Merge tag 'v6.1-rc7' into iommufd.git for-next

Resolve conflicts in drivers/vfio/vfio_main.c by using the iommfd version.
The rc fix was done a different way when iommufd patches reworked this
code.

Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>

7 files changed, 279 insertions, 31 deletions

diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore
index 2f0d705db9db..05d980fb083d 100644
--- a/tools/testing/selftests/kvm/.gitignore
+++ b/tools/testing/selftests/kvm/.gitignore
@@ -41,6 +41,7 @@
 /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
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index 0172eb6cb6ee..4a2caef2c939 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -101,6 +101,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/state_test
 TEST_GEN_PROGS_x86_64 += x86_64/vmx_preemption_timer_test
 TEST_GEN_PROGS_x86_64 += x86_64/svm_vmcall_test
 TEST_GEN_PROGS_x86_64 += x86_64/svm_int_ctl_test
+TEST_GEN_PROGS_x86_64 += x86_64/svm_nested_shutdown_test
 TEST_GEN_PROGS_x86_64 += x86_64/svm_nested_soft_inject_test
 TEST_GEN_PROGS_x86_64 += x86_64/tsc_scaling_sync
 TEST_GEN_PROGS_x86_64 += x86_64/sync_regs_test
diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h
index e8ca0d8a6a7e..5da0c5e2a7af 100644
--- a/tools/testing/selftests/kvm/include/x86_64/processor.h
+++ b/tools/testing/selftests/kvm/include/x86_64/processor.h
@@ -748,6 +748,19 @@ struct ex_regs {
 	uint64_t rflags;
 };
 
+struct idt_entry {
+	uint16_t offset0;
+	uint16_t selector;
+	uint16_t ist : 3;
+	uint16_t : 5;
+	uint16_t type : 4;
+	uint16_t : 1;
+	uint16_t dpl : 2;
+	uint16_t p : 1;
+	uint16_t offset1;
+	uint32_t offset2; uint32_t reserved;
+};
+
 void vm_init_descriptor_tables(struct kvm_vm *vm);
 void vcpu_init_descriptor_tables(struct kvm_vcpu *vcpu);
 void vm_install_exception_handler(struct kvm_vm *vm, int vector,
diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c
index 39c4409ef56a..41c1c73c464d 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/processor.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c
@@ -1074,19 +1074,6 @@ void kvm_get_cpu_address_width(unsigned int *pa_bits, unsigned int *va_bits)
 	}
 }
 
-struct idt_entry {
-	uint16_t offset0;
-	uint16_t selector;
-	uint16_t ist : 3;
-	uint16_t : 5;
-	uint16_t type : 4;
-	uint16_t : 1;
-	uint16_t dpl : 2;
-	uint16_t p : 1;
-	uint16_t offset1;
-	uint32_t offset2; uint32_t reserved;
-};
-
 static void set_idt_entry(struct kvm_vm *vm, int vector, unsigned long addr,
 			  int dpl, unsigned short selector)
 {
diff --git a/tools/testing/selftests/kvm/x86_64/svm_nested_shutdown_test.c b/tools/testing/selftests/kvm/x86_64/svm_nested_shutdown_test.c
new file mode 100644
index 000000000000..e73fcdef47bb
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/svm_nested_shutdown_test.c
@@ -0,0 +1,67 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * svm_nested_shutdown_test
+ *
+ * Copyright (C) 2022, Red Hat, Inc.
+ *
+ * Nested SVM testing: test that unintercepted shutdown in L2 doesn't crash the host
+ */
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "processor.h"
+#include "svm_util.h"
+
+static void l2_guest_code(struct svm_test_data *svm)
+{
+	__asm__ __volatile__("ud2");
+}
+
+static void l1_guest_code(struct svm_test_data *svm, struct idt_entry *idt)
+{
+	#define L2_GUEST_STACK_SIZE 64
+	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]);
+
+	vmcb->control.intercept &= ~(BIT(INTERCEPT_SHUTDOWN));
+
+	idt[6].p   = 0; // #UD is intercepted but its injection will cause #NP
+	idt[11].p  = 0; // #NP is not intercepted and will cause another
+			// #NP that will be converted to #DF
+	idt[8].p   = 0; // #DF will cause #NP which will cause SHUTDOWN
+
+	run_guest(vmcb, svm->vmcb_gpa);
+
+	/* should not reach here */
+	GUEST_ASSERT(0);
+}
+
+int main(int argc, char *argv[])
+{
+	struct kvm_vcpu *vcpu;
+	struct kvm_run *run;
+	vm_vaddr_t svm_gva;
+	struct kvm_vm *vm;
+
+	TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_SVM));
+
+	vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code);
+	vm_init_descriptor_tables(vm);
+	vcpu_init_descriptor_tables(vcpu);
+
+	vcpu_alloc_svm(vm, &svm_gva);
+
+	vcpu_args_set(vcpu, 2, svm_gva, vm->idt);
+	run = vcpu->run;
+
+	vcpu_run(vcpu);
+	TEST_ASSERT(run->exit_reason == KVM_EXIT_SHUTDOWN,
+		    "Got exit_reason other than KVM_EXIT_SHUTDOWN: %u (%s)\n",
+		    run->exit_reason,
+		    exit_reason_str(run->exit_reason));
+
+	kvm_vm_free(vm);
+}
diff --git a/tools/testing/selftests/kvm/x86_64/triple_fault_event_test.c b/tools/testing/selftests/kvm/x86_64/triple_fault_event_test.c
index 70b44f0b52fe..ead5d878a71c 100644
--- a/tools/testing/selftests/kvm/x86_64/triple_fault_event_test.c
+++ b/tools/testing/selftests/kvm/x86_64/triple_fault_event_test.c
@@ -3,6 +3,7 @@
 #include "kvm_util.h"
 #include "processor.h"
 #include "vmx.h"
+#include "svm_util.h"
 
 #include <string.h>
 #include <sys/ioctl.h>
@@ -20,10 +21,11 @@ static void l2_guest_code(void)
 		     : : [port] "d" (ARBITRARY_IO_PORT) : "rax");
 }
 
-void l1_guest_code(struct vmx_pages *vmx)
-{
 #define L2_GUEST_STACK_SIZE 64
-	unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE];
+unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE];
+
+void l1_guest_code_vmx(struct vmx_pages *vmx)
+{
 
 	GUEST_ASSERT(vmx->vmcs_gpa);
 	GUEST_ASSERT(prepare_for_vmx_operation(vmx));
@@ -38,24 +40,53 @@ void l1_guest_code(struct vmx_pages *vmx)
 	GUEST_DONE();
 }
 
+void l1_guest_code_svm(struct svm_test_data *svm)
+{
+	struct vmcb *vmcb = svm->vmcb;
+
+	generic_svm_setup(svm, l2_guest_code,
+			&l2_guest_stack[L2_GUEST_STACK_SIZE]);
+
+	/* don't intercept shutdown to test the case of SVM allowing to do so */
+	vmcb->control.intercept &= ~(BIT(INTERCEPT_SHUTDOWN));
+
+	run_guest(vmcb, svm->vmcb_gpa);
+
+	/* should not reach here, L1 should crash  */
+	GUEST_ASSERT(0);
+}
+
 int main(void)
 {
 	struct kvm_vcpu *vcpu;
 	struct kvm_run *run;
 	struct kvm_vcpu_events events;
-	vm_vaddr_t vmx_pages_gva;
 	struct ucall uc;
 
-	TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX));
+	bool has_vmx = kvm_cpu_has(X86_FEATURE_VMX);
+	bool has_svm = kvm_cpu_has(X86_FEATURE_SVM);
+
+	TEST_REQUIRE(has_vmx || has_svm);
 
 	TEST_REQUIRE(kvm_has_cap(KVM_CAP_X86_TRIPLE_FAULT_EVENT));
 
-	vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code);
-	vm_enable_cap(vm, KVM_CAP_X86_TRIPLE_FAULT_EVENT, 1);
 
+	if (has_vmx) {
+		vm_vaddr_t vmx_pages_gva;
+
+		vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code_vmx);
+		vcpu_alloc_vmx(vm, &vmx_pages_gva);
+		vcpu_args_set(vcpu, 1, vmx_pages_gva);
+	} else {
+		vm_vaddr_t svm_gva;
+
+		vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code_svm);
+		vcpu_alloc_svm(vm, &svm_gva);
+		vcpu_args_set(vcpu, 1, svm_gva);
+	}
+
+	vm_enable_cap(vm, KVM_CAP_X86_TRIPLE_FAULT_EVENT, 1);
 	run = vcpu->run;
-	vcpu_alloc_vmx(vm, &vmx_pages_gva);
-	vcpu_args_set(vcpu, 1, vmx_pages_gva);
 	vcpu_run(vcpu);
 
 	TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
@@ -78,13 +109,21 @@ int main(void)
 		    "No triple fault pending");
 	vcpu_run(vcpu);
 
-	switch (get_ucall(vcpu, &uc)) {
-	case UCALL_DONE:
-		break;
-	case UCALL_ABORT:
-		REPORT_GUEST_ASSERT(uc);
-	default:
-		TEST_FAIL("Unexpected ucall: %lu", uc.cmd);
-	}
 
+	if (has_svm) {
+		TEST_ASSERT(run->exit_reason == KVM_EXIT_SHUTDOWN,
+			    "Got exit_reason other than KVM_EXIT_SHUTDOWN: %u (%s)\n",
+			    run->exit_reason,
+			    exit_reason_str(run->exit_reason));
+	} else {
+		switch (get_ucall(vcpu, &uc)) {
+		case UCALL_DONE:
+			break;
+		case UCALL_ABORT:
+			REPORT_GUEST_ASSERT(uc);
+		default:
+			TEST_FAIL("Unexpected ucall: %lu", uc.cmd);
+		}
+	}
+	return 0;
 }
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 8a5cb800f50e..2a5727188c8d 100644
--- a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c
+++ b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c
@@ -15,9 +15,13 @@
 #include <time.h>
 #include <sched.h>
 #include <signal.h>
+#include <pthread.h>
 
 #include <sys/eventfd.h>
 
+/* Defined in include/linux/kvm_types.h */
+#define GPA_INVALID		(~(ulong)0)
+
 #define SHINFO_REGION_GVA	0xc0000000ULL
 #define SHINFO_REGION_GPA	0xc0000000ULL
 #define SHINFO_REGION_SLOT	10
@@ -44,6 +48,8 @@
 
 #define MIN_STEAL_TIME		50000
 
+#define SHINFO_RACE_TIMEOUT	2	/* seconds */
+
 #define __HYPERVISOR_set_timer_op	15
 #define __HYPERVISOR_sched_op		29
 #define __HYPERVISOR_event_channel_op	32
@@ -126,7 +132,7 @@ struct {
 	struct kvm_irq_routing_entry entries[2];
 } irq_routes;
 
-bool guest_saw_irq;
+static volatile bool guest_saw_irq;
 
 static void evtchn_handler(struct ex_regs *regs)
 {
@@ -148,6 +154,7 @@ static void guest_wait_for_irq(void)
 static void guest_code(void)
 {
 	struct vcpu_runstate_info *rs = (void *)RUNSTATE_VADDR;
+	int i;
 
 	__asm__ __volatile__(
 		"sti\n"
@@ -325,6 +332,49 @@ static void guest_code(void)
 	guest_wait_for_irq();
 
 	GUEST_SYNC(21);
+	/* Racing host ioctls */
+
+	guest_wait_for_irq();
+
+	GUEST_SYNC(22);
+	/* Racing vmcall against host ioctl */
+
+	ports[0] = 0;
+
+	p = (struct sched_poll) {
+		.ports = ports,
+		.nr_ports = 1,
+		.timeout = 0
+	};
+
+wait_for_timer:
+	/*
+	 * Poll for a timer wake event while the worker thread is mucking with
+	 * the shared info.  KVM XEN drops timer IRQs if the shared info is
+	 * invalid when the timer expires.  Arbitrarily poll 100 times before
+	 * giving up and asking the VMM to re-arm the timer.  100 polls should
+	 * consume enough time to beat on KVM without taking too long if the
+	 * timer IRQ is dropped due to an invalid event channel.
+	 */
+	for (i = 0; i < 100 && !guest_saw_irq; i++)
+		asm volatile("vmcall"
+			     : "=a" (rax)
+			     : "a" (__HYPERVISOR_sched_op),
+			       "D" (SCHEDOP_poll),
+			       "S" (&p)
+			     : "memory");
+
+	/*
+	 * Re-send the timer IRQ if it was (likely) dropped due to the timer
+	 * expiring while the event channel was invalid.
+	 */
+	if (!guest_saw_irq) {
+		GUEST_SYNC(23);
+		goto wait_for_timer;
+	}
+	guest_saw_irq = false;
+
+	GUEST_SYNC(24);
 }
 
 static int cmp_timespec(struct timespec *a, struct timespec *b)
@@ -352,11 +402,36 @@ static void handle_alrm(int sig)
 	TEST_FAIL("IRQ delivery timed out");
 }
 
+static void *juggle_shinfo_state(void *arg)
+{
+	struct kvm_vm *vm = (struct kvm_vm *)arg;
+
+	struct kvm_xen_hvm_attr cache_init = {
+		.type = KVM_XEN_ATTR_TYPE_SHARED_INFO,
+		.u.shared_info.gfn = SHINFO_REGION_GPA / PAGE_SIZE
+	};
+
+	struct kvm_xen_hvm_attr cache_destroy = {
+		.type = KVM_XEN_ATTR_TYPE_SHARED_INFO,
+		.u.shared_info.gfn = GPA_INVALID
+	};
+
+	for (;;) {
+		__vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &cache_init);
+		__vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &cache_destroy);
+		pthread_testcancel();
+	};
+
+	return NULL;
+}
+
 int main(int argc, char *argv[])
 {
 	struct timespec min_ts, max_ts, vm_ts;
 	struct kvm_vm *vm;
+	pthread_t thread;
 	bool verbose;
+	int ret;
 
 	verbose = argc > 1 && (!strncmp(argv[1], "-v", 3) ||
 			       !strncmp(argv[1], "--verbose", 10));
@@ -785,6 +860,71 @@ int main(int argc, char *argv[])
 			case 21:
 				TEST_ASSERT(!evtchn_irq_expected,
 					    "Expected event channel IRQ but it didn't happen");
+				alarm(0);
+
+				if (verbose)
+					printf("Testing shinfo lock corruption (KVM_XEN_HVM_EVTCHN_SEND)\n");
+
+				ret = pthread_create(&thread, NULL, &juggle_shinfo_state, (void *)vm);
+				TEST_ASSERT(ret == 0, "pthread_create() failed: %s", strerror(ret));
+
+				struct kvm_irq_routing_xen_evtchn uxe = {
+					.port = 1,
+					.vcpu = vcpu->id,
+					.priority = KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL
+				};
+
+				evtchn_irq_expected = true;
+				for (time_t t = time(NULL) + SHINFO_RACE_TIMEOUT; time(NULL) < t;)
+					__vm_ioctl(vm, KVM_XEN_HVM_EVTCHN_SEND, &uxe);
+				break;
+
+			case 22:
+				TEST_ASSERT(!evtchn_irq_expected,
+					    "Expected event channel IRQ but it didn't happen");
+
+				if (verbose)
+					printf("Testing shinfo lock corruption (SCHEDOP_poll)\n");
+
+				shinfo->evtchn_pending[0] = 1;
+
+				evtchn_irq_expected = true;
+				tmr.u.timer.expires_ns = rs->state_entry_time +
+							 SHINFO_RACE_TIMEOUT * 1000000000ULL;
+				vcpu_ioctl(vcpu, KVM_XEN_VCPU_SET_ATTR, &tmr);
+				break;
+
+			case 23:
+				/*
+				 * Optional and possibly repeated sync point.
+				 * Injecting the timer IRQ may fail if the
+				 * shinfo is invalid when the timer expires.
+				 * If the timer has expired but the IRQ hasn't
+				 * been delivered, rearm the timer and retry.
+				 */
+				vcpu_ioctl(vcpu, KVM_XEN_VCPU_GET_ATTR, &tmr);
+
+				/* Resume the guest if the timer is still pending. */
+				if (tmr.u.timer.expires_ns)
+					break;
+
+				/* All done if the IRQ was delivered. */
+				if (!evtchn_irq_expected)
+					break;
+
+				tmr.u.timer.expires_ns = rs->state_entry_time +
+							 SHINFO_RACE_TIMEOUT * 1000000000ULL;
+				vcpu_ioctl(vcpu, KVM_XEN_VCPU_SET_ATTR, &tmr);
+				break;
+			case 24:
+				TEST_ASSERT(!evtchn_irq_expected,
+					    "Expected event channel IRQ but it didn't happen");
+
+				ret = pthread_cancel(thread);
+				TEST_ASSERT(ret == 0, "pthread_cancel() failed: %s", strerror(ret));
+
+				ret = pthread_join(thread, 0);
+				TEST_ASSERT(ret == 0, "pthread_join() failed: %s", strerror(ret));
 				goto done;
 
 			case 0x20: