Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull more kvm updates from Paolo Bonzini:
  Generic:

   - Clean up locking of all vCPUs for a VM by using the *_nest_lock()
     family of functions, and move duplicated code to virt/kvm/. kernel/
     patches acked by Peter Zijlstra

   - Add MGLRU support to the access tracking perf test

  ARM fixes:

   - Make the irqbypass hooks resilient to changes in the GSI<->MSI
     routing, avoiding behind stale vLPI mappings being left behind. The
     fix is to resolve the VGIC IRQ using the host IRQ (which is stable)
     and nuking the vLPI mapping upon a routing change

   - Close another VGIC race where vCPU creation races with VGIC
     creation, leading to in-flight vCPUs entering the kernel w/o
     private IRQs allocated

   - Fix a build issue triggered by the recently added workaround for
     Ampere's AC04_CPU_23 erratum

   - Correctly sign-extend the VA when emulating a TLBI instruction
     potentially targeting a VNCR mapping

   - Avoid dereferencing a NULL pointer in the VGIC debug code, which
     can happen if the device doesn't have any mapping yet

  s390:

   - Fix interaction between some filesystems and Secure Execution

   - Some cleanups and refactorings, preparing for an upcoming big
     series

  x86:

   - Wait for target vCPU to ack KVM_REQ_UPDATE_PROTECTED_GUEST_STATE
     to fix a race between AP destroy and VMRUN

   - Decrypt and dump the VMSA in dump_vmcb() if debugging enabled for
     the VM

   - Refine and harden handling of spurious faults

   - Add support for ALLOWED_SEV_FEATURES

   - Add #VMGEXIT to the set of handlers special cased for
     CONFIG_RETPOLINE=y

   - Treat DEBUGCTL[5:2] as reserved to pave the way for virtualizing
     features that utilize those bits

   - Don't account temporary allocations in sev_send_update_data()

   - Add support for KVM_CAP_X86_BUS_LOCK_EXIT on SVM, via Bus Lock
     Threshold

   - Unify virtualization of IBRS on nested VM-Exit, and cross-vCPU
     IBPB, between SVM and VMX

   - Advertise support to userspace for WRMSRNS and PREFETCHI

   - Rescan I/O APIC routes after handling EOI that needed to be
     intercepted due to the old/previous routing, but not the
     new/current routing

   - Add a module param to control and enumerate support for device
     posted interrupts

   - Fix a potential overflow with nested virt on Intel systems running
     32-bit kernels

   - Flush shadow VMCSes on emergency reboot

   - Add support for SNP to the various SEV selftests

   - Add a selftest to verify fastops instructions via forced emulation

   - Refine and optimize KVM's software processing of the posted
     interrupt bitmap, and share the harvesting code between KVM and the
     kernel's Posted MSI handler"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (93 commits)
  rtmutex_api: provide correct extern functions
  KVM: arm64: vgic-debug: Avoid dereferencing NULL ITE pointer
  KVM: arm64: vgic-init: Plug vCPU vs. VGIC creation race
  KVM: arm64: Unmap vLPIs affected by changes to GSI routing information
  KVM: arm64: Resolve vLPI by host IRQ in vgic_v4_unset_forwarding()
  KVM: arm64: Protect vLPI translation with vgic_irq::irq_lock
  KVM: arm64: Use lock guard in vgic_v4_set_forwarding()
  KVM: arm64: Mask out non-VA bits from TLBI VA* on VNCR invalidation
  arm64: sysreg: Drag linux/kconfig.h to work around vdso build issue
  KVM: s390: Simplify and move pv code
  KVM: s390: Refactor and split some gmap helpers
  KVM: s390: Remove unneeded srcu lock
  s390: Remove unneeded includes
  s390/uv: Improve splitting of large folios that cannot be split while dirty
  s390/uv: Always return 0 from s390_wiggle_split_folio() if successful
  s390/uv: Don't return 0 from make_hva_secure() if the operation was not successful
  rust: add helper for mutex_trylock
  RISC-V: KVM: use kvm_trylock_all_vcpus when locking all vCPUs
  KVM: arm64: use kvm_trylock_all_vcpus when locking all vCPUs
  x86: KVM: SVM: use kvm_lock_all_vcpus instead of a custom implementation
  ...

24 files changed, 1409 insertions, 209 deletions

diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index bc81b9d1aeca..98c8931db4a5 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -336,6 +336,7 @@
 #define X86_FEATURE_AMD_IBRS		(13*32+14) /* Indirect Branch Restricted Speculation */
 #define X86_FEATURE_AMD_STIBP		(13*32+15) /* Single Thread Indirect Branch Predictors */
 #define X86_FEATURE_AMD_STIBP_ALWAYS_ON	(13*32+17) /* Single Thread Indirect Branch Predictors always-on preferred */
+#define X86_FEATURE_AMD_IBRS_SAME_MODE (13*32+19) /* Indirect Branch Restricted Speculation same mode protection*/
 #define X86_FEATURE_AMD_PPIN		(13*32+23) /* "amd_ppin" Protected Processor Inventory Number */
 #define X86_FEATURE_AMD_SSBD		(13*32+24) /* Speculative Store Bypass Disable */
 #define X86_FEATURE_VIRT_SSBD		(13*32+25) /* "virt_ssbd" Virtualized Speculative Store Bypass Disable */
diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h
index 460306b35a4b..b663d916f162 100644
--- a/tools/arch/x86/include/uapi/asm/kvm.h
+++ b/tools/arch/x86/include/uapi/asm/kvm.h
@@ -844,6 +844,7 @@ struct kvm_sev_snp_launch_start {
 };
 
 /* Kept in sync with firmware values for simplicity. */
+#define KVM_SEV_PAGE_TYPE_INVALID		0x0
 #define KVM_SEV_SNP_PAGE_TYPE_NORMAL		0x1
 #define KVM_SEV_SNP_PAGE_TYPE_ZERO		0x3
 #define KVM_SEV_SNP_PAGE_TYPE_UNMEASURED	0x4
diff --git a/tools/testing/selftests/cgroup/Makefile b/tools/testing/selftests/cgroup/Makefile
index 1b897152bab6..e01584c2189a 100644
--- a/tools/testing/selftests/cgroup/Makefile
+++ b/tools/testing/selftests/cgroup/Makefile
@@ -21,14 +21,15 @@ TEST_GEN_PROGS += test_zswap
 LOCAL_HDRS += $(selfdir)/clone3/clone3_selftests.h $(selfdir)/pidfd/pidfd.h
 
 include ../lib.mk
+include lib/libcgroup.mk
 
-$(OUTPUT)/test_core: cgroup_util.c
-$(OUTPUT)/test_cpu: cgroup_util.c
-$(OUTPUT)/test_cpuset: cgroup_util.c
-$(OUTPUT)/test_freezer: cgroup_util.c
-$(OUTPUT)/test_hugetlb_memcg: cgroup_util.c
-$(OUTPUT)/test_kill: cgroup_util.c
-$(OUTPUT)/test_kmem: cgroup_util.c
-$(OUTPUT)/test_memcontrol: cgroup_util.c
-$(OUTPUT)/test_pids: cgroup_util.c
-$(OUTPUT)/test_zswap: cgroup_util.c
+$(OUTPUT)/test_core: $(LIBCGROUP_O)
+$(OUTPUT)/test_cpu: $(LIBCGROUP_O)
+$(OUTPUT)/test_cpuset: $(LIBCGROUP_O)
+$(OUTPUT)/test_freezer: $(LIBCGROUP_O)
+$(OUTPUT)/test_hugetlb_memcg: $(LIBCGROUP_O)
+$(OUTPUT)/test_kill: $(LIBCGROUP_O)
+$(OUTPUT)/test_kmem: $(LIBCGROUP_O)
+$(OUTPUT)/test_memcontrol: $(LIBCGROUP_O)
+$(OUTPUT)/test_pids: $(LIBCGROUP_O)
+$(OUTPUT)/test_zswap: $(LIBCGROUP_O)
diff --git a/tools/testing/selftests/cgroup/cgroup_util.c b/tools/testing/selftests/cgroup/lib/cgroup_util.c
index 1e2d46636a0c..8832f3d1cb61 100644
--- a/tools/testing/selftests/cgroup/cgroup_util.c
+++ b/tools/testing/selftests/cgroup/lib/cgroup_util.c
@@ -17,10 +17,10 @@
 #include <unistd.h>
 
 #include "cgroup_util.h"
-#include "../clone3/clone3_selftests.h"
+#include "../../clone3/clone3_selftests.h"
 
 /* Returns read len on success, or -errno on failure. */
-static ssize_t read_text(const char *path, char *buf, size_t max_len)
+ssize_t read_text(const char *path, char *buf, size_t max_len)
 {
 	ssize_t len;
 	int fd;
@@ -39,7 +39,7 @@ static ssize_t read_text(const char *path, char *buf, size_t max_len)
 }
 
 /* Returns written len on success, or -errno on failure. */
-static ssize_t write_text(const char *path, char *buf, ssize_t len)
+ssize_t write_text(const char *path, char *buf, ssize_t len)
 {
 	int fd;
 
@@ -217,7 +217,8 @@ int cg_write_numeric(const char *cgroup, const char *control, long value)
 	return cg_write(cgroup, control, buf);
 }
 
-int cg_find_unified_root(char *root, size_t len, bool *nsdelegate)
+static int cg_find_root(char *root, size_t len, const char *controller,
+			bool *nsdelegate)
 {
 	char buf[10 * PAGE_SIZE];
 	char *fs, *mount, *type, *options;
@@ -236,18 +237,37 @@ int cg_find_unified_root(char *root, size_t len, bool *nsdelegate)
 		options = strtok(NULL, delim);
 		strtok(NULL, delim);
 		strtok(NULL, delim);
-
-		if (strcmp(type, "cgroup2") == 0) {
-			strncpy(root, mount, len);
-			if (nsdelegate)
-				*nsdelegate = !!strstr(options, "nsdelegate");
-			return 0;
+		if (strcmp(type, "cgroup") == 0) {
+			if (!controller || !strstr(options, controller))
+				continue;
+		} else if (strcmp(type, "cgroup2") == 0) {
+			if (controller &&
+					cg_read_strstr(mount, "cgroup.controllers", controller))
+				continue;
+		} else {
+			continue;
 		}
+		strncpy(root, mount, len);
+
+		if (nsdelegate)
+			*nsdelegate = !!strstr(options, "nsdelegate");
+		return 0;
+
 	}
 
 	return -1;
 }
 
+int cg_find_controller_root(char *root, size_t len, const char *controller)
+{
+	return cg_find_root(root, len, controller, NULL);
+}
+
+int cg_find_unified_root(char *root, size_t len, bool *nsdelegate)
+{
+	return cg_find_root(root, len, NULL, nsdelegate);
+}
+
 int cg_create(const char *cgroup)
 {
 	return mkdir(cgroup, 0755);
@@ -488,84 +508,6 @@ int cg_run_nowait(const char *cgroup,
 	return pid;
 }
 
-int get_temp_fd(void)
-{
-	return open(".", O_TMPFILE | O_RDWR | O_EXCL);
-}
-
-int alloc_pagecache(int fd, size_t size)
-{
-	char buf[PAGE_SIZE];
-	struct stat st;
-	int i;
-
-	if (fstat(fd, &st))
-		goto cleanup;
-
-	size += st.st_size;
-
-	if (ftruncate(fd, size))
-		goto cleanup;
-
-	for (i = 0; i < size; i += sizeof(buf))
-		read(fd, buf, sizeof(buf));
-
-	return 0;
-
-cleanup:
-	return -1;
-}
-
-int alloc_anon(const char *cgroup, void *arg)
-{
-	size_t size = (unsigned long)arg;
-	char *buf, *ptr;
-
-	buf = malloc(size);
-	for (ptr = buf; ptr < buf + size; ptr += PAGE_SIZE)
-		*ptr = 0;
-
-	free(buf);
-	return 0;
-}
-
-int is_swap_enabled(void)
-{
-	char buf[PAGE_SIZE];
-	const char delim[] = "\n";
-	int cnt = 0;
-	char *line;
-
-	if (read_text("/proc/swaps", buf, sizeof(buf)) <= 0)
-		return -1;
-
-	for (line = strtok(buf, delim); line; line = strtok(NULL, delim))
-		cnt++;
-
-	return cnt > 1;
-}
-
-int set_oom_adj_score(int pid, int score)
-{
-	char path[PATH_MAX];
-	int fd, len;
-
-	sprintf(path, "/proc/%d/oom_score_adj", pid);
-
-	fd = open(path, O_WRONLY | O_APPEND);
-	if (fd < 0)
-		return fd;
-
-	len = dprintf(fd, "%d", score);
-	if (len < 0) {
-		close(fd);
-		return len;
-	}
-
-	close(fd);
-	return 0;
-}
-
 int proc_mount_contains(const char *option)
 {
 	char buf[4 * PAGE_SIZE];
diff --git a/tools/testing/selftests/cgroup/cgroup_util.h b/tools/testing/selftests/cgroup/lib/include/cgroup_util.h
index 19b131ee7707..adb2bc193183 100644
--- a/tools/testing/selftests/cgroup/cgroup_util.h
+++ b/tools/testing/selftests/cgroup/lib/include/cgroup_util.h
@@ -2,9 +2,9 @@
 #include <stdbool.h>
 #include <stdlib.h>
 
-#include "../kselftest.h"
-
+#ifndef PAGE_SIZE
 #define PAGE_SIZE 4096
+#endif
 
 #define MB(x) (x << 20)
 
@@ -21,6 +21,10 @@ static inline int values_close(long a, long b, int err)
 	return labs(a - b) <= (a + b) / 100 * err;
 }
 
+extern ssize_t read_text(const char *path, char *buf, size_t max_len);
+extern ssize_t write_text(const char *path, char *buf, ssize_t len);
+
+extern int cg_find_controller_root(char *root, size_t len, const char *controller);
 extern int cg_find_unified_root(char *root, size_t len, bool *nsdelegate);
 extern char *cg_name(const char *root, const char *name);
 extern char *cg_name_indexed(const char *root, const char *name, int index);
@@ -49,11 +53,6 @@ extern int cg_enter_current_thread(const char *cgroup);
 extern int cg_run_nowait(const char *cgroup,
 			 int (*fn)(const char *cgroup, void *arg),
 			 void *arg);
-extern int get_temp_fd(void);
-extern int alloc_pagecache(int fd, size_t size);
-extern int alloc_anon(const char *cgroup, void *arg);
-extern int is_swap_enabled(void);
-extern int set_oom_adj_score(int pid, int score);
 extern int cg_wait_for_proc_count(const char *cgroup, int count);
 extern int cg_killall(const char *cgroup);
 int proc_mount_contains(const char *option);
diff --git a/tools/testing/selftests/cgroup/lib/libcgroup.mk b/tools/testing/selftests/cgroup/lib/libcgroup.mk
new file mode 100644
index 000000000000..7a73007204c3
--- /dev/null
+++ b/tools/testing/selftests/cgroup/lib/libcgroup.mk
@@ -0,0 +1,19 @@
+CGROUP_DIR := $(selfdir)/cgroup
+
+LIBCGROUP_C := lib/cgroup_util.c
+
+LIBCGROUP_O := $(patsubst %.c, $(OUTPUT)/%.o, $(LIBCGROUP_C))
+
+LIBCGROUP_O_DIRS := $(shell dirname $(LIBCGROUP_O) | uniq)
+
+CFLAGS += -I$(CGROUP_DIR)/lib/include
+
+EXTRA_HDRS := $(selfdir)/clone3/clone3_selftests.h
+
+$(LIBCGROUP_O_DIRS):
+	mkdir -p $@
+
+$(LIBCGROUP_O): $(OUTPUT)/%.o : $(CGROUP_DIR)/%.c $(EXTRA_HDRS) $(LIBCGROUP_O_DIRS)
+	$(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c $< -o $@
+
+EXTRA_CLEAN += $(LIBCGROUP_O)
diff --git a/tools/testing/selftests/cgroup/test_memcontrol.c b/tools/testing/selftests/cgroup/test_memcontrol.c
index d6534d7301a2..a680f773f2d5 100644
--- a/tools/testing/selftests/cgroup/test_memcontrol.c
+++ b/tools/testing/selftests/cgroup/test_memcontrol.c
@@ -24,6 +24,84 @@
 static bool has_localevents;
 static bool has_recursiveprot;
 
+int get_temp_fd(void)
+{
+	return open(".", O_TMPFILE | O_RDWR | O_EXCL);
+}
+
+int alloc_pagecache(int fd, size_t size)
+{
+	char buf[PAGE_SIZE];
+	struct stat st;
+	int i;
+
+	if (fstat(fd, &st))
+		goto cleanup;
+
+	size += st.st_size;
+
+	if (ftruncate(fd, size))
+		goto cleanup;
+
+	for (i = 0; i < size; i += sizeof(buf))
+		read(fd, buf, sizeof(buf));
+
+	return 0;
+
+cleanup:
+	return -1;
+}
+
+int alloc_anon(const char *cgroup, void *arg)
+{
+	size_t size = (unsigned long)arg;
+	char *buf, *ptr;
+
+	buf = malloc(size);
+	for (ptr = buf; ptr < buf + size; ptr += PAGE_SIZE)
+		*ptr = 0;
+
+	free(buf);
+	return 0;
+}
+
+int is_swap_enabled(void)
+{
+	char buf[PAGE_SIZE];
+	const char delim[] = "\n";
+	int cnt = 0;
+	char *line;
+
+	if (read_text("/proc/swaps", buf, sizeof(buf)) <= 0)
+		return -1;
+
+	for (line = strtok(buf, delim); line; line = strtok(NULL, delim))
+		cnt++;
+
+	return cnt > 1;
+}
+
+int set_oom_adj_score(int pid, int score)
+{
+	char path[PATH_MAX];
+	int fd, len;
+
+	sprintf(path, "/proc/%d/oom_score_adj", pid);
+
+	fd = open(path, O_WRONLY | O_APPEND);
+	if (fd < 0)
+		return fd;
+
+	len = dprintf(fd, "%d", score);
+	if (len < 0) {
+		close(fd);
+		return len;
+	}
+
+	close(fd);
+	return 0;
+}
+
 /*
  * This test creates two nested cgroups with and without enabling
  * the memory controller.
diff --git a/tools/testing/selftests/kvm/Makefile.kvm b/tools/testing/selftests/kvm/Makefile.kvm
index 3e786080473d..38b95998e1e6 100644
--- a/tools/testing/selftests/kvm/Makefile.kvm
+++ b/tools/testing/selftests/kvm/Makefile.kvm
@@ -8,6 +8,7 @@ LIBKVM += lib/elf.c
 LIBKVM += lib/guest_modes.c
 LIBKVM += lib/io.c
 LIBKVM += lib/kvm_util.c
+LIBKVM += lib/lru_gen_util.c
 LIBKVM += lib/memstress.c
 LIBKVM += lib/guest_sprintf.c
 LIBKVM += lib/rbtree.c
@@ -70,6 +71,7 @@ TEST_GEN_PROGS_x86 += x86/cr4_cpuid_sync_test
 TEST_GEN_PROGS_x86 += x86/dirty_log_page_splitting_test
 TEST_GEN_PROGS_x86 += x86/feature_msrs_test
 TEST_GEN_PROGS_x86 += x86/exit_on_emulation_failure_test
+TEST_GEN_PROGS_x86 += x86/fastops_test
 TEST_GEN_PROGS_x86 += x86/fix_hypercall_test
 TEST_GEN_PROGS_x86 += x86/hwcr_msr_test
 TEST_GEN_PROGS_x86 += x86/hyperv_clock
@@ -82,6 +84,7 @@ TEST_GEN_PROGS_x86 += x86/hyperv_svm_test
 TEST_GEN_PROGS_x86 += x86/hyperv_tlb_flush
 TEST_GEN_PROGS_x86 += x86/kvm_clock_test
 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/nested_emulation_test
 TEST_GEN_PROGS_x86 += x86/nested_exceptions_test
@@ -222,6 +225,7 @@ OVERRIDE_TARGETS = 1
 # importantly defines, i.e. overwrites, $(CC) (unless `make -e` or `make CC=`,
 # which causes the environment variable to override the makefile).
 include ../lib.mk
+include ../cgroup/lib/libcgroup.mk
 
 INSTALL_HDR_PATH = $(top_srcdir)/usr
 LINUX_HDR_PATH = $(INSTALL_HDR_PATH)/include/
@@ -275,7 +279,7 @@ LIBKVM_S := $(filter %.S,$(LIBKVM))
 LIBKVM_C_OBJ := $(patsubst %.c, $(OUTPUT)/%.o, $(LIBKVM_C))
 LIBKVM_S_OBJ := $(patsubst %.S, $(OUTPUT)/%.o, $(LIBKVM_S))
 LIBKVM_STRING_OBJ := $(patsubst %.c, $(OUTPUT)/%.o, $(LIBKVM_STRING))
-LIBKVM_OBJS = $(LIBKVM_C_OBJ) $(LIBKVM_S_OBJ) $(LIBKVM_STRING_OBJ)
+LIBKVM_OBJS = $(LIBKVM_C_OBJ) $(LIBKVM_S_OBJ) $(LIBKVM_STRING_OBJ) $(LIBCGROUP_O)
 SPLIT_TEST_GEN_PROGS := $(patsubst %, $(OUTPUT)/%, $(SPLIT_TESTS))
 SPLIT_TEST_GEN_OBJ := $(patsubst %, $(OUTPUT)/$(ARCH)/%.o, $(SPLIT_TESTS))
 
diff --git a/tools/testing/selftests/kvm/access_tracking_perf_test.c b/tools/testing/selftests/kvm/access_tracking_perf_test.c
index 447e619cf856..da7196fd1b23 100644
--- a/tools/testing/selftests/kvm/access_tracking_perf_test.c
+++ b/tools/testing/selftests/kvm/access_tracking_perf_test.c
@@ -7,9 +7,11 @@
  * This test measures the performance effects of KVM's access tracking.
  * Access tracking is driven by the MMU notifiers test_young, clear_young, and
  * clear_flush_young. These notifiers do not have a direct userspace API,
- * however the clear_young notifier can be triggered by marking a pages as idle
- * in /sys/kernel/mm/page_idle/bitmap. This test leverages that mechanism to
- * enable access tracking on guest memory.
+ * however the clear_young notifier can be triggered either by
+ *   1. marking a pages as idle in /sys/kernel/mm/page_idle/bitmap OR
+ *   2. adding a new MGLRU generation using the lru_gen debugfs file.
+ * This test leverages page_idle to enable access tracking on guest memory
+ * unless MGLRU is enabled, in which case MGLRU is used.
  *
  * To measure performance this test runs a VM with a configurable number of
  * vCPUs that each touch every page in disjoint regions of memory. Performance
@@ -17,10 +19,11 @@
  * predefined region.
  *
  * Note that a deterministic correctness test of access tracking is not possible
- * by using page_idle as it exists today. This is for a few reasons:
+ * by using page_idle or MGLRU aging as it exists today. This is for a few
+ * reasons:
  *
- * 1. page_idle only issues clear_young notifiers, which lack a TLB flush. This
- *    means subsequent guest accesses are not guaranteed to see page table
+ * 1. page_idle and MGLRU only issue clear_young notifiers, which lack a TLB flush.
+ *    This means subsequent guest accesses are not guaranteed to see page table
  *    updates made by KVM until some time in the future.
  *
  * 2. page_idle only operates on LRU pages. Newly allocated pages are not
@@ -48,9 +51,17 @@
 #include "guest_modes.h"
 #include "processor.h"
 
+#include "cgroup_util.h"
+#include "lru_gen_util.h"
+
+static const char *TEST_MEMCG_NAME = "access_tracking_perf_test";
+
 /* Global variable used to synchronize all of the vCPU threads. */
 static int iteration;
 
+/* The cgroup memory controller root. Needed for lru_gen-based aging. */
+char cgroup_root[PATH_MAX];
+
 /* Defines what vCPU threads should do during a given iteration. */
 static enum {
 	/* Run the vCPU to access all its memory. */
@@ -65,6 +76,25 @@ static int vcpu_last_completed_iteration[KVM_MAX_VCPUS];
 /* Whether to overlap the regions of memory vCPUs access. */
 static bool overlap_memory_access;
 
+/*
+ * If the test should only warn if there are too many idle pages (i.e., it is
+ * expected).
+ * -1: Not yet set.
+ *  0: We do not expect too many idle pages, so FAIL if too many idle pages.
+ *  1: Having too many idle pages is expected, so merely print a warning if
+ *     too many idle pages are found.
+ */
+static int idle_pages_warn_only = -1;
+
+/* Whether or not to use MGLRU instead of page_idle for access tracking */
+static bool use_lru_gen;
+
+/* Total number of pages to expect in the memcg after touching everything */
+static long test_pages;
+
+/* Last generation we found the pages in */
+static int lru_gen_last_gen = -1;
+
 struct test_params {
 	/* The backing source for the region of memory. */
 	enum vm_mem_backing_src_type backing_src;
@@ -123,8 +153,24 @@ static void mark_page_idle(int page_idle_fd, uint64_t pfn)
 		    "Set page_idle bits for PFN 0x%" PRIx64, pfn);
 }
 
-static void mark_vcpu_memory_idle(struct kvm_vm *vm,
-				  struct memstress_vcpu_args *vcpu_args)
+static void too_many_idle_pages(long idle_pages, long total_pages, int vcpu_idx)
+{
+	char prefix[18] = {};
+
+	if (vcpu_idx >= 0)
+		snprintf(prefix, 18, "vCPU%d: ", vcpu_idx);
+
+	TEST_ASSERT(idle_pages_warn_only,
+		    "%sToo many pages still idle (%lu out of %lu)",
+		    prefix, idle_pages, total_pages);
+
+	printf("WARNING: %sToo many pages still idle (%lu out of %lu), "
+	       "this will affect performance results.\n",
+	       prefix, idle_pages, total_pages);
+}
+
+static void pageidle_mark_vcpu_memory_idle(struct kvm_vm *vm,
+					   struct memstress_vcpu_args *vcpu_args)
 {
 	int vcpu_idx = vcpu_args->vcpu_idx;
 	uint64_t base_gva = vcpu_args->gva;
@@ -177,27 +223,79 @@ static void mark_vcpu_memory_idle(struct kvm_vm *vm,
 	 * arbitrary; high enough that we ensure most memory access went through
 	 * access tracking but low enough as to not make the test too brittle
 	 * over time and across architectures.
-	 *
-	 * When running the guest as a nested VM, "warn" instead of asserting
-	 * as the TLB size is effectively unlimited and the KVM doesn't
-	 * explicitly flush the TLB when aging SPTEs.  As a result, more pages
-	 * are cached and the guest won't see the "idle" bit cleared.
 	 */
-	if (still_idle >= pages / 10) {
-#ifdef __x86_64__
-		TEST_ASSERT(this_cpu_has(X86_FEATURE_HYPERVISOR),
-			    "vCPU%d: Too many pages still idle (%lu out of %lu)",
-			    vcpu_idx, still_idle, pages);
-#endif
-		printf("WARNING: vCPU%d: Too many pages still idle (%lu out of %lu), "
-		       "this will affect performance results.\n",
-		       vcpu_idx, still_idle, pages);
-	}
+	if (still_idle >= pages / 10)
+		too_many_idle_pages(still_idle, pages,
+				    overlap_memory_access ? -1 : vcpu_idx);
 
 	close(page_idle_fd);
 	close(pagemap_fd);
 }
 
+int find_generation(struct memcg_stats *stats, long total_pages)
+{
+	/*
+	 * For finding the generation that contains our pages, use the same
+	 * 90% threshold that page_idle uses.
+	 */
+	int gen = lru_gen_find_generation(stats, total_pages * 9 / 10);
+
+	if (gen >= 0)
+		return gen;
+
+	if (!idle_pages_warn_only) {
+		TEST_FAIL("Could not find a generation with 90%% of guest memory (%ld pages).",
+			   total_pages * 9 / 10);
+		return gen;
+	}
+
+	/*
+	 * We couldn't find a generation with 90% of guest memory, which can
+	 * happen if access tracking is unreliable. Simply look for a majority
+	 * of pages.
+	 */
+	puts("WARNING: Couldn't find a generation with 90% of guest memory. "
+	     "Performance results may not be accurate.");
+	gen = lru_gen_find_generation(stats, total_pages / 2);
+	TEST_ASSERT(gen >= 0,
+		    "Could not find a generation with 50%% of guest memory (%ld pages).",
+		    total_pages / 2);
+	return gen;
+}
+
+static void lru_gen_mark_memory_idle(struct kvm_vm *vm)
+{
+	struct timespec ts_start;
+	struct timespec ts_elapsed;
+	struct memcg_stats stats;
+	int new_gen;
+
+	/* Make a new generation */
+	clock_gettime(CLOCK_MONOTONIC, &ts_start);
+	lru_gen_do_aging(&stats, TEST_MEMCG_NAME);
+	ts_elapsed = timespec_elapsed(ts_start);
+
+	/* Check the generation again */
+	new_gen = find_generation(&stats, test_pages);
+
+	/*
+	 * This function should only be invoked with newly-accessed pages,
+	 * so pages should always move to a newer generation.
+	 */
+	if (new_gen <= lru_gen_last_gen) {
+		/* We did not move to a newer generation. */
+		long idle_pages = lru_gen_sum_memcg_stats_for_gen(lru_gen_last_gen,
+								  &stats);
+
+		too_many_idle_pages(min_t(long, idle_pages, test_pages),
+				    test_pages, -1);
+	}
+	pr_info("%-30s: %ld.%09lds\n",
+		"Mark memory idle (lru_gen)", ts_elapsed.tv_sec,
+		ts_elapsed.tv_nsec);
+	lru_gen_last_gen = new_gen;
+}
+
 static void assert_ucall(struct kvm_vcpu *vcpu, uint64_t expected_ucall)
 {
 	struct ucall uc;
@@ -237,7 +335,7 @@ static void vcpu_thread_main(struct memstress_vcpu_args *vcpu_args)
 			assert_ucall(vcpu, UCALL_SYNC);
 			break;
 		case ITERATION_MARK_IDLE:
-			mark_vcpu_memory_idle(vm, vcpu_args);
+			pageidle_mark_vcpu_memory_idle(vm, vcpu_args);
 			break;
 		}
 
@@ -289,15 +387,18 @@ static void access_memory(struct kvm_vm *vm, int nr_vcpus,
 
 static void mark_memory_idle(struct kvm_vm *vm, int nr_vcpus)
 {
+	if (use_lru_gen)
+		return lru_gen_mark_memory_idle(vm);
+
 	/*
 	 * Even though this parallelizes the work across vCPUs, this is still a
 	 * very slow operation because page_idle forces the test to mark one pfn
-	 * at a time and the clear_young notifier serializes on the KVM MMU
+	 * at a time and the clear_young notifier may serialize on the KVM MMU
 	 * lock.
 	 */
 	pr_debug("Marking VM memory idle (slow)...\n");
 	iteration_work = ITERATION_MARK_IDLE;
-	run_iteration(vm, nr_vcpus, "Mark memory idle");
+	run_iteration(vm, nr_vcpus, "Mark memory idle (page_idle)");
 }
 
 static void run_test(enum vm_guest_mode mode, void *arg)
@@ -309,11 +410,38 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	vm = memstress_create_vm(mode, nr_vcpus, params->vcpu_memory_bytes, 1,
 				 params->backing_src, !overlap_memory_access);
 
+	/*
+	 * If guest_page_size is larger than the host's page size, the
+	 * guest (memstress) will only fault in a subset of the host's pages.
+	 */
+	test_pages = params->nr_vcpus * params->vcpu_memory_bytes /
+		      max(memstress_args.guest_page_size,
+			  (uint64_t)getpagesize());
+
 	memstress_start_vcpu_threads(nr_vcpus, vcpu_thread_main);
 
 	pr_info("\n");
 	access_memory(vm, nr_vcpus, ACCESS_WRITE, "Populating memory");
 
+	if (use_lru_gen) {
+		struct memcg_stats stats;
+
+		/*
+		 * Do a page table scan now. Following initial population, aging
+		 * may not cause the pages to move to a newer generation. Do
+		 * an aging pass now so that future aging passes always move
+		 * pages to a newer generation.
+		 */
+		printf("Initial aging pass (lru_gen)\n");
+		lru_gen_do_aging(&stats, TEST_MEMCG_NAME);
+		TEST_ASSERT(lru_gen_sum_memcg_stats(&stats) >= test_pages,
+			    "Not all pages accounted for (looking for %ld). "
+			    "Was the memcg set up correctly?", test_pages);
+		access_memory(vm, nr_vcpus, ACCESS_WRITE, "Re-populating memory");
+		lru_gen_read_memcg_stats(&stats, TEST_MEMCG_NAME);
+		lru_gen_last_gen = find_generation(&stats, test_pages);
+	}
+
 	/* As a control, read and write to the populated memory first. */
 	access_memory(vm, nr_vcpus, ACCESS_WRITE, "Writing to populated memory");
 	access_memory(vm, nr_vcpus, ACCESS_READ, "Reading from populated memory");
@@ -328,6 +456,37 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	memstress_destroy_vm(vm);
 }
 
+static int access_tracking_unreliable(void)
+{
+#ifdef __x86_64__
+	/*
+	 * When running nested, the TLB size may be effectively unlimited (for
+	 * example, this is the case when running on KVM L0), and KVM doesn't
+	 * explicitly flush the TLB when aging SPTEs.  As a result, more pages
+	 * are cached and the guest won't see the "idle" bit cleared.
+	 */
+	if (this_cpu_has(X86_FEATURE_HYPERVISOR)) {
+		puts("Skipping idle page count sanity check, because the test is run nested");
+		return 1;
+	}
+#endif
+	/*
+	 * When NUMA balancing is enabled, guest memory will be unmapped to get
+	 * NUMA faults, dropping the Accessed bits.
+	 */
+	if (is_numa_balancing_enabled()) {
+		puts("Skipping idle page count sanity check, because NUMA balancing is enabled");
+		return 1;
+	}
+	return 0;
+}
+
+static int run_test_for_each_guest_mode(const char *cgroup, void *arg)
+{
+	for_each_guest_mode(run_test, arg);
+	return 0;
+}
+
 static void help(char *name)
 {
 	puts("");
@@ -342,11 +501,22 @@ static void help(char *name)
 	printf(" -v: specify the number of vCPUs to run.\n");
 	printf(" -o: Overlap guest memory accesses instead of partitioning\n"
 	       "     them into a separate region of memory for each vCPU.\n");
+	printf(" -w: Control whether the test warns or fails if more than 10%%\n"
+	       "     of pages are still seen as idle/old after accessing guest\n"
+	       "     memory.  >0 == warn only, 0 == fail, <0 == auto.  For auto\n"
+	       "     mode, the test fails by default, but switches to warn only\n"
+	       "     if NUMA balancing is enabled or the test detects it's running\n"
+	       "     in a VM.\n");
 	backing_src_help("-s");
 	puts("");
 	exit(0);
 }
 
+void destroy_cgroup(char *cg)
+{
+	printf("Destroying cgroup: %s\n", cg);
+}
+
 int main(int argc, char *argv[])
 {
 	struct test_params params = {
@@ -354,12 +524,13 @@ int main(int argc, char *argv[])
 		.vcpu_memory_bytes = DEFAULT_PER_VCPU_MEM_SIZE,
 		.nr_vcpus = 1,
 	};
+	char *new_cg = NULL;
 	int page_idle_fd;
 	int opt;
 
 	guest_modes_append_default();
 
-	while ((opt = getopt(argc, argv, "hm:b:v:os:")) != -1) {
+	while ((opt = getopt(argc, argv, "hm:b:v:os:w:")) != -1) {
 		switch (opt) {
 		case 'm':
 			guest_modes_cmdline(optarg);
@@ -376,6 +547,11 @@ int main(int argc, char *argv[])
 		case 's':
 			params.backing_src = parse_backing_src_type(optarg);
 			break;
+		case 'w':
+			idle_pages_warn_only =
+				atoi_non_negative("Idle pages warning",
+						  optarg);
+			break;
 		case 'h':
 		default:
 			help(argv[0]);
@@ -383,12 +559,53 @@ int main(int argc, char *argv[])
 		}
 	}
 
-	page_idle_fd = open("/sys/kernel/mm/page_idle/bitmap", O_RDWR);
-	__TEST_REQUIRE(page_idle_fd >= 0,
-		       "CONFIG_IDLE_PAGE_TRACKING is not enabled");
-	close(page_idle_fd);
+	if (idle_pages_warn_only == -1)
+		idle_pages_warn_only = access_tracking_unreliable();
+
+	if (lru_gen_usable()) {
+		bool cg_created = true;
+		int ret;
 
-	for_each_guest_mode(run_test, &params);
+		puts("Using lru_gen for aging");
+		use_lru_gen = true;
+
+		if (cg_find_controller_root(cgroup_root, sizeof(cgroup_root), "memory"))
+			ksft_exit_skip("Cannot find memory cgroup controller\n");
+
+		new_cg = cg_name(cgroup_root, TEST_MEMCG_NAME);
+		printf("Creating cgroup: %s\n", new_cg);
+		if (cg_create(new_cg)) {
+			if (errno == EEXIST) {
+				printf("Found existing cgroup");
+				cg_created = false;
+			} else {
+				ksft_exit_skip("could not create new cgroup: %s\n", new_cg);
+			}
+		}
+
+		/*
+		 * This will fork off a new process to run the test within
+		 * a new memcg, so we need to properly propagate the return
+		 * value up.
+		 */
+		ret = cg_run(new_cg, &run_test_for_each_guest_mode, &params);
+		if (cg_created)
+			cg_destroy(new_cg);
+		if (ret < 0)
+			TEST_FAIL("child did not spawn or was abnormally killed");
+		if (ret)
+			return ret;
+	} else {
+		page_idle_fd = open("/sys/kernel/mm/page_idle/bitmap", O_RDWR);
+		__TEST_REQUIRE(page_idle_fd >= 0,
+			       "Couldn't open /sys/kernel/mm/page_idle/bitmap. "
+			       "Is CONFIG_IDLE_PAGE_TRACKING enabled?");
+
+		close(page_idle_fd);
+
+		puts("Using page_idle for aging");
+		run_test_for_each_guest_mode(NULL, &params);
+	}
 
 	return 0;
 }
diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h
index 93013564428b..bee65ca08721 100644
--- a/tools/testing/selftests/kvm/include/kvm_util.h
+++ b/tools/testing/selftests/kvm/include/kvm_util.h
@@ -555,6 +555,41 @@ void kvm_get_stat(struct kvm_binary_stats *stats, const char *name,
 #define vm_get_stat(vm, stat) __get_stat(&(vm)->stats, stat)
 #define vcpu_get_stat(vcpu, stat) __get_stat(&(vcpu)->stats, stat)
 
+static inline bool read_smt_control(char *buf, size_t buf_size)
+{
+	FILE *f = fopen("/sys/devices/system/cpu/smt/control", "r");
+	bool ret;
+
+	if (!f)
+		return false;
+
+	ret = fread(buf, sizeof(*buf), buf_size, f) > 0;
+	fclose(f);
+
+	return ret;
+}
+
+static inline bool is_smt_possible(void)
+{
+	char buf[16];
+
+	if (read_smt_control(buf, sizeof(buf)) &&
+	    (!strncmp(buf, "forceoff", 8) || !strncmp(buf, "notsupported", 12)))
+		return false;
+
+	return true;
+}
+
+static inline bool is_smt_on(void)
+{
+	char buf[16];
+
+	if (read_smt_control(buf, sizeof(buf)) && !strncmp(buf, "on", 2))
+		return true;
+
+	return false;
+}
+
 void vm_create_irqchip(struct kvm_vm *vm);
 
 static inline int __vm_create_guest_memfd(struct kvm_vm *vm, uint64_t size,
diff --git a/tools/testing/selftests/kvm/include/lru_gen_util.h b/tools/testing/selftests/kvm/include/lru_gen_util.h
new file mode 100644
index 000000000000..d32ff5d8ffd0
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/lru_gen_util.h
@@ -0,0 +1,51 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Tools for integrating with lru_gen, like parsing the lru_gen debugfs output.
+ *
+ * Copyright (C) 2025, Google LLC.
+ */
+#ifndef SELFTEST_KVM_LRU_GEN_UTIL_H
+#define SELFTEST_KVM_LRU_GEN_UTIL_H
+
+#include <inttypes.h>
+#include <limits.h>
+#include <stdlib.h>
+
+#include "test_util.h"
+
+#define MAX_NR_GENS 16 /* MAX_NR_GENS in include/linux/mmzone.h */
+#define MAX_NR_NODES 4 /* Maximum number of nodes supported by the test */
+
+#define LRU_GEN_DEBUGFS "/sys/kernel/debug/lru_gen"
+#define LRU_GEN_ENABLED_PATH "/sys/kernel/mm/lru_gen/enabled"
+#define LRU_GEN_ENABLED 1
+#define LRU_GEN_MM_WALK 2
+
+struct generation_stats {
+	int gen;
+	long age_ms;
+	long nr_anon;
+	long nr_file;
+};
+
+struct node_stats {
+	int node;
+	int nr_gens; /* Number of populated gens entries. */
+	struct generation_stats gens[MAX_NR_GENS];
+};
+
+struct memcg_stats {
+	unsigned long memcg_id;
+	int nr_nodes; /* Number of populated nodes entries. */
+	struct node_stats nodes[MAX_NR_NODES];
+};
+
+void lru_gen_read_memcg_stats(struct memcg_stats *stats, const char *memcg);
+long lru_gen_sum_memcg_stats(const struct memcg_stats *stats);
+long lru_gen_sum_memcg_stats_for_gen(int gen, const struct memcg_stats *stats);
+void lru_gen_do_aging(struct memcg_stats *stats, const char *memcg);
+int lru_gen_find_generation(const struct memcg_stats *stats,
+			    unsigned long total_pages);
+bool lru_gen_usable(void);
+
+#endif /* SELFTEST_KVM_LRU_GEN_UTIL_H */
diff --git a/tools/testing/selftests/kvm/include/test_util.h b/tools/testing/selftests/kvm/include/test_util.h
index 77d13d7920cb..c6ef895fbd9a 100644
--- a/tools/testing/selftests/kvm/include/test_util.h
+++ b/tools/testing/selftests/kvm/include/test_util.h
@@ -153,6 +153,7 @@ bool is_backing_src_hugetlb(uint32_t i);
 void backing_src_help(const char *flag);
 enum vm_mem_backing_src_type parse_backing_src_type(const char *type_name);
 long get_run_delay(void);
+bool is_numa_balancing_enabled(void);
 
 /*
  * Whether or not the given source type is shared memory (as opposed to
diff --git a/tools/testing/selftests/kvm/include/x86/processor.h b/tools/testing/selftests/kvm/include/x86/processor.h
index 32ab6ca7ec32..b11b5a53ebd5 100644
--- a/tools/testing/selftests/kvm/include/x86/processor.h
+++ b/tools/testing/selftests/kvm/include/x86/processor.h
@@ -203,6 +203,7 @@ struct kvm_x86_cpu_feature {
 #define X86_FEATURE_IDLE_HLT		KVM_X86_CPU_FEATURE(0x8000000A, 0, EDX, 30)
 #define X86_FEATURE_SEV			KVM_X86_CPU_FEATURE(0x8000001F, 0, EAX, 1)
 #define X86_FEATURE_SEV_ES		KVM_X86_CPU_FEATURE(0x8000001F, 0, EAX, 3)
+#define X86_FEATURE_SEV_SNP		KVM_X86_CPU_FEATURE(0x8000001F, 0, EAX, 4)
 #define	X86_FEATURE_PERFMON_V2		KVM_X86_CPU_FEATURE(0x80000022, 0, EAX, 0)
 #define	X86_FEATURE_LBR_PMC_FREEZE	KVM_X86_CPU_FEATURE(0x80000022, 0, EAX, 2)
 
diff --git a/tools/testing/selftests/kvm/include/x86/sev.h b/tools/testing/selftests/kvm/include/x86/sev.h
index 82c11c81a956..008b4169f5e2 100644
--- a/tools/testing/selftests/kvm/include/x86/sev.h
+++ b/tools/testing/selftests/kvm/include/x86/sev.h
@@ -25,19 +25,51 @@ enum sev_guest_state {
 #define SEV_POLICY_NO_DBG	(1UL << 0)
 #define SEV_POLICY_ES		(1UL << 2)
 
+#define SNP_POLICY_SMT		(1ULL << 16)
+#define SNP_POLICY_RSVD_MBO	(1ULL << 17)
+#define SNP_POLICY_DBG		(1ULL << 19)
+
 #define GHCB_MSR_TERM_REQ	0x100
 
+static inline bool is_sev_snp_vm(struct kvm_vm *vm)
+{
+	return vm->type == KVM_X86_SNP_VM;
+}
+
+static inline bool is_sev_es_vm(struct kvm_vm *vm)
+{
+	return is_sev_snp_vm(vm) || vm->type == KVM_X86_SEV_ES_VM;
+}
+
+static inline bool is_sev_vm(struct kvm_vm *vm)
+{
+	return is_sev_es_vm(vm) || vm->type == KVM_X86_SEV_VM;
+}
+
 void sev_vm_launch(struct kvm_vm *vm, uint32_t policy);
 void sev_vm_launch_measure(struct kvm_vm *vm, uint8_t *measurement);
 void sev_vm_launch_finish(struct kvm_vm *vm);
+void snp_vm_launch_start(struct kvm_vm *vm, uint64_t policy);
+void snp_vm_launch_update(struct kvm_vm *vm);
+void snp_vm_launch_finish(struct kvm_vm *vm);
 
 struct kvm_vm *vm_sev_create_with_one_vcpu(uint32_t type, void *guest_code,
 					   struct kvm_vcpu **cpu);
-void vm_sev_launch(struct kvm_vm *vm, uint32_t policy, uint8_t *measurement);
+void vm_sev_launch(struct kvm_vm *vm, uint64_t policy, uint8_t *measurement);
 
 kvm_static_assert(SEV_RET_SUCCESS == 0);
 
 /*
+ * A SEV-SNP VM requires the policy reserved bit to always be set.
+ * The SMT policy bit is also required to be set based on SMT being
+ * available and active on the system.
+ */
+static inline u64 snp_default_policy(void)
+{
+	return SNP_POLICY_RSVD_MBO | (is_smt_on() ? SNP_POLICY_SMT : 0);
+}
+
+/*
  * The KVM_MEMORY_ENCRYPT_OP uAPI is utter garbage and takes an "unsigned long"
  * instead of a proper struct.  The size of the parameter is embedded in the
  * ioctl number, i.e. is ABI and thus immutable.  Hack around the mess by
@@ -70,6 +102,12 @@ kvm_static_assert(SEV_RET_SUCCESS == 0);
 
 void sev_vm_init(struct kvm_vm *vm);
 void sev_es_vm_init(struct kvm_vm *vm);
+void snp_vm_init(struct kvm_vm *vm);
+
+static inline void vmgexit(void)
+{
+	__asm__ __volatile__("rep; vmmcall");
+}
 
 static inline void sev_register_encrypted_memory(struct kvm_vm *vm,
 						 struct userspace_mem_region *region)
@@ -93,4 +131,17 @@ static inline void sev_launch_update_data(struct kvm_vm *vm, vm_paddr_t gpa,
 	vm_sev_ioctl(vm, KVM_SEV_LAUNCH_UPDATE_DATA, &update_data);
 }
 
+static inline void snp_launch_update_data(struct kvm_vm *vm, vm_paddr_t gpa,
+					  uint64_t hva, uint64_t size, uint8_t type)
+{
+	struct kvm_sev_snp_launch_update update_data = {
+		.uaddr = hva,
+		.gfn_start = gpa >> PAGE_SHIFT,
+		.len = size,
+		.type = type,
+	};
+
+	vm_sev_ioctl(vm, KVM_SEV_SNP_LAUNCH_UPDATE, &update_data);
+}
+
 #endif /* SELFTEST_KVM_SEV_H */
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 5649cf2f40e8..a055343a7bf7 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -447,6 +447,15 @@ void kvm_set_files_rlimit(uint32_t nr_vcpus)
 
 }
 
+static bool is_guest_memfd_required(struct vm_shape shape)
+{
+#ifdef __x86_64__
+	return shape.type == KVM_X86_SNP_VM;
+#else
+	return false;
+#endif
+}
+
 struct kvm_vm *__vm_create(struct vm_shape shape, uint32_t nr_runnable_vcpus,
 			   uint64_t nr_extra_pages)
 {
@@ -454,7 +463,7 @@ struct kvm_vm *__vm_create(struct vm_shape shape, uint32_t nr_runnable_vcpus,
 						 nr_extra_pages);
 	struct userspace_mem_region *slot0;
 	struct kvm_vm *vm;
-	int i;
+	int i, flags;
 
 	kvm_set_files_rlimit(nr_runnable_vcpus);
 
@@ -463,7 +472,15 @@ struct kvm_vm *__vm_create(struct vm_shape shape, uint32_t nr_runnable_vcpus,
 
 	vm = ____vm_create(shape);
 
-	vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, 0, 0, nr_pages, 0);
+	/*
+	 * Force GUEST_MEMFD for the primary memory region if necessary, e.g.
+	 * for CoCo VMs that require GUEST_MEMFD backed private memory.
+	 */
+	flags = 0;
+	if (is_guest_memfd_required(shape))
+		flags |= KVM_MEM_GUEST_MEMFD;
+
+	vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, 0, 0, nr_pages, flags);
 	for (i = 0; i < NR_MEM_REGIONS; i++)
 		vm->memslots[i] = 0;
 
diff --git a/tools/testing/selftests/kvm/lib/lru_gen_util.c b/tools/testing/selftests/kvm/lib/lru_gen_util.c
new file mode 100644
index 000000000000..46a14fd63d9e
--- /dev/null
+++ b/tools/testing/selftests/kvm/lib/lru_gen_util.c
@@ -0,0 +1,387 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2025, Google LLC.
+ */
+
+#include <time.h>
+
+#include "lru_gen_util.h"
+
+/*
+ * Tracks state while we parse memcg lru_gen stats. The file we're parsing is
+ * structured like this (some extra whitespace elided):
+ *
+ * memcg (id) (path)
+ * node (id)
+ * (gen_nr) (age_in_ms) (nr_anon_pages) (nr_file_pages)
+ */
+struct memcg_stats_parse_context {
+	bool consumed; /* Whether or not this line was consumed */
+	/* Next parse handler to invoke */
+	void (*next_handler)(struct memcg_stats *stats,
+			     struct memcg_stats_parse_context *ctx,
+			     char *line);
+	int current_node_idx; /* Current index in nodes array */
+	const char *name; /* The name of the memcg we're looking for */
+};
+
+static void memcg_stats_handle_searching(struct memcg_stats *stats,
+					 struct memcg_stats_parse_context *ctx,
+					 char *line);
+static void memcg_stats_handle_in_memcg(struct memcg_stats *stats,
+					struct memcg_stats_parse_context *ctx,
+					char *line);
+static void memcg_stats_handle_in_node(struct memcg_stats *stats,
+				       struct memcg_stats_parse_context *ctx,
+				       char *line);
+
+struct split_iterator {
+	char *str;
+	char *save;
+};
+
+static char *split_next(struct split_iterator *it)
+{
+	char *ret = strtok_r(it->str, " \t\n\r", &it->save);
+
+	it->str = NULL;
+	return ret;
+}
+
+static void memcg_stats_handle_searching(struct memcg_stats *stats,
+					 struct memcg_stats_parse_context *ctx,
+					 char *line)
+{
+	struct split_iterator it = { .str = line };
+	char *prefix = split_next(&it);
+	char *memcg_id = split_next(&it);
+	char *memcg_name = split_next(&it);
+	char *end;
+
+	ctx->consumed = true;
+
+	if (!prefix || strcmp("memcg", prefix))
+		return; /* Not a memcg line (maybe empty), skip */
+
+	TEST_ASSERT(memcg_id && memcg_name,
+		    "malformed memcg line; no memcg id or memcg_name");
+
+	if (strcmp(memcg_name + 1, ctx->name))
+		return; /* Wrong memcg, skip */
+
+	/* Found it! */
+
+	stats->memcg_id = strtoul(memcg_id, &end, 10);
+	TEST_ASSERT(*end == '\0', "malformed memcg id '%s'", memcg_id);
+	if (!stats->memcg_id)
+		return; /* Removed memcg? */
+
+	ctx->next_handler = memcg_stats_handle_in_memcg;
+}
+
+static void memcg_stats_handle_in_memcg(struct memcg_stats *stats,
+					struct memcg_stats_parse_context *ctx,
+					char *line)
+{
+	struct split_iterator it = { .str = line };
+	char *prefix = split_next(&it);
+	char *id = split_next(&it);
+	long found_node_id;
+	char *end;
+
+	ctx->consumed = true;
+	ctx->current_node_idx = -1;
+
+	if (!prefix)
+		return; /* Skip empty lines */
+
+	if (!strcmp("memcg", prefix)) {
+		/* Memcg done, found next one; stop. */
+		ctx->next_handler = NULL;
+		return;
+	} else if (strcmp("node", prefix))
+		TEST_ASSERT(false, "found malformed line after 'memcg ...',"
+				   "token: '%s'", prefix);
+
+	/* At this point we know we have a node line. Parse the ID. */
+
+	TEST_ASSERT(id, "malformed node line; no node id");
+
+	found_node_id = strtol(id, &end, 10);
+	TEST_ASSERT(*end == '\0', "malformed node id '%s'", id);
+
+	ctx->current_node_idx = stats->nr_nodes++;
+	TEST_ASSERT(ctx->current_node_idx < MAX_NR_NODES,
+		    "memcg has stats for too many nodes, max is %d",
+		    MAX_NR_NODES);
+	stats->nodes[ctx->current_node_idx].node = found_node_id;
+
+	ctx->next_handler = memcg_stats_handle_in_node;
+}
+
+static void memcg_stats_handle_in_node(struct memcg_stats *stats,
+				       struct memcg_stats_parse_context *ctx,
+				       char *line)
+{
+	char *my_line = strdup(line);
+	struct split_iterator it = { .str = my_line };
+	char *gen, *age, *nr_anon, *nr_file;
+	struct node_stats *node_stats;
+	struct generation_stats *gen_stats;
+	char *end;
+
+	TEST_ASSERT(it.str, "failed to copy input line");
+
+	gen = split_next(&it);
+
+	if (!gen)
+		goto out_consume; /* Skip empty lines */
+
+	if (!strcmp("memcg", gen) || !strcmp("node", gen)) {
+		/*
+		 * Reached next memcg or node section. Don't consume, let the
+		 * other handler deal with this.
+		 */
+		ctx->next_handler = memcg_stats_handle_in_memcg;
+		goto out;
+	}
+
+	node_stats = &stats->nodes[ctx->current_node_idx];
+	TEST_ASSERT(node_stats->nr_gens < MAX_NR_GENS,
+		    "found too many generation lines; max is %d",
+		    MAX_NR_GENS);
+	gen_stats = &node_stats->gens[node_stats->nr_gens++];
+
+	age = split_next(&it);
+	nr_anon = split_next(&it);
+	nr_file = split_next(&it);
+
+	TEST_ASSERT(age && nr_anon && nr_file,
+		    "malformed generation line; not enough tokens");
+
+	gen_stats->gen = (int)strtol(gen, &end, 10);
+	TEST_ASSERT(*end == '\0', "malformed generation number '%s'", gen);
+
+	gen_stats->age_ms = strtol(age, &end, 10);
+	TEST_ASSERT(*end == '\0', "malformed generation age '%s'", age);
+
+	gen_stats->nr_anon = strtol(nr_anon, &end, 10);
+	TEST_ASSERT(*end == '\0', "malformed anonymous page count '%s'",
+		    nr_anon);
+
+	gen_stats->nr_file = strtol(nr_file, &end, 10);
+	TEST_ASSERT(*end == '\0', "malformed file page count '%s'", nr_file);
+
+out_consume:
+	ctx->consumed = true;
+out:
+	free(my_line);
+}
+
+static void print_memcg_stats(const struct memcg_stats *stats, const char *name)
+{
+	int node, gen;
+
+	pr_debug("stats for memcg %s (id %lu):\n", name, stats->memcg_id);
+	for (node = 0; node < stats->nr_nodes; ++node) {
+		pr_debug("\tnode %d\n", stats->nodes[node].node);
+		for (gen = 0; gen < stats->nodes[node].nr_gens; ++gen) {
+			const struct generation_stats *gstats =
+				&stats->nodes[node].gens[gen];
+
+			pr_debug("\t\tgen %d\tage_ms %ld"
+				 "\tnr_anon %ld\tnr_file %ld\n",
+				 gstats->gen, gstats->age_ms, gstats->nr_anon,
+				 gstats->nr_file);
+		}
+	}
+}
+
+/* Re-read lru_gen debugfs information for @memcg into @stats. */
+void lru_gen_read_memcg_stats(struct memcg_stats *stats, const char *memcg)
+{
+	FILE *f;
+	ssize_t read = 0;
+	char *line = NULL;
+	size_t bufsz;
+	struct memcg_stats_parse_context ctx = {
+		.next_handler = memcg_stats_handle_searching,
+		.name = memcg,
+	};
+
+	memset(stats, 0, sizeof(struct memcg_stats));
+
+	f = fopen(LRU_GEN_DEBUGFS, "r");
+	TEST_ASSERT(f, "fopen(%s) failed", LRU_GEN_DEBUGFS);
+
+	while (ctx.next_handler && (read = getline(&line, &bufsz, f)) > 0) {
+		ctx.consumed = false;
+
+		do {
+			ctx.next_handler(stats, &ctx, line);
+			if (!ctx.next_handler)
+				break;
+		} while (!ctx.consumed);
+	}
+
+	if (read < 0 && !feof(f))
+		TEST_ASSERT(false, "getline(%s) failed", LRU_GEN_DEBUGFS);
+
+	TEST_ASSERT(stats->memcg_id > 0, "Couldn't find memcg: %s\n"
+		    "Did the memcg get created in the proper mount?",
+		    memcg);
+	if (line)
+		free(line);
+	TEST_ASSERT(!fclose(f), "fclose(%s) failed", LRU_GEN_DEBUGFS);
+
+	print_memcg_stats(stats, memcg);
+}
+
+/*
+ * Find all pages tracked by lru_gen for this memcg in generation @target_gen.
+ *
+ * If @target_gen is negative, look for all generations.
+ */
+long lru_gen_sum_memcg_stats_for_gen(int target_gen,
+				     const struct memcg_stats *stats)
+{
+	int node, gen;
+	long total_nr = 0;
+
+	for (node = 0; node < stats->nr_nodes; ++node) {
+		const struct node_stats *node_stats = &stats->nodes[node];
+
+		for (gen = 0; gen < node_stats->nr_gens; ++gen) {
+			const struct generation_stats *gen_stats =
+				&node_stats->gens[gen];
+
+			if (target_gen >= 0 && gen_stats->gen != target_gen)
+				continue;
+
+			total_nr += gen_stats->nr_anon + gen_stats->nr_file;
+		}
+	}
+
+	return total_nr;
+}
+
+/* Find all pages tracked by lru_gen for this memcg. */
+long lru_gen_sum_memcg_stats(const struct memcg_stats *stats)
+{
+	return lru_gen_sum_memcg_stats_for_gen(-1, stats);
+}
+
+/*
+ * If lru_gen aging should force page table scanning.
+ *
+ * If you want to set this to false, you will need to do eviction
+ * before doing extra aging passes.
+ */
+static const bool force_scan = true;
+
+static void run_aging_impl(unsigned long memcg_id, int node_id, int max_gen)
+{
+	FILE *f = fopen(LRU_GEN_DEBUGFS, "w");
+	char *command;
+	size_t sz;
+
+	TEST_ASSERT(f, "fopen(%s) failed", LRU_GEN_DEBUGFS);
+	sz = asprintf(&command, "+ %lu %d %d 1 %d\n",
+		      memcg_id, node_id, max_gen, force_scan);
+	TEST_ASSERT(sz > 0, "creating aging command failed");
+
+	pr_debug("Running aging command: %s", command);
+	if (fwrite(command, sizeof(char), sz, f) < sz) {
+		TEST_ASSERT(false, "writing aging command %s to %s failed",
+			    command, LRU_GEN_DEBUGFS);
+	}
+
+	TEST_ASSERT(!fclose(f), "fclose(%s) failed", LRU_GEN_DEBUGFS);
+}
+
+void lru_gen_do_aging(struct memcg_stats *stats, const char *memcg)
+{
+	int node, gen;
+
+	pr_debug("lru_gen: invoking aging...\n");
+
+	/* Must read memcg stats to construct the proper aging command. */
+	lru_gen_read_memcg_stats(stats, memcg);
+
+	for (node = 0; node < stats->nr_nodes; ++node) {
+		int max_gen = 0;
+
+		for (gen = 0; gen < stats->nodes[node].nr_gens; ++gen) {
+			int this_gen = stats->nodes[node].gens[gen].gen;
+
+			max_gen = max_gen > this_gen ? max_gen : this_gen;
+		}
+
+		run_aging_impl(stats->memcg_id, stats->nodes[node].node,
+			       max_gen);
+	}
+
+	/* Re-read so callers get updated information */
+	lru_gen_read_memcg_stats(stats, memcg);
+}
+
+/*
+ * Find which generation contains at least @pages pages, assuming that
+ * such a generation exists.
+ */
+int lru_gen_find_generation(const struct memcg_stats *stats,
+			    unsigned long pages)
+{
+	int node, gen, gen_idx, min_gen = INT_MAX, max_gen = -1;
+
+	for (node = 0; node < stats->nr_nodes; ++node)
+		for (gen_idx = 0; gen_idx < stats->nodes[node].nr_gens;
+		     ++gen_idx) {
+			gen = stats->nodes[node].gens[gen_idx].gen;
+			max_gen = gen > max_gen ? gen : max_gen;
+			min_gen = gen < min_gen ? gen : min_gen;
+		}
+
+	for (gen = min_gen; gen <= max_gen; ++gen)
+		/* See if this generation has enough pages. */
+		if (lru_gen_sum_memcg_stats_for_gen(gen, stats) > pages)
+			return gen;
+
+	return -1;
+}
+
+bool lru_gen_usable(void)
+{
+	long required_features = LRU_GEN_ENABLED | LRU_GEN_MM_WALK;
+	int lru_gen_fd, lru_gen_debug_fd;
+	char mglru_feature_str[8] = {};
+	long mglru_features;
+
+	lru_gen_fd = open(LRU_GEN_ENABLED_PATH, O_RDONLY);
+	if (lru_gen_fd < 0) {
+		puts("lru_gen: Could not open " LRU_GEN_ENABLED_PATH);
+		return false;
+	}
+	if (read(lru_gen_fd, &mglru_feature_str, 7) < 7) {
+		puts("lru_gen: Could not read from " LRU_GEN_ENABLED_PATH);
+		close(lru_gen_fd);
+		return false;
+	}
+	close(lru_gen_fd);
+
+	mglru_features = strtol(mglru_feature_str, NULL, 16);
+	if ((mglru_features & required_features) != required_features) {
+		printf("lru_gen: missing features, got: 0x%lx, expected: 0x%lx\n",
+		       mglru_features, required_features);
+		printf("lru_gen: Try 'echo 0x%lx > /sys/kernel/mm/lru_gen/enabled'\n",
+		       required_features);
+		return false;
+	}
+
+	lru_gen_debug_fd = open(LRU_GEN_DEBUGFS, O_RDWR);
+	__TEST_REQUIRE(lru_gen_debug_fd >= 0,
+		       "lru_gen: Could not open " LRU_GEN_DEBUGFS ", "
+		       "but lru_gen is enabled, so cannot use page_idle.");
+	close(lru_gen_debug_fd);
+	return true;
+}
diff --git a/tools/testing/selftests/kvm/lib/test_util.c b/tools/testing/selftests/kvm/lib/test_util.c
index 8ed0b74ae837..03eb99af9b8d 100644
--- a/tools/testing/selftests/kvm/lib/test_util.c
+++ b/tools/testing/selftests/kvm/lib/test_util.c
@@ -132,37 +132,57 @@ void print_skip(const char *fmt, ...)
 	puts(", skipping test");
 }
 
-bool thp_configured(void)
+static bool test_sysfs_path(const char *path)
 {
-	int ret;
 	struct stat statbuf;
+	int ret;
 
-	ret = stat("/sys/kernel/mm/transparent_hugepage", &statbuf);
+	ret = stat(path, &statbuf);
 	TEST_ASSERT(ret == 0 || (ret == -1 && errno == ENOENT),
-		    "Error in stating /sys/kernel/mm/transparent_hugepage");
+		    "Error in stat()ing '%s'", path);
 
 	return ret == 0;
 }
 
-size_t get_trans_hugepagesz(void)
+bool thp_configured(void)
+{
+	return test_sysfs_path("/sys/kernel/mm/transparent_hugepage");
+}
+
+static size_t get_sysfs_val(const char *path)
 {
 	size_t size;
 	FILE *f;
 	int ret;
 
-	TEST_ASSERT(thp_configured(), "THP is not configured in host kernel");
-
-	f = fopen("/sys/kernel/mm/transparent_hugepage/hpage_pmd_size", "r");
-	TEST_ASSERT(f != NULL, "Error in opening transparent_hugepage/hpage_pmd_size");
+	f = fopen(path, "r");
+	TEST_ASSERT(f, "Error opening '%s'", path);
 
 	ret = fscanf(f, "%ld", &size);
+	TEST_ASSERT(ret > 0, "Error reading '%s'", path);
+
+	/* Re-scan the input stream to verify the entire file was read. */
 	ret = fscanf(f, "%ld", &size);
-	TEST_ASSERT(ret < 1, "Error reading transparent_hugepage/hpage_pmd_size");
-	fclose(f);
+	TEST_ASSERT(ret < 1, "Error reading '%s'", path);
 
+	fclose(f);
 	return size;
 }
 
+size_t get_trans_hugepagesz(void)
+{
+	TEST_ASSERT(thp_configured(), "THP is not configured in host kernel");
+
+	return get_sysfs_val("/sys/kernel/mm/transparent_hugepage/hpage_pmd_size");
+}
+
+bool is_numa_balancing_enabled(void)
+{
+	if (!test_sysfs_path("/proc/sys/kernel/numa_balancing"))
+		return false;
+	return get_sysfs_val("/proc/sys/kernel/numa_balancing") == 1;
+}
+
 size_t get_def_hugetlb_pagesz(void)
 {
 	char buf[64];
diff --git a/tools/testing/selftests/kvm/lib/x86/processor.c b/tools/testing/selftests/kvm/lib/x86/processor.c
index bd5a802fa7a5..a92dc1dad085 100644
--- a/tools/testing/selftests/kvm/lib/x86/processor.c
+++ b/tools/testing/selftests/kvm/lib/x86/processor.c
@@ -639,7 +639,7 @@ void kvm_arch_vm_post_create(struct kvm_vm *vm)
 	sync_global_to_guest(vm, host_cpu_is_amd);
 	sync_global_to_guest(vm, is_forced_emulation_enabled);
 
-	if (vm->type == KVM_X86_SEV_VM || vm->type == KVM_X86_SEV_ES_VM) {
+	if (is_sev_vm(vm)) {
 		struct kvm_sev_init init = { 0 };
 
 		vm_sev_ioctl(vm, KVM_SEV_INIT2, &init);
@@ -1156,7 +1156,7 @@ void kvm_get_cpu_address_width(unsigned int *pa_bits, unsigned int *va_bits)
 
 void kvm_init_vm_address_properties(struct kvm_vm *vm)
 {
-	if (vm->type == KVM_X86_SEV_VM || vm->type == KVM_X86_SEV_ES_VM) {
+	if (is_sev_vm(vm)) {
 		vm->arch.sev_fd = open_sev_dev_path_or_exit();
 		vm->arch.c_bit = BIT_ULL(this_cpu_property(X86_PROPERTY_SEV_C_BIT));
 		vm->gpa_tag_mask = vm->arch.c_bit;
diff --git a/tools/testing/selftests/kvm/lib/x86/sev.c b/tools/testing/selftests/kvm/lib/x86/sev.c
index e9535ee20b7f..c3a9838f4806 100644
--- a/tools/testing/selftests/kvm/lib/x86/sev.c
+++ b/tools/testing/selftests/kvm/lib/x86/sev.c
@@ -14,7 +14,8 @@
  * and find the first range, but that's correct because the condition
  * expression would cause us to quit the loop.
  */
-static void encrypt_region(struct kvm_vm *vm, struct userspace_mem_region *region)
+static void encrypt_region(struct kvm_vm *vm, struct userspace_mem_region *region,
+			   uint8_t page_type, bool private)
 {
 	const struct sparsebit *protected_phy_pages = region->protected_phy_pages;
 	const vm_paddr_t gpa_base = region->region.guest_phys_addr;
@@ -24,25 +25,35 @@ static void encrypt_region(struct kvm_vm *vm, struct userspace_mem_region *regio
 	if (!sparsebit_any_set(protected_phy_pages))
 		return;
 
-	sev_register_encrypted_memory(vm, region);
+	if (!is_sev_snp_vm(vm))
+		sev_register_encrypted_memory(vm, region);
 
 	sparsebit_for_each_set_range(protected_phy_pages, i, j) {
 		const uint64_t size = (j - i + 1) * vm->page_size;
 		const uint64_t offset = (i - lowest_page_in_region) * vm->page_size;
 
-		sev_launch_update_data(vm, gpa_base + offset, size);
+		if (private)
+			vm_mem_set_private(vm, gpa_base + offset, size);
+
+		if (is_sev_snp_vm(vm))
+			snp_launch_update_data(vm, gpa_base + offset,
+					       (uint64_t)addr_gpa2hva(vm, gpa_base + offset),
+					       size, page_type);
+		else
+			sev_launch_update_data(vm, gpa_base + offset, size);
+
 	}
 }
 
 void sev_vm_init(struct kvm_vm *vm)
 {
 	if (vm->type == KVM_X86_DEFAULT_VM) {
-		assert(vm->arch.sev_fd == -1);
+		TEST_ASSERT_EQ(vm->arch.sev_fd, -1);
 		vm->arch.sev_fd = open_sev_dev_path_or_exit();
 		vm_sev_ioctl(vm, KVM_SEV_INIT, NULL);
 	} else {
 		struct kvm_sev_init init = { 0 };
-		assert(vm->type == KVM_X86_SEV_VM);
+		TEST_ASSERT_EQ(vm->type, KVM_X86_SEV_VM);
 		vm_sev_ioctl(vm, KVM_SEV_INIT2, &init);
 	}
 }
@@ -50,16 +61,24 @@ void sev_vm_init(struct kvm_vm *vm)
 void sev_es_vm_init(struct kvm_vm *vm)
 {
 	if (vm->type == KVM_X86_DEFAULT_VM) {
-		assert(vm->arch.sev_fd == -1);
+		TEST_ASSERT_EQ(vm->arch.sev_fd, -1);
 		vm->arch.sev_fd = open_sev_dev_path_or_exit();
 		vm_sev_ioctl(vm, KVM_SEV_ES_INIT, NULL);
 	} else {
 		struct kvm_sev_init init = { 0 };
-		assert(vm->type == KVM_X86_SEV_ES_VM);
+		TEST_ASSERT_EQ(vm->type, KVM_X86_SEV_ES_VM);
 		vm_sev_ioctl(vm, KVM_SEV_INIT2, &init);
 	}
 }
 
+void snp_vm_init(struct kvm_vm *vm)
+{
+	struct kvm_sev_init init = { 0 };
+
+	TEST_ASSERT_EQ(vm->type, KVM_X86_SNP_VM);
+	vm_sev_ioctl(vm, KVM_SEV_INIT2, &init);
+}
+
 void sev_vm_launch(struct kvm_vm *vm, uint32_t policy)
 {
 	struct kvm_sev_launch_start launch_start = {
@@ -76,7 +95,7 @@ void sev_vm_launch(struct kvm_vm *vm, uint32_t policy)
 	TEST_ASSERT_EQ(status.state, SEV_GUEST_STATE_LAUNCH_UPDATE);
 
 	hash_for_each(vm->regions.slot_hash, ctr, region, slot_node)
-		encrypt_region(vm, region);
+		encrypt_region(vm, region, KVM_SEV_PAGE_TYPE_INVALID, false);
 
 	if (policy & SEV_POLICY_ES)
 		vm_sev_ioctl(vm, KVM_SEV_LAUNCH_UPDATE_VMSA, NULL);
@@ -112,6 +131,33 @@ void sev_vm_launch_finish(struct kvm_vm *vm)
 	TEST_ASSERT_EQ(status.state, SEV_GUEST_STATE_RUNNING);
 }
 
+void snp_vm_launch_start(struct kvm_vm *vm, uint64_t policy)
+{
+	struct kvm_sev_snp_launch_start launch_start = {
+		.policy = policy,
+	};
+
+	vm_sev_ioctl(vm, KVM_SEV_SNP_LAUNCH_START, &launch_start);
+}
+
+void snp_vm_launch_update(struct kvm_vm *vm)
+{
+	struct userspace_mem_region *region;
+	int ctr;
+
+	hash_for_each(vm->regions.slot_hash, ctr, region, slot_node)
+		encrypt_region(vm, region, KVM_SEV_SNP_PAGE_TYPE_NORMAL, true);
+
+	vm->arch.is_pt_protected = true;
+}
+
+void snp_vm_launch_finish(struct kvm_vm *vm)
+{
+	struct kvm_sev_snp_launch_finish launch_finish = { 0 };
+
+	vm_sev_ioctl(vm, KVM_SEV_SNP_LAUNCH_FINISH, &launch_finish);
+}
+
 struct kvm_vm *vm_sev_create_with_one_vcpu(uint32_t type, void *guest_code,
 					   struct kvm_vcpu **cpu)
 {
@@ -128,8 +174,20 @@ struct kvm_vm *vm_sev_create_with_one_vcpu(uint32_t type, void *guest_code,
 	return vm;
 }
 
-void vm_sev_launch(struct kvm_vm *vm, uint32_t policy, uint8_t *measurement)
+void vm_sev_launch(struct kvm_vm *vm, uint64_t policy, uint8_t *measurement)
 {
+	if (is_sev_snp_vm(vm)) {
+		vm_enable_cap(vm, KVM_CAP_EXIT_HYPERCALL, BIT(KVM_HC_MAP_GPA_RANGE));
+
+		snp_vm_launch_start(vm, policy);
+
+		snp_vm_launch_update(vm);
+
+		snp_vm_launch_finish(vm);
+
+		return;
+	}
+
 	sev_vm_launch(vm, policy);
 
 	if (!measurement)
diff --git a/tools/testing/selftests/kvm/x86/fastops_test.c b/tools/testing/selftests/kvm/x86/fastops_test.c
new file mode 100644
index 000000000000..2ac89d6c1e46
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86/fastops_test.c
@@ -0,0 +1,165 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include "test_util.h"
+#include "kvm_util.h"
+#include "processor.h"
+
+/*
+ * Execute a fastop() instruction, with or without forced emulation.  BT bit 0
+ * to set RFLAGS.CF based on whether or not the input is even or odd, so that
+ * instructions like ADC and SBB are deterministic.
+ */
+#define guest_execute_fastop_1(FEP, insn, __val, __flags)				\
+({											\
+	__asm__ __volatile__("bt $0, %[val]\n\t"					\
+			     FEP insn " %[val]\n\t"					\
+			     "pushfq\n\t"						\
+			     "pop %[flags]\n\t"						\
+			     : [val]"+r"(__val), [flags]"=r"(__flags)			\
+			     : : "cc", "memory");					\
+})
+
+#define guest_test_fastop_1(insn, type_t, __val)					\
+({											\
+	type_t val = __val, ex_val = __val, input = __val;				\
+	uint64_t flags, ex_flags;							\
+											\
+	guest_execute_fastop_1("", insn, ex_val, ex_flags);				\
+	guest_execute_fastop_1(KVM_FEP, insn, val, flags);				\
+											\
+	__GUEST_ASSERT(val == ex_val,							\
+		       "Wanted 0x%lx for '%s 0x%lx', got 0x%lx",			\
+		       (uint64_t)ex_val, insn, (uint64_t)input, (uint64_t)val);		\
+	__GUEST_ASSERT(flags == ex_flags,						\
+			"Wanted flags 0x%lx for '%s 0x%lx', got 0x%lx",			\
+			ex_flags, insn, (uint64_t)input, flags);			\
+})
+
+#define guest_execute_fastop_2(FEP, insn, __input, __output, __flags)			\
+({											\
+	__asm__ __volatile__("bt $0, %[output]\n\t"					\
+			     FEP insn " %[input], %[output]\n\t"			\
+			     "pushfq\n\t"						\
+			     "pop %[flags]\n\t"						\
+			     : [output]"+r"(__output), [flags]"=r"(__flags)		\
+			     : [input]"r"(__input) : "cc", "memory");			\
+})
+
+#define guest_test_fastop_2(insn, type_t, __val1, __val2)				\
+({											\
+	type_t input = __val1, input2 = __val2, output = __val2, ex_output = __val2;	\
+	uint64_t flags, ex_flags;							\
+											\
+	guest_execute_fastop_2("", insn, input, ex_output, ex_flags);			\
+	guest_execute_fastop_2(KVM_FEP, insn, input, output, flags);			\
+											\
+	__GUEST_ASSERT(output == ex_output,						\
+		       "Wanted 0x%lx for '%s 0x%lx 0x%lx', got 0x%lx",			\
+		       (uint64_t)ex_output, insn, (uint64_t)input,			\
+		       (uint64_t)input2, (uint64_t)output);				\
+	__GUEST_ASSERT(flags == ex_flags,						\
+			"Wanted flags 0x%lx for '%s 0x%lx, 0x%lx', got 0x%lx",		\
+			ex_flags, insn, (uint64_t)input, (uint64_t)input2, flags);	\
+})
+
+#define guest_execute_fastop_cl(FEP, insn, __shift, __output, __flags)			\
+({											\
+	__asm__ __volatile__("bt $0, %[output]\n\t"					\
+			     FEP insn " %%cl, %[output]\n\t"				\
+			     "pushfq\n\t"						\
+			     "pop %[flags]\n\t"						\
+			     : [output]"+r"(__output), [flags]"=r"(__flags)		\
+			     : "c"(__shift) : "cc", "memory");				\
+})
+
+#define guest_test_fastop_cl(insn, type_t, __val1, __val2)				\
+({											\
+	type_t output = __val2, ex_output = __val2, input = __val2;			\
+	uint8_t shift = __val1;								\
+	uint64_t flags, ex_flags;							\
+											\
+	guest_execute_fastop_cl("", insn, shift, ex_output, ex_flags);			\
+	guest_execute_fastop_cl(KVM_FEP, insn, shift, output, flags);			\
+											\
+	__GUEST_ASSERT(output == ex_output,						\
+		       "Wanted 0x%lx for '%s 0x%x, 0x%lx', got 0x%lx",			\
+		       (uint64_t)ex_output, insn, shift, (uint64_t)input,		\
+		       (uint64_t)output);						\
+	__GUEST_ASSERT(flags == ex_flags,						\
+			"Wanted flags 0x%lx for '%s 0x%x, 0x%lx', got 0x%lx",		\
+			ex_flags, insn, shift, (uint64_t)input, flags);			\
+})
+
+static const uint64_t vals[] = {
+	0,
+	1,
+	2,
+	4,
+	7,
+	0x5555555555555555,
+	0xaaaaaaaaaaaaaaaa,
+	0xfefefefefefefefe,
+	0xffffffffffffffff,
+};
+
+#define guest_test_fastops(type_t, suffix)						\
+do {											\
+	int i, j;									\
+											\
+	for (i = 0; i < ARRAY_SIZE(vals); i++) {					\
+		guest_test_fastop_1("dec" suffix, type_t, vals[i]);			\
+		guest_test_fastop_1("inc" suffix, type_t, vals[i]);			\
+		guest_test_fastop_1("neg" suffix, type_t, vals[i]);			\
+		guest_test_fastop_1("not" suffix, type_t, vals[i]);			\
+											\
+		for (j = 0; j < ARRAY_SIZE(vals); j++) {				\
+			guest_test_fastop_2("add" suffix, type_t, vals[i], vals[j]);	\
+			guest_test_fastop_2("adc" suffix, type_t, vals[i], vals[j]);	\
+			guest_test_fastop_2("and" suffix, type_t, vals[i], vals[j]);	\
+			guest_test_fastop_2("bsf" suffix, type_t, vals[i], vals[j]);	\
+			guest_test_fastop_2("bsr" suffix, type_t, vals[i], vals[j]);	\
+			guest_test_fastop_2("bt" suffix, type_t, vals[i], vals[j]);	\
+			guest_test_fastop_2("btc" suffix, type_t, vals[i], vals[j]);	\
+			guest_test_fastop_2("btr" suffix, type_t, vals[i], vals[j]);	\
+			guest_test_fastop_2("bts" suffix, type_t, vals[i], vals[j]);	\
+			guest_test_fastop_2("cmp" suffix, type_t, vals[i], vals[j]);	\
+			guest_test_fastop_2("imul" suffix, type_t, vals[i], vals[j]);	\
+			guest_test_fastop_2("or" suffix, type_t, vals[i], vals[j]);	\
+			guest_test_fastop_2("sbb" suffix, type_t, vals[i], vals[j]);	\
+			guest_test_fastop_2("sub" suffix, type_t, vals[i], vals[j]);	\
+			guest_test_fastop_2("test" suffix, type_t, vals[i], vals[j]);	\
+			guest_test_fastop_2("xor" suffix, type_t, vals[i], vals[j]);	\
+											\
+			guest_test_fastop_cl("rol" suffix, type_t, vals[i], vals[j]);	\
+			guest_test_fastop_cl("ror" suffix, type_t, vals[i], vals[j]);	\
+			guest_test_fastop_cl("rcl" suffix, type_t, vals[i], vals[j]);	\
+			guest_test_fastop_cl("rcr" suffix, type_t, vals[i], vals[j]);	\
+			guest_test_fastop_cl("sar" suffix, type_t, vals[i], vals[j]);	\
+			guest_test_fastop_cl("shl" suffix, type_t, vals[i], vals[j]);	\
+			guest_test_fastop_cl("shr" suffix, type_t, vals[i], vals[j]);	\
+		}									\
+	}										\
+} while (0)
+
+static void guest_code(void)
+{
+	guest_test_fastops(uint16_t, "w");
+	guest_test_fastops(uint32_t, "l");
+	guest_test_fastops(uint64_t, "q");
+
+	GUEST_DONE();
+}
+
+int main(int argc, char *argv[])
+{
+	struct kvm_vcpu *vcpu;
+	struct kvm_vm *vm;
+
+	TEST_REQUIRE(is_forced_emulation_enabled);
+
+	vm = vm_create_with_one_vcpu(&vcpu, guest_code);
+
+	vcpu_run(vcpu);
+	TEST_ASSERT_EQ(get_ucall(vcpu, NULL), UCALL_DONE);
+
+	kvm_vm_free(vm);
+}
diff --git a/tools/testing/selftests/kvm/x86/hyperv_cpuid.c b/tools/testing/selftests/kvm/x86/hyperv_cpuid.c
index 4e920705681a..c863a689aa98 100644
--- a/tools/testing/selftests/kvm/x86/hyperv_cpuid.c
+++ b/tools/testing/selftests/kvm/x86/hyperv_cpuid.c
@@ -22,25 +22,6 @@ static void guest_code(void)
 {
 }
 
-static bool smt_possible(void)
-{
-	char buf[16];
-	FILE *f;
-	bool res = true;
-
-	f = fopen("/sys/devices/system/cpu/smt/control", "r");
-	if (f) {
-		if (fread(buf, sizeof(*buf), sizeof(buf), f) > 0) {
-			if (!strncmp(buf, "forceoff", 8) ||
-			    !strncmp(buf, "notsupported", 12))
-				res = false;
-		}
-		fclose(f);
-	}
-
-	return res;
-}
-
 static void test_hv_cpuid(struct kvm_vcpu *vcpu, bool evmcs_expected)
 {
 	const bool has_irqchip = !vcpu || vcpu->vm->has_irqchip;
@@ -93,7 +74,7 @@ static void test_hv_cpuid(struct kvm_vcpu *vcpu, bool evmcs_expected)
 		case 0x40000004:
 			test_val = entry->eax & (1UL << 18);
 
-			TEST_ASSERT(!!test_val == !smt_possible(),
+			TEST_ASSERT(!!test_val == !is_smt_possible(),
 				    "NoNonArchitecturalCoreSharing bit"
 				    " doesn't reflect SMT setting");
 
diff --git a/tools/testing/selftests/kvm/x86/kvm_buslock_test.c b/tools/testing/selftests/kvm/x86/kvm_buslock_test.c
new file mode 100644
index 000000000000..d88500c118eb
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86/kvm_buslock_test.c
@@ -0,0 +1,135 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2024 Advanced Micro Devices, Inc.
+ */
+#include <linux/atomic.h>
+
+#include "kvm_util.h"
+#include "processor.h"
+#include "svm_util.h"
+#include "vmx.h"
+#include "test_util.h"
+
+#define NR_BUS_LOCKS_PER_LEVEL 100
+#define CACHE_LINE_SIZE		64
+
+/*
+ * To generate a bus lock, carve out a buffer that precisely occupies two cache
+ * lines and perform an atomic access that splits the two lines.
+ */
+static u8 buffer[CACHE_LINE_SIZE * 2] __aligned(CACHE_LINE_SIZE);
+static atomic_t *val = (void *)&buffer[CACHE_LINE_SIZE - (sizeof(*val) / 2)];
+
+static void guest_generate_buslocks(void)
+{
+	for (int i = 0; i < NR_BUS_LOCKS_PER_LEVEL; i++)
+		atomic_inc(val);
+}
+
+#define L2_GUEST_STACK_SIZE	64
+
+static void l2_guest_code(void)
+{
+	guest_generate_buslocks();
+	GUEST_DONE();
+}
+
+static void l1_svm_code(struct svm_test_data *svm)
+{
+	unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE];
+	struct vmcb *vmcb = svm->vmcb;
+
+	generic_svm_setup(svm, l2_guest_code, &l2_guest_stack[L2_GUEST_STACK_SIZE]);
+	run_guest(vmcb, svm->vmcb_gpa);
+}
+
+static void l1_vmx_code(struct vmx_pages *vmx)
+{
+	unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE];
+
+	GUEST_ASSERT_EQ(prepare_for_vmx_operation(vmx), true);
+	GUEST_ASSERT_EQ(load_vmcs(vmx), true);
+
+	prepare_vmcs(vmx, NULL, &l2_guest_stack[L2_GUEST_STACK_SIZE]);
+
+	GUEST_ASSERT(!vmwrite(GUEST_RIP, (u64)l2_guest_code));
+	GUEST_ASSERT(!vmlaunch());
+}
+
+static void guest_code(void *test_data)
+{
+	guest_generate_buslocks();
+
+	if (this_cpu_has(X86_FEATURE_SVM))
+		l1_svm_code(test_data);
+	else if (this_cpu_has(X86_FEATURE_VMX))
+		l1_vmx_code(test_data);
+	else
+		GUEST_DONE();
+
+	TEST_FAIL("L2 should have signaled 'done'");
+}
+
+int main(int argc, char *argv[])
+{
+	const bool has_nested = kvm_cpu_has(X86_FEATURE_SVM) || kvm_cpu_has(X86_FEATURE_VMX);
+	vm_vaddr_t nested_test_data_gva;
+	struct kvm_vcpu *vcpu;
+	struct kvm_run *run;
+	struct kvm_vm *vm;
+	int i, bus_locks = 0;
+
+	TEST_REQUIRE(kvm_has_cap(KVM_CAP_X86_BUS_LOCK_EXIT));
+
+	vm = vm_create(1);
+	vm_enable_cap(vm, KVM_CAP_X86_BUS_LOCK_EXIT, KVM_BUS_LOCK_DETECTION_EXIT);
+	vcpu = vm_vcpu_add(vm, 0, guest_code);
+
+	if (kvm_cpu_has(X86_FEATURE_SVM))
+		vcpu_alloc_svm(vm, &nested_test_data_gva);
+	else
+		vcpu_alloc_vmx(vm, &nested_test_data_gva);
+
+	vcpu_args_set(vcpu, 1, nested_test_data_gva);
+
+	run = vcpu->run;
+
+	for (i = 0; i <= NR_BUS_LOCKS_PER_LEVEL * (1 + has_nested); i++) {
+		struct ucall uc;
+
+		vcpu_run(vcpu);
+
+		if (run->exit_reason == KVM_EXIT_IO) {
+			switch (get_ucall(vcpu, &uc)) {
+			case UCALL_ABORT:
+				REPORT_GUEST_ASSERT(uc);
+				goto done;
+			case UCALL_SYNC:
+				continue;
+			case UCALL_DONE:
+				goto done;
+			default:
+				TEST_FAIL("Unknown ucall 0x%lx.", uc.cmd);
+			}
+		}
+
+		TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_X86_BUS_LOCK);
+
+		/*
+		 * Verify the counter is actually getting incremented, e.g. that
+		 * KVM isn't skipping the instruction.  On Intel, the exit is
+		 * trap-like, i.e. the counter should already have been
+		 * incremented.  On AMD, it's fault-like, i.e. the counter will
+		 * be incremented when the guest re-executes the instruction.
+		 */
+		sync_global_from_guest(vm, *val);
+		TEST_ASSERT_EQ(atomic_read(val), bus_locks + host_cpu_is_intel);
+
+		bus_locks++;
+	}
+	TEST_FAIL("Didn't receive UCALL_DONE, took %u bus lock exits\n", bus_locks);
+done:
+	TEST_ASSERT_EQ(i, bus_locks);
+	kvm_vm_free(vm);
+	return 0;
+}
diff --git a/tools/testing/selftests/kvm/x86/sev_init2_tests.c b/tools/testing/selftests/kvm/x86/sev_init2_tests.c
index 3fb967f40c6a..b238615196ad 100644
--- a/tools/testing/selftests/kvm/x86/sev_init2_tests.c
+++ b/tools/testing/selftests/kvm/x86/sev_init2_tests.c
@@ -28,6 +28,7 @@
 int kvm_fd;
 u64 supported_vmsa_features;
 bool have_sev_es;
+bool have_snp;
 
 static int __sev_ioctl(int vm_fd, int cmd_id, void *data)
 {
@@ -83,6 +84,9 @@ void test_vm_types(void)
 	if (have_sev_es)
 		test_init2(KVM_X86_SEV_ES_VM, &(struct kvm_sev_init){});
 
+	if (have_snp)
+		test_init2(KVM_X86_SNP_VM, &(struct kvm_sev_init){});
+
 	test_init2_invalid(0, &(struct kvm_sev_init){},
 			   "VM type is KVM_X86_DEFAULT_VM");
 	if (kvm_check_cap(KVM_CAP_VM_TYPES) & BIT(KVM_X86_SW_PROTECTED_VM))
@@ -138,15 +142,24 @@ int main(int argc, char *argv[])
 		    "sev-es: KVM_CAP_VM_TYPES (%x) does not match cpuid (checking %x)",
 		    kvm_check_cap(KVM_CAP_VM_TYPES), 1 << KVM_X86_SEV_ES_VM);
 
+	have_snp = kvm_cpu_has(X86_FEATURE_SEV_SNP);
+	TEST_ASSERT(have_snp == !!(kvm_check_cap(KVM_CAP_VM_TYPES) & BIT(KVM_X86_SNP_VM)),
+		    "sev-snp: KVM_CAP_VM_TYPES (%x) indicates SNP support (bit %d), but CPUID does not",
+		    kvm_check_cap(KVM_CAP_VM_TYPES), KVM_X86_SNP_VM);
+
 	test_vm_types();
 
 	test_flags(KVM_X86_SEV_VM);
 	if (have_sev_es)
 		test_flags(KVM_X86_SEV_ES_VM);
+	if (have_snp)
+		test_flags(KVM_X86_SNP_VM);
 
 	test_features(KVM_X86_SEV_VM, 0);
 	if (have_sev_es)
 		test_features(KVM_X86_SEV_ES_VM, supported_vmsa_features);
+	if (have_snp)
+		test_features(KVM_X86_SNP_VM, supported_vmsa_features);
 
 	return 0;
 }
diff --git a/tools/testing/selftests/kvm/x86/sev_smoke_test.c b/tools/testing/selftests/kvm/x86/sev_smoke_test.c
index d97816dc476a..77256c89bb8d 100644
--- a/tools/testing/selftests/kvm/x86/sev_smoke_test.c
+++ b/tools/testing/selftests/kvm/x86/sev_smoke_test.c
@@ -16,6 +16,18 @@
 
 #define XFEATURE_MASK_X87_AVX (XFEATURE_MASK_FP | XFEATURE_MASK_SSE | XFEATURE_MASK_YMM)
 
+static void guest_snp_code(void)
+{
+	uint64_t sev_msr = rdmsr(MSR_AMD64_SEV);
+
+	GUEST_ASSERT(sev_msr & MSR_AMD64_SEV_ENABLED);
+	GUEST_ASSERT(sev_msr & MSR_AMD64_SEV_ES_ENABLED);
+	GUEST_ASSERT(sev_msr & MSR_AMD64_SEV_SNP_ENABLED);
+
+	wrmsr(MSR_AMD64_SEV_ES_GHCB, GHCB_MSR_TERM_REQ);
+	vmgexit();
+}
+
 static void guest_sev_es_code(void)
 {
 	/* TODO: Check CPUID after GHCB-based hypercall support is added. */
@@ -27,7 +39,7 @@ static void guest_sev_es_code(void)
 	 * force "termination" to signal "done" via the GHCB MSR protocol.
 	 */
 	wrmsr(MSR_AMD64_SEV_ES_GHCB, GHCB_MSR_TERM_REQ);
-	__asm__ __volatile__("rep; vmmcall");
+	vmgexit();
 }
 
 static void guest_sev_code(void)
@@ -62,7 +74,7 @@ static void compare_xsave(u8 *from_host, u8 *from_guest)
 		abort();
 }
 
-static void test_sync_vmsa(uint32_t policy)
+static void test_sync_vmsa(uint32_t type, uint64_t policy)
 {
 	struct kvm_vcpu *vcpu;
 	struct kvm_vm *vm;
@@ -72,7 +84,7 @@ static void test_sync_vmsa(uint32_t policy)
 	double x87val = M_PI;
 	struct kvm_xsave __attribute__((aligned(64))) xsave = { 0 };
 
-	vm = vm_sev_create_with_one_vcpu(KVM_X86_SEV_ES_VM, guest_code_xsave, &vcpu);
+	vm = vm_sev_create_with_one_vcpu(type, guest_code_xsave, &vcpu);
 	gva = vm_vaddr_alloc_shared(vm, PAGE_SIZE, KVM_UTIL_MIN_VADDR,
 				    MEM_REGION_TEST_DATA);
 	hva = addr_gva2hva(vm, gva);
@@ -89,7 +101,7 @@ static void test_sync_vmsa(uint32_t policy)
 	    : "ymm4", "st", "st(1)", "st(2)", "st(3)", "st(4)", "st(5)", "st(6)", "st(7)");
 	vcpu_xsave_set(vcpu, &xsave);
 
-	vm_sev_launch(vm, SEV_POLICY_ES | policy, NULL);
+	vm_sev_launch(vm, policy, NULL);
 
 	/* This page is shared, so make it decrypted.  */
 	memset(hva, 0, 4096);
@@ -108,14 +120,12 @@ static void test_sync_vmsa(uint32_t policy)
 	kvm_vm_free(vm);
 }
 
-static void test_sev(void *guest_code, uint64_t policy)
+static void test_sev(void *guest_code, uint32_t type, uint64_t policy)
 {
 	struct kvm_vcpu *vcpu;
 	struct kvm_vm *vm;
 	struct ucall uc;
 
-	uint32_t type = policy & SEV_POLICY_ES ? KVM_X86_SEV_ES_VM : KVM_X86_SEV_VM;
-
 	vm = vm_sev_create_with_one_vcpu(type, guest_code, &vcpu);
 
 	/* TODO: Validate the measurement is as expected. */
@@ -124,7 +134,7 @@ static void test_sev(void *guest_code, uint64_t policy)
 	for (;;) {
 		vcpu_run(vcpu);
 
-		if (policy & SEV_POLICY_ES) {
+		if (is_sev_es_vm(vm)) {
 			TEST_ASSERT(vcpu->run->exit_reason == KVM_EXIT_SYSTEM_EVENT,
 				    "Wanted SYSTEM_EVENT, got %s",
 				    exit_reason_str(vcpu->run->exit_reason));
@@ -161,16 +171,14 @@ static void guest_shutdown_code(void)
 	__asm__ __volatile__("ud2");
 }
 
-static void test_sev_es_shutdown(void)
+static void test_sev_shutdown(uint32_t type, uint64_t policy)
 {
 	struct kvm_vcpu *vcpu;
 	struct kvm_vm *vm;
 
-	uint32_t type = KVM_X86_SEV_ES_VM;
-
 	vm = vm_sev_create_with_one_vcpu(type, guest_shutdown_code, &vcpu);
 
-	vm_sev_launch(vm, SEV_POLICY_ES, NULL);
+	vm_sev_launch(vm, policy, NULL);
 
 	vcpu_run(vcpu);
 	TEST_ASSERT(vcpu->run->exit_reason == KVM_EXIT_SHUTDOWN,
@@ -180,27 +188,42 @@ static void test_sev_es_shutdown(void)
 	kvm_vm_free(vm);
 }
 
-int main(int argc, char *argv[])
+static void test_sev_smoke(void *guest, uint32_t type, uint64_t policy)
 {
 	const u64 xf_mask = XFEATURE_MASK_X87_AVX;
 
-	TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_SEV));
-
-	test_sev(guest_sev_code, SEV_POLICY_NO_DBG);
-	test_sev(guest_sev_code, 0);
+	if (type == KVM_X86_SNP_VM)
+		test_sev(guest, type, policy | SNP_POLICY_DBG);
+	else
+		test_sev(guest, type, policy | SEV_POLICY_NO_DBG);
+	test_sev(guest, type, policy);
 
-	if (kvm_cpu_has(X86_FEATURE_SEV_ES)) {
-		test_sev(guest_sev_es_code, SEV_POLICY_ES | SEV_POLICY_NO_DBG);
-		test_sev(guest_sev_es_code, SEV_POLICY_ES);
+	if (type == KVM_X86_SEV_VM)
+		return;
 
-		test_sev_es_shutdown();
+	test_sev_shutdown(type, policy);
 
-		if (kvm_has_cap(KVM_CAP_XCRS) &&
-		    (xgetbv(0) & kvm_cpu_supported_xcr0() & xf_mask) == xf_mask) {
-			test_sync_vmsa(0);
-			test_sync_vmsa(SEV_POLICY_NO_DBG);
-		}
+	if (kvm_has_cap(KVM_CAP_XCRS) &&
+	    (xgetbv(0) & kvm_cpu_supported_xcr0() & xf_mask) == xf_mask) {
+		test_sync_vmsa(type, policy);
+		if (type == KVM_X86_SNP_VM)
+			test_sync_vmsa(type, policy | SNP_POLICY_DBG);
+		else
+			test_sync_vmsa(type, policy | SEV_POLICY_NO_DBG);
 	}
+}
+
+int main(int argc, char *argv[])
+{
+	TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_SEV));
+
+	test_sev_smoke(guest_sev_code, KVM_X86_SEV_VM, 0);
+
+	if (kvm_cpu_has(X86_FEATURE_SEV_ES))
+		test_sev_smoke(guest_sev_es_code, KVM_X86_SEV_ES_VM, SEV_POLICY_ES);
+
+	if (kvm_cpu_has(X86_FEATURE_SEV_SNP))
+		test_sev_smoke(guest_snp_code, KVM_X86_SNP_VM, snp_default_policy());
 
 	return 0;
 }