1 files changed, 145 insertions, 39 deletions

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index ea433a7f4bca..28702932a908 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -51,25 +51,31 @@ static __u32 ext4_inode_csum(struct inode *inode, struct ext4_inode *raw,
 			      struct ext4_inode_info *ei)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
-	__u16 csum_lo;
-	__u16 csum_hi = 0;
 	__u32 csum;
+	__u16 dummy_csum = 0;
+	int offset = offsetof(struct ext4_inode, i_checksum_lo);
+	unsigned int csum_size = sizeof(dummy_csum);
 
-	csum_lo = le16_to_cpu(raw->i_checksum_lo);
-	raw->i_checksum_lo = 0;
-	if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE &&
-	    EXT4_FITS_IN_INODE(raw, ei, i_checksum_hi)) {
-		csum_hi = le16_to_cpu(raw->i_checksum_hi);
-		raw->i_checksum_hi = 0;
-	}
-
-	csum = ext4_chksum(sbi, ei->i_csum_seed, (__u8 *)raw,
-			   EXT4_INODE_SIZE(inode->i_sb));
+	csum = ext4_chksum(sbi, ei->i_csum_seed, (__u8 *)raw, offset);
+	csum = ext4_chksum(sbi, csum, (__u8 *)&dummy_csum, csum_size);
+	offset += csum_size;
+	csum = ext4_chksum(sbi, csum, (__u8 *)raw + offset,
+			   EXT4_GOOD_OLD_INODE_SIZE - offset);
 
-	raw->i_checksum_lo = cpu_to_le16(csum_lo);
-	if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE &&
-	    EXT4_FITS_IN_INODE(raw, ei, i_checksum_hi))
-		raw->i_checksum_hi = cpu_to_le16(csum_hi);
+	if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE) {
+		offset = offsetof(struct ext4_inode, i_checksum_hi);
+		csum = ext4_chksum(sbi, csum, (__u8 *)raw +
+				   EXT4_GOOD_OLD_INODE_SIZE,
+				   offset - EXT4_GOOD_OLD_INODE_SIZE);
+		if (EXT4_FITS_IN_INODE(raw, ei, i_checksum_hi)) {
+			csum = ext4_chksum(sbi, csum, (__u8 *)&dummy_csum,
+					   csum_size);
+			offset += csum_size;
+			csum = ext4_chksum(sbi, csum, (__u8 *)raw + offset,
+					   EXT4_INODE_SIZE(inode->i_sb) -
+					   offset);
+		}
+	}
 
 	return csum;
 }
@@ -205,9 +211,9 @@ void ext4_evict_inode(struct inode *inode)
 		 * Note that directories do not have this problem because they
 		 * don't use page cache.
 		 */
-		if (ext4_should_journal_data(inode) &&
-		    (S_ISLNK(inode->i_mode) || S_ISREG(inode->i_mode)) &&
-		    inode->i_ino != EXT4_JOURNAL_INO) {
+		if (inode->i_ino != EXT4_JOURNAL_INO &&
+		    ext4_should_journal_data(inode) &&
+		    (S_ISLNK(inode->i_mode) || S_ISREG(inode->i_mode))) {
 			journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
 			tid_t commit_tid = EXT4_I(inode)->i_datasync_tid;
 
@@ -657,6 +663,34 @@ has_zeroout:
 	return retval;
 }
 
+/*
+ * Update EXT4_MAP_FLAGS in bh->b_state. For buffer heads attached to pages
+ * we have to be careful as someone else may be manipulating b_state as well.
+ */
+static void ext4_update_bh_state(struct buffer_head *bh, unsigned long flags)
+{
+	unsigned long old_state;
+	unsigned long new_state;
+
+	flags &= EXT4_MAP_FLAGS;
+
+	/* Dummy buffer_head? Set non-atomically. */
+	if (!bh->b_page) {
+		bh->b_state = (bh->b_state & ~EXT4_MAP_FLAGS) | flags;
+		return;
+	}
+	/*
+	 * Someone else may be modifying b_state. Be careful! This is ugly but
+	 * once we get rid of using bh as a container for mapping information
+	 * to pass to / from get_block functions, this can go away.
+	 */
+	do {
+		old_state = READ_ONCE(bh->b_state);
+		new_state = (old_state & ~EXT4_MAP_FLAGS) | flags;
+	} while (unlikely(
+		 cmpxchg(&bh->b_state, old_state, new_state) != old_state));
+}
+
 /* Maximum number of blocks we map for direct IO at once. */
 #define DIO_MAX_BLOCKS 4096
 
@@ -693,7 +727,7 @@ static int _ext4_get_block(struct inode *inode, sector_t iblock,
 		ext4_io_end_t *io_end = ext4_inode_aio(inode);
 
 		map_bh(bh, inode->i_sb, map.m_pblk);
-		bh->b_state = (bh->b_state & ~EXT4_MAP_FLAGS) | map.m_flags;
+		ext4_update_bh_state(bh, map.m_flags);
 		if (IS_DAX(inode) && buffer_unwritten(bh)) {
 			/*
 			 * dgc: I suspect unwritten conversion on ext4+DAX is
@@ -1669,7 +1703,7 @@ int ext4_da_get_block_prep(struct inode *inode, sector_t iblock,
 		return ret;
 
 	map_bh(bh, inode->i_sb, map.m_pblk);
-	bh->b_state = (bh->b_state & ~EXT4_MAP_FLAGS) | map.m_flags;
+	ext4_update_bh_state(bh, map.m_flags);
 
 	if (buffer_unwritten(bh)) {
 		/* A delayed write to unwritten bh should be marked
@@ -2561,13 +2595,36 @@ retry:
 				done = true;
 			}
 		}
-		ext4_journal_stop(handle);
+		/*
+		 * Caution: If the handle is synchronous,
+		 * ext4_journal_stop() can wait for transaction commit
+		 * to finish which may depend on writeback of pages to
+		 * complete or on page lock to be released.  In that
+		 * case, we have to wait until after after we have
+		 * submitted all the IO, released page locks we hold,
+		 * and dropped io_end reference (for extent conversion
+		 * to be able to complete) before stopping the handle.
+		 */
+		if (!ext4_handle_valid(handle) || handle->h_sync == 0) {
+			ext4_journal_stop(handle);
+			handle = NULL;
+		}
 		/* Submit prepared bio */
 		ext4_io_submit(&mpd.io_submit);
 		/* Unlock pages we didn't use */
 		mpage_release_unused_pages(&mpd, give_up_on_write);
-		/* Drop our io_end reference we got from init */
-		ext4_put_io_end(mpd.io_submit.io_end);
+		/*
+		 * Drop our io_end reference we got from init. We have
+		 * to be careful and use deferred io_end finishing if
+		 * we are still holding the transaction as we can
+		 * release the last reference to io_end which may end
+		 * up doing unwritten extent conversion.
+		 */
+		if (handle) {
+			ext4_put_io_end_defer(mpd.io_submit.io_end);
+			ext4_journal_stop(handle);
+		} else
+			ext4_put_io_end(mpd.io_submit.io_end);
 
 		if (ret == -ENOSPC && sbi->s_journal) {
 			/*
@@ -3559,6 +3616,35 @@ 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 +3709,26 @@ 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 +3775,12 @@ 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 +4914,7 @@ 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 +4922,7 @@ 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) {
@@ -5081,6 +5174,8 @@ int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode)
 	might_sleep();
 	trace_ext4_mark_inode_dirty(inode, _RET_IP_);
 	err = ext4_reserve_inode_write(handle, inode, &iloc);
+	if (err)
+		return err;
 	if (ext4_handle_valid(handle) &&
 	    EXT4_I(inode)->i_extra_isize < sbi->s_want_extra_isize &&
 	    !ext4_test_inode_state(inode, EXT4_STATE_NO_EXPAND)) {
@@ -5097,8 +5192,6 @@ int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode)
 						      sbi->s_want_extra_isize,
 						      iloc, handle);
 			if (ret) {
-				ext4_set_inode_state(inode,
-						     EXT4_STATE_NO_EXPAND);
 				if (mnt_count !=
 					le16_to_cpu(sbi->s_es->s_mnt_count)) {
 					ext4_warning(inode->i_sb,
@@ -5111,9 +5204,7 @@ int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode)
 			}
 		}
 	}
-	if (!err)
-		err = ext4_mark_iloc_dirty(handle, inode, &iloc);
-	return err;
+	return ext4_mark_iloc_dirty(handle, inode, &iloc);
 }
 
 /*
@@ -5278,6 +5369,8 @@ 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 +5440,19 @@ 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;
+}