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

BugLink: https://bugs.launchpad.net/bugs/1933691
commit 26778aaa134a9aefdf5dbaad904054d7be9d656d upstream.

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
[yuz: stable-5.12.y backport: allocate a new number (15) for
 __KVM_HOST_SMCCC_FUNC___kvm_adjust_pc to keep the host_hcall array
 tightly packed]
Signed-off-by: Zenghui Yu <yuzenghui@huawei.com>
Reviewed-by: Marc Zyngier <maz@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
Signed-off-by: Kelsey Skunberg <kelsey.skunberg@canonical.com>

diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index 7b4a3f1907c16ec49041d65bef42bd3c6dc68fc7..4dbfd8a263c77d2eb6b9e41201b41edbef0f46bf 100644 (file)
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -57,6 +57,7 @@
 #define __KVM_HOST_SMCCC_FUNC___kvm_get_mdcr_el2               12
 #define __KVM_HOST_SMCCC_FUNC___vgic_v3_save_aprs              13
 #define __KVM_HOST_SMCCC_FUNC___vgic_v3_restore_aprs           14
+#define __KVM_HOST_SMCCC_FUNC___kvm_adjust_pc                  15
 
 #ifndef __ASSEMBLY__
 

diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 807c47b93f5f0da0a097055cc0d69ff694485ffe..0185a4dda190c60ea32b410bf750a1fe1ddc4184 100644 (file)
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -892,6 +892,17 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *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);
        return ret;
 }

diff --git a/arch/arm64/kvm/hyp/exception.c b/arch/arm64/kvm/hyp/exception.c
index 0812a496725f6884ecf59a85b1656192af970106..11541b94b328f8e1d110fa0be3fd37ec07f1ae59 100644 (file)
--- a/arch/arm64/kvm/hyp/exception.c
+++ b/arch/arm64/kvm/hyp/exception.c
@@ -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
- * for the purpose of emulation (MMIO, sysreg) or exception injection.
+ * Adjust the guest PC (and potentially exception state) depending on
+ * flags provided by the emulation code.
  */
 void __kvm_adjust_pc(struct kvm_vcpu *vcpu)
 {

diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
index 1b8ef37bf8054d506767a561e399b46b1f8b7d86..bb63e0717380420ba0ef1ae40047fbb02dcb3795 100644 (file)
--- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c
+++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
@@ -25,6 +25,13 @@ static void handle___kvm_vcpu_run(struct kvm_cpu_context *host_ctxt)
        cpu_reg(host_ctxt, 1) =  __kvm_vcpu_run(kern_hyp_va(vcpu));
 }
 
+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)
 {
        __kvm_flush_vm_context();
@@ -112,6 +119,7 @@ typedef void (*hcall_t)(struct kvm_cpu_context *);
 
 static const hcall_t *host_hcall[] = {
        HANDLE_FUNC(__kvm_vcpu_run),
+       HANDLE_FUNC(__kvm_adjust_pc),
        HANDLE_FUNC(__kvm_flush_vm_context),
        HANDLE_FUNC(__kvm_tlb_flush_vmid_ipa),
        HANDLE_FUNC(__kvm_tlb_flush_vmid),