| Message ID | 1461856591-5751-1-git-send-email-marc.zyngier@arm.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
On Thu, Apr 28, 2016 at 04:16:31PM +0100, Marc Zyngier wrote: > The ARM architecture mandates that when changing a page table entry > from a valid entry to another valid entry, an invalid entry is first > written, TLB invalidated, and only then the new entry being written. > > The current code doesn't respect this, directly writing the new > entry and only then invalidating TLBs. Let's fix it up. > > Signed-off-by: Marc Zyngier <marc.zyngier@arm.com> FWIW, this looks correct to me. Acked-by: Mark Rutland <mark.rutland@arm.com> Mark. > --- > arch/arm/kvm/mmu.c | 17 +++++++++++------ > 1 file changed, 11 insertions(+), 6 deletions(-) > > diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c > index 58dbd5c..edf1cd1 100644 > --- a/arch/arm/kvm/mmu.c > +++ b/arch/arm/kvm/mmu.c > @@ -893,11 +893,14 @@ static int stage2_set_pmd_huge(struct kvm *kvm, struct kvm_mmu_memory_cache > VM_BUG_ON(pmd_present(*pmd) && pmd_pfn(*pmd) != pmd_pfn(*new_pmd)); > > old_pmd = *pmd; > - kvm_set_pmd(pmd, *new_pmd); > - if (pmd_present(old_pmd)) > + if (pmd_present(old_pmd)) { > + pmd_clear(pmd); > kvm_tlb_flush_vmid_ipa(kvm, addr); > - else > + } else { > get_page(virt_to_page(pmd)); > + } > + > + kvm_set_pmd(pmd, *new_pmd); > return 0; > } > > @@ -946,12 +949,14 @@ static int stage2_set_pte(struct kvm *kvm, struct kvm_mmu_memory_cache *cache, > > /* Create 2nd stage page table mapping - Level 3 */ > old_pte = *pte; > - kvm_set_pte(pte, *new_pte); > - if (pte_present(old_pte)) > + if (pte_present(old_pte)) { > + kvm_set_pte(pte, __pte(0)); > kvm_tlb_flush_vmid_ipa(kvm, addr); > - else > + } else { > get_page(virt_to_page(pte)); > + } > > + kvm_set_pte(pte, *new_pte); > return 0; > } > > -- > 2.1.4 > > _______________________________________________ > kvmarm mailing list > kvmarm@lists.cs.columbia.edu > https://lists.cs.columbia.edu/mailman/listinfo/kvmarm >
On Thu, Apr 28, 2016 at 04:16:31PM +0100, Marc Zyngier wrote: > The ARM architecture mandates that when changing a page table entry > from a valid entry to another valid entry, an invalid entry is first > written, TLB invalidated, and only then the new entry being written. > > The current code doesn't respect this, directly writing the new > entry and only then invalidating TLBs. Let's fix it up. > > Signed-off-by: Marc Zyngier <marc.zyngier@arm.com> Thanks for fixing this, I've applied it to next. -Christoffer
diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c index 58dbd5c..edf1cd1 100644 --- a/arch/arm/kvm/mmu.c +++ b/arch/arm/kvm/mmu.c @@ -893,11 +893,14 @@ static int stage2_set_pmd_huge(struct kvm *kvm, struct kvm_mmu_memory_cache VM_BUG_ON(pmd_present(*pmd) && pmd_pfn(*pmd) != pmd_pfn(*new_pmd)); old_pmd = *pmd; - kvm_set_pmd(pmd, *new_pmd); - if (pmd_present(old_pmd)) + if (pmd_present(old_pmd)) { + pmd_clear(pmd); kvm_tlb_flush_vmid_ipa(kvm, addr); - else + } else { get_page(virt_to_page(pmd)); + } + + kvm_set_pmd(pmd, *new_pmd); return 0; } @@ -946,12 +949,14 @@ static int stage2_set_pte(struct kvm *kvm, struct kvm_mmu_memory_cache *cache, /* Create 2nd stage page table mapping - Level 3 */ old_pte = *pte; - kvm_set_pte(pte, *new_pte); - if (pte_present(old_pte)) + if (pte_present(old_pte)) { + kvm_set_pte(pte, __pte(0)); kvm_tlb_flush_vmid_ipa(kvm, addr); - else + } else { get_page(virt_to_page(pte)); + } + kvm_set_pte(pte, *new_pte); return 0; }
The ARM architecture mandates that when changing a page table entry from a valid entry to another valid entry, an invalid entry is first written, TLB invalidated, and only then the new entry being written. The current code doesn't respect this, directly writing the new entry and only then invalidating TLBs. Let's fix it up. Signed-off-by: Marc Zyngier <marc.zyngier@arm.com> --- arch/arm/kvm/mmu.c | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-)