mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: David Woodhouse <dwmw2@infradead.org>
To: kvm@vger.kernel.org
Cc: linux-kernel@vger.kernel.org, linux-kselftest@vger.kernel.org,
	rcu@vger.kernel.org, linux-rt-devel@lists.linux.dev,
	Paolo Bonzini <pbonzini@redhat.com>,
	Sean Christopherson <seanjc@google.com>,
	Paul Durrant <paul@xen.org>,
	Vitaly Kuznetsov <vkuznets@redhat.com>,
	Fred Griffoul <fgriffo@amazon.co.uk>,
	"Paul E . McKenney" <paulmck@kernel.org>,
	Kunwu Chan <kunwu.chan@linux.dev>,
	Kunwu Chan <kunwu.chan@gmail.com>,
	syzbot+208f7f3e5f59c11aeb90@syzkaller.appspotmail.com,
	David Woodhouse <dwmw@amazon.co.uk>
Subject: [PATCH v2 14/20] KVM: selftests: Add nested VMX APIC cache invalidation test
Date: Thu,  5 Nov 2026 02:00:56 +0000	[thread overview]
Message-ID: <20261105020104.2507083-15-dwmw2@infradead.org> (raw)
In-Reply-To: <20261105020104.2507083-1-dwmw2@infradead.org>

From: Fred Griffoul <fgriffo@amazon.co.uk>

Add a selftest for the nested VMX APIC page caches: an L2 guest
writes the APIC-access page while a second thread repeatedly
invalidates the underlying mapping, either with
madvise(MADV_DONTNEED) (MMU notifier path) or by moving the memslot
away and back (memslot update path), so the GPA under test is
repeatedly unbacked and re-latched.

The test asserts that L2 keeps running across the invalidations with
no guest-visible errors, that at least one invalidation actually ran
concurrently, and that the access only ever bounces to userspace as
MMIO in the memslot-move variant (while the slot is moved away the
GPA is unbacked; madvise never unbacks the GPA, so an MMIO exit
there means KVM lost the mapping).

Signed-off-by: Fred Griffoul <fgriffo@amazon.co.uk>

[dwmw2: Adapt to selftest API drift since the v4 posting: prepare_vmcs()
        no longer takes an L2 stack (4c396f19de5d), vm_vaddr_t is now
        gva_t, and the prepare_eptp()/nested_map*() EPT helpers were
        replaced by vm_enable_tdp()/tdp_map()/
        tdp_identity_map_default_memslots().]
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Assisted-by: LLM
---
 tools/testing/selftests/kvm/Makefile.kvm      |   1 +
 .../selftests/kvm/x86/vmx_apic_update_test.c  | 323 ++++++++++++++++++
 2 files changed, 324 insertions(+)
 create mode 100644 tools/testing/selftests/kvm/x86/vmx_apic_update_test.c

diff --git a/tools/testing/selftests/kvm/Makefile.kvm b/tools/testing/selftests/kvm/Makefile.kvm
index 17a4256e9081..dcfe815f4a02 100644
--- a/tools/testing/selftests/kvm/Makefile.kvm
+++ b/tools/testing/selftests/kvm/Makefile.kvm
@@ -161,6 +161,7 @@ TEST_GEN_PROGS_x86 += x86/triple_fault_event_test
 TEST_GEN_PROGS_x86 += x86/recalc_apic_map_test
 TEST_GEN_PROGS_x86 += x86/aperfmperf_test
 TEST_GEN_PROGS_x86 += x86/guest_memfd_conversions_test
+TEST_GEN_PROGS_x86 += x86/vmx_apic_update_test
 TEST_GEN_PROGS_x86 += access_tracking_perf_test
 TEST_GEN_PROGS_x86 += coalesced_io_test
 TEST_GEN_PROGS_x86 += dirty_log_perf_test
diff --git a/tools/testing/selftests/kvm/x86/vmx_apic_update_test.c b/tools/testing/selftests/kvm/x86/vmx_apic_update_test.c
new file mode 100644
index 000000000000..357e10c88cd0
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86/vmx_apic_update_test.c
@@ -0,0 +1,323 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * vmx_apic_update_test
+ *
+ * Copyright (C) 2025, Amazon.com, Inc. or its affiliates. All Rights Reserved.
+ *
+ * Test L2 guest APIC access page writes with concurrent MMU
+ * notification and memslot move updates.
+ */
+#include <limits.h>
+#include <pthread.h>
+#include "test_util.h"
+#include "kvm_util.h"
+#include "processor.h"
+#include "vmx.h"
+
+#define VAPIC_GPA	0xc0000000
+#define VAPIC_SLOT	1
+
+
+#define L2_DELAY	(100)
+
+static void l2_guest_code(void)
+{
+	uint32_t *vapic_addr = (uint32_t *) (VAPIC_GPA + 0x80);
+
+	/* Unroll the loop to avoid any compiler side effect */
+
+	WRITE_ONCE(*vapic_addr, 1 << 0);
+	udelay(msecs_to_usecs(L2_DELAY));
+
+	WRITE_ONCE(*vapic_addr, 1 << 1);
+	udelay(msecs_to_usecs(L2_DELAY));
+
+	WRITE_ONCE(*vapic_addr, 1 << 2);
+	udelay(msecs_to_usecs(L2_DELAY));
+
+	WRITE_ONCE(*vapic_addr, 1 << 3);
+	udelay(msecs_to_usecs(L2_DELAY));
+
+	WRITE_ONCE(*vapic_addr, 1 << 4);
+	udelay(msecs_to_usecs(L2_DELAY));
+
+	WRITE_ONCE(*vapic_addr, 1 << 5);
+	udelay(msecs_to_usecs(L2_DELAY));
+
+	WRITE_ONCE(*vapic_addr, 1 << 6);
+	udelay(msecs_to_usecs(L2_DELAY));
+
+	WRITE_ONCE(*vapic_addr, 0);
+	udelay(msecs_to_usecs(L2_DELAY));
+
+	/* Exit to L1 */
+	vmcall();
+}
+
+static void l1_guest_code(struct vmx_pages *vmx_pages)
+{
+	uint32_t control, exit_reason;
+
+	prepare_for_vmx_operation(vmx_pages);
+	load_vmcs(vmx_pages);
+	prepare_vmcs(vmx_pages, l2_guest_code);
+
+	/* Enable APIC access */
+	control = vmread(CPU_BASED_VM_EXEC_CONTROL);
+	control |= CPU_BASED_ACTIVATE_SECONDARY_CONTROLS;
+	vmwrite(CPU_BASED_VM_EXEC_CONTROL, control);
+	control = vmread(SECONDARY_VM_EXEC_CONTROL);
+	control |= SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
+	vmwrite(SECONDARY_VM_EXEC_CONTROL, control);
+	vmwrite(APIC_ACCESS_ADDR, VAPIC_GPA);
+
+	GUEST_SYNC1(0);
+	vmlaunch();
+again:
+	exit_reason = vmread(VM_EXIT_REASON);
+	if (exit_reason == EXIT_REASON_APIC_ACCESS) {
+		uint64_t guest_rip = vmread(GUEST_RIP);
+		uint64_t instr_len = vmread(VM_EXIT_INSTRUCTION_LEN);
+
+		vmwrite(GUEST_RIP, guest_rip + instr_len);
+		vmresume();
+		goto again;
+	}
+
+	GUEST_SYNC1(exit_reason);
+	GUEST_ASSERT(exit_reason == EXIT_REASON_VMCALL);
+	GUEST_DONE();
+}
+
+static const char *progname;
+static int update_period_ms = L2_DELAY / 4;
+
+struct update_control {
+	pthread_mutex_t mutex;
+	pthread_cond_t start_cond;
+	struct kvm_vm *vm;
+	bool running;
+	bool started;
+	int updates;
+};
+
+static void wait_for_start_signal(struct update_control *ctrl)
+{
+	pthread_mutex_lock(&ctrl->mutex);
+	while (!ctrl->started)
+		pthread_cond_wait(&ctrl->start_cond, &ctrl->mutex);
+
+	pthread_mutex_unlock(&ctrl->mutex);
+	printf("%s: starting update\n", progname);
+}
+
+static bool is_running(struct update_control *ctrl)
+{
+	return READ_ONCE(ctrl->running);
+}
+
+static void set_running(struct update_control *ctrl, bool running)
+{
+	WRITE_ONCE(ctrl->running, running);
+}
+
+static void signal_thread_start(struct update_control *ctrl)
+{
+	pthread_mutex_lock(&ctrl->mutex);
+	if (!ctrl->started) {
+		ctrl->started = true;
+		pthread_cond_signal(&ctrl->start_cond);
+	}
+	pthread_mutex_unlock(&ctrl->mutex);
+}
+
+static void *update_madvise(void *arg)
+{
+	struct update_control *ctrl = arg;
+	void *hva;
+
+	wait_for_start_signal(ctrl);
+
+	hva = addr_gpa2hva(ctrl->vm, VAPIC_GPA);
+	memset(hva, 0x45, ctrl->vm->page_size);
+
+	while (is_running(ctrl)) {
+		usleep(update_period_ms * 1000);
+		madvise(hva, ctrl->vm->page_size, MADV_DONTNEED);
+		ctrl->updates++;
+	}
+
+	return NULL;
+}
+
+static void *update_move_memslot(void *arg)
+{
+	struct update_control *ctrl = arg;
+	uint64_t gpa = VAPIC_GPA;
+
+	wait_for_start_signal(ctrl);
+
+	/*
+	 * Alternate the slot between VAPIC_GPA and an alternate address,
+	 * so that the GPA under test is repeatedly unbacked (L2's APIC
+	 * access bounces to userspace as MMIO) and re-backed (KVM must
+	 * re-latch the page). Moving strictly away would change
+	 * vCPU-visible state only once.
+	 */
+	while (is_running(ctrl)) {
+		usleep(update_period_ms * 1000);
+		gpa = (gpa == VAPIC_GPA) ? VAPIC_GPA + 0x10000 : VAPIC_GPA;
+		vm_mem_region_move(ctrl->vm, VAPIC_SLOT, gpa);
+		ctrl->updates++;
+	}
+
+	return NULL;
+}
+
+static void run(void * (*update)(void *), const char *name, bool mmio_ok)
+{
+	struct kvm_vm *vm;
+	struct kvm_vcpu *vcpu;
+	struct update_control ctrl;
+	struct ucall uc;
+	gva_t vmx_pages_gva;
+	pthread_t update_thread;
+	bool done = false;
+
+	vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code);
+
+	/* Set up nested EPT */
+	vm_enable_tdp(vm);
+
+	/* Allocate VMX pages */
+	vcpu_alloc_vmx(vm, &vmx_pages_gva);
+
+	/* Allocate memory and create VAPIC memslot */
+	vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, VAPIC_GPA,
+				    VAPIC_SLOT, 1, 0);
+
+	/* Allocate guest page table */
+	virt_map(vm, VAPIC_GPA, VAPIC_GPA, 1);
+
+	/* Identity-map everything, including the VAPIC page, in the EPT */
+	tdp_identity_map_default_memslots(vm);
+	tdp_map(vm, VAPIC_GPA, VAPIC_GPA, vm->page_size);
+
+	vcpu_args_set(vcpu, 1, vmx_pages_gva);
+
+	pthread_mutex_init(&ctrl.mutex, NULL);
+	pthread_cond_init(&ctrl.start_cond, NULL);
+	ctrl.vm = vm;
+	ctrl.running = true;
+	ctrl.started = false;
+	ctrl.updates = 0;
+
+	kvm_pthread_create(&update_thread, NULL, update, &ctrl);
+
+	printf("%s: running %s (tsc_khz %lu)\n", progname, name, guest_tsc_khz);
+
+	while (!done) {
+		vcpu_run(vcpu);
+
+		switch (vcpu->run->exit_reason) {
+		case KVM_EXIT_IO:
+			switch (get_ucall(vcpu, &uc)) {
+			case UCALL_SYNC:
+				printf("%s: sync(%ld)\n", progname, uc.args[0]);
+				if (uc.args[0] == 0)
+					signal_thread_start(&ctrl);
+				break;
+			case UCALL_ABORT:
+				REPORT_GUEST_ASSERT(uc);
+				/* NOT REACHED */
+			case UCALL_DONE:
+				done = true;
+				break;
+			default:
+				TEST_ASSERT(false, "Unknown ucall %lu", uc.cmd);
+			}
+			break;
+		case KVM_EXIT_MMIO:
+			/*
+			 * While the slot is moved away, the GPA under test
+			 * is unbacked and the access legitimately bounces
+			 * to userspace as MMIO (until the updater moves it
+			 * back). madvise() never unbacks the GPA, so there
+			 * an MMIO exit means KVM lost the mapping: fail.
+			 */
+			TEST_ASSERT(mmio_ok,
+				    "%s: unexpected APIC MMIO access at 0x%llx",
+				    progname, vcpu->run->mmio.phys_addr);
+			printf
+			    ("%s: APIC MMIO access at 0x%llx (memslot move effect)\n",
+			     progname, vcpu->run->mmio.phys_addr);
+			break;
+		default:
+			TEST_FAIL("%s: Unexpected exit reason: %d (flags 0x%x)",
+				  progname,
+				  vcpu->run->exit_reason, vcpu->run->flags);
+		}
+	}
+
+	set_running(&ctrl, false);
+	if (!ctrl.started)
+		signal_thread_start(&ctrl);
+	kvm_pthread_join(update_thread, NULL);
+	printf("%s: completed with %d updates\n", progname, ctrl.updates);
+	TEST_ASSERT(ctrl.updates > 0,
+		    "%s: %s performed no updates; nothing was tested",
+		    progname, name);
+
+	pthread_mutex_destroy(&ctrl.mutex);
+	pthread_cond_destroy(&ctrl.start_cond);
+	kvm_vm_free(vm);
+}
+
+int main(int argc, char *argv[])
+{
+	int opt_madvise = 0;
+	int opt_memslot_move = 0;
+
+	TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX));
+	TEST_REQUIRE(kvm_cpu_has_ept());
+
+	if (argc == 1) {
+		opt_madvise = 1;
+		opt_memslot_move = 1;
+	} else {
+		int opt;
+
+		while ((opt = getopt(argc, argv, "amp:")) != -1) {
+			switch (opt) {
+			case 'a':
+				opt_madvise = 1;
+				break;
+			case 'm':
+				opt_memslot_move = 1;
+				break;
+			case 'p':
+				update_period_ms = atoi(optarg);
+				TEST_ASSERT(update_period_ms > 0 &&
+					    update_period_ms < INT_MAX / 1000,
+					    "Update period must be a positive number of milliseconds, not '%s'",
+					    optarg);
+				break;
+			default:
+				exit(1);
+			}
+		}
+	}
+
+	TEST_ASSERT(opt_madvise
+		    || opt_memslot_move, "No update test configured");
+
+	progname = argv[0];
+
+	if (opt_madvise)
+		run(update_madvise, "madvise", false);
+
+	if (opt_memslot_move)
+		run(update_move_memslot, "move memslot", true);
+
+	return 0;
+}
-- 
2.43.0


  parent reply	other threads:[~2026-11-05  2:01 UTC|newest]

Thread overview: 30+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-11-05  2:00 [PATCH v2 00/20] KVM: Use atomic SRCU for gfn-to-pfn cache, reinstate guest mode for x86 nesting David Woodhouse
2026-11-05  2:00 ` [PATCH v2 01/20] KVM: x86/xen: Fill the hypercall page with a single guest write David Woodhouse
2026-11-05  2:00 ` [PATCH v2 02/20] KVM: x86/xen: Add KVM_XEN_VCPU_ATTR_TYPE_WRITE_HYPERCALL_PAGE David Woodhouse
2026-11-05  2:00 ` [PATCH v2 03/20] KVM: x86/xen: Extract delivery of event to vCPU into a separate helper David Woodhouse
2026-11-05  2:00 ` [PATCH v2 04/20] KVM: x86/xen: Explicitly tag "shared info" page as never being dirty tracked David Woodhouse
2026-11-05  2:00 ` [PATCH v2 05/20] KVM: x86/xen: Don't dirty track "vCPU info" page David Woodhouse
2026-11-05  2:00 ` [PATCH v2 06/20] KVM: x86: Request the guest TLB flush from record_steal_time() David Woodhouse
2026-11-10 20:19   ` Sean Christopherson
2026-11-10 21:14     ` David Woodhouse
2026-11-05  2:00 ` [PATCH v2 07/20] KVM: selftests: Actually deactivate the HVA-based shared_info cache in xen_shinfo_test David Woodhouse
2026-11-05  2:00 ` [PATCH v2 08/20] KVM: pfncache: Use atomic SRCU for readers instead of a rwlock David Woodhouse
2026-11-05  2:00 ` [PATCH v2 09/20] KVM: x86: Use gfn_to_pfn_cache for steal time / preempted status David Woodhouse
2026-11-05  2:00 ` [PATCH v2 10/20] KVM: pfncache: Add guest-mode pinning (GUEST_USES_PFN successor) David Woodhouse
2026-11-05  2:29   ` sashiko-bot
2026-11-05  2:00 ` [PATCH v2 11/20] KVM: nVMX: Implement cache for L1 MSR bitmap David Woodhouse
2026-11-05  2:00 ` [PATCH v2 12/20] KVM: nVMX: Use pinned pfncache for L1 APIC virtualization pages David Woodhouse
2026-11-05  2:33   ` sashiko-bot
2026-11-05  2:00 ` [PATCH v2 13/20] KVM: x86: Post KVM_REQ_GET_NESTED_STATE_PAGES on memslot updates David Woodhouse
2026-11-05  2:00 ` David Woodhouse [this message]
2026-11-05  2:25   ` [PATCH v2 14/20] KVM: selftests: Add nested VMX APIC cache invalidation test sashiko-bot
2026-11-05  2:00 ` [PATCH v2 15/20] KVM: nSVM: Use a gfn_to_pfn_cache for the vmcb12 page David Woodhouse
2026-11-05  2:00 ` [PATCH v2 16/20] KVM: nSVM: Cache L1's MSR permissions map pages David Woodhouse
2026-11-05  2:00 ` [PATCH v2 17/20] KVM: nSVM: Cache L1's IO " David Woodhouse
2026-11-05  2:01 ` [PATCH v2 18/20] KVM: selftests: Add nested transition benchmark David Woodhouse
2026-11-05  2:01 ` [PATCH v2 19/20] KVM: selftests: Add Xen evtchn vs memslot-update race test David Woodhouse
2026-11-05  2:01 ` [PATCH v2 20/20] KVM: selftests: Add Xen evtchn vs mmu_notifier race test for HVA caches David Woodhouse
2026-11-05  2:28   ` sashiko-bot
2026-11-10 19:52 ` [PATCH v2 00/20] KVM: Use atomic SRCU for gfn-to-pfn cache, reinstate guest mode for x86 nesting David Woodhouse
2026-11-10 20:14   ` Sean Christopherson
2026-11-11 18:38     ` David Woodhouse

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20261105020104.2507083-15-dwmw2@infradead.org \
    --to=dwmw2@infradead.org \
    --cc=dwmw@amazon.co.uk \
    --cc=fgriffo@amazon.co.uk \
    --cc=kunwu.chan@gmail.com \
    --cc=kunwu.chan@linux.dev \
    --cc=kvm@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-kselftest@vger.kernel.org \
    --cc=linux-rt-devel@lists.linux.dev \
    --cc=paul@xen.org \
    --cc=paulmck@kernel.org \
    --cc=pbonzini@redhat.com \
    --cc=rcu@vger.kernel.org \
    --cc=seanjc@google.com \
    --cc=syzbot+208f7f3e5f59c11aeb90@syzkaller.appspotmail.com \
    --cc=vkuznets@redhat.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

all inboxes | Powered by JetHome®