1 files changed, 359 insertions, 149 deletions

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 9c064727ed62..b9ffa9f4191f 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -37,6 +37,7 @@
 #include <linux/printk.h>
 #include <linux/slab.h>
 #include <linux/bitops.h>
+#include <linux/iomap.h>
 
 #include "ext4_jbd2.h"
 #include "xattr.h"
@@ -71,10 +72,9 @@ static __u32 ext4_inode_csum(struct inode *inode, struct ext4_inode *raw,
 			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);
 		}
+		csum = ext4_chksum(sbi, csum, (__u8 *)raw + offset,
+				   EXT4_INODE_SIZE(inode->i_sb) - offset);
 	}
 
 	return csum;
@@ -261,8 +261,15 @@ void ext4_evict_inode(struct inode *inode)
 			     "couldn't mark inode dirty (err %d)", err);
 		goto stop_handle;
 	}
-	if (inode->i_blocks)
-		ext4_truncate(inode);
+	if (inode->i_blocks) {
+		err = ext4_truncate(inode);
+		if (err) {
+			ext4_error(inode->i_sb,
+				   "couldn't truncate inode %lu (err %d)",
+				   inode->i_ino, err);
+			goto stop_handle;
+		}
+	}
 
 	/*
 	 * ext4_ext_truncate() doesn't reserve any slop when it
@@ -654,12 +661,8 @@ found:
 		if (flags & EXT4_GET_BLOCKS_ZERO &&
 		    map->m_flags & EXT4_MAP_MAPPED &&
 		    map->m_flags & EXT4_MAP_NEW) {
-			ext4_lblk_t i;
-
-			for (i = 0; i < map->m_len; i++) {
-				unmap_underlying_metadata(inode->i_sb->s_bdev,
-							  map->m_pblk + i);
-			}
+			clean_bdev_aliases(inode->i_sb->s_bdev, map->m_pblk,
+					   map->m_len);
 			ret = ext4_issue_zeroout(inode, map->m_lblk,
 						 map->m_pblk, map->m_len);
 			if (ret) {
@@ -767,6 +770,9 @@ static int _ext4_get_block(struct inode *inode, sector_t iblock,
 		ext4_update_bh_state(bh, map.m_flags);
 		bh->b_size = inode->i_sb->s_blocksize * map.m_len;
 		ret = 0;
+	} else if (ret == 0) {
+		/* hole case, need to fill in bh->b_size */
+		bh->b_size = inode->i_sb->s_blocksize * map.m_len;
 	}
 	return ret;
 }
@@ -1127,8 +1133,7 @@ static int ext4_block_write_begin(struct page *page, loff_t pos, unsigned len,
 			if (err)
 				break;
 			if (buffer_new(bh)) {
-				unmap_underlying_metadata(bh->b_bdev,
-							  bh->b_blocknr);
+				clean_bdev_bh_alias(bh);
 				if (PageUptodate(page)) {
 					clear_buffer_new(bh);
 					set_buffer_uptodate(bh);
@@ -1166,7 +1171,8 @@ static int ext4_block_write_begin(struct page *page, loff_t pos, unsigned len,
 	if (unlikely(err))
 		page_zero_new_buffers(page, from, to);
 	else if (decrypt)
-		err = fscrypt_decrypt_page(page);
+		err = fscrypt_decrypt_page(page->mapping->host, page,
+				PAGE_SIZE, 0, page->index);
 	return err;
 }
 #endif
@@ -1183,6 +1189,9 @@ static int ext4_write_begin(struct file *file, struct address_space *mapping,
 	pgoff_t index;
 	unsigned from, to;
 
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
+		return -EIO;
+
 	trace_ext4_write_begin(inode, pos, len, flags);
 	/*
 	 * Reserve one block more for addition to orphan list in case
@@ -1324,8 +1333,11 @@ static int ext4_write_end(struct file *file,
 	if (ext4_has_inline_data(inode)) {
 		ret = ext4_write_inline_data_end(inode, pos, len,
 						 copied, page);
-		if (ret < 0)
+		if (ret < 0) {
+			unlock_page(page);
+			put_page(page);
 			goto errout;
+		}
 		copied = ret;
 	} else
 		copied = block_write_end(file, mapping, pos,
@@ -1379,7 +1391,9 @@ errout:
  * set the buffer to be dirty, since in data=journalled mode we need
  * to call ext4_handle_dirty_metadata() instead.
  */
-static void zero_new_buffers(struct page *page, unsigned from, unsigned to)
+static void ext4_journalled_zero_new_buffers(handle_t *handle,
+					    struct page *page,
+					    unsigned from, unsigned to)
 {
 	unsigned int block_start = 0, block_end;
 	struct buffer_head *head, *bh;
@@ -1396,7 +1410,7 @@ static void zero_new_buffers(struct page *page, unsigned from, unsigned to)
 					size = min(to, block_end) - start;
 
 					zero_user(page, start, size);
-					set_buffer_uptodate(bh);
+					write_end_fn(handle, bh);
 				}
 				clear_buffer_new(bh);
 			}
@@ -1425,18 +1439,25 @@ static int ext4_journalled_write_end(struct file *file,
 
 	BUG_ON(!ext4_handle_valid(handle));
 
-	if (ext4_has_inline_data(inode))
-		copied = ext4_write_inline_data_end(inode, pos, len,
-						    copied, page);
-	else {
-		if (copied < len) {
-			if (!PageUptodate(page))
-				copied = 0;
-			zero_new_buffers(page, from+copied, to);
+	if (ext4_has_inline_data(inode)) {
+		ret = ext4_write_inline_data_end(inode, pos, len,
+						 copied, page);
+		if (ret < 0) {
+			unlock_page(page);
+			put_page(page);
+			goto errout;
 		}
-
+		copied = ret;
+	} else if (unlikely(copied < len) && !PageUptodate(page)) {
+		copied = 0;
+		ext4_journalled_zero_new_buffers(handle, page, from, to);
+	} else {
+		if (unlikely(copied < len))
+			ext4_journalled_zero_new_buffers(handle, page,
+							 from + copied, to);
 		ret = ext4_walk_page_buffers(handle, page_buffers(page), from,
-					     to, &partial, write_end_fn);
+					     from + copied, &partial,
+					     write_end_fn);
 		if (!partial)
 			SetPageUptodate(page);
 	}
@@ -1462,6 +1483,7 @@ static int ext4_journalled_write_end(struct file *file,
 		 */
 		ext4_orphan_add(handle, inode);
 
+errout:
 	ret2 = ext4_journal_stop(handle);
 	if (!ret)
 		ret = ret2;
@@ -2028,6 +2050,12 @@ static int ext4_writepage(struct page *page,
 	struct ext4_io_submit io_submit;
 	bool keep_towrite = false;
 
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb)))) {
+		ext4_invalidatepage(page, 0, PAGE_SIZE);
+		unlock_page(page);
+		return -EIO;
+	}
+
 	trace_ext4_writepage(page);
 	size = i_size_read(inode);
 	if (page->index == size >> PAGE_SHIFT)
@@ -2193,7 +2221,7 @@ static int mpage_process_page_bufs(struct mpage_da_data *mpd,
 {
 	struct inode *inode = mpd->inode;
 	int err;
-	ext4_lblk_t blocks = (i_size_read(inode) + (1 << inode->i_blkbits) - 1)
+	ext4_lblk_t blocks = (i_size_read(inode) + i_blocksize(inode) - 1)
 							>> inode->i_blkbits;
 
 	do {
@@ -2360,11 +2388,8 @@ static int mpage_map_one_extent(handle_t *handle, struct mpage_da_data *mpd)
 
 	BUG_ON(map->m_len == 0);
 	if (map->m_flags & EXT4_MAP_NEW) {
-		struct block_device *bdev = inode->i_sb->s_bdev;
-		int i;
-
-		for (i = 0; i < map->m_len; i++)
-			unmap_underlying_metadata(bdev, map->m_pblk + i);
+		clean_bdev_aliases(inode->i_sb->s_bdev, map->m_pblk,
+				   map->m_len);
 	}
 	return 0;
 }
@@ -2406,7 +2431,8 @@ static int mpage_map_and_submit_extent(handle_t *handle,
 		if (err < 0) {
 			struct super_block *sb = inode->i_sb;
 
-			if (EXT4_SB(sb)->s_mount_flags & EXT4_MF_FS_ABORTED)
+			if (ext4_forced_shutdown(EXT4_SB(sb)) ||
+			    EXT4_SB(sb)->s_mount_flags & EXT4_MF_FS_ABORTED)
 				goto invalidate_dirty_pages;
 			/*
 			 * Let the uper layers retry transient errors.
@@ -2461,8 +2487,8 @@ update_disksize:
 			disksize = i_size;
 		if (disksize > EXT4_I(inode)->i_disksize)
 			EXT4_I(inode)->i_disksize = disksize;
-		err2 = ext4_mark_inode_dirty(handle, inode);
 		up_write(&EXT4_I(inode)->i_data_sem);
+		err2 = ext4_mark_inode_dirty(handle, inode);
 		if (err2)
 			ext4_error(inode->i_sb,
 				   "Failed to mark inode %lu dirty",
@@ -2628,6 +2654,9 @@ static int ext4_writepages(struct address_space *mapping,
 	struct blk_plug plug;
 	bool give_up_on_write = false;
 
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
+		return -EIO;
+
 	percpu_down_read(&sbi->s_journal_flag_rwsem);
 	trace_ext4_writepages(inode, wbc);
 
@@ -2664,7 +2693,8 @@ static int ext4_writepages(struct address_space *mapping,
 	 * *never* be called, so if that ever happens, we would want
 	 * the stack trace.
 	 */
-	if (unlikely(sbi->s_mount_flags & EXT4_MF_FS_ABORTED)) {
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(mapping->host->i_sb)) ||
+		     sbi->s_mount_flags & EXT4_MF_FS_ABORTED)) {
 		ret = -EROFS;
 		goto out_writepages;
 	}
@@ -2889,9 +2919,13 @@ static int ext4_da_write_begin(struct file *file, struct address_space *mapping,
 	struct inode *inode = mapping->host;
 	handle_t *handle;
 
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
+		return -EIO;
+
 	index = pos >> PAGE_SHIFT;
 
-	if (ext4_nonda_switch(inode->i_sb)) {
+	if (ext4_nonda_switch(inode->i_sb) ||
+	    S_ISLNK(inode->i_mode)) {
 		*fsdata = (void *)FALL_BACK_TO_NONDELALLOC;
 		return ext4_write_begin(file, mapping, pos,
 					len, flags, pagep, fsdata);
@@ -3268,53 +3302,159 @@ static int ext4_releasepage(struct page *page, gfp_t wait)
 }
 
 #ifdef CONFIG_FS_DAX
-/*
- * Get block function for DAX IO and mmap faults. It takes care of converting
- * unwritten extents to written ones and initializes new / converted blocks
- * to zeros.
- */
-int ext4_dax_get_block(struct inode *inode, sector_t iblock,
-		       struct buffer_head *bh_result, int create)
+static int ext4_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
+			    unsigned flags, struct iomap *iomap)
 {
+	unsigned int blkbits = inode->i_blkbits;
+	unsigned long first_block = offset >> blkbits;
+	unsigned long last_block = (offset + length - 1) >> blkbits;
+	struct ext4_map_blocks map;
 	int ret;
 
-	ext4_debug("inode %lu, create flag %d\n", inode->i_ino, create);
-	if (!create)
-		return _ext4_get_block(inode, iblock, bh_result, 0);
+	if (WARN_ON_ONCE(ext4_has_inline_data(inode)))
+		return -ERANGE;
 
-	ret = ext4_get_block_trans(inode, iblock, bh_result,
-				   EXT4_GET_BLOCKS_PRE_IO |
-				   EXT4_GET_BLOCKS_CREATE_ZERO);
-	if (ret < 0)
-		return ret;
+	map.m_lblk = first_block;
+	map.m_len = last_block - first_block + 1;
+
+	if (!(flags & IOMAP_WRITE)) {
+		ret = ext4_map_blocks(NULL, inode, &map, 0);
+	} else {
+		int dio_credits;
+		handle_t *handle;
+		int retries = 0;
 
-	if (buffer_unwritten(bh_result)) {
+		/* Trim mapping request to maximum we can map at once for DIO */
+		if (map.m_len > DIO_MAX_BLOCKS)
+			map.m_len = DIO_MAX_BLOCKS;
+		dio_credits = ext4_chunk_trans_blocks(inode, map.m_len);
+retry:
 		/*
-		 * We are protected by i_mmap_sem or i_mutex 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.
+		 * Either we allocate blocks and then we don't get unwritten
+		 * extent so we have reserved enough credits, or the blocks
+		 * are already allocated and unwritten and in that case
+		 * extent conversion fits in the credits as well.
 		 */
-		ret = ext4_get_block_trans(inode, iblock, bh_result,
-					   EXT4_GET_BLOCKS_CONVERT |
-					   EXT4_GET_BLOCKS_CREATE_ZERO);
-		if (ret < 0)
+		handle = ext4_journal_start(inode, EXT4_HT_MAP_BLOCKS,
+					    dio_credits);
+		if (IS_ERR(handle))
+			return PTR_ERR(handle);
+
+		ret = ext4_map_blocks(handle, inode, &map,
+				      EXT4_GET_BLOCKS_CREATE_ZERO);
+		if (ret < 0) {
+			ext4_journal_stop(handle);
+			if (ret == -ENOSPC &&
+			    ext4_should_retry_alloc(inode->i_sb, &retries))
+				goto retry;
 			return ret;
+		}
+
+		/*
+		 * If we added blocks beyond i_size, we need to make sure they
+		 * will get truncated if we crash before updating i_size in
+		 * ext4_iomap_end(). For faults we don't need to do that (and
+		 * even cannot because for orphan list operations inode_lock is
+		 * required) - if we happen to instantiate block beyond i_size,
+		 * it is because we race with truncate which has already added
+		 * the inode to the orphan list.
+		 */
+		if (!(flags & IOMAP_FAULT) && first_block + map.m_len >
+		    (i_size_read(inode) + (1 << blkbits) - 1) >> blkbits) {
+			int err;
+
+			err = ext4_orphan_add(handle, inode);
+			if (err < 0) {
+				ext4_journal_stop(handle);
+				return err;
+			}
+		}
+		ext4_journal_stop(handle);
 	}
-	/*
-	 * 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.
-	 */
-	clear_buffer_new(bh_result);
+
+	iomap->flags = 0;
+	iomap->bdev = inode->i_sb->s_bdev;
+	iomap->offset = first_block << blkbits;
+
+	if (ret == 0) {
+		iomap->type = IOMAP_HOLE;
+		iomap->blkno = IOMAP_NULL_BLOCK;
+		iomap->length = (u64)map.m_len << blkbits;
+	} else {
+		if (map.m_flags & EXT4_MAP_MAPPED) {
+			iomap->type = IOMAP_MAPPED;
+		} else if (map.m_flags & EXT4_MAP_UNWRITTEN) {
+			iomap->type = IOMAP_UNWRITTEN;
+		} else {
+			WARN_ON_ONCE(1);
+			return -EIO;
+		}
+		iomap->blkno = (sector_t)map.m_pblk << (blkbits - 9);
+		iomap->length = (u64)map.m_len << blkbits;
+	}
+
+	if (map.m_flags & EXT4_MAP_NEW)
+		iomap->flags |= IOMAP_F_NEW;
 	return 0;
 }
-#else
-/* Just define empty function, it will never get called. */
-int ext4_dax_get_block(struct inode *inode, sector_t iblock,
-		       struct buffer_head *bh_result, int create)
+
+static int ext4_iomap_end(struct inode *inode, loff_t offset, loff_t length,
+			  ssize_t written, unsigned flags, struct iomap *iomap)
 {
-	BUG();
-	return 0;
+	int ret = 0;
+	handle_t *handle;
+	int blkbits = inode->i_blkbits;
+	bool truncate = false;
+
+	if (!(flags & IOMAP_WRITE) || (flags & IOMAP_FAULT))
+		return 0;
+
+	handle = ext4_journal_start(inode, EXT4_HT_INODE, 2);
+	if (IS_ERR(handle)) {
+		ret = PTR_ERR(handle);
+		goto orphan_del;
+	}
+	if (ext4_update_inode_size(inode, offset + written))
+		ext4_mark_inode_dirty(handle, inode);
+	/*
+	 * We may need to truncate allocated but not written blocks beyond EOF.
+	 */
+	if (iomap->offset + iomap->length > 
+	    ALIGN(inode->i_size, 1 << blkbits)) {
+		ext4_lblk_t written_blk, end_blk;
+
+		written_blk = (offset + written) >> blkbits;
+		end_blk = (offset + length) >> blkbits;
+		if (written_blk < end_blk && ext4_can_truncate(inode))
+			truncate = true;
+	}
+	/*
+	 * Remove inode from orphan list if we were extending a inode and
+	 * everything went fine.
+	 */
+	if (!truncate && inode->i_nlink &&
+	    !list_empty(&EXT4_I(inode)->i_orphan))
+		ext4_orphan_del(handle, inode);
+	ext4_journal_stop(handle);
+	if (truncate) {
+		ext4_truncate_failed_write(inode);
+orphan_del:
+		/*
+		 * If truncate failed early the inode might still be on the
+		 * orphan list; we need to make sure the inode is removed from
+		 * the orphan list in that case.
+		 */
+		if (inode->i_nlink)
+			ext4_orphan_del(NULL, inode);
+	}
+	return ret;
 }
+
+const struct iomap_ops ext4_iomap_ops = {
+	.iomap_begin		= ext4_iomap_begin,
+	.iomap_end		= ext4_iomap_end,
+};
+
 #endif
 
 static int ext4_end_io_dio(struct kiocb *iocb, loff_t offset,
@@ -3436,20 +3576,8 @@ static ssize_t ext4_direct_IO_write(struct kiocb *iocb, struct iov_iter *iter)
 	iocb->private = NULL;
 	if (overwrite)
 		get_block_func = ext4_dio_get_block_overwrite;
-	else if (IS_DAX(inode)) {
-		/*
-		 * We can avoid zeroing for aligned DAX writes beyond EOF. Other
-		 * writes need zeroing either because they can race with page
-		 * faults or because they use partial blocks.
-		 */
-		if (round_down(offset, 1<<inode->i_blkbits) >= inode->i_size &&
-		    ext4_aligned_io(inode, offset, count))
-			get_block_func = ext4_dio_get_block;
-		else
-			get_block_func = ext4_dax_get_block;
-		dio_flags = DIO_LOCKING;
-	} else if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS) ||
-		   round_down(offset, 1 << inode->i_blkbits) >= inode->i_size) {
+	else if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS) ||
+		   round_down(offset, i_blocksize(inode)) >= inode->i_size) {
 		get_block_func = ext4_dio_get_block;
 		dio_flags = DIO_LOCKING | DIO_SKIP_HOLES;
 	} else if (is_sync_kiocb(iocb)) {
@@ -3462,14 +3590,9 @@ static ssize_t ext4_direct_IO_write(struct kiocb *iocb, struct iov_iter *iter)
 #ifdef CONFIG_EXT4_FS_ENCRYPTION
 	BUG_ON(ext4_encrypted_inode(inode) && S_ISREG(inode->i_mode));
 #endif
-	if (IS_DAX(inode)) {
-		ret = dax_do_io(iocb, inode, iter, get_block_func,
-				ext4_end_io_dio, dio_flags);
-	} else
-		ret = __blockdev_direct_IO(iocb, inode,
-					   inode->i_sb->s_bdev, iter,
-					   get_block_func,
-					   ext4_end_io_dio, NULL, dio_flags);
+	ret = __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev, iter,
+				   get_block_func, ext4_end_io_dio, NULL,
+				   dio_flags);
 
 	if (ret > 0 && !overwrite && ext4_test_inode_state(inode,
 						EXT4_STATE_DIO_UNWRITTEN)) {
@@ -3538,6 +3661,7 @@ static ssize_t ext4_direct_IO_read(struct kiocb *iocb, struct iov_iter *iter)
 {
 	struct address_space *mapping = iocb->ki_filp->f_mapping;
 	struct inode *inode = mapping->host;
+	size_t count = iov_iter_count(iter);
 	ssize_t ret;
 
 	/*
@@ -3546,19 +3670,12 @@ static ssize_t ext4_direct_IO_read(struct kiocb *iocb, struct iov_iter *iter)
 	 * we are protected against page writeback as well.
 	 */
 	inode_lock_shared(inode);
-	if (IS_DAX(inode)) {
-		ret = dax_do_io(iocb, inode, iter, ext4_dio_get_block, NULL, 0);
-	} else {
-		size_t count = iov_iter_count(iter);
-
-		ret = filemap_write_and_wait_range(mapping, iocb->ki_pos,
-						   iocb->ki_pos + count);
-		if (ret)
-			goto out_unlock;
-		ret = __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev,
-					   iter, ext4_dio_get_block,
-					   NULL, NULL, 0);
-	}
+	ret = filemap_write_and_wait_range(mapping, iocb->ki_pos,
+					   iocb->ki_pos + count);
+	if (ret)
+		goto out_unlock;
+	ret = __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev,
+				   iter, ext4_dio_get_block, NULL, NULL, 0);
 out_unlock:
 	inode_unlock_shared(inode);
 	return ret;
@@ -3587,6 +3704,10 @@ static ssize_t ext4_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 	if (ext4_has_inline_data(inode))
 		return 0;
 
+	/* DAX uses iomap path now */
+	if (WARN_ON_ONCE(IS_DAX(inode)))
+		return 0;
+
 	trace_ext4_direct_IO_enter(inode, offset, count, iov_iter_rw(iter));
 	if (iov_iter_rw(iter) == READ)
 		ret = ext4_direct_IO_read(iocb, iter);
@@ -3615,6 +3736,13 @@ static int ext4_journalled_set_page_dirty(struct page *page)
 	return __set_page_dirty_nobuffers(page);
 }
 
+static int ext4_set_page_dirty(struct page *page)
+{
+	WARN_ON_ONCE(!PageLocked(page) && !PageDirty(page));
+	WARN_ON_ONCE(!page_has_buffers(page));
+	return __set_page_dirty_buffers(page);
+}
+
 static const struct address_space_operations ext4_aops = {
 	.readpage		= ext4_readpage,
 	.readpages		= ext4_readpages,
@@ -3622,6 +3750,7 @@ static const struct address_space_operations ext4_aops = {
 	.writepages		= ext4_writepages,
 	.write_begin		= ext4_write_begin,
 	.write_end		= ext4_write_end,
+	.set_page_dirty		= ext4_set_page_dirty,
 	.bmap			= ext4_bmap,
 	.invalidatepage		= ext4_invalidatepage,
 	.releasepage		= ext4_releasepage,
@@ -3654,6 +3783,7 @@ static const struct address_space_operations ext4_da_aops = {
 	.writepages		= ext4_writepages,
 	.write_begin		= ext4_da_write_begin,
 	.write_end		= ext4_da_write_end,
+	.set_page_dirty		= ext4_set_page_dirty,
 	.bmap			= ext4_bmap,
 	.invalidatepage		= ext4_da_invalidatepage,
 	.releasepage		= ext4_releasepage,
@@ -3743,7 +3873,8 @@ static int __ext4_block_zero_page_range(handle_t *handle,
 			/* We expect the key to be set. */
 			BUG_ON(!fscrypt_has_encryption_key(inode));
 			BUG_ON(blocksize != PAGE_SIZE);
-			WARN_ON_ONCE(fscrypt_decrypt_page(page));
+			WARN_ON_ONCE(fscrypt_decrypt_page(page->mapping->host,
+						page, PAGE_SIZE, 0, page->index));
 		}
 	}
 	if (ext4_should_journal_data(inode)) {
@@ -3792,8 +3923,10 @@ static int ext4_block_zero_page_range(handle_t *handle,
 	if (length > max || length < 0)
 		length = max;
 
-	if (IS_DAX(inode))
-		return dax_zero_page_range(inode, from, length, ext4_get_block);
+	if (IS_DAX(inode)) {
+		return iomap_zero_range(inode, from, length, NULL,
+					&ext4_iomap_ops);
+	}
 	return __ext4_block_zero_page_range(handle, mapping, from, length);
 }
 
@@ -3811,6 +3944,10 @@ static int ext4_block_truncate_page(handle_t *handle,
 	unsigned blocksize;
 	struct inode *inode = mapping->host;
 
+	/* If we are processing an encrypted inode during orphan list handling */
+	if (ext4_encrypted_inode(inode) && !fscrypt_has_encryption_key(inode))
+		return 0;
+
 	blocksize = inode->i_sb->s_blocksize;
 	length = blocksize - (offset & (blocksize - 1));
 
@@ -4026,7 +4163,7 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length)
 	if (IS_SYNC(inode))
 		ext4_handle_sync(handle);
 
-	inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
+	inode->i_mtime = inode->i_ctime = current_time(inode);
 	ext4_mark_inode_dirty(handle, inode);
 out_stop:
 	ext4_journal_stop(handle);
@@ -4091,10 +4228,11 @@ int ext4_inode_attach_jinode(struct inode *inode)
  * that's fine - as long as they are linked from the inode, the post-crash
  * ext4_truncate() run will find them and release them.
  */
-void ext4_truncate(struct inode *inode)
+int ext4_truncate(struct inode *inode)
 {
 	struct ext4_inode_info *ei = EXT4_I(inode);
 	unsigned int credits;
+	int err = 0;
 	handle_t *handle;
 	struct address_space *mapping = inode->i_mapping;
 
@@ -4108,7 +4246,7 @@ void ext4_truncate(struct inode *inode)
 	trace_ext4_truncate_enter(inode);
 
 	if (!ext4_can_truncate(inode))
-		return;
+		return 0;
 
 	ext4_clear_inode_flag(inode, EXT4_INODE_EOFBLOCKS);
 
@@ -4118,15 +4256,17 @@ void ext4_truncate(struct inode *inode)
 	if (ext4_has_inline_data(inode)) {
 		int has_inline = 1;
 
-		ext4_inline_data_truncate(inode, &has_inline);
+		err = ext4_inline_data_truncate(inode, &has_inline);
+		if (err)
+			return err;
 		if (has_inline)
-			return;
+			return 0;
 	}
 
 	/* If we zero-out tail of the page, we have to create jinode for jbd2 */
 	if (inode->i_size & (inode->i_sb->s_blocksize - 1)) {
 		if (ext4_inode_attach_jinode(inode) < 0)
-			return;
+			return 0;
 	}
 
 	if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
@@ -4135,10 +4275,8 @@ void ext4_truncate(struct inode *inode)
 		credits = ext4_blocks_for_truncate(inode);
 
 	handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, credits);
-	if (IS_ERR(handle)) {
-		ext4_std_error(inode->i_sb, PTR_ERR(handle));
-		return;
-	}
+	if (IS_ERR(handle))
+		return PTR_ERR(handle);
 
 	if (inode->i_size & (inode->i_sb->s_blocksize - 1))
 		ext4_block_truncate_page(handle, mapping, inode->i_size);
@@ -4152,7 +4290,8 @@ void ext4_truncate(struct inode *inode)
 	 * Implication: the file must always be in a sane, consistent
 	 * truncatable state while each transaction commits.
 	 */
-	if (ext4_orphan_add(handle, inode))
+	err = ext4_orphan_add(handle, inode);
+	if (err)
 		goto out_stop;
 
 	down_write(&EXT4_I(inode)->i_data_sem);
@@ -4160,11 +4299,13 @@ void ext4_truncate(struct inode *inode)
 	ext4_discard_preallocations(inode);
 
 	if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
-		ext4_ext_truncate(handle, inode);
+		err = ext4_ext_truncate(handle, inode);
 	else
 		ext4_ind_truncate(handle, inode);
 
 	up_write(&ei->i_data_sem);
+	if (err)
+		goto out_stop;
 
 	if (IS_SYNC(inode))
 		ext4_handle_sync(handle);
@@ -4180,11 +4321,12 @@ out_stop:
 	if (inode->i_nlink)
 		ext4_orphan_del(handle, inode);
 
-	inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
+	inode->i_mtime = inode->i_ctime = current_time(inode);
 	ext4_mark_inode_dirty(handle, inode);
 	ext4_journal_stop(handle);
 
 	trace_ext4_truncate_exit(inode);
+	return err;
 }
 
 /*
@@ -4352,7 +4494,9 @@ void ext4_set_inode_flags(struct inode *inode)
 		new_fl |= S_NOATIME;
 	if (flags & EXT4_DIRSYNC_FL)
 		new_fl |= S_DIRSYNC;
-	if (test_opt(inode->i_sb, DAX) && S_ISREG(inode->i_mode))
+	if (test_opt(inode->i_sb, DAX) && S_ISREG(inode->i_mode) &&
+	    !ext4_should_journal_data(inode) && !ext4_has_inline_data(inode) &&
+	    !ext4_encrypted_inode(inode))
 		new_fl |= S_DAX;
 	inode_set_flags(inode, new_fl,
 			S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC|S_DAX);
@@ -4411,7 +4555,9 @@ static inline void ext4_iget_extra_inode(struct inode *inode,
 {
 	__le32 *magic = (void *)raw_inode +
 			EXT4_GOOD_OLD_INODE_SIZE + ei->i_extra_isize;
-	if (*magic == cpu_to_le32(EXT4_XATTR_MAGIC)) {
+	if (EXT4_GOOD_OLD_INODE_SIZE + ei->i_extra_isize + sizeof(__le32) <=
+	    EXT4_INODE_SIZE(inode->i_sb) &&
+	    *magic == cpu_to_le32(EXT4_XATTR_MAGIC)) {
 		ext4_set_inode_state(inode, EXT4_STATE_XATTR);
 		ext4_find_inline_data_nolock(inode);
 	} else
@@ -4434,6 +4580,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
 	struct inode *inode;
 	journal_t *journal = EXT4_SB(sb)->s_journal;
 	long ret;
+	loff_t size;
 	int block;
 	uid_t i_uid;
 	gid_t i_gid;
@@ -4456,10 +4603,12 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
 	if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE) {
 		ei->i_extra_isize = le16_to_cpu(raw_inode->i_extra_isize);
 		if (EXT4_GOOD_OLD_INODE_SIZE + ei->i_extra_isize >
-		    EXT4_INODE_SIZE(inode->i_sb)) {
-			EXT4_ERROR_INODE(inode, "bad extra_isize (%u != %u)",
-				EXT4_GOOD_OLD_INODE_SIZE + ei->i_extra_isize,
-				EXT4_INODE_SIZE(inode->i_sb));
+			EXT4_INODE_SIZE(inode->i_sb) ||
+		    (ei->i_extra_isize & 3)) {
+			EXT4_ERROR_INODE(inode,
+					 "bad extra_isize %u (inode size %u)",
+					 ei->i_extra_isize,
+					 EXT4_INODE_SIZE(inode->i_sb));
 			ret = -EFSCORRUPTED;
 			goto bad_inode;
 		}
@@ -4534,6 +4683,11 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
 		ei->i_file_acl |=
 			((__u64)le16_to_cpu(raw_inode->i_file_acl_high)) << 32;
 	inode->i_size = ext4_isize(raw_inode);
+	if ((size = i_size_read(inode)) < 0) {
+		EXT4_ERROR_INODE(inode, "bad i_size value: %lld", size);
+		ret = -EFSCORRUPTED;
+		goto bad_inode;
+	}
 	ei->i_disksize = inode->i_size;
 #ifdef CONFIG_QUOTA
 	ei->i_reserved_quota = 0;
@@ -4577,6 +4731,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
 	if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE) {
 		if (ei->i_extra_isize == 0) {
 			/* The extra space is currently unused. Use it. */
+			BUILD_BUG_ON(sizeof(struct ext4_inode) & 3);
 			ei->i_extra_isize = sizeof(struct ext4_inode) -
 					    EXT4_GOOD_OLD_INODE_SIZE;
 		} else {
@@ -5024,7 +5179,7 @@ static void ext4_wait_for_tail_page_commit(struct inode *inode)
 	 * do. We do the check mainly to optimize the common PAGE_SIZE ==
 	 * blocksize case
 	 */
-	if (offset > PAGE_SIZE - (1 << inode->i_blkbits))
+	if (offset > PAGE_SIZE - i_blocksize(inode))
 		return;
 	while (1) {
 		page = find_lock_page(inode->i_mapping,
@@ -5078,6 +5233,9 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
 	int orphan = 0;
 	const unsigned int ia_valid = attr->ia_valid;
 
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
+		return -EIO;
+
 	error = setattr_prepare(dentry, attr);
 	if (error)
 		return error;
@@ -5154,7 +5312,7 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
 			 * update c/mtime in shrink case below
 			 */
 			if (!shrink) {
-				inode->i_mtime = ext4_current_time(inode);
+				inode->i_mtime = current_time(inode);
 				inode->i_ctime = inode->i_mtime;
 			}
 			down_write(&EXT4_I(inode)->i_data_sem);
@@ -5199,12 +5357,15 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
 		 * in data=journal mode to make pages freeable.
 		 */
 		truncate_pagecache(inode, inode->i_size);
-		if (shrink)
-			ext4_truncate(inode);
+		if (shrink) {
+			rc = ext4_truncate(inode);
+			if (rc)
+				error = rc;
+		}
 		up_write(&EXT4_I(inode)->i_mmap_sem);
 	}
 
-	if (!rc) {
+	if (!error) {
 		setattr_copy(inode, attr);
 		mark_inode_dirty(inode);
 	}
@@ -5216,7 +5377,7 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
 	if (orphan && inode->i_nlink)
 		ext4_orphan_del(NULL, inode);
 
-	if (!rc && (ia_valid & ATTR_MODE))
+	if (!error && (ia_valid & ATTR_MODE))
 		rc = posix_acl_chmod(inode, inode->i_mode);
 
 err_out:
@@ -5226,20 +5387,55 @@ err_out:
 	return error;
 }
 
-int ext4_getattr(struct vfsmount *mnt, struct dentry *dentry,
-		 struct kstat *stat)
+int ext4_getattr(const struct path *path, struct kstat *stat,
+		 u32 request_mask, unsigned int query_flags)
 {
-	struct inode *inode;
-	unsigned long long delalloc_blocks;
+	struct inode *inode = d_inode(path->dentry);
+	struct ext4_inode *raw_inode;
+	struct ext4_inode_info *ei = EXT4_I(inode);
+	unsigned int flags;
+
+	if (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;
+	}
+
+	flags = ei->i_flags & EXT4_FL_USER_VISIBLE;
+	if (flags & EXT4_APPEND_FL)
+		stat->attributes |= STATX_ATTR_APPEND;
+	if (flags & EXT4_COMPR_FL)
+		stat->attributes |= STATX_ATTR_COMPRESSED;
+	if (flags & EXT4_ENCRYPT_FL)
+		stat->attributes |= STATX_ATTR_ENCRYPTED;
+	if (flags & EXT4_IMMUTABLE_FL)
+		stat->attributes |= STATX_ATTR_IMMUTABLE;
+	if (flags & EXT4_NODUMP_FL)
+		stat->attributes |= STATX_ATTR_NODUMP;
+
+	stat->attributes_mask |= (STATX_ATTR_APPEND |
+				  STATX_ATTR_COMPRESSED |
+				  STATX_ATTR_ENCRYPTED |
+				  STATX_ATTR_IMMUTABLE |
+				  STATX_ATTR_NODUMP);
 
-	inode = d_inode(dentry);
 	generic_fillattr(inode, stat);
+	return 0;
+}
+
+int ext4_file_getattr(const struct path *path, struct kstat *stat,
+		      u32 request_mask, unsigned int query_flags)
+{
+	struct inode *inode = d_inode(path->dentry);
+	u64 delalloc_blocks;
+
+	ext4_getattr(path, stat, request_mask, query_flags);
 
 	/*
 	 * If there is inline data in the inode, the inode will normally not
 	 * have data blocks allocated (it may have an external xattr block).
 	 * Report at least one sector for such files, so tools like tar, rsync,
-	 * others doen't incorrectly think the file is completely sparse.
+	 * others don't incorrectly think the file is completely sparse.
 	 */
 	if (unlikely(ext4_has_inline_data(inode)))
 		stat->blocks += (stat->size + 511) >> 9;
@@ -5361,6 +5557,9 @@ int ext4_mark_iloc_dirty(handle_t *handle,
 {
 	int err = 0;
 
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
+		return -EIO;
+
 	if (IS_I_VERSION(inode))
 		inode_inc_iversion(inode);
 
@@ -5384,6 +5583,9 @@ ext4_reserve_inode_write(handle_t *handle, struct inode *inode,
 {
 	int err;
 
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
+		return -EIO;
+
 	err = ext4_get_inode_loc(inode, iloc);
 	if (!err) {
 		BUFFER_TRACE(iloc->bh, "get_write_access");
@@ -5455,18 +5657,20 @@ int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode)
 	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 &&
+	if (EXT4_I(inode)->i_extra_isize < sbi->s_want_extra_isize &&
 	    !ext4_test_inode_state(inode, EXT4_STATE_NO_EXPAND)) {
 		/*
-		 * We need extra buffer credits since we may write into EA block
+		 * In nojournal mode, we can immediately attempt to expand
+		 * the inode.  When journaled, we first need to obtain extra
+		 * buffer credits since we may write into the EA block
 		 * with this same handle. If journal_extend fails, then it will
 		 * only result in a minor loss of functionality for that inode.
 		 * If this is felt to be critical, then e2fsck should be run to
 		 * force a large enough s_min_extra_isize.
 		 */
-		if ((jbd2_journal_extend(handle,
-			     EXT4_DATA_TRANS_BLOCKS(inode->i_sb))) == 0) {
+		if (!ext4_handle_valid(handle) ||
+		    jbd2_journal_extend(handle,
+			     EXT4_DATA_TRANS_BLOCKS(inode->i_sb)) == 0) {
 			ret = ext4_expand_extra_isize(inode,
 						      sbi->s_want_extra_isize,
 						      iloc, handle);
@@ -5620,6 +5824,11 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val)
 		ext4_clear_inode_flag(inode, EXT4_INODE_JOURNAL_DATA);
 	}
 	ext4_set_aops(inode);
+	/*
+	 * Update inode->i_flags after EXT4_INODE_JOURNAL_DATA was updated.
+	 * E.g. S_DAX may get cleared / set.
+	 */
+	ext4_set_inode_flags(inode);
 
 	jbd2_journal_unlock_updates(journal);
 	percpu_up_write(&sbi->s_journal_flag_rwsem);
@@ -5647,8 +5856,9 @@ static int ext4_bh_unmapped(handle_t *handle, struct buffer_head *bh)
 	return !buffer_mapped(bh);
 }
 
-int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
+int ext4_page_mkwrite(struct vm_fault *vmf)
 {
+	struct vm_area_struct *vma = vmf->vma;
 	struct page *page = vmf->page;
 	loff_t size;
 	unsigned long len;
@@ -5738,13 +5948,13 @@ out:
 	return ret;
 }
 
-int ext4_filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
+int ext4_filemap_fault(struct vm_fault *vmf)
 {
-	struct inode *inode = file_inode(vma->vm_file);
+	struct inode *inode = file_inode(vmf->vma->vm_file);
 	int err;
 
 	down_read(&EXT4_I(inode)->i_mmap_sem);
-	err = filemap_fault(vma, vmf);
+	err = filemap_fault(vmf);
 	up_read(&EXT4_I(inode)->i_mmap_sem);
 
 	return err;