From ea3d7209ca01da209cda6f0dea8be9cc4b7a933b Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 7 Dec 2015 14:28:03 -0500 Subject: ext4: fix races between page faults and hole punching Currently, page faults and hole punching are completely unsynchronized. This can result in page fault faulting in a page into a range that we are punching after truncate_pagecache_range() has been called and thus we can end up with a page mapped to disk blocks that will be shortly freed. Filesystem corruption will shortly follow. Note that the same race is avoided for truncate by checking page fault offset against i_size but there isn't similar mechanism available for punching holes. Fix the problem by creating new rw semaphore i_mmap_sem in inode and grab it for writing over truncate, hole punching, and other functions removing blocks from extent tree and for read over page faults. We cannot easily use i_data_sem for this since that ranks below transaction start and we need something ranking above it so that it can be held over the whole truncate / hole punching operation. Also remove various workarounds we had in the code to reduce race window when page fault could have created pages with stale mapping information. Signed-off-by: Jan Kara Signed-off-by: Theodore Ts'o --- fs/ext4/inode.c | 36 +++++++++++++++++++++++++++--------- 1 file changed, 27 insertions(+), 9 deletions(-) (limited to 'fs/ext4/inode.c') diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index ea433a7f4bca..d1207d03c961 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -3623,6 +3623,15 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length) } + /* Wait all existing dio workers, newcomers will block on i_mutex */ + 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); first_block_offset = round_up(offset, sb->s_blocksize); last_block_offset = round_down((offset + length), sb->s_blocksize) - 1; @@ -3631,10 +3640,6 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length) truncate_pagecache_range(inode, first_block_offset, last_block_offset); - /* Wait all existing dio workers, newcomers will block on i_mutex */ - ext4_inode_block_unlocked_dio(inode); - inode_dio_wait(inode); - if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) credits = ext4_writepage_trans_blocks(inode); else @@ -3680,16 +3685,12 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length) if (IS_SYNC(inode)) ext4_handle_sync(handle); - /* Now release the pages again to reduce race window */ - if (last_block_offset > first_block_offset) - truncate_pagecache_range(inode, first_block_offset, - last_block_offset); - inode->i_mtime = inode->i_ctime = ext4_current_time(inode); ext4_mark_inode_dirty(handle, inode); out_stop: ext4_journal_stop(handle); out_dio: + up_write(&EXT4_I(inode)->i_mmap_sem); ext4_inode_resume_unlocked_dio(inode); out_mutex: mutex_unlock(&inode->i_mutex); @@ -4823,6 +4824,7 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr) } else ext4_wait_for_tail_page_commit(inode); } + down_write(&EXT4_I(inode)->i_mmap_sem); /* * Truncate pagecache after we've waited for commit * in data=journal mode to make pages freeable. @@ -4830,6 +4832,7 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr) truncate_pagecache(inode, inode->i_size); if (shrink) ext4_truncate(inode); + up_write(&EXT4_I(inode)->i_mmap_sem); } if (!rc) { @@ -5278,6 +5281,8 @@ int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) sb_start_pagefault(inode->i_sb); file_update_time(vma->vm_file); + + down_read(&EXT4_I(inode)->i_mmap_sem); /* Delalloc case is easy... */ if (test_opt(inode->i_sb, DELALLOC) && !ext4_should_journal_data(inode) && @@ -5347,6 +5352,19 @@ retry_alloc: out_ret: ret = block_page_mkwrite_return(ret); out: + up_read(&EXT4_I(inode)->i_mmap_sem); sb_end_pagefault(inode->i_sb); return ret; } + +int ext4_filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf) +{ + struct inode *inode = file_inode(vma->vm_file); + int err; + + down_read(&EXT4_I(inode)->i_mmap_sem); + err = filemap_fault(vma, vmf); + up_read(&EXT4_I(inode)->i_mmap_sem); + + return err; +} -- cgit v1.2.3 From 011278485ecc3cd2a3954b5d4c73101d919bf1fa Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 7 Dec 2015 14:34:49 -0500 Subject: ext4: fix races of writeback with punch hole and zero range When doing delayed allocation, update of on-disk inode size is postponed until IO submission time. However hole punch or zero range fallocate calls can end up discarding the tail page cache page and thus on-disk inode size would never be properly updated. Make sure the on-disk inode size is updated before truncating page cache. Signed-off-by: Jan Kara Signed-off-by: Theodore Ts'o --- fs/ext4/ext4.h | 3 +++ fs/ext4/extents.c | 5 +++++ fs/ext4/inode.c | 35 ++++++++++++++++++++++++++++++++++- 3 files changed, 42 insertions(+), 1 deletion(-) (limited to 'fs/ext4/inode.c') diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 348a5ff4a0e2..80f76f092079 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -2858,6 +2858,9 @@ 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; diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 4b105c96df08..3578b25fccfd 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -4847,6 +4847,11 @@ static long ext4_zero_range(struct file *file, loff_t offset, * 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); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index d1207d03c961..472e608da13d 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -3558,6 +3558,35 @@ int ext4_can_truncate(struct inode *inode) return 0; } +/* + * We have to make sure i_disksize gets properly updated before we truncate + * page cache due to hole punching or zero range. Otherwise i_disksize update + * can get lost as it may have been postponed to submission of writeback but + * that will never happen after we truncate page cache. + */ +int ext4_update_disksize_before_punch(struct inode *inode, loff_t offset, + loff_t len) +{ + handle_t *handle; + loff_t size = i_size_read(inode); + + WARN_ON(!mutex_is_locked(&inode->i_mutex)); + if (offset > size || offset + len < size) + return 0; + + if (EXT4_I(inode)->i_disksize >= size) + return 0; + + handle = ext4_journal_start(inode, EXT4_HT_MISC, 1); + if (IS_ERR(handle)) + return PTR_ERR(handle); + ext4_update_i_disksize(inode, size); + ext4_mark_inode_dirty(handle, inode); + ext4_journal_stop(handle); + + return 0; +} + /* * ext4_punch_hole: punches a hole in a file by releaseing the blocks * associated with the given offset and length @@ -3636,9 +3665,13 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length) last_block_offset = round_down((offset + length), sb->s_blocksize) - 1; /* Now release the pages and zero block aligned part of pages*/ - if (last_block_offset > first_block_offset) + if (last_block_offset > first_block_offset) { + ret = ext4_update_disksize_before_punch(inode, offset, length); + if (ret) + goto out_dio; truncate_pagecache_range(inode, first_block_offset, last_block_offset); + } if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) credits = ext4_writepage_trans_blocks(inode); -- cgit v1.2.3 From 2dcba4781fa3842e28f47ab23056d58cd283fca6 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 7 Dec 2015 15:04:57 -0500 Subject: ext4: get rid of EXT4_GET_BLOCKS_NO_LOCK flag When dioread_nolock mode is enabled, we grab i_data_sem in ext4_ext_direct_IO() and therefore we need to instruct _ext4_get_block() not to grab i_data_sem again using EXT4_GET_BLOCKS_NO_LOCK. However holding i_data_sem over overwrite direct IO isn't needed these days. We have exclusion against truncate / hole punching because we increase i_dio_count under i_mutex in ext4_ext_direct_IO() so once ext4_file_write_iter() verifies blocks are allocated & written, they are guaranteed to stay so during the whole direct IO even after we drop i_mutex. So we can just remove this locking abuse and the no longer necessary EXT4_GET_BLOCKS_NO_LOCK flag. Signed-off-by: Jan Kara Signed-off-by: Theodore Ts'o --- fs/ext4/ext4.h | 4 +--- fs/ext4/inode.c | 43 ++++++++++++++++++++----------------------- include/trace/events/ext4.h | 3 +-- 3 files changed, 22 insertions(+), 28 deletions(-) (limited to 'fs/ext4/inode.c') diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 80f76f092079..1008caf3136d 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -555,10 +555,8 @@ 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 /* * The bit position of these flags must not overlap with any of the diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 472e608da13d..f100c1780e03 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -403,8 +403,7 @@ 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 +411,7 @@ 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 +507,7 @@ 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 +538,7 @@ 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) { @@ -674,7 +670,7 @@ 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; @@ -879,9 +875,6 @@ 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) @@ -3054,13 +3047,21 @@ 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, @@ -3143,10 +3144,8 @@ static ssize_t ext4_ext_direct_IO(struct kiocb *iocb, struct iov_iter *iter, /* If we do a overwrite dio, i_mutex locking can be released */ overwrite = *((int *)iocb->private); - if (overwrite) { - down_read(&EXT4_I(inode)->i_data_sem); + if (overwrite) mutex_unlock(&inode->i_mutex); - } /* * We could direct write to holes and fallocate. @@ -3189,7 +3188,7 @@ static ssize_t ext4_ext_direct_IO(struct kiocb *iocb, struct iov_iter *iter, } if (overwrite) { - get_block_func = ext4_get_block_write_nolock; + get_block_func = ext4_get_block_overwrite; } else { get_block_func = ext4_get_block_write; dio_flags = DIO_LOCKING; @@ -3245,10 +3244,8 @@ retake_lock: if (iov_iter_rw(iter) == WRITE) inode_dio_end(inode); /* take i_mutex locking again if we do a ovewrite dio */ - if (overwrite) { - up_read(&EXT4_I(inode)->i_data_sem); + if (overwrite) mutex_lock(&inode->i_mutex); - } return ret; } diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h index 594b4b29a224..5f2ace56efc5 100644 --- a/include/trace/events/ext4.h +++ b/include/trace/events/ext4.h @@ -42,8 +42,7 @@ struct extent_status; { EXT4_GET_BLOCKS_CONVERT, "CONVERT" }, \ { EXT4_GET_BLOCKS_METADATA_NOFAIL, "METADATA_NOFAIL" }, \ { EXT4_GET_BLOCKS_NO_NORMALIZE, "NO_NORMALIZE" }, \ - { EXT4_GET_BLOCKS_KEEP_SIZE, "KEEP_SIZE" }, \ - { EXT4_GET_BLOCKS_NO_LOCK, "NO_LOCK" }) + { EXT4_GET_BLOCKS_KEEP_SIZE, "KEEP_SIZE" }) #define show_mflags(flags) __print_flags(flags, "", \ { EXT4_MAP_NEW, "N" }, \ -- cgit v1.2.3 From 53085fac02d12fcd29a9cb074ec480ff0f77ae5c Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 7 Dec 2015 15:09:35 -0500 Subject: ext4: provide ext4_issue_zeroout() Create new function ext4_issue_zeroout() to zeroout contiguous (both logically and physically) part of inode data. We will need to issue zeroout when extent structure is not readily available and this function will allow us to do it without making up fake extent structures. Signed-off-by: Jan Kara Signed-off-by: Theodore Ts'o --- fs/ext4/crypto.c | 6 ++---- fs/ext4/ext4.h | 5 ++++- fs/ext4/extents.c | 12 ++---------- fs/ext4/inode.c | 15 +++++++++++++++ 4 files changed, 23 insertions(+), 15 deletions(-) (limited to 'fs/ext4/inode.c') 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/ext4.h b/fs/ext4/ext4.h index 1008caf3136d..ffc6ab000c78 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -2241,7 +2241,8 @@ 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); @@ -2495,6 +2496,8 @@ 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 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, diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 3578b25fccfd..867e98b6bc6c 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); } /* diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index f100c1780e03..0c9a5ee3e106 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)) -- cgit v1.2.3 From c86d8db33a922da808a5560aa15ed663a9569b37 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 7 Dec 2015 15:10:26 -0500 Subject: ext4: implement allocation of pre-zeroed blocks DAX page fault path needs to get blocks that are pre-zeroed to avoid races when two concurrent page faults happen in the same block of a file. Implement support for this in ext4_map_blocks(). Signed-off-by: Jan Kara Signed-off-by: Theodore Ts'o --- fs/ext4/ext4.h | 4 ++++ fs/ext4/extents.c | 8 ++++++++ fs/ext4/inode.c | 25 ++++++++++++++++++++++--- include/trace/events/ext4.h | 3 ++- 4 files changed, 36 insertions(+), 4 deletions(-) (limited to 'fs/ext4/inode.c') diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index ffc6ab000c78..ae900b530d37 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -557,6 +557,10 @@ enum { #define EXT4_GET_BLOCKS_KEEP_SIZE 0x0080 /* Convert written extents to unwritten */ #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 diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 867e98b6bc6c..b52fea3b7219 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -4044,6 +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) { diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 0c9a5ee3e106..4241d0cff062 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -636,6 +636,22 @@ found: WARN_ON(1); } + /* + * 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. @@ -643,7 +659,7 @@ found: 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; @@ -654,11 +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); @@ -3083,6 +3101,7 @@ int ext4_get_block_dax(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", diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h index 5f2ace56efc5..4e4b2fa78609 100644 --- a/include/trace/events/ext4.h +++ b/include/trace/events/ext4.h @@ -42,7 +42,8 @@ struct extent_status; { EXT4_GET_BLOCKS_CONVERT, "CONVERT" }, \ { EXT4_GET_BLOCKS_METADATA_NOFAIL, "METADATA_NOFAIL" }, \ { EXT4_GET_BLOCKS_NO_NORMALIZE, "NO_NORMALIZE" }, \ - { EXT4_GET_BLOCKS_KEEP_SIZE, "KEEP_SIZE" }) + { EXT4_GET_BLOCKS_KEEP_SIZE, "KEEP_SIZE" }, \ + { EXT4_GET_BLOCKS_ZERO, "ZERO" }) #define show_mflags(flags) __print_flags(flags, "", \ { EXT4_MAP_NEW, "N" }, \ -- cgit v1.2.3 From ba5843f51d468644b094674c0317c9ab95632caa Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 7 Dec 2015 15:10:44 -0500 Subject: ext4: use pre-zeroed blocks for DAX page faults Make DAX fault path use pre-zeroed blocks to avoid races with extent conversion and zeroing when two page faults to the same block happen. Signed-off-by: Jan Kara Signed-off-by: Theodore Ts'o --- fs/ext4/ext4.h | 4 +-- fs/ext4/file.c | 20 ++------------ fs/ext4/inode.c | 86 +++++++++++++++++++++++++++++++++++++++++++++------------ 3 files changed, 74 insertions(+), 36 deletions(-) (limited to 'fs/ext4/inode.c') diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index ae900b530d37..1e20fa94fcf6 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -2452,8 +2452,8 @@ 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, diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 0d24ebcd7c9e..749b222e6498 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -193,18 +193,6 @@ 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; @@ -225,8 +213,7 @@ static int ext4_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf) 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)) @@ -262,7 +249,7 @@ static int ext4_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr, 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)) @@ -283,8 +270,7 @@ static int ext4_dax_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) 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_get_block_dax, - ext4_end_io_unwritten); + 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); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 4241d0cff062..ff2f3cd38522 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -723,16 +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; @@ -3097,17 +3087,79 @@ static int ext4_get_block_overwrite(struct inode *inode, sector_t iblock, 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; + int ret, err; + int credits; + struct ext4_map_blocks map; + handle_t *handle = NULL; + int flags = 0; - if (create) - flags |= EXT4_GET_BLOCKS_CREATE; - ext4_debug("ext4_get_block_dax: inode %lu, create flag %d\n", + ext4_debug("ext4_dax_mmap_get_block: inode %lu, create flag %d\n", inode->i_ino, create); - return _ext4_get_block(inode, iblock, bh_result, flags); + map.m_lblk = iblock; + map.m_len = bh_result->b_size >> inode->i_blkbits; + credits = ext4_chunk_trans_blocks(inode, map.m_len); + if (create) { + flags |= EXT4_GET_BLOCKS_PRE_IO | EXT4_GET_BLOCKS_CREATE_ZERO; + handle = ext4_journal_start(inode, EXT4_HT_MAP_BLOCKS, credits); + if (IS_ERR(handle)) { + ret = PTR_ERR(handle); + return ret; + } + } + + ret = ext4_map_blocks(handle, inode, &map, flags); + if (create) { + err = ext4_journal_stop(handle); + if (ret >= 0 && err < 0) + ret = err; + } + if (ret <= 0) + goto out; + if (map.m_flags & EXT4_MAP_UNWRITTEN) { + int err2; + + /* + * We are protected by i_mmap_sem so we know block cannot go + * away from under us even though we dropped i_data_sem. + * Convert extent to written and write zeros there. + * + * Note: We may get here even when create == 0. + */ + handle = ext4_journal_start(inode, EXT4_HT_MAP_BLOCKS, credits); + if (IS_ERR(handle)) { + ret = PTR_ERR(handle); + goto out; + } + + err = ext4_map_blocks(handle, inode, &map, + EXT4_GET_BLOCKS_CONVERT | EXT4_GET_BLOCKS_CREATE_ZERO); + if (err < 0) + ret = err; + err2 = ext4_journal_stop(handle); + if (err2 < 0 && ret > 0) + ret = err2; + } +out: + WARN_ON_ONCE(ret == 0 && create); + if (ret > 0) { + map_bh(bh_result, inode->i_sb, map.m_pblk); + bh_result->b_state = (bh_result->b_state & ~EXT4_MAP_FLAGS) | + map.m_flags; + /* + * At least for now we have to clear BH_New so that DAX code + * doesn't attempt to zero blocks again in a racy way. + */ + bh_result->b_state &= ~(1 << BH_New); + bh_result->b_size = map.m_len << inode->i_blkbits; + ret = 0; + } + return ret; } +#endif static void ext4_end_io_dio(struct kiocb *iocb, loff_t offset, ssize_t size, void *private) -- cgit v1.2.3 From 040cb3786d9b25293b8b0b05b90da0f871e1eb9b Mon Sep 17 00:00:00 2001 From: Li Xi Date: Fri, 8 Jan 2016 16:01:21 -0500 Subject: ext4: adds project ID support Signed-off-by: Li Xi Signed-off-by: Theodore Ts'o Reviewed-by: Andreas Dilger Reviewed-by: Jan Kara --- fs/ext4/ext4.h | 17 +++++++++++++---- fs/ext4/ialloc.c | 7 +++++++ fs/ext4/inode.c | 28 ++++++++++++++++++++++++++++ fs/ext4/namei.c | 19 +++++++++++++++++++ fs/ext4/super.c | 1 + 5 files changed, 68 insertions(+), 4 deletions(-) (limited to 'fs/ext4/inode.c') diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index f82da361a823..023781101bae 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -378,14 +378,15 @@ 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 */ /* 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)) @@ -1004,6 +1005,7 @@ struct ext4_inode_info { /* Encryption params */ struct ext4_crypt_info *i_crypt_info; #endif + kprojid_t i_projid; }; /* @@ -1765,7 +1767,8 @@ 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) \ @@ -1807,6 +1810,11 @@ 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 /* @@ -2498,6 +2506,7 @@ extern int ext4_zero_partial_blocks(handle_t *handle, struct inode *inode, 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, 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/inode.c b/fs/ext4/inode.c index ff2f3cd38522..6770c07ab39f 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -4193,6 +4193,14 @@ static inline void ext4_iget_extra_inode(struct inode *inode, EXT4_I(inode)->i_inline_off = 0; } +int ext4_get_projid(struct inode *inode, kprojid_t *projid) +{ + if (!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, EXT4_FEATURE_RO_COMPAT_PROJECT)) + return -EOPNOTSUPP; + *projid = EXT4_I(inode)->i_projid; + return 0; +} + struct inode *ext4_iget(struct super_block *sb, unsigned long ino) { struct ext4_iloc iloc; @@ -4204,6 +4212,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino) int block; uid_t i_uid; gid_t i_gid; + projid_t i_projid; inode = iget_locked(sb, ino); if (!inode) @@ -4253,12 +4262,20 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino) inode->i_mode = le16_to_cpu(raw_inode->i_mode); i_uid = (uid_t)le16_to_cpu(raw_inode->i_uid_low); i_gid = (gid_t)le16_to_cpu(raw_inode->i_gid_low); + if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_PROJECT) && + EXT4_INODE_SIZE(sb) > EXT4_GOOD_OLD_INODE_SIZE && + EXT4_FITS_IN_INODE(raw_inode, ei, i_projid)) + i_projid = (projid_t)le32_to_cpu(raw_inode->i_projid); + else + i_projid = EXT4_DEF_PROJID; + if (!(test_opt(inode->i_sb, NO_UID32))) { i_uid |= le16_to_cpu(raw_inode->i_uid_high) << 16; i_gid |= le16_to_cpu(raw_inode->i_gid_high) << 16; } i_uid_write(inode, i_uid); i_gid_write(inode, i_gid); + ei->i_projid = make_kprojid(&init_user_ns, i_projid); set_nlink(inode, le16_to_cpu(raw_inode->i_links_count)); ext4_clear_state_flags(ei); /* Only relevant on 32-bit archs */ @@ -4556,6 +4573,7 @@ static int ext4_do_update_inode(handle_t *handle, int need_datasync = 0, set_large_file = 0; uid_t i_uid; gid_t i_gid; + projid_t i_projid; spin_lock(&ei->i_raw_lock); @@ -4568,6 +4586,7 @@ static int ext4_do_update_inode(handle_t *handle, raw_inode->i_mode = cpu_to_le16(inode->i_mode); i_uid = i_uid_read(inode); i_gid = i_gid_read(inode); + i_projid = from_kprojid(&init_user_ns, ei->i_projid); if (!(test_opt(inode->i_sb, NO_UID32))) { raw_inode->i_uid_low = cpu_to_le16(low_16_bits(i_uid)); raw_inode->i_gid_low = cpu_to_le16(low_16_bits(i_gid)); @@ -4645,6 +4664,15 @@ static int ext4_do_update_inode(handle_t *handle, cpu_to_le16(ei->i_extra_isize); } } + + BUG_ON(!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, + EXT4_FEATURE_RO_COMPAT_PROJECT) && + i_projid != EXT4_DEF_PROJID); + + if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE && + EXT4_FITS_IN_INODE(raw_inode, ei, i_projid)) + raw_inode->i_projid = cpu_to_le32(i_projid); + ext4_inode_csum_set(inode, raw_inode, ei); spin_unlock(&ei->i_raw_lock); if (inode->i_sb->s_flags & MS_LAZYTIME) diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 06c3afcbfac8..2047ff7c5fbc 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -3208,6 +3208,12 @@ static int ext4_link(struct dentry *old_dentry, if (ext4_encrypted_inode(dir) && !ext4_is_child_context_consistent_with_parent(dir, inode)) return -EPERM; + + if ((ext4_test_inode_flag(dir, EXT4_INODE_PROJINHERIT)) && + (!projid_eq(EXT4_I(dir)->i_projid, + EXT4_I(old_dentry->d_inode)->i_projid))) + return -EXDEV; + err = dquot_initialize(dir); if (err) return err; @@ -3488,6 +3494,11 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry, int credits; u8 old_file_type; + if ((ext4_test_inode_flag(new_dir, EXT4_INODE_PROJINHERIT)) && + (!projid_eq(EXT4_I(new_dir)->i_projid, + EXT4_I(old_dentry->d_inode)->i_projid))) + return -EXDEV; + retval = dquot_initialize(old.dir); if (retval) return retval; @@ -3697,6 +3708,14 @@ static int ext4_cross_rename(struct inode *old_dir, struct dentry *old_dentry, new.inode))) return -EPERM; + if ((ext4_test_inode_flag(new_dir, EXT4_INODE_PROJINHERIT) && + !projid_eq(EXT4_I(new_dir)->i_projid, + EXT4_I(old_dentry->d_inode)->i_projid)) || + (ext4_test_inode_flag(old_dir, EXT4_INODE_PROJINHERIT) && + !projid_eq(EXT4_I(old_dir)->i_projid, + EXT4_I(new_dentry->d_inode)->i_projid))) + return -EXDEV; + retval = dquot_initialize(old.dir); if (retval) return retval; diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 486e869bd583..844c95d95821 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1131,6 +1131,7 @@ static const struct dquot_operations ext4_quota_operations = { .write_info = ext4_write_info, .alloc_dquot = dquot_alloc, .destroy_dquot = dquot_destroy, + .get_projid = ext4_get_projid, }; static const struct quotactl_ops ext4_qctl_operations = { -- cgit v1.2.3