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

Pull more kvm updates from Paolo Bonzini:
  Generic:

   - Clean up locking of all vCPUs for a VM by using the *_nest_lock()
     family of functions, and move duplicated code to virt/kvm/. kernel/
     patches acked by Peter Zijlstra

   - Add MGLRU support to the access tracking perf test

  ARM fixes:

   - Make the irqbypass hooks resilient to changes in the GSI<->MSI
     routing, avoiding behind stale vLPI mappings being left behind. The
     fix is to resolve the VGIC IRQ using the host IRQ (which is stable)
     and nuking the vLPI mapping upon a routing change

   - Close another VGIC race where vCPU creation races with VGIC
     creation, leading to in-flight vCPUs entering the kernel w/o
     private IRQs allocated

   - Fix a build issue triggered by the recently added workaround for
     Ampere's AC04_CPU_23 erratum

   - Correctly sign-extend the VA when emulating a TLBI instruction
     potentially targeting a VNCR mapping

   - Avoid dereferencing a NULL pointer in the VGIC debug code, which
     can happen if the device doesn't have any mapping yet

  s390:

   - Fix interaction between some filesystems and Secure Execution

   - Some cleanups and refactorings, preparing for an upcoming big
     series

  x86:

   - Wait for target vCPU to ack KVM_REQ_UPDATE_PROTECTED_GUEST_STATE
     to fix a race between AP destroy and VMRUN

   - Decrypt and dump the VMSA in dump_vmcb() if debugging enabled for
     the VM

   - Refine and harden handling of spurious faults

   - Add support for ALLOWED_SEV_FEATURES

   - Add #VMGEXIT to the set of handlers special cased for
     CONFIG_RETPOLINE=y

   - Treat DEBUGCTL[5:2] as reserved to pave the way for virtualizing
     features that utilize those bits

   - Don't account temporary allocations in sev_send_update_data()

   - Add support for KVM_CAP_X86_BUS_LOCK_EXIT on SVM, via Bus Lock
     Threshold

   - Unify virtualization of IBRS on nested VM-Exit, and cross-vCPU
     IBPB, between SVM and VMX

   - Advertise support to userspace for WRMSRNS and PREFETCHI

   - Rescan I/O APIC routes after handling EOI that needed to be
     intercepted due to the old/previous routing, but not the
     new/current routing

   - Add a module param to control and enumerate support for device
     posted interrupts

   - Fix a potential overflow with nested virt on Intel systems running
     32-bit kernels

   - Flush shadow VMCSes on emergency reboot

   - Add support for SNP to the various SEV selftests

   - Add a selftest to verify fastops instructions via forced emulation

   - Refine and optimize KVM's software processing of the posted
     interrupt bitmap, and share the harvesting code between KVM and the
     kernel's Posted MSI handler"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (93 commits)
  rtmutex_api: provide correct extern functions
  KVM: arm64: vgic-debug: Avoid dereferencing NULL ITE pointer
  KVM: arm64: vgic-init: Plug vCPU vs. VGIC creation race
  KVM: arm64: Unmap vLPIs affected by changes to GSI routing information
  KVM: arm64: Resolve vLPI by host IRQ in vgic_v4_unset_forwarding()
  KVM: arm64: Protect vLPI translation with vgic_irq::irq_lock
  KVM: arm64: Use lock guard in vgic_v4_set_forwarding()
  KVM: arm64: Mask out non-VA bits from TLBI VA* on VNCR invalidation
  arm64: sysreg: Drag linux/kconfig.h to work around vdso build issue
  KVM: s390: Simplify and move pv code
  KVM: s390: Refactor and split some gmap helpers
  KVM: s390: Remove unneeded srcu lock
  s390: Remove unneeded includes
  s390/uv: Improve splitting of large folios that cannot be split while dirty
  s390/uv: Always return 0 from s390_wiggle_split_folio() if successful
  s390/uv: Don't return 0 from make_hva_secure() if the operation was not successful
  rust: add helper for mutex_trylock
  RISC-V: KVM: use kvm_trylock_all_vcpus when locking all vCPUs
  KVM: arm64: use kvm_trylock_all_vcpus when locking all vCPUs
  x86: KVM: SVM: use kvm_lock_all_vcpus instead of a custom implementation
  ...

1 files changed, 249 insertions, 32 deletions

diff --git a/tools/testing/selftests/kvm/access_tracking_perf_test.c b/tools/testing/selftests/kvm/access_tracking_perf_test.c
index 447e619cf856..da7196fd1b23 100644
--- a/tools/testing/selftests/kvm/access_tracking_perf_test.c
+++ b/tools/testing/selftests/kvm/access_tracking_perf_test.c
@@ -7,9 +7,11 @@
  * This test measures the performance effects of KVM's access tracking.
  * Access tracking is driven by the MMU notifiers test_young, clear_young, and
  * clear_flush_young. These notifiers do not have a direct userspace API,
- * however the clear_young notifier can be triggered by marking a pages as idle
- * in /sys/kernel/mm/page_idle/bitmap. This test leverages that mechanism to
- * enable access tracking on guest memory.
+ * however the clear_young notifier can be triggered either by
+ *   1. marking a pages as idle in /sys/kernel/mm/page_idle/bitmap OR
+ *   2. adding a new MGLRU generation using the lru_gen debugfs file.
+ * This test leverages page_idle to enable access tracking on guest memory
+ * unless MGLRU is enabled, in which case MGLRU is used.
  *
  * To measure performance this test runs a VM with a configurable number of
  * vCPUs that each touch every page in disjoint regions of memory. Performance
@@ -17,10 +19,11 @@
  * predefined region.
  *
  * Note that a deterministic correctness test of access tracking is not possible
- * by using page_idle as it exists today. This is for a few reasons:
+ * by using page_idle or MGLRU aging as it exists today. This is for a few
+ * reasons:
  *
- * 1. page_idle only issues clear_young notifiers, which lack a TLB flush. This
- *    means subsequent guest accesses are not guaranteed to see page table
+ * 1. page_idle and MGLRU only issue clear_young notifiers, which lack a TLB flush.
+ *    This means subsequent guest accesses are not guaranteed to see page table
  *    updates made by KVM until some time in the future.
  *
  * 2. page_idle only operates on LRU pages. Newly allocated pages are not
@@ -48,9 +51,17 @@
 #include "guest_modes.h"
 #include "processor.h"
 
+#include "cgroup_util.h"
+#include "lru_gen_util.h"
+
+static const char *TEST_MEMCG_NAME = "access_tracking_perf_test";
+
 /* Global variable used to synchronize all of the vCPU threads. */
 static int iteration;
 
+/* The cgroup memory controller root. Needed for lru_gen-based aging. */
+char cgroup_root[PATH_MAX];
+
 /* Defines what vCPU threads should do during a given iteration. */
 static enum {
 	/* Run the vCPU to access all its memory. */
@@ -65,6 +76,25 @@ static int vcpu_last_completed_iteration[KVM_MAX_VCPUS];
 /* Whether to overlap the regions of memory vCPUs access. */
 static bool overlap_memory_access;
 
+/*
+ * If the test should only warn if there are too many idle pages (i.e., it is
+ * expected).
+ * -1: Not yet set.
+ *  0: We do not expect too many idle pages, so FAIL if too many idle pages.
+ *  1: Having too many idle pages is expected, so merely print a warning if
+ *     too many idle pages are found.
+ */
+static int idle_pages_warn_only = -1;
+
+/* Whether or not to use MGLRU instead of page_idle for access tracking */
+static bool use_lru_gen;
+
+/* Total number of pages to expect in the memcg after touching everything */
+static long test_pages;
+
+/* Last generation we found the pages in */
+static int lru_gen_last_gen = -1;
+
 struct test_params {
 	/* The backing source for the region of memory. */
 	enum vm_mem_backing_src_type backing_src;
@@ -123,8 +153,24 @@ static void mark_page_idle(int page_idle_fd, uint64_t pfn)
 		    "Set page_idle bits for PFN 0x%" PRIx64, pfn);
 }
 
-static void mark_vcpu_memory_idle(struct kvm_vm *vm,
-				  struct memstress_vcpu_args *vcpu_args)
+static void too_many_idle_pages(long idle_pages, long total_pages, int vcpu_idx)
+{
+	char prefix[18] = {};
+
+	if (vcpu_idx >= 0)
+		snprintf(prefix, 18, "vCPU%d: ", vcpu_idx);
+
+	TEST_ASSERT(idle_pages_warn_only,
+		    "%sToo many pages still idle (%lu out of %lu)",
+		    prefix, idle_pages, total_pages);
+
+	printf("WARNING: %sToo many pages still idle (%lu out of %lu), "
+	       "this will affect performance results.\n",
+	       prefix, idle_pages, total_pages);
+}
+
+static void pageidle_mark_vcpu_memory_idle(struct kvm_vm *vm,
+					   struct memstress_vcpu_args *vcpu_args)
 {
 	int vcpu_idx = vcpu_args->vcpu_idx;
 	uint64_t base_gva = vcpu_args->gva;
@@ -177,27 +223,79 @@ static void mark_vcpu_memory_idle(struct kvm_vm *vm,
 	 * arbitrary; high enough that we ensure most memory access went through
 	 * access tracking but low enough as to not make the test too brittle
 	 * over time and across architectures.
-	 *
-	 * When running the guest as a nested VM, "warn" instead of asserting
-	 * as the TLB size is effectively unlimited and the KVM doesn't
-	 * explicitly flush the TLB when aging SPTEs.  As a result, more pages
-	 * are cached and the guest won't see the "idle" bit cleared.
 	 */
-	if (still_idle >= pages / 10) {
-#ifdef __x86_64__
-		TEST_ASSERT(this_cpu_has(X86_FEATURE_HYPERVISOR),
-			    "vCPU%d: Too many pages still idle (%lu out of %lu)",
-			    vcpu_idx, still_idle, pages);
-#endif
-		printf("WARNING: vCPU%d: Too many pages still idle (%lu out of %lu), "
-		       "this will affect performance results.\n",
-		       vcpu_idx, still_idle, pages);
-	}
+	if (still_idle >= pages / 10)
+		too_many_idle_pages(still_idle, pages,
+				    overlap_memory_access ? -1 : vcpu_idx);
 
 	close(page_idle_fd);
 	close(pagemap_fd);
 }
 
+int find_generation(struct memcg_stats *stats, long total_pages)
+{
+	/*
+	 * For finding the generation that contains our pages, use the same
+	 * 90% threshold that page_idle uses.
+	 */
+	int gen = lru_gen_find_generation(stats, total_pages * 9 / 10);
+
+	if (gen >= 0)
+		return gen;
+
+	if (!idle_pages_warn_only) {
+		TEST_FAIL("Could not find a generation with 90%% of guest memory (%ld pages).",
+			   total_pages * 9 / 10);
+		return gen;
+	}
+
+	/*
+	 * We couldn't find a generation with 90% of guest memory, which can
+	 * happen if access tracking is unreliable. Simply look for a majority
+	 * of pages.
+	 */
+	puts("WARNING: Couldn't find a generation with 90% of guest memory. "
+	     "Performance results may not be accurate.");
+	gen = lru_gen_find_generation(stats, total_pages / 2);
+	TEST_ASSERT(gen >= 0,
+		    "Could not find a generation with 50%% of guest memory (%ld pages).",
+		    total_pages / 2);
+	return gen;
+}
+
+static void lru_gen_mark_memory_idle(struct kvm_vm *vm)
+{
+	struct timespec ts_start;
+	struct timespec ts_elapsed;
+	struct memcg_stats stats;
+	int new_gen;
+
+	/* Make a new generation */
+	clock_gettime(CLOCK_MONOTONIC, &ts_start);
+	lru_gen_do_aging(&stats, TEST_MEMCG_NAME);
+	ts_elapsed = timespec_elapsed(ts_start);
+
+	/* Check the generation again */
+	new_gen = find_generation(&stats, test_pages);
+
+	/*
+	 * This function should only be invoked with newly-accessed pages,
+	 * so pages should always move to a newer generation.
+	 */
+	if (new_gen <= lru_gen_last_gen) {
+		/* We did not move to a newer generation. */
+		long idle_pages = lru_gen_sum_memcg_stats_for_gen(lru_gen_last_gen,
+								  &stats);
+
+		too_many_idle_pages(min_t(long, idle_pages, test_pages),
+				    test_pages, -1);
+	}
+	pr_info("%-30s: %ld.%09lds\n",
+		"Mark memory idle (lru_gen)", ts_elapsed.tv_sec,
+		ts_elapsed.tv_nsec);
+	lru_gen_last_gen = new_gen;
+}
+
 static void assert_ucall(struct kvm_vcpu *vcpu, uint64_t expected_ucall)
 {
 	struct ucall uc;
@@ -237,7 +335,7 @@ static void vcpu_thread_main(struct memstress_vcpu_args *vcpu_args)
 			assert_ucall(vcpu, UCALL_SYNC);
 			break;
 		case ITERATION_MARK_IDLE:
-			mark_vcpu_memory_idle(vm, vcpu_args);
+			pageidle_mark_vcpu_memory_idle(vm, vcpu_args);
 			break;
 		}
 
@@ -289,15 +387,18 @@ static void access_memory(struct kvm_vm *vm, int nr_vcpus,
 
 static void mark_memory_idle(struct kvm_vm *vm, int nr_vcpus)
 {
+	if (use_lru_gen)
+		return lru_gen_mark_memory_idle(vm);
+
 	/*
 	 * Even though this parallelizes the work across vCPUs, this is still a
 	 * very slow operation because page_idle forces the test to mark one pfn
-	 * at a time and the clear_young notifier serializes on the KVM MMU
+	 * at a time and the clear_young notifier may serialize on the KVM MMU
 	 * lock.
 	 */
 	pr_debug("Marking VM memory idle (slow)...\n");
 	iteration_work = ITERATION_MARK_IDLE;
-	run_iteration(vm, nr_vcpus, "Mark memory idle");
+	run_iteration(vm, nr_vcpus, "Mark memory idle (page_idle)");
 }
 
 static void run_test(enum vm_guest_mode mode, void *arg)
@@ -309,11 +410,38 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	vm = memstress_create_vm(mode, nr_vcpus, params->vcpu_memory_bytes, 1,
 				 params->backing_src, !overlap_memory_access);
 
+	/*
+	 * If guest_page_size is larger than the host's page size, the
+	 * guest (memstress) will only fault in a subset of the host's pages.
+	 */
+	test_pages = params->nr_vcpus * params->vcpu_memory_bytes /
+		      max(memstress_args.guest_page_size,
+			  (uint64_t)getpagesize());
+
 	memstress_start_vcpu_threads(nr_vcpus, vcpu_thread_main);
 
 	pr_info("\n");
 	access_memory(vm, nr_vcpus, ACCESS_WRITE, "Populating memory");
 
+	if (use_lru_gen) {
+		struct memcg_stats stats;
+
+		/*
+		 * Do a page table scan now. Following initial population, aging
+		 * may not cause the pages to move to a newer generation. Do
+		 * an aging pass now so that future aging passes always move
+		 * pages to a newer generation.
+		 */
+		printf("Initial aging pass (lru_gen)\n");
+		lru_gen_do_aging(&stats, TEST_MEMCG_NAME);
+		TEST_ASSERT(lru_gen_sum_memcg_stats(&stats) >= test_pages,
+			    "Not all pages accounted for (looking for %ld). "
+			    "Was the memcg set up correctly?", test_pages);
+		access_memory(vm, nr_vcpus, ACCESS_WRITE, "Re-populating memory");
+		lru_gen_read_memcg_stats(&stats, TEST_MEMCG_NAME);
+		lru_gen_last_gen = find_generation(&stats, test_pages);
+	}
+
 	/* As a control, read and write to the populated memory first. */
 	access_memory(vm, nr_vcpus, ACCESS_WRITE, "Writing to populated memory");
 	access_memory(vm, nr_vcpus, ACCESS_READ, "Reading from populated memory");
@@ -328,6 +456,37 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	memstress_destroy_vm(vm);
 }
 
+static int access_tracking_unreliable(void)
+{
+#ifdef __x86_64__
+	/*
+	 * When running nested, the TLB size may be effectively unlimited (for
+	 * example, this is the case when running on KVM L0), and KVM doesn't
+	 * explicitly flush the TLB when aging SPTEs.  As a result, more pages
+	 * are cached and the guest won't see the "idle" bit cleared.
+	 */
+	if (this_cpu_has(X86_FEATURE_HYPERVISOR)) {
+		puts("Skipping idle page count sanity check, because the test is run nested");
+		return 1;
+	}
+#endif
+	/*
+	 * When NUMA balancing is enabled, guest memory will be unmapped to get
+	 * NUMA faults, dropping the Accessed bits.
+	 */
+	if (is_numa_balancing_enabled()) {
+		puts("Skipping idle page count sanity check, because NUMA balancing is enabled");
+		return 1;
+	}
+	return 0;
+}
+
+static int run_test_for_each_guest_mode(const char *cgroup, void *arg)
+{
+	for_each_guest_mode(run_test, arg);
+	return 0;
+}
+
 static void help(char *name)
 {
 	puts("");
@@ -342,11 +501,22 @@ static void help(char *name)
 	printf(" -v: specify the number of vCPUs to run.\n");
 	printf(" -o: Overlap guest memory accesses instead of partitioning\n"
 	       "     them into a separate region of memory for each vCPU.\n");
+	printf(" -w: Control whether the test warns or fails if more than 10%%\n"
+	       "     of pages are still seen as idle/old after accessing guest\n"
+	       "     memory.  >0 == warn only, 0 == fail, <0 == auto.  For auto\n"
+	       "     mode, the test fails by default, but switches to warn only\n"
+	       "     if NUMA balancing is enabled or the test detects it's running\n"
+	       "     in a VM.\n");
 	backing_src_help("-s");
 	puts("");
 	exit(0);
 }
 
+void destroy_cgroup(char *cg)
+{
+	printf("Destroying cgroup: %s\n", cg);
+}
+
 int main(int argc, char *argv[])
 {
 	struct test_params params = {
@@ -354,12 +524,13 @@ int main(int argc, char *argv[])
 		.vcpu_memory_bytes = DEFAULT_PER_VCPU_MEM_SIZE,
 		.nr_vcpus = 1,
 	};
+	char *new_cg = NULL;
 	int page_idle_fd;
 	int opt;
 
 	guest_modes_append_default();
 
-	while ((opt = getopt(argc, argv, "hm:b:v:os:")) != -1) {
+	while ((opt = getopt(argc, argv, "hm:b:v:os:w:")) != -1) {
 		switch (opt) {
 		case 'm':
 			guest_modes_cmdline(optarg);
@@ -376,6 +547,11 @@ int main(int argc, char *argv[])
 		case 's':
 			params.backing_src = parse_backing_src_type(optarg);
 			break;
+		case 'w':
+			idle_pages_warn_only =
+				atoi_non_negative("Idle pages warning",
+						  optarg);
+			break;
 		case 'h':
 		default:
 			help(argv[0]);
@@ -383,12 +559,53 @@ int main(int argc, char *argv[])
 		}
 	}
 
-	page_idle_fd = open("/sys/kernel/mm/page_idle/bitmap", O_RDWR);
-	__TEST_REQUIRE(page_idle_fd >= 0,
-		       "CONFIG_IDLE_PAGE_TRACKING is not enabled");
-	close(page_idle_fd);
+	if (idle_pages_warn_only == -1)
+		idle_pages_warn_only = access_tracking_unreliable();
+
+	if (lru_gen_usable()) {
+		bool cg_created = true;
+		int ret;
+
+		puts("Using lru_gen for aging");
+		use_lru_gen = true;
+
+		if (cg_find_controller_root(cgroup_root, sizeof(cgroup_root), "memory"))
+			ksft_exit_skip("Cannot find memory cgroup controller\n");
 
-	for_each_guest_mode(run_test, &params);
+		new_cg = cg_name(cgroup_root, TEST_MEMCG_NAME);
+		printf("Creating cgroup: %s\n", new_cg);
+		if (cg_create(new_cg)) {
+			if (errno == EEXIST) {
+				printf("Found existing cgroup");
+				cg_created = false;
+			} else {
+				ksft_exit_skip("could not create new cgroup: %s\n", new_cg);
+			}
+		}
+
+		/*
+		 * This will fork off a new process to run the test within
+		 * a new memcg, so we need to properly propagate the return
+		 * value up.
+		 */
+		ret = cg_run(new_cg, &run_test_for_each_guest_mode, &params);
+		if (cg_created)
+			cg_destroy(new_cg);
+		if (ret < 0)
+			TEST_FAIL("child did not spawn or was abnormally killed");
+		if (ret)
+			return ret;
+	} else {
+		page_idle_fd = open("/sys/kernel/mm/page_idle/bitmap", O_RDWR);
+		__TEST_REQUIRE(page_idle_fd >= 0,
+			       "Couldn't open /sys/kernel/mm/page_idle/bitmap. "
+			       "Is CONFIG_IDLE_PAGE_TRACKING enabled?");
+
+		close(page_idle_fd);
+
+		puts("Using page_idle for aging");
+		run_test_for_each_guest_mode(NULL, &params);
+	}
 
 	return 0;
 }