diff options
| -rw-r--r-- | fs/ext4/crypto.c | 6 | ||||
| -rw-r--r-- | fs/ext4/crypto_key.c | 4 | ||||
| -rw-r--r-- | fs/ext4/ext4.h | 99 | ||||
| -rw-r--r-- | fs/ext4/extents.c | 153 | ||||
| -rw-r--r-- | fs/ext4/file.c | 82 | ||||
| -rw-r--r-- | fs/ext4/ialloc.c | 7 | ||||
| -rw-r--r-- | fs/ext4/inline.c | 10 | ||||
| -rw-r--r-- | fs/ext4/inode.c | 268 | ||||
| -rw-r--r-- | fs/ext4/ioctl.c | 376 | ||||
| -rw-r--r-- | fs/ext4/namei.c | 34 | ||||
| -rw-r--r-- | fs/ext4/super.c | 97 | ||||
| -rw-r--r-- | fs/ext4/truncate.h | 2 | ||||
| -rw-r--r-- | include/trace/events/ext4.h | 2 | ||||
| -rw-r--r-- | include/uapi/linux/fs.h | 31 |
14 files changed, 895 insertions, 276 deletions
diff --git a/fs/ext4/crypto.c b/fs/ext4/crypto.c index 1a0835073663..c8021208a7eb 100644 --- a/fs/ext4/crypto.c +++ b/fs/ext4/crypto.c @@ -384,14 +384,12 @@ int ext4_decrypt(struct page *page) EXT4_DECRYPT, page->index, page, page); } -int ext4_encrypted_zeroout(struct inode *inode, struct ext4_extent *ex) +int ext4_encrypted_zeroout(struct inode *inode, ext4_lblk_t lblk, + ext4_fsblk_t pblk, ext4_lblk_t len) { struct ext4_crypto_ctx *ctx; struct page *ciphertext_page = NULL; struct bio *bio; - ext4_lblk_t lblk = le32_to_cpu(ex->ee_block); - ext4_fsblk_t pblk = ext4_ext_pblock(ex); - unsigned int len = ext4_ext_get_actual_len(ex); int ret, err = 0; #if 0 diff --git a/fs/ext4/crypto_key.c b/fs/ext4/crypto_key.c index c5882b36e558..9a16d1e75a49 100644 --- a/fs/ext4/crypto_key.c +++ b/fs/ext4/crypto_key.c @@ -213,9 +213,11 @@ retry: res = -ENOKEY; goto out; } + down_read(&keyring_key->sem); ukp = user_key_payload(keyring_key); if (ukp->datalen != sizeof(struct ext4_encryption_key)) { res = -EINVAL; + up_read(&keyring_key->sem); goto out; } master_key = (struct ext4_encryption_key *)ukp->data; @@ -226,10 +228,12 @@ retry: "ext4: key size incorrect: %d\n", master_key->size); res = -ENOKEY; + up_read(&keyring_key->sem); goto out; } res = ext4_derive_key_aes(ctx.nonce, master_key->raw, raw_key); + up_read(&keyring_key->sem); if (res) goto out; got_key: diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index cc7ca4e87144..1c127213363a 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -378,14 +378,22 @@ struct flex_groups { #define EXT4_PROJINHERIT_FL 0x20000000 /* Create with parents projid */ #define EXT4_RESERVED_FL 0x80000000 /* reserved for ext4 lib */ -#define EXT4_FL_USER_VISIBLE 0x004BDFFF /* User visible flags */ -#define EXT4_FL_USER_MODIFIABLE 0x004380FF /* User modifiable flags */ +#define EXT4_FL_USER_VISIBLE 0x304BDFFF /* User visible flags */ +#define EXT4_FL_USER_MODIFIABLE 0x204380FF /* User modifiable flags */ + +#define EXT4_FL_XFLAG_VISIBLE (EXT4_SYNC_FL | \ + EXT4_IMMUTABLE_FL | \ + EXT4_APPEND_FL | \ + EXT4_NODUMP_FL | \ + EXT4_NOATIME_FL | \ + EXT4_PROJINHERIT_FL) /* Flags that should be inherited by new inodes from their parent. */ #define EXT4_FL_INHERITED (EXT4_SECRM_FL | EXT4_UNRM_FL | EXT4_COMPR_FL |\ EXT4_SYNC_FL | EXT4_NODUMP_FL | EXT4_NOATIME_FL |\ EXT4_NOCOMPR_FL | EXT4_JOURNAL_DATA_FL |\ - EXT4_NOTAIL_FL | EXT4_DIRSYNC_FL) + EXT4_NOTAIL_FL | EXT4_DIRSYNC_FL |\ + EXT4_PROJINHERIT_FL) /* Flags that are appropriate for regular files (all but dir-specific ones). */ #define EXT4_REG_FLMASK (~(EXT4_DIRSYNC_FL | EXT4_TOPDIR_FL)) @@ -555,10 +563,12 @@ enum { #define EXT4_GET_BLOCKS_NO_NORMALIZE 0x0040 /* Request will not result in inode size update (user for fallocate) */ #define EXT4_GET_BLOCKS_KEEP_SIZE 0x0080 - /* Do not take i_data_sem locking in ext4_map_blocks */ -#define EXT4_GET_BLOCKS_NO_LOCK 0x0100 /* Convert written extents to unwritten */ -#define EXT4_GET_BLOCKS_CONVERT_UNWRITTEN 0x0200 +#define EXT4_GET_BLOCKS_CONVERT_UNWRITTEN 0x0100 + /* Write zeros to newly created written extents */ +#define EXT4_GET_BLOCKS_ZERO 0x0200 +#define EXT4_GET_BLOCKS_CREATE_ZERO (EXT4_GET_BLOCKS_CREATE |\ + EXT4_GET_BLOCKS_ZERO) /* * The bit position of these flags must not overlap with any of the @@ -616,6 +626,46 @@ enum { #define EXT4_IOC_GET_ENCRYPTION_PWSALT _IOW('f', 20, __u8[16]) #define EXT4_IOC_GET_ENCRYPTION_POLICY _IOW('f', 21, struct ext4_encryption_policy) +#ifndef FS_IOC_FSGETXATTR +/* Until the uapi changes get merged for project quota... */ + +#define FS_IOC_FSGETXATTR _IOR('X', 31, struct fsxattr) +#define FS_IOC_FSSETXATTR _IOW('X', 32, struct fsxattr) + +/* + * Structure for FS_IOC_FSGETXATTR and FS_IOC_FSSETXATTR. + */ +struct fsxattr { + __u32 fsx_xflags; /* xflags field value (get/set) */ + __u32 fsx_extsize; /* extsize field value (get/set)*/ + __u32 fsx_nextents; /* nextents field value (get) */ + __u32 fsx_projid; /* project identifier (get/set) */ + unsigned char fsx_pad[12]; +}; + +/* + * Flags for the fsx_xflags field + */ +#define FS_XFLAG_REALTIME 0x00000001 /* data in realtime volume */ +#define FS_XFLAG_PREALLOC 0x00000002 /* preallocated file extents */ +#define FS_XFLAG_IMMUTABLE 0x00000008 /* file cannot be modified */ +#define FS_XFLAG_APPEND 0x00000010 /* all writes append */ +#define FS_XFLAG_SYNC 0x00000020 /* all writes synchronous */ +#define FS_XFLAG_NOATIME 0x00000040 /* do not update access time */ +#define FS_XFLAG_NODUMP 0x00000080 /* do not include in backups */ +#define FS_XFLAG_RTINHERIT 0x00000100 /* create with rt bit set */ +#define FS_XFLAG_PROJINHERIT 0x00000200 /* create with parents projid */ +#define FS_XFLAG_NOSYMLINKS 0x00000400 /* disallow symlink creation */ +#define FS_XFLAG_EXTSIZE 0x00000800 /* extent size allocator hint */ +#define FS_XFLAG_EXTSZINHERIT 0x00001000 /* inherit inode extent size */ +#define FS_XFLAG_NODEFRAG 0x00002000 /* do not defragment */ +#define FS_XFLAG_FILESTREAM 0x00004000 /* use filestream allocator */ +#define FS_XFLAG_HASATTR 0x80000000 /* no DIFLAG for this */ +#endif /* !defined(FS_IOC_FSGETXATTR) */ + +#define EXT4_IOC_FSGETXATTR FS_IOC_FSGETXATTR +#define EXT4_IOC_FSSETXATTR FS_IOC_FSSETXATTR + #if defined(__KERNEL__) && defined(CONFIG_COMPAT) /* * ioctl commands in 32 bit emulation @@ -910,6 +960,15 @@ struct ext4_inode_info { * by other means, so we have i_data_sem. */ struct rw_semaphore i_data_sem; + /* + * i_mmap_sem is for serializing page faults with truncate / punch hole + * operations. We have to make sure that new page cannot be faulted in + * a section of the inode that is being punched. We cannot easily use + * i_data_sem for this since we need protection for the whole punch + * operation and i_data_sem ranks below transaction start so we have + * to occasionally drop it. + */ + struct rw_semaphore i_mmap_sem; struct inode vfs_inode; struct jbd2_inode *jinode; @@ -993,6 +1052,7 @@ struct ext4_inode_info { /* Encryption params */ struct ext4_crypt_info *i_crypt_info; #endif + kprojid_t i_projid; }; /* @@ -1248,7 +1308,7 @@ struct ext4_super_block { #endif /* Number of quota types we support */ -#define EXT4_MAXQUOTAS 2 +#define EXT4_MAXQUOTAS 3 /* * fourth extended-fs super-block data in memory @@ -1754,7 +1814,8 @@ EXT4_FEATURE_INCOMPAT_FUNCS(encrypt, ENCRYPT) EXT4_FEATURE_RO_COMPAT_HUGE_FILE |\ EXT4_FEATURE_RO_COMPAT_BIGALLOC |\ EXT4_FEATURE_RO_COMPAT_METADATA_CSUM|\ - EXT4_FEATURE_RO_COMPAT_QUOTA) + EXT4_FEATURE_RO_COMPAT_QUOTA |\ + EXT4_FEATURE_RO_COMPAT_PROJECT) #define EXTN_FEATURE_FUNCS(ver) \ static inline bool ext4_has_unknown_ext##ver##_compat_features(struct super_block *sb) \ @@ -1796,6 +1857,11 @@ static inline bool ext4_has_incompat_features(struct super_block *sb) #define EXT4_DEF_RESUID 0 #define EXT4_DEF_RESGID 0 +/* + * Default project ID + */ +#define EXT4_DEF_PROJID 0 + #define EXT4_DEF_INODE_READAHEAD_BLKS 32 /* @@ -2234,7 +2300,8 @@ void ext4_restore_control_page(struct page *data_page); struct page *ext4_encrypt(struct inode *inode, struct page *plaintext_page); int ext4_decrypt(struct page *page); -int ext4_encrypted_zeroout(struct inode *inode, struct ext4_extent *ex); +int ext4_encrypted_zeroout(struct inode *inode, ext4_lblk_t lblk, + ext4_fsblk_t pblk, ext4_lblk_t len); #ifdef CONFIG_EXT4_FS_ENCRYPTION int ext4_init_crypto(void); @@ -2440,8 +2507,8 @@ struct buffer_head *ext4_getblk(handle_t *, struct inode *, ext4_lblk_t, int); struct buffer_head *ext4_bread(handle_t *, struct inode *, ext4_lblk_t, int); int ext4_get_block_write(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create); -int ext4_get_block_dax(struct inode *inode, sector_t iblock, - struct buffer_head *bh_result, int create); +int ext4_dax_mmap_get_block(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_da_get_block_prep(struct inode *inode, sector_t iblock, @@ -2484,9 +2551,13 @@ extern int ext4_chunk_trans_blocks(struct inode *, int nrblocks); extern int ext4_zero_partial_blocks(handle_t *handle, struct inode *inode, loff_t lstart, loff_t lend); extern int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf); +extern int ext4_filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf); extern qsize_t *ext4_get_reserved_space(struct inode *inode); +extern int ext4_get_projid(struct inode *inode, kprojid_t *projid); extern void ext4_da_update_reserve_space(struct inode *inode, int used, int quota_claim); +extern int ext4_issue_zeroout(struct inode *inode, ext4_lblk_t lblk, + ext4_fsblk_t pblk, ext4_lblk_t len); /* indirect.c */ extern int ext4_ind_map_blocks(handle_t *handle, struct inode *inode, @@ -2848,6 +2919,9 @@ static inline int ext4_update_inode_size(struct inode *inode, loff_t newsize) return changed; } +int ext4_update_disksize_before_punch(struct inode *inode, loff_t offset, + loff_t len); + struct ext4_group_info { unsigned long bb_state; struct rb_root bb_free_root; @@ -2986,8 +3060,7 @@ extern int ext4_da_write_inline_data_end(struct inode *inode, loff_t pos, struct page *page); extern int ext4_try_add_inline_entry(handle_t *handle, struct ext4_filename *fname, - struct dentry *dentry, - struct inode *inode); + struct inode *dir, struct inode *inode); extern int ext4_try_create_inline_dir(handle_t *handle, struct inode *parent, struct inode *inode); diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 551353b1b17a..b52fea3b7219 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -3119,19 +3119,11 @@ static int ext4_ext_zeroout(struct inode *inode, struct ext4_extent *ex) { ext4_fsblk_t ee_pblock; unsigned int ee_len; - int ret; ee_len = ext4_ext_get_actual_len(ex); ee_pblock = ext4_ext_pblock(ex); - - if (ext4_encrypted_inode(inode)) - return ext4_encrypted_zeroout(inode, ex); - - ret = sb_issue_zeroout(inode->i_sb, ee_pblock, ee_len, GFP_NOFS); - if (ret > 0) - ret = 0; - - return ret; + return ext4_issue_zeroout(inode, le32_to_cpu(ex->ee_block), ee_pblock, + ee_len); } /* @@ -4052,6 +4044,14 @@ ext4_ext_handle_unwritten_extents(handle_t *handle, struct inode *inode, } /* IO end_io complete, convert the filled extent to written */ if (flags & EXT4_GET_BLOCKS_CONVERT) { + if (flags & EXT4_GET_BLOCKS_ZERO) { + if (allocated > map->m_len) + allocated = map->m_len; + err = ext4_issue_zeroout(inode, map->m_lblk, newblock, + allocated); + if (err < 0) + goto out2; + } ret = ext4_convert_unwritten_extents_endio(handle, inode, map, ppath); if (ret >= 0) { @@ -4685,10 +4685,6 @@ static int ext4_alloc_file_blocks(struct file *file, ext4_lblk_t offset, if (len <= EXT_UNWRITTEN_MAX_LEN) flags |= EXT4_GET_BLOCKS_NO_NORMALIZE; - /* Wait all existing dio workers, newcomers will block on i_mutex */ - ext4_inode_block_unlocked_dio(inode); - inode_dio_wait(inode); - /* * credits to insert 1 extent into extent tree */ @@ -4752,8 +4748,6 @@ retry: goto retry; } - ext4_inode_resume_unlocked_dio(inode); - return ret > 0 ? ret2 : ret; } @@ -4770,7 +4764,6 @@ static long ext4_zero_range(struct file *file, loff_t offset, int partial_begin, partial_end; loff_t start, end; ext4_lblk_t lblk; - struct address_space *mapping = inode->i_mapping; unsigned int blkbits = inode->i_blkbits; trace_ext4_zero_range(inode, offset, len, mode); @@ -4786,17 +4779,6 @@ static long ext4_zero_range(struct file *file, loff_t offset, } /* - * Write out all dirty pages to avoid race conditions - * Then release them. - */ - if (mapping->nrpages && mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) { - ret = filemap_write_and_wait_range(mapping, offset, - offset + len - 1); - if (ret) - return ret; - } - - /* * Round up offset. This is not fallocate, we neet to zero out * blocks, so convert interior block aligned part of the range to * unwritten and possibly manually zero out unaligned parts of the @@ -4839,6 +4821,10 @@ static long ext4_zero_range(struct file *file, loff_t offset, if (mode & FALLOC_FL_KEEP_SIZE) flags |= EXT4_GET_BLOCKS_KEEP_SIZE; + /* Wait all existing dio workers, newcomers will block on i_mutex */ + ext4_inode_block_unlocked_dio(inode); + inode_dio_wait(inode); + /* Preallocate the range including the unaligned edges */ if (partial_begin || partial_end) { ret = ext4_alloc_file_blocks(file, @@ -4847,7 +4833,7 @@ static long ext4_zero_range(struct file *file, loff_t offset, round_down(offset, 1 << blkbits)) >> blkbits, new_size, flags, mode); if (ret) - goto out_mutex; + goto out_dio; } @@ -4856,16 +4842,23 @@ static long ext4_zero_range(struct file *file, loff_t offset, flags |= (EXT4_GET_BLOCKS_CONVERT_UNWRITTEN | EXT4_EX_NOCACHE); - /* Now release the pages and zero block aligned part of pages*/ + /* + * Prevent page faults from reinstantiating pages we have + * released from page cache. + */ + down_write(&EXT4_I(inode)->i_mmap_sem); + ret = ext4_update_disksize_before_punch(inode, offset, len); + if (ret) { + up_write(&EXT4_I(inode)->i_mmap_sem); + goto out_dio; + } + /* Now release the pages and zero block aligned part of pages */ truncate_pagecache_range(inode, start, end - 1); inode->i_mtime = inode->i_ctime = ext4_current_time(inode); - /* Wait all existing dio workers, newcomers will block on i_mutex */ - ext4_inode_block_unlocked_dio(inode); - inode_dio_wait(inode); - ret = ext4_alloc_file_blocks(file, lblk, max_blocks, new_size, flags, mode); + up_write(&EXT4_I(inode)->i_mmap_sem); if (ret) goto out_dio; } @@ -4998,8 +4991,13 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len) goto out; } + /* Wait all existing dio workers, newcomers will block on i_mutex */ + ext4_inode_block_unlocked_dio(inode); + inode_dio_wait(inode); + ret = ext4_alloc_file_blocks(file, lblk, max_blocks, new_size, flags, mode); + ext4_inode_resume_unlocked_dio(inode); if (ret) goto out; @@ -5494,21 +5492,7 @@ int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len) return ret; } - /* - * Need to round down offset to be aligned with page size boundary - * for page size > block size. - */ - ioffset = round_down(offset, PAGE_SIZE); - - /* Write out all dirty pages */ - ret = filemap_write_and_wait_range(inode->i_mapping, ioffset, - LLONG_MAX); - if (ret) - return ret; - - /* Take mutex lock */ mutex_lock(&inode->i_mutex); - /* * There is no need to overlap collapse range with EOF, in which case * it is effectively a truncate operation @@ -5524,17 +5508,43 @@ int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len) goto out_mutex; } - truncate_pagecache(inode, ioffset); - /* Wait for existing dio to complete */ ext4_inode_block_unlocked_dio(inode); inode_dio_wait(inode); + /* + * Prevent page faults from reinstantiating pages we have released from + * page cache. + */ + down_write(&EXT4_I(inode)->i_mmap_sem); + /* + * Need to round down offset to be aligned with page size boundary + * for page size > block size. + */ + ioffset = round_down(offset, PAGE_SIZE); + /* + * Write tail of the last page before removed range since it will get + * removed from the page cache below. + */ + ret = filemap_write_and_wait_range(inode->i_mapping, ioffset, offset); + if (ret) + goto out_mmap; + /* + * Write data that will be shifted to preserve them when discarding + * page cache below. We are also protected from pages becoming dirty + * by i_mmap_sem. + */ + ret = filemap_write_and_wait_range(inode->i_mapping, offset + len, + LLONG_MAX); + if (ret) + goto out_mmap; + truncate_pagecache(inode, ioffset); + credits = ext4_writepage_trans_blocks(inode); handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, credits); if (IS_ERR(handle)) { ret = PTR_ERR(handle); - goto out_dio; + goto out_mmap; } down_write(&EXT4_I(inode)->i_data_sem); @@ -5573,7 +5583,8 @@ int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len) out_stop: ext4_journal_stop(handle); -out_dio: +out_mmap: + up_write(&EXT4_I(inode)->i_mmap_sem); ext4_inode_resume_unlocked_dio(inode); out_mutex: mutex_unlock(&inode->i_mutex); @@ -5627,21 +5638,7 @@ int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len) return ret; } - /* - * Need to round down to align start offset to page size boundary - * for page size > block size. - */ - ioffset = round_down(offset, PAGE_SIZE); - - /* Write out all dirty pages */ - ret = filemap_write_and_wait_range(inode->i_mapping, ioffset, - LLONG_MAX); - if (ret) - return ret; - - /* Take mutex lock */ mutex_lock(&inode->i_mutex); - /* Currently just for extent based files */ if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) { ret = -EOPNOTSUPP; @@ -5660,17 +5657,32 @@ int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len) goto out_mutex; } - truncate_pagecache(inode, ioffset); - /* Wait for existing dio to complete */ ext4_inode_block_unlocked_dio(inode); inode_dio_wait(inode); + /* + * Prevent page faults from reinstantiating pages we have released from + * page cache. + */ + down_write(&EXT4_I(inode)->i_mmap_sem); + /* + * Need to round down to align start offset to page size boundary + * for page size > block size. + */ + ioffset = round_down(offset, PAGE_SIZE); + /* Write out all dirty pages */ + ret = filemap_write_and_wait_range(inode->i_mapping, ioffset, + LLONG_MAX); + if (ret) + goto out_mmap; + truncate_pagecache(inode, ioffset); + credits = ext4_writepage_trans_blocks(inode); handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, credits); if (IS_ERR(handle)) { ret = PTR_ERR(handle); - goto out_dio; + goto out_mmap; } /* Expand file to avoid data loss if there is error while shifting */ @@ -5741,7 +5753,8 @@ int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len) out_stop: ext4_journal_stop(handle); -out_dio: +out_mmap: + up_write(&EXT4_I(inode)->i_mmap_sem); ext4_inode_resume_unlocked_dio(inode); out_mutex: mutex_unlock(&inode->i_mutex); diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 113837e7ba98..749b222e6498 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -193,43 +193,35 @@ out: } #ifdef CONFIG_FS_DAX -static void ext4_end_io_unwritten(struct buffer_head *bh, int uptodate) -{ - struct inode *inode = bh->b_assoc_map->host; - /* XXX: breaks on 32-bit > 16TB. Is that even supported? */ - loff_t offset = (loff_t)(uintptr_t)bh->b_private << inode->i_blkbits; - int err; - if (!uptodate) - return; - WARN_ON(!buffer_unwritten(bh)); - err = ext4_convert_unwritten_extents(NULL, inode, offset, bh->b_size); -} - static int ext4_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf) { int result; handle_t *handle = NULL; - struct super_block *sb = file_inode(vma->vm_file)->i_sb; + struct inode *inode = file_inode(vma->vm_file); + struct super_block *sb = inode->i_sb; bool write = vmf->flags & FAULT_FLAG_WRITE; if (write) { sb_start_pagefault(sb); file_update_time(vma->vm_file); + down_read(&EXT4_I(inode)->i_mmap_sem); handle = ext4_journal_start_sb(sb, EXT4_HT_WRITE_PAGE, EXT4_DATA_TRANS_BLOCKS(sb)); - } + } else + down_read(&EXT4_I(inode)->i_mmap_sem); if (IS_ERR(handle)) result = VM_FAULT_SIGBUS; else - result = __dax_fault(vma, vmf, ext4_get_block_dax, - ext4_end_io_unwritten); + result = __dax_fault(vma, vmf, ext4_dax_mmap_get_block, NULL); if (write) { if (!IS_ERR(handle)) ext4_journal_stop(handle); + up_read(&EXT4_I(inode)->i_mmap_sem); sb_end_pagefault(sb); - } + } else + up_read(&EXT4_I(inode)->i_mmap_sem); return result; } @@ -246,44 +238,86 @@ static int ext4_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr, if (write) { sb_start_pagefault(sb); file_update_time(vma->vm_file); + down_read(&EXT4_I(inode)->i_mmap_sem); handle = ext4_journal_start_sb(sb, EXT4_HT_WRITE_PAGE, ext4_chunk_trans_blocks(inode, PMD_SIZE / PAGE_SIZE)); - } + } else + down_read(&EXT4_I(inode)->i_mmap_sem); if (IS_ERR(handle)) result = VM_FAULT_SIGBUS; else result = __dax_pmd_fault(vma, addr, pmd, flags, - ext4_get_block_dax, ext4_end_io_unwritten); + ext4_dax_mmap_get_block, NULL); if (write) { if (!IS_ERR(handle)) ext4_journal_stop(handle); + up_read(&EXT4_I(inode)->i_mmap_sem); sb_end_pagefault(sb); - } + } else + up_read(&EXT4_I(inode)->i_mmap_sem); return result; } static int ext4_dax_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) { - return dax_mkwrite(vma, vmf, ext4_get_block_dax, - ext4_end_io_unwritten); + int err; + struct inode *inode = file_inode(vma->vm_file); + + sb_start_pagefault(inode->i_sb); + file_update_time(vma->vm_file); + down_read(&EXT4_I(inode)->i_mmap_sem); + err = __dax_mkwrite(vma, vmf, ext4_dax_mmap_get_block, NULL); + up_read(&EXT4_I(inode)->i_mmap_sem); + sb_end_pagefault(inode->i_sb); + + return err; +} + +/* + * Handle write fault for VM_MIXEDMAP mappings. Similarly to ext4_dax_mkwrite() + * handler we check for races agaist truncate. Note that since we cycle through + * i_mmap_sem, we are sure that also any hole punching that began before we + * were called is finished by now and so if it included part of the file we + * are working on, our pte will get unmapped and the check for pte_same() in + * wp_pfn_shared() fails. Thus fault gets retried and things work out as + * desired. + */ +static int ext4_dax_pfn_mkwrite(struct vm_area_struct *vma, + struct vm_fault *vmf) +{ + struct inode *inode = file_inode(vma->vm_file); + struct super_block *sb = inode->i_sb; + int ret = VM_FAULT_NOPAGE; + loff_t size; + + sb_start_pagefault(sb); + file_update_time(vma->vm_file); + down_read(&EXT4_I(inode)->i_mmap_sem); + size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT; + if (vmf->pgoff >= size) + ret = VM_FAULT_SIGBUS; + up_read(&EXT4_I(inode)->i_mmap_sem); + sb_end_pagefault(sb); + + return ret; } static const struct vm_operations_struct ext4_dax_vm_ops = { .fault = ext4_dax_fault, .pmd_fault = ext4_dax_pmd_fault, .page_mkwrite = ext4_dax_mkwrite, - .pfn_mkwrite = dax_pfn_mkwrite, + .pfn_mkwrite = ext4_dax_pfn_mkwrite, }; #else #define ext4_dax_vm_ops ext4_file_vm_ops #endif static const struct vm_operations_struct ext4_file_vm_ops = { - .fault = filemap_fault, + .fault = ext4_filemap_fault, .map_pages = filemap_map_pages, .page_mkwrite = ext4_page_mkwrite, }; diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index 1b8024d26f65..3fcfd50a2e8a 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -799,6 +799,13 @@ struct inode *__ext4_new_inode(handle_t *handle, struct inode *dir, inode->i_gid = dir->i_gid; } else inode_init_owner(inode, dir, mode); + + if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_PROJECT) && + ext4_test_inode_flag(dir, EXT4_INODE_PROJINHERIT)) + ei->i_projid = EXT4_I(dir)->i_projid; + else + ei->i_projid = make_kprojid(&init_user_ns, EXT4_DEF_PROJID); + err = dquot_initialize(inode); if (err) goto out; diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index d884989cc83d..dfe3b9bafc0d 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -995,12 +995,11 @@ void ext4_show_inline_dir(struct inode *dir, struct buffer_head *bh, */ static int ext4_add_dirent_to_inline(handle_t *handle, struct ext4_filename *fname, - struct dentry *dentry, + struct inode *dir, struct inode *inode, struct ext4_iloc *iloc, void *inline_start, int inline_size) { - struct inode *dir = d_inode(dentry->d_parent); int err; struct ext4_dir_entry_2 *de; @@ -1245,12 +1244,11 @@ out: * the new created block. */ int ext4_try_add_inline_entry(handle_t *handle, struct ext4_filename *fname, - struct dentry *dentry, struct inode *inode) + struct inode *dir, struct inode *inode) { int ret, inline_size; void *inline_start; struct ext4_iloc iloc; - struct inode *dir = d_inode(dentry->d_parent); ret = ext4_get_inode_loc(dir, &iloc); if (ret) @@ -1264,7 +1262,7 @@ int ext4_try_add_inline_entry(handle_t *handle, struct ext4_filename *fname, EXT4_INLINE_DOTDOT_SIZE; inline_size = EXT4_MIN_INLINE_DATA_SIZE - EXT4_INLINE_DOTDOT_SIZE; - ret = ext4_add_dirent_to_inline(handle, fname, dentry, inode, &iloc, + ret = ext4_add_dirent_to_inline(handle, fname, dir, inode, &iloc, inline_start, inline_size); if (ret != -ENOSPC) goto out; @@ -1285,7 +1283,7 @@ int ext4_try_add_inline_entry(handle_t *handle, struct ext4_filename *fname, if (inline_size) { inline_start = ext4_get_inline_xattr_pos(dir, &iloc); - ret = ext4_add_dirent_to_inline(handle, fname, dentry, + ret = ext4_add_dirent_to_inline(handle, fname, dir, inode, &iloc, inline_start, inline_size); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index b3bd912df6bf..d964195ea0e2 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -383,6 +383,21 @@ static int __check_block_validity(struct inode *inode, const char *func, return 0; } +int ext4_issue_zeroout(struct inode *inode, ext4_lblk_t lblk, ext4_fsblk_t pblk, + ext4_lblk_t len) +{ + int ret; + + if (ext4_encrypted_inode(inode)) + return ext4_encrypted_zeroout(inode, lblk, pblk, len); + + ret = sb_issue_zeroout(inode->i_sb, pblk, len, GFP_NOFS); + if (ret > 0) + ret = 0; + + return ret; +} + #define check_block_validity(inode, map) \ __check_block_validity((inode), __func__, __LINE__, (map)) @@ -403,8 +418,7 @@ static void ext4_map_blocks_es_recheck(handle_t *handle, * out taking i_data_sem. So at the time the unwritten extent * could be converted. */ - if (!(flags & EXT4_GET_BLOCKS_NO_LOCK)) - down_read(&EXT4_I(inode)->i_data_sem); + down_read(&EXT4_I(inode)->i_data_sem); if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) { retval = ext4_ext_map_blocks(handle, inode, map, flags & EXT4_GET_BLOCKS_KEEP_SIZE); @@ -412,8 +426,7 @@ static void ext4_map_blocks_es_recheck(handle_t *handle, retval = ext4_ind_map_blocks(handle, inode, map, flags & EXT4_GET_BLOCKS_KEEP_SIZE); } - if (!(flags & EXT4_GET_BLOCKS_NO_LOCK)) - up_read((&EXT4_I(inode)->i_data_sem)); + up_read((&EXT4_I(inode)->i_data_sem)); /* * We don't check m_len because extent will be collpased in status @@ -509,8 +522,7 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode, * Try to see if we can get the block without requesting a new * file system block. */ - if (!(flags & EXT4_GET_BLOCKS_NO_LOCK)) - down_read(&EXT4_I(inode)->i_data_sem); + down_read(&EXT4_I(inode)->i_data_sem); if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) { retval = ext4_ext_map_blocks(handle, inode, map, flags & EXT4_GET_BLOCKS_KEEP_SIZE); @@ -541,8 +553,7 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode, if (ret < 0) retval = ret; } - if (!(flags & EXT4_GET_BLOCKS_NO_LOCK)) - up_read((&EXT4_I(inode)->i_data_sem)); + up_read((&EXT4_I(inode)->i_data_sem)); found: if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) { @@ -626,13 +637,29 @@ found: } /* + * We have to zeroout blocks before inserting them into extent + * status tree. Otherwise someone could look them up there and + * use them before they are really zeroed. + */ + if (flags & EXT4_GET_BLOCKS_ZERO && + map->m_flags & EXT4_MAP_MAPPED && + map->m_flags & EXT4_MAP_NEW) { + ret = ext4_issue_zeroout(inode, map->m_lblk, + map->m_pblk, map->m_len); + if (ret) { + retval = ret; + goto out_sem; + } + } + + /* * If the extent has been zeroed out, we don't need to update * extent status tree. */ if ((flags & EXT4_GET_BLOCKS_PRE_IO) && ext4_es_lookup_extent(inode, map->m_lblk, &es)) { if (ext4_es_is_written(&es)) - goto has_zeroout; + goto out_sem; } status = map->m_flags & EXT4_MAP_UNWRITTEN ? EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN; @@ -643,11 +670,13 @@ found: status |= EXTENT_STATUS_DELAYED; ret = ext4_es_insert_extent(inode, map->m_lblk, map->m_len, map->m_pblk, status); - if (ret < 0) + if (ret < 0) { retval = ret; + goto out_sem; + } } -has_zeroout: +out_sem: up_write((&EXT4_I(inode)->i_data_sem)); if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) { ret = check_block_validity(inode, map); @@ -674,7 +703,7 @@ static int _ext4_get_block(struct inode *inode, sector_t iblock, map.m_lblk = iblock; map.m_len = bh->b_size >> inode->i_blkbits; - if (flags && !(flags & EXT4_GET_BLOCKS_NO_LOCK) && !handle) { + if (flags && !handle) { /* Direct IO write... */ if (map.m_len > DIO_MAX_BLOCKS) map.m_len = DIO_MAX_BLOCKS; @@ -694,16 +723,6 @@ static int _ext4_get_block(struct inode *inode, sector_t iblock, map_bh(bh, inode->i_sb, map.m_pblk); bh->b_state = (bh->b_state & ~EXT4_MAP_FLAGS) | map.m_flags; - if (IS_DAX(inode) && buffer_unwritten(bh)) { - /* - * dgc: I suspect unwritten conversion on ext4+DAX is - * fundamentally broken here when there are concurrent - * read/write in progress on this inode. - */ - WARN_ON_ONCE(io_end); - bh->b_assoc_map = inode->i_mapping; - bh->b_private = (void *)(unsigned long)iblock; - } if (io_end && io_end->flag & EXT4_IO_END_UNWRITTEN) set_buffer_defer_completion(bh); bh->b_size = inode->i_sb->s_blocksize * map.m_len; @@ -879,9 +898,6 @@ int do_journal_get_write_access(handle_t *handle, return ret; } -static int ext4_get_block_write_nolock(struct inode *inode, sector_t iblock, - struct buffer_head *bh_result, int create); - #ifdef CONFIG_EXT4_FS_ENCRYPTION static int ext4_block_write_begin(struct page *page, loff_t pos, unsigned len, get_block_t *get_block) @@ -3054,25 +3070,96 @@ int ext4_get_block_write(struct inode *inode, sector_t iblock, EXT4_GET_BLOCKS_IO_CREATE_EXT); } -static int ext4_get_block_write_nolock(struct inode *inode, sector_t iblock, +static int ext4_get_block_overwrite(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create) { - ext4_debug("ext4_get_block_write_nolock: inode %lu, create flag %d\n", + int ret; + + ext4_debug("ext4_get_block_overwrite: inode %lu, create flag %d\n", inode->i_ino, create); - return _ext4_get_block(inode, iblock, bh_result, - EXT4_GET_BLOCKS_NO_LOCK); + 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)); + + return ret; } -int ext4_get_block_dax(struct inode *inode, sector_t iblock, - struct buffer_head *bh_result, int create) +#ifdef CONFIG_FS_DAX +int ext4_dax_mmap_get_block(struct inode *inode, sector_t iblock, + struct buffer_head *bh_result, int create) { - int flags = EXT4_GET_BLOCKS_PRE_IO | EXT4_GET_BLOCKS_UNWRIT_EXT; - if (create) - flags |= EXT4_GET_BLOCKS_CREATE; - ext4_debug("ext4_get_block_dax: inode %lu, create flag %d\n", |