Re: [PATCH 3/3] vfio: disable filesystem-dax page pinning

On Sun, 04 Feb 2018 15:05:30 -0800 Dan Williams <dan.j.williams(a)intel.com&gt; wrote: > Filesystem-DAX is incompatible with 'longterm' page pinning. Without > page cache indirection a DAX mapping maps filesystem blocks directly. > This means that the filesystem must not modify a file's block map while > any page in a mapping is pinned. In order to prevent the situation of > userspace holding of filesystem operations indefinitely, disallow > 'longterm' Filesystem-DAX mappings. > > RDMA has the same conflict and the plan there is to add a 'with lease' > mechanism to allow the kernel to notify userspace that the mapping is > being torn down for block-map maintenance. Perhaps something similar can > be put in place for vfio. > > Note that xfs and ext4 still report: > > "DAX enabled. Warning: EXPERIMENTAL, use at your own risk" > > ...at mount time, and resolving the dax-dma-vs-truncate problem is one > of the last hurdles to remove that designation. > > Cc: Alex Williamson <alex.williamson(a)redhat.com&gt; > Cc: Michal Hocko <mhocko(a)suse.com&gt; > Cc: Christoph Hellwig <hch(a)lst.de&gt; > Cc: kvm(a)vger.kernel.org > Cc: <stable(a)vger.kernel.org&gt; > Reported-by: Haozhong Zhang <haozhong.zhang(a)intel.com&gt; > Fixes: d475c6346a38 ("dax,ext2: replace XIP read and write with DAX I/O") > Signed-off-by: Dan Williams <dan.j.williams(a)intel.com&gt; > --- > drivers/vfio/vfio_iommu_type1.c | 18 +++++++++++++++--- > 1 file changed, 15 insertions(+), 3 deletions(-) This isn't without some expense, a vfio mapping and un-mapping unit test incurs ~1.5% increase in system time losing access to gup_fast(). Also, I think tce_iommu_use_page() is going to have the same problem, it provides the same sort of functionality for a different vfio IOMMU backend. Please take this through your tree and I'll add a todo list item to see how we might improve this. Acked-by: Alex Williamson <alex.williamson(a)redhat.com&gt;