Merge: KVM: backport improvements to dirty_log_test

MR: https://gitlab.com/redhat/centos-stream/src/kernel/centos-stream-10/-/merge_requests/558

Backport a series of improvements to dirty_log_test that make this test more
robust, and in particular make it work in L1

Also backport a minor fix to KVM which needs to be present in L1 kernel to avoid the test failing,
when run on Intel.

JIRA: https://issues.redhat.com/browse/RHEL-58941

Tested: run the test few times

Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>

Approved-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Approved-by: Cathy Avery <cavery@redhat.com>
Approved-by: CKI KWF Bot <cki-ci-bot+kwf-gitlab-com@redhat.com>

Merged-by: Julio Faracco <jfaracco@redhat.com>

Author: jcfaracco

arch/x86/kvm/vmx/main.c

@@ -126,7 +126,7 @@ struct kvm_x86_ops vt_x86_ops __initdata = {
 	.check_intercept = vmx_check_intercept,
 	.handle_exit_irqoff = vmx_handle_exit_irqoff,
 
-	.cpu_dirty_log_size = PML_ENTITY_NUM,
+	.cpu_dirty_log_size = PML_LOG_NR_ENTRIES,
 	.update_cpu_dirty_logging = vmx_update_cpu_dirty_logging,
 
 	.nested_ops = &vmx_nested_ops,

arch/x86/kvm/vmx/nested.c

@@ -3442,7 +3442,7 @@ static int nested_vmx_write_pml_buffer(struct kvm_vcpu *vcpu, gpa_t gpa)
 	if (!nested_cpu_has_pml(vmcs12))
 		return 0;
 
-	if (vmcs12->guest_pml_index >= PML_ENTITY_NUM) {
+	if (vmcs12->guest_pml_index >= PML_LOG_NR_ENTRIES) {
 		vmx->nested.pml_full = true;
 		return 1;
 	}

arch/x86/kvm/vmx/vmx.c

@@ -4830,7 +4830,7 @@ static void init_vmcs(struct vcpu_vmx *vmx)
 
 	if (enable_pml) {
 		vmcs_write64(PML_ADDRESS, page_to_phys(vmx->pml_pg));
-		vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1);
+		vmcs_write16(GUEST_PML_INDEX, PML_HEAD_INDEX);
 	}
 
 	vmx_write_encls_bitmap(&vmx->vcpu, NULL);
@@ -6210,32 +6210,40 @@ static void vmx_destroy_pml_buffer(struct vcpu_vmx *vmx)
 static void vmx_flush_pml_buffer(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	u16 pml_idx, pml_tail_index;
 	u64 *pml_buf;
-	u16 pml_idx;
+	int i;
 
 	pml_idx = vmcs_read16(GUEST_PML_INDEX);
 
 	/* Do nothing if PML buffer is empty */
-	if (pml_idx == (PML_ENTITY_NUM - 1))
+	if (pml_idx == PML_HEAD_INDEX)
 		return;
+	/*
+	 * PML index always points to the next available PML buffer entity
+	 * unless PML log has just overflowed.
+	 */
+	pml_tail_index = (pml_idx >= PML_LOG_NR_ENTRIES) ? 0 : pml_idx + 1;
 
-	/* PML index always points to next available PML buffer entity */
-	if (pml_idx >= PML_ENTITY_NUM)
-		pml_idx = 0;
-	else
-		pml_idx++;
-
+	/*
+	 * PML log is written backwards: the CPU first writes the entry 511
+	 * then the entry 510, and so on.
+	 *
+	 * Read the entries in the same order they were written, to ensure that
+	 * the dirty ring is filled in the same order the CPU wrote them.
+	 */
 	pml_buf = page_address(vmx->pml_pg);
-	for (; pml_idx < PML_ENTITY_NUM; pml_idx++) {
+
+	for (i = PML_HEAD_INDEX; i >= pml_tail_index; i--) {
 		u64 gpa;
 
-		gpa = pml_buf[pml_idx];
+		gpa = pml_buf[i];
 		WARN_ON(gpa & (PAGE_SIZE - 1));
 		kvm_vcpu_mark_page_dirty(vcpu, gpa >> PAGE_SHIFT);
 	}
 
 	/* reset PML index */
-	vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1);
+	vmcs_write16(GUEST_PML_INDEX, PML_HEAD_INDEX);
 }
 
 static void vmx_dump_sel(char *name, uint32_t sel)

arch/x86/kvm/vmx/vmx.h

@@ -332,7 +332,10 @@ struct vcpu_vmx {
 	bool ple_window_dirty;
 
 	/* Support for PML */
-#define PML_ENTITY_NUM		512
+#define PML_LOG_NR_ENTRIES	512
+	/* PML is written backwards: this is the first entry written by the CPU */
+#define PML_HEAD_INDEX		(PML_LOG_NR_ENTRIES-1)
+
 	struct page *pml_pg;
 
 	/* apic deadline value in host tsc */