diff options
Diffstat (limited to 'fs/ext4')
-rw-r--r-- | fs/ext4/Kconfig | 24 | ||||
-rw-r--r-- | fs/ext4/Makefile | 3 | ||||
-rw-r--r-- | fs/ext4/balloc.c | 5 | ||||
-rw-r--r-- | fs/ext4/block_validity.c | 194 | ||||
-rw-r--r-- | fs/ext4/dir.c | 33 | ||||
-rw-r--r-- | fs/ext4/ext4.h | 205 | ||||
-rw-r--r-- | fs/ext4/ext4_extents.h | 5 | ||||
-rw-r--r-- | fs/ext4/ext4_jbd2.c | 57 | ||||
-rw-r--r-- | fs/ext4/ext4_jbd2.h | 126 | ||||
-rw-r--r-- | fs/ext4/extents.c | 452 | ||||
-rw-r--r-- | fs/ext4/extents_status.c | 521 | ||||
-rw-r--r-- | fs/ext4/extents_status.h | 14 | ||||
-rw-r--r-- | fs/ext4/file.c | 537 | ||||
-rw-r--r-- | fs/ext4/fsync.c | 72 | ||||
-rw-r--r-- | fs/ext4/hash.c | 2 | ||||
-rw-r--r-- | fs/ext4/ialloc.c | 15 | ||||
-rw-r--r-- | fs/ext4/indirect.c | 151 | ||||
-rw-r--r-- | fs/ext4/inline.c | 6 | ||||
-rw-r--r-- | fs/ext4/inode-test.c | 274 | ||||
-rw-r--r-- | fs/ext4/inode.c | 1148 | ||||
-rw-r--r-- | fs/ext4/ioctl.c | 146 | ||||
-rw-r--r-- | fs/ext4/mballoc.c | 4 | ||||
-rw-r--r-- | fs/ext4/migrate.c | 103 | ||||
-rw-r--r-- | fs/ext4/mmp.c | 18 | ||||
-rw-r--r-- | fs/ext4/namei.c | 117 | ||||
-rw-r--r-- | fs/ext4/page-io.c | 186 | ||||
-rw-r--r-- | fs/ext4/readpage.c | 225 | ||||
-rw-r--r-- | fs/ext4/resize.c | 56 | ||||
-rw-r--r-- | fs/ext4/super.c | 351 | ||||
-rw-r--r-- | fs/ext4/sysfs.c | 94 | ||||
-rw-r--r-- | fs/ext4/verity.c | 410 | ||||
-rw-r--r-- | fs/ext4/xattr.c | 100 |
32 files changed, 3800 insertions, 1854 deletions
diff --git a/fs/ext4/Kconfig b/fs/ext4/Kconfig index cbb5ca830e57..2a592e38cdfe 100644 --- a/fs/ext4/Kconfig +++ b/fs/ext4/Kconfig @@ -4,12 +4,7 @@ # kernels after the removal of ext3 driver. config EXT3_FS tristate "The Extended 3 (ext3) filesystem" - # These must match EXT4_FS selects... select EXT4_FS - select JBD2 - select CRC16 - select CRYPTO - select CRYPTO_CRC32C help This config option is here only for backward compatibility. ext3 filesystem is now handled by the ext4 driver. @@ -33,12 +28,12 @@ config EXT3_FS_SECURITY config EXT4_FS tristate "The Extended 4 (ext4) filesystem" - # Please update EXT3_FS selects when changing these select JBD2 select CRC16 select CRYPTO select CRYPTO_CRC32C select FS_IOMAP + select FS_ENCRYPTION_ALGS if FS_ENCRYPTION help This is the next generation of the ext3 filesystem. @@ -106,3 +101,20 @@ config EXT4_DEBUG If you select Y here, then you will be able to turn on debugging with a command such as: echo 1 > /sys/module/ext4/parameters/mballoc_debug + +config EXT4_KUNIT_TESTS + tristate "KUnit tests for ext4" + select EXT4_FS + depends on KUNIT + help + This builds the ext4 KUnit tests. + + KUnit tests run during boot and output the results to the debug log + in TAP format (http://testanything.org/). Only useful for kernel devs + running KUnit test harness and are not for inclusion into a production + build. + + For more information on KUnit and unit tests in general please refer + to the KUnit documentation in Documentation/dev-tools/kunit/. + + If unsure, say N. diff --git a/fs/ext4/Makefile b/fs/ext4/Makefile index 8fdfcd3c3e04..4ccb3c9189d8 100644 --- a/fs/ext4/Makefile +++ b/fs/ext4/Makefile @@ -13,3 +13,6 @@ ext4-y := balloc.o bitmap.o block_validity.o dir.o ext4_jbd2.o extents.o \ ext4-$(CONFIG_EXT4_FS_POSIX_ACL) += acl.o ext4-$(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 diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index 0b202e00d93f..5f993a411251 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -371,7 +371,8 @@ static int ext4_validate_block_bitmap(struct super_block *sb, if (buffer_verified(bh)) goto verified; if (unlikely(!ext4_block_bitmap_csum_verify(sb, block_group, - desc, bh))) { + desc, bh) || + ext4_simulate_fail(sb, EXT4_SIM_BBITMAP_CRC))) { ext4_unlock_group(sb, block_group); ext4_error(sb, "bg %u: bad block bitmap checksum", block_group); ext4_mark_group_bitmap_corrupted(sb, block_group, @@ -505,7 +506,9 @@ int ext4_wait_block_bitmap(struct super_block *sb, ext4_group_t block_group, if (!desc) return -EFSCORRUPTED; wait_on_buffer(bh); + ext4_simulate_fail_bh(sb, bh, EXT4_SIM_BBITMAP_EIO); if (!buffer_uptodate(bh)) { + ext4_set_errno(sb, EIO); ext4_error(sb, "Cannot read block bitmap - " "block_group = %u, block_bitmap = %llu", block_group, (unsigned long long) bh->b_blocknr); diff --git a/fs/ext4/block_validity.c b/fs/ext4/block_validity.c index 8e83741b02e0..0a734ffb4310 100644 --- a/fs/ext4/block_validity.c +++ b/fs/ext4/block_validity.c @@ -38,6 +38,7 @@ int __init ext4_init_system_zone(void) void ext4_exit_system_zone(void) { + rcu_barrier(); kmem_cache_destroy(ext4_system_zone_cachep); } @@ -49,17 +50,26 @@ static inline int can_merge(struct ext4_system_zone *entry1, return 0; } +static void release_system_zone(struct ext4_system_blocks *system_blks) +{ + struct ext4_system_zone *entry, *n; + + rbtree_postorder_for_each_entry_safe(entry, n, + &system_blks->root, node) + kmem_cache_free(ext4_system_zone_cachep, entry); +} + /* * Mark a range of blocks as belonging to the "system zone" --- that * is, filesystem metadata blocks which should never be used by * inodes. */ -static int add_system_zone(struct ext4_sb_info *sbi, +static int add_system_zone(struct ext4_system_blocks *system_blks, ext4_fsblk_t start_blk, unsigned int count) { struct ext4_system_zone *new_entry = NULL, *entry; - struct rb_node **n = &sbi->system_blks.rb_node, *node; + struct rb_node **n = &system_blks->root.rb_node, *node; struct rb_node *parent = NULL, *new_node = NULL; while (*n) { @@ -91,7 +101,7 @@ static int add_system_zone(struct ext4_sb_info *sbi, new_node = &new_entry->node; rb_link_node(new_node, parent, n); - rb_insert_color(new_node, &sbi->system_blks); + rb_insert_color(new_node, &system_blks->root); } /* Can we merge to the left? */ @@ -101,7 +111,7 @@ static int add_system_zone(struct ext4_sb_info *sbi, if (can_merge(entry, new_entry)) { new_entry->start_blk = entry->start_blk; new_entry->count += entry->count; - rb_erase(node, &sbi->system_blks); + rb_erase(node, &system_blks->root); kmem_cache_free(ext4_system_zone_cachep, entry); } } @@ -112,7 +122,7 @@ static int add_system_zone(struct ext4_sb_info *sbi, entry = rb_entry(node, struct ext4_system_zone, node); if (can_merge(new_entry, entry)) { new_entry->count += entry->count; - rb_erase(node, &sbi->system_blks); + rb_erase(node, &system_blks->root); kmem_cache_free(ext4_system_zone_cachep, entry); } } @@ -123,10 +133,13 @@ static void debug_print_tree(struct ext4_sb_info *sbi) { struct rb_node *node; struct ext4_system_zone *entry; + struct ext4_system_blocks *system_blks; int first = 1; printk(KERN_INFO "System zones: "); - node = rb_first(&sbi->system_blks); + rcu_read_lock(); + system_blks = rcu_dereference(sbi->system_blks); + node = rb_first(&system_blks->root); while (node) { entry = rb_entry(node, struct ext4_system_zone, node); printk(KERN_CONT "%s%llu-%llu", first ? "" : ", ", @@ -134,10 +147,51 @@ static void debug_print_tree(struct ext4_sb_info *sbi) first = 0; node = rb_next(node); } + rcu_read_unlock(); printk(KERN_CONT "\n"); } -static int ext4_protect_reserved_inode(struct super_block *sb, u32 ino) +/* + * 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 filesystem metadata blocks. + */ +static int ext4_data_block_valid_rcu(struct ext4_sb_info *sbi, + struct ext4_system_blocks *system_blks, + ext4_fsblk_t start_blk, + unsigned int count) +{ + struct ext4_system_zone *entry; + struct rb_node *n; + + if ((start_blk <= le32_to_cpu(sbi->s_es->s_first_data_block)) || + (start_blk + count < start_blk) || + (start_blk + count > ext4_blocks_count(sbi->s_es))) { + sbi->s_es->s_last_error_block = cpu_to_le64(start_blk); + return 0; + } + + if (system_blks == NULL) + return 1; + + n = system_blks->root.rb_node; + while (n) { + entry = rb_entry(n, struct ext4_system_zone, node); + if (start_blk + count - 1 < entry->start_blk) + n = n->rb_left; + else if (start_blk >= (entry->start_blk + entry->count)) + n = n->rb_right; + else { + sbi->s_es->s_last_error_block = cpu_to_le64(start_blk); + return 0; + } + } + return 1; +} + +static int ext4_protect_reserved_inode(struct super_block *sb, + struct ext4_system_blocks *system_blks, + u32 ino) { struct inode *inode; struct ext4_sb_info *sbi = EXT4_SB(sb); @@ -153,6 +207,7 @@ static int ext4_protect_reserved_inode(struct super_block *sb, u32 ino) return PTR_ERR(inode); num = (inode->i_size + sb->s_blocksize - 1) >> sb->s_blocksize_bits; while (i < num) { + cond_resched(); map.m_lblk = i; map.m_len = num - i; n = ext4_map_blocks(NULL, inode, &map, 0); @@ -163,14 +218,15 @@ static int ext4_protect_reserved_inode(struct super_block *sb, u32 ino) if (n == 0) { i++; } else { - if (!ext4_data_block_valid(sbi, map.m_pblk, n)) { + if (!ext4_data_block_valid_rcu(sbi, system_blks, + map.m_pblk, n)) { ext4_error(sb, "blocks %llu-%llu from inode %u " "overlap system zone", map.m_pblk, map.m_pblk + map.m_len - 1, ino); err = -EFSCORRUPTED; break; } - err = add_system_zone(sbi, map.m_pblk, n); + err = add_system_zone(system_blks, map.m_pblk, n); if (err < 0) break; i += n; @@ -180,94 +236,130 @@ static int ext4_protect_reserved_inode(struct super_block *sb, u32 ino) return err; } +static void ext4_destroy_system_zone(struct rcu_head *rcu) +{ + struct ext4_system_blocks *system_blks; + + system_blks = container_of(rcu, struct ext4_system_blocks, rcu); + release_system_zone(system_blks); + kfree(system_blks); +} + +/* + * Build system zone rbtree which is used for block validity checking. + * + * The update of system_blks pointer in this function is protected by + * sb->s_umount semaphore. However we have to be careful as we can be + * racing with ext4_data_block_valid() calls reading system_blks rbtree + * protected only by RCU. That's why we first build the rbtree and then + * swap it in place. + */ int ext4_setup_system_zone(struct super_block *sb) { ext4_group_t ngroups = ext4_get_groups_count(sb); struct ext4_sb_info *sbi = EXT4_SB(sb); + struct ext4_system_blocks *system_blks; struct ext4_group_desc *gdp; ext4_group_t i; int flex_size = ext4_flex_bg_size(sbi); int ret; if (!test_opt(sb, BLOCK_VALIDITY)) { - if (sbi->system_blks.rb_node) + if (sbi->system_blks) ext4_release_system_zone(sb); return 0; } - if (sbi->system_blks.rb_node) + if (sbi->system_blks) return 0; + system_blks = kzalloc(sizeof(*system_blks), GFP_KERNEL); + if (!system_blks) + return -ENOMEM; + for (i=0; i < ngroups; i++) { cond_resched(); if (ext4_bg_has_super(sb, i) && ((i < 5) || ((i % flex_size) == 0))) - add_system_zone(sbi, ext4_group_first_block_no(sb, i), + add_system_zone(system_blks, + ext4_group_first_block_no(sb, i), ext4_bg_num_gdb(sb, i) + 1); gdp = ext4_get_group_desc(sb, i, NULL); - ret = add_system_zone(sbi, ext4_block_bitmap(sb, gdp), 1); + ret = add_system_zone(system_blks, + ext4_block_bitmap(sb, gdp), 1); if (ret) - return ret; - ret = add_system_zone(sbi, ext4_inode_bitmap(sb, gdp), 1); + goto err; + ret = add_system_zone(system_blks, + ext4_inode_bitmap(sb, gdp), 1); if (ret) - return ret; - ret = add_system_zone(sbi, ext4_inode_table(sb, gdp), + goto err; + ret = add_system_zone(system_blks, + ext4_inode_table(sb, gdp), sbi->s_itb_per_group); if (ret) - return ret; + goto err; } if (ext4_has_feature_journal(sb) && sbi->s_es->s_journal_inum) { - ret = ext4_protect_reserved_inode(sb, + ret = ext4_protect_reserved_inode(sb, system_blks, le32_to_cpu(sbi->s_es->s_journal_inum)); if (ret) - return ret; + goto err; } + /* + * System blks rbtree complete, announce it once to prevent racing + * with ext4_data_block_valid() accessing the rbtree at the same + * time. + */ + rcu_assign_pointer(sbi->system_blks, system_blks); + if (test_opt(sb, DEBUG)) debug_print_tree(sbi); return 0; +err: + release_system_zone(system_blks); + kfree(system_blks); + return ret; } -/* Called when the filesystem is unmounted */ +/* + * Called when the filesystem is unmounted or when remounting it with + * noblock_validity specified. + * + * The update of system_blks pointer in this function is protected by + * sb->s_umount semaphore. However we have to be careful as we can be + * racing with ext4_data_block_valid() calls reading system_blks rbtree + * protected only by RCU. So we first clear the system_blks pointer and + * then free the rbtree only after RCU grace period expires. + */ void ext4_release_system_zone(struct super_block *sb) { - struct ext4_system_zone *entry, *n; + struct ext4_system_blocks *system_blks; - rbtree_postorder_for_each_entry_safe(entry, n, - &EXT4_SB(sb)->system_blks, node) - kmem_cache_free(ext4_system_zone_cachep, entry); + system_blks = rcu_dereference_protected(EXT4_SB(sb)->system_blks, + lockdep_is_held(&sb->s_umount)); + rcu_assign_pointer(EXT4_SB(sb)->system_blks, NULL); - EXT4_SB(sb)->system_blks = RB_ROOT; + if (system_blks) + 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 filesystem metadata blocks. - */ int ext4_data_block_valid(struct ext4_sb_info *sbi, ext4_fsblk_t start_blk, unsigned int count) { - struct ext4_system_zone *entry; - struct rb_node *n = sbi->system_blks.rb_node; + struct ext4_system_blocks *system_blks; + int ret; - if ((start_blk <= le32_to_cpu(sbi->s_es->s_first_data_block)) || - (start_blk + count < start_blk) || - (start_blk + count > ext4_blocks_count(sbi->s_es))) { - sbi->s_es->s_last_error_block = cpu_to_le64(start_blk); - return 0; - } - while (n) { - entry = rb_entry(n, struct ext4_system_zone, node); - if (start_blk + count - 1 < entry->start_blk) - n = n->rb_left; - else if (start_blk >= (entry->start_blk + entry->count)) - n = n->rb_right; - else { - sbi->s_es->s_last_error_block = cpu_to_le64(start_blk); - return 0; - } - } - return 1; + /* + * Lock the system zone to prevent it being released concurrently + * when doing a remount which inverse current "[no]block_validity" + * mount option. + */ + rcu_read_lock(); + system_blks = rcu_dereference(sbi->system_blks); + ret = ext4_data_block_valid_rcu(sbi, system_blks, start_blk, + count); + rcu_read_unlock(); + return ret; } int ext4_check_blockref(const char *function, unsigned int line, diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c index 86054f31fe4d..9aa1f75409b0 100644 --- a/fs/ext4/dir.c +++ b/fs/ext4/dir.c @@ -72,6 +72,7 @@ int __ext4_check_dir_entry(const char *function, unsigned int line, const char *error_msg = NULL; const int rlen = ext4_rec_len_from_disk(de->rec_len, dir->i_sb->s_blocksize); + const int next_offset = ((char *) de - buf) + rlen; if (unlikely(rlen < EXT4_DIR_REC_LEN(1))) error_msg = "rec_len is smaller than minimal"; @@ -79,8 +80,11 @@ int __ext4_check_dir_entry(const char *function, unsigned int line, error_msg = "rec_len % 4 != 0"; else if (unlikely(rlen < EXT4_DIR_REC_LEN(de->name_len))) error_msg = "rec_len is too small for name_len"; - else if (unlikely(((char *) de - buf) + rlen > size)) + else if (unlikely(next_offset > size)) error_msg = "directory entry overrun"; + else if (unlikely(next_offset > size - EXT4_DIR_REC_LEN(1) && + next_offset != size)) + error_msg = "directory entry too close to block end"; else if (unlikely(le32_to_cpu(de->inode) > le32_to_cpu(EXT4_SB(dir->i_sb)->s_es->s_inodes_count))) error_msg = "inode out of bounds"; @@ -116,7 +120,7 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx) if (IS_ENCRYPTED(inode)) { err = fscrypt_get_encryption_info(inode); - if (err && err != -ENOKEY) + if (err) return err; } @@ -125,12 +129,14 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx) if (err != ERR_BAD_DX_DIR) { return err; } - /* - * We don't set the inode dirty flag since it's not - * critical that it get flushed back to the disk. - */ - ext4_clear_inode_flag(file_inode(file), - EXT4_INODE_INDEX); + /* Can we just clear INDEX flag to ignore htree information? */ + if (!ext4_has_metadata_csum(sb)) { + /* + * We don't set the inode dirty flag since it's not + * critical that it gets flushed back to the disk. + */ + ext4_clear_inode_flag(inode, EXT4_INODE_INDEX); + } } if (ext4_has_inline_data(inode)) { @@ -458,7 +464,6 @@ int ext4_htree_store_dirent(struct file *dir_file, __u32 hash, new_fn->name_len = ent_name->len; new_fn->file_type = dirent->file_type; memcpy(new_fn->name, ent_name->name, ent_name->len); - new_fn->name[ent_name->len] = 0; while (*p) { parent = *p; @@ -668,24 +673,28 @@ static int ext4_d_compare(const struct dentry *dentry, unsigned int len, const char *str, const struct qstr *name) { struct qstr qstr = {.name = str, .len = len }; + const struct dentry *parent = READ_ONCE(dentry->d_parent); + const struct inode *inode = READ_ONCE(parent->d_inode); - if (!IS_CASEFOLDED(dentry->d_parent->d_inode)) { + if (!inode || !IS_CASEFOLDED(inode) || + !EXT4_SB(inode->i_sb)->s_encoding) { if (len != name->len) return -1; return memcmp(str, name->name, len); } - return ext4_ci_compare(dentry->d_parent->d_inode, name, &qstr, false); + return ext4_ci_compare(inode, name, &qstr, false); } static int ext4_d_hash(const struct dentry *dentry, struct qstr *str) { const struct ext4_sb_info *sbi = EXT4_SB(dentry->d_sb); const struct unicode_map *um = sbi->s_encoding; + const struct inode *inode = READ_ONCE(dentry->d_inode); unsigned char *norm; int len, ret = 0; - if (!IS_CASEFOLDED(dentry->d_inode)) + if (!inode || !IS_CASEFOLDED(inode) || !um) return 0; norm = kmalloc(PATH_MAX, GFP_ATOMIC); diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index bf660aa7a9e0..4441331d06cc 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -41,6 +41,7 @@ #endif #include <linux/fscrypt.h> +#include <linux/fsverity.h> #include <linux/compiler.h> @@ -185,10 +186,24 @@ struct ext4_map_blocks { }; /* + * Block validity checking, system zone rbtree. + */ +struct ext4_system_blocks { + struct rb_root root; + struct rcu_head rcu; +}; + +/* * Flags for ext4_io_end->flags */ #define EXT4_IO_END_UNWRITTEN 0x0001 +struct ext4_io_end_vec { + struct list_head list; /* list of io_end_vec */ + loff_t offset; /* offset in the file */ + ssize_t size; /* size of the extent */ +}; + /* * For converting unwritten extents on a work queue. 'handle' is used for * buffered writeback. @@ -202,8 +217,7 @@ typedef struct ext4_io_end { * bios covering the extent */ unsigned int flag; /* unwritten or not */ atomic_t count; /* reference counter */ - loff_t offset; /* offset in the file */ - ssize_t size; /* size of the extent */ + struct list_head list_vec; /* list of ext4_io_end_vec */ } ext4_io_end_t; struct ext4_io_submit { @@ -284,6 +298,9 @@ struct ext4_io_submit { ~((ext4_fsblk_t) (s)->s_cluster_ratio - 1)) #define EXT4_LBLK_CMASK(s, lblk) ((lblk) & \ ~((ext4_lblk_t) (s)->s_cluster_ratio - 1)) +/* Fill in the low bits to get the last block of the cluster */ +#define EXT4_LBLK_CFILL(sbi, lblk) ((lblk) | \ + ((ext4_lblk_t) (sbi)->s_cluster_ratio - 1)) /* Get the cluster offset */ #define EXT4_PBLK_COFF(s, pblk) ((pblk) & \ ((ext4_fsblk_t) (s)->s_cluster_ratio - 1)) @@ -395,6 +412,7 @@ struct flex_groups { #define EXT4_TOPDIR_FL 0x00020000 /* Top of directory hierarchies*/ #define EXT4_HUGE_FILE_FL 0x00040000 /* Set to each huge file */ #define EXT4_EXTENTS_FL 0x00080000 /* Inode uses extents */ +#define EXT4_VERITY_FL 0x00100000 /* Verity protected inode */ #define EXT4_EA_INODE_FL 0x00200000 /* Inode used for large EA */ #define EXT4_EOFBLOCKS_FL 0x00400000 /* Blocks allocated beyond EOF */ #define EXT4_INLINE_DATA_FL 0x10000000 /* Inode has inline data. */ @@ -402,7 +420,7 @@ struct flex_groups { #define EXT4_CASEFOLD_FL 0x40000000 /* Casefolded file */ #define EXT4_RESERVED_FL 0x80000000 /* reserved for ext4 lib */ -#define EXT4_FL_USER_VISIBLE 0x704BDFFF /* User visible flags */ +#define EXT4_FL_USER_VISIBLE 0x705BDFFF /* User visible flags */ #define EXT4_FL_USER_MODIFIABLE 0x604BC0FF /* User modifiable flags */ /* Flags we can manipulate with through EXT4_IOC_FSSETXATTR */ @@ -467,6 +485,7 @@ enum { EXT4_INODE_TOPDIR = 17, /* Top of directory hierarchies*/ EXT4_INODE_HUGE_FILE = 18, /* Set to each huge file */ EXT4_INODE_EXTENTS = 19, /* Inode uses extents */ + EXT4_INODE_VERITY = 20, /* Verity protected inode */ EXT4_INODE_EA_INODE = 21, /* Inode used for large EA */ EXT4_INODE_EOFBLOCKS = 22, /* Blocks allocated beyond EOF */ EXT4_INODE_INLINE_DATA = 28, /* Data in inode. */ @@ -512,6 +531,7 @@ static inline void ext4_check_flag_values(void) CHECK_FLAG_VALUE(TOPDIR); CHECK_FLAG_VALUE(HUGE_FILE); CHECK_FLAG_VALUE(EXTENTS); + CHECK_FLAG_VALUE(VERITY); CHECK_FLAG_VALUE(EA_INODE); CHECK_FLAG_VALUE(EOFBLOCKS); CHECK_FLAG_VALUE(INLINE_DATA); @@ -649,6 +669,10 @@ enum { #define EXT4_IOC_SET_ENCRYPTION_POLICY FS_IOC_SET_ENCRYPTION_POLICY #define EXT4_IOC_GET_ENCRYPTION_PWSALT FS_IOC_GET_ENCRYPTION_PWSALT #define EXT4_IOC_GET_ENCRYPTION_POLICY FS_IOC_GET_ENCRYPTION_POLICY +/* ioctl codes 19--39 are reserved for fscrypt */ +#define EXT4_IOC_CLEAR_ES_CACHE _IO('f', 40) +#define EXT4_IOC_GETSTATE _IOW('f', 41, __u32) +#define EXT4_IOC_GET_ES_CACHE _IOWR('f', 42, struct fiemap) #define EXT4_IOC_FSGETXATTR FS_IOC_FSGETXATTR #define EXT4_IOC_FSSETXATTR FS_IOC_FSSETXATTR @@ -662,6 +686,16 @@ enum { #define EXT4_GOING_FLAGS_LOGFLUSH 0x1 /* flush log but not data */ #define EXT4_GOING_FLAGS_NOLOGFLUSH 0x2 /* don't flush log nor data */ +/* + * Flags returned by EXT4_IOC_GETSTATE + * + * We only expose to userspace a subset of the state flags in + * i_state_flags + */ +#define EXT4_STATE_FLAG_EXT_PRECACHED 0x00000001 +#define EXT4_STATE_FLAG_NEW 0x00000002 +#define EXT4_STATE_FLAG_NEWENTRY 0x00000004 +#define EXT4_STATE_FLAG_DA_ALLOC_CLOSE 0x00000008 #if defined(__KERNEL__) && defined(CONFIG_COMPAT) /* @@ -679,6 +713,12 @@ enum { #define EXT4_IOC32_SETVERSION_OLD FS_IOC32_SETVERSION #endif +/* + * Returned by EXT4_IOC_GET_ES_CACHE as an additional possible flag. + * It indicates that the entry in extent status cache is for a hole. + */ +#define EXT4_FIEMAP_EXTENT_HOLE 0x08000000 + /* Max physical block we can address w/o extents */ #define EXT4_MAX_BLOCK_FILE_PHYS 0xFFFFFFFF @@ -808,31 +848,20 @@ static inline __le32 ext4_encode_extra_time(struct timespec64 *time) static inline void ext4_decode_extra_time(struct timespec64 *time, __le32 extra) { - if (unlikely(extra & cpu_to_le32(EXT4_EPOCH_MASK))) { - -#if 1 - /* Handle legacy encoding of pre-1970 dates with epoch - * bits 1,1. (This backwards compatibility may be removed - * at the discretion of the ext4 developers.) - */ - u64 extra_bits = le32_to_cpu(extra) & EXT4_EPOCH_MASK; - if (extra_bits == 3 && ((time->tv_sec) & 0x80000000) != 0) - extra_bits = 0; - time->tv_sec += extra_bits << 32; -#else + if (unlikely(extra & cpu_to_le32(EXT4_EPOCH_MASK))) time->tv_sec += (u64)(le32_to_cpu(extra) & EXT4_EPOCH_MASK) << 32; -#endif - } time->tv_nsec = (le32_to_cpu(extra) & EXT4_NSEC_MASK) >> EXT4_EPOCH_BITS; } #define EXT4_INODE_SET_XTIME(xtime, inode, raw_inode) \ do { \ - (raw_inode)->xtime = cpu_to_le32((inode)->xtime.tv_sec); \ if (EXT4_FITS_IN_INODE(raw_inode, EXT4_I(inode), xtime ## _extra)) {\ + (raw_inode)->xtime = cpu_to_le32((inode)->xtime.tv_sec); \ (raw_inode)->xtime ## _extra = \ ext4_encode_extra_time(&(inode)->xtime); \ } \ + else \ + (raw_inode)->xtime = cpu_to_le32(clamp_t(int32_t, (inode)->xtime.tv_sec, S32_MIN, S32_MAX)); \ } while (0) #define EXT4_EINODE_SET_XTIME(xtime, einode, raw_inode) \ @@ -1023,8 +1052,6 @@ struct ext4_inode_info { /* allocation reservation info for delalloc */ /* In case of bigalloc, this refer to clusters rather than blocks */ unsigned int i_reserved_data_blocks; - ext4_lblk_t i_da_metadata_calc_last_lblock; - int i_da_metadata_calc_len; /* pending cluster reservations for bigalloc file systems */ struct ext4_pending_tree i_pending_tree; @@ -1314,7 +1341,8 @@ struct ext4_super_block { __u8 s_lastcheck_hi; __u8 s_first_error_time_hi; __u8 s_last_error_time_hi; - __u8 s_pad[2]; + __u8 s_first_error_errcode; + __u8 s_last_error_errcode; __le16 s_encoding; /* Filename charset encoding */ __le16 s_encoding_flags; /* Filename charset encoding flags */ __le32 s_reserved[95]; /* Padding to the end of the block */ @@ -1421,7 +1449,7 @@ struct ext4_sb_info { int s_jquota_fmt; /* Format of quota to use */ #endif unsigned int s_want_extra_isize; /* New inodes should reserve # bytes */ - struct rb_root system_blks; + struct ext4_system_blocks __rcu *system_blks; #ifdef EXTENTS_STATS /* ext4 extents stats */ @@ -1527,6 +1555,9 @@ struct ext4_sb_info { /* Barrier between changing inodes' journal flags and writepages ops. */ struct percpu_rw_semaphore s_journal_flag_rwsem; struct dax_device *s_daxdev; +#ifdef CONFIG_EXT4_DEBUG + unsigned long s_simulate_fail; +#endif }; static inline struct ext4_sb_info *EXT4_SB(struct super_block *sb) @@ -1546,6 +1577,66 @@ static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino) } /* + * Simulate_fail codes + */ +#define EXT4_SIM_BBITMAP_EIO 1 +#define EXT4_SIM_BBITMAP_CRC 2 +#define EXT4_SIM_IBITMAP_EIO 3 +#define EXT4_SIM_IBITMAP_CRC 4 +#define EXT4_SIM_INODE_EIO 5 +#define EXT4_SIM_INODE_CRC 6 +#define EXT4_SIM_DIRBLOCK_EIO 7 +#define EXT4_SIM_DIRBLOCK_CRC 8 + +static inline bool ext4_simulate_fail(struct super_block *sb, + unsigned long code) +{ +#ifdef CONFIG_EXT4_DEBUG + struct ext4_sb_info *sbi = EXT4_SB(sb); + + if (unlikely(sbi->s_simulate_fail == code)) { + sbi->s_simulate_fail = 0; + return true; + } +#endif + return false; +} + +static inline void ext4_simulate_fail_bh(struct super_block *sb, + struct buffer_head *bh, + unsigned long code) +{ + if (!IS_ERR(bh) && ext4_simulate_fail(sb, code)) + clear_buffer_uptodate(bh); +} + +/* + * Error number codes for s_{first,last}_error_errno + * + * Linux errno numbers are architecture specific, so we need to translate + * them into something which is architecture independent. We don't define + * codes for all errno's; just the ones which are most likely to be the cause + * of an ext4_error() call. + */ +#define EXT4_ERR_UNKNOWN 1 +#define EXT4_ERR_EIO 2 +#define EXT4_ERR_ENOMEM 3 +#define EXT4_ERR_EFSBADCRC 4 +#define EXT4_ERR_EFSCORRUPTED 5 +#define EXT4_ERR_ENOSPC 6 +#define EXT4_ERR_ENOKEY 7 +#define EXT4_ERR_EROFS 8 +#define EXT4_ERR_EFBIG 9 +#define EXT4_ERR_EEXIST 10 +#define EXT4_ERR_ERANGE 11 +#define EXT4_ERR_EOVERFLOW 12 +#define EXT4_ERR_EBUSY 13 +#define EXT4_ERR_ENOTDIR 14 +#define EXT4_ERR_ENOTEMPTY 15 +#define EXT4_ERR_ESHUTDOWN 16 +#define EXT4_ERR_EFAULT 17 + +/* * Inode dynamic state flags */ enum { @@ -1555,11 +1646,11 @@ enum { EXT4_STATE_NO_EXPAND, /* No space for expansion */ EXT4_STATE_DA_ALLOC_CLOSE, /* Alloc DA blks on close */ EXT4_STATE_EXT_MIGRATE, /* Inode is migrating */ - EXT4_STATE_DIO_UNWRITTEN, /* need convert on dio done*/ EXT4_STATE_NEWENTRY, /* File just added to dir */ EXT4_STATE_MAY_INLINE_DATA, /* may have in-inode data */ EXT4_STATE_EXT_PRECACHED, /* extents have been precached */ EXT4_STATE_LUSTRE_EA_INODE, /* Lustre-style ea_inode */ + EXT4_STATE_VERITY_IN_PROGRESS, /* building fs-verity Merkle tree */ }; #define EXT4_INODE_BIT_FNS(name, field, offset) \ @@ -1610,6 +1701,12 @@ static inline void ext4_clear_state_flags(struct ext4_inode_info *ei) #define EXT4_SB(sb) (sb) #endif +static inline bool ext4_verity_in_progress(struct inode *inode) +{ + return IS_ENABLED(CONFIG_FS_VERITY) && + ext4_test_inode_state(inode, EXT4_STATE_VERITY_IN_PROGRESS); +} + #define NEXT_ORPHAN(inode) EXT4_I(inode)->i_dtime /* @@ -1632,6 +1729,10 @@ static inline void ext4_clear_state_flags(struct ext4_inode_info *ei) #define EXT4_GOOD_OLD_INODE_SIZE 128 +#define EXT4_EXTRA_TIMESTAMP_MAX (((s64)1 << 34) - 1 + S32_MIN) +#define EXT4_NON_EXTRA_TIMESTAMP_MAX S32_MAX +#define EXT4_TIMESTAMP_MIN S32_MIN + /* * Feature set definitions */ @@ -1643,6 +1744,7 @@ static inline void ext4_clear_state_flags(struct ext4_inode_info *ei) #define EXT4_FEATURE_COMPAT_RESIZE_INODE 0x0010 #define EXT4_FEATURE_COMPAT_DIR_INDEX 0x0020 #define EXT4_FEATURE_COMPAT_SPARSE_SUPER2 0x0200 +#define EXT4_FEATURE_COMPAT_STABLE_INODES 0x0800 #define EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER 0x0001 #define EXT4_FEATURE_RO_COMPAT_LARGE_FILE 0x0002 @@ -1662,6 +1764,7 @@ static inline void ext4_clear_state_flags(struct ext4_inode_info *ei) #define EXT4_FEATURE_RO_COMPAT_METADATA_CSUM 0x0400 #define EXT4_FEATURE_RO_COMPAT_READONLY 0x1000 #define EXT4_FEATURE_RO_COMPAT_PROJECT 0x2000 +#define EXT4_FEATURE_RO_COMPAT_VERITY 0x8000 #define EXT4_FEATURE_INCOMPAT_COMPRESSION 0x0001 #define EXT4_FEATURE_INCOMPAT_FILETYPE 0x0002 @@ -1743,6 +1846,7 @@ EXT4_FEATURE_COMPAT_FUNCS(xattr, EXT_ATTR) EXT4_FEATURE_COMPAT_FUNCS(resize_inode, RESIZE_INODE) EXT4_FEATURE_COMPAT_FUNCS(dir_index, DIR_INDEX) EXT4_FEATURE_COMPAT_FUNCS(sparse_super2, SPARSE_SUPER2) +EXT4_FEATURE_COMPAT_FUNCS(stable_inodes, STABLE_INODES) EXT4_FEATURE_RO_COMPAT_FUNCS(sparse_super, SPARSE_SUPER) EXT4_FEATURE_RO_COMPAT_FUNCS(large_file, LARGE_FILE) @@ -1756,6 +1860,7 @@ EXT4_FEATURE_RO_COMPAT_FUNCS(bigalloc, BIGALLOC) EXT4_FEATURE_RO_COMPAT_FUNCS(metadata_csum, METADATA_CSUM) EXT4_FEATURE_RO_COMPAT_FUNCS(readonly, READONLY) EXT4_FEATURE_RO_COMPAT_FUNCS(project, PROJECT) +EXT4_FEATURE_RO_COMPAT_FUNCS(verity, VERITY) EXT4_FEATURE_INCOMPAT_FUNCS(compression, COMPRESSION) EXT4_FEATURE_INCOMPAT_FUNCS(filetype, FILETYPE) @@ -1813,7 +1918,8 @@ EXT4_FEATURE_INCOMPAT_FUNCS(casefold, CASEFOLD) EXT4_FEATURE_RO_COMPAT_BIGALLOC |\ EXT4_FEATURE_RO_COMPAT_METADATA_CSUM|\ EXT4_FEATURE_RO_COMPAT_QUOTA |\ - EXT4_FEATURE_RO_COMPAT_PROJECT) + EXT4_FEATURE_RO_COMPAT_PROJECT |\ + EXT4_FEATURE_RO_COMPAT_VERITY) #define EXTN_FEATURE_FUNCS(ver) \ static inline bool ext4_has_unknown_ext##ver##_compat_features(struct super_block *sb) \ @@ -2438,8 +2544,11 @@ void ext4_insert_dentry(struct inode *inode, struct ext4_filename *fname); static inline void ext4_update_dx_flag(struct inode *inode) { - if (!ext4_has_feature_dir_index(inode->i_sb)) + if (!ext4_has_feature_dir_index(inode->i_sb)) { + /* ext4_iget() should have caught this... */ + WARN_ON_ONCE(ext4_has_feature_metadata_csum(inode->i_sb)); ext4_clear_inode_flag(inode, EXT4_INODE_INDEX); + } } static const unsigned char ext4_filetype_table[] = { DT_UNKNOWN, DT_REG, DT_DIR, DT_CHR, DT_BLK, DT_FIFO, DT_SOCK, DT_LNK @@ -2522,8 +2631,6 @@ int ext4_get_block_unwritten(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create); int ext4_get_block(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create); -int ext4_dio_get_block(struct inode *inode, sector_t iblock, - struct buffer_head *bh_result, int create); int ext4_da_get_block_prep(struct inode *inode, sector_t iblock, struct buffer_head *bh, int create); int ext4_walk_page_buffers(handle_t *handle, @@ -2566,7 +2673,6 @@ 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_truncate_restart_trans(handle_t *, struct inode *, int nblocks); extern void ext4_set_inode_flags(struct inode *); extern int ext4_alloc_da_blocks(struct inode *inode); extern void ext4_set_aops(struct inode *inode); @@ -2587,7 +2693,6 @@ extern int ext4_issue_zeroout(struct inode *inode, ext4_lblk_t lblk, /* indirect.c */ extern int ext4_ind_map_blocks(handle_t *handle, struct inode *inode, struct ext4_map_blocks *map, int flags); -extern int ext4_ind_calc_metadata_amount(struct inode *inode, sector_t lblock); extern int ext4_ind_trans_blocks(struct inode *inode, int nrblocks); extern void ext4_ind_truncate(handle_t *, struct inode *inode); extern int ext4_ind_remove_space(handle_t *handle, struct inode *inode, @@ -2638,8 +2743,6 @@ extern struct buffer_head *ext4_sb_bread(struct super_block *sb, extern int ext4_seq_options_show(struct seq_file *seq, void *offset); extern int ext4_calculate_overhead(struct super_block *sb); extern void ext4_superblock_csum_set(struct super_block *sb); -extern void *ext4_kvmalloc(size_t size, gfp_t flags); -extern void *ext4_kvzalloc(size_t size, gfp_t flags); extern int ext4_alloc_flex_bg_array(struct super_block *sb, ext4_group_t ngroup); extern const char *ext4_decode_error(struct super_block *sb, int errno, @@ -2647,6 +2750,7 @@ extern const char *ext4_decode_error(struct super_block *sb, int errno, extern void ext4_mark_group_bitmap_corrupted(struct super_block *sb, ext4_group_t block_group, unsigned int flags); +extern void ext4_set_errno(struct super_block *sb, int err); extern __printf(4, 5) void __ext4_error(struct super_block *, const char *, unsigned int, @@ -3177,6 +3281,8 @@ static inline void ext4_set_de_type(struct super_block *sb, extern int ext4_mpage_readpages(struct address_space *mapping, struct list_head *pages, struct page *page, unsigned nr_pages, bool is_readahead); +extern int __init ext4_init_post_read_processing(void); +extern void ext4_exit_post_read_processing(void); /* symlink.c */ extern const struct inode_operations ext4_encrypted_symlink_inode_operations; @@ -3211,7 +3317,6 @@ struct ext4_extent; #define EXT_MAX_BLOCKS 0xffffffff extern int ext4_ext_tree_init(handle_t *handle, struct inode *); -extern int ext4_ext_writepage_trans_blocks(struct inode *, int); extern int ext4_ext_index_trans_blocks(struct inode *inode, int extents); extern int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, struct ext4_map_blocks *map, int flags); @@ -3224,16 +3329,13 @@ extern long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len); extern int ext4_convert_unwritten_extents(handle_t *handle, struct inode *inode, loff_t offset, ssize_t len); +extern int ext4_convert_unwritten_io_end_vec(handle_t *handle, + ext4_io_end_t *io_end); extern int ext4_map_blocks(handle_t *handle, struct inode *inode, struct ext4_map_blocks *map, int flags); -extern int ext4_ext_calc_metadata_amount(struct inode *inode, - ext4_lblk_t lblocks); extern int ext4_ext_calc_credits_for_single_extent(struct inode *inode, int num, struct ext4_ext_path *path); -extern int ext4_can_extents_be_merged(struct inode *inode, - struct ext4_extent *ex1, - struct ext4_extent *ex2); extern int ext4_ext_insert_extent(handle_t *, struct inode *, struct ext4_ext_path **, struct ext4_extent *, int); @@ -3245,14 +3347,19 @@ 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, __u64 start, __u64 len); +extern int ext4_get_es_cache(struct inode *inode, + struct fiemap_extent_info *fieinfo, + __u64 start, __u64 len); extern int ext4_ext_precache(struct inode *inode); -extern int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len); -extern int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len); extern int ext4_swap_extents(handle_t *handle, struct inode *inode1, struct inode *inode2, ext4_lblk_t lblk1, ext4_lblk_t lblk2, ext4_lblk_t count, int mark_unwritten,int *err); extern int ext4_clu_mapped(struct inode *inode, ext4_lblk_t lclu); +extern int ext4_datasem_ensure_credits(handle_t *handle, struct inode *inode, + int check_cred, int restart_cred, + int revoke_cred); + /* move_extent.c */ extern void ext4_double_down_write_data_sem(struct inode *first, @@ -3279,10 +3386,15 @@ extern int ext4_bio_write_page(struct ext4_io_submit *io, int len, struct writeback_control *wbc, bool keep_towrite); +extern struct ext4_io_end_vec *ext4_alloc_io_end_vec(ext4_io_end_t *io_end); +extern struct ext4_io_end_vec *ext4_last_io_end_vec(ext4_io_end_t *io_end); /* mmp.c */ extern int ext4_multi_mount_protect(struct super_block *, ext4_fsblk_t); +/* verity.c */ +extern const struct fsverity_operations ext4_verityops; + /* * Add new method to test whether block and inode bitmaps are properly * initialized. With uninit_bg reading the block from disk is not enough @@ -3333,6 +3445,21 @@ static inline void ext4_clear_io_unwritten_flag(ext4_io_end_t *io_end) } extern const struct iomap_ops ext4_iomap_ops; +extern const struct iomap_ops ext4_iomap_overwrite_ops; +extern const struct iomap_ops ext4_iomap_report_ops; + +static inline int ext4_buffer_uptodate(struct buffer_head *bh) +{ + /* + * If the buffer has the write error flag, we have failed + * to write out data in the block. In this case, we don't + * have to read the block because we may read the old data + * successfully. + */ + if (!buffer_uptodate(bh) && buffer_write_io_error(bh)) + set_buffer_uptodate(bh); + return buffer_uptodate(bh); +} #endif /* __KERNEL__ */ diff --git a/fs/ext4/ext4_extents.h b/fs/ext4/ext4_extents.h index 98bd0e9ee7df..1c216fcc202a 100644 --- a/fs/ext4/ext4_extents.h +++ b/fs/ext4/ext4_extents.h @@ -267,10 +267,5 @@ static inline void ext4_idx_store_pblock(struct ext4_extent_idx *ix, 0xffff); } -#define ext4_ext_dirty(handle, inode, path) \ - __ext4_ext_dirty(__func__, __LINE__, (handle), (inode), (path)) -int __ext4_ext_dirty(const char *where, unsigned int line, handle_t *handle, - struct inode *inode, struct ext4_ext_path *path); - #endif /* _EXT4_EXTENTS */ diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c index 7c70b08d104c..1f53d64e42a5 100644 --- a/fs/ext4/ext4_jbd2.c +++ b/fs/ext4/ext4_jbd2.c @@ -7,6 +7,28 @@ #include <trace/events/ext4.h> +int ext4_inode_journal_mode(struct inode *inode) +{ + if (EXT4_JOURNAL(inode) == NULL) + return EXT4_INODE_WRITEBACK_DATA_MODE; /* writeback */ + /* We do not support data journalling with delayed allocation */ + if (!S_ISREG(inode->i_mode) || + ext4_test_inode_flag(inode, EXT4_INODE_EA_INODE) || + test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA || + (ext4_test_inode_flag(inode, EXT4_INODE_JOURNAL_DATA) && + !test_opt(inode->i_sb, DELALLOC))) { + /* We do not support data journalling for encrypted data */ + if (S_ISREG(inode->i_mode) && IS_ENCRYPTED(inode)) + return EXT4_INODE_ORDERED_DATA_MODE; /* ordered */ + return EXT4_INODE_JOURNAL_DATA_MODE; /* journal data */ + } + if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA) + return EXT4_INODE_ORDERED_DATA_MODE; /* ordered */ + if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA) + return EXT4_INODE_WRITEBACK_DATA_MODE; /* writeback */ + BUG(); +} + /* Just increment the non-pointer handle value */ static handle_t *ext4_get_nojournal(void) { @@ -58,6 +80,7 @@ static int ext4_journal_check_start(struct super_block *sb) * take the FS itself readonly cleanly. */ if (journal && is_journal_aborted(journal)) { + ext4_set_errno(sb, -journal->j_errno); ext4_abort(sb, "Detected aborted journal"); return -EROFS; } @@ -65,12 +88,14 @@ static int ext4_journal_check_start(struct super_block *sb) } handle_t *__ext4_journal_start_sb(struct super_block *sb, unsigned int line, - int type, int blocks, int rsv_blocks) + int type, int blocks, int rsv_blocks, + int revoke_creds) { journal_t *journal; int err; - trace_ext4_journal_start(sb, blocks, rsv_blocks, _RET_IP_); + trace_ext4_journal_start(sb, blocks, rsv_blocks, revoke_creds, + _RET_IP_); err = ext4_journal_check_start(sb); if (err < 0) return ERR_PTR(err); @@ -78,8 +103,8 @@ handle_t *__ext4_journal_start_sb(struct super_block *sb, unsigned int line, journal = EXT4_SB(sb)->s_journal; if (!journal) return ext4_get_nojournal(); - return jbd2__journal_start(journal, blocks, rsv_blocks, GFP_NOFS, - type, line); + return jbd2__journal_start(journal, blocks, rsv_blocks, revoke_creds, + GFP_NOFS, type, line); } int __ext4_journal_stop(const char *where, unsigned int line, handle_t *handle) @@ -119,8 +144,8 @@ handle_t *__ext4_journal_start_reserved(handle_t *handle, unsigned int line, return ext4_get_nojournal(); sb = handle->h_journal->j_private; - trace_ext4_journal_start_reserved(sb, handle->h_buffer_credits, - _RET_IP_); + trace_ext4_journal_start_reserved(sb, + jbd2_handle_buffer_credits(handle), _RET_IP_); err = ext4_journal_check_start(sb); if (err < 0) { jbd2_journal_free_reserved(handle); @@ -133,6 +158,19 @@ handle_t *__ext4_journal_start_reserved(handle_t *handle, unsigned int line, return handle; } +int __ext4_journal_ensure_credits(handle_t *handle, int check_cred, + int extend_cred, int revoke_cred) +{ + if (!ext4_handle_valid(handle)) + return 0; + if (jbd2_handle_buffer_credits(handle) >= check_cred && + handle->h_revoke_credits >= revoke_cred) + return 0; + extend_cred = max(0, extend_cred - jbd2_handle_buffer_credits(handle)); + revoke_cred = max(0, revoke_cred - handle->h_revoke_credits); + return ext4_journal_extend(handle, extend_cred, revoke_cred); +} + static void ext4_journal_abort_handle(const char *caller, unsigned int line, const char *err_fn, struct buffer_head *bh, @@ -234,6 +272,7 @@ int __ext4_forget(const char *where, unsigned int line, handle_t *handle, if (err) { ext4_journal_abort_handle(where, line, __func__, bh, handle, err); + ext4_set_errno(inode->i_sb, -err); __ext4_abort(inode->i_sb, where, line, "error %d when attempting revoke", err); } @@ -278,7 +317,7 @@ int __ext4_handle_dirty_metadata(const char *where, unsigned int line, handle->h_type, handle->h_line_no, handle->h_requested_credits, - handle->h_buffer_credits, err); + jbd2_handle_buffer_credits(handle), err); return err; } ext4_error_inode(inode, where, line, @@ -289,7 +328,8 @@ int __ext4_handle_dirty_metadata(const char *where, unsigned int line, handle->h_type, handle->h_line_no, handle->h_requested_credits, - handle->h_buffer_credits, err); + jbd2_handle_buffer_credits(handle), + err); } } else { if (inode) @@ -304,6 +344,7 @@ int __ext4_handle_dirty_metadata(const char *where, unsigned int line, es = EXT4_SB(inode->i_sb)->s_es; es->s_last_error_block = cpu_to_le64(bh->b_blocknr); + ext4_set_errno(inode->i_sb, EIO); ext4_error_inode(inode, where, line, bh->b_blocknr, "IO error syncing itable block"); diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h index ef8fcf7d0d3b..7ea4f6fa173b 100644 --- a/fs/ext4/ext4_jbd2.h +++ b/fs/ext4/ext4_jbd2.h @@ -261,7 +261,8 @@ int __ext4_handle_dirty_super(const char *where, unsigned int line, __ext4_handle_dirty_super(__func__, __LINE__, (handle), (sb)) handle_t *__ext4_journal_start_sb(struct super_block *sb, unsigned int line, - int type, int blocks, int rsv_blocks); + int type, int blocks, int rsv_blocks, + int revoke_creds); int __ext4_journal_stop(const char *where, unsigned int line, handle_t *handle); #define EXT4_NOJOURNAL_MAX_REF_COUNT ((unsigned long) 4096) @@ -288,28 +289,41 @@ static inline int ext4_handle_is_aborted(handle_t *handle) return 0; } -static inline int ext4_handle_has_enough_credits(handle_t *handle, int needed) +static inline int ext4_free_metadata_revoke_credits(struct super_block *sb, + int blocks) { - if (ext4_handle_valid(handle) && handle->h_buffer_credits < needed) - return 0; - return 1; + /* Freeing each metadata block can result in freeing one cluster */ + return blocks * EXT4_SB(sb)->s_cluster_ratio; +} + +static inline int ext4_trans_default_revoke_credits(struct super_block *sb) +{ + return ext4_free_metadata_revoke_credits(sb, 8); } #define ext4_journal_start_sb(sb, type, nblocks) \ - __ext4_journal_start_sb((sb), __LINE__, (type), (nblocks), 0) + __ext4_journal_start_sb((sb), __LINE__, (type), (nblocks), 0, \ + ext4_trans_default_revoke_credits(sb)) #define ext4_journal_start(inode, type, nblocks) \ - __ext4_journal_start((inode), __LINE__, (type), (nblocks), 0) + __ext4_journal_start((inode), __LINE__, (type), (nblocks), 0, \ + ext4_trans_default_revoke_credits((inode)->i_sb)) + +#define ext4_journal_start_with_reserve(inode, type, blocks, rsv_blocks)\ + __ext4_journal_start((inode), __LINE__, (type), (blocks), (rsv_blocks),\ + ext4_trans_default_revoke_credits((inode)->i_sb)) -#define ext4_journal_start_with_reserve(inode, type, blocks, rsv_blocks) \ - __ext4_journal_start((inode), __LINE__, (type), (blocks), (rsv_blocks)) +#define ext4_journal_start_with_revoke(inode, type, blocks, revoke_creds) \ + __ext4_journal_start((inode), __LINE__, (type), (blocks), 0, \ + (revoke_creds)) static inline handle_t *__ext4_journal_start(struct inode *inode, unsigned int line, int type, - int blocks, int rsv_blocks) + int blocks, int rsv_blocks, + int revoke_creds) { return __ext4_journal_start_sb(inode->i_sb, line, type, blocks, - rsv_blocks); + rsv_blocks, revoke_creds); } #define ext4_journal_stop(handle) \ @@ -332,20 +346,68 @@ static inline handle_t *ext4_journal_current_handle(void) return journal_current_handle(); } -static inline int ext4_journal_extend(handle_t *handle, int nblocks) +static inline int ext4_journal_extend(handle_t *handle, int nblocks, int revoke) { if (ext4_handle_valid(handle)) - return jbd2_journal_extend(handle, nblocks); + return jbd2_journal_extend(handle, nblocks, revoke); return 0; } -static inline int ext4_journal_restart(handle_t *handle, int nblocks) +static inline int ext4_journal_restart(handle_t *handle, int nblocks, + int revoke) { if (ext4_handle_valid(handle)) - return jbd2_journal_restart(handle, nblocks); + return jbd2__journal_restart(handle, nblocks, revoke, GFP_NOFS); return 0; } +int __ext4_journal_ensure_credits(handle_t *handle, int check_cred, + int extend_cred, int revoke_cred); + + +/* + * Ensure @handle has at least @check_creds credits available. If not, + * transaction will be extended or restarted to contain at least @extend_cred + * credits. Before restarting transaction @fn is executed to allow for cleanup + * before the transaction is restarted. + * + * The return value is < 0 in case of error, 0 in case the handle has enough + * credits or transaction extension succeeded, 1 in case transaction had to be + * restarted. + */ +#define ext4_journal_ensure_credits_fn(handle, check_cred, extend_cred, \ + revoke_cred, fn) \ +({ \ + __label__ __ensure_end; \ + int err = __ext4_journal_ensure_credits((handle), (check_cred), \ + (extend_cred), (revoke_cred)); \ + \ + if (err <= 0) \ + goto __ensure_end; \ + err = (fn); \ + if (err < 0) \ + goto __ensure_end; \ + err = ext4_journal_restart((handle), (extend_cred), (revoke_cred)); \ + if (err == 0) \ + err = 1; \ +__ensure_end: \ + err; \ +}) + +/* + * Ensure given handle has at least requested amount of credits available, + * possibly restarting transaction if needed. We also make sure the transaction + * has space for at least ext4_trans_default_revoke_credits(sb) revoke records + * as freeing one or two blocks is very common pattern and requesting this is + * very cheap. + */ +static inline int ext4_journal_ensure_credits(handle_t *handle, int credits, + int revoke_creds) +{ + return ext4_journal_ensure_credits_fn(handle, credits, credits, + revoke_creds, 0); +} + static inline int ext4_journal_blocks_per_page(struct inode *inode) { if (EXT4_JOURNAL(inode) != NULL) @@ -401,26 +463,7 @@ int ext4_force_commit(struct super_block *sb); #define EXT4_INODE_ORDERED_DATA_MODE 0x02 /* ordered data mode */ #define EXT4_INODE_WRITEBACK_DATA_MODE 0x04 /* writeback data mode */ -static inline int ext4_inode_journal_mode(struct inode *inode) -{ - if (EXT4_JOURNAL(inode) == NULL) - return EXT4_INODE_WRITEBACK_DATA_MODE; /* writeback */ - /* We do not support data journalling with delayed allocation */ - if (!S_ISREG(inode->i_mode) || - test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA || - (ext4_test_inode_flag(inode, EXT4_INODE_JOURNAL_DATA) && - !test_opt(inode->i_sb, DELALLOC))) { - /* We do not support data journalling for encrypted data */ - if (S_ISREG(inode->i_mode) && IS_ENCRYPTED(inode)) - return EXT4_INODE_ORDERED_DATA_MODE; /* ordered */ - return EXT4_INODE_JOURNAL_DATA_MODE; /* journal data */ - } - if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA) - return EXT4_INODE_ORDERED_DATA_MODE; /* ordered */ - if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA) - return EXT4_INODE_WRITEBACK_DATA_MODE; /* writeback */ - BUG(); -} +int ext4_inode_journal_mode(struct inode *inode); static inline int ext4_should_journal_data(struct inode *inode) { @@ -437,6 +480,19 @@ static inline int ext4_should_writeback_data(struct inode *inode) return ext4_inode_journal_mode(inode) & EXT4_INODE_WRITEBACK_DATA_MODE; } +static inline int ext4_free_data_revoke_credits(struct inode *inode, int blocks) +{ + if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) + return 0; + if (!ext4_should_journal_data(inode)) + return 0; + /* + * Data blocks in one extent are contiguous, just account for partial + * clusters at extent boundaries + */ + return blocks + 2*(EXT4_SB(inode->i_sb)->s_cluster_ratio - 1); +} + /* * This function controls whether or not we should try to go down the * dioread_nolock code paths, which makes it safe to avoid taking diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 92266a2da7d6..954013d6076b 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -100,29 +100,41 @@ static int ext4_split_extent_at(handle_t *handle, static int ext4_find_delayed_extent(struct inode *inode, struct extent_status *newes); -static int ext4_ext_truncate_extend_restart(handle_t *handle, - struct inode *inode, - int needed) +static int ext4_ext_trunc_restart_fn(struct inode *inode, int *dropped) { - int err; - - if (!ext4_handle_valid(handle)) - return 0; - if (handle->h_buffer_credits >= needed) - return 0; /* - * If we need to extend the journal get a few extra blocks - * while we're at it for efficiency's sake. + * 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. */ - needed += 3; - err = ext4_journal_extend(handle, needed - handle->h_buffer_credits); - if (err <= 0) - return err; - err = ext4_truncate_restart_trans(handle, inode, needed); - if (err == 0) - err = -EAGAIN; + BUG_ON(EXT4_JOURNAL(inode) == NULL); + ext4_discard_preallocations(inode); + up_write(&EXT4_I(inode)->i_data_sem); + *dropped = 1; + return 0; +} - return err; +/* + * Make sure 'handle' has at least 'check_cred' credits. If not, restart + * transaction with 'restart_cred' credits. The function drops i_data_sem + * when restarting transaction and gets it after transaction is restarted. + * + * The function returns 0 on success, 1 if transaction had to be restarted, + * and < 0 in case of fatal error. + */ +int ext4_datasem_ensure_credits(handle_t *handle, struct inode *inode, + int check_cred, int restart_cred, + int revoke_cred) +{ + int ret; + int dropped = 0; + + ret = ext4_journal_ensure_credits_fn(handle, check_cred, restart_cred, + revoke_cred, ext4_ext_trunc_restart_fn(inode, &dropped)); + if (dropped) + down_write(&EXT4_I(inode)->i_data_sem); + return ret; } /* @@ -149,8 +161,9 @@ static int ext4_ext_get_access(handle_t *handle, struct inode *inode, * - ENOMEM * - EIO */ -int __ext4_ext_dirty(const char *where, unsigned int line, handle_t *handle, - struct inode *inode, struct ext4_ext_path *path) +static int __ext4_ext_dirty(const char *where, unsigned int line, + handle_t *handle, struct inode *inode, + struct ext4_ext_path *path) { int err; @@ -167,6 +180,9 @@ int __ext4_ext_dirty(const char *where, unsigned int line, handle_t *handle, return err; } +#define ext4_ext_dirty(handle, inode, path) \ + __ext4_ext_dirty(__func__, __LINE__, (handle), (inode), (path)) + static ext4_fsblk_t ext4_ext_find_goal(struct inode *inode, struct ext4_ext_path *path, ext4_lblk_t block) @@ -297,53 +313,6 @@ ext4_force_split_extent_at(handle_t *handle, struct inode *inode, (nofail ? EXT4_GET_BLOCKS_METADATA_NOFAIL:0)); } -/* - * Calculate the number of metadata blocks needed - * to allocate @blocks - * Worse case is one block per extent - */ -int ext4_ext_calc_metadata_amount(struct inode *inode, ext4_lblk_t lblock) -{ - struct ext4_inode_info *ei = EXT4_I(inode); - int idxs; - - idxs = ((inode->i_sb->s_blocksize - sizeof(struct ext4_extent_header)) - / sizeof(struct ext4_extent_idx)); - - /* - * If the new delayed allocation block is contiguous with the - * previous da block, it can share index blocks with the - * previous block, so we only need to allocate a new index - * block every idxs leaf blocks. At ldxs**2 blocks, we need - * an additional index block, and at ldxs**3 blocks, yet - * another index blocks. - */ - if (ei->i_da_metadata_calc_len && - ei->i_da_metadata_calc_last_lblock+1 == lblock) { - int num = 0; - - if ((ei->i_da_metadata_calc_len % idxs) == 0) - num++; - if ((ei->i_da_metadata_calc_len % (idxs*idxs)) == 0) - num++; - if ((ei->i_da_metadata_calc_len % (idxs*idxs*idxs)) == 0) { - num++; - ei->i_da_metadata_calc_len = 0; - } else - ei->i_da_metadata_calc_len++; - ei->i_da_metadata_calc_last_lblock++; - return num; - } - - /* - * In the worst case we need a new set of index blocks at - * every level of the inode's extent tree. - */ - ei->i_da_metadata_calc_len = 1; - ei->i_da_metadata_calc_last_lblock = lblock; - return ext_depth(inode) + 1; -} - static int ext4_ext_max_entries(struct inode *inode, int depth) { @@ -480,6 +449,7 @@ static int __ext4_ext_check(const char *function, unsigned int line, return 0; corrupted: + ext4_set_errno(inode->i_sb, -err); ext4_error_inode(inode, function, line, 0, "pblk %llu bad header/extent: %s - magic %x, " "entries %u, max %u(%u), depth %u(%u)", @@ -498,6 +468,30 @@ int ext4_ext_check_inode(struct inode *inode) return ext4_ext_check(inode, ext_inode_hdr(inode), ext_depth(inode), 0); } +static void ext4_cache_extents(struct inode *inode, + struct ext4_extent_header *eh) +{ + struct ext4_extent *ex = EXT_FIRST_EXTENT(eh); + ext4_lblk_t prev = 0; + int i; + + for (i = le16_to_cpu(eh->eh_entries); i > 0; i--, ex++) { + unsigned int status = EXTENT_STATUS_WRITTEN; + ext4_lblk_t lblk = le32_to_cpu(ex->ee_block); + int len = ext4_ext_get_actual_len(ex); + + if (prev && (prev != lblk)) + ext4_es_cache_extent(inode, prev, lblk - prev, ~0, + EXTENT_STATUS_HOLE); + + if (ext4_ext_is_unwritten(ex)) + status = EXTENT_STATUS_UNWRITTEN; + ext4_es_cache_extent(inode, lblk, len, + ext4_ext_pblock(ex), status); + prev = lblk + len; + } +} + static struct buffer_head * __read_extent_tree_block(const char *function, unsigned int line, struct inode *inode, ext4_fsblk_t pblk, int depth, @@ -532,26 +526,7 @@ __read_extent_tree_block(const char *function, unsigned int line, */ if (!(flags & EXT4_EX_NOCACHE) && depth == 0) { struct ext4_extent_header *eh = ext_block_hdr(bh); - struct ext4_extent *ex = EXT_FIRST_EXTENT(eh); - ext4_lblk_t prev = 0; - int i; - - for (i = le16_to_cpu(eh->eh_entries); i > 0; i--, ex++) { - unsigned int status = EXTENT_STATUS_WRITTEN; - ext4_lblk_t lblk = le32_to_cpu(ex->ee_block); - int len = ext4_ext_get_actual_len(ex); - - if (prev && (prev != lblk)) - ext4_es_cache_extent(inode, prev, - lblk - prev, ~0, - EXTENT_STATUS_HOLE); - - if (ext4_ext_is_unwritten(ex)) - status = EXTENT_STATUS_UNWRITTEN; - ext4_es_cache_extent(inode, lblk, len, - ext4_ext_pblock(ex), status); - prev = lblk + len; - } + ext4_cache_extents(inode, eh); } return bh; errout: @@ -637,8 +612,9 @@ static void ext4_ext_show_path(struct inode *inode, struct ext4_ext_path *path) ext_debug("path:"); for (k = 0; k <= l; k++, path++) { if (path->p_idx) { - ext_debug(" %d->%llu", le32_to_cpu(path->p_idx->ei_block), - ext4_idx_pblock(path->p_idx)); + ext_debug(" %d->%llu", + le32_to_cpu(path->p_idx->ei_block), + ext4_idx_pblock(path->p_idx)); } else if (path->p_ext) { ext_debug(" %d:[%d]%d:%llu ", le32_to_cpu(path->p_ext->ee_block), @@ -719,11 +695,12 @@ void ext4_ext_drop_refs(struct ext4_ext_path *path) if (!path) return; depth = path->p_depth; - for (i = 0; i <= depth; i++, path++) + for (i = 0; i <= depth; i++, path++) { if (path->p_bh) { brelse(path->p_bh); path->p_bh = NULL; } + } } /* @@ -765,8 +742,8 @@ ext4_ext_binsearch_idx(struct inode *inode, chix = ix = EXT_FIRST_INDEX(eh); for (k = 0; k < le16_to_cpu(eh->eh_entries); k++, ix++) { - if (k != 0 && - le32_to_cpu(ix->ei_block) <= le32_to_cpu(ix[-1].ei_block)) { + if (k != 0 && le32_to_cpu(ix->ei_block) <= + le32_to_cpu(ix[-1].ei_block)) { printk(KERN_DEBUG "k=%d, ix=0x%p, " "first=0x%p\n", k, ix, EXT_FIRST_INDEX(eh)); @@ -899,6 +876,8 @@ ext4_find_extent(struct inode *inode, ext4_lblk_t block, path[0].p_bh = NULL; i = depth; + if (!(flags & EXT4_EX_NOCACHE) && depth == 0) + ext4_cache_extents(inode, eh); /* walk through the tree */ while (i) { ext_debug("depth %d: num %d, max %d\n", @@ -1620,17 +1599,16 @@ ext4_ext_next_allocated_block(struct ext4_ext_path *path) return EXT_MAX_BLOCKS; while (depth >= 0) { + struct ext4_ext_path *p = &path[depth]; + if (depth == path->p_depth) { /* leaf */ - if (path[depth].p_ext && - path[depth].p_ext != - EXT_LAST_EXTENT(path[depth].p_hdr)) - return le32_to_cpu(path[depth].p_ext[1].ee_block); + if (p->p_ext && p->p_ext != EXT_LAST_EXTENT(p->p_hdr)) + return le32_to_cpu(p->p_ext[1].ee_block); } else { /* index */ - if (path[depth].p_idx != - EXT_LAST_INDEX(path[depth].p_hdr)) - return le32_to_cpu(path[depth].p_idx[1].ei_block); + if (p->p_idx != EXT_LAST_INDEX(p->p_hdr)) + return le32_to_cpu(p->p_idx[1].ei_block); } depth--; } @@ -1730,9 +1708,9 @@ static int ext4_ext_correct_indexes(handle_t *handle, struct inode *inode, return err; } -int -ext4_can_extents_be_merged(struct inode *inode, struct ext4_extent *ex1, - struct ext4_extent *ex2) +static int ext4_can_extents_be_merged(struct inode *inode, + struct ext4_extent *ex1, + struct ext4_extent *ex2) { unsigned short ext1_ee_len, ext2_ee_len; @@ -1746,23 +1724,11 @@ ext4_can_extents_be_merged(struct inode *inode, struct ext4_extent *ex1, le32_to_cpu(ex2->ee_block)) return 0; - /* - * To allow future support for preallocated extents to be added - * as an RO_COMPAT feature, refuse to merge to extents if - * this can result in the top bit of ee_len being set. - */ if (ext1_ee_len + ext2_ee_len > EXT_INIT_MAX_LEN) return 0; - /* - * The check for IO to unwritten extent is somewhat racy as we - * increment i_unwritten / set EXT4_STATE_DIO_UNWRITTEN only after - * dropping i_data_sem. But reserved blocks should save us in that - * case. - */ + if (ext4_ext_is_unwritten(ex1) && - (ext4_test_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN) || - atomic_read(&EXT4_I(inode)->i_unwritten) || - (ext1_ee_len + ext2_ee_len > EXT_UNWRITTEN_MAX_LEN))) + ext1_ee_len + ext2_ee_len > EXT_UNWRITTEN_MAX_LEN) return 0; #ifdef AGGRESSIVE_TEST if (ext1_ee_len >= 4) @@ -1840,7 +1806,8 @@ static void ext4_ext_try_to_merge_up(handle_t *handle, * group descriptor to release the extent tree block. If we * can't get the journal credits, give up. */ - if (ext4_journal_extend(handle, 2)) + if (ext4_journal_extend(handle, 2, + ext4_free_metadata_revoke_credits(inode->i_sb, 1))) return; /* @@ -1864,13 +1831,14 @@ static void ext4_ext_try_to_merge_up(handle_t *handle, } /* - * This function tries to merge the @ex extent to neighbours in the tree. - * return 1 if merge left else 0. + * This function tries to merge the @ex extent to neighbours in the tree, then + * tries to collapse the extent tree into the inode. */ static void ext4_ext_try_to_merge(handle_t *handle, struct inode *inode, struct ext4_ext_path *path, - struct ext4_extent *ex) { + struct ext4_extent *ex) +{ struct ext4_extent_header *eh; unsigned int depth; int merge_done = 0; @@ -2315,6 +2283,52 @@ static int ext4_fill_fiemap_extents(struct inode *inode, return err; } +static int ext4_fill_es_cache_info(struct inode *inode, + ext4_lblk_t block, ext4_lblk_t num, + struct fiemap_extent_info *fieinfo) +{ + ext4_lblk_t next, end = block + num - 1; + struct extent_status es; + unsigned char blksize_bits = inode->i_sb->s_blocksize_bits; + unsigned int flags; + int err; + + while (block <= end) { + next = 0; + flags = 0; + if (!ext4_es_lookup_extent(inode, block, &next, &es)) + break; + if (ext4_es_is_unwritten(&es)) + flags |= FIEMAP_EXTENT_UNWRITTEN; + if (ext4_es_is_delayed(&es)) + flags |= (FIEMAP_EXTENT_DELALLOC | + FIEMAP_EXTENT_UNKNOWN); + if (ext4_es_is_hole(&es)) + flags |= EXT4_FIEMAP_EXTENT_HOLE; + if (next == 0) + flags |= FIEMAP_EXTENT_LAST; + if (flags & (FIEMAP_EXTENT_DELALLOC| + EXT4_FIEMAP_EXTENT_HOLE)) + es.es_pblk = 0; + else + es.es_pblk = ext4_es_pblock(&es); + err = fiemap_fill_next_extent(fieinfo, + (__u64)es.es_lblk << blksize_bits, + (__u64)es.es_pblk << blksize_bits, + (__u64)es.es_len << blksize_bits, + flags); + if (next == 0) + break; + block = next; + if (err < 0) + return err; + if (err == 1) + return 0; + } + return 0; +} + + /* * ext4_ext_determine_hole - determine hole around given block * @inode: inode we lookup in @@ -2681,7 +2695,7 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode, { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); int err = 0, correct_index = 0; - int depth = ext_depth(inode), credits; + int depth = ext_depth(inode), credits, revoke_credits; struct ext4_extent_header *eh; ext4_lblk_t a, b; unsigned num; @@ -2773,10 +2787,23 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode, credits += (ext_depth(inode)) + 1; } credits += EXT4_MAXQUOTAS_TRANS_BLOCKS(inode->i_sb); - - err = ext4_ext_truncate_extend_restart(handle, inode, credits); - if (err) + /* + * We may end up freeing some index blocks and data from the + * punched range. Note that partial clusters are accounted for + * by ext4_free_data_revoke_credits(). + */ + revoke_credits = + ext4_free_metadata_revoke_credits(inode->i_sb, + ext_depth(inode)) + + ext4_free_data_revoke_credits(inode, b - a + 1); + + err = ext4_datasem_ensure_credits(handle, inode, credits, + credits, revoke_credits); + if (err) { + if (err > 0) + err = -EAGAIN; goto out; + } err = ext4_ext_get_access(handle, inode, path + depth); if (err) @@ -2902,7 +2929,9 @@ int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start, ext_debug("truncate since %u to %u\n", start, end); /* probably first extent we're gonna free will be last in block */ - handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, depth + 1); + handle = ext4_journal_start_with_revoke(inode, EXT4_HT_TRUNCATE, + depth + 1, + ext4_free_metadata_revoke_credits(inode->i_sb, depth)); if (IS_ERR(handle)) return PTR_ERR(handle); @@ -3651,9 +3680,6 @@ static int ext4_ext_convert_to_initialized(handle_t *handle, max_zeroout = sbi->s_extent_max_zeroout_kb >> (inode->i_sb->s_blocksize_bits - 10); - if (IS_ENCRYPTED(inode)) - max_zeroout = 0; - /* * five cases: * 1. split the extent into three extents. @@ -3813,8 +3839,8 @@ static int ext4_convert_unwritten_extents_endio(handle_t *handle, * illegal. */ if (ee_block != map->m_lblk || ee_len > map->m_len) { -#ifdef EXT4_DEBUG - ext4_warning("Inode (%ld) finished: extent logical block %llu," +#ifdef CONFIG_EXT4_DEBUG + ext4_warning(inode->i_sb, "Inode (%ld) finished: extent logical block %llu," " len %u; IO logical block %llu, len %u", inode->i_ino, (unsigned long long)ee_block, ee_len, (unsigned long long)map->m_lblk, map->m_len); @@ -4639,6 +4665,10 @@ retry: return ret > 0 ? ret2 : ret; } +static int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len); + +static int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len); + static long ext4_zero_range(struct file *file, loff_t offset, loff_t len, int mode) { @@ -4656,9 +4686,6 @@ static long ext4_zero_range(struct file *file, loff_t offset, trace_ext4_zero_range(inode, offset, len, mode); - if (!S_ISREG(inode->i_mode)) - return -EINVAL; - /* Call ext4_force_commit to flush all data in case of data=journal. */ if (ext4_should_journal_data(inode)) { ret = ext4_force_commit(inode->i_sb); @@ -4698,7 +4725,7 @@ static long ext4_zero_range(struct file *file, loff_t offset, } if (!(mode & FALLOC_FL_KEEP_SIZE) && - (offset + len > i_size_read(inode) || + (offset + len > inode->i_size || offset + len > EXT4_I(inode)->i_disksize)) { new_size = offset + len; ret = inode_newsize_ok(inode, new_size); @@ -4782,7 +4809,7 @@ static long ext4_zero_range(struct file *file, loff_t offset, * Mark that we allocate beyond EOF so the subsequent truncate * can proceed even if the new size is the same as i_size. */ - if ((offset + len) > i_size_read(inode)) + if (offset + len > inode->i_size) ext4_set_inode_flag(inode, EXT4_INODE_EOFBLOCKS); } ext4_mark_inode_dirty(handle, inode); @@ -4823,14 +4850,9 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len) * range since we would need to re-encrypt blocks with a * different IV or XTS tweak (which are based on the logical * block number). - * - * XXX It's not clear why zero range isn't working, but we'll - * leave it disabled for encrypted inodes for now. This is a - * bug we should fix.... */ if (IS_ENCRYPTED(inode) && - (mode & (FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_INSERT_RANGE | - FALLOC_FL_ZERO_RANGE))) + (mode & (FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_INSERT_RANGE))) return -EOPNOTSUPP; /* Return error if mode is not supported */ @@ -4874,7 +4896,7 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len) } if (!(mode & FALLOC_FL_KEEP_SIZE) && - (offset + len > i_size_read(inode) || + (offset + len > inode->i_size || offset + len > EXT4_I(inode)->i_disksize)) { new_size = offset + len; ret = inode_newsize_ok(inode, new_size); @@ -4916,23 +4938,13 @@ int ext4_convert_unwritten_extents(handle_t *handle, struct inode *inode, int ret = 0; int ret2 = 0; struct ext4_map_blocks map; - unsigned int credits, blkbits = inode->i_blkbits; + unsigned int blkbits = inode->i_blkbits; + unsigned int credits = 0; map.m_lblk = offset >> blkbits; max_blocks = EXT4_MAX_BLOCKS(len, offset, blkbits); - /* - * This is somewhat ugly but the idea is clear: When transaction is - * reserved, everything goes into it. Otherwise we rather start several - * smaller transactions for conversion of each extent separately. - */ - if (handle) { - handle = ext4_journal_start_reserved(handle, - EXT4_HT_EXT_CONVERT); - if (IS_ERR(handle)) - return PTR_ERR(handle); - credits = 0; - } else { + if (!handle) { /* * credits to insert 1 extent into extent tree */ @@ -4963,11 +4975,40 @@ int ext4_convert_unwritten_extents(handle_t *handle, struct inode *inode, if (ret <= 0 || ret2) break; } - if (!credits) - ret2 = ext4_journal_stop(handle); return ret > 0 ? ret2 : ret; } +int ext4_convert_unwritten_io_end_vec(handle_t *handle, ext4_io_end_t *io_end) +{ + int ret, err = 0; + struct ext4_io_end_vec *io_end_vec; + + /* + * This is somewhat ugly but the idea is clear: When transaction is + * reserved, everything goes into it. Otherwise we rather start several + * smaller transactions for conversion of each extent separately. + */ + if (handle) { + handle = ext4_journal_start_reserved(handle, + EXT4_HT_EXT_CONVERT); + if (IS_ERR(handle)) + return PTR_ERR(handle); + } + + list_for_each_entry(io_end_vec, &io_end->list_vec, list) { + ret = ext4_convert_unwritten_extents(handle, io_end->inode, + io_end_vec->offset, + io_end_vec->size); + if (ret) + break; + } + + if (handle) + err = ext4_journal_stop(handle); + + return ret < 0 ? ret : err; +} + /* * If newes is not existing extent (newes->ec_pblk equals zero) find * delayed extent at start of newes and update newes accordingly and @@ -5017,8 +5058,6 @@ static int ext4_find_delayed_extent(struct inode *inode, return next_del; } -/* fiemap flags we can handle specified here */ -#define EXT4_FIEMAP_FLAGS (FIEMAP_FLAG_SYNC|FIEMAP_FLAG_XATTR) static int ext4_xattr_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo) @@ -5055,10 +5094,16 @@ static int ext4_xattr_fiemap(struct inode *inode, return (error < 0 ? error : 0); } -int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, - __u64 start, __u64 len) +static int _ext4_fiemap(struct inode *inode, + struct fiemap_extent_info *fieinfo, + __u64 start, __u64 len, + int (*fill)(struct inode *, ext4_lblk_t, + ext4_lblk_t, + struct fiemap_extent_info *)) { ext4_lblk_t start_blk; + u32 ext4_fiemap_flags = FIEMAP_FLAG_SYNC|FIEMAP_FLAG_XATTR; + int error = 0; if (ext4_has_inline_data(inode)) { @@ -5075,14 +5120,18 @@ int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, error = ext4_ext_precache(inode); if (error) return error; + fieinfo->fi_flags &= ~FIEMAP_FLAG_CACHE; } /* fallback to generic here if not in extents fmt */ - if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) + if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) && + fill == ext4_fill_fiemap_extents) return generic_block_fiemap(inode, fieinfo, start, len, ext4_get_block); - if (fiemap_check_flags(fieinfo, EXT4_FIEMAP_FLAGS)) + if (fill == ext4_fill_es_cache_info) + ext4_fiemap_flags &= FIEMAP_FLAG_XATTR; + if (fiemap_check_flags(fieinfo, ext4_fiemap_flags)) return -EBADR; if (fieinfo->fi_flags & FIEMAP_FLAG_XATTR) { @@ -5101,12 +5150,36 @@ int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, * Walk the extent tree gathering extent information * and pushing extents back to the user. */ - error = ext4_fill_fiemap_extents(inode, start_blk, - len_blks, fieinfo); + error = fill(inode, start_blk, len_blks, fieinfo); } return error; } +int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, + __u64 start, __u64 len) +{ + return _ext4_fiemap(inode, fieinfo, start, len, + ext4_fill_fiemap_extents); +} + +int ext4_get_es_cache(struct inode *inode, struct fiemap_extent_info *fieinfo, + __u64 start, __u64 len) +{ + if (ext4_has_inline_data(inode)) { + int has_inline; + + down_read(&EXT4_I(inode)->xattr_sem); + has_inline = ext4_has_inline_data(inode); + up_read(&EXT4_I(inode)->xattr_sem); + if (has_inline) + return 0; + } + + return _ext4_fiemap(inode, fieinfo, start, len, + ext4_fill_es_cache_info); +} + + /* * ext4_access_path: * Function to access the path buffer for marking it dirty. @@ -5128,13 +5201,10 @@ ext4_access_path(handle_t *handle, struct inode *inode, * descriptor) for each block group; assume two block * groups */ - if (handle->h_buffer_credits < 7) { - credits = ext4_writepage_trans_blocks(inode); - err = ext4_ext_truncate_extend_restart(handle, inode, credits); - /* EAGAIN is success */ - if (err && err != -EAGAIN) - return err; - } + credits = ext4_writepage_trans_blocks(inode); + err = ext4_datasem_ensure_credits(handle, inode, 7, credits, 0); + if (err < 0) + return err; err = ext4_ext_get_access(handle, inode, path); return err; @@ -5153,7 +5223,7 @@ ext4_ext_shift_path_extents(struct ext4_ext_path *path, ext4_lblk_t shift, { int depth, err = 0; struct ext4_extent *ex_start, *ex_last; - bool update = 0; + bool update = false; depth = path->p_depth; while (depth >= 0) { @@ -5169,7 +5239,7 @@ ext4_ext_shift_path_extents(struct ext4_ext_path *path, ext4_lblk_t shift, goto out; if (ex_start == EXT_FIRST_EXTENT(path[depth].p_hdr)) - update = 1; + update = true; while (ex_start <= ex_last) { if (SHIFT == SHIFT_LEFT) { @@ -5357,7 +5427,7 @@ out: * This implements the fallocate's collapse range functionality for ext4 * Returns: 0 and non-zero on error. */ -int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len) +static int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len) { struct super_block *sb = inode->i_sb; ext4_lblk_t punch_start, punch_stop; @@ -5374,12 +5444,8 @@ int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len) if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) return -EOPNOTSUPP; - /* Collapse range works only on fs block size aligned offsets. */ - if (offset & (EXT4_CLUSTER_SIZE(sb) - 1) || - len & (EXT4_CLUSTER_SIZE(sb) - 1)) - return -EINVAL; - - if (!S_ISREG(inode->i_mode)) + /* Collapse range works only on fs cluster size aligned regions. */ + if (!IS_ALIGNED(offset | len, EXT4_CLUSTER_SIZE(sb))) return -EINVAL; trace_ext4_collapse_range(inode, offset, len); @@ -5399,7 +5465,7 @@ int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len) * There is no need to overlap collapse range with EOF, in which case * it is effectively a truncate operation */ - if (offset + len >= i_size_read(inode)) { + if (offset + len >= inode->i_size) { ret = -EINVAL; goto out_mutex; } @@ -5477,7 +5543,7 @@ int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len) goto out_stop; } - new_size = i_size_read(inode) - len; + new_size = inode->i_size - len; i_size_write(inode, new_size); EXT4_I(inode)->i_disksize = new_size; @@ -5505,7 +5571,7 @@ out_mutex: * by len bytes. * Returns 0 on success, error otherwise. */ -int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len) +static int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len) { struct super_block *sb = inode->i_sb; handle_t *handle; @@ -5524,14 +5590,10 @@ int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len) if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) return -EOPNOTSUPP; - /* Insert range works only on fs block size aligned offsets. */ - if (offset & (EXT4_CLUSTER_SIZE(sb) - 1) || - len & (EXT4_CLUSTER_SIZE(sb) - 1)) + /* Insert range works only on fs cluster size aligned regions. */ + if (!IS_ALIGNED(offset | len, EXT4_CLUSTER_SIZE(sb))) return -EINVAL; - if (!S_ISREG(inode->i_mode)) - return -EOPNOTSUPP; - trace_ext4_insert_range(inode, offset, len); offset_lblk = offset >> EXT4_BLOCK_SIZE_BITS(sb); @@ -5551,14 +5613,14 @@ int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len) goto out_mutex; } - /* Check for wrap through zero */ - if (inode->i_size + len > inode->i_sb->s_maxbytes) { + /* Check whether the maximum file size would be exceeded */ + if (len > inode->i_sb->s_maxbytes - inode->i_size) { ret = -EFBIG; goto out_mutex; } - /* Offset should be less than i_size */ - if (offset >= i_size_read(inode)) { + /* Offset must be less than i_size */ + if (offset >= inode->i_size) { ret = -EINVAL; goto out_mutex; } diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c index 7521de2dcf3a..d996b44d2265 100644 --- a/fs/ext4/extents_status.c +++ b/fs/ext4/extents_status.c @@ -146,7 +146,7 @@ static struct kmem_cache *ext4_pending_cachep; static int __es_insert_extent(struct inode *inode, struct extent_status *newes); static int __es_remove_extent(struct inode *inode, ext4_lblk_t lblk, - ext4_lblk_t end); + ext4_lblk_t end, int *reserved); static int es_reclaim_extents(struct ext4_inode_info *ei, int *nr_to_scan); static int __es_shrink(struct ext4_sb_info *sbi, int nr_to_scan, struct ext4_inode_info *locked_ei); @@ -836,7 +836,7 @@ int ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk, ext4_es_insert_extent_check(inode, &newes); write_lock(&EXT4_I(inode)->i_es_lock); - err = __es_remove_extent(inode, lblk, end); + err = __es_remove_extent(inode, lblk, end, NULL); if (err != 0) goto error; retry: @@ -899,6 +899,7 @@ void ext4_es_cache_extent(struct inode *inode, ext4_lblk_t lblk, * Return: 1 on found, 0 on not */ int ext4_es_lookup_extent(struct inode *inode, ext4_lblk_t lblk, + ext4_lblk_t *next_lblk, struct extent_status *es) { struct ext4_es_tree *tree; @@ -947,9 +948,18 @@ out: es->es_pblk = es1->es_pblk; if (!ext4_es_is_referenced(es1)) ext4_es_set_referenced(es1); - stats->es_stats_cache_hits++; + percpu_counter_inc(&stats->es_stats_cache_hits); + if (next_lblk) { + node = rb_next(&es1->rb_node); + if (node) { + es1 = rb_entry(node, struct extent_status, + rb_node); + *next_lblk = es1->es_lblk; + } else + *next_lblk = 0; + } } else { - stats->es_stats_cache_misses++; + percpu_counter_inc(&stats->es_stats_cache_misses); } read_unlock(&EXT4_I(inode)->i_es_lock); @@ -958,8 +968,322 @@ out: return found; } +struct rsvd_count { + int ndelonly; + bool first_do_lblk_found; + ext4_lblk_t first_do_lblk; + ext4_lblk_t last_do_lblk; + struct extent_status *left_es; + bool partial; + ext4_lblk_t lclu; +}; + +/* + * init_rsvd - initialize reserved count data before removing block range + * in file from extent status tree + * + * @inode - file containing range + * @lblk - first block in range + * @es - pointer to first extent in range + * @rc - pointer to reserved count data + * + * Assumes es is not NULL + */ +static void init_rsvd(struct inode *inode, ext4_lblk_t lblk, + struct extent_status *es, struct rsvd_count *rc) +{ + struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); + struct rb_node *node; + + rc->ndelonly = 0; + + /* + * for bigalloc, note the first delonly block in the range has not + * been found, record the extent containing the block to the left of + * the region to be removed, if any, and note that there's no partial + * cluster to track + */ + if (sbi->s_cluster_ratio > 1) { + rc->first_do_lblk_found = false; + if (lblk > es->es_lblk) { + rc->left_es = es; + } else { + node = rb_prev(&es->rb_node); + rc->left_es = node ? rb_entry(node, + struct extent_status, + rb_node) : NULL; + } + rc->partial = false; + } +} + +/* + * count_rsvd - count the clusters containing delayed and not unwritten + * (delonly) blocks in a range within an extent and add to + * the running tally in rsvd_count + * + * @inode - file containing extent + * @lblk - first block in range + * @len - length of range in blocks + * @es - pointer to extent containing clusters to be counted + * @rc - pointer to reserved count data + * + * Tracks partial clusters found at the beginning and end of extents so + * they aren't overcounted when they span adjacent extents + */ +static void count_rsvd(struct inode *inode, ext4_lblk_t lblk, long len, + struct extent_status *es, struct rsvd_count *rc) +{ + struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); + ext4_lblk_t i, end, nclu; + + if (!ext4_es_is_delonly(es)) + return; + + WARN_ON(len <= 0); + + if (sbi->s_cluster_ratio == 1) { + rc->ndelonly += (int) len; + return; + } + + /* bigalloc */ + + i = (lblk < es->es_lblk) ? es->es_lblk : lblk; + end = lblk + (ext4_lblk_t) len - 1; + end = (end > ext4_es_end(es)) ? ext4_es_end(es) : end; + + /* record the first block of the first delonly extent seen */ + if (rc->first_do_lblk_found == false) { + rc->first_do_lblk = i; + rc->first_do_lblk_found = true; + } + + /* update the last lblk in the region seen so far */ + rc->last_do_lblk = end; + + /* + * if we're tracking a partial cluster and the current extent + * doesn't start with it, count it and stop tracking + */ + if (rc->partial && (rc->lclu != EXT4_B2C(sbi, i))) { + rc->ndelonly++; + rc->partial = false; + } + + /* + * if the first cluster doesn't start on a cluster boundary but + * ends on one, count it + */ + if (EXT4_LBLK_COFF(sbi, i) != 0) { + if (end >= EXT4_LBLK_CFILL(sbi, i)) { + rc->ndelonly++; + rc->partial = false; + i = EXT4_LBLK_CFILL(sbi, i) + 1; + } + } + + /* + * if the current cluster starts on a cluster boundary, count the + * number of whole delonly clusters in the extent + */ + if ((i + sbi->s_cluster_ratio - 1) <= end) { + nclu = (end - i + 1) >> sbi->s_cluster_bits; + rc->ndelonly += nclu; + i += nclu << sbi->s_cluster_bits; + } + + /* + * start tracking a partial cluster if there's a partial at the end + * of the current extent and we're not already tracking one + */ + if (!rc->partial && i <= end) { + rc->partial = true; + rc->lclu = EXT4_B2C(sbi, i); + } +} + +/* + * __pr_tree_search - search for a pending cluster reservation + * + * @root - root of pending reservation tree + * @lclu - logical cluster to search for + * + * Returns the pending reservation for the cluster identified by @lclu + * if found. If not, returns a reservation for the next cluster if any, + * and if not, returns NULL. + */ +static struct pending_reservation *__pr_tree_search(struct rb_root *root, + ext4_lblk_t lclu) +{ + struct rb_node *node = root->rb_node; + struct pending_reservation *pr = NULL; + + while (node) { + pr = rb_entry(node, struct pending_reservation, rb_node); + if (lclu < pr->lclu) + node = node->rb_left; + else if (lclu > pr->lclu) + node = node->rb_right; + else + return pr; + } + if (pr && lclu < pr->lclu) + return pr; + if (pr && lclu > pr->lclu) { + node = rb_next(&pr->rb_node); + return node ? rb_entry(node, struct pending_reservation, + rb_node) : NULL; + } + return NULL; +} + +/* + * get_rsvd - calculates and returns the number of cluster reservations to be + * released when removing a block range from the extent status tree + * and releases any pending reservations within the range + * + * @inode - file containing block range + * @end - last block in range + * @right_es - pointer to extent containing next block beyond end or NULL + * @rc - pointer to reserved count data + * + * The number of reservations to be released is equal to the number of + * clusters containing delayed and not unwritten (delonly) blocks within + * the range, minus the number of clusters still containing delonly blocks + * at the ends of the range, and minus the number of pending reservations + * within the range. + */ +static unsigned int get_rsvd(struct inode *inode, ext4_lblk_t end, + struct extent_status *right_es, + struct rsvd_count *rc) +{ + struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); + struct pending_reservation *pr; + struct ext4_pending_tree *tree = &EXT4_I(inode)->i_pending_tree; + struct rb_node *node; + ext4_lblk_t first_lclu, last_lclu; + bool left_delonly, right_delonly, count_pending; + struct extent_status *es; + + if (sbi->s_cluster_ratio > 1) { + /* count any remaining partial cluster */ + if (rc->partial) + rc->ndelonly++; + + if (rc->ndelonly == 0) + return 0; + + first_lclu = EXT4_B2C(sbi, rc->first_do_lblk); + last_lclu = EXT4_B2C(sbi, rc->last_do_lblk); + + /* + * decrease the delonly count by the number of clusters at the + * ends of the range that still contain delonly blocks - + * these clusters still need to be reserved + */ + left_delonly = right_delonly = false; + + es = rc->left_es; + while (es && ext4_es_end(es) >= + EXT4_LBLK_CMASK(sbi, rc->first_do_lblk)) { + if (ext4_es_is_delonly(es)) { + rc->ndelonly--; + left_delonly = true; + break; + } + node = rb_prev(&es->rb_node); + if (!node) + break; + es = rb_entry(node, struct extent_status, rb_node); + } + if (right_es && (!left_delonly || first_lclu != last_lclu)) { + if (end < ext4_es_end(right_es)) { + es = right_es; + } else { + node = rb_next(&right_es->rb_node); + es = node ? rb_entry(node, struct extent_status, + rb_node) : NULL; + } + while (es && es->es_lblk <= + EXT4_LBLK_CFILL(sbi, rc->last_do_lblk)) { + if (ext4_es_is_delonly(es)) { + rc->ndelonly--; + right_delonly = true; + break; + } + node = rb_next(&es->rb_node); + if (!node) + break; + es = rb_entry(node, struct extent_status, + rb_node); + } + } + + /* + * Determine the block range that should be searched for + * pending reservations, if any. Clusters on the ends of the + * original removed range containing delonly blocks are + * excluded. They've already been accounted for and it's not + * possible to determine if an associated pending reservation + * should be released with the information available in the + * extents status tree. + */ + if (first_lclu == last_lclu) { + if (left_delonly | right_delonly) + count_pending = false; + else + count_pending = true; + } else { + if (left_delonly) + first_lclu++; + if (right_delonly) + last_lclu--; + if (first_lclu <= last_lclu) + count_pending = true; + else + count_pending = false; + } + + /* + * a pending reservation found between first_lclu and last_lclu + * represents an allocated cluster that contained at least one + * delonly block, so the delonly total must be reduced by one + * for each pending reservation found and released + */ + if (count_pending) { + pr = __pr_tree_search(&tree->root, first_lclu); + while (pr && pr->lclu <= last_lclu) { + rc->ndelonly--; + node = rb_next(&pr->rb_node); + rb_erase(&pr->rb_node, &tree->root); + kmem_cache_free(ext4_pending_cachep, pr); + if (!node) + break; + pr = rb_entry(node, struct pending_reservation, + rb_node); + } + } + } + return rc->ndelonly; +} + + +/* + * __es_remove_extent - removes block range from extent status tree + * + * @inode - file containing range + * @lblk - first block in range + * @end - last block in range + * @reserved - number of cluster reservations released + * + * If @reserved is not NULL and delayed allocation is enabled, counts + * block/cluster reservations freed by removing range and if bigalloc + * enabled cancels pending reservations as needed. Returns 0 on success, + * error code on failure. + */ static int __es_remove_extent(struct inode *inode, ext4_lblk_t lblk, - ext4_lblk_t end) + ext4_lblk_t end, int *reserved) { struct ext4_es_tree *tree = &EXT4_I(inode)->i_es_tree; struct rb_node *node; @@ -968,9 +1292,14 @@ static int __es_remove_extent(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t len1, len2; ext4_fsblk_t block; int err; + bool count_reserved = true; + struct rsvd_count rc; + if (reserved == NULL || !test_opt(inode->i_sb, DELALLOC)) + count_reserved = false; retry: err = 0; + es = __es_tree_search(&tree->root, lblk); if (!es) goto out; @@ -979,6 +1308,8 @@ retry: /* Simply invalidate cache_es. */ tree->cache_es = NULL; + if (count_reserved) + init_rsvd(inode, lblk, es, &rc); orig_es.es_lblk = es->es_lblk; orig_es.es_len = es->es_len; @@ -1020,10 +1351,16 @@ retry: ext4_es_store_pblock(es, block); } } + if (count_reserved) + count_rsvd(inode, lblk, orig_es.es_len - len1 - len2, + &orig_es, &rc); goto out; } if (len1 > 0) { + if (count_reserved) + count_rsvd(inode, lblk, orig_es.es_len - len1, + &orig_es, &rc); node = rb_next(&es->rb_node); if (node) es = rb_entry(node, struct extent_status, rb_node); @@ -1032,6 +1369,8 @@ retry: } while (es && ext4_es_end(es) <= end) { + if (count_reserved) + count_rsvd(inode, es->es_lblk, es->es_len, es, &rc); node = rb_next(&es->rb_node); rb_erase(&es->rb_node, &tree->root); ext4_es_free_extent(inode, es); @@ -1046,6 +1385,9 @@ retry: ext4_lblk_t orig_len = es->es_len; len1 = ext4_es_end(es) - end; + if (count_reserved) + count_rsvd(inode, es->es_lblk, orig_len - len1, + es, &rc); es->es_lblk = end + 1; es->es_len = len1; if (ext4_es_is_written(es) || ext4_es_is_unwritten(es)) { @@ -1054,20 +1396,28 @@ retry: } } + if (count_reserved) + *reserved = get_rsvd(inode, end, es, &rc); out: return err; } /* - * ext4_es_remove_extent() removes a space from a extent status tree. + * ext4_es_remove_extent - removes block range from extent status tree * - * Return 0 on success, error code on failure. + * @inode - file containing range + * @lblk - first block in range + * @len - number of blocks to remove + * + * Reduces block/cluster reservation count and for bigalloc cancels pending + * reservations as needed. Returns 0 on success, error code on failure. */ int ext4_es_remove_extent(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t len) { ext4_lblk_t end; int err = 0; + int reserved = 0; trace_ext4_es_remove_extent(inode, lblk, len); es_debug("remove [%u/%u) from extent status tree of inode %lu\n", @@ -1085,9 +1435,10 @@ int ext4_es_remove_extent(struct inode *inode, ext4_lblk_t lblk, * is reclaimed. */ write_lock(&EXT4_I(inode)->i_es_lock); - err = __es_remove_extent(inode, lblk, end); + err = __es_remove_extent(inode, lblk, end, &reserved); write_unlock(&EXT4_I(inode)->i_es_lock); ext4_es_print_tree(inode); + ext4_da_release_space(inode, reserved); return err; } @@ -1235,9 +1586,9 @@ int ext4_seq_es_shrinker_info_show(struct seq_file *seq, void *v) seq_printf(seq, "stats:\n %lld objects\n %lld reclaimable objects\n", percpu_counter_sum_positive(&es_stats->es_stats_all_cnt), percpu_counter_sum_positive(&es_stats->es_stats_shk_cnt)); - seq_printf(seq, " %lu/%lu cache hits/misses\n", - es_stats->es_stats_cache_hits, - es_stats->es_stats_cache_misses); + seq_printf(seq, " %lld/%lld cache hits/misses\n", + percpu_counter_sum_positive(&es_stats->es_stats_cache_hits), + percpu_counter_sum_positive(&es_stats->es_stats_cache_misses)); if (inode_cnt) seq_printf(seq, " %d inodes on list\n", inode_cnt); @@ -1264,35 +1615,46 @@ int ext4_es_register_shrinker(struct ext4_sb_info *sbi) sbi->s_es_nr_inode = 0; spin_lock_init(&sbi->s_es_lock); sbi->s_es_stats.es_stats_shrunk = 0; - sbi->s_es_stats.es_stats_cache_hits = 0; - sbi->s_es_stats.es_stats_cache_misses = 0; + err = percpu_counter_init(&sbi->s_es_stats.es_stats_cache_hits, 0, + GFP_KERNEL); + if (err) + return err; + err = percpu_counter_init(&sbi->s_es_stats.es_stats_cache_misses, 0, + GFP_KERNEL); + if (err) + goto err1; sbi->s_es_stats.es_stats_scan_time = 0; sbi->s_es_stats.es_stats_max_scan_time = 0; err = percpu_counter_init(&sbi->s_es_stats.es_stats_all_cnt, 0, GFP_KERNEL); if (err) - return err; + goto err2; err = percpu_counter_init(&sbi->s_es_stats.es_stats_shk_cnt, 0, GFP_KERNEL); if (err) - goto err1; + goto err3; 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); if (err) - goto err2; + goto err4; return 0; - -err2: +err4: percpu_counter_destroy(&sbi->s_es_stats.es_stats_shk_cnt); -err1: +err3: percpu_counter_destroy(&sbi->s_es_stats.es_stats_all_cnt); +err2: + percpu_counter_destroy(&sbi->s_es_stats.es_stats_cache_misses); +err1: + percpu_counter_destroy(&sbi->s_es_stats.es_stats_cache_hits); return err; } void ext4_es_unregister_shrinker(struct ext4_sb_info *sbi) { + percpu_counter_destroy(&sbi->s_es_stats.es_stats_cache_hits); + percpu_counter_destroy(&sbi->s_es_stats.es_stats_cache_misses); percpu_counter_destroy(&sbi->s_es_stats.es_stats_all_cnt); percpu_counter_destroy(&sbi->s_es_stats.es_stats_shk_cnt); unregister_shrinker(&sbi->s_es_shrinker); @@ -1317,6 +1679,7 @@ static int es_do_reclaim_extents(struct ext4_inode_info *ei, ext4_lblk_t end, es = __es_tree_search(&tree->root, ei->i_es_shrink_lblk); if (!es) goto out_wrap; + while (*nr_to_scan > 0) { if (es->es_lblk > end) { ei->i_es_shrink_lblk = end + 1; @@ -1374,6 +1737,34 @@ static int es_reclaim_extents(struct ext4_inode_info *ei, int *nr_to_scan) return nr_shrunk; } +/* + * Called to support EXT4_IOC_CLEAR_ES_CACHE. We can only remove + * discretionary entries from the extent status cache. (Some entries + * must be present for proper operations.) + */ +void ext4_clear_inode_es(struct inode *inode) +{ + struct ext4_inode_info *ei = EXT4_I(inode); + struct extent_status *es; + struct ext4_es_tree *tree; + struct rb_node *node; + + write_lock(&ei->i_es_lock); + tree = &EXT4_I(inode)->i_es_tree; + tree->cache_es = NULL; + node = rb_first(&tree->root); + while (node) { + es = rb_entry(node, struct extent_status, rb_node); + node = rb_next(node); + if (!ext4_es_is_delayed(es)) { + rb_erase(&es->rb_node, &tree->root); + ext4_es_free_extent(inode, es); + } + } + ext4_clear_inode_state(inode, EXT4_STATE_EXT_PRECACHED); + write_unlock(&ei->i_es_lock); +} + #ifdef ES_DEBUG__ static void ext4_print_pending_tree(struct inode *inode) { @@ -1590,7 +1981,7 @@ int ext4_es_insert_delayed_block(struct inode *inode, ext4_lblk_t lblk, write_lock(&EXT4_I(inode)->i_es_lock); - err = __es_remove_extent(inode, lblk, lblk); + err = __es_remove_extent(inode, lblk, lblk, NULL); if (err != 0) goto error; retry: @@ -1779,93 +2170,3 @@ static void __revise_pending(struct inode *inode, ext4_lblk_t lblk, __remove_pending(inode, last); } } - -/* - * ext4_es_remove_blks - remove block range from extents status tree and - * reduce reservation count or cancel pending - * reservation as needed - * - * @inode - file containing range - * @lblk - first block in range - * @len - number of blocks to remove - * - */ -void ext4_es_remove_blks(struct inode *inode, ext4_lblk_t lblk, - ext4_lblk_t len) -{ - struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); - unsigned int clu_size, reserved = 0; - ext4_lblk_t last_lclu, first, length, remainder, last; - bool delonly; - int err = 0; - struct pending_reservation *pr; - struct ext4_pending_tree *tree; - - /* - * Process cluster by cluster for bigalloc - there may be up to - * two clusters in a 4k page with a 1k block size and two blocks - * per cluster. Also necessary for systems with larger page sizes - * and potentially larger block sizes. - */ - clu_size = sbi->s_cluster_ratio; - last_lclu = EXT4_B2C(sbi, lblk + len - 1); - - write_lock(&EXT4_I(inode)->i_es_lock); - - for (first = lblk, remainder = len; - remainder > 0; - first += length, remainder -= length) { - - if (EXT4_B2C(sbi, first) == last_lclu) - length = remainder; - else - length = clu_size - EXT4_LBLK_COFF(sbi, first); - - /* - * The BH_Delay flag, which triggers calls to this function, - * and the contents of the extents status tree can be - * inconsistent due to writepages activity. So, note whether - * the blocks to be removed actually belong to an extent with - * delayed only status. - */ - delonly = __es_scan_clu(inode, &ext4_es_is_delonly, first); - - /* - * because of the writepages effect, written and unwritten - * blocks could be removed here - */ - last = first + length - 1; - err = __es_remove_extent(inode, first, last); - if (err) - ext4_warning(inode->i_sb, - "%s: couldn't remove page (err = %d)", - __func__, err); - - /* non-bigalloc case: simply count the cluster for release */ - if (sbi->s_cluster_ratio == 1 && delonly) { - reserved++; - continue; - } - - /* - * bigalloc case: if all delayed allocated only blocks have - * just been removed from a cluster, either cancel a pending - * reservation if it exists or count a cluster for release - */ - if (delonly && - !__es_scan_clu(inode, &ext4_es_is_delonly, first)) { - pr = __get_pending(inode, EXT4_B2C(sbi, first)); - if (pr != NULL) { - tree = &EXT4_I(inode)->i_pending_tree; - rb_erase(&pr->rb_node, &tree->root); - kmem_cache_free(ext4_pending_cachep, pr); - } else { - reserved++; - } - } - } - - write_unlock(&EXT4_I(inode)->i_es_lock); - - ext4_da_release_space(inode, reserved); -} diff --git a/fs/ext4/extents_status.h b/fs/ext4/extents_status.h index 131a8b7df265..4ec30a798260 100644 --- a/fs/ext4/extents_status.h +++ b/fs/ext4/extents_status.h @@ -70,8 +70,8 @@ struct ext4_es_tree { struct ext4_es_stats { unsigned long es_stats_shrunk; - unsigned long es_stats_cache_hits; - unsigned long es_stats_cache_misses; + struct percpu_counter es_stats_cache_hits; + struct percpu_counter es_stats_cache_misses; u64 es_stats_scan_time; u64 es_stats_max_scan_time; struct percpu_counter es_stats_all_cnt; @@ -140,6 +140,7 @@ extern void ext4_es_find_extent_range(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t end, struct extent_status *es); extern int ext4_es_lookup_extent(struct inode *inode, ext4_lblk_t lblk, + ext4_lblk_t *next_lblk, struct extent_status *es); extern bool ext4_es_scan_range(struct inode *inode, int (*matching_fn)(struct extent_status *es), @@ -208,6 +209,12 @@ static inline ext4_fsblk_t ext4_es_pblock(struct extent_status *es) return es->es_pblk & ~ES_MASK; } +static inline ext4_fsblk_t ext4_es_show_pblock(struct extent_status *es) +{ + ext4_fsblk_t pblock = ext4_es_pblock(es); + return pblock == ~ES_MASK ? 0 : pblock; +} + static inline void ext4_es_store_pblock(struct extent_status *es, ext4_fsblk_t pb) { @@ -246,7 +253,6 @@ extern int ext4_es_insert_delayed_block(struct inode *inode, ext4_lblk_t lblk, bool allocated); extern unsigned int ext4_es_delayed_clu(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t len); -extern void ext4_es_remove_blks(struct inode *inode, ext4_lblk_t lblk, - ext4_lblk_t len); +extern void ext4_clear_inode_es(struct inode *inode); #endif /* _EXT4_EXTENTS_STATUS_H */ diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 70b0438dbc94..5f225881176b 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -29,10 +29,58 @@ #include <linux/pagevec.h> #include <linux/uio.h> #include <linux/mman.h> +#include <linux/backing-dev.h> #include "ext4.h" #include "ext4_jbd2.h" #include "xattr.h" #include "acl.h" +#include "truncate.h" + +static bool ext4_dio_supported(struct inode *inode) +{ + 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)) + return false; + return true; +} + +static ssize_t ext4_dio_read_iter(struct kiocb *iocb, struct iov_iter *to) +{ + ssize_t ret; + struct inode *inode = file_inode(iocb->ki_filp); + + if (iocb->ki_flags & IOCB_NOWAIT) { + if (!inode_trylock_shared(inode)) + return -EAGAIN; + } else { + inode_lock_shared(inode); + } + + if (!ext4_dio_supported(inode)) { + inode_unlock_shared(inode); + /* + * Fallback to buffered I/O if the operation being performed on + * the inode is not supported by direct I/O. The IOCB_DIRECT + * flag needs to be cleared here in order to ensure that the + * direct I/O path within generic_file_read_iter() is not + * taken. + */ + iocb->ki_flags &= ~IOCB_DIRECT; + return generic_file_read_iter(iocb, to); + } + + ret = iomap_dio_rw(iocb, to, &ext4_iomap_ops, NULL, + is_sync_kiocb(iocb)); + inode_unlock_shared(inode); + + file_accessed(iocb->ki_filp); + return ret; +} #ifdef CONFIG_FS_DAX static ssize_t ext4_dax_read_iter(struct kiocb *iocb, struct iov_iter *to) @@ -40,9 +88,10 @@ static ssize_t ext4_dax_read_iter(struct kiocb *iocb, struct iov_iter *to) struct inode *inode = file_inode(iocb->ki_filp); ssize_t ret; - if (!inode_trylock_shared(inode)) { - if (iocb->ki_flags & IOCB_NOWAIT) + if (iocb->ki_flags & IOCB_NOWAIT) { + if (!inode_trylock_shared(inode)) return -EAGAIN; + } else { inode_lock_shared(inode); } /* @@ -64,16 +113,21 @@ static ssize_t ext4_dax_read_iter(struct kiocb *iocb, struct iov_iter *to) static ssize_t ext4_file_read_iter(struct kiocb *iocb, struct iov_iter *to) { - if (unlikely(ext4_forced_shutdown(EXT4_SB(file_inode(iocb->ki_filp)->i_sb)))) + struct inode *inode = file_inode(iocb->ki_filp); + + if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb)))) return -EIO; if (!iov_iter_count(to)) return 0; /* skip atime */ #ifdef CONFIG_FS_DAX - if (IS_DAX(file_inode(iocb->ki_filp))) + if (IS_DAX(inode)) return ext4_dax_read_iter(iocb, to); #endif + if (iocb->ki_flags & IOCB_DIRECT) + return ext4_dio_read_iter(iocb, to); + return generic_file_read_iter(iocb, to); } @@ -103,13 +157,6 @@ static int ext4_release_file(struct inode *inode, struct file *filp) return 0; } -static void ext4_unwritten_wait(struct inode *inode) -{ - wait_queue_head_t *wq = ext4_ioend_wq(inode); - - wait_event(*wq, (atomic_read(&EXT4_I(inode)->i_unwritten) == 0)); -} - /* * This tests whether the IO in question is block-aligned or not. * Ext4 utilizes unwritten extents when hole-filling during direct IO, and they @@ -119,19 +166,25 @@ static void ext4_unwritten_wait(struct inode *inode) * threads are at work on the same unwritten block, they must be synchronized * or one thread will zero the other's data, causing corruption. */ -static int -ext4_unaligned_aio(struct inode *inode, struct iov_iter *from, loff_t pos) +static bool +ext4_unaligned_io(struct inode *inode, struct iov_iter *from, loff_t pos) { struct super_block *sb = inode->i_sb; - int blockmask = sb->s_blocksize - 1; - - if (pos >= ALIGN(i_size_read(inode), sb->s_blocksize)) - return 0; + unsigned long blockmask = sb->s_blocksize - 1; if ((pos | iov_iter_alignment(from)) & blockmask) - return 1; + return true; - return 0; + return false; +} + +static bool +ext4_extending_io(struct inode *inode, loff_t offset, size_t len) +{ + if (offset + len > i_size_read(inode) || + offset + len > EXT4_I(inode)->i_disksize) + return true; + return false; } /* Is IO overwriting allocated and initialized blocks? */ @@ -157,18 +210,19 @@ static bool ext4_overwrite_io(struct inode *inode, loff_t pos, loff_t len) return err == blklen && (map.m_flags & EXT4_MAP_MAPPED); } -static ssize_t ext4_write_checks(struct kiocb *iocb, struct iov_iter *from) +static ssize_t ext4_generic_write_checks(struct kiocb *iocb, + struct iov_iter *from) { struct inode *inode = file_inode(iocb->ki_filp); ssize_t ret; + if (unlikely(IS_IMMUTABLE(inode))) + return -EPERM; + ret = generic_write_checks(iocb, from); if (ret <= 0) return ret; - if (unlikely(IS_IMMUTABLE(inode))) - return -EPERM; - /* * If we have encountered a bitmap-format file, the size limit * is smaller than s_maxbytes, which is for extent-mapped files. @@ -180,112 +234,413 @@ static ssize_t ext4_write_checks(struct kiocb *iocb, struct iov_iter *from) return -EFBIG; iov_iter_truncate(from, sbi->s_bitmap_maxbytes - iocb->ki_pos); } + return iov_iter_count(from); } -#ifdef CONFIG_FS_DAX -static ssize_t -ext4_dax_write_iter(struct kiocb *iocb, struct iov_iter *from) +static ssize_t ext4_write_checks(struct kiocb *iocb, struct iov_iter *from) +{ + ssize_t ret, count; + + count = ext4_generic_write_checks(iocb, from); + if (count <= 0) + return count; + + ret = file_modified(iocb->ki_filp); + if (ret) + return ret; + return count; +} + +static ssize_t ext4_buffered_write_iter(struct kiocb *iocb, + struct iov_iter *from) { - struct inode *inode = file_inode(iocb->ki_filp); ssize_t ret; + struct inode *inode = file_inode(iocb->ki_filp); - if (!inode_trylock(inode)) { - if (iocb->ki_flags & IOCB_NOWAIT) - return -EAGAIN; - inode_lock(inode); - } + if (iocb->ki_flags & IOCB_NOWAIT) + return -EOPNOTSUPP; + + inode_lock(inode); ret = ext4_write_checks(iocb, from); if (ret <= 0) goto out; - ret = file_remove_privs(iocb->ki_filp); - if (ret) - goto out; - ret = file_update_time(iocb->ki_filp); - if (ret) - goto out; - ret = dax_iomap_rw(iocb, from, &ext4_iomap_ops); + current->backing_dev_info = inode_to_bdi(inode); + ret = generic_perform_write(iocb->ki_filp, from, iocb->ki_pos); + current->backing_dev_info = NULL; + out: inode_unlock(inode); - if (ret > 0) + if (likely(ret > 0)) { + iocb->ki_pos += ret; ret = generic_write_sync(iocb, ret); + } + return ret; } -#endif -static ssize_t -ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from) +static ssize_t ext4_handle_inode_extension(struct inode *inode, loff_t offset, + ssize_t written, size_t count) { - struct inode *inode = file_inode(iocb->ki_filp); - int o_direct = iocb->ki_flags & IOCB_DIRECT; - int unaligned_aio = 0; - int overwrite = 0; - ssize_t ret; + handle_t *handle; + bool truncate = false; + u8 blkbits = inode->i_blkbits; + ext4_lblk_t written_blk, end_blk; - if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb)))) - return -EIO; + /* + * Note that EXT4_I(inode)->i_disksize can get extended up to + * inode->i_size while the I/O was running due to writeback of delalloc + * blocks. But, the code in ext4_iomap_alloc() is careful to use + * zeroed/unwritten extents if this is possible; thus we won't leave + * uninitialized blocks in a file even if we didn't succeed in writing + * as much as we intended. + */ + WARN_ON_ONCE(i_size_read(inode) < EXT4_I(inode)->i_disksize); + if (offset + count <= EXT4_I(inode)->i_disksize) { + /* + * We need to ensure that the inode is removed from the orphan + * list if it has been added prematurely, due to writeback of + * delalloc blocks. + */ + if (!list_empty(&EXT4_I(inode)->i_orphan) && inode->i_nlink) { + handle = ext4_journal_start(inode, EXT4_HT_INODE, 2); + + if (IS_ERR(handle)) { + ext4_orphan_del(NULL, inode); + return PTR_ERR(handle); + } + + ext4_orphan_del(handle, inode); + ext4_journal_stop(handle); + } -#ifdef CONFIG_FS_DAX - if (IS_DAX(inode)) - return ext4_dax_write_iter(iocb, from); -#endif - if (!o_direct && (iocb->ki_flags & IOCB_NOWAIT)) - return -EOPNOTSUPP; + return written; + } - if (!inode_trylock(inode)) { - if (iocb->ki_flags & IOCB_NOWAIT) - return -EAGAIN; - inode_lock(inode); + if (written < 0) + goto truncate; + + handle = ext4_journal_start(inode, EXT4_HT_INODE, 2); + if (IS_ERR(handle)) { + written = PTR_ERR(handle); + goto truncate; } - ret = ext4_write_checks(iocb, from); + if (ext4_update_inode_size(inode, offset + written)) + ext4_mark_inode_dirty(handle, inode); + + /* + * We may need to truncate allocated but not written blocks beyond EOF. + */ + written_blk = ALIGN(offset + written, 1 << blkbits); + end_blk = ALIGN(offset + count, 1 << blkbits); + if (written_blk < end_blk && ext4_can_truncate(inode)) + truncate = true; + + /* + * Remove the inode from the orphan list if it has been extended and + * everything went OK. + */ + if (!truncate && inode->i_nlink) + ext4_orphan_del(handle, inode); + ext4_journal_stop(handle); + + if (truncate) { +truncate: + ext4_truncate_failed_write(inode); + /* + * If the truncate operation failed early, then the inode may + * still be on the orphan list. In that case, we need to try + * remove the inode from the in-memory linked list. + */ + if (inode->i_nlink) + ext4_orphan_del(NULL, inode); + } + + return written; +} + +static int ext4_dio_write_end_io(struct kiocb *iocb, ssize_t size, + int error, unsigned int flags) +{ + loff_t offset = iocb->ki_pos; + struct inode *inode = file_inode(iocb->ki_filp); + + if (error) + return error; + + if (size && flags & IOMAP_DIO_UNWRITTEN) + return ext4_convert_unwritten_extents(NULL, inode, + offset, size); + + return 0; +} + +static const struct iomap_dio_ops ext4_dio_write_ops = { + .end_io = ext4_dio_write_end_io, +}; + +/* + * The intention here is to start with shared lock acquired then see if any + * condition requires an exclusive inode lock. If yes, then we restart the + * whole operation by releasing the shared lock and acquiring exclusive lock. + * + * - For unaligned_io we never take shared lock as it may cause data corruption + * when two unaligned IO tries to modify the same block e.g. while zeroing. + * + * - For extending writes case we don't take the shared lock, since it requires + * updating inode i_disksize and/or orphan handling with exclusive lock. + * + * - shared locking will only be true mostly with overwrites. Otherwise we will + * switch to exclusive i_rwsem lock. + */ +static ssize_t ext4_dio_write_checks(struct kiocb *iocb, struct iov_iter *from, + bool *ilock_shared, bool *extend) +{ + struct file *file = iocb->ki_filp; + struct inode *inode = file_inode(file); + loff_t offset; + size_t count; + ssize_t ret; + +restart: + ret = ext4_generic_write_checks(iocb, from); if (ret <= 0) goto out; + offset = iocb->ki_pos; + count = ret; + if (ext4_extending_io(inode, offset, count)) + *extend = true; /* - * Unaligned direct AIO must be serialized among each other as zeroing - * of partial blocks of two competing unaligned AIOs can result in data - * corruption. + * Determine whether the IO operation will overwrite allocated + * and initialized blocks. + * We need exclusive i_rwsem for changing security info + * in file_modified(). */ - if (o_direct && ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS) && - !is_sync_kiocb(iocb) && - ext4_unaligned_aio(inode, from, iocb->ki_pos)) { - unaligned_aio = 1; - ext4_unwritten_wait(inode); + if (*ilock_shared && (!IS_NOSEC(inode) || *extend || + !ext4_overwrite_io(inode, offset, count))) { + inode_unlock_shared(inode); + *ilock_shared = false; + inode_lock(inode); + goto restart; } - iocb->private = &overwrite; - /* Check whether we do a DIO overwrite or not */ - if (o_direct && !unaligned_aio) { - if (ext4_overwrite_io(inode, iocb->ki_pos, iov_iter_count(from))) { - if (ext4_should_dioread_nolock(inode)) - overwrite = 1; - } else if (iocb->ki_flags & IOCB_NOWAIT) { - ret = -EAGAIN; - goto out; + ret = file_modified(file); + if (ret < 0) + goto out; + + return count; +out: + if (*ilock_shared) + inode_unlock_shared(inode); + else + inode_unlock(inode); + return ret; +} + +static ssize_t ext4_dio_write_iter(struct kiocb *iocb, struct iov_iter *from) +{ + ssize_t ret; + handle_t *handle; + struct inode *inode = file_inode(iocb->ki_filp); + loff_t offset = iocb->ki_pos; + size_t count = iov_iter_count(from); + const struct iomap_ops *iomap_ops = &ext4_iomap_ops; + bool extend = false, unaligned_io = false; + bool ilock_shared = true; + + /* + * We initially start with shared inode lock unless it is + * unaligned IO which needs exclusive lock anyways. + */ + if (ext4_unaligned_io(inode, from, offset)) { + unaligned_io = true; + ilock_shared = false; + } + /* + * Quick check here without any i_rwsem lock to see if it is extending + * IO. A more reliable check is done in ext4_dio_write_checks() with + * proper locking in place. + */ + if (offset + count > i_size_read(inode)) + ilock_shared = false; + + if (iocb->ki_flags & IOCB_NOWAIT) { + if (ilock_shared) { + if (!inode_trylock_shared(inode)) + return -EAGAIN; + } else { + if (!inode_trylock(inode)) + return -EAGAIN; } + } else { + if (ilock_shared) + inode_lock_shared(inode); + else + inode_lock(inode); } - ret = __generic_file_write_iter(iocb, from); + /* Fallback to buffered I/O if the inode does not support direct I/O. */ + if (!ext4_dio_supported(inode)) { + if (ilock_shared) + inode_unlock_shared(inode); + else + inode_unlock(inode); + return ext4_buffered_write_iter(iocb, from); + } + + ret = ext4_dio_write_checks(iocb, from, &ilock_shared, &extend); + if (ret <= 0) + return ret; + + offset = iocb->ki_pos; + count = ret; + /* - * Unaligned direct AIO must be the only IO in flight. Otherwise - * overlapping aligned IO after unaligned might result in data + * Unaligned direct IO must be serialized among each other as zeroing + * of partial blocks of two competing unaligned IOs can result in data * corruption. + * + * So we make sure we don't allow any unaligned IO in flight. + * For IOs where we need not wait (like unaligned non-AIO DIO), + * below inode_dio_wait() may anyway become a no-op, since we start + * with exclusive lock. */ - if (ret == -EIOCBQUEUED && unaligned_aio) - ext4_unwritten_wait(inode); - inode_unlock(inode); + if (unaligned_io) + inode_dio_wait(inode); - if (ret > 0) - ret = generic_write_sync(iocb, ret); + if (extend) { + handle = ext4_journal_start(inode, EXT4_HT_INODE, 2); + if (IS_ERR(handle)) { + ret = PTR_ERR(handle); + goto out; + } + + ret = ext4_orphan_add(handle, inode); + if (ret) { + ext4_journal_stop(handle); + goto out; + } + + ext4_journal_stop(handle); + } + + if (ilock_shared) + iomap_ops = &ext4_iomap_overwrite_ops; + ret = iomap_dio_rw(iocb, from, iomap_ops, &ext4_dio_write_ops, + is_sync_kiocb(iocb) || unaligned_io || extend); + + if (extend) + ret = ext4_handle_inode_extension(inode, offset, ret, count); + +out: + if (ilock_shared) + inode_unlock_shared(inode); + else + inode_unlock(inode); + + if (ret >= 0 && iov_iter_count(from)) { + ssize_t err; + loff_t endbyte; + + offset = iocb->ki_pos; + err = ext4_buffered_write_iter(iocb, from); + if (err < 0) + return err; + + /* + * We need to ensure that the pages within the page cache for + * the range covered by this I/O are written to disk and + * invalidated. This is in attempt to preserve the expected + * direct I/O semantics in the case we fallback to buffered I/O + * to complete off the I/O request. + */ + ret += err; + endbyte = offset + err - 1; + err = filemap_write_and_wait_range(iocb->ki_filp->f_mapping, + offset, endbyte); + if (!err) + invalidate_mapping_pages(iocb->ki_filp->f_mapping, + offset >> PAGE_SHIFT, + endbyte >> PAGE_SHIFT); + } return ret; +} +#ifdef CONFIG_FS_DAX +static ssize_t +ext4_dax_write_iter(struct kiocb *iocb, struct iov_iter *from) +{ + ssize_t ret; + size_t count; + loff_t offset; + handle_t *handle; + bool extend = false; + struct inode *inode = file_inode(iocb->ki_filp); + + if (iocb->ki_flags & IOCB_NOWAIT) { + if (!inode_trylock(inode)) + return -EAGAIN; + } else { + inode_lock(inode); + } + + ret = ext4_write_checks(iocb, from); + if (ret <= 0) + goto out; + + offset = iocb->ki_pos; + count = iov_iter_count(from); + + if (offset + count > EXT4_I(inode)->i_disksize) { + handle = ext4_journal_start(inode, EXT4_HT_INODE, 2); + if (IS_ERR(handle)) { + ret = PTR_ERR(handle); + goto out; + } + + ret = ext4_orphan_add(handle, inode); + if (ret) { + ext4_journal_stop(handle); + goto out; + } + + extend = true; + ext4_journal_stop(handle); + } + + ret = dax_iomap_rw(iocb, from, &ext4_iomap_ops); + + if (extend) + ret = ext4_handle_inode_extension(inode, offset, ret, count); out: inode_unlock(inode); + if (ret > 0) + ret = generic_write_sync(iocb, ret); return ret; } +#endif + +static ssize_t +ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from) +{ + struct inode *inode = file_inode(iocb->ki_filp); + + if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb)))) + return -EIO; + +#ifdef CONFIG_FS_DAX + if (IS_DAX(inode)) + return ext4_dax_write_iter(iocb, from); +#endif + if (iocb->ki_flags & IOCB_DIRECT) + return ext4_dio_write_iter(iocb, from); + + return ext4_buffered_write_iter(iocb, from); +} #ifdef CONFIG_FS_DAX static vm_fault_t ext4_dax_huge_fault(struct vm_fault *vmf, @@ -457,6 +812,10 @@ static int ext4_file_open(struct inode * inode, struct file * filp) if (ret) return ret; + ret = fsverity_file_open(inode, filp); + if (ret) + return ret; + /* * Set up the jbd2_inode if we are opening the inode for * writing and the journal is present @@ -492,12 +851,14 @@ loff_t ext4_llseek(struct file *file, loff_t offset, int whence) maxbytes, i_size_read(inode)); case SEEK_HOLE: inode_lock_shared(inode); - offset = iomap_seek_hole(inode, offset, &ext4_iomap_ops); + offset = iomap_seek_hole(inode, offset, + &ext4_iomap_report_ops); inode_unlock_shared(inode); break; case SEEK_DATA: inode_lock_shared(inode); - offset = iomap_seek_data(inode, offset, &ext4_iomap_ops); + offset = iomap_seek_data(inode, offset, + &ext4_iomap_report_ops); inode_unlock_shared(inode); break; } diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c index 5508baa11bb6..e10206e7f4bb 100644 --- a/fs/ext4/fsync.c +++ b/fs/ext4/fsync.c @@ -80,6 +80,43 @@ static int ext4_sync_parent(struct inode *inode) return ret; } +static int ext4_fsync_nojournal(struct inode *inode, bool datasync, + bool *needs_barrier) +{ + int ret, err; + + ret = sync_mapping_buffers(inode->i_mapping); + if (!(inode->i_state & I_DIRTY_ALL)) + return ret; + if (datasync && !(inode->i_state & I_DIRTY_DATASYNC)) + return ret; + + err = sync_inode_metadata(inode, 1); + if (!ret) + ret = err; + + if (!ret) + ret = ext4_sync_parent(inode); + if (test_opt(inode->i_sb, BARRIER)) + *needs_barrier = true; + + return ret; +} + +static int ext4_fsync_journal(struct inode *inode, bool datasync, + bool *needs_barrier) +{ + struct ext4_inode_info *ei = EXT4_I(inode); + journal_t *journal = EXT4_SB(inode->i_sb)->s_journal; + tid_t commit_tid = datasync ? ei->i_datasync_tid : ei->i_sync_tid; + + if (journal->j_flags & JBD2_BARRIER && + !jbd2_trans_will_send_data_barrier(journal, commit_tid)) + *needs_barrier = true; + + return jbd2_complete_transaction(journal, commit_tid); +} + /* * akpm: A new design for ext4_sync_file(). * @@ -91,17 +128,14 @@ static int ext4_sync_parent(struct inode *inode) * What we do is just kick off a commit and wait on it. This will snapshot the * inode to disk. */ - int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync) { - struct inode *inode = file->f_mapping->host; - struct ext4_inode_info *ei = EXT4_I(inode); - journal_t *journal = EXT4_SB(inode->i_sb)->s_journal; int ret = 0, err; - tid_t commit_tid; bool needs_barrier = false; + struct inode *inode = file->f_mapping->host; + struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); - if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb)))) + if (unlikely(ext4_forced_shutdown(sbi))) return -EIO; J_ASSERT(ext4_journal_current_handle() == NULL); @@ -111,23 +145,15 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync) if (sb_rdonly(inode->i_sb)) { /* Make sure that we read updated s_mount_flags value */ smp_rmb(); - if (EXT4_SB(inode->i_sb)->s_mount_flags & EXT4_MF_FS_ABORTED) + if (sbi->s_mount_flags & EXT4_MF_FS_ABORTED) ret = -EROFS; goto out; } - if (!journal) { - ret = __generic_file_fsync(file, start, end, datasync); - if (!ret) - ret = ext4_sync_parent(inode); - if (test_opt(inode->i_sb, BARRIER)) - goto issue_flush; - goto out; - } - ret = file_write_and_wait_range(file, start, end); if (ret) return ret; + /* * data=writeback,ordered: * The caller's filemap_fdatawrite()/wait will sync the data. @@ -142,18 +168,14 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync) * (they were dirtied by commit). But that's OK - the blocks are * safe in-journal, which is all fsync() needs to ensure. */ - if (ext4_should_journal_data(inode)) { + if (!sbi->s_journal) + ret = ext4_fsync_nojournal(inode, datasync, &needs_barrier); + else if (ext4_should_journal_data(inode)) ret = ext4_force_commit(inode->i_sb); - goto out; - } + else + ret = ext4_fsync_journal(inode, datasync, &needs_barrier); - commit_tid = datasync ? ei->i_datasync_tid : ei->i_sync_tid; - if (journal->j_flags & JBD2_BARRIER && - !jbd2_trans_will_send_data_barrier(journal, commit_tid)) - needs_barrier = true; - ret = jbd2_complete_transaction(journal, commit_tid); if (needs_barrier) { - issue_flush: err = blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL); if (!ret) ret = err; diff --git a/fs/ext4/hash.c b/fs/ext4/hash.c index d358bfcb6b3f..3e133793a5a3 100644 --- a/fs/ext4/hash.c +++ b/fs/ext4/hash.c @@ -280,7 +280,7 @@ int ext4fs_dirhash(const struct inode *dir, const char *name, int len, unsigned char *buff; struct qstr qstr = {.name = name, .len = len }; - if (len && IS_CASEFOLDED(dir)) { + if (len && IS_CASEFOLDED(dir) && um) { buff = kzalloc(sizeof(char) * PATH_MAX, GFP_KERNEL); if (!buff) return -ENOMEM; diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index 764ff4c56233..c66e8f9451a2 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -94,7 +94,8 @@ static int ext4_validate_inode_bitmap(struct super_block *sb, goto verified; blk = ext4_inode_bitmap(sb, desc); if (!ext4_inode_bitmap_csum_verify(sb, block_group, desc, bh, - EXT4_INODES_PER_GROUP(sb) / 8)) { + EXT4_INODES_PER_GROUP(sb) / 8) || + ext4_simulate_fail(sb, EXT4_SIM_IBITMAP_CRC)) { ext4_unlock_group(sb, block_group); ext4_error(sb, "Corrupt inode bitmap - block_group = %u, " "inode_bitmap = %llu", block_group, blk); @@ -192,8 +193,10 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group) get_bh(bh); submit_bh(REQ_OP_READ, REQ_META | REQ_PRIO, bh); wait_on_buffer(bh); + ext4_simulate_fail_bh(sb, bh, EXT4_SIM_IBITMAP_EIO); if (!buffer_uptodate(bh)) { put_bh(bh); + ext4_set_errno(sb, EIO); ext4_error(sb, "Cannot read inode bitmap - " "block_group = %u, inode_bitmap = %llu", block_group, bitmap_blk); @@ -265,13 +268,8 @@ void ext4_free_inode(handle_t *handle, struct inode *inode) ext4_debug("freeing inode %lu\n", ino); trace_ext4_free_inode(inode); - /* - * Note: we must free any quota before locking the superblock, - * as writing the quota to disk may need the lock as well. - */ dquot_initialize(inode); dquot_free_inode(inode); - dquot_drop(inode); is_directory = S_ISDIR(inode->i_mode); @@ -926,8 +924,8 @@ repeat_in_this_group: if (!handle) { BUG_ON(nblocks <= 0); handle = __ext4_journal_start_sb(dir->i_sb, line_no, - handle_type, nblocks, - 0); + handle_type, nblocks, 0, + ext4_trans_default_revoke_credits(sb)); if (IS_ERR(handle)) { err = PTR_ERR(handle); ext4_std_error(sb, err); @@ -1228,6 +1226,7 @@ struct inode *ext4_orphan_get(struct super_block *sb, unsigned long ino) inode = ext4_iget(sb, ino, EXT4_IGET_NORMAL); if (IS_ERR(inode)) { err = PTR_ERR(inode); + ext4_set_errno(sb, -err); ext4_error(sb, "couldn't read orphan inode %lu (err %d)", ino, err); return inode; diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c index 36699a131168..569fc68e8975 100644 --- a/fs/ext4/indirect.c +++ b/fs/ext4/indirect.c @@ -331,11 +331,14 @@ static int ext4_alloc_branch(handle_t *handle, for (i = 0; i <= indirect_blks; i++) { if (i == indirect_blks) { new_blocks[i] = ext4_mb_new_blocks(handle, ar, &err); - } else + } else { ar->goal = new_blocks[i] = ext4_new_meta_blocks(handle, ar->inode, ar->goal, ar->flags & EXT4_MB_DELALLOC_RESERVED, NULL, &err); + /* Simplify error cleanup... */ + branch[i+1].bh = NULL; + } if (err) { i--; goto failed; @@ -377,18 +380,25 @@ static int ext4_alloc_branch(handle_t *handle, } return 0; failed: + if (i == indirect_blks) { + /* Free data blocks */ + ext4_free_blocks(handle, ar->inode, NULL, new_blocks[i], + ar->len, 0); + i--; + } for (; i >= 0; i--) { /* * We want to ext4_forget() only freshly allocated indirect - * blocks. Buffer for new_blocks[i-1] is at branch[i].bh and - * buffer at branch[0].bh is indirect block / inode already - * existing before ext4_alloc_branch() was called. + * blocks. Buffer for new_blocks[i] is at branch[i+1].bh + * (buffer at branch[0].bh is indirect block / inode already + * existing before ext4_alloc_branch() was called). Also + * because blocks are freshly allocated, we don't need to + * revoke them which is why we don't set + * EXT4_FREE_BLOCKS_METADATA. */ - if (i > 0 && i != indirect_blks && branch[i].bh) - ext4_forget(handle, 1, ar->inode, branch[i].bh, - branch[i].bh->b_blocknr); - ext4_free_blocks(handle, ar->inode, NULL, new_blocks[i], - (i == indirect_blks) ? ar->len : 1, 0); + ext4_free_blocks(handle, ar->inode, branch[i+1].bh, + new_blocks[i], 1, + branch[i+1].bh ? EXT4_FREE_BLOCKS_FORGET : 0); } return err; } @@ -650,32 +660,6 @@ out: } /* - * Calculate the number of metadata blocks need to reserve - * to allocate a new block at @lblocks for non extent file based file - */ -int ext4_ind_calc_metadata_amount(struct inode *inode, sector_t lblock) -{ - struct ext4_inode_info *ei = EXT4_I(inode); - sector_t dind_mask = ~((sector_t)EXT4_ADDR_PER_BLOCK(inode->i_sb) - 1); - int blk_bits; - - if (lblock < EXT4_NDIR_BLOCKS) - return 0; - - lblock -= EXT4_NDIR_BLOCKS; - - if (ei->i_da_metadata_calc_len && - (lblock & dind_mask) == ei->i_da_metadata_calc_last_lblock) { - ei->i_da_metadata_calc_len++; - return 0; - } - ei->i_da_metadata_calc_last_lblock = lblock & dind_mask; - ei->i_da_metadata_calc_len = 1; - blk_bits = order_base_2(lblock); - return (blk_bits / EXT4_ADDR_PER_BLOCK_BITS(inode->i_sb)) + 1; -} - -/* * Calculate number of indirect blocks touched by mapping @nrblocks logically * contiguous blocks */ @@ -689,27 +673,63 @@ int ext4_ind_trans_blocks(struct inode *inode, int nrblocks) return DIV_ROUND_UP(nrblocks, EXT4_ADDR_PER_BLOCK(inode->i_sb)) + 4; } +static int ext4_ind_trunc_restart_fn(handle_t *handle, struct inode *inode, + struct buffer_head *bh, int *dropped) +{ + int err; + + if (bh) { + BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata"); + err = ext4_handle_dirty_metadata(handle, inode, bh); + if (unlikely(err)) + return err; + } + err = ext4_mark_inode_dirty(handle, inode); + if (unlikely(err)) + return err; + /* + * 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. + */ + BUG_ON(EXT4_JOURNAL(inode) == NULL); + ext4_discard_preallocations(inode); + up_write(&EXT4_I(inode)->i_data_sem); + *dropped = 1; + return 0; +} + /* * Truncate transactions can be complex and absolutely huge. So we need to * be able to restart the transaction at a conventient checkpoint to make * sure we don't overflow the journal. * * Try to extend this transaction for the purposes of truncation. If - * extend fails, we need to propagate the failure up and restart the - * transaction in the top-level truncate loop. --sct - * - * Returns 0 if we managed to create more room. If we can't create more - * room, and the transaction must be restarted we return 1. + * extend fails, we restart transaction. */ -static int try_to_extend_transaction(handle_t *handle, struct inode *inode) +static int ext4_ind_truncate_ensure_credits(handle_t *handle, + struct inode *inode, + struct buffer_head *bh, + int revoke_creds) { - if (!ext4_handle_valid(handle)) - return 0; - if (ext4_handle_has_enough_credits(handle, EXT4_RESERVE_TRANS_BLOCKS+1)) - return 0; - if (!ext4_journal_extend(handle, ext4_blocks_for_truncate(inode))) - return 0; - return 1; + int ret; + int dropped = 0; + + ret = ext4_journal_ensure_credits_fn(handle, EXT4_RESERVE_TRANS_BLOCKS, + ext4_blocks_for_truncate(inode), revoke_creds, + ext4_ind_trunc_restart_fn(handle, inode, bh, &dropped)); + if (dropped) + down_write(&EXT4_I(inode)->i_data_sem); + if (ret <= 0) + return ret; + if (bh) { + BUFFER_TRACE(bh, "retaking write access"); + ret = ext4_journal_get_write_access(handle, bh); + if (unlikely(ret)) + return ret; + } + return 0; } /* @@ -844,27 +864,10 @@ static int ext4_clear_blocks(handle_t *handle, struct inode *inode, return 1; } - if (try_to_extend_transaction(handle, inode)) { - if (bh) { - BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata"); - err = ext4_handle_dirty_metadata(handle, inode, bh); - if (unlikely(err)) - goto out_err; - } - err = ext4_mark_inode_dirty(handle, inode); - if (unlikely(err)) - goto out_err; - err = ext4_truncate_restart_trans(handle, inode, - ext4_blocks_for_truncate(inode)); - if (unlikely(err)) - goto out_err; - if (bh) { - BUFFER_TRACE(bh, "retaking write access"); - err = ext4_journal_get_write_access(handle, bh); - if (unlikely(err)) - goto out_err; - } - } + err = ext4_ind_truncate_ensure_credits(handle, inode, bh, + ext4_free_data_revoke_credits(inode, count)); + if (err < 0) + goto out_err; for (p = first; p < last; p++) *p = 0; @@ -1047,11 +1050,11 @@ static void ext4_free_branches(handle_t *handle, struct inode *inode, */ if (ext4_handle_is_aborted(handle)) return; - if (try_to_extend_transaction(handle, inode)) { - ext4_mark_inode_dirty(handle, inode); - ext4_truncate_restart_trans(handle, inode, - ext4_blocks_for_truncate(inode)); - } + if (ext4_ind_truncate_ensure_credits(handle, inode, + NULL, + ext4_free_metadata_revoke_credits( + inode->i_sb, 1)) < 0) + return; /* * The forget flag here is critical because if diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index 88cdf3c90bd1..fad82d08fca5 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -98,6 +98,7 @@ int ext4_get_max_inline_size(struct inode *inode) error = ext4_get_inode_loc(inode, &iloc); if (error) { + ext4_set_errno(inode->i_sb, -error); ext4_error_inode(inode, __func__, __LINE__, 0, "can't get inode location %lu", inode->i_ino); @@ -849,7 +850,7 @@ out: /* * Prepare the write for the inline data. - * If the the data can be written into the inode, we just read + * If the data can be written into the inode, we just read * the page and make it uptodate, and start the journal. * Otherwise read the page, makes it dirty so that it can be * handle in writepages(the i_disksize update is left to the @@ -1416,7 +1417,7 @@ int ext4_inlinedir_to_tree(struct file *dir_file, err = ext4_htree_store_dirent(dir_file, hinfo->hash, hinfo->minor_hash, de, &tmp_str); if (err) { - count = err; + ret = err; goto out; } count++; @@ -1761,6 +1762,7 @@ bool empty_inline_dir(struct inode *dir, int *has_inline_data) err = ext4_get_inode_loc(dir, &iloc); if (err) { + ext4_set_errno(dir->i_sb, -err); EXT4_ERROR_INODE(dir, "error %d getting inode %lu block", err, dir->i_ino); return true; diff --git a/fs/ext4/inode-test.c b/fs/ext4/inode-test.c new file mode 100644 index 000000000000..d62d802c9c12 --- /dev/null +++ b/fs/ext4/inode-test.c @@ -0,0 +1,274 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * KUnit test of ext4 inode that verify the seconds part of [a/c/m] + * timestamps in ext4 inode structs are decoded correctly. + */ + +#include <kunit/test.h> +#include <linux/kernel.h> +#include <linux/time64.h> + +#include "ext4.h" + +/* + * For constructing the nonnegative timestamp lower bound value. + * binary: 00000000 00000000 00000000 00000000 + */ +#define LOWER_MSB_0 0L +/* + * For constructing the nonnegative timestamp upper bound value. + * binary: 01111111 11111111 11111111 11111111 + * + */ +#define UPPER_MSB_0 0x7fffffffL +/* + * For constructing the negative timestamp lower bound value. + * binary: 10000000 00000000 00000000 00000000 + */ +#define LOWER_MSB_1 (-(UPPER_MSB_0) - 1L) /* avoid overflow */ +/* + * For constructing the negative timestamp upper bound value. + * binary: 11111111 11111111 11111111 11111111 + */ +#define UPPER_MSB_1 (-1L) +/* + * Upper bound for nanoseconds value supported by the encoding. + * binary: 00111111 11111111 11111111 11111111 + */ +#define MAX_NANOSECONDS ((1L << 30) - 1) + +#define CASE_NAME_FORMAT "%s: msb:%x lower_bound:%x extra_bits: %x" + +#define LOWER_BOUND_NEG_NO_EXTRA_BITS_CASE\ + "1901-12-13 Lower bound of 32bit < 0 timestamp, no extra bits" +#define UPPER_BOUND_NEG_NO_EXTRA_BITS_CASE\ + "1969-12-31 Upper bound of 32bit < 0 timestamp, no extra bits" +#define LOWER_BOUND_NONNEG_NO_EXTRA_BITS_CASE\ + "1970-01-01 Lower bound of 32bit >=0 timestamp, no extra bits" +#define UPPER_BOUND_NONNEG_NO_EXTRA_BITS_CASE\ + "2038-01-19 Upper bound of 32bit >=0 timestamp, no extra bits" +#define LOWER_BOUND_NEG_LO_1_CASE\ + "2038-01-19 Lower bound of 32bit <0 timestamp, lo extra sec bit on" +#define UPPER_BOUND_NEG_LO_1_CASE\ + "2106-02-07 Upper bound of 32bit <0 timestamp, lo extra sec bit on" +#define LOWER_BOUND_NONNEG_LO_1_CASE\ + "2106-02-07 Lower bound of 32bit >=0 timestamp, lo extra sec bit on" +#define UPPER_BOUND_NONNEG_LO_1_CASE\ + "2174-02-25 Upper bound of 32bit >=0 timestamp, lo extra sec bit on" +#define LOWER_BOUND_NEG_HI_1_CASE\ + "2174-02-25 Lower bound of 32bit <0 timestamp, hi extra sec bit on" +#define UPPER_BOUND_NEG_HI_1_CASE\ + "2242-03-16 Upper bound of 32bit <0 timestamp, hi extra sec bit on" +#define LOWER_BOUND_NONNEG_HI_1_CASE\ + "2242-03-16 Lower bound of 32bit >=0 timestamp, hi extra sec bit on" +#define UPPER_BOUND_NONNEG_HI_1_CASE\ + "2310-04-04 Upper bound of 32bit >=0 timestamp, hi extra sec bit on" +#define UPPER_BOUND_NONNEG_HI_1_NS_1_CASE\ + "2310-04-04 Upper bound of 32bit>=0 timestamp, hi extra sec bit 1. 1 ns" +#define LOWER_BOUND_NONNEG_HI_1_NS_MAX_CASE\ + "2378-04-22 Lower bound of 32bit>= timestamp. Extra sec bits 1. Max ns" +#define LOWER_BOUND_NONNEG_EXTRA_BITS_1_CASE\ + "2378-04-22 Lower bound of 32bit >=0 timestamp. All extra sec bits on" +#define UPPER_BOUND_NONNEG_EXTRA_BITS_1_CASE\ + "2446-05-10 Upper bound of 32bit >=0 timestamp. All extra sec bits on" + +struct timestamp_expectation { + const char *test_case_name; + struct timespec64 expected; + u32 extra_bits; + bool msb_set; + bool lower_bound; +}; + +static time64_t get_32bit_time(const struct timestamp_expectation * const test) +{ + if (test->msb_set) { + if (test->lower_bound) + return LOWER_MSB_1; + + return UPPER_MSB_1; + } + + if (test->lower_bound) + return LOWER_MSB_0; + return UPPER_MSB_0; +} + + +/* + * Test data is derived from the table in the Inode Timestamps section of + * Documentation/filesystems/ext4/inodes.rst. + */ +static void inode_test_xtimestamp_decoding(struct kunit *test) +{ + const struct timestamp_expectation test_data[] = { + { + .test_case_name = LOWER_BOUND_NEG_NO_EXTRA_BITS_CASE, + .msb_set = true, + .lower_bound = true, + .extra_bits = 0, + .expected = {.tv_sec = -0x80000000LL, .tv_nsec = 0L}, + }, + + { + .test_case_name = UPPER_BOUND_NEG_NO_EXTRA_BITS_CASE, + .msb_set = true, + .lower_bound = false, + .extra_bits = 0, + .expected = {.tv_sec = -1LL, .tv_nsec = 0L}, + }, + + { + .test_case_name = LOWER_BOUND_NONNEG_NO_EXTRA_BITS_CASE, + .msb_set = false, + .lower_bound = true, + .extra_bits = 0, + .expected = {0LL, 0L}, + }, + + { + .test_case_name = UPPER_BOUND_NONNEG_NO_EXTRA_BITS_CASE, + .msb_set = false, + .lower_bound = false, + .extra_bits = 0, + .expected = {.tv_sec = 0x7fffffffLL, .tv_nsec = 0L}, + }, + + { + .test_case_name = LOWER_BOUND_NEG_LO_1_CASE, + .msb_set = true, + .lower_bound = true, + .extra_bits = 1, + .expected = {.tv_sec = 0x80000000LL, .tv_nsec = 0L}, + }, + + { + .test_case_name = UPPER_BOUND_NEG_LO_1_CASE, + .msb_set = true, + .lower_bound = false, + .extra_bits = 1, + .expected = {.tv_sec = 0xffffffffLL, .tv_nsec = 0L}, + }, + + { + .test_case_name = LOWER_BOUND_NONNEG_LO_1_CASE, + .msb_set = false, + .lower_bound = true, + .extra_bits = 1, + .expected = {.tv_sec = 0x100000000LL, .tv_nsec = 0L}, + }, + + { + .test_case_name = UPPER_BOUND_NONNEG_LO_1_CASE, + .msb_set = false, + .lower_bound = false, + .extra_bits = 1, + .expected = {.tv_sec = 0x17fffffffLL, .tv_nsec = 0L}, + }, + + { + .test_case_name = LOWER_BOUND_NEG_HI_1_CASE, + .msb_set = true, + .lower_bound = true, + .extra_bits = 2, + .expected = {.tv_sec = 0x180000000LL, .tv_nsec = 0L}, + }, + + { + .test_case_name = UPPER_BOUND_NEG_HI_1_CASE, + .msb_set = true, + .lower_bound = false, + .extra_bits = 2, + .expected = {.tv_sec = 0x1ffffffffLL, .tv_nsec = 0L}, + }, + + { + .test_case_name = LOWER_BOUND_NONNEG_HI_1_CASE, + .msb_set = false, + .lower_bound = true, + .extra_bits = 2, + .expected = {.tv_sec = 0x200000000LL, .tv_nsec = 0L}, + }, + + { + .test_case_name = UPPER_BOUND_NONNEG_HI_1_CASE, + .msb_set = false, + .lower_bound = false, + .extra_bits = 2, + .expected = {.tv_sec = 0x27fffffffLL, .tv_nsec = 0L}, + }, + + { + .test_case_name = UPPER_BOUND_NONNEG_HI_1_NS_1_CASE, + .msb_set = false, + .lower_bound = false, + .extra_bits = 6, + .expected = {.tv_sec = 0x27fffffffLL, .tv_nsec = 1L}, + }, + + { + .test_case_name = LOWER_BOUND_NONNEG_HI_1_NS_MAX_CASE, + .msb_set = false, + .lower_bound = true, + .extra_bits = 0xFFFFFFFF, + .expected = {.tv_sec = 0x300000000LL, + .tv_nsec = MAX_NANOSECONDS}, + }, + + { + .test_case_name = LOWER_BOUND_NONNEG_EXTRA_BITS_1_CASE, + .msb_set = false, + .lower_bound = true, + .extra_bits = 3, + .expected = {.tv_sec = 0x300000000LL, .tv_nsec = 0L}, + }, + + { + .test_case_name = UPPER_BOUND_NONNEG_EXTRA_BITS_1_CASE, + .msb_set = false, + .lower_bound = false, + .extra_bits = 3, + .expected = {.tv_sec = 0x37fffffffLL, .tv_nsec = 0L}, + } + }; + + struct timespec64 timestamp; + int i; + + for (i = 0; i < ARRAY_SIZE(test_data); ++i) { + timestamp.tv_sec = get_32bit_time(&test_data[i]); + ext4_decode_extra_time(×tamp, + cpu_to_le32(test_data[i].extra_bits)); + + KUNIT_EXPECT_EQ_MSG(test, + test_data[i].expected.tv_sec, + timestamp.tv_sec, + CASE_NAME_FORMAT, + test_data[i].test_case_name, + test_data[i].msb_set, + test_data[i].lower_bound, + test_data[i].extra_bits); + KUNIT_EXPECT_EQ_MSG(test, + test_data[i].expected.tv_nsec, + timestamp.tv_nsec, + CASE_NAME_FORMAT, + test_data[i].test_case_name, + test_data[i].msb_set, + test_data[i].lower_bound, + test_data[i].extra_bits); + } +} + +static struct kunit_case ext4_inode_test_cases[] = { + KUNIT_CASE(inode_test_xtimestamp_decoding), + {} +}; + +static struct kunit_suite ext4_inode_test_suite = { + .name = "ext4_inode_test", + .test_cases = ext4_inode_test_cases, +}; + +kunit_test_suites(&ext4_inode_test_suite); + +MODULE_LICENSE("GPL v2"); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 420fe3deed39..e60aca791d3f 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -48,8 +48,6 @@ #include <trace/events/ext4.h> -#define MPAGE_DA_EXTENT_TAIL 0x01 - static __u32 ext4_inode_csum(struct inode *inode, struct ext4_inode *raw, struct ext4_inode_info *ei) { @@ -164,39 +162,18 @@ int ext4_inode_is_fast_symlink(struct inode *inode) } /* - * Restart the transaction associated with *handle. This does a commit, - * so before we call here everything must be consistently dirtied against - * this transaction. - */ -int ext4_truncate_restart_trans(handle_t *handle, struct inode *inode, - int nblocks) -{ - int ret; - - /* - * 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. - */ - BUG_ON(EXT4_JOURNAL(inode) == NULL); - jbd_debug(2, "restarting handle %p\n", handle); - up_write(&EXT4_I(inode)->i_data_sem); - ret = ext4_journal_restart(handle, nblocks); - down_write(&EXT4_I(inode)->i_data_sem); - ext4_discard_preallocations(inode); - - return ret; -} - -/* * Called at the last iput() if i_nlink is zero. */ void ext4_evict_inode(struct inode *inode) { handle_t *handle; int err; - int extra_credits = 3; + /* + * Credits for final inode cleanup and freeing: + * sb + inode (ext4_orphan_del()), block bitmap, group descriptor + * (xattr block freeing), bitmap, group descriptor (inode freeing) + */ + int extra_credits = 6; struct ext4_xattr_inode_array *ea_inode_array = NULL; trace_ext4_evict_inode(inode); @@ -252,8 +229,12 @@ void ext4_evict_inode(struct inode *inode) if (!IS_NOQUOTA(inode)) extra_credits += EXT4_MAXQUOTAS_DEL_BLOCKS(inode->i_sb); + /* + * Block bitmap, group descriptor, and inode are accounted in both + * ext4_blocks_for_truncate() and extra_credits. So subtract 3. + */ handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, - ext4_blocks_for_truncate(inode)+extra_credits); + ext4_blocks_for_truncate(inode) + extra_credits - 3); if (IS_ERR(handle)) { ext4_std_error(inode->i_sb, PTR_ERR(handle)); /* @@ -288,6 +269,7 @@ void ext4_evict_inode(struct inode *inode) if (inode->i_blocks) { err = ext4_truncate(inode); if (err) { + ext4_set_errno(inode->i_sb, -err); ext4_error(inode->i_sb, "couldn't truncate inode %lu (err %d)", inode->i_ino, err); @@ -419,7 +401,7 @@ int ext4_issue_zeroout(struct inode *inode, ext4_lblk_t lblk, ext4_fsblk_t pblk, { int ret; - if (IS_ENCRYPTED(inode)) + if (IS_ENCRYPTED(inode) && S_ISREG(inode->i_mode)) return fscrypt_zeroout_range(inode, lblk, pblk, len); ret = sb_issue_zeroout(inode->i_sb, pblk, len, GFP_NOFS); @@ -527,7 +509,7 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode, return -EFSCORRUPTED; /* Lookup extent status tree firstly */ - if (ext4_es_lookup_extent(inode, map->m_lblk, &es)) { + if (ext4_es_lookup_extent(inode, map->m_lblk, NULL, &es)) { if (ext4_es_is_written(&es) || ext4_es_is_unwritten(&es)) { map->m_pblk = ext4_es_pblock(&es) + map->m_lblk - es.es_lblk; @@ -695,7 +677,7 @@ found: * extent status tree. */ if ((flags & EXT4_GET_BLOCKS_PRE_IO) && - ext4_es_lookup_extent(inode, map->m_lblk, &es)) { + ext4_es_lookup_extent(inode, map->m_lblk, NULL, &es)) { if (ext4_es_is_written(&es)) goto out_sem; } @@ -827,136 +809,6 @@ int ext4_get_block_unwritten(struct inode *inode, sector_t iblock, #define DIO_MAX_BLOCKS 4096 /* - * Get blocks function for the cases that need to start a transaction - - * generally difference cases of direct IO and DAX IO. It also handles retries - * in case of ENOSPC. - */ -static int ext4_get_block_trans(struct inode *inode, sector_t iblock, - struct buffer_head *bh_result, int flags) -{ - int dio_credits; - handle_t *handle; - int retries = 0; - int ret; - - /* Trim mapping request to maximum we can map at once for DIO */ - if (bh_result->b_size >> inode->i_blkbits > DIO_MAX_BLOCKS) - bh_result->b_size = DIO_MAX_BLOCKS << inode->i_blkbits; - dio_credits = ext4_chunk_trans_blocks(inode, - bh_result->b_size >> inode->i_blkbits); -retry: - handle = ext4_journal_start(inode, EXT4_HT_MAP_BLOCKS, dio_credits); - if (IS_ERR(handle)) - return PTR_ERR(handle); - - ret = _ext4_get_block(inode, iblock, bh_result, flags); - ext4_journal_stop(handle); - - if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)) - goto retry; - return ret; -} - -/* Get block function for DIO reads and writes to inodes without extents */ -int ext4_dio_get_block(struct inode *inode, sector_t iblock, - struct buffer_head *bh, int create) -{ - /* We don't expect handle for direct IO */ - WARN_ON_ONCE(ext4_journal_current_handle()); - - if (!create) - return _ext4_get_block(inode, iblock, bh, 0); - return ext4_get_block_trans(inode, iblock, bh, EXT4_GET_BLOCKS_CREATE); -} - -/* - * Get block function for AIO DIO writes when we create unwritten extent if - * blocks are not allocated yet. The extent will be converted to written - * after IO is complete. - */ -static int ext4_dio_get_block_unwritten_async(struct inode *inode, - sector_t iblock, struct buffer_head *bh_result, int create) -{ - int ret; - - /* We don't expect handle for direct IO */ - WARN_ON_ONCE(ext4_journal_current_handle()); - - ret = ext4_get_block_trans(inode, iblock, bh_result, - EXT4_GET_BLOCKS_IO_CREATE_EXT); - - /* - * When doing DIO using unwritten extents, we need io_end to convert - * unwritten extents to written on IO completion. We allocate io_end - * once we spot unwritten extent and store it in b_private. Generic - * DIO code keeps b_private set and furthermore passes the value to - * our completion callback in 'private' argument. - */ - if (!ret && buffer_unwritten(bh_result)) { - if (!bh_result->b_private) { - ext4_io_end_t *io_end; - - io_end = ext4_init_io_end(inode, GFP_KERNEL); - if (!io_end) - return -ENOMEM; - bh_result->b_private = io_end; - ext4_set_io_unwritten_flag(inode, io_end); - } - set_buffer_defer_completion(bh_result); - } - - return ret; -} - -/* - * Get block function for non-AIO DIO writes when we create unwritten extent if - * blocks are not allocated yet. The extent will be converted to written - * after IO is complete by ext4_direct_IO_write(). - */ -static int ext4_dio_get_block_unwritten_sync(struct inode *inode, - sector_t iblock, struct buffer_head *bh_result, int create) -{ - int ret; - - /* We don't expect handle for direct IO */ - WARN_ON_ONCE(ext4_journal_current_handle()); - - ret = ext4_get_block_trans(inode, iblock, bh_result, - EXT4_GET_BLOCKS_IO_CREATE_EXT); - - /* - * Mark inode as having pending DIO writes to unwritten extents. - * ext4_direct_IO_write() checks this flag and converts extents to - * written. - */ - if (!ret && buffer_unwritten(bh_result)) - ext4_set_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN); - - return ret; -} - -static int ext4_dio_get_block_overwrite(struct inode *inode, sector_t iblock, - struct buffer_head *bh_result, int create) -{ - int ret; - - ext4_debug("ext4_dio_get_block_overwrite: inode %lu, create flag %d\n", - inode->i_ino, create); - /* We don't expect handle for direct IO */ - WARN_ON_ONCE(ext4_journal_current_handle()); - - ret = _ext4_get_block(inode, iblock, bh_result, 0); - /* - * Blocks should have been preallocated! ext4_file_write_iter() checks - * that. - */ - WARN_ON_ONCE(!buffer_mapped(bh_result) || buffer_unwritten(bh_result)); - - return ret; -} - - -/* * `handle' can be NULL if create is zero */ struct buffer_head *ext4_getblk(handle_t *handle, struct inode *inode, @@ -1024,7 +876,7 @@ struct buffer_head *ext4_bread(handle_t *handle, struct inode *inode, bh = ext4_getblk(handle, inode, block, map_flags); if (IS_ERR(bh)) return bh; - if (!bh || buffer_uptodate(bh)) + if (!bh || ext4_buffer_uptodate(bh)) return bh; ll_rw_block(REQ_OP_READ, REQ_META | REQ_PRIO, 1, &bh); wait_on_buffer(bh); @@ -1051,7 +903,7 @@ int ext4_bread_batch(struct inode *inode, ext4_lblk_t block, int bh_count, for (i = 0; i < bh_count; i++) /* Note that NULL bhs[i] is valid because of holes. */ - if (bhs[i] && !buffer_uptodate(bhs[i])) + if (bhs[i] && !ext4_buffer_uptodate(bhs[i])) ll_rw_block(REQ_OP_READ, REQ_META | REQ_PRIO, 1, &bhs[i]); @@ -1340,6 +1192,9 @@ retry_journal: } if (ret) { + bool extended = (pos + len > inode->i_size) && + !ext4_verity_in_progress(inode); + unlock_page(page); /* * __block_write_begin may have instantiated a few blocks @@ -1349,11 +1204,11 @@ retry_journal: * Add inode to orphan list in case we crash before * truncate finishes */ - if (pos + len > inode->i_size && ext4_can_truncate(inode)) + if (extended && ext4_can_truncate(inode)) ext4_orphan_add(handle, inode); ext4_journal_stop(handle); - if (pos + len > inode->i_size) { + if (extended) { ext4_truncate_failed_write(inode); /* * If truncate failed early the inode might @@ -1406,6 +1261,7 @@ static int ext4_write_end(struct file *file, int ret = 0, ret2; int i_size_changed = 0; int inline_data = ext4_has_inline_data(inode); + bool verity = ext4_verity_in_progress(inode); trace_ext4_write_end(inode, pos, len, copied); if (inline_data) { @@ -1423,12 +1279,16 @@ static int ext4_write_end(struct file *file, /* * it's important to update i_size while still holding page lock: * page writeout could otherwise come in and zero beyond i_size. + * + * If FS_IOC_ENABLE_VERITY is running on this inode, then Merkle tree + * blocks are being written past EOF, so skip the i_size update. */ - i_size_changed = ext4_update_inode_size(inode, pos + copied); + if (!verity) + i_size_changed = ext4_update_inode_size(inode, pos + copied); unlock_page(page); put_page(page); - if (old_size < pos) + if (old_size < pos && !verity) pagecache_isize_extended(inode, old_size, pos); /* * Don't mark the inode dirty under page lock. First, it unnecessarily @@ -1439,7 +1299,7 @@ static int ext4_write_end(struct file *file, if (i_size_changed || inline_data) ext4_mark_inode_dirty(handle, inode); - if (pos + len > inode->i_size && ext4_can_truncate(inode)) + if (pos + len > inode->i_size && !verity && ext4_can_truncate(inode)) /* if we have allocated more blocks and copied * less. We will have blocks allocated outside * inode->i_size. So truncate them @@ -1450,7 +1310,7 @@ errout: if (!ret) ret = ret2; - if (pos + len > inode->i_size) { + if (pos + len > inode->i_size && !verity) { ext4_truncate_failed_write(inode); /* * If truncate failed early the inode might still be @@ -1511,6 +1371,7 @@ static int ext4_journalled_write_end(struct file *file, unsigned from, to; int size_changed = 0; int inline_data = ext4_has_inline_data(inode); + bool verity = ext4_verity_in_progress(inode); trace_ext4_journalled_write_end(inode, pos, len, copied); from = pos & (PAGE_SIZE - 1); @@ -1540,13 +1401,14 @@ static int ext4_journalled_write_end(struct file *file, if (!partial) SetPageUptodate(page); } - size_changed = ext4_update_inode_size(inode, pos + copied); + if (!verity) + size_changed = ext4_update_inode_size(inode, pos + copied); ext4_set_inode_state(inode, EXT4_STATE_JDATA); EXT4_I(inode)->i_datasync_tid = handle->h_transaction->t_tid; unlock_page(page); put_page(page); - if (old_size < pos) + if (old_size < pos && !verity) pagecache_isize_extended(inode, old_size, pos); if (size_changed || inline_data) { @@ -1555,7 +1417,7 @@ static int ext4_journalled_write_end(struct file *file, ret = ret2; } - if (pos + len > inode->i_size && ext4_can_truncate(inode)) + if (pos + len > inode->i_size && !verity && ext4_can_truncate(inode)) /* if we have allocated more blocks and copied * less. We will have blocks allocated outside * inode->i_size. So truncate them @@ -1566,7 +1428,7 @@ errout: ret2 = ext4_journal_stop(handle); if (!ret) ret = ret2; - if (pos + len > inode->i_size) { + if (pos + len > inode->i_size && !verity) { ext4_truncate_failed_write(inode); /* * If truncate failed early the inode might still be @@ -1646,49 +1508,6 @@ void ext4_da_release_space(struct inode *inode, int to_free) dquot_release_reservation_block(inode, EXT4_C2B(sbi, to_free)); } -static void ext4_da_page_release_reservation(struct page *page, - unsigned int offset, - unsigned int length) -{ - int contiguous_blks = 0; - struct buffer_head *head, *bh; - unsigned int curr_off = 0; - struct inode *inode = page->mapping->host; - unsigned int stop = offset + length; - ext4_fsblk_t lblk; - - BUG_ON(stop > PAGE_SIZE || stop < length); - - head = page_buffers(page); - bh = head; - do { - unsigned int next_off = curr_off + bh->b_size; - - if (next_off > stop) - break; - - if ((offset <= curr_off) && (buffer_delay(bh))) { - contiguous_blks++; - clear_buffer_delay(bh); - } else if (contiguous_blks) { - lblk = page->index << - (PAGE_SHIFT - inode->i_blkbits); - lblk += (curr_off >> inode->i_blkbits) - - contiguous_blks; - ext4_es_remove_blks(inode, lblk, contiguous_blks); - contiguous_blks = 0; - } - curr_off = next_off; - } while ((bh = bh->b_this_page) != head); - - if (contiguous_blks) { - lblk = page->index << (PAGE_SHIFT - inode->i_blkbits); - lblk += (curr_off >> inode->i_blkbits) - contiguous_blks; - ext4_es_remove_blks(inode, lblk, contiguous_blks); - } - -} - /* * Delayed allocation stuff */ @@ -1868,7 +1687,7 @@ static int ext4_da_map_blocks(struct inode *inode, sector_t iblock, (unsigned long) map->m_lblk); /* Lookup extent status tree firstly */ - if (ext4_es_lookup_extent(inode, iblock, &es)) { + if (ext4_es_lookup_extent(inode, iblock, NULL, &es)) { if (ext4_es_is_hole(&es)) { retval = 0; down_read(&EXT4_I(inode)->i_data_sem); @@ -2162,7 +1981,8 @@ static int ext4_writepage(struct page *page, trace_ext4_writepage(page); size = i_size_read(inode); - if (page->index == size >> PAGE_SHIFT) + if (page->index == size >> PAGE_SHIFT && + !ext4_verity_in_progress(inode)) len = size & ~PAGE_MASK; else len = PAGE_SIZE; @@ -2246,7 +2066,8 @@ static int mpage_submit_page(struct mpage_da_data *mpd, struct page *page) * after page tables are updated. */ size = i_size_read(mpd->inode); - if (page->index == size >> PAGE_SHIFT) + if (page->index == size >> PAGE_SHIFT && + !ext4_verity_in_progress(mpd->inode)) len = size & ~PAGE_MASK; else len = PAGE_SIZE; @@ -2345,6 +2166,9 @@ static int mpage_process_page_bufs(struct mpage_da_data *mpd, ext4_lblk_t blocks = (i_size_read(inode) + i_blocksize(inode) - 1) >> inode->i_blkbits; + if (ext4_verity_in_progress(inode)) + blocks = EXT_MAX_BLOCKS; + do { BUG_ON(buffer_locked(bh)); @@ -2369,6 +2193,79 @@ static int mpage_process_page_bufs(struct mpage_da_data *mpd, } /* + * mpage_process_page - update page buffers corresponding to changed extent and + * may submit fully mapped page for IO + * + * @mpd - description of extent to map, on return next extent to map + * @m_lblk - logical block mapping. + * @m_pblk - corresponding physical mapping. + * @map_bh - determines on return whether this page requires any further + * mapping or not. + * Scan given page buffers corresponding to changed extent and update buffer + * state according to new extent state. + * We map delalloc buffers to their physical location, clear unwritten bits. + * If the given page is not fully mapped, we update @map to the next extent in + * the given page that needs mapping & return @map_bh as true. + */ +static int mpage_process_page(struct mpage_da_data *mpd, struct page *page, + ext4_lblk_t *m_lblk, ext4_fsblk_t *m_pblk, + bool *map_bh) +{ + struct buffer_head *head, *bh; + ext4_io_end_t *io_end = mpd->io_submit.io_end; + ext4_lblk_t lblk = *m_lblk; + ext4_fsblk_t pblock = *m_pblk; + int err = 0; + int blkbits = mpd->inode->i_blkbits; + ssize_t io_end_size = 0; + struct ext4_io_end_vec *io_end_vec = ext4_last_io_end_vec(io_end); + + bh = head = page_buffers(page); + do { + if (lblk < mpd->map.m_lblk) + continue; + if (lblk >= mpd->map.m_lblk + mpd->map.m_len) { + /* + * Buffer after end of mapped extent. + * Find next buffer in the page to map. + */ + 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) + err = 0; + if (!err && mpd->map.m_len && mpd->map.m_lblk > lblk) { + io_end_vec = ext4_alloc_io_end_vec(io_end); + if (IS_ERR(io_end_vec)) { + err = PTR_ERR(io_end_vec); + goto out; + } + io_end_vec->offset = mpd->map.m_lblk << blkbits; + } + *map_bh = true; + goto out; + } + if (buffer_delay(bh)) { + clear_buffer_delay(bh); + bh->b_blocknr = pblock++; + } + clear_buffer_unwritten(bh); + io_end_size += (1 << blkbits); + } 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; + *m_pblk = pblock; + return err; +} + +/* * mpage_map_buffers - update buffers corresponding to changed extent and * submit fully mapped pages for IO * @@ -2387,12 +2284,12 @@ static int mpage_map_and_submit_buffers(struct mpage_da_data *mpd) struct pagevec pvec; int nr_pages, i; struct inode *inode = mpd->inode; - struct buffer_head *head, *bh; int bpp_bits = PAGE_SHIFT - inode->i_blkbits; pgoff_t start, end; ext4_lblk_t lblk; - sector_t pblock; + ext4_fsblk_t pblock; int err; + bool map_bh = false; start = mpd->map.m_lblk >> bpp_bits; end = (mpd->map.m_lblk + mpd->map.m_len - 1) >> bpp_bits; @@ -2408,50 +2305,19 @@ static int mpage_map_and_submit_buffers(struct mpage_da_data *mpd) for (i = 0; i < nr_pages; i++) { struct page *page = pvec.pages[i]; - bh = head = page_buffers(page); - do { - if (lblk < mpd->map.m_lblk) - continue; - if (lblk >= mpd->map.m_lblk + mpd->map.m_len) { - /* - * Buffer after end of mapped extent. - * Find next buffer in the page to map. - */ - mpd->map.m_len = 0; - mpd->map.m_flags = 0; - /* - * FIXME: If dioread_nolock supports - * blocksize < pagesize, we need to make - * sure we add size mapped so far to - * io_end->size as the following call - * can submit the page for IO. - */ - err = mpage_process_page_bufs(mpd, head, - bh, lblk); - pagevec_release(&pvec); - if (err > 0) - err = 0; - return err; - } - if (buffer_delay(bh)) { - clear_buffer_delay(bh); - bh->b_blocknr = pblock++; - } - clear_buffer_unwritten(bh); - } while (lblk++, (bh = bh->b_this_page) != head); - + err = mpage_process_page(mpd, page, &lblk, &pblock, + &map_bh); /* - * FIXME: This is going to break if dioread_nolock - * supports blocksize < pagesize as we will try to - * convert potentially unmapped parts of inode. + * If map_bh is true, means page may require further bh + * mapping, or maybe the page was submitted for IO. + * So we return to call further extent mapping. */ - mpd->io_submit.io_end->size += PAGE_SIZE; + if (err < 0 || map_bh == true) + goto out; /* Page fully mapped - let IO run! */ err = mpage_submit_page(mpd, page); - if (err < 0) { - pagevec_release(&pvec); - return err; - } + if (err < 0) + goto out; } pagevec_release(&pvec); } @@ -2459,6 +2325,9 @@ static int mpage_map_and_submit_buffers(struct mpage_da_data *mpd) mpd->map.m_len = 0; mpd->map.m_flags = 0; return 0; +out: + pagevec_release(&pvec); + return err; } static int mpage_map_one_extent(handle_t *handle, struct mpage_da_data *mpd) @@ -2538,9 +2407,13 @@ static int mpage_map_and_submit_extent(handle_t *handle, int err; loff_t disksize; int progress = 0; + ext4_io_end_t *io_end = mpd->io_submit.io_end; + struct ext4_io_end_vec *io_end_vec; - mpd->io_submit.io_end->offset = - ((loff_t)map->m_lblk) << inode->i_blkbits; + io_end_vec = ext4_alloc_io_end_vec(io_end); + if (IS_ERR(io_end_vec)) + return PTR_ERR(io_end_vec); + io_end_vec->offset = ((loff_t)map->m_lblk) << inode->i_blkbits; do { err = mpage_map_one_extent(handle, mpd); if (err < 0) { @@ -2604,10 +2477,12 @@ update_disksize: EXT4_I(inode)->i_disksize = disksize; up_write(&EXT4_I(inode)->i_data_sem); err2 = ext4_mark_inode_dirty(handle, inode); - if (err2) + if (err2) { + ext4_set_errno(inode->i_sb, -err2); ext4_error(inode->i_sb, "Failed to mark inode %lu dirty", inode->i_ino); + } if (!err) err = err2; } @@ -2785,15 +2660,6 @@ static int ext4_writepages(struct address_space *mapping, goto out_writepages; } - if (ext4_should_dioread_nolock(inode)) { - /* - * We may need to convert up to one extent per block in - * the page and we may dirty the inode. - */ - rsv_blocks = 1 + ext4_chunk_trans_blocks(inode, - PAGE_SIZE >> inode->i_blkbits); - } - /* * If we have inline data and arrive here, it means that * we will soon create the block for the 1st page, so @@ -2812,6 +2678,15 @@ static int ext4_writepages(struct address_space *mapping, ext4_journal_stop(handle); } + if (ext4_should_dioread_nolock(inode)) { + /* + * We may need to convert up to one extent per block in + * the page and we may dirty the inode. + */ + rsv_blocks = 1 + ext4_chunk_trans_blocks(inode, + PAGE_SIZE >> inode->i_blkbits); + } + if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX) range_whole = 1; @@ -2992,7 +2867,7 @@ static int ext4_dax_writepages(struct address_space *mapping, percpu_down_read(&sbi->s_journal_flag_rwsem); trace_ext4_writepages(inode, wbc); - ret = dax_writeback_mapping_range(mapping, inode->i_sb->s_bdev, wbc); + ret = dax_writeback_mapping_range(mapping, sbi->s_daxdev, wbc); trace_ext4_writepages_result(inode, wbc, ret, nr_to_write - wbc->nr_to_write); percpu_up_read(&sbi->s_journal_flag_rwsem); @@ -3061,8 +2936,8 @@ 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)) { + if (ext4_nonda_switch(inode->i_sb) || S_ISLNK(inode->i_mode) || + ext4_verity_in_progress(inode)) { *fsdata = (void *)FALL_BACK_TO_NONDELALLOC; return ext4_write_begin(file, mapping, pos, len, flags, pagep, fsdata); @@ -3227,24 +3102,6 @@ static int ext4_da_write_end(struct file *file, return ret ? ret : copied; } -static void ext4_da_invalidatepage(struct page *page, unsigned int offset, - unsigned int length) -{ - /* - * Drop reserved blocks - */ - BUG_ON(!PageLocked(page)); - if (!page_has_buffers(page)) - goto out; - - ext4_da_page_release_reservation(page, offset, length); - -out: - ext4_invalidatepage(page, offset, length); - - return; -} - /* * Force all delayed allocation blocks to be allocated for a given inode. */ @@ -3452,471 +3309,256 @@ static bool ext4_inode_datasync_dirty(struct inode *inode) return inode->i_state & I_DIRTY_DATASYNC; } -static int ext4_iomap_begin(struct inode *inode, loff_t offset, loff_t length, - unsigned flags, struct iomap *iomap) +static void ext4_set_iomap(struct inode *inode, struct iomap *iomap, + struct ext4_map_blocks *map, loff_t offset, + loff_t length) { - struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); - unsigned int blkbits = inode->i_blkbits; - unsigned long first_block, last_block; - struct ext4_map_blocks map; - bool delalloc = false; - int ret; - - if ((offset >> blkbits) > EXT4_MAX_LOGICAL_BLOCK) - return -EINVAL; - first_block = offset >> blkbits; - last_block = min_t(loff_t, (offset + length - 1) >> blkbits, - EXT4_MAX_LOGICAL_BLOCK); - - if (flags & IOMAP_REPORT) { - if (ext4_has_inline_data(inode)) { - ret = ext4_inline_data_iomap(inode, iomap); - if (ret != -EAGAIN) { - if (ret == 0 && offset >= iomap->length) - ret = -ENOENT; - return ret; - } - } - } else { - if (WARN_ON_ONCE(ext4_has_inline_data(inode))) - return -ERANGE; - } - - map.m_lblk = first_block; - map.m_len = last_block - first_block + 1; - - if (flags & IOMAP_REPORT) { - ret = ext4_map_blocks(NULL, inode, &map, 0); - if (ret < 0) - return ret; - - if (ret == 0) { - ext4_lblk_t end = map.m_lblk + map.m_len - 1; - struct extent_status es; - - ext4_es_find_extent_range(inode, &ext4_es_is_delayed, - map.m_lblk, end, &es); - - if (!es.es_len || es.es_lblk > end) { - /* entire range is a hole */ - } else if (es.es_lblk > map.m_lblk) { - /* range starts with a hole */ - map.m_len = es.es_lblk - map.m_lblk; - } else { - ext4_lblk_t offs = 0; - - if (es.es_lblk < map.m_lblk) - offs = map.m_lblk - es.es_lblk; - map.m_lblk = es.es_lblk + offs; - map.m_len = es.es_len - offs; - delalloc = true; - } - } - } else if (flags & IOMAP_WRITE) { - int dio_credits; - handle_t *handle; - int retries = 0; - - /* Trim mapping request to maximum we can map at once for DIO */ - if (map.m_len > DIO_MAX_BLOCKS) - map.m_len = DIO_MAX_BLOCKS; - dio_credits = ext4_chunk_trans_blocks(inode, map.m_len); -retry: - /* - * Either we allocate blocks and then we don't get unwritten - * extent so we have reserved enough credits, or the blocks - * are already allocated and unwritten and in that case - * extent conversion fits in the credits as well. - */ - handle = ext4_journal_start(inode, EXT4_HT_MAP_BLOCKS, - dio_credits); - if (IS_ERR(handle)) - return PTR_ERR(handle); - - ret = ext4_map_blocks(handle, inode, &map, - EXT4_GET_BLOCKS_CREATE_ZERO); - if (ret < 0) { - ext4_journal_stop(handle); - if (ret == -ENOSPC && - ext4_should_retry_alloc(inode->i_sb, &retries)) - goto retry; - return ret; - } - - /* - * If we added blocks beyond i_size, we need to make sure they - * will get truncated if we crash before updating i_size in - * ext4_iomap_end(). For faults we don't need to do that (and - * even cannot because for orphan list operations inode_lock is - * required) - if we happen to instantiate block beyond i_size, - * it is because we race with truncate which has already added - * the inode to the orphan list. - */ - if (!(flags & IOMAP_FAULT) && first_block + map.m_len > - (i_size_read(inode) + (1 << blkbits) - 1) >> blkbits) { - int err; - - err = ext4_orphan_add(handle, inode); - if (err < 0) { - ext4_journal_stop(handle); - return err; - } - } - ext4_journal_stop(handle); - } else { - ret = ext4_map_blocks(NULL, inode, &map, 0); - if (ret < 0) - return ret; - } + u8 blkbits = inode->i_blkbits; + /* + * Writes that span EOF might trigger an I/O size update on completion, + * so consider them to be dirty for the purpose of O_DSYNC, even if + * there is no other metadata changes being made or are pending. + */ iomap->flags = 0; - if (ext4_inode_datasync_dirty(inode)) + if (ext4_inode_datasync_dirty(inode) || + offset + length > i_size_read(inode)) iomap->flags |= IOMAP_F_DIRTY; + + if (map->m_flags & EXT4_MAP_NEW) + iomap->flags |= IOMAP_F_NEW; + iomap->bdev = inode->i_sb->s_bdev; - iomap->dax_dev = sbi->s_daxdev; - iomap->offset = (u64)first_block << blkbits; - iomap->length = (u64)map.m_len << blkbits; + iomap->dax_dev = EXT4_SB(inode->i_sb)->s_daxdev; + iomap->offset = (u64) map->m_lblk << blkbits; + iomap->length = (u64) map->m_len << blkbits; - if (ret == 0) { - iomap->type = delalloc ? IOMAP_DELALLOC : IOMAP_HOLE; - iomap->addr = IOMAP_NULL_ADDR; + /* + * Flags passed to ext4_map_blocks() for direct I/O writes can result + * in m_flags having both EXT4_MAP_MAPPED and EXT4_MAP_UNWRITTEN bits + * set. In order for any allocated unwritten extents to be converted + * into written extents correctly within the ->end_io() handler, we + * need to ensure that the iomap->type is set appropriately. Hence, the + * reason why we need to check whether the EXT4_MAP_UNWRITTEN bit has + * been set first. + */ + if (map->m_flags & EXT4_MAP_UNWRITTEN) { + iomap->type = IOMAP_UNWRITTEN; + iomap->addr = (u64) map->m_pblk << blkbits; + } else if (map->m_flags & EXT4_MAP_MAPPED) { + iomap->type = IOMAP_MAPPED; + iomap->addr = (u64) map->m_pblk << blkbits; } else { - if (map.m_flags & EXT4_MAP_MAPPED) { - iomap->type = IOMAP_MAPPED; - } else if (map.m_flags & EXT4_MAP_UNWRITTEN) { - iomap->type = IOMAP_UNWRITTEN; - } else { - WARN_ON_ONCE(1); - return -EIO; - } - iomap->addr = (u64)map.m_pblk << blkbits; + iomap->type = IOMAP_HOLE; + iomap->addr = IOMAP_NULL_ADDR; } - - if (map.m_flags & EXT4_MAP_NEW) - iomap->flags |= IOMAP_F_NEW; - - return 0; } -static int ext4_iomap_end(struct inode *inode, loff_t offset, loff_t length, - ssize_t written, unsigned flags, struct iomap *iomap) +static int ext4_iomap_alloc(struct inode *inode, struct ext4_map_blocks *map, + unsigned int flags) { - int ret = 0; handle_t *handle; - int blkbits = inode->i_blkbits; - bool truncate = false; + u8 blkbits = inode->i_blkbits; + int ret, dio_credits, m_flags = 0, retries = 0; - if (!(flags & IOMAP_WRITE) || (flags & IOMAP_FAULT)) - return 0; + /* + * Trim the mapping request to the maximum value that we can map at + * once for direct I/O. + */ + if (map->m_len > DIO_MAX_BLOCKS) + map->m_len = DIO_MAX_BLOCKS; + dio_credits = ext4_chunk_trans_blocks(inode, map->m_len); - handle = ext4_journal_start(inode, EXT4_HT_INODE, 2); - if (IS_ERR(handle)) { - ret = PTR_ERR(handle); - goto orphan_del; - } - if (ext4_update_inode_size(inode, offset + written)) - ext4_mark_inode_dirty(handle, inode); +retry: /* - * We may need to truncate allocated but not written blocks beyond EOF. + * Either we allocate blocks and then don't get an unwritten extent, so + * in that case we have reserved enough credits. Or, the blocks are + * already allocated and unwritten. In that case, the extent conversion + * fits into the credits as well. */ - if (iomap->offset + iomap->length > - ALIGN(inode->i_size, 1 << blkbits)) { - ext4_lblk_t written_blk, end_blk; + handle = ext4_journal_start(inode, EXT4_HT_MAP_BLOCKS, dio_credits); + if (IS_ERR(handle)) + return PTR_ERR(handle); - written_blk = (offset + written) >> blkbits; - end_blk = (offset + length) >> blkbits; - if (written_blk < end_blk && ext4_can_truncate(inode)) - truncate = true; - } /* - * Remove inode from orphan list if we were extending a inode and - * everything went fine. + * DAX and direct I/O are the only two operations that are currently + * supported with IOMAP_WRITE. */ - if (!truncate && inode->i_nlink && - !list_empty(&EXT4_I(inode)->i_orphan)) - ext4_orphan_del(handle, inode); + WARN_ON(!IS_DAX(inode) && !(flags & IOMAP_DIRECT)); + if (IS_DAX(inode)) + m_flags = EXT4_GET_BLOCKS_CREATE_ZERO; + /* + * We use i_size instead of i_disksize here because delalloc writeback + * can complete at any point during the I/O and subsequently push the + * i_disksize out to i_size. This could be beyond where direct I/O is + * happening and thus expose allocated blocks to direct I/O reads. + */ + else if ((map->m_lblk * (1 << blkbits)) >= i_size_read(inode)) + m_flags = EXT4_GET_BLOCKS_CREATE; + else if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) + m_flags = EXT4_GET_BLOCKS_IO_CREATE_EXT; + + ret = ext4_map_blocks(handle, inode, map, m_flags); + + /* + * We cannot fill holes in indirect tree based inodes as that could + * expose stale data in the case of a crash. Use the magic error code + * to fallback to buffered I/O. + */ + if (!m_flags && !ret) + ret = -ENOTBLK; + ext4_journal_stop(handle); - if (truncate) { - ext4_truncate_failed_write(inode); -orphan_del: - /* - * If truncate failed early the inode might still be on the - * orphan list; we need to make sure the inode is removed from - * the orphan list in that case. - */ - if (inode->i_nlink) - ext4_orphan_del(NULL, inode); - } + if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)) + goto retry; + return ret; } -const struct iomap_ops ext4_iomap_ops = { - .iomap_begin = ext4_iomap_begin, - .iomap_end = ext4_iomap_end, -}; -static int ext4_end_io_dio(struct kiocb *iocb, loff_t offset, - ssize_t size, void *private) +static int ext4_iomap_begin(struct inode *inode, loff_t offset, loff_t length, + unsigned flags, struct iomap *iomap, struct iomap *srcmap) { - ext4_io_end_t *io_end = private; + int ret; + struct ext4_map_blocks map; + u8 blkbits = inode->i_blkbits; - /* if not async direct IO just return */ - if (!io_end) - return 0; + if ((offset >> blkbits) > EXT4_MAX_LOGICAL_BLOCK) + return -EINVAL; - ext_debug("ext4_end_io_dio(): io_end 0x%p " - "for inode %lu, iocb 0x%p, offset %llu, size %zd\n", - io_end, io_end->inode->i_ino, iocb, offset, size); + if (WARN_ON_ONCE(ext4_has_inline_data(inode))) + return -ERANGE; /* - * Error during AIO DIO. We cannot convert unwritten extents as the - * data was not written. Just clear the unwritten flag and drop io_end. + * Calculate the first and last logical blocks respectively. */ - if (size <= 0) { - ext4_clear_io_unwritten_flag(io_end); - size = 0; - } - io_end->offset = offset; - io_end->size = size; - ext4_put_io_end(io_end); + map.m_lblk = offset >> blkbits; + map.m_len = min_t(loff_t, (offset + length - 1) >> blkbits, + EXT4_MAX_LOGICAL_BLOCK) - map.m_lblk + 1; + + if (flags & IOMAP_WRITE) + ret = ext4_iomap_alloc(inode, &map, flags); + else + ret = ext4_map_blocks(NULL, inode, &map, 0); + + if (ret < 0) + return ret; + + ext4_set_iomap(inode, iomap, &map, offset, length); return 0; } -/* - * Handling of direct IO writes. - * - * For ext4 extent files, ext4 will do direct-io write even to holes, - * preallocated extents, and those write extend the file, no need to - * fall back to buffered IO. - * - * For holes, we fallocate those blocks, mark them as unwritten - * If those blocks were preallocated, we mark sure they are split, but - * still keep the range to write as unwritten. - * - * The unwritten extents will be converted to written when DIO is completed. - * For async direct IO, since the IO may still pending when return, we - * set up an end_io call back function, which will do the conversion - * when async direct IO completed. - * - * If the O_DIRECT write will extend the file then add this inode to the - * orphan list. So recovery will truncate it back to the original size - * if the machine crashes during the write. - * - */ -static ssize_t ext4_direct_IO_write(struct kiocb *iocb, struct iov_iter *iter) +static int ext4_iomap_overwrite_begin(struct inode *inode, loff_t offset, + loff_t length, unsigned flags, struct iomap *iomap, + struct iomap *srcmap) { - struct file *file = iocb->ki_filp; - struct inode *inode = file->f_mapping->host; - struct ext4_inode_info *ei = EXT4_I(inode); - ssize_t ret; - loff_t offset = iocb->ki_pos; - size_t count = iov_iter_count(iter); - int overwrite = 0; - get_block_t *get_block_func = NULL; - int dio_flags = 0; - loff_t final_size = offset + count; - int orphan = 0; - handle_t *handle; - - if (final_size > inode->i_size || final_size > ei->i_disksize) { - /* Credits for sb + inode write */ - handle = ext4_journal_start(inode, EXT4_HT_INODE, 2); - if (IS_ERR(handle)) { - ret = PTR_ERR(handle); - goto out; - } - ret = ext4_orphan_add(handle, inode); - if (ret) { - ext4_journal_stop(handle); - goto out; - } - orphan = 1; - ext4_update_i_disksize(inode, inode->i_size); - ext4_journal_stop(handle); - } - - BUG_ON(iocb->private == NULL); + int ret; /* - * Make all waiters for direct IO properly wait also for extent - * conversion. This also disallows race between truncate() and - * overwrite DIO as i_dio_count needs to be incremented under i_mutex. + * Even for writes we don't need to allocate blocks, so just pretend + * we are reading to save overhead of starting a transaction. */ - inode_dio_begin(inode); - - /* If we do a overwrite dio, i_mutex locking can be released */ - overwrite = *((int *)iocb->private); - - if (overwrite) - inode_unlock(inode); + flags &= ~IOMAP_WRITE; + ret = ext4_iomap_begin(inode, offset, length, flags, iomap, srcmap); + WARN_ON_ONCE(iomap->type != IOMAP_MAPPED); + return ret; +} +static int ext4_iomap_end(struct inode *inode, loff_t offset, loff_t length, + ssize_t written, unsigned flags, struct iomap *iomap) +{ /* - * For extent mapped files we could direct write to holes and fallocate. - * - * Allocated blocks to fill the hole are marked as unwritten to prevent - * parallel buffered read to expose the stale data before DIO complete - * the data IO. - * - * As to previously fallocated extents, ext4 get_block will just simply - * mark the buffer mapped but still keep the extents unwritten. - * - * For non AIO case, we will convert those unwritten extents to written - * after return back from blockdev_direct_IO. That way we save us from - * allocating io_end structure and also the overhead of offloading - * the extent convertion to a workqueue. - * - * For async DIO, the conversion needs to be deferred when the - * IO is completed. The ext4 end_io callback function will be - * called to take care of the conversion work. Here for async - * case, we allocate an io_end structure to hook to the iocb. + * Check to see whether an error occurred while writing out the data to + * the allocated blocks. If so, return the magic error code so that we + * fallback to buffered I/O and attempt to complete the remainder of + * the I/O. Any blocks that may have been allocated in preparation for + * the direct I/O will be reused during buffered I/O. */ - iocb->private = NULL; - if (overwrite) - get_block_func = ext4_dio_get_block_overwrite; - else if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS) || - round_down(offset, i_blocksize(inode)) >= inode->i_size) { - get_block_func = ext4_dio_get_block; - dio_flags = DIO_LOCKING | DIO_SKIP_HOLES; - } else if (is_sync_kiocb(iocb)) { - get_block_func = ext4_dio_get_block_unwritten_sync; - dio_flags = DIO_LOCKING; - } else { - get_block_func = ext4_dio_get_block_unwritten_async; - dio_flags = DIO_LOCKING; - } - ret = __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev, iter, - get_block_func, ext4_end_io_dio, NULL, - dio_flags); + if (flags & (IOMAP_WRITE | IOMAP_DIRECT) && written == 0) + return -ENOTBLK; - if (ret > 0 && !overwrite && ext4_test_inode_state(inode, - EXT4_STATE_DIO_UNWRITTEN)) { - int err; - /* - * for non AIO case, since the IO is already - * completed, we could do the conversion right here - */ - err = ext4_convert_unwritten_extents(NULL, inode, - offset, ret); - if (err < 0) - ret = err; - ext4_clear_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN); - } + return 0; +} - inode_dio_end(inode); - /* take i_mutex locking again if we do a ovewrite dio */ - if (overwrite) - inode_lock(inode); +const struct iomap_ops ext4_iomap_ops = { + .iomap_begin = ext4_iomap_begin, + .iomap_end = ext4_iomap_end, +}; - if (ret < 0 && final_size > inode->i_size) - ext4_truncate_failed_write(inode); +const struct iomap_ops ext4_iomap_overwrite_ops = { + .iomap_begin = ext4_iomap_overwrite_begin, + .iomap_end = ext4_iomap_end, +}; - /* Handle extending of i_size after direct IO write */ - if (orphan) { - int err; +static bool ext4_iomap_is_delalloc(struct inode *inode, + struct ext4_map_blocks *map) +{ + struct extent_status es; + ext4_lblk_t offset = 0, end = map->m_lblk + map->m_len - 1; - /* Credits for sb + inode write */ - handle = ext4_journal_start(inode, EXT4_HT_INODE, 2); - if (IS_ERR(handle)) { - /* - * We wrote the data but cannot extend - * i_size. Bail out. In async io case, we do - * not return error here because we have - * already submmitted the corresponding - * bio. Returning error here makes the caller - * think that this IO is done and failed - * resulting in race with bio's completion - * handler. - */ - if (!ret) - ret = PTR_ERR(handle); - if (inode->i_nlink) - ext4_orphan_del(NULL, inode); + ext4_es_find_extent_range(inode, &ext4_es_is_delayed, + map->m_lblk, end, &es); - goto out; - } - if (inode->i_nlink) - ext4_orphan_del(handle, inode); - if (ret > 0) { - loff_t end = offset + ret; - if (end > inode->i_size || end > ei->i_disksize) { - ext4_update_i_disksize(inode, end); - if (end > inode->i_size) - i_size_write(inode, end); - /* - * We're going to return a positive `ret' - * here due to non-zero-length I/O, so there's - * no way of reporting error returns from - * ext4_mark_inode_dirty() to userspace. So - * ignore it. - */ - ext4_mark_inode_dirty(handle, inode); - } - } - err = ext4_journal_stop(handle); - if (ret == 0) - ret = err; + if (!es.es_len || es.es_lblk > end) + return false; + + if (es.es_lblk > map->m_lblk) { + map->m_len = es.es_lblk - map->m_lblk; + return false; } -out: - return ret; -} -static ssize_t ext4_direct_IO_read(struct kiocb *iocb, struct iov_iter *iter) -{ - struct address_space *mapping = iocb->ki_filp->f_mapping; - struct inode *inode = mapping->host; - size_t count = iov_iter_count(iter); - ssize_t ret; + offset = map->m_lblk - es.es_lblk; + map->m_len = es.es_len - offset; - /* - * Shared inode_lock is enough for us - it protects against concurrent - * writes & truncates and since we take care of writing back page cache, - * we are protected against page writeback as well. - */ - inode_lock_shared(inode); - ret = filemap_write_and_wait_range(mapping, iocb->ki_pos, - iocb->ki_pos + count - 1); - if (ret) - goto out_unlock; - ret = __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev, - iter, ext4_dio_get_block, NULL, NULL, 0); -out_unlock: - inode_unlock_shared(inode); - return ret; + return true; } -static ssize_t ext4_direct_IO(struct kiocb *iocb, struct iov_iter *iter) +static int ext4_iomap_begin_report(struct inode *inode, loff_t offset, + loff_t length, unsigned int flags, + struct iomap *iomap, struct iomap *srcmap) { - struct file *file = iocb->ki_filp; - struct inode *inode = file->f_mapping->host; - size_t count = iov_iter_count(iter); - loff_t offset = iocb->ki_pos; - ssize_t ret; + int ret; + bool delalloc = false; + struct ext4_map_blocks map; + u8 blkbits = inode->i_blkbits; -#ifdef CONFIG_FS_ENCRYPTION - if (IS_ENCRYPTED(inode) && S_ISREG(inode->i_mode)) - return 0; -#endif + if ((offset >> blkbits) > EXT4_MAX_LOGICAL_BLOCK) + return -EINVAL; + + if (ext4_has_inline_data(inode)) { + ret = ext4_inline_data_iomap(inode, iomap); + if (ret != -EAGAIN) { + if (ret == 0 && offset >= iomap->length) + ret = -ENOENT; + return ret; + } + } /* - * If we are doing data journalling we don't support O_DIRECT + * Calculate the first and last logical block respectively. */ - if (ext4_should_journal_data(inode)) - return 0; + map.m_lblk = offset >> blkbits; + map.m_len = min_t(loff_t, (offset + length - 1) >> blkbits, + EXT4_MAX_LOGICAL_BLOCK) - map.m_lblk + 1; - /* Let buffer I/O handle the inline data case. */ - if (ext4_has_inline_data(inode)) - return 0; + ret = ext4_map_blocks(NULL, inode, &map, 0); + if (ret < 0) + return ret; + if (ret == 0) + delalloc = ext4_iomap_is_delalloc(inode, &map); - trace_ext4_direct_IO_enter(inode, offset, count, iov_iter_rw(iter)); - if (iov_iter_rw(iter) == READ) - ret = ext4_direct_IO_read(iocb, iter); - else - ret = ext4_direct_IO_write(iocb, iter); - trace_ext4_direct_IO_exit(inode, offset, count, iov_iter_rw(iter), ret); - return ret; + ext4_set_iomap(inode, iomap, &map, offset, length); + if (delalloc && iomap->type == IOMAP_HOLE) + iomap->type = IOMAP_DELALLOC; + + return 0; } +const struct iomap_ops ext4_iomap_report_ops = { + .iomap_begin = ext4_iomap_begin_report, +}; + /* * Pages can be marked dirty completely asynchronously from ext4's journalling * activity. By filemap_sync_pte(), try_to_unmap_one(), etc. We cannot do @@ -3954,7 +3596,7 @@ static const struct address_space_operations ext4_aops = { .bmap = ext4_bmap, .invalidatepage = ext4_invalidatepage, .releasepage = ext4_releasepage, - .direct_IO = ext4_direct_IO, + .direct_IO = noop_direct_IO, .migratepage = buffer_migrate_page, .is_partially_uptodate = block_is_partially_uptodate, .error_remove_page = generic_error_remove_page, @@ -3971,7 +3613,7 @@ static const struct address_space_operations ext4_journalled_aops = { .bmap = ext4_bmap, .invalidatepage = ext4_journalled_invalidatepage, .releasepage = ext4_releasepage, - .direct_IO = ext4_direct_IO, + .direct_IO = noop_direct_IO, .is_partially_uptodate = block_is_partially_uptodate, .error_remove_page = generic_error_remove_page, }; @@ -3985,9 +3627,9 @@ static const struct address_space_operations ext4_da_aops = { .write_end = ext4_da_write_end, .set_page_dirty = ext4_set_page_dirty, .bmap = ext4_bmap, - .invalidatepage = ext4_da_invalidatepage, + .invalidatepage = ext4_invalidatepage, .releasepage = ext4_releasepage, - .direct_IO = ext4_direct_IO, + .direct_IO = noop_direct_IO, .migratepage = buffer_migrate_page, .is_partially_uptodate = block_is_partially_uptodate, .error_remove_page = generic_error_remove_page, @@ -4081,8 +3723,12 @@ static int __ext4_block_zero_page_range(handle_t *handle, if (S_ISREG(inode->i_mode) && IS_ENCRYPTED(inode)) { /* We expect the key to be set. */ BUG_ON(!fscrypt_has_encryption_key(inode)); - WARN_ON_ONCE(fscrypt_decrypt_pagecache_blocks( - page, blocksize, bh_offset(bh))); + err = fscrypt_decrypt_pagecache_blocks(page, blocksize, + bh_offset(bh)); + if (err) { + clear_buffer_uptodate(bh); + goto unlock; + } } } if (ext4_should_journal_data(inode)) { @@ -4292,11 +3938,17 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length) unsigned int credits; int ret = 0; - if (!S_ISREG(inode->i_mode)) - return -EOPNOTSUPP; - trace_ext4_punch_hole(inode, offset, length, 0); + ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA); + if (ext4_has_inline_data(inode)) { + down_write(&EXT4_I(inode)->i_mmap_sem); + ret = ext4_convert_inline_data(inode); + up_write(&EXT4_I(inode)->i_mmap_sem); + if (ret) + return ret; + } + /* * Write out all dirty pages to avoid race conditions * Then release them. @@ -4611,6 +4263,8 @@ static int __ext4_get_inode_loc(struct inode *inode, bh = sb_getblk(sb, block); if (unlikely(!bh)) return -ENOMEM; + if (ext4_simulate_fail(sb, EXT4_SIM_INODE_EIO)) + goto simulate_eio; if (!buffer_uptodate(bh)) { lock_buffer(bh); @@ -4709,6 +4363,8 @@ make_io: blk_finish_plug(&plug); wait_on_buffer(bh); if (!buffer_uptodate(bh)) { + simulate_eio: + ext4_set_errno(inode->i_sb, EIO); EXT4_ERROR_INODE_BLOCK(inode, block, "unable to read itable block"); brelse(bh); @@ -4739,6 +4395,8 @@ static bool ext4_should_use_dax(struct inode *inode) return false; if (ext4_test_inode_flag(inode, EXT4_INODE_ENCRYPT)) return false; + if (ext4_test_inode_flag(inode, EXT4_INODE_VERITY)) + return false; return true; } @@ -4763,9 +4421,11 @@ void ext4_set_inode_flags(struct inode *inode) new_fl |= S_ENCRYPTED; if (flags & EXT4_CASEFOLD_FL) new_fl |= S_CASEFOLD; + if (flags & EXT4_VERITY_FL) + new_fl |= S_VERITY; inode_set_flags(inode, new_fl, S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC|S_DAX| - S_ENCRYPTED|S_CASEFOLD); + S_ENCRYPTED|S_CASEFOLD|S_VERITY); } static blkcnt_t ext4_inode_blocks(struct ext4_inode *raw_inode, @@ -4918,7 +4578,9 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino, sizeof(gen)); } - if (!ext4_inode_csum_verify(inode, raw_inode, ei)) { + if (!ext4_inode_csum_verify(inode, raw_inode, ei) || + ext4_simulate_fail(sb, EXT4_SIM_INODE_CRC)) { + ext4_set_errno(inode->i_sb, EFSBADCRC); ext4_error_inode(inode, function, line, 0, "iget: checksum invalid"); ret = -EFSBADCRC; @@ -4982,6 +4644,18 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino, ret = -EFSCORRUPTED; goto bad_inode; } + /* + * If dir_index is not enabled but there's dir with INDEX flag set, + * we'd normally treat htree data as empty space. But with metadata + * checksumming that corrupts checksums so forbid that. + */ + if (!ext4_has_feature_dir_index(sb) && ext4_has_metadata_csum(sb) && + ext4_test_inode_flag(inode, EXT4_INODE_INDEX)) { + ext4_error_inode(inode, function, line, 0, + "iget: Dir with htree data on filesystem without dir_index feature."); + ret = -EFSCORRUPTED; + goto bad_inode; + } ei->i_disksize = inode->i_size; #ifdef CONFIG_QUOTA ei->i_reserved_quota = 0; @@ -5119,6 +4793,9 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino, "iget: bogus i_mode (%o)", inode->i_mode); goto bad_inode; } + if (IS_CASEFOLDED(inode) && !ext4_has_feature_casefold(inode->i_sb)) + ext4_error_inode(inode, function, line, 0, + "casefold flag without casefold feature"); brelse(iloc.bh); unlock_new_inode(inode); @@ -5454,6 +5131,7 @@ int ext4_write_inode(struct inode *inode, struct writeback_control *wbc) if (wbc->sync_mode == WB_SYNC_ALL && !wbc->for_sync) sync_dirty_buffer(iloc.bh); if (buffer_req(iloc.bh) && !buffer_uptodate(iloc.bh)) { + ext4_set_errno(inode->i_sb, EIO); EXT4_ERROR_INODE_BLOCK(inode, iloc.bh->b_blocknr, "IO error syncing inode"); err = -EIO; @@ -5478,11 +5156,15 @@ static void ext4_wait_for_tail_page_commit(struct inode *inode) offset = inode->i_size & (PAGE_SIZE - 1); /* - * All buffers in the last page remain valid? Then there's nothing to - * do. We do the check mainly to optimize the common PAGE_SIZE == - * blocksize case + * 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 + * 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 + * blocksize == PAGESIZE. */ - if (offset > PAGE_SIZE - i_blocksize(inode)) + if (!offset || offset > (PAGE_SIZE - i_blocksize(inode))) return; while (1) { page = find_lock_page(inode->i_mapping, @@ -5555,6 +5237,10 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr) if (error) return error; + error = fsverity_prepare_setattr(dentry, attr); + if (error) + return error; + if (is_quota_modification(inode, attr)) { error = dquot_initialize(inode); if (error) @@ -5724,7 +5410,8 @@ int ext4_getattr(const struct path *path, struct kstat *stat, struct ext4_inode_info *ei = EXT4_I(inode); unsigned int flags; - if (EXT4_FITS_IN_INODE(raw_inode, ei, i_crtime)) { + if ((request_mask & STATX_BTIME) && + EXT4_FITS_IN_INODE(raw_inode, ei, i_crtime)) { stat->result_mask |= STATX_BTIME; stat->btime.tv_sec = ei->i_crtime.tv_sec; stat->btime.tv_nsec = ei->i_crtime.tv_nsec; @@ -5741,12 +5428,15 @@ int ext4_getattr(const struct path *path, struct kstat *stat, stat->attributes |= STATX_ATTR_IMMUTABLE; if (flags & EXT4_NODUMP_FL) stat->attributes |= STATX_ATTR_NODUMP; + if (flags & EXT4_VERITY_FL) + stat->attributes |= STATX_ATTR_VERITY; stat->attributes_mask |= (STATX_ATTR_APPEND | STATX_ATTR_COMPRESSED | STATX_ATTR_ENCRYPTED | STATX_ATTR_IMMUTABLE | - STATX_ATTR_NODUMP); + STATX_ATTR_NODUMP | + STATX_ATTR_VERITY); generic_fillattr(inode, stat); return 0; @@ -5936,8 +5626,23 @@ static int __ext4_expand_extra_isize(struct inode *inode, { struct ext4_inode *raw_inode; struct ext4_xattr_ibody_header *header; + unsigned int inode_size = EXT4_INODE_SIZE(inode->i_sb); + struct ext4_inode_info *ei = EXT4_I(inode); int error; + /* this was checked at iget time, but double check for good measure */ + if ((EXT4_GOOD_OLD_INODE_SIZE + ei->i_extra_isize > inode_size) || + (ei->i_extra_isize & 3)) { + EXT4_ERROR_INODE(inode, "bad extra_isize %u (inode size %u)", + ei->i_extra_isize, + EXT4_INODE_SIZE(inode->i_sb)); + return -EFSCORRUPTED; + } + if ((new_extra_isize < ei->i_extra_isize) || + (new_extra_isize < 4) || + (new_extra_isize > inode_size - EXT4_GOOD_OLD_INODE_SIZE)) + return -EINVAL; /* Should never happen */ + raw_inode = ext4_raw_inode(iloc); header = IHDR(inode, raw_inode); @@ -5989,9 +5694,8 @@ static int ext4_try_to_expand_extra_isize(struct inode *inode, * If this is felt to be critical, then e2fsck should be run to * force a large enough s_min_extra_isize. */ - if (ext4_handle_valid(handle) && - jbd2_journal_extend(handle, - EXT4_DATA_TRANS_BLOCKS(inode->i_sb)) != 0) + if (ext4_journal_extend(handle, + EXT4_DATA_TRANS_BLOCKS(inode->i_sb), 0) != 0) return -ENOSPC; if (ext4_write_trylock_xattr(inode, &no_expand) == 0) @@ -6031,7 +5735,7 @@ int ext4_expand_extra_isize(struct inode *inode, error = ext4_journal_get_write_access(handle, iloc->bh); if (error) { brelse(iloc->bh); - goto out_stop; + goto out_unlock; } error = __ext4_expand_extra_isize(inode, new_extra_isize, iloc, @@ -6041,8 +5745,8 @@ int ext4_expand_extra_isize(struct inode *inode, if (!error) error = rc; +out_unlock: ext4_write_unlock_xattr(inode, &no_expand); -out_stop: ext4_journal_stop(handle); return error; } diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index 442f7ef873fc..a0ec750018dd 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -745,6 +745,74 @@ static void ext4_fill_fsxattr(struct inode *inode, struct fsxattr *fa) fa->fsx_projid = from_kprojid(&init_user_ns, ei->i_projid); } +/* copied from fs/ioctl.c */ +static int fiemap_check_ranges(struct super_block *sb, + u64 start, u64 len, u64 *new_len) +{ + u64 maxbytes = (u64) sb->s_maxbytes; + + *new_len = len; + + if (len == 0) + return -EINVAL; + + if (start > maxbytes) + return -EFBIG; + + /* + * Shrink request scope to what the fs can actually handle. + */ + if (len > maxbytes || (maxbytes - len) < start) + *new_len = maxbytes - start; + + return 0; +} + +/* So that the fiemap access checks can't overflow on 32 bit machines. */ +#define FIEMAP_MAX_EXTENTS (UINT_MAX / sizeof(struct fiemap_extent)) + +static int ext4_ioctl_get_es_cache(struct file *filp, unsigned long arg) +{ + struct fiemap fiemap; + struct fiemap __user *ufiemap = (struct fiemap __user *) arg; + struct fiemap_extent_info fieinfo = { 0, }; + struct inode *inode = file_inode(filp); + struct super_block *sb = inode->i_sb; + u64 len; + int error; + + if (copy_from_user(&fiemap, ufiemap, sizeof(fiemap))) + return -EFAULT; + + if (fiemap.fm_extent_count > FIEMAP_MAX_EXTENTS) + return -EINVAL; + + error = fiemap_check_ranges(sb, fiemap.fm_start, fiemap.fm_length, + &len); + if (error) + return error; + + fieinfo.fi_flags = fiemap.fm_flags; + fieinfo.fi_extents_max = fiemap.fm_extent_count; + fieinfo.fi_extents_start = ufiemap->fm_extents; + + if (fiemap.fm_extent_count != 0 && + !access_ok(fieinfo.fi_extents_start, + fieinfo.fi_extents_max * sizeof(struct fiemap_extent))) + return -EFAULT; + + if (fieinfo.fi_flags & FIEMAP_FLAG_SYNC) + filemap_write_and_wait(inode->i_mapping); + + error = ext4_get_es_cache(inode, &fieinfo, fiemap.fm_start, len); + fiemap.fm_flags = fieinfo.fi_flags; + fiemap.fm_mapped_extents = fieinfo.fi_extents_mapped; + if (copy_to_user(ufiemap, &fiemap, sizeof(fiemap))) + error = -EFAULT; + + return error; +} + long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { struct inode *inode = file_inode(filp); @@ -1113,8 +1181,62 @@ resizefs_out: #endif } case EXT4_IOC_GET_ENCRYPTION_POLICY: + if (!ext4_has_feature_encrypt(sb)) + return -EOPNOTSUPP; return fscrypt_ioctl_get_policy(filp, (void __user *)arg); + case FS_IOC_GET_ENCRYPTION_POLICY_EX: + if (!ext4_has_feature_encrypt(sb)) + return -EOPNOTSUPP; + return fscrypt_ioctl_get_policy_ex(filp, (void __user *)arg); + + case FS_IOC_ADD_ENCRYPTION_KEY: + if (!ext4_has_feature_encrypt(sb)) + return -EOPNOTSUPP; + return fscrypt_ioctl_add_key(filp, (void __user *)arg); + + case FS_IOC_REMOVE_ENCRYPTION_KEY: + if (!ext4_has_feature_encrypt(sb)) + return -EOPNOTSUPP; + return fscrypt_ioctl_remove_key(filp, (void __user *)arg); + + case FS_IOC_REMOVE_ENCRYPTION_KEY_ALL_USERS: + if (!ext4_has_feature_encrypt(sb)) + return -EOPNOTSUPP; + return fscrypt_ioctl_remove_key_all_users(filp, + (void __user *)arg); + case FS_IOC_GET_ENCRYPTION_KEY_STATUS: + if (!ext4_has_feature_encrypt(sb)) + return -EOPNOTSUPP; + return fscrypt_ioctl_get_key_status(filp, (void __user *)arg); + + case EXT4_IOC_CLEAR_ES_CACHE: + { + if (!inode_owner_or_capable(inode)) + return -EACCES; + ext4_clear_inode_es(inode); + return 0; + } + + case EXT4_IOC_GETSTATE: + { + __u32 state = 0; + + if (ext4_test_inode_state(inode, EXT4_STATE_EXT_PRECACHED)) + state |= EXT4_STATE_FLAG_EXT_PRECACHED; + if (ext4_test_inode_state(inode, EXT4_STATE_NEW)) + state |= EXT4_STATE_FLAG_NEW; + if (ext4_test_inode_state(inode, EXT4_STATE_NEWENTRY)) + state |= EXT4_STATE_FLAG_NEWENTRY; + if (ext4_test_inode_state(inode, EXT4_STATE_DA_ALLOC_CLOSE)) + state |= EXT4_STATE_FLAG_DA_ALLOC_CLOSE; + + return put_user(state, (__u32 __user *) arg); + } + + case EXT4_IOC_GET_ES_CACHE: + return ext4_ioctl_get_es_cache(filp, arg); + case EXT4_IOC_FSGETXATTR: { struct fsxattr fa; @@ -1171,6 +1293,17 @@ out: } case EXT4_IOC_SHUTDOWN: return ext4_shutdown(sb, arg); + + case FS_IOC_ENABLE_VERITY: + if (!ext4_has_feature_verity(sb)) + return -EOPNOTSUPP; + return fsverity_ioctl_enable(filp, (const void __user *)arg); + + case FS_IOC_MEASURE_VERITY: + if (!ext4_has_feature_verity(sb)) + return -EOPNOTSUPP; + return fsverity_ioctl_measure(filp, (void __user *)arg); + default: return -ENOTTY; } @@ -1227,12 +1360,25 @@ long ext4_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) } case EXT4_IOC_MOVE_EXT: case EXT4_IOC_RESIZE_FS: + case FITRIM: case EXT4_IOC_PRECACHE_EXTENTS: case EXT4_IOC_SET_ENCRYPTION_POLICY: case EXT4_IOC_GET_ENCRYPTION_PWSALT: case EXT4_IOC_GET_ENCRYPTION_POLICY: + case FS_IOC_GET_ENCRYPTION_POLICY_EX: + case FS_IOC_ADD_ENCRYPTION_KEY: + case FS_IOC_REMOVE_ENCRYPTION_KEY: + case FS_IOC_REMOVE_ENCRYPTION_KEY_ALL_USERS: + case FS_IOC_GET_ENCRYPTION_KEY_STATUS: case EXT4_IOC_SHUTDOWN: case FS_IOC_GETFSMAP: + case FS_IOC_ENABLE_VERITY: + case FS_IOC_MEASURE_VERITY: + case EXT4_IOC_CLEAR_ES_CACHE: + case EXT4_IOC_GETSTATE: + case EXT4_IOC_GET_ES_CACHE: + case EXT4_IOC_FSGETXATTR: + case EXT4_IOC_FSSETXATTR: break; default: return -ENOIOCTLCMD; diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index a3e2767bdf2f..f64838187559 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -3895,6 +3895,7 @@ ext4_mb_discard_group_preallocations(struct super_block *sb, bitmap_bh = ext4_read_block_bitmap(sb, group); if (IS_ERR(bitmap_bh)) { err = PTR_ERR(bitmap_bh); + ext4_set_errno(sb, -err); ext4_error(sb, "Error %d reading block bitmap for %u", err, group); return 0; @@ -4063,6 +4064,7 @@ repeat: err = ext4_mb_load_buddy_gfp(sb, group, &e4b, GFP_NOFS|__GFP_NOFAIL); if (err) { + ext4_set_errno(sb, -err); ext4_error(sb, "Error %d loading buddy information for %u", err, group); continue; @@ -4071,6 +4073,7 @@ repeat: bitmap_bh = ext4_read_block_bitmap(sb, group); if (IS_ERR(bitmap_bh)) { err = PTR_ERR(bitmap_bh); + ext4_set_errno(sb, -err); ext4_error(sb, "Error %d reading block bitmap for %u", err, group); ext4_mb_unload_buddy(&e4b); @@ -4325,6 +4328,7 @@ ext4_mb_discard_lg_preallocations(struct super_block *sb, err = ext4_mb_load_buddy_gfp(sb, group, &e4b, GFP_NOFS|__GFP_NOFAIL); if (err) { + ext4_set_errno(sb, -err); ext4_error(sb, "Error %d loading buddy information for %u", err, group); continue; diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c index b1e4d359f73b..89725fa42573 100644 --- a/fs/ext4/migrate.c +++ b/fs/ext4/migrate.c @@ -50,29 +50,9 @@ static int finish_range(handle_t *handle, struct inode *inode, needed = ext4_ext_calc_credits_for_single_extent(inode, lb->last_block - lb->first_block + 1, path); - /* - * Make sure the credit we accumalated is not really high - */ - if (needed && ext4_handle_has_enough_credits(handle, - EXT4_RESERVE_TRANS_BLOCKS)) { - up_write((&EXT4_I(inode)->i_data_sem)); - retval = ext4_journal_restart(handle, needed); - down_write((&EXT4_I(inode)->i_data_sem)); - if (retval) - goto err_out; - } else if (needed) { - retval = ext4_journal_extend(handle, needed); - if (retval) { - /* - * IF not able to extend the journal restart the journal - */ - up_write((&EXT4_I(inode)->i_data_sem)); - retval = ext4_journal_restart(handle, needed); - down_write((&EXT4_I(inode)->i_data_sem)); - if (retval) - goto err_out; - } - } + retval = ext4_datasem_ensure_credits(handle, inode, needed, needed, 0); + if (retval < 0) + goto err_out; retval = ext4_ext_insert_extent(handle, inode, &path, &newext, 0); err_out: up_write((&EXT4_I(inode)->i_data_sem)); @@ -196,42 +176,30 @@ static int update_tind_extent_range(handle_t *handle, struct inode *inode, } -static int extend_credit_for_blkdel(handle_t *handle, struct inode *inode) -{ - int retval = 0, needed; - - if (ext4_handle_has_enough_credits(handle, EXT4_RESERVE_TRANS_BLOCKS+1)) - return 0; - /* - * We are freeing a blocks. During this we touch - * superblock, group descriptor and block bitmap. - * So allocate a credit of 3. We may update - * quota (user and group). - */ - needed = 3 + EXT4_MAXQUOTAS_TRANS_BLOCKS(inode->i_sb); - - if (ext4_journal_extend(handle, needed) != 0) - retval = ext4_journal_restart(handle, needed); - - return retval; -} - static int free_dind_blocks(handle_t *handle, struct inode *inode, __le32 i_data) { int i; __le32 *tmp_idata; struct buffer_head *bh; + struct super_block *sb = inode->i_sb; unsigned long max_entries = inode->i_sb->s_blocksize >> 2; + int err; - bh = ext4_sb_bread(inode->i_sb, le32_to_cpu(i_data), 0); + bh = ext4_sb_bread(sb, le32_to_cpu(i_data), 0); if (IS_ERR(bh)) return PTR_ERR(bh); tmp_idata = (__le32 *)bh->b_data; for (i = 0; i < max_entries; i++) { if (tmp_idata[i]) { - extend_credit_for_blkdel(handle, inode); + err = ext4_journal_ensure_credits(handle, + EXT4_RESERVE_TRANS_BLOCKS, + ext4_free_metadata_revoke_credits(sb, 1)); + if (err < 0) { + put_bh(bh); + return err; + } ext4_free_blocks(handle, inode, NULL, le32_to_cpu(tmp_idata[i]), 1, EXT4_FREE_BLOCKS_METADATA | @@ -239,7 +207,10 @@ static int free_dind_blocks(handle_t *handle, } } put_bh(bh); - extend_credit_for_blkdel(handle, inode); + err = ext4_journal_ensure_credits(handle, EXT4_RESERVE_TRANS_BLOCKS, + ext4_free_metadata_revoke_credits(sb, 1)); + if (err < 0) + return err; ext4_free_blocks(handle, inode, NULL, le32_to_cpu(i_data), 1, EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET); @@ -270,7 +241,10 @@ static int free_tind_blocks(handle_t *handle, } } put_bh(bh); - extend_credit_for_blkdel(handle, inode); + retval = ext4_journal_ensure_credits(handle, EXT4_RESERVE_TRANS_BLOCKS, + ext4_free_metadata_revoke_credits(inode->i_sb, 1)); + if (retval < 0) + return retval; ext4_free_blocks(handle, inode, NULL, le32_to_cpu(i_data), 1, EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET); @@ -283,7 +257,11 @@ static int free_ind_block(handle_t *handle, struct inode *inode, __le32 *i_data) /* ei->i_data[EXT4_IND_BLOCK] */ if (i_data[0]) { - extend_credit_for_blkdel(handle, inode); + retval = ext4_journal_ensure_credits(handle, + EXT4_RESERVE_TRANS_BLOCKS, + ext4_free_metadata_revoke_credits(inode->i_sb, 1)); + if (retval < 0) + return retval; ext4_free_blocks(handle, inode, NULL, le32_to_cpu(i_data[0]), 1, EXT4_FREE_BLOCKS_METADATA | @@ -318,12 +296,9 @@ static int ext4_ext_swap_inode_data(handle_t *handle, struct inode *inode, * One credit accounted for writing the * i_data field of the original inode */ - retval = ext4_journal_extend(handle, 1); - if (retval) { - retval = ext4_journal_restart(handle, 1); - if (retval) - goto err_out; - } + retval = ext4_journal_ensure_credits(handle, 1, 0); + if (retval < 0) + goto err_out; i_data[0] = ei->i_data[EXT4_IND_BLOCK]; i_data[1] = ei->i_data[EXT4_DIND_BLOCK]; @@ -391,15 +366,20 @@ static int free_ext_idx(handle_t *handle, struct inode *inode, ix = EXT_FIRST_INDEX(eh); for (i = 0; i < le16_to_cpu(eh->eh_entries); i++, ix++) { retval = free_ext_idx(handle, inode, ix); - if (retval) - break; + if (retval) { + put_bh(bh); + return retval; + } } } put_bh(bh); - extend_credit_for_blkdel(handle, inode); + retval = ext4_journal_ensure_credits(handle, EXT4_RESERVE_TRANS_BLOCKS, + ext4_free_metadata_revoke_credits(inode->i_sb, 1)); + if (retval < 0) + return retval; ext4_free_blocks(handle, inode, NULL, block, 1, EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET); - return retval; + return 0; } /* @@ -574,9 +554,9 @@ err_out: } /* We mark the tmp_inode dirty via ext4_ext_tree_init. */ - if (ext4_journal_extend(handle, 1) != 0) - ext4_journal_restart(handle, 1); - + retval = ext4_journal_ensure_credits(handle, 1, 0); + if (retval < 0) + goto out_stop; /* * Mark the tmp_inode as of size zero */ @@ -594,6 +574,7 @@ err_out: /* Reset the extent details */ ext4_ext_tree_init(handle, tmp_inode); +out_stop: ext4_journal_stop(handle); out: unlock_new_inode(tmp_inode); diff --git a/fs/ext4/mmp.c b/fs/ext4/mmp.c index 2305b4374fd3..87f7551c5132 100644 --- a/fs/ext4/mmp.c +++ b/fs/ext4/mmp.c @@ -120,10 +120,10 @@ void __dump_mmp_msg(struct super_block *sb, struct mmp_struct *mmp, { __ext4_warning(sb, function, line, "%s", msg); __ext4_warning(sb, function, line, - "MMP failure info: last update time: %llu, last update " - "node: %s, last update device: %s", - (long long unsigned int) le64_to_cpu(mmp->mmp_time), - mmp->mmp_nodename, mmp->mmp_bdevname); + "MMP failure info: last update time: %llu, last update node: %.*s, last update device: %.*s", + (unsigned long long)le64_to_cpu(mmp->mmp_time), + (int)sizeof(mmp->mmp_nodename), mmp->mmp_nodename, + (int)sizeof(mmp->mmp_bdevname), mmp->mmp_bdevname); } /* @@ -154,6 +154,7 @@ 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, @@ -173,8 +174,10 @@ static int kmmpd(void *data) * (s_mmp_update_interval * 60) seconds. */ if (retval) { - if ((failed_writes % 60) == 0) + if ((failed_writes % 60) == 0) { + ext4_set_errno(sb, -retval); ext4_error(sb, "Error writing to MMP block"); + } failed_writes++; } @@ -205,6 +208,7 @@ static int kmmpd(void *data) retval = read_mmp_block(sb, &bh_check, mmp_block); if (retval) { + ext4_set_errno(sb, -retval); ext4_error(sb, "error reading MMP data: %d", retval); goto exit_thread; @@ -218,6 +222,7 @@ static int kmmpd(void *data) "Error while updating MMP info. " "The filesystem seems to have been" " multiply mounted."); + ext4_set_errno(sb, EBUSY); ext4_error(sb, "abort"); put_bh(bh_check); retval = -EBUSY; @@ -375,7 +380,8 @@ skip: /* * Start a kernel thread to update the MMP block periodically. */ - EXT4_SB(sb)->s_mmp_tsk = kthread_run(kmmpd, mmpd_data, "kmmpd-%s", + EXT4_SB(sb)->s_mmp_tsk = kthread_run(kmmpd, mmpd_data, "kmmpd-%.*s", + (int)sizeof(mmp->mmp_bdevname), bdevname(bh->b_bdev, mmp->mmp_bdevname)); if (IS_ERR(EXT4_SB(sb)->s_mmp_tsk)) { diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 129029534075..ceff4b4b1877 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -109,7 +109,10 @@ static struct buffer_head *__ext4_read_dirblock(struct inode *inode, struct ext4_dir_entry *dirent; int is_dx_block = 0; - bh = ext4_bread(NULL, inode, block, 0); + if (ext4_simulate_fail(inode->i_sb, EXT4_SIM_DIRBLOCK_EIO)) + bh = ERR_PTR(-EIO); + else + bh = ext4_bread(NULL, inode, block, 0); if (IS_ERR(bh)) { __ext4_warning(inode->i_sb, func, line, "inode #%lu: lblock %lu: comm %s: " @@ -153,9 +156,11 @@ static struct buffer_head *__ext4_read_dirblock(struct inode *inode, * caller is sure it should be an index block. */ if (is_dx_block && type == INDEX) { - if (ext4_dx_csum_verify(inode, dirent)) + if (ext4_dx_csum_verify(inode, dirent) && + !ext4_simulate_fail(inode->i_sb, EXT4_SIM_DIRBLOCK_CRC)) set_buffer_verified(bh); else { + ext4_set_errno(inode->i_sb, EFSBADCRC); ext4_error_inode(inode, func, line, block, "Directory index failed checksum"); brelse(bh); @@ -163,9 +168,11 @@ static struct buffer_head *__ext4_read_dirblock(struct inode *inode, } } if (!is_dx_block) { - if (ext4_dirblock_csum_verify(inode, bh)) + if (ext4_dirblock_csum_verify(inode, bh) && + !ext4_simulate_fail(inode->i_sb, EXT4_SIM_DIRBLOCK_CRC)) set_buffer_verified(bh); else { + ext4_set_errno(inode->i_sb, EFSBADCRC); ext4_error_inode(inode, func, line, block, "Directory block failed checksum"); brelse(bh); @@ -1002,7 +1009,6 @@ static int htree_dirblock_to_tree(struct file *dir_file, top = (struct ext4_dir_entry_2 *) ((char *) de + dir->i_sb->s_blocksize - EXT4_DIR_REC_LEN(0)); -#ifdef CONFIG_FS_ENCRYPTION /* Check if the directory is encrypted */ if (IS_ENCRYPTED(dir)) { err = fscrypt_get_encryption_info(dir); @@ -1017,7 +1023,7 @@ static int htree_dirblock_to_tree(struct file *dir_file, return err; } } -#endif + for (; de < top; de = ext4_next_entry(de, dir->i_sb->s_blocksize)) { if (ext4_check_dir_entry(dir, NULL, de, bh, bh->b_data, bh->b_size, @@ -1065,9 +1071,7 @@ static int htree_dirblock_to_tree(struct file *dir_file, } errout: brelse(bh); -#ifdef CONFIG_FS_ENCRYPTION fscrypt_fname_free_buffer(&fname_crypto_str); -#endif return count; } @@ -1312,7 +1316,7 @@ void ext4_fname_setup_ci_filename(struct inode *dir, const struct qstr *iname, { int len; - if (!IS_CASEFOLDED(dir)) { + if (!IS_CASEFOLDED(dir) || !EXT4_SB(dir->i_sb)->s_encoding) { cf_name->name = NULL; return; } @@ -1527,6 +1531,7 @@ restart: goto next; wait_on_buffer(bh); if (!buffer_uptodate(bh)) { + ext4_set_errno(sb, EIO); EXT4_ERROR_INODE(dir, "reading directory lblock %lu", (unsigned long) block); brelse(bh); @@ -1537,6 +1542,7 @@ restart: !is_dx_internal_node(dir, block, (struct ext4_dir_entry *)bh->b_data) && !ext4_dirblock_csum_verify(dir, bh)) { + ext4_set_errno(sb, EFSBADCRC); EXT4_ERROR_INODE(dir, "checksumming directory " "block %lu", (unsigned long)block); brelse(bh); @@ -2164,7 +2170,9 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry, struct buffer_head *bh = NULL; struct ext4_dir_entry_2 *de; struct super_block *sb; +#ifdef CONFIG_UNICODE struct ext4_sb_info *sbi; +#endif struct ext4_filename fname; int retval; int dx_fallback=0; @@ -2176,14 +2184,14 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry, csum_size = sizeof(struct ext4_dir_entry_tail); sb = dir->i_sb; - sbi = EXT4_SB(sb); blocksize = sb->s_blocksize; if (!dentry->d_name.len) return -EINVAL; #ifdef CONFIG_UNICODE + sbi = EXT4_SB(sb); if (ext4_has_strict_mode(sbi) && IS_CASEFOLDED(dir) && - utf8_validate(sbi->s_encoding, &dentry->d_name)) + sbi->s_encoding && utf8_validate(sbi->s_encoding, &dentry->d_name)) return -EINVAL; #endif @@ -2205,6 +2213,13 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry, retval = ext4_dx_add_entry(handle, &fname, dir, inode); if (!retval || (retval != ERR_BAD_DX_DIR)) goto out; + /* Can we just ignore htree data? */ + if (ext4_has_metadata_csum(sb)) { + EXT4_ERROR_INODE(dir, + "Directory has corrupted htree index."); + retval = -EFSCORRUPTED; + goto out; + } ext4_clear_inode_flag(dir, EXT4_INODE_INDEX); dx_fallback++; ext4_mark_inode_dirty(handle, dir); @@ -2547,18 +2562,29 @@ static void ext4_dec_count(handle_t *handle, struct inode *inode) } +/* + * Add non-directory inode to a directory. On success, the inode reference is + * consumed by dentry is instantiation. This is also indicated by clearing of + * *inodep pointer. On failure, the caller is responsible for dropping the + * inode reference in the safe context. + */ static int ext4_add_nondir(handle_t *handle, - struct dentry *dentry, struct inode *inode) + struct dentry *dentry, struct inode **inodep) { + struct inode *dir = d_inode(dentry->d_parent); + struct inode *inode = *inodep; int err = ext4_add_entry(handle, dentry, inode); if (!err) { ext4_mark_inode_dirty(handle, inode); + if (IS_DIRSYNC(dir)) + ext4_handle_sync(handle); d_instantiate_new(dentry, inode); + *inodep = NULL; return 0; } drop_nlink(inode); + ext4_orphan_add(handle, inode); unlock_new_inode(inode); - iput(inode); return err; } @@ -2592,12 +2618,12 @@ retry: inode->i_op = &ext4_file_inode_operations; inode->i_fop = &ext4_file_operations; ext4_set_aops(inode); - err = ext4_add_nondir(handle, dentry, inode); - if (!err && IS_DIRSYNC(dir)) - ext4_handle_sync(handle); + err = ext4_add_nondir(handle, dentry, &inode); } if (handle) ext4_journal_stop(handle); + if (!IS_ERR_OR_NULL(inode)) + iput(inode); if (err == -ENOSPC && ext4_should_retry_alloc(dir->i_sb, &retries)) goto retry; return err; @@ -2624,12 +2650,12 @@ retry: if (!IS_ERR(inode)) { init_special_inode(inode, inode->i_mode, rdev); inode->i_op = &ext4_special_inode_operations; - err = ext4_add_nondir(handle, dentry, inode); - if (!err && IS_DIRSYNC(dir)) - ext4_handle_sync(handle); + err = ext4_add_nondir(handle, dentry, &inode); } if (handle) ext4_journal_stop(handle); + if (!IS_ERR_OR_NULL(inode)) + iput(inode); if (err == -ENOSPC && ext4_should_retry_alloc(dir->i_sb, &retries)) goto retry; return err; @@ -2779,10 +2805,12 @@ retry: if (err) { out_clear_inode: clear_nlink(inode); + ext4_orphan_add(handle, inode); unlock_new_inode(inode); ext4_mark_inode_dirty(handle, inode); + ext4_journal_stop(handle); iput(inode); - goto out_stop; + goto out_retry; } ext4_inc_count(handle, dir); ext4_update_dx_flag(dir); @@ -2796,6 +2824,7 @@ out_clear_inode: out_stop: if (handle) ext4_journal_stop(handle); +out_retry: if (err == -ENOSPC && ext4_should_retry_alloc(dir->i_sb, &retries)) goto retry; return err; @@ -2808,7 +2837,7 @@ bool ext4_empty_dir(struct inode *inode) { unsigned int offset; struct buffer_head *bh; - struct ext4_dir_entry_2 *de, *de1; + struct ext4_dir_entry_2 *de; struct super_block *sb; if (ext4_has_inline_data(inode)) { @@ -2833,19 +2862,25 @@ bool ext4_empty_dir(struct inode *inode) return true; de = (struct ext4_dir_entry_2 *) bh->b_data; - de1 = ext4_next_entry(de, sb->s_blocksize); - if (le32_to_cpu(de->inode) != inode->i_ino || - le32_to_cpu(de1->inode) == 0 || - strcmp(".", de->name) || strcmp("..", de1->name)) { - ext4_warning_inode(inode, "directory missing '.' and/or '..'"); + 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_warning_inode(inode, "directory missing '.'"); brelse(bh); return true; } - offset = ext4_rec_len_from_disk(de->rec_len, sb->s_blocksize) + - ext4_rec_len_from_disk(de1->rec_len, sb->s_blocksize); - de = ext4_next_entry(de1, sb->s_blocksize); + offset = ext4_rec_len_from_disk(de->rec_len, sb->s_blocksize); + de = ext4_next_entry(de, 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_warning_inode(inode, "directory missing '..'"); + brelse(bh); + return true; + } + offset += ext4_rec_len_from_disk(de->rec_len, sb->s_blocksize); while (offset < inode->i_size) { - if ((void *) de >= (void *) (bh->b_data+sb->s_blocksize)) { + if (!(offset & (sb->s_blocksize - 1))) { unsigned int lblock; brelse(bh); lblock = offset >> EXT4_BLOCK_SIZE_BITS(sb); @@ -2856,12 +2891,11 @@ bool ext4_empty_dir(struct inode *inode) } if (IS_ERR(bh)) return true; - de = (struct ext4_dir_entry_2 *) bh->b_data; } + 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)) { - de = (struct ext4_dir_entry_2 *)(bh->b_data + - sb->s_blocksize); offset = (offset | (sb->s_blocksize - 1)) + 1; continue; } @@ -2870,7 +2904,6 @@ bool ext4_empty_dir(struct inode *inode) return false; } offset += ext4_rec_len_from_disk(de->rec_len, sb->s_blocksize); - de = ext4_next_entry(de, sb->s_blocksize); } brelse(bh); return true; @@ -3182,18 +3215,17 @@ static int ext4_unlink(struct inode *dir, struct dentry *dentry) if (IS_DIRSYNC(dir)) ext4_handle_sync(handle); - if (inode->i_nlink == 0) { - ext4_warning_inode(inode, "Deleting file '%.*s' with no links", - dentry->d_name.len, dentry->d_name.name); - set_nlink(inode, 1); - } retval = ext4_delete_entry(handle, dir, de, bh); if (retval) goto end_unlink; dir->i_ctime = dir->i_mtime = current_time(dir); ext4_update_dx_flag(dir); ext4_mark_inode_dirty(handle, dir); - drop_nlink(inode); + if (inode->i_nlink == 0) + ext4_warning_inode(inode, "Deleting file '%.*s' with no links", + dentry->d_name.len, dentry->d_name.name); + else + drop_nlink(inode); if (!inode->i_nlink) ext4_orphan_add(handle, inode); inode->i_ctime = current_time(inode); @@ -3328,12 +3360,11 @@ static int ext4_symlink(struct inode *dir, inode->i_size = disk_link.len - 1; } EXT4_I(inode)->i_disksize = inode->i_size; - err = ext4_add_nondir(handle, dentry, inode); - if (!err && IS_DIRSYNC(dir)) - ext4_handle_sync(handle); - + err = ext4_add_nondir(handle, dentry, &inode); if (handle) ext4_journal_stop(handle); + if (inode) + iput(inode); goto out_free_encrypted_link; err_drop_inode: diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c index 12ceadef32c5..68b39e75446a 100644 --- a/fs/ext4/page-io.c +++ b/fs/ext4/page-io.c @@ -31,18 +31,56 @@ #include "acl.h" static struct kmem_cache *io_end_cachep; +static struct kmem_cache *io_end_vec_cachep; int __init ext4_init_pageio(void) { io_end_cachep = KMEM_CACHE(ext4_io_end, SLAB_RECLAIM_ACCOUNT); if (io_end_cachep == NULL) return -ENOMEM; + + io_end_vec_cachep = KMEM_CACHE(ext4_io_end_vec, 0); + if (io_end_vec_cachep == NULL) { + kmem_cache_destroy(io_end_cachep); + return -ENOMEM; + } return 0; } void ext4_exit_pageio(void) { kmem_cache_destroy(io_end_cachep); + kmem_cache_destroy(io_end_vec_cachep); +} + +struct ext4_io_end_vec *ext4_alloc_io_end_vec(ext4_io_end_t *io_end) +{ + struct ext4_io_end_vec *io_end_vec; + + io_end_vec = kmem_cache_zalloc(io_end_vec_cachep, GFP_NOFS); + if (!io_end_vec) + return ERR_PTR(-ENOMEM); + INIT_LIST_HEAD(&io_end_vec->list); + list_add_tail(&io_end_vec->list, &io_end->list_vec); + return io_end_vec; +} + +static void ext4_free_io_end_vec(ext4_io_end_t *io_end) +{ + struct ext4_io_end_vec *io_end_vec, *tmp; + + if (list_empty(&io_end->list_vec)) + return; + list_for_each_entry_safe(io_end_vec, tmp, &io_end->list_vec, list) { + list_del(&io_end_vec->list); + kmem_cache_free(io_end_vec_cachep, io_end_vec); + } +} + +struct ext4_io_end_vec *ext4_last_io_end_vec(ext4_io_end_t *io_end) +{ + BUG_ON(list_empty(&io_end->list_vec)); + return list_last_entry(&io_end->list_vec, struct ext4_io_end_vec, list); } /* @@ -125,6 +163,7 @@ static void ext4_release_io_end(ext4_io_end_t *io_end) ext4_finish_bio(bio); bio_put(bio); } + ext4_free_io_end_vec(io_end); kmem_cache_free(io_end_cachep, io_end); } @@ -136,29 +175,26 @@ static void ext4_release_io_end(ext4_io_end_t *io_end) * cannot get to ext4_ext_truncate() before all IOs overlapping that range are * completed (happens from ext4_free_ioend()). */ -static int ext4_end_io(ext4_io_end_t *io) +static int ext4_end_io_end(ext4_io_end_t *io_end) { - struct inode *inode = io->inode; - loff_t offset = io->offset; - ssize_t size = io->size; - handle_t *handle = io->handle; + struct inode *inode = io_end->inode; + handle_t *handle = io_end->handle; int ret = 0; - ext4_debug("ext4_end_io_nolock: io 0x%p from inode %lu,list->next 0x%p," + ext4_debug("ext4_end_io_nolock: io_end 0x%p from inode %lu,list->next 0x%p," "list->prev 0x%p\n", - io, inode->i_ino, io->list.next, io->list.prev); + io_end, inode->i_ino, io_end->list.next, io_end->list.prev); - io->handle = NULL; /* Following call will use up the handle */ - ret = ext4_convert_unwritten_extents(handle, inode, offset, size); + io_end->handle = NULL; /* Following call will use up the handle */ + ret = ext4_convert_unwritten_io_end_vec(handle, io_end); if (ret < 0 && !ext4_forced_shutdown(EXT4_SB(inode->i_sb))) { ext4_msg(inode->i_sb, KERN_EMERG, "failed to convert unwritten extents to written " "extents -- potential data loss! " - "(inode %lu, offset %llu, size %zd, error %d)", - inode->i_ino, offset, size, ret); + "(inode %lu, error %d)", inode->i_ino, ret); } - ext4_clear_io_unwritten_flag(io); - ext4_release_io_end(io); + ext4_clear_io_unwritten_flag(io_end); + ext4_release_io_end(io_end); return ret; } @@ -166,21 +202,21 @@ static void dump_completed_IO(struct inode *inode, struct list_head *head) { #ifdef EXT4FS_DEBUG struct list_head *cur, *before, *after; - ext4_io_end_t *io, *io0, *io1; + ext4_io_end_t *io_end, *io_end0, *io_end1; if (list_empty(head)) return; ext4_debug("Dump inode %lu completed io list\n", inode->i_ino); - list_for_each_entry(io, head, list) { - cur = &io->list; + list_for_each_entry(io_end, head, list) { + cur = &io_end->list; before = cur->prev; - io0 = container_of(before, ext4_io_end_t, list); + io_end0 = container_of(before, ext4_io_end_t, list); after = cur->next; - io1 = container_of(after, ext4_io_end_t, list); + io_end1 = container_of(after, ext4_io_end_t, list); ext4_debug("io 0x%p from inode %lu,prev 0x%p,next 0x%p\n", - io, inode->i_ino, io0, io1); + io_end, inode->i_ino, io_end0, io_end1); } #endif } @@ -207,7 +243,7 @@ static void ext4_add_complete_io(ext4_io_end_t *io_end) static int ext4_do_flush_completed_IO(struct inode *inode, struct list_head *head) { - ext4_io_end_t *io; + ext4_io_end_t *io_end; struct list_head unwritten; unsigned long flags; struct ext4_inode_info *ei = EXT4_I(inode); @@ -219,11 +255,11 @@ static int ext4_do_flush_completed_IO(struct inode *inode, spin_unlock_irqrestore(&ei->i_completed_io_lock, flags); while (!list_empty(&unwritten)) { - io = list_entry(unwritten.next, ext4_io_end_t, list); - BUG_ON(!(io->flag & EXT4_IO_END_UNWRITTEN)); - list_del_init(&io->list); + io_end = list_entry(unwritten.next, ext4_io_end_t, list); + BUG_ON(!(io_end->flag & EXT4_IO_END_UNWRITTEN)); + list_del_init(&io_end->list); - err = ext4_end_io(io); + err = ext4_end_io_end(io_end); if (unlikely(!ret && err)) ret = err; } @@ -242,19 +278,22 @@ void ext4_end_io_rsv_work(struct work_struct *work) ext4_io_end_t *ext4_init_io_end(struct inode *inode, gfp_t flags) { - ext4_io_end_t *io = kmem_cache_zalloc(io_end_cachep, flags); - if (io) { - io->inode = inode; - INIT_LIST_HEAD(&io->list); - atomic_set(&io->count, 1); + ext4_io_end_t *io_end = kmem_cache_zalloc(io_end_cachep, flags); + + if (io_end) { + io_end->inode = inode; + INIT_LIST_HEAD(&io_end->list); + INIT_LIST_HEAD(&io_end->list_vec); + atomic_set(&io_end->count, 1); } - return io; + return io_end; } void ext4_put_io_end_defer(ext4_io_end_t *io_end) { if (atomic_dec_and_test(&io_end->count)) { - if (!(io_end->flag & EXT4_IO_END_UNWRITTEN) || !io_end->size) { + if (!(io_end->flag & EXT4_IO_END_UNWRITTEN) || + list_empty(&io_end->list_vec)) { ext4_release_io_end(io_end); return; } @@ -268,9 +307,8 @@ int ext4_put_io_end(ext4_io_end_t *io_end) if (atomic_dec_and_test(&io_end->count)) { if (io_end->flag & EXT4_IO_END_UNWRITTEN) { - err = ext4_convert_unwritten_extents(io_end->handle, - io_end->inode, io_end->offset, - io_end->size); + err = ext4_convert_unwritten_io_end_vec(io_end->handle, + io_end); io_end->handle = NULL; ext4_clear_io_unwritten_flag(io_end); } @@ -307,10 +345,8 @@ static void ext4_end_bio(struct bio *bio) struct inode *inode = io_end->inode; ext4_warning(inode->i_sb, "I/O error %d writing to inode %lu " - "(offset %llu size %ld starting block %llu)", + "starting block %llu)", bio->bi_status, inode->i_ino, - (unsigned long long) io_end->offset, - (long) io_end->size, (unsigned long long) bi_sector >> (inode->i_blkbits - 9)); mapping_set_error(inode->i_mapping, @@ -358,14 +394,16 @@ void ext4_io_submit_init(struct ext4_io_submit *io, io->io_end = NULL; } -static int io_submit_init_bio(struct ext4_io_submit *io, - struct buffer_head *bh) +static void io_submit_init_bio(struct ext4_io_submit *io, + struct buffer_head *bh) { struct bio *bio; + /* + * 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_PAGES); - if (!bio) - return -ENOMEM; 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; @@ -373,13 +411,12 @@ static int io_submit_init_bio(struct ext4_io_submit *io, io->io_bio = bio; io->io_next_block = bh->b_blocknr; wbc_init_bio(io->io_wbc, bio); - return 0; } -static int io_submit_add_bh(struct ext4_io_submit *io, - struct inode *inode, - struct page *page, - struct buffer_head *bh) +static void io_submit_add_bh(struct ext4_io_submit *io, + struct inode *inode, + struct page *page, + struct buffer_head *bh) { int ret; @@ -388,9 +425,7 @@ submit_and_retry: ext4_io_submit(io); } if (io->io_bio == NULL) { - ret = io_submit_init_bio(io, bh); - if (ret) - return ret; + 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)); @@ -398,7 +433,6 @@ submit_and_retry: goto submit_and_retry; wbc_account_cgroup_owner(io->io_wbc, page, bh->b_size); io->io_next_block++; - return 0; } int ext4_bio_write_page(struct ext4_io_submit *io, @@ -478,21 +512,36 @@ int ext4_bio_write_page(struct ext4_io_submit *io, gfp_t gfp_flags = GFP_NOFS; unsigned int enc_bytes = round_up(len, i_blocksize(inode)); + /* + * Since bounce page allocation uses a mempool, we can only use + * a waiting mask (i.e. request guaranteed allocation) on the + * first page of the bio. Otherwise it can deadlock. + */ + if (io->io_bio) + gfp_flags = GFP_NOWAIT | __GFP_NOWARN; retry_encrypt: bounce_page = fscrypt_encrypt_pagecache_blocks(page, enc_bytes, 0, gfp_flags); if (IS_ERR(bounce_page)) { ret = PTR_ERR(bounce_page); - if (ret == -ENOMEM && wbc->sync_mode == WB_SYNC_ALL) { - if (io->io_bio) { + if (ret == -ENOMEM && + (io->io_bio || wbc->sync_mode == WB_SYNC_ALL)) { + gfp_flags = GFP_NOFS; + if (io->io_bio) ext4_io_submit(io); - congestion_wait(BLK_RW_ASYNC, HZ/50); - } - gfp_flags |= __GFP_NOFAIL; + else + gfp_flags |= __GFP_NOFAIL; + congestion_wait(BLK_RW_ASYNC, HZ/50); goto retry_encrypt; } - bounce_page = NULL; - goto out; + + printk_ratelimited(KERN_ERR "%s: ret = %d\n", __func__, ret); + redirty_page_for_writepage(wbc, page); + do { + clear_buffer_async_write(bh); + bh = bh->b_this_page; + } while (bh != head); + goto unlock; } } @@ -500,30 +549,13 @@ int ext4_bio_write_page(struct ext4_io_submit *io, do { if (!buffer_async_write(bh)) continue; - ret = io_submit_add_bh(io, inode, bounce_page ?: page, bh); - if (ret) { - /* - * We only get here on ENOMEM. Not much else - * we can do but mark the page as dirty, and - * better luck next time. - */ - break; - } + io_submit_add_bh(io, inode, + bounce_page ? bounce_page : page, bh); nr_submitted++; clear_buffer_dirty(bh); } while ((bh = bh->b_this_page) != head); - /* Error stopped previous loop? Clean up buffers... */ - if (ret) { - out: - fscrypt_free_bounce_page(bounce_page); - printk_ratelimited(KERN_ERR "%s: ret = %d\n", __func__, ret); - redirty_page_for_writepage(wbc, page); - do { - clear_buffer_async_write(bh); - bh = bh->b_this_page; - } while (bh != head); - } +unlock: unlock_page(page); /* Nothing submitted - we have to end page writeback */ if (!nr_submitted) diff --git a/fs/ext4/readpage.c b/fs/ext4/readpage.c index c916017db334..c1769afbf799 100644 --- a/fs/ext4/readpage.c +++ b/fs/ext4/readpage.c @@ -47,13 +47,116 @@ #include "ext4.h" -static inline bool ext4_bio_encrypted(struct bio *bio) +#define NUM_PREALLOC_POST_READ_CTXS 128 + +static struct kmem_cache *bio_post_read_ctx_cache; +static mempool_t *bio_post_read_ctx_pool; + +/* postprocessing steps for read bios */ +enum bio_post_read_step { + STEP_INITIAL = 0, + STEP_DECRYPT, + STEP_VERITY, + STEP_MAX, +}; + +struct bio_post_read_ctx { + struct bio *bio; + struct work_struct work; + unsigned int cur_step; + unsigned int enabled_steps; +}; + +static void __read_end_io(struct bio *bio) +{ + struct page *page; + struct bio_vec *bv; + struct bvec_iter_all iter_all; + + bio_for_each_segment_all(bv, bio, iter_all) { + page = bv->bv_page; + + /* PG_error was set if any post_read step failed */ + if (bio->bi_status || PageError(page)) { + ClearPageUptodate(page); + /* will re-read again later */ + ClearPageError(page); + } else { + SetPageUptodate(page); + } + unlock_page(page); + } + if (bio->bi_private) + mempool_free(bio->bi_private, bio_post_read_ctx_pool); + bio_put(bio); +} + +static void bio_post_read_processing(struct bio_post_read_ctx *ctx); + +static void decrypt_work(struct work_struct *work) +{ + struct bio_post_read_ctx *ctx = + container_of(work, struct bio_post_read_ctx, work); + + fscrypt_decrypt_bio(ctx->bio); + + bio_post_read_processing(ctx); +} + +static void verity_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; + + /* + * fsverity_verify_bio() may call readpages() 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. + * This is safe because verity is the last post-read step. + */ + BUILD_BUG_ON(STEP_VERITY + 1 != STEP_MAX); + mempool_free(ctx, bio_post_read_ctx_pool); + bio->bi_private = NULL; + + fsverity_verify_bio(bio); + + __read_end_io(bio); +} + +static void bio_post_read_processing(struct bio_post_read_ctx *ctx) +{ + /* + * We use different work queues for decryption and for verity because + * verity may require reading metadata pages that need decryption, and + * we shouldn't recurse to the same workqueue. + */ + switch (++ctx->cur_step) { + case STEP_DECRYPT: + if (ctx->enabled_steps & (1 << STEP_DECRYPT)) { + INIT_WORK(&ctx->work, decrypt_work); + fscrypt_enqueue_decrypt_work(&ctx->work); + return; + } + ctx->cur_step++; + /* fall-through */ + case STEP_VERITY: + if (ctx->enabled_steps & (1 << STEP_VERITY)) { + INIT_WORK(&ctx->work, verity_work); + fsverity_enqueue_verify_work(&ctx->work); + return; + } + ctx->cur_step++; + /* fall-through */ + default: + __read_end_io(ctx->bio); + } +} + +static bool bio_post_read_required(struct bio *bio) { -#ifdef CONFIG_FS_ENCRYPTION - return unlikely(bio->bi_private != NULL); -#else - return false; -#endif + return bio->bi_private && !bio->bi_status; } /* @@ -70,30 +173,52 @@ static inline bool ext4_bio_encrypted(struct bio *bio) */ static void mpage_end_io(struct bio *bio) { - struct bio_vec *bv; - struct bvec_iter_all iter_all; + if (bio_post_read_required(bio)) { + struct bio_post_read_ctx *ctx = bio->bi_private; - if (ext4_bio_encrypted(bio)) { - if (bio->bi_status) { - fscrypt_release_ctx(bio->bi_private); - } else { - fscrypt_enqueue_decrypt_bio(bio->bi_private, bio); - return; - } + ctx->cur_step = STEP_INITIAL; + bio_post_read_processing(ctx); + return; } - bio_for_each_segment_all(bv, bio, iter_all) { - struct page *page = bv->bv_page; + __read_end_io(bio); +} - if (!bio->bi_status) { - SetPageUptodate(page); - } else { - ClearPageUptodate(page); - SetPageError(page); - } - unlock_page(page); +static inline bool ext4_need_verity(const struct inode *inode, pgoff_t idx) +{ + return fsverity_active(inode) && + idx < DIV_ROUND_UP(inode->i_size, PAGE_SIZE); +} + +static void ext4_set_bio_post_read_ctx(struct bio *bio, + const struct inode *inode, + pgoff_t first_idx) +{ + unsigned int post_read_steps = 0; + + if (IS_ENCRYPTED(inode) && S_ISREG(inode->i_mode)) + post_read_steps |= 1 << STEP_DECRYPT; + + if (ext4_need_verity(inode, first_idx)) + post_read_steps |= 1 << STEP_VERITY; + + if (post_read_steps) { + /* Due to the mempool, this never fails. */ + struct bio_post_read_ctx *ctx = + mempool_alloc(bio_post_read_ctx_pool, GFP_NOFS); + + ctx->bio = bio; + ctx->enabled_steps = post_read_steps; + bio->bi_private = ctx; } +} - bio_put(bio); +static inline loff_t ext4_readpage_limit(struct inode *inode) +{ + if (IS_ENABLED(CONFIG_FS_VERITY) && + (IS_VERITY(inode) || ext4_verity_in_progress(inode))) + return inode->i_sb->s_maxbytes; + + return i_size_read(inode); } int ext4_mpage_readpages(struct address_space *mapping, @@ -141,7 +266,8 @@ int ext4_mpage_readpages(struct address_space *mapping, block_in_file = (sector_t)page->index << (PAGE_SHIFT - blkbits); last_block = block_in_file + nr_pages * blocks_per_page; - last_block_in_file = (i_size_read(inode) + blocksize - 1) >> blkbits; + last_block_in_file = (ext4_readpage_limit(inode) + + blocksize - 1) >> blkbits; if (last_block > last_block_in_file) last_block = last_block_in_file; page_block = 0; @@ -218,6 +344,9 @@ int ext4_mpage_readpages(struct address_space *mapping, zero_user_segment(page, first_hole << blkbits, PAGE_SIZE); if (first_hole == 0) { + if (ext4_need_verity(inode, page->index) && + !fsverity_verify_page(page)) + goto set_error_page; SetPageUptodate(page); unlock_page(page); goto next_page; @@ -241,24 +370,16 @@ int ext4_mpage_readpages(struct address_space *mapping, bio = NULL; } if (bio == NULL) { - struct fscrypt_ctx *ctx = NULL; - - if (IS_ENCRYPTED(inode) && S_ISREG(inode->i_mode)) { - ctx = fscrypt_get_ctx(GFP_NOFS); - if (IS_ERR(ctx)) - goto set_error_page; - } + /* + * 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, min_t(int, nr_pages, BIO_MAX_PAGES)); - if (!bio) { - if (ctx) - fscrypt_release_ctx(ctx); - goto set_error_page; - } + 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->bi_private = ctx; bio_set_op_attrs(bio, REQ_OP_READ, is_readahead ? REQ_RAHEAD : 0); } @@ -293,3 +414,29 @@ int ext4_mpage_readpages(struct address_space *mapping, submit_bio(bio); return 0; } + +int __init ext4_init_post_read_processing(void) +{ + bio_post_read_ctx_cache = + kmem_cache_create("ext4_bio_post_read_ctx", + sizeof(struct bio_post_read_ctx), 0, 0, NULL); + if (!bio_post_read_ctx_cache) + goto fail; + bio_post_read_ctx_pool = + mempool_create_slab_pool(NUM_PREALLOC_POST_READ_CTXS, + bio_post_read_ctx_cache); + if (!bio_post_read_ctx_pool) + goto fail_free_cache; + return 0; + +fail_free_cache: + kmem_cache_destroy(bio_post_read_ctx_cache); +fail: + return -ENOMEM; +} + +void ext4_exit_post_read_processing(void) +{ + mempool_destroy(bio_post_read_ctx_pool); + kmem_cache_destroy(bio_post_read_ctx_cache); +} diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index c0e9aef376a7..86a2500ed292 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -388,28 +388,10 @@ static struct buffer_head *bclean(handle_t *handle, struct super_block *sb, return bh; } -/* - * If we have fewer than thresh credits, extend by EXT4_MAX_TRANS_DATA. - * If that fails, restart the transaction & regain write access for the - * buffer head which is used for block_bitmap modifications. - */ -static int extend_or_restart_transaction(handle_t *handle, int thresh) +static int ext4_resize_ensure_credits_batch(handle_t *handle, int credits) { - int err; - - if (ext4_handle_has_enough_credits(handle, thresh)) - return 0; - - err = ext4_journal_extend(handle, EXT4_MAX_TRANS_DATA); - if (err < 0) - return err; - if (err) { - err = ext4_journal_restart(handle, EXT4_MAX_TRANS_DATA); - if (err) - return err; - } - - return 0; + return ext4_journal_ensure_credits_fn(handle, credits, + EXT4_MAX_TRANS_DATA, 0, 0); } /* @@ -451,8 +433,8 @@ static int set_flexbg_block_bitmap(struct super_block *sb, handle_t *handle, continue; } - err = extend_or_restart_transaction(handle, 1); - if (err) + err = ext4_resize_ensure_credits_batch(handle, 1); + if (err < 0) return err; bh = sb_getblk(sb, flex_gd->groups[group].block_bitmap); @@ -544,8 +526,8 @@ static int setup_new_flex_group_blocks(struct super_block *sb, struct buffer_head *gdb; ext4_debug("update backup group %#04llx\n", block); - err = extend_or_restart_transaction(handle, 1); - if (err) + err = ext4_resize_ensure_credits_batch(handle, 1); + if (err < 0) goto out; gdb = sb_getblk(sb, block); @@ -602,8 +584,8 @@ handle_bb: /* Initialize block bitmap of the @group */ block = group_data[i].block_bitmap; - err = extend_or_restart_transaction(handle, 1); - if (err) + err = ext4_resize_ensure_credits_batch(handle, 1); + if (err < 0) goto out; bh = bclean(handle, sb, block); @@ -631,8 +613,8 @@ handle_ib: /* Initialize inode bitmap of the @group */ block = group_data[i].inode_bitmap; - err = extend_or_restart_transaction(handle, 1); - if (err) + err = ext4_resize_ensure_credits_batch(handle, 1); + if (err < 0) goto out; /* Mark unused entries in inode bitmap used */ bh = bclean(handle, sb, block); @@ -842,9 +824,8 @@ static int add_new_gdb(handle_t *handle, struct inode *inode, if (unlikely(err)) goto errout; - n_group_desc = ext4_kvmalloc((gdb_num + 1) * - sizeof(struct buffer_head *), - GFP_NOFS); + n_group_desc = kvmalloc((gdb_num + 1) * sizeof(struct buffer_head *), + GFP_KERNEL); if (!n_group_desc) { err = -ENOMEM; ext4_warning(sb, "not enough memory for %lu groups", @@ -918,9 +899,8 @@ static int add_new_gdb_meta_bg(struct super_block *sb, gdb_bh = ext4_sb_bread(sb, gdblock, 0); if (IS_ERR(gdb_bh)) return PTR_ERR(gdb_bh); - n_group_desc = ext4_kvmalloc((gdb_num + 1) * - sizeof(struct buffer_head *), - GFP_NOFS); + n_group_desc = kvmalloc((gdb_num + 1) * sizeof(struct buffer_head *), + GFP_KERNEL); if (!n_group_desc) { brelse(gdb_bh); err = -ENOMEM; @@ -1109,10 +1089,8 @@ static void update_backups(struct super_block *sb, sector_t blk_off, char *data, ext4_fsblk_t backup_block; /* Out of journal space, and can't get more - abort - so sad */ - if (ext4_handle_valid(handle) && - handle->h_buffer_credits == 0 && - ext4_journal_extend(handle, EXT4_MAX_TRANS_DATA) && - (err = ext4_journal_restart(handle, EXT4_MAX_TRANS_DATA))) + err = ext4_resize_ensure_credits_batch(handle, 1); + if (err < 0) break; if (meta_bg == 0) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 4079605d437a..f464dff09774 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -154,7 +154,7 @@ ext4_sb_bread(struct super_block *sb, sector_t block, int op_flags) if (bh == NULL) return ERR_PTR(-ENOMEM); - if (buffer_uptodate(bh)) + if (ext4_buffer_uptodate(bh)) return bh; ll_rw_block(REQ_OP_READ, REQ_META | op_flags, 1, &bh); wait_on_buffer(bh); @@ -204,26 +204,6 @@ void ext4_superblock_csum_set(struct super_block *sb) es->s_checksum = ext4_superblock_csum(sb, es); } -void *ext4_kvmalloc(size_t size, gfp_t flags) -{ - void *ret; - - ret = kmalloc(size, flags | __GFP_NOWARN); - if (!ret) - ret = __vmalloc(size, flags, PAGE_KERNEL); - return ret; -} - -void *ext4_kvzalloc(size_t size, gfp_t flags) -{ - void *ret; - - ret = kzalloc(size, flags | __GFP_NOWARN); - if (!ret) - ret = __vmalloc(size, flags | __GFP_ZERO, PAGE_KERNEL); - return ret; -} - ext4_fsblk_t ext4_block_bitmap(struct super_block *sb, struct ext4_group_desc *bg) { @@ -367,6 +347,8 @@ static void __save_error_info(struct super_block *sb, const char *func, ext4_update_tstamp(es, s_last_error_time); strncpy(es->s_last_error_func, func, sizeof(es->s_last_error_func)); es->s_last_error_line = cpu_to_le32(line); + if (es->s_last_error_errcode == 0) + es->s_last_error_errcode = EXT4_ERR_EFSCORRUPTED; if (!es->s_first_error_time) { es->s_first_error_time = es->s_last_error_time; es->s_first_error_time_hi = es->s_last_error_time_hi; @@ -375,6 +357,7 @@ static void __save_error_info(struct super_block *sb, const char *func, es->s_first_error_line = cpu_to_le32(line); es->s_first_error_ino = es->s_last_error_ino; es->s_first_error_block = es->s_last_error_block; + es->s_first_error_errcode = es->s_last_error_errcode; } /* * Start the daily error reporting function if it hasn't been @@ -631,6 +614,66 @@ const char *ext4_decode_error(struct super_block *sb, int errno, return errstr; } +void ext4_set_errno(struct super_block *sb, int err) +{ + if (err < 0) + err = -err; + + switch (err) { + case EIO: + err = EXT4_ERR_EIO; + break; + case ENOMEM: + err = EXT4_ERR_ENOMEM; + break; + case EFSBADCRC: + err = EXT4_ERR_EFSBADCRC; + break; + case EFSCORRUPTED: + err = EXT4_ERR_EFSCORRUPTED; + break; + case ENOSPC: + err = EXT4_ERR_ENOSPC; + break; + case ENOKEY: + err = EXT4_ERR_ENOKEY; + break; + case EROFS: + err = EXT4_ERR_EROFS; + break; + case EFBIG: + err = EXT4_ERR_EFBIG; + break; + case EEXIST: + err = EXT4_ERR_EEXIST; + break; + case ERANGE: + err = EXT4_ERR_ERANGE; + break; + case EOVERFLOW: + err = EXT4_ERR_EOVERFLOW; + break; + case EBUSY: + err = EXT4_ERR_EBUSY; + break; + case ENOTDIR: + err = EXT4_ERR_ENOTDIR; + break; + case ENOTEMPTY: + err = EXT4_ERR_ENOTEMPTY; + break; + case ESHUTDOWN: + err = EXT4_ERR_ESHUTDOWN; + break; + case EFAULT: + err = EXT4_ERR_EFAULT; + break; + default: + err = EXT4_ERR_UNKNOWN; + } + EXT4_SB(sb)->s_es->s_last_error_errcode = err; +} + /* __ext4_std_error decodes expected errors from journaling functions * automatically and invokes the appropriate error response. */ @@ -655,6 +698,7 @@ void __ext4_std_error(struct super_block *sb, const char *function, sb->s_id, function, line, errstr); } + ext4_set_errno(sb, -errno); save_error_info(sb, function, line); ext4_handle_error(sb); } @@ -982,8 +1026,10 @@ static void ext4_put_super(struct super_block *sb) aborted = is_journal_aborted(sbi->s_journal); err = jbd2_journal_destroy(sbi->s_journal); sbi->s_journal = NULL; - if ((err < 0) && !aborted) + if ((err < 0) && !aborted) { + ext4_set_errno(sb, -err); ext4_abort(sb, "Couldn't clean up the journal"); + } } ext4_unregister_sysfs(sb); @@ -1085,8 +1131,6 @@ static struct inode *ext4_alloc_inode(struct super_block *sb) ei->i_es_shk_nr = 0; ei->i_es_shrink_lblk = 0; ei->i_reserved_data_blocks = 0; - ei->i_da_metadata_calc_len = 0; - ei->i_da_metadata_calc_last_lblock = 0; spin_lock_init(&(ei->i_block_reservation_lock)); ext4_init_pending_tree(&ei->i_pending_tree); #ifdef CONFIG_QUOTA @@ -1107,6 +1151,9 @@ static int ext4_drop_inode(struct inode *inode) { int drop = generic_drop_inode(inode); + if (!drop) + drop = fscrypt_drop_inode(inode); + trace_ext4_drop_inode(inode, drop); return drop; } @@ -1169,9 +1216,9 @@ void ext4_clear_inode(struct inode *inode) { invalidate_inode_buffers(inode); clear_inode(inode); - dquot_drop(inode); ext4_discard_preallocations(inode); ext4_es_remove_extent(inode, 0, EXT_MAX_BLOCKS); + dquot_drop(inode); if (EXT4_I(inode)->jinode) { jbd2_journal_release_jbd_inode(EXT4_JOURNAL(inode), EXT4_I(inode)->jinode); @@ -1179,6 +1226,7 @@ void ext4_clear_inode(struct inode *inode) EXT4_I(inode)->jinode = NULL; } fscrypt_put_encryption_info(inode); + fsverity_cleanup_inode(inode); } static struct inode *ext4_nfs_get_inode(struct super_block *sb, @@ -1341,6 +1389,18 @@ static bool ext4_dummy_context(struct inode *inode) return DUMMY_ENCRYPTION_ENABLED(EXT4_SB(inode->i_sb)); } +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, @@ -1348,6 +1408,8 @@ static const struct fscrypt_operations ext4_cryptops = { .dummy_context = ext4_dummy_context, .empty_dir = ext4_empty_dir, .max_namelen = EXT4_NAME_LEN, + .has_stable_inodes = ext4_has_stable_inodes, + .get_ino_and_lblk_bits = ext4_get_ino_and_lblk_bits, }; #endif @@ -1370,7 +1432,6 @@ static ssize_t ext4_quota_write(struct super_block *sb, int type, static int ext4_quota_enable(struct super_block *sb, int type, int format_id, unsigned int flags); static int ext4_enable_quotas(struct super_block *sb); -static int ext4_get_next_id(struct super_block *sb, struct kqid *qid); static struct dquot **ext4_get_dquots(struct inode *inode) { @@ -1388,7 +1449,7 @@ static const struct dquot_operations ext4_quota_operations = { .destroy_dquot = dquot_destroy, .get_projid = ext4_get_projid, .get_inode_usage = ext4_get_inode_usage, - .get_next_id = ext4_get_next_id, + .get_next_id = dquot_get_next_id, }; static const struct quotactl_ops ext4_qctl_operations = { @@ -1531,6 +1592,7 @@ static const match_table_t tokens = { {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"}, @@ -1874,8 +1936,22 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token, } 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, + "Invalid commit interval %d, " + "must be smaller than %d", + arg, INT_MAX / HZ); + return -1; + } 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; + } sbi->s_want_extra_isize = arg; } else if (token == Opt_max_batch_time) { sbi->s_max_batch_time = arg; @@ -2040,7 +2116,7 @@ static int parse_options(char *options, struct super_block *sb, unsigned int *journal_ioprio, int is_remount) { - struct ext4_sb_info *sbi = EXT4_SB(sb); + 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; @@ -2094,16 +2170,6 @@ static int parse_options(char *options, struct super_block *sb, } } #endif - if (test_opt(sb, DIOREAD_NOLOCK)) { - int blocksize = - BLOCK_SIZE << le32_to_cpu(sbi->s_es->s_log_block_size); - - if (blocksize < PAGE_SIZE) { - ext4_msg(sb, KERN_ERR, "can't mount with " - "dioread_nolock if block size != PAGE_SIZE"); - return 0; - } - } return 1; } @@ -2943,17 +3009,11 @@ static int ext4_feature_set_ok(struct super_block *sb, int readonly) return 0; } -#ifndef CONFIG_QUOTA - if (ext4_has_feature_quota(sb) && !readonly) { +#if !defined(CONFIG_QUOTA) || !defined(CONFIG_QFMT_V2) + if (!readonly && (ext4_has_feature_quota(sb) || + ext4_has_feature_project(sb))) { ext4_msg(sb, KERN_ERR, - "Filesystem with quota feature cannot be mounted RDWR " - "without CONFIG_QUOTA"); - return 0; - } - if (ext4_has_feature_project(sb) && !readonly) { - ext4_msg(sb, KERN_ERR, - "Filesystem with project quota feature cannot be mounted RDWR " - "without CONFIG_QUOTA"); + "The kernel was not built with CONFIG_QUOTA and CONFIG_QFMT_V2"); return 0; } #endif /* CONFIG_QUOTA */ @@ -3540,37 +3600,6 @@ int ext4_calculate_overhead(struct super_block *sb) return 0; } -static void ext4_clamp_want_extra_isize(struct super_block *sb) -{ - struct ext4_sb_info *sbi = EXT4_SB(sb); - struct ext4_super_block *es = sbi->s_es; - - /* determine the minimum size of new large inodes, if present */ - if (sbi->s_inode_size > EXT4_GOOD_OLD_INODE_SIZE && - sbi->s_want_extra_isize == 0) { - sbi->s_want_extra_isize = sizeof(struct ext4_inode) - - EXT4_GOOD_OLD_INODE_SIZE; - if (ext4_has_feature_extra_isize(sb)) { - if (sbi->s_want_extra_isize < - le16_to_cpu(es->s_want_extra_isize)) - sbi->s_want_extra_isize = - le16_to_cpu(es->s_want_extra_isize); - if (sbi->s_want_extra_isize < - le16_to_cpu(es->s_min_extra_isize)) - sbi->s_want_extra_isize = - le16_to_cpu(es->s_min_extra_isize); - } - } - /* Check if enough inode space is available */ - if (EXT4_GOOD_OLD_INODE_SIZE + sbi->s_want_extra_isize > - sbi->s_inode_size) { - sbi->s_want_extra_isize = sizeof(struct ext4_inode) - - EXT4_GOOD_OLD_INODE_SIZE; - ext4_msg(sb, KERN_INFO, - "required extra inode space not available"); - } -} - static void ext4_set_resv_clusters(struct super_block *sb) { ext4_fsblk_t resv_clusters; @@ -3730,6 +3759,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) set_opt(sb, NO_UID32); /* xattr user namespace & acls are now defaulted on */ set_opt(sb, XATTR_USER); + set_opt(sb, DIOREAD_NOLOCK); #ifdef CONFIG_EXT4_FS_POSIX_ACL set_opt(sb, POSIX_ACL); #endif @@ -3778,6 +3808,78 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) */ sbi->s_li_wait_mult = EXT4_DEF_LI_WAIT_MULT; + blocksize = BLOCK_SIZE << le32_to_cpu(es->s_log_block_size); + if (blocksize < EXT4_MIN_BLOCK_SIZE || + blocksize > EXT4_MAX_BLOCK_SIZE) { + ext4_msg(sb, KERN_ERR, + "Unsupported filesystem blocksize %d (%d log_block_size)", + blocksize, le32_to_cpu(es->s_log_block_size)); + goto failed_mount; + } + + if (le32_to_cpu(es->s_rev_level) == EXT4_GOOD_OLD_REV) { + sbi->s_inode_size = EXT4_GOOD_OLD_INODE_SIZE; + sbi->s_first_ino = EXT4_GOOD_OLD_FIRST_INO; + } else { + sbi->s_inode_size = le16_to_cpu(es->s_inode_size); + sbi->s_first_ino = le32_to_cpu(es->s_first_ino); + 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; + } + if ((sbi->s_inode_size < EXT4_GOOD_OLD_INODE_SIZE) || + (!is_power_of_2(sbi->s_inode_size)) || + (sbi->s_inode_size > 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; + } + /* + * i_atime_extra is the last extra field available for + * [acm]times in struct ext4_inode. Checking for that + * field should suffice to ensure we have extra space + * for all three. + */ + if (sbi->s_inode_size >= offsetof(struct ext4_inode, i_atime_extra) + + sizeof(((struct ext4_inode *)0)->i_atime_extra)) { + sb->s_time_gran = 1; + sb->s_time_max = EXT4_EXTRA_TIMESTAMP_MAX; + } else { + sb->s_time_gran = NSEC_PER_SEC; + sb->s_time_max = EXT4_NON_EXTRA_TIMESTAMP_MAX; + } + 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; + if (ext4_has_feature_extra_isize(sb)) { + unsigned v, max = (sbi->s_inode_size - + EXT4_GOOD_OLD_INODE_SIZE); + + v = le16_to_cpu(es->s_want_extra_isize); + if (v > max) { + ext4_msg(sb, KERN_ERR, + "bad s_want_extra_isize: %d", v); + goto failed_mount; + } + if (sbi->s_want_extra_isize < v) + sbi->s_want_extra_isize = v; + + v = le16_to_cpu(es->s_min_extra_isize); + if (v > max) { + ext4_msg(sb, KERN_ERR, + "bad s_min_extra_isize: %d", v); + goto failed_mount; + } + 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), @@ -3835,9 +3937,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) #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 and O_DIRECT support!\n"); + printk_once(KERN_WARNING "EXT4-fs: Warning: mounting with data=journal disables delayed allocation, dioread_nolock, and O_DIRECT support!\n"); + clear_opt(sb, DIOREAD_NOLOCK); if (test_opt2(sb, EXPLICIT_DELALLOC)) { ext4_msg(sb, KERN_ERR, "can't mount with " "both data=journal and delalloc"); @@ -3936,14 +4037,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) if (!ext4_feature_set_ok(sb, (sb_rdonly(sb)))) goto failed_mount; - blocksize = BLOCK_SIZE << le32_to_cpu(es->s_log_block_size); - if (blocksize < EXT4_MIN_BLOCK_SIZE || - blocksize > EXT4_MAX_BLOCK_SIZE) { - ext4_msg(sb, KERN_ERR, - "Unsupported filesystem blocksize %d (%d log_block_size)", - blocksize, le32_to_cpu(es->s_log_block_size)); - goto failed_mount; - } if (le32_to_cpu(es->s_log_block_size) > (EXT4_MAX_BLOCK_LOG_SIZE - EXT4_MIN_BLOCK_LOG_SIZE)) { ext4_msg(sb, KERN_ERR, @@ -4016,29 +4109,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) has_huge_files); sb->s_maxbytes = ext4_max_size(sb->s_blocksize_bits, has_huge_files); - if (le32_to_cpu(es->s_rev_level) == EXT4_GOOD_OLD_REV) { - sbi->s_inode_size = EXT4_GOOD_OLD_INODE_SIZE; - sbi->s_first_ino = EXT4_GOOD_OLD_FIRST_INO; - } else { - sbi->s_inode_size = le16_to_cpu(es->s_inode_size); - sbi->s_first_ino = le32_to_cpu(es->s_first_ino); - 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; - } - if ((sbi->s_inode_size < EXT4_GOOD_OLD_INODE_SIZE) || - (!is_power_of_2(sbi->s_inode_size)) || - (sbi->s_inode_size > blocksize)) { - ext4_msg(sb, KERN_ERR, - "unsupported inode size: %d", - sbi->s_inode_size); - goto failed_mount; - } - if (sbi->s_inode_size > EXT4_GOOD_OLD_INODE_SIZE) - sb->s_time_gran = 1 << (EXT4_EPOCH_BITS - 2); - } - sbi->s_desc_size = le16_to_cpu(es->s_desc_size); if (ext4_has_feature_64bit(sb)) { if (sbi->s_desc_size < EXT4_MIN_DESC_SIZE_64BIT || @@ -4272,6 +4342,9 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) #ifdef CONFIG_FS_ENCRYPTION sb->s_cop = &ext4_cryptops; #endif +#ifdef CONFIG_FS_VERITY + sb->s_vop = &ext4_verityops; +#endif #ifdef CONFIG_QUOTA sb->dq_op = &ext4_quota_operations; if (ext4_has_feature_quota(sb)) @@ -4412,10 +4485,8 @@ no_journal: } } - if ((DUMMY_ENCRYPTION_ENABLED(sbi) || ext4_has_feature_encrypt(sb)) && - (blocksize != PAGE_SIZE)) { - ext4_msg(sb, KERN_ERR, - "Unsupported blocksize for fs encryption"); + if (ext4_has_feature_verity(sb) && blocksize != PAGE_SIZE) { + ext4_msg(sb, KERN_ERR, "Unsupported blocksize for fs-verity"); goto failed_mount_wq; } @@ -4486,8 +4557,6 @@ no_journal: } else if (ret) goto failed_mount4a; - ext4_clamp_want_extra_isize(sb); - ext4_set_resv_clusters(sb); err = ext4_setup_system_zone(sb); @@ -5275,8 +5344,6 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) goto restore_opts; } - ext4_clamp_want_extra_isize(sb); - if ((old_opts.s_mount_opt & EXT4_MOUNT_JOURNAL_CHECKSUM) ^ test_opt(sb, JOURNAL_CHECKSUM)) { ext4_msg(sb, KERN_ERR, "changing journal_checksum " @@ -5514,9 +5581,12 @@ static int ext4_statfs_project(struct super_block *sb, return PTR_ERR(dquot); spin_lock(&dquot->dq_dqb_lock); - limit = (dquot->dq_dqb.dqb_bsoftlimit ? - dquot->dq_dqb.dqb_bsoftlimit : - dquot->dq_dqb.dqb_bhardlimit) >> sb->s_blocksize_bits; + limit = dquot->dq_dqb.dqb_bsoftlimit; + if (dquot->dq_dqb.dqb_bhardlimit && + (!limit || dquot->dq_dqb.dqb_bhardlimit < limit)) + limit = dquot->dq_dqb.dqb_bhardlimit; + limit >>= sb->s_blocksize_bits; + if (limit && buf->f_blocks > limit) { curblock = (dquot->dq_dqb.dqb_curspace + dquot->dq_dqb.dqb_rsvspace) >> sb->s_blocksize_bits; @@ -5526,9 +5596,11 @@ static int ext4_statfs_project(struct super_block *sb, (buf->f_blocks - curblock) : 0; } - limit = dquot->dq_dqb.dqb_isoftlimit ? - dquot->dq_dqb.dqb_isoftlimit : - dquot->dq_dqb.dqb_ihardlimit; + limit = dquot->dq_dqb.dqb_isoftlimit; + if (dquot->dq_dqb.dqb_ihardlimit && + (!limit || dquot->dq_dqb.dqb_ihardlimit < limit)) + limit = dquot->dq_dqb.dqb_ihardlimit; + if (limit && buf->f_files > limit) { buf->f_files = limit; buf->f_ffree = @@ -5803,7 +5875,7 @@ static int ext4_quota_enable(struct super_block *sb, int type, int format_id, /* Don't account quota for quota files to avoid recursion */ qf_inode->i_flags |= S_NOQUOTA; lockdep_set_quota_inode(qf_inode, I_DATA_SEM_QUOTA); - err = dquot_enable(qf_inode, type, format_id, flags); + err = dquot_load_quota_inode(qf_inode, type, format_id, flags); if (err) lockdep_set_quota_inode(qf_inode, I_DATA_SEM_NORMAL); iput(qf_inode); @@ -5961,7 +6033,7 @@ static ssize_t ext4_quota_write(struct super_block *sb, int type, bh = ext4_bread(handle, inode, blk, EXT4_GET_BLOCKS_CREATE | EXT4_GET_BLOCKS_METADATA_NOFAIL); - } while (IS_ERR(bh) && (PTR_ERR(bh) == -ENOSPC) && + } while (PTR_ERR(bh) == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)); if (IS_ERR(bh)) return PTR_ERR(bh); @@ -5987,18 +6059,6 @@ out: } return len; } - -static int ext4_get_next_id(struct super_block *sb, struct kqid *qid) -{ - const struct quota_format_ops *ops; - - if (!sb_has_quota_loaded(sb, qid->type)) - return -ESRCH; - ops = sb_dqopt(sb)->ops[qid->type]; - if (!ops || !ops->get_next_id) - return -ENOSYS; - return dquot_get_next_id(sb, qid); -} #endif static struct dentry *ext4_mount(struct file_system_type *fs_type, int flags, @@ -6095,6 +6155,10 @@ static int __init ext4_init_fs(void) err = ext4_init_pending(); if (err) + goto out7; + + err = ext4_init_post_read_processing(); + if (err) goto out6; err = ext4_init_pageio(); @@ -6135,8 +6199,10 @@ out3: out4: ext4_exit_pageio(); out5: - ext4_exit_pending(); + ext4_exit_post_read_processing(); out6: + ext4_exit_pending(); +out7: ext4_exit_es(); return err; @@ -6153,6 +6219,7 @@ static void __exit ext4_exit_fs(void) ext4_exit_sysfs(); ext4_exit_system_zone(); ext4_exit_pageio(); + ext4_exit_post_read_processing(); ext4_exit_es(); ext4_exit_pending(); } diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c index b3cd7655a6ff..d218ebdafa4a 100644 --- a/fs/ext4/sysfs.c +++ b/fs/ext4/sysfs.c @@ -29,6 +29,10 @@ typedef enum { attr_last_error_time, attr_feature, attr_pointer_ui, + attr_pointer_ul, + attr_pointer_u64, + attr_pointer_u8, + attr_pointer_string, attr_pointer_atomic, attr_journal_task, } attr_id_t; @@ -46,6 +50,7 @@ struct ext4_attr { struct attribute attr; short attr_id; short attr_ptr; + unsigned short attr_size; union { int offset; void *explicit_ptr; @@ -154,12 +159,35 @@ static struct ext4_attr ext4_attr_##_name = { \ }, \ } +#define EXT4_ATTR_STRING(_name,_mode,_size,_struct,_elname) \ +static struct ext4_attr ext4_attr_##_name = { \ + .attr = {.name = __stringify(_name), .mode = _mode }, \ + .attr_id = attr_pointer_string, \ + .attr_size = _size, \ + .attr_ptr = ptr_##_struct##_offset, \ + .u = { \ + .offset = offsetof(struct _struct, _elname),\ + }, \ +} + #define EXT4_RO_ATTR_ES_UI(_name,_elname) \ EXT4_ATTR_OFFSET(_name, 0444, pointer_ui, ext4_super_block, _elname) +#define EXT4_RO_ATTR_ES_U8(_name,_elname) \ + EXT4_ATTR_OFFSET(_name, 0444, pointer_u8, ext4_super_block, _elname) + +#define EXT4_RO_ATTR_ES_U64(_name,_elname) \ + EXT4_ATTR_OFFSET(_name, 0444, pointer_u64, ext4_super_block, _elname) + +#define EXT4_RO_ATTR_ES_STRING(_name,_elname,_size) \ + EXT4_ATTR_STRING(_name, 0444, _size, ext4_super_block, _elname) + #define EXT4_RW_ATTR_SBI_UI(_name,_elname) \ EXT4_ATTR_OFFSET(_name, 0644, pointer_ui, ext4_sb_info, _elname) +#define EXT4_RW_ATTR_SBI_UL(_name,_elname) \ + EXT4_ATTR_OFFSET(_name, 0644, pointer_ul, ext4_sb_info, _elname) + #define EXT4_ATTR_PTR(_name,_mode,_id,_ptr) \ static struct ext4_attr ext4_attr_##_name = { \ .attr = {.name = __stringify(_name), .mode = _mode }, \ @@ -194,7 +222,20 @@ EXT4_RW_ATTR_SBI_UI(warning_ratelimit_interval_ms, s_warning_ratelimit_state.int EXT4_RW_ATTR_SBI_UI(warning_ratelimit_burst, s_warning_ratelimit_state.burst); EXT4_RW_ATTR_SBI_UI(msg_ratelimit_interval_ms, s_msg_ratelimit_state.interval); EXT4_RW_ATTR_SBI_UI(msg_ratelimit_burst, s_msg_ratelimit_state.burst); +#ifdef CONFIG_EXT4_DEBUG +EXT4_RW_ATTR_SBI_UL(simulate_fail, s_simulate_fail); +#endif EXT4_RO_ATTR_ES_UI(errors_count, s_error_count); +EXT4_RO_ATTR_ES_U8(first_error_errcode, s_first_error_errcode); +EXT4_RO_ATTR_ES_U8(last_error_errcode, s_last_error_errcode); +EXT4_RO_ATTR_ES_UI(first_error_ino, s_first_error_ino); +EXT4_RO_ATTR_ES_UI(last_error_ino, s_last_error_ino); +EXT4_RO_ATTR_ES_U64(first_error_block, s_first_error_block); +EXT4_RO_ATTR_ES_U64(last_error_block, s_last_error_block); +EXT4_RO_ATTR_ES_UI(first_error_line, s_first_error_line); +EXT4_RO_ATTR_ES_UI(last_error_line, s_last_error_line); +EXT4_RO_ATTR_ES_STRING(first_error_func, s_first_error_func, 32); +EXT4_RO_ATTR_ES_STRING(last_error_func, s_last_error_func, 32); EXT4_ATTR(first_error_time, 0444, first_error_time); EXT4_ATTR(last_error_time, 0444, last_error_time); EXT4_ATTR(journal_task, 0444, journal_task); @@ -225,9 +266,22 @@ static struct attribute *ext4_attrs[] = { ATTR_LIST(msg_ratelimit_interval_ms), ATTR_LIST(msg_ratelimit_burst), ATTR_LIST(errors_count), + ATTR_LIST(first_error_ino), + ATTR_LIST(last_error_ino), + ATTR_LIST(first_error_block), + ATTR_LIST(last_error_block), + ATTR_LIST(first_error_line), + ATTR_LIST(last_error_line), + ATTR_LIST(first_error_func), + ATTR_LIST(last_error_func), + ATTR_LIST(first_error_errcode), + ATTR_LIST(last_error_errcode), ATTR_LIST(first_error_time), ATTR_LIST(last_error_time), ATTR_LIST(journal_task), +#ifdef CONFIG_EXT4_DEBUG + ATTR_LIST(simulate_fail), +#endif NULL, }; ATTRIBUTE_GROUPS(ext4); @@ -242,6 +296,9 @@ EXT4_ATTR_FEATURE(encryption); #ifdef CONFIG_UNICODE EXT4_ATTR_FEATURE(casefold); #endif +#ifdef CONFIG_FS_VERITY +EXT4_ATTR_FEATURE(verity); +#endif EXT4_ATTR_FEATURE(metadata_csum_seed); static struct attribute *ext4_feat_attrs[] = { @@ -254,6 +311,9 @@ static struct attribute *ext4_feat_attrs[] = { #ifdef CONFIG_UNICODE ATTR_LIST(casefold), #endif +#ifdef CONFIG_FS_VERITY + ATTR_LIST(verity), +#endif ATTR_LIST(metadata_csum_seed), NULL, }; @@ -274,7 +334,7 @@ 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", + return snprintf(buf, PAGE_SIZE, "%lld\n", ((time64_t)hi << 32) + le32_to_cpu(lo)); } @@ -312,6 +372,30 @@ static ssize_t ext4_attr_show(struct kobject *kobj, else return snprintf(buf, PAGE_SIZE, "%u\n", *((unsigned int *) ptr)); + case attr_pointer_ul: + if (!ptr) + return 0; + return snprintf(buf, PAGE_SIZE, "%lu\n", + *((unsigned long *) ptr)); + case attr_pointer_u8: + if (!ptr) + return 0; + return snprintf(buf, PAGE_SIZE, "%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", + le64_to_cpup(ptr)); + else + return snprintf(buf, PAGE_SIZE, "%llu\n", + *((unsigned long long *) ptr)); + case attr_pointer_string: + if (!ptr) + return 0; + return snprintf(buf, PAGE_SIZE, "%.*s\n", a->attr_size, + (char *) ptr); case attr_pointer_atomic: if (!ptr) return 0; @@ -355,6 +439,14 @@ static ssize_t ext4_attr_store(struct kobject *kobj, else *((unsigned int *) ptr) = t; return len; + case attr_pointer_ul: + if (!ptr) + return 0; + ret = kstrtoul(skip_spaces(buf), 0, &t); + if (ret) + return ret; + *((unsigned long *) ptr) = t; + return len; case attr_inode_readahead: return inode_readahead_blks_store(sbi, buf, len); case attr_trigger_test_error: diff --git a/fs/ext4/verity.c b/fs/ext4/verity.c new file mode 100644 index 000000000000..dc5ec724d889 --- /dev/null +++ b/fs/ext4/verity.c @@ -0,0 +1,410 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * fs/ext4/verity.c: fs-verity support for ext4 + * + * Copyright 2019 Google LLC + */ + +/* + * Implementation of fsverity_operations for ext4. + * + * ext4 stores the verity metadata (Merkle tree and fsverity_descriptor) past + * the end of the file, starting at the first 64K boundary beyond i_size. This + * approach works because (a) verity files are readonly, and (b) pages fully + * beyond i_size aren't visible to userspace but can be read/written internally + * by ext4 with only some relatively small changes to ext4. This approach + * avoids having to depend on the EA_INODE feature and on rearchitecturing + * ext4's xattr support to support paging multi-gigabyte xattrs into memory, and + * to support encrypting xattrs. Note that the verity metadata *must* be + * encrypted when the file is, since it contains hashes of the plaintext data. + * + * Using a 64K boundary rather than a 4K one keeps things ready for + * architectures with 64K pages, and it doesn't necessarily waste space on-disk + * since there can be a hole between i_size and the start of the Merkle tree. + */ + +#include <linux/quotaops.h> + +#include "ext4.h" +#include "ext4_extents.h" +#include "ext4_jbd2.h" + +static inline loff_t ext4_verity_metadata_pos(const struct inode *inode) +{ + return round_up(inode->i_size, 65536); +} + +/* + * Read some verity metadata from the inode. __vfs_read() can't be used because + * we need to read beyond i_size. + */ +static int pagecache_read(struct inode *inode, void *buf, size_t count, + loff_t pos) +{ + while (count) { + size_t n = min_t(size_t, count, + PAGE_SIZE - offset_in_page(pos)); + struct page *page; + void *addr; + + page = read_mapping_page(inode->i_mapping, pos >> PAGE_SHIFT, + NULL); + if (IS_ERR(page)) + return PTR_ERR(page); + + addr = kmap_atomic(page); + memcpy(buf, addr + offset_in_page(pos), n); + kunmap_atomic(addr); + + put_page(page); + + buf += n; + pos += n; + count -= n; + } + return 0; +} + +/* + * Write some verity metadata to the inode for FS_IOC_ENABLE_VERITY. + * kernel_write() can't be used because the file descriptor is readonly. + */ +static int pagecache_write(struct inode *inode, const void *buf, size_t count, + loff_t pos) +{ + if (pos + count > inode->i_sb->s_maxbytes) + return -EFBIG; + + while (count) { + size_t n = min_t(size_t, count, + PAGE_SIZE - offset_in_page(pos)); + struct page *page; + void *fsdata; + void *addr; + int res; + + res = pagecache_write_begin(NULL, inode->i_mapping, pos, n, 0, + &page, &fsdata); + if (res) + return res; + + addr = kmap_atomic(page); + memcpy(addr + offset_in_page(pos), buf, n); + kunmap_atomic(addr); + + res = pagecache_write_end(NULL, inode->i_mapping, pos, n, n, + page, fsdata); + if (res < 0) + return res; + if (res != n) + return -EIO; + + buf += n; + pos += n; + count -= n; + } + return 0; +} + +static int ext4_begin_enable_verity(struct file *filp) +{ + struct inode *inode = file_inode(filp); + const int credits = 2; /* superblock and inode for ext4_orphan_add() */ + handle_t *handle; + int err; + + if (ext4_verity_in_progress(inode)) + return -EBUSY; + + /* + * Since the file was opened readonly, we have to initialize the jbd + * inode and quotas here and not rely on ->open() doing it. This must + * be done before evicting the inline data. + */ + + err = ext4_inode_attach_jinode(inode); + if (err) + return err; + + err = dquot_initialize(inode); + if (err) + return err; + + err = ext4_convert_inline_data(inode); + if (err) + return err; + + if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) { + ext4_warning_inode(inode, + "verity is only allowed on extent-based files"); + return -EOPNOTSUPP; + } + + /* + * ext4 uses the last allocated block to find the verity descriptor, so + * we must remove any other blocks past EOF which might confuse things. + */ + err = ext4_truncate(inode); + if (err) + return err; + + handle = ext4_journal_start(inode, EXT4_HT_INODE, credits); + if (IS_ERR(handle)) + return PTR_ERR(handle); + + err = ext4_orphan_add(handle, inode); + if (err == 0) + ext4_set_inode_state(inode, EXT4_STATE_VERITY_IN_PROGRESS); + + ext4_journal_stop(handle); + return err; +} + +/* + * ext4 stores the verity descriptor beginning on the next filesystem block + * boundary after the Merkle tree. Then, the descriptor size is stored in the + * last 4 bytes of the last allocated filesystem block --- which is either the + * block in which the descriptor ends, or the next block after that if there + * weren't at least 4 bytes remaining. + * + * We can't simply store the descriptor in an xattr because it *must* be + * encrypted when ext4 encryption is used, but ext4 encryption doesn't encrypt + * xattrs. Also, if the descriptor includes a large signature blob it may be + * too large to store in an xattr without the EA_INODE feature. + */ +static int ext4_write_verity_descriptor(struct inode *inode, const void *desc, + size_t desc_size, u64 merkle_tree_size) +{ + const u64 desc_pos = round_up(ext4_verity_metadata_pos(inode) + + merkle_tree_size, i_blocksize(inode)); + const u64 desc_end = desc_pos + desc_size; + const __le32 desc_size_disk = cpu_to_le32(desc_size); + const u64 desc_size_pos = round_up(desc_end + sizeof(desc_size_disk), + i_blocksize(inode)) - + sizeof(desc_size_disk); + int err; + + err = pagecache_write(inode, desc, desc_size, desc_pos); + if (err) + return err; + + return pagecache_write(inode, &desc_size_disk, sizeof(desc_size_disk), + desc_size_pos); +} + +static int ext4_end_enable_verity(struct file *filp, const void *desc, + size_t desc_size, u64 merkle_tree_size) +{ + struct inode *inode = file_inode(filp); + const int credits = 2; /* superblock and inode for ext4_orphan_del() */ + handle_t *handle; + int err = 0; + int err2; + + if (desc != NULL) { + /* Succeeded; write the verity descriptor. */ + err = ext4_write_verity_descriptor(inode, desc, desc_size, + merkle_tree_size); + + /* Write all pages before clearing VERITY_IN_PROGRESS. */ + if (!err) + err = filemap_write_and_wait(inode->i_mapping); + } + + /* If we failed, truncate anything we wrote past i_size. */ + if (desc == NULL || err) + ext4_truncate(inode); + + /* + * We must always clean up by clearing EXT4_STATE_VERITY_IN_PROGRESS and + * deleting the inode from the orphan list, even if something failed. + * If everything succeeded, we'll also set the verity bit in the same + * transaction. + */ + + ext4_clear_inode_state(inode, EXT4_STATE_VERITY_IN_PROGRESS); + + handle = ext4_journal_start(inode, EXT4_HT_INODE, credits); + if (IS_ERR(handle)) { + ext4_orphan_del(NULL, inode); + return PTR_ERR(handle); + } + + err2 = ext4_orphan_del(handle, inode); + if (err2) + goto out_stop; + + if (desc != NULL && !err) { + struct ext4_iloc iloc; + + err = ext4_reserve_inode_write(handle, inode, &iloc); + if (err) + goto out_stop; + ext4_set_inode_flag(inode, EXT4_INODE_VERITY); + ext4_set_inode_flags(inode); + err = ext4_mark_iloc_dirty(handle, inode, &iloc); + } +out_stop: + ext4_journal_stop(handle); + return err ?: err2; +} + +static int ext4_get_verity_descriptor_location(struct inode *inode, + size_t *desc_size_ret, + u64 *desc_pos_ret) +{ + struct ext4_ext_path *path; + struct ext4_extent *last_extent; + u32 end_lblk; + u64 desc_size_pos; + __le32 desc_size_disk; + u32 desc_size; + u64 desc_pos; + int err; + + /* + * Descriptor size is in last 4 bytes of last allocated block. + * See ext4_write_verity_descriptor(). + */ + + if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) { + EXT4_ERROR_INODE(inode, "verity file doesn't use extents"); + return -EFSCORRUPTED; + } + + path = ext4_find_extent(inode, EXT_MAX_BLOCKS - 1, NULL, 0); + if (IS_ERR(path)) + return PTR_ERR(path); + + 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); + 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); + + if (desc_size_pos < sizeof(desc_size_disk)) + goto bad; + desc_size_pos -= sizeof(desc_size_disk); + + err = pagecache_read(inode, &desc_size_disk, sizeof(desc_size_disk), + desc_size_pos); + if (err) + return err; + desc_size = le32_to_cpu(desc_size_disk); + + /* + * The descriptor is stored just before the desc_size_disk, but starting + * on a filesystem block boundary. + */ + + if (desc_size > INT_MAX || desc_size > desc_size_pos) + goto bad; + + desc_pos = round_down(desc_size_pos - desc_size, i_blocksize(inode)); + if (desc_pos < ext4_verity_metadata_pos(inode)) + goto bad; + + *desc_size_ret = desc_size; + *desc_pos_ret = desc_pos; + return 0; + +bad: + EXT4_ERROR_INODE(inode, "verity file corrupted; can't find descriptor"); + return -EFSCORRUPTED; +} + +static int ext4_get_verity_descriptor(struct inode *inode, void *buf, + size_t buf_size) +{ + size_t desc_size = 0; + u64 desc_pos = 0; + int err; + + err = ext4_get_verity_descriptor_location(inode, &desc_size, &desc_pos); + if (err) + return err; + + if (buf_size) { + if (desc_size > buf_size) + return -ERANGE; + err = pagecache_read(inode, buf, desc_size, desc_pos); + if (err) + return err; + } + return desc_size; +} + +/* + * Prefetch some pages from the file's Merkle tree. + * + * This is basically a stripped-down version of __do_page_cache_readahead() + * which works on pages past i_size. + */ +static void ext4_merkle_tree_readahead(struct address_space *mapping, + pgoff_t start_index, unsigned long count) +{ + LIST_HEAD(pages); + unsigned int nr_pages = 0; + struct page *page; + pgoff_t index; + struct blk_plug plug; + + for (index = start_index; index < start_index + count; index++) { + page = xa_load(&mapping->i_pages, index); + if (!page || xa_is_value(page)) { + page = __page_cache_alloc(readahead_gfp_mask(mapping)); + if (!page) + break; + page->index = index; + list_add(&page->lru, &pages); + nr_pages++; + } + } + blk_start_plug(&plug); + ext4_mpage_readpages(mapping, &pages, NULL, nr_pages, true); + blk_finish_plug(&plug); +} + +static struct page *ext4_read_merkle_tree_page(struct inode *inode, + pgoff_t index, + unsigned long num_ra_pages) +{ + 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)) { + if (page) + put_page(page); + else if (num_ra_pages > 1) + ext4_merkle_tree_readahead(inode->i_mapping, index, + num_ra_pages); + page = read_mapping_page(inode->i_mapping, index, NULL); + } + return page; +} + +static int ext4_write_merkle_tree_block(struct inode *inode, const void *buf, + u64 index, int log_blocksize) +{ + loff_t pos = ext4_verity_metadata_pos(inode) + (index << log_blocksize); + + return pagecache_write(inode, buf, 1 << log_blocksize, pos); +} + +const struct fsverity_operations ext4_verityops = { + .begin_enable_verity = ext4_begin_enable_verity, + .end_enable_verity = ext4_end_enable_verity, + .get_verity_descriptor = ext4_get_verity_descriptor, + .read_merkle_tree_page = ext4_read_merkle_tree_page, + .write_merkle_tree_block = ext4_write_merkle_tree_block, +}; diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 491f9ee4040e..8cac7d95c3ad 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -967,55 +967,6 @@ int __ext4_xattr_set_credits(struct super_block *sb, struct inode *inode, return credits; } -static int ext4_xattr_ensure_credits(handle_t *handle, struct inode *inode, - int credits, struct buffer_head *bh, - bool dirty, bool block_csum) -{ - int error; - - if (!ext4_handle_valid(handle)) - return 0; - - if (handle->h_buffer_credits >= credits) - return 0; - - error = ext4_journal_extend(handle, credits - handle->h_buffer_credits); - if (!error) - return 0; - if (error < 0) { - ext4_warning(inode->i_sb, "Extend journal (error %d)", error); - return error; - } - - if (bh && dirty) { - if (block_csum) - ext4_xattr_block_csum_set(inode, bh); - error = ext4_handle_dirty_metadata(handle, NULL, bh); - if (error) { - ext4_warning(inode->i_sb, "Handle metadata (error %d)", - error); - return error; - } - } - - error = ext4_journal_restart(handle, credits); - if (error) { - ext4_warning(inode->i_sb, "Restart journal (error %d)", error); - return error; - } - - if (bh) { - error = ext4_journal_get_write_access(handle, bh); - if (error) { - ext4_warning(inode->i_sb, - "Get write access failed (error %d)", - error); - return error; - } - } - return 0; -} - static int ext4_xattr_inode_update_ref(handle_t *handle, struct inode *ea_inode, int ref_change) { @@ -1149,6 +1100,24 @@ cleanup: return saved_err; } +static int ext4_xattr_restart_fn(handle_t *handle, struct inode *inode, + struct buffer_head *bh, bool block_csum, bool dirty) +{ + int error; + + if (bh && dirty) { + if (block_csum) + ext4_xattr_block_csum_set(inode, bh); + error = ext4_handle_dirty_metadata(handle, NULL, bh); + if (error) { + ext4_warning(inode->i_sb, "Handle metadata (error %d)", + error); + return error; + } + } + return 0; +} + static void ext4_xattr_inode_dec_ref_all(handle_t *handle, struct inode *parent, struct buffer_head *bh, @@ -1185,13 +1154,24 @@ ext4_xattr_inode_dec_ref_all(handle_t *handle, struct inode *parent, continue; } - err = ext4_xattr_ensure_credits(handle, parent, credits, bh, - dirty, block_csum); - if (err) { + err = ext4_journal_ensure_credits_fn(handle, credits, credits, + ext4_free_metadata_revoke_credits(parent->i_sb, 1), + ext4_xattr_restart_fn(handle, parent, bh, block_csum, + dirty)); + if (err < 0) { ext4_warning_inode(ea_inode, "Ensure credits err=%d", err); continue; } + if (err > 0) { + err = ext4_journal_get_write_access(handle, bh); + if (err) { + ext4_warning_inode(ea_inode, + "Re-get write access err=%d", + err); + continue; + } + } err = ext4_xattr_inode_dec_ref(handle, ea_inode); if (err) { @@ -1476,7 +1456,7 @@ ext4_xattr_inode_cache_find(struct inode *inode, const void *value, if (!ce) return NULL; - ea_data = ext4_kvmalloc(value_len, GFP_NOFS); + ea_data = kvmalloc(value_len, GFP_KERNEL); if (!ea_data) { mb_cache_entry_put(ea_inode_cache, ce); return NULL; @@ -2335,7 +2315,7 @@ ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index, flags & XATTR_CREATE); brelse(bh); - if (!ext4_handle_has_enough_credits(handle, credits)) { + if (jbd2_handle_buffer_credits(handle) < credits) { error = -ENOSPC; goto cleanup; } @@ -2862,11 +2842,9 @@ int ext4_xattr_delete_inode(handle_t *handle, struct inode *inode, struct inode *ea_inode; int error; - error = ext4_xattr_ensure_credits(handle, inode, extra_credits, - NULL /* bh */, - false /* dirty */, - false /* block_csum */); - if (error) { + error = ext4_journal_ensure_credits(handle, extra_credits, + ext4_free_metadata_revoke_credits(inode->i_sb, 1)); + if (error < 0) { EXT4_ERROR_INODE(inode, "ensure credits (error %d)", error); goto cleanup; } @@ -2901,9 +2879,11 @@ int ext4_xattr_delete_inode(handle_t *handle, struct inode *inode, bh = ext4_sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl, REQ_PRIO); if (IS_ERR(bh)) { error = PTR_ERR(bh); - if (error == -EIO) + if (error == -EIO) { + ext4_set_errno(inode->i_sb, EIO); EXT4_ERROR_INODE(inode, "block %llu read error", EXT4_I(inode)->i_file_acl); + } bh = NULL; goto cleanup; } |