Merge branch 'kvm-older-features' into HEAD

Merge branch for features that did not make it into 5.18:

* New ioctls to get/set TSC frequency for a whole VM

* Allow userspace to opt out of hypercall patching

Nested virtualization improvements for AMD:

* Support for "nested nested" optimizations (nested vVMLOAD/VMSAVE,
  nested vGIF)

* Allow AVIC to co-exist with a nested guest running

* Fixes for LBR virtualizations when a nested guest is running,
  and nested LBR virtualization support

* PAUSE filtering for nested hypervisors

Guest support:

* Decoupling of vcpu_is_preempted from PV spinlocks

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

5 files changed, 646 insertions, 12 deletions

diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore
index 0b0e4402bba6..56140068b763 100644
--- a/tools/testing/selftests/kvm/.gitignore
+++ b/tools/testing/selftests/kvm/.gitignore
@@ -16,6 +16,7 @@
 /x86_64/debug_regs
 /x86_64/evmcs_test
 /x86_64/emulator_error_test
+/x86_64/fix_hypercall_test
 /x86_64/get_msr_index_features
 /x86_64/kvm_clock_test
 /x86_64/kvm_pv_test
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index 681b173aa87c..af582d168621 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -48,6 +48,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/cr4_cpuid_sync_test
 TEST_GEN_PROGS_x86_64 += x86_64/get_msr_index_features
 TEST_GEN_PROGS_x86_64 += x86_64/evmcs_test
 TEST_GEN_PROGS_x86_64 += x86_64/emulator_error_test
+TEST_GEN_PROGS_x86_64 += x86_64/fix_hypercall_test
 TEST_GEN_PROGS_x86_64 += x86_64/hyperv_clock
 TEST_GEN_PROGS_x86_64 += x86_64/hyperv_cpuid
 TEST_GEN_PROGS_x86_64 += x86_64/hyperv_features
@@ -65,6 +66,7 @@ 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/tsc_scaling_sync
 TEST_GEN_PROGS_x86_64 += x86_64/sync_regs_test
 TEST_GEN_PROGS_x86_64 += x86_64/userspace_io_test
 TEST_GEN_PROGS_x86_64 += x86_64/userspace_msr_exit_test
diff --git a/tools/testing/selftests/kvm/x86_64/fix_hypercall_test.c b/tools/testing/selftests/kvm/x86_64/fix_hypercall_test.c
new file mode 100644
index 000000000000..1f5c32146f3d
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/fix_hypercall_test.c
@@ -0,0 +1,170 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2020, Google LLC.
+ *
+ * Tests for KVM paravirtual feature disablement
+ */
+#include <asm/kvm_para.h>
+#include <linux/kvm_para.h>
+#include <linux/stringify.h>
+#include <stdint.h>
+
+#include "apic.h"
+#include "test_util.h"
+#include "kvm_util.h"
+#include "processor.h"
+
+#define VCPU_ID 0
+
+static bool ud_expected;
+
+static void guest_ud_handler(struct ex_regs *regs)
+{
+	GUEST_ASSERT(ud_expected);
+	GUEST_DONE();
+}
+
+extern unsigned char svm_hypercall_insn;
+static uint64_t svm_do_sched_yield(uint8_t apic_id)
+{
+	uint64_t ret;
+
+	asm volatile("mov %1, %%rax\n\t"
+		     "mov %2, %%rbx\n\t"
+		     "svm_hypercall_insn:\n\t"
+		     "vmmcall\n\t"
+		     "mov %%rax, %0\n\t"
+		     : "=r"(ret)
+		     : "r"((uint64_t)KVM_HC_SCHED_YIELD), "r"((uint64_t)apic_id)
+		     : "rax", "rbx", "memory");
+
+	return ret;
+}
+
+extern unsigned char vmx_hypercall_insn;
+static uint64_t vmx_do_sched_yield(uint8_t apic_id)
+{
+	uint64_t ret;
+
+	asm volatile("mov %1, %%rax\n\t"
+		     "mov %2, %%rbx\n\t"
+		     "vmx_hypercall_insn:\n\t"
+		     "vmcall\n\t"
+		     "mov %%rax, %0\n\t"
+		     : "=r"(ret)
+		     : "r"((uint64_t)KVM_HC_SCHED_YIELD), "r"((uint64_t)apic_id)
+		     : "rax", "rbx", "memory");
+
+	return ret;
+}
+
+static void assert_hypercall_insn(unsigned char *exp_insn, unsigned char *obs_insn)
+{
+	uint32_t exp = 0, obs = 0;
+
+	memcpy(&exp, exp_insn, sizeof(exp));
+	memcpy(&obs, obs_insn, sizeof(obs));
+
+	GUEST_ASSERT_EQ(exp, obs);
+}
+
+static void guest_main(void)
+{
+	unsigned char *native_hypercall_insn, *hypercall_insn;
+	uint8_t apic_id;
+
+	apic_id = GET_APIC_ID_FIELD(xapic_read_reg(APIC_ID));
+
+	if (is_intel_cpu()) {
+		native_hypercall_insn = &vmx_hypercall_insn;
+		hypercall_insn = &svm_hypercall_insn;
+		svm_do_sched_yield(apic_id);
+	} else if (is_amd_cpu()) {
+		native_hypercall_insn = &svm_hypercall_insn;
+		hypercall_insn = &vmx_hypercall_insn;
+		vmx_do_sched_yield(apic_id);
+	} else {
+		GUEST_ASSERT(0);
+		/* unreachable */
+		return;
+	}
+
+	GUEST_ASSERT(!ud_expected);
+	assert_hypercall_insn(native_hypercall_insn, hypercall_insn);
+	GUEST_DONE();
+}
+
+static void setup_ud_vector(struct kvm_vm *vm)
+{
+	vm_init_descriptor_tables(vm);
+	vcpu_init_descriptor_tables(vm, VCPU_ID);
+	vm_install_exception_handler(vm, UD_VECTOR, guest_ud_handler);
+}
+
+static void enter_guest(struct kvm_vm *vm)
+{
+	struct kvm_run *run;
+	struct ucall uc;
+
+	run = vcpu_state(vm, VCPU_ID);
+
+	vcpu_run(vm, VCPU_ID);
+	switch (get_ucall(vm, VCPU_ID, &uc)) {
+	case UCALL_SYNC:
+		pr_info("%s: %016lx\n", (const char *)uc.args[2], uc.args[3]);
+		break;
+	case UCALL_DONE:
+		return;
+	case UCALL_ABORT:
+		TEST_FAIL("%s at %s:%ld", (const char *)uc.args[0], __FILE__, uc.args[1]);
+	default:
+		TEST_FAIL("Unhandled ucall: %ld\nexit_reason: %u (%s)",
+			  uc.cmd, run->exit_reason, exit_reason_str(run->exit_reason));
+	}
+}
+
+static void test_fix_hypercall(void)
+{
+	struct kvm_vm *vm;
+
+	vm = vm_create_default(VCPU_ID, 0, guest_main);
+	setup_ud_vector(vm);
+
+	ud_expected = false;
+	sync_global_to_guest(vm, ud_expected);
+
+	virt_pg_map(vm, APIC_DEFAULT_GPA, APIC_DEFAULT_GPA);
+
+	enter_guest(vm);
+}
+
+static void test_fix_hypercall_disabled(void)
+{
+	struct kvm_enable_cap cap = {0};
+	struct kvm_vm *vm;
+
+	vm = vm_create_default(VCPU_ID, 0, guest_main);
+	setup_ud_vector(vm);
+
+	cap.cap = KVM_CAP_DISABLE_QUIRKS2;
+	cap.args[0] = KVM_X86_QUIRK_FIX_HYPERCALL_INSN;
+	vm_enable_cap(vm, &cap);
+
+	ud_expected = true;
+	sync_global_to_guest(vm, ud_expected);
+
+	virt_pg_map(vm, APIC_DEFAULT_GPA, APIC_DEFAULT_GPA);
+
+	enter_guest(vm);
+}
+
+int main(void)
+{
+	if (!(kvm_check_cap(KVM_CAP_DISABLE_QUIRKS2) & KVM_X86_QUIRK_FIX_HYPERCALL_INSN)) {
+		print_skip("KVM_X86_QUIRK_HYPERCALL_INSN not supported");
+		exit(KSFT_SKIP);
+	}
+
+	test_fix_hypercall();
+	test_fix_hypercall_disabled();
+}
diff --git a/tools/testing/selftests/kvm/x86_64/tsc_scaling_sync.c b/tools/testing/selftests/kvm/x86_64/tsc_scaling_sync.c
new file mode 100644
index 000000000000..f0083d8cfe98
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/tsc_scaling_sync.c
@@ -0,0 +1,119 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * svm_vmcall_test
+ *
+ * Copyright © 2021 Amazon.com, Inc. or its affiliates.
+ *
+ * Xen shared_info / pvclock testing
+ */
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "processor.h"
+
+#include <stdint.h>
+#include <time.h>
+#include <sched.h>
+#include <signal.h>
+#include <pthread.h>
+
+#define NR_TEST_VCPUS 20
+
+static struct kvm_vm *vm;
+pthread_spinlock_t create_lock;
+
+#define TEST_TSC_KHZ    2345678UL
+#define TEST_TSC_OFFSET 200000000
+
+uint64_t tsc_sync;
+static void guest_code(void)
+{
+	uint64_t start_tsc, local_tsc, tmp;
+
+	start_tsc = rdtsc();
+	do {
+		tmp = READ_ONCE(tsc_sync);
+		local_tsc = rdtsc();
+		WRITE_ONCE(tsc_sync, local_tsc);
+		if (unlikely(local_tsc < tmp))
+			GUEST_SYNC_ARGS(0, local_tsc, tmp, 0, 0);
+
+	} while (local_tsc - start_tsc < 5000 * TEST_TSC_KHZ);
+
+	GUEST_DONE();
+}
+
+
+static void *run_vcpu(void *_cpu_nr)
+{
+	unsigned long cpu = (unsigned long)_cpu_nr;
+	unsigned long failures = 0;
+	static bool first_cpu_done;
+
+	/* The kernel is fine, but vm_vcpu_add_default() needs locking */
+	pthread_spin_lock(&create_lock);
+
+	vm_vcpu_add_default(vm, cpu, guest_code);
+
+	if (!first_cpu_done) {
+		first_cpu_done = true;
+		vcpu_set_msr(vm, cpu, MSR_IA32_TSC, TEST_TSC_OFFSET);
+	}
+
+	pthread_spin_unlock(&create_lock);
+
+	for (;;) {
+		volatile struct kvm_run *run = vcpu_state(vm, cpu);
+                struct ucall uc;
+
+                vcpu_run(vm, cpu);
+                TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
+                            "Got exit_reason other than KVM_EXIT_IO: %u (%s)\n",
+                            run->exit_reason,
+                            exit_reason_str(run->exit_reason));
+
+                switch (get_ucall(vm, cpu, &uc)) {
+                case UCALL_DONE:
+			goto out;
+
+                case UCALL_SYNC:
+			printf("Guest %ld sync %lx %lx %ld\n", cpu, uc.args[2], uc.args[3], uc.args[2] - uc.args[3]);
+			failures++;
+			break;
+
+                default:
+                        TEST_FAIL("Unknown ucall %lu", uc.cmd);
+		}
+	}
+ out:
+	return (void *)failures;
+}
+
+int main(int argc, char *argv[])
+{
+        if (!kvm_check_cap(KVM_CAP_VM_TSC_CONTROL)) {
+		print_skip("KVM_CAP_VM_TSC_CONTROL not available");
+		exit(KSFT_SKIP);
+	}
+
+	vm = vm_create_default_with_vcpus(0, DEFAULT_STACK_PGS * NR_TEST_VCPUS, 0, guest_code, NULL);
+	vm_ioctl(vm, KVM_SET_TSC_KHZ, (void *) TEST_TSC_KHZ);
+
+	pthread_spin_init(&create_lock, PTHREAD_PROCESS_PRIVATE);
+	pthread_t cpu_threads[NR_TEST_VCPUS];
+	unsigned long cpu;
+	for (cpu = 0; cpu < NR_TEST_VCPUS; cpu++)
+		pthread_create(&cpu_threads[cpu], NULL, run_vcpu, (void *)cpu);
+
+	unsigned long failures = 0;
+	for (cpu = 0; cpu < NR_TEST_VCPUS; cpu++) {
+		void *this_cpu_failures;
+		pthread_join(cpu_threads[cpu], &this_cpu_failures);
+		failures += (unsigned long)this_cpu_failures;
+	}
+
+	TEST_ASSERT(!failures, "TSC sync failed");
+	pthread_spin_destroy(&create_lock);
+	kvm_vm_free(vm);
+	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 865e17146815..d9d9d1deec45 100644
--- a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c
+++ b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c
@@ -39,12 +39,36 @@
 
 #define EVTCHN_VECTOR	0x10
 
+#define EVTCHN_TEST1 15
+#define EVTCHN_TEST2 66
+#define EVTCHN_TIMER 13
+
 static struct kvm_vm *vm;
 
 #define XEN_HYPERCALL_MSR	0x40000000
 
 #define MIN_STEAL_TIME		50000
 
+#define __HYPERVISOR_set_timer_op	15
+#define __HYPERVISOR_sched_op		29
+#define __HYPERVISOR_event_channel_op	32
+
+#define SCHEDOP_poll			3
+
+#define EVTCHNOP_send			4
+
+#define EVTCHNSTAT_interdomain		2
+
+struct evtchn_send {
+	u32 port;
+};
+
+struct sched_poll {
+	u32 *ports;
+	unsigned int nr_ports;
+	u64 timeout;
+};
+
 struct pvclock_vcpu_time_info {
 	u32   version;
 	u32   pad0;
@@ -107,15 +131,25 @@ struct {
 	struct kvm_irq_routing_entry entries[2];
 } irq_routes;
 
+bool guest_saw_irq;
+
 static void evtchn_handler(struct ex_regs *regs)
 {
 	struct vcpu_info *vi = (void *)VCPU_INFO_VADDR;
 	vi->evtchn_upcall_pending = 0;
 	vi->evtchn_pending_sel = 0;
+	guest_saw_irq = true;
 
 	GUEST_SYNC(0x20);
 }
 
+static void guest_wait_for_irq(void)
+{
+	while (!guest_saw_irq)
+		__asm__ __volatile__ ("rep nop" : : : "memory");
+	guest_saw_irq = false;
+}
+
 static void guest_code(void)
 {
 	struct vcpu_runstate_info *rs = (void *)RUNSTATE_VADDR;
@@ -128,6 +162,8 @@ static void guest_code(void)
 	/* Trigger an interrupt injection */
 	GUEST_SYNC(0);
 
+	guest_wait_for_irq();
+
 	/* Test having the host set runstates manually */
 	GUEST_SYNC(RUNSTATE_runnable);
 	GUEST_ASSERT(rs->time[RUNSTATE_runnable] != 0);
@@ -168,14 +204,132 @@ static void guest_code(void)
 	/* Now deliver an *unmasked* interrupt */
 	GUEST_SYNC(8);
 
-	while (!si->evtchn_pending[1])
-		__asm__ __volatile__ ("rep nop" : : : "memory");
+	guest_wait_for_irq();
 
 	/* Change memslots and deliver an interrupt */
 	GUEST_SYNC(9);
 
-	for (;;)
-		__asm__ __volatile__ ("rep nop" : : : "memory");
+	guest_wait_for_irq();
+
+	/* Deliver event channel with KVM_XEN_HVM_EVTCHN_SEND */
+	GUEST_SYNC(10);
+
+	guest_wait_for_irq();
+
+	GUEST_SYNC(11);
+
+	/* Our turn. Deliver event channel (to ourselves) with
+	 * EVTCHNOP_send hypercall. */
+	unsigned long rax;
+	struct evtchn_send s = { .port = 127 };
+	__asm__ __volatile__ ("vmcall" :
+			      "=a" (rax) :
+			      "a" (__HYPERVISOR_event_channel_op),
+			      "D" (EVTCHNOP_send),
+			      "S" (&s));
+
+	GUEST_ASSERT(rax == 0);
+
+	guest_wait_for_irq();
+
+	GUEST_SYNC(12);
+
+	/* Deliver "outbound" event channel to an eventfd which
+	 * happens to be one of our own irqfds. */
+	s.port = 197;
+	__asm__ __volatile__ ("vmcall" :
+			      "=a" (rax) :
+			      "a" (__HYPERVISOR_event_channel_op),
+			      "D" (EVTCHNOP_send),
+			      "S" (&s));
+
+	GUEST_ASSERT(rax == 0);
+
+	guest_wait_for_irq();
+
+	GUEST_SYNC(13);
+
+	/* Set a timer 100ms in the future. */
+	__asm__ __volatile__ ("vmcall" :
+			      "=a" (rax) :
+			      "a" (__HYPERVISOR_set_timer_op),
+			      "D" (rs->state_entry_time + 100000000));
+	GUEST_ASSERT(rax == 0);
+
+	GUEST_SYNC(14);
+
+	/* Now wait for the timer */
+	guest_wait_for_irq();
+
+	GUEST_SYNC(15);
+
+	/* The host has 'restored' the timer. Just wait for it. */
+	guest_wait_for_irq();
+
+	GUEST_SYNC(16);
+
+	/* Poll for an event channel port which is already set */
+	u32 ports[1] = { EVTCHN_TIMER };
+	struct sched_poll p = {
+		.ports = ports,
+		.nr_ports = 1,
+		.timeout = 0,
+	};
+
+	__asm__ __volatile__ ("vmcall" :
+			      "=a" (rax) :
+			      "a" (__HYPERVISOR_sched_op),
+			      "D" (SCHEDOP_poll),
+			      "S" (&p));
+
+	GUEST_ASSERT(rax == 0);
+
+	GUEST_SYNC(17);
+
+	/* Poll for an unset port and wait for the timeout. */
+	p.timeout = 100000000;
+	__asm__ __volatile__ ("vmcall" :
+			      "=a" (rax) :
+			      "a" (__HYPERVISOR_sched_op),
+			      "D" (SCHEDOP_poll),
+			      "S" (&p));
+
+	GUEST_ASSERT(rax == 0);
+
+	GUEST_SYNC(18);
+
+	/* A timer will wake the masked port we're waiting on, while we poll */
+	p.timeout = 0;
+	__asm__ __volatile__ ("vmcall" :
+			      "=a" (rax) :
+			      "a" (__HYPERVISOR_sched_op),
+			      "D" (SCHEDOP_poll),
+			      "S" (&p));
+
+	GUEST_ASSERT(rax == 0);
+
+	GUEST_SYNC(19);
+
+	/* A timer wake an *unmasked* port which should wake us with an
+	 * actual interrupt, while we're polling on a different port. */
+	ports[0]++;
+	p.timeout = 0;
+	__asm__ __volatile__ ("vmcall" :
+			      "=a" (rax) :
+			      "a" (__HYPERVISOR_sched_op),
+			      "D" (SCHEDOP_poll),
+			      "S" (&p));
+
+	GUEST_ASSERT(rax == 0);
+
+	guest_wait_for_irq();
+
+	GUEST_SYNC(20);
+
+	/* Timer should have fired already */
+	guest_wait_for_irq();
+
+	GUEST_SYNC(21);
 }
 
 static int cmp_timespec(struct timespec *a, struct timespec *b)
@@ -191,9 +345,13 @@ static int cmp_timespec(struct timespec *a, struct timespec *b)
 	else
 		return 0;
 }
+struct vcpu_info *vinfo;
 
 static void handle_alrm(int sig)
 {
+	if (vinfo)
+		printf("evtchn_upcall_pending 0x%x\n", vinfo->evtchn_upcall_pending);
+	vcpu_dump(stdout, vm, VCPU_ID, 0);
 	TEST_FAIL("IRQ delivery timed out");
 }
 
@@ -213,6 +371,7 @@ int main(int argc, char *argv[])
 
 	bool do_runstate_tests = !!(xen_caps & KVM_XEN_HVM_CONFIG_RUNSTATE);
 	bool do_eventfd_tests = !!(xen_caps & KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL);
+	bool do_evtchn_tests = do_eventfd_tests && !!(xen_caps & KVM_XEN_HVM_CONFIG_EVTCHN_SEND);
 
 	clock_gettime(CLOCK_REALTIME, &min_ts);
 
@@ -233,6 +392,12 @@ int main(int argc, char *argv[])
 		.flags = KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL,
 		.msr = XEN_HYPERCALL_MSR,
 	};
+
+	/* Let the kernel know that we *will* use it for sending all
+	 * event channels, which lets it intercept SCHEDOP_poll */
+	if (do_evtchn_tests)
+		hvmc.flags |= KVM_XEN_HVM_CONFIG_EVTCHN_SEND;
+
 	vm_ioctl(vm, KVM_XEN_HVM_CONFIG, &hvmc);
 
 	struct kvm_xen_hvm_attr lm = {
@@ -295,7 +460,7 @@ int main(int argc, char *argv[])
 
 		/* Unexpected, but not a KVM failure */
 		if (irq_fd[0] == -1 || irq_fd[1] == -1)
-			do_eventfd_tests = false;
+			do_evtchn_tests = do_eventfd_tests = false;
 	}
 
 	if (do_eventfd_tests) {
@@ -303,13 +468,13 @@ int main(int argc, char *argv[])
 
 		irq_routes.entries[0].gsi = 32;
 		irq_routes.entries[0].type = KVM_IRQ_ROUTING_XEN_EVTCHN;
-		irq_routes.entries[0].u.xen_evtchn.port = 15;
+		irq_routes.entries[0].u.xen_evtchn.port = EVTCHN_TEST1;
 		irq_routes.entries[0].u.xen_evtchn.vcpu = VCPU_ID;
 		irq_routes.entries[0].u.xen_evtchn.priority = KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL;
 
 		irq_routes.entries[1].gsi = 33;
 		irq_routes.entries[1].type = KVM_IRQ_ROUTING_XEN_EVTCHN;
-		irq_routes.entries[1].u.xen_evtchn.port = 66;
+		irq_routes.entries[1].u.xen_evtchn.port = EVTCHN_TEST2;
 		irq_routes.entries[1].u.xen_evtchn.vcpu = VCPU_ID;
 		irq_routes.entries[1].u.xen_evtchn.priority = KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL;
 
@@ -330,7 +495,39 @@ int main(int argc, char *argv[])
 		sigaction(SIGALRM, &sa, NULL);
 	}
 
-	struct vcpu_info *vinfo = addr_gpa2hva(vm, VCPU_INFO_VADDR);
+	struct kvm_xen_vcpu_attr tmr = {
+		.type = KVM_XEN_VCPU_ATTR_TYPE_TIMER,
+		.u.timer.port = EVTCHN_TIMER,
+		.u.timer.priority = KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL,
+		.u.timer.expires_ns = 0
+	};
+
+	if (do_evtchn_tests) {
+		struct kvm_xen_hvm_attr inj = {
+			.type = KVM_XEN_ATTR_TYPE_EVTCHN,
+			.u.evtchn.send_port = 127,
+			.u.evtchn.type = EVTCHNSTAT_interdomain,
+			.u.evtchn.flags = 0,
+			.u.evtchn.deliver.port.port = EVTCHN_TEST1,
+			.u.evtchn.deliver.port.vcpu = VCPU_ID + 1,
+			.u.evtchn.deliver.port.priority = KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL,
+		};
+		vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &inj);
+
+		/* Test migration to a different vCPU */
+		inj.u.evtchn.flags = KVM_XEN_EVTCHN_UPDATE;
+		inj.u.evtchn.deliver.port.vcpu = VCPU_ID;
+		vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &inj);
+
+		inj.u.evtchn.send_port = 197;
+		inj.u.evtchn.deliver.eventfd.port = 0;
+		inj.u.evtchn.deliver.eventfd.fd = irq_fd[1];
+		inj.u.evtchn.flags = 0;
+		vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &inj);
+
+		vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &tmr);
+	}
+	vinfo = addr_gpa2hva(vm, VCPU_INFO_VADDR);
 	vinfo->evtchn_upcall_pending = 0;
 
 	struct vcpu_runstate_info *rs = addr_gpa2hva(vm, RUNSTATE_ADDR);
@@ -423,7 +620,7 @@ int main(int argc, char *argv[])
 					goto done;
 				if (verbose)
 					printf("Testing masked event channel\n");
-				shinfo->evtchn_mask[0] = 0x8000;
+				shinfo->evtchn_mask[0] = 1UL << EVTCHN_TEST1;
 				eventfd_write(irq_fd[0], 1UL);
 				alarm(1);
 				break;
@@ -440,6 +637,9 @@ int main(int argc, char *argv[])
 				break;
 
 			case 9:
+				TEST_ASSERT(!evtchn_irq_expected,
+					    "Expected event channel IRQ but it didn't happen");
+				shinfo->evtchn_pending[1] = 0;
 				if (verbose)
 					printf("Testing event channel after memslot change\n");
 				vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS,
@@ -449,12 +649,153 @@ int main(int argc, char *argv[])
 				alarm(1);
 				break;
 
+			case 10:
+				TEST_ASSERT(!evtchn_irq_expected,
+					    "Expected event channel IRQ but it didn't happen");
+				if (!do_evtchn_tests)
+					goto done;
+
+				shinfo->evtchn_pending[0] = 0;
+				if (verbose)
+					printf("Testing injection with KVM_XEN_HVM_EVTCHN_SEND\n");
+
+				struct kvm_irq_routing_xen_evtchn e;
+				e.port = EVTCHN_TEST2;
+				e.vcpu = VCPU_ID;
+				e.priority = KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL;
+
+				vm_ioctl(vm, KVM_XEN_HVM_EVTCHN_SEND, &e);
+				evtchn_irq_expected = true;
+				alarm(1);
+				break;
+
+			case 11:
+				TEST_ASSERT(!evtchn_irq_expected,
+					    "Expected event channel IRQ but it didn't happen");
+				shinfo->evtchn_pending[1] = 0;
+
+				if (verbose)
+					printf("Testing guest EVTCHNOP_send direct to evtchn\n");
+				evtchn_irq_expected = true;
+				alarm(1);
+				break;
+
+			case 12:
+				TEST_ASSERT(!evtchn_irq_expected,
+					    "Expected event channel IRQ but it didn't happen");
+				shinfo->evtchn_pending[0] = 0;
+
+				if (verbose)
+					printf("Testing guest EVTCHNOP_send to eventfd\n");
+				evtchn_irq_expected = true;
+				alarm(1);
+				break;
+
+			case 13:
+				TEST_ASSERT(!evtchn_irq_expected,
+					    "Expected event channel IRQ but it didn't happen");
+				shinfo->evtchn_pending[1] = 0;
+
+				if (verbose)
+					printf("Testing guest oneshot timer\n");
+				break;
+
+			case 14:
+				memset(&tmr, 0, sizeof(tmr));
+				tmr.type = KVM_XEN_VCPU_ATTR_TYPE_TIMER,
+				vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_GET_ATTR, &tmr);
+				TEST_ASSERT(tmr.u.timer.port == EVTCHN_TIMER,
+					    "Timer port not returned");
+				TEST_ASSERT(tmr.u.timer.priority == KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL,
+					    "Timer priority not returned");
+				TEST_ASSERT(tmr.u.timer.expires_ns > rs->state_entry_time,
+					    "Timer expiry not returned");
+				evtchn_irq_expected = true;
+				alarm(1);
+				break;
+
+			case 15:
+				TEST_ASSERT(!evtchn_irq_expected,
+					    "Expected event channel IRQ but it didn't happen");
+				shinfo->evtchn_pending[0] = 0;
+
+				if (verbose)
+					printf("Testing restored oneshot timer\n");
+
+				tmr.u.timer.expires_ns = rs->state_entry_time + 100000000,
+				vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &tmr);
+				evtchn_irq_expected = true;
+				alarm(1);
+				break;
+
+			case 16:
+				TEST_ASSERT(!evtchn_irq_expected,
+					    "Expected event channel IRQ but it didn't happen");
+
+				if (verbose)
+					printf("Testing SCHEDOP_poll with already pending event\n");
+				shinfo->evtchn_pending[0] = shinfo->evtchn_mask[0] = 1UL << EVTCHN_TIMER;
+				alarm(1);
+				break;
+
+			case 17:
+				if (verbose)
+					printf("Testing SCHEDOP_poll timeout\n");
+				shinfo->evtchn_pending[0] = 0;
+				alarm(1);
+				break;
+
+			case 18:
+				if (verbose)
+					printf("Testing SCHEDOP_poll wake on masked event\n");
+
+				tmr.u.timer.expires_ns = rs->state_entry_time + 100000000,
+				vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &tmr);
+				alarm(1);
+				break;
+
+			case 19:
+				shinfo->evtchn_pending[0] = shinfo->evtchn_mask[0] = 0;
+				if (verbose)
+					printf("Testing SCHEDOP_poll wake on unmasked event\n");
+
+				evtchn_irq_expected = true;
+				tmr.u.timer.expires_ns = rs->state_entry_time + 100000000;
+				vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &tmr);
+
+				/* Read it back and check the pending time is reported correctly */
+				tmr.u.timer.expires_ns = 0;
+				vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_GET_ATTR, &tmr);
+				TEST_ASSERT(tmr.u.timer.expires_ns == rs->state_entry_time + 100000000,
+					    "Timer not reported pending");
+				alarm(1);
+				break;
+
+			case 20:
+				TEST_ASSERT(!evtchn_irq_expected,
+					    "Expected event channel IRQ but it didn't happen");
+				/* Read timer and check it is no longer pending */
+				vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_GET_ATTR, &tmr);
+				TEST_ASSERT(!tmr.u.timer.expires_ns, "Timer still reported pending");
+
+				shinfo->evtchn_pending[0] = 0;
+				if (verbose)
+					printf("Testing timer in the past\n");
+
+				evtchn_irq_expected = true;
+				tmr.u.timer.expires_ns = rs->state_entry_time - 100000000ULL;
+				vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &tmr);
+				alarm(1);
+				break;
+
+			case 21:
+				TEST_ASSERT(!evtchn_irq_expected,
+					    "Expected event channel IRQ but it didn't happen");
+				goto done;
+
 			case 0x20:
 				TEST_ASSERT(evtchn_irq_expected, "Unexpected event channel IRQ");
 				evtchn_irq_expected = false;
-				if (shinfo->evtchn_pending[1] &&
-				    shinfo->evtchn_pending[0])
-					goto done;
 				break;
 			}
 			break;
@@ -467,6 +808,7 @@ int main(int argc, char *argv[])
 	}
 
  done:
+	alarm(0);
 	clock_gettime(CLOCK_REALTIME, &max_ts);
 
 	/*