); return -EFBIG; } } if (!S_ISREG(inode->i_mode)) { - ext4_fc_stop_update(inode); return -EINVAL; } - if (IS_I_VERSION(inode) && attr->ia_size != inode->i_size) - inode_inc_iversion(inode); + if (attr->ia_size == inode->i_size) + inc_ivers = false; if (shrink) { if (ext4_should_order_data(inode)) { @@ -5427,8 +5481,7 @@ int ext4_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, ext4_fc_track_range(handle, inode, (attr->ia_size > 0 ? attr->ia_size - 1 : 0) >> inode->i_sb->s_blocksize_bits, - (oldsize > 0 ? oldsize - 1 : 0) >> - inode->i_sb->s_blocksize_bits); + EXT_MAX_BLOCKS - 1); else ext4_fc_track_range( handle, inode, @@ -5438,6 +5491,7 @@ int ext4_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, inode->i_sb->s_blocksize_bits); down_write(&EXT4_I(inode)->i_data_sem); + old_disksize = EXT4_I(inode)->i_disksize; EXT4_I(inode)->i_disksize = attr->ia_size; rc = ext4_mark_inode_dirty(handle, inode); if (!error) @@ -5449,6 +5503,8 @@ int ext4_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, */ if (!error) i_size_write(inode, attr->ia_size); + else + EXT4_I(inode)->i_disksize = old_disksize; up_write(&EXT4_I(inode)->i_data_sem); ext4_journal_stop(handle); if (error) @@ -5480,6 +5536,8 @@ out_mmap_sem: } if (!error) { + if (inc_ivers) + inode_inc_iversion(inode); setattr_copy(mnt_userns, inode, attr); mark_inode_dirty(inode); } @@ -5499,10 +5557,25 @@ err_out: ext4_std_error(inode->i_sb, error); if (!error) error = rc; - ext4_fc_stop_update(inode); return error; } +u32 ext4_dio_alignment(struct inode *inode) +{ + if (fsverity_active(inode)) + return 0; + if (ext4_should_journal_data(inode)) + return 0; + if (ext4_has_inline_data(inode)) + return 0; + if (IS_ENCRYPTED(inode)) { + if (!fscrypt_dio_supported(inode)) + return 0; + return i_blocksize(inode); + } + return 1; /* use the iomap defaults */ +} + int ext4_getattr(struct user_namespace *mnt_userns, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { @@ -5518,6 +5591,27 @@ int ext4_getattr(struct user_namespace *mnt_userns, const struct path *path, stat->btime.tv_nsec = ei->i_crtime.tv_nsec; } + /* + * Return the DIO alignment restrictions if requested. We only return + * this information when requested, since on encrypted files it might + * take a fair bit of work to get if the file wasn't opened recently. + */ + if ((request_mask & STATX_DIOALIGN) && S_ISREG(inode->i_mode)) { + u32 dio_align = ext4_dio_alignment(inode); + + stat->result_mask |= STATX_DIOALIGN; + if (dio_align == 1) { + struct block_device *bdev = inode->i_sb->s_bdev; + + /* iomap defaults */ + stat->dio_mem_align = bdev_dma_alignment(bdev) + 1; + stat->dio_offset_align = bdev_logical_block_size(bdev); + } else { + stat->dio_mem_align = dio_align; + stat->dio_offset_align = dio_align; + } + } + flags = ei->i_flags & EXT4_FL_USER_VISIBLE; if (flags & EXT4_APPEND_FL) stat->attributes |= STATX_ATTR_APPEND; @@ -5684,9 +5778,6 @@ int ext4_mark_iloc_dirty(handle_t *handle, } ext4_fc_track_inode(handle, inode); - if (IS_I_VERSION(inode)) - inode_inc_iversion(inode); - /* the do_update_inode consumes one bh->b_count */ get_bh(iloc->bh); @@ -6000,7 +6091,7 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val) return PTR_ERR(handle); ext4_fc_mark_ineligible(inode->i_sb, - EXT4_FC_REASON_JOURNAL_FLAG_CHANGE); + EXT4_FC_REASON_JOURNAL_FLAG_CHANGE, handle); err = ext4_mark_inode_dirty(handle, inode); ext4_handle_sync(handle); ext4_journal_stop(handle); diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index 606dee9e08a3..95dfea28bf4e 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -16,18 +16,268 @@ #include <linux/file.h> #include <linux/quotaops.h> #include <linux/random.h> -#include <linux/uuid.h> #include <linux/uaccess.h> #include <linux/delay.h> #include <linux/iversion.h> #include <linux/fileattr.h> +#include <linux/uuid.h> #include "ext4_jbd2.h" #include "ext4.h" #include <linux/fsmap.h> #include "fsmap.h" #include <trace/events/ext4.h> -/** +typedef void ext4_update_sb_callback(struct ext4_super_block *es, + const void *arg); + +/* + * Superblock modification callback function for changing file system + * label + */ +static void ext4_sb_setlabel(struct ext4_super_block *es, const void *arg) +{ + /* Sanity check, this should never happen */ + BUILD_BUG_ON(sizeof(es->s_volume_name) < EXT4_LABEL_MAX); + + memcpy(es->s_volume_name, (char *)arg, EXT4_LABEL_MAX); +} + +/* + * Superblock modification callback function for changing file system + * UUID. + */ +static void ext4_sb_setuuid(struct ext4_super_block *es, const void *arg) +{ + memcpy(es->s_uuid, (__u8 *)arg, UUID_SIZE); +} + +static +int ext4_update_primary_sb(struct super_block *sb, handle_t *handle, + ext4_update_sb_callback func, + const void *arg) +{ + int err = 0; + struct ext4_sb_info *sbi = EXT4_SB(sb); + struct buffer_head *bh = sbi->s_sbh; + struct ext4_super_block *es = sbi->s_es; + + trace_ext4_update_sb(sb, bh->b_blocknr, 1); + + BUFFER_TRACE(bh, "get_write_access"); + err = ext4_journal_get_write_access(handle, sb, + bh, + EXT4_JTR_NONE); + if (err) + goto out_err; + + lock_buffer(bh); + func(es, arg); + ext4_superblock_csum_set(sb); + unlock_buffer(bh); + + if (buffer_write_io_error(bh) || !buffer_uptodate(bh)) { + ext4_msg(sbi->s_sb, KERN_ERR, "previous I/O error to " + "superblock detected"); + clear_buffer_write_io_error(bh); + set_buffer_uptodate(bh); + } + + err = ext4_handle_dirty_metadata(handle, NULL, bh); + if (err) + goto out_err; + err = sync_dirty_buffer(bh); +out_err: + ext4_std_error(sb, err); + return err; +} + +/* + * Update one backup superblock in the group 'grp' using the callback + * function 'func' and argument 'arg'. If the handle is NULL the + * modification is not journalled. + * + * Returns: 0 when no modification was done (no superblock in the group) + * 1 when the modification was successful + * <0 on error + */ +static int ext4_update_backup_sb(struct super_block *sb, + handle_t *handle, ext4_group_t grp, + ext4_update_sb_callback func, const void *arg) +{ + int err = 0; + ext4_fsblk_t sb_block; + struct buffer_head *bh; + unsigned long offset = 0; + struct ext4_super_block *es; + + if (!ext4_bg_has_super(sb, grp)) + return 0; + + /* + * For the group 0 there is always 1k padding, so we have + * either adjust offset, or sb_block depending on blocksize + */ + if (grp == 0) { + sb_block = 1 * EXT4_MIN_BLOCK_SIZE; + offset = do_div(sb_block, sb->s_blocksize); + } else { + sb_block = ext4_group_first_block_no(sb, grp); + offset = 0; + } + + trace_ext4_update_sb(sb, sb_block, handle ? 1 : 0); + + bh = ext4_sb_bread(sb, sb_block, 0); + if (IS_ERR(bh)) + return PTR_ERR(bh); + + if (handle) { + BUFFER_TRACE(bh, "get_write_access"); + err = ext4_journal_get_write_access(handle, sb, + bh, + EXT4_JTR_NONE); + if (err) + goto out_bh; + } + + es = (struct ext4_super_block *) (bh->b_data + offset); + lock_buffer(bh); + if (ext4_has_metadata_csum(sb) && + es->s_checksum != ext4_superblock_csum(sb, es)) { + ext4_msg(sb, KERN_ERR, "Invalid checksum for backup " + "superblock %llu", sb_block); + unlock_buffer(bh); + goto out_bh; + } + func(es, arg); + if (ext4_has_metadata_csum(sb)) + es->s_checksum = ext4_superblock_csum(sb, es); + set_buffer_uptodate(bh); + unlock_buffer(bh); + + if (err) + goto out_bh; + + if (handle) { + err = ext4_handle_dirty_metadata(handle, NULL, bh); + if (err) + goto out_bh; + } else { + BUFFER_TRACE(bh, "marking dirty"); + mark_buffer_dirty(bh); + } + err = sync_dirty_buffer(bh); + +out_bh: + brelse(bh); + ext4_std_error(sb, err); + return (err) ? err : 1; +} + +/* + * Update primary and backup superblocks using the provided function + * func and argument arg. + * + * Only the primary superblock and at most two backup superblock + * modifications are journalled; the rest is modified without journal. + * This is safe because e2fsck will re-write them if there is a problem, + * and we're very unlikely to ever need more than two backups. + */ +static +int ext4_update_superblocks_fn(struct super_block *sb, + ext4_update_sb_callback func, + const void *arg) +{ + handle_t *handle; + ext4_group_t ngroups; + unsigned int three = 1; + unsigned int five = 5; + unsigned int seven = 7; + int err = 0, ret, i; + ext4_group_t grp, primary_grp; + struct ext4_sb_info *sbi = EXT4_SB(sb); + + /* + * We can't update superblocks while the online resize is running + */ + if (test_and_set_bit_lock(EXT4_FLAGS_RESIZING, + &sbi->s_ext4_flags)) { + ext4_msg(sb, KERN_ERR, "Can't modify superblock while" + "performing online resize"); + return -EBUSY; + } + + /* + * We're only going to update primary superblock and two + * backup superblocks in this transaction. + */ + handle = ext4_journal_start_sb(sb, EXT4_HT_MISC, 3); + if (IS_ERR(handle)) { + err = PTR_ERR(handle); + goto out; + } + + /* Update primary superblock */ + err = ext4_update_primary_sb(sb, handle, func, arg); + if (err) { + ext4_msg(sb, KERN_ERR, "Failed to update primary " + "superblock"); + goto out_journal; + } + + primary_grp = ext4_get_group_number(sb, sbi->s_sbh->b_blocknr); + ngroups = ext4_get_groups_count(sb); + + /* + * Update backup superblocks. We have to start from group 0 + * because it might not be where the primary superblock is + * if the fs is mounted with -o sb=<backup_sb_block> + */ + i = 0; + grp = 0; + while (grp < ngroups) { + /* Skip primary superblock */ + if (grp == primary_grp) + goto next_grp; + + ret = ext4_update_backup_sb(sb, handle, grp, func, arg); + if (ret < 0) { + /* Ignore bad checksum; try to update next sb */ + if (ret == -EFSBADCRC) + goto next_grp; + err = ret; + goto out_journal; + } + + i += ret; + if (handle && i > 1) { + /* + * We're only journalling primary superblock and + * two backup superblocks; the rest is not + * journalled. + */ + err = ext4_journal_stop(handle); + if (err) + goto out; + handle = NULL; + } +next_grp: + grp = ext4_list_backups(sb, &three, &five, &seven); + } + +out_journal: + if (handle) { + ret = ext4_journal_stop(handle); + if (ret && !err) + err = ret; + } +out: + clear_bit_unlock(EXT4_FLAGS_RESIZING, &sbi->s_ext4_flags); + smp_mb__after_atomic(); + return err ? err : 0; +} + +/* * Swap memory between @a and @b for @len bytes. * * @a: pointer to first memory area @@ -48,7 +298,7 @@ static void memswap(void *a, void *b, size_t len) } } -/** +/* * Swap i_data and associated attributes between @inode1 and @inode2. * This function is used for the primary swap between inode1 and inode2 * and also to revert this primary swap in case of errors. @@ -102,7 +352,7 @@ void ext4_reset_inode_seed(struct inode *inode) ei->i_csum_seed = ext4_chksum(sbi, csum, (__u8 *)&gen, sizeof(gen)); } -/** +/* * Swap the information from the given @inode and the inode * EXT4_BOOT_LOADER_INO. It will basically swap i_data and all other * important fields of the inodes. @@ -169,7 +419,7 @@ static long swap_inode_boot_loader(struct super_block *sb, err = -EINVAL; goto err_out; } - ext4_fc_start_ineligible(sb, EXT4_FC_REASON_SWAP_BOOT); + ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_SWAP_BOOT, handle); /* Protect extent tree against block allocations via delalloc */ ext4_double_down_write_data_sem(inode, inode_bl); @@ -201,9 +451,10 @@ static long swap_inode_boot_loader(struct super_block *sb, swap_inode_data(inode, inode_bl); inode->i_ctime = inode_bl->i_ctime = current_time(inode); + inode_inc_iversion(inode); - inode->i_generation = prandom_u32(); - inode_bl->i_generation = prandom_u32(); + inode->i_generation = get_random_u32(); + inode_bl->i_generation = get_random_u32(); ext4_reset_inode_seed(inode); ext4_reset_inode_seed(inode_bl); @@ -252,7 +503,6 @@ revert: err_out1: ext4_journal_stop(handle); - ext4_fc_stop_ineligible(sb); ext4_double_up_write_data_sem(inode, inode_bl); err_out: @@ -263,18 +513,6 @@ journal_err_out: return err; } -#ifdef CONFIG_FS_ENCRYPTION -static int uuid_is_zero(__u8 u[16]) -{ - int i; - - for (i = 0; i < 16; i++) - if (u[i]) - return 0; - return 1; -} -#endif - /* * If immutable is set and we are not clearing it, we're not allowed to change * anything else in the inode. Don't error out if we're only trying to set @@ -427,6 +665,7 @@ static int ext4_ioctl_setflags(struct inode *inode, ext4_set_inode_flags(inode, false); inode->i_ctime = current_time(inode); + inode_inc_iversion(inode); err = ext4_mark_iloc_dirty(handle, inode, &iloc); flags_err: @@ -537,6 +776,7 @@ static int ext4_ioctl_setproject(struct inode *inode, __u32 projid) EXT4_I(inode)->i_projid = kprojid; inode->i_ctime = current_time(inode); + inode_inc_iversion(inode); out_dirty: rc = ext4_mark_iloc_dirty(handle, inode, &iloc); if (!err) @@ -716,7 +956,9 @@ static long ext4_ioctl_group_add(struct file *file, test_opt(sb, INIT_INODE_TABLE)) err = ext4_register_li_request(sb, input->group); group_add_out: - ext4_resize_end(sb); + err2 = ext4_resize_end(sb, false); + if (err == 0) + err = err2; return err; } @@ -743,7 +985,6 @@ int ext4_fileattr_set(struct user_namespace *mnt_userns, u32 flags = fa->flags; int err = -EOPNOTSUPP; - ext4_fc_start_update(inode); if (flags & ~EXT4_FL_USER_VISIBLE) goto out; @@ -764,7 +1005,6 @@ int ext4_fileattr_set(struct user_namespace *mnt_userns, goto out; err = ext4_ioctl_setproject(inode, fa->fsx_projid); out: - ext4_fc_stop_update(inode); return err; } @@ -805,7 +1045,6 @@ static int ext4_ioctl_checkpoint(struct file *filp, unsigned long arg) __u32 flags = 0; unsigned int flush_flags = 0; struct super_block *sb = file_inode(filp)->i_sb; - struct request_queue *q; if (copy_from_user(&flags, (__u32 __user *)arg, sizeof(__u32))) @@ -823,13 +1062,8 @@ static int ext4_ioctl_checkpoint(struct file *filp, unsigned long arg) if (!EXT4_SB(sb)->s_journal) return -ENODEV; - if (flags & ~EXT4_IOC_CHECKPOINT_FLAG_VALID) - return -EINVAL; - - q = bdev_get_queue(EXT4_SB(sb)->s_journal->j_dev); - if (!q) - return -ENXIO; - if ((flags & JBD2_JOURNAL_FLUSH_DISCARD) && !blk_queue_discard(q)) + if ((flags & JBD2_JOURNAL_FLUSH_DISCARD) && + !bdev_max_discard_sectors(EXT4_SB(sb)->s_journal->j_dev)) return -EOPNOTSUPP; if (flags & EXT4_IOC_CHECKPOINT_FLAG_DRY_RUN) @@ -850,6 +1084,131 @@ static int ext4_ioctl_checkpoint(struct file *filp, unsigned long arg) return err; } +static int ext4_ioctl_setlabel(struct file *filp, const char __user *user_label) +{ + size_t len; + int ret = 0; + char new_label[EXT4_LABEL_MAX + 1]; + struct super_block *sb = file_inode(filp)->i_sb; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + /* + * Copy the maximum length allowed for ext4 label with one more to + * find the required terminating null byte in order to test the + * label length. The on disk label doesn't need to be null terminated. + */ + if (copy_from_user(new_label, user_label, EXT4_LABEL_MAX + 1)) + return -EFAULT; + + len = strnlen(new_label, EXT4_LABEL_MAX + 1); + if (len > EXT4_LABEL_MAX) + return -EINVAL; + + /* + * Clear the buffer after the new label + */ + memset(new_label + len, 0, EXT4_LABEL_MAX - len); + + ret = mnt_want_write_file(filp); + if (ret) + return ret; + + ret = ext4_update_superblocks_fn(sb, ext4_sb_setlabel, new_label); + + mnt_drop_write_file(filp); + return ret; +} + +static int ext4_ioctl_getlabel(struct ext4_sb_info *sbi, char __user *user_label) +{ + char label[EXT4_LABEL_MAX + 1]; + + /* + * EXT4_LABEL_MAX must always be smaller than FSLABEL_MAX because + * FSLABEL_MAX must include terminating null byte, while s_volume_name + * does not have to. + */ + BUILD_BUG_ON(EXT4_LABEL_MAX >= FSLABEL_MAX); + + memset(label, 0, sizeof(label)); + lock_buffer(sbi->s_sbh); + strncpy(label, sbi->s_es->s_volume_name, EXT4_LABEL_MAX); + unlock_buffer(sbi->s_sbh); + + if (copy_to_user(user_label, label, sizeof(label))) + return -EFAULT; + return 0; +} + +static int ext4_ioctl_getuuid(struct ext4_sb_info *sbi, + struct fsuuid __user *ufsuuid) +{ + struct fsuuid fsuuid; + __u8 uuid[UUID_SIZE]; + + if (copy_from_user(&fsuuid, ufsuuid, sizeof(fsuuid))) + return -EFAULT; + + if (fsuuid.fsu_len == 0) { + fsuuid.fsu_len = UUID_SIZE; + if (copy_to_user(ufsuuid, &fsuuid, sizeof(fsuuid.fsu_len))) + return -EFAULT; + return -EINVAL; + } + + if (fsuuid.fsu_len != UUID_SIZE || fsuuid.fsu_flags != 0) + return -EINVAL; + + lock_buffer(sbi->s_sbh); + memcpy(uuid, sbi->s_es->s_uuid, UUID_SIZE); + unlock_buffer(sbi->s_sbh); + + if (copy_to_user(&ufsuuid->fsu_uuid[0], uuid, UUID_SIZE)) + return -EFAULT; + return 0; +} + +static int ext4_ioctl_setuuid(struct file *filp, + const struct fsuuid __user *ufsuuid) +{ + int ret = 0; + struct super_block *sb = file_inode(filp)->i_sb; + struct fsuuid fsuuid; + __u8 uuid[UUID_SIZE]; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + /* + * If any checksums (group descriptors or metadata) are being used + * then the checksum seed feature is required to change the UUID. + */ + if (((ext4_has_feature_gdt_csum(sb) || ext4_has_metadata_csum(sb)) + && !ext4_has_feature_csum_seed(sb)) + || ext4_has_feature_stable_inodes(sb)) + return -EOPNOTSUPP; + + if (copy_from_user(&fsuuid, ufsuuid, sizeof(fsuuid))) + return -EFAULT; + + if (fsuuid.fsu_len != UUID_SIZE || fsuuid.fsu_flags != 0) + return -EINVAL; + + if (copy_from_user(uuid, &ufsuuid->fsu_uuid[0], UUID_SIZE)) + return -EFAULT; + + ret = mnt_want_write_file(filp); + if (ret) + return ret; + + ret = ext4_update_superblocks_fn(sb, ext4_sb_setuuid, &uuid); + mnt_drop_write_file(filp); + + return ret; +} + static long __ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { struct inode *inode = file_inode(filp); @@ -897,6 +1256,7 @@ static long __ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) err = ext4_reserve_inode_write(handle, inode, &iloc); if (err == 0) { inode->i_ctime = current_time(inode); + inode_inc_iversion(inode); inode->i_generation = generation; err = ext4_mark_iloc_dirty(handle, inode, &iloc); } @@ -942,7 +1302,9 @@ setversion_out: err = err2; mnt_drop_write_file(filp); group_extend_out: - ext4_resize_end(sb); + err2 = ext4_resize_end(sb, false); + if (err == 0) + err = err2; return err; } @@ -1076,7 +1438,7 @@ mext_out: err = ext4_resize_fs(sb, n_blocks_count); if (EXT4_SB(sb)->s_journal) { - ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_RESIZE); + ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_RESIZE, NULL); jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal); err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal, 0); jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal); @@ -1090,20 +1452,21 @@ mext_out: err = ext4_register_li_request(sb, o_group); resizefs_out: - ext4_resize_end(sb); + err2 = ext4_resize_end(sb, true); + if (err == 0) + err = err2; return err; } case FITRIM: { - struct request_queue *q = bdev_get_queue(sb->s_bdev); struct fstrim_range range; int ret = 0; if (!capable(CAP_SYS_ADMIN)) return -EPERM; - if (!blk_queue_discard(q)) + if (!bdev_max_discard_sectors(sb->s_bdev)) return -EOPNOTSUPP; /* @@ -1117,8 +1480,6 @@ resizefs_out: sizeof(range))) return -EFAULT; - range.minlen = max((unsigned int)range.minlen, - q->limits.discard_granularity); ret = ext4_trim_fs(sb, &range); if (ret < 0) return ret; @@ -1137,51 +1498,9 @@ resizefs_out: return -EOPNOTSUPP; return fscrypt_ioctl_set_policy(filp, (const void __user *)arg); - case FS_IOC_GET_ENCRYPTION_PWSALT: { -#ifdef CONFIG_FS_ENCRYPTION - int err, err2; - struct ext4_sb_info *sbi = EXT4_SB(sb); - handle_t *handle; + case FS_IOC_GET_ENCRYPTION_PWSALT: + return ext4_ioctl_get_encryption_pwsalt(filp, (void __user *)arg); - if (!ext4_has_feature_encrypt(sb)) - return -EOPNOTSUPP; - if (uuid_is_zero(sbi->s_es->s_encrypt_pw_salt)) { - err = mnt_want_write_file(filp); - if (err) - return err; - handle = ext4_journal_start_sb(sb, EXT4_HT_MISC, 1); - if (IS_ERR(handle)) { - err = PTR_ERR(handle); - goto pwsalt_err_exit; - } - err = ext4_journal_get_write_access(handle, sb, - sbi->s_sbh, - EXT4_JTR_NONE); - if (err) - goto pwsalt_err_journal; - lock_buffer(sbi->s_sbh); - generate_random_uuid(sbi->s_es->s_encrypt_pw_salt); - ext4_superblock_csum_set(sb); - unlock_buffer(sbi->s_sbh); - err = ext4_handle_dirty_metadata(handle, NULL, - sbi->s_sbh); - pwsalt_err_journal: - err2 = ext4_journal_stop(handle); - if (err2 && !err) - err = err2; - pwsalt_err_exit: - mnt_drop_write_file(filp); - if (err) - return err; - } - if (copy_to_user((void __user *) arg, - sbi->s_es->s_encrypt_pw_salt, 16)) - return -EFAULT; - return 0; -#else - return -EOPNOTSUPP; -#endif - } case FS_IOC_GET_ENCRYPTION_POLICY: if (!ext4_has_feature_encrypt(sb)) return -EOPNOTSUPP; @@ -1266,6 +1585,17 @@ resizefs_out: case EXT4_IOC_CHECKPOINT: return ext4_ioctl_checkpoint(filp, arg); + case FS_IOC_GETFSLABEL: + return ext4_ioctl_getlabel(EXT4_SB(sb), (void __user *)arg); + + case FS_IOC_SETFSLABEL: + return ext4_ioctl_setlabel(filp, + (const void __user *)arg); + + case EXT4_IOC_GETFSUUID: + return ext4_ioctl_getuuid(EXT4_SB(sb), (void __user *)arg); + case EXT4_IOC_SETFSUUID: + return ext4_ioctl_setuuid(filp, (const void __user *)arg); default: return -ENOTTY; } @@ -1273,13 +1603,7 @@ resizefs_out: long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { - long ret; - - ext4_fc_start_update(file_inode(filp)); - ret = __ext4_ioctl(filp, cmd, arg); - ext4_fc_stop_update(file_inode(filp)); - - return ret; + return __ext4_ioctl(filp, cmd, arg); } #ifdef CONFIG_COMPAT @@ -1347,6 +1671,10 @@ long ext4_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) case EXT4_IOC_GETSTATE: case EXT4_IOC_GET_ES_CACHE: case EXT4_IOC_CHECKPOINT: + case FS_IOC_GETFSLABEL: + case FS_IOC_SETFSLABEL: + case EXT4_IOC_GETFSUUID: + case EXT4_IOC_SETFSUUID: break; default: return -ENOIOCTLCMD; @@ -1354,3 +1682,21 @@ long ext4_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) return ext4_ioctl(file, cmd, (unsigned long) compat_ptr(arg)); } #endif + +static void set_overhead(struct ext4_super_block *es, const void *arg) +{ + es->s_overhead_clusters = cpu_to_le32(*((unsigned long *) arg)); +} + +int ext4_update_overhead(struct super_block *sb, bool force) +{ + struct ext4_sb_info *sbi = EXT4_SB(sb); + + if (sb_rdonly(sb)) + return 0; + if (!force && + (sbi->s_overhead == 0 || + sbi->s_overhead == le32_to_cpu(sbi->s_es->s_overhead_clusters))) + return 0; + return ext4_update_superblocks_fn(sb, set_overhead, &sbi->s_overhead); +} diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 215b7068f548..9dad93059945 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -140,13 +140,15 @@ * 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) + * 2) Average fragment size lists (sbi->s_mb_avg_fragment_size) * - * Locking: sbi->s_mb_rb_lock (rwlock) + * Locking: sbi->s_mb_avg_fragment_size_locks(array of rw locks) * - * 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). + * This is an array of lists where in the i-th list there are groups with + * average fragment size >= 2^i and < 2^(i+1). The average fragment size + * is computed as ext4_group_info->bb_free / ext4_group_info->bb_fragments. + * Note that we don't bother with a special list for completely empty groups + * so we only have MB_NUM_ORDERS(sb) lists. * * 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 @@ -160,7 +162,8 @@ * * 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. + * equal to request size using our average fragment size group lists (data + * structure 2) in O(1) 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. @@ -695,13 +698,10 @@ static int __mb_check_buddy(struct ext4_buddy *e4b, char *file, for (i = 0; i < max; i++) { if (mb_test_bit(i, buddy)) { - /* only single bit in buddy2 may be 1 */ + /* only single bit in buddy2 may be 0 */ if (!mb_test_bit(i << 1, buddy2)) { MB_CHECK_ASSERT( mb_test_bit((i<<1)+1, buddy2)); - } else if (!mb_test_bit((i << 1) + 1, buddy2)) { - MB_CHECK_ASSERT( - mb_test_bit(i << 1, buddy2)); } continue; } @@ -805,65 +805,51 @@ 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) +static int mb_avg_fragment_size_order(struct super_block *sb, ext4_grpblk_t len) { - 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; + int order; - 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); + /* + * We don't bother with a special lists groups with only 1 block free + * extents and for completely empty groups. + */ + order = fls(len) - 2; + if (order < 0) + return 0; + if (order == MB_NUM_ORDERS(sb)) + order--; + return order; } -/* - * Reinsert grpinfo into the avg_fragment_size tree with new average - * fragment size. - */ +/* Move group to appropriate avg_fragment_size list */ static void mb_update_avg_fragment_size(struct super_block *sb, struct ext4_group_info *grp) { struct ext4_sb_info *sbi = EXT4_SB(sb); + int new_order; 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); - } + new_order = mb_avg_fragment_size_order(sb, + grp->bb_free / grp->bb_fragments); + if (new_order == grp->bb_avg_fragment_size_order) + return; - 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); + if (grp->bb_avg_fragment_size_order != -1) { + write_lock(&sbi->s_mb_avg_fragment_size_locks[ + grp->bb_avg_fragment_size_order]); + list_del(&grp->bb_avg_fragment_size_node); + write_unlock(&sbi->s_mb_avg_fragment_size_locks[ + grp->bb_avg_fragment_size_order]); + } + grp->bb_avg_fragment_size_order = new_order; + write_lock(&sbi->s_mb_avg_fragment_size_locks[ + grp->bb_avg_fragment_size_order]); + list_add_tail(&grp->bb_avg_fragment_size_node, + &sbi->s_mb_avg_fragment_size[grp->bb_avg_fragment_size_order]); + write_unlock(&sbi->s_mb_avg_fragment_size_locks[ + grp->bb_avg_fragment_size_order]); } /* @@ -912,86 +898,55 @@ static void ext4_mb_choose_next_group_cr0(struct ext4_allocation_context *ac, *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. + * Choose next group by traversing average fragment size list of suitable + * order. Updates *new_cr if cr level needs an update. */ 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; - } + struct ext4_group_info *grp = NULL, *iter; + int i; 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); + } + + for (i = mb_avg_fragment_size_order(ac->ac_sb, ac->ac_g_ex.fe_len); + i < MB_NUM_ORDERS(ac->ac_sb); i++) { + if (list_empty(&sbi->s_mb_avg_fragment_size[i])) + continue; + read_lock(&sbi->s_mb_avg_fragment_size_locks[i]); + if (list_empty(&sbi->s_mb_avg_fragment_size[i])) { + read_unlock(&sbi->s_mb_avg_fragment_size_locks[i]); + continue; + } + list_for_each_entry(iter, &sbi->s_mb_avg_fragment_size[i], + bb_avg_fragment_size_node) { 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))) + if (likely(ext4_mb_good_group(ac, iter->bb_group, 1))) { + grp = iter; 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; + read_unlock(&sbi->s_mb_avg_fragment_size_locks[i]); + if (grp) + break; } -done: - if (found) { - grp = rb_entry(found, struct ext4_group_info, - bb_avg_fragment_size_rb); + if (grp) { *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) @@ -1000,7 +955,7 @@ static inline int should_optimize_scan(struct ext4_allocation_context *ac) return 0; if (ac->ac_criteria >= 2) return 0; - if (ext4_test_inode_flag(ac->ac_inode, EXT4_INODE_EXTENTS)) + if (!ext4_test_inode_flag(ac->ac_inode, EXT4_INODE_EXTENTS)) return 0; return 1; } @@ -1020,11 +975,6 @@ next_linear_group(struct ext4_allocation_context *ac, int group, int ngroups) 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: /* @@ -1052,8 +1002,10 @@ static void ext4_mb_choose_next_group(struct ext4_allocation_context *ac, { *new_cr = ac->ac_criteria; - if (!should_optimize_scan(ac) || ac->ac_groups_linear_remaining) + if (!should_optimize_scan(ac) || ac->ac_groups_linear_remaining) { + *group = next_linear_group(ac, *group, ngroups); return; + } if (*new_cr == 0) { ext4_mb_choose_next_group_cr0(ac, new_cr, group, ngroups); @@ -1078,23 +1030,25 @@ mb_set_largest_free_order(struct super_block *sb, struct ext4_group_info *grp) struct ext4_sb_info *sbi = EXT4_SB(sb); int i; - if (test_opt2(sb, MB_OPTIMIZE_SCAN) && grp->bb_largest_free_order >= 0) { + for (i = MB_NUM_ORDERS(sb) - 1; i >= 0; i--) + if (grp->bb_counters[i] > 0) + break; + /* No need to move between order lists? */ + if (!test_opt2(sb, MB_OPTIMIZE_SCAN) || + i == grp->bb_largest_free_order) { + grp->bb_largest_free_order = i; + return; + } + + if (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 */ - - 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) { + grp->bb_largest_free_order = i; + if (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, @@ -1151,13 +1105,13 @@ void ext4_mb_generate_buddy(struct super_block *sb, EXT4_GROUP_INFO_BBITMAP_CORRUPT); } mb_set_largest_free_order(sb, grp); + mb_update_avg_fragment_size(sb, grp); clear_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &(grp->bb_state)); period = get_cycles() - period; 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 @@ -1689,7 +1643,7 @@ static int mb_test_and_clear_bits(void *bm, int cur, int len) return zero_bit; } -void ext4_set_bits(void *bm, int cur, int len) +void mb_set_bits(void *bm, int cur, int len) { __u32 *addr; @@ -1936,6 +1890,7 @@ static int mb_mark_used(struct ext4_buddy *e4b, struct ext4_free_extent *ex) unsigned ret = 0; int len0 = len; void *buddy; + bool split = false; BUG_ON(start + len > (e4b->bd_sb->s_blocksize << 3)); BUG_ON(e4b->bd_group != ex->fe_group); @@ -1960,12 +1915,16 @@ static int mb_mark_used(struct ext4_buddy *e4b, struct ext4_free_extent *ex) /* let's maintain buddy itself */ while (len) { - ord = mb_find_order_for_block(e4b, start); + if (!split) + ord = mb_find_order_for_block(e4b, start); if (((start >> ord) << ord) == start && len >= (1 << ord)) { /* the whole chunk may be allocated at once! */ mlen = 1 << ord; - buddy = mb_find_buddy(e4b, ord, &max); + if (!split) + buddy = mb_find_buddy(e4b, ord, &max); + else + split = false; BUG_ON((start >> ord) >= max); mb_set_bit(start >> ord, buddy); e4b->bd_info->bb_counters[ord]--; @@ -1992,11 +1951,12 @@ static int mb_mark_used(struct ext4_buddy *e4b, struct ext4_free_extent *ex) mb_clear_bit(cur + 1, buddy); e4b->bd_info->bb_counters[ord]++; e4b->bd_info->bb_counters[ord]++; + split = true; } 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_set_bits(e4b->bd_bitmap, ex->fe_start, len0); mb_check_buddy(e4b); return ret; @@ -2633,7 +2593,7 @@ static noinline_for_stack int ext4_mb_regular_allocator(struct ext4_allocation_context *ac) { ext4_group_t prefetch_grp = 0, ngroups, group, i; - int cr = -1; + int cr = -1, new_cr; int err = 0, first_err = 0; unsigned int nr = 0, prefetch_ios = 0; struct ext4_sb_info *sbi; @@ -2704,17 +2664,14 @@ 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 = next_linear_group(ac, group, ngroups), - i++) { - int ret = 0, new_cr; + for (i = 0, new_cr = cr; i < ngroups; i++, + ext4_mb_choose_next_group(ac, &new_cr, &group, ngroups)) { + int ret = 0; cond_resched(); - - ext4_mb_choose_next_group(ac, &new_cr, &group, ngroups); if (new_cr != cr) { cr = new_cr; goto repeat; @@ -2834,7 +2791,7 @@ out: static void *ext4_mb_seq_groups_start(struct seq_file *seq, loff_t *pos) { - struct super_block *sb = PDE_DATA(file_inode(seq->file)); + struct super_block *sb = pde_data(file_inode(seq->file)); ext4_group_t group; if (*pos < 0 || *pos >= ext4_get_groups_count(sb)) @@ -2845,7 +2802,7 @@ static void *ext4_mb_seq_groups_start(struct seq_file *seq, loff_t *pos) static void *ext4_mb_seq_groups_next(struct seq_file *seq, void *v, loff_t *pos) { - struct super_block *sb = PDE_DATA(file_inode(seq->file)); + struct super_block *sb = pde_data(file_inode(seq->file)); ext4_group_t group; ++*pos; @@ -2857,7 +2814,7 @@ static void *ext4_mb_seq_groups_next(struct seq_file *seq, void *v, loff_t *pos) static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v) { - struct super_block *sb = PDE_DATA(file_inode(seq->file)); + struct super_block *sb = pde_data(file_inode(seq->file)); ext4_group_t group = (ext4_group_t) ((unsigned long) v); int i; int err, buddy_loaded = 0; @@ -2919,7 +2876,7 @@ const struct seq_operations ext4_mb_seq_groups_ops = { int ext4_seq_mb_stats_show(struct seq_file *seq, void *offset) { - struct super_block *sb = (struct super_block *)seq->private; + struct super_block *sb = seq->private; struct ext4_sb_info *sbi = EXT4_SB(sb); seq_puts(seq, "mballoc:\n"); @@ -2985,12 +2942,10 @@ int ext4_seq_mb_stats_show(struct seq_file *seq, void *offset) static void *ext4_mb_seq_structs_summary_start(struct seq_file *seq, loff_t *pos) __acquires(&EXT4_SB(sb)->s_mb_rb_lock) { - struct super_block *sb = PDE_DATA(file_inode(seq->file)); + 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) + if (*pos < 0 || *pos >= 2*MB_NUM_ORDERS(sb)) return NULL; position = *pos + 1; return (void *) ((unsigned long) position); @@ -2998,11 +2953,11 @@ __acquires(&EXT4_SB(sb)->s_mb_rb_lock) 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)); + struct super_block *sb = pde_data(file_inode(seq->file)); unsigned long position; ++*pos; - if (*pos < 0 || *pos >= MB_NUM_ORDERS(sb) + 1) + if (*pos < 0 || *pos >= 2*MB_NUM_ORDERS(sb)) return NULL; position = *pos + 1; return (void *) ((unsigned long) position); @@ -3010,33 +2965,26 @@ static void *ext4_mb_seq_structs_summary_next(struct seq_file *seq, void *v, lof 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 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; + unsigned int count; 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; + position -= MB_NUM_ORDERS(sb); + if (position == 0) + seq_puts(seq, "avg_fragment_size_lists:\n"); - seq_printf(seq, "\ttree_min: %u\n\ttree_max: %u\n\ttree_nodes: %u\n", - min, max, count); + count = 0; + read_lock(&sbi->s_mb_avg_fragment_size_locks[position]); + list_for_each_entry(grp, &sbi->s_mb_avg_fragment_size[position], + bb_avg_fragment_size_node) + count++; + read_unlock(&sbi->s_mb_avg_fragment_size_locks[position]); + seq_printf(seq, "\tlist_order_%u_groups: %u\n", + (unsigned int)position, count); return 0; } @@ -3046,9 +2994,11 @@ static int ext4_mb_seq_structs_summary_show(struct seq_file *seq, void *v) seq_puts(seq, "max_free_order_lists:\n"); } count = 0; + read_lock(&sbi->s_mb_largest_free_orders_locks[position]); list_for_each_entry(grp, &sbi->s_mb_largest_free_orders[position], bb_largest_free_order_node) count++; + read_unlock(&sbi->s_mb_largest_free_orders_locks[position]); seq_printf(seq, "\tlist_order_%u_groups: %u\n", (unsigned int)position, count); @@ -3056,11 +3006,7 @@ static int ext4_mb_seq_structs_summary_show(struct seq_file *seq, void *v) } static void ext4_mb_seq_structs_summary_stop(struct seq_file *seq, void *v) -__releases(&EXT4_SB(sb)->s_mb_rb_lock) { - 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 = { @@ -3173,8 +3119,9 @@ int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t group, 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); + INIT_LIST_HEAD(&meta_group_info[i]->bb_avg_fragment_size_node); meta_group_info[i]->bb_largest_free_order = -1; /* uninit */ + meta_group_info[i]->bb_avg_fragment_size_order = -1; /* uninit */ meta_group_info[i]->bb_group = group; mb_group_bb_bitmap_alloc(sb, meta_group_info[i], group); @@ -3423,7 +3370,24 @@ int ext4_mb_init(struct super_block *sb) i++; } while (i < MB_NUM_ORDERS(sb)); - sbi->s_mb_avg_fragment_size_root = RB_ROOT; + sbi->s_mb_avg_fragment_size = + kmalloc_array(MB_NUM_ORDERS(sb), sizeof(struct list_head), + GFP_KERNEL); + if (!sbi->s_mb_avg_fragment_size) { + ret = -ENOMEM; + goto out; + } + sbi->s_mb_avg_fragment_size_locks = + kmalloc_array(MB_NUM_ORDERS(sb), sizeof(rwlock_t), + GFP_KERNEL); + if (!sbi->s_mb_avg_fragment_size_locks) { + ret = -ENOMEM; + goto out; + } + for (i = 0; i < MB_NUM_ORDERS(sb); i++) { + INIT_LIST_HEAD(&sbi->s_mb_avg_fragment_size[i]); + rwlock_init(&sbi->s_mb_avg_fragment_size_locks[i]); + } sbi->s_mb_largest_free_orders = kmalloc_array(MB_NUM_ORDERS(sb), sizeof(struct list_head), GFP_KERNEL); @@ -3442,7 +3406,6 @@ int ext4_mb_init(struct super_block *sb) 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); sbi->s_mb_free_pending = 0; @@ -3498,7 +3461,7 @@ 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))) + if (bdev_nonrot(sb->s_bdev)) sbi->s_mb_max_linear_groups = 0; else sbi->s_mb_max_linear_groups = MB_DEFAULT_LINEAR_LIMIT; @@ -3513,6 +3476,8 @@ out_free_locality_groups: free_percpu(sbi->s_locality_groups); sbi->s_locality_groups = NULL; out: + kfree(sbi->s_mb_avg_fragment_size); + kfree(sbi->s_mb_avg_fragment_size_locks); kfree(sbi->s_mb_largest_free_orders); kfree(sbi->s_mb_largest_free_orders_locks); kfree(sbi->s_mb_offsets); @@ -3579,6 +3544,8 @@ int ext4_mb_release(struct super_block *sb) kvfree(group_info); rcu_read_unlock(); } + kfree(sbi->s_mb_avg_fragment_size); + kfree(sbi->s_mb_avg_fragment_size_locks); kfree(sbi->s_mb_largest_free_orders); kfree(sbi->s_mb_largest_free_orders_locks); kfree(sbi->s_mb_offsets); @@ -3629,7 +3596,7 @@ static inline int ext4_issue_discard(struct super_block *sb, return __blkdev_issue_discard(sb->s_bdev, (sector_t)discard_block << (sb->s_blocksize_bits - 9), (sector_t)count << (sb->s_blocksize_bits - 9), - GFP_NOFS, 0, biop); + GFP_NOFS, biop); } else return sb_issue_discard(sb, discard_block, count, GFP_NOFS, 0); } @@ -3825,7 +3792,7 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac, * We leak some of the blocks here. */ ext4_lock_group(sb, ac->ac_b_ex.fe_group); - ext4_set_bits(bitmap_bh->b_data, ac->ac_b_ex.fe_start, + mb_set_bits(bitmap_bh->b_data, ac->ac_b_ex.fe_start, ac->ac_b_ex.fe_len); ext4_unlock_group(sb, ac->ac_b_ex.fe_group); err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh); @@ -3844,7 +3811,7 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac, } } #endif - ext4_set_bits(bitmap_bh->b_data, ac->ac_b_ex.fe_start, + mb_set_bits(bitmap_bh->b_data, ac->ac_b_ex.fe_start, ac->ac_b_ex.fe_len); if (ext4_has_group_desc_csum(sb) && (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT))) { @@ -3899,69 +3866,103 @@ void ext4_mb_mark_bb(struct super_block *sb, ext4_fsblk_t block, struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_group_t group; ext4_grpblk_t blkoff; - int i, clen, err; + int i, err; int already; + unsigned int clen, clen_changed, thisgrp_len; - clen = EXT4_B2C(sbi, len); + while (len > 0) { + ext4_get_group_no_and_offset(sb, block, &group, &blkoff); - ext4_get_group_no_and_offset(sb, block, &group, &blkoff); - bitmap_bh = ext4_read_block_bitmap(sb, group); - if (IS_ERR(bitmap_bh)) { - err = PTR_ERR(bitmap_bh); - bitmap_bh = NULL; - goto out_err; - } + /* + * Check to see if we are freeing blocks across a group + * boundary. + * In case of flex_bg, this can happen that (block, len) may + * span across more than one group. In that case we need to + * get the corresponding group metadata to work with. + * For this we have goto again loop. + */ + thisgrp_len = min_t(unsigned int, (unsigned int)len, + EXT4_BLOCKS_PER_GROUP(sb) - EXT4_C2B(sbi, blkoff)); + clen = EXT4_NUM_B2C(sbi, thisgrp_len); + + if (!ext4_sb_block_valid(sb, NULL, block, thisgrp_len)) { + ext4_error(sb, "Marking blocks in system zone - " + "Block = %llu, len = %u", + block, thisgrp_len); + bitmap_bh = NULL; + break; + } - err = -EIO; - gdp = ext4_get_group_desc(sb, group, &gdp_bh); - if (!gdp) - goto out_err; + bitmap_bh = ext4_read_block_bitmap(sb, group); + if (IS_ERR(bitmap_bh)) { + err = PTR_ERR(bitmap_bh); + bitmap_bh = NULL; + break; + } - ext4_lock_group(sb, group); - already = 0; - for (i = 0; i < clen; i++) - if (!mb_test_bit(blkoff + i, bitmap_bh->b_data) == !state) - already++; + err = -EIO; + gdp = ext4_get_group_desc(sb, group, &gdp_bh); + if (!gdp) + break; - if (state) - ext4_set_bits(bitmap_bh->b_data, blkoff, clen); - else - mb_test_and_clear_bits(bitmap_bh->b_data, blkoff, clen); - if (ext4_has_group_desc_csum(sb) && - (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT))) { - gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT); - ext4_free_group_clusters_set(sb, gdp, - ext4_free_clusters_after_init(sb, - group, gdp)); - } - if (state) - clen = ext4_free_group_clusters(sb, gdp) - clen + already; - else - clen = ext4_free_group_clusters(sb, gdp) + clen - already; + ext4_lock_group(sb, group); + already = 0; + for (i = 0; i < clen; i++) + if (!mb_test_bit(blkoff + i, bitmap_bh->b_data) == + !state) + already++; + + clen_changed = clen - already; + if (state) + mb_set_bits(bitmap_bh->b_data, blkoff, clen); + else + mb_clear_bits(bitmap_bh->b_data, blkoff, clen); + if (ext4_has_group_desc_csum(sb) && + (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT))) { + gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT); + ext4_free_group_clusters_set(sb, gdp, + ext4_free_clusters_after_init(sb, group, gdp)); + } + if (state) + clen = ext4_free_group_clusters(sb, gdp) - clen_changed; + else + clen = ext4_free_group_clusters(sb, gdp) + clen_changed; - ext4_free_group_clusters_set(sb, gdp, clen); - ext4_block_bitmap_csum_set(sb, group, gdp, bitmap_bh); - ext4_group_desc_csum_set(sb, group, gdp); + ext4_free_group_clusters_set(sb, gdp, clen); + ext4_block_bitmap_csum_set(sb, group, gdp, bitmap_bh); + ext4_group_desc_csum_set(sb, group, gdp); - ext4_unlock_group(sb, group); + ext4_unlock_group(sb, group); - if (sbi->s_log_groups_per_flex) { - ext4_group_t flex_group = ext4_flex_group(sbi, group); + if (sbi->s_log_groups_per_flex) { + ext4_group_t flex_group = ext4_flex_group(sbi, group); + struct flex_groups *fg = sbi_array_rcu_deref(sbi, + s_flex_groups, flex_group); - atomic64_sub(len, - &sbi_array_rcu_deref(sbi, s_flex_groups, - flex_group)->free_clusters); + if (state) + atomic64_sub(clen_changed, &fg->free_clusters); + else + atomic64_add(clen_changed, &fg->free_clusters); + + } + + err = ext4_handle_dirty_metadata(NULL, NULL, bitmap_bh); + if (err) + break; + sync_dirty_buffer(bitmap_bh); + err = ext4_handle_dirty_metadata(NULL, NULL, gdp_bh); + sync_dirty_buffer(gdp_bh); + if (err) + break; + + block += thisgrp_len; + len -= thisgrp_len; + brelse(bitmap_bh); + BUG_ON(len < 0); } - err = ext4_handle_dirty_metadata(NULL, NULL, bitmap_bh); if (err) - goto out_err; - sync_dirty_buffer(bitmap_bh); - err = ext4_handle_dirty_metadata(NULL, NULL, gdp_bh); - sync_dirty_buffer(gdp_bh); - -out_err: - brelse(bitmap_bh); + brelse(bitmap_bh); } /* @@ -4073,6 +4074,15 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac, size = size >> bsbits; start = start_off >> bsbits; + /* + * For tiny groups (smaller than 8MB) the chosen allocation + * alignment may be larger than group size. Make sure the + * alignment does not move allocation to a different group which + * makes mballoc fail assertions later. + */ + start = max(start, rounddown(ac->ac_o_ex.fe_logical, + (ext4_lblk_t)EXT4_BLOCKS_PER_GROUP(ac->ac_sb))); + /* don't cover already allocated blocks in selected range */ if (ar->pleft && start <= ar->lleft) { size -= ar->lleft + 1 - start; @@ -4145,7 +4155,22 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac, } rcu_read_unlock(); - if (start + size <= ac->ac_o_ex.fe_logical && + /* + * In this function "start" and "size" are normalized for better + * alignment and length such that we could preallocate more blocks. + * This normalization is done such that original request of + * ac->ac_o_ex.fe_logical & fe_len should always lie within "start" and + * "size" boundaries. + * (Note fe_len can be relaxed since FS block allocation API does not + * provide gurantee on number of contiguous blocks allocation since that + * depends upon free space left, etc). + * In case of inode pa, later we use the allocated blocks + * [pa_start + fe_logical - pa_lstart, fe_len/size] from the preallocated + * range of goal/best blocks [start, size] to put it at the + * ac_o_ex.fe_logical extent of this inode. + * (See ext4_mb_use_inode_pa() for more details) + */ + if (start + size <= ac->ac_o_ex.fe_logical || start > ac->ac_o_ex.fe_logical) { ext4_msg(ac->ac_sb, KERN_ERR, "start %lu, size %lu, fe_logical %lu", @@ -4433,7 +4458,7 @@ static void ext4_mb_generate_from_freelist(struct super_block *sb, void *bitmap, while (n) { entry = rb_entry(n, struct ext4_free_data, efd_node); - ext4_set_bits(bitmap, entry->efd_start_cluster, entry->efd_count); + mb_set_bits(bitmap, entry->efd_start_cluster, entry->efd_count); n = rb_next(n); } return; @@ -4474,7 +4499,7 @@ void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap, if (unlikely(len == 0)) continue; BUG_ON(groupnr != group); - ext4_set_bits(bitmap, start, len); + mb_set_bits(bitmap, start, len); preallocated += len; } mb_debug(sb, "preallocated %d for group %u\n", preallocated, group); @@ -4814,7 +4839,7 @@ ext4_mb_release_group_pa(struct ext4_buddy *e4b, */ static noinline_for_stack int ext4_mb_discard_group_preallocations(struct super_block *sb, - ext4_group_t group, int needed) + ext4_group_t group, int *busy) { struct ext4_group_info *grp = ext4_get_group_info(sb, group); struct buffer_head *bitmap_bh = NULL; @@ -4822,8 +4847,7 @@ ext4_mb_discard_group_preallocations(struct super_block *sb, struct list_head list; struct ext4_buddy e4b; int err; - int busy = 0; - int free, free_total = 0; + int free = 0; mb_debug(sb, "discard preallocation for group %u\n", group); if (list_empty(&grp->bb_prealloc_list)) @@ -4846,19 +4870,14 @@ ext4_mb_discard_group_preallocations(struct super_block *sb, goto out_dbg; } - if (needed == 0) - needed = EXT4_CLUSTERS_PER_GROUP(sb) + 1; - INIT_LIST_HEAD(&list); -repeat: - free = 0; ext4_lock_group(sb, group); list_for_each_entry_safe(pa, tmp, &grp->bb_prealloc_list, pa_group_list) { spin_lock(&pa->pa_lock); if (atomic_read(&pa->pa_count)) { spin_unlock(&pa->pa_lock); - busy = 1; + *busy = 1; continue; } if (pa->pa_deleted) { @@ -4898,22 +4917,13 @@ repeat: call_rcu(&(pa)->u.pa_rcu, ext4_mb_pa_callback); } - free_total += free; - - /* if we still need more blocks and some PAs were used, try again */ - if (free_total < needed && busy) { - ext4_unlock_group(sb, group); - cond_resched(); - busy = 0; - goto repeat; - } ext4_unlock_group(sb, group); ext4_mb_unload_buddy(&e4b); put_bh(bitmap_bh); out_dbg: mb_debug(sb, "discarded (%d) blocks preallocated for group %u bb_free (%d)\n", - free_total, group, grp->bb_free); - return free_total; + free, group, grp->bb_free); + return free; } /* @@ -5147,6 +5157,7 @@ static void ext4_mb_group_or_file(struct ext4_allocation_context *ac) struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); int bsbits = ac->ac_sb->s_blocksize_bits; loff_t size, isize; + bool inode_pa_eligible, group_pa_eligible; if (!(ac->ac_flags & EXT4_MB_HINT_DATA)) return; @@ -5154,25 +5165,27 @@ static void ext4_mb_group_or_file(struct ext4_allocation_context *ac) if (unlikely(ac->ac_flags & EXT4_MB_HINT_GOAL_ONLY)) return; + group_pa_eligible = sbi->s_mb_group_prealloc > 0; + inode_pa_eligible = true; size = ac->ac_o_ex.fe_logical + EXT4_C2B(sbi, ac->ac_o_ex.fe_len); isize = (i_size_read(ac->ac_inode) + ac->ac_sb->s_blocksize - 1) >> bsbits; + /* No point in using inode preallocation for closed files */ if ((size == isize) && !ext4_fs_is_busy(sbi) && - !inode_is_open_for_write(ac->ac_inode)) { - ac->ac_flags |= EXT4_MB_HINT_NOPREALLOC; - return; - } + !inode_is_open_for_write(ac->ac_inode)) + inode_pa_eligible = false; - if (sbi->s_mb_group_prealloc <= 0) { - ac->ac_flags |= EXT4_MB_STREAM_ALLOC; - return; - } - - /* don't use group allocation for large files */ size = max(size, isize); - if (size > sbi->s_mb_stream_request) { - ac->ac_flags |= EXT4_MB_STREAM_ALLOC; + /* Don't use group allocation for large files */ + if (size > sbi->s_mb_stream_request) + group_pa_eligible = false; + + if (!group_pa_eligible) { + if (inode_pa_eligible) + ac->ac_flags |= EXT4_MB_STREAM_ALLOC; + else + ac->ac_flags |= EXT4_MB_HINT_NOPREALLOC; return; } @@ -5455,13 +5468,24 @@ static int ext4_mb_discard_preallocations(struct super_block *sb, int needed) { ext4_group_t i, ngroups = ext4_get_groups_count(sb); int ret; - int freed = 0; + int freed = 0, busy = 0; + int retry = 0; trace_ext4_mb_discard_preallocations(sb, needed); + + if (needed == 0) + needed = EXT4_CLUSTERS_PER_GROUP(sb) + 1; + repeat: for (i = 0; i < ngroups && needed > 0; i++) { - ret = ext4_mb_discard_group_preallocations(sb, i, needed); + ret = ext4_mb_discard_group_preallocations(sb, i, &busy); freed += ret; needed -= ret; + cond_resched(); + } + + if (needed > 0 && busy && ++retry < 3) { + busy = 0; + goto repeat; } return freed; @@ -5508,6 +5532,7 @@ ext4_fsblk_t ext4_mb_new_blocks(handle_t *handle, ext4_fsblk_t block = 0; unsigned int inquota = 0; unsigned int reserv_clstrs = 0; + int retries = 0; u64 seq; might_sleep(); @@ -5610,7 +5635,8 @@ repeat: ar->len = ac->ac_b_ex.fe_len; } } else { - if (ext4_mb_discard_preallocations_should_retry(sb, ac, &seq)) + if (++retries < 3 && + ext4_mb_discard_preallocations_should_retry(sb, ac, &seq)) goto repeat; /* * If block allocation fails then the pa allocated above @@ -5757,7 +5783,8 @@ static ext4_fsblk_t ext4_mb_new_blocks_simple(handle_t *handle, struct super_block *sb = ar->inode->i_sb; ext4_group_t group; ext4_grpblk_t blkoff; - int i = sb->s_blocksize; + ext4_grpblk_t max = EXT4_CLUSTERS_PER_GROUP(sb); + ext4_grpblk_t i = 0; ext4_fsblk_t goal, block; struct ext4_super_block *es = EXT4_SB(sb)->s_es; @@ -5779,19 +5806,26 @@ static ext4_fsblk_t ext4_mb_new_blocks_simple(handle_t *handle, ext4_get_group_no_and_offset(sb, max(ext4_group_first_block_no(sb, group), goal), NULL, &blkoff); - i = mb_find_next_zero_bit(bitmap_bh->b_data, sb->s_blocksize, + while (1) { + i = mb_find_next_zero_bit(bitmap_bh->b_data, max, blkoff); + if (i >= max) + break; + if (ext4_fc_replay_check_excluded(sb, + ext4_group_first_block_no(sb, group) + i)) { + blkoff = i + 1; + } else + break; + } brelse(bitmap_bh); - if (i >= sb->s_blocksize) - continue; - if (ext4_fc_replay_check_excluded(sb, - ext4_group_first_block_no(sb, group) + i)) - continue; - break; + if (i < max) + break; } - if (group >= ext4_get_groups_count(sb) && i >= sb->s_blocksize) + if (group >= ext4_get_groups_count(sb) || i >= max) { + *errp = -ENOSPC; return 0; + } block = ext4_group_first_block_no(sb, group) + i; ext4_mb_mark_bb(sb, block, 1, 1); @@ -5842,17 +5876,17 @@ static void ext4_free_blocks_simple(struct inode *inode, ext4_fsblk_t block, } /** - * ext4_free_blocks() -- Free given blocks and update quota + * ext4_mb_clear_bb() -- helper function for freeing blocks. + * Used by ext4_free_blocks() * @handle: handle for this transaction * @inode: inode - * @bh: optional buffer of the block to be freed * @block: starting physical block to be freed * @count: number of blocks to be freed * @flags: flags used by ext4_free_blocks */ -void ext4_free_blocks(handle_t *handle, struct inode *inode, - struct buffer_head *bh, ext4_fsblk_t block, - unsigned long count, int flags) +static void ext4_mb_clear_bb(handle_t *handle, struct inode *inode, + ext4_fsblk_t block, unsigned long count, + int flags) { struct buffer_head *bitmap_bh = NULL; struct super_block *sb = inode->i_sb; @@ -5869,79 +5903,14 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode, sbi = EXT4_SB(sb); - if (sbi->s_mount_state & EXT4_FC_REPLAY) { - ext4_free_blocks_simple(inode, block, count); - return; - } - - might_sleep(); - if (bh) { - if (block) - BUG_ON(block != bh->b_blocknr); - else - block = bh->b_blocknr; - } - if (!(flags & EXT4_FREE_BLOCKS_VALIDATED) && !ext4_inode_block_valid(inode, block, count)) { - ext4_error(sb, "Freeing blocks not in datazone - " - "block = %llu, count = %lu", block, count); + ext4_error(sb, "Freeing blocks in system zone - " + "Block = %llu, count = %lu", block, count); + /* err = 0. ext4_std_error should be a no op */ goto error_return; } - - ext4_debug("freeing block %llu\n", block); - trace_ext4_free_blocks(inode, block, count, flags); - - if (bh && (flags & EXT4_FREE_BLOCKS_FORGET)) { - BUG_ON(count > 1); - - ext4_forget(handle, flags & EXT4_FREE_BLOCKS_METADATA, - inode, bh, block); - } - - /* - * If the extent to be freed does not begin on a cluster - * boundary, we need to deal with partial clusters at the - * beginning and end of the extent. Normally we will free - * blocks at the beginning or the end unless we are explicitly - * requested to avoid doing so. - */ - overflow = EXT4_PBLK_COFF(sbi, block); - if (overflow) { - if (flags & EXT4_FREE_BLOCKS_NOFREE_FIRST_CLUSTER) { - overflow = sbi->s_cluster_ratio - overflow; - block += overflow; - if (count > overflow) - count -= overflow; - else - return; - } else { - block -= overflow; - count += overflow; - } - } - overflow = EXT4_LBLK_COFF(sbi, count); - if (overflow) { - if (flags & EXT4_FREE_BLOCKS_NOFREE_LAST_CLUSTER) { - if (count > overflow) - count -= overflow; - else - return; - } else - count += sbi->s_cluster_ratio - overflow; - } - - if (!bh && (flags & EXT4_FREE_BLOCKS_FORGET)) { - int i; - int is_metadata = flags & EXT4_FREE_BLOCKS_METADATA; - - for (i = 0; i < count; i++) { - cond_resched(); - if (is_metadata) - bh = sb_find_get_block(inode->i_sb, block + i); - ext4_forget(handle, is_metadata, inode, bh, block + i); - } - } + flags |= EXT4_FREE_BLOCKS_VALIDATED; do_more: overflow = 0; @@ -5959,6 +5928,8 @@ do_more: overflow = EXT4_C2B(sbi, bit) + count - EXT4_BLOCKS_PER_GROUP(sb); count -= overflow; + /* The range changed so it's no longer validated */ + flags &= ~EXT4_FREE_BLOCKS_VALIDATED; } count_clusters = EXT4_NUM_B2C(sbi, count); bitmap_bh = ext4_read_block_bitmap(sb, block_group); @@ -5973,13 +5944,8 @@ do_more: goto error_return; } - if (in_range(ext4_block_bitmap(sb, gdp), block, count) || - in_range(ext4_inode_bitmap(sb, gdp), block, count) || - in_range(block, ext4_inode_table(sb, gdp), - sbi->s_itb_per_group) || - in_range(block + count - 1, ext4_inode_table(sb, gdp), - sbi->s_itb_per_group)) { - + if (!(flags & EXT4_FREE_BLOCKS_VALIDATED) && + !ext4_inode_block_valid(inode, block, count)) { ext4_error(sb, "Freeing blocks in system zone - " "Block = %llu, count = %lu", block, count); /* err = 0. ext4_std_error should be a no op */ @@ -6050,7 +6016,7 @@ do_more: NULL); if (err && err != -EOPNOTSUPP) ext4_msg(sb, KERN_WARNING, "discard request in" - " group:%d block:%d count:%lu failed" + " group:%u block:%d count:%lu failed" " with %d", block_group, bit, count, err); } else @@ -6102,6 +6068,8 @@ do_more: block += count; count = overflow; put_bh(bitmap_bh); + /* The range changed so it's no longer validated */ + flags &= ~EXT4_FREE_BLOCKS_VALIDATED; goto do_more; } error_return: @@ -6111,6 +6079,108 @@ error_return: } /** + * ext4_free_blocks() -- Free given blocks and update quota + * @handle: handle for this transaction + * @inode: inode + * @bh: optional buffer of the block to be freed + * @block: starting physical block to be freed + * @count: number of blocks to be freed + * @flags: flags used by ext4_free_blocks + */ +void ext4_free_blocks(handle_t *handle, struct inode *inode, + struct buffer_head *bh, ext4_fsblk_t block, + unsigned long count, int flags) +{ + struct super_block *sb = inode->i_sb; + unsigned int overflow; + struct ext4_sb_info *sbi; + + sbi = EXT4_SB(sb); + + if (sbi->s_mount_state & EXT4_FC_REPLAY) { + ext4_free_blocks_simple(inode, block, count); + return; + } + + might_sleep(); + if (bh) { + if (block) + BUG_ON(block != bh->b_blocknr); + else + block = bh->b_blocknr; + } + + if (!(flags & EXT4_FREE_BLOCKS_VALIDATED) && + !ext4_inode_block_valid(inode, block, count)) { + ext4_error(sb, "Freeing blocks not in datazone - " + "block = %llu, count = %lu", block, count); + return; + } + flags |= EXT4_FREE_BLOCKS_VALIDATED; + + ext4_debug("freeing block %llu\n", block); + trace_ext4_free_blocks(inode, block, count, flags); + + if (bh && (flags & EXT4_FREE_BLOCKS_FORGET)) { + BUG_ON(count > 1); + + ext4_forget(handle, flags & EXT4_FREE_BLOCKS_METADATA, + inode, bh, block); + } + + /* + * If the extent to be freed does not begin on a cluster + * boundary, we need to deal with partial clusters at the + * beginning and end of the extent. Normally we will free + * blocks at the beginning or the end unless we are explicitly + * requested to avoid doing so. + */ + overflow = EXT4_PBLK_COFF(sbi, block); + if (overflow) { + if (flags & EXT4_FREE_BLOCKS_NOFREE_FIRST_CLUSTER) { + overflow = sbi->s_cluster_ratio - overflow; + block += overflow; + if (count > overflow) + count -= overflow; + else + return; + } else { + block -= overflow; + count += overflow; + } + /* The range changed so it's no longer validated */ + flags &= ~EXT4_FREE_BLOCKS_VALIDATED; + } + overflow = EXT4_LBLK_COFF(sbi, count); + if (overflow) { + if (flags & EXT4_FREE_BLOCKS_NOFREE_LAST_CLUSTER) { + if (count > overflow) + count -= overflow; + else + return; + } else + count += sbi->s_cluster_ratio - overflow; + /* The range changed so it's no longer validated */ + flags &= ~EXT4_FREE_BLOCKS_VALIDATED; + } + + if (!bh && (flags & EXT4_FREE_BLOCKS_FORGET)) { + int i; + int is_metadata = flags & EXT4_FREE_BLOCKS_METADATA; + + for (i = 0; i < count; i++) { + cond_resched(); + if (is_metadata) + bh = sb_find_get_block(inode->i_sb, block + i); + ext4_forget(handle, is_metadata, inode, bh, block + i); + } + } + + ext4_mb_clear_bb(handle, inode, block, count, flags); + return; +} + +/** * ext4_group_add_blocks() -- Add given blocks to an existing group * @handle: handle to this transaction * @sb: super block @@ -6166,11 +6236,7 @@ int ext4_group_add_blocks(handle_t *handle, struct super_block *sb, goto error_return; } - if (in_range(ext4_block_bitmap(sb, desc), block, count) || - in_range(ext4_inode_bitmap(sb, desc), block, count) || - in_range(block, ext4_inode_table(sb, desc), sbi->s_itb_per_group) || - in_range(block + count - 1, ext4_inode_table(sb, desc), - sbi->s_itb_per_group)) { + if (!ext4_sb_block_valid(sb, NULL, block, count)) { ext4_error(sb, "Adding blocks in system zones - " "Block = %llu, count = %lu", block, count); @@ -6347,6 +6413,7 @@ __releases(ext4_group_lock_ptr(sb, e4b->bd_group)) * @start: first group block to examine * @max: last group block to examine * @minblocks: minimum extent block count + * @set_trimmed: set the trimmed flag if at least one block is trimmed * * ext4_trim_all_free walks through group's block bitmap searching for free * extents. When the free extent is found, mark it as used in group buddy @@ -6356,7 +6423,7 @@ __releases(ext4_group_lock_ptr(sb, e4b->bd_group)) static ext4_grpblk_t ext4_trim_all_free(struct super_block *sb, ext4_group_t group, ext4_grpblk_t start, ext4_grpblk_t max, - ext4_grpblk_t minblocks) + ext4_grpblk_t minblocks, bool set_trimmed) { struct ext4_buddy e4b; int ret; @@ -6373,9 +6440,9 @@ ext4_trim_all_free(struct super_block *sb, ext4_group_t group, ext4_lock_group(sb, group); if (!EXT4_MB_GRP_WAS_TRIMMED(e4b.bd_info) || - minblocks < atomic_read(&EXT4_SB(sb)->s_last_trim_minblks)) { + minblocks < EXT4_SB(sb)->s_last_trim_minblks) { ret = ext4_try_to_trim_range(sb, &e4b, start, max, minblocks); - if (ret >= 0) + if (ret >= 0 && set_trimmed) EXT4_MB_GRP_SET_TRIMMED(e4b.bd_info); } else { ret = 0; @@ -6404,6 +6471,7 @@ ext4_trim_all_free(struct super_block *sb, ext4_group_t group, */ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range) { + unsigned int discard_granularity = bdev_discard_granularity(sb->s_bdev); struct ext4_group_info *grp; ext4_group_t group, first_group, last_group; ext4_grpblk_t cnt = 0, first_cluster, last_cluster; @@ -6411,6 +6479,7 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range) ext4_fsblk_t first_data_blk = le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block); ext4_fsblk_t max_blks = ext4_blocks_count(EXT4_SB(sb)->s_es); + bool whole_group, eof = false; int ret = 0; start = range->start >> sb->s_blocksize_bits; @@ -6422,8 +6491,17 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range) start >= max_blks || range->len < sb->s_blocksize) return -EINVAL; - if (end >= max_blks) + /* No point to try to trim less than discard granularity */ + if (range->minlen < discard_granularity) { + minlen = EXT4_NUM_B2C(EXT4_SB(sb), + discard_granularity >> sb->s_blocksize_bits); + if (minlen > EXT4_CLUSTERS_PER_GROUP(sb)) + goto out; + } + if (end >= max_blks - 1) { end = max_blks - 1; + eof = true; + } if (end <= first_data_blk) goto out; if (start < first_data_blk) @@ -6437,6 +6515,7 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range) /* end now represents the last cluster to discard in this group */ end = EXT4_CLUSTERS_PER_GROUP(sb) - 1; + whole_group = true; for (group = first_group; group <= last_group; group++) { grp = ext4_get_group_info(sb, group); @@ -6453,12 +6532,13 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range) * change it for the last group, note that last_cluster is * already computed earlier by ext4_get_group_no_and_offset() */ - if (group == last_group) + if (group == last_group) { end = last_cluster; - + whole_group = eof ? true : end == EXT4_CLUSTERS_PER_GROUP(sb) - 1; + } if (grp->bb_free >= minlen) { cnt = ext4_trim_all_free(sb, group, first_cluster, - end, minlen); + end, minlen, whole_group); if (cnt < 0) { ret = cnt; break; @@ -6474,7 +6554,7 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range) } if (!ret) - atomic_set(&EXT4_SB(sb)->s_last_trim_minblks, minlen); + EXT4_SB(sb)->s_last_trim_minblks = minlen; out: range->len = EXT4_C2B(EXT4_SB(sb), trimmed) << sb->s_blocksize_bits; diff --git a/fs/ext4/mballoc.h b/fs/ext4/mballoc.h index 39da92ceabf8..dcda2a943cee 100644 --- a/fs/ext4/mballoc.h +++ b/fs/ext4/mballoc.h @@ -178,7 +178,6 @@ 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; diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c index 7e0b4f81c6c0..a19a9661646e 100644 --- a/fs/ext4/migrate.c +++ b/fs/ext4/migrate.c @@ -56,8 +56,7 @@ static int finish_range(handle_t *handle, struct inode *inode, retval = ext4_ext_insert_extent(handle, inode, &path, &newext, 0); err_out: up_write((&EXT4_I(inode)->i_data_sem)); - ext4_ext_drop_refs(path); - kfree(path); + ext4_free_ext_path(path); lb->first_pblock = 0; return retval; } @@ -417,7 +416,7 @@ int ext4_ext_migrate(struct inode *inode) struct inode *tmp_inode = NULL; struct migrate_struct lb; unsigned long max_entries; - __u32 goal; + __u32 goal, tmp_csum_seed; uid_t owner[2]; /* @@ -425,7 +424,8 @@ int ext4_ext_migrate(struct inode *inode) * already is extent-based, error out. */ if (!ext4_has_feature_extents(inode->i_sb) || - (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) + ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS) || + ext4_has_inline_data(inode)) return -EINVAL; if (S_ISLNK(inode->i_mode) && inode->i_blocks == 0) @@ -437,12 +437,12 @@ int ext4_ext_migrate(struct inode *inode) percpu_down_write(&sbi->s_writepages_rwsem); /* - * Worst case we can touch the allocation bitmaps, a bgd - * block, and a block to link in the orphan list. We do need - * need to worry about credits for modifying the quota inode. + * Worst case we can touch the allocation bitmaps and a block + * group descriptor block. We do need to worry about + * credits for modifying the quota inode. */ handle = ext4_journal_start(inode, EXT4_HT_MIGRATE, - 4 + EXT4_MAXQUOTAS_TRANS_BLOCKS(inode->i_sb)); + 3 + EXT4_MAXQUOTAS_TRANS_BLOCKS(inode->i_sb)); if (IS_ERR(handle)) { retval = PTR_ERR(handle); @@ -459,6 +459,14 @@ int ext4_ext_migrate(struct inode *inode) ext4_journal_stop(handle); goto out_unlock; } + /* + * Use the correct seed for checksum (i.e. the seed from 'inode'). This + * is so that the metadata blocks will have the correct checksum after + * the migration. + */ + ei = EXT4_I(inode); + tmp_csum_seed = EXT4_I(tmp_inode)->i_csum_seed; + EXT4_I(tmp_inode)->i_csum_seed = ei->i_csum_seed; i_size_write(tmp_inode, i_size_read(inode)); /* * Set the i_nlink to zero so it will be deleted later @@ -467,7 +475,6 @@ int ext4_ext_migrate(struct inode *inode) clear_nlink(tmp_inode); ext4_ext_tree_init(handle, tmp_inode); - ext4_orphan_add(handle, tmp_inode); ext4_journal_stop(handle); /* @@ -479,7 +486,7 @@ int ext4_ext_migrate(struct inode *inode) * when we add extents we extent the journal */ /* - * Even though we take i_mutex we can still cause block + * Even though we take i_rwsem we can still cause block * allocation via mmap write to holes. If we have allocated * new blocks we fail migrate. New block allocation will * clear EXT4_STATE_EXT_MIGRATE flag. The flag is updated @@ -492,17 +499,10 @@ int ext4_ext_migrate(struct inode *inode) handle = ext4_journal_start(inode, EXT4_HT_MIGRATE, 1); if (IS_ERR(handle)) { - /* - * It is impossible to update on-disk structures without - * a handle, so just rollback in-core changes and live other - * work to orphan_list_cleanup() - */ - ext4_orphan_del(NULL, tmp_inode); retval = PTR_ERR(handle); goto out_tmp_inode; } - ei = EXT4_I(inode); i_data = ei->i_data; memset(&lb, 0, sizeof(lb)); @@ -576,6 +576,7 @@ err_out: * the inode is not visible to user space. */ tmp_inode->i_blocks = 0; + EXT4_I(tmp_inode)->i_csum_seed = tmp_csum_seed; /* Reset the extent details */ ext4_ext_tree_init(handle, tmp_inode); diff --git a/fs/ext4/mmp.c b/fs/ext4/mmp.c index cebea4270817..588cb09c5291 100644 --- a/fs/ext4/mmp.c +++ b/fs/ext4/mmp.c @@ -52,7 +52,7 @@ static int write_mmp_block(struct super_block *sb, struct buffer_head *bh) lock_buffer(bh); bh->b_end_io = end_buffer_write_sync; get_bh(bh); - submit_bh(REQ_OP_WRITE, REQ_SYNC | REQ_META | REQ_PRIO, bh); + submit_bh(REQ_OP_WRITE | REQ_SYNC | REQ_META | REQ_PRIO, bh); wait_on_buffer(bh); sb_end_write(sb); if (unlikely(!buffer_uptodate(bh))) @@ -127,7 +127,7 @@ void __dump_mmp_msg(struct super_block *sb, struct mmp_struct *mmp, */ static int kmmpd(void *data) { - struct super_block *sb = (struct super_block *) data; + struct super_block *sb = data; struct ext4_super_block *es = EXT4_SB(sb)->s_es; struct buffer_head *bh = EXT4_SB(sb)->s_mmp_bh; struct mmp_struct *mmp; @@ -150,8 +150,6 @@ static int kmmpd(void *data) mmp_check_interval = max(EXT4_MMP_CHECK_MULT * mmp_update_interval, EXT4_MMP_MIN_CHECK_INTERVAL); mmp->mmp_check_interval = cpu_to_le16(mmp_check_interval); - BUILD_BUG_ON(sizeof(mmp->mmp_bdevname) < BDEVNAME_SIZE); - bdevname(bh->b_bdev, mmp->mmp_bdevname); memcpy(mmp->mmp_nodename, init_utsname()->nodename, sizeof(mmp->mmp_nodename)); @@ -267,7 +265,7 @@ static unsigned int mmp_new_seq(void) u32 new_seq; do { - new_seq = prandom_u32(); + new_seq = get_random_u32(); } while (new_seq > EXT4_MMP_SEQ_MAX); return new_seq; @@ -372,13 +370,16 @@ skip: EXT4_SB(sb)->s_mmp_bh = bh; + BUILD_BUG_ON(sizeof(mmp->mmp_bdevname) < BDEVNAME_SIZE); + snprintf(mmp->mmp_bdevname, sizeof(mmp->mmp_bdevname), + "%pg", bh->b_bdev); + /* * Start a kernel thread to update the MMP block periodically. */ EXT4_SB(sb)->s_mmp_tsk = kthread_run(kmmpd, sb, "kmmpd-%.*s", (int)sizeof(mmp->mmp_bdevname), - bdevname(bh->b_bdev, - mmp->mmp_bdevname)); + mmp->mmp_bdevname); if (IS_ERR(EXT4_SB(sb)->s_mmp_tsk)) { EXT4_SB(sb)->s_mmp_tsk = NULL; ext4_warning(sb, "Unable to create kmmpd thread for %s.", diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c index 64a579734f93..044e34cd835c 100644 --- a/fs/ext4/move_extent.c +++ b/fs/ext4/move_extent.c @@ -8,6 +8,7 @@ #include <linux/fs.h> #include <linux/quotaops.h> #include <linux/slab.h> +#include <linux/sched/mm.h> #include "ext4_jbd2.h" #include "ext4.h" #include "ext4_extents.h" @@ -31,8 +32,7 @@ get_ext_path(struct inode *inode, ext4_lblk_t lblock, if (IS_ERR(path)) return PTR_ERR(path); if (path[ext_depth(inode)].p_ext == NULL) { - ext4_ext_drop_refs(path); - kfree(path); + ext4_free_ext_path(path); *ppath = NULL; return -ENODATA; } @@ -102,12 +102,10 @@ mext_check_coverage(struct inode *inode, ext4_lblk_t from, ext4_lblk_t count, if (unwritten != ext4_ext_is_unwritten(ext)) goto out; from += ext4_ext_get_actual_len(ext); - ext4_ext_drop_refs(path); } ret = 1; out: - ext4_ext_drop_refs(path); - kfree(path); + ext4_free_ext_path(path); return ret; } @@ -127,7 +125,7 @@ mext_page_double_lock(struct inode *inode1, struct inode *inode2, pgoff_t index1, pgoff_t index2, struct page *page[2]) { struct address_space *mapping[2]; - unsigned fl = AOP_FLAG_NOFS; + unsigned int flags; BUG_ON(!inode1 || !inode2); if (inode1 < inode2) { @@ -139,11 +137,15 @@ mext_page_double_lock(struct inode *inode1, struct inode *inode2, mapping[1] = inode1->i_mapping; } - page[0] = grab_cache_page_write_begin(mapping[0], index1, fl); - if (!page[0]) + flags = memalloc_nofs_save(); + page[0] = grab_cache_page_write_begin(mapping[0], index1); + if (!page[0]) { + memalloc_nofs_restore(flags); return -ENOMEM; + } - page[1] = grab_cache_page_write_begin(mapping[1], index2, fl); + page[1] = grab_cache_page_write_begin(mapping[1], index2); + memalloc_nofs_restore(flags); if (!page[1]) { unlock_page(page[0]); put_page(page[0]); @@ -467,19 +469,17 @@ mext_check_arguments(struct inode *orig_inode, if (IS_IMMUTABLE(donor_inode) || IS_APPEND(donor_inode)) return -EPERM; - /* Ext4 move extent does not support swapfile */ + /* Ext4 move extent does not support swap files */ if (IS_SWAPFILE(orig_inode) || IS_SWAPFILE(donor_inode)) { - ext4_debug("ext4 move extent: The argument files should " - "not be swapfile [ino:orig %lu, donor %lu]\n", + ext4_debug("ext4 move extent: The argument files should not be swap files [ino:orig %lu, donor %lu]\n", orig_inode->i_ino, donor_inode->i_ino); - return -EBUSY; + return -ETXTBSY; } if (ext4_is_quota_file(orig_inode) && ext4_is_quota_file(donor_inode)) { - ext4_debug("ext4 move extent: The argument files should " - "not be quota files [ino:orig %lu, donor %lu]\n", + ext4_debug("ext4 move extent: The argument files should not be quota files [ino:orig %lu, donor %lu]\n", orig_inode->i_ino, donor_inode->i_ino); - return -EBUSY; + return -EOPNOTSUPP; } /* Ext4 move extent supports only extent based file */ @@ -626,13 +626,12 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, __u64 orig_blk, if (ret) goto out; ex = path[path->p_depth].p_ext; - next_blk = ext4_ext_next_allocated_block(path); cur_blk = le32_to_cpu(ex->ee_block); cur_len = ext4_ext_get_actual_len(ex); /* Check hole before the start pos */ if (cur_blk + cur_len - 1 < o_start) { + next_blk = ext4_ext_next_allocated_block(path); if (next_blk == EXT_MAX_BLOCKS) { - o_start = o_end; ret = -ENODATA; goto out; } @@ -659,14 +658,14 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, __u64 orig_blk, donor_page_index = d_start >> (PAGE_SHIFT - donor_inode->i_blkbits); offset_in_page = o_start % blocks_per_page; - if (cur_len > blocks_per_page- offset_in_page) + if (cur_len > blocks_per_page - offset_in_page) cur_len = blocks_per_page - offset_in_page; /* * Up semaphore to avoid following problems: * a. transaction deadlock among ext4_journal_start, * ->write_begin via pagefault, and jbd2_journal_commit - * b. racing with ->readpage, ->write_begin, and ext4_get_block - * in move_extent_per_page + * b. racing with ->read_folio, ->write_begin, and + * ext4_get_block in move_extent_per_page */ ext4_double_up_write_data_sem(orig_inode, donor_inode); /* Swap original branches with new branches */ @@ -690,8 +689,7 @@ out: ext4_discard_preallocations(donor_inode, 0); } - ext4_ext_drop_refs(path); - kfree(path); + ext4_free_ext_path(path); ext4_double_up_write_data_sem(orig_inode, donor_inode); unlock_two_nondirectories(orig_inode, donor_inode); diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 52c9bd154122..c08c0aba1883 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -54,6 +54,7 @@ static struct buffer_head *ext4_append(handle_t *handle, struct inode *inode, ext4_lblk_t *block) { + struct ext4_map_blocks map; struct buffer_head *bh; int err; @@ -63,21 +64,41 @@ static struct buffer_head *ext4_append(handle_t *handle, return ERR_PTR(-ENOSPC); *block = inode->i_size >> inode->i_sb->s_blocksize_bits; + map.m_lblk = *block; + map.m_len = 1; + + /* + * We're appending new directory block. Make sure the block is not + * allocated yet, otherwise we will end up corrupting the + * directory. + */ + err = ext4_map_blocks(NULL, inode, &map, 0); + if (err < 0) + return ERR_PTR(err); + if (err) { + EXT4_ERROR_INODE(inode, "Logical block already allocated"); + return ERR_PTR(-EFSCORRUPTED); + } bh = ext4_bread(handle, inode, *block, EXT4_GET_BLOCKS_CREATE); if (IS_ERR(bh)) return bh; inode->i_size += inode->i_sb->s_blocksize; EXT4_I(inode)->i_disksize = inode->i_size; + err = ext4_mark_inode_dirty(handle, inode); + if (err) + goto out; BUFFER_TRACE(bh, "get_write_access"); err = ext4_journal_get_write_access(handle, inode->i_sb, bh, EXT4_JTR_NONE); - if (err) { - brelse(bh); - ext4_std_error(inode->i_sb, err); - return ERR_PTR(err); - } + if (err) + goto out; return bh; + +out: + brelse(bh); + ext4_std_error(inode->i_sb, err); + return ERR_PTR(err); } static int ext4_dx_csum_verify(struct inode *inode, @@ -110,6 +131,13 @@ static struct buffer_head *__ext4_read_dirblock(struct inode *inode, struct ext4_dir_entry *dirent; int is_dx_block = 0; + if (block >= inode->i_size >> inode->i_blkbits) { + ext4_error_inode(inode, func, line, block, + "Attempting to read directory block (%u) that is past i_size (%llu)", + block, inode->i_size); + return ERR_PTR(-EFSCORRUPTED); + } + if (ext4_simulate_fail(inode->i_sb, EXT4_SIM_DIRBLOCK_EIO)) bh = ERR_PTR(-EIO); else @@ -277,9 +305,9 @@ static struct dx_frame *dx_probe(struct ext4_filename *fname, struct dx_hash_info *hinfo, struct dx_frame *frame); static void dx_release(struct dx_frame *frames); -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 int dx_make_map(struct inode *dir, struct buffer_head *bh, + struct dx_hash_info *hinfo, + struct dx_map_entry *map_tail); static void dx_sort_map(struct dx_map_entry *map, unsigned count); static struct ext4_dir_entry_2 *dx_move_dirents(struct inode *dir, char *from, char *to, struct dx_map_entry *offsets, @@ -777,12 +805,14 @@ static struct dx_frame * dx_probe(struct ext4_filename *fname, struct inode *dir, struct dx_hash_info *hinfo, struct dx_frame *frame_in) { - unsigned count, indirect; + unsigned count, indirect, level, i; struct dx_entry *at, *entries, *p, *q, *m; struct dx_root *root; struct dx_frame *frame = frame_in; struct dx_frame *ret_err = ERR_PTR(ERR_BAD_DX_DIR); u32 hash; + ext4_lblk_t block; + ext4_lblk_t blocks[EXT4_HTREE_LEVEL]; memset(frame_in, 0, EXT4_HTREE_LEVEL * sizeof(frame_in[0])); frame->bh = ext4_read_dirblock(dir, 0, INDEX); @@ -854,6 +884,8 @@ dx_probe(struct ext4_filename *fname, struct inode *dir, } dxtrace(printk("Look up %x", hash)); + level = 0; + blocks[0] = 0; while (1) { count = dx_get_count(entries); if (!count || count > dx_get_limit(entries)) { @@ -882,15 +914,27 @@ dx_probe(struct ext4_filename *fname, struct inode *dir, dx_get_block(at))); frame->entries = entries; frame->at = at; - if (!indirect--) + + block = dx_get_block(at); + for (i = 0; i <= level; i++) { + if (blocks[i] == block) { + ext4_warning_inode(dir, + "dx entry: tree cycle block %u points back to block %u", + blocks[level], block); + goto fail; + } + } + if (++level > indirect) return frame; + blocks[level] = block; frame++; - frame->bh = ext4_read_dirblock(dir, dx_get_block(at), INDEX); + frame->bh = ext4_read_dirblock(dir, block, INDEX); if (IS_ERR(frame->bh)) { ret_err = (struct dx_frame *) frame->bh; frame->bh = NULL; goto fail; } + entries = ((struct dx_node *) frame->bh->b_data)->entries; if (dx_get_limit(entries) != dx_node_limit(dir)) { @@ -1249,15 +1293,23 @@ static inline int search_dirblock(struct buffer_head *bh, * Create map of hash values, offsets, and sizes, stored at end of block. * Returns number of entries mapped. */ -static int dx_make_map(struct inode *dir, struct ext4_dir_entry_2 *de, - unsigned blocksize, struct dx_hash_info *hinfo, +static int dx_make_map(struct inode *dir, struct buffer_head *bh, + struct dx_hash_info *hinfo, struct dx_map_entry *map_tail) { int count = 0; - char *base = (char *) de; + struct ext4_dir_entry_2 *de = (struct ext4_dir_entry_2 *)bh->b_data; + unsigned int buflen = bh->b_size; + char *base = bh->b_data; struct dx_hash_info h = *hinfo; - while ((char *) de < base + blocksize) { + if (ext4_has_metadata_csum(dir->i_sb)) + buflen -= sizeof(struct ext4_dir_entry_tail); + + while ((char *) de < base + buflen) { + if (ext4_check_dir_entry(dir, NULL, de, bh, base, buflen, + ((char *)de) - base)) + return -EFSCORRUPTED; if (de->name_len && de->inode) { if (ext4_hash_in_dirent(dir)) h.hash = EXT4_DIRENT_HASH(de); @@ -1270,8 +1322,7 @@ static int dx_make_map(struct inode *dir, struct ext4_dir_entry_2 *de, count++; cond_resched(); } - /* XXX: do we need to check rec_len == 0 case? -Chris */ - de = ext4_next_entry(de, blocksize); + de = ext4_next_entry(de, dir->i_sb->s_blocksize); } return count; } @@ -1317,7 +1368,7 @@ static void dx_insert_block(struct dx_frame *frame, u32 hash, ext4_lblk_t block) dx_set_count(entries, count + 1); } -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) /* * Test whether a case-insensitive directory entry matches the filename * being searched for. If quick is set, assume the name being looked up @@ -1428,7 +1479,7 @@ static bool ext4_match(struct inode *parent, f.crypto_buf = fname->crypto_buf; #endif -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) if (parent->i_sb->s_encoding && IS_CASEFOLDED(parent) && (!IS_ENCRYPTED(parent) || fscrypt_has_encryption_key(parent))) { if (fname->cf_name.name) { @@ -1466,10 +1517,10 @@ int ext4_search_dir(struct buffer_head *bh, char *search_buf, int buf_size, de = (struct ext4_dir_entry_2 *)search_buf; dlimit = search_buf + buf_size; - while ((char *) de < dlimit) { + while ((char *) de < dlimit - EXT4_BASE_DIR_LEN) { /* this code is executed quadratically often */ /* do minimal checking `by hand' */ - if ((char *) de + de->name_len <= dlimit && + if (de->name + de->name_len <= dlimit && ext4_match(dir, fname, de)) { /* found a match - just to be sure, do * a full check */ @@ -1800,7 +1851,7 @@ static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, unsi } } -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) if (!inode && IS_CASEFOLDED(dir)) { /* Eventually we want to call d_add_ci(dentry, NULL) * for negative dentries in the encoding case as @@ -1906,7 +1957,8 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir, struct dx_hash_info *hinfo) { unsigned blocksize = dir->i_sb->s_blocksize; - unsigned count, continued; + unsigned continued; + int count; struct buffer_head *bh2; ext4_lblk_t newblock; u32 hash2; @@ -1943,8 +1995,11 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir, /* create map in the end of data2 block */ map = (struct dx_map_entry *) (data2 + blocksize); - count = dx_make_map(dir, (struct ext4_dir_entry_2 *) data1, - blocksize, hinfo, map); + count = dx_make_map(dir, *bh, hinfo, map); + if (count < 0) { + err = count; + goto journal_error; + } map -= count; dx_sort_map(map, count); /* Ensure that neither split block is over half full */ @@ -2031,7 +2086,7 @@ int ext4_find_dest_de(struct inode *dir, struct inode *inode, unsigned int offset = 0; char *top; - de = (struct ext4_dir_entry_2 *)buf; + de = buf; top = buf + buf_size - reclen; while ((char *) de <= top) { if (ext4_check_dir_entry(dir, NULL, de, bh, @@ -2204,8 +2259,16 @@ static int make_indexed_dir(handle_t *handle, struct ext4_filename *fname, 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) + while ((char *)(de2 = ext4_next_entry(de, blocksize)) < top) { + if (ext4_check_dir_entry(dir, NULL, de, bh2, data2, len, + (data2 + (blocksize - csum_size) - + (char *) de))) { + brelse(bh2); + brelse(bh); + return -EFSCORRUPTED; + } de = de2; + } de->rec_len = ext4_rec_len_to_disk(data2 + (blocksize - csum_size) - (char *) de, blocksize); @@ -2308,7 +2371,7 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry, if (fscrypt_is_nokey_name(dentry)) return -ENOKEY; -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) if (sb_has_strict_encoding(sb) && IS_CASEFOLDED(dir) && sb->s_encoding && utf8_validate(sb->s_encoding, &dentry->d_name)) return -EINVAL; @@ -2587,7 +2650,7 @@ int ext4_generic_delete_entry(struct inode *dir, i = 0; pde = NULL; - de = (struct ext4_dir_entry_2 *)entry_buf; + de = entry_buf; while (i < buf_size - csum_size) { if (ext4_check_dir_entry(dir, NULL, de, bh, entry_buf, buf_size, i)) @@ -2799,7 +2862,7 @@ retry: } static int ext4_tmpfile(struct user_namespace *mnt_userns, struct inode *dir, - struct dentry *dentry, umode_t mode) + struct file *file, umode_t mode) { handle_t *handle; struct inode *inode; @@ -2821,7 +2884,7 @@ retry: inode->i_op = &ext4_file_inode_operations; inode->i_fop = &ext4_file_operations; ext4_set_aops(inode); - d_tmpfile(dentry, inode); + d_tmpfile(file, inode); err = ext4_orphan_add(handle, inode); if (err) goto err_unlock_inode; @@ -2832,7 +2895,7 @@ retry: ext4_journal_stop(handle); if (err == -ENOSPC && ext4_should_retry_alloc(dir->i_sb, &retries)) goto retry; - return err; + return finish_open_simple(file, err); err_unlock_inode: ext4_journal_stop(handle); unlock_new_inode(inode); @@ -2997,14 +3060,14 @@ bool ext4_empty_dir(struct inode *inode) if (inode->i_size < ext4_dir_rec_len(1, NULL) + ext4_dir_rec_len(2, NULL)) { EXT4_ERROR_INODE(inode, "invalid size"); - return true; + return false; } /* The first directory block must not be a hole, * so treat it as DIRENT_HTREE */ bh = ext4_read_dirblock(inode, 0, DIRENT_HTREE); if (IS_ERR(bh)) - return true; + return false; de = (struct ext4_dir_entry_2 *) bh->b_data; if (ext4_check_dir_entry(inode, NULL, de, bh, bh->b_data, bh->b_size, @@ -3012,7 +3075,7 @@ bool ext4_empty_dir(struct inode *inode) le32_to_cpu(de->inode) != inode->i_ino || strcmp(".", de->name)) { ext4_warning_inode(inode, "directory missing '.'"); brelse(bh); - return true; + return false; } offset = ext4_rec_len_from_disk(de->rec_len, sb->s_blocksize); de = ext4_next_entry(de, sb->s_blocksize); @@ -3021,7 +3084,7 @@ bool ext4_empty_dir(struct inode *inode) le32_to_cpu(de->inode) == 0 || strcmp("..", de->name)) { ext4_warning_inode(inode, "directory missing '..'"); brelse(bh); - return true; + return false; } offset += ext4_rec_len_from_disk(de->rec_len, sb->s_blocksize); while (offset < inode->i_size) { @@ -3035,16 +3098,13 @@ bool ext4_empty_dir(struct inode *inode) continue; } if (IS_ERR(bh)) - return true; + return false; } de = (struct ext4_dir_entry_2 *) (bh->b_data + (offset & (sb->s_blocksize - 1))); if (ext4_check_dir_entry(inode, NULL, de, bh, - bh->b_data, bh->b_size, offset)) { - offset = (offset | (sb->s_blocksize - 1)) + 1; - continue; - } - if (le32_to_cpu(de->inode)) { + bh->b_data, bh->b_size, offset) || + le32_to_cpu(de->inode)) { brelse(bh); return false; } @@ -3126,7 +3186,7 @@ static int ext4_rmdir(struct inode *dir, struct dentry *dentry) ext4_fc_track_unlink(handle, dentry); retval = ext4_mark_inode_dirty(handle, dir); -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) /* VFS negative dentries are incompatible with Encoding and * Case-insensitiveness. Eventually we'll want avoid * invalidating the dentries here, alongside with returning the @@ -3231,7 +3291,7 @@ static int ext4_unlink(struct inode *dir, struct dentry *dentry) retval = __ext4_unlink(handle, dir, &dentry->d_name, d_inode(dentry)); if (!retval) ext4_fc_track_unlink(handle, dentry); -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) /* VFS negative dentries are incompatible with Encoding and * Case-insensitiveness. Eventually we'll want avoid * invalidating the dentries here, alongside with returning the @@ -3249,6 +3309,32 @@ out_trace: return retval; } +static int ext4_init_symlink_block(handle_t *handle, struct inode *inode, + struct fscrypt_str *disk_link) +{ + struct buffer_head *bh; + char *kaddr; + int err = 0; + + bh = ext4_bread(handle, inode, 0, EXT4_GET_BLOCKS_CREATE); + if (IS_ERR(bh)) + return PTR_ERR(bh); + + BUFFER_TRACE(bh, "get_write_access"); + err = ext4_journal_get_write_access(handle, inode->i_sb, bh, EXT4_JTR_NONE); + if (err) + goto out; + + kaddr = (char *)bh->b_data; + memcpy(kaddr, disk_link->name, disk_link->len); + inode->i_size = disk_link->len - 1; + EXT4_I(inode)->i_disksize = inode->i_size; + err = ext4_handle_dirty_metadata(handle, inode, bh); +out: + brelse(bh); + return err; +} + static int ext4_symlink(struct user_namespace *mnt_userns, struct inode *dir, struct dentry *dentry, const char *symname) { @@ -3257,6 +3343,7 @@ static int ext4_symlink(struct user_namespace *mnt_userns, struct inode *dir, int err, len = strlen(symname); int credits; struct fscrypt_str disk_link; + int retries = 0; if (unlikely(ext4_forced_shutdown(EXT4_SB(dir->i_sb)))) return -EIO; @@ -3270,26 +3357,15 @@ static int ext4_symlink(struct user_namespace *mnt_userns, struct inode *dir, if (err) return err; - if ((disk_link.len > EXT4_N_BLOCKS * 4)) { - /* - * For non-fast symlinks, we just allocate inode and put it on - * orphan list in the first transaction => we need bitmap, - * group descriptor, sb, inode block, quota blocks, and - * possibly selinux xattr blocks. - */ - credits = 4 + EXT4_MAXQUOTAS_INIT_BLOCKS(dir->i_sb) + - EXT4_XATTR_TRANS_BLOCKS; - } else { - /* - * Fast symlink. We have to add entry to directory - * (EXT4_DATA_TRANS_BLOCKS + EXT4_INDEX_EXTRA_TRANS_BLOCKS), - * allocate new inode (bitmap, group descriptor, inode block, - * quota blocks, sb is already counted in previous macros). - */ - credits = EXT4_DATA_TRANS_BLOCKS(dir->i_sb) + - EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3; - } - + /* + * EXT4_INDEX_EXTRA_TRANS_BLOCKS for addition of entry into the + * directory. +3 for inode, inode bitmap, group descriptor allocation. + * EXT4_DATA_TRANS_BLOCKS for the data block allocation and + * modification. + */ + credits = EXT4_DATA_TRANS_BLOCKS(dir->i_sb) + + EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3; +retry: inode = ext4_new_inode_start_handle(mnt_userns, dir, S_IFLNK|S_IRWXUGO, &dentry->d_name, 0, NULL, EXT4_HT_DIR, credits); @@ -3297,7 +3373,8 @@ static int ext4_symlink(struct user_namespace *mnt_userns, struct inode *dir, if (IS_ERR(inode)) { if (handle) ext4_journal_stop(handle); - return PTR_ERR(inode); + err = PTR_ERR(inode); + goto out_retry; } if (IS_ENCRYPTED(inode)) { @@ -3305,75 +3382,44 @@ static int ext4_symlink(struct user_namespace *mnt_userns, struct inode *dir, if (err) goto err_drop_inode; inode->i_op = &ext4_encrypted_symlink_inode_operations; + } else { + if ((disk_link.len > EXT4_N_BLOCKS * 4)) { + inode->i_op = &ext4_symlink_inode_operations; + } else { + inode->i_op = &ext4_fast_symlink_inode_operations; + inode->i_link = (char *)&EXT4_I(inode)->i_data; + } } if ((disk_link.len > EXT4_N_BLOCKS * 4)) { - if (!IS_ENCRYPTED(inode)) - inode->i_op = &ext4_symlink_inode_operations; - inode_nohighmem(inode); - ext4_set_aops(inode); - /* - * We cannot call page_symlink() with transaction started - * because it calls into ext4_write_begin() which can wait - * 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. - */ - drop_nlink(inode); - err = ext4_orphan_add(handle, inode); - if (handle) - ext4_journal_stop(handle); - handle = NULL; - if (err) - goto err_drop_inode; - err = __page_symlink(inode, disk_link.name, disk_link.len, 1); - if (err) - goto err_drop_inode; - /* - * Now inode is being linked into dir (EXT4_DATA_TRANS_BLOCKS - * + EXT4_INDEX_EXTRA_TRANS_BLOCKS), inode is also modified - */ - handle = ext4_journal_start(dir, EXT4_HT_DIR, - EXT4_DATA_TRANS_BLOCKS(dir->i_sb) + - EXT4_INDEX_EXTRA_TRANS_BLOCKS + 1); - if (IS_ERR(handle)) { - err = PTR_ERR(handle); - handle = NULL; - goto err_drop_inode; - } - set_nlink(inode, 1); - err = ext4_orphan_del(handle, inode); + /* alloc symlink block and fill it */ + err = ext4_init_symlink_block(handle, inode, &disk_link); if (err) goto err_drop_inode; } else { /* clear the extent format for fast symlink */ ext4_clear_inode_flag(inode, EXT4_INODE_EXTENTS); - if (!IS_ENCRYPTED(inode)) { - inode->i_op = &ext4_fast_symlink_inode_operations; - inode->i_link = (char *)&EXT4_I(inode)->i_data; - } memcpy((char *)&EXT4_I(inode)->i_data, disk_link.name, disk_link.len); inode->i_size = disk_link.len - 1; + EXT4_I(inode)->i_disksize = inode->i_size; } - EXT4_I(inode)->i_disksize = inode->i_size; err = ext4_add_nondir(handle, dentry, &inode); if (handle) ext4_journal_stop(handle); - if (inode) - iput(inode); - goto out_free_encrypted_link; + iput(inode); + goto out_retry; err_drop_inode: - if (handle) - ext4_journal_stop(handle); clear_nlink(inode); + ext4_orphan_add(handle, inode); unlock_new_inode(inode); + if (handle) + ext4_journal_stop(handle); iput(inode); -out_free_encrypted_link: +out_retry: + if (err == -ENOSPC && ext4_should_retry_alloc(dir->i_sb, &retries)) + goto retry; if (disk_link.name != (unsigned char *)symname) kfree(disk_link.name); return err; @@ -3455,6 +3501,9 @@ static struct buffer_head *ext4_get_first_dir_block(handle_t *handle, struct buffer_head *bh; if (!ext4_has_inline_data(inode)) { + struct ext4_dir_entry_2 *de; + unsigned int offset; + /* The first directory block must not be a hole, so * treat it as DIRENT_HTREE */ @@ -3463,9 +3512,30 @@ static struct buffer_head *ext4_get_first_dir_block(handle_t *handle, *retval = PTR_ERR(bh); return NULL; } - *parent_de = ext4_next_entry( - (struct ext4_dir_entry_2 *)bh->b_data, - inode->i_sb->s_blocksize); + + de = (struct ext4_dir_entry_2 *) bh->b_data; + if (ext4_check_dir_entry(inode, NULL, de, bh, bh->b_data, + bh->b_size, 0) || + le32_to_cpu(de->inode) != inode->i_ino || + strcmp(".", de->name)) { + EXT4_ERROR_INODE(inode, "directory missing '.'"); + brelse(bh); + *retval = -EFSCORRUPTED; + return NULL; + } + offset = ext4_rec_len_from_disk(de->rec_len, + inode->i_sb->s_blocksize); + de = ext4_next_entry(de, inode->i_sb->s_blocksize); + if (ext4_check_dir_entry(inode, NULL, de, bh, bh->b_data, + bh->b_size, offset) || + le32_to_cpu(de->inode) == 0 || strcmp("..", de->name)) { + EXT4_ERROR_INODE(inode, "directory missing '..'"); + brelse(bh); + *retval = -EFSCORRUPTED; + return NULL; + } + *parent_de = de; + return bh; } @@ -3889,14 +3959,21 @@ static int ext4_rename(struct user_namespace *mnt_userns, struct inode *old_dir, * dirents in directories. */ ext4_fc_mark_ineligible(old.inode->i_sb, - EXT4_FC_REASON_RENAME_DIR); + EXT4_FC_REASON_RENAME_DIR, handle); } else { + struct super_block *sb = old.inode->i_sb; + if (new.inode) ext4_fc_track_unlink(handle, new.dentry); - __ext4_fc_track_link(handle, old.inode, new.dentry); - __ext4_fc_track_unlink(handle, old.inode, old.dentry); - if (whiteout) - __ext4_fc_track_create(handle, whiteout, old.dentry); + if (test_opt2(sb, JOURNAL_FAST_COMMIT) && + !(EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY) && + !(ext4_test_mount_flag(sb, EXT4_MF_FC_INELIGIBLE))) { + __ext4_fc_track_link(handle, old.inode, new.dentry); + __ext4_fc_track_unlink(handle, old.inode, old.dentry); + if (whiteout) + __ext4_fc_track_create(handle, whiteout, + old.dentry); + } } if (new.inode) { @@ -4049,7 +4126,7 @@ static int ext4_cross_rename(struct inode *old_dir, struct dentry *old_dentry, if (unlikely(retval)) goto end_rename; ext4_fc_mark_ineligible(new.inode->i_sb, - EXT4_FC_REASON_CROSS_RENAME); + EXT4_FC_REASON_CROSS_RENAME, handle); if (old.dir_bh) { retval = ext4_rename_dir_finish(handle, &old, new.dir->i_ino); if (retval) diff --git a/fs/ext4/orphan.c b/fs/ext4/orphan.c index 53adc8f570a3..69a9cf9137a6 100644 --- a/fs/ext4/orphan.c +++ b/fs/ext4/orphan.c @@ -93,7 +93,7 @@ static int ext4_orphan_file_add(handle_t *handle, struct inode *inode) * At filesystem recovery time, we walk this list deleting unlinked * inodes and truncating linked inodes in ext4_orphan_cleanup(). * - * Orphan list manipulation functions must be called under i_mutex unless + * Orphan list manipulation functions must be called under i_rwsem unless * we are just creating the inode or deleting it. */ int ext4_orphan_add(handle_t *handle, struct inode *inode) @@ -119,7 +119,7 @@ int ext4_orphan_add(handle_t *handle, struct inode *inode) /* * Orphan handling is only valid for files with data blocks * being truncated, or files being unlinked. Note that we either - * hold i_mutex, or the inode can not be referenced from outside, + * hold i_rwsem, or the inode can not be referenced from outside, * so i_nlink should not be bumped due to race */ ASSERT((S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || @@ -181,8 +181,8 @@ int ext4_orphan_add(handle_t *handle, struct inode *inode) } else brelse(iloc.bh); - jbd_debug(4, "superblock will point to %lu\n", inode->i_ino); - jbd_debug(4, "orphan inode %lu will point to %d\n", + ext4_debug("superblock will point to %lu\n", inode->i_ino); + ext4_debug("orphan inode %lu will point to %d\n", inode->i_ino, NEXT_ORPHAN(inode)); out: ext4_std_error(sb, err); @@ -251,7 +251,7 @@ int ext4_orphan_del(handle_t *handle, struct inode *inode) } mutex_lock(&sbi->s_orphan_lock); - jbd_debug(4, "remove inode %lu from orphan list\n", inode->i_ino); + ext4_debug("remove inode %lu from orphan list\n", inode->i_ino); prev = ei->i_orphan.prev; list_del_init(&ei->i_orphan); @@ -267,7 +267,7 @@ int ext4_orphan_del(handle_t *handle, struct inode *inode) ino_next = NEXT_ORPHAN(inode); if (prev == &sbi->s_orphan) { - jbd_debug(4, "superblock will point to %u\n", ino_next); + ext4_debug("superblock will point to %u\n", ino_next); BUFFER_TRACE(sbi->s_sbh, "get_write_access"); err = ext4_journal_get_write_access(handle, inode->i_sb, sbi->s_sbh, EXT4_JTR_NONE); @@ -286,7 +286,7 @@ int ext4_orphan_del(handle_t *handle, struct inode *inode) struct inode *i_prev = &list_entry(prev, struct ext4_inode_info, i_orphan)->vfs_inode; - jbd_debug(4, "orphan inode %lu will point to %u\n", + ext4_debug("orphan inode %lu will point to %u\n", i_prev->i_ino, ino_next); err = ext4_reserve_inode_write(handle, i_prev, &iloc2); if (err) { @@ -332,8 +332,8 @@ static void ext4_process_orphan(struct inode *inode, ext4_msg(sb, KERN_DEBUG, "%s: truncating inode %lu to %lld bytes", __func__, inode->i_ino, inode->i_size); - jbd_debug(2, "truncating inode %lu to %lld bytes\n", - inode->i_ino, inode->i_size); + ext4_debug("truncating inode %lu to %lld bytes\n", + inode->i_ino, inode->i_size); inode_lock(inode); truncate_inode_pages(inode->i_mapping, inode->i_size); ret = ext4_truncate(inode); @@ -353,8 +353,8 @@ static void ext4_process_orphan(struct inode *inode, ext4_msg(sb, KERN_DEBUG, "%s: deleting unreferenced inode %lu", __func__, inode->i_ino); - jbd_debug(2, "deleting unreferenced inode %lu\n", - inode->i_ino); + ext4_debug("deleting unreferenced inode %lu\n", + inode->i_ino); (*nr_orphans)++; } iput(inode); /* The delete magic happens here! */ @@ -391,7 +391,7 @@ void ext4_orphan_cleanup(struct super_block *sb, struct ext4_super_block *es) int inodes_per_ob = ext4_inodes_per_orphan_block(sb); if (!es->s_last_orphan && !oi->of_blocks) { - jbd_debug(4, "no orphan inodes to clean up\n"); + ext4_debug("no orphan inodes to clean up\n"); return; } @@ -415,7 +415,7 @@ void ext4_orphan_cleanup(struct super_block *sb, struct ext4_super_block *es) "clearing orphan list.\n"); es->s_last_orphan = 0; } - jbd_debug(1, "Skipping orphan recovery on fs with errors.\n"); + ext4_debug("Skipping orphan recovery on fs with errors.\n"); return; } @@ -459,7 +459,7 @@ void ext4_orphan_cleanup(struct super_block *sb, struct ext4_super_block *es) * so, skip the rest. */ if (EXT4_SB(sb)->s_mount_state & EXT4_ERROR_FS) { - jbd_debug(1, "Skipping orphan recovery on fs with errors.\n"); + ext4_debug("Skipping orphan recovery on fs with errors.\n"); es->s_last_orphan = 0; break; } diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c index 9cb261714991..97fa7b4c645f 100644 --- a/fs/ext4/page-io.c +++ b/fs/ext4/page-io.c @@ -24,7 +24,7 @@ #include <linux/kernel.h> #include <linux/slab.h> #include <linux/mm.h> -#include <linux/backing-dev.h> +#include <linux/sched/mm.h> #include "ext4_jbd2.h" #include "xattr.h" @@ -134,8 +134,10 @@ static void ext4_finish_bio(struct bio *bio) continue; } clear_buffer_async_write(bh); - if (bio->bi_status) + if (bio->bi_status) { + set_buffer_write_io_error(bh); buffer_io_error(bh); + } } while ((bh = bh->b_this_page) != head); spin_unlock_irqrestore(&head->b_uptodate_lock, flags); if (!under_io) { @@ -323,10 +325,9 @@ static void ext4_end_bio(struct bio *bio) { ext4_io_end_t *io_end = bio->bi_private; sector_t bi_sector = bio->bi_iter.bi_sector; - char b[BDEVNAME_SIZE]; - if (WARN_ONCE(!io_end, "io_end is NULL: %s: sector %Lu len %u err %d\n", - bio_devname(bio, b), + if (WARN_ONCE(!io_end, "io_end is NULL: %pg: sector %Lu len %u err %d\n", + bio->bi_bdev, (long long) bio->bi_iter.bi_sector, (unsigned) bio_sectors(bio), bio->bi_status)) { @@ -372,10 +373,8 @@ void ext4_io_submit(struct ext4_io_submit *io) struct bio *bio = io->io_bio; if (bio) { - int io_op_flags = io->io_wbc->sync_mode == WB_SYNC_ALL ? - REQ_SYNC : 0; - io->io_bio->bi_write_hint = io->io_end->inode->i_write_hint; - bio_set_op_attrs(io->io_bio, REQ_OP_WRITE, io_op_flags); + if (io->io_wbc->sync_mode == WB_SYNC_ALL) + io->io_bio->bi_opf |= REQ_SYNC; submit_bio(io->io_bio); } io->io_bio = NULL; @@ -398,10 +397,9 @@ static void io_submit_init_bio(struct ext4_io_submit *io, * bio_alloc will _always_ be able to allocate a bio if * __GFP_DIRECT_RECLAIM is set, see comments for bio_alloc_bioset(). */ - bio = bio_alloc(GFP_NOIO, BIO_MAX_VECS); + bio = bio_alloc(bh->b_bdev, BIO_MAX_VECS, REQ_OP_WRITE, GFP_NOIO); fscrypt_set_bio_crypt_ctx_bh(bio, bh, GFP_NOIO); bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9); - bio_set_dev(bio, bh->b_bdev); bio->bi_end_io = ext4_end_bio; bio->bi_private = ext4_get_io_end(io->io_end); io->io_bio = bio; @@ -421,10 +419,8 @@ static void io_submit_add_bh(struct ext4_io_submit *io, submit_and_retry: ext4_io_submit(io); } - if (io->io_bio == NULL) { + if (io->io_bio == NULL) io_submit_init_bio(io, bh); - io->io_bio->bi_write_hint = inode->i_write_hint; - } ret = bio_add_page(io->io_bio, page, bh->b_size, bh_offset(bh)); if (ret != bh->b_size) goto submit_and_retry; @@ -469,7 +465,7 @@ int ext4_bio_write_page(struct ext4_io_submit *io, /* * In the first loop we prepare and mark buffers to submit. We have to * mark all buffers in the page before submitting so that - * end_page_writeback() cannot be called from ext4_bio_end_io() when IO + * end_page_writeback() cannot be called from ext4_end_bio() when IO * on the first buffer finishes and we are still working on submitting * the second buffer. */ @@ -523,12 +519,13 @@ int ext4_bio_write_page(struct ext4_io_submit *io, ret = PTR_ERR(bounce_page); if (ret == -ENOMEM && (io->io_bio || wbc->sync_mode == WB_SYNC_ALL)) { - gfp_flags = GFP_NOFS; + gfp_t new_gfp_flags = GFP_NOFS; if (io->io_bio) ext4_io_submit(io); else - gfp_flags |= __GFP_NOFAIL; - congestion_wait(BLK_RW_ASYNC, HZ/50); + new_gfp_flags |= __GFP_NOFAIL; + memalloc_retry_wait(gfp_flags); + gfp_flags = new_gfp_flags; goto retry_encrypt; } diff --git a/fs/ext4/readpage.c b/fs/ext4/readpage.c index 3db923403505..3d21eae267fc 100644 --- a/fs/ext4/readpage.c +++ b/fs/ext4/readpage.c @@ -43,7 +43,6 @@ #include <linux/writeback.h> #include <linux/backing-dev.h> #include <linux/pagevec.h> -#include <linux/cleancache.h> #include "ext4.h" @@ -76,7 +75,7 @@ static void __read_end_io(struct bio *bio) bio_for_each_segment_all(bv, bio, iter_all) { page = bv->bv_page; - /* PG_error was set if any post_read step failed */ + /* PG_error was set if verity failed. */ if (bio->bi_status || PageError(page)) { ClearPageUptodate(page); /* will re-read again later */ @@ -97,10 +96,12 @@ static void decrypt_work(struct work_struct *work) { struct bio_post_read_ctx *ctx = container_of(work, struct bio_post_read_ctx, work); + struct bio *bio = ctx->bio; - fscrypt_decrypt_bio(ctx->bio); - - bio_post_read_processing(ctx); + if (fscrypt_decrypt_bio(bio)) + bio_post_read_processing(ctx); + else + __read_end_io(bio); } static void verity_work(struct work_struct *work) @@ -110,7 +111,7 @@ static void verity_work(struct work_struct *work) struct bio *bio = ctx->bio; /* - * fsverity_verify_bio() may call readpages() again, and although verity + * fsverity_verify_bio() may call readahead() again, and although verity * will be disabled for that, decryption may still be needed, causing * another bio_post_read_ctx to be allocated. So to guarantee that * mempool_alloc() never deadlocks we must free the current ctx first. @@ -164,7 +165,7 @@ static bool bio_post_read_required(struct bio *bio) * * The mpage code never puts partial pages into a BIO (except for end-of-file). * If a page does not map to a contiguous run of blocks then it simply falls - * back to block_read_full_page(). + * back to block_read_full_folio(). * * Why is this? If a page's completion depends on a number of different BIOs * which can complete in any order (or at the same time) then determining the @@ -350,11 +351,6 @@ int ext4_mpage_readpages(struct inode *inode, } else if (fully_mapped) { SetPageMappedToDisk(page); } - if (fully_mapped && blocks_per_page == 1 && - !PageUptodate(page) && cleancache_get_page(page) == 0) { - SetPageUptodate(page); - goto confused; - } /* * This page will go to BIO. Do we need to send this @@ -371,15 +367,15 @@ int ext4_mpage_readpages(struct inode *inode, * bio_alloc will _always_ be able to allocate a bio if * __GFP_DIRECT_RECLAIM is set, see bio_alloc_bioset(). */ - bio = bio_alloc(GFP_KERNEL, bio_max_segs(nr_pages)); + bio = bio_alloc(bdev, bio_max_segs(nr_pages), + REQ_OP_READ, GFP_KERNEL); fscrypt_set_bio_crypt_ctx(bio, inode, next_block, GFP_KERNEL); ext4_set_bio_post_read_ctx(bio, inode, page->index); - bio_set_dev(bio, bdev); bio->bi_iter.bi_sector = blocks[0] << (blkbits - 9); bio->bi_end_io = mpage_end_io; - bio_set_op_attrs(bio, REQ_OP_READ, - rac ? REQ_RAHEAD : 0); + if (rac) + bio->bi_opf |= REQ_RAHEAD; } length = first_hole << blkbits; @@ -400,7 +396,7 @@ int ext4_mpage_readpages(struct inode *inode, bio = NULL; } if (!PageUptodate(page)) - block_read_full_page(page, ext4_get_block); + block_read_full_folio(page_folio(page), ext4_get_block); else unlock_page(page); next_page: diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index b63cb88ccdae..46b87ffeb304 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -14,6 +14,7 @@ #include <linux/errno.h> #include <linux/slab.h> +#include <linux/jiffies.h> #include "ext4_jbd2.h" @@ -53,6 +54,16 @@ int ext4_resize_begin(struct super_block *sb) return -EPERM; /* + * If the reserved GDT blocks is non-zero, the resize_inode feature + * should always be set. + */ + if (EXT4_SB(sb)->s_es->s_reserved_gdt_blocks && + !ext4_has_feature_resize_inode(sb)) { + ext4_error(sb, "resize_inode disabled but reserved GDT blocks non-zero"); + return -EFSCORRUPTED; + } + + /* * If we are not using the primary superblock/GDT copy don't resize, * because the user tools have no way of handling this. Probably a * bad time to do it anyways. @@ -86,10 +97,13 @@ int ext4_resize_begin(struct super_block *sb) return ret; } -void ext4_resize_end(struct super_block *sb) +int ext4_resize_end(struct super_block *sb, bool update_backups) { clear_bit_unlock(EXT4_FLAGS_RESIZING, &EXT4_SB(sb)->s_ext4_flags); smp_mb__after_atomic(); + if (update_backups) + return ext4_update_overhead(sb, true); + return 0; } static ext4_group_t ext4_meta_bg_first_group(struct super_block *sb, @@ -483,7 +497,7 @@ static int set_flexbg_block_bitmap(struct super_block *sb, handle_t *handle, } ext4_debug("mark block bitmap %#04llx (+%llu/%u)\n", first_cluster, first_cluster - start, count2); - ext4_set_bits(bh->b_data, first_cluster - start, count2); + mb_set_bits(bh->b_data, first_cluster - start, count2); err = ext4_handle_dirty_metadata(handle, NULL, bh); brelse(bh); @@ -632,7 +646,7 @@ handle_bb: if (overhead != 0) { ext4_debug("mark backup superblock %#04llx (+0)\n", start); - ext4_set_bits(bh->b_data, 0, + mb_set_bits(bh->b_data, 0, EXT4_NUM_B2C(sbi, overhead)); } ext4_mark_bitmap_end(EXT4_B2C(sbi, group_data[i].blocks_count), @@ -717,12 +731,23 @@ out: * sequence of powers of 3, 5, and 7: 1, 3, 5, 7, 9, 25, 27, 49, 81, ... * For a non-sparse filesystem it will be every group: 1, 2, 3, 4, ... */ -static unsigned ext4_list_backups(struct super_block *sb, unsigned *three, - unsigned *five, unsigned *seven) +unsigned int ext4_list_backups(struct super_block *sb, unsigned int *three, + unsigned int *five, unsigned int *seven) { - unsigned *min = three; + struct ext4_super_block *es = EXT4_SB(sb)->s_es; + unsigned int *min = three; int mult = 3; - unsigned ret; + unsigned int ret; + + if (ext4_has_feature_sparse_super2(sb)) { + do { + if (*min > 2) + return UINT_MAX; + ret = le32_to_cpu(es->s_backup_bgs[*min - 1]); + *min += 1; + } while (!ret); + return ret; + } if (!ext4_has_feature_sparse_super(sb)) { ret = *min; @@ -1133,6 +1158,7 @@ static void update_backups(struct super_block *sb, sector_t blk_off, char *data, while (group < sbi->s_groups_count) { struct buffer_head *bh; ext4_fsblk_t backup_block; + struct ext4_super_block *es; /* Out of journal space, and can't get more - abort - so sad */ err = ext4_resize_ensure_credits_batch(handle, 1); @@ -1161,6 +1187,10 @@ static void update_backups(struct super_block *sb, sector_t blk_off, char *data, memcpy(bh->b_data, data, size); if (rest) memset(bh->b_data + size, 0, rest); + es = (struct ext4_super_block *) bh->b_data; + es->s_block_group_nr = cpu_to_le16(group); + if (ext4_has_metadata_csum(sb)) + es->s_checksum = ext4_superblock_csum(sb, es); set_buffer_uptodate(bh); unlock_buffer(bh); err = ext4_handle_dirty_metadata(handle, NULL, bh); @@ -1358,6 +1388,17 @@ static int ext4_setup_new_descs(handle_t *handle, struct super_block *sb, return err; } +static void ext4_add_overhead(struct super_block *sb, + const ext4_fsblk_t overhead) +{ + struct ext4_sb_info *sbi = EXT4_SB(sb); + struct ext4_super_block *es = sbi->s_es; + + sbi->s_overhead += overhead; + es->s_overhead_clusters = cpu_to_le32(sbi->s_overhead); + smp_wmb(); +} + /* * ext4_update_super() updates the super block so that the newly added * groups can be seen by the filesystem. @@ -1459,9 +1500,18 @@ static void ext4_update_super(struct super_block *sb, } /* - * Update the fs overhead information + * Update the fs overhead information. + * + * For bigalloc, if the superblock already has a properly calculated + * overhead, update it with a value based on numbers already computed + * above for the newly allocated capacity. */ - ext4_calculate_overhead(sb); + if (ext4_has_feature_bigalloc(sb) && (sbi->s_overhead != 0)) + ext4_add_overhead(sb, + EXT4_NUM_B2C(sbi, blocks_count - free_blocks)); + else + ext4_calculate_overhead(sb); + es->s_overhead_clusters = cpu_to_le32(sbi->s_overhead); if (test_opt(sb, DEBUG)) printk(KERN_DEBUG "EXT4-fs: added group %u:" @@ -1966,6 +2016,16 @@ int ext4_resize_fs(struct super_block *sb, ext4_fsblk_t n_blocks_count) } brelse(bh); + /* + * For bigalloc, trim the requested size to the nearest cluster + * boundary to avoid creating an unusable filesystem. We do this + * silently, instead of returning an error, to avoid breaking + * callers that blindly resize the filesystem to the full size of + * the underlying block device. + */ + if (ext4_has_feature_bigalloc(sb)) + n_blocks_count &= ~((1 << EXT4_CLUSTER_BITS(sb)) - 1); + retry: o_blocks_count = ext4_blocks_count(es); @@ -2067,7 +2127,7 @@ retry: goto out; } - if (ext4_blocks_count(es) == n_blocks_count) + if (ext4_blocks_count(es) == n_blocks_count && n_blocks_count_retry == 0) goto out; err = ext4_alloc_flex_bg_array(sb, n_group + 1); @@ -2089,7 +2149,7 @@ retry: */ while (ext4_setup_next_flex_gd(sb, flex_gd, n_blocks_count, flexbg_size)) { - if (jiffies - last_update_time > HZ * 10) { + if (time_is_before_jiffies(last_update_time + HZ * 10)) { if (last_update_time) ext4_msg(sb, KERN_INFO, "resized to %llu blocks", diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 4e33b5eca694..7cdd2138c897 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -39,7 +39,6 @@ #include <linux/log2.h> #include <linux/crc16.h> #include <linux/dax.h> -#include <linux/cleancache.h> #include <linux/uaccess.h> #include <linux/iversion.h> #include <linux/unicode.h> @@ -47,6 +46,8 @@ #include <linux/kthread.h> #include <linux/freezer.h> #include <linux/fsnotify.h> +#include <linux/fs_context.h> +#include <linux/fs_parser.h> #include "ext4.h" #include "ext4_extents.h" /* Needed for trace points definition */ @@ -73,12 +74,9 @@ static int ext4_mark_recovery_complete(struct super_block *sb, static int ext4_clear_journal_err(struct super_block *sb, struct ext4_super_block *es); static int ext4_sync_fs(struct super_block *sb, int wait); -static int ext4_remount(struct super_block *sb, int *flags, char *data); static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf); static int ext4_unfreeze(struct super_block *sb); static int ext4_freeze(struct super_block *sb); -static struct dentry *ext4_mount(struct file_system_type *fs_type, int flags, - const char *dev_name, void *data); static inline int ext2_feature_set_ok(struct super_block *sb); static inline int ext3_feature_set_ok(struct super_block *sb); static void ext4_destroy_lazyinit_thread(void); @@ -86,6 +84,16 @@ static void ext4_unregister_li_request(struct super_block *sb); static void ext4_clear_request_list(void); static struct inode *ext4_get_journal_inode(struct super_block *sb, unsigned int journal_inum); +static int ext4_validate_options(struct fs_context *fc); +static int ext4_check_opt_consistency(struct fs_context *fc, + struct super_block *sb); +static void ext4_apply_options(struct fs_context *fc, struct super_block *sb); +static int ext4_parse_param(struct fs_context *fc, struct fs_parameter *param); +static int ext4_get_tree(struct fs_context *fc); +static int ext4_reconfigure(struct fs_context *fc); +static void ext4_fc_free(struct fs_context *fc); +static int ext4_init_fs_context(struct fs_context *fc); +static const struct fs_parameter_spec ext4_param_specs[]; /* * Lock ordering @@ -113,13 +121,22 @@ static struct inode *ext4_get_journal_inode(struct super_block *sb, * transaction start -> page lock(s) -> i_data_sem (rw) */ +static const struct fs_context_operations ext4_context_ops = { + .parse_param = ext4_parse_param, + .get_tree = ext4_get_tree, + .reconfigure = ext4_reconfigure, + .free = ext4_fc_free, +}; + + #if !defined(CONFIG_EXT2_FS) && !defined(CONFIG_EXT2_FS_MODULE) && defined(CONFIG_EXT4_USE_FOR_EXT2) static struct file_system_type ext2_fs_type = { - .owner = THIS_MODULE, - .name = "ext2", - .mount = ext4_mount, - .kill_sb = kill_block_super, - .fs_flags = FS_REQUIRES_DEV, + .owner = THIS_MODULE, + .name = "ext2", + .init_fs_context = ext4_init_fs_context, + .parameters = ext4_param_specs, + .kill_sb = kill_block_super, + .fs_flags = FS_REQUIRES_DEV, }; MODULE_ALIAS_FS("ext2"); MODULE_ALIAS("ext2"); @@ -130,18 +147,19 @@ MODULE_ALIAS("ext2"); static struct file_system_type ext3_fs_type = { - .owner = THIS_MODULE, - .name = "ext3", - .mount = ext4_mount, - .kill_sb = kill_block_super, - .fs_flags = FS_REQUIRES_DEV, + .owner = THIS_MODULE, + .name = "ext3", + .init_fs_context = ext4_init_fs_context, + .parameters = ext4_param_specs, + .kill_sb = kill_block_super, + .fs_flags = FS_REQUIRES_DEV, }; MODULE_ALIAS_FS("ext3"); MODULE_ALIAS("ext3"); #define IS_EXT3_SB(sb) ((sb)->s_bdev->bd_holder == &ext3_fs_type) -static inline void __ext4_read_bh(struct buffer_head *bh, int op_flags, +static inline void __ext4_read_bh(struct buffer_head *bh, blk_opf_t op_flags, bh_end_io_t *end_io) { /* @@ -153,10 +171,10 @@ static inline void __ext4_read_bh(struct buffer_head *bh, int op_flags, bh->b_end_io = end_io ? end_io : end_buffer_read_sync; get_bh(bh); - submit_bh(REQ_OP_READ, op_flags, bh); + submit_bh(REQ_OP_READ | op_flags, bh); } -void ext4_read_bh_nowait(struct buffer_head *bh, int op_flags, +void ext4_read_bh_nowait(struct buffer_head *bh, blk_opf_t op_flags, bh_end_io_t *end_io) { BUG_ON(!buffer_locked(bh)); @@ -168,7 +186,7 @@ void ext4_read_bh_nowait(struct buffer_head *bh, int op_flags, __ext4_read_bh(bh, op_flags, end_io); } -int ext4_read_bh(struct buffer_head *bh, int op_flags, bh_end_io_t *end_io) +int ext4_read_bh(struct buffer_head *bh, blk_opf_t op_flags, bh_end_io_t *end_io) { BUG_ON(!buffer_locked(bh)); @@ -185,21 +203,14 @@ int ext4_read_bh(struct buffer_head *bh, int op_flags, bh_end_io_t *end_io) return -EIO; } -int ext4_read_bh_lock(struct buffer_head *bh, int op_flags, bool wait) +int ext4_read_bh_lock(struct buffer_head *bh, blk_opf_t op_flags, bool wait) { - if (trylock_buffer(bh)) { - if (wait) - return ext4_read_bh(bh, op_flags, NULL); + lock_buffer(bh); + if (!wait) { ext4_read_bh_nowait(bh, op_flags, NULL); return 0; } - if (wait) { - wait_on_buffer(bh); - if (buffer_uptodate(bh)) - return 0; - return -EIO; - } - return 0; + return ext4_read_bh(bh, op_flags, NULL); } /* @@ -209,8 +220,8 @@ int ext4_read_bh_lock(struct buffer_head *bh, int op_flags, bool wait) * return. */ static struct buffer_head *__ext4_sb_bread_gfp(struct super_block *sb, - sector_t block, int op_flags, - gfp_t gfp) + sector_t block, + blk_opf_t op_flags, gfp_t gfp) { struct buffer_head *bh; int ret; @@ -230,7 +241,7 @@ static struct buffer_head *__ext4_sb_bread_gfp(struct super_block *sb, } struct buffer_head *ext4_sb_bread(struct super_block *sb, sector_t block, - int op_flags) + blk_opf_t op_flags) { return __ext4_sb_bread_gfp(sb, block, op_flags, __GFP_MOVABLE); } @@ -246,7 +257,8 @@ void ext4_sb_breadahead_unmovable(struct super_block *sb, sector_t block) struct buffer_head *bh = sb_getblk_gfp(sb, block, 0); if (likely(bh)) { - ext4_read_bh_lock(bh, REQ_RAHEAD, false); + if (trylock_buffer(bh)) + ext4_read_bh_nowait(bh, REQ_RAHEAD, NULL); brelse(bh); } } @@ -260,8 +272,8 @@ static int ext4_verify_csum_type(struct super_block *sb, return es->s_checksum_type == EXT4_CRC32C_CHKSUM; } -static __le32 ext4_superblock_csum(struct super_block *sb, - struct ext4_super_block *es) +__le32 ext4_superblock_csum(struct super_block *sb, + struct ext4_super_block *es) { struct ext4_sb_info *sbi = EXT4_SB(sb); int offset = offsetof(struct ext4_super_block, s_checksum); @@ -912,14 +924,20 @@ void __ext4_msg(struct super_block *sb, struct va_format vaf; va_list args; - atomic_inc(&EXT4_SB(sb)->s_msg_count); - if (!___ratelimit(&(EXT4_SB(sb)->s_msg_ratelimit_state), "EXT4-fs")) - return; + if (sb) { + atomic_inc(&EXT4_SB(sb)->s_msg_count); + if (!___ratelimit(&(EXT4_SB(sb)->s_msg_ratelimit_state), + "EXT4-fs")) + return; + } va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; - printk("%sEXT4-fs (%s): %pV\n", prefix, sb->s_id, &vaf); + if (sb) + printk("%sEXT4-fs (%s): %pV\n", prefix, sb->s_id, &vaf); + else + printk("%sEXT4-fs: %pV\n", prefix, &vaf); va_end(args); } @@ -1175,20 +1193,28 @@ static void ext4_put_super(struct super_block *sb) int aborted = 0; int i, err; - ext4_unregister_li_request(sb); - ext4_quota_off_umount(sb); - - flush_work(&sbi->s_error_work); - destroy_workqueue(sbi->rsv_conversion_wq); - ext4_release_orphan_info(sb); - /* * Unregister sysfs before destroying jbd2 journal. * Since we could still access attr_journal_task attribute via sysfs * path which could have sbi->s_journal->j_task as NULL + * Unregister sysfs before flush sbi->s_error_work. + * Since user may read /proc/fs/ext4/xx/mb_groups during umount, If + * read metadata verify failed then will queue error work. + * flush_stashed_error_work will call start_this_handle may trigger + * BUG_ON. */ ext4_unregister_sysfs(sb); + if (___ratelimit(&ext4_mount_msg_ratelimit, "EXT4-fs unmount")) + ext4_msg(sb, KERN_INFO, "unmounting filesystem."); + + ext4_unregister_li_request(sb); + ext4_quota_off_umount(sb); + + flush_work(&sbi->s_error_work); + destroy_workqueue(sbi->rsv_conversion_wq); + ext4_release_orphan_info(sb); + if (sbi->s_journal) { aborted = is_journal_aborted(sbi->s_journal); err = jbd2_journal_destroy(sbi->s_journal); @@ -1275,9 +1301,9 @@ static void ext4_put_super(struct super_block *sb) if (sbi->s_chksum_driver) crypto_free_shash(sbi->s_chksum_driver); kfree(sbi->s_blockgroup_lock); - fs_put_dax(sbi->s_daxdev); + fs_put_dax(sbi->s_daxdev, NULL); fscrypt_free_dummy_policy(&sbi->s_dummy_enc_policy); -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) utf8_unload(sb->s_encoding); #endif kfree(sbi); @@ -1292,7 +1318,7 @@ static struct inode *ext4_alloc_inode(struct super_block *sb) { struct ext4_inode_info *ei; - ei = kmem_cache_alloc(ext4_inode_cachep, GFP_NOFS); + ei = alloc_inode_sb(sb, ext4_inode_cachep, GFP_NOFS); if (!ei) return NULL; @@ -1368,7 +1394,7 @@ static void ext4_destroy_inode(struct inode *inode) static void init_once(void *foo) { - struct ext4_inode_info *ei = (struct ext4_inode_info *) foo; + struct ext4_inode_info *ei = foo; INIT_LIST_HEAD(&ei->i_orphan); init_rwsem(&ei->xattr_sem); @@ -1463,128 +1489,6 @@ static int ext4_nfs_commit_metadata(struct inode *inode) return ext4_write_inode(inode, &wbc); } -#ifdef CONFIG_FS_ENCRYPTION -static int ext4_get_context(struct inode *inode, void *ctx, size_t len) -{ - return ext4_xattr_get(inode, EXT4_XATTR_INDEX_ENCRYPTION, - EXT4_XATTR_NAME_ENCRYPTION_CONTEXT, ctx, len); -} - -static int ext4_set_context(struct inode *inode, const void *ctx, size_t len, - void *fs_data) -{ - handle_t *handle = fs_data; - int res, res2, credits, retries = 0; - - /* - * Encrypting the root directory is not allowed because e2fsck expects - * lost+found to exist and be unencrypted, and encrypting the root - * directory would imply encrypting the lost+found directory as well as - * the filename "lost+found" itself. - */ - if (inode->i_ino == EXT4_ROOT_INO) - return -EPERM; - - if (WARN_ON_ONCE(IS_DAX(inode) && i_size_read(inode))) - return -EINVAL; - - if (ext4_test_inode_flag(inode, EXT4_INODE_DAX)) - return -EOPNOTSUPP; - - res = ext4_convert_inline_data(inode); - if (res) - return res; - - /* - * If a journal handle was specified, then the encryption context is - * being set on a new inode via inheritance and is part of a larger - * transaction to create the inode. Otherwise the encryption context is - * being set on an existing inode in its own transaction. Only in the - * latter case should the "retry on ENOSPC" logic be used. - */ - - if (handle) { - res = ext4_xattr_set_handle(handle, inode, - EXT4_XATTR_INDEX_ENCRYPTION, - EXT4_XATTR_NAME_ENCRYPTION_CONTEXT, - ctx, len, 0); - if (!res) { - ext4_set_inode_flag(inode, EXT4_INODE_ENCRYPT); - ext4_clear_inode_state(inode, - EXT4_STATE_MAY_INLINE_DATA); - /* - * Update inode->i_flags - S_ENCRYPTED will be enabled, - * S_DAX may be disabled - */ - ext4_set_inode_flags(inode, false); - } - return res; - } - - res = dquot_initialize(inode); - if (res) - return res; -retry: - res = ext4_xattr_set_credits(inode, len, false /* is_create */, - &credits); - if (res) - return res; - - handle = ext4_journal_start(inode, EXT4_HT_MISC, credits); - if (IS_ERR(handle)) - return PTR_ERR(handle); - - res = ext4_xattr_set_handle(handle, inode, EXT4_XATTR_INDEX_ENCRYPTION, - EXT4_XATTR_NAME_ENCRYPTION_CONTEXT, - ctx, len, 0); - if (!res) { - ext4_set_inode_flag(inode, EXT4_INODE_ENCRYPT); - /* - * Update inode->i_flags - S_ENCRYPTED will be enabled, - * S_DAX may be disabled - */ - ext4_set_inode_flags(inode, false); - res = ext4_mark_inode_dirty(handle, inode); - if (res) - EXT4_ERROR_INODE(inode, "Failed to mark inode dirty"); - } - res2 = ext4_journal_stop(handle); - - if (res == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)) - goto retry; - if (!res) - res = res2; - return res; -} - -static const union fscrypt_policy *ext4_get_dummy_policy(struct super_block *sb) -{ - return EXT4_SB(sb)->s_dummy_enc_policy.policy; -} - -static bool ext4_has_stable_inodes(struct super_block *sb) -{ - return ext4_has_feature_stable_inodes(sb); -} - -static void ext4_get_ino_and_lblk_bits(struct super_block *sb, - int *ino_bits_ret, int *lblk_bits_ret) -{ - *ino_bits_ret = 8 * sizeof(EXT4_SB(sb)->s_es->s_inodes_count); - *lblk_bits_ret = 8 * sizeof(ext4_lblk_t); -} - -static const struct fscrypt_operations ext4_cryptops = { - .key_prefix = "ext4:", - .get_context = ext4_get_context, - .set_context = ext4_set_context, - .get_dummy_policy = ext4_get_dummy_policy, - .empty_dir = ext4_empty_dir, - .has_stable_inodes = ext4_has_stable_inodes, - .get_ino_and_lblk_bits = ext4_get_ino_and_lblk_bits, -}; -#endif - #ifdef CONFIG_QUOTA static const char * const quotatypes[] = INITQFNAMES; #define QTYPE2NAME(t) (quotatypes[t]) @@ -1647,7 +1551,6 @@ static const struct super_operations ext4_sops = { .freeze_fs = ext4_freeze, .unfreeze_fs = ext4_unfreeze, .statfs = ext4_statfs, - .remount_fs = ext4_remount, .show_options = ext4_show_options, #ifdef CONFIG_QUOTA .quota_read = ext4_quota_read, @@ -1665,253 +1568,195 @@ static const struct export_operations ext4_export_ops = { enum { Opt_bsd_df, Opt_minix_df, Opt_grpid, Opt_nogrpid, - Opt_resgid, Opt_resuid, Opt_sb, Opt_err_cont, Opt_err_panic, Opt_err_ro, + Opt_resgid, Opt_resuid, Opt_sb, Opt_nouid32, Opt_debug, Opt_removed, - Opt_user_xattr, Opt_nouser_xattr, Opt_acl, Opt_noacl, + Opt_user_xattr, Opt_acl, Opt_auto_da_alloc, Opt_noauto_da_alloc, Opt_noload, Opt_commit, Opt_min_batch_time, Opt_max_batch_time, Opt_journal_dev, Opt_journal_path, Opt_journal_checksum, Opt_journal_async_commit, Opt_abort, Opt_data_journal, Opt_data_ordered, Opt_data_writeback, Opt_data_err_abort, Opt_data_err_ignore, Opt_test_dummy_encryption, Opt_inlinecrypt, - Opt_usrjquota, Opt_grpjquota, Opt_offusrjquota, Opt_offgrpjquota, - Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0, Opt_jqfmt_vfsv1, Opt_quota, + Opt_usrjquota, Opt_grpjquota, Opt_quota, Opt_noquota, Opt_barrier, Opt_nobarrier, Opt_err, - Opt_usrquota, Opt_grpquota, Opt_prjquota, Opt_i_version, + Opt_usrquota, Opt_grpquota, Opt_prjquota, Opt_dax, Opt_dax_always, Opt_dax_inode, Opt_dax_never, Opt_stripe, Opt_delalloc, Opt_nodelalloc, Opt_warn_on_error, - Opt_nowarn_on_error, Opt_mblk_io_submit, - Opt_lazytime, Opt_nolazytime, Opt_debug_want_extra_isize, + Opt_nowarn_on_error, Opt_mblk_io_submit, Opt_debug_want_extra_isize, Opt_nomblk_io_submit, Opt_block_validity, Opt_noblock_validity, Opt_inode_readahead_blks, Opt_journal_ioprio, 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_no_prefetch_block_bitmaps, Opt_mb_optimize_scan, + Opt_errors, Opt_data, Opt_data_err, Opt_jqfmt, Opt_dax_type, #ifdef CONFIG_EXT4_DEBUG Opt_fc_debug_max_replay, Opt_fc_debug_force #endif }; -static const match_table_t tokens = { - {Opt_bsd_df, "bsddf"}, - {Opt_minix_df, "minixdf"}, - {Opt_grpid, "grpid"}, - {Opt_grpid, "bsdgroups"}, - {Opt_nogrpid, "nogrpid"}, - {Opt_nogrpid, "sysvgroups"}, - {Opt_resgid, "resgid=%u"}, - {Opt_resuid, "resuid=%u"}, - {Opt_sb, "sb=%u"}, - {Opt_err_cont, "errors=continue"}, - {Opt_err_panic, "errors=panic"}, - {Opt_err_ro, "errors=remount-ro"}, - {Opt_nouid32, "nouid32"}, - {Opt_debug, "debug"}, - {Opt_removed, "oldalloc"}, - {Opt_removed, "orlov"}, - {Opt_user_xattr, "user_xattr"}, - {Opt_nouser_xattr, "nouser_xattr"}, - {Opt_acl, "acl"}, - {Opt_noacl, "noacl"}, - {Opt_noload, "norecovery"}, - {Opt_noload, "noload"}, - {Opt_removed, "nobh"}, - {Opt_removed, "bh"}, - {Opt_commit, "commit=%u"}, - {Opt_min_batch_time, "min_batch_time=%u"}, - {Opt_max_batch_time, "max_batch_time=%u"}, - {Opt_journal_dev, "journal_dev=%u"}, - {Opt_journal_path, "journal_path=%s"}, - {Opt_journal_checksum, "journal_checksum"}, - {Opt_nojournal_checksum, "nojournal_checksum"}, - {Opt_journal_async_commit, "journal_async_commit"}, - {Opt_abort, "abort"}, - {Opt_data_journal, "data=journal"}, - {Opt_data_ordered, "data=ordered"}, - {Opt_data_writeback, "data=writeback"}, - {Opt_data_err_abort, "data_err=abort"}, - {Opt_data_err_ignore, "data_err=ignore"}, - {Opt_offusrjquota, "usrjquota="}, - {Opt_usrjquota, "usrjquota=%s"}, - {Opt_offgrpjquota, "grpjquota="}, - {Opt_grpjquota, "grpjquota=%s"}, - {Opt_jqfmt_vfsold, "jqfmt=vfsold"}, - {Opt_jqfmt_vfsv0, "jqfmt=vfsv0"}, - {Opt_jqfmt_vfsv1, "jqfmt=vfsv1"}, - {Opt_grpquota, "grpquota"}, - {Opt_noquota, "noquota"}, - {Opt_quota, "quota"}, - {Opt_usrquota, "usrquota"}, - {Opt_prjquota, "prjquota"}, - {Opt_barrier, "barrier=%u"}, - {Opt_barrier, "barrier"}, - {Opt_nobarrier, "nobarrier"}, - {Opt_i_version, "i_version"}, - {Opt_dax, "dax"}, - {Opt_dax_always, "dax=always"}, - {Opt_dax_inode, "dax=inode"}, - {Opt_dax_never, "dax=never"}, - {Opt_stripe, "stripe=%u"}, - {Opt_delalloc, "delalloc"}, - {Opt_warn_on_error, "warn_on_error"}, - {Opt_nowarn_on_error, "nowarn_on_error"}, - {Opt_lazytime, "lazytime"}, - {Opt_nolazytime, "nolazytime"}, - {Opt_debug_want_extra_isize, "debug_want_extra_isize=%u"}, - {Opt_nodelalloc, "nodelalloc"}, - {Opt_removed, "mblk_io_submit"}, - {Opt_removed, "nomblk_io_submit"}, - {Opt_block_validity, "block_validity"}, - {Opt_noblock_validity, "noblock_validity"}, - {Opt_inode_readahead_blks, "inode_readahead_blks=%u"}, - {Opt_journal_ioprio, "journal_ioprio=%u"}, - {Opt_auto_da_alloc, "auto_da_alloc=%u"}, - {Opt_auto_da_alloc, "auto_da_alloc"}, - {Opt_noauto_da_alloc, "noauto_da_alloc"}, - {Opt_dioread_nolock, "dioread_nolock"}, - {Opt_dioread_lock, "nodioread_nolock"}, - {Opt_dioread_lock, "dioread_lock"}, - {Opt_discard, "discard"}, - {Opt_nodiscard, "nodiscard"}, - {Opt_init_itable, "init_itable=%u"}, - {Opt_init_itable, "init_itable"}, - {Opt_noinit_itable, "noinit_itable"}, -#ifdef CONFIG_EXT4_DEBUG - {Opt_fc_debug_force, "fc_debug_force"}, - {Opt_fc_debug_max_replay, "fc_debug_max_replay=%u"}, -#endif - {Opt_max_dir_size_kb, "max_dir_size_kb=%u"}, - {Opt_test_dummy_encryption, "test_dummy_encryption=%s"}, - {Opt_test_dummy_encryption, "test_dummy_encryption"}, - {Opt_inlinecrypt, "inlinecrypt"}, - {Opt_nombcache, "nombcache"}, - {Opt_nombcache, "no_mbcache"}, /* for backward compatibility */ - {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 */ - {Opt_removed, "noreservation"}, /* mount option from ext2/3 */ - {Opt_removed, "journal=%u"}, /* mount option from ext2/3 */ - {Opt_err, NULL}, +static const struct constant_table ext4_param_errors[] = { + {"continue", EXT4_MOUNT_ERRORS_CONT}, + {"panic", EXT4_MOUNT_ERRORS_PANIC}, + {"remount-ro", EXT4_MOUNT_ERRORS_RO}, + {} }; -static ext4_fsblk_t get_sb_block(void **data) -{ - ext4_fsblk_t sb_block; - char *options = (char *) *data; - - if (!options || strncmp(options, "sb=", 3) != 0) - return 1; /* Default location */ - - options += 3; - /* TODO: use simple_strtoll with >32bit ext4 */ - sb_block = simple_strtoul(options, &options, 0); - if (*options && *options != ',') { - printk(KERN_ERR "EXT4-fs: Invalid sb specification: %s\n", - (char *) *data); - return 1; - } - if (*options == ',') - options++; - *data = (void *) options; - - return sb_block; -} - -#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"; +static const struct constant_table ext4_param_data[] = { + {"journal", EXT4_MOUNT_JOURNAL_DATA}, + {"ordered", EXT4_MOUNT_ORDERED_DATA}, + {"writeback", EXT4_MOUNT_WRITEBACK_DATA}, + {} +}; -#ifdef CONFIG_QUOTA -static int set_qf_name(struct super_block *sb, int qtype, substring_t *args) -{ - struct ext4_sb_info *sbi = EXT4_SB(sb); - char *qname, *old_qname = get_qf_name(sb, sbi, qtype); - int ret = -1; +static const struct constant_table ext4_param_data_err[] = { + {"abort", Opt_data_err_abort}, + {"ignore", Opt_data_err_ignore}, + {} +}; - if (sb_any_quota_loaded(sb) && !old_qname) { - ext4_msg(sb, KERN_ERR, - "Cannot change journaled " - "quota options when quota turned on"); - return -1; - } - if (ext4_has_feature_quota(sb)) { - ext4_msg(sb, KERN_INFO, "Journaled quota options " - "ignored when QUOTA feature is enabled"); - return 1; - } - qname = match_strdup(args); - if (!qname) { - ext4_msg(sb, KERN_ERR, - "Not enough memory for storing quotafile name"); - return -1; - } - if (old_qname) { - if (strcmp(old_qname, qname) == 0) - ret = 1; - else - ext4_msg(sb, KERN_ERR, - "%s quota file already specified", - QTYPE2NAME(qtype)); - goto errout; - } - if (strchr(qname, '/')) { - ext4_msg(sb, KERN_ERR, - "quotafile must be on filesystem root"); - goto errout; - } - rcu_assign_pointer(sbi->s_qf_names[qtype], qname); - set_opt(sb, QUOTA); - return 1; -errout: - kfree(qname); - return ret; -} +static const struct constant_table ext4_param_jqfmt[] = { + {"vfsold", QFMT_VFS_OLD}, + {"vfsv0", QFMT_VFS_V0}, + {"vfsv1", QFMT_VFS_V1}, + {} +}; -static int clear_qf_name(struct super_block *sb, int qtype) -{ +static const struct constant_table ext4_param_dax[] = { + {"always", Opt_dax_always}, + {"inode", Opt_dax_inode}, + {"never", Opt_dax_never}, + {} +}; - struct ext4_sb_info *sbi = EXT4_SB(sb); - char *old_qname = get_qf_name(sb, sbi, qtype); +/* String parameter that allows empty argument */ +#define fsparam_string_empty(NAME, OPT) \ + __fsparam(fs_param_is_string, NAME, OPT, fs_param_can_be_empty, NULL) - if (sb_any_quota_loaded(sb) && old_qname) { - ext4_msg(sb, KERN_ERR, "Cannot change journaled quota options" - " when quota turned on"); - return -1; - } - rcu_assign_pointer(sbi->s_qf_names[qtype], NULL); - synchronize_rcu(); - kfree(old_qname); - return 1; -} +/* + * Mount option specification + * We don't use fsparam_flag_no because of the way we set the + * options and the way we show them in _ext4_show_options(). To + * keep the changes to a minimum, let's keep the negative options + * separate for now. + */ +static const struct fs_parameter_spec ext4_param_specs[] = { + fsparam_flag ("bsddf", Opt_bsd_df), + fsparam_flag ("minixdf", Opt_minix_df), + fsparam_flag ("grpid", Opt_grpid), + fsparam_flag ("bsdgroups", Opt_grpid), + fsparam_flag ("nogrpid", Opt_nogrpid), + fsparam_flag ("sysvgroups", Opt_nogrpid), + fsparam_u32 ("resgid", Opt_resgid), + fsparam_u32 ("resuid", Opt_resuid), + fsparam_u32 ("sb", Opt_sb), + fsparam_enum ("errors", Opt_errors, ext4_param_errors), + fsparam_flag ("nouid32", Opt_nouid32), + fsparam_flag ("debug", Opt_debug), + fsparam_flag ("oldalloc", Opt_removed), + fsparam_flag ("orlov", Opt_removed), + fsparam_flag ("user_xattr", Opt_user_xattr), + fsparam_flag ("acl", Opt_acl), + fsparam_flag ("norecovery", Opt_noload), + fsparam_flag ("noload", Opt_noload), + fsparam_flag ("bh", Opt_removed), + fsparam_flag ("nobh", Opt_removed), + fsparam_u32 ("commit", Opt_commit), + fsparam_u32 ("min_batch_time", Opt_min_batch_time), + fsparam_u32 ("max_batch_time", Opt_max_batch_time), + fsparam_u32 ("journal_dev", Opt_journal_dev), + fsparam_bdev ("journal_path", Opt_journal_path), + fsparam_flag ("journal_checksum", Opt_journal_checksum), + fsparam_flag ("nojournal_checksum", Opt_nojournal_checksum), + fsparam_flag ("journal_async_commit",Opt_journal_async_commit), + fsparam_flag ("abort", Opt_abort), + fsparam_enum ("data", Opt_data, ext4_param_data), + fsparam_enum ("data_err", Opt_data_err, + ext4_param_data_err), + fsparam_string_empty + ("usrjquota", Opt_usrjquota), + fsparam_string_empty + ("grpjquota", Opt_grpjquota), + fsparam_enum ("jqfmt", Opt_jqfmt, ext4_param_jqfmt), + fsparam_flag ("grpquota", Opt_grpquota), + fsparam_flag ("quota", Opt_quota), + fsparam_flag ("noquota", Opt_noquota), + fsparam_flag ("usrquota", Opt_usrquota), + fsparam_flag ("prjquota", Opt_prjquota), + fsparam_flag ("barrier", Opt_barrier), + fsparam_u32 ("barrier", Opt_barrier), + fsparam_flag ("nobarrier", Opt_nobarrier), + fsparam_flag ("i_version", Opt_removed), + fsparam_flag ("dax", Opt_dax), + fsparam_enum ("dax", Opt_dax_type, ext4_param_dax), + fsparam_u32 ("stripe", Opt_stripe), + fsparam_flag ("delalloc", Opt_delalloc), + fsparam_flag ("nodelalloc", Opt_nodelalloc), + fsparam_flag ("warn_on_error", Opt_warn_on_error), + fsparam_flag ("nowarn_on_error", Opt_nowarn_on_error), + fsparam_u32 ("debug_want_extra_isize", + Opt_debug_want_extra_isize), + fsparam_flag ("mblk_io_submit", Opt_removed), + fsparam_flag ("nomblk_io_submit", Opt_removed), + fsparam_flag ("block_validity", Opt_block_validity), + fsparam_flag ("noblock_validity", Opt_noblock_validity), + fsparam_u32 ("inode_readahead_blks", + Opt_inode_readahead_blks), + fsparam_u32 ("journal_ioprio", Opt_journal_ioprio), + fsparam_u32 ("auto_da_alloc", Opt_auto_da_alloc), + fsparam_flag ("auto_da_alloc", Opt_auto_da_alloc), + fsparam_flag ("noauto_da_alloc", Opt_noauto_da_alloc), + fsparam_flag ("dioread_nolock", Opt_dioread_nolock), + fsparam_flag ("nodioread_nolock", Opt_dioread_lock), + fsparam_flag ("dioread_lock", Opt_dioread_lock), + fsparam_flag ("discard", Opt_discard), + fsparam_flag ("nodiscard", Opt_nodiscard), + fsparam_u32 ("init_itable", Opt_init_itable), + fsparam_flag ("init_itable", Opt_init_itable), + fsparam_flag ("noinit_itable", Opt_noinit_itable), +#ifdef CONFIG_EXT4_DEBUG + fsparam_flag ("fc_debug_force", Opt_fc_debug_force), + fsparam_u32 ("fc_debug_max_replay", Opt_fc_debug_max_replay), #endif + fsparam_u32 ("max_dir_size_kb", Opt_max_dir_size_kb), + fsparam_flag ("test_dummy_encryption", + Opt_test_dummy_encryption), + fsparam_string ("test_dummy_encryption", + Opt_test_dummy_encryption), + fsparam_flag ("inlinecrypt", Opt_inlinecrypt), + fsparam_flag ("nombcache", Opt_nombcache), + fsparam_flag ("no_mbcache", Opt_nombcache), /* for backward compatibility */ + fsparam_flag ("prefetch_block_bitmaps", + Opt_removed), + fsparam_flag ("no_prefetch_block_bitmaps", + Opt_no_prefetch_block_bitmaps), + fsparam_s32 ("mb_optimize_scan", Opt_mb_optimize_scan), + fsparam_string ("check", Opt_removed), /* mount option from ext2/3 */ + fsparam_flag ("nocheck", Opt_removed), /* mount option from ext2/3 */ + fsparam_flag ("reservation", Opt_removed), /* mount option from ext2/3 */ + fsparam_flag ("noreservation", Opt_removed), /* mount option from ext2/3 */ + fsparam_u32 ("journal", Opt_removed), /* mount option from ext2/3 */ + {} +}; + +#define DEFAULT_JOURNAL_IOPRIO (IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, 3)) #define MOPT_SET 0x0001 #define MOPT_CLEAR 0x0002 #define MOPT_NOSUPPORT 0x0004 #define MOPT_EXPLICIT 0x0008 -#define MOPT_CLEAR_ERR 0x0010 -#define MOPT_GTE0 0x0020 #ifdef CONFIG_QUOTA #define MOPT_Q 0 -#define MOPT_QFMT 0x0040 +#define MOPT_QFMT 0x0010 #else #define MOPT_Q MOPT_NOSUPPORT #define MOPT_QFMT MOPT_NOSUPPORT #endif -#define MOPT_DATAJ 0x0080 -#define MOPT_NO_EXT2 0x0100 -#define MOPT_NO_EXT3 0x0200 +#define MOPT_NO_EXT2 0x0020 +#define MOPT_NO_EXT3 0x0040 #define MOPT_EXT4_ONLY (MOPT_NO_EXT2 | MOPT_NO_EXT3) -#define MOPT_STRING 0x0400 -#define MOPT_SKIP 0x0800 -#define MOPT_2 0x1000 +#define MOPT_SKIP 0x0080 +#define MOPT_2 0x0100 static const struct mount_opts { int token; @@ -1936,6 +1781,7 @@ static const struct mount_opts { MOPT_EXT4_ONLY | MOPT_CLEAR}, {Opt_warn_on_error, EXT4_MOUNT_WARN_ON_ERROR, MOPT_SET}, {Opt_nowarn_on_error, EXT4_MOUNT_WARN_ON_ERROR, MOPT_CLEAR}, + {Opt_commit, 0, MOPT_NO_EXT2}, {Opt_nojournal_checksum, EXT4_MOUNT_JOURNAL_CHECKSUM, MOPT_EXT4_ONLY | MOPT_CLEAR}, {Opt_journal_checksum, EXT4_MOUNT_JOURNAL_CHECKSUM, @@ -1944,52 +1790,25 @@ static const struct mount_opts { EXT4_MOUNT_JOURNAL_CHECKSUM), MOPT_EXT4_ONLY | MOPT_SET | MOPT_EXPLICIT}, {Opt_noload, EXT4_MOUNT_NOLOAD, MOPT_NO_EXT2 | MOPT_SET}, - {Opt_err_panic, EXT4_MOUNT_ERRORS_PANIC, MOPT_SET | MOPT_CLEAR_ERR}, - {Opt_err_ro, EXT4_MOUNT_ERRORS_RO, MOPT_SET | MOPT_CLEAR_ERR}, - {Opt_err_cont, EXT4_MOUNT_ERRORS_CONT, MOPT_SET | MOPT_CLEAR_ERR}, - {Opt_data_err_abort, EXT4_MOUNT_DATA_ERR_ABORT, - MOPT_NO_EXT2}, - {Opt_data_err_ignore, EXT4_MOUNT_DATA_ERR_ABORT, - MOPT_NO_EXT2}, + {Opt_data_err, EXT4_MOUNT_DATA_ERR_ABORT, MOPT_NO_EXT2}, {Opt_barrier, EXT4_MOUNT_BARRIER, MOPT_SET}, {Opt_nobarrier, EXT4_MOUNT_BARRIER, MOPT_CLEAR}, {Opt_noauto_da_alloc, EXT4_MOUNT_NO_AUTO_DA_ALLOC, MOPT_SET}, {Opt_auto_da_alloc, EXT4_MOUNT_NO_AUTO_DA_ALLOC, MOPT_CLEAR}, {Opt_noinit_itable, EXT4_MOUNT_INIT_INODE_TABLE, MOPT_CLEAR}, - {Opt_commit, 0, MOPT_GTE0}, - {Opt_max_batch_time, 0, MOPT_GTE0}, - {Opt_min_batch_time, 0, MOPT_GTE0}, - {Opt_inode_readahead_blks, 0, MOPT_GTE0}, - {Opt_init_itable, 0, MOPT_GTE0}, - {Opt_dax, EXT4_MOUNT_DAX_ALWAYS, MOPT_SET | MOPT_SKIP}, - {Opt_dax_always, EXT4_MOUNT_DAX_ALWAYS, - MOPT_EXT4_ONLY | MOPT_SET | MOPT_SKIP}, - {Opt_dax_inode, EXT4_MOUNT2_DAX_INODE, - MOPT_EXT4_ONLY | MOPT_SET | MOPT_SKIP}, - {Opt_dax_never, EXT4_MOUNT2_DAX_NEVER, - MOPT_EXT4_ONLY | MOPT_SET | MOPT_SKIP}, - {Opt_stripe, 0, MOPT_GTE0}, - {Opt_resuid, 0, MOPT_GTE0}, - {Opt_resgid, 0, MOPT_GTE0}, - {Opt_journal_dev, 0, MOPT_NO_EXT2 | MOPT_GTE0}, - {Opt_journal_path, 0, MOPT_NO_EXT2 | MOPT_STRING}, - {Opt_journal_ioprio, 0, MOPT_NO_EXT2 | MOPT_GTE0}, - {Opt_data_journal, EXT4_MOUNT_JOURNAL_DATA, MOPT_NO_EXT2 | MOPT_DATAJ}, - {Opt_data_ordered, EXT4_MOUNT_ORDERED_DATA, MOPT_NO_EXT2 | MOPT_DATAJ}, - {Opt_data_writeback, EXT4_MOUNT_WRITEBACK_DATA, - MOPT_NO_EXT2 | MOPT_DATAJ}, + {Opt_dax_type, 0, MOPT_EXT4_ONLY}, + {Opt_journal_dev, 0, MOPT_NO_EXT2}, + {Opt_journal_path, 0, MOPT_NO_EXT2}, + {Opt_journal_ioprio, 0, MOPT_NO_EXT2}, + {Opt_data, 0, MOPT_NO_EXT2}, {Opt_user_xattr, EXT4_MOUNT_XATTR_USER, MOPT_SET}, - {Opt_nouser_xattr, EXT4_MOUNT_XATTR_USER, MOPT_CLEAR}, #ifdef CONFIG_EXT4_FS_POSIX_ACL {Opt_acl, EXT4_MOUNT_POSIX_ACL, MOPT_SET}, - {Opt_noacl, EXT4_MOUNT_POSIX_ACL, MOPT_CLEAR}, #else {Opt_acl, 0, MOPT_NOSUPPORT}, - {Opt_noacl, 0, MOPT_NOSUPPORT}, #endif {Opt_nouid32, EXT4_MOUNT_NO_UID32, MOPT_SET}, {Opt_debug, EXT4_MOUNT_DEBUG, MOPT_SET}, - {Opt_debug_want_extra_isize, 0, MOPT_GTE0}, {Opt_quota, EXT4_MOUNT_QUOTA | EXT4_MOUNT_USRQUOTA, MOPT_SET | MOPT_Q}, {Opt_usrquota, EXT4_MOUNT_QUOTA | EXT4_MOUNT_USRQUOTA, MOPT_SET | MOPT_Q}, @@ -2000,499 +1819,1022 @@ static const struct mount_opts { {Opt_noquota, (EXT4_MOUNT_QUOTA | EXT4_MOUNT_USRQUOTA | EXT4_MOUNT_GRPQUOTA | EXT4_MOUNT_PRJQUOTA), MOPT_CLEAR | MOPT_Q}, - {Opt_usrjquota, 0, MOPT_Q | MOPT_STRING}, - {Opt_grpjquota, 0, MOPT_Q | MOPT_STRING}, - {Opt_offusrjquota, 0, MOPT_Q}, - {Opt_offgrpjquota, 0, MOPT_Q}, - {Opt_jqfmt_vfsold, QFMT_VFS_OLD, MOPT_QFMT}, - {Opt_jqfmt_vfsv0, QFMT_VFS_V0, MOPT_QFMT}, - {Opt_jqfmt_vfsv1, QFMT_VFS_V1, MOPT_QFMT}, - {Opt_max_dir_size_kb, 0, MOPT_GTE0}, - {Opt_test_dummy_encryption, 0, MOPT_STRING}, + {Opt_usrjquota, 0, MOPT_Q}, + {Opt_grpjquota, 0, MOPT_Q}, + {Opt_jqfmt, 0, MOPT_QFMT}, {Opt_nombcache, EXT4_MOUNT_NO_MBCACHE, MOPT_SET}, {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}, - {Opt_fc_debug_max_replay, 0, MOPT_GTE0}, #endif {Opt_err, 0, 0} }; -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) static const struct ext4_sb_encodings { __u16 magic; char *name; - char *version; + unsigned int version; } ext4_sb_encoding_map[] = { - {EXT4_ENC_UTF8_12_1, "utf8", "12.1.0"}, + {EXT4_ENC_UTF8_12_1, "utf8", UNICODE_AGE(12, 1, 0)}, }; -static int ext4_sb_read_encoding(const struct ext4_super_block *es, - const struct ext4_sb_encodings **encoding, - __u16 *flags) +static const struct ext4_sb_encodings * +ext4_sb_read_encoding(const struct ext4_super_block *es) { __u16 magic = le16_to_cpu(es->s_encoding); int i; for (i = 0; i < ARRAY_SIZE(ext4_sb_encoding_map); i++) if (magic == ext4_sb_encoding_map[i].magic) - break; + return &ext4_sb_encoding_map[i]; + + return NULL; +} +#endif + +#define EXT4_SPEC_JQUOTA (1 << 0) +#define EXT4_SPEC_JQFMT (1 << 1) +#define EXT4_SPEC_DATAJ (1 << 2) +#define EXT4_SPEC_SB_BLOCK (1 << 3) +#define EXT4_SPEC_JOURNAL_DEV (1 << 4) +#define EXT4_SPEC_JOURNAL_IOPRIO (1 << 5) +#define EXT4_SPEC_s_want_extra_isize (1 << 7) +#define EXT4_SPEC_s_max_batch_time (1 << 8) +#define EXT4_SPEC_s_min_batch_time (1 << 9) +#define EXT4_SPEC_s_inode_readahead_blks (1 << 10) +#define EXT4_SPEC_s_li_wait_mult (1 << 11) +#define EXT4_SPEC_s_max_dir_size_kb (1 << 12) +#define EXT4_SPEC_s_stripe (1 << 13) +#define EXT4_SPEC_s_resuid (1 << 14) +#define EXT4_SPEC_s_resgid (1 << 15) +#define EXT4_SPEC_s_commit_interval (1 << 16) +#define EXT4_SPEC_s_fc_debug_max_replay (1 << 17) +#define EXT4_SPEC_s_sb_block (1 << 18) +#define EXT4_SPEC_mb_optimize_scan (1 << 19) + +struct ext4_fs_context { + char *s_qf_names[EXT4_MAXQUOTAS]; + struct fscrypt_dummy_policy dummy_enc_policy; + int s_jquota_fmt; /* Format of quota to use */ +#ifdef CONFIG_EXT4_DEBUG + int s_fc_debug_max_replay; +#endif + unsigned short qname_spec; + unsigned long vals_s_flags; /* Bits to set in s_flags */ + unsigned long mask_s_flags; /* Bits changed in s_flags */ + unsigned long journal_devnum; + unsigned long s_commit_interval; + unsigned long s_stripe; + unsigned int s_inode_readahead_blks; + unsigned int s_want_extra_isize; + unsigned int s_li_wait_mult; + unsigned int s_max_dir_size_kb; + unsigned int journal_ioprio; + unsigned int vals_s_mount_opt; + unsigned int mask_s_mount_opt; + unsigned int vals_s_mount_opt2; + unsigned int mask_s_mount_opt2; + unsigned long vals_s_mount_flags; + unsigned long mask_s_mount_flags; + unsigned int opt_flags; /* MOPT flags */ + unsigned int spec; + u32 s_max_batch_time; + u32 s_min_batch_time; + kuid_t s_resuid; + kgid_t s_resgid; + ext4_fsblk_t s_sb_block; +}; + +static void ext4_fc_free(struct fs_context *fc) +{ + struct ext4_fs_context *ctx = fc->fs_private; + int i; + + if (!ctx) + return; + + for (i = 0; i < EXT4_MAXQUOTAS; i++) + kfree(ctx->s_qf_names[i]); - if (i >= ARRAY_SIZE(ext4_sb_encoding_map)) + fscrypt_free_dummy_policy(&ctx->dummy_enc_policy); + kfree(ctx); +} + +int ext4_init_fs_context(struct fs_context *fc) +{ + struct ext4_fs_context *ctx; + + ctx = kzalloc(sizeof(struct ext4_fs_context), GFP_KERNEL); + if (!ctx) + return -ENOMEM; + + fc->fs_private = ctx; + fc->ops = &ext4_context_ops; + + return 0; +} + +#ifdef CONFIG_QUOTA +/* + * Note the name of the specified quota file. + */ +static int note_qf_name(struct fs_context *fc, int qtype, + struct fs_parameter *param) +{ + struct ext4_fs_context *ctx = fc->fs_private; + char *qname; + + if (param->size < 1) { + ext4_msg(NULL, KERN_ERR, "Missing quota name"); return -EINVAL; + } + if (strchr(param->string, '/')) { + ext4_msg(NULL, KERN_ERR, + "quotafile must be on filesystem root"); + return -EINVAL; + } + if (ctx->s_qf_names[qtype]) { + if (strcmp(ctx->s_qf_names[qtype], param->string) != 0) { + ext4_msg(NULL, KERN_ERR, + "%s quota file already specified", + QTYPE2NAME(qtype)); + return -EINVAL; + } + return 0; + } - *encoding = &ext4_sb_encoding_map[i]; - *flags = le16_to_cpu(es->s_encoding_flags); + qname = kmemdup_nul(param->string, param->size, GFP_KERNEL); + if (!qname) { + ext4_msg(NULL, KERN_ERR, + "Not enough memory for storing quotafile name"); + return -ENOMEM; + } + ctx->s_qf_names[qtype] = qname; + ctx->qname_spec |= 1 << qtype; + ctx->spec |= EXT4_SPEC_JQUOTA; + return 0; +} + +/* + * Clear the name of the specified quota file. + */ +static int unnote_qf_name(struct fs_context *fc, int qtype) +{ + struct ext4_fs_context *ctx = fc->fs_private; + + if (ctx->s_qf_names[qtype]) + kfree(ctx->s_qf_names[qtype]); + ctx->s_qf_names[qtype] = NULL; + ctx->qname_spec |= 1 << qtype; + ctx->spec |= EXT4_SPEC_JQUOTA; return 0; } #endif -static int ext4_set_test_dummy_encryption(struct super_block *sb, - const char *opt, - const substring_t *arg, - bool is_remount) +static int ext4_parse_test_dummy_encryption(const struct fs_parameter *param, + struct ext4_fs_context *ctx) { -#ifdef CONFIG_FS_ENCRYPTION - struct ext4_sb_info *sbi = EXT4_SB(sb); int err; - /* - * This mount option is just for testing, and it's not worthwhile to - * implement the extra complexity (e.g. RCU protection) that would be - * needed to allow it to be set or changed during remount. We do allow - * it to be specified during remount, but only if there is no change. - */ - if (is_remount && !sbi->s_dummy_enc_policy.policy) { - ext4_msg(sb, KERN_WARNING, - "Can't set test_dummy_encryption on remount"); - return -1; + if (!IS_ENABLED(CONFIG_FS_ENCRYPTION)) { + ext4_msg(NULL, KERN_WARNING, + "test_dummy_encryption option not supported"); + return -EINVAL; } - err = fscrypt_set_test_dummy_encryption(sb, arg->from, - &sbi->s_dummy_enc_policy); - if (err) { - if (err == -EEXIST) - ext4_msg(sb, KERN_WARNING, - "Can't change test_dummy_encryption on remount"); - else if (err == -EINVAL) - ext4_msg(sb, KERN_WARNING, - "Value of option \"%s\" is unrecognized", opt); - else - ext4_msg(sb, KERN_WARNING, - "Error processing option \"%s\" [%d]", - opt, err); - return -1; + err = fscrypt_parse_test_dummy_encryption(param, + &ctx->dummy_enc_policy); + if (err == -EINVAL) { + ext4_msg(NULL, KERN_WARNING, + "Value of option \"%s\" is unrecognized", param->key); + } else if (err == -EEXIST) { + ext4_msg(NULL, KERN_WARNING, + "Conflicting test_dummy_encryption options"); + return -EINVAL; } - ext4_msg(sb, KERN_WARNING, "Test dummy encryption mode enabled"); -#else - ext4_msg(sb, KERN_WARNING, - "Test dummy encryption mount option ignored"); -#endif - return 1; + return err; } -struct ext4_parsed_options { - unsigned long journal_devnum; - unsigned int journal_ioprio; - int mb_optimize_scan; -}; +#define EXT4_SET_CTX(name) \ +static inline void ctx_set_##name(struct ext4_fs_context *ctx, \ + unsigned long flag) \ +{ \ + ctx->mask_s_##name |= flag; \ + ctx->vals_s_##name |= flag; \ +} + +#define EXT4_CLEAR_CTX(name) \ +static inline void ctx_clear_##name(struct ext4_fs_context *ctx, \ + unsigned long flag) \ +{ \ + ctx->mask_s_##name |= flag; \ + ctx->vals_s_##name &= ~flag; \ +} + +#define EXT4_TEST_CTX(name) \ +static inline unsigned long \ +ctx_test_##name(struct ext4_fs_context *ctx, unsigned long flag) \ +{ \ + return (ctx->vals_s_##name & flag); \ +} -static int handle_mount_opt(struct super_block *sb, char *opt, int token, - substring_t *args, struct ext4_parsed_options *parsed_opts, - int is_remount) +EXT4_SET_CTX(flags); /* set only */ +EXT4_SET_CTX(mount_opt); +EXT4_CLEAR_CTX(mount_opt); +EXT4_TEST_CTX(mount_opt); +EXT4_SET_CTX(mount_opt2); +EXT4_CLEAR_CTX(mount_opt2); +EXT4_TEST_CTX(mount_opt2); + +static inline void ctx_set_mount_flag(struct ext4_fs_context *ctx, int bit) { - struct ext4_sb_info *sbi = EXT4_SB(sb); + set_bit(bit, &ctx->mask_s_mount_flags); + set_bit(bit, &ctx->vals_s_mount_flags); +} + +static int ext4_parse_param(struct fs_context *fc, struct fs_parameter *param) +{ + struct ext4_fs_context *ctx = fc->fs_private; + struct fs_parse_result result; const struct mount_opts *m; + int is_remount; kuid_t uid; kgid_t gid; - int arg = 0; + int token; -#ifdef CONFIG_QUOTA - if (token == Opt_usrjquota) - return set_qf_name(sb, USRQUOTA, &args[0]); - else if (token == Opt_grpjquota) - return set_qf_name(sb, GRPQUOTA, &args[0]); - else if (token == Opt_offusrjquota) - return clear_qf_name(sb, USRQUOTA); - else if (token == Opt_offgrpjquota) - return clear_qf_name(sb, GRPQUOTA); -#endif - switch (token) { - case Opt_noacl: - case Opt_nouser_xattr: - ext4_msg(sb, KERN_WARNING, deprecated_msg, opt, "3.5"); - break; - case Opt_sb: - return 1; /* handled by get_sb_block() */ - case Opt_removed: - ext4_msg(sb, KERN_WARNING, "Ignoring removed %s option", opt); - return 1; - case Opt_abort: - ext4_set_mount_flag(sb, EXT4_MF_FS_ABORTED); - return 1; - case Opt_i_version: - sb->s_flags |= SB_I_VERSION; - return 1; - case Opt_lazytime: - sb->s_flags |= SB_LAZYTIME; - return 1; - case Opt_nolazytime: - sb->s_flags &= ~SB_LAZYTIME; - return 1; - case Opt_inlinecrypt: -#ifdef CONFIG_FS_ENCRYPTION_INLINE_CRYPT - sb->s_flags |= SB_INLINECRYPT; -#else - ext4_msg(sb, KERN_ERR, "inline encryption not supported"); -#endif - return 1; - } + token = fs_parse(fc, ext4_param_specs, param, &result); + if (token < 0) + return token; + is_remount = fc->purpose == FS_CONTEXT_FOR_RECONFIGURE; for (m = ext4_mount_opts; m->token != Opt_err; m++) if (token == m->token) break; - if (m->token == Opt_err) { - ext4_msg(sb, KERN_ERR, "Unrecognized mount option \"%s\" " - "or missing value", opt); - return -1; - } - - if ((m->flags & MOPT_NO_EXT2) && IS_EXT2_SB(sb)) { - ext4_msg(sb, KERN_ERR, - "Mount option \"%s\" incompatible with ext2", opt); - return -1; - } - if ((m->flags & MOPT_NO_EXT3) && IS_EXT3_SB(sb)) { - ext4_msg(sb, KERN_ERR, - "Mount option \"%s\" incompatible with ext3", opt); - return -1; - } + ctx->opt_flags |= m->flags; - if (args->from && !(m->flags & MOPT_STRING) && match_int(args, &arg)) - return -1; - if (args->from && (m->flags & MOPT_GTE0) && (arg < 0)) - return -1; if (m->flags & MOPT_EXPLICIT) { if (m->mount_opt & EXT4_MOUNT_DELALLOC) { - set_opt2(sb, EXPLICIT_DELALLOC); + ctx_set_mount_opt2(ctx, EXT4_MOUNT2_EXPLICIT_DELALLOC); } else if (m->mount_opt & EXT4_MOUNT_JOURNAL_CHECKSUM) { - set_opt2(sb, EXPLICIT_JOURNAL_CHECKSUM); + ctx_set_mount_opt2(ctx, + EXT4_MOUNT2_EXPLICIT_JOURNAL_CHECKSUM); } else - return -1; - } - if (m->flags & MOPT_CLEAR_ERR) - clear_opt(sb, ERRORS_MASK); - if (token == Opt_noquota && sb_any_quota_loaded(sb)) { - ext4_msg(sb, KERN_ERR, "Cannot change quota " - "options when quota turned on"); - return -1; + return -EINVAL; } if (m->flags & MOPT_NOSUPPORT) { - ext4_msg(sb, KERN_ERR, "%s option not supported", opt); - } else if (token == Opt_commit) { - if (arg == 0) - arg = JBD2_DEFAULT_MAX_COMMIT_AGE; - else if (arg > INT_MAX / HZ) { - ext4_msg(sb, KERN_ERR, + ext4_msg(NULL, KERN_ERR, "%s option not supported", + param->key); + return 0; + } + + switch (token) { +#ifdef CONFIG_QUOTA + case Opt_usrjquota: + if (!*param->string) + return unnote_qf_name(fc, USRQUOTA); + else + return note_qf_name(fc, USRQUOTA, param); + case Opt_grpjquota: + if (!*param->string) + return unnote_qf_name(fc, GRPQUOTA); + else + return note_qf_name(fc, GRPQUOTA, param); +#endif + case Opt_sb: + if (fc->purpose == FS_CONTEXT_FOR_RECONFIGURE) { + ext4_msg(NULL, KERN_WARNING, + "Ignoring %s option on remount", param->key); + } else { + ctx->s_sb_block = result.uint_32; + ctx->spec |= EXT4_SPEC_s_sb_block; + } + return 0; + case Opt_removed: + ext4_msg(NULL, KERN_WARNING, "Ignoring removed %s option", + param->key); + return 0; + case Opt_abort: + ctx_set_mount_flag(ctx, EXT4_MF_FS_ABORTED); + return 0; + case Opt_inlinecrypt: +#ifdef CONFIG_FS_ENCRYPTION_INLINE_CRYPT + ctx_set_flags(ctx, SB_INLINECRYPT); +#else + ext4_msg(NULL, KERN_ERR, "inline encryption not supported"); +#endif + return 0; + case Opt_errors: + ctx_clear_mount_opt(ctx, EXT4_MOUNT_ERRORS_MASK); + ctx_set_mount_opt(ctx, result.uint_32); + return 0; +#ifdef CONFIG_QUOTA + case Opt_jqfmt: + ctx->s_jquota_fmt = result.uint_32; + ctx->spec |= EXT4_SPEC_JQFMT; + return 0; +#endif + case Opt_data: + ctx_clear_mount_opt(ctx, EXT4_MOUNT_DATA_FLAGS); + ctx_set_mount_opt(ctx, result.uint_32); + ctx->spec |= EXT4_SPEC_DATAJ; + return 0; + case Opt_commit: + if (result.uint_32 == 0) + ctx->s_commit_interval = JBD2_DEFAULT_MAX_COMMIT_AGE; + else if (result.uint_32 > INT_MAX / HZ) { + ext4_msg(NULL, KERN_ERR, "Invalid commit interval %d, " "must be smaller than %d", - arg, INT_MAX / HZ); - return -1; + result.uint_32, INT_MAX / HZ); + return -EINVAL; } - sbi->s_commit_interval = HZ * arg; - } else if (token == Opt_debug_want_extra_isize) { - if ((arg & 1) || - (arg < 4) || - (arg > (sbi->s_inode_size - EXT4_GOOD_OLD_INODE_SIZE))) { - ext4_msg(sb, KERN_ERR, - "Invalid want_extra_isize %d", arg); - return -1; + ctx->s_commit_interval = HZ * result.uint_32; + ctx->spec |= EXT4_SPEC_s_commit_interval; + return 0; + case Opt_debug_want_extra_isize: + if ((result.uint_32 & 1) || (result.uint_32 < 4)) { + ext4_msg(NULL, KERN_ERR, + "Invalid want_extra_isize %d", result.uint_32); + return -EINVAL; } - sbi->s_want_extra_isize = arg; - } else if (token == Opt_max_batch_time) { - sbi->s_max_batch_time = arg; - } else if (token == Opt_min_batch_time) { - sbi->s_min_batch_time = arg; - } else if (token == Opt_inode_readahead_blks) { - if (arg && (arg > (1 << 30) || !is_power_of_2(arg))) { - ext4_msg(sb, KERN_ERR, + ctx->s_want_extra_isize = result.uint_32; + ctx->spec |= EXT4_SPEC_s_want_extra_isize; + return 0; + case Opt_max_batch_time: + ctx->s_max_batch_time = result.uint_32; + ctx->spec |= EXT4_SPEC_s_max_batch_time; + return 0; + case Opt_min_batch_time: + ctx->s_min_batch_time = result.uint_32; + ctx->spec |= EXT4_SPEC_s_min_batch_time; + return 0; + case Opt_inode_readahead_blks: + if (result.uint_32 && + (result.uint_32 > (1 << 30) || + !is_power_of_2(result.uint_32))) { + ext4_msg(NULL, KERN_ERR, "EXT4-fs: inode_readahead_blks must be " "0 or a power of 2 smaller than 2^31"); - return -1; + return -EINVAL; } - sbi->s_inode_readahead_blks = arg; - } else if (token == Opt_init_itable) { - set_opt(sb, INIT_INODE_TABLE); - if (!args->from) - arg = EXT4_DEF_LI_WAIT_MULT; - sbi->s_li_wait_mult = arg; - } else if (token == Opt_max_dir_size_kb) { - sbi->s_max_dir_size_kb = arg; + ctx->s_inode_readahead_blks = result.uint_32; + ctx->spec |= EXT4_SPEC_s_inode_readahead_blks; + return 0; + case Opt_init_itable: + ctx_set_mount_opt(ctx, EXT4_MOUNT_INIT_INODE_TABLE); + ctx->s_li_wait_mult = EXT4_DEF_LI_WAIT_MULT; + if (param->type == fs_value_is_string) + ctx->s_li_wait_mult = result.uint_32; + ctx->spec |= EXT4_SPEC_s_li_wait_mult; + return 0; + case Opt_max_dir_size_kb: + ctx->s_max_dir_size_kb = result.uint_32; + ctx->spec |= EXT4_SPEC_s_max_dir_size_kb; + return 0; #ifdef CONFIG_EXT4_DEBUG - } else if (token == Opt_fc_debug_max_replay) { - sbi->s_fc_debug_max_replay = arg; + case Opt_fc_debug_max_replay: + ctx->s_fc_debug_max_replay = result.uint_32; + ctx->spec |= EXT4_SPEC_s_fc_debug_max_replay; + return 0; #endif - } else if (token == Opt_stripe) { - sbi->s_stripe = arg; - } else if (token == Opt_resuid) { - uid = make_kuid(current_user_ns(), arg); + case Opt_stripe: + ctx->s_stripe = result.uint_32; + ctx->spec |= EXT4_SPEC_s_stripe; + return 0; + case Opt_resuid: + uid = make_kuid(current_user_ns(), result.uint_32); if (!uid_valid(uid)) { - ext4_msg(sb, KERN_ERR, "Invalid uid value %d", arg); - return -1; + ext4_msg(NULL, KERN_ERR, "Invalid uid value %d", + result.uint_32); + return -EINVAL; } - sbi->s_resuid = uid; - } else if (token == Opt_resgid) { - gid = make_kgid(current_user_ns(), arg); + ctx->s_resuid = uid; + ctx->spec |= EXT4_SPEC_s_resuid; + return 0; + case Opt_resgid: + gid = make_kgid(current_user_ns(), result.uint_32); if (!gid_valid(gid)) { - ext4_msg(sb, KERN_ERR, "Invalid gid value %d", arg); - return -1; + ext4_msg(NULL, KERN_ERR, "Invalid gid value %d", + result.uint_32); + return -EINVAL; } - sbi->s_resgid = gid; - } else if (token == Opt_journal_dev) { + ctx->s_resgid = gid; + ctx->spec |= EXT4_SPEC_s_resgid; + return 0; + case Opt_journal_dev: if (is_remount) { - ext4_msg(sb, KERN_ERR, + ext4_msg(NULL, KERN_ERR, "Cannot specify journal on remount"); - return -1; + return -EINVAL; } - parsed_opts->journal_devnum = arg; - } else if (token == Opt_journal_path) { - char *journal_path; + ctx->journal_devnum = result.uint_32; + ctx->spec |= EXT4_SPEC_JOURNAL_DEV; + return 0; + case Opt_journal_path: + { struct inode *journal_inode; struct path path; int error; if (is_remount) { - ext4_msg(sb, KERN_ERR, + ext4_msg(NULL, KERN_ERR, "Cannot specify journal on remount"); - return -1; - } - journal_path = match_strdup(&args[0]); - if (!journal_path) { - ext4_msg(sb, KERN_ERR, "error: could not dup " - "journal device string"); - return -1; + return -EINVAL; } - error = kern_path(journal_path, LOOKUP_FOLLOW, &path); + error = fs_lookup_param(fc, param, 1, &path); if (error) { - ext4_msg(sb, KERN_ERR, "error: could not find " - "journal device path: error %d", error); - kfree(journal_path); - return -1; + ext4_msg(NULL, KERN_ERR, "error: could not find " + "journal device path"); + return -EINVAL; } journal_inode = d_inode(path.dentry); - if (!S_ISBLK(journal_inode->i_mode)) { - ext4_msg(sb, KERN_ERR, "error: journal path %s " - "is not a block device", journal_path); - path_put(&path); - kfree(journal_path); - return -1; - } - - parsed_opts->journal_devnum = new_encode_dev(journal_inode->i_rdev); + ctx->journal_devnum = new_encode_dev(journal_inode->i_rdev); + ctx->spec |= EXT4_SPEC_JOURNAL_DEV; path_put(&path); - kfree(journal_path); - } else if (token == Opt_journal_ioprio) { - if (arg > 7) { - ext4_msg(sb, KERN_ERR, "Invalid journal IO priority" + return 0; + } + case Opt_journal_ioprio: + if (result.uint_32 > 7) { + ext4_msg(NULL, KERN_ERR, "Invalid journal IO priority" " (must be 0-7)"); - return -1; - } - 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], - is_remount); - } else if (m->flags & MOPT_DATAJ) { - if (is_remount) { - if (!sbi->s_journal) - ext4_msg(sb, KERN_WARNING, "Remounting file system with no journal so ignoring journalled data option"); - else if (test_opt(sb, DATA_FLAGS) != m->mount_opt) { - ext4_msg(sb, KERN_ERR, - "Cannot change data mode on remount"); - return -1; - } - } else { - clear_opt(sb, DATA_FLAGS); - sbi->s_mount_opt |= m->mount_opt; - } -#ifdef CONFIG_QUOTA - } else if (m->flags & MOPT_QFMT) { - if (sb_any_quota_loaded(sb) && - sbi->s_jquota_fmt != m->mount_opt) { - ext4_msg(sb, KERN_ERR, "Cannot change journaled " - "quota options when quota turned on"); - return -1; - } - if (ext4_has_feature_quota(sb)) { - ext4_msg(sb, KERN_INFO, - "Quota format mount options ignored " - "when QUOTA feature is enabled"); - return 1; + return -EINVAL; } - sbi->s_jquota_fmt = m->mount_opt; -#endif - } else if (token == Opt_dax || token == Opt_dax_always || - token == Opt_dax_inode || token == Opt_dax_never) { + ctx->journal_ioprio = + IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, result.uint_32); + ctx->spec |= EXT4_SPEC_JOURNAL_IOPRIO; + return 0; + case Opt_test_dummy_encryption: + return ext4_parse_test_dummy_encryption(param, ctx); + case Opt_dax: + case Opt_dax_type: #ifdef CONFIG_FS_DAX - switch (token) { + { + int type = (token == Opt_dax) ? + Opt_dax : result.uint_32; + + switch (type) { case Opt_dax: case Opt_dax_always: - if (is_remount && - (!(sbi->s_mount_opt & EXT4_MOUNT_DAX_ALWAYS) || - (sbi->s_mount_opt2 & EXT4_MOUNT2_DAX_NEVER))) { - fail_dax_change_remount: - ext4_msg(sb, KERN_ERR, "can't change " - "dax mount option while remounting"); - return -1; - } - if (is_remount && - (test_opt(sb, DATA_FLAGS) == - EXT4_MOUNT_JOURNAL_DATA)) { - ext4_msg(sb, KERN_ERR, "can't mount with " - "both data=journal and dax"); - return -1; - } - ext4_msg(sb, KERN_WARNING, - "DAX enabled. Warning: EXPERIMENTAL, use at your own risk"); - sbi->s_mount_opt |= EXT4_MOUNT_DAX_ALWAYS; - sbi->s_mount_opt2 &= ~EXT4_MOUNT2_DAX_NEVER; + ctx_set_mount_opt(ctx, EXT4_MOUNT_DAX_ALWAYS); + ctx_clear_mount_opt2(ctx, EXT4_MOUNT2_DAX_NEVER); break; case Opt_dax_never: - if (is_remount && - (!(sbi->s_mount_opt2 & EXT4_MOUNT2_DAX_NEVER) || - (sbi->s_mount_opt & EXT4_MOUNT_DAX_ALWAYS))) - goto fail_dax_change_remount; - sbi->s_mount_opt2 |= EXT4_MOUNT2_DAX_NEVER; - sbi->s_mount_opt &= ~EXT4_MOUNT_DAX_ALWAYS; + ctx_set_mount_opt2(ctx, EXT4_MOUNT2_DAX_NEVER); + ctx_clear_mount_opt(ctx, EXT4_MOUNT_DAX_ALWAYS); break; case Opt_dax_inode: - if (is_remount && - ((sbi->s_mount_opt & EXT4_MOUNT_DAX_ALWAYS) || - (sbi->s_mount_opt2 & EXT4_MOUNT2_DAX_NEVER) || - !(sbi->s_mount_opt2 & EXT4_MOUNT2_DAX_INODE))) - goto fail_dax_change_remount; - sbi->s_mount_opt &= ~EXT4_MOUNT_DAX_ALWAYS; - sbi->s_mount_opt2 &= ~EXT4_MOUNT2_DAX_NEVER; + ctx_clear_mount_opt(ctx, EXT4_MOUNT_DAX_ALWAYS); + ctx_clear_mount_opt2(ctx, EXT4_MOUNT2_DAX_NEVER); /* Strictly for printing options */ - sbi->s_mount_opt2 |= EXT4_MOUNT2_DAX_INODE; + ctx_set_mount_opt2(ctx, EXT4_MOUNT2_DAX_INODE); break; } + return 0; + } #else - ext4_msg(sb, KERN_INFO, "dax option not supported"); - sbi->s_mount_opt2 |= EXT4_MOUNT2_DAX_NEVER; - sbi->s_mount_opt &= ~EXT4_MOUNT_DAX_ALWAYS; - return -1; + ext4_msg(NULL, KERN_INFO, "dax option not supported"); + return -EINVAL; #endif - } else if (token == Opt_data_err_abort) { - 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, + case Opt_data_err: + if (result.uint_32 == Opt_data_err_abort) + ctx_set_mount_opt(ctx, m->mount_opt); + else if (result.uint_32 == Opt_data_err_ignore) + ctx_clear_mount_opt(ctx, m->mount_opt); + return 0; + case Opt_mb_optimize_scan: + if (result.int_32 == 1) { + ctx_set_mount_opt2(ctx, EXT4_MOUNT2_MB_OPTIMIZE_SCAN); + ctx->spec |= EXT4_SPEC_mb_optimize_scan; + } else if (result.int_32 == 0) { + ctx_clear_mount_opt2(ctx, EXT4_MOUNT2_MB_OPTIMIZE_SCAN); + ctx->spec |= EXT4_SPEC_mb_optimize_scan; + } else { + ext4_msg(NULL, KERN_WARNING, "mb_optimize_scan should be set to 0 or 1."); - return -1; + return -EINVAL; } - parsed_opts->mb_optimize_scan = arg; - } else { - if (!args->from) - arg = 1; + return 0; + } + + /* + * At this point we should only be getting options requiring MOPT_SET, + * or MOPT_CLEAR. Anything else is a bug + */ + if (m->token == Opt_err) { + ext4_msg(NULL, KERN_WARNING, "buggy handling of option %s", + param->key); + WARN_ON(1); + return -EINVAL; + } + + else { + unsigned int set = 0; + + if ((param->type == fs_value_is_flag) || + result.uint_32 > 0) + set = 1; + if (m->flags & MOPT_CLEAR) - arg = !arg; + set = !set; else if (unlikely(!(m->flags & MOPT_SET))) { - ext4_msg(sb, KERN_WARNING, - "buggy handling of option %s", opt); + ext4_msg(NULL, KERN_WARNING, + "buggy handling of option %s", + param->key); WARN_ON(1); - return -1; + return -EINVAL; } if (m->flags & MOPT_2) { - if (arg != 0) - sbi->s_mount_opt2 |= m->mount_opt; + if (set != 0) + ctx_set_mount_opt2(ctx, m->mount_opt); else - sbi->s_mount_opt2 &= ~m->mount_opt; + ctx_clear_mount_opt2(ctx, m->mount_opt); } else { - if (arg != 0) - sbi->s_mount_opt |= m->mount_opt; + if (set != 0) + ctx_set_mount_opt(ctx, m->mount_opt); else - sbi->s_mount_opt &= ~m->mount_opt; + ctx_clear_mount_opt(ctx, m->mount_opt); } } - return 1; + + return 0; } -static int parse_options(char *options, struct super_block *sb, - struct ext4_parsed_options *ret_opts, - int is_remount) +static int parse_options(struct fs_context *fc, char *options) { - struct ext4_sb_info __maybe_unused *sbi = EXT4_SB(sb); - char *p, __maybe_unused *usr_qf_name, __maybe_unused *grp_qf_name; - substring_t args[MAX_OPT_ARGS]; - int token; + struct fs_parameter param; + int ret; + char *key; if (!options) - return 1; + return 0; - while ((p = strsep(&options, ",")) != NULL) { - if (!*p) - continue; - /* - * Initialize args struct so we know whether arg was - * found; some options take optional arguments. - */ - args[0].to = args[0].from = NULL; - token = match_token(p, tokens, args); - if (handle_mount_opt(sb, p, token, args, ret_opts, - is_remount) < 0) - return 0; + while ((key = strsep(&options, ",")) != NULL) { + if (*key) { + size_t v_len = 0; + char *value = strchr(key, '='); + + param.type = fs_value_is_flag; + param.string = NULL; + + if (value) { + if (value == key) + continue; + + *value++ = 0; + v_len = strlen(value); + param.string = kmemdup_nul(value, v_len, + GFP_KERNEL); + if (!param.string) + return -ENOMEM; + param.type = fs_value_is_string; + } + + param.key = key; + param.size = v_len; + + ret = ext4_parse_param(fc, ¶m); + if (param.string) + kfree(param.string); + if (ret < 0) + return ret; + } + } + + ret = ext4_validate_options(fc); + if (ret < 0) + return ret; + + return 0; +} + +static int parse_apply_sb_mount_options(struct super_block *sb, + struct ext4_fs_context *m_ctx) +{ + struct ext4_sb_info *sbi = EXT4_SB(sb); + char *s_mount_opts = NULL; + struct ext4_fs_context *s_ctx = NULL; + struct fs_context *fc = NULL; + int ret = -ENOMEM; + + if (!sbi->s_es->s_mount_opts[0]) + return 0; + + s_mount_opts = kstrndup(sbi->s_es->s_mount_opts, + sizeof(sbi->s_es->s_mount_opts), + GFP_KERNEL); + if (!s_mount_opts) + return ret; + + fc = kzalloc(sizeof(struct fs_context), GFP_KERNEL); + if (!fc) + goto out_free; + + s_ctx = kzalloc(sizeof(struct ext4_fs_context), GFP_KERNEL); + if (!s_ctx) + goto out_free; + + fc->fs_private = s_ctx; + fc->s_fs_info = sbi; + + ret = parse_options(fc, s_mount_opts); + if (ret < 0) + goto parse_failed; + + ret = ext4_check_opt_consistency(fc, sb); + if (ret < 0) { +parse_failed: + ext4_msg(sb, KERN_WARNING, + "failed to parse options in superblock: %s", + s_mount_opts); + ret = 0; + goto out_free; + } + + if (s_ctx->spec & EXT4_SPEC_JOURNAL_DEV) + m_ctx->journal_devnum = s_ctx->journal_devnum; + if (s_ctx->spec & EXT4_SPEC_JOURNAL_IOPRIO) + m_ctx->journal_ioprio = s_ctx->journal_ioprio; + + ext4_apply_options(fc, sb); + ret = 0; + +out_free: + if (fc) { + ext4_fc_free(fc); + kfree(fc); } + kfree(s_mount_opts); + return ret; +} + +static void ext4_apply_quota_options(struct fs_context *fc, + struct super_block *sb) +{ #ifdef CONFIG_QUOTA + bool quota_feature = ext4_has_feature_quota(sb); + struct ext4_fs_context *ctx = fc->fs_private; + struct ext4_sb_info *sbi = EXT4_SB(sb); + char *qname; + int i; + + if (quota_feature) + return; + + if (ctx->spec & EXT4_SPEC_JQUOTA) { + for (i = 0; i < EXT4_MAXQUOTAS; i++) { + if (!(ctx->qname_spec & (1 << i))) + continue; + + qname = ctx->s_qf_names[i]; /* May be NULL */ + if (qname) + set_opt(sb, QUOTA); + ctx->s_qf_names[i] = NULL; + qname = rcu_replace_pointer(sbi->s_qf_names[i], qname, + lockdep_is_held(&sb->s_umount)); + if (qname) + kfree_rcu(qname); + } + } + + if (ctx->spec & EXT4_SPEC_JQFMT) + sbi->s_jquota_fmt = ctx->s_jquota_fmt; +#endif +} + +/* + * Check quota settings consistency. + */ +static int ext4_check_quota_consistency(struct fs_context *fc, + struct super_block *sb) +{ +#ifdef CONFIG_QUOTA + struct ext4_fs_context *ctx = fc->fs_private; + struct ext4_sb_info *sbi = EXT4_SB(sb); + bool quota_feature = ext4_has_feature_quota(sb); + bool quota_loaded = sb_any_quota_loaded(sb); + bool usr_qf_name, grp_qf_name, usrquota, grpquota; + int quota_flags, i; + /* * We do the test below only for project quotas. 'usrquota' and * 'grpquota' mount options are allowed even without quota feature * to support legacy quotas in quota files. */ - if (test_opt(sb, PRJQUOTA) && !ext4_has_feature_project(sb)) { - ext4_msg(sb, KERN_ERR, "Project quota feature not enabled. " + if (ctx_test_mount_opt(ctx, EXT4_MOUNT_PRJQUOTA) && + !ext4_has_feature_project(sb)) { + ext4_msg(NULL, KERN_ERR, "Project quota feature not enabled. " "Cannot enable project quota enforcement."); - return 0; + return -EINVAL; } - usr_qf_name = get_qf_name(sb, sbi, USRQUOTA); - grp_qf_name = get_qf_name(sb, sbi, GRPQUOTA); - if (usr_qf_name || grp_qf_name) { - if (test_opt(sb, USRQUOTA) && usr_qf_name) - clear_opt(sb, USRQUOTA); - if (test_opt(sb, GRPQUOTA) && grp_qf_name) - clear_opt(sb, GRPQUOTA); + quota_flags = EXT4_MOUNT_QUOTA | EXT4_MOUNT_USRQUOTA | + EXT4_MOUNT_GRPQUOTA | EXT4_MOUNT_PRJQUOTA; + if (quota_loaded && + ctx->mask_s_mount_opt & quota_flags && + !ctx_test_mount_opt(ctx, quota_flags)) + goto err_quota_change; + + if (ctx->spec & EXT4_SPEC_JQUOTA) { + + for (i = 0; i < EXT4_MAXQUOTAS; i++) { + if (!(ctx->qname_spec & (1 << i))) + continue; + + if (quota_loaded && + !!sbi->s_qf_names[i] != !!ctx->s_qf_names[i]) + goto err_jquota_change; - if (test_opt(sb, GRPQUOTA) || test_opt(sb, USRQUOTA)) { - ext4_msg(sb, KERN_ERR, "old and new quota " - "format mixing"); + if (sbi->s_qf_names[i] && ctx->s_qf_names[i] && + strcmp(get_qf_name(sb, sbi, i), + ctx->s_qf_names[i]) != 0) + goto err_jquota_specified; + } + + if (quota_feature) { + ext4_msg(NULL, KERN_INFO, + "Journaled quota options ignored when " + "QUOTA feature is enabled"); return 0; } + } - if (!sbi->s_jquota_fmt) { - ext4_msg(sb, KERN_ERR, "journaled quota format " - "not specified"); + if (ctx->spec & EXT4_SPEC_JQFMT) { + if (sbi->s_jquota_fmt != ctx->s_jquota_fmt && quota_loaded) + goto err_jquota_change; + if (quota_feature) { + ext4_msg(NULL, KERN_INFO, "Quota format mount options " + "ignored when QUOTA feature is enabled"); return 0; } } + + /* Make sure we don't mix old and new quota format */ + usr_qf_name = (get_qf_name(sb, sbi, USRQUOTA) || + ctx->s_qf_names[USRQUOTA]); + grp_qf_name = (get_qf_name(sb, sbi, GRPQUOTA) || + ctx->s_qf_names[GRPQUOTA]); + + usrquota = (ctx_test_mount_opt(ctx, EXT4_MOUNT_USRQUOTA) || + test_opt(sb, USRQUOTA)); + + grpquota = (ctx_test_mount_opt(ctx, EXT4_MOUNT_GRPQUOTA) || + test_opt(sb, GRPQUOTA)); + + if (usr_qf_name) { + ctx_clear_mount_opt(ctx, EXT4_MOUNT_USRQUOTA); + usrquota = false; + } + if (grp_qf_name) { + ctx_clear_mount_opt(ctx, EXT4_MOUNT_GRPQUOTA); + grpquota = false; + } + + if (usr_qf_name || grp_qf_name) { + if (usrquota || grpquota) { + ext4_msg(NULL, KERN_ERR, "old and new quota " + "format mixing"); + return -EINVAL; + } + + if (!(ctx->spec & EXT4_SPEC_JQFMT || sbi->s_jquota_fmt)) { + ext4_msg(NULL, KERN_ERR, "journaled quota format " + "not specified"); + return -EINVAL; + } + } + + return 0; + +err_quota_change: + ext4_msg(NULL, KERN_ERR, + "Cannot change quota options when quota turned on"); + return -EINVAL; +err_jquota_change: + ext4_msg(NULL, KERN_ERR, "Cannot change journaled quota " + "options when quota turned on"); + return -EINVAL; +err_jquota_specified: + ext4_msg(NULL, KERN_ERR, "%s quota file already specified", + QTYPE2NAME(i)); + return -EINVAL; +#else + return 0; #endif - if (test_opt(sb, DIOREAD_NOLOCK)) { +} + +static int ext4_check_test_dummy_encryption(const struct fs_context *fc, + struct super_block *sb) +{ + const struct ext4_fs_context *ctx = fc->fs_private; + const struct ext4_sb_info *sbi = EXT4_SB(sb); + int err; + + if (!fscrypt_is_dummy_policy_set(&ctx->dummy_enc_policy)) + return 0; + + if (!ext4_has_feature_encrypt(sb)) { + ext4_msg(NULL, KERN_WARNING, + "test_dummy_encryption requires encrypt feature"); + return -EINVAL; + } + /* + * This mount option is just for testing, and it's not worthwhile to + * implement the extra complexity (e.g. RCU protection) that would be + * needed to allow it to be set or changed during remount. We do allow + * it to be specified during remount, but only if there is no change. + */ + if (fc->purpose == FS_CONTEXT_FOR_RECONFIGURE) { + if (fscrypt_dummy_policies_equal(&sbi->s_dummy_enc_policy, + &ctx->dummy_enc_policy)) + return 0; + ext4_msg(NULL, KERN_WARNING, + "Can't set or change test_dummy_encryption on remount"); + return -EINVAL; + } + /* Also make sure s_mount_opts didn't contain a conflicting value. */ + if (fscrypt_is_dummy_policy_set(&sbi->s_dummy_enc_policy)) { + if (fscrypt_dummy_policies_equal(&sbi->s_dummy_enc_policy, + &ctx->dummy_enc_policy)) + return 0; + ext4_msg(NULL, KERN_WARNING, + "Conflicting test_dummy_encryption options"); + return -EINVAL; + } + /* + * fscrypt_add_test_dummy_key() technically changes the super_block, so + * technically it should be delayed until ext4_apply_options() like the + * other changes. But since we never get here for remounts (see above), + * and this is the last chance to report errors, we do it here. + */ + err = fscrypt_add_test_dummy_key(sb, &ctx->dummy_enc_policy); + if (err) + ext4_msg(NULL, KERN_WARNING, + "Error adding test dummy encryption key [%d]", err); + return err; +} + +static void ext4_apply_test_dummy_encryption(struct ext4_fs_context *ctx, + struct super_block *sb) +{ + if (!fscrypt_is_dummy_policy_set(&ctx->dummy_enc_policy) || + /* if already set, it was already verified to be the same */ + fscrypt_is_dummy_policy_set(&EXT4_SB(sb)->s_dummy_enc_policy)) + return; + EXT4_SB(sb)->s_dummy_enc_policy = ctx->dummy_enc_policy; + memset(&ctx->dummy_enc_policy, 0, sizeof(ctx->dummy_enc_policy)); + ext4_msg(sb, KERN_WARNING, "Test dummy encryption mode enabled"); +} + +static int ext4_check_opt_consistency(struct fs_context *fc, + struct super_block *sb) +{ + struct ext4_fs_context *ctx = fc->fs_private; + struct ext4_sb_info *sbi = fc->s_fs_info; + int is_remount = fc->purpose == FS_CONTEXT_FOR_RECONFIGURE; + int err; + + if ((ctx->opt_flags & MOPT_NO_EXT2) && IS_EXT2_SB(sb)) { + ext4_msg(NULL, KERN_ERR, + "Mount option(s) incompatible with ext2"); + return -EINVAL; + } + if ((ctx->opt_flags & MOPT_NO_EXT3) && IS_EXT3_SB(sb)) { + ext4_msg(NULL, KERN_ERR, + "Mount option(s) incompatible with ext3"); + return -EINVAL; + } + + if (ctx->s_want_extra_isize > + (sbi->s_inode_size - EXT4_GOOD_OLD_INODE_SIZE)) { + ext4_msg(NULL, KERN_ERR, + "Invalid want_extra_isize %d", + ctx->s_want_extra_isize); + return -EINVAL; + } + + if (ctx_test_mount_opt(ctx, EXT4_MOUNT_DIOREAD_NOLOCK)) { int blocksize = BLOCK_SIZE << le32_to_cpu(sbi->s_es->s_log_block_size); if (blocksize < PAGE_SIZE) - ext4_msg(sb, KERN_WARNING, "Warning: mounting with an " + ext4_msg(NULL, KERN_WARNING, "Warning: mounting with an " "experimental mount option 'dioread_nolock' " "for blocksize < PAGE_SIZE"); } + + err = ext4_check_test_dummy_encryption(fc, sb); + if (err) + return err; + + if ((ctx->spec & EXT4_SPEC_DATAJ) && is_remount) { + if (!sbi->s_journal) { + ext4_msg(NULL, KERN_WARNING, + "Remounting file system with no journal " + "so ignoring journalled data option"); + ctx_clear_mount_opt(ctx, EXT4_MOUNT_DATA_FLAGS); + } else if (ctx_test_mount_opt(ctx, EXT4_MOUNT_DATA_FLAGS) != + test_opt(sb, DATA_FLAGS)) { + ext4_msg(NULL, KERN_ERR, "Cannot change data mode " + "on remount"); + return -EINVAL; + } + } + + if (is_remount) { + if (ctx_test_mount_opt(ctx, EXT4_MOUNT_DAX_ALWAYS) && + (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA)) { + ext4_msg(NULL, KERN_ERR, "can't mount with " + "both data=journal and dax"); + return -EINVAL; + } + + if (ctx_test_mount_opt(ctx, EXT4_MOUNT_DAX_ALWAYS) && + (!(sbi->s_mount_opt & EXT4_MOUNT_DAX_ALWAYS) || + (sbi->s_mount_opt2 & EXT4_MOUNT2_DAX_NEVER))) { +fail_dax_change_remount: + ext4_msg(NULL, KERN_ERR, "can't change " + "dax mount option while remounting"); + return -EINVAL; + } else if (ctx_test_mount_opt2(ctx, EXT4_MOUNT2_DAX_NEVER) && + (!(sbi->s_mount_opt2 & EXT4_MOUNT2_DAX_NEVER) || + (sbi->s_mount_opt & EXT4_MOUNT_DAX_ALWAYS))) { + goto fail_dax_change_remount; + } else if (ctx_test_mount_opt2(ctx, EXT4_MOUNT2_DAX_INODE) && + ((sbi->s_mount_opt & EXT4_MOUNT_DAX_ALWAYS) || + (sbi->s_mount_opt2 & EXT4_MOUNT2_DAX_NEVER) || + !(sbi->s_mount_opt2 & EXT4_MOUNT2_DAX_INODE))) { + goto fail_dax_change_remount; + } + } + + return ext4_check_quota_consistency(fc, sb); +} + +static void ext4_apply_options(struct fs_context *fc, struct super_block *sb) +{ + struct ext4_fs_context *ctx = fc->fs_private; + struct ext4_sb_info *sbi = fc->s_fs_info; + + sbi->s_mount_opt &= ~ctx->mask_s_mount_opt; + sbi->s_mount_opt |= ctx->vals_s_mount_opt; + sbi->s_mount_opt2 &= ~ctx->mask_s_mount_opt2; + sbi->s_mount_opt2 |= ctx->vals_s_mount_opt2; + sbi->s_mount_flags &= ~ctx->mask_s_mount_flags; + sbi->s_mount_flags |= ctx->vals_s_mount_flags; + sb->s_flags &= ~ctx->mask_s_flags; + sb->s_flags |= ctx->vals_s_flags; + +#define APPLY(X) ({ if (ctx->spec & EXT4_SPEC_##X) sbi->X = ctx->X; }) + APPLY(s_commit_interval); + APPLY(s_stripe); + APPLY(s_max_batch_time); + APPLY(s_min_batch_time); + APPLY(s_want_extra_isize); + APPLY(s_inode_readahead_blks); + APPLY(s_max_dir_size_kb); + APPLY(s_li_wait_mult); + APPLY(s_resgid); + APPLY(s_resuid); + +#ifdef CONFIG_EXT4_DEBUG + APPLY(s_fc_debug_max_replay); +#endif + + ext4_apply_quota_options(fc, sb); + ext4_apply_test_dummy_encryption(ctx, sb); +} + + +static int ext4_validate_options(struct fs_context *fc) +{ +#ifdef CONFIG_QUOTA + struct ext4_fs_context *ctx = fc->fs_private; + char *usr_qf_name, *grp_qf_name; + + usr_qf_name = ctx->s_qf_names[USRQUOTA]; + grp_qf_name = ctx->s_qf_names[GRPQUOTA]; + + if (usr_qf_name || grp_qf_name) { + if (ctx_test_mount_opt(ctx, EXT4_MOUNT_USRQUOTA) && usr_qf_name) + ctx_clear_mount_opt(ctx, EXT4_MOUNT_USRQUOTA); + + if (ctx_test_mount_opt(ctx, EXT4_MOUNT_GRPQUOTA) && grp_qf_name) + ctx_clear_mount_opt(ctx, EXT4_MOUNT_GRPQUOTA); + + if (ctx_test_mount_opt(ctx, EXT4_MOUNT_USRQUOTA) || + ctx_test_mount_opt(ctx, EXT4_MOUNT_GRPQUOTA)) { + ext4_msg(NULL, KERN_ERR, "old and new quota " + "format mixing"); + return -EINVAL; + } + } +#endif return 1; } @@ -2533,12 +2875,12 @@ static inline void ext4_show_quota_options(struct seq_file *seq, static const char *token2str(int token) { - const struct match_token *t; + const struct fs_parameter_spec *spec; - for (t = tokens; t->token != Opt_err; t++) - if (t->token == token && !strchr(t->pattern, '=')) + for (spec = ext4_param_specs; spec->name != NULL; spec++) + if (spec->opt == token && !spec->type) break; - return t->pattern; + return spec->name; } /* @@ -2564,7 +2906,7 @@ static int _ext4_show_options(struct seq_file *seq, struct super_block *sb, for (m = ext4_mount_opts; m->token != Opt_err; m++) { int want_set = m->flags & MOPT_SET; if (((m->flags & (MOPT_SET|MOPT_CLEAR)) == 0) || - (m->flags & MOPT_CLEAR_ERR) || m->flags & MOPT_SKIP) + m->flags & MOPT_SKIP) continue; if (!nodefs && !(m->mount_opt & (sbi->s_mount_opt ^ def_mount_opt))) continue; /* skip if same as the default */ @@ -2596,8 +2938,6 @@ static int _ext4_show_options(struct seq_file *seq, struct super_block *sb, SEQ_OPTS_PRINT("min_batch_time=%u", sbi->s_min_batch_time); if (nodefs || sbi->s_max_batch_time != EXT4_DEF_MAX_BATCH_TIME) SEQ_OPTS_PRINT("max_batch_time=%u", sbi->s_max_batch_time); - if (sb->s_flags & SB_I_VERSION) - SEQ_OPTS_PUTS("i_version"); if (nodefs || sbi->s_stripe) SEQ_OPTS_PRINT("stripe=%lu", sbi->s_stripe); if (nodefs || EXT4_MOUNT_DATA_FLAGS & @@ -2637,6 +2977,15 @@ static int _ext4_show_options(struct seq_file *seq, struct super_block *sb, } else if (test_opt2(sb, DAX_INODE)) { SEQ_OPTS_PUTS("dax=inode"); } + + if (sbi->s_groups_count >= MB_DEFAULT_LINEAR_SCAN_THRESHOLD && + !test_opt2(sb, MB_OPTIMIZE_SCAN)) { + SEQ_OPTS_PUTS("mb_optimize_scan=0"); + } else if (sbi->s_groups_count < MB_DEFAULT_LINEAR_SCAN_THRESHOLD && + test_opt2(sb, MB_OPTIMIZE_SCAN)) { + SEQ_OPTS_PUTS("mb_optimize_scan=1"); + } + ext4_show_quota_options(seq, sb); return 0; } @@ -2712,8 +3061,6 @@ done: EXT4_BLOCKS_PER_GROUP(sb), EXT4_INODES_PER_GROUP(sb), sbi->s_mount_opt, sbi->s_mount_opt2); - - cleancache_init_fs(sb); return err; } @@ -3034,8 +3381,9 @@ static loff_t ext4_max_size(int blkbits, int has_huge_files) */ static loff_t ext4_max_bitmap_size(int bits, int has_huge_files) { - unsigned long long upper_limit, res = EXT4_NDIR_BLOCKS; + loff_t upper_limit, res = EXT4_NDIR_BLOCKS; int meta_blocks; + unsigned int ppb = 1 << (bits - 2); /* * This is calculated to be the largest file size for a dense, block @@ -3067,27 +3415,42 @@ static loff_t ext4_max_bitmap_size(int bits, int has_huge_files) } + /* Compute how many blocks we can address by block tree */ + res += ppb; + res += ppb * ppb; + res += ((loff_t)ppb) * ppb * ppb; + /* Compute how many metadata blocks are needed */ + meta_blocks = 1; + meta_blocks += 1 + ppb; + meta_blocks += 1 + ppb + ppb * ppb; + /* Does block tree limit file size? */ + if (res + meta_blocks <= upper_limit) + goto check_lfs; + + res = upper_limit; + /* How many metadata blocks are needed for addressing upper_limit? */ + upper_limit -= EXT4_NDIR_BLOCKS; /* indirect blocks */ meta_blocks = 1; + upper_limit -= ppb; /* double indirect blocks */ - meta_blocks += 1 + (1LL << (bits-2)); - /* tripple indirect blocks */ - meta_blocks += 1 + (1LL << (bits-2)) + (1LL << (2*(bits-2))); - - upper_limit -= meta_blocks; - upper_limit <<= bits; - - res += 1LL << (bits-2); - res += 1LL << (2*(bits-2)); - res += 1LL << (3*(bits-2)); + if (upper_limit < ppb * ppb) { + meta_blocks += 1 + DIV_ROUND_UP_ULL(upper_limit, ppb); + res -= meta_blocks; + goto check_lfs; + } + meta_blocks += 1 + ppb; + upper_limit -= ppb * ppb; + /* tripple indirect blocks for the rest */ + meta_blocks += 1 + DIV_ROUND_UP_ULL(upper_limit, ppb) + + DIV_ROUND_UP_ULL(upper_limit, ppb*ppb); + res -= meta_blocks; +check_lfs: res <<= bits; - if (res > upper_limit) - res = upper_limit; - if (res > MAX_LFS_FILESIZE) res = MAX_LFS_FILESIZE; - return (loff_t)res; + return res; } static ext4_fsblk_t descriptor_loc(struct super_block *sb, @@ -3172,7 +3535,7 @@ int ext4_feature_set_ok(struct super_block *sb, int readonly) return 0; } -#ifndef CONFIG_UNICODE +#if !IS_ENABLED(CONFIG_UNICODE) if (ext4_has_feature_casefold(sb)) { ext4_msg(sb, KERN_ERR, "Filesystem with casefold feature cannot be " @@ -3364,12 +3727,13 @@ static struct task_struct *ext4_lazyinit_task; */ static int ext4_lazyinit_thread(void *arg) { - struct ext4_lazy_init *eli = (struct ext4_lazy_init *)arg; + struct ext4_lazy_init *eli = arg; struct list_head *pos, *n; struct ext4_li_request *elr; unsigned long next_wakeup, cur; BUG_ON(NULL == eli); + set_freezable(); cont_thread: while (true) { @@ -3414,8 +3778,7 @@ cont_thread: } if (!progress) { elr->lr_next_sched = jiffies + - (prandom_u32() - % (EXT4_DEF_LI_MAX_START_DELAY * HZ)); + prandom_u32_max(EXT4_DEF_LI_MAX_START_DELAY * HZ); } if (time_before(elr->lr_next_sched, next_wakeup)) next_wakeup = elr->lr_next_sched; @@ -3562,8 +3925,8 @@ static struct ext4_li_request *ext4_li_request_new(struct super_block *sb, * spread the inode table initialization requests * better. */ - elr->lr_next_sched = jiffies + (prandom_u32() % - (EXT4_DEF_LI_MAX_START_DELAY * HZ)); + elr->lr_next_sched = jiffies + prandom_u32_max( + EXT4_DEF_LI_MAX_START_DELAY * HZ); return elr; } @@ -3585,9 +3948,9 @@ int ext4_register_li_request(struct super_block *sb, goto out; } - if (test_opt(sb, NO_PREFETCH_BLOCK_BITMAPS) && - (first_not_zeroed == ngroups || sb_rdonly(sb) || - !test_opt(sb, INIT_INODE_TABLE))) + if (sb_rdonly(sb) || + (test_opt(sb, NO_PREFETCH_BLOCK_BITMAPS) && + (first_not_zeroed == ngroups || !test_opt(sb, INIT_INODE_TABLE)))) goto out; elr = ext4_li_request_new(sb, first_not_zeroed); @@ -3704,9 +4067,11 @@ static int count_overhead(struct super_block *sb, ext4_group_t grp, ext4_fsblk_t first_block, last_block, b; ext4_group_t i, ngroups = ext4_get_groups_count(sb); int s, j, count = 0; + int has_super = ext4_bg_has_super(sb, grp); if (!ext4_has_feature_bigalloc(sb)) - return (ext4_bg_has_super(sb, grp) + ext4_bg_num_gdb(sb, grp) + + return (has_super + ext4_bg_num_gdb(sb, grp) + + (has_super ? le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks) : 0) + sbi->s_itb_per_group + 2); first_block = le32_to_cpu(sbi->s_es->s_first_data_block) + @@ -3876,131 +4241,46 @@ static void ext4_setup_csum_trigger(struct super_block *sb, sbi->s_journal_triggers[type].tr_triggers.t_frozen = trigger; } -static int ext4_fill_super(struct super_block *sb, void *data, int silent) +static void ext4_free_sbi(struct ext4_sb_info *sbi) { - struct dax_device *dax_dev = fs_dax_get_by_bdev(sb->s_bdev); - char *orig_data = kstrdup(data, GFP_KERNEL); - struct buffer_head *bh, **group_desc; - struct ext4_super_block *es = NULL; - struct ext4_sb_info *sbi = kzalloc(sizeof(*sbi), GFP_KERNEL); - struct flex_groups **flex_groups; - ext4_fsblk_t block; - ext4_fsblk_t sb_block = get_sb_block(&data); - ext4_fsblk_t logical_sb_block; - unsigned long offset = 0; - unsigned long def_mount_opts; - struct inode *root; - const char *descr; - int ret = -ENOMEM; - int blocksize, clustersize; - unsigned int db_count; - unsigned int i; - int needs_recovery, has_huge_files; - __u64 blocks_count; - int err = 0; - ext4_group_t first_not_zeroed; - struct ext4_parsed_options parsed_opts; + if (!sbi) + return; - /* 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; + kfree(sbi->s_blockgroup_lock); + fs_put_dax(sbi->s_daxdev, NULL); + kfree(sbi); +} - if ((data && !orig_data) || !sbi) - goto out_free_base; +static struct ext4_sb_info *ext4_alloc_sbi(struct super_block *sb) +{ + struct ext4_sb_info *sbi; + + sbi = kzalloc(sizeof(*sbi), GFP_KERNEL); + if (!sbi) + return NULL; + + sbi->s_daxdev = fs_dax_get_by_bdev(sb->s_bdev, &sbi->s_dax_part_off, + NULL, NULL); - sbi->s_daxdev = dax_dev; sbi->s_blockgroup_lock = kzalloc(sizeof(struct blockgroup_lock), GFP_KERNEL); + if (!sbi->s_blockgroup_lock) - goto out_free_base; + goto err_out; sb->s_fs_info = sbi; sbi->s_sb = sb; - sbi->s_inode_readahead_blks = EXT4_DEF_INODE_READAHEAD_BLKS; - sbi->s_sb_block = sb_block; - sbi->s_sectors_written_start = - part_stat_read(sb->s_bdev, sectors[STAT_WRITE]); - - /* Cleanup superblock name */ - strreplace(sb->s_id, '/', '!'); - - /* -EINVAL is default */ - ret = -EINVAL; - blocksize = sb_min_blocksize(sb, EXT4_MIN_BLOCK_SIZE); - if (!blocksize) { - ext4_msg(sb, KERN_ERR, "unable to set blocksize"); - goto out_fail; - } - - /* - * The ext4 superblock will not be buffer aligned for other than 1kB - * block sizes. We need to calculate the offset from buffer start. - */ - if (blocksize != EXT4_MIN_BLOCK_SIZE) { - logical_sb_block = sb_block * EXT4_MIN_BLOCK_SIZE; - offset = do_div(logical_sb_block, blocksize); - } else { - logical_sb_block = sb_block; - } - - bh = ext4_sb_bread_unmovable(sb, logical_sb_block); - if (IS_ERR(bh)) { - ext4_msg(sb, KERN_ERR, "unable to read superblock"); - ret = PTR_ERR(bh); - goto out_fail; - } - /* - * Note: s_es must be initialized as soon as possible because - * some ext4 macro-instructions depend on its value - */ - es = (struct ext4_super_block *) (bh->b_data + offset); - sbi->s_es = es; - sb->s_magic = le16_to_cpu(es->s_magic); - if (sb->s_magic != EXT4_SUPER_MAGIC) - goto cantfind_ext4; - sbi->s_kbytes_written = le64_to_cpu(es->s_kbytes_written); - - /* Warn if metadata_csum and gdt_csum are both set. */ - if (ext4_has_feature_metadata_csum(sb) && - ext4_has_feature_gdt_csum(sb)) - ext4_warning(sb, "metadata_csum and uninit_bg are " - "redundant flags; please run fsck."); - - /* Check for a known checksum algorithm */ - if (!ext4_verify_csum_type(sb, es)) { - ext4_msg(sb, KERN_ERR, "VFS: Found ext4 filesystem with " - "unknown checksum algorithm."); - silent = 1; - goto cantfind_ext4; - } - ext4_setup_csum_trigger(sb, EXT4_JTR_ORPHAN_FILE, - ext4_orphan_file_block_trigger); - - /* Load the checksum driver */ - sbi->s_chksum_driver = crypto_alloc_shash("crc32c", 0, 0); - if (IS_ERR(sbi->s_chksum_driver)) { - ext4_msg(sb, KERN_ERR, "Cannot load crc32c driver."); - ret = PTR_ERR(sbi->s_chksum_driver); - sbi->s_chksum_driver = NULL; - goto failed_mount; - } - - /* Check superblock checksum */ - if (!ext4_superblock_csum_verify(sb, es)) { - ext4_msg(sb, KERN_ERR, "VFS: Found ext4 filesystem with " - "invalid superblock checksum. Run e2fsck?"); - silent = 1; - ret = -EFSBADCRC; - goto cantfind_ext4; - } + return sbi; +err_out: + fs_put_dax(sbi->s_daxdev, NULL); + kfree(sbi); + return NULL; +} - /* Precompute checksum seed for all metadata */ - if (ext4_has_feature_csum_seed(sb)) - sbi->s_csum_seed = le32_to_cpu(es->s_checksum_seed); - else if (ext4_has_metadata_csum(sb) || ext4_has_feature_ea_inode(sb)) - sbi->s_csum_seed = ext4_chksum(sbi, ~0, es->s_uuid, - sizeof(es->s_uuid)); +static void ext4_set_def_opts(struct super_block *sb, + struct ext4_super_block *es) +{ + unsigned long def_mount_opts; /* Set defaults before we parse the mount options */ def_mount_opts = le32_to_cpu(es->s_default_mount_opts); @@ -4029,9 +4309,9 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) else if ((def_mount_opts & EXT4_DEFM_JMODE) == EXT4_DEFM_JMODE_WBACK) set_opt(sb, WRITEBACK_DATA); - if (le16_to_cpu(sbi->s_es->s_errors) == EXT4_ERRORS_PANIC) + if (le16_to_cpu(es->s_errors) == EXT4_ERRORS_PANIC) set_opt(sb, ERRORS_PANIC); - else if (le16_to_cpu(sbi->s_es->s_errors) == EXT4_ERRORS_CONTINUE) + else if (le16_to_cpu(es->s_errors) == EXT4_ERRORS_CONTINUE) set_opt(sb, ERRORS_CONT); else set_opt(sb, ERRORS_RO); @@ -4040,12 +4320,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) if (def_mount_opts & EXT4_DEFM_DISCARD) set_opt(sb, DISCARD); - sbi->s_resuid = make_kuid(&init_user_ns, le16_to_cpu(es->s_def_resuid)); - sbi->s_resgid = make_kgid(&init_user_ns, le16_to_cpu(es->s_def_resgid)); - sbi->s_commit_interval = JBD2_DEFAULT_MAX_COMMIT_AGE * HZ; - sbi->s_min_batch_time = EXT4_DEF_MIN_BATCH_TIME; - sbi->s_max_batch_time = EXT4_DEF_MAX_BATCH_TIME; - if ((def_mount_opts & EXT4_DEFM_NOBARRIER) == 0) set_opt(sb, BARRIER); @@ -4057,31 +4331,96 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) ((def_mount_opts & EXT4_DEFM_NODELALLOC) == 0)) set_opt(sb, DELALLOC); - /* - * set default s_li_wait_mult for lazyinit, for the case there is - * no mount option specified. - */ - sbi->s_li_wait_mult = EXT4_DEF_LI_WAIT_MULT; + if (sb->s_blocksize == PAGE_SIZE) + set_opt(sb, DIOREAD_NOLOCK); +} - if (le32_to_cpu(es->s_log_block_size) > - (EXT4_MAX_BLOCK_LOG_SIZE - EXT4_MIN_BLOCK_LOG_SIZE)) { - ext4_msg(sb, KERN_ERR, - "Invalid log block size: %u", - le32_to_cpu(es->s_log_block_size)); - goto failed_mount; - } - if (le32_to_cpu(es->s_log_cluster_size) > - (EXT4_MAX_CLUSTER_LOG_SIZE - EXT4_MIN_BLOCK_LOG_SIZE)) { - ext4_msg(sb, KERN_ERR, - "Invalid log cluster size: %u", - le32_to_cpu(es->s_log_cluster_size)); - goto failed_mount; +static int ext4_handle_clustersize(struct super_block *sb) +{ + struct ext4_sb_info *sbi = EXT4_SB(sb); + struct ext4_super_block *es = sbi->s_es; + int clustersize; + + /* Handle clustersize */ + clustersize = BLOCK_SIZE << le32_to_cpu(es->s_log_cluster_size); + if (ext4_has_feature_bigalloc(sb)) { + if (clustersize < sb->s_blocksize) { + ext4_msg(sb, KERN_ERR, + "cluster size (%d) smaller than " + "block size (%lu)", clustersize, sb->s_blocksize); + return -EINVAL; + } + sbi->s_cluster_bits = le32_to_cpu(es->s_log_cluster_size) - + le32_to_cpu(es->s_log_block_size); + sbi->s_clusters_per_group = + le32_to_cpu(es->s_clusters_per_group); + if (sbi->s_clusters_per_group > sb->s_blocksize * 8) { + ext4_msg(sb, KERN_ERR, + "#clusters per group too big: %lu", + sbi->s_clusters_per_group); + return -EINVAL; + } + if (sbi->s_blocks_per_group != + (sbi->s_clusters_per_group * (clustersize / sb->s_blocksize))) { + ext4_msg(sb, KERN_ERR, "blocks per group (%lu) and " + "clusters per group (%lu) inconsistent", + sbi->s_blocks_per_group, + sbi->s_clusters_per_group); + return -EINVAL; + } + } else { + if (clustersize != sb->s_blocksize) { + ext4_msg(sb, KERN_ERR, + "fragment/cluster size (%d) != " + "block size (%lu)", clustersize, sb->s_blocksize); + return -EINVAL; + } + if (sbi->s_blocks_per_group > sb->s_blocksize * 8) { + ext4_msg(sb, KERN_ERR, + "#blocks per group too big: %lu", + sbi->s_blocks_per_group); + return -EINVAL; + } + sbi->s_clusters_per_group = sbi->s_blocks_per_group; + sbi->s_cluster_bits = 0; } + sbi->s_cluster_ratio = clustersize / sb->s_blocksize; - blocksize = EXT4_MIN_BLOCK_SIZE << le32_to_cpu(es->s_log_block_size); + /* Do we have standard group size of clustersize * 8 blocks ? */ + if (sbi->s_blocks_per_group == clustersize << 3) + set_opt2(sb, STD_GROUP_SIZE); - if (blocksize == PAGE_SIZE) - set_opt(sb, DIOREAD_NOLOCK); + return 0; +} + +static void ext4_fast_commit_init(struct super_block *sb) +{ + struct ext4_sb_info *sbi = EXT4_SB(sb); + + /* Initialize fast commit stuff */ + atomic_set(&sbi->s_fc_subtid, 0); + INIT_LIST_HEAD(&sbi->s_fc_q[FC_Q_MAIN]); + INIT_LIST_HEAD(&sbi->s_fc_q[FC_Q_STAGING]); + INIT_LIST_HEAD(&sbi->s_fc_dentry_q[FC_Q_MAIN]); + INIT_LIST_HEAD(&sbi->s_fc_dentry_q[FC_Q_STAGING]); + sbi->s_fc_bytes = 0; + ext4_clear_mount_flag(sb, EXT4_MF_FC_INELIGIBLE); + sbi->s_fc_ineligible_tid = 0; + spin_lock_init(&sbi->s_fc_lock); + memset(&sbi->s_fc_stats, 0, sizeof(sbi->s_fc_stats)); + sbi->s_fc_replay_state.fc_regions = NULL; + sbi->s_fc_replay_state.fc_regions_size = 0; + sbi->s_fc_replay_state.fc_regions_used = 0; + sbi->s_fc_replay_state.fc_regions_valid = 0; + sbi->s_fc_replay_state.fc_modified_inodes = NULL; + sbi->s_fc_replay_state.fc_modified_inodes_size = 0; + sbi->s_fc_replay_state.fc_modified_inodes_used = 0; +} + +static int ext4_inode_info_init(struct super_block *sb, + struct ext4_super_block *es) +{ + struct ext4_sb_info *sbi = EXT4_SB(sb); if (le32_to_cpu(es->s_rev_level) == EXT4_GOOD_OLD_REV) { sbi->s_inode_size = EXT4_GOOD_OLD_INODE_SIZE; @@ -4092,16 +4431,16 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) if (sbi->s_first_ino < EXT4_GOOD_OLD_FIRST_INO) { ext4_msg(sb, KERN_ERR, "invalid first ino: %u", sbi->s_first_ino); - goto failed_mount; + return -EINVAL; } if ((sbi->s_inode_size < EXT4_GOOD_OLD_INODE_SIZE) || (!is_power_of_2(sbi->s_inode_size)) || - (sbi->s_inode_size > blocksize)) { + (sbi->s_inode_size > sb->s_blocksize)) { ext4_msg(sb, KERN_ERR, "unsupported inode size: %d", sbi->s_inode_size); - ext4_msg(sb, KERN_ERR, "blocksize: %d", blocksize); - goto failed_mount; + ext4_msg(sb, KERN_ERR, "blocksize: %lu", sb->s_blocksize); + return -EINVAL; } /* * i_atime_extra is the last extra field available for @@ -4119,6 +4458,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) } sb->s_time_min = EXT4_TIMESTAMP_MIN; } + if (sbi->s_inode_size > EXT4_GOOD_OLD_INODE_SIZE) { sbi->s_want_extra_isize = sizeof(struct ext4_inode) - EXT4_GOOD_OLD_INODE_SIZE; @@ -4130,7 +4470,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) if (v > max) { ext4_msg(sb, KERN_ERR, "bad s_want_extra_isize: %d", v); - goto failed_mount; + return -EINVAL; } if (sbi->s_want_extra_isize < v) sbi->s_want_extra_isize = v; @@ -4139,90 +4479,112 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) if (v > max) { ext4_msg(sb, KERN_ERR, "bad s_min_extra_isize: %d", v); - goto failed_mount; + return -EINVAL; } if (sbi->s_want_extra_isize < v) sbi->s_want_extra_isize = v; } } - if (sbi->s_es->s_mount_opts[0]) { - char *s_mount_opts = kstrndup(sbi->s_es->s_mount_opts, - sizeof(sbi->s_es->s_mount_opts), - GFP_KERNEL); - if (!s_mount_opts) - goto failed_mount; - 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); - } - kfree(s_mount_opts); - } - sbi->s_def_mount_opt = sbi->s_mount_opt; - if (!parse_options((char *) data, sb, &parsed_opts, 0)) - goto failed_mount; + return 0; +} -#ifdef CONFIG_UNICODE - if (ext4_has_feature_casefold(sb) && !sb->s_encoding) { - const struct ext4_sb_encodings *encoding_info; - struct unicode_map *encoding; - __u16 encoding_flags; +#if IS_ENABLED(CONFIG_UNICODE) +static int ext4_encoding_init(struct super_block *sb, struct ext4_super_block *es) +{ + const struct ext4_sb_encodings *encoding_info; + struct unicode_map *encoding; + __u16 encoding_flags = le16_to_cpu(es->s_encoding_flags); - if (ext4_sb_read_encoding(es, &encoding_info, - &encoding_flags)) { - ext4_msg(sb, KERN_ERR, - "Encoding requested by superblock is unknown"); - goto failed_mount; - } + if (!ext4_has_feature_casefold(sb) || sb->s_encoding) + return 0; - encoding = utf8_load(encoding_info->version); - if (IS_ERR(encoding)) { - ext4_msg(sb, KERN_ERR, - "can't mount with superblock charset: %s-%s " - "not supported by the kernel. flags: 0x%x.", - encoding_info->name, encoding_info->version, - encoding_flags); - goto failed_mount; - } - ext4_msg(sb, KERN_INFO,"Using encoding defined by superblock: " - "%s-%s with flags 0x%hx", encoding_info->name, - encoding_info->version?:"\b", encoding_flags); + encoding_info = ext4_sb_read_encoding(es); + if (!encoding_info) { + ext4_msg(sb, KERN_ERR, + "Encoding requested by superblock is unknown"); + return -EINVAL; + } - sb->s_encoding = encoding; - sb->s_encoding_flags = encoding_flags; + encoding = utf8_load(encoding_info->version); + if (IS_ERR(encoding)) { + ext4_msg(sb, KERN_ERR, + "can't mount with superblock charset: %s-%u.%u.%u " + "not supported by the kernel. flags: 0x%x.", + encoding_info->name, + unicode_major(encoding_info->version), + unicode_minor(encoding_info->version), + unicode_rev(encoding_info->version), + encoding_flags); + return -EINVAL; } + ext4_msg(sb, KERN_INFO,"Using encoding defined by superblock: " + "%s-%u.%u.%u with flags 0x%hx", encoding_info->name, + unicode_major(encoding_info->version), + unicode_minor(encoding_info->version), + unicode_rev(encoding_info->version), + encoding_flags); + + sb->s_encoding = encoding; + sb->s_encoding_flags = encoding_flags; + + return 0; +} +#else +static inline int ext4_encoding_init(struct super_block *sb, struct ext4_super_block *es) +{ + return 0; +} #endif - if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) { - printk_once(KERN_WARNING "EXT4-fs: Warning: mounting with data=journal disables delayed allocation, dioread_nolock, O_DIRECT and fast_commit support!\n"); - /* can't mount with both data=journal and dioread_nolock. */ - clear_opt(sb, DIOREAD_NOLOCK); - clear_opt2(sb, JOURNAL_FAST_COMMIT); - if (test_opt2(sb, EXPLICIT_DELALLOC)) { - ext4_msg(sb, KERN_ERR, "can't mount with " - "both data=journal and delalloc"); - goto failed_mount; - } - if (test_opt(sb, DAX_ALWAYS)) { - ext4_msg(sb, KERN_ERR, "can't mount with " - "both data=journal and dax"); - goto failed_mount; - } - if (ext4_has_feature_encrypt(sb)) { - ext4_msg(sb, KERN_WARNING, - "encrypted files will use data=ordered " - "instead of data journaling mode"); - } - if (test_opt(sb, DELALLOC)) - clear_opt(sb, DELALLOC); - } else { - sb->s_iflags |= SB_I_CGROUPWB; +static int ext4_init_metadata_csum(struct super_block *sb, struct ext4_super_block *es) +{ + struct ext4_sb_info *sbi = EXT4_SB(sb); + + /* Warn if metadata_csum and gdt_csum are both set. */ + if (ext4_has_feature_metadata_csum(sb) && + ext4_has_feature_gdt_csum(sb)) + ext4_warning(sb, "metadata_csum and uninit_bg are " + "redundant flags; please run fsck."); + + /* Check for a known checksum algorithm */ + if (!ext4_verify_csum_type(sb, es)) { + ext4_msg(sb, KERN_ERR, "VFS: Found ext4 filesystem with " + "unknown checksum algorithm."); + return -EINVAL; } + ext4_setup_csum_trigger(sb, EXT4_JTR_ORPHAN_FILE, + ext4_orphan_file_block_trigger); - sb->s_flags = (sb->s_flags & ~SB_POSIXACL) | - (test_opt(sb, POSIX_ACL) ? SB_POSIXACL : 0); + /* Load the checksum driver */ + sbi->s_chksum_driver = crypto_alloc_shash("crc32c", 0, 0); + if (IS_ERR(sbi->s_chksum_driver)) { + int ret = PTR_ERR(sbi->s_chksum_driver); + ext4_msg(sb, KERN_ERR, "Cannot load crc32c driver."); + sbi->s_chksum_driver = NULL; + return ret; + } + /* Check superblock checksum */ + if (!ext4_superblock_csum_verify(sb, es)) { + ext4_msg(sb, KERN_ERR, "VFS: Found ext4 filesystem with " + "invalid superblock checksum. Run e2fsck?"); + return -EFSBADCRC; + } + + /* Precompute checksum seed for all metadata */ + if (ext4_has_feature_csum_seed(sb)) + sbi->s_csum_seed = le32_to_cpu(es->s_checksum_seed); + else if (ext4_has_metadata_csum(sb) || ext4_has_feature_ea_inode(sb)) + sbi->s_csum_seed = ext4_chksum(sbi, ~0, es->s_uuid, + sizeof(es->s_uuid)); + return 0; +} + +static int ext4_check_feature_compatibility(struct super_block *sb, + struct ext4_super_block *es, + int silent) +{ if (le32_to_cpu(es->s_rev_level) == EXT4_GOOD_OLD_REV && (ext4_has_compat_features(sb) || ext4_has_ro_compat_features(sb) || @@ -4236,7 +4598,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) if (ext4_has_feature_64bit(sb)) { ext4_msg(sb, KERN_ERR, "The Hurd can't support 64-bit file systems"); - goto failed_mount; + return -EINVAL; } /* @@ -4246,7 +4608,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) if (ext4_has_feature_ea_inode(sb)) { ext4_msg(sb, KERN_ERR, "ea_inode feature is not supported for Hurd"); - goto failed_mount; + return -EINVAL; } } @@ -4260,10 +4622,10 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) * it's actually an ext[34] filesystem. */ if (silent && ext4_feature_set_ok(sb, sb_rdonly(sb))) - goto failed_mount; + return -EINVAL; ext4_msg(sb, KERN_ERR, "couldn't mount as ext2 due " "to feature incompatibilities"); - goto failed_mount; + return -EINVAL; } } @@ -4277,10 +4639,10 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) * it's actually an ext4 filesystem. */ if (silent && ext4_feature_set_ok(sb, sb_rdonly(sb))) - goto failed_mount; + return -EINVAL; ext4_msg(sb, KERN_ERR, "couldn't mount as ext3 due " "to feature incompatibilities"); - goto failed_mount; + return -EINVAL; } } @@ -4290,18 +4652,475 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) * so there is a chance incompat flags are set on a rev 0 filesystem. */ if (!ext4_feature_set_ok(sb, (sb_rdonly(sb)))) + return -EINVAL; + + return 0; +} + +static int ext4_geometry_check(struct super_block *sb, + struct ext4_super_block *es) +{ + struct ext4_sb_info *sbi = EXT4_SB(sb); + __u64 blocks_count; + + /* check blocks count against device size */ + blocks_count = sb_bdev_nr_blocks(sb); + if (blocks_count && ext4_blocks_count(es) > blocks_count) { + ext4_msg(sb, KERN_WARNING, "bad geometry: block count %llu " + "exceeds size of device (%llu blocks)", + ext4_blocks_count(es), blocks_count); + return -EINVAL; + } + + /* + * It makes no sense for the first data block to be beyond the end + * of the filesystem. + */ + if (le32_to_cpu(es->s_first_data_block) >= ext4_blocks_count(es)) { + ext4_msg(sb, KERN_WARNING, "bad geometry: first data " + "block %u is beyond end of filesystem (%llu)", + le32_to_cpu(es->s_first_data_block), + ext4_blocks_count(es)); + return -EINVAL; + } + if ((es->s_first_data_block == 0) && (es->s_log_block_size == 0) && + (sbi->s_cluster_ratio == 1)) { + ext4_msg(sb, KERN_WARNING, "bad geometry: first data " + "block is 0 with a 1k block and cluster size"); + return -EINVAL; + } + + blocks_count = (ext4_blocks_count(es) - + le32_to_cpu(es->s_first_data_block) + + EXT4_BLOCKS_PER_GROUP(sb) - 1); + do_div(blocks_count, EXT4_BLOCKS_PER_GROUP(sb)); + if (blocks_count > ((uint64_t)1<<32) - EXT4_DESC_PER_BLOCK(sb)) { + ext4_msg(sb, KERN_WARNING, "groups count too large: %llu " + "(block count %llu, first data block %u, " + "blocks per group %lu)", blocks_count, + ext4_blocks_count(es), + le32_to_cpu(es->s_first_data_block), + EXT4_BLOCKS_PER_GROUP(sb)); + return -EINVAL; + } + sbi->s_groups_count = blocks_count; + sbi->s_blockfile_groups = min_t(ext4_group_t, sbi->s_groups_count, + (EXT4_MAX_BLOCK_FILE_PHYS / EXT4_BLOCKS_PER_GROUP(sb))); + if (((u64)sbi->s_groups_count * sbi->s_inodes_per_group) != + le32_to_cpu(es->s_inodes_count)) { + ext4_msg(sb, KERN_ERR, "inodes count not valid: %u vs %llu", + le32_to_cpu(es->s_inodes_count), + ((u64)sbi->s_groups_count * sbi->s_inodes_per_group)); + return -EINVAL; + } + + return 0; +} + +static void ext4_group_desc_free(struct ext4_sb_info *sbi) +{ + struct buffer_head **group_desc; + int i; + + rcu_read_lock(); + group_desc = rcu_dereference(sbi->s_group_desc); + for (i = 0; i < sbi->s_gdb_count; i++) + brelse(group_desc[i]); + kvfree(group_desc); + rcu_read_unlock(); +} + +static int ext4_group_desc_init(struct super_block *sb, + struct ext4_super_block *es, + ext4_fsblk_t logical_sb_block, + ext4_group_t *first_not_zeroed) +{ + struct ext4_sb_info *sbi = EXT4_SB(sb); + unsigned int db_count; + ext4_fsblk_t block; + int ret; + int i; + + db_count = (sbi->s_groups_count + EXT4_DESC_PER_BLOCK(sb) - 1) / + EXT4_DESC_PER_BLOCK(sb); + if (ext4_has_feature_meta_bg(sb)) { + if (le32_to_cpu(es->s_first_meta_bg) > db_count) { + ext4_msg(sb, KERN_WARNING, + "first meta block group too large: %u " + "(group descriptor block count %u)", + le32_to_cpu(es->s_first_meta_bg), db_count); + return -EINVAL; + } + } + rcu_assign_pointer(sbi->s_group_desc, + kvmalloc_array(db_count, + sizeof(struct buffer_head *), + GFP_KERNEL)); + if (sbi->s_group_desc == NULL) { + ext4_msg(sb, KERN_ERR, "not enough memory"); + return -ENOMEM; + } + + bgl_lock_init(sbi->s_blockgroup_lock); + + /* Pre-read the descriptors into the buffer cache */ + for (i = 0; i < db_count; i++) { + block = descriptor_loc(sb, logical_sb_block, i); + ext4_sb_breadahead_unmovable(sb, block); + } + + for (i = 0; i < db_count; i++) { + struct buffer_head *bh; + + block = descriptor_loc(sb, logical_sb_block, i); + bh = ext4_sb_bread_unmovable(sb, block); + if (IS_ERR(bh)) { + ext4_msg(sb, KERN_ERR, + "can't read group descriptor %d", i); + sbi->s_gdb_count = i; + ret = PTR_ERR(bh); + goto out; + } + rcu_read_lock(); + rcu_dereference(sbi->s_group_desc)[i] = bh; + rcu_read_unlock(); + } + sbi->s_gdb_count = db_count; + if (!ext4_check_descriptors(sb, logical_sb_block, first_not_zeroed)) { + ext4_msg(sb, KERN_ERR, "group descriptors corrupted!"); + ret = -EFSCORRUPTED; + goto out; + } + return 0; +out: + ext4_group_desc_free(sbi); + return ret; +} + +static int ext4_load_and_init_journal(struct super_block *sb, + struct ext4_super_block *es, + struct ext4_fs_context *ctx) +{ + struct ext4_sb_info *sbi = EXT4_SB(sb); + int err; + + err = ext4_load_journal(sb, es, ctx->journal_devnum); + if (err) + return err; + + if (ext4_has_feature_64bit(sb) && + !jbd2_journal_set_features(EXT4_SB(sb)->s_journal, 0, 0, + JBD2_FEATURE_INCOMPAT_64BIT)) { + ext4_msg(sb, KERN_ERR, "Failed to set 64-bit journal feature"); + goto out; + } + + if (!set_journal_csum_feature_set(sb)) { + ext4_msg(sb, KERN_ERR, "Failed to set journal checksum " + "feature set"); + goto out; + } + + if (test_opt2(sb, JOURNAL_FAST_COMMIT) && + !jbd2_journal_set_features(EXT4_SB(sb)->s_journal, 0, 0, + JBD2_FEATURE_INCOMPAT_FAST_COMMIT)) { + ext4_msg(sb, KERN_ERR, + "Failed to set fast commit journal feature"); + goto out; + } + + /* We have now updated the journal if required, so we can + * validate the data journaling mode. */ + switch (test_opt(sb, DATA_FLAGS)) { + case 0: + /* No mode set, assume a default based on the journal + * capabilities: ORDERED_DATA if the journal can + * cope, else JOURNAL_DATA + */ + if (jbd2_journal_check_available_features + (sbi->s_journal, 0, 0, JBD2_FEATURE_INCOMPAT_REVOKE)) { + set_opt(sb, ORDERED_DATA); + sbi->s_def_mount_opt |= EXT4_MOUNT_ORDERED_DATA; + } else { + set_opt(sb, JOURNAL_DATA); + sbi->s_def_mount_opt |= EXT4_MOUNT_JOURNAL_DATA; + } + break; + + case EXT4_MOUNT_ORDERED_DATA: + case EXT4_MOUNT_WRITEBACK_DATA: + if (!jbd2_journal_check_available_features + (sbi->s_journal, 0, 0, JBD2_FEATURE_INCOMPAT_REVOKE)) { + ext4_msg(sb, KERN_ERR, "Journal does not support " + "requested data journaling mode"); + goto out; + } + break; + default: + break; + } + + if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA && + test_opt(sb, JOURNAL_ASYNC_COMMIT)) { + ext4_msg(sb, KERN_ERR, "can't mount with " + "journal_async_commit in data=ordered mode"); + goto out; + } + + set_task_ioprio(sbi->s_journal->j_task, ctx->journal_ioprio); + + sbi->s_journal->j_submit_inode_data_buffers = + ext4_journal_submit_inode_data_buffers; + sbi->s_journal->j_finish_inode_data_buffers = + ext4_journal_finish_inode_data_buffers; + + return 0; + +out: + /* flush s_error_work before journal destroy. */ + flush_work(&sbi->s_error_work); + jbd2_journal_destroy(sbi->s_journal); + sbi->s_journal = NULL; + return -EINVAL; +} + +static int ext4_journal_data_mode_check(struct super_block *sb) +{ + if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) { + printk_once(KERN_WARNING "EXT4-fs: Warning: mounting with " + "data=journal disables delayed allocation, " + "dioread_nolock, O_DIRECT and fast_commit support!\n"); + /* can't mount with both data=journal and dioread_nolock. */ + clear_opt(sb, DIOREAD_NOLOCK); + clear_opt2(sb, JOURNAL_FAST_COMMIT); + if (test_opt2(sb, EXPLICIT_DELALLOC)) { + ext4_msg(sb, KERN_ERR, "can't mount with " + "both data=journal and delalloc"); + return -EINVAL; + } + if (test_opt(sb, DAX_ALWAYS)) { + ext4_msg(sb, KERN_ERR, "can't mount with " + "both data=journal and dax"); + return -EINVAL; + } + if (ext4_has_feature_encrypt(sb)) { + ext4_msg(sb, KERN_WARNING, + "encrypted files will use data=ordered " + "instead of data journaling mode"); + } + if (test_opt(sb, DELALLOC)) + clear_opt(sb, DELALLOC); + } else { + sb->s_iflags |= SB_I_CGROUPWB; + } + + return 0; +} + +static int ext4_load_super(struct super_block *sb, ext4_fsblk_t *lsb, + int silent) +{ + struct ext4_sb_info *sbi = EXT4_SB(sb); + struct ext4_super_block *es; + ext4_fsblk_t logical_sb_block; + unsigned long offset = 0; + struct buffer_head *bh; + int ret = -EINVAL; + int blocksize; + + blocksize = sb_min_blocksize(sb, EXT4_MIN_BLOCK_SIZE); + if (!blocksize) { + ext4_msg(sb, KERN_ERR, "unable to set blocksize"); + return -EINVAL; + } + + /* + * The ext4 superblock will not be buffer aligned for other than 1kB + * block sizes. We need to calculate the offset from buffer start. + */ + if (blocksize != EXT4_MIN_BLOCK_SIZE) { + logical_sb_block = sbi->s_sb_block * EXT4_MIN_BLOCK_SIZE; + offset = do_div(logical_sb_block, blocksize); + } else { + logical_sb_block = sbi->s_sb_block; + } + + bh = ext4_sb_bread_unmovable(sb, logical_sb_block); + if (IS_ERR(bh)) { + ext4_msg(sb, KERN_ERR, "unable to read superblock"); + return PTR_ERR(bh); + } + /* + * Note: s_es must be initialized as soon as possible because + * some ext4 macro-instructions depend on its value + */ + es = (struct ext4_super_block *) (bh->b_data + offset); + sbi->s_es = es; + sb->s_magic = le16_to_cpu(es->s_magic); + if (sb->s_magic != EXT4_SUPER_MAGIC) { + if (!silent) + ext4_msg(sb, KERN_ERR, "VFS: Can't find ext4 filesystem"); + goto out; + } + + if (le32_to_cpu(es->s_log_block_size) > + (EXT4_MAX_BLOCK_LOG_SIZE - EXT4_MIN_BLOCK_LOG_SIZE)) { + ext4_msg(sb, KERN_ERR, + "Invalid log block size: %u", + le32_to_cpu(es->s_log_block_size)); + goto out; + } + if (le32_to_cpu(es->s_log_cluster_size) > + (EXT4_MAX_CLUSTER_LOG_SIZE - EXT4_MIN_BLOCK_LOG_SIZE)) { + ext4_msg(sb, KERN_ERR, + "Invalid log cluster size: %u", + le32_to_cpu(es->s_log_cluster_size)); + goto out; + } + + blocksize = EXT4_MIN_BLOCK_SIZE << le32_to_cpu(es->s_log_block_size); + + /* + * If the default block size is not the same as the real block size, + * we need to reload it. + */ + if (sb->s_blocksize == blocksize) { + *lsb = logical_sb_block; + sbi->s_sbh = bh; + return 0; + } + + /* + * bh must be released before kill_bdev(), otherwise + * it won't be freed and its page also. kill_bdev() + * is called by sb_set_blocksize(). + */ + brelse(bh); + /* Validate the filesystem blocksize */ + if (!sb_set_blocksize(sb, blocksize)) { + ext4_msg(sb, KERN_ERR, "bad block size %d", + blocksize); + bh = NULL; + goto out; + } + + logical_sb_block = sbi->s_sb_block * EXT4_MIN_BLOCK_SIZE; + offset = do_div(logical_sb_block, blocksize); + bh = ext4_sb_bread_unmovable(sb, logical_sb_block); + if (IS_ERR(bh)) { + ext4_msg(sb, KERN_ERR, "Can't read superblock on 2nd try"); + ret = PTR_ERR(bh); + bh = NULL; + goto out; + } + es = (struct ext4_super_block *)(bh->b_data + offset); + sbi->s_es = es; + if (es->s_magic != cpu_to_le16(EXT4_SUPER_MAGIC)) { + ext4_msg(sb, KERN_ERR, "Magic mismatch, very weird!"); + goto out; + } + *lsb = logical_sb_block; + sbi->s_sbh = bh; + return 0; +out: + brelse(bh); + return ret; +} + +static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb) +{ + struct ext4_super_block *es = NULL; + struct ext4_sb_info *sbi = EXT4_SB(sb); + struct flex_groups **flex_groups; + ext4_fsblk_t block; + ext4_fsblk_t logical_sb_block; + struct inode *root; + int ret = -ENOMEM; + unsigned int i; + int needs_recovery, has_huge_files; + int err = 0; + ext4_group_t first_not_zeroed; + struct ext4_fs_context *ctx = fc->fs_private; + int silent = fc->sb_flags & SB_SILENT; + + /* Set defaults for the variables that will be set during parsing */ + if (!(ctx->spec & EXT4_SPEC_JOURNAL_IOPRIO)) + ctx->journal_ioprio = DEFAULT_JOURNAL_IOPRIO; + + sbi->s_inode_readahead_blks = EXT4_DEF_INODE_READAHEAD_BLKS; + sbi->s_sectors_written_start = + part_stat_read(sb->s_bdev, sectors[STAT_WRITE]); + + /* -EINVAL is default */ + ret = -EINVAL; + err = ext4_load_super(sb, &logical_sb_block, silent); + if (err) + goto out_fail; + + es = sbi->s_es; + sbi->s_kbytes_written = le64_to_cpu(es->s_kbytes_written); + + err = ext4_init_metadata_csum(sb, es); + if (err) + goto failed_mount; + + ext4_set_def_opts(sb, es); + + sbi->s_resuid = make_kuid(&init_user_ns, le16_to_cpu(es->s_def_resuid)); + sbi->s_resgid = make_kgid(&init_user_ns, le16_to_cpu(es->s_def_resgid)); + sbi->s_commit_interval = JBD2_DEFAULT_MAX_COMMIT_AGE * HZ; + sbi->s_min_batch_time = EXT4_DEF_MIN_BATCH_TIME; + sbi->s_max_batch_time = EXT4_DEF_MAX_BATCH_TIME; + + /* + * set default s_li_wait_mult for lazyinit, for the case there is + * no mount option specified. + */ + sbi->s_li_wait_mult = EXT4_DEF_LI_WAIT_MULT; + + if (ext4_inode_info_init(sb, es)) goto failed_mount; - if (le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks) > (blocksize / 4)) { + err = parse_apply_sb_mount_options(sb, ctx); + if (err < 0) + goto failed_mount; + + sbi->s_def_mount_opt = sbi->s_mount_opt; + + err = ext4_check_opt_consistency(fc, sb); + if (err < 0) + goto failed_mount; + + ext4_apply_options(fc, sb); + + if (ext4_encoding_init(sb, es)) + goto failed_mount; + + if (ext4_journal_data_mode_check(sb)) + goto failed_mount; + + sb->s_flags = (sb->s_flags & ~SB_POSIXACL) | + (test_opt(sb, POSIX_ACL) ? SB_POSIXACL : 0); + + /* i_version is always enabled now */ + sb->s_flags |= SB_I_VERSION; + + if (ext4_check_feature_compatibility(sb, es, silent)) + goto failed_mount; + + if (le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks) > (sb->s_blocksize / 4)) { ext4_msg(sb, KERN_ERR, "Number of reserved GDT blocks insanely large: %d", le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks)); goto failed_mount; } - if (dax_supported(dax_dev, sb->s_bdev, blocksize, 0, - bdev_nr_sectors(sb->s_bdev))) - set_bit(EXT4_FLAGS_BDEV_IS_DAX, &sbi->s_ext4_flags); + if (sbi->s_daxdev) { + if (sb->s_blocksize == PAGE_SIZE) + set_bit(EXT4_FLAGS_BDEV_IS_DAX, &sbi->s_ext4_flags); + else + ext4_msg(sb, KERN_ERR, "unsupported blocksize for DAX\n"); + } if (sbi->s_mount_opt & EXT4_MOUNT_DAX_ALWAYS) { if (ext4_has_feature_inline_data(sb)) { @@ -4322,40 +5141,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) goto failed_mount; } - if (sb->s_blocksize != blocksize) { - /* - * bh must be released before kill_bdev(), otherwise - * it won't be freed and its page also. kill_bdev() - * is called by sb_set_blocksize(). - */ - brelse(bh); - /* Validate the filesystem blocksize */ - if (!sb_set_blocksize(sb, blocksize)) { - ext4_msg(sb, KERN_ERR, "bad block size %d", - blocksize); - bh = NULL; - goto failed_mount; - } - - logical_sb_block = sb_block * EXT4_MIN_BLOCK_SIZE; - offset = do_div(logical_sb_block, blocksize); - bh = ext4_sb_bread_unmovable(sb, logical_sb_block); - if (IS_ERR(bh)) { - ext4_msg(sb, KERN_ERR, - "Can't read superblock on 2nd try"); - ret = PTR_ERR(bh); - bh = NULL; - goto failed_mount; - } - es = (struct ext4_super_block *)(bh->b_data + offset); - sbi->s_es = es; - if (es->s_magic != cpu_to_le16(EXT4_SUPER_MAGIC)) { - ext4_msg(sb, KERN_ERR, - "Magic mismatch, very weird!"); - goto failed_mount; - } - } - has_huge_files = ext4_has_feature_huge_file(sb); sbi->s_bitmap_maxbytes = ext4_max_bitmap_size(sb->s_blocksize_bits, has_huge_files); @@ -4377,20 +5162,22 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) sbi->s_blocks_per_group = le32_to_cpu(es->s_blocks_per_group); sbi->s_inodes_per_group = le32_to_cpu(es->s_inodes_per_group); - sbi->s_inodes_per_block = blocksize / EXT4_INODE_SIZE(sb); - if (sbi->s_inodes_per_block == 0) - goto cantfind_ext4; + sbi->s_inodes_per_block = sb->s_blocksize / EXT4_INODE_SIZE(sb); + if (sbi->s_inodes_per_block == 0 || sbi->s_blocks_per_group == 0) { + if (!silent) + ext4_msg(sb, KERN_ERR, "VFS: Can't find ext4 filesystem"); + goto failed_mount; + } if (sbi->s_inodes_per_group < sbi->s_inodes_per_block || - sbi->s_inodes_per_group > blocksize * 8) { + sbi->s_inodes_per_group > sb->s_blocksize * 8) { ext4_msg(sb, KERN_ERR, "invalid inodes per group: %lu\n", sbi->s_inodes_per_group); goto failed_mount; } sbi->s_itb_per_group = sbi->s_inodes_per_group / sbi->s_inodes_per_block; - sbi->s_desc_per_block = blocksize / EXT4_DESC_SIZE(sb); - sbi->s_sbh = bh; - sbi->s_mount_state = le16_to_cpu(es->s_state); + sbi->s_desc_per_block = sb->s_blocksize / EXT4_DESC_SIZE(sb); + sbi->s_mount_state = le16_to_cpu(es->s_state) & ~EXT4_FC_REPLAY; sbi->s_addr_per_block_bits = ilog2(EXT4_ADDR_PER_BLOCK(sb)); sbi->s_desc_per_block_bits = ilog2(EXT4_DESC_PER_BLOCK(sb)); @@ -4415,54 +5202,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) } } - /* Handle clustersize */ - clustersize = BLOCK_SIZE << le32_to_cpu(es->s_log_cluster_size); - if (ext4_has_feature_bigalloc(sb)) { - if (clustersize < blocksize) { - ext4_msg(sb, KERN_ERR, - "cluster size (%d) smaller than " - "block size (%d)", clustersize, blocksize); - goto failed_mount; - } - sbi->s_cluster_bits = le32_to_cpu(es->s_log_cluster_size) - - le32_to_cpu(es->s_log_block_size); - sbi->s_clusters_per_group = - le32_to_cpu(es->s_clusters_per_group); - if (sbi->s_clusters_per_group > blocksize * 8) { - ext4_msg(sb, KERN_ERR, - "#clusters per group too big: %lu", - sbi->s_clusters_per_group); - goto failed_mount; - } - if (sbi->s_blocks_per_group != - (sbi->s_clusters_per_group * (clustersize / blocksize))) { - ext4_msg(sb, KERN_ERR, "blocks per group (%lu) and " - "clusters per group (%lu) inconsistent", - sbi->s_blocks_per_group, - sbi->s_clusters_per_group); - goto failed_mount; - } - } else { - if (clustersize != blocksize) { - ext4_msg(sb, KERN_ERR, - "fragment/cluster size (%d) != " - "block size (%d)", clustersize, blocksize); - goto failed_mount; - } - if (sbi->s_blocks_per_group > blocksize * 8) { - ext4_msg(sb, KERN_ERR, - "#blocks per group too big: %lu", - sbi->s_blocks_per_group); - goto failed_mount; - } - sbi->s_clusters_per_group = sbi->s_blocks_per_group; - sbi->s_cluster_bits = 0; - } - sbi->s_cluster_ratio = clustersize / blocksize; - - /* Do we have standard group size of clustersize * 8 blocks ? */ - if (sbi->s_blocks_per_group == clustersize << 3) - set_opt2(sb, STD_GROUP_SIZE); + if (ext4_handle_clustersize(sb)) + goto failed_mount; /* * Test whether we have more sectors than will fit in sector_t, @@ -4476,111 +5217,12 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) goto failed_mount; } - if (EXT4_BLOCKS_PER_GROUP(sb) == 0) - goto cantfind_ext4; - - /* check blocks count against device size */ - blocks_count = sb_bdev_nr_blocks(sb); - if (blocks_count && ext4_blocks_count(es) > blocks_count) { - ext4_msg(sb, KERN_WARNING, "bad geometry: block count %llu " - "exceeds size of device (%llu blocks)", - ext4_blocks_count(es), blocks_count); + if (ext4_geometry_check(sb, es)) goto failed_mount; - } - /* - * It makes no sense for the first data block to be beyond the end - * of the filesystem. - */ - if (le32_to_cpu(es->s_first_data_block) >= ext4_blocks_count(es)) { - ext4_msg(sb, KERN_WARNING, "bad geometry: first data " - "block %u is beyond end of filesystem (%llu)", - le32_to_cpu(es->s_first_data_block), - ext4_blocks_count(es)); - goto failed_mount; - } - if ((es->s_first_data_block == 0) && (es->s_log_block_size == 0) && - (sbi->s_cluster_ratio == 1)) { - ext4_msg(sb, KERN_WARNING, "bad geometry: first data " - "block is 0 with a 1k block and cluster size"); - goto failed_mount; - } - - blocks_count = (ext4_blocks_count(es) - - le32_to_cpu(es->s_first_data_block) + - EXT4_BLOCKS_PER_GROUP(sb) - 1); - do_div(blocks_count, EXT4_BLOCKS_PER_GROUP(sb)); - if (blocks_count > ((uint64_t)1<<32) - EXT4_DESC_PER_BLOCK(sb)) { - ext4_msg(sb, KERN_WARNING, "groups count too large: %llu " - "(block count %llu, first data block %u, " - "blocks per group %lu)", blocks_count, - ext4_blocks_count(es), - le32_to_cpu(es->s_first_data_block), - EXT4_BLOCKS_PER_GROUP(sb)); - goto failed_mount; - } - sbi->s_groups_count = blocks_count; - sbi->s_blockfile_groups = min_t(ext4_group_t, sbi->s_groups_count, - (EXT4_MAX_BLOCK_FILE_PHYS / EXT4_BLOCKS_PER_GROUP(sb))); - if (((u64)sbi->s_groups_count * sbi->s_inodes_per_group) != - le32_to_cpu(es->s_inodes_count)) { - ext4_msg(sb, KERN_ERR, "inodes count not valid: %u vs %llu", - le32_to_cpu(es->s_inodes_count), - ((u64)sbi->s_groups_count * sbi->s_inodes_per_group)); - ret = -EINVAL; - goto failed_mount; - } - db_count = (sbi->s_groups_count + EXT4_DESC_PER_BLOCK(sb) - 1) / - EXT4_DESC_PER_BLOCK(sb); - if (ext4_has_feature_meta_bg(sb)) { - if (le32_to_cpu(es->s_first_meta_bg) > db_count) { - ext4_msg(sb, KERN_WARNING, - "first meta block group too large: %u " - "(group descriptor block count %u)", - le32_to_cpu(es->s_first_meta_bg), db_count); - goto failed_mount; - } - } - rcu_assign_pointer(sbi->s_group_desc, - kvmalloc_array(db_count, - sizeof(struct buffer_head *), - GFP_KERNEL)); - if (sbi->s_group_desc == NULL) { - ext4_msg(sb, KERN_ERR, "not enough memory"); - ret = -ENOMEM; + err = ext4_group_desc_init(sb, es, logical_sb_block, &first_not_zeroed); + if (err) goto failed_mount; - } - - bgl_lock_init(sbi->s_blockgroup_lock); - - /* Pre-read the descriptors into the buffer cache */ - for (i = 0; i < db_count; i++) { - block = descriptor_loc(sb, logical_sb_block, i); - ext4_sb_breadahead_unmovable(sb, block); - } - - for (i = 0; i < db_count; i++) { - struct buffer_head *bh; - - block = descriptor_loc(sb, logical_sb_block, i); - bh = ext4_sb_bread_unmovable(sb, block); - if (IS_ERR(bh)) { - ext4_msg(sb, KERN_ERR, - "can't read group descriptor %d", i); - db_count = i; - ret = PTR_ERR(bh); - goto failed_mount2; - } - rcu_read_lock(); - rcu_dereference(sbi->s_group_desc)[i] = bh; - rcu_read_unlock(); - } - sbi->s_gdb_count = db_count; - if (!ext4_check_descriptors(sb, logical_sb_block, &first_not_zeroed)) { - ext4_msg(sb, KERN_ERR, "group descriptors corrupted!"); - ret = -EFSCORRUPTED; - goto failed_mount2; - } timer_setup(&sbi->s_err_report, print_daily_error_info, 0); spin_lock_init(&sbi->s_error_lock); @@ -4618,25 +5260,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) INIT_LIST_HEAD(&sbi->s_orphan); /* unlinked but open files */ mutex_init(&sbi->s_orphan_lock); - /* Initialize fast commit stuff */ - atomic_set(&sbi->s_fc_subtid, 0); - atomic_set(&sbi->s_fc_ineligible_updates, 0); - INIT_LIST_HEAD(&sbi->s_fc_q[FC_Q_MAIN]); - INIT_LIST_HEAD(&sbi->s_fc_q[FC_Q_STAGING]); - INIT_LIST_HEAD(&sbi->s_fc_dentry_q[FC_Q_MAIN]); - INIT_LIST_HEAD(&sbi->s_fc_dentry_q[FC_Q_STAGING]); - sbi->s_fc_bytes = 0; - ext4_clear_mount_flag(sb, EXT4_MF_FC_INELIGIBLE); - ext4_clear_mount_flag(sb, EXT4_MF_FC_COMMITTING); - spin_lock_init(&sbi->s_fc_lock); - memset(&sbi->s_fc_stats, 0, sizeof(sbi->s_fc_stats)); - sbi->s_fc_replay_state.fc_regions = NULL; - sbi->s_fc_replay_state.fc_regions_size = 0; - sbi->s_fc_replay_state.fc_regions_used = 0; - sbi->s_fc_replay_state.fc_regions_valid = 0; - sbi->s_fc_replay_state.fc_modified_inodes = NULL; - sbi->s_fc_replay_state.fc_modified_inodes_size = 0; - sbi->s_fc_replay_state.fc_modified_inodes_used = 0; + ext4_fast_commit_init(sb); sb->s_root = NULL; @@ -4653,37 +5277,37 @@ 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, parsed_opts.journal_devnum); + err = ext4_load_and_init_journal(sb, es, ctx); if (err) goto failed_mount3a; } else if (test_opt(sb, NOLOAD) && !sb_rdonly(sb) && ext4_has_feature_journal_needs_recovery(sb)) { ext4_msg(sb, KERN_ERR, "required journal recovery " "suppressed and not mounted read-only"); - goto failed_mount_wq; + goto failed_mount3a; } else { /* Nojournal mode, all journal mount options are illegal */ if (test_opt2(sb, EXPLICIT_JOURNAL_CHECKSUM)) { ext4_msg(sb, KERN_ERR, "can't mount with " "journal_checksum, fs mounted w/o journal"); - goto failed_mount_wq; + goto failed_mount3a; } if (test_opt(sb, JOURNAL_ASYNC_COMMIT)) { ext4_msg(sb, KERN_ERR, "can't mount with " "journal_async_commit, fs mounted w/o journal"); - goto failed_mount_wq; + goto failed_mount3a; } if (sbi->s_commit_interval != JBD2_DEFAULT_MAX_COMMIT_AGE*HZ) { ext4_msg(sb, KERN_ERR, "can't mount with " "commit=%lu, fs mounted w/o journal", sbi->s_commit_interval / HZ); - goto failed_mount_wq; + goto failed_mount3a; } if (EXT4_MOUNT_DATA_FLAGS & (sbi->s_mount_opt ^ sbi->s_def_mount_opt)) { ext4_msg(sb, KERN_ERR, "can't mount with " "data=, fs mounted w/o journal"); - goto failed_mount_wq; + goto failed_mount3a; } sbi->s_def_mount_opt &= ~EXT4_MOUNT_JOURNAL_CHECKSUM; clear_opt(sb, JOURNAL_CHECKSUM); @@ -4691,76 +5315,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) clear_opt2(sb, JOURNAL_FAST_COMMIT); sbi->s_journal = NULL; needs_recovery = 0; - goto no_journal; - } - - if (ext4_has_feature_64bit(sb) && - !jbd2_journal_set_features(EXT4_SB(sb)->s_journal, 0, 0, - JBD2_FEATURE_INCOMPAT_64BIT)) { - ext4_msg(sb, KERN_ERR, "Failed to set 64-bit journal feature"); - goto failed_mount_wq; - } - - if (!set_journal_csum_feature_set(sb)) { - ext4_msg(sb, KERN_ERR, "Failed to set journal checksum " - "feature set"); - goto failed_mount_wq; - } - - if (test_opt2(sb, JOURNAL_FAST_COMMIT) && - !jbd2_journal_set_features(EXT4_SB(sb)->s_journal, 0, 0, - JBD2_FEATURE_INCOMPAT_FAST_COMMIT)) { - ext4_msg(sb, KERN_ERR, - "Failed to set fast commit journal feature"); - goto failed_mount_wq; } - /* We have now updated the journal if required, so we can - * validate the data journaling mode. */ - switch (test_opt(sb, DATA_FLAGS)) { - case 0: - /* No mode set, assume a default based on the journal - * capabilities: ORDERED_DATA if the journal can - * cope, else JOURNAL_DATA - */ - if (jbd2_journal_check_available_features - (sbi->s_journal, 0, 0, JBD2_FEATURE_INCOMPAT_REVOKE)) { - set_opt(sb, ORDERED_DATA); - sbi->s_def_mount_opt |= EXT4_MOUNT_ORDERED_DATA; - } else { - set_opt(sb, JOURNAL_DATA); - sbi->s_def_mount_opt |= EXT4_MOUNT_JOURNAL_DATA; - } - break; - - case EXT4_MOUNT_ORDERED_DATA: - case EXT4_MOUNT_WRITEBACK_DATA: - if (!jbd2_journal_check_available_features - (sbi->s_journal, 0, 0, JBD2_FEATURE_INCOMPAT_REVOKE)) { - ext4_msg(sb, KERN_ERR, "Journal does not support " - "requested data journaling mode"); - goto failed_mount_wq; - } - break; - default: - break; - } - - if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA && - test_opt(sb, JOURNAL_ASYNC_COMMIT)) { - ext4_msg(sb, KERN_ERR, "can't mount with " - "journal_async_commit in data=ordered mode"); - goto failed_mount_wq; - } - - 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; - sbi->s_journal->j_finish_inode_data_buffers = - ext4_journal_finish_inode_data_buffers; - -no_journal: if (!test_opt(sb, NO_MBCACHE)) { sbi->s_ea_block_cache = ext4_xattr_create_cache(); if (!sbi->s_ea_block_cache) { @@ -4779,24 +5335,27 @@ no_journal: } } - if (ext4_has_feature_verity(sb) && blocksize != PAGE_SIZE) { + if (ext4_has_feature_verity(sb) && sb->s_blocksize != PAGE_SIZE) { ext4_msg(sb, KERN_ERR, "Unsupported blocksize for fs-verity"); goto failed_mount_wq; } - if (DUMMY_ENCRYPTION_ENABLED(sbi) && !sb_rdonly(sb) && - !ext4_has_feature_encrypt(sb)) { - ext4_set_feature_encrypt(sb); - ext4_commit_super(sb); - } - /* * Get the # of file system overhead blocks from the * superblock if present. */ - if (es->s_overhead_clusters) - sbi->s_overhead = le32_to_cpu(es->s_overhead_clusters); - else { + sbi->s_overhead = le32_to_cpu(es->s_overhead_clusters); + /* ignore the precalculated value if it is ridiculous */ + if (sbi->s_overhead > ext4_blocks_count(es)) + sbi->s_overhead = 0; + /* + * If the bigalloc feature is not enabled recalculating the + * overhead doesn't take long, so we might as well just redo + * it to make sure we are using the correct value. + */ + if (!ext4_has_feature_bigalloc(sb)) + sbi->s_overhead = 0; + if (sbi->s_overhead == 0) { err = ext4_calculate_overhead(sb); if (err) goto failed_mount_wq; @@ -4865,12 +5424,12 @@ no_journal: * 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); + if (!(ctx->spec & EXT4_SPEC_mb_optimize_scan)) { + if (sbi->s_groups_count >= MB_DEFAULT_LINEAR_SCAN_THRESHOLD) + set_opt2(sb, MB_OPTIMIZE_SCAN); + else + clear_opt2(sb, MB_OPTIMIZE_SCAN); + } err = ext4_mb_init(sb); if (err) { @@ -4898,14 +5457,6 @@ no_journal: err = percpu_counter_init(&sbi->s_freeinodes_counter, freei, GFP_KERNEL); } - /* - * Update the checksum after updating free space/inode - * counters. Otherwise the superblock can have an incorrect - * checksum in the buffer cache until it is written out and - * e2fsprogs programs trying to open a file system immediately - * after it is mounted can fail. - */ - ext4_superblock_csum_set(sb); if (!err) err = percpu_counter_init(&sbi->s_dirs_counter, ext4_count_dirs(sb), GFP_KERNEL); @@ -4963,37 +5514,24 @@ no_journal: EXT4_SB(sb)->s_mount_state |= EXT4_ORPHAN_FS; ext4_orphan_cleanup(sb, es); EXT4_SB(sb)->s_mount_state &= ~EXT4_ORPHAN_FS; + /* + * Update the checksum after updating free space/inode counters and + * ext4_orphan_cleanup. Otherwise the superblock can have an incorrect + * checksum in the buffer cache until it is written out and + * e2fsprogs programs trying to open a file system immediately + * after it is mounted can fail. + */ + ext4_superblock_csum_set(sb); if (needs_recovery) { ext4_msg(sb, KERN_INFO, "recovery complete"); err = ext4_mark_recovery_complete(sb, es); if (err) goto failed_mount9; } - if (EXT4_SB(sb)->s_journal) { - if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) - descr = " journalled data mode"; - else if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA) - descr = " ordered data mode"; - else - descr = " writeback data mode"; - } else - descr = "out journal"; - if (test_opt(sb, DISCARD)) { - struct request_queue *q = bdev_get_queue(sb->s_bdev); - if (!blk_queue_discard(q)) - ext4_msg(sb, KERN_WARNING, - "mounting with \"discard\" option, but " - "the device does not support discard"); - } - - if (___ratelimit(&ext4_mount_msg_ratelimit, "EXT4-fs mount")) - ext4_msg(sb, KERN_INFO, "mounted filesystem with%s. " - "Opts: %.*s%s%s. Quota mode: %s.", descr, - (int) sizeof(sbi->s_es->s_mount_opts), - sbi->s_es->s_mount_opts, - *sbi->s_es->s_mount_opts ? "; " : "", orig_data, - ext4_quota_mode(sb)); + if (test_opt(sb, DISCARD) && !bdev_max_discard_sectors(sb->s_bdev)) + ext4_msg(sb, KERN_WARNING, + "mounting with \"discard\" option, but the device does not support discard"); if (es->s_error_count) mod_timer(&sbi->s_err_report, jiffies + 300*HZ); /* 5 minutes */ @@ -5005,14 +5543,8 @@ no_journal: atomic_set(&sbi->s_warning_count, 0); atomic_set(&sbi->s_msg_count, 0); - kfree(orig_data); return 0; -cantfind_ext4: - if (!silent) - ext4_msg(sb, KERN_ERR, "VFS: Can't find ext4 filesystem"); - goto failed_mount; - failed_mount9: ext4_release_orphan_info(sb); failed_mount8: @@ -5066,18 +5598,12 @@ failed_mount3: flush_work(&sbi->s_error_work); del_timer_sync(&sbi->s_err_report); ext4_stop_mmpd(sbi); -failed_mount2: - rcu_read_lock(); - group_desc = rcu_dereference(sbi->s_group_desc); - for (i = 0; i < db_count; i++) - brelse(group_desc[i]); - kvfree(group_desc); - rcu_read_unlock(); + ext4_group_desc_free(sbi); failed_mount: if (sbi->s_chksum_driver) crypto_free_shash(sbi->s_chksum_driver); -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) utf8_unload(sb->s_encoding); #endif @@ -5087,18 +5613,66 @@ failed_mount: #endif fscrypt_free_dummy_policy(&sbi->s_dummy_enc_policy); /* ext4_blkdev_remove() calls kill_bdev(), release bh before it. */ - brelse(bh); + brelse(sbi->s_sbh); ext4_blkdev_remove(sbi); out_fail: sb->s_fs_info = NULL; - kfree(sbi->s_blockgroup_lock); -out_free_base: - kfree(sbi); - kfree(orig_data); - fs_put_dax(dax_dev); return err ? err : ret; } +static int ext4_fill_super(struct super_block *sb, struct fs_context *fc) +{ + struct ext4_fs_context *ctx = fc->fs_private; + struct ext4_sb_info *sbi; + const char *descr; + int ret; + + sbi = ext4_alloc_sbi(sb); + if (!sbi) + return -ENOMEM; + + fc->s_fs_info = sbi; + + /* Cleanup superblock name */ + strreplace(sb->s_id, '/', '!'); + + sbi->s_sb_block = 1; /* Default super block location */ + if (ctx->spec & EXT4_SPEC_s_sb_block) + sbi->s_sb_block = ctx->s_sb_block; + + ret = __ext4_fill_super(fc, sb); + if (ret < 0) + goto free_sbi; + + if (sbi->s_journal) { + if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) + descr = " journalled data mode"; + else if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA) + descr = " ordered data mode"; + else + descr = " writeback data mode"; + } else + descr = "out journal"; + + if (___ratelimit(&ext4_mount_msg_ratelimit, "EXT4-fs mount")) + ext4_msg(sb, KERN_INFO, "mounted filesystem with%s. " + "Quota mode: %s.", descr, ext4_quota_mode(sb)); + + /* Update the s_overhead_clusters if necessary */ + ext4_update_overhead(sb, false); + return 0; + +free_sbi: + ext4_free_sbi(sbi); + fc->s_fs_info = NULL; + return ret; +} + +static int ext4_get_tree(struct fs_context *fc) +{ + return get_tree_bdev(fc, ext4_fill_super); +} + /* * Setup any per-fs journal parameters now. We'll do this both on * initial mount, once the journal has been initialised but before we've @@ -5147,7 +5721,7 @@ static struct inode *ext4_get_journal_inode(struct super_block *sb, return NULL; } - jbd_debug(2, "Journal inode found at %p: %lld bytes\n", + ext4_debug("Journal inode found at %p: %lld bytes\n", journal_inode, journal_inode->i_size); if (!S_ISREG(journal_inode->i_mode)) { ext4_msg(sb, KERN_ERR, "invalid journal inode"); @@ -5468,7 +6042,6 @@ static void ext4_update_super(struct super_block *sb) static int ext4_commit_super(struct super_block *sb) { struct buffer_head *sbh = EXT4_SB(sb)->s_sbh; - int error = 0; if (!sbh) return -EINVAL; @@ -5477,6 +6050,13 @@ static int ext4_commit_super(struct super_block *sb) ext4_update_super(sb); + lock_buffer(sbh); + /* Buffer got discarded which means block device got invalidated */ + if (!buffer_mapped(sbh)) { + unlock_buffer(sbh); + return -EIO; + } + if (buffer_write_io_error(sbh) || !buffer_uptodate(sbh)) { /* * Oh, dear. A previous attempt to write the @@ -5491,17 +6071,21 @@ static int ext4_commit_super(struct super_block *sb) clear_buffer_write_io_error(sbh); set_buffer_uptodate(sbh); } - BUFFER_TRACE(sbh, "marking dirty"); - mark_buffer_dirty(sbh); - error = __sync_dirty_buffer(sbh, - REQ_SYNC | (test_opt(sb, BARRIER) ? REQ_FUA : 0)); + get_bh(sbh); + /* Clear potential dirty bit if it was journalled update */ + clear_buffer_dirty(sbh); + sbh->b_end_io = end_buffer_write_sync; + submit_bh(REQ_OP_WRITE | REQ_SYNC | + (test_opt(sb, BARRIER) ? REQ_FUA : 0), sbh); + wait_on_buffer(sbh); if (buffer_write_io_error(sbh)) { ext4_msg(sb, KERN_ERR, "I/O error while writing " "superblock"); clear_buffer_write_io_error(sbh); set_buffer_uptodate(sbh); + return -EIO; } - return error; + return 0; } /* @@ -5727,11 +6311,12 @@ struct ext4_mount_options { #endif }; -static int ext4_remount(struct super_block *sb, int *flags, char *data) +static int __ext4_remount(struct fs_context *fc, struct super_block *sb) { + struct ext4_fs_context *ctx = fc->fs_private; struct ext4_super_block *es; struct ext4_sb_info *sbi = EXT4_SB(sb); - unsigned long old_sb_flags, vfs_flags; + unsigned long old_sb_flags; struct ext4_mount_options old_opts; ext4_group_t g; int err = 0; @@ -5740,14 +6325,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) 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; /* Store the original options */ old_sb_flags = sb->s_flags; @@ -5768,29 +6346,22 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) if (!old_opts.s_qf_names[i]) { for (j = 0; j < i; j++) kfree(old_opts.s_qf_names[j]); - kfree(orig_data); return -ENOMEM; } } else old_opts.s_qf_names[i] = NULL; #endif - if (sbi->s_journal && sbi->s_journal->j_task->io_context) - 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 - * either way we need to make sure it matches in both *flags and - * s_flags. Copy those selected flags from *flags to s_flags - */ - vfs_flags = SB_LAZYTIME | SB_I_VERSION; - sb->s_flags = (sb->s_flags & ~vfs_flags) | (*flags & vfs_flags); + if (!(ctx->spec & EXT4_SPEC_JOURNAL_IOPRIO)) { + if (sbi->s_journal && sbi->s_journal->j_task->io_context) + ctx->journal_ioprio = + sbi->s_journal->j_task->io_context->ioprio; + else + ctx->journal_ioprio = DEFAULT_JOURNAL_IOPRIO; - if (!parse_options(data, sb, &parsed_opts, 1)) { - err = -EINVAL; - goto restore_opts; } + ext4_apply_options(fc, sb); + if ((old_opts.s_mount_opt & EXT4_MOUNT_JOURNAL_CHECKSUM) ^ test_opt(sb, JOURNAL_CHECKSUM)) { ext4_msg(sb, KERN_ERR, "changing journal_checksum " @@ -5836,19 +6407,19 @@ 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, parsed_opts.journal_ioprio); + set_task_ioprio(sbi->s_journal->j_task, ctx->journal_ioprio); } /* Flush outstanding errors before changing fs state */ flush_work(&sbi->s_error_work); - if ((bool)(*flags & SB_RDONLY) != sb_rdonly(sb)) { + if ((bool)(fc->sb_flags & SB_RDONLY) != sb_rdonly(sb)) { if (ext4_test_mount_flag(sb, EXT4_MF_FS_ABORTED)) { err = -EROFS; goto restore_opts; } - if (*flags & SB_RDONLY) { + if (fc->sb_flags & SB_RDONLY) { err = sync_filesystem(sb); if (err < 0) goto restore_opts; @@ -5928,7 +6499,8 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) if (err) goto restore_opts; } - sbi->s_mount_state = le16_to_cpu(es->s_state); + sbi->s_mount_state = (le16_to_cpu(es->s_state) & + ~EXT4_FC_REPLAY); err = ext4_setup_super(sb, es, 0); if (err) @@ -5996,16 +6568,6 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) if (!ext4_has_feature_mmp(sb) || sb_rdonly(sb)) ext4_stop_mmpd(sbi); - /* - * Some options can be enabled by ext4 and/or by VFS mount flag - * either way we need to make sure it matches in both *flags and - * s_flags. Copy those selected flags from s_flags to *flags - */ - *flags = (*flags & ~vfs_flags) | (sb->s_flags & vfs_flags); - - ext4_msg(sb, KERN_INFO, "re-mounted. Opts: %s. Quota mode: %s.", - orig_data, ext4_quota_mode(sb)); - kfree(orig_data); return 0; restore_opts: @@ -6031,10 +6593,30 @@ restore_opts: #endif if (!ext4_has_feature_mmp(sb) || sb_rdonly(sb)) ext4_stop_mmpd(sbi); - kfree(orig_data); return err; } +static int ext4_reconfigure(struct fs_context *fc) +{ + struct super_block *sb = fc->root->d_sb; + int ret; + + fc->s_fs_info = EXT4_SB(sb); + + ret = ext4_check_opt_consistency(fc, sb); + if (ret < 0) + return ret; + + ret = __ext4_remount(fc, sb); + if (ret < 0) + return ret; + + ext4_msg(sb, KERN_INFO, "re-mounted. Quota mode: %s.", + ext4_quota_mode(sb)); + + return 0; +} + #ifdef CONFIG_QUOTA static int ext4_statfs_project(struct super_block *sb, kprojid_t projid, struct kstatfs *buf) @@ -6197,7 +6779,7 @@ static int ext4_write_info(struct super_block *sb, int type) handle_t *handle; /* Data block + inode block */ - handle = ext4_journal_start(d_inode(sb->s_root), EXT4_HT_QUOTA, 2); + handle = ext4_journal_start_sb(sb, EXT4_HT_QUOTA, 2); if (IS_ERR(handle)) return PTR_ERR(handle); ret = dquot_commit_info(sb, type); @@ -6275,10 +6857,7 @@ static int ext4_quota_on(struct super_block *sb, int type, int format_id, lockdep_set_quota_inode(path->dentry->d_inode, I_DATA_SEM_QUOTA); err = dquot_quota_on(sb, type, format_id, path); - if (err) { - lockdep_set_quota_inode(path->dentry->d_inode, - I_DATA_SEM_NORMAL); - } else { + if (!err) { struct inode *inode = d_inode(path->dentry); handle_t *handle; @@ -6298,7 +6877,12 @@ static int ext4_quota_on(struct super_block *sb, int type, int format_id, ext4_journal_stop(handle); unlock_inode: inode_unlock(inode); + if (err) + dquot_quota_off(sb, type); } + if (err) + lockdep_set_quota_inode(path->dentry->d_inode, + I_DATA_SEM_NORMAL); return err; } @@ -6361,8 +6945,19 @@ int ext4_enable_quotas(struct super_block *sb) "Failed to enable quota tracking " "(type=%d, err=%d). Please run " "e2fsck to fix.", type, err); - for (type--; type >= 0; type--) + for (type--; type >= 0; type--) { + struct inode *inode; + + inode = sb_dqopt(sb)->files[type]; + if (inode) + inode = igrab(inode); dquot_quota_off(sb, type); + if (inode) { + lockdep_set_quota_inode(inode, + I_DATA_SEM_NORMAL); + iput(inode); + } + } return err; } @@ -6466,7 +7061,7 @@ static ssize_t ext4_quota_write(struct super_block *sb, int type, struct buffer_head *bh; handle_t *handle = journal_current_handle(); - if (EXT4_SB(sb)->s_journal && !handle) { + if (!handle) { ext4_msg(sb, KERN_WARNING, "Quota write (off=%llu, len=%llu)" " cancelled because transaction is not started", (unsigned long long)off, (unsigned long long)len); @@ -6517,12 +7112,6 @@ out: } #endif -static struct dentry *ext4_mount(struct file_system_type *fs_type, int flags, - const char *dev_name, void *data) -{ - return mount_bdev(fs_type, flags, dev_name, data, ext4_fill_super); -} - #if !defined(CONFIG_EXT2_FS) && !defined(CONFIG_EXT2_FS_MODULE) && defined(CONFIG_EXT4_USE_FOR_EXT2) static inline void register_as_ext2(void) { @@ -6580,11 +7169,12 @@ static inline int ext3_feature_set_ok(struct super_block *sb) } static struct file_system_type ext4_fs_type = { - .owner = THIS_MODULE, - .name = "ext4", - .mount = ext4_mount, - .kill_sb = kill_block_super, - .fs_flags = FS_REQUIRES_DEV | FS_ALLOW_IDMAP, + .owner = THIS_MODULE, + .name = "ext4", + .init_fs_context = ext4_init_fs_context, + .parameters = ext4_param_specs, + .kill_sb = kill_block_super, + .fs_flags = FS_REQUIRES_DEV | FS_ALLOW_IDMAP, }; MODULE_ALIAS_FS("ext4"); @@ -6649,6 +7239,7 @@ static int __init ext4_init_fs(void) out: unregister_as_ext2(); unregister_as_ext3(); + ext4_fc_destroy_dentry_cache(); out05: destroy_inodecache(); out1: @@ -6675,6 +7266,7 @@ static void __exit ext4_exit_fs(void) unregister_as_ext2(); unregister_as_ext3(); unregister_filesystem(&ext4_fs_type); + ext4_fc_destroy_dentry_cache(); destroy_inodecache(); ext4_exit_mballoc(); ext4_exit_sysfs(); diff --git a/fs/ext4/symlink.c b/fs/ext4/symlink.c index 69109746e6e2..3d3ed3c38f56 100644 --- a/fs/ext4/symlink.c +++ b/fs/ext4/symlink.c @@ -27,7 +27,7 @@ static const char *ext4_encrypted_get_link(struct dentry *dentry, struct inode *inode, struct delayed_call *done) { - struct page *cpage = NULL; + struct buffer_head *bh = NULL; const void *caddr; unsigned int max_size; const char *paddr; @@ -39,16 +39,19 @@ static const char *ext4_encrypted_get_link(struct dentry *dentry, caddr = EXT4_I(inode)->i_data; max_size = sizeof(EXT4_I(inode)->i_data); } else { - cpage = read_mapping_page(inode->i_mapping, 0, NULL); - if (IS_ERR(cpage)) - return ERR_CAST(cpage); - caddr = page_address(cpage); + bh = ext4_bread(NULL, inode, 0, 0); + if (IS_ERR(bh)) + return ERR_CAST(bh); + if (!bh) { + EXT4_ERROR_INODE(inode, "bad symlink."); + return ERR_PTR(-EFSCORRUPTED); + } + caddr = bh->b_data; max_size = inode->i_sb->s_blocksize; } paddr = fscrypt_get_symlink(inode, caddr, max_size, done); - if (cpage) - put_page(cpage); + brelse(bh); return paddr; } @@ -62,6 +65,53 @@ static int ext4_encrypted_symlink_getattr(struct user_namespace *mnt_userns, return fscrypt_symlink_getattr(path, stat); } +static void ext4_free_link(void *bh) +{ + brelse(bh); +} + +static const char *ext4_get_link(struct dentry *dentry, struct inode *inode, + struct delayed_call *callback) +{ + struct buffer_head *bh; + char *inline_link; + + /* + * Create a new inlined symlink is not supported, just provide a + * method to read the leftovers. + */ + if (ext4_has_inline_data(inode)) { + if (!dentry) + return ERR_PTR(-ECHILD); + + inline_link = ext4_read_inline_link(inode); + if (!IS_ERR(inline_link)) + set_delayed_call(callback, kfree_link, inline_link); + return inline_link; + } + + if (!dentry) { + bh = ext4_getblk(NULL, inode, 0, EXT4_GET_BLOCKS_CACHED_NOWAIT); + if (IS_ERR(bh)) + return ERR_CAST(bh); + if (!bh || !ext4_buffer_uptodate(bh)) + return ERR_PTR(-ECHILD); + } else { + bh = ext4_bread(NULL, inode, 0, 0); + if (IS_ERR(bh)) + return ERR_CAST(bh); + if (!bh) { + EXT4_ERROR_INODE(inode, "bad symlink."); + return ERR_PTR(-EFSCORRUPTED); + } + } + + set_delayed_call(callback, ext4_free_link, bh); + nd_terminate_link(bh->b_data, inode->i_size, + inode->i_sb->s_blocksize - 1); + return bh->b_data; +} + const struct inode_operations ext4_encrypted_symlink_inode_operations = { .get_link = ext4_encrypted_get_link, .setattr = ext4_setattr, @@ -70,7 +120,7 @@ const struct inode_operations ext4_encrypted_symlink_inode_operations = { }; const struct inode_operations ext4_symlink_inode_operations = { - .get_link = page_get_link, + .get_link = ext4_get_link, .setattr = ext4_setattr, .getattr = ext4_getattr, .listxattr = ext4_listxattr, diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c index 2314f7446592..d233c24ea342 100644 --- a/fs/ext4/sysfs.c +++ b/fs/ext4/sysfs.c @@ -63,7 +63,7 @@ static ssize_t session_write_kbytes_show(struct ext4_sb_info *sbi, char *buf) { struct super_block *sb = sbi->s_buddy_cache->i_sb; - return snprintf(buf, PAGE_SIZE, "%lu\n", + return sysfs_emit(buf, "%lu\n", (part_stat_read(sb->s_bdev, sectors[STAT_WRITE]) - sbi->s_sectors_written_start) >> 1); } @@ -72,7 +72,7 @@ static ssize_t lifetime_write_kbytes_show(struct ext4_sb_info *sbi, char *buf) { struct super_block *sb = sbi->s_buddy_cache->i_sb; - return snprintf(buf, PAGE_SIZE, "%llu\n", + return sysfs_emit(buf, "%llu\n", (unsigned long long)(sbi->s_kbytes_written + ((part_stat_read(sb->s_bdev, sectors[STAT_WRITE]) - EXT4_SB(sb)->s_sectors_written_start) >> 1))); @@ -130,8 +130,8 @@ static ssize_t trigger_test_error(struct ext4_sb_info *sbi, static ssize_t journal_task_show(struct ext4_sb_info *sbi, char *buf) { if (!sbi->s_journal) - return snprintf(buf, PAGE_SIZE, "<none>\n"); - return snprintf(buf, PAGE_SIZE, "%d\n", + return sysfs_emit(buf, "<none>\n"); + return sysfs_emit(buf, "%d\n", task_pid_vnr(sbi->s_journal->j_task)); } @@ -245,6 +245,7 @@ EXT4_ATTR(last_error_time, 0444, last_error_time); EXT4_ATTR(journal_task, 0444, journal_task); EXT4_RW_ATTR_SBI_UI(mb_prefetch, s_mb_prefetch); EXT4_RW_ATTR_SBI_UI(mb_prefetch_limit, s_mb_prefetch_limit); +EXT4_RW_ATTR_SBI_UL(last_trim_minblks, s_last_trim_minblks); static unsigned int old_bump_val = 128; EXT4_ATTR_PTR(max_writeback_mb_bump, 0444, pointer_ui, &old_bump_val); @@ -295,6 +296,7 @@ static struct attribute *ext4_attrs[] = { #endif ATTR_LIST(mb_prefetch), ATTR_LIST(mb_prefetch_limit), + ATTR_LIST(last_trim_minblks), NULL, }; ATTRIBUTE_GROUPS(ext4); @@ -307,7 +309,7 @@ EXT4_ATTR_FEATURE(meta_bg_resize); EXT4_ATTR_FEATURE(encryption); EXT4_ATTR_FEATURE(test_dummy_encryption_v2); #endif -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) EXT4_ATTR_FEATURE(casefold); #endif #ifdef CONFIG_FS_VERITY @@ -315,7 +317,7 @@ EXT4_ATTR_FEATURE(verity); #endif EXT4_ATTR_FEATURE(metadata_csum_seed); EXT4_ATTR_FEATURE(fast_commit); -#if defined(CONFIG_UNICODE) && defined(CONFIG_FS_ENCRYPTION) +#if IS_ENABLED(CONFIG_UNICODE) && defined(CONFIG_FS_ENCRYPTION) EXT4_ATTR_FEATURE(encrypted_casefold); #endif @@ -327,7 +329,7 @@ static struct attribute *ext4_feat_attrs[] = { ATTR_LIST(encryption), ATTR_LIST(test_dummy_encryption_v2), #endif -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) ATTR_LIST(casefold), #endif #ifdef CONFIG_FS_VERITY @@ -335,7 +337,7 @@ static struct attribute *ext4_feat_attrs[] = { #endif ATTR_LIST(metadata_csum_seed), ATTR_LIST(fast_commit), -#if defined(CONFIG_UNICODE) && defined(CONFIG_FS_ENCRYPTION) +#if IS_ENABLED(CONFIG_UNICODE) && defined(CONFIG_FS_ENCRYPTION) ATTR_LIST(encrypted_casefold), #endif NULL, @@ -357,7 +359,7 @@ static void *calc_ptr(struct ext4_attr *a, struct ext4_sb_info *sbi) static ssize_t __print_tstamp(char *buf, __le32 lo, __u8 hi) { - return snprintf(buf, PAGE_SIZE, "%lld\n", + return sysfs_emit(buf, "%lld\n", ((time64_t)hi << 32) + le32_to_cpu(lo)); } @@ -374,7 +376,7 @@ static ssize_t ext4_attr_show(struct kobject *kobj, switch (a->attr_id) { case attr_delayed_allocation_blocks: - return snprintf(buf, PAGE_SIZE, "%llu\n", + return sysfs_emit(buf, "%llu\n", (s64) EXT4_C2B(sbi, percpu_counter_sum(&sbi->s_dirtyclusters_counter))); case attr_session_write_kbytes: @@ -382,11 +384,11 @@ static ssize_t ext4_attr_show(struct kobject *kobj, case attr_lifetime_write_kbytes: return lifetime_write_kbytes_show(sbi, buf); case attr_reserved_clusters: - return snprintf(buf, PAGE_SIZE, "%llu\n", + return sysfs_emit(buf, "%llu\n", (unsigned long long) atomic64_read(&sbi->s_resv_clusters)); case attr_sra_exceeded_retry_limit: - return snprintf(buf, PAGE_SIZE, "%llu\n", + return sysfs_emit(buf, "%llu\n", (unsigned long long) percpu_counter_sum(&sbi->s_sra_exceeded_retry_limit)); case attr_inode_readahead: @@ -394,42 +396,42 @@ static ssize_t ext4_attr_show(struct kobject *kobj, if (!ptr) return 0; if (a->attr_ptr == ptr_ext4_super_block_offset) - return snprintf(buf, PAGE_SIZE, "%u\n", + return sysfs_emit(buf, "%u\n", le32_to_cpup(ptr)); else - return snprintf(buf, PAGE_SIZE, "%u\n", + return sysfs_emit(buf, "%u\n", *((unsigned int *) ptr)); case attr_pointer_ul: if (!ptr) return 0; - return snprintf(buf, PAGE_SIZE, "%lu\n", + return sysfs_emit(buf, "%lu\n", *((unsigned long *) ptr)); case attr_pointer_u8: if (!ptr) return 0; - return snprintf(buf, PAGE_SIZE, "%u\n", + return sysfs_emit(buf, "%u\n", *((unsigned char *) ptr)); case attr_pointer_u64: if (!ptr) return 0; if (a->attr_ptr == ptr_ext4_super_block_offset) - return snprintf(buf, PAGE_SIZE, "%llu\n", + return sysfs_emit(buf, "%llu\n", le64_to_cpup(ptr)); else - return snprintf(buf, PAGE_SIZE, "%llu\n", + return sysfs_emit(buf, "%llu\n", *((unsigned long long *) ptr)); case attr_pointer_string: if (!ptr) return 0; - return snprintf(buf, PAGE_SIZE, "%.*s\n", a->attr_size, + return sysfs_emit(buf, "%.*s\n", a->attr_size, (char *) ptr); case attr_pointer_atomic: if (!ptr) return 0; - return snprintf(buf, PAGE_SIZE, "%d\n", + return sysfs_emit(buf, "%d\n", atomic_read((atomic_t *) ptr)); case attr_feature: - return snprintf(buf, PAGE_SIZE, "supported\n"); + return sysfs_emit(buf, "supported\n"); case attr_first_error_time: return print_tstamp(buf, sbi->s_es, s_first_error_time); case attr_last_error_time: diff --git a/fs/ext4/verity.c b/fs/ext4/verity.c index eacbd489e3bf..3c640bd7ecae 100644 --- a/fs/ext4/verity.c +++ b/fs/ext4/verity.c @@ -69,6 +69,9 @@ static int pagecache_read(struct inode *inode, void *buf, size_t count, static int pagecache_write(struct inode *inode, const void *buf, size_t count, loff_t pos) { + struct address_space *mapping = inode->i_mapping; + const struct address_space_operations *aops = mapping->a_ops; + if (pos + count > inode->i_sb->s_maxbytes) return -EFBIG; @@ -79,15 +82,13 @@ static int pagecache_write(struct inode *inode, const void *buf, size_t count, void *fsdata; int res; - res = pagecache_write_begin(NULL, inode->i_mapping, pos, n, 0, - &page, &fsdata); + res = aops->write_begin(NULL, mapping, pos, n, &page, &fsdata); if (res) return res; memcpy_to_page(page, offset_in_page(pos), buf, n); - res = pagecache_write_end(NULL, inode->i_mapping, pos, n, n, - page, fsdata); + res = aops->write_end(NULL, mapping, pos, n, n, page, fsdata); if (res < 0) return res; if (res != n) @@ -297,16 +298,14 @@ static int ext4_get_verity_descriptor_location(struct inode *inode, last_extent = path[path->p_depth].p_ext; if (!last_extent) { EXT4_ERROR_INODE(inode, "verity file has no extents"); - ext4_ext_drop_refs(path); - kfree(path); + ext4_free_ext_path(path); return -EFSCORRUPTED; } end_lblk = le32_to_cpu(last_extent->ee_block) + ext4_ext_get_actual_len(last_extent); desc_size_pos = (u64)end_lblk << inode->i_blkbits; - ext4_ext_drop_refs(path); - kfree(path); + ext4_free_ext_path(path); if (desc_size_pos < sizeof(desc_size_disk)) goto bad; @@ -364,13 +363,14 @@ static struct page *ext4_read_merkle_tree_page(struct inode *inode, pgoff_t index, unsigned long num_ra_pages) { - DEFINE_READAHEAD(ractl, NULL, NULL, inode->i_mapping, index); struct page *page; index += ext4_verity_metadata_pos(inode) >> PAGE_SHIFT; page = find_get_page_flags(inode->i_mapping, index, FGP_ACCESSED); if (!page || !PageUptodate(page)) { + DEFINE_READAHEAD(ractl, NULL, NULL, inode->i_mapping, index); + if (page) put_page(page); else if (num_ra_pages > 1) diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 1e0fc1ed845b..36d6ba7190b6 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -436,6 +436,21 @@ error: return err; } +/* Remove entry from mbcache when EA inode is getting evicted */ +void ext4_evict_ea_inode(struct inode *inode) +{ + struct mb_cache_entry *oe; + + if (!EA_INODE_CACHE(inode)) + return; + /* Wait for entry to get unused so that we can remove it */ + while ((oe = mb_cache_entry_delete_or_get(EA_INODE_CACHE(inode), + ext4_xattr_inode_get_hash(inode), inode->i_ino))) { + mb_cache_entry_wait_unused(oe); + mb_cache_entry_put(EA_INODE_CACHE(inode), oe); + } +} + static int ext4_xattr_inode_verify_hashes(struct inode *ea_inode, struct ext4_xattr_entry *entry, void *buffer, @@ -976,10 +991,8 @@ int __ext4_xattr_set_credits(struct super_block *sb, struct inode *inode, static int ext4_xattr_inode_update_ref(handle_t *handle, struct inode *ea_inode, int ref_change) { - struct mb_cache *ea_inode_cache = EA_INODE_CACHE(ea_inode); struct ext4_iloc iloc; s64 ref_count; - u32 hash; int ret; inode_lock(ea_inode); @@ -1002,14 +1015,6 @@ static int ext4_xattr_inode_update_ref(handle_t *handle, struct inode *ea_inode, set_nlink(ea_inode, 1); ext4_orphan_del(handle, ea_inode); - - if (ea_inode_cache) { - hash = ext4_xattr_inode_get_hash(ea_inode); - mb_cache_entry_create(ea_inode_cache, - GFP_NOFS, hash, - ea_inode->i_ino, - true /* reusable */); - } } } else { WARN_ONCE(ref_count < 0, "EA inode %lu ref_count=%lld", @@ -1022,12 +1027,6 @@ static int ext4_xattr_inode_update_ref(handle_t *handle, struct inode *ea_inode, clear_nlink(ea_inode); ext4_orphan_add(handle, ea_inode); - - if (ea_inode_cache) { - hash = ext4_xattr_inode_get_hash(ea_inode); - mb_cache_entry_delete(ea_inode_cache, hash, - ea_inode->i_ino); - } } } @@ -1237,6 +1236,7 @@ ext4_xattr_release_block(handle_t *handle, struct inode *inode, if (error) goto out; +retry_ref: lock_buffer(bh); hash = le32_to_cpu(BHDR(bh)->h_hash); ref = le32_to_cpu(BHDR(bh)->h_refcount); @@ -1246,9 +1246,18 @@ ext4_xattr_release_block(handle_t *handle, struct inode *inode, * This must happen under buffer lock for * ext4_xattr_block_set() to reliably detect freed block */ - if (ea_block_cache) - mb_cache_entry_delete(ea_block_cache, hash, - bh->b_blocknr); + if (ea_block_cache) { + struct mb_cache_entry *oe; + + oe = mb_cache_entry_delete_or_get(ea_block_cache, hash, + bh->b_blocknr); + if (oe) { + unlock_buffer(bh); + mb_cache_entry_wait_unused(oe); + mb_cache_entry_put(ea_block_cache, oe); + goto retry_ref; + } + } get_bh(bh); unlock_buffer(bh); @@ -1858,6 +1867,8 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode, #define header(x) ((struct ext4_xattr_header *)(x)) if (s->base) { + int offset = (char *)s->here - bs->bh->b_data; + BUFFER_TRACE(bs->bh, "get_write_access"); error = ext4_journal_get_write_access(handle, sb, bs->bh, EXT4_JTR_NONE); @@ -1873,9 +1884,20 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode, * ext4_xattr_block_set() to reliably detect modified * block */ - if (ea_block_cache) - mb_cache_entry_delete(ea_block_cache, hash, - bs->bh->b_blocknr); + if (ea_block_cache) { + struct mb_cache_entry *oe; + + oe = mb_cache_entry_delete_or_get(ea_block_cache, + hash, bs->bh->b_blocknr); + if (oe) { + /* + * Xattr block is getting reused. Leave + * it alone. + */ + mb_cache_entry_put(ea_block_cache, oe); + goto clone_block; + } + } ea_bdebug(bs->bh, "modifying in-place"); error = ext4_xattr_set_entry(i, s, handle, inode, true /* is_block */); @@ -1890,50 +1912,47 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode, if (error) goto cleanup; goto inserted; - } else { - int offset = (char *)s->here - bs->bh->b_data; + } +clone_block: + unlock_buffer(bs->bh); + ea_bdebug(bs->bh, "cloning"); + s->base = kmemdup(BHDR(bs->bh), bs->bh->b_size, GFP_NOFS); + error = -ENOMEM; + if (s->base == NULL) + goto cleanup; + s->first = ENTRY(header(s->base)+1); + header(s->base)->h_refcount = cpu_to_le32(1); + s->here = ENTRY(s->base + offset); + s->end = s->base + bs->bh->b_size; - unlock_buffer(bs->bh); - ea_bdebug(bs->bh, "cloning"); - s->base = kmalloc(bs->bh->b_size, GFP_NOFS); - error = -ENOMEM; - if (s->base == NULL) + /* + * If existing entry points to an xattr inode, we need + * to prevent ext4_xattr_set_entry() from decrementing + * ref count on it because the reference belongs to the + * original block. In this case, make the entry look + * like it has an empty value. + */ + if (!s->not_found && s->here->e_value_inum) { + ea_ino = le32_to_cpu(s->here->e_value_inum); + error = ext4_xattr_inode_iget(inode, ea_ino, + le32_to_cpu(s->here->e_hash), + &tmp_inode); + if (error) goto cleanup; - memcpy(s->base, BHDR(bs->bh), bs->bh->b_size); - s->first = ENTRY(header(s->base)+1); - header(s->base)->h_refcount = cpu_to_le32(1); - s->here = ENTRY(s->base + offset); - s->end = s->base + bs->bh->b_size; - - /* - * If existing entry points to an xattr inode, we need - * to prevent ext4_xattr_set_entry() from decrementing - * ref count on it because the reference belongs to the - * original block. In this case, make the entry look - * like it has an empty value. - */ - if (!s->not_found && s->here->e_value_inum) { - ea_ino = le32_to_cpu(s->here->e_value_inum); - error = ext4_xattr_inode_iget(inode, ea_ino, - le32_to_cpu(s->here->e_hash), - &tmp_inode); - if (error) - goto cleanup; - - if (!ext4_test_inode_state(tmp_inode, - EXT4_STATE_LUSTRE_EA_INODE)) { - /* - * Defer quota free call for previous - * inode until success is guaranteed. - */ - old_ea_inode_quota = le32_to_cpu( - s->here->e_value_size); - } - iput(tmp_inode); - s->here->e_value_inum = 0; - s->here->e_value_size = 0; + if (!ext4_test_inode_state(tmp_inode, + EXT4_STATE_LUSTRE_EA_INODE)) { + /* + * Defer quota free call for previous + * inode until success is guaranteed. + */ + old_ea_inode_quota = le32_to_cpu( + s->here->e_value_size); } + iput(tmp_inode); + + s->here->e_value_inum = 0; + s->here->e_value_size = 0; } } else { /* Allocate a buffer where we construct the new block. */ @@ -2000,18 +2019,13 @@ inserted: lock_buffer(new_bh); /* * We have to be careful about races with - * freeing, rehashing or adding references to - * xattr block. Once we hold buffer lock xattr - * block's state is stable so we can check - * whether the block got freed / rehashed or - * not. Since we unhash mbcache entry under - * buffer lock when freeing / rehashing xattr - * block, checking whether entry is still - * hashed is reliable. Same rules hold for - * e_reusable handling. + * adding references to xattr block. Once we + * hold buffer lock xattr block's state is + * stable so we can check the additional + * reference fits. */ - if (hlist_bl_unhashed(&ce->e_hash_list) || - !ce->e_reusable) { + ref = le32_to_cpu(BHDR(new_bh)->h_refcount) + 1; + if (ref > EXT4_XATTR_REFCOUNT_MAX) { /* * Undo everything and check mbcache * again. @@ -2026,9 +2040,8 @@ inserted: new_bh = NULL; goto inserted; } - ref = le32_to_cpu(BHDR(new_bh)->h_refcount) + 1; BHDR(new_bh)->h_refcount = cpu_to_le32(ref); - if (ref >= EXT4_XATTR_REFCOUNT_MAX) + if (ref == EXT4_XATTR_REFCOUNT_MAX) ce->e_reusable = 0; ea_bdebug(new_bh, "reusing; refcount now=%d", ref); @@ -2176,8 +2189,9 @@ int ext4_xattr_ibody_find(struct inode *inode, struct ext4_xattr_info *i, struct ext4_inode *raw_inode; int error; - if (EXT4_I(inode)->i_extra_isize == 0) + if (!EXT4_INODE_HAS_XATTR_SPACE(inode)) return 0; + raw_inode = ext4_raw_inode(&is->iloc); header = IHDR(inode, raw_inode); is->s.base = is->s.first = IFIRST(header); @@ -2205,8 +2219,9 @@ int ext4_xattr_ibody_set(handle_t *handle, struct inode *inode, struct ext4_xattr_search *s = &is->s; int error; - if (EXT4_I(inode)->i_extra_isize == 0) + if (!EXT4_INODE_HAS_XATTR_SPACE(inode)) return -ENOSPC; + error = ext4_xattr_set_entry(i, s, handle, inode, false /* is_block */); if (error) return error; @@ -2397,6 +2412,7 @@ retry_inode: if (!error) { ext4_xattr_update_super_block(handle, inode->i_sb); inode->i_ctime = current_time(inode); + inode_inc_iversion(inode); if (!value) no_expand = 0; error = ext4_mark_iloc_dirty(handle, inode, &is.iloc); @@ -2408,7 +2424,7 @@ retry_inode: if (IS_SYNC(inode)) ext4_handle_sync(handle); } - ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_XATTR); + ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_XATTR, handle); cleanup: brelse(is.iloc.bh); @@ -2486,7 +2502,7 @@ retry: if (error == 0) error = error2; } - ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_XATTR); + ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_XATTR, NULL); return error; } @@ -2920,7 +2936,7 @@ int ext4_xattr_delete_inode(handle_t *handle, struct inode *inode, error); goto cleanup; } - ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_XATTR); + ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_XATTR, handle); } error = 0; cleanup: diff --git a/fs/ext4/xattr.h b/fs/ext4/xattr.h index 77efb9a627ad..824faf0b15a8 100644 --- a/fs/ext4/xattr.h +++ b/fs/ext4/xattr.h @@ -84,7 +84,7 @@ struct ext4_xattr_entry { /* * The minimum size of EA value when you start storing it in an external inode * size of block - size of header - size of 1 entry - 4 null bytes -*/ + */ #define EXT4_XATTR_MIN_LARGE_EA_SIZE(b) \ ((b) - EXT4_XATTR_LEN(3) - sizeof(struct ext4_xattr_header) - 4) @@ -95,6 +95,19 @@ struct ext4_xattr_entry { #define EXT4_ZERO_XATTR_VALUE ((void *)-1) +/* + * If we want to add an xattr to the inode, we should make sure that + * i_extra_isize is not 0 and that the inode size is not less than + * EXT4_GOOD_OLD_INODE_SIZE + extra_isize + pad. + * EXT4_GOOD_OLD_INODE_SIZE extra_isize header entry pad data + * |--------------------------|------------|------|---------|---|-------| + */ +#define EXT4_INODE_HAS_XATTR_SPACE(inode) \ + ((EXT4_I(inode)->i_extra_isize != 0) && \ + (EXT4_GOOD_OLD_INODE_SIZE + EXT4_I(inode)->i_extra_isize + \ + sizeof(struct ext4_xattr_ibody_header) + EXT4_XATTR_PAD <= \ + EXT4_INODE_SIZE((inode)->i_sb))) + struct ext4_xattr_info { const char *name; const void *value; @@ -178,6 +191,7 @@ extern void ext4_xattr_inode_array_free(struct ext4_xattr_inode_array *array); extern int ext4_expand_extra_isize_ea(struct inode *inode, int new_extra_isize, struct ext4_inode *raw_inode, handle_t *handle); +extern void ext4_evict_ea_inode(struct inode *inode); extern const struct xattr_handler *ext4_xattr_handlers[]; |