Merge branch 'kvm-late-6.1-fixes' into HEAD

x86:

* several fixes to nested VMX execution controls

* fixes and clarification to the documentation for Xen emulation

* do not unnecessarily release a pmu event with zero period

* MMU fixes

* fix Coverity warning in kvm_hv_flush_tlb()

selftests:

* fixes for the ucall mechanism in selftests

* other fixes mostly related to compilation with clang

12 files changed, 82 insertions, 142 deletions

diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore
index 6ce8c488d62e..6d9381d60172 100644
--- a/tools/testing/selftests/kvm/.gitignore
+++ b/tools/testing/selftests/kvm/.gitignore
@@ -1,86 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0-only
-/aarch64/aarch32_id_regs
-/aarch64/arch_timer
-/aarch64/debug-exceptions
-/aarch64/get-reg-list
-/aarch64/hypercalls
-/aarch64/page_fault_test
-/aarch64/psci_test
-/aarch64/vcpu_width_config
-/aarch64/vgic_init
-/aarch64/vgic_irq
-/s390x/memop
-/s390x/resets
-/s390x/sync_regs_test
-/s390x/tprot
-/x86_64/amx_test
-/x86_64/cpuid_test
-/x86_64/cr4_cpuid_sync_test
-/x86_64/debug_regs
-/x86_64/exit_on_emulation_failure_test
-/x86_64/fix_hypercall_test
-/x86_64/get_msr_index_features
-/x86_64/kvm_clock_test
-/x86_64/kvm_pv_test
-/x86_64/hyperv_clock
-/x86_64/hyperv_cpuid
-/x86_64/hyperv_evmcs
-/x86_64/hyperv_features
-/x86_64/hyperv_ipi
-/x86_64/hyperv_svm_test
-/x86_64/hyperv_tlb_flush
-/x86_64/max_vcpuid_cap_test
-/x86_64/mmio_warning_test
-/x86_64/monitor_mwait_test
-/x86_64/nested_exceptions_test
-/x86_64/nx_huge_pages_test
-/x86_64/platform_info_test
-/x86_64/pmu_event_filter_test
-/x86_64/set_boot_cpu_id
-/x86_64/set_sregs_test
-/x86_64/sev_migrate_tests
-/x86_64/smaller_maxphyaddr_emulation_test
-/x86_64/smm_test
-/x86_64/state_test
-/x86_64/svm_vmcall_test
-/x86_64/svm_int_ctl_test
-/x86_64/svm_nested_soft_inject_test
-/x86_64/svm_nested_shutdown_test
-/x86_64/sync_regs_test
-/x86_64/tsc_msrs_test
-/x86_64/tsc_scaling_sync
-/x86_64/ucna_injection_test
-/x86_64/userspace_io_test
-/x86_64/userspace_msr_exit_test
-/x86_64/vmx_apic_access_test
-/x86_64/vmx_close_while_nested_test
-/x86_64/vmx_dirty_log_test
-/x86_64/vmx_exception_with_invalid_guest_state
-/x86_64/vmx_invalid_nested_guest_state
-/x86_64/vmx_msrs_test
-/x86_64/vmx_preemption_timer_test
-/x86_64/vmx_set_nested_state_test
-/x86_64/vmx_tsc_adjust_test
-/x86_64/vmx_nested_tsc_scaling_test
-/x86_64/xapic_ipi_test
-/x86_64/xapic_state_test
-/x86_64/xen_shinfo_test
-/x86_64/xen_vmcall_test
-/x86_64/xss_msr_test
-/x86_64/vmx_pmu_caps_test
-/x86_64/triple_fault_event_test
-/access_tracking_perf_test
-/demand_paging_test
-/dirty_log_test
-/dirty_log_perf_test
-/hardware_disable_test
-/kvm_create_max_vcpus
-/kvm_page_table_test
-/max_guest_memory_test
-/memslot_modification_stress_test
-/memslot_perf_test
-/rseq_test
-/set_memory_region_test
-/steal_time
-/kvm_binary_stats_test
-/system_counter_offset_test
+*
+!/**/
+!*.c
+!*.h
+!*.S
+!*.sh
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index 947676983da1..1750f91dd936 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -7,35 +7,14 @@ top_srcdir = ../../../..
 include $(top_srcdir)/scripts/subarch.include
 ARCH            ?= $(SUBARCH)
 
-# For cross-builds to work, UNAME_M has to map to ARCH and arch specific
-# directories and targets in this Makefile. "uname -m" doesn't map to
-# arch specific sub-directory names.
-#
-# UNAME_M variable to used to run the compiles pointing to the right arch
-# directories and build the right targets for these supported architectures.
-#
-# TEST_GEN_PROGS and LIBKVM are set using UNAME_M variable.
-# LINUX_TOOL_ARCH_INCLUDE is set using ARCH variable.
-#
-# x86_64 targets are named to include x86_64 as a suffix and directories
-# for includes are in x86_64 sub-directory. s390x and aarch64 follow the
-# same convention. "uname -m" doesn't result in the correct mapping for
-# s390x and aarch64.
-#
-# No change necessary for x86_64
-UNAME_M := $(shell uname -m)
-
-# Set UNAME_M for arm64 compile/install to work
-ifeq ($(ARCH),arm64)
-	UNAME_M := aarch64
-endif
-# Set UNAME_M s390x compile/install to work
-ifeq ($(ARCH),s390)
-	UNAME_M := s390x
-endif
-# Set UNAME_M riscv compile/install to work
-ifeq ($(ARCH),riscv)
-	UNAME_M := riscv
+ifeq ($(ARCH),x86)
+	ARCH_DIR := x86_64
+else ifeq ($(ARCH),arm64)
+	ARCH_DIR := aarch64
+else ifeq ($(ARCH),s390)
+	ARCH_DIR := s390x
+else
+	ARCH_DIR := $(ARCH)
 endif
 
 LIBKVM += lib/assert.c
@@ -196,10 +175,15 @@ TEST_GEN_PROGS_riscv += kvm_page_table_test
 TEST_GEN_PROGS_riscv += set_memory_region_test
 TEST_GEN_PROGS_riscv += kvm_binary_stats_test
 
-TEST_PROGS += $(TEST_PROGS_$(UNAME_M))
-TEST_GEN_PROGS += $(TEST_GEN_PROGS_$(UNAME_M))
-TEST_GEN_PROGS_EXTENDED += $(TEST_GEN_PROGS_EXTENDED_$(UNAME_M))
-LIBKVM += $(LIBKVM_$(UNAME_M))
+TEST_PROGS += $(TEST_PROGS_$(ARCH_DIR))
+TEST_GEN_PROGS += $(TEST_GEN_PROGS_$(ARCH_DIR))
+TEST_GEN_PROGS_EXTENDED += $(TEST_GEN_PROGS_EXTENDED_$(ARCH_DIR))
+LIBKVM += $(LIBKVM_$(ARCH_DIR))
+
+# 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).
+include ../lib.mk
 
 INSTALL_HDR_PATH = $(top_srcdir)/usr
 LINUX_HDR_PATH = $(INSTALL_HDR_PATH)/include/
@@ -210,25 +194,23 @@ 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 \
+	-fno-builtin-memcmp -fno-builtin-memcpy -fno-builtin-memset \
 	-fno-stack-protector -fno-PIE -I$(LINUX_TOOL_INCLUDE) \
 	-I$(LINUX_TOOL_ARCH_INCLUDE) -I$(LINUX_HDR_PATH) -Iinclude \
-	-I$(<D) -Iinclude/$(UNAME_M) -I ../rseq -I.. $(EXTRA_CFLAGS) \
+	-I$(<D) -Iinclude/$(ARCH_DIR) -I ../rseq -I.. $(EXTRA_CFLAGS) \
 	$(KHDR_INCLUDES)
 
-no-pie-option := $(call try-run, echo 'int main() { return 0; }' | \
-        $(CC) -Werror -no-pie -x c - -o "$$TMP", -no-pie)
+no-pie-option := $(call try-run, echo 'int main(void) { return 0; }' | \
+        $(CC) -Werror $(CFLAGS) -no-pie -x c - -o "$$TMP", -no-pie)
 
 # On s390, build the testcases KVM-enabled
-pgste-option = $(call try-run, echo 'int main() { return 0; }' | \
+pgste-option = $(call try-run, echo 'int main(void) { return 0; }' | \
 	$(CC) -Werror -Wl$(comma)--s390-pgste -x c - -o "$$TMP",-Wl$(comma)--s390-pgste)
 
 LDLIBS += -ldl
 LDFLAGS += -pthread $(no-pie-option) $(pgste-option)
 
-# After inclusion, $(OUTPUT) is defined and
-# $(TEST_GEN_PROGS) starts with $(OUTPUT)/
-include ../lib.mk
-
 LIBKVM_C := $(filter %.c,$(LIBKVM))
 LIBKVM_S := $(filter %.S,$(LIBKVM))
 LIBKVM_C_OBJ := $(patsubst %.c, $(OUTPUT)/%.o, $(LIBKVM_C))
diff --git a/tools/testing/selftests/kvm/aarch64/page_fault_test.c b/tools/testing/selftests/kvm/aarch64/page_fault_test.c
index 95d22cfb7b41..beb944fa6fd4 100644
--- a/tools/testing/selftests/kvm/aarch64/page_fault_test.c
+++ b/tools/testing/selftests/kvm/aarch64/page_fault_test.c
@@ -117,7 +117,7 @@ static void guest_cas(void)
 	GUEST_ASSERT(guest_check_lse());
 	asm volatile(".arch_extension lse\n"
 		     "casal %0, %1, [%2]\n"
-		     :: "r" (0), "r" (TEST_DATA), "r" (guest_test_memory));
+		     :: "r" (0ul), "r" (TEST_DATA), "r" (guest_test_memory));
 	val = READ_ONCE(*guest_test_memory);
 	GUEST_ASSERT_EQ(val, TEST_DATA);
 }
diff --git a/tools/testing/selftests/kvm/lib/aarch64/ucall.c b/tools/testing/selftests/kvm/lib/aarch64/ucall.c
index 562c16dfbb00..f212bd8ab93d 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/ucall.c
+++ b/tools/testing/selftests/kvm/lib/aarch64/ucall.c
@@ -14,11 +14,13 @@ static vm_vaddr_t *ucall_exit_mmio_addr;
 
 void ucall_arch_init(struct kvm_vm *vm, vm_paddr_t mmio_gpa)
 {
-	virt_pg_map(vm, mmio_gpa, mmio_gpa);
+	vm_vaddr_t mmio_gva = vm_vaddr_unused_gap(vm, vm->page_size, KVM_UTIL_MIN_VADDR);
+
+	virt_map(vm, mmio_gva, mmio_gpa, 1);
 
 	vm->ucall_mmio_addr = mmio_gpa;
 
-	write_guest_global(vm, ucall_exit_mmio_addr, (vm_vaddr_t *)mmio_gpa);
+	write_guest_global(vm, ucall_exit_mmio_addr, (vm_vaddr_t *)mmio_gva);
 }
 
 void ucall_arch_do_ucall(vm_vaddr_t uc)
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index c88c3ace16d2..56d5ea949cbb 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -186,6 +186,15 @@ const struct vm_guest_mode_params vm_guest_mode_params[] = {
 _Static_assert(sizeof(vm_guest_mode_params)/sizeof(struct vm_guest_mode_params) == NUM_VM_MODES,
 	       "Missing new mode params?");
 
+/*
+ * Initializes vm->vpages_valid to match the canonical VA space of the
+ * architecture.
+ *
+ * The default implementation is valid for architectures which split the
+ * range addressed by a single page table into a low and high region
+ * based on the MSB of the VA. On architectures with this behavior
+ * the VA region spans [0, 2^(va_bits - 1)), [-(2^(va_bits - 1), -1].
+ */
 __weak void vm_vaddr_populate_bitmap(struct kvm_vm *vm)
 {
 	sparsebit_set_num(vm->vpages_valid,
@@ -1416,10 +1425,10 @@ void virt_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
 
 	while (npages--) {
 		virt_pg_map(vm, vaddr, paddr);
+		sparsebit_set(vm->vpages_mapped, vaddr >> vm->page_shift);
+
 		vaddr += page_size;
 		paddr += page_size;
-
-		sparsebit_set(vm->vpages_mapped, vaddr >> vm->page_shift);
 	}
 }
 
diff --git a/tools/testing/selftests/kvm/lib/ucall_common.c b/tools/testing/selftests/kvm/lib/ucall_common.c
index 0cc0971ce60e..2f0e2ea941cc 100644
--- a/tools/testing/selftests/kvm/lib/ucall_common.c
+++ b/tools/testing/selftests/kvm/lib/ucall_common.c
@@ -4,6 +4,8 @@
 #include "linux/bitmap.h"
 #include "linux/atomic.h"
 
+#define GUEST_UCALL_FAILED -1
+
 struct ucall_header {
 	DECLARE_BITMAP(in_use, KVM_MAX_VCPUS);
 	struct ucall ucalls[KVM_MAX_VCPUS];
@@ -41,7 +43,8 @@ static struct ucall *ucall_alloc(void)
 	struct ucall *uc;
 	int i;
 
-	GUEST_ASSERT(ucall_pool);
+	if (!ucall_pool)
+		goto ucall_failed;
 
 	for (i = 0; i < KVM_MAX_VCPUS; ++i) {
 		if (!test_and_set_bit(i, ucall_pool->in_use)) {
@@ -51,7 +54,13 @@ static struct ucall *ucall_alloc(void)
 		}
 	}
 
-	GUEST_ASSERT(0);
+ucall_failed:
+	/*
+	 * If the vCPU cannot grab a ucall structure, make a bare ucall with a
+	 * magic value to signal to get_ucall() that things went sideways.
+	 * GUEST_ASSERT() depends on ucall_alloc() and so cannot be used here.
+	 */
+	ucall_arch_do_ucall(GUEST_UCALL_FAILED);
 	return NULL;
 }
 
@@ -93,6 +102,9 @@ uint64_t get_ucall(struct kvm_vcpu *vcpu, struct ucall *uc)
 
 	addr = ucall_arch_get_ucall(vcpu);
 	if (addr) {
+		TEST_ASSERT(addr != (void *)GUEST_UCALL_FAILED,
+			    "Guest failed to allocate ucall struct");
+
 		memcpy(uc, addr, sizeof(*uc));
 		vcpu_run_complete_io(vcpu);
 	} else {
diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c
index c4d368d56cfe..acfa1d01e7df 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/processor.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c
@@ -1031,7 +1031,7 @@ bool is_amd_cpu(void)
 void kvm_get_cpu_address_width(unsigned int *pa_bits, unsigned int *va_bits)
 {
 	if (!kvm_cpu_has_p(X86_PROPERTY_MAX_PHY_ADDR)) {
-		*pa_bits == kvm_cpu_has(X86_FEATURE_PAE) ? 36 : 32;
+		*pa_bits = kvm_cpu_has(X86_FEATURE_PAE) ? 36 : 32;
 		*va_bits = 32;
 	} else {
 		*pa_bits = kvm_cpu_property(X86_PROPERTY_MAX_PHY_ADDR);
diff --git a/tools/testing/selftests/kvm/memslot_perf_test.c b/tools/testing/selftests/kvm/memslot_perf_test.c
index e698306bf49d..e6587e193490 100644
--- a/tools/testing/selftests/kvm/memslot_perf_test.c
+++ b/tools/testing/selftests/kvm/memslot_perf_test.c
@@ -265,6 +265,9 @@ static uint64_t get_max_slots(struct vm_data *data, uint32_t host_page_size)
 	slots = data->nslots;
 	while (--slots > 1) {
 		pages_per_slot = mempages / slots;
+		if (!pages_per_slot)
+			continue;
+
 		rempages = mempages % pages_per_slot;
 		if (check_slot_pages(host_page_size, guest_page_size,
 				     pages_per_slot, rempages))
diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_ipi.c b/tools/testing/selftests/kvm/x86_64/hyperv_ipi.c
index 8b791eac7d5a..0cbb0e646ef8 100644
--- a/tools/testing/selftests/kvm/x86_64/hyperv_ipi.c
+++ b/tools/testing/selftests/kvm/x86_64/hyperv_ipi.c
@@ -193,8 +193,9 @@ static void sender_guest_code(void *hcall_page, vm_vaddr_t pgs_gpa)
 	GUEST_SYNC(stage++);
 	/*
 	 * 'XMM Fast' HvCallSendSyntheticClusterIpiEx to HV_GENERIC_SET_ALL.
-	 * Nothing to write anything to XMM regs.
 	 */
+	ipi_ex->vp_set.valid_bank_mask = 0;
+	hyperv_write_xmm_input(&ipi_ex->vp_set.valid_bank_mask, 2);
 	hyperv_hypercall(HVCALL_SEND_IPI_EX | HV_HYPERCALL_FAST_BIT,
 			 IPI_VECTOR, HV_GENERIC_SET_ALL);
 	nop_loop();
diff --git a/tools/testing/selftests/kvm/x86_64/svm_nested_soft_inject_test.c b/tools/testing/selftests/kvm/x86_64/svm_nested_soft_inject_test.c
index e497ace629c1..b34980d45648 100644
--- a/tools/testing/selftests/kvm/x86_64/svm_nested_soft_inject_test.c
+++ b/tools/testing/selftests/kvm/x86_64/svm_nested_soft_inject_test.c
@@ -41,8 +41,17 @@ static void guest_int_handler(struct ex_regs *regs)
 static void l2_guest_code_int(void)
 {
 	GUEST_ASSERT_1(int_fired == 1, int_fired);
-	vmmcall();
-	ud2();
+
+	/*
+         * Same as the vmmcall() function, but with a ud2 sneaked after the
+         * vmmcall.  The caller injects an exception with the return address
+         * increased by 2, so the "pop rbp" must be after the ud2 and we cannot
+	 * use vmmcall() directly.
+         */
+	__asm__ __volatile__("push %%rbp; vmmcall; ud2; pop %%rbp"
+                             : : "a"(0xdeadbeef), "c"(0xbeefdead)
+                             : "rbx", "rdx", "rsi", "rdi", "r8", "r9",
+                               "r10", "r11", "r12", "r13", "r14", "r15");
 
 	GUEST_ASSERT_1(bp_fired == 1, bp_fired);
 	hlt();
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c b/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c
index 5943187e8594..ff8ecdf32ae0 100644
--- a/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c
+++ b/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c
@@ -49,11 +49,6 @@ enum {
 	NUM_VMX_PAGES,
 };
 
-struct kvm_single_msr {
-	struct kvm_msrs header;
-	struct kvm_msr_entry entry;
-} __attribute__((packed));
-
 /* The virtual machine object. */
 static struct kvm_vm *vm;
 
diff --git a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c
index 721f6a693799..dae510c263b4 100644
--- a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c
+++ b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c
@@ -962,6 +962,12 @@ int main(int argc, char *argv[])
 	}
 
  done:
+	struct kvm_xen_hvm_attr evt_reset = {
+		.type = KVM_XEN_ATTR_TYPE_EVTCHN,
+		.u.evtchn.flags = KVM_XEN_EVTCHN_RESET,
+	};
+	vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &evt_reset);
+
 	alarm(0);
 	clock_gettime(CLOCK_REALTIME, &max_ts);