[patch] KVM: add MSR based hypercall API

[Ingo Molnar <mingo-X9Un+BFzKDI@public.gmane.org>]

Subject: [patch] KVM: add MSR based hypercall API
From: Ingo Molnar <mingo-X9Un+BFzKDI@public.gmane.org>

this adds a special MSR based hypercall API to KVM. This is to be used 
by paravirtual kernels and virtual drivers.

VMX-only at the moment.

Signed-off-by: Ingo Molnar <mingo-X9Un+BFzKDI@public.gmane.org>
---
 drivers/kvm/kvm.h        |    5 +++
 drivers/kvm/mmu.c        |    1 
 drivers/kvm/vmx.c        |   74 +++++++++++++++++++++++++++++++++++++++++++++--
 include/linux/kvm_para.h |   64 ++++++++++++++++++++++++++++++++++++++++
 4 files changed, 142 insertions(+), 2 deletions(-)

Index: linux/drivers/kvm/kvm.h
===================================================================
--- linux.orig/drivers/kvm/kvm.h
+++ linux/drivers/kvm/kvm.h
@@ -14,6 +14,7 @@
 
 #include "vmx.h"
 #include <linux/kvm.h>
+#include <linux/kvm_para.h>
 
 #define CR0_PE_MASK (1ULL << 0)
 #define CR0_TS_MASK (1ULL << 3)
@@ -237,6 +238,8 @@ struct kvm_vcpu {
 	unsigned long cr0;
 	unsigned long cr2;
 	unsigned long cr3;
+	struct kvm_vcpu_para_state *para_state;
+	hpa_t vm_syscall_hpa;
 	unsigned long cr4;
 	unsigned long cr8;
 	u64 pdptrs[4]; /* pae */
@@ -626,4 +629,6 @@ static inline u32 get_rdx_init_val(void)
 #define TSS_REDIRECTION_SIZE (256 / 8)
 #define RMODE_TSS_SIZE (TSS_BASE_SIZE + TSS_REDIRECTION_SIZE + TSS_IOPB_SIZE + 1)
 
+extern int vcpu_register_para(struct kvm_vcpu *vcpu, gpa_t para_state_gpa);
+
 #endif
Index: linux/drivers/kvm/mmu.c
===================================================================
--- linux.orig/drivers/kvm/mmu.c
+++ linux/drivers/kvm/mmu.c
@@ -719,6 +719,7 @@ hpa_t gpa_to_hpa(struct kvm_vcpu *vcpu, 
 	return ((hpa_t)page_to_pfn(page) << PAGE_SHIFT)
 		| (gpa & (PAGE_SIZE-1));
 }
+EXPORT_SYMBOL_GPL(gpa_to_hpa);
 
 hpa_t gva_to_hpa(struct kvm_vcpu *vcpu, gva_t gva)
 {
Index: linux/drivers/kvm/vmx.c
===================================================================
--- linux.orig/drivers/kvm/vmx.c
+++ linux/drivers/kvm/vmx.c
@@ -406,10 +406,15 @@ static int vmx_set_msr(struct kvm_vcpu *
 	case MSR_IA32_SYSENTER_ESP:
 		vmcs_write32(GUEST_SYSENTER_ESP, data);
 		break;
-	case MSR_IA32_TIME_STAMP_COUNTER: {
+	case MSR_IA32_TIME_STAMP_COUNTER:
 		guest_write_tsc(data);
 		break;
-	}
+	/*
+	 * This is the 'probe whether the host is KVM' logic:
+	 */
+	case MSR_KVM_API_MAGIC:
+		return vcpu_register_para(vcpu, data);
+
 	default:
 		msr = find_msr_entry(vcpu, msr_index);
 		if (msr) {
@@ -1448,6 +1453,71 @@ static int handle_io(struct kvm_vcpu *vc
 	return 0;
 }
 
+/*
+ * Register the para guest with the host:
+ */
+int vcpu_register_para(struct kvm_vcpu *vcpu, gpa_t para_state_gpa)
+{
+	struct kvm_vcpu_para_state *para_state;
+	hpa_t para_state_hpa, vm_syscall_hpa;
+	unsigned char *vm_syscall;
+
+	printk("KVM: guest trying to enter paravirtual mode\n");
+	printk(".... para_state_gpa: %08Lx\n", para_state_gpa);
+
+	/*
+	 * Needs to be page aligned:
+	 */
+	if (para_state_gpa != PAGE_ALIGN(para_state_gpa))
+		goto err_gp;
+
+	para_state_hpa = gpa_to_hpa(vcpu, para_state_gpa);
+	printk(".... para_state_hpa: %08Lx\n", para_state_hpa);
+	if (is_error_hpa(para_state_hpa))
+		goto err_gp;
+
+	para_state = (void *)__va(para_state_hpa);
+	printk(".... para_state_hva: %p\n", para_state);
+
+	printk("....  guest version: %d\n", para_state->guest_version);
+	printk("....           size: %d\n", para_state->size);
+
+	para_state->host_version = KVM_PARA_API_VERSION;
+	/*
+	 * We cannot support guests that try to register themselves
+	 * with a newer API version than the host supports:
+	 */
+	if (para_state->guest_version > KVM_PARA_API_VERSION) {
+		para_state->ret = -EINVAL;
+		goto err_skip;
+	}
+
+	vm_syscall_hpa = gpa_to_hpa(vcpu, para_state->vm_syscall_addr);
+	printk(".... vm_syscall_hpa: %08Lx\n", vm_syscall_hpa);
+	if (is_error_hpa(vm_syscall_hpa)) {
+		para_state->ret = -EINVAL;
+		goto err_skip;
+	}
+
+	printk("KVM: para guest successfully registered.\n");
+	vcpu->para_state = para_state;
+	vcpu->vm_syscall_hpa = vm_syscall_hpa;
+
+	vm_syscall = __va(vm_syscall_hpa);
+	/*
+	 * Patch in the VMCALL instruction:
+	 */
+	vm_syscall[0] = 0x0f;
+	vm_syscall[1] = 0x01;
+	vm_syscall[2] = 0xc1;
+
+	para_state->ret = 0;
+err_skip:
+	return 0;
+err_gp:
+	return 1;
+}
+
 static int handle_cr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 {
 	u64 exit_qualification;
Index: linux/include/linux/kvm_para.h
===================================================================
--- /dev/null
+++ linux/include/linux/kvm_para.h
@@ -0,0 +1,64 @@
+#ifndef __LINUX_KVM_PARA_H
+#define __LINUX_KVM_PARA_H
+
+/*
+ * Guest OS interface for KVM paravirtualization
+ *
+ * Note: this interface is considered experimental and may change without
+ *       notice.
+ */
+
+#define KVM_CR3_CACHE_SIZE	4
+
+struct kvm_cr3_cache_entry {
+	u64 guest_cr3;
+	u64 host_cr3;
+};
+
+struct kvm_cr3_cache {
+	struct kvm_cr3_cache_entry entry[KVM_CR3_CACHE_SIZE];
+	u32 max_idx;
+};
+
+/*
+ * Per-VCPU descriptor area shared between guest and host. Writable to
+ * both guest and host. Registered with the host by the guest when
+ * a guest acknowledges paravirtual mode.
+ */
+struct kvm_vcpu_para_state {
+	/*
+	 * API version information for compatibility. If there's any support
+	 * mismatch (too old host trying to execute too new guest) then
+	 * the host will deny entry into paravirtual mode. Any other
+	 * combination (new host + old guest and new host + new guest)
+	 * is supposed to work - new host versions will support all old
+	 * guest API versions.
+	 */
+	u32 guest_version;
+	u32 host_version;
+	u32 size;
+	u32 ret;
+
+	/*
+	 * The address of the vm exit instruction (VMCALL or VMMCALL),
+	 * which the host will patch according to the CPU model the
+	 * VM runs on:
+	 */
+	u64 vm_syscall_addr;
+
+	struct kvm_cr3_cache cr3_cache;
+
+} __attribute__ ((aligned(PAGE_SIZE)));
+
+#define KVM_PARA_API_VERSION 1
+
+/*
+ * This is used for an RDMSR's ECX parameter to probe for a KVM host.
+ * Hopefully no CPU vendor will use up this number. This is placed well
+ * out of way of the typical space occupied by CPU vendors' MSR indices,
+ * and we think (or at least hope) it wont be occupied in the future
+ * either.
+ */
+#define MSR_KVM_API_MAGIC 0x87655678
+
+#endif

-------------------------------------------------------------------------
Take Surveys. Earn Cash. Influence the Future of IT
Join SourceForge.net's Techsay panel and you'll get the chance to share your
opinions on IT & business topics through brief surveys - and earn cash
http://www.techsay.com/default.php?page=join.php&p=sourceforge&CID=DEVDEV