[PATCH 2/2] KVM: selftests: Test KVM_PRE_FAULT_MEMORY against a full dirty ring

[Fuad Tabba <fuad.tabba@linux.dev>]

Pre-fault more populated, dirty-logged pages than the vCPU's dirty ring
holds, and check that each call stops before the ring overflows, that a
retry returns ENOSPC without progress, and that the harvested entries
are the pages in order. A read pre-fault can map a page read-only, or
access-tracked on x86 without EPT A/D bits, so skip the case if
pre-faulting dirties nothing.

Signed-off-by: Fuad Tabba <fuad.tabba@linux.dev>
---
 .../selftests/kvm/pre_fault_memory_test.c     | 85 +++++++++++++++++++
 1 file changed, 85 insertions(+)

diff --git a/tools/testing/selftests/kvm/pre_fault_memory_test.c b/tools/testing/selftests/kvm/pre_fault_memory_test.c
index 3082fe09b95fa..18fc1d69acbf0 100644
--- a/tools/testing/selftests/kvm/pre_fault_memory_test.c
+++ b/tools/testing/selftests/kvm/pre_fault_memory_test.c
@@ -5,6 +5,7 @@
  * Author:
  * Isaku Yamahata <isaku.yamahata at gmail.com>
  */
+#include <asm/barrier.h>
 #include <linux/sizes.h>
 
 #include <test_util.h>
@@ -17,6 +18,8 @@
 /* Arbitrarily chosen values */
 #define TEST_BASE_SIZE		SZ_2M
 #define TEST_SLOT		10
+/* Large enough for the entries every architecture reserves. */
+#define TEST_RING_SIZE		SZ_64K
 
 /* Storage of test info to share with guest code */
 struct test_config {
@@ -281,6 +284,87 @@ static void test_pre_fault_memory(unsigned long vm_type, enum vm_mem_backing_src
 	for_each_guest_mode(__test_pre_fault_memory, &p);
 }
 
+/*
+ * Pre-fault more dirty-logged pages than the ring holds: each call has to stop
+ * before the ring overflows, and no entry may be lost.
+ */
+static void test_pre_fault_dirty_ring(void)
+{
+	const u64 entries = TEST_RING_SIZE / sizeof(struct kvm_dirty_gfn);
+	const u64 npages = entries + entries / 4;
+	struct kvm_pre_fault_memory range, left;
+	struct kvm_dirty_gfn *gfns, *cur;
+	u64 harvested = 0, n, size;
+	struct kvm_vcpu *vcpu;
+	int ret, stops = 0;
+	struct kvm_vm *vm;
+	u32 fetch = 0;
+	gpa_t gpa;
+
+	if (!kvm_has_cap(KVM_CAP_DIRTY_LOG_RING) && !kvm_has_cap(KVM_CAP_DIRTY_LOG_RING_ACQ_REL)) {
+		pr_info("Skipping the dirty ring test: no dirty ring\n");
+		return;
+	}
+
+	vm = vm_create(1);
+	vm_enable_dirty_ring(vm, TEST_RING_SIZE);
+	vcpu = vm_vcpu_add(vm, 0, NULL);
+	gfns = vcpu_map_dirty_ring(vcpu);
+
+	size = npages * vm->page_size;
+	gpa = align_down(vm->max_gfn * vm->page_size - size, SZ_2M);
+	vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, gpa, TEST_SLOT, npages,
+				    KVM_MEM_LOG_DIRTY_PAGES);
+
+	/* Populate the pages, so that pre-faulting can map them writable. */
+	memset(addr_gpa2hva(vm, gpa), 1, size);
+
+	range = (struct kvm_pre_fault_memory) { .gpa = gpa, .size = size };
+	while (range.size) {
+		vcpu_ioctl(vcpu, KVM_PRE_FAULT_MEMORY, &range);
+
+		if (range.size) {
+			left = range;
+			ret = __vcpu_ioctl(vcpu, KVM_PRE_FAULT_MEMORY, &range);
+			TEST_ASSERT_VM_VCPU_IOCTL(ret == -1 && errno == ENOSPC,
+						  KVM_PRE_FAULT_MEMORY, ret, vm);
+			TEST_ASSERT(range.gpa == left.gpa && range.size == left.size,
+				    "KVM_PRE_FAULT_MEMORY made progress on a full ring");
+			stops++;
+		}
+
+		for (n = 0; ; n++) {
+			cur = &gfns[fetch % entries];
+			if (smp_load_acquire(&cur->flags) != KVM_DIRTY_GFN_F_DIRTY)
+				break;
+
+			TEST_ASSERT(cur->slot == TEST_SLOT && cur->offset == harvested + n,
+				    "Ring entry %u: slot %u offset 0x%llx, expected slot %u offset 0x%lx",
+				    fetch, cur->slot, cur->offset, TEST_SLOT, harvested + n);
+			smp_store_release(&cur->flags, KVM_DIRTY_GFN_F_RESET);
+			fetch++;
+		}
+
+		/* A read pre-fault can map a page read-only, or access-tracked on x86. */
+		if (!n && !harvested && !range.size) {
+			pr_info("Skipping the dirty ring test: pre-faulting dirtied no pages\n");
+			kvm_vm_free(vm);
+			return;
+		}
+		TEST_ASSERT(n, "KVM_PRE_FAULT_MEMORY pushed nothing to the ring");
+		TEST_ASSERT(kvm_vm_reset_dirty_ring(vm) == n,
+			    "KVM_RESET_DIRTY_RINGS didn't reset %lu entries", n);
+		harvested += n;
+	}
+
+	TEST_ASSERT(harvested == npages, "%lu ring entries for %lu pages", harvested, npages);
+	TEST_ASSERT(stops, "KVM_PRE_FAULT_MEMORY never stopped for a %lu-entry ring", entries);
+	pr_info("Pre-faulted %lu pages through a %lu-entry ring, stopping %d times\n",
+		npages, entries, stops);
+
+	kvm_vm_free(vm);
+}
+
 static void help(char *name)
 {
 	puts("");
@@ -320,5 +404,6 @@ int main(int argc, char *argv[])
 	test_pre_fault_memory(KVM_X86_SW_PROTECTED_VM, backing, false);
 	test_pre_fault_memory(KVM_X86_SW_PROTECTED_VM, backing, true);
 #endif
+	test_pre_fault_dirty_ring();
 	return 0;
 }
-- 
2.47.3