[PATCH -next v5 17/32] ext4: implement mmap path using iomap

From: Zhang Yi <[email protected]>

Introduce ext4_iomap_page_mkwrite() to implement the mmap iomap path
for ext4. The heavy lifting is delegated to iomap_page_mkwrite(), which
only requires ext4_iomap_buffered_write_ops and
ext4_iomap_buffered_da_write_ops to allocate and map blocks.

Note that the lock ordering between folio lock and transaction start in
this path is reversed compared to the buffer_head buffered write path.
The lock ordering documentation in super.c has been updated accordingly.

Signed-off-by: Zhang Yi <[email protected]>
Reviewed-by: Ojaswin Mujoo <[email protected]>
Reviewed-by: Jan Kara <[email protected]>
---
 fs/ext4/inode.c | 32 +++++++++++++++++++++++++++++++-
 fs/ext4/super.c |  8 ++++++--
 2 files changed, 37 insertions(+), 3 deletions(-)

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 0b3e54e12b78..a05445625895 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -4027,7 +4027,7 @@ static int ext4_iomap_buffered_do_write_begin(struct inode *inode,
 		return -ERANGE;
 	if (WARN_ON_ONCE(!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
 		return -EINVAL;
-	if (WARN_ON_ONCE(!(flags & IOMAP_WRITE)))
+	if (WARN_ON_ONCE(!(flags & (IOMAP_WRITE | IOMAP_FAULT))))
 		return -EINVAL;
 
 	map_flags = delalloc ? EXT4_GET_BLOCKS_DELALLOC_RESERVE :
@@ -4085,6 +4085,14 @@ static int ext4_iomap_buffered_da_write_end(struct inode *inode, loff_t offset,
 	if (iomap->type != IOMAP_DELALLOC || !(iomap->flags & IOMAP_F_NEW))
 		return 0;
 
+	/*
+	 * iomap_page_mkwrite() will never fail in a way that requires delalloc
+	 * extents that it allocated to be revoked.  Hence never try to release
+	 * them here.
+	 */
+	if (flags & IOMAP_FAULT)
+		return 0;
+
 	/* Nothing to do if we've written the entire delalloc extent */
 	start_byte = iomap_last_written_block(inode, offset, written);
 	end_byte = round_up(offset + length, i_blocksize(inode));
@@ -7296,6 +7304,23 @@ static int ext4_block_page_mkwrite(struct inode *inode, struct folio *folio,
 	return ret;
 }
 
+static vm_fault_t ext4_iomap_page_mkwrite(struct vm_fault *vmf)
+{
+	struct inode *inode = file_inode(vmf->vma->vm_file);
+	const struct iomap_ops *iomap_ops;
+
+	/*
+	 * ext4_nonda_switch() could writeback this folio, so have to
+	 * call it before lock folio.
+	 */
+	if (test_opt(inode->i_sb, DELALLOC) && !ext4_nonda_switch(inode->i_sb))
+		iomap_ops = &ext4_iomap_buffered_da_write_ops;
+	else
+		iomap_ops = &ext4_iomap_buffered_write_ops;
+
+	return iomap_page_mkwrite(vmf, iomap_ops, NULL);
+}
+
 vm_fault_t ext4_page_mkwrite(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
@@ -7318,6 +7343,11 @@ vm_fault_t ext4_page_mkwrite(struct vm_fault *vmf)
 
 	filemap_invalidate_lock_shared(mapping);
 
+	if (ext4_inode_buffered_iomap(inode)) {
+		ret = ext4_iomap_page_mkwrite(vmf);
+		goto out;
+	}
+
 	err = ext4_convert_inline_data(inode);
 	if (err)
 		goto out_ret;
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 6d2d323604f9..1c2395aa1d53 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -100,8 +100,12 @@ static const struct fs_parameter_spec ext4_param_specs[];
  * Lock ordering
  *
  * page fault path:
- * mmap_lock -> sb_start_pagefault -> invalidate_lock (r) -> transaction start
- *   -> page lock -> i_data_sem (rw)
+ * - buffer_head path:
+ *   mmap_lock -> sb_start_pagefault -> invalidate_lock (r) ->
+ *     transaction start -> folio lock -> i_data_sem (rw)
+ * - iomap path:
+ *   mmap_lock -> sb_start_pagefault -> invalidate_lock (r) ->
+ *     folio lock -> transaction start -> i_data_sem (rw)
  *
  * buffered write path:
  * sb_start_write -> i_rwsem (w) -> mmap_lock
-- 
2.52.0