Ccing David
On 2016/11/16 at 17:02, Xunlei Pang wrote:
> We met the DMAR fault both on hpsa P420i and P421 SmartArray controllers
> under kdump, it can be steadily reproduced on several different machines,
> the dmesg log is like:
> HP HPSA Driver (v 3.4.16-0)
> hpsa 0000:02:00.0: using doorbell to reset controller
> hpsa 0000:02:00.0: board ready after hard reset.
> hpsa 0000:02:00.0: Waiting for controller to respond to no-op
> DMAR: Setting identity map for device 0000:02:00.0 [0xe8000 - 0xe8fff]
> DMAR: Setting identity map for device 0000:02:00.0 [0xf4000 - 0xf4fff]
> DMAR: Setting identity map for device 0000:02:00.0 [0xbdf6e000 - 0xbdf6efff]
> DMAR: Setting identity map for device 0000:02:00.0 [0xbdf6f000 - 0xbdf7efff]
> DMAR: Setting identity map for device 0000:02:00.0 [0xbdf7f000 - 0xbdf82fff]
> DMAR: Setting identity map for device 0000:02:00.0 [0xbdf83000 - 0xbdf84fff]
> DMAR: DRHD: handling fault status reg 2
> DMAR: [DMA Read] Request device [02:00.0] fault addr fffff000 [fault reason 06] PTE Read access is not set
> hpsa 0000:02:00.0: controller message 03:00 timed out
> hpsa 0000:02:00.0: no-op failed; re-trying
>
> After some debugging, we found that the corresponding pte entry value
> is correct, and the value of the iommu caching mode is 0, the fault is
> probably due to the old iotlb cache of the in-flight DMA.
>
> Thus need to flush the old iotlb after context mapping is setup for the
> device, where the device is supposed to finish reset at its driver probe
> stage and no in-flight DMA exists hereafter.
>
> With this patch, all our problematic machines can survive the kdump tests.
>
> CC: Myron Stowe <myron.stowe at redhat.com>
> CC: Don Brace <don.brace at microsemi.com>
> CC: Baoquan He <bhe at redhat.com>
> CC: Dave Young <dyoung at redhat.com>
> Tested-by: Joseph Szczypek <jszczype at redhat.com>
> Signed-off-by: Xunlei Pang <xlpang at redhat.com>
> ---
> drivers/iommu/intel-iommu.c | 11 +++++++++--
> 1 file changed, 9 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
> index 3965e73..eb79288 100644
> --- a/drivers/iommu/intel-iommu.c
> +++ b/drivers/iommu/intel-iommu.c
> @@ -2067,9 +2067,16 @@ static int domain_context_mapping_one(struct dmar_domain *domain,
> * It's a non-present to present mapping. If hardware doesn't cache
> * non-present entry we only need to flush the write-buffer. If the
> * _does_ cache non-present entries, then it does so in the special
> - * domain #0, which we have to flush:
> + * domain #0, which we have to flush.
> + *
> + * For kdump cases, present entries may be cached due to the in-flight
> + * DMA and copied old pgtable, but there is no unmapping behaviour for
> + * them, so we need an explicit iotlb flush for the newly-mapped device.
> + * For kdump, at this point, the device is supposed to finish reset at
> + * the driver probe stage, no in-flight DMA will exist, thus we do not
> + * need to worry about that anymore hereafter.
> */
> - if (cap_caching_mode(iommu->cap)) {
> + if (is_kdump_kernel() || cap_caching_mode(iommu->cap)) {
> iommu->flush.flush_context(iommu, 0,
> (((u16)bus) << 8) | devfn,
> DMA_CCMD_MASK_NOBIT,
