| Message ID | 20180820060659.GA19336@fergus (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | KVM: PPC: Book3S HV: Don't truncate HPTE index in xlate function | expand |
On Mon, Aug 20, 2018 at 04:06:59PM +1000, Paul Mackerras wrote: > This fixes a bug which causes guest virtual addresses to get translated > to guest real addresses incorrectly when the guest is using the HPT MMU > and has more than 256GB of RAM, or more specifically has a HPT larger > than 2GB. This has showed up in testing as a failure of the host to > emulate doorbell instructions correctly on POWER9 for HPT guests with > more than 256GB of RAM. > > The bug is that the HPTE index in kvmppc_mmu_book3s_64_hv_xlate() > is stored as an int, and in forming the HPTE address, the index gets > shifted left 4 bits as an int before being signed-extended to 64 bits. > The simple fix is to make the variable a long int, matching the > return type of kvmppc_hv_find_lock_hpte(), which is what calculates > the index. > > Fixes: 697d3899dcb4 ("KVM: PPC: Implement MMIO emulation support for Book3S HV guests") > Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Unfortunately I haven't been able to get a hold of POWER9 time to test it yet, still working on it. > --- > arch/powerpc/kvm/book3s_64_mmu_hv.c | 2 +- > 1 file changed, 1 insertion(+), 1 deletion(-) > > diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c > index 7f3a8cf..4c08f42 100644 > --- a/arch/powerpc/kvm/book3s_64_mmu_hv.c > +++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c > @@ -359,7 +359,7 @@ static int kvmppc_mmu_book3s_64_hv_xlate(struct kvm_vcpu *vcpu, gva_t eaddr, > unsigned long pp, key; > unsigned long v, orig_v, gr; > __be64 *hptep; > - int index; > + long int index; > int virtmode = vcpu->arch.shregs.msr & (data ? MSR_DR : MSR_IR); > > if (kvm_is_radix(vcpu->kvm))
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c index 7f3a8cf..4c08f42 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_hv.c +++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c @@ -359,7 +359,7 @@ static int kvmppc_mmu_book3s_64_hv_xlate(struct kvm_vcpu *vcpu, gva_t eaddr, unsigned long pp, key; unsigned long v, orig_v, gr; __be64 *hptep; - int index; + long int index; int virtmode = vcpu->arch.shregs.msr & (data ? MSR_DR : MSR_IR); if (kvm_is_radix(vcpu->kvm))
This fixes a bug which causes guest virtual addresses to get translated to guest real addresses incorrectly when the guest is using the HPT MMU and has more than 256GB of RAM, or more specifically has a HPT larger than 2GB. This has showed up in testing as a failure of the host to emulate doorbell instructions correctly on POWER9 for HPT guests with more than 256GB of RAM. The bug is that the HPTE index in kvmppc_mmu_book3s_64_hv_xlate() is stored as an int, and in forming the HPTE address, the index gets shifted left 4 bits as an int before being signed-extended to 64 bits. The simple fix is to make the variable a long int, matching the return type of kvmppc_hv_find_lock_hpte(), which is what calculates the index. Fixes: 697d3899dcb4 ("KVM: PPC: Implement MMIO emulation support for Book3S HV guests") Signed-off-by: Paul Mackerras <paulus@ozlabs.org> --- arch/powerpc/kvm/book3s_64_mmu_hv.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)