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

Pull more KVM updates from Paolo Bonzini:
 "x86:

   - take into account HVA before retrying on MMU notifier race

   - fixes for nested AMD guests without NPT

   - allow INVPCID in guest without PCID

   - disable PML in hardware when not in use

   - MMU code cleanups:

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (28 commits)
  KVM: SVM: Fix nested VM-Exit on #GP interception handling
  KVM: vmx/pmu: Fix dummy check if lbr_desc->event is created
  KVM: x86/mmu: Consider the hva in mmu_notifier retry
  KVM: x86/mmu: Skip mmu_notifier check when handling MMIO page fault
  KVM: Documentation: rectify rst markup in KVM_GET_SUPPORTED_HV_CPUID
  KVM: nSVM: prepare guest save area while is_guest_mode is true
  KVM: x86/mmu: Remove a variety of unnecessary exports
  KVM: x86: Fold "write-protect large" use case into generic write-protect
  KVM: x86/mmu: Don't set dirty bits when disabling dirty logging w/ PML
  KVM: VMX: Dynamically enable/disable PML based on memslot dirty logging
  KVM: x86: Further clarify the logic and comments for toggling log dirty
  KVM: x86: Move MMU's PML logic to common code
  KVM: x86/mmu: Make dirty log size hook (PML) a value, not a function
  KVM: x86/mmu: Expand on the comment in kvm_vcpu_ad_need_write_protect()
  KVM: nVMX: Disable PML in hardware when running L2
  KVM: x86/mmu: Consult max mapping level when zapping collapsible SPTEs
  KVM: x86/mmu: Pass the memslot to the rmap callbacks
  KVM: x86/mmu: Split out max mapping level calculation to helper
  KVM: x86/mmu: Expand collapsible SPTE zap for TDP MMU to ZONE_DEVICE and HugeTLB pages
  KVM: nVMX: no need to undo inject_page_fault change on nested vmexit
  ...

4 files changed, 169 insertions, 1 deletions

diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore
index 3a84394829ea..32b87cc77c8e 100644
--- a/tools/testing/selftests/kvm/.gitignore
+++ b/tools/testing/selftests/kvm/.gitignore
@@ -33,6 +33,7 @@
 /demand_paging_test
 /dirty_log_test
 /dirty_log_perf_test
+/hardware_disable_test
 /kvm_create_max_vcpus
 /memslot_modification_stress_test
 /set_memory_region_test
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index 8c8eda429576..a6d61f451f88 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -67,6 +67,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/xen_vmcall_test
 TEST_GEN_PROGS_x86_64 += demand_paging_test
 TEST_GEN_PROGS_x86_64 += dirty_log_test
 TEST_GEN_PROGS_x86_64 += dirty_log_perf_test
+TEST_GEN_PROGS_x86_64 += hardware_disable_test
 TEST_GEN_PROGS_x86_64 += kvm_create_max_vcpus
 TEST_GEN_PROGS_x86_64 += memslot_modification_stress_test
 TEST_GEN_PROGS_x86_64 += set_memory_region_test
diff --git a/tools/testing/selftests/kvm/hardware_disable_test.c b/tools/testing/selftests/kvm/hardware_disable_test.c
new file mode 100644
index 000000000000..2f2eeb8a1d86
--- /dev/null
+++ b/tools/testing/selftests/kvm/hardware_disable_test.c
@@ -0,0 +1,165 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * This test is intended to reproduce a crash that happens when
+ * kvm_arch_hardware_disable is called and it attempts to unregister the user
+ * return notifiers.
+ */
+
+#define _GNU_SOURCE
+
+#include <fcntl.h>
+#include <pthread.h>
+#include <semaphore.h>
+#include <stdint.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <sys/wait.h>
+
+#include <test_util.h>
+
+#include "kvm_util.h"
+
+#define VCPU_NUM 4
+#define SLEEPING_THREAD_NUM (1 << 4)
+#define FORK_NUM (1ULL << 9)
+#define DELAY_US_MAX 2000
+#define GUEST_CODE_PIO_PORT 4
+
+sem_t *sem;
+
+/* Arguments for the pthreads */
+struct payload {
+	struct kvm_vm *vm;
+	uint32_t index;
+};
+
+static void guest_code(void)
+{
+	for (;;)
+		;  /* Some busy work */
+	printf("Should not be reached.\n");
+}
+
+static void *run_vcpu(void *arg)
+{
+	struct payload *payload = (struct payload *)arg;
+	struct kvm_run *state = vcpu_state(payload->vm, payload->index);
+
+	vcpu_run(payload->vm, payload->index);
+
+	TEST_ASSERT(false, "%s: exited with reason %d: %s\n",
+		    __func__, state->exit_reason,
+		    exit_reason_str(state->exit_reason));
+	pthread_exit(NULL);
+}
+
+static void *sleeping_thread(void *arg)
+{
+	int fd;
+
+	while (true) {
+		fd = open("/dev/null", O_RDWR);
+		close(fd);
+	}
+	TEST_ASSERT(false, "%s: exited\n", __func__);
+	pthread_exit(NULL);
+}
+
+static inline void check_create_thread(pthread_t *thread, pthread_attr_t *attr,
+				       void *(*f)(void *), void *arg)
+{
+	int r;
+
+	r = pthread_create(thread, attr, f, arg);
+	TEST_ASSERT(r == 0, "%s: failed to create thread", __func__);
+}
+
+static inline void check_set_affinity(pthread_t thread, cpu_set_t *cpu_set)
+{
+	int r;
+
+	r = pthread_setaffinity_np(thread, sizeof(cpu_set_t), cpu_set);
+	TEST_ASSERT(r == 0, "%s: failed set affinity", __func__);
+}
+
+static inline void check_join(pthread_t thread, void **retval)
+{
+	int r;
+
+	r = pthread_join(thread, retval);
+	TEST_ASSERT(r == 0, "%s: failed to join thread", __func__);
+}
+
+static void run_test(uint32_t run)
+{
+	struct kvm_vm *vm;
+	cpu_set_t cpu_set;
+	pthread_t threads[VCPU_NUM];
+	pthread_t throw_away;
+	struct payload payloads[VCPU_NUM];
+	void *b;
+	uint32_t i, j;
+
+	CPU_ZERO(&cpu_set);
+	for (i = 0; i < VCPU_NUM; i++)
+		CPU_SET(i, &cpu_set);
+
+	vm = vm_create(VM_MODE_DEFAULT, DEFAULT_GUEST_PHY_PAGES, O_RDWR);
+	kvm_vm_elf_load(vm, program_invocation_name, 0, 0);
+	vm_create_irqchip(vm);
+
+	fprintf(stderr, "%s: [%d] start vcpus\n", __func__, run);
+	for (i = 0; i < VCPU_NUM; ++i) {
+		vm_vcpu_add_default(vm, i, guest_code);
+		payloads[i].vm = vm;
+		payloads[i].index = i;
+
+		check_create_thread(&threads[i], NULL, run_vcpu,
+				    (void *)&payloads[i]);
+		check_set_affinity(threads[i], &cpu_set);
+
+		for (j = 0; j < SLEEPING_THREAD_NUM; ++j) {
+			check_create_thread(&throw_away, NULL, sleeping_thread,
+					    (void *)NULL);
+			check_set_affinity(throw_away, &cpu_set);
+		}
+	}
+	fprintf(stderr, "%s: [%d] all threads launched\n", __func__, run);
+	sem_post(sem);
+	for (i = 0; i < VCPU_NUM; ++i)
+		check_join(threads[i], &b);
+	/* Should not be reached */
+	TEST_ASSERT(false, "%s: [%d] child escaped the ninja\n", __func__, run);
+}
+
+int main(int argc, char **argv)
+{
+	uint32_t i;
+	int s, r;
+	pid_t pid;
+
+	sem = sem_open("vm_sem", O_CREAT | O_EXCL, 0644, 0);
+	sem_unlink("vm_sem");
+
+	for (i = 0; i < FORK_NUM; ++i) {
+		pid = fork();
+		TEST_ASSERT(pid >= 0, "%s: unable to fork", __func__);
+		if (pid == 0)
+			run_test(i); /* This function always exits */
+
+		fprintf(stderr, "%s: [%d] waiting semaphore\n", __func__, i);
+		sem_wait(sem);
+		r = (rand() % DELAY_US_MAX) + 1;
+		fprintf(stderr, "%s: [%d] waiting %dus\n", __func__, i, r);
+		usleep(r);
+		r = waitpid(pid, &s, WNOHANG);
+		TEST_ASSERT(r != pid,
+			    "%s: [%d] child exited unexpectedly status: [%d]",
+			    __func__, i, s);
+		fprintf(stderr, "%s: [%d] killing child\n", __func__, i);
+		kill(pid, SIGKILL);
+	}
+
+	sem_destroy(sem);
+	exit(0);
+}
diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c
index de0c76177d02..a8906e60a108 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/processor.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c
@@ -720,7 +720,8 @@ struct kvm_cpuid2 *vcpu_get_cpuid(struct kvm_vm *vm, uint32_t vcpuid)
 {
 	struct vcpu *vcpu = vcpu_find(vm, vcpuid);
 	struct kvm_cpuid2 *cpuid;
-	int rc, max_ent;
+	int max_ent;
+	int rc = -1;
 
 	TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);