1 files changed, 63 insertions, 20 deletions

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 629a25d999f0..fa0ff78dc033 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -48,8 +48,6 @@
 
 #include <trace/events/ext4.h>
 
-#define MPAGE_DA_EXTENT_TAIL 0x01
-
 static __u32 ext4_inode_csum(struct inode *inode, struct ext4_inode *raw,
 			      struct ext4_inode_info *ei)
 {
@@ -271,6 +269,7 @@ void ext4_evict_inode(struct inode *inode)
 	if (inode->i_blocks) {
 		err = ext4_truncate(inode);
 		if (err) {
+			ext4_set_errno(inode->i_sb, -err);
 			ext4_error(inode->i_sb,
 				   "couldn't truncate inode %lu (err %d)",
 				   inode->i_ino, err);
@@ -402,7 +401,7 @@ int ext4_issue_zeroout(struct inode *inode, ext4_lblk_t lblk, ext4_fsblk_t pblk,
 {
 	int ret;
 
-	if (IS_ENCRYPTED(inode))
+	if (IS_ENCRYPTED(inode) && S_ISREG(inode->i_mode))
 		return fscrypt_zeroout_range(inode, lblk, pblk, len);
 
 	ret = sb_issue_zeroout(inode->i_sb, pblk, len, GFP_NOFS);
@@ -2466,7 +2465,7 @@ update_disksize:
 	 * truncate are avoided by checking i_size under i_data_sem.
 	 */
 	disksize = ((loff_t)mpd->first_page) << PAGE_SHIFT;
-	if (disksize > EXT4_I(inode)->i_disksize) {
+	if (disksize > READ_ONCE(EXT4_I(inode)->i_disksize)) {
 		int err2;
 		loff_t i_size;
 
@@ -2478,10 +2477,12 @@ update_disksize:
 			EXT4_I(inode)->i_disksize = disksize;
 		up_write(&EXT4_I(inode)->i_data_sem);
 		err2 = ext4_mark_inode_dirty(handle, inode);
-		if (err2)
+		if (err2) {
+			ext4_set_errno(inode->i_sb, -err2);
 			ext4_error(inode->i_sb,
 				   "Failed to mark inode %lu dirty",
 				   inode->i_ino);
+		}
 		if (!err)
 			err = err2;
 	}
@@ -2627,7 +2628,7 @@ static int ext4_writepages(struct address_space *mapping,
 	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
 		return -EIO;
 
-	percpu_down_read(&sbi->s_journal_flag_rwsem);
+	percpu_down_read(&sbi->s_writepages_rwsem);
 	trace_ext4_writepages(inode, wbc);
 
 	/*
@@ -2848,7 +2849,7 @@ unplug:
 out_writepages:
 	trace_ext4_writepages_result(inode, wbc, ret,
 				     nr_to_write - wbc->nr_to_write);
-	percpu_up_read(&sbi->s_journal_flag_rwsem);
+	percpu_up_read(&sbi->s_writepages_rwsem);
 	return ret;
 }
 
@@ -2863,13 +2864,13 @@ static int ext4_dax_writepages(struct address_space *mapping,
 	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
 		return -EIO;
 
-	percpu_down_read(&sbi->s_journal_flag_rwsem);
+	percpu_down_read(&sbi->s_writepages_rwsem);
 	trace_ext4_writepages(inode, wbc);
 
-	ret = dax_writeback_mapping_range(mapping, inode->i_sb->s_bdev, wbc);
+	ret = dax_writeback_mapping_range(mapping, sbi->s_daxdev, wbc);
 	trace_ext4_writepages_result(inode, wbc, ret,
 				     nr_to_write - wbc->nr_to_write);
-	percpu_up_read(&sbi->s_journal_flag_rwsem);
+	percpu_up_read(&sbi->s_writepages_rwsem);
 	return ret;
 }
 
@@ -3448,6 +3449,22 @@ static int ext4_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
 	return 0;
 }
 
+static int ext4_iomap_overwrite_begin(struct inode *inode, loff_t offset,
+		loff_t length, unsigned flags, struct iomap *iomap,
+		struct iomap *srcmap)
+{
+	int ret;
+
+	/*
+	 * Even for writes we don't need to allocate blocks, so just pretend
+	 * we are reading to save overhead of starting a transaction.
+	 */
+	flags &= ~IOMAP_WRITE;
+	ret = ext4_iomap_begin(inode, offset, length, flags, iomap, srcmap);
+	WARN_ON_ONCE(iomap->type != IOMAP_MAPPED);
+	return ret;
+}
+
 static int ext4_iomap_end(struct inode *inode, loff_t offset, loff_t length,
 			  ssize_t written, unsigned flags, struct iomap *iomap)
 {
@@ -3469,6 +3486,11 @@ const struct iomap_ops ext4_iomap_ops = {
 	.iomap_end		= ext4_iomap_end,
 };
 
+const struct iomap_ops ext4_iomap_overwrite_ops = {
+	.iomap_begin		= ext4_iomap_overwrite_begin,
+	.iomap_end		= ext4_iomap_end,
+};
+
 static bool ext4_iomap_is_delalloc(struct inode *inode,
 				   struct ext4_map_blocks *map)
 {
@@ -3701,8 +3723,12 @@ static int __ext4_block_zero_page_range(handle_t *handle,
 		if (S_ISREG(inode->i_mode) && IS_ENCRYPTED(inode)) {
 			/* We expect the key to be set. */
 			BUG_ON(!fscrypt_has_encryption_key(inode));
-			WARN_ON_ONCE(fscrypt_decrypt_pagecache_blocks(
-					page, blocksize, bh_offset(bh)));
+			err = fscrypt_decrypt_pagecache_blocks(page, blocksize,
+							       bh_offset(bh));
+			if (err) {
+				clear_buffer_uptodate(bh);
+				goto unlock;
+			}
 		}
 	}
 	if (ext4_should_journal_data(inode)) {
@@ -3912,9 +3938,6 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length)
 	unsigned int credits;
 	int ret = 0;
 
-	if (!S_ISREG(inode->i_mode))
-		return -EOPNOTSUPP;
-
 	trace_ext4_punch_hole(inode, offset, length, 0);
 
 	ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA);
@@ -4240,6 +4263,8 @@ static int __ext4_get_inode_loc(struct inode *inode,
 	bh = sb_getblk(sb, block);
 	if (unlikely(!bh))
 		return -ENOMEM;
+	if (ext4_simulate_fail(sb, EXT4_SIM_INODE_EIO))
+		goto simulate_eio;
 	if (!buffer_uptodate(bh)) {
 		lock_buffer(bh);
 
@@ -4338,6 +4363,8 @@ make_io:
 		blk_finish_plug(&plug);
 		wait_on_buffer(bh);
 		if (!buffer_uptodate(bh)) {
+		simulate_eio:
+			ext4_set_errno(inode->i_sb, EIO);
 			EXT4_ERROR_INODE_BLOCK(inode, block,
 					       "unable to read itable block");
 			brelse(bh);
@@ -4551,7 +4578,9 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino,
 					      sizeof(gen));
 	}
 
-	if (!ext4_inode_csum_verify(inode, raw_inode, ei)) {
+	if (!ext4_inode_csum_verify(inode, raw_inode, ei) ||
+	    ext4_simulate_fail(sb, EXT4_SIM_INODE_CRC)) {
+		ext4_set_errno(inode->i_sb, EFSBADCRC);
 		ext4_error_inode(inode, function, line, 0,
 				 "iget: checksum invalid");
 		ret = -EFSBADCRC;
@@ -4615,6 +4644,18 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino,
 		ret = -EFSCORRUPTED;
 		goto bad_inode;
 	}
+	/*
+	 * If dir_index is not enabled but there's dir with INDEX flag set,
+	 * we'd normally treat htree data as empty space. But with metadata
+	 * checksumming that corrupts checksums so forbid that.
+	 */
+	if (!ext4_has_feature_dir_index(sb) && ext4_has_metadata_csum(sb) &&
+	    ext4_test_inode_flag(inode, EXT4_INODE_INDEX)) {
+		ext4_error_inode(inode, function, line, 0,
+			 "iget: Dir with htree data on filesystem without dir_index feature.");
+		ret = -EFSCORRUPTED;
+		goto bad_inode;
+	}
 	ei->i_disksize = inode->i_size;
 #ifdef CONFIG_QUOTA
 	ei->i_reserved_quota = 0;
@@ -5090,6 +5131,7 @@ int ext4_write_inode(struct inode *inode, struct writeback_control *wbc)
 		if (wbc->sync_mode == WB_SYNC_ALL && !wbc->for_sync)
 			sync_dirty_buffer(iloc.bh);
 		if (buffer_req(iloc.bh) && !buffer_uptodate(iloc.bh)) {
+			ext4_set_errno(inode->i_sb, EIO);
 			EXT4_ERROR_INODE_BLOCK(inode, iloc.bh->b_blocknr,
 					 "IO error syncing inode");
 			err = -EIO;
@@ -5368,7 +5410,8 @@ int ext4_getattr(const struct path *path, struct kstat *stat,
 	struct ext4_inode_info *ei = EXT4_I(inode);
 	unsigned int flags;
 
-	if (EXT4_FITS_IN_INODE(raw_inode, ei, i_crtime)) {
+	if ((request_mask & STATX_BTIME) &&
+	    EXT4_FITS_IN_INODE(raw_inode, ei, i_crtime)) {
 		stat->result_mask |= STATX_BTIME;
 		stat->btime.tv_sec = ei->i_crtime.tv_sec;
 		stat->btime.tv_nsec = ei->i_crtime.tv_nsec;
@@ -5818,7 +5861,7 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val)
 		}
 	}
 
-	percpu_down_write(&sbi->s_journal_flag_rwsem);
+	percpu_down_write(&sbi->s_writepages_rwsem);
 	jbd2_journal_lock_updates(journal);
 
 	/*
@@ -5835,7 +5878,7 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val)
 		err = jbd2_journal_flush(journal);
 		if (err < 0) {
 			jbd2_journal_unlock_updates(journal);
-			percpu_up_write(&sbi->s_journal_flag_rwsem);
+			percpu_up_write(&sbi->s_writepages_rwsem);
 			return err;
 		}
 		ext4_clear_inode_flag(inode, EXT4_INODE_JOURNAL_DATA);
@@ -5843,7 +5886,7 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val)
 	ext4_set_aops(inode);
 
 	jbd2_journal_unlock_updates(journal);
-	percpu_up_write(&sbi->s_journal_flag_rwsem);
+	percpu_up_write(&sbi->s_writepages_rwsem);
 
 	if (val)
 		up_write(&EXT4_I(inode)->i_mmap_sem);