mm, dax: enable filesystems to trigger dev_pagemap ->page_free callbacks

In order to resolve collisions between filesystem operations and DMA to
DAX mapped pages we need a callback when DMA completes. With a callback
we can hold off filesystem operations while DMA is in-flight and then
resume those operations when the last put_page() occurs on a DMA page.

Recall that the 'struct page' entries for DAX memory are created with
devm_memremap_pages(). That routine arranges for the pages to be
allocated, but never onlined, so a DAX page is DMA-idle when its
reference count reaches one.

Also recall that the HMM sub-system added infrastructure to trap the
page-idle (2-to-1 reference count) transition of the pages allocated by
devm_memremap_pages() and trigger a callback via the 'struct
dev_pagemap' associated with the page range. Whereas the HMM callbacks
are going to a device driver to manage bounce pages in device-memory in
the filesystem-dax case we will call back to filesystem specified
callback.

Since the callback is not known at devm_memremap_pages() time we arrange
for the filesystem to install it at mount time. No functional changes
are expected as this only registers a nop handler for the ->page_free()
event for device-mapped pages.

Cc: Michal Hocko <mhocko@suse.com>
Reviewed-by: "Jérôme Glisse" <jglisse@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>

1 files changed, 10 insertions, 10 deletions

diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 93588ea3d3d2..ef7dd7148c0b 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -724,7 +724,7 @@ xfs_close_devices(
 
 		xfs_free_buftarg(mp, mp->m_logdev_targp);
 		xfs_blkdev_put(logdev);
-		fs_put_dax(dax_logdev);
+		fs_dax_release(dax_logdev, mp);
 	}
 	if (mp->m_rtdev_targp) {
 		struct block_device *rtdev = mp->m_rtdev_targp->bt_bdev;
@@ -732,10 +732,10 @@ xfs_close_devices(
 
 		xfs_free_buftarg(mp, mp->m_rtdev_targp);
 		xfs_blkdev_put(rtdev);
-		fs_put_dax(dax_rtdev);
+		fs_dax_release(dax_rtdev, mp);
 	}
 	xfs_free_buftarg(mp, mp->m_ddev_targp);
-	fs_put_dax(dax_ddev);
+	fs_dax_release(dax_ddev, mp);
 }
 
 /*
@@ -753,9 +753,9 @@ xfs_open_devices(
 	struct xfs_mount	*mp)
 {
 	struct block_device	*ddev = mp->m_super->s_bdev;
-	struct dax_device	*dax_ddev = fs_dax_get_by_bdev(ddev);
-	struct dax_device	*dax_logdev = NULL, *dax_rtdev = NULL;
+	struct dax_device	*dax_ddev = fs_dax_claim_bdev(ddev, mp);
 	struct block_device	*logdev = NULL, *rtdev = NULL;
+	struct dax_device	*dax_logdev = NULL, *dax_rtdev = NULL;
 	int			error;
 
 	/*
@@ -765,7 +765,7 @@ xfs_open_devices(
 		error = xfs_blkdev_get(mp, mp->m_logname, &logdev);
 		if (error)
 			goto out;
-		dax_logdev = fs_dax_get_by_bdev(logdev);
+		dax_logdev = fs_dax_claim_bdev(logdev, mp);
 	}
 
 	if (mp->m_rtname) {
@@ -779,7 +779,7 @@ xfs_open_devices(
 			error = -EINVAL;
 			goto out_close_rtdev;
 		}
-		dax_rtdev = fs_dax_get_by_bdev(rtdev);
+		dax_rtdev = fs_dax_claim_bdev(rtdev, mp);
 	}
 
 	/*
@@ -813,14 +813,14 @@ xfs_open_devices(
 	xfs_free_buftarg(mp, mp->m_ddev_targp);
  out_close_rtdev:
 	xfs_blkdev_put(rtdev);
-	fs_put_dax(dax_rtdev);
+	fs_dax_release(dax_rtdev, mp);
  out_close_logdev:
 	if (logdev && logdev != ddev) {
 		xfs_blkdev_put(logdev);
-		fs_put_dax(dax_logdev);
+		fs_dax_release(dax_logdev, mp);
 	}
  out:
-	fs_put_dax(dax_ddev);
+	fs_dax_release(dax_ddev, mp);
 	return error;
 }