Re: swiotlb/caamjr regression (Was: [GIT PULL] (swiotlb) stable/for-linus-5.12)

[Jianxiong Gao <jxgao@google.com>]

On Fri, Jun 11, 2021 at 3:35 AM Konrad Rzeszutek Wilk
<konrad.wilk@oracle.com> wrote:
>
> On Fri, Jun 11, 2021 at 08:21:53AM +0200, Christoph Hellwig wrote:
> > On Thu, Jun 10, 2021 at 05:52:07PM +0300, Horia Geantă wrote:
> > > I've noticed the failure also in v5.10 and v5.11 stable kernels,
> > > since the patch set has been backported.
> >
> > FYI, there has been a patch on the list that should have fixed this
> > for about a month:
> >
> > https://lore.kernel.org/linux-iommu/20210510091816.GA2084@lst.de/T/#m0d0df6490350a08dcc24c9086c8edc165b402d6f
> >
> > but it seems like it never got picked up.
>
> Jianxiong,
> Would you be up for testing this patch on your NVMe rig please? I don't
> forsee a problem.. but just in case
>
I have tested the attached patch and it generates an error when
formatting a disk to xfs format in Rhel 8 environment:

sudo mkfs.xfs -f /dev/nvme0n2
meta-data=/dev/nvme0n2           isize=512    agcount=4, agsize=32768000 blks
         =                       sectsz=512   attr=2, projid32bit=1
         =                       crc=1        finobt=1, sparse=1, rmapbt=0
         =                       reflink=1
data     =                       bsize=4096   blocks=131072000, imaxpct=25
         =                       sunit=0      swidth=0 blks
naming   =version 2              bsize=4096   ascii-ci=0, ftype=1
log      =internal log           bsize=4096   blocks=64000, version=2
         =                       sectsz=512   sunit=0 blks, lazy-count=1
realtime =none                   extsz=4096   blocks=0, rtextents=0
Discarding blocks...Done.
bad magic number
bad magic number
Metadata corruption detected at 0x56211de4c0c8, xfs_sb block 0x0/0x200
libxfs_writebufr: write verifer failed on xfs_sb bno 0x0/0x200
releasing dirty buffer (bulk) to free list!

I applied the patch on commit 06af8679449d.