summaryrefslogtreecommitdiff
path: root/fs/ext4/inode.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2016-01-22 11:23:35 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2016-01-22 11:23:35 -0800
commit391f2a16b74b95da2f05a607f53213fc8ed24b8e (patch)
tree93bfd1906778d7ff24f6ce7c03f2e7c0f91caef5 /fs/ext4/inode.c
parentd5ffdf8b4ac6e6db5702ba31870c476d5fa30660 (diff)
parent68ce7bfcd995a8a393b1b14fa67dbc16fa3dc784 (diff)
Merge tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4
Pull ext4 updates from Ted Ts'o: "Some locking and page fault bug fixes from Jan Kara, some ext4 encryption fixes from me, and Li Xi's Project Quota commits" * tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: fs: clean up the flags definition in uapi/linux/fs.h ext4: add FS_IOC_FSSETXATTR/FS_IOC_FSGETXATTR interface support ext4: add project quota support ext4: adds project ID support ext4 crypto: simplify interfaces to directory entry insert functions ext4 crypto: add missing locking for keyring_key access ext4: use pre-zeroed blocks for DAX page faults ext4: implement allocation of pre-zeroed blocks ext4: provide ext4_issue_zeroout() ext4: get rid of EXT4_GET_BLOCKS_NO_LOCK flag ext4: document lock ordering ext4: fix races of writeback with punch hole and zero range ext4: fix races between buffered IO and collapse / insert range ext4: move unlocked dio protection from ext4_alloc_file_blocks() ext4: fix races between page faults and hole punching
Diffstat (limited to 'fs/ext4/inode.c')
-rw-r--r--fs/ext4/inode.c268
1 files changed, 215 insertions, 53 deletions
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",
+ int ret, err;
+ int credits;
+ struct ext4_map_blocks map;
+ handle_t *handle = NULL;
+ int flags = 0;
+
+ 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)
@@ -3143,10 +3230,8 @@ 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 +3274,7 @@ 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 +3330,8 @@ 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;
}
@@ -3559,6 +3642,35 @@ int ext4_can_truncate(struct inode *inode)
}
/*
+ * 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
*
@@ -3623,17 +3735,26 @@ 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;
/* 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);
-
- /* 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);
@@ -3680,16 +3801,12 @@ 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);
@@ -4076,6 +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;
@@ -4087,6 +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)
@@ -4136,12 +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 */
@@ -4440,6 +4574,7 @@ 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);
@@ -4452,6 +4587,7 @@ 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));
@@ -4529,6 +4665,15 @@ 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)
@@ -4824,6 +4969,7 @@ 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.
@@ -4831,6 +4977,7 @@ 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) {
@@ -5279,6 +5426,8 @@ 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) &&
@@ -5348,6 +5497,19 @@ 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;
+}