From 3223560c93eb725f479fe20f462ce202a44803b8 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Thu, 16 Oct 2025 10:28:47 -0700
Subject: KVM: selftests: Define wrappers for common syscalls to assert success

Add kvm_<sycall> wrappers for munmap(), close(), fallocate(), and
ftruncate() to cut down on boilerplate code when a sycall is expected
to succeed, and to make it easier for developers to remember to assert
success.

Implement and use a macro framework similar to the kernel's SYSCALL_DEFINE
infrastructure to further cut down on boilerplate code, and to drastically
reduce the probability of typos as the kernel's syscall definitions can be
copy+paste almost verbatim.

Provide macros to build the raw <sycall>() wrappers as well, e.g. to
replace hand-coded wrappers (NUMA) or pure open-coded calls.

Reviewed-by: Ackerley Tng <ackerleytng@google.com>
Tested-by: Ackerley Tng <ackerleytng@google.com>
Reviewed-by: Shivank Garg <shivankg@amd.com>
Tested-by: Shivank Garg <shivankg@amd.com>
Link: https://lore.kernel.org/r/20251016172853.52451-7-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 tools/testing/selftests/kvm/arm64/vgic_irq.c       |  2 +-
 tools/testing/selftests/kvm/include/kvm_syscalls.h | 81 ++++++++++++++++++++++
 tools/testing/selftests/kvm/include/kvm_util.h     | 29 +-------
 .../testing/selftests/kvm/kvm_binary_stats_test.c  |  4 +-
 tools/testing/selftests/kvm/lib/kvm_util.c         | 31 +++------
 .../kvm/x86/private_mem_conversions_test.c         |  9 +--
 6 files changed, 96 insertions(+), 60 deletions(-)
 create mode 100644 tools/testing/selftests/kvm/include/kvm_syscalls.h

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/kvm/arm64/vgic_irq.c b/tools/testing/selftests/kvm/arm64/vgic_irq.c
index 6338f5bbdb70..8d7758f12280 100644
--- a/tools/testing/selftests/kvm/arm64/vgic_irq.c
+++ b/tools/testing/selftests/kvm/arm64/vgic_irq.c
@@ -636,7 +636,7 @@ static void kvm_routing_and_irqfd_check(struct kvm_vm *vm,
 	}
 
 	for (f = 0, i = intid; i < (uint64_t)intid + num; i++, f++)
-		close(fd[f]);
+		kvm_close(fd[f]);
 }
 
 /* handles the valid case: intid=0xffffffff num=1 */
diff --git a/tools/testing/selftests/kvm/include/kvm_syscalls.h b/tools/testing/selftests/kvm/include/kvm_syscalls.h
new file mode 100644
index 000000000000..d4e613162bba
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/kvm_syscalls.h
@@ -0,0 +1,81 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef SELFTEST_KVM_SYSCALLS_H
+#define SELFTEST_KVM_SYSCALLS_H
+
+#include <sys/syscall.h>
+
+#define MAP_ARGS0(m,...)
+#define MAP_ARGS1(m,t,a,...) m(t,a)
+#define MAP_ARGS2(m,t,a,...) m(t,a), MAP_ARGS1(m,__VA_ARGS__)
+#define MAP_ARGS3(m,t,a,...) m(t,a), MAP_ARGS2(m,__VA_ARGS__)
+#define MAP_ARGS4(m,t,a,...) m(t,a), MAP_ARGS3(m,__VA_ARGS__)
+#define MAP_ARGS5(m,t,a,...) m(t,a), MAP_ARGS4(m,__VA_ARGS__)
+#define MAP_ARGS6(m,t,a,...) m(t,a), MAP_ARGS5(m,__VA_ARGS__)
+#define MAP_ARGS(n,...) MAP_ARGS##n(__VA_ARGS__)
+
+#define __DECLARE_ARGS(t, a)	t a
+#define __UNPACK_ARGS(t, a)	a
+
+#define DECLARE_ARGS(nr_args, args...) MAP_ARGS(nr_args, __DECLARE_ARGS, args)
+#define UNPACK_ARGS(nr_args, args...) MAP_ARGS(nr_args, __UNPACK_ARGS, args)
+
+#define __KVM_SYSCALL_ERROR(_name, _ret) \
+	"%s failed, rc: %i errno: %i (%s)", (_name), (_ret), errno, strerror(errno)
+
+/* Define a kvm_<syscall>() API to assert success. */
+#define __KVM_SYSCALL_DEFINE(name, nr_args, args...)			\
+static inline void kvm_##name(DECLARE_ARGS(nr_args, args))		\
+{									\
+	int r;								\
+									\
+	r = name(UNPACK_ARGS(nr_args, args));				\
+	TEST_ASSERT(!r, __KVM_SYSCALL_ERROR(#name, r));			\
+}
+
+/*
+ * Macro to define syscall APIs, either because KVM selftests doesn't link to
+ * the standard library, e.g. libnuma, or because there is no library that yet
+ * provides the syscall.  These
+ */
+#define KVM_SYSCALL_DEFINE(name, nr_args, args...)			\
+static inline long name(DECLARE_ARGS(nr_args, args))			\
+{									\
+	return syscall(__NR_##name, UNPACK_ARGS(nr_args, args));	\
+}									\
+__KVM_SYSCALL_DEFINE(name, nr_args, args)
+
+/*
+ * Special case mmap(), as KVM selftest rarely/never specific an address,
+ * rarely specify an offset, and because the unique return code requires
+ * special handling anyways.
+ */
+static inline void *__kvm_mmap(size_t size, int prot, int flags, int fd,
+			       off_t offset)
+{
+	void *mem;
+
+	mem = mmap(NULL, size, prot, flags, fd, offset);
+	TEST_ASSERT(mem != MAP_FAILED, __KVM_SYSCALL_ERROR("mmap()",
+		    (int)(unsigned long)MAP_FAILED));
+	return mem;
+}
+
+static inline void *kvm_mmap(size_t size, int prot, int flags, int fd)
+{
+	return __kvm_mmap(size, prot, flags, fd, 0);
+}
+
+static inline int kvm_dup(int fd)
+{
+	int new_fd = dup(fd);
+
+	TEST_ASSERT(new_fd >= 0, __KVM_SYSCALL_ERROR("dup()", new_fd));
+	return new_fd;
+}
+
+__KVM_SYSCALL_DEFINE(munmap, 2, void *, mem, size_t, size);
+__KVM_SYSCALL_DEFINE(close, 1, int, fd);
+__KVM_SYSCALL_DEFINE(fallocate, 4, int, fd, int, mode, loff_t, offset, loff_t, len);
+__KVM_SYSCALL_DEFINE(ftruncate, 2, unsigned int, fd, off_t, length);
+
+#endif /* SELFTEST_KVM_SYSCALLS_H */
diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h
index d3f3e455c031..af52cd938b50 100644
--- a/tools/testing/selftests/kvm/include/kvm_util.h
+++ b/tools/testing/selftests/kvm/include/kvm_util.h
@@ -23,6 +23,7 @@
 
 #include <pthread.h>
 
+#include "kvm_syscalls.h"
 #include "kvm_util_arch.h"
 #include "kvm_util_types.h"
 #include "sparsebit.h"
@@ -283,34 +284,6 @@ static inline bool kvm_has_cap(long cap)
 	return kvm_check_cap(cap);
 }
 
-#define __KVM_SYSCALL_ERROR(_name, _ret) \
-	"%s failed, rc: %i errno: %i (%s)", (_name), (_ret), errno, strerror(errno)
-
-static inline void *__kvm_mmap(size_t size, int prot, int flags, int fd,
-			       off_t offset)
-{
-	void *mem;
-
-	mem = mmap(NULL, size, prot, flags, fd, offset);
-	TEST_ASSERT(mem != MAP_FAILED, __KVM_SYSCALL_ERROR("mmap()",
-		    (int)(unsigned long)MAP_FAILED));
-
-	return mem;
-}
-
-static inline void *kvm_mmap(size_t size, int prot, int flags, int fd)
-{
-	return __kvm_mmap(size, prot, flags, fd, 0);
-}
-
-static inline void kvm_munmap(void *mem, size_t size)
-{
-	int ret;
-
-	ret = munmap(mem, size);
-	TEST_ASSERT(!ret, __KVM_SYSCALL_ERROR("munmap()", ret));
-}
-
 /*
  * Use the "inner", double-underscore macro when reporting errors from within
  * other macros so that the name of ioctl() and not its literal numeric value
diff --git a/tools/testing/selftests/kvm/kvm_binary_stats_test.c b/tools/testing/selftests/kvm/kvm_binary_stats_test.c
index f02355c3c4c2..b7dbde9c0843 100644
--- a/tools/testing/selftests/kvm/kvm_binary_stats_test.c
+++ b/tools/testing/selftests/kvm/kvm_binary_stats_test.c
@@ -239,14 +239,14 @@ int main(int argc, char *argv[])
 		 * single stats file works and doesn't cause explosions.
 		 */
 		vm_stats_fds = vm_get_stats_fd(vms[i]);
-		stats_test(dup(vm_stats_fds));
+		stats_test(kvm_dup(vm_stats_fds));
 
 		/* Verify userspace can instantiate multiple stats files. */
 		stats_test(vm_get_stats_fd(vms[i]));
 
 		for (j = 0; j < max_vcpu; ++j) {
 			vcpu_stats_fds[j] = vcpu_get_stats_fd(vcpus[i * max_vcpu + j]);
-			stats_test(dup(vcpu_stats_fds[j]));
+			stats_test(kvm_dup(vcpu_stats_fds[j]));
 			stats_test(vcpu_get_stats_fd(vcpus[i * max_vcpu + j]));
 		}
 
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 1a93d6361671..203e33697492 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -704,8 +704,6 @@ userspace_mem_region_find(struct kvm_vm *vm, uint64_t start, uint64_t end)
 
 static void kvm_stats_release(struct kvm_binary_stats *stats)
 {
-	int ret;
-
 	if (stats->fd < 0)
 		return;
 
@@ -714,8 +712,7 @@ static void kvm_stats_release(struct kvm_binary_stats *stats)
 		stats->desc = NULL;
 	}
 
-	ret = close(stats->fd);
-	TEST_ASSERT(!ret,  __KVM_SYSCALL_ERROR("close()", ret));
+	kvm_close(stats->fd);
 	stats->fd = -1;
 }
 
@@ -738,8 +735,6 @@ __weak void vcpu_arch_free(struct kvm_vcpu *vcpu)
  */
 static void vm_vcpu_rm(struct kvm_vm *vm, struct kvm_vcpu *vcpu)
 {
-	int ret;
-
 	if (vcpu->dirty_gfns) {
 		kvm_munmap(vcpu->dirty_gfns, vm->dirty_ring_size);
 		vcpu->dirty_gfns = NULL;
@@ -747,9 +742,7 @@ static void vm_vcpu_rm(struct kvm_vm *vm, struct kvm_vcpu *vcpu)
 
 	kvm_munmap(vcpu->run, vcpu_mmap_sz());
 
-	ret = close(vcpu->fd);
-	TEST_ASSERT(!ret,  __KVM_SYSCALL_ERROR("close()", ret));
-
+	kvm_close(vcpu->fd);
 	kvm_stats_release(&vcpu->stats);
 
 	list_del(&vcpu->list);
@@ -761,16 +754,12 @@ static void vm_vcpu_rm(struct kvm_vm *vm, struct kvm_vcpu *vcpu)
 void kvm_vm_release(struct kvm_vm *vmp)
 {
 	struct kvm_vcpu *vcpu, *tmp;
-	int ret;
 
 	list_for_each_entry_safe(vcpu, tmp, &vmp->vcpus, list)
 		vm_vcpu_rm(vmp, vcpu);
 
-	ret = close(vmp->fd);
-	TEST_ASSERT(!ret,  __KVM_SYSCALL_ERROR("close()", ret));
-
-	ret = close(vmp->kvm_fd);
-	TEST_ASSERT(!ret,  __KVM_SYSCALL_ERROR("close()", ret));
+	kvm_close(vmp->fd);
+	kvm_close(vmp->kvm_fd);
 
 	/* Free cached stats metadata and close FD */
 	kvm_stats_release(&vmp->stats);
@@ -828,7 +817,7 @@ void kvm_vm_free(struct kvm_vm *vmp)
 int kvm_memfd_alloc(size_t size, bool hugepages)
 {
 	int memfd_flags = MFD_CLOEXEC;
-	int fd, r;
+	int fd;
 
 	if (hugepages)
 		memfd_flags |= MFD_HUGETLB;
@@ -836,11 +825,8 @@ int kvm_memfd_alloc(size_t size, bool hugepages)
 	fd = memfd_create("kvm_selftest", memfd_flags);
 	TEST_ASSERT(fd != -1, __KVM_SYSCALL_ERROR("memfd_create()", fd));
 
-	r = ftruncate(fd, size);
-	TEST_ASSERT(!r, __KVM_SYSCALL_ERROR("ftruncate()", r));
-
-	r = fallocate(fd, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, 0, size);
-	TEST_ASSERT(!r, __KVM_SYSCALL_ERROR("fallocate()", r));
+	kvm_ftruncate(fd, size);
+	kvm_fallocate(fd, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, 0, size);
 
 	return fd;
 }
@@ -1084,8 +1070,7 @@ void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type,
 			 * needing to track if the fd is owned by the framework
 			 * or by the caller.
 			 */
-			guest_memfd = dup(guest_memfd);
-			TEST_ASSERT(guest_memfd >= 0, __KVM_SYSCALL_ERROR("dup()", guest_memfd));
+			guest_memfd = kvm_dup(guest_memfd);
 		}
 
 		region->region.guest_memfd = guest_memfd;
diff --git a/tools/testing/selftests/kvm/x86/private_mem_conversions_test.c b/tools/testing/selftests/kvm/x86/private_mem_conversions_test.c
index 82a8d88b5338..1969f4ab9b28 100644
--- a/tools/testing/selftests/kvm/x86/private_mem_conversions_test.c
+++ b/tools/testing/selftests/kvm/x86/private_mem_conversions_test.c
@@ -380,7 +380,7 @@ static void test_mem_conversions(enum vm_mem_backing_src_type src_type, uint32_t
 	struct kvm_vcpu *vcpus[KVM_MAX_VCPUS];
 	pthread_t threads[KVM_MAX_VCPUS];
 	struct kvm_vm *vm;
-	int memfd, i, r;
+	int memfd, i;
 
 	const struct vm_shape shape = {
 		.mode = VM_MODE_DEFAULT,
@@ -428,11 +428,8 @@ static void test_mem_conversions(enum vm_mem_backing_src_type src_type, uint32_t
 	 * should prevent the VM from being fully destroyed until the last
 	 * reference to the guest_memfd is also put.
 	 */
-	r = fallocate(memfd, FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE, 0, memfd_size);
-	TEST_ASSERT(!r, __KVM_SYSCALL_ERROR("fallocate()", r));
-
-	r = fallocate(memfd, FALLOC_FL_KEEP_SIZE, 0, memfd_size);
-	TEST_ASSERT(!r, __KVM_SYSCALL_ERROR("fallocate()", r));
+	kvm_fallocate(memfd, FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE, 0, memfd_size);
+	kvm_fallocate(memfd, FALLOC_FL_KEEP_SIZE, 0, memfd_size);
 
 	close(memfd);
 }
-- 
cgit v1.2.3


From 29dc539d74abd1ec4e509fda29bc821f3586d333 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Thu, 16 Oct 2025 10:28:48 -0700
Subject: KVM: selftests: Report stacktraces SIGBUS, SIGSEGV, SIGILL, and
 SIGFPE by default

Register handlers for signals for all selftests that are likely happen due
to test (or kernel) bugs, and explicitly fail tests on unexpected signals
so that users get a stack trace, i.e. don't have to go spelunking to do
basic triage.

Register the handlers as early as possible, to catch as many unexpected
signals as possible, and also so that the common code doesn't clobber a
handler that's installed by test (or arch) code.

Tested-by: Ackerley Tng <ackerleytng@google.com>
Reviewed-by: Ackerley Tng <ackerleytng@google.com>
Reviewed-by: Shivank Garg <shivankg@amd.com>
Tested-by: Shivank Garg <shivankg@amd.com>
Link: https://lore.kernel.org/r/20251016172853.52451-8-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 tools/testing/selftests/kvm/lib/kvm_util.c | 24 ++++++++++++++++++++++++
 1 file changed, 24 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 203e33697492..5744643d9ec3 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -2290,11 +2290,35 @@ __weak void kvm_selftest_arch_init(void)
 {
 }
 
+static void report_unexpected_signal(int signum)
+{
+#define KVM_CASE_SIGNUM(sig)					\
+	case sig: TEST_FAIL("Unexpected " #sig " (%d)\n", signum)
+
+	switch (signum) {
+	KVM_CASE_SIGNUM(SIGBUS);
+	KVM_CASE_SIGNUM(SIGSEGV);
+	KVM_CASE_SIGNUM(SIGILL);
+	KVM_CASE_SIGNUM(SIGFPE);
+	default:
+		TEST_FAIL("Unexpected signal %d\n", signum);
+	}
+}
+
 void __attribute((constructor)) kvm_selftest_init(void)
 {
+	struct sigaction sig_sa = {
+		.sa_handler = report_unexpected_signal,
+	};
+
 	/* Tell stdout not to buffer its content. */
 	setbuf(stdout, NULL);
 
+	sigaction(SIGBUS, &sig_sa, NULL);
+	sigaction(SIGSEGV, &sig_sa, NULL);
+	sigaction(SIGILL, &sig_sa, NULL);
+	sigaction(SIGFPE, &sig_sa, NULL);
+
 	guest_random_seed = last_guest_seed = random();
 	pr_info("Random seed: 0x%x\n", guest_random_seed);
 
-- 
cgit v1.2.3


From 2189d78269c5055e6014862cb4d47f0613204856 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Thu, 16 Oct 2025 10:28:49 -0700
Subject: KVM: selftests: Add additional equivalents to libnuma APIs in KVM's
 numaif.h

Add APIs for all syscalls defined in the kernel's mm/mempolicy.c to match
those that would be provided by linking to libnuma.  Opportunistically use
the recently inroduced KVM_SYSCALL_DEFINE() builders to take care of the
boilerplate, and to fix a flaw where the two existing wrappers would
generate multiple symbols if numaif.h were to be included multiple times.

Reviewed-by: Ackerley Tng <ackerleytng@google.com>
Tested-by: Ackerley Tng <ackerleytng@google.com>
Reviewed-by: Shivank Garg <shivankg@amd.com>
Tested-by: Shivank Garg <shivankg@amd.com>
Link: https://lore.kernel.org/r/20251016172853.52451-9-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 tools/testing/selftests/kvm/include/numaif.h     | 40 ++++++++++++++----------
 tools/testing/selftests/kvm/x86/xapic_ipi_test.c |  5 ++-
 2 files changed, 25 insertions(+), 20 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/kvm/include/numaif.h b/tools/testing/selftests/kvm/include/numaif.h
index b020547403fd..aaa4ac174890 100644
--- a/tools/testing/selftests/kvm/include/numaif.h
+++ b/tools/testing/selftests/kvm/include/numaif.h
@@ -13,23 +13,29 @@
 #ifndef SELFTEST_KVM_NUMAIF_H
 #define SELFTEST_KVM_NUMAIF_H
 
-#define __NR_get_mempolicy 239
-#define __NR_migrate_pages 256
-
-/* System calls */
-long get_mempolicy(int *policy, const unsigned long *nmask,
-		   unsigned long maxnode, void *addr, int flags)
-{
-	return syscall(__NR_get_mempolicy, policy, nmask,
-		       maxnode, addr, flags);
-}
-
-long migrate_pages(int pid, unsigned long maxnode,
-		   const unsigned long *frommask,
-		   const unsigned long *tomask)
-{
-	return syscall(__NR_migrate_pages, pid, maxnode, frommask, tomask);
-}
+#include <linux/mempolicy.h>
+
+#include "kvm_syscalls.h"
+
+KVM_SYSCALL_DEFINE(get_mempolicy, 5, int *, policy, const unsigned long *, nmask,
+		   unsigned long, maxnode, void *, addr, int, flags);
+
+KVM_SYSCALL_DEFINE(set_mempolicy, 3, int, mode, const unsigned long *, nmask,
+		   unsigned long, maxnode);
+
+KVM_SYSCALL_DEFINE(set_mempolicy_home_node, 4, unsigned long, start,
+		   unsigned long, len, unsigned long, home_node,
+		   unsigned long, flags);
+
+KVM_SYSCALL_DEFINE(migrate_pages, 4, int, pid, unsigned long, maxnode,
+		   const unsigned long *, frommask, const unsigned long *, tomask);
+
+KVM_SYSCALL_DEFINE(move_pages, 6, int, pid, unsigned long, count, void *, pages,
+		   const int *, nodes, int *, status, int, flags);
+
+KVM_SYSCALL_DEFINE(mbind, 6, void *, addr, unsigned long, size, int, mode,
+		   const unsigned long *, nodemask, unsigned long, maxnode,
+		   unsigned int, flags);
 
 /* Policies */
 #define MPOL_DEFAULT	 0
diff --git a/tools/testing/selftests/kvm/x86/xapic_ipi_test.c b/tools/testing/selftests/kvm/x86/xapic_ipi_test.c
index 35cb9de54a82..ae4a4b6c05ca 100644
--- a/tools/testing/selftests/kvm/x86/xapic_ipi_test.c
+++ b/tools/testing/selftests/kvm/x86/xapic_ipi_test.c
@@ -256,7 +256,7 @@ void do_migrations(struct test_data_page *data, int run_secs, int delay_usecs,
 	int nodes = 0;
 	time_t start_time, last_update, now;
 	time_t interval_secs = 1;
-	int i, r;
+	int i;
 	int from, to;
 	unsigned long bit;
 	uint64_t hlt_count;
@@ -267,9 +267,8 @@ void do_migrations(struct test_data_page *data, int run_secs, int delay_usecs,
 		delay_usecs);
 
 	/* Get set of first 64 numa nodes available */
-	r = get_mempolicy(NULL, &nodemask, sizeof(nodemask) * 8,
+	kvm_get_mempolicy(NULL, &nodemask, sizeof(nodemask) * 8,
 			  0, MPOL_F_MEMS_ALLOWED);
-	TEST_ASSERT(r == 0, "get_mempolicy failed errno=%d", errno);
 
 	fprintf(stderr, "Numa nodes found amongst first %lu possible nodes "
 		"(each 1-bit indicates node is present): %#lx\n",
-- 
cgit v1.2.3


From fe7baebb99de95f171911d085abcfab1db04a7ed Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Thu, 16 Oct 2025 10:28:50 -0700
Subject: KVM: selftests: Use proper uAPI headers to pick up mempolicy.h
 definitions

Drop the KVM's re-definitions of MPOL_xxx flags in numaif.h as they are
defined by the already-included, kernel-provided mempolicy.h.  The only
reason the duplicate definitions don't cause compiler warnings is because
they are identical, but only on x86-64!  The syscall numbers in particular
are subtly x86_64-specific, i.e. will cause problems if/when numaif.h is
used outsize of x86.

Opportunistically clean up the file comment as the license information is
covered by the SPDX header, the path is superfluous, and as above the
comment about the contents is flat out wrong.

Fixes: 346b59f220a2 ("KVM: selftests: Add missing header file needed by xAPIC IPI tests")
Reviewed-by: Shivank Garg <shivankg@amd.com>
Tested-by: Shivank Garg <shivankg@amd.com>
Link: https://lore.kernel.org/r/20251016172853.52451-10-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 tools/testing/selftests/kvm/include/numaif.h | 32 +---------------------------
 1 file changed, 1 insertion(+), 31 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/kvm/include/numaif.h b/tools/testing/selftests/kvm/include/numaif.h
index aaa4ac174890..1554003c40a1 100644
--- a/tools/testing/selftests/kvm/include/numaif.h
+++ b/tools/testing/selftests/kvm/include/numaif.h
@@ -1,14 +1,5 @@
 /* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * tools/testing/selftests/kvm/include/numaif.h
- *
- * Copyright (C) 2020, Google LLC.
- *
- * This work is licensed under the terms of the GNU GPL, version 2.
- *
- * Header file that provides access to NUMA API functions not explicitly
- * exported to user space.
- */
+/* Copyright (C) 2020, Google LLC. */
 
 #ifndef SELFTEST_KVM_NUMAIF_H
 #define SELFTEST_KVM_NUMAIF_H
@@ -37,25 +28,4 @@ KVM_SYSCALL_DEFINE(mbind, 6, void *, addr, unsigned long, size, int, mode,
 		   const unsigned long *, nodemask, unsigned long, maxnode,
 		   unsigned int, flags);
 
-/* Policies */
-#define MPOL_DEFAULT	 0
-#define MPOL_PREFERRED	 1
-#define MPOL_BIND	 2
-#define MPOL_INTERLEAVE	 3
-
-#define MPOL_MAX MPOL_INTERLEAVE
-
-/* Flags for get_mem_policy */
-#define MPOL_F_NODE	    (1<<0)  /* return next il node or node of address */
-				    /* Warning: MPOL_F_NODE is unsupported and
-				     * subject to change. Don't use.
-				     */
-#define MPOL_F_ADDR	    (1<<1)  /* look up vma using address */
-#define MPOL_F_MEMS_ALLOWED (1<<2)  /* query nodes allowed in cpuset */
-
-/* Flags for mbind */
-#define MPOL_MF_STRICT	     (1<<0) /* Verify existing pages in the mapping */
-#define MPOL_MF_MOVE	     (1<<1) /* Move pages owned by this process to conform to mapping */
-#define MPOL_MF_MOVE_ALL     (1<<2) /* Move every page to conform to mapping */
-
 #endif /* SELFTEST_KVM_NUMAIF_H */
-- 
cgit v1.2.3


From e698e89b3ed1772e543a5ab4c072b9bbdb730948 Mon Sep 17 00:00:00 2001
From: Shivank Garg <shivankg@amd.com>
Date: Thu, 16 Oct 2025 10:28:51 -0700
Subject: KVM: selftests: Add helpers to probe for NUMA support, and multi-node
 systems

Add NUMA helpers to probe for support/availability and to check if the
test is running on a multi-node system.  The APIs will be used to verify
guest_memfd NUMA support.

Signed-off-by: Shivank Garg <shivankg@amd.com>
[sean: land helpers in numaif.h, add comments, tweak names]
Link: https://lore.kernel.org/r/20251016172853.52451-11-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 tools/testing/selftests/kvm/include/numaif.h | 52 ++++++++++++++++++++++++++++
 1 file changed, 52 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/kvm/include/numaif.h b/tools/testing/selftests/kvm/include/numaif.h
index 1554003c40a1..29572a6d789c 100644
--- a/tools/testing/selftests/kvm/include/numaif.h
+++ b/tools/testing/selftests/kvm/include/numaif.h
@@ -4,6 +4,8 @@
 #ifndef SELFTEST_KVM_NUMAIF_H
 #define SELFTEST_KVM_NUMAIF_H
 
+#include <dirent.h>
+
 #include <linux/mempolicy.h>
 
 #include "kvm_syscalls.h"
@@ -28,4 +30,54 @@ KVM_SYSCALL_DEFINE(mbind, 6, void *, addr, unsigned long, size, int, mode,
 		   const unsigned long *, nodemask, unsigned long, maxnode,
 		   unsigned int, flags);
 
+static inline int get_max_numa_node(void)
+{
+	struct dirent *de;
+	int max_node = 0;
+	DIR *d;
+
+	/*
+	 * Assume there's a single node if the kernel doesn't support NUMA,
+	 * or if no nodes are found.
+	 */
+	d = opendir("/sys/devices/system/node");
+	if (!d)
+		return 0;
+
+	while ((de = readdir(d)) != NULL) {
+		int node_id;
+		char *endptr;
+
+		if (strncmp(de->d_name, "node", 4) != 0)
+			continue;
+
+		node_id = strtol(de->d_name + 4, &endptr, 10);
+		if (*endptr != '\0')
+			continue;
+
+		if (node_id > max_node)
+			max_node = node_id;
+	}
+	closedir(d);
+
+	return max_node;
+}
+
+static bool is_numa_available(void)
+{
+	/*
+	 * Probe for NUMA by doing a dummy get_mempolicy().  If the syscall
+	 * fails with ENOSYS, then the kernel was built without NUMA support.
+	 * if the syscall fails with EPERM, then the process/user lacks the
+	 * necessary capabilities (CAP_SYS_NICE).
+	 */
+	return !get_mempolicy(NULL, NULL, 0, NULL, 0) ||
+		(errno != ENOSYS && errno != EPERM);
+}
+
+static inline bool is_multi_numa_node_system(void)
+{
+	return is_numa_available() && get_max_numa_node() >= 1;
+}
+
 #endif /* SELFTEST_KVM_NUMAIF_H */
-- 
cgit v1.2.3


From 38ccc50ac037ab79609c33556b696064ef52521c Mon Sep 17 00:00:00 2001
From: Shivank Garg <shivankg@amd.com>
Date: Thu, 16 Oct 2025 10:28:52 -0700
Subject: KVM: selftests: Add guest_memfd tests for mmap and NUMA policy
 support

Add tests for NUMA memory policy binding and NUMA aware allocation in
guest_memfd. This extends the existing selftests by adding proper
validation for:
  - KVM GMEM set_policy and get_policy() vm_ops functionality using
    mbind() and get_mempolicy()
  - NUMA policy application before and after memory allocation

Run the NUMA mbind() test with and without INIT_SHARED, as KVM should allow
doing mbind(), madvise(), etc. on guest-private memory, e.g. so that
userspace can set NUMA policy for CoCo VMs.

Run the NUMA allocation test only for INIT_SHARED, i.e. if the host can't
fault-in memory (via direct access, madvise(), etc.) as move_pages()
returns -ENOENT if the page hasn't been faulted in (walks the host page
tables to find the associated folio)

[sean: don't skip entire test when running on non-NUMA system, test mbind()
       with private memory, provide more info in assert messages]

Signed-off-by: Shivank Garg <shivankg@amd.com>
Tested-by: Ashish Kalra <ashish.kalra@amd.com>
Link: https://lore.kernel.org/r/20251016172853.52451-12-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 tools/testing/selftests/kvm/guest_memfd_test.c | 98 ++++++++++++++++++++++++++
 1 file changed, 98 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/kvm/guest_memfd_test.c b/tools/testing/selftests/kvm/guest_memfd_test.c
index e7d9aeb418d3..618c937f3c90 100644
--- a/tools/testing/selftests/kvm/guest_memfd_test.c
+++ b/tools/testing/selftests/kvm/guest_memfd_test.c
@@ -19,6 +19,7 @@
 #include <sys/stat.h>
 
 #include "kvm_util.h"
+#include "numaif.h"
 #include "test_util.h"
 #include "ucall_common.h"
 
@@ -75,6 +76,101 @@ static void test_mmap_supported(int fd, size_t total_size)
 	kvm_munmap(mem, total_size);
 }
 
+static void test_mbind(int fd, size_t total_size)
+{
+	const unsigned long nodemask_0 = 1; /* nid: 0 */
+	unsigned long nodemask = 0;
+	unsigned long maxnode = 8;
+	int policy;
+	char *mem;
+	int ret;
+
+	if (!is_multi_numa_node_system())
+		return;
+
+	mem = kvm_mmap(total_size, PROT_READ | PROT_WRITE, MAP_SHARED, fd);
+
+	/* Test MPOL_INTERLEAVE policy */
+	kvm_mbind(mem, page_size * 2, MPOL_INTERLEAVE, &nodemask_0, maxnode, 0);
+	kvm_get_mempolicy(&policy, &nodemask, maxnode, mem, MPOL_F_ADDR);
+	TEST_ASSERT(policy == MPOL_INTERLEAVE && nodemask == nodemask_0,
+		    "Wanted MPOL_INTERLEAVE (%u) and nodemask 0x%lx, got %u and 0x%lx",
+		    MPOL_INTERLEAVE, nodemask_0, policy, nodemask);
+
+	/* Test basic MPOL_BIND policy */
+	kvm_mbind(mem + page_size * 2, page_size * 2, MPOL_BIND, &nodemask_0, maxnode, 0);
+	kvm_get_mempolicy(&policy, &nodemask, maxnode, mem + page_size * 2, MPOL_F_ADDR);
+	TEST_ASSERT(policy == MPOL_BIND && nodemask == nodemask_0,
+		    "Wanted MPOL_BIND (%u) and nodemask 0x%lx, got %u and 0x%lx",
+		    MPOL_BIND, nodemask_0, policy, nodemask);
+
+	/* Test MPOL_DEFAULT policy */
+	kvm_mbind(mem, total_size, MPOL_DEFAULT, NULL, 0, 0);
+	kvm_get_mempolicy(&policy, &nodemask, maxnode, mem, MPOL_F_ADDR);
+	TEST_ASSERT(policy == MPOL_DEFAULT && !nodemask,
+		    "Wanted MPOL_DEFAULT (%u) and nodemask 0x0, got %u and 0x%lx",
+		    MPOL_DEFAULT, policy, nodemask);
+
+	/* Test with invalid policy */
+	ret = mbind(mem, page_size, 999, &nodemask_0, maxnode, 0);
+	TEST_ASSERT(ret == -1 && errno == EINVAL,
+		    "mbind with invalid policy should fail with EINVAL");
+
+	kvm_munmap(mem, total_size);
+}
+
+static void test_numa_allocation(int fd, size_t total_size)
+{
+	unsigned long node0_mask = 1;  /* Node 0 */
+	unsigned long node1_mask = 2;  /* Node 1 */
+	unsigned long maxnode = 8;
+	void *pages[4];
+	int status[4];
+	char *mem;
+	int i;
+
+	if (!is_multi_numa_node_system())
+		return;
+
+	mem = kvm_mmap(total_size, PROT_READ | PROT_WRITE, MAP_SHARED, fd);
+
+	for (i = 0; i < 4; i++)
+		pages[i] = (char *)mem + page_size * i;
+
+	/* Set NUMA policy after allocation */
+	memset(mem, 0xaa, page_size);
+	kvm_mbind(pages[0], page_size, MPOL_BIND, &node0_mask, maxnode, 0);
+	kvm_fallocate(fd, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, 0, page_size);
+
+	/* Set NUMA policy before allocation */
+	kvm_mbind(pages[0], page_size * 2, MPOL_BIND, &node1_mask, maxnode, 0);
+	kvm_mbind(pages[2], page_size * 2, MPOL_BIND, &node0_mask, maxnode, 0);
+	memset(mem, 0xaa, total_size);
+
+	/* Validate if pages are allocated on specified NUMA nodes */
+	kvm_move_pages(0, 4, pages, NULL, status, 0);
+	TEST_ASSERT(status[0] == 1, "Expected page 0 on node 1, got it on node %d", status[0]);
+	TEST_ASSERT(status[1] == 1, "Expected page 1 on node 1, got it on node %d", status[1]);
+	TEST_ASSERT(status[2] == 0, "Expected page 2 on node 0, got it on node %d", status[2]);
+	TEST_ASSERT(status[3] == 0, "Expected page 3 on node 0, got it on node %d", status[3]);
+
+	/* Punch hole for all pages */
+	kvm_fallocate(fd, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, 0, total_size);
+
+	/* Change NUMA policy nodes and reallocate */
+	kvm_mbind(pages[0], page_size * 2, MPOL_BIND, &node0_mask, maxnode, 0);
+	kvm_mbind(pages[2], page_size * 2, MPOL_BIND, &node1_mask, maxnode, 0);
+	memset(mem, 0xaa, total_size);
+
+	kvm_move_pages(0, 4, pages, NULL, status, 0);
+	TEST_ASSERT(status[0] == 0, "Expected page 0 on node 0, got it on node %d", status[0]);
+	TEST_ASSERT(status[1] == 0, "Expected page 1 on node 0, got it on node %d", status[1]);
+	TEST_ASSERT(status[2] == 1, "Expected page 2 on node 1, got it on node %d", status[2]);
+	TEST_ASSERT(status[3] == 1, "Expected page 3 on node 1, got it on node %d", status[3]);
+
+	kvm_munmap(mem, total_size);
+}
+
 static void test_fault_sigbus(int fd, size_t accessible_size, size_t map_size)
 {
 	const char val = 0xaa;
@@ -273,11 +369,13 @@ static void __test_guest_memfd(struct kvm_vm *vm, uint64_t flags)
 		if (flags & GUEST_MEMFD_FLAG_INIT_SHARED) {
 			gmem_test(mmap_supported, vm, flags);
 			gmem_test(fault_overflow, vm, flags);
+			gmem_test(numa_allocation, vm, flags);
 		} else {
 			gmem_test(fault_private, vm, flags);
 		}
 
 		gmem_test(mmap_cow, vm, flags);
+		gmem_test(mbind, vm, flags);
 	} else {
 		gmem_test(mmap_not_supported, vm, flags);
 	}
-- 
cgit v1.2.3


From b146b289f759315fd27402a40bc15214515e6c45 Mon Sep 17 00:00:00 2001
From: Brendan Jackman <jackmanb@google.com>
Date: Tue, 7 Oct 2025 19:12:31 +0000
Subject: KVM: selftests: Don't fall over in mmu_stress_test when only one CPU
 is present

Running mmu_stress_test on a system with only one CPU is not a recipe for
success. However, there's no clear-cut reason why it absolutely
shouldn't work, so the test shouldn't completely reject such a platform.

At present, the *3/4 calculation will return zero on these platforms and
the test fails. So, instead just skip that calculation.

Suggested-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Brendan Jackman <jackmanb@google.com>
Link: https://lore.kernel.org/r/20251007-b4-kvm-mmu-stresstest-1proc-v1-1-8c95aa0e30b6@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 tools/testing/selftests/kvm/mmu_stress_test.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/kvm/mmu_stress_test.c b/tools/testing/selftests/kvm/mmu_stress_test.c
index 37b7e6524533..c799e0d0694f 100644
--- a/tools/testing/selftests/kvm/mmu_stress_test.c
+++ b/tools/testing/selftests/kvm/mmu_stress_test.c
@@ -263,8 +263,10 @@ static void calc_default_nr_vcpus(void)
 	TEST_ASSERT(!r, "sched_getaffinity failed, errno = %d (%s)",
 		    errno, strerror(errno));
 
-	nr_vcpus = CPU_COUNT(&possible_mask) * 3/4;
+	nr_vcpus = CPU_COUNT(&possible_mask);
 	TEST_ASSERT(nr_vcpus > 0, "Uh, no CPUs?");
+	if (nr_vcpus >= 2)
+		nr_vcpus = nr_vcpus * 3/4;
 }
 
 int main(int argc, char *argv[])
-- 
cgit v1.2.3


From 17e5a9b77716564540d81f0c1e6082d28cf305c9 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Tue, 7 Oct 2025 15:30:57 -0700
Subject: KVM: selftests: Forcefully override ARCH from x86_64 to x86

Forcefully override ARCH from x86_64 to x86 to handle the scenario where
the user specifies ARCH=x86_64 on the command line.

Fixes: 9af04539d474 ("KVM: selftests: Override ARCH for x86_64 instead of using ARCH_DIR")
Cc: stable@vger.kernel.org
Reported-by: David Matlack <dmatlack@google.com>
Closes: https://lore.kernel.org/all/20250724213130.3374922-1-dmatlack@google.com
Link: https://lore.kernel.org/r/20251007223057.368082-1-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 tools/testing/selftests/kvm/Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index d9fffe06d3ea..f2b223072b62 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -6,7 +6,7 @@ ARCH            ?= $(SUBARCH)
 ifeq ($(ARCH),$(filter $(ARCH),arm64 s390 riscv x86 x86_64 loongarch))
 # Top-level selftests allows ARCH=x86_64 :-(
 ifeq ($(ARCH),x86_64)
-	ARCH := x86
+	override ARCH := x86
 endif
 include Makefile.kvm
 else
-- 
cgit v1.2.3


From 9e4ce7a89e0b5f1d400f05533f38fe2590166ea6 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Tue, 7 Oct 2025 15:45:15 -0700
Subject: KVM: selftests: Use "gpa" and "gva" for local variable names in
 pre-fault test

Rename guest_test_{phys,virt}_mem to g{p,v}a in the pre-fault memory test
to shorten line lengths and to use standard terminology.

Opportunsitically use "base_gva" in the guest code instead of "base_gpa"
to match the host side code, which now passes in "gva" (and because
referencing the virtual address avoids having to know that the data is
identity mapped).

No functional change intended.

Cc: Yan Zhao <yan.y.zhao@intel.com>
Link: https://lore.kernel.org/r/20251007224515.374516-1-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 .../testing/selftests/kvm/pre_fault_memory_test.c  | 32 ++++++++++------------
 1 file changed, 14 insertions(+), 18 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/kvm/pre_fault_memory_test.c b/tools/testing/selftests/kvm/pre_fault_memory_test.c
index f04768c1d2e4..93e603d91311 100644
--- a/tools/testing/selftests/kvm/pre_fault_memory_test.c
+++ b/tools/testing/selftests/kvm/pre_fault_memory_test.c
@@ -17,13 +17,13 @@
 #define TEST_NPAGES		(TEST_SIZE / PAGE_SIZE)
 #define TEST_SLOT		10
 
-static void guest_code(uint64_t base_gpa)
+static void guest_code(uint64_t base_gva)
 {
 	volatile uint64_t val __used;
 	int i;
 
 	for (i = 0; i < TEST_NPAGES; i++) {
-		uint64_t *src = (uint64_t *)(base_gpa + i * PAGE_SIZE);
+		uint64_t *src = (uint64_t *)(base_gva + i * PAGE_SIZE);
 
 		val = *src;
 	}
@@ -161,6 +161,7 @@ static void pre_fault_memory(struct kvm_vcpu *vcpu, u64 base_gpa, u64 offset,
 
 static void __test_pre_fault_memory(unsigned long vm_type, bool private)
 {
+	uint64_t gpa, gva, alignment, guest_page_size;
 	const struct vm_shape shape = {
 		.mode = VM_MODE_DEFAULT,
 		.type = vm_type,
@@ -170,35 +171,30 @@ static void __test_pre_fault_memory(unsigned long vm_type, bool private)
 	struct kvm_vm *vm;
 	struct ucall uc;
 
-	uint64_t guest_test_phys_mem;
-	uint64_t guest_test_virt_mem;
-	uint64_t alignment, guest_page_size;
-
 	vm = vm_create_shape_with_one_vcpu(shape, &vcpu, guest_code);
 
 	alignment = guest_page_size = vm_guest_mode_params[VM_MODE_DEFAULT].page_size;
-	guest_test_phys_mem = (vm->max_gfn - TEST_NPAGES) * guest_page_size;
+	gpa = (vm->max_gfn - TEST_NPAGES) * guest_page_size;
 #ifdef __s390x__
 	alignment = max(0x100000UL, guest_page_size);
 #else
 	alignment = SZ_2M;
 #endif
-	guest_test_phys_mem = align_down(guest_test_phys_mem, alignment);
-	guest_test_virt_mem = guest_test_phys_mem & ((1ULL << (vm->va_bits - 1)) - 1);
+	gpa = align_down(gpa, alignment);
+	gva = gpa & ((1ULL << (vm->va_bits - 1)) - 1);
 
-	vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS,
-				    guest_test_phys_mem, TEST_SLOT, TEST_NPAGES,
-				    private ? KVM_MEM_GUEST_MEMFD : 0);
-	virt_map(vm, guest_test_virt_mem, guest_test_phys_mem, TEST_NPAGES);
+	vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, gpa, TEST_SLOT,
+				    TEST_NPAGES, private ? KVM_MEM_GUEST_MEMFD : 0);
+	virt_map(vm, gva, gpa, TEST_NPAGES);
 
 	if (private)
-		vm_mem_set_private(vm, guest_test_phys_mem, TEST_SIZE);
+		vm_mem_set_private(vm, gpa, TEST_SIZE);
 
-	pre_fault_memory(vcpu, guest_test_phys_mem, 0, SZ_2M, 0, private);
-	pre_fault_memory(vcpu, guest_test_phys_mem, SZ_2M, PAGE_SIZE * 2, PAGE_SIZE, private);
-	pre_fault_memory(vcpu, guest_test_phys_mem, TEST_SIZE, PAGE_SIZE, PAGE_SIZE, private);
+	pre_fault_memory(vcpu, gpa, 0, SZ_2M, 0, private);
+	pre_fault_memory(vcpu, gpa, SZ_2M, PAGE_SIZE * 2, PAGE_SIZE, private);
+	pre_fault_memory(vcpu, gpa, TEST_SIZE, PAGE_SIZE, PAGE_SIZE, private);
 
-	vcpu_args_set(vcpu, 1, guest_test_virt_mem);
+	vcpu_args_set(vcpu, 1, gva);
 	vcpu_run(vcpu);
 
 	run = vcpu->run;
-- 
cgit v1.2.3


From 83e0e12219a402bf7b8fdef067e51f945a92fd26 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Tue, 7 Oct 2025 15:36:25 -0700
Subject: KVM: selftests: Rename "guest_paddr" variables to "gpa"

Rename "guest_paddr" variables in vm_userspace_mem_region_add() and
vm_mem_add() to KVM's de facto standard "gpa", both for consistency and
to shorten line lengths.

Opportunistically fix the indentation of the
vm_userspace_mem_region_add() declaration.

Link: https://patch.msgid.link/20251007223625.369939-1-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 tools/testing/selftests/kvm/include/kvm_util.h | 10 +++---
 tools/testing/selftests/kvm/lib/kvm_util.c     | 46 ++++++++++++--------------
 2 files changed, 26 insertions(+), 30 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h
index af52cd938b50..c2481be61434 100644
--- a/tools/testing/selftests/kvm/include/kvm_util.h
+++ b/tools/testing/selftests/kvm/include/kvm_util.h
@@ -673,12 +673,12 @@ int __vm_set_user_memory_region2(struct kvm_vm *vm, uint32_t slot, uint32_t flag
 				 uint32_t guest_memfd, uint64_t guest_memfd_offset);
 
 void vm_userspace_mem_region_add(struct kvm_vm *vm,
-	enum vm_mem_backing_src_type src_type,
-	uint64_t guest_paddr, uint32_t slot, uint64_t npages,
-	uint32_t flags);
+				 enum vm_mem_backing_src_type src_type,
+				 uint64_t gpa, uint32_t slot, uint64_t npages,
+				 uint32_t flags);
 void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type,
-		uint64_t guest_paddr, uint32_t slot, uint64_t npages,
-		uint32_t flags, int guest_memfd_fd, uint64_t guest_memfd_offset);
+		uint64_t gpa, uint32_t slot, uint64_t npages, uint32_t flags,
+		int guest_memfd_fd, uint64_t guest_memfd_offset);
 
 #ifndef vm_arch_has_protected_memory
 static inline bool vm_arch_has_protected_memory(struct kvm_vm *vm)
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 5744643d9ec3..a334f6ed50d6 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -943,8 +943,8 @@ void vm_set_user_memory_region2(struct kvm_vm *vm, uint32_t slot, uint32_t flags
 
 /* FIXME: This thing needs to be ripped apart and rewritten. */
 void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type,
-		uint64_t guest_paddr, uint32_t slot, uint64_t npages,
-		uint32_t flags, int guest_memfd, uint64_t guest_memfd_offset)
+		uint64_t gpa, uint32_t slot, uint64_t npages, uint32_t flags,
+		int guest_memfd, uint64_t guest_memfd_offset)
 {
 	int ret;
 	struct userspace_mem_region *region;
@@ -958,30 +958,29 @@ void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type,
 		"Number of guest pages is not compatible with the host. "
 		"Try npages=%d", vm_adjust_num_guest_pages(vm->mode, npages));
 
-	TEST_ASSERT((guest_paddr % vm->page_size) == 0, "Guest physical "
+	TEST_ASSERT((gpa % vm->page_size) == 0, "Guest physical "
 		"address not on a page boundary.\n"
-		"  guest_paddr: 0x%lx vm->page_size: 0x%x",
-		guest_paddr, vm->page_size);
-	TEST_ASSERT((((guest_paddr >> vm->page_shift) + npages) - 1)
+		"  gpa: 0x%lx vm->page_size: 0x%x",
+		gpa, vm->page_size);
+	TEST_ASSERT((((gpa >> vm->page_shift) + npages) - 1)
 		<= vm->max_gfn, "Physical range beyond maximum "
 		"supported physical address,\n"
-		"  guest_paddr: 0x%lx npages: 0x%lx\n"
+		"  gpa: 0x%lx npages: 0x%lx\n"
 		"  vm->max_gfn: 0x%lx vm->page_size: 0x%x",
-		guest_paddr, npages, vm->max_gfn, vm->page_size);
+		gpa, npages, vm->max_gfn, vm->page_size);
 
 	/*
 	 * Confirm a mem region with an overlapping address doesn't
 	 * already exist.
 	 */
 	region = (struct userspace_mem_region *) userspace_mem_region_find(
-		vm, guest_paddr, (guest_paddr + npages * vm->page_size) - 1);
+		vm, gpa, (gpa + npages * vm->page_size) - 1);
 	if (region != NULL)
 		TEST_FAIL("overlapping userspace_mem_region already "
 			"exists\n"
-			"  requested guest_paddr: 0x%lx npages: 0x%lx "
-			"page_size: 0x%x\n"
-			"  existing guest_paddr: 0x%lx size: 0x%lx",
-			guest_paddr, npages, vm->page_size,
+			"  requested gpa: 0x%lx npages: 0x%lx page_size: 0x%x\n"
+			"  existing gpa: 0x%lx size: 0x%lx",
+			gpa, npages, vm->page_size,
 			(uint64_t) region->region.guest_phys_addr,
 			(uint64_t) region->region.memory_size);
 
@@ -995,8 +994,7 @@ void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type,
 			"already exists.\n"
 			"  requested slot: %u paddr: 0x%lx npages: 0x%lx\n"
 			"  existing slot: %u paddr: 0x%lx size: 0x%lx",
-			slot, guest_paddr, npages,
-			region->region.slot,
+			slot, gpa, npages, region->region.slot,
 			(uint64_t) region->region.guest_phys_addr,
 			(uint64_t) region->region.memory_size);
 	}
@@ -1022,7 +1020,7 @@ void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type,
 	if (src_type == VM_MEM_SRC_ANONYMOUS_THP)
 		alignment = max(backing_src_pagesz, alignment);
 
-	TEST_ASSERT_EQ(guest_paddr, align_up(guest_paddr, backing_src_pagesz));
+	TEST_ASSERT_EQ(gpa, align_up(gpa, backing_src_pagesz));
 
 	/* Add enough memory to align up if necessary */
 	if (alignment > 1)
@@ -1082,20 +1080,18 @@ void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type,
 	region->unused_phy_pages = sparsebit_alloc();
 	if (vm_arch_has_protected_memory(vm))
 		region->protected_phy_pages = sparsebit_alloc();
-	sparsebit_set_num(region->unused_phy_pages,
-		guest_paddr >> vm->page_shift, npages);
+	sparsebit_set_num(region->unused_phy_pages, gpa >> vm->page_shift, npages);
 	region->region.slot = slot;
 	region->region.flags = flags;
-	region->region.guest_phys_addr = guest_paddr;
+	region->region.guest_phys_addr = gpa;
 	region->region.memory_size = npages * vm->page_size;
 	region->region.userspace_addr = (uintptr_t) region->host_mem;
 	ret = __vm_ioctl(vm, KVM_SET_USER_MEMORY_REGION2, &region->region);
 	TEST_ASSERT(ret == 0, "KVM_SET_USER_MEMORY_REGION2 IOCTL failed,\n"
 		"  rc: %i errno: %i\n"
 		"  slot: %u flags: 0x%x\n"
-		"  guest_phys_addr: 0x%lx size: 0x%lx guest_memfd: %d",
-		ret, errno, slot, flags,
-		guest_paddr, (uint64_t) region->region.memory_size,
+		"  guest_phys_addr: 0x%lx size: 0x%llx guest_memfd: %d",
+		ret, errno, slot, flags, gpa, region->region.memory_size,
 		region->region.guest_memfd);
 
 	/* Add to quick lookup data structures */
@@ -1117,10 +1113,10 @@ void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type,
 
 void vm_userspace_mem_region_add(struct kvm_vm *vm,
 				 enum vm_mem_backing_src_type src_type,
-				 uint64_t guest_paddr, uint32_t slot,
-				 uint64_t npages, uint32_t flags)
+				 uint64_t gpa, uint32_t slot, uint64_t npages,
+				 uint32_t flags)
 {
-	vm_mem_add(vm, src_type, guest_paddr, slot, npages, flags, -1, 0);
+	vm_mem_add(vm, src_type, gpa, slot, npages, flags, -1, 0);
 }
 
 /*
-- 
cgit v1.2.3


From feee9ef7ac1648835c3b1e35ba4833cf7c8b3669 Mon Sep 17 00:00:00 2001
From: Jiaqi Yan <jiaqiyan@google.com>
Date: Mon, 13 Oct 2025 18:59:02 +0000
Subject: KVM: selftests: Test for KVM_EXIT_ARM_SEA

Test how KVM handles guest SEA when APEI is unable to claim it, and
KVM_CAP_ARM_SEA_TO_USER is enabled.

The behavior is triggered by consuming recoverable memory error (UER)
injected via EINJ. The test asserts two major things:
1. KVM returns to userspace with KVM_EXIT_ARM_SEA exit reason, and
   has provided expected fault information, e.g. esr, flags, gva, gpa.
2. Userspace is able to handle KVM_EXIT_ARM_SEA by injecting SEA to
   guest and KVM injects expected SEA into the VCPU.

Tested on a data center server running Siryn AmpereOne processor
that has RAS support.

Several things to notice before attempting to run this selftest:
- The test relies on EINJ support in both firmware and kernel to
  inject UER. Otherwise the test will be skipped.
- The under-test platform's APEI should be unable to claim the SEA.
  Otherwise the test will be skipped.
- Some platform doesn't support notrigger in EINJ, which may cause
  APEI and GHES to offline the memory before guest can consume
  injected UER, and making test unable to trigger SEA.

Signed-off-by: Jiaqi Yan <jiaqiyan@google.com>
Link: https://msgid.link/20251013185903.1372553-3-jiaqiyan@google.com
Signed-off-by: Oliver Upton <oupton@kernel.org>
---
 tools/arch/arm64/include/asm/esr.h              |   2 +
 tools/testing/selftests/kvm/Makefile.kvm        |   1 +
 tools/testing/selftests/kvm/arm64/sea_to_user.c | 331 ++++++++++++++++++++++++
 tools/testing/selftests/kvm/lib/kvm_util.c      |   1 +
 4 files changed, 335 insertions(+)
 create mode 100644 tools/testing/selftests/kvm/arm64/sea_to_user.c

(limited to 'tools/testing')

diff --git a/tools/arch/arm64/include/asm/esr.h b/tools/arch/arm64/include/asm/esr.h
index bd592ca81571..0fa17b3af1f7 100644
--- a/tools/arch/arm64/include/asm/esr.h
+++ b/tools/arch/arm64/include/asm/esr.h
@@ -141,6 +141,8 @@
 #define ESR_ELx_SF 		(UL(1) << ESR_ELx_SF_SHIFT)
 #define ESR_ELx_AR_SHIFT	(14)
 #define ESR_ELx_AR 		(UL(1) << ESR_ELx_AR_SHIFT)
+#define ESR_ELx_VNCR_SHIFT	(13)
+#define ESR_ELx_VNCR		(UL(1) << ESR_ELx_VNCR_SHIFT)
 #define ESR_ELx_CM_SHIFT	(8)
 #define ESR_ELx_CM 		(UL(1) << ESR_ELx_CM_SHIFT)
 
diff --git a/tools/testing/selftests/kvm/Makefile.kvm b/tools/testing/selftests/kvm/Makefile.kvm
index 148d427ff24b..02a7663c097b 100644
--- a/tools/testing/selftests/kvm/Makefile.kvm
+++ b/tools/testing/selftests/kvm/Makefile.kvm
@@ -163,6 +163,7 @@ TEST_GEN_PROGS_arm64 += arm64/hypercalls
 TEST_GEN_PROGS_arm64 += arm64/external_aborts
 TEST_GEN_PROGS_arm64 += arm64/page_fault_test
 TEST_GEN_PROGS_arm64 += arm64/psci_test
+TEST_GEN_PROGS_arm64 += arm64/sea_to_user
 TEST_GEN_PROGS_arm64 += arm64/set_id_regs
 TEST_GEN_PROGS_arm64 += arm64/smccc_filter
 TEST_GEN_PROGS_arm64 += arm64/vcpu_width_config
diff --git a/tools/testing/selftests/kvm/arm64/sea_to_user.c b/tools/testing/selftests/kvm/arm64/sea_to_user.c
new file mode 100644
index 000000000000..573dd790aeb8
--- /dev/null
+++ b/tools/testing/selftests/kvm/arm64/sea_to_user.c
@@ -0,0 +1,331 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Test KVM returns to userspace with KVM_EXIT_ARM_SEA if host APEI fails
+ * to handle SEA and userspace has opt-ed in KVM_CAP_ARM_SEA_TO_USER.
+ *
+ * After reaching userspace with expected arm_sea info, also test userspace
+ * injecting a synchronous external data abort into the guest.
+ *
+ * This test utilizes EINJ to generate a REAL synchronous external data
+ * abort by consuming a recoverable uncorrectable memory error. Therefore
+ * the device under test must support EINJ in both firmware and host kernel,
+ * including the notrigger feature. Otherwise the test will be skipped.
+ * The under-test platform's APEI should be unable to claim SEA. Otherwise
+ * the test will also be skipped.
+ */
+
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "processor.h"
+#include "guest_modes.h"
+
+#define PAGE_PRESENT		(1ULL << 63)
+#define PAGE_PHYSICAL		0x007fffffffffffffULL
+#define PAGE_ADDR_MASK		(~(0xfffULL))
+
+/* Group ISV and ISS[23:14]. */
+#define ESR_ELx_INST_SYNDROME	((ESR_ELx_ISV) | (ESR_ELx_SAS) | \
+				 (ESR_ELx_SSE) | (ESR_ELx_SRT_MASK) | \
+				 (ESR_ELx_SF) | (ESR_ELx_AR))
+
+#define EINJ_ETYPE		"/sys/kernel/debug/apei/einj/error_type"
+#define EINJ_ADDR		"/sys/kernel/debug/apei/einj/param1"
+#define EINJ_MASK		"/sys/kernel/debug/apei/einj/param2"
+#define EINJ_FLAGS		"/sys/kernel/debug/apei/einj/flags"
+#define EINJ_NOTRIGGER		"/sys/kernel/debug/apei/einj/notrigger"
+#define EINJ_DOIT		"/sys/kernel/debug/apei/einj/error_inject"
+/* Memory Uncorrectable non-fatal. */
+#define ERROR_TYPE_MEMORY_UER	0x10
+/* Memory address and mask valid (param1 and param2). */
+#define MASK_MEMORY_UER		0b10
+
+/* Guest virtual address region = [2G, 3G).  */
+#define START_GVA		0x80000000UL
+#define VM_MEM_SIZE		0x40000000UL
+/* Note: EINJ_OFFSET must < VM_MEM_SIZE. */
+#define EINJ_OFFSET		0x01234badUL
+#define EINJ_GVA		((START_GVA) + (EINJ_OFFSET))
+
+static vm_paddr_t einj_gpa;
+static void *einj_hva;
+static uint64_t einj_hpa;
+static bool far_invalid;
+
+static uint64_t translate_to_host_paddr(unsigned long vaddr)
+{
+	uint64_t pinfo;
+	int64_t offset = vaddr / getpagesize() * sizeof(pinfo);
+	int fd;
+	uint64_t page_addr;
+	uint64_t paddr;
+
+	fd = open("/proc/self/pagemap", O_RDONLY);
+	if (fd < 0)
+		ksft_exit_fail_perror("Failed to open /proc/self/pagemap");
+	if (pread(fd, &pinfo, sizeof(pinfo), offset) != sizeof(pinfo)) {
+		close(fd);
+		ksft_exit_fail_perror("Failed to read /proc/self/pagemap");
+	}
+
+	close(fd);
+
+	if ((pinfo & PAGE_PRESENT) == 0)
+		ksft_exit_fail_perror("Page not present");
+
+	page_addr = (pinfo & PAGE_PHYSICAL) << MIN_PAGE_SHIFT;
+	paddr = page_addr + (vaddr & (getpagesize() - 1));
+	return paddr;
+}
+
+static void write_einj_entry(const char *einj_path, uint64_t val)
+{
+	char cmd[256] = {0};
+	FILE *cmdfile = NULL;
+
+	sprintf(cmd, "echo %#lx > %s", val, einj_path);
+	cmdfile = popen(cmd, "r");
+
+	if (pclose(cmdfile) == 0)
+		ksft_print_msg("echo %#lx > %s - done\n", val, einj_path);
+	else
+		ksft_exit_fail_perror("Failed to write EINJ entry");
+}
+
+static void inject_uer(uint64_t paddr)
+{
+	if (access("/sys/firmware/acpi/tables/EINJ", R_OK) == -1)
+		ksft_test_result_skip("EINJ table no available in firmware");
+
+	if (access(EINJ_ETYPE, R_OK | W_OK) == -1)
+		ksft_test_result_skip("EINJ module probably not loaded?");
+
+	write_einj_entry(EINJ_ETYPE, ERROR_TYPE_MEMORY_UER);
+	write_einj_entry(EINJ_FLAGS, MASK_MEMORY_UER);
+	write_einj_entry(EINJ_ADDR, paddr);
+	write_einj_entry(EINJ_MASK, ~0x0UL);
+	write_einj_entry(EINJ_NOTRIGGER, 1);
+	write_einj_entry(EINJ_DOIT, 1);
+}
+
+/*
+ * When host APEI successfully claims the SEA caused by guest_code, kernel
+ * will send SIGBUS signal with BUS_MCEERR_AR to test thread.
+ *
+ * We set up this SIGBUS handler to skip the test for that case.
+ */
+static void sigbus_signal_handler(int sig, siginfo_t *si, void *v)
+{
+	ksft_print_msg("SIGBUS (%d) received, dumping siginfo...\n", sig);
+	ksft_print_msg("si_signo=%d, si_errno=%d, si_code=%d, si_addr=%p\n",
+		       si->si_signo, si->si_errno, si->si_code, si->si_addr);
+	if (si->si_code == BUS_MCEERR_AR)
+		ksft_test_result_skip("SEA is claimed by host APEI\n");
+	else
+		ksft_test_result_fail("Exit with signal unhandled\n");
+
+	exit(0);
+}
+
+static void setup_sigbus_handler(void)
+{
+	struct sigaction act;
+
+	memset(&act, 0, sizeof(act));
+	sigemptyset(&act.sa_mask);
+	act.sa_sigaction = sigbus_signal_handler;
+	act.sa_flags = SA_SIGINFO;
+	TEST_ASSERT(sigaction(SIGBUS, &act, NULL) == 0,
+		    "Failed to setup SIGBUS handler");
+}
+
+static void guest_code(void)
+{
+	uint64_t guest_data;
+
+	/* Consumes error will cause a SEA. */
+	guest_data = *(uint64_t *)EINJ_GVA;
+
+	GUEST_FAIL("Poison not protected by SEA: gva=%#lx, guest_data=%#lx\n",
+		   EINJ_GVA, guest_data);
+}
+
+static void expect_sea_handler(struct ex_regs *regs)
+{
+	u64 esr = read_sysreg(esr_el1);
+	u64 far = read_sysreg(far_el1);
+	bool expect_far_invalid = far_invalid;
+
+	GUEST_PRINTF("Handling Guest SEA\n");
+	GUEST_PRINTF("ESR_EL1=%#lx, FAR_EL1=%#lx\n", esr, far);
+
+	GUEST_ASSERT_EQ(ESR_ELx_EC(esr), ESR_ELx_EC_DABT_CUR);
+	GUEST_ASSERT_EQ(esr & ESR_ELx_FSC_TYPE, ESR_ELx_FSC_EXTABT);
+
+	if (expect_far_invalid) {
+		GUEST_ASSERT_EQ(esr & ESR_ELx_FnV, ESR_ELx_FnV);
+		GUEST_PRINTF("Guest observed garbage value in FAR\n");
+	} else {
+		GUEST_ASSERT_EQ(esr & ESR_ELx_FnV, 0);
+		GUEST_ASSERT_EQ(far, EINJ_GVA);
+	}
+
+	GUEST_DONE();
+}
+
+static void vcpu_inject_sea(struct kvm_vcpu *vcpu)
+{
+	struct kvm_vcpu_events events = {};
+
+	events.exception.ext_dabt_pending = true;
+	vcpu_events_set(vcpu, &events);
+}
+
+static void run_vm(struct kvm_vm *vm, struct kvm_vcpu *vcpu)
+{
+	struct ucall uc;
+	bool guest_done = false;
+	struct kvm_run *run = vcpu->run;
+	u64 esr;
+
+	/* Resume the vCPU after error injection to consume the error. */
+	vcpu_run(vcpu);
+
+	ksft_print_msg("Dump kvm_run info about KVM_EXIT_%s\n",
+		       exit_reason_str(run->exit_reason));
+	ksft_print_msg("kvm_run.arm_sea: esr=%#llx, flags=%#llx\n",
+		       run->arm_sea.esr, run->arm_sea.flags);
+	ksft_print_msg("kvm_run.arm_sea: gva=%#llx, gpa=%#llx\n",
+		       run->arm_sea.gva, run->arm_sea.gpa);
+
+	TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_ARM_SEA);
+
+	esr = run->arm_sea.esr;
+	TEST_ASSERT_EQ(ESR_ELx_EC(esr), ESR_ELx_EC_DABT_LOW);
+	TEST_ASSERT_EQ(esr & ESR_ELx_FSC_TYPE, ESR_ELx_FSC_EXTABT);
+	TEST_ASSERT_EQ(ESR_ELx_ISS2(esr), 0);
+	TEST_ASSERT_EQ((esr & ESR_ELx_INST_SYNDROME), 0);
+	TEST_ASSERT_EQ(esr & ESR_ELx_VNCR, 0);
+
+	if (!(esr & ESR_ELx_FnV)) {
+		ksft_print_msg("Expect gva to match given FnV bit is 0\n");
+		TEST_ASSERT_EQ(run->arm_sea.gva, EINJ_GVA);
+	}
+
+	if (run->arm_sea.flags & KVM_EXIT_ARM_SEA_FLAG_GPA_VALID) {
+		ksft_print_msg("Expect gpa to match given KVM_EXIT_ARM_SEA_FLAG_GPA_VALID is set\n");
+		TEST_ASSERT_EQ(run->arm_sea.gpa, einj_gpa & PAGE_ADDR_MASK);
+	}
+
+	far_invalid = esr & ESR_ELx_FnV;
+
+	/* Inject a SEA into guest and expect handled in SEA handler. */
+	vcpu_inject_sea(vcpu);
+
+	/* Expect the guest to reach GUEST_DONE gracefully. */
+	do {
+		vcpu_run(vcpu);
+		switch (get_ucall(vcpu, &uc)) {
+		case UCALL_PRINTF:
+			ksft_print_msg("From guest: %s", uc.buffer);
+			break;
+		case UCALL_DONE:
+			ksft_print_msg("Guest done gracefully!\n");
+			guest_done = 1;
+			break;
+		case UCALL_ABORT:
+			ksft_print_msg("Guest aborted!\n");
+			guest_done = 1;
+			REPORT_GUEST_ASSERT(uc);
+			break;
+		default:
+			TEST_FAIL("Unexpected ucall: %lu\n", uc.cmd);
+		}
+	} while (!guest_done);
+}
+
+static struct kvm_vm *vm_create_with_sea_handler(struct kvm_vcpu **vcpu)
+{
+	size_t backing_page_size;
+	size_t guest_page_size;
+	size_t alignment;
+	uint64_t num_guest_pages;
+	vm_paddr_t start_gpa;
+	enum vm_mem_backing_src_type src_type = VM_MEM_SRC_ANONYMOUS_HUGETLB_1GB;
+	struct kvm_vm *vm;
+
+	backing_page_size = get_backing_src_pagesz(src_type);
+	guest_page_size = vm_guest_mode_params[VM_MODE_DEFAULT].page_size;
+	alignment = max(backing_page_size, guest_page_size);
+	num_guest_pages = VM_MEM_SIZE / guest_page_size;
+
+	vm = __vm_create_with_one_vcpu(vcpu, num_guest_pages, guest_code);
+	vm_init_descriptor_tables(vm);
+	vcpu_init_descriptor_tables(*vcpu);
+
+	vm_install_sync_handler(vm,
+		/*vector=*/VECTOR_SYNC_CURRENT,
+		/*ec=*/ESR_ELx_EC_DABT_CUR,
+		/*handler=*/expect_sea_handler);
+
+	start_gpa = (vm->max_gfn - num_guest_pages) * guest_page_size;
+	start_gpa = align_down(start_gpa, alignment);
+
+	vm_userspace_mem_region_add(
+		/*vm=*/vm,
+		/*src_type=*/src_type,
+		/*guest_paddr=*/start_gpa,
+		/*slot=*/1,
+		/*npages=*/num_guest_pages,
+		/*flags=*/0);
+
+	virt_map(vm, START_GVA, start_gpa, num_guest_pages);
+
+	ksft_print_msg("Mapped %#lx pages: gva=%#lx to gpa=%#lx\n",
+		       num_guest_pages, START_GVA, start_gpa);
+	return vm;
+}
+
+static void vm_inject_memory_uer(struct kvm_vm *vm)
+{
+	uint64_t guest_data;
+
+	einj_gpa = addr_gva2gpa(vm, EINJ_GVA);
+	einj_hva = addr_gva2hva(vm, EINJ_GVA);
+
+	/* Populate certain data before injecting UER. */
+	*(uint64_t *)einj_hva = 0xBAADCAFE;
+	guest_data = *(uint64_t *)einj_hva;
+	ksft_print_msg("Before EINJect: data=%#lx\n",
+		guest_data);
+
+	einj_hpa = translate_to_host_paddr((unsigned long)einj_hva);
+
+	ksft_print_msg("EINJ_GVA=%#lx, einj_gpa=%#lx, einj_hva=%p, einj_hpa=%#lx\n",
+		       EINJ_GVA, einj_gpa, einj_hva, einj_hpa);
+
+	inject_uer(einj_hpa);
+	ksft_print_msg("Memory UER EINJected\n");
+}
+
+int main(int argc, char *argv[])
+{
+	struct kvm_vm *vm;
+	struct kvm_vcpu *vcpu;
+
+	TEST_REQUIRE(kvm_has_cap(KVM_CAP_ARM_SEA_TO_USER));
+
+	setup_sigbus_handler();
+
+	vm = vm_create_with_sea_handler(&vcpu);
+	vm_enable_cap(vm, KVM_CAP_ARM_SEA_TO_USER, 0);
+	vm_inject_memory_uer(vm);
+	run_vm(vm, vcpu);
+	kvm_vm_free(vm);
+
+	return 0;
+}
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 1a93d6361671..234b0b7bf6e8 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -2025,6 +2025,7 @@ static struct exit_reason {
 	KVM_EXIT_STRING(NOTIFY),
 	KVM_EXIT_STRING(LOONGARCH_IOCSR),
 	KVM_EXIT_STRING(MEMORY_FAULT),
+	KVM_EXIT_STRING(ARM_SEA),
 };
 
 /*
-- 
cgit v1.2.3


From 31df012da496968d8d4368f693ad45dfcbfba40b Mon Sep 17 00:00:00 2001
From: Maximilian Dittgen <mdittgen@amazon.de>
Date: Wed, 19 Nov 2025 14:57:43 +0100
Subject: KVM: selftests: Assert GICR_TYPER.Processor_Number matches selftest
 CPU number

The selftests GIC library and tests assume that the
GICR_TYPER.Processor_number associated with a given CPU is the same as
the CPU's selftest index.

Since this assumption is not guaranteed by specification, add an assert
in gicv3_cpu_init() that validates this is true.

Signed-off-by: Maximilian Dittgen <mdittgen@amazon.de>
Link: https://msgid.link/20251119135744.68552-1-mdittgen@amazon.de
Signed-off-by: Oliver Upton <oupton@kernel.org>
---
 tools/testing/selftests/kvm/lib/arm64/gic_v3.c | 5 +++++
 1 file changed, 5 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/kvm/lib/arm64/gic_v3.c b/tools/testing/selftests/kvm/lib/arm64/gic_v3.c
index 66d05506f78b..f81025cd32e2 100644
--- a/tools/testing/selftests/kvm/lib/arm64/gic_v3.c
+++ b/tools/testing/selftests/kvm/lib/arm64/gic_v3.c
@@ -298,12 +298,17 @@ static void gicv3_cpu_init(unsigned int cpu)
 	volatile void *sgi_base;
 	unsigned int i;
 	volatile void *redist_base_cpu;
+	u64 typer;
 
 	GUEST_ASSERT(cpu < gicv3_data.nr_cpus);
 
 	redist_base_cpu = gicr_base_cpu(cpu);
 	sgi_base = sgi_base_from_redist(redist_base_cpu);
 
+	/* Verify assumption that GICR_TYPER.Processor_number == cpu */
+	typer = readq_relaxed(redist_base_cpu + GICR_TYPER);
+	GUEST_ASSERT_EQ(GICR_TYPER_CPU_NUMBER(typer), cpu);
+
 	gicv3_enable_redist(redist_base_cpu);
 
 	/*
-- 
cgit v1.2.3


From 85f329df293119d6ba1a26453d109556631081a4 Mon Sep 17 00:00:00 2001
From: Maximilian Dittgen <mdittgen@amazon.de>
Date: Wed, 19 Nov 2025 14:57:44 +0100
Subject: KVM: selftests: SYNC after guest ITS setup in vgic_lpi_stress

vgic_lpi_stress sends MAPTI and MAPC commands during guest GIC setup to
map interrupt events to ITT entries and collection IDs to
redistributors, respectively.

We have no guarantee that the ITS will finish handling these mapping
commands before the selftest calls KVM_SIGNAL_MSI to inject LPIs to the
guest. If LPIs are injected before ITS mapping completes, the ITS cannot
properly pass the interrupt on to the redistributor.

Fix by adding a SYNC command to the selftests ITS library, then calling
SYNC after ITS mapping to ensure mapping completes before signal_lpi()
writes to GITS_TRANSLATER.

Signed-off-by: Maximilian Dittgen <mdittgen@amazon.de>
Link: https://msgid.link/20251119135744.68552-2-mdittgen@amazon.de
Signed-off-by: Oliver Upton <oupton@kernel.org>
---
 tools/testing/selftests/kvm/arm64/vgic_lpi_stress.c    |  4 ++++
 tools/testing/selftests/kvm/include/arm64/gic_v3_its.h |  1 +
 tools/testing/selftests/kvm/lib/arm64/gic_v3_its.c     | 10 ++++++++++
 3 files changed, 15 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/kvm/arm64/vgic_lpi_stress.c b/tools/testing/selftests/kvm/arm64/vgic_lpi_stress.c
index 687d04463983..e857a605f577 100644
--- a/tools/testing/selftests/kvm/arm64/vgic_lpi_stress.c
+++ b/tools/testing/selftests/kvm/arm64/vgic_lpi_stress.c
@@ -118,6 +118,10 @@ static void guest_setup_gic(void)
 
 	guest_setup_its_mappings();
 	guest_invalidate_all_rdists();
+
+	/* SYNC to ensure ITS setup is complete */
+	for (cpuid = 0; cpuid < test_data.nr_cpus; cpuid++)
+		its_send_sync_cmd(test_data.cmdq_base_va, cpuid);
 }
 
 static void guest_code(size_t nr_lpis)
diff --git a/tools/testing/selftests/kvm/include/arm64/gic_v3_its.h b/tools/testing/selftests/kvm/include/arm64/gic_v3_its.h
index 3722ed9c8f96..58feef3eb386 100644
--- a/tools/testing/selftests/kvm/include/arm64/gic_v3_its.h
+++ b/tools/testing/selftests/kvm/include/arm64/gic_v3_its.h
@@ -15,5 +15,6 @@ void its_send_mapc_cmd(void *cmdq_base, u32 vcpu_id, u32 collection_id, bool val
 void its_send_mapti_cmd(void *cmdq_base, u32 device_id, u32 event_id,
 			u32 collection_id, u32 intid);
 void its_send_invall_cmd(void *cmdq_base, u32 collection_id);
+void its_send_sync_cmd(void *cmdq_base, u32 vcpu_id);
 
 #endif // __SELFTESTS_GIC_V3_ITS_H__
diff --git a/tools/testing/selftests/kvm/lib/arm64/gic_v3_its.c b/tools/testing/selftests/kvm/lib/arm64/gic_v3_its.c
index 09f270545646..aec1b69a4de3 100644
--- a/tools/testing/selftests/kvm/lib/arm64/gic_v3_its.c
+++ b/tools/testing/selftests/kvm/lib/arm64/gic_v3_its.c
@@ -246,3 +246,13 @@ void its_send_invall_cmd(void *cmdq_base, u32 collection_id)
 
 	its_send_cmd(cmdq_base, &cmd);
 }
+
+void its_send_sync_cmd(void *cmdq_base, u32 vcpu_id)
+{
+	struct its_cmd_block cmd = {};
+
+	its_encode_cmd(&cmd, GITS_CMD_SYNC);
+	its_encode_target(&cmd, procnum_to_rdbase(vcpu_id));
+
+	its_send_cmd(cmdq_base, &cmd);
+}
-- 
cgit v1.2.3


From 0a9eb2afa185e84cd6c6b35aefb190e8f92c4c5c Mon Sep 17 00:00:00 2001
From: Yosry Ahmed <yosry.ahmed@linux.dev>
Date: Tue, 21 Oct 2025 07:47:16 +0000
Subject: KVM: selftests: Extend vmx_close_while_nested_test to cover SVM

Add SVM L1 code to run the nested guest, and allow the test to run with
SVM as well as VMX.

Reviewed-by: Jim Mattson <jmattson@google.com>
Signed-off-by: Yosry Ahmed <yosry.ahmed@linux.dev>
Link: https://patch.msgid.link/20251021074736.1324328-4-yosry.ahmed@linux.dev
[sean: rename to "nested_close_kvm_test" to provide nested_* sorting]
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 tools/testing/selftests/kvm/Makefile.kvm           |   2 +-
 .../selftests/kvm/x86/nested_close_kvm_test.c      | 104 +++++++++++++++++++++
 .../kvm/x86/vmx_close_while_nested_test.c          |  80 ----------------
 3 files changed, 105 insertions(+), 81 deletions(-)
 create mode 100644 tools/testing/selftests/kvm/x86/nested_close_kvm_test.c
 delete mode 100644 tools/testing/selftests/kvm/x86/vmx_close_while_nested_test.c

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/kvm/Makefile.kvm b/tools/testing/selftests/kvm/Makefile.kvm
index 148d427ff24b..89ad8c82a7b2 100644
--- a/tools/testing/selftests/kvm/Makefile.kvm
+++ b/tools/testing/selftests/kvm/Makefile.kvm
@@ -88,6 +88,7 @@ TEST_GEN_PROGS_x86 += x86/kvm_pv_test
 TEST_GEN_PROGS_x86 += x86/kvm_buslock_test
 TEST_GEN_PROGS_x86 += x86/monitor_mwait_test
 TEST_GEN_PROGS_x86 += x86/msrs_test
+TEST_GEN_PROGS_x86 += x86/nested_close_kvm_test
 TEST_GEN_PROGS_x86 += x86/nested_emulation_test
 TEST_GEN_PROGS_x86 += x86/nested_exceptions_test
 TEST_GEN_PROGS_x86 += x86/platform_info_test
@@ -111,7 +112,6 @@ TEST_GEN_PROGS_x86 += x86/ucna_injection_test
 TEST_GEN_PROGS_x86 += x86/userspace_io_test
 TEST_GEN_PROGS_x86 += x86/userspace_msr_exit_test
 TEST_GEN_PROGS_x86 += x86/vmx_apic_access_test
-TEST_GEN_PROGS_x86 += x86/vmx_close_while_nested_test
 TEST_GEN_PROGS_x86 += x86/vmx_dirty_log_test
 TEST_GEN_PROGS_x86 += x86/vmx_exception_with_invalid_guest_state
 TEST_GEN_PROGS_x86 += x86/vmx_msrs_test
diff --git a/tools/testing/selftests/kvm/x86/nested_close_kvm_test.c b/tools/testing/selftests/kvm/x86/nested_close_kvm_test.c
new file mode 100644
index 000000000000..f001cb836bfa
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86/nested_close_kvm_test.c
@@ -0,0 +1,104 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2019, Red Hat, Inc.
+ *
+ * Verify that nothing bad happens if a KVM user exits with open
+ * file descriptors while executing a nested guest.
+ */
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "processor.h"
+#include "vmx.h"
+#include "svm_util.h"
+
+#include <string.h>
+#include <sys/ioctl.h>
+
+#include "kselftest.h"
+
+enum {
+	PORT_L0_EXIT = 0x2000,
+};
+
+#define L2_GUEST_STACK_SIZE 64
+
+static void l2_guest_code(void)
+{
+	/* Exit to L0 */
+	asm volatile("inb %%dx, %%al"
+		     : : [port] "d" (PORT_L0_EXIT) : "rax");
+}
+
+static void l1_vmx_code(struct vmx_pages *vmx_pages)
+{
+	unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE];
+
+	GUEST_ASSERT(prepare_for_vmx_operation(vmx_pages));
+	GUEST_ASSERT(load_vmcs(vmx_pages));
+
+	/* Prepare the VMCS for L2 execution. */
+	prepare_vmcs(vmx_pages, l2_guest_code,
+		     &l2_guest_stack[L2_GUEST_STACK_SIZE]);
+
+	GUEST_ASSERT(!vmlaunch());
+	GUEST_ASSERT(0);
+}
+
+static void l1_svm_code(struct svm_test_data *svm)
+{
+	unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE];
+
+	/* Prepare the VMCB for L2 execution. */
+	generic_svm_setup(svm, l2_guest_code,
+			  &l2_guest_stack[L2_GUEST_STACK_SIZE]);
+
+	run_guest(svm->vmcb, svm->vmcb_gpa);
+	GUEST_ASSERT(0);
+}
+
+static void l1_guest_code(void *data)
+{
+	if (this_cpu_has(X86_FEATURE_VMX))
+		l1_vmx_code(data);
+	else
+		l1_svm_code(data);
+}
+
+int main(int argc, char *argv[])
+{
+	vm_vaddr_t guest_gva;
+	struct kvm_vcpu *vcpu;
+	struct kvm_vm *vm;
+
+	TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX) ||
+		     kvm_cpu_has(X86_FEATURE_SVM));
+
+	vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code);
+
+	if (kvm_cpu_has(X86_FEATURE_VMX))
+		vcpu_alloc_vmx(vm, &guest_gva);
+	else
+		vcpu_alloc_svm(vm, &guest_gva);
+
+	vcpu_args_set(vcpu, 1, guest_gva);
+
+	for (;;) {
+		volatile struct kvm_run *run = vcpu->run;
+		struct ucall uc;
+
+		vcpu_run(vcpu);
+		TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO);
+
+		if (run->io.port == PORT_L0_EXIT)
+			break;
+
+		switch (get_ucall(vcpu, &uc)) {
+		case UCALL_ABORT:
+			REPORT_GUEST_ASSERT(uc);
+			/* NOT REACHED */
+		default:
+			TEST_FAIL("Unknown ucall %lu", uc.cmd);
+		}
+	}
+}
diff --git a/tools/testing/selftests/kvm/x86/vmx_close_while_nested_test.c b/tools/testing/selftests/kvm/x86/vmx_close_while_nested_test.c
deleted file mode 100644
index dad988351493..000000000000
--- a/tools/testing/selftests/kvm/x86/vmx_close_while_nested_test.c
+++ /dev/null
@@ -1,80 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * vmx_close_while_nested
- *
- * Copyright (C) 2019, Red Hat, Inc.
- *
- * Verify that nothing bad happens if a KVM user exits with open
- * file descriptors while executing a nested guest.
- */
-
-#include "test_util.h"
-#include "kvm_util.h"
-#include "processor.h"
-#include "vmx.h"
-
-#include <string.h>
-#include <sys/ioctl.h>
-
-#include "kselftest.h"
-
-enum {
-	PORT_L0_EXIT = 0x2000,
-};
-
-static void l2_guest_code(void)
-{
-	/* Exit to L0 */
-	asm volatile("inb %%dx, %%al"
-		     : : [port] "d" (PORT_L0_EXIT) : "rax");
-}
-
-static void l1_guest_code(struct vmx_pages *vmx_pages)
-{
-#define L2_GUEST_STACK_SIZE 64
-	unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE];
-
-	GUEST_ASSERT(prepare_for_vmx_operation(vmx_pages));
-	GUEST_ASSERT(load_vmcs(vmx_pages));
-
-	/* Prepare the VMCS for L2 execution. */
-	prepare_vmcs(vmx_pages, l2_guest_code,
-		     &l2_guest_stack[L2_GUEST_STACK_SIZE]);
-
-	GUEST_ASSERT(!vmlaunch());
-	GUEST_ASSERT(0);
-}
-
-int main(int argc, char *argv[])
-{
-	vm_vaddr_t vmx_pages_gva;
-	struct kvm_vcpu *vcpu;
-	struct kvm_vm *vm;
-
-	TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX));
-
-	vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code);
-
-	/* Allocate VMX pages and shared descriptors (vmx_pages). */
-	vcpu_alloc_vmx(vm, &vmx_pages_gva);
-	vcpu_args_set(vcpu, 1, vmx_pages_gva);
-
-	for (;;) {
-		volatile struct kvm_run *run = vcpu->run;
-		struct ucall uc;
-
-		vcpu_run(vcpu);
-		TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO);
-
-		if (run->io.port == PORT_L0_EXIT)
-			break;
-
-		switch (get_ucall(vcpu, &uc)) {
-		case UCALL_ABORT:
-			REPORT_GUEST_ASSERT(uc);
-			/* NOT REACHED */
-		default:
-			TEST_FAIL("Unknown ucall %lu", uc.cmd);
-		}
-	}
-}
-- 
cgit v1.2.3


From e6bcdd21223835a6a5691af224c7c5ff4934436a Mon Sep 17 00:00:00 2001
From: Yosry Ahmed <yosry.ahmed@linux.dev>
Date: Tue, 21 Oct 2025 07:47:17 +0000
Subject: KVM: selftests: Extend vmx_nested_tsc_scaling_test to cover SVM

Add SVM L1 code to run the nested guest, and allow the test to run with
SVM as well as VMX.

Signed-off-by: Yosry Ahmed <yosry.ahmed@linux.dev>
Link: https://patch.msgid.link/20251021074736.1324328-5-yosry.ahmed@linux.dev
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 tools/testing/selftests/kvm/Makefile.kvm           |   2 +-
 .../selftests/kvm/x86/nested_tsc_scaling_test.c    | 244 +++++++++++++++++++++
 .../kvm/x86/vmx_nested_tsc_scaling_test.c          | 206 -----------------
 3 files changed, 245 insertions(+), 207 deletions(-)
 create mode 100644 tools/testing/selftests/kvm/x86/nested_tsc_scaling_test.c
 delete mode 100644 tools/testing/selftests/kvm/x86/vmx_nested_tsc_scaling_test.c

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/kvm/Makefile.kvm b/tools/testing/selftests/kvm/Makefile.kvm
index 89ad8c82a7b2..9ffa0d5c7654 100644
--- a/tools/testing/selftests/kvm/Makefile.kvm
+++ b/tools/testing/selftests/kvm/Makefile.kvm
@@ -91,6 +91,7 @@ TEST_GEN_PROGS_x86 += x86/msrs_test
 TEST_GEN_PROGS_x86 += x86/nested_close_kvm_test
 TEST_GEN_PROGS_x86 += x86/nested_emulation_test
 TEST_GEN_PROGS_x86 += x86/nested_exceptions_test
+TEST_GEN_PROGS_x86 += x86/nested_tsc_scaling_test
 TEST_GEN_PROGS_x86 += x86/platform_info_test
 TEST_GEN_PROGS_x86 += x86/pmu_counters_test
 TEST_GEN_PROGS_x86 += x86/pmu_event_filter_test
@@ -118,7 +119,6 @@ TEST_GEN_PROGS_x86 += x86/vmx_msrs_test
 TEST_GEN_PROGS_x86 += x86/vmx_invalid_nested_guest_state
 TEST_GEN_PROGS_x86 += x86/vmx_set_nested_state_test
 TEST_GEN_PROGS_x86 += x86/vmx_tsc_adjust_test
-TEST_GEN_PROGS_x86 += x86/vmx_nested_tsc_scaling_test
 TEST_GEN_PROGS_x86 += x86/apic_bus_clock_test
 TEST_GEN_PROGS_x86 += x86/xapic_ipi_test
 TEST_GEN_PROGS_x86 += x86/xapic_state_test
diff --git a/tools/testing/selftests/kvm/x86/nested_tsc_scaling_test.c b/tools/testing/selftests/kvm/x86/nested_tsc_scaling_test.c
new file mode 100644
index 000000000000..4260c9e4f489
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86/nested_tsc_scaling_test.c
@@ -0,0 +1,244 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * vmx_nested_tsc_scaling_test
+ *
+ * Copyright 2021 Amazon.com, Inc. or its affiliates. All Rights Reserved.
+ *
+ * This test case verifies that nested TSC scaling behaves as expected when
+ * both L1 and L2 are scaled using different ratios. For this test we scale
+ * L1 down and scale L2 up.
+ */
+
+#include <time.h>
+
+#include "kvm_util.h"
+#include "vmx.h"
+#include "svm_util.h"
+#include "kselftest.h"
+
+/* L2 is scaled up (from L1's perspective) by this factor */
+#define L2_SCALE_FACTOR 4ULL
+
+#define TSC_OFFSET_L2 ((uint64_t) -33125236320908)
+#define TSC_MULTIPLIER_L2 (L2_SCALE_FACTOR << 48)
+
+#define L2_GUEST_STACK_SIZE 64
+
+enum { USLEEP, UCHECK_L1, UCHECK_L2 };
+#define GUEST_SLEEP(sec)         ucall(UCALL_SYNC, 2, USLEEP, sec)
+#define GUEST_CHECK(level, freq) ucall(UCALL_SYNC, 2, level, freq)
+
+
+/*
+ * This function checks whether the "actual" TSC frequency of a guest matches
+ * its expected frequency. In order to account for delays in taking the TSC
+ * measurements, a difference of 1% between the actual and the expected value
+ * is tolerated.
+ */
+static void compare_tsc_freq(uint64_t actual, uint64_t expected)
+{
+	uint64_t tolerance, thresh_low, thresh_high;
+
+	tolerance = expected / 100;
+	thresh_low = expected - tolerance;
+	thresh_high = expected + tolerance;
+
+	TEST_ASSERT(thresh_low < actual,
+		"TSC freq is expected to be between %"PRIu64" and %"PRIu64
+		" but it actually is %"PRIu64,
+		thresh_low, thresh_high, actual);
+	TEST_ASSERT(thresh_high > actual,
+		"TSC freq is expected to be between %"PRIu64" and %"PRIu64
+		" but it actually is %"PRIu64,
+		thresh_low, thresh_high, actual);
+}
+
+static void check_tsc_freq(int level)
+{
+	uint64_t tsc_start, tsc_end, tsc_freq;
+
+	/*
+	 * Reading the TSC twice with about a second's difference should give
+	 * us an approximation of the TSC frequency from the guest's
+	 * perspective. Now, this won't be completely accurate, but it should
+	 * be good enough for the purposes of this test.
+	 */
+	tsc_start = rdmsr(MSR_IA32_TSC);
+	GUEST_SLEEP(1);
+	tsc_end = rdmsr(MSR_IA32_TSC);
+
+	tsc_freq = tsc_end - tsc_start;
+
+	GUEST_CHECK(level, tsc_freq);
+}
+
+static void l2_guest_code(void)
+{
+	check_tsc_freq(UCHECK_L2);
+
+	/* exit to L1 */
+	__asm__ __volatile__("vmcall");
+}
+
+static void l1_svm_code(struct svm_test_data *svm)
+{
+	unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE];
+
+	/* check that L1's frequency looks alright before launching L2 */
+	check_tsc_freq(UCHECK_L1);
+
+	generic_svm_setup(svm, l2_guest_code,
+			  &l2_guest_stack[L2_GUEST_STACK_SIZE]);
+
+	/* enable TSC scaling for L2 */
+	wrmsr(MSR_AMD64_TSC_RATIO, L2_SCALE_FACTOR << 32);
+
+	/* launch L2 */
+	run_guest(svm->vmcb, svm->vmcb_gpa);
+	GUEST_ASSERT(svm->vmcb->control.exit_code == SVM_EXIT_VMMCALL);
+
+	/* check that L1's frequency still looks good */
+	check_tsc_freq(UCHECK_L1);
+
+	GUEST_DONE();
+}
+
+static void l1_vmx_code(struct vmx_pages *vmx_pages)
+{
+	unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE];
+	uint32_t control;
+
+	/* check that L1's frequency looks alright before launching L2 */
+	check_tsc_freq(UCHECK_L1);
+
+	GUEST_ASSERT(prepare_for_vmx_operation(vmx_pages));
+	GUEST_ASSERT(load_vmcs(vmx_pages));
+
+	/* prepare the VMCS for L2 execution */
+	prepare_vmcs(vmx_pages, l2_guest_code, &l2_guest_stack[L2_GUEST_STACK_SIZE]);
+
+	/* enable TSC offsetting and TSC scaling for L2 */
+	control = vmreadz(CPU_BASED_VM_EXEC_CONTROL);
+	control |= CPU_BASED_USE_MSR_BITMAPS | CPU_BASED_USE_TSC_OFFSETTING;
+	vmwrite(CPU_BASED_VM_EXEC_CONTROL, control);
+
+	control = vmreadz(SECONDARY_VM_EXEC_CONTROL);
+	control |= SECONDARY_EXEC_TSC_SCALING;
+	vmwrite(SECONDARY_VM_EXEC_CONTROL, control);
+
+	vmwrite(TSC_OFFSET, TSC_OFFSET_L2);
+	vmwrite(TSC_MULTIPLIER, TSC_MULTIPLIER_L2);
+	vmwrite(TSC_MULTIPLIER_HIGH, TSC_MULTIPLIER_L2 >> 32);
+
+	/* launch L2 */
+	GUEST_ASSERT(!vmlaunch());
+	GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL);
+
+	/* check that L1's frequency still looks good */
+	check_tsc_freq(UCHECK_L1);
+
+	GUEST_DONE();
+}
+
+static void l1_guest_code(void *data)
+{
+	if (this_cpu_has(X86_FEATURE_VMX))
+		l1_vmx_code(data);
+	else
+		l1_svm_code(data);
+}
+
+int main(int argc, char *argv[])
+{
+	struct kvm_vcpu *vcpu;
+	struct kvm_vm *vm;
+	vm_vaddr_t guest_gva = 0;
+
+	uint64_t tsc_start, tsc_end;
+	uint64_t tsc_khz;
+	uint64_t l1_scale_factor;
+	uint64_t l0_tsc_freq = 0;
+	uint64_t l1_tsc_freq = 0;
+	uint64_t l2_tsc_freq = 0;
+
+	TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX) ||
+		     kvm_cpu_has(X86_FEATURE_SVM));
+	TEST_REQUIRE(kvm_has_cap(KVM_CAP_TSC_CONTROL));
+	TEST_REQUIRE(sys_clocksource_is_based_on_tsc());
+
+	/*
+	 * We set L1's scale factor to be a random number from 2 to 10.
+	 * Ideally we would do the same for L2's factor but that one is
+	 * referenced by both main() and l1_guest_code() and using a global
+	 * variable does not work.
+	 */
+	srand(time(NULL));
+	l1_scale_factor = (rand() % 9) + 2;
+	printf("L1's scale down factor is: %"PRIu64"\n", l1_scale_factor);
+	printf("L2's scale up factor is: %llu\n", L2_SCALE_FACTOR);
+
+	tsc_start = rdtsc();
+	sleep(1);
+	tsc_end = rdtsc();
+
+	l0_tsc_freq = tsc_end - tsc_start;
+	printf("real TSC frequency is around: %"PRIu64"\n", l0_tsc_freq);
+
+	vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code);
+
+	if (kvm_cpu_has(X86_FEATURE_VMX))
+		vcpu_alloc_vmx(vm, &guest_gva);
+	else
+		vcpu_alloc_svm(vm, &guest_gva);
+
+	vcpu_args_set(vcpu, 1, guest_gva);
+
+	tsc_khz = __vcpu_ioctl(vcpu, KVM_GET_TSC_KHZ, NULL);
+	TEST_ASSERT(tsc_khz != -1, "vcpu ioctl KVM_GET_TSC_KHZ failed");
+
+	/* scale down L1's TSC frequency */
+	vcpu_ioctl(vcpu, KVM_SET_TSC_KHZ, (void *) (tsc_khz / l1_scale_factor));
+
+	for (;;) {
+		struct ucall uc;
+
+		vcpu_run(vcpu);
+		TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO);
+
+		switch (get_ucall(vcpu, &uc)) {
+		case UCALL_ABORT:
+			REPORT_GUEST_ASSERT(uc);
+		case UCALL_SYNC:
+			switch (uc.args[0]) {
+			case USLEEP:
+				sleep(uc.args[1]);
+				break;
+			case UCHECK_L1:
+				l1_tsc_freq = uc.args[1];
+				printf("L1's TSC frequency is around: %"PRIu64
+				       "\n", l1_tsc_freq);
+
+				compare_tsc_freq(l1_tsc_freq,
+						 l0_tsc_freq / l1_scale_factor);
+				break;
+			case UCHECK_L2:
+				l2_tsc_freq = uc.args[1];
+				printf("L2's TSC frequency is around: %"PRIu64
+				       "\n", l2_tsc_freq);
+
+				compare_tsc_freq(l2_tsc_freq,
+						 l1_tsc_freq * L2_SCALE_FACTOR);
+				break;
+			}
+			break;
+		case UCALL_DONE:
+			goto done;
+		default:
+			TEST_FAIL("Unknown ucall %lu", uc.cmd);
+		}
+	}
+
+done:
+	kvm_vm_free(vm);
+	return 0;
+}
diff --git a/tools/testing/selftests/kvm/x86/vmx_nested_tsc_scaling_test.c b/tools/testing/selftests/kvm/x86/vmx_nested_tsc_scaling_test.c
deleted file mode 100644
index 1759fa5cb3f2..000000000000
--- a/tools/testing/selftests/kvm/x86/vmx_nested_tsc_scaling_test.c
+++ /dev/null
@@ -1,206 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * vmx_nested_tsc_scaling_test
- *
- * Copyright 2021 Amazon.com, Inc. or its affiliates. All Rights Reserved.
- *
- * This test case verifies that nested TSC scaling behaves as expected when
- * both L1 and L2 are scaled using different ratios. For this test we scale
- * L1 down and scale L2 up.
- */
-
-#include <time.h>
-
-#include "kvm_util.h"
-#include "vmx.h"
-#include "kselftest.h"
-
-/* L2 is scaled up (from L1's perspective) by this factor */
-#define L2_SCALE_FACTOR 4ULL
-
-#define TSC_OFFSET_L2 ((uint64_t) -33125236320908)
-#define TSC_MULTIPLIER_L2 (L2_SCALE_FACTOR << 48)
-
-#define L2_GUEST_STACK_SIZE 64
-
-enum { USLEEP, UCHECK_L1, UCHECK_L2 };
-#define GUEST_SLEEP(sec)         ucall(UCALL_SYNC, 2, USLEEP, sec)
-#define GUEST_CHECK(level, freq) ucall(UCALL_SYNC, 2, level, freq)
-
-
-/*
- * This function checks whether the "actual" TSC frequency of a guest matches
- * its expected frequency. In order to account for delays in taking the TSC
- * measurements, a difference of 1% between the actual and the expected value
- * is tolerated.
- */
-static void compare_tsc_freq(uint64_t actual, uint64_t expected)
-{
-	uint64_t tolerance, thresh_low, thresh_high;
-
-	tolerance = expected / 100;
-	thresh_low = expected - tolerance;
-	thresh_high = expected + tolerance;
-
-	TEST_ASSERT(thresh_low < actual,
-		"TSC freq is expected to be between %"PRIu64" and %"PRIu64
-		" but it actually is %"PRIu64,
-		thresh_low, thresh_high, actual);
-	TEST_ASSERT(thresh_high > actual,
-		"TSC freq is expected to be between %"PRIu64" and %"PRIu64
-		" but it actually is %"PRIu64,
-		thresh_low, thresh_high, actual);
-}
-
-static void check_tsc_freq(int level)
-{
-	uint64_t tsc_start, tsc_end, tsc_freq;
-
-	/*
-	 * Reading the TSC twice with about a second's difference should give
-	 * us an approximation of the TSC frequency from the guest's
-	 * perspective. Now, this won't be completely accurate, but it should
-	 * be good enough for the purposes of this test.
-	 */
-	tsc_start = rdmsr(MSR_IA32_TSC);
-	GUEST_SLEEP(1);
-	tsc_end = rdmsr(MSR_IA32_TSC);
-
-	tsc_freq = tsc_end - tsc_start;
-
-	GUEST_CHECK(level, tsc_freq);
-}
-
-static void l2_guest_code(void)
-{
-	check_tsc_freq(UCHECK_L2);
-
-	/* exit to L1 */
-	__asm__ __volatile__("vmcall");
-}
-
-static void l1_guest_code(struct vmx_pages *vmx_pages)
-{
-	unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE];
-	uint32_t control;
-
-	/* check that L1's frequency looks alright before launching L2 */
-	check_tsc_freq(UCHECK_L1);
-
-	GUEST_ASSERT(prepare_for_vmx_operation(vmx_pages));
-	GUEST_ASSERT(load_vmcs(vmx_pages));
-
-	/* prepare the VMCS for L2 execution */
-	prepare_vmcs(vmx_pages, l2_guest_code, &l2_guest_stack[L2_GUEST_STACK_SIZE]);
-
-	/* enable TSC offsetting and TSC scaling for L2 */
-	control = vmreadz(CPU_BASED_VM_EXEC_CONTROL);
-	control |= CPU_BASED_USE_MSR_BITMAPS | CPU_BASED_USE_TSC_OFFSETTING;
-	vmwrite(CPU_BASED_VM_EXEC_CONTROL, control);
-
-	control = vmreadz(SECONDARY_VM_EXEC_CONTROL);
-	control |= SECONDARY_EXEC_TSC_SCALING;
-	vmwrite(SECONDARY_VM_EXEC_CONTROL, control);
-
-	vmwrite(TSC_OFFSET, TSC_OFFSET_L2);
-	vmwrite(TSC_MULTIPLIER, TSC_MULTIPLIER_L2);
-	vmwrite(TSC_MULTIPLIER_HIGH, TSC_MULTIPLIER_L2 >> 32);
-
-	/* launch L2 */
-	GUEST_ASSERT(!vmlaunch());
-	GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL);
-
-	/* check that L1's frequency still looks good */
-	check_tsc_freq(UCHECK_L1);
-
-	GUEST_DONE();
-}
-
-int main(int argc, char *argv[])
-{
-	struct kvm_vcpu *vcpu;
-	struct kvm_vm *vm;
-	vm_vaddr_t vmx_pages_gva;
-
-	uint64_t tsc_start, tsc_end;
-	uint64_t tsc_khz;
-	uint64_t l1_scale_factor;
-	uint64_t l0_tsc_freq = 0;
-	uint64_t l1_tsc_freq = 0;
-	uint64_t l2_tsc_freq = 0;
-
-	TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX));
-	TEST_REQUIRE(kvm_has_cap(KVM_CAP_TSC_CONTROL));
-	TEST_REQUIRE(sys_clocksource_is_based_on_tsc());
-
-	/*
-	 * We set L1's scale factor to be a random number from 2 to 10.
-	 * Ideally we would do the same for L2's factor but that one is
-	 * referenced by both main() and l1_guest_code() and using a global
-	 * variable does not work.
-	 */
-	srand(time(NULL));
-	l1_scale_factor = (rand() % 9) + 2;
-	printf("L1's scale down factor is: %"PRIu64"\n", l1_scale_factor);
-	printf("L2's scale up factor is: %llu\n", L2_SCALE_FACTOR);
-
-	tsc_start = rdtsc();
-	sleep(1);
-	tsc_end = rdtsc();
-
-	l0_tsc_freq = tsc_end - tsc_start;
-	printf("real TSC frequency is around: %"PRIu64"\n", l0_tsc_freq);
-
-	vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code);
-	vcpu_alloc_vmx(vm, &vmx_pages_gva);
-	vcpu_args_set(vcpu, 1, vmx_pages_gva);
-
-	tsc_khz = __vcpu_ioctl(vcpu, KVM_GET_TSC_KHZ, NULL);
-	TEST_ASSERT(tsc_khz != -1, "vcpu ioctl KVM_GET_TSC_KHZ failed");
-
-	/* scale down L1's TSC frequency */
-	vcpu_ioctl(vcpu, KVM_SET_TSC_KHZ, (void *) (tsc_khz / l1_scale_factor));
-
-	for (;;) {
-		struct ucall uc;
-
-		vcpu_run(vcpu);
-		TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO);
-
-		switch (get_ucall(vcpu, &uc)) {
-		case UCALL_ABORT:
-			REPORT_GUEST_ASSERT(uc);
-		case UCALL_SYNC:
-			switch (uc.args[0]) {
-			case USLEEP:
-				sleep(uc.args[1]);
-				break;
-			case UCHECK_L1:
-				l1_tsc_freq = uc.args[1];
-				printf("L1's TSC frequency is around: %"PRIu64
-				       "\n", l1_tsc_freq);
-
-				compare_tsc_freq(l1_tsc_freq,
-						 l0_tsc_freq / l1_scale_factor);
-				break;
-			case UCHECK_L2:
-				l2_tsc_freq = uc.args[1];
-				printf("L2's TSC frequency is around: %"PRIu64
-				       "\n", l2_tsc_freq);
-
-				compare_tsc_freq(l2_tsc_freq,
-						 l1_tsc_freq * L2_SCALE_FACTOR);
-				break;
-			}
-			break;
-		case UCALL_DONE:
-			goto done;
-		default:
-			TEST_FAIL("Unknown ucall %lu", uc.cmd);
-		}
-	}
-
-done:
-	kvm_vm_free(vm);
-	return 0;
-}
-- 
cgit v1.2.3


From 4d256d00e44e02fae84851729d70df2bc2ebe6e9 Mon Sep 17 00:00:00 2001
From: Yosry Ahmed <yosry.ahmed@linux.dev>
Date: Tue, 21 Oct 2025 07:47:18 +0000
Subject: KVM: selftests: Move nested invalid CR3 check to its own test

vmx_tsc_adjust_test currently verifies that a nested VMLAUNCH fails with
an invalid CR3. This is irrelevant to TSC scaling, move it to a
standalone test.

Signed-off-by: Yosry Ahmed <yosry.ahmed@linux.dev>
Link: https://patch.msgid.link/20251021074736.1324328-6-yosry.ahmed@linux.dev
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 tools/testing/selftests/kvm/Makefile.kvm           |  1 +
 .../selftests/kvm/x86/nested_invalid_cr3_test.c    | 79 ++++++++++++++++++++++
 .../selftests/kvm/x86/vmx_tsc_adjust_test.c        | 10 ---
 3 files changed, 80 insertions(+), 10 deletions(-)
 create mode 100644 tools/testing/selftests/kvm/x86/nested_invalid_cr3_test.c

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/kvm/Makefile.kvm b/tools/testing/selftests/kvm/Makefile.kvm
index 9ffa0d5c7654..5bfd242da1ca 100644
--- a/tools/testing/selftests/kvm/Makefile.kvm
+++ b/tools/testing/selftests/kvm/Makefile.kvm
@@ -91,6 +91,7 @@ TEST_GEN_PROGS_x86 += x86/msrs_test
 TEST_GEN_PROGS_x86 += x86/nested_close_kvm_test
 TEST_GEN_PROGS_x86 += x86/nested_emulation_test
 TEST_GEN_PROGS_x86 += x86/nested_exceptions_test
+TEST_GEN_PROGS_x86 += x86/nested_invalid_cr3_test
 TEST_GEN_PROGS_x86 += x86/nested_tsc_scaling_test
 TEST_GEN_PROGS_x86 += x86/platform_info_test
 TEST_GEN_PROGS_x86 += x86/pmu_counters_test
diff --git a/tools/testing/selftests/kvm/x86/nested_invalid_cr3_test.c b/tools/testing/selftests/kvm/x86/nested_invalid_cr3_test.c
new file mode 100644
index 000000000000..e839bcf5f8ad
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86/nested_invalid_cr3_test.c
@@ -0,0 +1,79 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2025, Google LLC.
+ *
+ * This test verifies that L1 fails to enter L2 with an invalid CR3, and
+ * succeeds otherwise.
+ */
+#include "kvm_util.h"
+#include "vmx.h"
+#include "kselftest.h"
+
+
+#define L2_GUEST_STACK_SIZE 64
+
+static void l2_guest_code(void)
+{
+	vmcall();
+}
+
+static void l1_vmx_code(struct vmx_pages *vmx_pages)
+{
+	unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE];
+	uintptr_t save_cr3;
+
+	GUEST_ASSERT(prepare_for_vmx_operation(vmx_pages));
+	GUEST_ASSERT(load_vmcs(vmx_pages));
+
+	prepare_vmcs(vmx_pages, l2_guest_code,
+		     &l2_guest_stack[L2_GUEST_STACK_SIZE]);
+
+	/* Try to run L2 with invalid CR3 and make sure it fails */
+	save_cr3 = vmreadz(GUEST_CR3);
+	vmwrite(GUEST_CR3, -1ull);
+	GUEST_ASSERT(!vmlaunch());
+	GUEST_ASSERT(vmreadz(VM_EXIT_REASON) ==
+		     (EXIT_REASON_FAILED_VMENTRY | EXIT_REASON_INVALID_STATE));
+
+	/* Now restore CR3 and make sure L2 runs successfully */
+	vmwrite(GUEST_CR3, save_cr3);
+	GUEST_ASSERT(!vmlaunch());
+	GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL);
+
+	GUEST_DONE();
+}
+
+int main(int argc, char *argv[])
+{
+	struct kvm_vcpu *vcpu;
+	struct kvm_vm *vm;
+	vm_vaddr_t guest_gva = 0;
+
+	TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX));
+
+	vm = vm_create_with_one_vcpu(&vcpu, l1_vmx_code);
+	vcpu_alloc_vmx(vm, &guest_gva);
+	vcpu_args_set(vcpu, 1, guest_gva);
+
+	for (;;) {
+		struct ucall uc;
+
+		vcpu_run(vcpu);
+		TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO);
+
+		switch (get_ucall(vcpu, &uc)) {
+		case UCALL_ABORT:
+			REPORT_GUEST_ASSERT(uc);
+		case UCALL_SYNC:
+			break;
+		case UCALL_DONE:
+			goto done;
+		default:
+			TEST_FAIL("Unknown ucall %lu", uc.cmd);
+		}
+	}
+
+done:
+	kvm_vm_free(vm);
+	return 0;
+}
diff --git a/tools/testing/selftests/kvm/x86/vmx_tsc_adjust_test.c b/tools/testing/selftests/kvm/x86/vmx_tsc_adjust_test.c
index 2ceb5c78c442..2dcc0306a0d9 100644
--- a/tools/testing/selftests/kvm/x86/vmx_tsc_adjust_test.c
+++ b/tools/testing/selftests/kvm/x86/vmx_tsc_adjust_test.c
@@ -77,7 +77,6 @@ static void l1_guest_code(struct vmx_pages *vmx_pages)
 #define L2_GUEST_STACK_SIZE 64
 	unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE];
 	uint32_t control;
-	uintptr_t save_cr3;
 
 	GUEST_ASSERT(rdtsc() < TSC_ADJUST_VALUE);
 	wrmsr(MSR_IA32_TSC, rdtsc() - TSC_ADJUST_VALUE);
@@ -94,15 +93,6 @@ static void l1_guest_code(struct vmx_pages *vmx_pages)
 	vmwrite(CPU_BASED_VM_EXEC_CONTROL, control);
 	vmwrite(TSC_OFFSET, TSC_OFFSET_VALUE);
 
-	/* Jump into L2.  First, test failure to load guest CR3.  */
-	save_cr3 = vmreadz(GUEST_CR3);
-	vmwrite(GUEST_CR3, -1ull);
-	GUEST_ASSERT(!vmlaunch());
-	GUEST_ASSERT(vmreadz(VM_EXIT_REASON) ==
-		     (EXIT_REASON_FAILED_VMENTRY | EXIT_REASON_INVALID_STATE));
-	check_ia32_tsc_adjust(-1 * TSC_ADJUST_VALUE);
-	vmwrite(GUEST_CR3, save_cr3);
-
 	GUEST_ASSERT(!vmlaunch());
 	GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL);
 
-- 
cgit v1.2.3


From 91423b041d3ca9f07ebc0c7859a20ac7eac8c755 Mon Sep 17 00:00:00 2001
From: Yosry Ahmed <yosry.ahmed@linux.dev>
Date: Tue, 21 Oct 2025 07:47:19 +0000
Subject: KVM: selftests: Extend nested_invalid_cr3_test to cover SVM

Add SVM L1 code to run the nested guest, and allow the test to run with
SVM as well as VMX.

Signed-off-by: Yosry Ahmed <yosry.ahmed@linux.dev>
Link: https://patch.msgid.link/20251021074736.1324328-7-yosry.ahmed@linux.dev
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 .../selftests/kvm/x86/nested_invalid_cr3_test.c    | 43 ++++++++++++++++++++--
 1 file changed, 40 insertions(+), 3 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/kvm/x86/nested_invalid_cr3_test.c b/tools/testing/selftests/kvm/x86/nested_invalid_cr3_test.c
index e839bcf5f8ad..a6b6da9cf7fe 100644
--- a/tools/testing/selftests/kvm/x86/nested_invalid_cr3_test.c
+++ b/tools/testing/selftests/kvm/x86/nested_invalid_cr3_test.c
@@ -7,6 +7,7 @@
  */
 #include "kvm_util.h"
 #include "vmx.h"
+#include "svm_util.h"
 #include "kselftest.h"
 
 
@@ -17,6 +18,28 @@ static void l2_guest_code(void)
 	vmcall();
 }
 
+static void l1_svm_code(struct svm_test_data *svm)
+{
+	unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE];
+	uintptr_t save_cr3;
+
+	generic_svm_setup(svm, l2_guest_code,
+			  &l2_guest_stack[L2_GUEST_STACK_SIZE]);
+
+	/* Try to run L2 with invalid CR3 and make sure it fails */
+	save_cr3 = svm->vmcb->save.cr3;
+	svm->vmcb->save.cr3 = -1ull;
+	run_guest(svm->vmcb, svm->vmcb_gpa);
+	GUEST_ASSERT(svm->vmcb->control.exit_code == SVM_EXIT_ERR);
+
+	/* Now restore CR3 and make sure L2 runs successfully */
+	svm->vmcb->save.cr3 = save_cr3;
+	run_guest(svm->vmcb, svm->vmcb_gpa);
+	GUEST_ASSERT(svm->vmcb->control.exit_code == SVM_EXIT_VMMCALL);
+
+	GUEST_DONE();
+}
+
 static void l1_vmx_code(struct vmx_pages *vmx_pages)
 {
 	unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE];
@@ -43,16 +66,30 @@ static void l1_vmx_code(struct vmx_pages *vmx_pages)
 	GUEST_DONE();
 }
 
+static void l1_guest_code(void *data)
+{
+	if (this_cpu_has(X86_FEATURE_VMX))
+		l1_vmx_code(data);
+	else
+		l1_svm_code(data);
+}
+
 int main(int argc, char *argv[])
 {
 	struct kvm_vcpu *vcpu;
 	struct kvm_vm *vm;
 	vm_vaddr_t guest_gva = 0;
 
-	TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX));
+	TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX) ||
+		     kvm_cpu_has(X86_FEATURE_SVM));
+
+	vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code);
+
+	if (kvm_cpu_has(X86_FEATURE_VMX))
+		vcpu_alloc_vmx(vm, &guest_gva);
+	else
+		vcpu_alloc_svm(vm, &guest_gva);
 
-	vm = vm_create_with_one_vcpu(&vcpu, l1_vmx_code);
-	vcpu_alloc_vmx(vm, &guest_gva);
 	vcpu_args_set(vcpu, 1, guest_gva);
 
 	for (;;) {
-- 
cgit v1.2.3


From 3c40777f0ed81e8b8f7047319ad195e407614b69 Mon Sep 17 00:00:00 2001
From: Yosry Ahmed <yosry.ahmed@linux.dev>
Date: Tue, 21 Oct 2025 07:47:20 +0000
Subject: KVM: selftests: Extend vmx_tsc_adjust_test to cover SVM

Add SVM L1 code to run the nested guest, and allow the test to run with
SVM as well as VMX.

Reviewed-by: Jim Mattson <jmattson@google.com>

Signed-off-by: Yosry Ahmed <yosry.ahmed@linux.dev>
Link: https://patch.msgid.link/20251021074736.1324328-8-yosry.ahmed@linux.dev
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 tools/testing/selftests/kvm/Makefile.kvm           |   2 +-
 .../selftests/kvm/x86/nested_tsc_adjust_test.c     | 165 +++++++++++++++++++++
 .../selftests/kvm/x86/vmx_tsc_adjust_test.c        | 146 ------------------
 3 files changed, 166 insertions(+), 147 deletions(-)
 create mode 100644 tools/testing/selftests/kvm/x86/nested_tsc_adjust_test.c
 delete mode 100644 tools/testing/selftests/kvm/x86/vmx_tsc_adjust_test.c

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/kvm/Makefile.kvm b/tools/testing/selftests/kvm/Makefile.kvm
index 5bfd242da1ca..3127983c1285 100644
--- a/tools/testing/selftests/kvm/Makefile.kvm
+++ b/tools/testing/selftests/kvm/Makefile.kvm
@@ -92,6 +92,7 @@ TEST_GEN_PROGS_x86 += x86/nested_close_kvm_test
 TEST_GEN_PROGS_x86 += x86/nested_emulation_test
 TEST_GEN_PROGS_x86 += x86/nested_exceptions_test
 TEST_GEN_PROGS_x86 += x86/nested_invalid_cr3_test
+TEST_GEN_PROGS_x86 += x86/nested_tsc_adjust_test
 TEST_GEN_PROGS_x86 += x86/nested_tsc_scaling_test
 TEST_GEN_PROGS_x86 += x86/platform_info_test
 TEST_GEN_PROGS_x86 += x86/pmu_counters_test
@@ -119,7 +120,6 @@ TEST_GEN_PROGS_x86 += x86/vmx_exception_with_invalid_guest_state
 TEST_GEN_PROGS_x86 += x86/vmx_msrs_test
 TEST_GEN_PROGS_x86 += x86/vmx_invalid_nested_guest_state
 TEST_GEN_PROGS_x86 += x86/vmx_set_nested_state_test
-TEST_GEN_PROGS_x86 += x86/vmx_tsc_adjust_test
 TEST_GEN_PROGS_x86 += x86/apic_bus_clock_test
 TEST_GEN_PROGS_x86 += x86/xapic_ipi_test
 TEST_GEN_PROGS_x86 += x86/xapic_state_test
diff --git a/tools/testing/selftests/kvm/x86/nested_tsc_adjust_test.c b/tools/testing/selftests/kvm/x86/nested_tsc_adjust_test.c
new file mode 100644
index 000000000000..2839f650e5c9
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86/nested_tsc_adjust_test.c
@@ -0,0 +1,165 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2018, Google LLC.
+ *
+ * IA32_TSC_ADJUST test
+ *
+ * According to the SDM, "if an execution of WRMSR to the
+ * IA32_TIME_STAMP_COUNTER MSR adds (or subtracts) value X from the TSC,
+ * the logical processor also adds (or subtracts) value X from the
+ * IA32_TSC_ADJUST MSR.
+ *
+ * Note that when L1 doesn't intercept writes to IA32_TSC, a
+ * WRMSR(IA32_TSC) from L2 sets L1's TSC value, not L2's perceived TSC
+ * value.
+ *
+ * This test verifies that this unusual case is handled correctly.
+ */
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "processor.h"
+#include "vmx.h"
+#include "svm_util.h"
+
+#include <string.h>
+#include <sys/ioctl.h>
+
+#include "kselftest.h"
+
+#ifndef MSR_IA32_TSC_ADJUST
+#define MSR_IA32_TSC_ADJUST 0x3b
+#endif
+
+#define TSC_ADJUST_VALUE (1ll << 32)
+#define TSC_OFFSET_VALUE -(1ll << 48)
+
+#define L2_GUEST_STACK_SIZE 64
+
+enum {
+	PORT_ABORT = 0x1000,
+	PORT_REPORT,
+	PORT_DONE,
+};
+
+enum {
+	VMXON_PAGE = 0,
+	VMCS_PAGE,
+	MSR_BITMAP_PAGE,
+
+	NUM_VMX_PAGES,
+};
+
+/* The virtual machine object. */
+static struct kvm_vm *vm;
+
+static void check_ia32_tsc_adjust(int64_t max)
+{
+	int64_t adjust;
+
+	adjust = rdmsr(MSR_IA32_TSC_ADJUST);
+	GUEST_SYNC(adjust);
+	GUEST_ASSERT(adjust <= max);
+}
+
+static void l2_guest_code(void)
+{
+	uint64_t l1_tsc = rdtsc() - TSC_OFFSET_VALUE;
+
+	wrmsr(MSR_IA32_TSC, l1_tsc - TSC_ADJUST_VALUE);
+	check_ia32_tsc_adjust(-2 * TSC_ADJUST_VALUE);
+
+	/* Exit to L1 */
+	__asm__ __volatile__("vmcall");
+}
+
+static void l1_guest_code(void *data)
+{
+	unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE];
+
+	/* Set TSC from L1 and make sure TSC_ADJUST is updated correctly */
+	GUEST_ASSERT(rdtsc() < TSC_ADJUST_VALUE);
+	wrmsr(MSR_IA32_TSC, rdtsc() - TSC_ADJUST_VALUE);
+	check_ia32_tsc_adjust(-1 * TSC_ADJUST_VALUE);
+
+	/*
+	 * Run L2 with TSC_OFFSET. L2 will write to TSC, and L1 is not
+	 * intercepting the write so it should update L1's TSC_ADJUST.
+	 */
+	if (this_cpu_has(X86_FEATURE_VMX)) {
+		struct vmx_pages *vmx_pages = data;
+		uint32_t control;
+
+		GUEST_ASSERT(prepare_for_vmx_operation(vmx_pages));
+		GUEST_ASSERT(load_vmcs(vmx_pages));
+
+		prepare_vmcs(vmx_pages, l2_guest_code,
+			     &l2_guest_stack[L2_GUEST_STACK_SIZE]);
+		control = vmreadz(CPU_BASED_VM_EXEC_CONTROL);
+		control |= CPU_BASED_USE_MSR_BITMAPS | CPU_BASED_USE_TSC_OFFSETTING;
+		vmwrite(CPU_BASED_VM_EXEC_CONTROL, control);
+		vmwrite(TSC_OFFSET, TSC_OFFSET_VALUE);
+
+		GUEST_ASSERT(!vmlaunch());
+		GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL);
+	} else {
+		struct svm_test_data *svm = data;
+
+		generic_svm_setup(svm, l2_guest_code,
+				  &l2_guest_stack[L2_GUEST_STACK_SIZE]);
+
+		svm->vmcb->control.tsc_offset = TSC_OFFSET_VALUE;
+		run_guest(svm->vmcb, svm->vmcb_gpa);
+		GUEST_ASSERT(svm->vmcb->control.exit_code == SVM_EXIT_VMMCALL);
+	}
+
+	check_ia32_tsc_adjust(-2 * TSC_ADJUST_VALUE);
+	GUEST_DONE();
+}
+
+static void report(int64_t val)
+{
+	pr_info("IA32_TSC_ADJUST is %ld (%lld * TSC_ADJUST_VALUE + %lld).\n",
+		val, val / TSC_ADJUST_VALUE, val % TSC_ADJUST_VALUE);
+}
+
+int main(int argc, char *argv[])
+{
+	vm_vaddr_t nested_gva;
+	struct kvm_vcpu *vcpu;
+
+	TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX) ||
+		     kvm_cpu_has(X86_FEATURE_SVM));
+
+	vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code);
+	if (kvm_cpu_has(X86_FEATURE_VMX))
+		vcpu_alloc_vmx(vm, &nested_gva);
+	else
+		vcpu_alloc_svm(vm, &nested_gva);
+
+	vcpu_args_set(vcpu, 1, nested_gva);
+
+	for (;;) {
+		struct ucall uc;
+
+		vcpu_run(vcpu);
+		TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO);
+
+		switch (get_ucall(vcpu, &uc)) {
+		case UCALL_ABORT:
+			REPORT_GUEST_ASSERT(uc);
+			/* NOT REACHED */
+		case UCALL_SYNC:
+			report(uc.args[1]);
+			break;
+		case UCALL_DONE:
+			goto done;
+		default:
+			TEST_FAIL("Unknown ucall %lu", uc.cmd);
+		}
+	}
+
+done:
+	kvm_vm_free(vm);
+	return 0;
+}
diff --git a/tools/testing/selftests/kvm/x86/vmx_tsc_adjust_test.c b/tools/testing/selftests/kvm/x86/vmx_tsc_adjust_test.c
deleted file mode 100644
index 2dcc0306a0d9..000000000000
--- a/tools/testing/selftests/kvm/x86/vmx_tsc_adjust_test.c
+++ /dev/null
@@ -1,146 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * vmx_tsc_adjust_test
- *
- * Copyright (C) 2018, Google LLC.
- *
- * IA32_TSC_ADJUST test
- *
- * According to the SDM, "if an execution of WRMSR to the
- * IA32_TIME_STAMP_COUNTER MSR adds (or subtracts) value X from the TSC,
- * the logical processor also adds (or subtracts) value X from the
- * IA32_TSC_ADJUST MSR.
- *
- * Note that when L1 doesn't intercept writes to IA32_TSC, a
- * WRMSR(IA32_TSC) from L2 sets L1's TSC value, not L2's perceived TSC
- * value.
- *
- * This test verifies that this unusual case is handled correctly.
- */
-
-#include "test_util.h"
-#include "kvm_util.h"
-#include "processor.h"
-#include "vmx.h"
-
-#include <string.h>
-#include <sys/ioctl.h>
-
-#include "kselftest.h"
-
-#ifndef MSR_IA32_TSC_ADJUST
-#define MSR_IA32_TSC_ADJUST 0x3b
-#endif
-
-#define TSC_ADJUST_VALUE (1ll << 32)
-#define TSC_OFFSET_VALUE -(1ll << 48)
-
-enum {
-	PORT_ABORT = 0x1000,
-	PORT_REPORT,
-	PORT_DONE,
-};
-
-enum {
-	VMXON_PAGE = 0,
-	VMCS_PAGE,
-	MSR_BITMAP_PAGE,
-
-	NUM_VMX_PAGES,
-};
-
-/* The virtual machine object. */
-static struct kvm_vm *vm;
-
-static void check_ia32_tsc_adjust(int64_t max)
-{
-	int64_t adjust;
-
-	adjust = rdmsr(MSR_IA32_TSC_ADJUST);
-	GUEST_SYNC(adjust);
-	GUEST_ASSERT(adjust <= max);
-}
-
-static void l2_guest_code(void)
-{
-	uint64_t l1_tsc = rdtsc() - TSC_OFFSET_VALUE;
-
-	wrmsr(MSR_IA32_TSC, l1_tsc - TSC_ADJUST_VALUE);
-	check_ia32_tsc_adjust(-2 * TSC_ADJUST_VALUE);
-
-	/* Exit to L1 */
-	__asm__ __volatile__("vmcall");
-}
-
-static void l1_guest_code(struct vmx_pages *vmx_pages)
-{
-#define L2_GUEST_STACK_SIZE 64
-	unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE];
-	uint32_t control;
-
-	GUEST_ASSERT(rdtsc() < TSC_ADJUST_VALUE);
-	wrmsr(MSR_IA32_TSC, rdtsc() - TSC_ADJUST_VALUE);
-	check_ia32_tsc_adjust(-1 * TSC_ADJUST_VALUE);
-
-	GUEST_ASSERT(prepare_for_vmx_operation(vmx_pages));
-	GUEST_ASSERT(load_vmcs(vmx_pages));
-
-	/* Prepare the VMCS for L2 execution. */
-	prepare_vmcs(vmx_pages, l2_guest_code,
-		     &l2_guest_stack[L2_GUEST_STACK_SIZE]);
-	control = vmreadz(CPU_BASED_VM_EXEC_CONTROL);
-	control |= CPU_BASED_USE_MSR_BITMAPS | CPU_BASED_USE_TSC_OFFSETTING;
-	vmwrite(CPU_BASED_VM_EXEC_CONTROL, control);
-	vmwrite(TSC_OFFSET, TSC_OFFSET_VALUE);
-
-	GUEST_ASSERT(!vmlaunch());
-	GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL);
-
-	check_ia32_tsc_adjust(-2 * TSC_ADJUST_VALUE);
-
-	GUEST_DONE();
-}
-
-static void report(int64_t val)
-{
-	pr_info("IA32_TSC_ADJUST is %ld (%lld * TSC_ADJUST_VALUE + %lld).\n",
-		val, val / TSC_ADJUST_VALUE, val % TSC_ADJUST_VALUE);
-}
-
-int main(int argc, char *argv[])
-{
-	vm_vaddr_t vmx_pages_gva;
-	struct kvm_vcpu *vcpu;
-
-	TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX));
-
-	vm = vm_create_with_one_vcpu(&vcpu, (void *) l1_guest_code);
-
-	/* Allocate VMX pages and shared descriptors (vmx_pages). */
-	vcpu_alloc_vmx(vm, &vmx_pages_gva);
-	vcpu_args_set(vcpu, 1, vmx_pages_gva);
-
-	for (;;) {
-		struct ucall uc;
-
-		vcpu_run(vcpu);
-		TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO);
-
-		switch (get_ucall(vcpu, &uc)) {
-		case UCALL_ABORT:
-			REPORT_GUEST_ASSERT(uc);
-			/* NOT REACHED */
-		case UCALL_SYNC:
-			report(uc.args[1]);
-			break;
-		case UCALL_DONE:
-			goto done;
-		default:
-			TEST_FAIL("Unknown ucall %lu", uc.cmd);
-		}
-	}
-
-done:
-	kvm_vm_free(vm);
-	return 0;
-}
-- 
cgit v1.2.3


From 28b2dced8ba4604b2cdd97c11d7fbd0fa99f9835 Mon Sep 17 00:00:00 2001
From: Yosry Ahmed <yosry.ahmed@linux.dev>
Date: Tue, 21 Oct 2025 07:47:21 +0000
Subject: KVM: selftests: Stop hardcoding PAGE_SIZE in x86 selftests

Use PAGE_SIZE instead of 4096.

Signed-off-by: Yosry Ahmed <yosry.ahmed@linux.dev>
Link: https://patch.msgid.link/20251021074736.1324328-9-yosry.ahmed@linux.dev
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 tools/testing/selftests/kvm/x86/hyperv_features.c    |  2 +-
 tools/testing/selftests/kvm/x86/hyperv_ipi.c         | 18 +++++++++---------
 tools/testing/selftests/kvm/x86/sev_smoke_test.c     |  2 +-
 tools/testing/selftests/kvm/x86/state_test.c         |  2 +-
 tools/testing/selftests/kvm/x86/userspace_io_test.c  |  2 +-
 tools/testing/selftests/kvm/x86/vmx_dirty_log_test.c | 10 +++++-----
 6 files changed, 18 insertions(+), 18 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/kvm/x86/hyperv_features.c b/tools/testing/selftests/kvm/x86/hyperv_features.c
index 99d327084172..130b9ce7e5dd 100644
--- a/tools/testing/selftests/kvm/x86/hyperv_features.c
+++ b/tools/testing/selftests/kvm/x86/hyperv_features.c
@@ -94,7 +94,7 @@ static void guest_hcall(vm_vaddr_t pgs_gpa, struct hcall_data *hcall)
 
 	if (!(hcall->control & HV_HYPERCALL_FAST_BIT)) {
 		input = pgs_gpa;
-		output = pgs_gpa + 4096;
+		output = pgs_gpa + PAGE_SIZE;
 	} else {
 		input = output = 0;
 	}
diff --git a/tools/testing/selftests/kvm/x86/hyperv_ipi.c b/tools/testing/selftests/kvm/x86/hyperv_ipi.c
index 2b5b4bc6ef7e..ca61836c4e32 100644
--- a/tools/testing/selftests/kvm/x86/hyperv_ipi.c
+++ b/tools/testing/selftests/kvm/x86/hyperv_ipi.c
@@ -102,7 +102,7 @@ static void sender_guest_code(void *hcall_page, vm_vaddr_t pgs_gpa)
 	/* 'Slow' HvCallSendSyntheticClusterIpi to RECEIVER_VCPU_ID_1 */
 	ipi->vector = IPI_VECTOR;
 	ipi->cpu_mask = 1 << RECEIVER_VCPU_ID_1;
-	hyperv_hypercall(HVCALL_SEND_IPI, pgs_gpa, pgs_gpa + 4096);
+	hyperv_hypercall(HVCALL_SEND_IPI, pgs_gpa, pgs_gpa + PAGE_SIZE);
 	nop_loop();
 	GUEST_ASSERT(ipis_rcvd[RECEIVER_VCPU_ID_1] == ++ipis_expected[0]);
 	GUEST_ASSERT(ipis_rcvd[RECEIVER_VCPU_ID_2] == ipis_expected[1]);
@@ -116,13 +116,13 @@ static void sender_guest_code(void *hcall_page, vm_vaddr_t pgs_gpa)
 	GUEST_SYNC(stage++);
 
 	/* 'Slow' HvCallSendSyntheticClusterIpiEx to RECEIVER_VCPU_ID_1 */
-	memset(hcall_page, 0, 4096);
+	memset(hcall_page, 0, PAGE_SIZE);
 	ipi_ex->vector = IPI_VECTOR;
 	ipi_ex->vp_set.format = HV_GENERIC_SET_SPARSE_4K;
 	ipi_ex->vp_set.valid_bank_mask = 1 << 0;
 	ipi_ex->vp_set.bank_contents[0] = BIT(RECEIVER_VCPU_ID_1);
 	hyperv_hypercall(HVCALL_SEND_IPI_EX | (1 << HV_HYPERCALL_VARHEAD_OFFSET),
-			 pgs_gpa, pgs_gpa + 4096);
+			 pgs_gpa, pgs_gpa + PAGE_SIZE);
 	nop_loop();
 	GUEST_ASSERT(ipis_rcvd[RECEIVER_VCPU_ID_1] == ++ipis_expected[0]);
 	GUEST_ASSERT(ipis_rcvd[RECEIVER_VCPU_ID_2] == ipis_expected[1]);
@@ -138,13 +138,13 @@ static void sender_guest_code(void *hcall_page, vm_vaddr_t pgs_gpa)
 	GUEST_SYNC(stage++);
 
 	/* 'Slow' HvCallSendSyntheticClusterIpiEx to RECEIVER_VCPU_ID_2 */
-	memset(hcall_page, 0, 4096);
+	memset(hcall_page, 0, PAGE_SIZE);
 	ipi_ex->vector = IPI_VECTOR;
 	ipi_ex->vp_set.format = HV_GENERIC_SET_SPARSE_4K;
 	ipi_ex->vp_set.valid_bank_mask = 1 << 1;
 	ipi_ex->vp_set.bank_contents[0] = BIT(RECEIVER_VCPU_ID_2 - 64);
 	hyperv_hypercall(HVCALL_SEND_IPI_EX | (1 << HV_HYPERCALL_VARHEAD_OFFSET),
-			 pgs_gpa, pgs_gpa + 4096);
+			 pgs_gpa, pgs_gpa + PAGE_SIZE);
 	nop_loop();
 	GUEST_ASSERT(ipis_rcvd[RECEIVER_VCPU_ID_1] == ipis_expected[0]);
 	GUEST_ASSERT(ipis_rcvd[RECEIVER_VCPU_ID_2] == ++ipis_expected[1]);
@@ -160,14 +160,14 @@ static void sender_guest_code(void *hcall_page, vm_vaddr_t pgs_gpa)
 	GUEST_SYNC(stage++);
 
 	/* 'Slow' HvCallSendSyntheticClusterIpiEx to both RECEIVER_VCPU_ID_{1,2} */
-	memset(hcall_page, 0, 4096);
+	memset(hcall_page, 0, PAGE_SIZE);
 	ipi_ex->vector = IPI_VECTOR;
 	ipi_ex->vp_set.format = HV_GENERIC_SET_SPARSE_4K;
 	ipi_ex->vp_set.valid_bank_mask = 1 << 1 | 1;
 	ipi_ex->vp_set.bank_contents[0] = BIT(RECEIVER_VCPU_ID_1);
 	ipi_ex->vp_set.bank_contents[1] = BIT(RECEIVER_VCPU_ID_2 - 64);
 	hyperv_hypercall(HVCALL_SEND_IPI_EX | (2 << HV_HYPERCALL_VARHEAD_OFFSET),
-			 pgs_gpa, pgs_gpa + 4096);
+			 pgs_gpa, pgs_gpa + PAGE_SIZE);
 	nop_loop();
 	GUEST_ASSERT(ipis_rcvd[RECEIVER_VCPU_ID_1] == ++ipis_expected[0]);
 	GUEST_ASSERT(ipis_rcvd[RECEIVER_VCPU_ID_2] == ++ipis_expected[1]);
@@ -183,10 +183,10 @@ static void sender_guest_code(void *hcall_page, vm_vaddr_t pgs_gpa)
 	GUEST_SYNC(stage++);
 
 	/* 'Slow' HvCallSendSyntheticClusterIpiEx to HV_GENERIC_SET_ALL */
-	memset(hcall_page, 0, 4096);
+	memset(hcall_page, 0, PAGE_SIZE);
 	ipi_ex->vector = IPI_VECTOR;
 	ipi_ex->vp_set.format = HV_GENERIC_SET_ALL;
-	hyperv_hypercall(HVCALL_SEND_IPI_EX, pgs_gpa, pgs_gpa + 4096);
+	hyperv_hypercall(HVCALL_SEND_IPI_EX, pgs_gpa, pgs_gpa + PAGE_SIZE);
 	nop_loop();
 	GUEST_ASSERT(ipis_rcvd[RECEIVER_VCPU_ID_1] == ++ipis_expected[0]);
 	GUEST_ASSERT(ipis_rcvd[RECEIVER_VCPU_ID_2] == ++ipis_expected[1]);
diff --git a/tools/testing/selftests/kvm/x86/sev_smoke_test.c b/tools/testing/selftests/kvm/x86/sev_smoke_test.c
index 77256c89bb8d..86ad1c7d068f 100644
--- a/tools/testing/selftests/kvm/x86/sev_smoke_test.c
+++ b/tools/testing/selftests/kvm/x86/sev_smoke_test.c
@@ -104,7 +104,7 @@ static void test_sync_vmsa(uint32_t type, uint64_t policy)
 	vm_sev_launch(vm, policy, NULL);
 
 	/* This page is shared, so make it decrypted.  */
-	memset(hva, 0, 4096);
+	memset(hva, 0, PAGE_SIZE);
 
 	vcpu_run(vcpu);
 
diff --git a/tools/testing/selftests/kvm/x86/state_test.c b/tools/testing/selftests/kvm/x86/state_test.c
index 141b7fc0c965..f2c7a1c297e3 100644
--- a/tools/testing/selftests/kvm/x86/state_test.c
+++ b/tools/testing/selftests/kvm/x86/state_test.c
@@ -141,7 +141,7 @@ static void __attribute__((__flatten__)) guest_code(void *arg)
 
 	if (this_cpu_has(X86_FEATURE_XSAVE)) {
 		uint64_t supported_xcr0 = this_cpu_supported_xcr0();
-		uint8_t buffer[4096];
+		uint8_t buffer[PAGE_SIZE];
 
 		memset(buffer, 0xcc, sizeof(buffer));
 
diff --git a/tools/testing/selftests/kvm/x86/userspace_io_test.c b/tools/testing/selftests/kvm/x86/userspace_io_test.c
index 9481cbcf284f..be7d72f3c029 100644
--- a/tools/testing/selftests/kvm/x86/userspace_io_test.c
+++ b/tools/testing/selftests/kvm/x86/userspace_io_test.c
@@ -85,7 +85,7 @@ int main(int argc, char *argv[])
 			regs.rcx = 1;
 		if (regs.rcx == 3)
 			regs.rcx = 8192;
-		memset((void *)run + run->io.data_offset, 0xaa, 4096);
+		memset((void *)run + run->io.data_offset, 0xaa, PAGE_SIZE);
 		vcpu_regs_set(vcpu, &regs);
 	}
 
diff --git a/tools/testing/selftests/kvm/x86/vmx_dirty_log_test.c b/tools/testing/selftests/kvm/x86/vmx_dirty_log_test.c
index fa512d033205..34a57fe747f6 100644
--- a/tools/testing/selftests/kvm/x86/vmx_dirty_log_test.c
+++ b/tools/testing/selftests/kvm/x86/vmx_dirty_log_test.c
@@ -122,15 +122,15 @@ static void test_vmx_dirty_log(bool enable_ept)
 	if (enable_ept) {
 		prepare_eptp(vmx, vm, 0);
 		nested_map_memslot(vmx, vm, 0);
-		nested_map(vmx, vm, NESTED_TEST_MEM1, GUEST_TEST_MEM, 4096);
-		nested_map(vmx, vm, NESTED_TEST_MEM2, GUEST_TEST_MEM, 4096);
+		nested_map(vmx, vm, NESTED_TEST_MEM1, GUEST_TEST_MEM, PAGE_SIZE);
+		nested_map(vmx, vm, NESTED_TEST_MEM2, GUEST_TEST_MEM, PAGE_SIZE);
 	}
 
 	bmap = bitmap_zalloc(TEST_MEM_PAGES);
 	host_test_mem = addr_gpa2hva(vm, GUEST_TEST_MEM);
 
 	while (!done) {
-		memset(host_test_mem, 0xaa, TEST_MEM_PAGES * 4096);
+		memset(host_test_mem, 0xaa, TEST_MEM_PAGES * PAGE_SIZE);
 		vcpu_run(vcpu);
 		TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO);
 
@@ -153,9 +153,9 @@ static void test_vmx_dirty_log(bool enable_ept)
 			}
 
 			TEST_ASSERT(!test_bit(1, bmap), "Page 1 incorrectly reported dirty");
-			TEST_ASSERT(host_test_mem[4096 / 8] == 0xaaaaaaaaaaaaaaaaULL, "Page 1 written by guest");
+			TEST_ASSERT(host_test_mem[PAGE_SIZE / 8] == 0xaaaaaaaaaaaaaaaaULL, "Page 1 written by guest");
 			TEST_ASSERT(!test_bit(2, bmap), "Page 2 incorrectly reported dirty");
-			TEST_ASSERT(host_test_mem[8192 / 8] == 0xaaaaaaaaaaaaaaaaULL, "Page 2 written by guest");
+			TEST_ASSERT(host_test_mem[PAGE_SIZE*2 / 8] == 0xaaaaaaaaaaaaaaaaULL, "Page 2 written by guest");
 			break;
 		case UCALL_DONE:
 			done = true;
-- 
cgit v1.2.3


From ff736dba478c2bcf8c8c8328ff8936b1e6d65e81 Mon Sep 17 00:00:00 2001
From: Yosry Ahmed <yosry.ahmed@linux.dev>
Date: Tue, 21 Oct 2025 07:47:22 +0000
Subject: KVM: selftests: Remove the unused argument to prepare_eptp()

eptp_memslot is unused, remove it. No functional change intended.

Signed-off-by: Yosry Ahmed <yosry.ahmed@linux.dev>
Link: https://patch.msgid.link/20251021074736.1324328-10-yosry.ahmed@linux.dev
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 tools/testing/selftests/kvm/include/x86/vmx.h        | 3 +--
 tools/testing/selftests/kvm/lib/x86/memstress.c      | 2 +-
 tools/testing/selftests/kvm/lib/x86/vmx.c            | 3 +--
 tools/testing/selftests/kvm/x86/vmx_dirty_log_test.c | 2 +-
 4 files changed, 4 insertions(+), 6 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/kvm/include/x86/vmx.h b/tools/testing/selftests/kvm/include/x86/vmx.h
index edb3c391b982..96e2b4c630a9 100644
--- a/tools/testing/selftests/kvm/include/x86/vmx.h
+++ b/tools/testing/selftests/kvm/include/x86/vmx.h
@@ -568,8 +568,7 @@ void nested_map_memslot(struct vmx_pages *vmx, struct kvm_vm *vm,
 void nested_identity_map_1g(struct vmx_pages *vmx, struct kvm_vm *vm,
 			    uint64_t addr, uint64_t size);
 bool kvm_cpu_has_ept(void);
-void prepare_eptp(struct vmx_pages *vmx, struct kvm_vm *vm,
-		  uint32_t eptp_memslot);
+void prepare_eptp(struct vmx_pages *vmx, struct kvm_vm *vm);
 void prepare_virtualize_apic_accesses(struct vmx_pages *vmx, struct kvm_vm *vm);
 
 #endif /* SELFTEST_KVM_VMX_H */
diff --git a/tools/testing/selftests/kvm/lib/x86/memstress.c b/tools/testing/selftests/kvm/lib/x86/memstress.c
index 7f5d62a65c68..0b1f288ad556 100644
--- a/tools/testing/selftests/kvm/lib/x86/memstress.c
+++ b/tools/testing/selftests/kvm/lib/x86/memstress.c
@@ -63,7 +63,7 @@ void memstress_setup_ept(struct vmx_pages *vmx, struct kvm_vm *vm)
 {
 	uint64_t start, end;
 
-	prepare_eptp(vmx, vm, 0);
+	prepare_eptp(vmx, vm);
 
 	/*
 	 * Identity map the first 4G and the test region with 1G pages so that
diff --git a/tools/testing/selftests/kvm/lib/x86/vmx.c b/tools/testing/selftests/kvm/lib/x86/vmx.c
index d4d1208dd023..9906456af11f 100644
--- a/tools/testing/selftests/kvm/lib/x86/vmx.c
+++ b/tools/testing/selftests/kvm/lib/x86/vmx.c
@@ -534,8 +534,7 @@ bool kvm_cpu_has_ept(void)
 	return ctrl & SECONDARY_EXEC_ENABLE_EPT;
 }
 
-void prepare_eptp(struct vmx_pages *vmx, struct kvm_vm *vm,
-		  uint32_t eptp_memslot)
+void prepare_eptp(struct vmx_pages *vmx, struct kvm_vm *vm)
 {
 	TEST_ASSERT(kvm_cpu_has_ept(), "KVM doesn't support nested EPT");
 
diff --git a/tools/testing/selftests/kvm/x86/vmx_dirty_log_test.c b/tools/testing/selftests/kvm/x86/vmx_dirty_log_test.c
index 34a57fe747f6..98cb6bdab3e6 100644
--- a/tools/testing/selftests/kvm/x86/vmx_dirty_log_test.c
+++ b/tools/testing/selftests/kvm/x86/vmx_dirty_log_test.c
@@ -120,7 +120,7 @@ static void test_vmx_dirty_log(bool enable_ept)
 	 * GPAs as the EPT enabled case.
 	 */
 	if (enable_ept) {
-		prepare_eptp(vmx, vm, 0);
+		prepare_eptp(vmx, vm);
 		nested_map_memslot(vmx, vm, 0);
 		nested_map(vmx, vm, NESTED_TEST_MEM1, GUEST_TEST_MEM, PAGE_SIZE);
 		nested_map(vmx, vm, NESTED_TEST_MEM2, GUEST_TEST_MEM, PAGE_SIZE);
-- 
cgit v1.2.3


From ae5b498b8da96749cdad7b5a013053d17d815a6e Mon Sep 17 00:00:00 2001
From: Jim Mattson <jmattson@google.com>
Date: Tue, 28 Oct 2025 15:30:39 -0700
Subject: KVM: selftests: Use a loop to create guest page tables

Walk the guest page tables via a loop when creating new mappings,
instead of using unique variables for each level of the page tables.

This simplifies the code and makes it easier to support 5-level paging
in the future.

Signed-off-by: Jim Mattson <jmattson@google.com>
Reviewed-by: Yosry Ahmed <yosry.ahmed@linux.dev>
Link: https://patch.msgid.link/20251028225827.2269128-2-jmattson@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 tools/testing/selftests/kvm/lib/x86/processor.c | 25 +++++++++++--------------
 1 file changed, 11 insertions(+), 14 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/kvm/lib/x86/processor.c b/tools/testing/selftests/kvm/lib/x86/processor.c
index b418502c5ecc..738f2a44083f 100644
--- a/tools/testing/selftests/kvm/lib/x86/processor.c
+++ b/tools/testing/selftests/kvm/lib/x86/processor.c
@@ -218,8 +218,8 @@ static uint64_t *virt_create_upper_pte(struct kvm_vm *vm,
 void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, int level)
 {
 	const uint64_t pg_size = PG_LEVEL_SIZE(level);
-	uint64_t *pml4e, *pdpe, *pde;
-	uint64_t *pte;
+	uint64_t *pte = &vm->pgd;
+	int current_level;
 
 	TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K,
 		    "Unknown or unsupported guest mode, mode: 0x%x", vm->mode);
@@ -243,20 +243,17 @@ void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, int level)
 	 * Allocate upper level page tables, if not already present.  Return
 	 * early if a hugepage was created.
 	 */
-	pml4e = virt_create_upper_pte(vm, &vm->pgd, vaddr, paddr, PG_LEVEL_512G, level);
-	if (*pml4e & PTE_LARGE_MASK)
-		return;
-
-	pdpe = virt_create_upper_pte(vm, pml4e, vaddr, paddr, PG_LEVEL_1G, level);
-	if (*pdpe & PTE_LARGE_MASK)
-		return;
-
-	pde = virt_create_upper_pte(vm, pdpe, vaddr, paddr, PG_LEVEL_2M, level);
-	if (*pde & PTE_LARGE_MASK)
-		return;
+	for (current_level = vm->pgtable_levels;
+	     current_level > PG_LEVEL_4K;
+	     current_level--) {
+		pte = virt_create_upper_pte(vm, pte, vaddr, paddr,
+					    current_level, level);
+		if (*pte & PTE_LARGE_MASK)
+			return;
+	}
 
 	/* Fill in page table entry. */
-	pte = virt_get_pte(vm, pde, vaddr, PG_LEVEL_4K);
+	pte = virt_get_pte(vm, pte, vaddr, PG_LEVEL_4K);
 	TEST_ASSERT(!(*pte & PTE_PRESENT_MASK),
 		    "PTE already present for 4k page at vaddr: 0x%lx", vaddr);
 	*pte = PTE_PRESENT_MASK | PTE_WRITABLE_MASK | (paddr & PHYSICAL_PAGE_MASK);
-- 
cgit v1.2.3


From 2103a8baf5cb7e6169434e5f2cc6c311929f529a Mon Sep 17 00:00:00 2001
From: Jim Mattson <jmattson@google.com>
Date: Tue, 28 Oct 2025 15:30:40 -0700
Subject: KVM: selftests: Use a loop to walk guest page tables

Walk the guest page tables via a loop when searching for a PTE,
instead of using unique variables for each level of the page tables.

This simplifies the code and makes it easier to support 5-level paging
in the future.

Signed-off-by: Jim Mattson <jmattson@google.com>
Reviewed-by: Yosry Ahmed <yosry.ahmed@linux.dev>
Link: https://patch.msgid.link/20251028225827.2269128-3-jmattson@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 tools/testing/selftests/kvm/lib/x86/processor.c | 23 ++++++++++-------------
 1 file changed, 10 insertions(+), 13 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/kvm/lib/x86/processor.c b/tools/testing/selftests/kvm/lib/x86/processor.c
index 738f2a44083f..720c678187b5 100644
--- a/tools/testing/selftests/kvm/lib/x86/processor.c
+++ b/tools/testing/selftests/kvm/lib/x86/processor.c
@@ -307,7 +307,8 @@ static bool vm_is_target_pte(uint64_t *pte, int *level, int current_level)
 uint64_t *__vm_get_page_table_entry(struct kvm_vm *vm, uint64_t vaddr,
 				    int *level)
 {
-	uint64_t *pml4e, *pdpe, *pde;
+	uint64_t *pte = &vm->pgd;
+	int current_level;
 
 	TEST_ASSERT(!vm->arch.is_pt_protected,
 		    "Walking page tables of protected guests is impossible");
@@ -328,19 +329,15 @@ uint64_t *__vm_get_page_table_entry(struct kvm_vm *vm, uint64_t vaddr,
 	TEST_ASSERT(vaddr == (((int64_t)vaddr << 16) >> 16),
 		"Canonical check failed.  The virtual address is invalid.");
 
-	pml4e = virt_get_pte(vm, &vm->pgd, vaddr, PG_LEVEL_512G);
-	if (vm_is_target_pte(pml4e, level, PG_LEVEL_512G))
-		return pml4e;
-
-	pdpe = virt_get_pte(vm, pml4e, vaddr, PG_LEVEL_1G);
-	if (vm_is_target_pte(pdpe, level, PG_LEVEL_1G))
-		return pdpe;
-
-	pde = virt_get_pte(vm, pdpe, vaddr, PG_LEVEL_2M);
-	if (vm_is_target_pte(pde, level, PG_LEVEL_2M))
-		return pde;
+	for (current_level = vm->pgtable_levels;
+	     current_level > PG_LEVEL_4K;
+	     current_level--) {
+		pte = virt_get_pte(vm, pte, vaddr, current_level);
+		if (vm_is_target_pte(pte, level, current_level))
+			return pte;
+	}
 
-	return virt_get_pte(vm, pde, vaddr, PG_LEVEL_4K);
+	return virt_get_pte(vm, pte, vaddr, PG_LEVEL_4K);
 }
 
 uint64_t *vm_get_page_table_entry(struct kvm_vm *vm, uint64_t vaddr)
-- 
cgit v1.2.3


From ec5806639e39950527593e3be0efe7f0d7b65bf7 Mon Sep 17 00:00:00 2001
From: Jim Mattson <jmattson@google.com>
Date: Tue, 28 Oct 2025 15:30:41 -0700
Subject: KVM: selftests: Change VM_MODE_PXXV48_4K to VM_MODE_PXXVYY_4K

Use 57-bit addresses with 5-level paging on hardware that supports
LA57. Continue to use 48-bit addresses with 4-level paging on hardware
that doesn't support LA57.

Suggested-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Jim Mattson <jmattson@google.com>
Link: https://patch.msgid.link/20251028225827.2269128-4-jmattson@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 tools/testing/selftests/kvm/include/kvm_util.h     |  4 +--
 .../testing/selftests/kvm/include/x86/processor.h  |  2 +-
 tools/testing/selftests/kvm/lib/arm64/processor.c  |  2 +-
 tools/testing/selftests/kvm/lib/kvm_util.c         | 30 ++++++++++++----------
 tools/testing/selftests/kvm/lib/x86/processor.c    | 30 ++++++++++++----------
 tools/testing/selftests/kvm/lib/x86/vmx.c          |  6 ++---
 6 files changed, 40 insertions(+), 34 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h
index d3f3e455c031..8a54a1279d44 100644
--- a/tools/testing/selftests/kvm/include/kvm_util.h
+++ b/tools/testing/selftests/kvm/include/kvm_util.h
@@ -177,7 +177,7 @@ enum vm_guest_mode {
 	VM_MODE_P40V48_4K,
 	VM_MODE_P40V48_16K,
 	VM_MODE_P40V48_64K,
-	VM_MODE_PXXV48_4K,	/* For 48bits VA but ANY bits PA */
+	VM_MODE_PXXVYY_4K,	/* For 48-bit or 57-bit VA, depending on host support */
 	VM_MODE_P47V64_4K,
 	VM_MODE_P44V64_4K,
 	VM_MODE_P36V48_4K,
@@ -219,7 +219,7 @@ extern enum vm_guest_mode vm_mode_default;
 
 #elif defined(__x86_64__)
 
-#define VM_MODE_DEFAULT			VM_MODE_PXXV48_4K
+#define VM_MODE_DEFAULT			VM_MODE_PXXVYY_4K
 #define MIN_PAGE_SHIFT			12U
 #define ptes_per_page(page_size)	((page_size) / 8)
 
diff --git a/tools/testing/selftests/kvm/include/x86/processor.h b/tools/testing/selftests/kvm/include/x86/processor.h
index 51cd84b9ca66..57d62a425109 100644
--- a/tools/testing/selftests/kvm/include/x86/processor.h
+++ b/tools/testing/selftests/kvm/include/x86/processor.h
@@ -1441,7 +1441,7 @@ enum pg_level {
 	PG_LEVEL_2M,
 	PG_LEVEL_1G,
 	PG_LEVEL_512G,
-	PG_LEVEL_NUM
+	PG_LEVEL_256T
 };
 
 #define PG_LEVEL_SHIFT(_level) ((_level - 1) * 9 + 12)
diff --git a/tools/testing/selftests/kvm/lib/arm64/processor.c b/tools/testing/selftests/kvm/lib/arm64/processor.c
index 54f6d17c78f7..d46e4b13b92c 100644
--- a/tools/testing/selftests/kvm/lib/arm64/processor.c
+++ b/tools/testing/selftests/kvm/lib/arm64/processor.c
@@ -324,7 +324,7 @@ void aarch64_vcpu_setup(struct kvm_vcpu *vcpu, struct kvm_vcpu_init *init)
 
 	/* Configure base granule size */
 	switch (vm->mode) {
-	case VM_MODE_PXXV48_4K:
+	case VM_MODE_PXXVYY_4K:
 		TEST_FAIL("AArch64 does not support 4K sized pages "
 			  "with ANY-bit physical address ranges");
 	case VM_MODE_P52V48_64K:
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 1a93d6361671..364efd02ad4a 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -201,7 +201,7 @@ const char *vm_guest_mode_string(uint32_t i)
 		[VM_MODE_P40V48_4K]	= "PA-bits:40,  VA-bits:48,  4K pages",
 		[VM_MODE_P40V48_16K]	= "PA-bits:40,  VA-bits:48, 16K pages",
 		[VM_MODE_P40V48_64K]	= "PA-bits:40,  VA-bits:48, 64K pages",
-		[VM_MODE_PXXV48_4K]	= "PA-bits:ANY, VA-bits:48,  4K pages",
+		[VM_MODE_PXXVYY_4K]	= "PA-bits:ANY, VA-bits:48 or 57, 4K pages",
 		[VM_MODE_P47V64_4K]	= "PA-bits:47,  VA-bits:64,  4K pages",
 		[VM_MODE_P44V64_4K]	= "PA-bits:44,  VA-bits:64,  4K pages",
 		[VM_MODE_P36V48_4K]	= "PA-bits:36,  VA-bits:48,  4K pages",
@@ -228,7 +228,7 @@ const struct vm_guest_mode_params vm_guest_mode_params[] = {
 	[VM_MODE_P40V48_4K]	= { 40, 48,  0x1000, 12 },
 	[VM_MODE_P40V48_16K]	= { 40, 48,  0x4000, 14 },
 	[VM_MODE_P40V48_64K]	= { 40, 48, 0x10000, 16 },
-	[VM_MODE_PXXV48_4K]	= {  0,  0,  0x1000, 12 },
+	[VM_MODE_PXXVYY_4K]	= {  0,  0,  0x1000, 12 },
 	[VM_MODE_P47V64_4K]	= { 47, 64,  0x1000, 12 },
 	[VM_MODE_P44V64_4K]	= { 44, 64,  0x1000, 12 },
 	[VM_MODE_P36V48_4K]	= { 36, 48,  0x1000, 12 },
@@ -310,24 +310,26 @@ struct kvm_vm *____vm_create(struct vm_shape shape)
 	case VM_MODE_P36V47_16K:
 		vm->pgtable_levels = 3;
 		break;
-	case VM_MODE_PXXV48_4K:
+	case VM_MODE_PXXVYY_4K:
 #ifdef __x86_64__
 		kvm_get_cpu_address_width(&vm->pa_bits, &vm->va_bits);
 		kvm_init_vm_address_properties(vm);
-		/*
-		 * Ignore KVM support for 5-level paging (vm->va_bits == 57),
-		 * it doesn't take effect unless a CR4.LA57 is set, which it
-		 * isn't for this mode (48-bit virtual address space).
-		 */
-		TEST_ASSERT(vm->va_bits == 48 || vm->va_bits == 57,
-			    "Linear address width (%d bits) not supported",
-			    vm->va_bits);
+
 		pr_debug("Guest physical address width detected: %d\n",
 			 vm->pa_bits);
-		vm->pgtable_levels = 4;
-		vm->va_bits = 48;
+		pr_debug("Guest virtual address width detected: %d\n",
+			 vm->va_bits);
+
+		if (vm->va_bits == 57) {
+			vm->pgtable_levels = 5;
+		} else {
+			TEST_ASSERT(vm->va_bits == 48,
+				    "Unexpected guest virtual address width: %d",
+				    vm->va_bits);
+			vm->pgtable_levels = 4;
+		}
 #else
-		TEST_FAIL("VM_MODE_PXXV48_4K not supported on non-x86 platforms");
+		TEST_FAIL("VM_MODE_PXXVYY_4K not supported on non-x86 platforms");
 #endif
 		break;
 	case VM_MODE_P47V64_4K:
diff --git a/tools/testing/selftests/kvm/lib/x86/processor.c b/tools/testing/selftests/kvm/lib/x86/processor.c
index 720c678187b5..40bd69b265ef 100644
--- a/tools/testing/selftests/kvm/lib/x86/processor.c
+++ b/tools/testing/selftests/kvm/lib/x86/processor.c
@@ -158,10 +158,10 @@ bool kvm_is_tdp_enabled(void)
 
 void virt_arch_pgd_alloc(struct kvm_vm *vm)
 {
-	TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K, "Attempt to use "
-		"unknown or unsupported guest mode, mode: 0x%x", vm->mode);
+	TEST_ASSERT(vm->mode == VM_MODE_PXXVYY_4K,
+		    "Unknown or unsupported guest mode: 0x%x", vm->mode);
 
-	/* If needed, create page map l4 table. */
+	/* If needed, create the top-level page table. */
 	if (!vm->pgd_created) {
 		vm->pgd = vm_alloc_page_table(vm);
 		vm->pgd_created = true;
@@ -221,8 +221,8 @@ void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, int level)
 	uint64_t *pte = &vm->pgd;
 	int current_level;
 
-	TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K,
-		    "Unknown or unsupported guest mode, mode: 0x%x", vm->mode);
+	TEST_ASSERT(vm->mode == VM_MODE_PXXVYY_4K,
+		    "Unknown or unsupported guest mode: 0x%x", vm->mode);
 
 	TEST_ASSERT((vaddr % pg_size) == 0,
 		    "Virtual address not aligned,\n"
@@ -307,27 +307,28 @@ static bool vm_is_target_pte(uint64_t *pte, int *level, int current_level)
 uint64_t *__vm_get_page_table_entry(struct kvm_vm *vm, uint64_t vaddr,
 				    int *level)
 {
+	int va_width = 12 + (vm->pgtable_levels) * 9;
 	uint64_t *pte = &vm->pgd;
 	int current_level;
 
 	TEST_ASSERT(!vm->arch.is_pt_protected,
 		    "Walking page tables of protected guests is impossible");
 
-	TEST_ASSERT(*level >= PG_LEVEL_NONE && *level < PG_LEVEL_NUM,
+	TEST_ASSERT(*level >= PG_LEVEL_NONE && *level <= vm->pgtable_levels,
 		    "Invalid PG_LEVEL_* '%d'", *level);
 
-	TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K, "Attempt to use "
-		"unknown or unsupported guest mode, mode: 0x%x", vm->mode);
+	TEST_ASSERT(vm->mode == VM_MODE_PXXVYY_4K,
+		    "Unknown or unsupported guest mode: 0x%x", vm->mode);
 	TEST_ASSERT(sparsebit_is_set(vm->vpages_valid,
 		(vaddr >> vm->page_shift)),
 		"Invalid virtual address, vaddr: 0x%lx",
 		vaddr);
 	/*
-	 * Based on the mode check above there are 48 bits in the vaddr, so
-	 * shift 16 to sign extend the last bit (bit-47),
+	 * Check that the vaddr is a sign-extended va_width value.
 	 */
-	TEST_ASSERT(vaddr == (((int64_t)vaddr << 16) >> 16),
-		"Canonical check failed.  The virtual address is invalid.");
+	TEST_ASSERT(vaddr ==
+		    (((int64_t)vaddr << (64 - va_width) >> (64 - va_width))),
+		    "Canonical check failed.  The virtual address is invalid.");
 
 	for (current_level = vm->pgtable_levels;
 	     current_level > PG_LEVEL_4K;
@@ -520,7 +521,8 @@ static void vcpu_init_sregs(struct kvm_vm *vm, struct kvm_vcpu *vcpu)
 {
 	struct kvm_sregs sregs;
 
-	TEST_ASSERT_EQ(vm->mode, VM_MODE_PXXV48_4K);
+	TEST_ASSERT(vm->mode == VM_MODE_PXXVYY_4K,
+		    "Unknown or unsupported guest mode: 0x%x", vm->mode);
 
 	/* Set mode specific system register values. */
 	vcpu_sregs_get(vcpu, &sregs);
@@ -534,6 +536,8 @@ static void vcpu_init_sregs(struct kvm_vm *vm, struct kvm_vcpu *vcpu)
 	sregs.cr4 |= X86_CR4_PAE | X86_CR4_OSFXSR;
 	if (kvm_cpu_has(X86_FEATURE_XSAVE))
 		sregs.cr4 |= X86_CR4_OSXSAVE;
+	if (vm->pgtable_levels == 5)
+		sregs.cr4 |= X86_CR4_LA57;
 	sregs.efer |= (EFER_LME | EFER_LMA | EFER_NX);
 
 	kvm_seg_set_unusable(&sregs.ldt);
diff --git a/tools/testing/selftests/kvm/lib/x86/vmx.c b/tools/testing/selftests/kvm/lib/x86/vmx.c
index 9906456af11f..29b082a58daa 100644
--- a/tools/testing/selftests/kvm/lib/x86/vmx.c
+++ b/tools/testing/selftests/kvm/lib/x86/vmx.c
@@ -401,11 +401,11 @@ void __nested_pg_map(struct vmx_pages *vmx, struct kvm_vm *vm,
 	struct eptPageTableEntry *pt = vmx->eptp_hva, *pte;
 	uint16_t index;
 
-	TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K, "Attempt to use "
-		    "unknown or unsupported guest mode, mode: 0x%x", vm->mode);
+	TEST_ASSERT(vm->mode == VM_MODE_PXXVYY_4K,
+		    "Unknown or unsupported guest mode: 0x%x", vm->mode);
 
 	TEST_ASSERT((nested_paddr >> 48) == 0,
-		    "Nested physical address 0x%lx requires 5-level paging",
+		    "Nested physical address 0x%lx is > 48-bits and requires 5-level EPT",
 		    nested_paddr);
 	TEST_ASSERT((nested_paddr % page_size) == 0,
 		    "Nested physical address not on page boundary,\n"
-- 
cgit v1.2.3


From 6a8818de21d294c1de6be9a71afe184d08350875 Mon Sep 17 00:00:00 2001
From: Jim Mattson <jmattson@google.com>
Date: Tue, 28 Oct 2025 15:30:42 -0700
Subject: KVM: selftests: Add a VMX test for LA57 nested state

Add a selftest that verifies KVM's ability to save and restore
nested state when the L1 guest is using 5-level paging and the L2
guest is using 4-level paging. Specifically, canonicality tests of
the VMCS12 host-state fields should accept 57-bit virtual addresses.

Signed-off-by: Jim Mattson <jmattson@google.com>
Link: https://patch.msgid.link/20251028225827.2269128-5-jmattson@google.com
[sean: rename to vmx_nested_la57_state_test to prep nested_<test> namespace]
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 tools/testing/selftests/kvm/Makefile.kvm           |   1 +
 .../selftests/kvm/x86/vmx_nested_la57_state_test.c | 132 +++++++++++++++++++++
 2 files changed, 133 insertions(+)
 create mode 100644 tools/testing/selftests/kvm/x86/vmx_nested_la57_state_test.c

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/kvm/Makefile.kvm b/tools/testing/selftests/kvm/Makefile.kvm
index 3127983c1285..7ebf30a87a2b 100644
--- a/tools/testing/selftests/kvm/Makefile.kvm
+++ b/tools/testing/selftests/kvm/Makefile.kvm
@@ -119,6 +119,7 @@ TEST_GEN_PROGS_x86 += x86/vmx_dirty_log_test
 TEST_GEN_PROGS_x86 += x86/vmx_exception_with_invalid_guest_state
 TEST_GEN_PROGS_x86 += x86/vmx_msrs_test
 TEST_GEN_PROGS_x86 += x86/vmx_invalid_nested_guest_state
+TEST_GEN_PROGS_x86 += x86/vmx_nested_la57_state_test
 TEST_GEN_PROGS_x86 += x86/vmx_set_nested_state_test
 TEST_GEN_PROGS_x86 += x86/apic_bus_clock_test
 TEST_GEN_PROGS_x86 += x86/xapic_ipi_test
diff --git a/tools/testing/selftests/kvm/x86/vmx_nested_la57_state_test.c b/tools/testing/selftests/kvm/x86/vmx_nested_la57_state_test.c
new file mode 100644
index 000000000000..cf1d2d1f2a8f
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86/vmx_nested_la57_state_test.c
@@ -0,0 +1,132 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2025, Google LLC.
+ *
+ * Test KVM's ability to save and restore nested state when the L1 guest
+ * is using 5-level paging and the L2 guest is using 4-level paging.
+ *
+ * This test would have failed prior to commit 9245fd6b8531 ("KVM: x86:
+ * model canonical checks more precisely").
+ */
+#include "test_util.h"
+#include "kvm_util.h"
+#include "processor.h"
+#include "vmx.h"
+
+#define LA57_GS_BASE 0xff2bc0311fb00000ull
+
+static void l2_guest_code(void)
+{
+	/*
+	 * Sync with L0 to trigger save/restore.  After
+	 * resuming, execute VMCALL to exit back to L1.
+	 */
+	GUEST_SYNC(1);
+	vmcall();
+}
+
+static void l1_guest_code(struct vmx_pages *vmx_pages)
+{
+#define L2_GUEST_STACK_SIZE 64
+	unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE];
+	u64 guest_cr4;
+	vm_paddr_t pml5_pa, pml4_pa;
+	u64 *pml5;
+	u64 exit_reason;
+
+	/* Set GS_BASE to a value that is only canonical with LA57. */
+	wrmsr(MSR_GS_BASE, LA57_GS_BASE);
+	GUEST_ASSERT(rdmsr(MSR_GS_BASE) == LA57_GS_BASE);
+
+	GUEST_ASSERT(vmx_pages->vmcs_gpa);
+	GUEST_ASSERT(prepare_for_vmx_operation(vmx_pages));
+	GUEST_ASSERT(load_vmcs(vmx_pages));
+
+	prepare_vmcs(vmx_pages, l2_guest_code,
+		     &l2_guest_stack[L2_GUEST_STACK_SIZE]);
+
+	/*
+	 * Set up L2 with a 4-level page table by pointing its CR3 to
+	 * L1's first PML4 table and clearing CR4.LA57. This creates
+	 * the CR4.LA57 mismatch that exercises the bug.
+	 */
+	pml5_pa = get_cr3() & PHYSICAL_PAGE_MASK;
+	pml5 = (u64 *)pml5_pa;
+	pml4_pa = pml5[0] & PHYSICAL_PAGE_MASK;
+	vmwrite(GUEST_CR3, pml4_pa);
+
+	guest_cr4 = vmreadz(GUEST_CR4);
+	guest_cr4 &= ~X86_CR4_LA57;
+	vmwrite(GUEST_CR4, guest_cr4);
+
+	GUEST_ASSERT(!vmlaunch());
+
+	exit_reason = vmreadz(VM_EXIT_REASON);
+	GUEST_ASSERT(exit_reason == EXIT_REASON_VMCALL);
+}
+
+void guest_code(struct vmx_pages *vmx_pages)
+{
+	l1_guest_code(vmx_pages);
+	GUEST_DONE();
+}
+
+int main(int argc, char *argv[])
+{
+	vm_vaddr_t vmx_pages_gva = 0;
+	struct kvm_vm *vm;
+	struct kvm_vcpu *vcpu;
+	struct kvm_x86_state *state;
+	struct ucall uc;
+	int stage;
+
+	TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX));
+	TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_LA57));
+	TEST_REQUIRE(kvm_has_cap(KVM_CAP_NESTED_STATE));
+
+	vm = vm_create_with_one_vcpu(&vcpu, guest_code);
+
+	/*
+	 * L1 needs to read its own PML5 table to set up L2. Identity map
+	 * the PML5 table to facilitate this.
+	 */
+	virt_map(vm, vm->pgd, vm->pgd, 1);
+
+	vcpu_alloc_vmx(vm, &vmx_pages_gva);
+	vcpu_args_set(vcpu, 1, vmx_pages_gva);
+
+	for (stage = 1;; stage++) {
+		vcpu_run(vcpu);
+		TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO);
+
+		switch (get_ucall(vcpu, &uc)) {
+		case UCALL_ABORT:
+			REPORT_GUEST_ASSERT(uc);
+			/* NOT REACHED */
+		case UCALL_SYNC:
+			break;
+		case UCALL_DONE:
+			goto done;
+		default:
+			TEST_FAIL("Unknown ucall %lu", uc.cmd);
+		}
+
+		TEST_ASSERT(uc.args[1] == stage,
+			    "Expected stage %d, got stage %lu", stage, (ulong)uc.args[1]);
+		if (stage == 1) {
+			pr_info("L2 is active; performing save/restore.\n");
+			state = vcpu_save_state(vcpu);
+
+			kvm_vm_release(vm);
+
+			/* Restore state in a new VM. */
+			vcpu = vm_recreate_with_one_vcpu(vm);
+			vcpu_load_state(vcpu, state);
+			kvm_x86_state_cleanup(state);
+		}
+	}
+
+done:
+	kvm_vm_free(vm);
+	return 0;
+}
-- 
cgit v1.2.3


From 8e8678e740ecde2ae4a0404fd9b4ed2b726e236d Mon Sep 17 00:00:00 2001
From: Janosch Frank <frankja@linux.ibm.com>
Date: Tue, 8 Jul 2025 12:57:57 +0000
Subject: KVM: s390: Add capability that forwards operation exceptions

Setting KVM_CAP_S390_USER_OPEREXEC will forward all operation
exceptions to user space. This also includes the 0x0000 instructions
managed by KVM_CAP_S390_USER_INSTR0. It's helpful if user space wants
to emulate instructions which do not (yet) have an opcode.

While we're at it refine the documentation for
KVM_CAP_S390_USER_INSTR0.

Signed-off-by: Janosch Frank <frankja@linux.ibm.com>
Reviewed-by: Claudio Imbrenda <imbrenda@linux.ibm.com>
Acked-by: Christian Borntraeger <borntraeger@linux.ibm.com>
Signed-off-by: Janosch Frank <frankja@linux.ibm.com>
---
 Documentation/virt/kvm/api.rst                   |  17 ++-
 arch/s390/include/asm/kvm_host.h                 |   1 +
 arch/s390/kvm/intercept.c                        |   3 +
 arch/s390/kvm/kvm-s390.c                         |   7 ++
 include/uapi/linux/kvm.h                         |   1 +
 tools/testing/selftests/kvm/Makefile.kvm         |   1 +
 tools/testing/selftests/kvm/s390/user_operexec.c | 140 +++++++++++++++++++++++
 7 files changed, 169 insertions(+), 1 deletion(-)
 create mode 100644 tools/testing/selftests/kvm/s390/user_operexec.c

(limited to 'tools/testing')

diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index 72b2fae99a83..1bc2a84c59ee 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -7820,7 +7820,7 @@ where 0xff represents CPUs 0-7 in cluster 0.
 :Architectures: s390
 :Parameters: none
 
-With this capability enabled, all illegal instructions 0x0000 (2 bytes) will
+With this capability enabled, the illegal instruction 0x0000 (2 bytes) will
 be intercepted and forwarded to user space. User space can use this
 mechanism e.g. to realize 2-byte software breakpoints. The kernel will
 not inject an operating exception for these instructions, user space has
@@ -8703,6 +8703,21 @@ This capability indicate to the userspace whether a PFNMAP memory region
 can be safely mapped as cacheable. This relies on the presence of
 force write back (FWB) feature support on the hardware.
 
+7.45 KVM_CAP_S390_USER_OPEREXEC
+-------------------------------
+
+:Architectures: s390
+:Parameters: none
+
+When this capability is enabled KVM forwards all operation exceptions
+that it doesn't handle itself to user space. This also includes the
+0x0000 instructions managed by KVM_CAP_S390_USER_INSTR0. This is
+helpful if user space wants to emulate instructions which are not
+(yet) implemented in hardware.
+
+This capability can be enabled dynamically even if VCPUs were already
+created and are running.
+
 8. Other capabilities.
 ======================
 
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index 22cedcaea475..1e4829c70216 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -648,6 +648,7 @@ struct kvm_arch {
 	int user_sigp;
 	int user_stsi;
 	int user_instr0;
+	int user_operexec;
 	struct s390_io_adapter *adapters[MAX_S390_IO_ADAPTERS];
 	wait_queue_head_t ipte_wq;
 	int ipte_lock_count;
diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c
index c7908950c1f4..420ae62977e2 100644
--- a/arch/s390/kvm/intercept.c
+++ b/arch/s390/kvm/intercept.c
@@ -471,6 +471,9 @@ static int handle_operexc(struct kvm_vcpu *vcpu)
 	if (vcpu->arch.sie_block->ipa == 0xb256)
 		return handle_sthyi(vcpu);
 
+	if (vcpu->kvm->arch.user_operexec)
+		return -EOPNOTSUPP;
+
 	if (vcpu->arch.sie_block->ipa == 0 && vcpu->kvm->arch.user_instr0)
 		return -EOPNOTSUPP;
 	rc = read_guest_lc(vcpu, __LC_PGM_NEW_PSW, &newpsw, sizeof(psw_t));
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 70ebc54b1bb1..56d4730b7c41 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -606,6 +606,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_SET_GUEST_DEBUG:
 	case KVM_CAP_S390_DIAG318:
 	case KVM_CAP_IRQFD_RESAMPLE:
+	case KVM_CAP_S390_USER_OPEREXEC:
 		r = 1;
 		break;
 	case KVM_CAP_SET_GUEST_DEBUG2:
@@ -921,6 +922,12 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap)
 		VM_EVENT(kvm, 3, "ENABLE: CAP_S390_CPU_TOPOLOGY %s",
 			 r ? "(not available)" : "(success)");
 		break;
+	case KVM_CAP_S390_USER_OPEREXEC:
+		VM_EVENT(kvm, 3, "%s", "ENABLE: CAP_S390_USER_OPEREXEC");
+		kvm->arch.user_operexec = 1;
+		icpt_operexc_on_all_vcpus(kvm);
+		r = 0;
+		break;
 	default:
 		r = -EINVAL;
 		break;
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 52f6000ab020..8ab07396ce3b 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -963,6 +963,7 @@ struct kvm_enable_cap {
 #define KVM_CAP_RISCV_MP_STATE_RESET 242
 #define KVM_CAP_ARM_CACHEABLE_PFNMAP_SUPPORTED 243
 #define KVM_CAP_GUEST_MEMFD_FLAGS 244
+#define KVM_CAP_S390_USER_OPEREXEC 245
 
 struct kvm_irq_routing_irqchip {
 	__u32 irqchip;
diff --git a/tools/testing/selftests/kvm/Makefile.kvm b/tools/testing/selftests/kvm/Makefile.kvm
index 148d427ff24b..87e429206bb8 100644
--- a/tools/testing/selftests/kvm/Makefile.kvm
+++ b/tools/testing/selftests/kvm/Makefile.kvm
@@ -194,6 +194,7 @@ TEST_GEN_PROGS_s390 += s390/debug_test
 TEST_GEN_PROGS_s390 += s390/cpumodel_subfuncs_test
 TEST_GEN_PROGS_s390 += s390/shared_zeropage_test
 TEST_GEN_PROGS_s390 += s390/ucontrol_test
+TEST_GEN_PROGS_s390 += s390/user_operexec
 TEST_GEN_PROGS_s390 += rseq_test
 
 TEST_GEN_PROGS_riscv = $(TEST_GEN_PROGS_COMMON)
diff --git a/tools/testing/selftests/kvm/s390/user_operexec.c b/tools/testing/selftests/kvm/s390/user_operexec.c
new file mode 100644
index 000000000000..714906c1d12a
--- /dev/null
+++ b/tools/testing/selftests/kvm/s390/user_operexec.c
@@ -0,0 +1,140 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Test operation exception forwarding.
+ *
+ * Copyright IBM Corp. 2025
+ *
+ * Authors:
+ *  Janosch Frank <frankja@linux.ibm.com>
+ */
+#include "kselftest.h"
+#include "kvm_util.h"
+#include "test_util.h"
+#include "sie.h"
+
+#include <linux/kvm.h>
+
+static void guest_code_instr0(void)
+{
+	asm(".word 0x0000");
+}
+
+static void test_user_instr0(void)
+{
+	struct kvm_vcpu *vcpu;
+	struct kvm_vm *vm;
+	int rc;
+
+	vm = vm_create_with_one_vcpu(&vcpu, guest_code_instr0);
+	rc = __vm_enable_cap(vm, KVM_CAP_S390_USER_INSTR0, 0);
+	TEST_ASSERT_EQ(0, rc);
+
+	vcpu_run(vcpu);
+	TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_S390_SIEIC);
+	TEST_ASSERT_EQ(vcpu->run->s390_sieic.icptcode, ICPT_OPEREXC);
+	TEST_ASSERT_EQ(vcpu->run->s390_sieic.ipa, 0);
+
+	kvm_vm_free(vm);
+}
+
+static void guest_code_user_operexec(void)
+{
+	asm(".word 0x0807");
+}
+
+static void test_user_operexec(void)
+{
+	struct kvm_vcpu *vcpu;
+	struct kvm_vm *vm;
+	int rc;
+
+	vm = vm_create_with_one_vcpu(&vcpu, guest_code_user_operexec);
+	rc = __vm_enable_cap(vm, KVM_CAP_S390_USER_OPEREXEC, 0);
+	TEST_ASSERT_EQ(0, rc);
+
+	vcpu_run(vcpu);
+	TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_S390_SIEIC);
+	TEST_ASSERT_EQ(vcpu->run->s390_sieic.icptcode, ICPT_OPEREXC);
+	TEST_ASSERT_EQ(vcpu->run->s390_sieic.ipa, 0x0807);
+
+	kvm_vm_free(vm);
+
+	/*
+	 * Since user_operexec is the superset it can be used for the
+	 * 0 instruction.
+	 */
+	vm = vm_create_with_one_vcpu(&vcpu, guest_code_instr0);
+	rc = __vm_enable_cap(vm, KVM_CAP_S390_USER_OPEREXEC, 0);
+	TEST_ASSERT_EQ(0, rc);
+
+	vcpu_run(vcpu);
+	TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_S390_SIEIC);
+	TEST_ASSERT_EQ(vcpu->run->s390_sieic.icptcode, ICPT_OPEREXC);
+	TEST_ASSERT_EQ(vcpu->run->s390_sieic.ipa, 0);
+
+	kvm_vm_free(vm);
+}
+
+/* combine user_instr0 and user_operexec */
+static void test_user_operexec_combined(void)
+{
+	struct kvm_vcpu *vcpu;
+	struct kvm_vm *vm;
+	int rc;
+
+	vm = vm_create_with_one_vcpu(&vcpu, guest_code_user_operexec);
+	rc = __vm_enable_cap(vm, KVM_CAP_S390_USER_INSTR0, 0);
+	TEST_ASSERT_EQ(0, rc);
+	rc = __vm_enable_cap(vm, KVM_CAP_S390_USER_OPEREXEC, 0);
+	TEST_ASSERT_EQ(0, rc);
+
+	vcpu_run(vcpu);
+	TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_S390_SIEIC);
+	TEST_ASSERT_EQ(vcpu->run->s390_sieic.icptcode, ICPT_OPEREXC);
+	TEST_ASSERT_EQ(vcpu->run->s390_sieic.ipa, 0x0807);
+
+	kvm_vm_free(vm);
+
+	/* Reverse enablement order */
+	vm = vm_create_with_one_vcpu(&vcpu, guest_code_user_operexec);
+	rc = __vm_enable_cap(vm, KVM_CAP_S390_USER_OPEREXEC, 0);
+	TEST_ASSERT_EQ(0, rc);
+	rc = __vm_enable_cap(vm, KVM_CAP_S390_USER_INSTR0, 0);
+	TEST_ASSERT_EQ(0, rc);
+
+	vcpu_run(vcpu);
+	TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_S390_SIEIC);
+	TEST_ASSERT_EQ(vcpu->run->s390_sieic.icptcode, ICPT_OPEREXC);
+	TEST_ASSERT_EQ(vcpu->run->s390_sieic.ipa, 0x0807);
+
+	kvm_vm_free(vm);
+}
+
+/*
+ * Run all tests above.
+ *
+ * Enablement after VCPU has been added is automatically tested since
+ * we enable the capability after VCPU creation.
+ */
+static struct testdef {
+	const char *name;
+	void (*test)(void);
+} testlist[] = {
+	{ "instr0", test_user_instr0 },
+	{ "operexec", test_user_operexec },
+	{ "operexec_combined", test_user_operexec_combined},
+};
+
+int main(int argc, char *argv[])
+{
+	int idx;
+
+	TEST_REQUIRE(kvm_has_cap(KVM_CAP_S390_USER_INSTR0));
+
+	ksft_print_header();
+	ksft_set_plan(ARRAY_SIZE(testlist));
+	for (idx = 0; idx < ARRAY_SIZE(testlist); idx++) {
+		testlist[idx].test();
+		ksft_test_result_pass("%s\n", testlist[idx].name);
+	}
+	ksft_finished();
+}
-- 
cgit v1.2.3


From 1de4dc15baa1917adb3a0b369d00d818be9d9bab Mon Sep 17 00:00:00 2001
From: Yosry Ahmed <yosry.ahmed@linux.dev>
Date: Tue, 21 Oct 2025 07:47:23 +0000
Subject: KVM: selftests: Stop using __virt_pg_map() directly in tests

Replace __virt_pg_map() calls in tests by high-level equivalent
functions, removing some loops in the process.

No functional change intended.

Signed-off-by: Yosry Ahmed <yosry.ahmed@linux.dev>
Link: https://patch.msgid.link/20251021074736.1324328-11-yosry.ahmed@linux.dev
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 tools/testing/selftests/kvm/mmu_stress_test.c      | 6 ++----
 tools/testing/selftests/kvm/x86/hyperv_tlb_flush.c | 2 +-
 2 files changed, 3 insertions(+), 5 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/kvm/mmu_stress_test.c b/tools/testing/selftests/kvm/mmu_stress_test.c
index c799e0d0694f..51c070556f3e 100644
--- a/tools/testing/selftests/kvm/mmu_stress_test.c
+++ b/tools/testing/selftests/kvm/mmu_stress_test.c
@@ -362,11 +362,9 @@ int main(int argc, char *argv[])
 
 #ifdef __x86_64__
 		/* Identity map memory in the guest using 1gb pages. */
-		for (i = 0; i < slot_size; i += SZ_1G)
-			__virt_pg_map(vm, gpa + i, gpa + i, PG_LEVEL_1G);
+		virt_map_level(vm, gpa, gpa, slot_size, PG_LEVEL_1G);
 #else
-		for (i = 0; i < slot_size; i += vm->page_size)
-			virt_pg_map(vm, gpa + i, gpa + i);
+		virt_map(vm, gpa, gpa, slot_size >> vm->page_shift);
 #endif
 	}
 
diff --git a/tools/testing/selftests/kvm/x86/hyperv_tlb_flush.c b/tools/testing/selftests/kvm/x86/hyperv_tlb_flush.c
index 077cd0ec3040..a3b7ce155981 100644
--- a/tools/testing/selftests/kvm/x86/hyperv_tlb_flush.c
+++ b/tools/testing/selftests/kvm/x86/hyperv_tlb_flush.c
@@ -621,7 +621,7 @@ int main(int argc, char *argv[])
 	for (i = 0; i < NTEST_PAGES; i++) {
 		pte = vm_get_page_table_entry(vm, data->test_pages + i * PAGE_SIZE);
 		gpa = addr_hva2gpa(vm, pte);
-		__virt_pg_map(vm, gva + PAGE_SIZE * i, gpa & PAGE_MASK, PG_LEVEL_4K);
+		virt_pg_map(vm, gva + PAGE_SIZE * i, gpa & PAGE_MASK);
 		data->test_pages_pte[i] = gva + (gpa & ~PAGE_MASK);
 	}
 
-- 
cgit v1.2.3


From d2e50389ab44acfa05e72604d701a70b234f9938 Mon Sep 17 00:00:00 2001
From: Yosry Ahmed <yosry.ahmed@linux.dev>
Date: Tue, 21 Oct 2025 07:47:24 +0000
Subject: KVM: selftests: Make sure vm->vpages_mapped is always up-to-date

Call paths leading to __virt_pg_map() are currently:
(a) virt_pg_map() -> virt_arch_pg_map() -> __virt_pg_map()
(b) virt_map_level() -> __virt_pg_map()

For (a), calls to virt_pg_map() from kvm_util.c make sure they update
vm->vpages_mapped, but other callers do not. Move the sparsebit_set()
call into virt_pg_map() to make sure all callers are captured.

For (b), call sparsebit_set_num() from virt_map_level().

It's tempting to have a single the call inside __virt_pg_map(), however:
- The call path in (a) is not x86-specific, while (b) is. Moving the
  call into __virt_pg_map() would require doing something similar for
  other archs implementing virt_pg_map().

- Future changes will reusue __virt_pg_map() for nested PTEs, which should
  not update vm->vpages_mapped, i.e. a triple underscore version that does
  not update vm->vpages_mapped would need to be provided.

Signed-off-by: Yosry Ahmed <yosry.ahmed@linux.dev>
Link: https://patch.msgid.link/20251021074736.1324328-12-yosry.ahmed@linux.dev
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 tools/testing/selftests/kvm/include/kvm_util.h  | 1 +
 tools/testing/selftests/kvm/lib/kvm_util.c      | 3 ---
 tools/testing/selftests/kvm/lib/x86/processor.c | 2 ++
 3 files changed, 3 insertions(+), 3 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h
index 8a54a1279d44..d701ee557f5b 100644
--- a/tools/testing/selftests/kvm/include/kvm_util.h
+++ b/tools/testing/selftests/kvm/include/kvm_util.h
@@ -1230,6 +1230,7 @@ void virt_arch_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr);
 static inline void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr)
 {
 	virt_arch_pg_map(vm, vaddr, paddr);
+	sparsebit_set(vm->vpages_mapped, vaddr >> vm->page_shift);
 }
 
 
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 364efd02ad4a..33aebedfc050 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -1458,8 +1458,6 @@ static vm_vaddr_t ____vm_vaddr_alloc(struct kvm_vm *vm, size_t sz,
 		pages--, vaddr += vm->page_size, paddr += vm->page_size) {
 
 		virt_pg_map(vm, vaddr, paddr);
-
-		sparsebit_set(vm->vpages_mapped, vaddr >> vm->page_shift);
 	}
 
 	return vaddr_start;
@@ -1573,7 +1571,6 @@ void virt_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
 
 	while (npages--) {
 		virt_pg_map(vm, vaddr, paddr);
-		sparsebit_set(vm->vpages_mapped, vaddr >> vm->page_shift);
 
 		vaddr += page_size;
 		paddr += page_size;
diff --git a/tools/testing/selftests/kvm/lib/x86/processor.c b/tools/testing/selftests/kvm/lib/x86/processor.c
index 40bd69b265ef..36104d27f3d9 100644
--- a/tools/testing/selftests/kvm/lib/x86/processor.c
+++ b/tools/testing/selftests/kvm/lib/x86/processor.c
@@ -286,6 +286,8 @@ void virt_map_level(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
 
 	for (i = 0; i < nr_pages; i++) {
 		__virt_pg_map(vm, vaddr, paddr, level);
+		sparsebit_set_num(vm->vpages_mapped, vaddr >> vm->page_shift,
+				  nr_bytes / PAGE_SIZE);
 
 		vaddr += pg_size;
 		paddr += pg_size;
-- 
cgit v1.2.3


From d1c5620781d590b07543f8d31a5c87abf046c126 Mon Sep 17 00:00:00 2001
From: Anup Patel <apatel@ventanamicro.com>
Date: Fri, 17 Oct 2025 21:29:25 +0530
Subject: KVM: riscv: selftests: Add SBI MPXY extension to get-reg-list

The KVM RISC-V allows SBI MPXY extensions for Guest/VM so add
it to the get-reg-list test.

Signed-off-by: Anup Patel <apatel@ventanamicro.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Link: https://lore.kernel.org/r/20251017155925.361560-5-apatel@ventanamicro.com
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 tools/testing/selftests/kvm/riscv/get-reg-list.c | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/kvm/riscv/get-reg-list.c b/tools/testing/selftests/kvm/riscv/get-reg-list.c
index 705ab3d7778b..cb54a56990a0 100644
--- a/tools/testing/selftests/kvm/riscv/get-reg-list.c
+++ b/tools/testing/selftests/kvm/riscv/get-reg-list.c
@@ -133,6 +133,7 @@ bool filter_reg(__u64 reg)
 	case KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_SUSP:
 	case KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_STA:
 	case KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_FWFT:
+	case KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_MPXY:
 	case KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_EXPERIMENTAL:
 	case KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_VENDOR:
 		return true;
@@ -639,6 +640,7 @@ static const char *sbi_ext_single_id_to_str(__u64 reg_off)
 		KVM_SBI_EXT_ARR(KVM_RISCV_SBI_EXT_SUSP),
 		KVM_SBI_EXT_ARR(KVM_RISCV_SBI_EXT_STA),
 		KVM_SBI_EXT_ARR(KVM_RISCV_SBI_EXT_FWFT),
+		KVM_SBI_EXT_ARR(KVM_RISCV_SBI_EXT_MPXY),
 		KVM_SBI_EXT_ARR(KVM_RISCV_SBI_EXT_EXPERIMENTAL),
 		KVM_SBI_EXT_ARR(KVM_RISCV_SBI_EXT_VENDOR),
 	};
@@ -1142,6 +1144,7 @@ KVM_SBI_EXT_SUBLIST_CONFIG(sta, STA);
 KVM_SBI_EXT_SIMPLE_CONFIG(pmu, PMU);
 KVM_SBI_EXT_SIMPLE_CONFIG(dbcn, DBCN);
 KVM_SBI_EXT_SIMPLE_CONFIG(susp, SUSP);
+KVM_SBI_EXT_SIMPLE_CONFIG(mpxy, MPXY);
 KVM_SBI_EXT_SUBLIST_CONFIG(fwft, FWFT);
 
 KVM_ISA_EXT_SUBLIST_CONFIG(aia, AIA);
@@ -1222,6 +1225,7 @@ struct vcpu_reg_list *vcpu_configs[] = {
 	&config_sbi_pmu,
 	&config_sbi_dbcn,
 	&config_sbi_susp,
+	&config_sbi_mpxy,
 	&config_sbi_fwft,
 	&config_aia,
 	&config_fp_f,
-- 
cgit v1.2.3


From a1650de7c160aace941d27d39b60c38f6f795aa1 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Thu, 20 Nov 2025 17:25:30 +0000
Subject: KVM: arm64: selftests: gic_v3: Add irq group setting helper

Being able to set the group of an interrupt is pretty useful.
Add such a helper.

Tested-by: Fuad Tabba <tabba@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Tested-by: Mark Brown <broonie@kernel.org>
Link: https://msgid.link/20251120172540.2267180-41-maz@kernel.org
Signed-off-by: Oliver Upton <oupton@kernel.org>
---
 tools/testing/selftests/kvm/include/arm64/gic.h     |  1 +
 tools/testing/selftests/kvm/lib/arm64/gic.c         |  6 ++++++
 tools/testing/selftests/kvm/lib/arm64/gic_private.h |  1 +
 tools/testing/selftests/kvm/lib/arm64/gic_v3.c      | 15 +++++++++++++++
 4 files changed, 23 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/kvm/include/arm64/gic.h b/tools/testing/selftests/kvm/include/arm64/gic.h
index baeb3c859389..cc7a7f34ed37 100644
--- a/tools/testing/selftests/kvm/include/arm64/gic.h
+++ b/tools/testing/selftests/kvm/include/arm64/gic.h
@@ -57,6 +57,7 @@ void gic_irq_set_pending(unsigned int intid);
 void gic_irq_clear_pending(unsigned int intid);
 bool gic_irq_get_pending(unsigned int intid);
 void gic_irq_set_config(unsigned int intid, bool is_edge);
+void gic_irq_set_group(unsigned int intid, bool group);
 
 void gic_rdist_enable_lpis(vm_paddr_t cfg_table, size_t cfg_table_size,
 			   vm_paddr_t pend_table);
diff --git a/tools/testing/selftests/kvm/lib/arm64/gic.c b/tools/testing/selftests/kvm/lib/arm64/gic.c
index 7abbf8866512..b023868fe0b8 100644
--- a/tools/testing/selftests/kvm/lib/arm64/gic.c
+++ b/tools/testing/selftests/kvm/lib/arm64/gic.c
@@ -155,3 +155,9 @@ void gic_irq_set_config(unsigned int intid, bool is_edge)
 	GUEST_ASSERT(gic_common_ops);
 	gic_common_ops->gic_irq_set_config(intid, is_edge);
 }
+
+void gic_irq_set_group(unsigned int intid, bool group)
+{
+	GUEST_ASSERT(gic_common_ops);
+	gic_common_ops->gic_irq_set_group(intid, group);
+}
diff --git a/tools/testing/selftests/kvm/lib/arm64/gic_private.h b/tools/testing/selftests/kvm/lib/arm64/gic_private.h
index d24e9ecc96c6..b6a7e30c3eb1 100644
--- a/tools/testing/selftests/kvm/lib/arm64/gic_private.h
+++ b/tools/testing/selftests/kvm/lib/arm64/gic_private.h
@@ -25,6 +25,7 @@ struct gic_common_ops {
 	void (*gic_irq_clear_pending)(uint32_t intid);
 	bool (*gic_irq_get_pending)(uint32_t intid);
 	void (*gic_irq_set_config)(uint32_t intid, bool is_edge);
+	void (*gic_irq_set_group)(uint32_t intid, bool group);
 };
 
 extern const struct gic_common_ops gicv3_ops;
diff --git a/tools/testing/selftests/kvm/lib/arm64/gic_v3.c b/tools/testing/selftests/kvm/lib/arm64/gic_v3.c
index 66d05506f78b..3e4e1a6a4f7c 100644
--- a/tools/testing/selftests/kvm/lib/arm64/gic_v3.c
+++ b/tools/testing/selftests/kvm/lib/arm64/gic_v3.c
@@ -293,6 +293,20 @@ static void gicv3_enable_redist(volatile void *redist_base)
 	}
 }
 
+static void gicv3_set_group(uint32_t intid, bool grp)
+{
+	uint32_t cpu_or_dist;
+	uint32_t val;
+
+	cpu_or_dist = (get_intid_range(intid) == SPI_RANGE) ? DIST_BIT : guest_get_vcpuid();
+	val = gicv3_reg_readl(cpu_or_dist, GICD_IGROUPR + (intid / 32) * 4);
+	if (grp)
+		val |= BIT(intid % 32);
+	else
+		val &= ~BIT(intid % 32);
+	gicv3_reg_writel(cpu_or_dist, GICD_IGROUPR + (intid / 32) * 4, val);
+}
+
 static void gicv3_cpu_init(unsigned int cpu)
 {
 	volatile void *sgi_base;
@@ -400,6 +414,7 @@ const struct gic_common_ops gicv3_ops = {
 	.gic_irq_clear_pending = gicv3_irq_clear_pending,
 	.gic_irq_get_pending = gicv3_irq_get_pending,
 	.gic_irq_set_config = gicv3_irq_set_config,
+	.gic_irq_set_group = gicv3_set_group,
 };
 
 void gic_rdist_enable_lpis(vm_paddr_t cfg_table, size_t cfg_table_size,
-- 
cgit v1.2.3


From 2366295c76c2e09b969b4a5a0829d750bb1ab062 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Thu, 20 Nov 2025 17:25:31 +0000
Subject: KVM: arm64: selftests: gic_v3: Disable Group-0 interrupts by default

Make sure G0 is disabled at the point of initialising the GIC.

Tested-by: Fuad Tabba <tabba@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Tested-by: Mark Brown <broonie@kernel.org>
Link: https://msgid.link/20251120172540.2267180-42-maz@kernel.org
Signed-off-by: Oliver Upton <oupton@kernel.org>
---
 tools/testing/selftests/kvm/lib/arm64/gic_v3.c | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/kvm/lib/arm64/gic_v3.c b/tools/testing/selftests/kvm/lib/arm64/gic_v3.c
index 3e4e1a6a4f7c..5b0fd95c6b48 100644
--- a/tools/testing/selftests/kvm/lib/arm64/gic_v3.c
+++ b/tools/testing/selftests/kvm/lib/arm64/gic_v3.c
@@ -342,6 +342,8 @@ static void gicv3_cpu_init(unsigned int cpu)
 	/* Set a default priority threshold */
 	write_sysreg_s(ICC_PMR_DEF_PRIO, SYS_ICC_PMR_EL1);
 
+	/* Disable Group-0 interrupts */
+	write_sysreg_s(ICC_IGRPEN0_EL1_MASK, SYS_ICC_IGRPEN1_EL1);
 	/* Enable non-secure Group-1 interrupts */
 	write_sysreg_s(ICC_IGRPEN1_EL1_MASK, SYS_ICC_IGRPEN1_EL1);
 }
-- 
cgit v1.2.3


From 27392612c8823f4b65240949eb0dc77de946285d Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Thu, 20 Nov 2025 17:25:32 +0000
Subject: KVM: arm64: selftests: vgic_irq: Fix GUEST_ASSERT_IAR_EMPTY() helper

No, 0 is not a spurious INTID. Never been, never was.

Tested-by: Fuad Tabba <tabba@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Tested-by: Mark Brown <broonie@kernel.org>
Link: https://msgid.link/20251120172540.2267180-43-maz@kernel.org
Signed-off-by: Oliver Upton <oupton@kernel.org>
---
 tools/testing/selftests/kvm/arm64/vgic_irq.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/kvm/arm64/vgic_irq.c b/tools/testing/selftests/kvm/arm64/vgic_irq.c
index 6338f5bbdb70..a77562b2976a 100644
--- a/tools/testing/selftests/kvm/arm64/vgic_irq.c
+++ b/tools/testing/selftests/kvm/arm64/vgic_irq.c
@@ -205,7 +205,7 @@ static void kvm_inject_call(kvm_inject_cmd cmd, uint32_t first_intid,
 do { 										\
 	uint32_t _intid;							\
 	_intid = gic_get_and_ack_irq();						\
-	GUEST_ASSERT(_intid == 0 || _intid == IAR_SPURIOUS);			\
+	GUEST_ASSERT(_intid == IAR_SPURIOUS);					\
 } while (0)
 
 #define CAT_HELPER(a, b) a ## b
-- 
cgit v1.2.3


From 8b7888c5114d280b071f341c072775ee222178b1 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Thu, 20 Nov 2025 17:25:33 +0000
Subject: KVM: arm64: selftests: vgic_irq: Change configuration before enabling
 interrupt

The architecture is pretty clear that changing the configuration of
an enable interrupt is not OK. It doesn't really matter here, but
doing the right thing is not more expensive.

Tested-by: Fuad Tabba <tabba@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Tested-by: Mark Brown <broonie@kernel.org>
Link: https://msgid.link/20251120172540.2267180-44-maz@kernel.org
Signed-off-by: Oliver Upton <oupton@kernel.org>
---
 tools/testing/selftests/kvm/arm64/vgic_irq.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/kvm/arm64/vgic_irq.c b/tools/testing/selftests/kvm/arm64/vgic_irq.c
index a77562b2976a..a8919ef3cea2 100644
--- a/tools/testing/selftests/kvm/arm64/vgic_irq.c
+++ b/tools/testing/selftests/kvm/arm64/vgic_irq.c
@@ -473,12 +473,12 @@ static void guest_code(struct test_args *args)
 
 	gic_init(GIC_V3, 1);
 
-	for (i = 0; i < nr_irqs; i++)
-		gic_irq_enable(i);
-
 	for (i = MIN_SPI; i < nr_irqs; i++)
 		gic_irq_set_config(i, !level_sensitive);
 
+	for (i = 0; i < nr_irqs; i++)
+		gic_irq_enable(i);
+
 	gic_set_eoi_split(args->eoi_split);
 
 	reset_priorities(args);
-- 
cgit v1.2.3


From 5053c2ab92a1e7cbfd3705be2f4371bf843aad2c Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Thu, 20 Nov 2025 17:25:34 +0000
Subject: KVM: arm64: selftests: vgic_irq: Exclude timer-controlled interrupts

The PPI injection API is clear that you can't inject the timer PPIs
from userspace, since they are controlled by the timers themselves.

Add an exclusion list for this purpose.

Tested-by: Fuad Tabba <tabba@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Tested-by: Mark Brown <broonie@kernel.org>
Link: https://msgid.link/20251120172540.2267180-45-maz@kernel.org
Signed-off-by: Oliver Upton <oupton@kernel.org>
---
 tools/testing/selftests/kvm/arm64/vgic_irq.c | 31 ++++++++++++++++++++++------
 1 file changed, 25 insertions(+), 6 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/kvm/arm64/vgic_irq.c b/tools/testing/selftests/kvm/arm64/vgic_irq.c
index a8919ef3cea2..b0415bdb8952 100644
--- a/tools/testing/selftests/kvm/arm64/vgic_irq.c
+++ b/tools/testing/selftests/kvm/arm64/vgic_irq.c
@@ -359,8 +359,9 @@ static uint32_t wait_for_and_activate_irq(void)
  * interrupts for the whole test.
  */
 static void test_inject_preemption(struct test_args *args,
-		uint32_t first_intid, int num,
-		kvm_inject_cmd cmd)
+				   uint32_t first_intid, int num,
+				   const unsigned long *exclude,
+				   kvm_inject_cmd cmd)
 {
 	uint32_t intid, prio, step = KVM_PRIO_STEPS;
 	int i;
@@ -379,6 +380,10 @@ static void test_inject_preemption(struct test_args *args,
 	for (i = 0; i < num; i++) {
 		uint32_t tmp;
 		intid = i + first_intid;
+
+		if (exclude && test_bit(i, exclude))
+			continue;
+
 		KVM_INJECT(cmd, intid);
 		/* Each successive IRQ will preempt the previous one. */
 		tmp = wait_for_and_activate_irq();
@@ -390,6 +395,10 @@ static void test_inject_preemption(struct test_args *args,
 	/* finish handling the IRQs starting with the highest priority one. */
 	for (i = 0; i < num; i++) {
 		intid = num - i - 1 + first_intid;
+
+		if (exclude && test_bit(intid - first_intid, exclude))
+			continue;
+
 		gic_set_eoi(intid);
 		if (args->eoi_split)
 			gic_set_dir(intid);
@@ -397,8 +406,12 @@ static void test_inject_preemption(struct test_args *args,
 
 	local_irq_enable();
 
-	for (i = 0; i < num; i++)
+	for (i = 0; i < num; i++) {
+		if (exclude && test_bit(i, exclude))
+			continue;
+
 		GUEST_ASSERT(!gic_irq_get_active(i + first_intid));
+	}
 	GUEST_ASSERT_EQ(gic_read_ap1r0(), 0);
 	GUEST_ASSERT_IAR_EMPTY();
 
@@ -442,14 +455,20 @@ static void test_preemption(struct test_args *args, struct kvm_inject_desc *f)
 	 * number of concurrently active IRQs. The number of LRs implemented is
 	 * IMPLEMENTATION DEFINED, however, it seems that most implement 4.
 	 */
+	/* Timer PPIs cannot be injected from userspace */
+	static const unsigned long ppi_exclude = (BIT(27 - MIN_PPI) |
+						  BIT(30 - MIN_PPI) |
+						  BIT(28 - MIN_PPI) |
+						  BIT(26 - MIN_PPI));
+
 	if (f->sgi)
-		test_inject_preemption(args, MIN_SGI, 4, f->cmd);
+		test_inject_preemption(args, MIN_SGI, 4, NULL, f->cmd);
 
 	if (f->ppi)
-		test_inject_preemption(args, MIN_PPI, 4, f->cmd);
+		test_inject_preemption(args, MIN_PPI, 4, &ppi_exclude, f->cmd);
 
 	if (f->spi)
-		test_inject_preemption(args, MIN_SPI, 4, f->cmd);
+		test_inject_preemption(args, MIN_SPI, 4, NULL, f->cmd);
 }
 
 static void test_restore_active(struct test_args *args, struct kvm_inject_desc *f)
-- 
cgit v1.2.3


From fd5fa1c8d09a77c0986158af5b522f6d35830329 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Thu, 20 Nov 2025 17:25:35 +0000
Subject: KVM: arm64: selftests: vgic_irq: Remove LR-bound limitation

Good news: our GIC emulation is not completely broken, and we can
activate as many interrupts as we want.

Bump the test to cover all the SGIs, all the allowed PPIs, and
31 SPIs. Yes, 31, because we have 31 available priorities, and the
test is not happy with having two interrupts with the same priority.

Tested-by: Fuad Tabba <tabba@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Tested-by: Mark Brown <broonie@kernel.org>
Link: https://msgid.link/20251120172540.2267180-46-maz@kernel.org
Signed-off-by: Oliver Upton <oupton@kernel.org>
---
 tools/testing/selftests/kvm/arm64/vgic_irq.c | 19 ++++++-------------
 1 file changed, 6 insertions(+), 13 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/kvm/arm64/vgic_irq.c b/tools/testing/selftests/kvm/arm64/vgic_irq.c
index b0415bdb8952..9d4761f1a320 100644
--- a/tools/testing/selftests/kvm/arm64/vgic_irq.c
+++ b/tools/testing/selftests/kvm/arm64/vgic_irq.c
@@ -449,12 +449,6 @@ static void test_injection_failure(struct test_args *args,
 
 static void test_preemption(struct test_args *args, struct kvm_inject_desc *f)
 {
-	/*
-	 * Test up to 4 levels of preemption. The reason is that KVM doesn't
-	 * currently implement the ability to have more than the number-of-LRs
-	 * number of concurrently active IRQs. The number of LRs implemented is
-	 * IMPLEMENTATION DEFINED, however, it seems that most implement 4.
-	 */
 	/* Timer PPIs cannot be injected from userspace */
 	static const unsigned long ppi_exclude = (BIT(27 - MIN_PPI) |
 						  BIT(30 - MIN_PPI) |
@@ -462,26 +456,25 @@ static void test_preemption(struct test_args *args, struct kvm_inject_desc *f)
 						  BIT(26 - MIN_PPI));
 
 	if (f->sgi)
-		test_inject_preemption(args, MIN_SGI, 4, NULL, f->cmd);
+		test_inject_preemption(args, MIN_SGI, 16, NULL, f->cmd);
 
 	if (f->ppi)
-		test_inject_preemption(args, MIN_PPI, 4, &ppi_exclude, f->cmd);
+		test_inject_preemption(args, MIN_PPI, 16, &ppi_exclude, f->cmd);
 
 	if (f->spi)
-		test_inject_preemption(args, MIN_SPI, 4, NULL, f->cmd);
+		test_inject_preemption(args, MIN_SPI, 31, NULL, f->cmd);
 }
 
 static void test_restore_active(struct test_args *args, struct kvm_inject_desc *f)
 {
-	/* Test up to 4 active IRQs. Same reason as in test_preemption. */
 	if (f->sgi)
-		guest_restore_active(args, MIN_SGI, 4, f->cmd);
+		guest_restore_active(args, MIN_SGI, 16, f->cmd);
 
 	if (f->ppi)
-		guest_restore_active(args, MIN_PPI, 4, f->cmd);
+		guest_restore_active(args, MIN_PPI, 16, f->cmd);
 
 	if (f->spi)
-		guest_restore_active(args, MIN_SPI, 4, f->cmd);
+		guest_restore_active(args, MIN_SPI, 31, f->cmd);
 }
 
 static void guest_code(struct test_args *args)
-- 
cgit v1.2.3


From b6c68612ab4171e07a7c2ba8864b967207fc3add Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Thu, 20 Nov 2025 17:25:36 +0000
Subject: KVM: arm64: selftests: vgic_irq: Perform EOImode==1 deactivation in
 ack order

When EOImode==1, perform the deactivation in the order of activation,
just to make things a bit worse for KVM. Yes, I'm nasty.

Tested-by: Fuad Tabba <tabba@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Tested-by: Mark Brown <broonie@kernel.org>
Link: https://msgid.link/20251120172540.2267180-47-maz@kernel.org
Signed-off-by: Oliver Upton <oupton@kernel.org>
---
 tools/testing/selftests/kvm/arm64/vgic_irq.c | 14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/kvm/arm64/vgic_irq.c b/tools/testing/selftests/kvm/arm64/vgic_irq.c
index 9d4761f1a320..72f7bb0d201e 100644
--- a/tools/testing/selftests/kvm/arm64/vgic_irq.c
+++ b/tools/testing/selftests/kvm/arm64/vgic_irq.c
@@ -400,8 +400,18 @@ static void test_inject_preemption(struct test_args *args,
 			continue;
 
 		gic_set_eoi(intid);
-		if (args->eoi_split)
-			gic_set_dir(intid);
+	}
+
+	if (args->eoi_split) {
+		for (i = 0; i < num; i++) {
+			intid = i + first_intid;
+
+			if (exclude && test_bit(i, exclude))
+				continue;
+
+			if (args->eoi_split)
+				gic_set_dir(intid);
+		}
 	}
 
 	local_irq_enable();
-- 
cgit v1.2.3


From d2dee2e849834564293ec9c33165df56dd441399 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Thu, 20 Nov 2025 17:25:37 +0000
Subject: KVM: arm64: selftests: vgic_irq: Add asymmetric SPI deaectivation
 test

Add a new test case that makes an interrupt pending on a vcpu,
activates it, do the priority drop, and then get *another* vcpu
to do the deactivation.

Special care is taken not to trigger an exit in the process, so
that we are sure that the active interrupt is in an LR. Joy.

Tested-by: Fuad Tabba <tabba@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Tested-by: Mark Brown <broonie@kernel.org>
Link: https://msgid.link/20251120172540.2267180-48-maz@kernel.org
Signed-off-by: Oliver Upton <oupton@kernel.org>
---
 tools/testing/selftests/kvm/arm64/vgic_irq.c | 105 +++++++++++++++++++++++++++
 1 file changed, 105 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/kvm/arm64/vgic_irq.c b/tools/testing/selftests/kvm/arm64/vgic_irq.c
index 72f7bb0d201e..a53ab809fe8a 100644
--- a/tools/testing/selftests/kvm/arm64/vgic_irq.c
+++ b/tools/testing/selftests/kvm/arm64/vgic_irq.c
@@ -29,6 +29,7 @@ struct test_args {
 	bool level_sensitive; /* 1 is level, 0 is edge */
 	int kvm_max_routes; /* output of KVM_CAP_IRQ_ROUTING */
 	bool kvm_supports_irqfd; /* output of KVM_CAP_IRQFD */
+	uint32_t shared_data;
 };
 
 /*
@@ -801,6 +802,109 @@ done:
 	kvm_vm_free(vm);
 }
 
+static void guest_code_asym_dir(struct test_args *args, int cpuid)
+{
+	gic_init(GIC_V3, 2);
+
+	gic_set_eoi_split(1);
+	gic_set_priority_mask(CPU_PRIO_MASK);
+
+	if (cpuid == 0) {
+		uint32_t intid;
+
+		local_irq_disable();
+
+		gic_set_priority(MIN_PPI, IRQ_DEFAULT_PRIO);
+		gic_irq_enable(MIN_SPI);
+		gic_irq_set_pending(MIN_SPI);
+
+		intid = wait_for_and_activate_irq();
+		GUEST_ASSERT_EQ(intid, MIN_SPI);
+
+		gic_set_eoi(intid);
+		isb();
+
+		WRITE_ONCE(args->shared_data, MIN_SPI);
+		dsb(ishst);
+
+		do {
+			dsb(ishld);
+		} while (READ_ONCE(args->shared_data) == MIN_SPI);
+		GUEST_ASSERT(!gic_irq_get_active(MIN_SPI));
+	} else {
+		do {
+			dsb(ishld);
+		} while (READ_ONCE(args->shared_data) != MIN_SPI);
+
+		gic_set_dir(MIN_SPI);
+		isb();
+
+		WRITE_ONCE(args->shared_data, 0);
+		dsb(ishst);
+	}
+
+	GUEST_DONE();
+}
+
+static void *test_vcpu_run(void *arg)
+{
+	struct kvm_vcpu *vcpu = arg;
+	struct ucall uc;
+
+	while (1) {
+		vcpu_run(vcpu);
+
+		switch (get_ucall(vcpu, &uc)) {
+		case UCALL_ABORT:
+			REPORT_GUEST_ASSERT(uc);
+			break;
+		case UCALL_DONE:
+			return NULL;
+		default:
+			TEST_FAIL("Unknown ucall %lu", uc.cmd);
+		}
+	}
+
+	return NULL;
+}
+
+static void test_vgic_two_cpus(void *gcode)
+{
+	pthread_t thr[2];
+	struct kvm_vcpu *vcpus[2];
+	struct test_args args = {};
+	struct kvm_vm *vm;
+	vm_vaddr_t args_gva;
+	int gic_fd, ret;
+
+	vm = vm_create_with_vcpus(2, gcode, vcpus);
+
+	vm_init_descriptor_tables(vm);
+	vcpu_init_descriptor_tables(vcpus[0]);
+	vcpu_init_descriptor_tables(vcpus[1]);
+
+	/* Setup the guest args page (so it gets the args). */
+	args_gva = vm_vaddr_alloc_page(vm);
+	memcpy(addr_gva2hva(vm, args_gva), &args, sizeof(args));
+	vcpu_args_set(vcpus[0], 2, args_gva, 0);
+	vcpu_args_set(vcpus[1], 2, args_gva, 1);
+
+	gic_fd = vgic_v3_setup(vm, 2, 64);
+
+	ret = pthread_create(&thr[0], NULL, test_vcpu_run, vcpus[0]);
+	if (ret)
+		TEST_FAIL("Can't create thread for vcpu 0 (%d)\n", ret);
+	ret = pthread_create(&thr[1], NULL, test_vcpu_run, vcpus[1]);
+	if (ret)
+		TEST_FAIL("Can't create thread for vcpu 1 (%d)\n", ret);
+
+	pthread_join(thr[0], NULL);
+	pthread_join(thr[1], NULL);
+
+	close(gic_fd);
+	kvm_vm_free(vm);
+}
+
 static void help(const char *name)
 {
 	printf(
@@ -857,6 +961,7 @@ int main(int argc, char **argv)
 		test_vgic(nr_irqs, false /* level */, true /* eoi_split */);
 		test_vgic(nr_irqs, true /* level */, false /* eoi_split */);
 		test_vgic(nr_irqs, true /* level */, true /* eoi_split */);
+		test_vgic_two_cpus(guest_code_asym_dir);
 	} else {
 		test_vgic(nr_irqs, level_sensitive, eoi_split);
 	}
-- 
cgit v1.2.3


From 1c9c71ac1b9f86b3d1841c703e3e928b2ec224c7 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Thu, 20 Nov 2025 17:25:38 +0000
Subject: KVM: arm64: selftests: vgic_irq: Add Group-0 enable test

Add a new test case that inject a Group-0 interrupt together
with a bunch of Group-1 interrupts, Ack/EOI the G1 interrupts,
and only then enable G0, expecting to get the G0 interrupt.

Tested-by: Fuad Tabba <tabba@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Tested-by: Mark Brown <broonie@kernel.org>
Link: https://msgid.link/20251120172540.2267180-49-maz@kernel.org
Signed-off-by: Oliver Upton <oupton@kernel.org>
---
 tools/testing/selftests/kvm/arm64/vgic_irq.c | 49 ++++++++++++++++++++++++++++
 1 file changed, 49 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/kvm/arm64/vgic_irq.c b/tools/testing/selftests/kvm/arm64/vgic_irq.c
index a53ab809fe8a..ff2c75749f5c 100644
--- a/tools/testing/selftests/kvm/arm64/vgic_irq.c
+++ b/tools/testing/selftests/kvm/arm64/vgic_irq.c
@@ -846,6 +846,54 @@ static void guest_code_asym_dir(struct test_args *args, int cpuid)
 	GUEST_DONE();
 }
 
+static void guest_code_group_en(struct test_args *args, int cpuid)
+{
+	uint32_t intid;
+
+	gic_init(GIC_V3, 2);
+
+	gic_set_eoi_split(0);
+	gic_set_priority_mask(CPU_PRIO_MASK);
+	/* SGI0 is G0, which is disabled */
+	gic_irq_set_group(0, 0);
+
+	/* Configure all SGIs with decreasing priority */
+	for (intid = 0; intid < MIN_PPI; intid++) {
+		gic_set_priority(intid, (intid + 1) * 8);
+		gic_irq_enable(intid);
+		gic_irq_set_pending(intid);
+	}
+
+	/* Ack and EOI all G1 interrupts */
+	for (int i = 1; i < MIN_PPI; i++) {
+		intid = wait_for_and_activate_irq();
+
+		GUEST_ASSERT(intid < MIN_PPI);
+		gic_set_eoi(intid);
+		isb();
+	}
+
+	/*
+	 * Check that SGI0 is still pending, inactive, and that we cannot
+	 * ack anything.
+	 */
+	GUEST_ASSERT(gic_irq_get_pending(0));
+	GUEST_ASSERT(!gic_irq_get_active(0));
+	GUEST_ASSERT_IAR_EMPTY();
+	GUEST_ASSERT(read_sysreg_s(SYS_ICC_IAR0_EL1) == IAR_SPURIOUS);
+
+	/* Open the G0 gates, and verify we can ack SGI0 */
+	write_sysreg_s(1, SYS_ICC_IGRPEN0_EL1);
+	isb();
+
+	do {
+		intid = read_sysreg_s(SYS_ICC_IAR0_EL1);
+	} while (intid == IAR_SPURIOUS);
+
+	GUEST_ASSERT(intid == 0);
+	GUEST_DONE();
+}
+
 static void *test_vcpu_run(void *arg)
 {
 	struct kvm_vcpu *vcpu = arg;
@@ -962,6 +1010,7 @@ int main(int argc, char **argv)
 		test_vgic(nr_irqs, true /* level */, false /* eoi_split */);
 		test_vgic(nr_irqs, true /* level */, true /* eoi_split */);
 		test_vgic_two_cpus(guest_code_asym_dir);
+		test_vgic_two_cpus(guest_code_group_en);
 	} else {
 		test_vgic(nr_irqs, level_sensitive, eoi_split);
 	}
-- 
cgit v1.2.3


From de8842327728d07b5d836688a66ae5fa56902527 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Thu, 20 Nov 2025 17:25:39 +0000
Subject: KVM: arm64: selftests: vgic_irq: Add timer deactivation test

Add a new test case that triggers the HW deactivation emulation path
when trapping ICV_DIR_EL1. This is obviously tied to the way KVM
works now, but the test follows the expected architectural behaviour.

Tested-by: Fuad Tabba <tabba@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Tested-by: Mark Brown <broonie@kernel.org>
Link: https://msgid.link/20251120172540.2267180-50-maz@kernel.org
Signed-off-by: Oliver Upton <oupton@kernel.org>
---
 tools/testing/selftests/kvm/arm64/vgic_irq.c | 65 ++++++++++++++++++++++++++++
 1 file changed, 65 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/kvm/arm64/vgic_irq.c b/tools/testing/selftests/kvm/arm64/vgic_irq.c
index ff2c75749f5c..9858187c7b6e 100644
--- a/tools/testing/selftests/kvm/arm64/vgic_irq.c
+++ b/tools/testing/selftests/kvm/arm64/vgic_irq.c
@@ -894,6 +894,70 @@ static void guest_code_group_en(struct test_args *args, int cpuid)
 	GUEST_DONE();
 }
 
+static void guest_code_timer_spi(struct test_args *args, int cpuid)
+{
+	uint32_t intid;
+	u64 val;
+
+	gic_init(GIC_V3, 2);
+
+	gic_set_eoi_split(1);
+	gic_set_priority_mask(CPU_PRIO_MASK);
+
+	/* Add a pending SPI so that KVM starts trapping DIR */
+	gic_set_priority(MIN_SPI + cpuid, IRQ_DEFAULT_PRIO);
+	gic_irq_set_pending(MIN_SPI + cpuid);
+
+	/* Configure the timer with a higher priority, make it pending */
+	gic_set_priority(27, IRQ_DEFAULT_PRIO - 8);
+
+	isb();
+	val = read_sysreg(cntvct_el0);
+	write_sysreg(val, cntv_cval_el0);
+	write_sysreg(1, cntv_ctl_el0);
+	isb();
+
+	GUEST_ASSERT(gic_irq_get_pending(27));
+
+	/* Enable both interrupts */
+	gic_irq_enable(MIN_SPI + cpuid);
+	gic_irq_enable(27);
+
+	/* The timer must fire */
+	intid = wait_for_and_activate_irq();
+	GUEST_ASSERT(intid == 27);
+
+	/* Check that we can deassert it */
+	write_sysreg(0, cntv_ctl_el0);
+	isb();
+
+	GUEST_ASSERT(!gic_irq_get_pending(27));
+
+	/*
+	 * Priority drop, deactivation -- we expect that the host
+	 * deactivation will have been effective
+	 */
+	gic_set_eoi(27);
+	gic_set_dir(27);
+
+	GUEST_ASSERT(!gic_irq_get_active(27));
+
+	/* Do it one more time */
+	isb();
+	val = read_sysreg(cntvct_el0);
+	write_sysreg(val, cntv_cval_el0);
+	write_sysreg(1, cntv_ctl_el0);
+	isb();
+
+	GUEST_ASSERT(gic_irq_get_pending(27));
+
+	/* The timer must fire again */
+	intid = wait_for_and_activate_irq();
+	GUEST_ASSERT(intid == 27);
+
+	GUEST_DONE();
+}
+
 static void *test_vcpu_run(void *arg)
 {
 	struct kvm_vcpu *vcpu = arg;
@@ -1011,6 +1075,7 @@ int main(int argc, char **argv)
 		test_vgic(nr_irqs, true /* level */, true /* eoi_split */);
 		test_vgic_two_cpus(guest_code_asym_dir);
 		test_vgic_two_cpus(guest_code_group_en);
+		test_vgic_two_cpus(guest_code_timer_spi);
 	} else {
 		test_vgic(nr_irqs, level_sensitive, eoi_split);
 	}
-- 
cgit v1.2.3


From 985a96983bedf04fa61315e68806f3468450c8a1 Mon Sep 17 00:00:00 2001
From: Bibo Mao <maobibo@loongson.cn>
Date: Thu, 27 Nov 2025 11:00:18 +0800
Subject: KVM: LoongArch: selftests: Add system registers save/restore on
 exception

When system returns from exception with ertn instruction, PC comes from
LOONGARCH_CSR_ERA, and CSR.CRMD comes LOONGARCH_CSR_PRMD.

Here save CSR register CSR.ERA and CSR.PRMD into stack, and then restore
them from stack. So it can be modified by exception handlers in future.

Signed-off-by: Bibo Mao <maobibo@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 tools/testing/selftests/kvm/include/loongarch/processor.h | 5 ++++-
 tools/testing/selftests/kvm/lib/loongarch/exception.S     | 6 ++++++
 2 files changed, 10 insertions(+), 1 deletion(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/kvm/include/loongarch/processor.h b/tools/testing/selftests/kvm/include/loongarch/processor.h
index 6427a3275e6a..374caddfb0db 100644
--- a/tools/testing/selftests/kvm/include/loongarch/processor.h
+++ b/tools/testing/selftests/kvm/include/loongarch/processor.h
@@ -124,18 +124,21 @@ struct ex_regs {
 	unsigned long pc;
 	unsigned long estat;
 	unsigned long badv;
+	unsigned long prmd;
 };
 
 #define PC_OFFSET_EXREGS		offsetof(struct ex_regs, pc)
 #define ESTAT_OFFSET_EXREGS		offsetof(struct ex_regs, estat)
 #define BADV_OFFSET_EXREGS		offsetof(struct ex_regs, badv)
+#define PRMD_OFFSET_EXREGS		offsetof(struct ex_regs, prmd)
 #define EXREGS_SIZE			sizeof(struct ex_regs)
 
 #else
 #define PC_OFFSET_EXREGS		((EXREGS_GPRS + 0) * 8)
 #define ESTAT_OFFSET_EXREGS		((EXREGS_GPRS + 1) * 8)
 #define BADV_OFFSET_EXREGS		((EXREGS_GPRS + 2) * 8)
-#define EXREGS_SIZE			((EXREGS_GPRS + 3) * 8)
+#define PRMD_OFFSET_EXREGS		((EXREGS_GPRS + 3) * 8)
+#define EXREGS_SIZE			((EXREGS_GPRS + 4) * 8)
 #endif
 
 #endif /* SELFTEST_KVM_PROCESSOR_H */
diff --git a/tools/testing/selftests/kvm/lib/loongarch/exception.S b/tools/testing/selftests/kvm/lib/loongarch/exception.S
index 88bfa505c6f5..3f1e4b67c5ae 100644
--- a/tools/testing/selftests/kvm/lib/loongarch/exception.S
+++ b/tools/testing/selftests/kvm/lib/loongarch/exception.S
@@ -51,9 +51,15 @@ handle_exception:
 	st.d   t0, sp, ESTAT_OFFSET_EXREGS
 	csrrd  t0, LOONGARCH_CSR_BADV
 	st.d   t0, sp, BADV_OFFSET_EXREGS
+	csrrd  t0, LOONGARCH_CSR_PRMD
+	st.d   t0, sp, PRMD_OFFSET_EXREGS
 
 	or     a0, sp, zero
 	bl route_exception
+	ld.d   t0, sp, PC_OFFSET_EXREGS
+	csrwr  t0, LOONGARCH_CSR_ERA
+	ld.d   t0, sp, PRMD_OFFSET_EXREGS
+	csrwr  t0, LOONGARCH_CSR_PRMD
 	restore_gprs sp
 	csrrd  sp, LOONGARCH_CSR_KS0
 	ertn
-- 
cgit v1.2.3


From 1c5d3a1eab32db1ebb0d5d30736e9236e8a7014f Mon Sep 17 00:00:00 2001
From: Bibo Mao <maobibo@loongson.cn>
Date: Thu, 27 Nov 2025 11:00:18 +0800
Subject: KVM: LoongArch: selftests: Add basic interfaces

Add some basic function interfaces such as CSR register access, local
irq enable or disable APIs.

Signed-off-by: Bibo Mao <maobibo@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 .../selftests/kvm/include/loongarch/processor.h    | 50 ++++++++++++++++++++++
 .../selftests/kvm/lib/loongarch/processor.c        |  5 +++
 2 files changed, 55 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/kvm/include/loongarch/processor.h b/tools/testing/selftests/kvm/include/loongarch/processor.h
index 374caddfb0db..f1bfc06a2264 100644
--- a/tools/testing/selftests/kvm/include/loongarch/processor.h
+++ b/tools/testing/selftests/kvm/include/loongarch/processor.h
@@ -113,6 +113,28 @@
 #define  CSR_TLBREHI_PS_SHIFT		0
 #define  CSR_TLBREHI_PS			(0x3fUL << CSR_TLBREHI_PS_SHIFT)
 
+#define csr_read(csr)				\
+({						\
+	register unsigned long __v;		\
+	__asm__ __volatile__(			\
+		"csrrd %[val], %[reg]\n\t"	\
+		: [val] "=r" (__v)		\
+		: [reg] "i" (csr)		\
+		: "memory");			\
+	__v;					\
+})
+
+#define csr_write(v, csr)			\
+({						\
+	register unsigned long __v = v;		\
+	__asm__ __volatile__ (			\
+		"csrwr %[val], %[reg]\n\t"	\
+		: [val] "+r" (__v)		\
+		: [reg] "i" (csr)		\
+		: "memory");			\
+	__v;					\
+})
+
 #define EXREGS_GPRS			(32)
 
 #ifndef __ASSEMBLER__
@@ -133,6 +155,34 @@ struct ex_regs {
 #define PRMD_OFFSET_EXREGS		offsetof(struct ex_regs, prmd)
 #define EXREGS_SIZE			sizeof(struct ex_regs)
 
+static inline void cpu_relax(void)
+{
+	asm volatile("nop" ::: "memory");
+}
+
+static inline void local_irq_enable(void)
+{
+	unsigned int flags = CSR_CRMD_IE;
+	register unsigned int mask asm("$t0") = CSR_CRMD_IE;
+
+	__asm__ __volatile__(
+		"csrxchg %[val], %[mask], %[reg]\n\t"
+		: [val] "+r" (flags)
+		: [mask] "r" (mask), [reg] "i" (LOONGARCH_CSR_CRMD)
+		: "memory");
+}
+
+static inline void local_irq_disable(void)
+{
+	unsigned int flags = 0;
+	register unsigned int mask asm("$t0") = CSR_CRMD_IE;
+
+	__asm__ __volatile__(
+		"csrxchg %[val], %[mask], %[reg]\n\t"
+		: [val] "+r" (flags)
+		: [mask] "r" (mask), [reg] "i" (LOONGARCH_CSR_CRMD)
+		: "memory");
+}
 #else
 #define PC_OFFSET_EXREGS		((EXREGS_GPRS + 0) * 8)
 #define ESTAT_OFFSET_EXREGS		((EXREGS_GPRS + 1) * 8)
diff --git a/tools/testing/selftests/kvm/lib/loongarch/processor.c b/tools/testing/selftests/kvm/lib/loongarch/processor.c
index 0ac1abcb71cb..08b4cef48e44 100644
--- a/tools/testing/selftests/kvm/lib/loongarch/processor.c
+++ b/tools/testing/selftests/kvm/lib/loongarch/processor.c
@@ -192,6 +192,11 @@ void route_exception(struct ex_regs *regs)
 	while (1) ;
 }
 
+uint32_t guest_get_vcpuid(void)
+{
+	return csr_read(LOONGARCH_CSR_CPUID);
+}
+
 void vcpu_args_set(struct kvm_vcpu *vcpu, unsigned int num, ...)
 {
 	int i;
-- 
cgit v1.2.3


From d84fe2f30b0a0cbe08260c00a84ffe42161c95ce Mon Sep 17 00:00:00 2001
From: Bibo Mao <maobibo@loongson.cn>
Date: Thu, 27 Nov 2025 11:00:18 +0800
Subject: KVM: LoongArch: selftests: Add exception handler register interface

Add interrupt and exception handler register interface. When exception
happens, execute registered exception handler if exists, else report an
error.

Signed-off-by: Bibo Mao <maobibo@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 .../selftests/kvm/include/loongarch/processor.h    | 16 ++++++++++++
 .../selftests/kvm/lib/loongarch/processor.c        | 29 ++++++++++++++++++++++
 2 files changed, 45 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/kvm/include/loongarch/processor.h b/tools/testing/selftests/kvm/include/loongarch/processor.h
index f1bfc06a2264..a1930f28e044 100644
--- a/tools/testing/selftests/kvm/include/loongarch/processor.h
+++ b/tools/testing/selftests/kvm/include/loongarch/processor.h
@@ -84,6 +84,11 @@
 #define LOONGARCH_CSR_EUEN		0x2
 #define LOONGARCH_CSR_ECFG		0x4
 #define LOONGARCH_CSR_ESTAT		0x5  /* Exception status */
+#define  CSR_ESTAT_EXC_SHIFT		16
+#define  CSR_ESTAT_EXC_WIDTH		6
+#define  CSR_ESTAT_EXC			(0x3f << CSR_ESTAT_EXC_SHIFT)
+#define    EXCCODE_INT			0    /* Interrupt */
+#define      INT_TI			11   /* Timer interrupt*/
 #define LOONGARCH_CSR_ERA		0x6  /* ERA */
 #define LOONGARCH_CSR_BADV		0x7  /* Bad virtual address */
 #define LOONGARCH_CSR_EENTRY		0xc
@@ -155,6 +160,17 @@ struct ex_regs {
 #define PRMD_OFFSET_EXREGS		offsetof(struct ex_regs, prmd)
 #define EXREGS_SIZE			sizeof(struct ex_regs)
 
+#define VECTOR_NUM			64
+
+typedef void(*handler_fn)(struct ex_regs *);
+
+struct handlers {
+	handler_fn exception_handlers[VECTOR_NUM];
+};
+
+void vm_init_descriptor_tables(struct kvm_vm *vm);
+void vm_install_exception_handler(struct kvm_vm *vm, int vector, handler_fn handler);
+
 static inline void cpu_relax(void)
 {
 	asm volatile("nop" ::: "memory");
diff --git a/tools/testing/selftests/kvm/lib/loongarch/processor.c b/tools/testing/selftests/kvm/lib/loongarch/processor.c
index 08b4cef48e44..b2a1fa7b18da 100644
--- a/tools/testing/selftests/kvm/lib/loongarch/processor.c
+++ b/tools/testing/selftests/kvm/lib/loongarch/processor.c
@@ -11,6 +11,7 @@
 #define LOONGARCH_GUEST_STACK_VADDR_MIN		0x200000
 
 static vm_paddr_t invalid_pgtable[4];
+static vm_vaddr_t exception_handlers;
 
 static uint64_t virt_pte_index(struct kvm_vm *vm, vm_vaddr_t gva, int level)
 {
@@ -183,7 +184,14 @@ void assert_on_unhandled_exception(struct kvm_vcpu *vcpu)
 
 void route_exception(struct ex_regs *regs)
 {
+	int vector;
 	unsigned long pc, estat, badv;
+	struct handlers *handlers;
+
+	handlers = (struct handlers *)exception_handlers;
+	vector = (regs->estat & CSR_ESTAT_EXC) >> CSR_ESTAT_EXC_SHIFT;
+	if (handlers && handlers->exception_handlers[vector])
+		return handlers->exception_handlers[vector](regs);
 
 	pc = regs->pc;
 	badv  = regs->badv;
@@ -192,6 +200,27 @@ void route_exception(struct ex_regs *regs)
 	while (1) ;
 }
 
+void vm_init_descriptor_tables(struct kvm_vm *vm)
+{
+	void *addr;
+
+	vm->handlers = __vm_vaddr_alloc(vm, sizeof(struct handlers),
+			LOONGARCH_GUEST_STACK_VADDR_MIN, MEM_REGION_DATA);
+
+	addr = addr_gva2hva(vm, vm->handlers);
+	memset(addr, 0, vm->page_size);
+	exception_handlers = vm->handlers;
+	sync_global_to_guest(vm, exception_handlers);
+}
+
+void vm_install_exception_handler(struct kvm_vm *vm, int vector, handler_fn handler)
+{
+	struct handlers *handlers = addr_gva2hva(vm, vm->handlers);
+
+	assert(vector < VECTOR_NUM);
+	handlers->exception_handlers[vector] = handler;
+}
+
 uint32_t guest_get_vcpuid(void)
 {
 	return csr_read(LOONGARCH_CSR_CPUID);
-- 
cgit v1.2.3


From df41742343fad11fde06e085096003d64599785f Mon Sep 17 00:00:00 2001
From: Bibo Mao <maobibo@loongson.cn>
Date: Fri, 28 Nov 2025 14:49:44 +0800
Subject: KVM: LoongArch: selftests: Add timer interrupt test case

Add timer test case based on common arch_timer code, timer interrupt
with one-shot and period mode is tested.

Signed-off-by: Bibo Mao <maobibo@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 tools/testing/selftests/kvm/Makefile.kvm           |   1 +
 .../selftests/kvm/include/loongarch/arch_timer.h   |  85 ++++++++++++++
 .../selftests/kvm/include/loongarch/processor.h    |  10 ++
 .../selftests/kvm/lib/loongarch/processor.c        |   4 +-
 tools/testing/selftests/kvm/loongarch/arch_timer.c | 130 +++++++++++++++++++++
 5 files changed, 228 insertions(+), 2 deletions(-)
 create mode 100644 tools/testing/selftests/kvm/include/loongarch/arch_timer.h
 create mode 100644 tools/testing/selftests/kvm/loongarch/arch_timer.c

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/kvm/Makefile.kvm b/tools/testing/selftests/kvm/Makefile.kvm
index 148d427ff24b..9d01f4d0e3f9 100644
--- a/tools/testing/selftests/kvm/Makefile.kvm
+++ b/tools/testing/selftests/kvm/Makefile.kvm
@@ -210,6 +210,7 @@ TEST_GEN_PROGS_riscv += mmu_stress_test
 TEST_GEN_PROGS_riscv += rseq_test
 TEST_GEN_PROGS_riscv += steal_time
 
+TEST_GEN_PROGS_loongarch = arch_timer
 TEST_GEN_PROGS_loongarch += coalesced_io_test
 TEST_GEN_PROGS_loongarch += demand_paging_test
 TEST_GEN_PROGS_loongarch += dirty_log_perf_test
diff --git a/tools/testing/selftests/kvm/include/loongarch/arch_timer.h b/tools/testing/selftests/kvm/include/loongarch/arch_timer.h
new file mode 100644
index 000000000000..2ed106b32c81
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/loongarch/arch_timer.h
@@ -0,0 +1,85 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * LoongArch Constant Timer specific interface
+ */
+#ifndef SELFTEST_KVM_ARCH_TIMER_H
+#define SELFTEST_KVM_ARCH_TIMER_H
+
+#include "processor.h"
+
+/* LoongArch timer frequency is constant 100MHZ */
+#define TIMER_FREQ		(100UL << 20)
+#define msec_to_cycles(msec)	(TIMER_FREQ * (unsigned long)(msec) / 1000)
+#define usec_to_cycles(usec)	(TIMER_FREQ * (unsigned long)(usec) / 1000000)
+#define cycles_to_usec(cycles)	((unsigned long)(cycles) * 1000000 / TIMER_FREQ)
+
+static inline unsigned long timer_get_cycles(void)
+{
+	unsigned long val = 0;
+
+	__asm__ __volatile__(
+		"rdtime.d %0, $zero\n\t"
+		: "=r"(val)
+		:
+	);
+
+	return val;
+}
+
+static inline unsigned long timer_get_cfg(void)
+{
+	return csr_read(LOONGARCH_CSR_TCFG);
+}
+
+static inline unsigned long timer_get_val(void)
+{
+	return csr_read(LOONGARCH_CSR_TVAL);
+}
+
+static inline void disable_timer(void)
+{
+	csr_write(0, LOONGARCH_CSR_TCFG);
+}
+
+static inline void timer_irq_enable(void)
+{
+	unsigned long val;
+
+	val = csr_read(LOONGARCH_CSR_ECFG);
+	val |= ECFGF_TIMER;
+	csr_write(val, LOONGARCH_CSR_ECFG);
+}
+
+static inline void timer_irq_disable(void)
+{
+	unsigned long val;
+
+	val = csr_read(LOONGARCH_CSR_ECFG);
+	val &= ~ECFGF_TIMER;
+	csr_write(val, LOONGARCH_CSR_ECFG);
+}
+
+static inline void timer_set_next_cmp_ms(unsigned int msec, bool period)
+{
+	unsigned long val;
+
+	val = msec_to_cycles(msec) & CSR_TCFG_VAL;
+	val |= CSR_TCFG_EN;
+	if (period)
+		val |= CSR_TCFG_PERIOD;
+	csr_write(val, LOONGARCH_CSR_TCFG);
+}
+
+static inline void __delay(uint64_t cycles)
+{
+	uint64_t start = timer_get_cycles();
+
+	while ((timer_get_cycles() - start) < cycles)
+		cpu_relax();
+}
+
+static inline void udelay(unsigned long usec)
+{
+	__delay(usec_to_cycles(usec));
+}
+#endif /* SELFTEST_KVM_ARCH_TIMER_H */
diff --git a/tools/testing/selftests/kvm/include/loongarch/processor.h b/tools/testing/selftests/kvm/include/loongarch/processor.h
index a1930f28e044..76840ddda57d 100644
--- a/tools/testing/selftests/kvm/include/loongarch/processor.h
+++ b/tools/testing/selftests/kvm/include/loongarch/processor.h
@@ -83,6 +83,8 @@
 #define LOONGARCH_CSR_PRMD		0x1
 #define LOONGARCH_CSR_EUEN		0x2
 #define LOONGARCH_CSR_ECFG		0x4
+#define  ECFGB_TIMER			11
+#define  ECFGF_TIMER			(BIT_ULL(ECFGB_TIMER))
 #define LOONGARCH_CSR_ESTAT		0x5  /* Exception status */
 #define  CSR_ESTAT_EXC_SHIFT		16
 #define  CSR_ESTAT_EXC_WIDTH		6
@@ -111,6 +113,14 @@
 #define LOONGARCH_CSR_KS1		0x31
 #define LOONGARCH_CSR_TMID		0x40
 #define LOONGARCH_CSR_TCFG		0x41
+#define  CSR_TCFG_VAL			(BIT_ULL(48) - BIT_ULL(2))
+#define  CSR_TCFG_PERIOD_SHIFT		1
+#define  CSR_TCFG_PERIOD		(0x1UL << CSR_TCFG_PERIOD_SHIFT)
+#define  CSR_TCFG_EN			(0x1UL)
+#define LOONGARCH_CSR_TVAL		0x42
+#define LOONGARCH_CSR_TINTCLR		0x44 /* Timer interrupt clear */
+#define  CSR_TINTCLR_TI_SHIFT		0
+#define  CSR_TINTCLR_TI			(1 << CSR_TINTCLR_TI_SHIFT)
 /* TLB refill exception entry */
 #define LOONGARCH_CSR_TLBRENTRY		0x88
 #define LOONGARCH_CSR_TLBRSAVE		0x8b
diff --git a/tools/testing/selftests/kvm/lib/loongarch/processor.c b/tools/testing/selftests/kvm/lib/loongarch/processor.c
index b2a1fa7b18da..a1b16140942b 100644
--- a/tools/testing/selftests/kvm/lib/loongarch/processor.c
+++ b/tools/testing/selftests/kvm/lib/loongarch/processor.c
@@ -276,8 +276,8 @@ static void loongarch_vcpu_setup(struct kvm_vcpu *vcpu)
 		TEST_FAIL("Unknown guest mode, mode: 0x%x", vm->mode);
 	}
 
-	/* user mode and page enable mode */
-	val = PLV_USER | CSR_CRMD_PG;
+	/* kernel mode and page enable mode */
+	val = PLV_KERN | CSR_CRMD_PG;
 	loongarch_set_csr(vcpu, LOONGARCH_CSR_CRMD, val);
 	loongarch_set_csr(vcpu, LOONGARCH_CSR_PRMD, val);
 	loongarch_set_csr(vcpu, LOONGARCH_CSR_EUEN, 1);
diff --git a/tools/testing/selftests/kvm/loongarch/arch_timer.c b/tools/testing/selftests/kvm/loongarch/arch_timer.c
new file mode 100644
index 000000000000..6cc671671663
--- /dev/null
+++ b/tools/testing/selftests/kvm/loongarch/arch_timer.c
@@ -0,0 +1,130 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * The test validates periodic/one-shot constant timer IRQ using
+ * CSR.TCFG and CSR.TVAL registers.
+ */
+#include "arch_timer.h"
+#include "kvm_util.h"
+#include "processor.h"
+#include "timer_test.h"
+#include "ucall_common.h"
+
+static void guest_irq_handler(struct ex_regs *regs)
+{
+	unsigned int intid;
+	uint32_t cpu = guest_get_vcpuid();
+	uint64_t xcnt, val, cfg, xcnt_diff_us;
+	struct test_vcpu_shared_data *shared_data = &vcpu_shared_data[cpu];
+
+	intid = !!(regs->estat & BIT(INT_TI));
+
+	/* Make sure we are dealing with the correct timer IRQ */
+	GUEST_ASSERT_EQ(intid, 1);
+
+	cfg = timer_get_cfg();
+	if (cfg & CSR_TCFG_PERIOD) {
+		WRITE_ONCE(shared_data->nr_iter, shared_data->nr_iter - 1);
+		if (shared_data->nr_iter == 0)
+			disable_timer();
+		csr_write(CSR_TINTCLR_TI, LOONGARCH_CSR_TINTCLR);
+		return;
+	}
+
+	/*
+	 * On real machine, value of LOONGARCH_CSR_TVAL is BIT_ULL(48) - 1
+	 * On virtual machine, its value counts down from BIT_ULL(48) - 1
+	 */
+	val = timer_get_val();
+	xcnt = timer_get_cycles();
+	xcnt_diff_us = cycles_to_usec(xcnt - shared_data->xcnt);
+
+	/* Basic 'timer condition met' check */
+	__GUEST_ASSERT(val > cfg,
+			"val = 0x%lx, cfg = 0x%lx, xcnt_diff_us = 0x%lx",
+			val, cfg, xcnt_diff_us);
+
+	csr_write(CSR_TINTCLR_TI, LOONGARCH_CSR_TINTCLR);
+	WRITE_ONCE(shared_data->nr_iter, shared_data->nr_iter + 1);
+}
+
+static void guest_test_period_timer(uint32_t cpu)
+{
+	uint32_t irq_iter, config_iter;
+	uint64_t us;
+	struct test_vcpu_shared_data *shared_data = &vcpu_shared_data[cpu];
+
+	shared_data->nr_iter = test_args.nr_iter;
+	shared_data->xcnt = timer_get_cycles();
+	us = msecs_to_usecs(test_args.timer_period_ms) + test_args.timer_err_margin_us;
+	timer_set_next_cmp_ms(test_args.timer_period_ms, true);
+
+	for (config_iter = 0; config_iter < test_args.nr_iter; config_iter++) {
+		/* Setup a timeout for the interrupt to arrive */
+		udelay(us);
+	}
+
+	irq_iter = READ_ONCE(shared_data->nr_iter);
+	__GUEST_ASSERT(irq_iter == 0,
+			"irq_iter = 0x%x.\n"
+			"  Guest period timer interrupt was not triggered within the specified\n"
+			"  interval, try to increase the error margin by [-e] option.\n",
+			irq_iter);
+}
+
+static void guest_test_oneshot_timer(uint32_t cpu)
+{
+	uint32_t irq_iter, config_iter;
+	uint64_t us;
+	struct test_vcpu_shared_data *shared_data = &vcpu_shared_data[cpu];
+
+	shared_data->nr_iter = 0;
+	shared_data->guest_stage = 0;
+	us = msecs_to_usecs(test_args.timer_period_ms) + test_args.timer_err_margin_us;
+	for (config_iter = 0; config_iter < test_args.nr_iter; config_iter++) {
+		shared_data->xcnt = timer_get_cycles();
+
+		/* Setup the next interrupt */
+		timer_set_next_cmp_ms(test_args.timer_period_ms, false);
+		/* Setup a timeout for the interrupt to arrive */
+		udelay(us);
+
+		irq_iter = READ_ONCE(shared_data->nr_iter);
+		__GUEST_ASSERT(config_iter + 1 == irq_iter,
+				"config_iter + 1 = 0x%x, irq_iter = 0x%x.\n"
+				"  Guest timer interrupt was not triggered within the specified\n"
+				"  interval, try to increase the error margin by [-e] option.\n",
+				config_iter + 1, irq_iter);
+	}
+}
+
+static void guest_code(void)
+{
+	uint32_t cpu = guest_get_vcpuid();
+
+	timer_irq_enable();
+	local_irq_enable();
+	guest_test_period_timer(cpu);
+	guest_test_oneshot_timer(cpu);
+
+	GUEST_DONE();
+}
+
+struct kvm_vm *test_vm_create(void)
+{
+	struct kvm_vm *vm;
+	int nr_vcpus = test_args.nr_vcpus;
+
+	vm = vm_create_with_vcpus(nr_vcpus, guest_code, vcpus);
+	vm_init_descriptor_tables(vm);
+	vm_install_exception_handler(vm, EXCCODE_INT, guest_irq_handler);
+
+	/* Make all the test's cmdline args visible to the guest */
+	sync_global_to_guest(vm, test_args);
+
+	return vm;
+}
+
+void test_vm_cleanup(struct kvm_vm *vm)
+{
+	kvm_vm_free(vm);
+}
-- 
cgit v1.2.3


From 4e8824094069b04e3b3583d855c975ccb6a9bec5 Mon Sep 17 00:00:00 2001
From: Bibo Mao <maobibo@loongson.cn>
Date: Fri, 28 Nov 2025 14:49:47 +0800
Subject: KVM: LoongArch: selftests: Add SW emulated timer test case

This test case setup one-shot timer and execute idle instruction
immediately to indicate giving up CPU, hypervisor will emulate SW
hrtimer and wakeup vCPU when SW hrtimer is fired.

Signed-off-by: Bibo Mao <maobibo@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 tools/testing/selftests/kvm/loongarch/arch_timer.c | 40 ++++++++++++++++++++++
 1 file changed, 40 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/kvm/loongarch/arch_timer.c b/tools/testing/selftests/kvm/loongarch/arch_timer.c
index 6cc671671663..baa30fd296f5 100644
--- a/tools/testing/selftests/kvm/loongarch/arch_timer.c
+++ b/tools/testing/selftests/kvm/loongarch/arch_timer.c
@@ -9,6 +9,21 @@
 #include "timer_test.h"
 #include "ucall_common.h"
 
+static void do_idle(void)
+{
+	unsigned int intid;
+	unsigned long estat;
+
+	__asm__ __volatile__("idle 0" : : : "memory");
+
+	estat = csr_read(LOONGARCH_CSR_ESTAT);
+	intid = !!(estat & BIT(INT_TI));
+
+	/* Make sure pending timer IRQ arrived */
+	GUEST_ASSERT_EQ(intid, 1);
+	csr_write(CSR_TINTCLR_TI, LOONGARCH_CSR_TINTCLR);
+}
+
 static void guest_irq_handler(struct ex_regs *regs)
 {
 	unsigned int intid;
@@ -97,6 +112,30 @@ static void guest_test_oneshot_timer(uint32_t cpu)
 	}
 }
 
+static void guest_test_emulate_timer(uint32_t cpu)
+{
+	uint32_t config_iter;
+	uint64_t xcnt_diff_us, us;
+	struct test_vcpu_shared_data *shared_data = &vcpu_shared_data[cpu];
+
+	local_irq_disable();
+	shared_data->nr_iter = 0;
+	us = msecs_to_usecs(test_args.timer_period_ms);
+	for (config_iter = 0; config_iter < test_args.nr_iter; config_iter++) {
+		shared_data->xcnt = timer_get_cycles();
+
+		/* Setup the next interrupt */
+		timer_set_next_cmp_ms(test_args.timer_period_ms, false);
+		do_idle();
+
+		xcnt_diff_us = cycles_to_usec(timer_get_cycles() - shared_data->xcnt);
+		__GUEST_ASSERT(xcnt_diff_us >= us,
+				"xcnt_diff_us = 0x%lx, us = 0x%lx.\n",
+				xcnt_diff_us, us);
+	}
+	local_irq_enable();
+}
+
 static void guest_code(void)
 {
 	uint32_t cpu = guest_get_vcpuid();
@@ -105,6 +144,7 @@ static void guest_code(void)
 	local_irq_enable();
 	guest_test_period_timer(cpu);
 	guest_test_oneshot_timer(cpu);
+	guest_test_emulate_timer(cpu);
 
 	GUEST_DONE();
 }
-- 
cgit v1.2.3


From 0f90fa6e2e9d98349492d9968c11ceaf2f958c98 Mon Sep 17 00:00:00 2001
From: Bibo Mao <maobibo@loongson.cn>
Date: Fri, 28 Nov 2025 14:49:48 +0800
Subject: KVM: LoongArch: selftests: Add time counter test case

With time counter test, it is to verify that time count starts from 0
and always grows up then.

Signed-off-by: Bibo Mao <maobibo@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 .../selftests/kvm/lib/loongarch/processor.c        |  9 +++++++
 tools/testing/selftests/kvm/loongarch/arch_timer.c | 30 ++++++++++++++++++++++
 2 files changed, 39 insertions(+)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/kvm/lib/loongarch/processor.c b/tools/testing/selftests/kvm/lib/loongarch/processor.c
index a1b16140942b..07c103369ddb 100644
--- a/tools/testing/selftests/kvm/lib/loongarch/processor.c
+++ b/tools/testing/selftests/kvm/lib/loongarch/processor.c
@@ -3,6 +3,7 @@
 #include <assert.h>
 #include <linux/compiler.h>
 
+#include <asm/kvm.h>
 #include "kvm_util.h"
 #include "processor.h"
 #include "ucall_common.h"
@@ -245,6 +246,11 @@ void vcpu_args_set(struct kvm_vcpu *vcpu, unsigned int num, ...)
 	vcpu_regs_set(vcpu, &regs);
 }
 
+static void loongarch_set_reg(struct kvm_vcpu *vcpu, uint64_t id, uint64_t val)
+{
+	__vcpu_set_reg(vcpu, id, val);
+}
+
 static void loongarch_get_csr(struct kvm_vcpu *vcpu, uint64_t id, void *addr)
 {
 	uint64_t csrid;
@@ -285,7 +291,10 @@ static void loongarch_vcpu_setup(struct kvm_vcpu *vcpu)
 	loongarch_set_csr(vcpu, LOONGARCH_CSR_TCFG, 0);
 	loongarch_set_csr(vcpu, LOONGARCH_CSR_ASID, 1);
 
+	/* time count start from 0 */
 	val = 0;
+	loongarch_set_reg(vcpu, KVM_REG_LOONGARCH_COUNTER, val);
+
 	width = vm->page_shift - 3;
 
 	switch (vm->pgtable_levels) {
diff --git a/tools/testing/selftests/kvm/loongarch/arch_timer.c b/tools/testing/selftests/kvm/loongarch/arch_timer.c
index baa30fd296f5..355ecac30954 100644
--- a/tools/testing/selftests/kvm/loongarch/arch_timer.c
+++ b/tools/testing/selftests/kvm/loongarch/arch_timer.c
@@ -136,10 +136,40 @@ static void guest_test_emulate_timer(uint32_t cpu)
 	local_irq_enable();
 }
 
+static void guest_time_count_test(uint32_t cpu)
+{
+	uint32_t config_iter;
+	unsigned long start, end, prev, us;
+
+	/* Assuming that test case starts to run in 1 second */
+	start = timer_get_cycles();
+	us = msec_to_cycles(1000);
+	__GUEST_ASSERT(start <= us,
+			"start = 0x%lx, us = 0x%lx.\n",
+			start, us);
+
+	us = msec_to_cycles(test_args.timer_period_ms);
+	for (config_iter = 0; config_iter < test_args.nr_iter; config_iter++) {
+		start = timer_get_cycles();
+		end = start + us;
+		/* test time count growing up always */
+		while (start < end) {
+			prev = start;
+			start = timer_get_cycles();
+			__GUEST_ASSERT(prev <= start,
+					"prev = 0x%lx, start = 0x%lx.\n",
+					prev, start);
+		}
+	}
+}
+
 static void guest_code(void)
 {
 	uint32_t cpu = guest_get_vcpuid();
 
+	/* must run at first */
+	guest_time_count_test(cpu);
+
 	timer_irq_enable();
 	local_irq_enable();
 	guest_test_period_timer(cpu);
-- 
cgit v1.2.3


From 66f188858385d640163fbf866d9c11b7741da91a Mon Sep 17 00:00:00 2001
From: Oliver Upton <oupton@kernel.org>
Date: Mon, 24 Nov 2025 11:01:57 -0800
Subject: KVM: arm64: selftests: Add test for AT emulation

Add a basic test for AT emulation in the EL2&0 and EL1&0 translation
regimes.

Reviewed-by: Marc Zyngier <maz@kernel.org>
Tested-by: Marc Zyngier <maz@kernel.org>
Link: https://msgid.link/20251124190158.177318-16-oupton@kernel.org
Signed-off-by: Oliver Upton <oupton@kernel.org>
---
 tools/testing/selftests/kvm/Makefile.kvm       |   1 +
 tools/testing/selftests/kvm/arm64/at.c         | 166 +++++++++++++++++++++++++
 tools/testing/selftests/kvm/include/kvm_util.h |   1 +
 tools/testing/selftests/kvm/lib/kvm_util.c     |  10 ++
 4 files changed, 178 insertions(+)
 create mode 100644 tools/testing/selftests/kvm/arm64/at.c

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/kvm/Makefile.kvm b/tools/testing/selftests/kvm/Makefile.kvm
index 148d427ff24b..81b3aa54678a 100644
--- a/tools/testing/selftests/kvm/Makefile.kvm
+++ b/tools/testing/selftests/kvm/Makefile.kvm
@@ -156,6 +156,7 @@ TEST_GEN_PROGS_EXTENDED_x86 += x86/nx_huge_pages_test
 TEST_GEN_PROGS_arm64 = $(TEST_GEN_PROGS_COMMON)
 TEST_GEN_PROGS_arm64 += arm64/aarch32_id_regs
 TEST_GEN_PROGS_arm64 += arm64/arch_timer_edge_cases
+TEST_GEN_PROGS_arm64 += arm64/at
 TEST_GEN_PROGS_arm64 += arm64/debug-exceptions
 TEST_GEN_PROGS_arm64 += arm64/hello_el2
 TEST_GEN_PROGS_arm64 += arm64/host_sve
diff --git a/tools/testing/selftests/kvm/arm64/at.c b/tools/testing/selftests/kvm/arm64/at.c
new file mode 100644
index 000000000000..acecb6ab5071
--- /dev/null
+++ b/tools/testing/selftests/kvm/arm64/at.c
@@ -0,0 +1,166 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * at - Test for KVM's AT emulation in the EL2&0 and EL1&0 translation regimes.
+ */
+#include "kvm_util.h"
+#include "processor.h"
+#include "test_util.h"
+#include "ucall.h"
+
+#include <asm/sysreg.h>
+
+#define TEST_ADDR	0x80000000
+
+enum {
+	CLEAR_ACCESS_FLAG,
+	TEST_ACCESS_FLAG,
+};
+
+static u64 *ptep_hva;
+
+#define copy_el2_to_el1(reg)						\
+	write_sysreg_s(read_sysreg_s(SYS_##reg##_EL1), SYS_##reg##_EL12)
+
+/* Yes, this is an ugly hack */
+#define __at(op, addr)	write_sysreg_s(addr, op)
+
+#define test_at_insn(op, expect_fault)							\
+do {											\
+	u64 par, fsc;									\
+	bool fault;									\
+											\
+	GUEST_SYNC(CLEAR_ACCESS_FLAG);							\
+											\
+	__at(OP_AT_##op, TEST_ADDR);							\
+	isb();										\
+	par = read_sysreg(par_el1);							\
+											\
+	fault = par & SYS_PAR_EL1_F;							\
+	fsc = FIELD_GET(SYS_PAR_EL1_FST, par);						\
+											\
+	__GUEST_ASSERT((expect_fault) == fault,						\
+		       "AT "#op": %sexpected fault (par: %lx)1",			\
+		       (expect_fault) ? "" : "un", par);				\
+	if ((expect_fault)) {								\
+		__GUEST_ASSERT(fsc == ESR_ELx_FSC_ACCESS_L(3),				\
+			       "AT "#op": expected access flag fault (par: %lx)",	\
+			       par);							\
+	} else {									\
+		GUEST_ASSERT_EQ(FIELD_GET(SYS_PAR_EL1_ATTR, par), MAIR_ATTR_NORMAL);	\
+		GUEST_ASSERT_EQ(FIELD_GET(SYS_PAR_EL1_SH, par), PTE_SHARED >> 8);	\
+		GUEST_ASSERT_EQ(par & SYS_PAR_EL1_PA, TEST_ADDR);			\
+		GUEST_SYNC(TEST_ACCESS_FLAG);						\
+	}										\
+} while (0)
+
+static void test_at(bool expect_fault)
+{
+	test_at_insn(S1E2R, expect_fault);
+	test_at_insn(S1E2W, expect_fault);
+
+	/* Reuse the stage-1 MMU context from EL2 at EL1 */
+	copy_el2_to_el1(SCTLR);
+	copy_el2_to_el1(MAIR);
+	copy_el2_to_el1(TCR);
+	copy_el2_to_el1(TTBR0);
+	copy_el2_to_el1(TTBR1);
+
+	/* Disable stage-2 translation and enter a non-host context */
+	write_sysreg(0, vtcr_el2);
+	write_sysreg(0, vttbr_el2);
+	sysreg_clear_set(hcr_el2, HCR_EL2_TGE | HCR_EL2_VM, 0);
+	isb();
+
+	test_at_insn(S1E1R, expect_fault);
+	test_at_insn(S1E1W, expect_fault);
+}
+
+static void guest_code(void)
+{
+	sysreg_clear_set(tcr_el1, TCR_HA, 0);
+	isb();
+
+	test_at(true);
+
+	if (!SYS_FIELD_GET(ID_AA64MMFR1_EL1, HAFDBS, read_sysreg(id_aa64mmfr1_el1)))
+		GUEST_DONE();
+
+	/*
+	 * KVM's software PTW makes the implementation choice that the AT
+	 * instruction sets the access flag.
+	 */
+	sysreg_clear_set(tcr_el1, 0, TCR_HA);
+	isb();
+	test_at(false);
+
+	GUEST_DONE();
+}
+
+static void handle_sync(struct kvm_vcpu *vcpu, struct ucall *uc)
+{
+	switch (uc->args[1]) {
+	case CLEAR_ACCESS_FLAG:
+		/*
+		 * Delete + reinstall the memslot to invalidate stage-2
+		 * mappings of the stage-1 page tables, forcing KVM to
+		 * use the 'slow' AT emulation path.
+		 *
+		 * This and clearing the access flag from host userspace
+		 * ensures that the access flag cannot be set speculatively
+		 * and is reliably cleared at the time of the AT instruction.
+		 */
+		clear_bit(__ffs(PTE_AF), ptep_hva);
+		vm_mem_region_reload(vcpu->vm, vcpu->vm->memslots[MEM_REGION_PT]);
+		break;
+	case TEST_ACCESS_FLAG:
+		TEST_ASSERT(test_bit(__ffs(PTE_AF), ptep_hva),
+			    "Expected access flag to be set (desc: %lu)", *ptep_hva);
+		break;
+	default:
+		TEST_FAIL("Unexpected SYNC arg: %lu", uc->args[1]);
+	}
+}
+
+static void run_test(struct kvm_vcpu *vcpu)
+{
+	struct ucall uc;
+
+	while (true) {
+		vcpu_run(vcpu);
+		switch (get_ucall(vcpu, &uc)) {
+		case UCALL_DONE:
+			return;
+		case UCALL_SYNC:
+			handle_sync(vcpu, &uc);
+			continue;
+		case UCALL_ABORT:
+			REPORT_GUEST_ASSERT(uc);
+			return;
+		default:
+			TEST_FAIL("Unexpeced ucall: %lu", uc.cmd);
+		}
+	}
+}
+
+int main(void)
+{
+	struct kvm_vcpu_init init;
+	struct kvm_vcpu *vcpu;
+	struct kvm_vm *vm;
+
+	TEST_REQUIRE(kvm_check_cap(KVM_CAP_ARM_EL2));
+
+	vm = vm_create(1);
+
+	kvm_get_default_vcpu_target(vm, &init);
+	init.features[0] |= BIT(KVM_ARM_VCPU_HAS_EL2);
+	vcpu = aarch64_vcpu_add(vm, 0, &init, guest_code);
+	kvm_arch_vm_finalize_vcpus(vm);
+
+	virt_map(vm, TEST_ADDR, TEST_ADDR, 1);
+	ptep_hva = virt_get_pte_hva_at_level(vm, TEST_ADDR, 3);
+	run_test(vcpu);
+
+	kvm_vm_free(vm);
+	return 0;
+}
diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h
index d3f3e455c031..41467dad9178 100644
--- a/tools/testing/selftests/kvm/include/kvm_util.h
+++ b/tools/testing/selftests/kvm/include/kvm_util.h
@@ -715,6 +715,7 @@ static inline bool vm_arch_has_protected_memory(struct kvm_vm *vm)
 #endif
 
 void vm_mem_region_set_flags(struct kvm_vm *vm, uint32_t slot, uint32_t flags);
+void vm_mem_region_reload(struct kvm_vm *vm, uint32_t slot);
 void vm_mem_region_move(struct kvm_vm *vm, uint32_t slot, uint64_t new_gpa);
 void vm_mem_region_delete(struct kvm_vm *vm, uint32_t slot);
 struct kvm_vcpu *__vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id);
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 1a93d6361671..d6538bb17740 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -1201,6 +1201,16 @@ void vm_mem_region_set_flags(struct kvm_vm *vm, uint32_t slot, uint32_t flags)
 		ret, errno, slot, flags);
 }
 
+void vm_mem_region_reload(struct kvm_vm *vm, uint32_t slot)
+{
+	struct userspace_mem_region *region = memslot2region(vm, slot);
+	struct kvm_userspace_memory_region2 tmp = region->region;
+
+	tmp.memory_size = 0;
+	vm_ioctl(vm, KVM_SET_USER_MEMORY_REGION2, &tmp);
+	vm_ioctl(vm, KVM_SET_USER_MEMORY_REGION2, &region->region);
+}
+
 /*
  * VM Memory Region Move
  *
-- 
cgit v1.2.3


From 05474b7bc75d215a147b44b339ba4e9638b74382 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.i.king@gmail.com>
Date: Fri, 28 Nov 2025 17:51:24 +0000
Subject: KVM: arm64: Fix spelling mistake "Unexpeced" -> "Unexpected"

There is a spelling mistake in a TEST_FAIL message. Fix it.

Signed-off-by: Colin Ian King <colin.i.king@gmail.com>
Link: https://msgid.link/20251128175124.319094-1-colin.i.king@gmail.com
Signed-off-by: Oliver Upton <oupton@kernel.org>
---
 tools/testing/selftests/kvm/arm64/at.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/kvm/arm64/at.c b/tools/testing/selftests/kvm/arm64/at.c
index acecb6ab5071..c8ee6f520734 100644
--- a/tools/testing/selftests/kvm/arm64/at.c
+++ b/tools/testing/selftests/kvm/arm64/at.c
@@ -137,7 +137,7 @@ static void run_test(struct kvm_vcpu *vcpu)
 			REPORT_GUEST_ASSERT(uc);
 			return;
 		default:
-			TEST_FAIL("Unexpeced ucall: %lu", uc.cmd);
+			TEST_FAIL("Unexpected ucall: %lu", uc.cmd);
 		}
 	}
 }
-- 
cgit v1.2.3