Re: [PATCH 1/1] iommu/vt-d: Fix dmar pte read access not set error

From: Lu Baolu
Date: Fri Dec 13 2019 - 00:02:20 EST


On 12/13/19 11:16 AM, Jerry Snitselaar wrote:
On Thu Dec 12 19, Jerry Snitselaar wrote:
On Fri Dec 13 19, Lu Baolu wrote:

On 12/13/19 8:30 AM, Jerry Snitselaar wrote:
On Thu Dec 12 19, Lu Baolu wrote:

On 12/12/19 9:49 AM, Jerry Snitselaar wrote:
On Wed Dec 11 19, Lu Baolu wrote:
If the default DMA domain of a group doesn't fit a device, it
will still sit in the group but use a private identity domain.
When map/unmap/iova_to_phys come through iommu API, the driver
should still serve them, otherwise, other devices in the same
group will be impacted. Since identity domain has been mapped
with the whole available memory space and RMRRs, we don't need
to worry about the impact on it.

Cc: Jerry Snitselaar <jsnitsel@xxxxxxxxxx>
Reported-by: Jerry Snitselaar <jsnitsel@xxxxxxxxxx>
Fixes: 942067f1b6b97 ("iommu/vt-d: Identify default domains replaced with private")
Cc: stable@xxxxxxxxxxxxxxx # v5.3+
Signed-off-by: Lu Baolu <>

Reviewed-by: Jerry Snitselaar <jsnitsel@xxxxxxxxxx>

Can you please try this fix and check whether it can fix your problem?
If it helps, do you mind adding a Tested-by?

Best regards,

I'm testing with this patch, my patch that moves the direct mapping call,
and Alex's patch for the ISA bridge. It solved the 2 iommu mapping errors
I was seeing with default passthrough, I no longer see all the dmar pte
read access errors, and the system boots allowing me to login. I'm tracking
down 2 issues at the moment. With passthrough I see a problem with 01:00.4
that I mentioned in the earlier email:

[ÂÂ 78.978573] uhci_hcd: USB Universal Host Controller Interface driver
[ÂÂ 78.980842] uhci_hcd 0000:01:00.4: UHCI Host Controller
[ÂÂ 78.982738] uhci_hcd 0000:01:00.4: new USB bus registered, assigned bus number 3
[ÂÂ 78.985222] uhci_hcd 0000:01:00.4: detected 8 ports
[ÂÂ 78.986907] uhci_hcd 0000:01:00.4: port count misdetected? forcing to 2 ports
[ÂÂ 78.989316] uhci_hcd 0000:01:00.4: irq 16, io base 0x00003c00
[ÂÂ 78.994634] uhci_hcd 0000:01:00.4: DMAR: 32bit DMA uses non-identity mapping
[ÂÂ 7 0000:01:00.4: unable to allocate consistent memory for frame list
[ÂÂ 79.499891] uhci_hcd 0000:01:00.4: startup error -16
[ÂÂ 79.501588] uhci_hcd 0000:01:00.4: USB bus 3 deregistered
[ÂÂ 79.503494] uhci_hcd 0000:01:00.4: init 0000:01:00.4 fail, -16
[ÂÂ 79.505497] uhci_hcd: probe of 0000:01:00.4 failed with error -16

If I boot the system with iommu=nopt I see an iommu map failure due to
the prot check in __domain_mapping:

[ÂÂ 40.940589] pci 0000:00:1f.0: iommu_group_add_device: calling iommu_group_create_direct_mappings
[ÂÂ 40.943558] pci 0000:00:1f.0: iommu_group_create_direct_mappings: iterating through mappings
[ÂÂ 40.946402] pci 0000:00:1f.0: iommu_group_create_direct_mappings: calling apply_resv_region
[ÂÂ 40.949184] pci 0000:00:1f.0: iommu_group_create_direct_mappings: entry type is direct
[ÂÂ 40.951819] DMAR: intel_iommu_map: enter
[ÂÂ 40.953128] DMAR: __domain_mapping: prot & (DMA_PTE_READ|DMA_PTE_WRITE) == 0
[ÂÂ 40.955486] DMAR: domain_mapping: __domain_mapping failed
[ÂÂ 40.957348] DMAR: intel_iommu_map: domain_pfn_mapping returned -22
[ÂÂ 40.959466] DMAR: intel_iommu_map: leave
[ÂÂ 40.959468] iommu: iommu_map: ops->map failed iova 0x0 pa 0x0000000000000000 pgsize 0x1000
[ÂÂ 40.963511] pci 0000:00:1f.0: iommu_group_create_direct_mappings: iommu_map failed
[ÂÂ 40.966026] pci 0000:00:1f.0: iommu_group_create_direct_mappings: leaving func
[ÂÂ 40.968487] pci 0000:00:1f.0: iommu_group_add_device: calling __iommu_attach_device
[ÂÂ 40.971016] pci 0000:00:1f.0: Adding to iommu group 19
[ÂÂ 40.972731] pci 0000:00:1f.0: DMAR: domain->type is dma

[root@hp-dl388g8-07 19]# cat reserved_regions 0x0000000000000000 0x0000000000ffffff direct
0x00000000bdf6e000 0x00000000bdf84fff direct
0x00000000fee00000 0x00000000feefffff msi

00:1f.0 ISA bridge: Intel Corporation C600/X79 series chipset LPC Controller

This seems to be another issue?

Best regards,

In intel_iommu_get_resv_regions this iommu_alloc_resv_region is called
with prot set to 0:

ÂÂÂÂÂÂÂÂÂÂÂÂÂÂ if ((pdev->class >> 8) == PCI_CLASS_BRIDGE_ISA) {
ÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂ reg = iommu_alloc_resv_region(0, 1UL << 24, 0,

Looking at the older code for the ISA bridge it looks like it called
iommu_prepare_identity_map -> domain_prepare_identity_map ->
iommu_domain_identity_map -> and finally __domain_mapping with DMA_PTE_READ|DMA_PTE_WRITE?

Yes. Returning a reserved region without any access permission makes no
sense. Can you please post a fix for this?

Best regards,