[v8,18/43] KVM: arm64: Handle realm MMIO emulation

Commit Message

Steven Price April 16, 2025, 1:41 p.m. UTC

MMIO emulation for a realm cannot be done directly with the VM's
registers as they are protected from the host. However, for emulatable
data aborts, the RMM uses GPRS[0] to provide the read/written value.
We can transfer this from/to the equivalent VCPU's register entry and
then depend on the generic MMIO handling code in KVM.

For a MMIO read, the value is placed in the shared RecExit structure
during kvm_handle_mmio_return() rather than in the VCPU's register
entry.

Signed-off-by: Steven Price <[e-mail]>
Reviewed-by: Gavin Shan <[e-mail]>
---
Changes since v7:
 * New comment for rec_exit_sync_dabt() explaining the call to
   vcpu_set_reg().
Changes since v5:
 * Inject SEA to the guest is an emulatable MMIO access triggers a data
   abort.
 * kvm_handle_mmio_return() - disable kvm_incr_pc() for a REC (as the PC
   isn't under the host's control) and move the REC_ENTER_EMULATED_MMIO
   flag setting to this location (as that tells the RMM to skip the
   instruction).
---
 arch/arm64/kvm/inject_fault.c |  4 +++-
 arch/arm64/kvm/mmio.c         | 16 ++++++++++++----
 arch/arm64/kvm/rme-exit.c     | 14 ++++++++++++++
 3 files changed, 29 insertions(+), 5 deletions(-)

Patch

diff --git a/arch/arm64/kvm/inject_fault.c b/arch/arm64/kvm/inject_fault.c
index a640e839848e..2a9682b9834f 100644
--- a/arch/arm64/kvm/inject_fault.c
+++ b/arch/arm64/kvm/inject_fault.c
@@ -165,7 +165,9 @@  static void inject_abt32(struct kvm_vcpu *vcpu, bool is_pabt, u32 addr)
  */
 void kvm_inject_dabt(struct kvm_vcpu *vcpu, unsigned long addr)
 {
-	if (vcpu_el1_is_32bit(vcpu))
+	if (unlikely(vcpu_is_rec(vcpu)))
+		vcpu->arch.rec.run->enter.flags |= REC_ENTER_FLAG_INJECT_SEA;
+	else if (vcpu_el1_is_32bit(vcpu))
 		inject_abt32(vcpu, false, addr);
 	else
 		inject_abt64(vcpu, false, addr);
diff --git a/arch/arm64/kvm/mmio.c b/arch/arm64/kvm/mmio.c
index ab365e839874..bff89d47a4d5 100644
--- a/arch/arm64/kvm/mmio.c
+++ b/arch/arm64/kvm/mmio.c
@@ -6,6 +6,7 @@ 
 
 #include <linux/kvm_host.h>
 #include <asm/kvm_emulate.h>
+#include <asm/rmi_smc.h>
 #include <trace/events/kvm.h>
 
 #include "trace.h"
@@ -136,14 +137,21 @@  int kvm_handle_mmio_return(struct kvm_vcpu *vcpu)
 		trace_kvm_mmio(KVM_TRACE_MMIO_READ, len, run->mmio.phys_addr,
 			       &data);
 		data = vcpu_data_host_to_guest(vcpu, data, len);
-		vcpu_set_reg(vcpu, kvm_vcpu_dabt_get_rd(vcpu), data);
+
+		if (vcpu_is_rec(vcpu))
+			vcpu->arch.rec.run->enter.gprs[0] = data;
+		else
+			vcpu_set_reg(vcpu, kvm_vcpu_dabt_get_rd(vcpu), data);
 	}
 
 	/*
 	 * The MMIO instruction is emulated and should not be re-executed
 	 * in the guest.
 	 */
-	kvm_incr_pc(vcpu);
+	if (vcpu_is_rec(vcpu))
+		vcpu->arch.rec.run->enter.flags |= REC_ENTER_FLAG_EMULATED_MMIO;
+	else
+		kvm_incr_pc(vcpu);
 
 	return 1;
 }
@@ -162,14 +170,14 @@  int io_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa)
 	 * No valid syndrome? Ask userspace for help if it has
 	 * volunteered to do so, and bail out otherwise.
 	 *
-	 * In the protected VM case, there isn't much userspace can do
+	 * In the protected/realm VM case, there isn't much userspace can do
 	 * though, so directly deliver an exception to the guest.
 	 */
 	if (!kvm_vcpu_dabt_isvalid(vcpu)) {
 		trace_kvm_mmio_nisv(*vcpu_pc(vcpu), kvm_vcpu_get_esr(vcpu),
 				    kvm_vcpu_get_hfar(vcpu), fault_ipa);
 
-		if (vcpu_is_protected(vcpu)) {
+		if (vcpu_is_protected(vcpu) || vcpu_is_rec(vcpu)) {
 			kvm_inject_dabt(vcpu, kvm_vcpu_get_hfar(vcpu));
 			return 1;
 		}
diff --git a/arch/arm64/kvm/rme-exit.c b/arch/arm64/kvm/rme-exit.c
index a1adf5610455..6830dc080610 100644
--- a/arch/arm64/kvm/rme-exit.c
+++ b/arch/arm64/kvm/rme-exit.c
@@ -25,6 +25,20 @@  static int rec_exit_reason_notimpl(struct kvm_vcpu *vcpu)
 
 static int rec_exit_sync_dabt(struct kvm_vcpu *vcpu)
 {
+	struct realm_rec *rec = &vcpu->arch.rec;
+
+	/*
+	 * In the case of a write, copy over gprs[0] to the target GPR,
+	 * preparing to handle MMIO write fault. The content to be written has
+	 * been saved to gprs[0] by the RMM (even if another register was used
+	 * by the guest). In the case of normal memory access this is redundant
+	 * (the guest will replay the instruction), but the overhead is
+	 * minimal.
+	 */
+	if (kvm_vcpu_dabt_iswrite(vcpu) && kvm_vcpu_dabt_isvalid(vcpu))
+		vcpu_set_reg(vcpu, kvm_vcpu_dabt_get_rd(vcpu),
+			     rec->run->exit.gprs[0]);
+
 	return kvm_handle_guest_abort(vcpu);
 }