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

Pull kvm updates from Paolo Bonzini:
 "ARM64:

   - Eager page splitting optimization for dirty logging, optionally
     allowing for a VM to avoid the cost of hugepage splitting in the
     stage-2 fault path.

   - Arm FF-A proxy for pKVM, allowing a pKVM host to safely interact
     with services that live in the Secure world. pKVM intervenes on
     FF-A calls to guarantee the host doesn't misuse memory donated to
     the hyp or a pKVM guest.

   - Support for running the split hypervisor with VHE enabled, known as
     'hVHE' mode. This is extremely useful for testing the split
     hypervisor on VHE-only systems, and paves the way for new use cases
     that depend on having two TTBRs available at EL2.

   - Generalized framework for configurable ID registers from userspace.
     KVM/arm64 currently prevents arbitrary CPU feature set
     configuration from userspace, but the intent is to relax this
     limitation and allow userspace to select a feature set consistent
     with the CPU.

   - Enable the use of Branch Target Identification (FEAT_BTI) in the
     hypervisor.

   - Use a separate set of pointer authentication keys for the
     hypervisor when running in protected mode, as the host is untrusted
     at runtime.

   - Ensure timer IRQs are consistently released in the init failure
     paths.

   - Avoid trapping CTR_EL0 on systems with Enhanced Virtualization
     Traps (FEAT_EVT), as it is a register commonly read from userspace.

   - Erratum workaround for the upcoming AmpereOne part, which has
     broken hardware A/D state management.

  RISC-V:

   - Redirect AMO load/store misaligned traps to KVM guest

   - Trap-n-emulate AIA in-kernel irqchip for KVM guest

   - Svnapot support for KVM Guest

  s390:

   - New uvdevice secret API

   - CMM selftest and fixes

   - fix racy access to target CPU for diag 9c

  x86:

   - Fix missing/incorrect #GP checks on ENCLS

   - Use standard mmu_notifier hooks for handling APIC access page

   - Drop now unnecessary TR/TSS load after VM-Exit on AMD

   - Print more descriptive information about the status of SEV and
     SEV-ES during module load

   - Add a test for splitting and reconstituting hugepages during and
     after dirty logging

   - Add support for CPU pinning in demand paging test

   - Add support for AMD PerfMonV2, with a variety of cleanups and minor
     fixes included along the way

   - Add a "nx_huge_pages=never" option to effectively avoid creating NX
     hugepage recovery threads (because nx_huge_pages=off can be toggled
     at runtime)

   - Move handling of PAT out of MTRR code and dedup SVM+VMX code

   - Fix output of PIC poll command emulation when there's an interrupt

   - Add a maintainer's handbook to document KVM x86 processes,
     preferred coding style, testing expectations, etc.

   - Misc cleanups, fixes and comments

  Generic:

   - Miscellaneous bugfixes and cleanups

  Selftests:

   - Generate dependency files so that partial rebuilds work as
     expected"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (153 commits)
  Documentation/process: Add a maintainer handbook for KVM x86
  Documentation/process: Add a label for the tip tree handbook's coding style
  KVM: arm64: Fix misuse of KVM_ARM_VCPU_POWER_OFF bit index
  RISC-V: KVM: Remove unneeded semicolon
  RISC-V: KVM: Allow Svnapot extension for Guest/VM
  riscv: kvm: define vcpu_sbi_ext_pmu in header
  RISC-V: KVM: Expose IMSIC registers as attributes of AIA irqchip
  RISC-V: KVM: Add in-kernel virtualization of AIA IMSIC
  RISC-V: KVM: Expose APLIC registers as attributes of AIA irqchip
  RISC-V: KVM: Add in-kernel emulation of AIA APLIC
  RISC-V: KVM: Implement device interface for AIA irqchip
  RISC-V: KVM: Skeletal in-kernel AIA irqchip support
  RISC-V: KVM: Set kvm_riscv_aia_nr_hgei to zero
  RISC-V: KVM: Add APLIC related defines
  RISC-V: KVM: Add IMSIC related defines
  RISC-V: KVM: Implement guest external interrupt line management
  KVM: x86: Remove PRIx* definitions as they are solely for user space
  s390/uv: Update query for secret-UVCs
  s390/uv: replace scnprintf with sysfs_emit
  s390/uvdevice: Add 'Lock Secret Store' UVC
  ...

13 files changed, 1138 insertions, 118 deletions

diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index 4761b768b773..c692cc86e7da 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -61,6 +61,7 @@ TEST_PROGS_x86_64 += x86_64/nx_huge_pages_test.sh
 # Compiled test targets
 TEST_GEN_PROGS_x86_64 = x86_64/cpuid_test
 TEST_GEN_PROGS_x86_64 += x86_64/cr4_cpuid_sync_test
+TEST_GEN_PROGS_x86_64 += x86_64/dirty_log_page_splitting_test
 TEST_GEN_PROGS_x86_64 += x86_64/get_msr_index_features
 TEST_GEN_PROGS_x86_64 += x86_64/exit_on_emulation_failure_test
 TEST_GEN_PROGS_x86_64 += x86_64/fix_hypercall_test
@@ -164,6 +165,7 @@ TEST_GEN_PROGS_s390x = s390x/memop
 TEST_GEN_PROGS_s390x += s390x/resets
 TEST_GEN_PROGS_s390x += s390x/sync_regs_test
 TEST_GEN_PROGS_s390x += s390x/tprot
+TEST_GEN_PROGS_s390x += s390x/cmma_test
 TEST_GEN_PROGS_s390x += demand_paging_test
 TEST_GEN_PROGS_s390x += dirty_log_test
 TEST_GEN_PROGS_s390x += kvm_create_max_vcpus
@@ -184,6 +186,8 @@ TEST_GEN_PROGS += $(TEST_GEN_PROGS_$(ARCH_DIR))
 TEST_GEN_PROGS_EXTENDED += $(TEST_GEN_PROGS_EXTENDED_$(ARCH_DIR))
 LIBKVM += $(LIBKVM_$(ARCH_DIR))
 
+OVERRIDE_TARGETS = 1
+
 # lib.mak defines $(OUTPUT), prepends $(OUTPUT)/ to $(TEST_GEN_PROGS), and most
 # importantly defines, i.e. overwrites, $(CC) (unless `make -e` or `make CC=`,
 # which causes the environment variable to override the makefile).
@@ -198,7 +202,7 @@ else
 LINUX_TOOL_ARCH_INCLUDE = $(top_srcdir)/tools/arch/$(ARCH)/include
 endif
 CFLAGS += -Wall -Wstrict-prototypes -Wuninitialized -O2 -g -std=gnu99 \
-	-Wno-gnu-variable-sized-type-not-at-end \
+	-Wno-gnu-variable-sized-type-not-at-end -MD\
 	-fno-builtin-memcmp -fno-builtin-memcpy -fno-builtin-memset \
 	-fno-stack-protector -fno-PIE -I$(LINUX_TOOL_INCLUDE) \
 	-I$(LINUX_TOOL_ARCH_INCLUDE) -I$(LINUX_HDR_PATH) -Iinclude \
@@ -225,7 +229,18 @@ 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)
 
-EXTRA_CLEAN += $(LIBKVM_OBJS) cscope.*
+TEST_GEN_OBJ = $(patsubst %, %.o, $(TEST_GEN_PROGS))
+TEST_GEN_OBJ += $(patsubst %, %.o, $(TEST_GEN_PROGS_EXTENDED))
+TEST_DEP_FILES = $(patsubst %.o, %.d, $(TEST_GEN_OBJ))
+TEST_DEP_FILES += $(patsubst %.o, %.d, $(LIBKVM_OBJS))
+-include $(TEST_DEP_FILES)
+
+$(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED): %: %.o
+	$(CC) $(CFLAGS) $(CPPFLAGS) $(LDFLAGS) $(TARGET_ARCH) $< $(LIBKVM_OBJS) $(LDLIBS) -o $@
+$(TEST_GEN_OBJ): $(OUTPUT)/%.o: %.c
+	$(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c $< -o $@
+
+EXTRA_CLEAN += $(LIBKVM_OBJS) $(TEST_DEP_FILES) $(TEST_GEN_OBJ) cscope.*
 
 x := $(shell mkdir -p $(sort $(dir $(LIBKVM_C_OBJ) $(LIBKVM_S_OBJ))))
 $(LIBKVM_C_OBJ): $(OUTPUT)/%.o: %.c
diff --git a/tools/testing/selftests/kvm/demand_paging_test.c b/tools/testing/selftests/kvm/demand_paging_test.c
index 2439c4043fed..09c116a82a84 100644
--- a/tools/testing/selftests/kvm/demand_paging_test.c
+++ b/tools/testing/selftests/kvm/demand_paging_test.c
@@ -128,6 +128,7 @@ static void prefault_mem(void *alias, uint64_t len)
 
 static void run_test(enum vm_guest_mode mode, void *arg)
 {
+	struct memstress_vcpu_args *vcpu_args;
 	struct test_params *p = arg;
 	struct uffd_desc **uffd_descs = NULL;
 	struct timespec start;
@@ -145,24 +146,24 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 		    "Failed to allocate buffer for guest data pattern");
 	memset(guest_data_prototype, 0xAB, demand_paging_size);
 
+	if (p->uffd_mode == UFFDIO_REGISTER_MODE_MINOR) {
+		for (i = 0; i < nr_vcpus; i++) {
+			vcpu_args = &memstress_args.vcpu_args[i];
+			prefault_mem(addr_gpa2alias(vm, vcpu_args->gpa),
+				     vcpu_args->pages * memstress_args.guest_page_size);
+		}
+	}
+
 	if (p->uffd_mode) {
 		uffd_descs = malloc(nr_vcpus * sizeof(struct uffd_desc *));
 		TEST_ASSERT(uffd_descs, "Memory allocation failed");
-
 		for (i = 0; i < nr_vcpus; i++) {
-			struct memstress_vcpu_args *vcpu_args;
 			void *vcpu_hva;
-			void *vcpu_alias;
 
 			vcpu_args = &memstress_args.vcpu_args[i];
 
 			/* Cache the host addresses of the region */
 			vcpu_hva = addr_gpa2hva(vm, vcpu_args->gpa);
-			vcpu_alias = addr_gpa2alias(vm, vcpu_args->gpa);
-
-			prefault_mem(vcpu_alias,
-				vcpu_args->pages * memstress_args.guest_page_size);
-
 			/*
 			 * Set up user fault fd to handle demand paging
 			 * requests.
@@ -207,10 +208,11 @@ static void help(char *name)
 {
 	puts("");
 	printf("usage: %s [-h] [-m vm_mode] [-u uffd_mode] [-d uffd_delay_usec]\n"
-	       "          [-b memory] [-s type] [-v vcpus] [-o]\n", name);
+	       "          [-b memory] [-s type] [-v vcpus] [-c cpu_list] [-o]\n", name);
 	guest_modes_help();
 	printf(" -u: use userfaultfd to handle vCPU page faults. Mode is a\n"
 	       "     UFFD registration mode: 'MISSING' or 'MINOR'.\n");
+	kvm_print_vcpu_pinning_help();
 	printf(" -d: add a delay in usec to the User Fault\n"
 	       "     FD handler to simulate demand paging\n"
 	       "     overheads. Ignored without -u.\n");
@@ -228,6 +230,7 @@ static void help(char *name)
 int main(int argc, char *argv[])
 {
 	int max_vcpus = kvm_check_cap(KVM_CAP_MAX_VCPUS);
+	const char *cpulist = NULL;
 	struct test_params p = {
 		.src_type = DEFAULT_VM_MEM_SRC,
 		.partition_vcpu_memory_access = true,
@@ -236,7 +239,7 @@ int main(int argc, char *argv[])
 
 	guest_modes_append_default();
 
-	while ((opt = getopt(argc, argv, "hm:u:d:b:s:v:o")) != -1) {
+	while ((opt = getopt(argc, argv, "hm:u:d:b:s:v:c:o")) != -1) {
 		switch (opt) {
 		case 'm':
 			guest_modes_cmdline(optarg);
@@ -263,6 +266,9 @@ int main(int argc, char *argv[])
 			TEST_ASSERT(nr_vcpus <= max_vcpus,
 				    "Invalid number of vcpus, must be between 1 and %d", max_vcpus);
 			break;
+		case 'c':
+			cpulist = optarg;
+			break;
 		case 'o':
 			p.partition_vcpu_memory_access = false;
 			break;
@@ -278,6 +284,12 @@ int main(int argc, char *argv[])
 		TEST_FAIL("userfaultfd MINOR mode requires shared memory; pick a different -s");
 	}
 
+	if (cpulist) {
+		kvm_parse_vcpu_pinning(cpulist, memstress_args.vcpu_to_pcpu,
+				       nr_vcpus);
+		memstress_args.pin_vcpus = true;
+	}
+
 	for_each_guest_mode(run_test, &p);
 
 	return 0;
diff --git a/tools/testing/selftests/kvm/dirty_log_perf_test.c b/tools/testing/selftests/kvm/dirty_log_perf_test.c
index e9d6d1aecf89..d374dbcf9a53 100644
--- a/tools/testing/selftests/kvm/dirty_log_perf_test.c
+++ b/tools/testing/selftests/kvm/dirty_log_perf_test.c
@@ -136,77 +136,6 @@ struct test_params {
 	bool random_access;
 };
 
-static void toggle_dirty_logging(struct kvm_vm *vm, int slots, bool enable)
-{
-	int i;
-
-	for (i = 0; i < slots; i++) {
-		int slot = MEMSTRESS_MEM_SLOT_INDEX + i;
-		int flags = enable ? KVM_MEM_LOG_DIRTY_PAGES : 0;
-
-		vm_mem_region_set_flags(vm, slot, flags);
-	}
-}
-
-static inline void enable_dirty_logging(struct kvm_vm *vm, int slots)
-{
-	toggle_dirty_logging(vm, slots, true);
-}
-
-static inline void disable_dirty_logging(struct kvm_vm *vm, int slots)
-{
-	toggle_dirty_logging(vm, slots, false);
-}
-
-static void get_dirty_log(struct kvm_vm *vm, unsigned long *bitmaps[], int slots)
-{
-	int i;
-
-	for (i = 0; i < slots; i++) {
-		int slot = MEMSTRESS_MEM_SLOT_INDEX + i;
-
-		kvm_vm_get_dirty_log(vm, slot, bitmaps[i]);
-	}
-}
-
-static void clear_dirty_log(struct kvm_vm *vm, unsigned long *bitmaps[],
-			    int slots, uint64_t pages_per_slot)
-{
-	int i;
-
-	for (i = 0; i < slots; i++) {
-		int slot = MEMSTRESS_MEM_SLOT_INDEX + i;
-
-		kvm_vm_clear_dirty_log(vm, slot, bitmaps[i], 0, pages_per_slot);
-	}
-}
-
-static unsigned long **alloc_bitmaps(int slots, uint64_t pages_per_slot)
-{
-	unsigned long **bitmaps;
-	int i;
-
-	bitmaps = malloc(slots * sizeof(bitmaps[0]));
-	TEST_ASSERT(bitmaps, "Failed to allocate bitmaps array.");
-
-	for (i = 0; i < slots; i++) {
-		bitmaps[i] = bitmap_zalloc(pages_per_slot);
-		TEST_ASSERT(bitmaps[i], "Failed to allocate slot bitmap.");
-	}
-
-	return bitmaps;
-}
-
-static void free_bitmaps(unsigned long *bitmaps[], int slots)
-{
-	int i;
-
-	for (i = 0; i < slots; i++)
-		free(bitmaps[i]);
-
-	free(bitmaps);
-}
-
 static void run_test(enum vm_guest_mode mode, void *arg)
 {
 	struct test_params *p = arg;
@@ -236,7 +165,7 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	host_num_pages = vm_num_host_pages(mode, guest_num_pages);
 	pages_per_slot = host_num_pages / p->slots;
 
-	bitmaps = alloc_bitmaps(p->slots, pages_per_slot);
+	bitmaps = memstress_alloc_bitmaps(p->slots, pages_per_slot);
 
 	if (dirty_log_manual_caps)
 		vm_enable_cap(vm, KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2,
@@ -277,7 +206,7 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 
 	/* Enable dirty logging */
 	clock_gettime(CLOCK_MONOTONIC, &start);
-	enable_dirty_logging(vm, p->slots);
+	memstress_enable_dirty_logging(vm, p->slots);
 	ts_diff = timespec_elapsed(start);
 	pr_info("Enabling dirty logging time: %ld.%.9lds\n\n",
 		ts_diff.tv_sec, ts_diff.tv_nsec);
@@ -306,7 +235,7 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 			iteration, ts_diff.tv_sec, ts_diff.tv_nsec);
 
 		clock_gettime(CLOCK_MONOTONIC, &start);
-		get_dirty_log(vm, bitmaps, p->slots);
+		memstress_get_dirty_log(vm, bitmaps, p->slots);
 		ts_diff = timespec_elapsed(start);
 		get_dirty_log_total = timespec_add(get_dirty_log_total,
 						   ts_diff);
@@ -315,7 +244,8 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 
 		if (dirty_log_manual_caps) {
 			clock_gettime(CLOCK_MONOTONIC, &start);
-			clear_dirty_log(vm, bitmaps, p->slots, pages_per_slot);
+			memstress_clear_dirty_log(vm, bitmaps, p->slots,
+						  pages_per_slot);
 			ts_diff = timespec_elapsed(start);
 			clear_dirty_log_total = timespec_add(clear_dirty_log_total,
 							     ts_diff);
@@ -334,7 +264,7 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 
 	/* Disable dirty logging */
 	clock_gettime(CLOCK_MONOTONIC, &start);
-	disable_dirty_logging(vm, p->slots);
+	memstress_disable_dirty_logging(vm, p->slots);
 	ts_diff = timespec_elapsed(start);
 	pr_info("Disabling dirty logging time: %ld.%.9lds\n",
 		ts_diff.tv_sec, ts_diff.tv_nsec);
@@ -359,7 +289,7 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 			clear_dirty_log_total.tv_nsec, avg.tv_sec, avg.tv_nsec);
 	}
 
-	free_bitmaps(bitmaps, p->slots);
+	memstress_free_bitmaps(bitmaps, p->slots);
 	arch_cleanup_vm(vm);
 	memstress_destroy_vm(vm);
 }
@@ -402,17 +332,7 @@ static void help(char *name)
 	       "     so -w X means each page has an X%% chance of writing\n"
 	       "     and a (100-X)%% chance of reading.\n"
 	       "     (default: 100 i.e. all pages are written to.)\n");
-	printf(" -c: Pin tasks to physical CPUs.  Takes a list of comma separated\n"
-	       "     values (target pCPU), one for each vCPU, plus an optional\n"
-	       "     entry for the main application task (specified via entry\n"
-	       "     <nr_vcpus + 1>).  If used, entries must be provided for all\n"
-	       "     vCPUs, i.e. pinning vCPUs is all or nothing.\n\n"
-	       "     E.g. to create 3 vCPUs, pin vCPU0=>pCPU22, vCPU1=>pCPU23,\n"
-	       "     vCPU2=>pCPU24, and pin the application task to pCPU50:\n\n"
-	       "         ./dirty_log_perf_test -v 3 -c 22,23,24,50\n\n"
-	       "     To leave the application task unpinned, drop the final entry:\n\n"
-	       "         ./dirty_log_perf_test -v 3 -c 22,23,24\n\n"
-	       "     (default: no pinning)\n");
+	kvm_print_vcpu_pinning_help();
 	puts("");
 	exit(0);
 }
diff --git a/tools/testing/selftests/kvm/include/kvm_util_base.h b/tools/testing/selftests/kvm/include/kvm_util_base.h
index a089c356f354..07732a157ccd 100644
--- a/tools/testing/selftests/kvm/include/kvm_util_base.h
+++ b/tools/testing/selftests/kvm/include/kvm_util_base.h
@@ -733,6 +733,7 @@ static inline struct kvm_vm *vm_create_with_one_vcpu(struct kvm_vcpu **vcpu,
 struct kvm_vcpu *vm_recreate_with_one_vcpu(struct kvm_vm *vm);
 
 void kvm_pin_this_task_to_pcpu(uint32_t pcpu);
+void kvm_print_vcpu_pinning_help(void);
 void kvm_parse_vcpu_pinning(const char *pcpus_string, uint32_t vcpu_to_pcpu[],
 			    int nr_vcpus);
 
diff --git a/tools/testing/selftests/kvm/include/memstress.h b/tools/testing/selftests/kvm/include/memstress.h
index 72e3e358ef7b..ce4e603050ea 100644
--- a/tools/testing/selftests/kvm/include/memstress.h
+++ b/tools/testing/selftests/kvm/include/memstress.h
@@ -72,4 +72,12 @@ void memstress_guest_code(uint32_t vcpu_id);
 uint64_t memstress_nested_pages(int nr_vcpus);
 void memstress_setup_nested(struct kvm_vm *vm, int nr_vcpus, struct kvm_vcpu *vcpus[]);
 
+void memstress_enable_dirty_logging(struct kvm_vm *vm, int slots);
+void memstress_disable_dirty_logging(struct kvm_vm *vm, int slots);
+void memstress_get_dirty_log(struct kvm_vm *vm, unsigned long *bitmaps[], int slots);
+void memstress_clear_dirty_log(struct kvm_vm *vm, unsigned long *bitmaps[],
+			       int slots, uint64_t pages_per_slot);
+unsigned long **memstress_alloc_bitmaps(int slots, uint64_t pages_per_slot);
+void memstress_free_bitmaps(unsigned long *bitmaps[], int slots);
+
 #endif /* SELFTEST_KVM_MEMSTRESS_H */
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 298c4372fb1a..9741a7ff6380 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -494,6 +494,23 @@ static uint32_t parse_pcpu(const char *cpu_str, const cpu_set_t *allowed_mask)
 	return pcpu;
 }
 
+void kvm_print_vcpu_pinning_help(void)
+{
+	const char *name = program_invocation_name;
+
+	printf(" -c: Pin tasks to physical CPUs.  Takes a list of comma separated\n"
+	       "     values (target pCPU), one for each vCPU, plus an optional\n"
+	       "     entry for the main application task (specified via entry\n"
+	       "     <nr_vcpus + 1>).  If used, entries must be provided for all\n"
+	       "     vCPUs, i.e. pinning vCPUs is all or nothing.\n\n"
+	       "     E.g. to create 3 vCPUs, pin vCPU0=>pCPU22, vCPU1=>pCPU23,\n"
+	       "     vCPU2=>pCPU24, and pin the application task to pCPU50:\n\n"
+	       "         %s -v 3 -c 22,23,24,50\n\n"
+	       "     To leave the application task unpinned, drop the final entry:\n\n"
+	       "         %s -v 3 -c 22,23,24\n\n"
+	       "     (default: no pinning)\n", name, name);
+}
+
 void kvm_parse_vcpu_pinning(const char *pcpus_string, uint32_t vcpu_to_pcpu[],
 			    int nr_vcpus)
 {
diff --git a/tools/testing/selftests/kvm/lib/memstress.c b/tools/testing/selftests/kvm/lib/memstress.c
index 5f1d3173c238..df457452d146 100644
--- a/tools/testing/selftests/kvm/lib/memstress.c
+++ b/tools/testing/selftests/kvm/lib/memstress.c
@@ -5,6 +5,7 @@
 #define _GNU_SOURCE
 
 #include <inttypes.h>
+#include <linux/bitmap.h>
 
 #include "kvm_util.h"
 #include "memstress.h"
@@ -64,6 +65,9 @@ void memstress_guest_code(uint32_t vcpu_idx)
 	GUEST_ASSERT(vcpu_args->vcpu_idx == vcpu_idx);
 
 	while (true) {
+		for (i = 0; i < sizeof(memstress_args); i += args->guest_page_size)
+			(void) *((volatile char *)args + i);
+
 		for (i = 0; i < pages; i++) {
 			if (args->random_access)
 				page = guest_random_u32(&rand_state) % pages;
@@ -320,3 +324,74 @@ void memstress_join_vcpu_threads(int nr_vcpus)
 	for (i = 0; i < nr_vcpus; i++)
 		pthread_join(vcpu_threads[i].thread, NULL);
 }
+
+static void toggle_dirty_logging(struct kvm_vm *vm, int slots, bool enable)
+{
+	int i;
+
+	for (i = 0; i < slots; i++) {
+		int slot = MEMSTRESS_MEM_SLOT_INDEX + i;
+		int flags = enable ? KVM_MEM_LOG_DIRTY_PAGES : 0;
+
+		vm_mem_region_set_flags(vm, slot, flags);
+	}
+}
+
+void memstress_enable_dirty_logging(struct kvm_vm *vm, int slots)
+{
+	toggle_dirty_logging(vm, slots, true);
+}
+
+void memstress_disable_dirty_logging(struct kvm_vm *vm, int slots)
+{
+	toggle_dirty_logging(vm, slots, false);
+}
+
+void memstress_get_dirty_log(struct kvm_vm *vm, unsigned long *bitmaps[], int slots)
+{
+	int i;
+
+	for (i = 0; i < slots; i++) {
+		int slot = MEMSTRESS_MEM_SLOT_INDEX + i;
+
+		kvm_vm_get_dirty_log(vm, slot, bitmaps[i]);
+	}
+}
+
+void memstress_clear_dirty_log(struct kvm_vm *vm, unsigned long *bitmaps[],
+			       int slots, uint64_t pages_per_slot)
+{
+	int i;
+
+	for (i = 0; i < slots; i++) {
+		int slot = MEMSTRESS_MEM_SLOT_INDEX + i;
+
+		kvm_vm_clear_dirty_log(vm, slot, bitmaps[i], 0, pages_per_slot);
+	}
+}
+
+unsigned long **memstress_alloc_bitmaps(int slots, uint64_t pages_per_slot)
+{
+	unsigned long **bitmaps;
+	int i;
+
+	bitmaps = malloc(slots * sizeof(bitmaps[0]));
+	TEST_ASSERT(bitmaps, "Failed to allocate bitmaps array.");
+
+	for (i = 0; i < slots; i++) {
+		bitmaps[i] = bitmap_zalloc(pages_per_slot);
+		TEST_ASSERT(bitmaps[i], "Failed to allocate slot bitmap.");
+	}
+
+	return bitmaps;
+}
+
+void memstress_free_bitmaps(unsigned long *bitmaps[], int slots)
+{
+	int i;
+
+	for (i = 0; i < slots; i++)
+		free(bitmaps[i]);
+
+	free(bitmaps);
+}
diff --git a/tools/testing/selftests/kvm/lib/userfaultfd_util.c b/tools/testing/selftests/kvm/lib/userfaultfd_util.c
index 92cef20902f1..271f63891581 100644
--- a/tools/testing/selftests/kvm/lib/userfaultfd_util.c
+++ b/tools/testing/selftests/kvm/lib/userfaultfd_util.c
@@ -70,7 +70,7 @@ static void *uffd_handler_thread_fn(void *arg)
 			r = read(pollfd[1].fd, &tmp_chr, 1);
 			TEST_ASSERT(r == 1,
 				    "Error reading pipefd in UFFD thread\n");
-			return NULL;
+			break;
 		}
 
 		if (!(pollfd[0].revents & POLLIN))
@@ -103,7 +103,7 @@ static void *uffd_handler_thread_fn(void *arg)
 	ts_diff = timespec_elapsed(start);
 	PER_VCPU_DEBUG("userfaulted %ld pages over %ld.%.9lds. (%f/sec)\n",
 		       pages, ts_diff.tv_sec, ts_diff.tv_nsec,
-		       pages / ((double)ts_diff.tv_sec + (double)ts_diff.tv_nsec / 100000000.0));
+		       pages / ((double)ts_diff.tv_sec + (double)ts_diff.tv_nsec / NSEC_PER_SEC));
 
 	return NULL;
 }
diff --git a/tools/testing/selftests/kvm/s390x/cmma_test.c b/tools/testing/selftests/kvm/s390x/cmma_test.c
new file mode 100644
index 000000000000..1d73e78e8fa7
--- /dev/null
+++ b/tools/testing/selftests/kvm/s390x/cmma_test.c
@@ -0,0 +1,700 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Test for s390x CMMA migration
+ *
+ * Copyright IBM Corp. 2023
+ *
+ * Authors:
+ *  Nico Boehr <nrb@linux.ibm.com>
+ */
+
+#define _GNU_SOURCE /* for program_invocation_short_name */
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "kselftest.h"
+
+#define MAIN_PAGE_COUNT 512
+
+#define TEST_DATA_PAGE_COUNT 512
+#define TEST_DATA_MEMSLOT 1
+#define TEST_DATA_START_GFN 4096
+
+#define TEST_DATA_TWO_PAGE_COUNT 256
+#define TEST_DATA_TWO_MEMSLOT 2
+#define TEST_DATA_TWO_START_GFN 8192
+
+static char cmma_value_buf[MAIN_PAGE_COUNT + TEST_DATA_PAGE_COUNT];
+
+/**
+ * Dirty CMMA attributes of exactly one page in the TEST_DATA memslot,
+ * so use_cmma goes on and the CMMA related ioctls do something.
+ */
+static void guest_do_one_essa(void)
+{
+	asm volatile(
+		/* load TEST_DATA_START_GFN into r1 */
+		"	llilf 1,%[start_gfn]\n"
+		/* calculate the address from the gfn */
+		"	sllg 1,1,12(0)\n"
+		/* set the first page in TEST_DATA memslot to STABLE */
+		"	.insn rrf,0xb9ab0000,2,1,1,0\n"
+		/* hypercall */
+		"	diag 0,0,0x501\n"
+		"0:	j 0b"
+		:
+		: [start_gfn] "L"(TEST_DATA_START_GFN)
+		: "r1", "r2", "memory", "cc"
+	);
+}
+
+/**
+ * Touch CMMA attributes of all pages in TEST_DATA memslot. Set them to stable
+ * state.
+ */
+static void guest_dirty_test_data(void)
+{
+	asm volatile(
+		/* r1 = TEST_DATA_START_GFN */
+		"	xgr 1,1\n"
+		"	llilf 1,%[start_gfn]\n"
+		/* r5 = TEST_DATA_PAGE_COUNT */
+		"	lghi 5,%[page_count]\n"
+		/* r5 += r1 */
+		"2:	agfr 5,1\n"
+		/* r2 = r1 << 12 */
+		"1:	sllg 2,1,12(0)\n"
+		/* essa(r4, r2, SET_STABLE) */
+		"	.insn rrf,0xb9ab0000,4,2,1,0\n"
+		/* i++ */
+		"	agfi 1,1\n"
+		/* if r1 < r5 goto 1 */
+		"	cgrjl 1,5,1b\n"
+		/* hypercall */
+		"	diag 0,0,0x501\n"
+		"0:	j 0b"
+		:
+		: [start_gfn] "L"(TEST_DATA_START_GFN),
+		  [page_count] "L"(TEST_DATA_PAGE_COUNT)
+		:
+			/* the counter in our loop over the pages */
+			"r1",
+			/* the calculated page physical address */
+			"r2",
+			/* ESSA output register */
+			"r4",
+			/* last page */
+			"r5",
+			"cc", "memory"
+	);
+}
+
+static struct kvm_vm *create_vm(void)
+{
+	return ____vm_create(VM_MODE_DEFAULT);
+}
+
+static void create_main_memslot(struct kvm_vm *vm)
+{
+	int i;
+
+	vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, 0, 0, MAIN_PAGE_COUNT, 0);
+	/* set the array of memslots to zero like __vm_create does */
+	for (i = 0; i < NR_MEM_REGIONS; i++)
+		vm->memslots[i] = 0;
+}
+
+static void create_test_memslot(struct kvm_vm *vm)
+{
+	vm_userspace_mem_region_add(vm,
+				    VM_MEM_SRC_ANONYMOUS,
+				    TEST_DATA_START_GFN << vm->page_shift,
+				    TEST_DATA_MEMSLOT,
+				    TEST_DATA_PAGE_COUNT,
+				    0
+				   );
+	vm->memslots[MEM_REGION_TEST_DATA] = TEST_DATA_MEMSLOT;
+}
+
+static void create_memslots(struct kvm_vm *vm)
+{
+	/*
+	 * Our VM has the following memory layout:
+	 * +------+---------------------------+
+	 * | GFN  | Memslot                   |
+	 * +------+---------------------------+
+	 * | 0    |                           |
+	 * | ...  | MAIN (Code, Stack, ...)   |
+	 * | 511  |                           |
+	 * +------+---------------------------+
+	 * | 4096 |                           |
+	 * | ...  | TEST_DATA                 |
+	 * | 4607 |                           |
+	 * +------+---------------------------+
+	 */
+	create_main_memslot(vm);
+	create_test_memslot(vm);
+}
+
+static void finish_vm_setup(struct kvm_vm *vm)
+{
+	struct userspace_mem_region *slot0;
+
+	kvm_vm_elf_load(vm, program_invocation_name);
+
+	slot0 = memslot2region(vm, 0);
+	ucall_init(vm, slot0->region.guest_phys_addr + slot0->region.memory_size);
+
+	kvm_arch_vm_post_create(vm);
+}
+
+static struct kvm_vm *create_vm_two_memslots(void)
+{
+	struct kvm_vm *vm;
+
+	vm = create_vm();
+
+	create_memslots(vm);
+
+	finish_vm_setup(vm);
+
+	return vm;
+}
+
+static void enable_cmma(struct kvm_vm *vm)
+{
+	int r;
+
+	r = __kvm_device_attr_set(vm->fd, KVM_S390_VM_MEM_CTRL, KVM_S390_VM_MEM_ENABLE_CMMA, NULL);
+	TEST_ASSERT(!r, "enabling cmma failed r=%d errno=%d", r, errno);
+}
+
+static void enable_dirty_tracking(struct kvm_vm *vm)
+{
+	vm_mem_region_set_flags(vm, 0, KVM_MEM_LOG_DIRTY_PAGES);
+	vm_mem_region_set_flags(vm, TEST_DATA_MEMSLOT, KVM_MEM_LOG_DIRTY_PAGES);
+}
+
+static int __enable_migration_mode(struct kvm_vm *vm)
+{
+	return __kvm_device_attr_set(vm->fd,
+				     KVM_S390_VM_MIGRATION,
+				     KVM_S390_VM_MIGRATION_START,
+				     NULL
+				    );
+}
+
+static void enable_migration_mode(struct kvm_vm *vm)
+{
+	int r = __enable_migration_mode(vm);
+
+	TEST_ASSERT(!r, "enabling migration mode failed r=%d errno=%d", r, errno);
+}
+
+static bool is_migration_mode_on(struct kvm_vm *vm)
+{
+	u64 out;
+	int r;
+
+	r = __kvm_device_attr_get(vm->fd,
+				  KVM_S390_VM_MIGRATION,
+				  KVM_S390_VM_MIGRATION_STATUS,
+				  &out
+				 );
+	TEST_ASSERT(!r, "getting migration mode status failed r=%d errno=%d", r, errno);
+	return out;
+}
+
+static int vm_get_cmma_bits(struct kvm_vm *vm, u64 flags, int *errno_out)
+{
+	struct kvm_s390_cmma_log args;
+	int rc;
+
+	errno = 0;
+
+	args = (struct kvm_s390_cmma_log){
+		.start_gfn = 0,
+		.count = sizeof(cmma_value_buf),
+		.flags = flags,
+		.values = (__u64)&cmma_value_buf[0]
+	};
+	rc = __vm_ioctl(vm, KVM_S390_GET_CMMA_BITS, &args);
+
+	*errno_out = errno;
+	return rc;
+}
+
+static void test_get_cmma_basic(void)
+{
+	struct kvm_vm *vm = create_vm_two_memslots();
+	struct kvm_vcpu *vcpu;
+	int rc, errno_out;
+
+	/* GET_CMMA_BITS without CMMA enabled should fail */
+	rc = vm_get_cmma_bits(vm, 0, &errno_out);
+	ASSERT_EQ(rc, -1);
+	ASSERT_EQ(errno_out, ENXIO);
+
+	enable_cmma(vm);
+	vcpu = vm_vcpu_add(vm, 1, guest_do_one_essa);
+
+	vcpu_run(vcpu);
+
+	/* GET_CMMA_BITS without migration mode and without peeking should fail */
+	rc = vm_get_cmma_bits(vm, 0, &errno_out);
+	ASSERT_EQ(rc, -1);
+	ASSERT_EQ(errno_out, EINVAL);
+
+	/* GET_CMMA_BITS without migration mode and with peeking should work */
+	rc = vm_get_cmma_bits(vm, KVM_S390_CMMA_PEEK, &errno_out);
+	ASSERT_EQ(rc, 0);
+	ASSERT_EQ(errno_out, 0);
+
+	enable_dirty_tracking(vm);
+	enable_migration_mode(vm);
+
+	/* GET_CMMA_BITS with invalid flags */
+	rc = vm_get_cmma_bits(vm, 0xfeedc0fe, &errno_out);
+	ASSERT_EQ(rc, -1);
+	ASSERT_EQ(errno_out, EINVAL);
+
+	kvm_vm_free(vm);
+}
+
+static void assert_exit_was_hypercall(struct kvm_vcpu *vcpu)
+{
+	ASSERT_EQ(vcpu->run->exit_reason, 13);
+	ASSERT_EQ(vcpu->run->s390_sieic.icptcode, 4);
+	ASSERT_EQ(vcpu->run->s390_sieic.ipa, 0x8300);
+	ASSERT_EQ(vcpu->run->s390_sieic.ipb, 0x5010000);
+}
+
+static void test_migration_mode(void)
+{
+	struct kvm_vm *vm = create_vm();
+	struct kvm_vcpu *vcpu;
+	u64 orig_psw;
+	int rc;
+
+	/* enabling migration mode on a VM without memory should fail */
+	rc = __enable_migration_mode(vm);
+	ASSERT_EQ(rc, -1);
+	ASSERT_EQ(errno, EINVAL);
+	TEST_ASSERT(!is_migration_mode_on(vm), "migration mode should still be off");
+	errno = 0;
+
+	create_memslots(vm);
+	finish_vm_setup(vm);
+
+	enable_cmma(vm);
+	vcpu = vm_vcpu_add(vm, 1, guest_do_one_essa);
+	orig_psw = vcpu->run->psw_addr;
+
+	/*
+	 * Execute one essa instruction in the guest. Otherwise the guest will
+	 * not have use_cmm enabled and GET_CMMA_BITS will return no pages.
+	 */
+	vcpu_run(vcpu);
+	assert_exit_was_hypercall(vcpu);
+
+	/* migration mode when memslots have dirty tracking off should fail */
+	rc = __enable_migration_mode(vm);
+	ASSERT_EQ(rc, -1);
+	ASSERT_EQ(errno, EINVAL);
+	TEST_ASSERT(!is_migration_mode_on(vm), "migration mode should still be off");
+	errno = 0;
+
+	/* enable dirty tracking */
+	enable_dirty_tracking(vm);
+
+	/* enabling migration mode should work now */
+	rc = __enable_migration_mode(vm);
+	ASSERT_EQ(rc, 0);
+	TEST_ASSERT(is_migration_mode_on(vm), "migration mode should be on");
+	errno = 0;
+
+	/* execute another ESSA instruction to see this goes fine */
+	vcpu->run->psw_addr = orig_psw;
+	vcpu_run(vcpu);
+	assert_exit_was_hypercall(vcpu);
+
+	/*
+	 * With migration mode on, create a new memslot with dirty tracking off.
+	 * This should turn off migration mode.
+	 */
+	TEST_ASSERT(is_migration_mode_on(vm), "migration mode should be on");
+	vm_userspace_mem_region_add(vm,
+				    VM_MEM_SRC_ANONYMOUS,
+				    TEST_DATA_TWO_START_GFN << vm->page_shift,
+				    TEST_DATA_TWO_MEMSLOT,
+				    TEST_DATA_TWO_PAGE_COUNT,
+				    0
+				   );
+	TEST_ASSERT(!is_migration_mode_on(vm),
+		    "creating memslot without dirty tracking turns off migration mode"
+		   );
+
+	/* ESSA instructions should still execute fine */
+	vcpu->run->psw_addr = orig_psw;
+	vcpu_run(vcpu);
+	assert_exit_was_hypercall(vcpu);
+
+	/*
+	 * Turn on dirty tracking on the new memslot.
+	 * It should be possible to turn migration mode back on again.