Skip to contentSkip to conversation

Use the correct page tables for SVA under PTI

PATCH In review Jacob Pan 3 participants 8 messages Aug 22, 2022 – Aug 31, 2022

Subsystems (4)
lore
Share & tools
lore

Jacob Pan

author
#0 lore raw

cover Use the correct page tables for SVA under PTI

Shared virtual addressing allows DMA to user virtual address, But the x86 IOMMU drivers are using the kernel copy of the process page tables when PTI is enabled. This patchset tightens the security intended by PTI by performing SVA binding with the appropriate process PGDs.

I have tested on Intel platform only, would appreciate itif someone could help with testing SVA-KPTI on an AMD system.

Jacob Pan (2):
x86: mm: Allow PTI helpers to be used outside x86/mm
iommu: Use the user PGD for SVA if PTI is enabled

 arch/x86/include/asm/pgtable.h | 5 +++++
 drivers/iommu/amd/iommu_v2.c   | 4 +++-
 drivers/iommu/intel/svm.c      | 5 ++++-
 3 files changed, 12 insertions(+), 2 deletions(-)
Signature · 1 line
2.25.1
author
#1 lore raw

PATCH 1/2 x86: mm: Allow PTI helpers to be used outside x86/mm

With the support of shared virtual addressing(SVA), x86 IOMMUs also need to get access to user PGD when sharing user mappings.

This patch makes sure the PTI helper function to retrieve user PGD is available regardless the state of CONFIG_PAGE_TABLE_ISOLATION. So far, such need is x86 only.

---
 arch/x86/include/asm/pgtable.h | 5 +++++
 1 file changed, 5 insertions(+)
arch/x86/include/asm/pgtable.h +5 -0
index 44e2d6f1dbaa..42f55281e232 100644
@@ -1227,6 +1227,11 @@ static inline p4d_t *user_to_kernel_p4dp(p4d_t *p4dp)
 {
 	return ptr_clear_bit(p4dp, PTI_PGTABLE_SWITCH_BIT);
 }
+#else
+static inline pgd_t *kernel_to_user_pgdp(pgd_t *pgdp)
+{
+	return pgdp;
+}
 #endif /* CONFIG_PAGE_TABLE_ISOLATION */
 
 /*
Signature · 1 line
2.25.1
author
#2 lore raw

PATCH 2/2 iommu: Use the user PGD for SVA if PTI is enabled

In reply to Jacob Pan

With page table isolation, the kernel manages two sets of page tables for each process: one for user one for kernel. When enabling SVA, the current x86 IOMMU drivers bind device and PASID with the kernel copy of the process page table.

While there is no known "Meltdown" type of DMA attack, exposing kernel mapping to DMA intended for userspace makes the system vulnerable unnecessarily. It also breaks the intention of PTI.

This patch replaces kernel page table PGD with the user counterpart, thus fulfill the promise of PTI on the DMA side.

---
 drivers/iommu/amd/iommu_v2.c | 4 +++-
 drivers/iommu/intel/svm.c    | 5 ++++-
 2 files changed, 7 insertions(+), 2 deletions(-)
drivers/iommu/amd/iommu_v2.c +3 -1
index 696d5555be57..aea3075b94af 100644
@@ -600,6 +600,7 @@ int amd_iommu_bind_pasid(struct pci_dev *pdev, u32 pasid,
 	struct pasid_state *pasid_state;
 	struct device_state *dev_state;
 	struct mm_struct *mm;
+	pgd_t *pgd;
 	u32 sbdf;
 	int ret;
 
@@ -645,8 +646,9 @@ int amd_iommu_bind_pasid(struct pci_dev *pdev, u32 pasid,
 	if (ret)
 		goto out_unregister;
 
+	pgd = static_cpu_has(X86_FEATURE_PTI) ? kernel_to_user_pgdp(mm->pgd) : mm->pgd;
 	ret = amd_iommu_domain_set_gcr3(dev_state->domain, pasid,
-					__pa(pasid_state->mm->pgd));
+					__pa(pgd));
 	if (ret)
 		goto out_clear_state;
 
drivers/iommu/intel/svm.c +4 -1
index 8bcfb93dda56..7472cd98d3e8 100644
@@ -332,6 +332,7 @@ static struct iommu_sva *intel_svm_bind_mm(struct intel_iommu *iommu,
 	struct intel_svm *svm;
 	unsigned long sflags;
 	int ret = 0;
+	pgd_t *pgd;
 
 	svm = pasid_private_find(mm->pasid);
 	if (!svm) {
@@ -394,7 +395,9 @@ static struct iommu_sva *intel_svm_bind_mm(struct intel_iommu *iommu,
 	sflags = (flags & SVM_FLAG_SUPERVISOR_MODE) ?
 			PASID_FLAG_SUPERVISOR_MODE : 0;
 	sflags |= cpu_feature_enabled(X86_FEATURE_LA57) ? PASID_FLAG_FL5LP : 0;
-	ret = intel_pasid_setup_first_level(iommu, dev, mm->pgd, mm->pasid,
+
+	pgd = static_cpu_has(X86_FEATURE_PTI) ? kernel_to_user_pgdp(mm->pgd) : mm->pgd;
+	ret = intel_pasid_setup_first_level(iommu, dev, pgd, mm->pasid,
 					    FLPT_DEFAULT_DID, sflags);
 	if (ret)
 		goto free_sdev;
Signature · 1 line
2.25.1
#3 lore raw

Re: [PATCH 2/2] iommu: Use the user PGD for SVA if PTI is enabled

drivers/iommu/intel/svm.c static struct iommu_sva *intel_svm_bind_mm(struct intel_iommu *iommu, · line 401

Quoted 9 lines · Jacob Pan
drivers/iommu/intel/svm.c +3 -1
@@ -394,7 +395,9 @@ static struct iommu_sva *intel_svm_bind_mm(struct intel_iommu *iommu,
 	sflags = (flags & SVM_FLAG_SUPERVISOR_MODE) ?
 			PASID_FLAG_SUPERVISOR_MODE : 0;
 	sflags |= cpu_feature_enabled(X86_FEATURE_LA57) ? PASID_FLAG_FL5LP : 0;
-	ret = intel_pasid_setup_first_level(iommu, dev, mm->pgd, mm->pasid,
+
+	pgd = static_cpu_has(X86_FEATURE_PTI) ? kernel_to_user_pgdp(mm->pgd) : mm->pgd;
+	ret = intel_pasid_setup_first_level(iommu, dev, pgd, mm->pasid,
 					    FLPT_DEFAULT_DID, sflags);

This X86_FEATURE_PTI should really be done within a helper.

I'd probably do this with a *new* helper since all of the existing kernel_to_user_pgdp() users seem to be within a PTI #ifdef.

Maybe something like:

pgd_t *mm_user_pgd(struct mm_struct *mm)
{

#ifdef CONFIG_PAGE_TABLE_ISOLATION
	if (cpu_feature_enabled(X86_FEATURE_PTI))
		return kernel_to_user_pgdp(mm->pgd);
#endif
	return mm->pgd;
}

That #ifdef could even go away if your kernel_to_user_pgdp() stub from patch 1/2 was available. I'm not sure it's worth it though.

author
#4 lore raw

Re: [PATCH 2/2] iommu: Use the user PGD for SVA if PTI is enabled

Hi Dave,

Quoted 21 lines · Dave Hansen

drivers/iommu/intel/svm.c static struct iommu_sva *intel_svm_bind_mm(struct intel_iommu *iommu, · line 401

Quoted 12 lines · Jacob Pan
(quoted diff) +0 -0
@@ -394,7 +395,9 @@ static struct iommu_sva *intel_svm_bind_mm(struct

intel_iommu *iommu, sflags = (flags & SVM_FLAG_SUPERVISOR_MODE) ?

(quoted diff) +0 -0
 			PASID_FLAG_SUPERVISOR_MODE : 0;
 	sflags |= cpu_feature_enabled(X86_FEATURE_LA57) ?

PASID_FLAG_FL5LP : 0;

(quoted diff) +0 -1
-	ret = intel_pasid_setup_first_level(iommu, dev, mm->pgd,

mm->pasid, +

(quoted diff) +1 -0
+	pgd = static_cpu_has(X86_FEATURE_PTI) ?

kernel_to_user_pgdp(mm->pgd) : mm->pgd;

drivers/iommu/intel/svm.c +1 -0
+	ret = intel_pasid_setup_first_level(iommu, dev, pgd, mm->pasid,
 					    FLPT_DEFAULT_DID, sflags);

This X86_FEATURE_PTI should really be done within a helper.

I'd probably do this with a *new* helper since all of the existing kernel_to_user_pgdp() users seem to be within a PTI #ifdef.

Maybe something like:

Quoted 9 lines

pgd_t *mm_user_pgd(struct mm_struct *mm)
{

#ifdef CONFIG_PAGE_TABLE_ISOLATION
	if (cpu_feature_enabled(X86_FEATURE_PTI))
		return kernel_to_user_pgdp(mm->pgd);
#endif
	return mm->pgd;
}

Sounds good. I thought about a helper also, thinking there are so many other cpu_has(X86_FEATURE_PTI) checks already :)

Quoted 2 lines

That #ifdef could even go away if your kernel_to_user_pgdp() stub from patch 1/2 was available. I'm not sure it's worth it though.

I will remove 1/2 and keep the uniform style of the existing helpers.

Thanks for the suggestion,

Jacob

#5 lore raw

Re: [PATCH 2/2] iommu: Use the user PGD for SVA if PTI is enabled

Quoted 2 lines · Jacob Pan

Sounds good. I thought about a helper also, thinking there are so many other cpu_has(X86_FEATURE_PTI) checks already :)

Yes, but almost all of those are in PTI-#ifdef'd code already.

maintainer Reviewed-by on v1 2/2
#6 lore raw

Re: [PATCH 2/2] iommu: Use the user PGD for SVA if PTI is enabled

In reply to Jacob Pan
Quoted 5 lines · Jacob Pan

With page table isolation, the kernel manages two sets of page tables for each process: one for user one for kernel. When enabling SVA, the current x86 IOMMU drivers bind device and PASID with the kernel copy of the process page table.

Quoted 8 lines

While there is no known "Meltdown" type of DMA attack, exposing kernel mapping to DMA intended for userspace makes the system vulnerable unnecessarily. It also breaks the intention of PTI.

This patch replaces kernel page table PGD with the user counterpart, thus fulfill the promise of PTI on the DMA side.

Best regards,
baolu

author
#7 lore raw
In reply to Jacob Pan

Hi Baolu/Joerg,

Just wondering if you have any comments? Thanks.

Quoted 8 lines · Jacob Pan

Shared virtual addressing allows DMA to user virtual address, But the x86 IOMMU drivers are using the kernel copy of the process page tables when PTI is enabled. This patchset tightens the security intended by PTI by performing SVA binding with the appropriate process PGDs.

I have tested on Intel platform only, would appreciate itif someone could help with testing SVA-KPTI on an AMD system.

Quoted 9 lines

Jacob Pan (2):
x86: mm: Allow PTI helpers to be used outside x86/mm
iommu: Use the user PGD for SVA if PTI is enabled

 arch/x86/include/asm/pgtable.h | 5 +++++
 drivers/iommu/amd/iommu_v2.c   | 4 +++-
 drivers/iommu/intel/svm.c      | 5 ++++-
 3 files changed, 12 insertions(+), 2 deletions(-)

Thanks,

Jacob