[PATCH 0/2] KVM: arm64: Fix and test MMIO sign-extending loads

[PATCH 0/2] KVM: arm64: Fix and test MMIO sign-extending loads

[Fuad Tabba]

Hi folks,

A sign-extending load (LDRSB/LDRSH/LDRSW) from emulated MMIO returns a
zero-extended value rather than the sign-extended one the architecture
requires; vcpu_data_host_to_guest() strips the sign bits when it masks
the data to the access width.

If my git archeology is right, the masking dates to 2014 (b30070862edbd,
big-endian support) and has been wrong ever since, but sign-extending
loads from device memory are rare enough that nobody hit it. Patch 1
fixes it; patch 2 adds a selftest so it doesn't regress.

Cheers,
/fuad

Fuad Tabba (2):
  KVM: arm64: Fix sign-extension of MMIO loads
  KVM: arm64: selftests: Add MMIO sign-extending load test

 arch/arm64/kvm/mmio.c                         |   7 +-
 tools/testing/selftests/kvm/Makefile.kvm      |   1 +
 .../selftests/kvm/arm64/mmio_sign_ext.c       | 133 ++++++++++++++++++
 3 files changed, 138 insertions(+), 3 deletions(-)
 create mode 100644 tools/testing/selftests/kvm/arm64/mmio_sign_ext.c


base-commit: 8cd9520d35a6c38db6567e97dd93b1f11f185dc6
-- 
2.39.5

[PATCH 1/2] KVM: arm64: Fix sign-extension of MMIO loads

[Fuad Tabba]

A sign-extending load from MMIO (LDRSB, LDRSH, LDRSW) delivers a
zero-extended value: in kvm_handle_mmio_return(), vcpu_data_host_to_guest()
masks the data to the access width after sign-extension, stripping the
sign bits.

Move vcpu_data_host_to_guest() ahead of sign-extension so the width mask
runs first. trace_kvm_mmio() moves with it and keeps reporting the raw
access-width data.

Fixes: b30070862edbd ("ARM64: KVM: MMIO support BE host running LE code")
Signed-off-by: Fuad Tabba <fuad.tabba@linux.dev>
---
 arch/arm64/kvm/mmio.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/arch/arm64/kvm/mmio.c b/arch/arm64/kvm/mmio.c
index e2285ed8c91de..d1c3a352d5a22 100644
--- a/arch/arm64/kvm/mmio.c
+++ b/arch/arm64/kvm/mmio.c
@@ -126,6 +126,10 @@ int kvm_handle_mmio_return(struct kvm_vcpu *vcpu)
 		len = kvm_vcpu_dabt_get_as(vcpu);
 		data = kvm_mmio_read_buf(run->mmio.data, len);
 
+		trace_kvm_mmio(KVM_TRACE_MMIO_READ, len, run->mmio.phys_addr,
+			       &data);
+		data = vcpu_data_host_to_guest(vcpu, data, len);
+
 		if (kvm_vcpu_dabt_issext(vcpu) &&
 		    len < sizeof(unsigned long)) {
 			mask = 1U << ((len * 8) - 1);
@@ -135,9 +139,6 @@ int kvm_handle_mmio_return(struct kvm_vcpu *vcpu)
 		if (!kvm_vcpu_dabt_issf(vcpu))
 			data = data & 0xffffffff;
 
-		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);
 	}
 
-- 
2.39.5

[PATCH 2/2] KVM: arm64: selftests: Add MMIO sign-extending load test

[Fuad Tabba]

Add a test for sign-extending MMIO loads (LDRSB, LDRSH, LDRSW) into Xt
and Wt destinations, with and without the sign bit set. The host supplies
the MMIO data and checks the guest register holds the sign-extended value.

Signed-off-by: Fuad Tabba <fuad.tabba@linux.dev>
---
 tools/testing/selftests/kvm/Makefile.kvm      |   1 +
 .../selftests/kvm/arm64/mmio_sign_ext.c       | 133 ++++++++++++++++++
 2 files changed, 134 insertions(+)
 create mode 100644 tools/testing/selftests/kvm/arm64/mmio_sign_ext.c

diff --git a/tools/testing/selftests/kvm/Makefile.kvm b/tools/testing/selftests/kvm/Makefile.kvm
index 9118a5a51b89f..0f5803a1092e1 100644
--- a/tools/testing/selftests/kvm/Makefile.kvm
+++ b/tools/testing/selftests/kvm/Makefile.kvm
@@ -171,6 +171,7 @@ TEST_GEN_PROGS_arm64 += arm64/hello_el2
 TEST_GEN_PROGS_arm64 += arm64/host_sve
 TEST_GEN_PROGS_arm64 += arm64/hypercalls
 TEST_GEN_PROGS_arm64 += arm64/external_aborts
+TEST_GEN_PROGS_arm64 += arm64/mmio_sign_ext
 TEST_GEN_PROGS_arm64 += arm64/page_fault_test
 TEST_GEN_PROGS_arm64 += arm64/psci_test
 TEST_GEN_PROGS_arm64 += arm64/sea_to_user
diff --git a/tools/testing/selftests/kvm/arm64/mmio_sign_ext.c b/tools/testing/selftests/kvm/arm64/mmio_sign_ext.c
new file mode 100644
index 0000000000000..d1efbccd1603a
--- /dev/null
+++ b/tools/testing/selftests/kvm/arm64/mmio_sign_ext.c
@@ -0,0 +1,133 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * mmio_sign_ext - Test sign-extending MMIO load emulation (LDRSB/LDRSH/LDRSW)
+ *
+ * Copyright (c) 2026 Google LLC
+ */
+
+#include "processor.h"
+#include "test_util.h"
+
+#define MMIO_ADDR	0x8000000ULL
+
+struct mmio_test {
+	const char *name;
+	uint64_t data;
+	uint8_t len;
+	uint64_t expected;
+};
+
+/* Paired 1:1, in order, with the loads in guest_code() below. */
+static const struct mmio_test tests[] = {
+	/* LDRSB Xt: byte sign-extended to 64 bits */
+	{ "LDRSB Xt 0xFF",	0xFF,		1, 0xFFFFFFFFFFFFFFFFULL },
+	{ "LDRSB Xt 0x7F",	0x7F,		1, 0x7FULL },
+
+	/* LDRSB Wt: byte sign-extended to 32 bits, upper 32 bits zeroed */
+	{ "LDRSB Wt 0xFF",	0xFF,		1, 0xFFFFFFFFULL },
+	{ "LDRSB Wt 0x7F",	0x7F,		1, 0x7FULL },
+
+	/* LDRSH Xt: halfword sign-extended to 64 bits */
+	{ "LDRSH Xt 0x8001",	0x8001,		2, 0xFFFFFFFFFFFF8001ULL },
+	{ "LDRSH Xt 0x7FFF",	0x7FFF,		2, 0x7FFFULL },
+
+	/* LDRSH Wt: halfword sign-extended to 32 bits, upper 32 bits zeroed */
+	{ "LDRSH Wt 0x8001",	0x8001,		2, 0xFFFF8001ULL },
+	{ "LDRSH Wt 0x7FFF",	0x7FFF,		2, 0x7FFFULL },
+
+	/* LDRSW Xt: word sign-extended to 64 bits (no Wt form) */
+	{ "LDRSW Xt 0x80000001", 0x80000001,	4, 0xFFFFFFFF80000001ULL },
+	{ "LDRSW Xt 0x7FFFFFFF", 0x7FFFFFFF,	4, 0x7FFFFFFFULL },
+};
+
+static void guest_code(void)
+{
+	uint64_t val;
+
+	asm volatile("ldrsb %0, [%1]" : "=r"(val) : "r"(MMIO_ADDR) : "memory");
+	GUEST_SYNC(val);
+
+	asm volatile("ldrsb %0, [%1]" : "=r"(val) : "r"(MMIO_ADDR) : "memory");
+	GUEST_SYNC(val);
+
+	asm volatile("ldrsb %w0, [%1]" : "=r"(val) : "r"(MMIO_ADDR) : "memory");
+	GUEST_SYNC(val);
+
+	asm volatile("ldrsb %w0, [%1]" : "=r"(val) : "r"(MMIO_ADDR) : "memory");
+	GUEST_SYNC(val);
+
+	asm volatile("ldrsh %0, [%1]" : "=r"(val) : "r"(MMIO_ADDR) : "memory");
+	GUEST_SYNC(val);
+
+	asm volatile("ldrsh %0, [%1]" : "=r"(val) : "r"(MMIO_ADDR) : "memory");
+	GUEST_SYNC(val);
+
+	asm volatile("ldrsh %w0, [%1]" : "=r"(val) : "r"(MMIO_ADDR) : "memory");
+	GUEST_SYNC(val);
+
+	asm volatile("ldrsh %w0, [%1]" : "=r"(val) : "r"(MMIO_ADDR) : "memory");
+	GUEST_SYNC(val);
+
+	asm volatile("ldrsw %0, [%1]" : "=r"(val) : "r"(MMIO_ADDR) : "memory");
+	GUEST_SYNC(val);
+
+	asm volatile("ldrsw %0, [%1]" : "=r"(val) : "r"(MMIO_ADDR) : "memory");
+	GUEST_SYNC(val);
+
+	GUEST_DONE();
+}
+
+static void handle_mmio(struct kvm_run *run, const struct mmio_test *t)
+{
+	TEST_ASSERT_EQ(run->mmio.phys_addr, MMIO_ADDR);
+	TEST_ASSERT(!run->mmio.is_write, "Expected MMIO read for %s", t->name);
+	TEST_ASSERT_EQ(run->mmio.len, t->len);
+
+	memset(run->mmio.data, 0, sizeof(run->mmio.data));
+	/* Works because arm64 KVM hosts are always little-endian. */
+	memcpy(run->mmio.data, &t->data, t->len);
+}
+
+int main(void)
+{
+	struct kvm_vcpu *vcpu;
+	struct kvm_vm *vm;
+	struct ucall uc;
+	unsigned int i;
+
+	vm = vm_create_with_one_vcpu(&vcpu, guest_code);
+	virt_map(vm, MMIO_ADDR, MMIO_ADDR, 1);
+
+	ksft_print_header();
+	ksft_set_plan(ARRAY_SIZE(tests));
+
+	for (i = 0; i < ARRAY_SIZE(tests); i++) {
+		const struct mmio_test *t = &tests[i];
+
+		vcpu_run(vcpu);
+		TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_MMIO);
+
+		handle_mmio(vcpu->run, t);
+		vcpu_run(vcpu);
+
+		switch (get_ucall(vcpu, &uc)) {
+		case UCALL_SYNC:
+			TEST_ASSERT_EQ(uc.args[1], t->expected);
+			break;
+		case UCALL_ABORT:
+			REPORT_GUEST_ASSERT(uc);
+			break;
+		default:
+			TEST_FAIL("Unexpected ucall for %s", t->name);
+		}
+
+		ksft_test_result_pass("%s\n", t->name);
+	}
+
+	vcpu_run(vcpu);
+	TEST_ASSERT(get_ucall(vcpu, &uc) == UCALL_DONE, "Expected UCALL_DONE");
+
+	kvm_vm_free(vm);
+
+	ksft_finished();
+}
-- 
2.39.5