Merge branch 'iommufd/arm-smmuv3-nested' of iommu/linux into iommufd for-next

Common SMMUv3 patches for the following patches adding nesting, shared
branch with the iommu tree.

* 'iommufd/arm-smmuv3-nested' of ssh://gitolite.kernel.org/pub/scm/linux/kernel/git/iommu/linux:
  iommu/arm-smmu-v3: Expose the arm_smmu_attach interface
  iommu/arm-smmu-v3: Implement IOMMU_HWPT_ALLOC_NEST_PARENT
  iommu/arm-smmu-v3: Support IOMMU_GET_HW_INFO via struct arm_smmu_hw_info
  iommu/arm-smmu-v3: Report IOMMU_CAP_ENFORCE_CACHE_COHERENCY for CANWBS
  ACPI/IORT: Support CANWBS memory access flag
  ACPICA: IORT: Update for revision E.f
  vfio: Remove VFIO_TYPE1_NESTING_IOMMU
  ...

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

1 files changed, 23 insertions, 14 deletions

diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index a680e5b82672..6b119a7a324f 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -1280,14 +1280,17 @@ xfs_inode_clear_eofblocks_tag(
 }
 
 /*
- * Set ourselves up to free CoW blocks from this file.  If it's already clean
- * then we can bail out quickly, but otherwise we must back off if the file
- * is undergoing some kind of write.
+ * Prepare to free COW fork blocks from an inode.
  */
 static bool
 xfs_prep_free_cowblocks(
-	struct xfs_inode	*ip)
+	struct xfs_inode	*ip,
+	struct xfs_icwalk	*icw)
 {
+	bool			sync;
+
+	sync = icw && (icw->icw_flags & XFS_ICWALK_FLAG_SYNC);
+
 	/*
 	 * Just clear the tag if we have an empty cow fork or none at all. It's
 	 * possible the inode was fully unshared since it was originally tagged.
@@ -1299,16 +1302,22 @@ xfs_prep_free_cowblocks(
 	}
 
 	/*
-	 * If the mapping is dirty or under writeback we cannot touch the
-	 * CoW fork.  Leave it alone if we're in the midst of a directio.
+	 * A cowblocks trim of an inode can have a significant effect on
+	 * fragmentation even when a reasonable COW extent size hint is set.
+	 * Therefore, we prefer to not process cowblocks unless they are clean
+	 * and idle. We can never process a cowblocks inode that is dirty or has
+	 * in-flight I/O under any circumstances, because outstanding writeback
+	 * or dio expects targeted COW fork blocks exist through write
+	 * completion where they can be remapped into the data fork.
+	 *
+	 * Therefore, the heuristic used here is to never process inodes
+	 * currently opened for write from background (i.e. non-sync) scans. For
+	 * sync scans, use the pagecache/dio state of the inode to ensure we
+	 * never free COW fork blocks out from under pending I/O.
 	 */
-	if ((VFS_I(ip)->i_state & I_DIRTY_PAGES) ||
-	    mapping_tagged(VFS_I(ip)->i_mapping, PAGECACHE_TAG_DIRTY) ||
-	    mapping_tagged(VFS_I(ip)->i_mapping, PAGECACHE_TAG_WRITEBACK) ||
-	    atomic_read(&VFS_I(ip)->i_dio_count))
+	if (!sync && inode_is_open_for_write(VFS_I(ip)))
 		return false;
-
-	return true;
+	return xfs_can_free_cowblocks(ip);
 }
 
 /*
@@ -1337,7 +1346,7 @@ xfs_inode_free_cowblocks(
 	if (!xfs_iflags_test(ip, XFS_ICOWBLOCKS))
 		return 0;
 
-	if (!xfs_prep_free_cowblocks(ip))
+	if (!xfs_prep_free_cowblocks(ip, icw))
 		return 0;
 
 	if (!xfs_icwalk_match(ip, icw))
@@ -1366,7 +1375,7 @@ xfs_inode_free_cowblocks(
 	 * Check again, nobody else should be able to dirty blocks or change
 	 * the reflink iflag now that we have the first two locks held.
 	 */
-	if (xfs_prep_free_cowblocks(ip))
+	if (xfs_prep_free_cowblocks(ip, icw))
 		ret = xfs_reflink_cancel_cow_range(ip, 0, NULLFILEOFF, false);
 	return ret;
 }