Re: [Xen-devel] [PATCH v2] iommu: leave IOMMU enabled by default during kexec crash transition

2019-02-22 Thread Jan Beulich
>>> On 21.02.19 at 23:08, wrote: > It's unsafe to disable IOMMU on a live system which is the case > if we're crashing since remapping hardware doesn't usually know what > to do with ongoing bus transactions and frequently raises NMI/MCE/SMI, > etc. (depends on the firmware configuration) to

Re: [Xen-devel] [PATCH v2] iommu: leave IOMMU enabled by default during kexec crash transition

2019-02-22 Thread Igor Druzhinin
On 22/02/2019 12:34, Jan Beulich wrote: On 21.02.19 at 23:08, wrote: >> Modern Linux kernels taught to copy all the necessary DMAR/IR tables >> following kexec from the previous kernel (Xen in our case) - so it's >> currently normal to keep IOMMU enabled. It might require minor changes to >>

Re: [Xen-devel] [PATCH v2] iommu: leave IOMMU enabled by default during kexec crash transition

2019-02-22 Thread Jan Beulich
>>> On 21.02.19 at 23:08, wrote: > Modern Linux kernels taught to copy all the necessary DMAR/IR tables > following kexec from the previous kernel (Xen in our case) - so it's > currently normal to keep IOMMU enabled. It might require minor changes to > kdump command line that enables IOMMU

[Xen-devel] [PATCH v2] iommu: leave IOMMU enabled by default during kexec crash transition

2019-02-21 Thread Igor Druzhinin
It's unsafe to disable IOMMU on a live system which is the case if we're crashing since remapping hardware doesn't usually know what to do with ongoing bus transactions and frequently raises NMI/MCE/SMI, etc. (depends on the firmware configuration) to signal these abnormalities. This, in turn,