KVM: arm64: Commit pending PC adjustemnts before returning to userspace

KVM currently updates PC (and the corresponding exception state)
using a two phase approach: first by setting a set of flags,
then by converting these flags into a state update when the vcpu
is about to enter the guest.

However, this creates a disconnect with userspace if the vcpu thread
returns there with any exception/PC flag set. In this case, the exposed
context is wrong, as userspace doesn't have access to these flags
(they aren't architectural). It also means that these flags are
preserved across a reset, which isn't expected.

To solve this problem, force an explicit synchronisation of the
exception state on vcpu exit to userspace. As an optimisation
for nVHE systems, only perform this when there is something pending.

Reported-by: Zenghui Yu <yuzenghui@huawei.com>
Reviewed-by: Alexandru Elisei <alexandru.elisei@arm.com>
Reviewed-by: Zenghui Yu <yuzenghui@huawei.com>
Tested-by: Zenghui Yu <yuzenghui@huawei.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Cc: stable@vger.kernel.org # 5.11
This commit is contained in:
Marc Zyngier 2021-05-06 15:20:12 +01:00
parent f5e3068061
commit 26778aaa13
4 changed files with 22 additions and 2 deletions

View File

@ -63,6 +63,7 @@
#define __KVM_HOST_SMCCC_FUNC___pkvm_cpu_set_vector 18 #define __KVM_HOST_SMCCC_FUNC___pkvm_cpu_set_vector 18
#define __KVM_HOST_SMCCC_FUNC___pkvm_prot_finalize 19 #define __KVM_HOST_SMCCC_FUNC___pkvm_prot_finalize 19
#define __KVM_HOST_SMCCC_FUNC___pkvm_mark_hyp 20 #define __KVM_HOST_SMCCC_FUNC___pkvm_mark_hyp 20
#define __KVM_HOST_SMCCC_FUNC___kvm_adjust_pc 21
#ifndef __ASSEMBLY__ #ifndef __ASSEMBLY__

View File

@ -897,6 +897,17 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
kvm_sigset_deactivate(vcpu); kvm_sigset_deactivate(vcpu);
/*
* In the unlikely event that we are returning to userspace
* with pending exceptions or PC adjustment, commit these
* adjustments in order to give userspace a consistent view of
* the vcpu state. Note that this relies on __kvm_adjust_pc()
* being preempt-safe on VHE.
*/
if (unlikely(vcpu->arch.flags & (KVM_ARM64_PENDING_EXCEPTION |
KVM_ARM64_INCREMENT_PC)))
kvm_call_hyp(__kvm_adjust_pc, vcpu);
vcpu_put(vcpu); vcpu_put(vcpu);
return ret; return ret;
} }

View File

@ -331,8 +331,8 @@ static void kvm_inject_exception(struct kvm_vcpu *vcpu)
} }
/* /*
* Adjust the guest PC on entry, depending on flags provided by EL1 * Adjust the guest PC (and potentially exception state) depending on
* for the purpose of emulation (MMIO, sysreg) or exception injection. * flags provided by the emulation code.
*/ */
void __kvm_adjust_pc(struct kvm_vcpu *vcpu) void __kvm_adjust_pc(struct kvm_vcpu *vcpu)
{ {

View File

@ -28,6 +28,13 @@ static void handle___kvm_vcpu_run(struct kvm_cpu_context *host_ctxt)
cpu_reg(host_ctxt, 1) = __kvm_vcpu_run(kern_hyp_va(vcpu)); cpu_reg(host_ctxt, 1) = __kvm_vcpu_run(kern_hyp_va(vcpu));
} }
static void handle___kvm_adjust_pc(struct kvm_cpu_context *host_ctxt)
{
DECLARE_REG(struct kvm_vcpu *, vcpu, host_ctxt, 1);
__kvm_adjust_pc(kern_hyp_va(vcpu));
}
static void handle___kvm_flush_vm_context(struct kvm_cpu_context *host_ctxt) static void handle___kvm_flush_vm_context(struct kvm_cpu_context *host_ctxt)
{ {
__kvm_flush_vm_context(); __kvm_flush_vm_context();
@ -170,6 +177,7 @@ typedef void (*hcall_t)(struct kvm_cpu_context *);
static const hcall_t host_hcall[] = { static const hcall_t host_hcall[] = {
HANDLE_FUNC(__kvm_vcpu_run), HANDLE_FUNC(__kvm_vcpu_run),
HANDLE_FUNC(__kvm_adjust_pc),
HANDLE_FUNC(__kvm_flush_vm_context), HANDLE_FUNC(__kvm_flush_vm_context),
HANDLE_FUNC(__kvm_tlb_flush_vmid_ipa), HANDLE_FUNC(__kvm_tlb_flush_vmid_ipa),
HANDLE_FUNC(__kvm_tlb_flush_vmid), HANDLE_FUNC(__kvm_tlb_flush_vmid),