Merge branch 'devx-async' into k.o/for-next

Yishai Hadas says:

Enable DEVX asynchronous query commands

This series enables querying a DEVX object in an asynchronous mode.

The userspace application won't block when calling the firmware and it will be
able to get the response back once that it will be ready.

To enable the above functionality:

- DEVX asynchronous command completion FD object was introduced.
- The applicable file operations were implemented to enable using it by
  the user application.
- Query asynchronous method was added to the DEVX object, it will call the
  firmware asynchronously and manages the response on the given input FD.
- Hot unplug support was added for the FD to work properly upon
  unbind/disassociate.
- mlx5 core fence for asynchronous commands was implemented and used to
  prevent racing upon unbind/disassociate.

This branch is based on mlx5-next & v5.0-rc2 due to dependencies, from
git://git.kernel.org/pub/scm/linux/kernel/git/mellanox/linux

* branch 'devx-async':
  IB/mlx5: Implement DEVX hot unplug for async command FD
  IB/mlx5: Implement the file ops of DEVX async command FD
  IB/mlx5: Introduce async DEVX obj query API
  IB/mlx5: Introduce MLX5_IB_OBJECT_DEVX_ASYNC_CMD_FD

Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

1 files changed, 43 insertions, 6 deletions

diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index fab9443f6a42..9c8e1734429c 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -3221,6 +3221,26 @@ static void btrfs_double_inode_lock(struct inode *inode1, struct inode *inode2)
 	inode_lock_nested(inode2, I_MUTEX_CHILD);
 }
 
+static void btrfs_double_extent_unlock(struct inode *inode1, u64 loff1,
+				       struct inode *inode2, u64 loff2, u64 len)
+{
+	unlock_extent(&BTRFS_I(inode1)->io_tree, loff1, loff1 + len - 1);
+	unlock_extent(&BTRFS_I(inode2)->io_tree, loff2, loff2 + len - 1);
+}
+
+static void btrfs_double_extent_lock(struct inode *inode1, u64 loff1,
+				     struct inode *inode2, u64 loff2, u64 len)
+{
+	if (inode1 < inode2) {
+		swap(inode1, inode2);
+		swap(loff1, loff2);
+	} else if (inode1 == inode2 && loff2 < loff1) {
+		swap(loff1, loff2);
+	}
+	lock_extent(&BTRFS_I(inode1)->io_tree, loff1, loff1 + len - 1);
+	lock_extent(&BTRFS_I(inode2)->io_tree, loff2, loff2 + len - 1);
+}
+
 static int btrfs_extent_same_range(struct inode *src, u64 loff, u64 olen,
 				   struct inode *dst, u64 dst_loff)
 {
@@ -3242,11 +3262,12 @@ static int btrfs_extent_same_range(struct inode *src, u64 loff, u64 olen,
 		return -EINVAL;
 
 	/*
-	 * Lock destination range to serialize with concurrent readpages().
+	 * Lock destination range to serialize with concurrent readpages() and
+	 * source range to serialize with relocation.
 	 */
-	lock_extent(&BTRFS_I(dst)->io_tree, dst_loff, dst_loff + len - 1);
+	btrfs_double_extent_lock(src, loff, dst, dst_loff, len);
 	ret = btrfs_clone(src, dst, loff, olen, len, dst_loff, 1);
-	unlock_extent(&BTRFS_I(dst)->io_tree, dst_loff, dst_loff + len - 1);
+	btrfs_double_extent_unlock(src, loff, dst, dst_loff, len);
 
 	return ret;
 }
@@ -3905,17 +3926,33 @@ static noinline int btrfs_clone_files(struct file *file, struct file *file_src,
 		len = ALIGN(src->i_size, bs) - off;
 
 	if (destoff > inode->i_size) {
+		const u64 wb_start = ALIGN_DOWN(inode->i_size, bs);
+
 		ret = btrfs_cont_expand(inode, inode->i_size, destoff);
 		if (ret)
 			return ret;
+		/*
+		 * We may have truncated the last block if the inode's size is
+		 * not sector size aligned, so we need to wait for writeback to
+		 * complete before proceeding further, otherwise we can race
+		 * with cloning and attempt to increment a reference to an
+		 * extent that no longer exists (writeback completed right after
+		 * we found the previous extent covering eof and before we
+		 * attempted to increment its reference count).
+		 */
+		ret = btrfs_wait_ordered_range(inode, wb_start,
+					       destoff - wb_start);
+		if (ret)
+			return ret;
 	}
 
 	/*
-	 * Lock destination range to serialize with concurrent readpages().
+	 * Lock destination range to serialize with concurrent readpages() and
+	 * source range to serialize with relocation.
 	 */
-	lock_extent(&BTRFS_I(inode)->io_tree, destoff, destoff + len - 1);
+	btrfs_double_extent_lock(src, off, inode, destoff, len);
 	ret = btrfs_clone(src, inode, off, olen, len, destoff, 0);
-	unlock_extent(&BTRFS_I(inode)->io_tree, destoff, destoff + len - 1);
+	btrfs_double_extent_unlock(src, off, inode, destoff, len);
 	/*
 	 * Truncate page cache pages so that future reads will see the cloned
 	 * data immediately and not the previous data.