Hi, Iain Kyte wrote: > What has made the KVM-13 stop working with Linux 2.6.20 kvm and kvm-intel? >
API has been modified.
As said Avi in kvm-13 release note : "if you use the modules from Linux 2.6.20,
you need to use kvm-12".
You can also apply attached patch on linux-2.6.20 source tree (it's just a copy
of kvm-13 in linux-2.6.20/drivers/kernel)
Regards,
Laurent
--
------------- [EMAIL PROTECTED] --------------
"Any sufficiently advanced technology is
indistinguishable from magic." - Arthur C. Clarke
Index: linux-2.6.20/drivers/kvm/kvm.h
===================================================================
--- linux-2.6.20.orig/drivers/kvm/kvm.h 2007-02-08 13:43:04.000000000 +0100
+++ linux-2.6.20/drivers/kvm/kvm.h 2007-02-08 13:43:07.000000000 +0100
@@ -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 +238,9 @@
unsigned long cr0;
unsigned long cr2;
unsigned long cr3;
+ gpa_t para_state_gpa;
+ struct page *para_state_page;
+ gpa_t hypercall_gpa;
unsigned long cr4;
unsigned long cr8;
u64 pdptrs[4]; /* pae */
@@ -304,6 +308,7 @@
int memory_config_version;
int busy;
unsigned long rmap_overflow;
+ struct list_head vm_list;
};
struct kvm_stat {
@@ -340,6 +345,7 @@
struct kvm_vcpu *(*vcpu_load)(struct kvm_vcpu *vcpu);
void (*vcpu_put)(struct kvm_vcpu *vcpu);
+ void (*vcpu_decache)(struct kvm_vcpu *vcpu);
int (*set_guest_debug)(struct kvm_vcpu *vcpu,
struct kvm_debug_guest *dbg);
@@ -380,6 +386,8 @@
int (*run)(struct kvm_vcpu *vcpu, struct kvm_run *run);
int (*vcpu_setup)(struct kvm_vcpu *vcpu);
void (*skip_emulated_instruction)(struct kvm_vcpu *vcpu);
+ void (*patch_hypercall)(struct kvm_vcpu *vcpu,
+ unsigned char *hypercall_addr);
};
extern struct kvm_stat kvm_stat;
@@ -474,6 +482,8 @@
int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva);
void kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu);
+int kvm_hypercall(struct kvm_vcpu *vcpu, struct kvm_run *run);
+
static inline int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t gva,
u32 error_code)
{
@@ -521,7 +531,7 @@
{
struct page *page = pfn_to_page(shadow_page >> PAGE_SHIFT);
- return (struct kvm_mmu_page *)page->private;
+ return (struct kvm_mmu_page *)page_private(page);
}
static inline u16 read_fs(void)
@@ -558,7 +568,7 @@
#ifndef load_ldt
static inline void load_ldt(u16 sel)
{
- asm ("lldt %0" : : "g"(sel));
+ asm ("lldt %0" : : "rm"(sel));
}
#endif
Index: linux-2.6.20/drivers/kvm/kvm_main.c
===================================================================
--- linux-2.6.20.orig/drivers/kvm/kvm_main.c 2007-02-08 13:43:04.000000000
+0100
+++ linux-2.6.20/drivers/kvm/kvm_main.c 2007-02-08 13:43:07.000000000 +0100
@@ -34,6 +34,8 @@
#include <linux/highmem.h>
#include <linux/file.h>
#include <asm/desc.h>
+#include <linux/sysdev.h>
+#include <linux/cpu.h>
#include "x86_emulate.h"
#include "segment_descriptor.h"
@@ -41,6 +43,9 @@
MODULE_AUTHOR("Qumranet");
MODULE_LICENSE("GPL");
+static spinlock_t kvm_lock = SPIN_LOCK_UNLOCKED;
+static struct list_head vm_list = LIST_HEAD_INIT(vm_list);
+
struct kvm_arch_ops *kvm_arch_ops;
struct kvm_stat kvm_stat;
EXPORT_SYMBOL_GPL(kvm_stat);
@@ -121,10 +126,8 @@
return likely(n >= 0 && n < KVM_MAX_VCPUS);
}
-int kvm_read_guest(struct kvm_vcpu *vcpu,
- gva_t addr,
- unsigned long size,
- void *dest)
+int kvm_read_guest(struct kvm_vcpu *vcpu, gva_t addr, unsigned long size,
+ void *dest)
{
unsigned char *host_buf = dest;
unsigned long req_size = size;
@@ -156,10 +159,8 @@
}
EXPORT_SYMBOL_GPL(kvm_read_guest);
-int kvm_write_guest(struct kvm_vcpu *vcpu,
- gva_t addr,
- unsigned long size,
- void *data)
+int kvm_write_guest(struct kvm_vcpu *vcpu, gva_t addr, unsigned long size,
+ void *data)
{
unsigned char *host_buf = data;
unsigned long req_size = size;
@@ -230,9 +231,13 @@
struct kvm_vcpu *vcpu = &kvm->vcpus[i];
mutex_init(&vcpu->mutex);
+ vcpu->cpu = -1;
vcpu->kvm = kvm;
vcpu->mmu.root_hpa = INVALID_PAGE;
INIT_LIST_HEAD(&vcpu->free_pages);
+ spin_lock(&kvm_lock);
+ list_add(&kvm->vm_list, &vm_list);
+ spin_unlock(&kvm_lock);
}
filp->private_data = kvm;
return 0;
@@ -272,7 +277,9 @@
static void kvm_free_vcpu(struct kvm_vcpu *vcpu)
{
- vcpu_load(vcpu->kvm, vcpu_slot(vcpu));
+ if (!vcpu_load(vcpu->kvm, vcpu_slot(vcpu)))
+ return;
+
kvm_mmu_destroy(vcpu);
vcpu_put(vcpu);
kvm_arch_ops->vcpu_free(vcpu);
@@ -290,6 +297,9 @@
{
struct kvm *kvm = filp->private_data;
+ spin_lock(&kvm_lock);
+ list_del(&kvm->vm_list);
+ spin_unlock(&kvm_lock);
kvm_free_vcpus(kvm);
kvm_free_physmem(kvm);
kfree(kvm);
@@ -443,7 +453,7 @@
void set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
{
if (is_long_mode(vcpu)) {
- if ( cr3 & CR3_L_MODE_RESEVED_BITS) {
+ if (cr3 & CR3_L_MODE_RESEVED_BITS) {
printk(KERN_DEBUG "set_cr3: #GP, reserved bits\n");
inject_gp(vcpu);
return;
@@ -544,7 +554,6 @@
FX_IMAGE_ALIGN);
vcpu->guest_fx_image = vcpu->host_fx_image + FX_IMAGE_SIZE;
- vcpu->cpu = -1; /* First load will set up TR */
r = kvm_arch_ops->vcpu_create(vcpu);
if (r < 0)
goto out_free_vcpus;
@@ -661,7 +670,7 @@
| __GFP_ZERO);
if (!new.phys_mem[i])
goto out_free;
- new.phys_mem[i]->private = 0;
+ set_page_private(new.phys_mem[i],0);
}
}
@@ -761,7 +770,6 @@
if (copy_to_user(log->dirty_bitmap, memslot->dirty_bitmap, n))
goto out;
-
if (any) {
cleared = 0;
for (i = 0; i < KVM_MAX_VCPUS; ++i) {
@@ -890,8 +898,9 @@
return X86EMUL_CONTINUE;
else {
gpa_t gpa = vcpu->mmu.gva_to_gpa(vcpu, addr);
+
if (gpa == UNMAPPED_GVA)
- return vcpu_printf(vcpu, "not present\n"),
X86EMUL_PROPAGATE_FAULT;
+ return X86EMUL_PROPAGATE_FAULT;
vcpu->mmio_needed = 1;
vcpu->mmio_phys_addr = gpa;
vcpu->mmio_size = bytes;
@@ -1129,6 +1138,42 @@
}
EXPORT_SYMBOL_GPL(emulate_instruction);
+int kvm_hypercall(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+ unsigned long nr, a0, a1, a2, a3, a4, a5, ret;
+
+ kvm_arch_ops->decache_regs(vcpu);
+ ret = -KVM_EINVAL;
+#ifdef CONFIG_X86_64
+ if (is_long_mode(vcpu)) {
+ nr = vcpu->regs[VCPU_REGS_RAX];
+ a0 = vcpu->regs[VCPU_REGS_RDI];
+ a1 = vcpu->regs[VCPU_REGS_RSI];
+ a2 = vcpu->regs[VCPU_REGS_RDX];
+ a3 = vcpu->regs[VCPU_REGS_RCX];
+ a4 = vcpu->regs[VCPU_REGS_R8];
+ a5 = vcpu->regs[VCPU_REGS_R9];
+ } else
+#endif
+ {
+ nr = vcpu->regs[VCPU_REGS_RBX] & -1u;
+ a0 = vcpu->regs[VCPU_REGS_RAX] & -1u;
+ a1 = vcpu->regs[VCPU_REGS_RCX] & -1u;
+ a2 = vcpu->regs[VCPU_REGS_RDX] & -1u;
+ a3 = vcpu->regs[VCPU_REGS_RSI] & -1u;
+ a4 = vcpu->regs[VCPU_REGS_RDI] & -1u;
+ a5 = vcpu->regs[VCPU_REGS_RBP] & -1u;
+ }
+ switch (nr) {
+ default:
+ ;
+ }
+ vcpu->regs[VCPU_REGS_RAX] = ret;
+ kvm_arch_ops->cache_regs(vcpu);
+ return 1;
+}
+EXPORT_SYMBOL_GPL(kvm_hypercall);
+
static u64 mk_cr_64(u64 curr_cr, u32 new_val)
{
return (curr_cr & ~((1ULL << 32) - 1)) | new_val;
@@ -1195,6 +1240,73 @@
}
}
+/*
+ * Register the para guest with the host:
+ */
+static 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, hypercall_hpa;
+ struct page *para_state_page;
+ unsigned char *hypercall;
+ gpa_t hypercall_gpa;
+
+ printk(KERN_DEBUG "kvm: guest trying to enter paravirtual mode\n");
+ printk(KERN_DEBUG ".... 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(KERN_DEBUG ".... para_state_hpa: %08Lx\n", para_state_hpa);
+ if (is_error_hpa(para_state_hpa))
+ goto err_gp;
+
+ para_state_page = pfn_to_page(para_state_hpa >> PAGE_SHIFT);
+ para_state = kmap_atomic(para_state_page, KM_USER0);
+
+ printk(KERN_DEBUG ".... guest version: %d\n",
para_state->guest_version);
+ printk(KERN_DEBUG ".... 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 = -KVM_EINVAL;
+ goto err_kunmap_skip;
+ }
+
+ hypercall_gpa = para_state->hypercall_gpa;
+ hypercall_hpa = gpa_to_hpa(vcpu, hypercall_gpa);
+ printk(KERN_DEBUG ".... hypercall_hpa: %08Lx\n", hypercall_hpa);
+ if (is_error_hpa(hypercall_hpa)) {
+ para_state->ret = -KVM_EINVAL;
+ goto err_kunmap_skip;
+ }
+
+ printk(KERN_DEBUG "kvm: para guest successfully registered.\n");
+ vcpu->para_state_page = para_state_page;
+ vcpu->para_state_gpa = para_state_gpa;
+ vcpu->hypercall_gpa = hypercall_gpa;
+
+ hypercall = kmap_atomic(pfn_to_page(hypercall_hpa >> PAGE_SHIFT),
+ KM_USER1) + (hypercall_hpa & ~PAGE_MASK);
+ kvm_arch_ops->patch_hypercall(vcpu, hypercall);
+ kunmap_atomic(hypercall, KM_USER1);
+
+ para_state->ret = 0;
+err_kunmap_skip:
+ kunmap_atomic(para_state, KM_USER0);
+ return 0;
+err_gp:
+ return 1;
+}
+
int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
{
u64 data;
@@ -1303,6 +1415,12 @@
case MSR_IA32_MISC_ENABLE:
vcpu->ia32_misc_enable_msr = data;
break;
+ /*
+ * This is the 'probe whether the host is KVM' logic:
+ */
+ case MSR_KVM_API_MAGIC:
+ return vcpu_register_para(vcpu, data);
+
default:
printk(KERN_ERR "kvm: unhandled wrmsr: 0x%x\n", msr);
return 1;
@@ -1360,6 +1478,9 @@
if (!vcpu)
return -ENOENT;
+ /* re-sync apic's tpr */
+ vcpu->cr8 = kvm_run->cr8;
+
if (kvm_run->emulated) {
kvm_arch_ops->skip_emulated_instruction(vcpu);
kvm_run->emulated = 0;
@@ -1784,12 +1905,11 @@
case KVM_GET_API_VERSION:
r = KVM_API_VERSION;
break;
- case KVM_CREATE_VCPU: {
+ case KVM_CREATE_VCPU:
r = kvm_dev_ioctl_create_vcpu(kvm, arg);
if (r)
goto out;
break;
- }
case KVM_RUN: {
struct kvm_run kvm_run;
@@ -2024,6 +2144,68 @@
.priority = 0,
};
+/*
+ * Make sure that a cpu that is being hot-unplugged does not have any vcpus
+ * cached on it.
+ */
+static void decache_vcpus_on_cpu(int cpu)
+{
+ struct kvm *vm;
+ struct kvm_vcpu *vcpu;
+ int i;
+
+ spin_lock(&kvm_lock);
+ list_for_each_entry(vm, &vm_list, vm_list)
+ for (i = 0; i < KVM_MAX_VCPUS; ++i) {
+ vcpu = &vm->vcpus[i];
+ /*
+ * If the vcpu is locked, then it is running on some
+ * other cpu and therefore it is not cached on the
+ * cpu in question.
+ *
+ * If it's not locked, check the last cpu it executed
+ * on.
+ */
+ if (mutex_trylock(&vcpu->mutex)) {
+ if (vcpu->cpu == cpu) {
+ kvm_arch_ops->vcpu_decache(vcpu);
+ vcpu->cpu = -1;
+ }
+ mutex_unlock(&vcpu->mutex);
+ }
+ }
+ spin_unlock(&kvm_lock);
+}
+
+static int kvm_cpu_hotplug(struct notifier_block *notifier, unsigned long val,
+ void *v)
+{
+ int cpu = (long)v;
+
+ switch (val) {
+ case CPU_DOWN_PREPARE:
+ case CPU_UP_CANCELED:
+ printk(KERN_INFO "kvm: disabling virtualization on CPU%d\n",
+ cpu);
+ decache_vcpus_on_cpu(cpu);
+ smp_call_function_single(cpu, kvm_arch_ops->hardware_disable,
+ NULL, 0, 1);
+ break;
+ case CPU_ONLINE:
+ printk(KERN_INFO "kvm: enabling virtualization on CPU%d\n",
+ cpu);
+ smp_call_function_single(cpu, kvm_arch_ops->hardware_enable,
+ NULL, 0, 1);
+ break;
+ }
+ return NOTIFY_OK;
+}
+
+static struct notifier_block kvm_cpu_notifier = {
+ .notifier_call = kvm_cpu_hotplug,
+ .priority = 20, /* must be > scheduler priority */
+};
+
static __init void kvm_init_debug(void)
{
struct kvm_stats_debugfs_item *p;
@@ -2043,6 +2225,30 @@
debugfs_remove(debugfs_dir);
}
+static int kvm_suspend(struct sys_device *dev, pm_message_t state)
+{
+ decache_vcpus_on_cpu(raw_smp_processor_id());
+ on_each_cpu(kvm_arch_ops->hardware_disable, 0, 0, 1);
+ return 0;
+}
+
+static int kvm_resume(struct sys_device *dev)
+{
+ on_each_cpu(kvm_arch_ops->hardware_enable, 0, 0, 1);
+ return 0;
+}
+
+static struct sysdev_class kvm_sysdev_class = {
+ set_kset_name("kvm"),
+ .suspend = kvm_suspend,
+ .resume = kvm_resume,
+};
+
+static struct sys_device kvm_sysdev = {
+ .id = 0,
+ .cls = &kvm_sysdev_class,
+};
+
hpa_t bad_page_address;
int kvm_init_arch(struct kvm_arch_ops *ops, struct module *module)
@@ -2070,8 +2276,19 @@
return r;
on_each_cpu(kvm_arch_ops->hardware_enable, 0, 0, 1);
+ r = register_cpu_notifier(&kvm_cpu_notifier);
+ if (r)
+ goto out_free_1;
register_reboot_notifier(&kvm_reboot_notifier);
+ r = sysdev_class_register(&kvm_sysdev_class);
+ if (r)
+ goto out_free_2;
+
+ r = sysdev_register(&kvm_sysdev);
+ if (r)
+ goto out_free_3;
+
kvm_chardev_ops.owner = module;
r = misc_register(&kvm_dev);
@@ -2083,7 +2300,13 @@
return r;
out_free:
+ sysdev_unregister(&kvm_sysdev);
+out_free_3:
+ sysdev_class_unregister(&kvm_sysdev_class);
+out_free_2:
unregister_reboot_notifier(&kvm_reboot_notifier);
+ unregister_cpu_notifier(&kvm_cpu_notifier);
+out_free_1:
on_each_cpu(kvm_arch_ops->hardware_disable, 0, 0, 1);
kvm_arch_ops->hardware_unsetup();
return r;
@@ -2092,8 +2315,10 @@
void kvm_exit_arch(void)
{
misc_deregister(&kvm_dev);
-
+ sysdev_unregister(&kvm_sysdev);
+ sysdev_class_unregister(&kvm_sysdev_class);
unregister_reboot_notifier(&kvm_reboot_notifier);
+ unregister_cpu_notifier(&kvm_cpu_notifier);
on_each_cpu(kvm_arch_ops->hardware_disable, 0, 0, 1);
kvm_arch_ops->hardware_unsetup();
kvm_arch_ops = NULL;
Index: linux-2.6.20/drivers/kvm/kvm_svm.h
===================================================================
--- linux-2.6.20.orig/drivers/kvm/kvm_svm.h 2007-02-08 13:43:04.000000000
+0100
+++ linux-2.6.20/drivers/kvm/kvm_svm.h 2007-02-08 13:43:07.000000000 +0100
@@ -1,6 +1,7 @@
#ifndef __KVM_SVM_H
#define __KVM_SVM_H
+#include <linux/kernel.h>
#include <linux/types.h>
#include <linux/list.h>
#include <asm/msr.h>
@@ -18,7 +19,7 @@
MSR_IA32_LASTBRANCHTOIP, MSR_IA32_LASTINTFROMIP,MSR_IA32_LASTINTTOIP,*/
};
-#define NR_HOST_SAVE_MSRS (sizeof(host_save_msrs) / sizeof(*host_save_msrs))
+#define NR_HOST_SAVE_MSRS ARRAY_SIZE(host_save_msrs)
#define NUM_DB_REGS 4
struct vcpu_svm {
Index: linux-2.6.20/drivers/kvm/mmu.c
===================================================================
--- linux-2.6.20.orig/drivers/kvm/mmu.c 2007-02-08 13:43:05.000000000 +0100
+++ linux-2.6.20/drivers/kvm/mmu.c 2007-02-08 13:43:07.000000000 +0100
@@ -298,18 +298,18 @@
if (!is_rmap_pte(*spte))
return;
page = pfn_to_page((*spte & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT);
- if (!page->private) {
+ if (!page_private(page)) {
rmap_printk("rmap_add: %p %llx 0->1\n", spte, *spte);
- page->private = (unsigned long)spte;
- } else if (!(page->private & 1)) {
+ set_page_private(page,(unsigned long)spte);
+ } else if (!(page_private(page) & 1)) {
rmap_printk("rmap_add: %p %llx 1->many\n", spte, *spte);
desc = mmu_alloc_rmap_desc(vcpu);
- desc->shadow_ptes[0] = (u64 *)page->private;
+ desc->shadow_ptes[0] = (u64 *)page_private(page);
desc->shadow_ptes[1] = spte;
- page->private = (unsigned long)desc | 1;
+ set_page_private(page,(unsigned long)desc | 1);
} else {
rmap_printk("rmap_add: %p %llx many->many\n", spte, *spte);
- desc = (struct kvm_rmap_desc *)(page->private & ~1ul);
+ desc = (struct kvm_rmap_desc *)(page_private(page) & ~1ul);
while (desc->shadow_ptes[RMAP_EXT-1] && desc->more)
desc = desc->more;
if (desc->shadow_ptes[RMAP_EXT-1]) {
@@ -337,12 +337,12 @@
if (j != 0)
return;
if (!prev_desc && !desc->more)
- page->private = (unsigned long)desc->shadow_ptes[0];
+ set_page_private(page,(unsigned long)desc->shadow_ptes[0]);
else
if (prev_desc)
prev_desc->more = desc->more;
else
- page->private = (unsigned long)desc->more | 1;
+ set_page_private(page,(unsigned long)desc->more | 1);
mmu_free_rmap_desc(vcpu, desc);
}
@@ -356,20 +356,20 @@
if (!is_rmap_pte(*spte))
return;
page = pfn_to_page((*spte & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT);
- if (!page->private) {
+ if (!page_private(page)) {
printk(KERN_ERR "rmap_remove: %p %llx 0->BUG\n", spte, *spte);
BUG();
- } else if (!(page->private & 1)) {
+ } else if (!(page_private(page) & 1)) {
rmap_printk("rmap_remove: %p %llx 1->0\n", spte, *spte);
- if ((u64 *)page->private != spte) {
+ if ((u64 *)page_private(page) != spte) {
printk(KERN_ERR "rmap_remove: %p %llx 1->BUG\n",
spte, *spte);
BUG();
}
- page->private = 0;
+ set_page_private(page,0);
} else {
rmap_printk("rmap_remove: %p %llx many->many\n", spte, *spte);
- desc = (struct kvm_rmap_desc *)(page->private & ~1ul);
+ desc = (struct kvm_rmap_desc *)(page_private(page) & ~1ul);
prev_desc = NULL;
while (desc) {
for (i = 0; i < RMAP_EXT && desc->shadow_ptes[i]; ++i)
@@ -398,11 +398,11 @@
BUG_ON(!slot);
page = gfn_to_page(slot, gfn);
- while (page->private) {
- if (!(page->private & 1))
- spte = (u64 *)page->private;
+ while (page_private(page)) {
+ if (!(page_private(page) & 1))
+ spte = (u64 *)page_private(page);
else {
- desc = (struct kvm_rmap_desc *)(page->private & ~1ul);
+ desc = (struct kvm_rmap_desc *)(page_private(page) &
~1ul);
spte = desc->shadow_ptes[0];
}
BUG_ON(!spte);
@@ -1218,7 +1218,7 @@
INIT_LIST_HEAD(&page_header->link);
if ((page = alloc_page(GFP_KERNEL)) == NULL)
goto error_1;
- page->private = (unsigned long)page_header;
+ set_page_private(page, (unsigned long)page_header);
page_header->page_hpa = (hpa_t)page_to_pfn(page) << PAGE_SHIFT;
memset(__va(page_header->page_hpa), 0, PAGE_SIZE);
list_add(&page_header->link, &vcpu->free_pages);
Index: linux-2.6.20/drivers/kvm/paging_tmpl.h
===================================================================
--- linux-2.6.20.orig/drivers/kvm/paging_tmpl.h 2007-02-08 13:43:05.000000000
+0100
+++ linux-2.6.20/drivers/kvm/paging_tmpl.h 2007-02-08 13:43:07.000000000
+0100
@@ -128,8 +128,10 @@
goto access_error;
#endif
- if (!(*ptep & PT_ACCESSED_MASK))
- *ptep |= PT_ACCESSED_MASK; /* avoid rmw */
+ if (!(*ptep & PT_ACCESSED_MASK)) {
+ mark_page_dirty(vcpu->kvm, table_gfn);
+ *ptep |= PT_ACCESSED_MASK;
+ }
if (walker->level == PT_PAGE_TABLE_LEVEL) {
walker->gfn = (*ptep & PT_BASE_ADDR_MASK)
@@ -185,6 +187,12 @@
kunmap_atomic(walker->table, KM_USER0);
}
+static void FNAME(mark_pagetable_dirty)(struct kvm *kvm,
+ struct guest_walker *walker)
+{
+ mark_page_dirty(kvm, walker->table_gfn[walker->level - 1]);
+}
+
static void FNAME(set_pte)(struct kvm_vcpu *vcpu, u64 guest_pte,
u64 *shadow_pte, u64 access_bits, gfn_t gfn)
{
@@ -348,12 +356,15 @@
} else if (kvm_mmu_lookup_page(vcpu, gfn)) {
pgprintk("%s: found shadow page for %lx, marking ro\n",
__FUNCTION__, gfn);
+ mark_page_dirty(vcpu->kvm, gfn);
+ FNAME(mark_pagetable_dirty)(vcpu->kvm, walker);
*guest_ent |= PT_DIRTY_MASK;
*write_pt = 1;
return 0;
}
mark_page_dirty(vcpu->kvm, gfn);
*shadow_ent |= PT_WRITABLE_MASK;
+ FNAME(mark_pagetable_dirty)(vcpu->kvm, walker);
*guest_ent |= PT_DIRTY_MASK;
rmap_add(vcpu, shadow_ent);
@@ -430,9 +441,8 @@
/*
* mmio: emulate if accessible, otherwise its a guest fault.
*/
- if (is_io_pte(*shadow_pte)) {
+ if (is_io_pte(*shadow_pte))
return 1;
- }
++kvm_stat.pf_fixed;
kvm_mmu_audit(vcpu, "post page fault (fixed)");
@@ -443,31 +453,17 @@
static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t vaddr)
{
struct guest_walker walker;
- pt_element_t guest_pte;
- gpa_t gpa;
-
- FNAME(walk_addr)(&walker, vcpu, vaddr, 0, 0, 0);
- guest_pte = *walker.ptep;
- FNAME(release_walker)(&walker);
+ gpa_t gpa = UNMAPPED_GVA;
+ int r;
- if (!is_present_pte(guest_pte))
- return UNMAPPED_GVA;
+ r = FNAME(walk_addr)(&walker, vcpu, vaddr, 0, 0, 0);
- if (walker.level == PT_DIRECTORY_LEVEL) {
- ASSERT((guest_pte & PT_PAGE_SIZE_MASK));
- ASSERT(PTTYPE == 64 || is_pse(vcpu));
-
- gpa = (guest_pte & PT_DIR_BASE_ADDR_MASK) | (vaddr &
- (PT_LEVEL_MASK(PT_PAGE_TABLE_LEVEL) | ~PAGE_MASK));
-
- if (PTTYPE == 32 && is_cpuid_PSE36())
- gpa |= (guest_pte & PT32_DIR_PSE36_MASK) <<
- (32 - PT32_DIR_PSE36_SHIFT);
- } else {
- gpa = (guest_pte & PT_BASE_ADDR_MASK);
- gpa |= (vaddr & ~PAGE_MASK);
+ if (r) {
+ gpa = (gpa_t)walker.gfn << PAGE_SHIFT;
+ gpa |= vaddr & ~PAGE_MASK;
}
+ FNAME(release_walker)(&walker);
return gpa;
}
Index: linux-2.6.20/drivers/kvm/svm.c
===================================================================
--- linux-2.6.20.orig/drivers/kvm/svm.c 2007-02-08 13:43:05.000000000 +0100
+++ linux-2.6.20/drivers/kvm/svm.c 2007-02-08 13:43:07.000000000 +0100
@@ -15,6 +15,7 @@
*/
#include <linux/module.h>
+#include <linux/kernel.h>
#include <linux/vmalloc.h>
#include <linux/highmem.h>
#include <linux/profile.h>
@@ -75,7 +76,7 @@
static u32 msrpm_ranges[] = {0, 0xc0000000, 0xc0010000};
-#define NUM_MSR_MAPS (sizeof(msrpm_ranges) / sizeof(*msrpm_ranges))
+#define NUM_MSR_MAPS ARRAY_SIZE(msrpm_ranges)
#define MSRS_RANGE_SIZE 2048
#define MSRS_IN_RANGE (MSRS_RANGE_SIZE * 8 / 2)
@@ -528,7 +529,13 @@
save->cs.attrib = SVM_SELECTOR_READ_MASK | SVM_SELECTOR_P_MASK |
SVM_SELECTOR_S_MASK | SVM_SELECTOR_CODE_MASK;
save->cs.limit = 0xffff;
- save->cs.base = 0xffff0000;
+ /*
+ * cs.base should really be 0xffff0000, but vmx can't handle that, so
+ * be consistent with it.
+ *
+ * Replace when we have real mode working for vmx.
+ */
+ save->cs.base = 0xf0000;
save->gdtr.limit = 0xffff;
save->idtr.limit = 0xffff;
@@ -603,6 +610,10 @@
put_cpu();
}
+static void svm_vcpu_decache(struct kvm_vcpu *vcpu)
+{
+}
+
static void svm_cache_regs(struct kvm_vcpu *vcpu)
{
vcpu->regs[VCPU_REGS_RAX] = vcpu->svm->vmcb->save.rax;
@@ -723,7 +734,7 @@
}
#endif
vcpu->svm->cr0 = cr0;
- vcpu->svm->vmcb->save.cr0 = cr0 | CR0_PG_MASK;
+ vcpu->svm->vmcb->save.cr0 = cr0 | CR0_PG_MASK | CR0_WP_MASK;
vcpu->cr0 = cr0;
}
@@ -1032,22 +1043,22 @@
addr_mask = io_adress(vcpu, _in, &kvm_run->io.address);
if (!addr_mask) {
- printk(KERN_DEBUG "%s: get io address failed\n",
__FUNCTION__);
+ printk(KERN_DEBUG "%s: get io address failed\n",
+ __FUNCTION__);
return 1;
}
if (kvm_run->io.rep) {
- kvm_run->io.count = vcpu->regs[VCPU_REGS_RCX] &
addr_mask;
+ kvm_run->io.count
+ = vcpu->regs[VCPU_REGS_RCX] & addr_mask;
kvm_run->io.string_down = (vcpu->svm->vmcb->save.rflags
& X86_EFLAGS_DF) != 0;
}
- } else {
+ } else
kvm_run->io.value = vcpu->svm->vmcb->save.rax;
- }
return 0;
}
-
static int nop_on_interception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
{
return 1;
@@ -1065,6 +1076,12 @@
return 0;
}
+static int vmmcall_interception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+{
+ vcpu->svm->vmcb->save.rip += 3;
+ return kvm_hypercall(vcpu, kvm_run);
+}
+
static int invalid_op_interception(struct kvm_vcpu *vcpu, struct kvm_run
*kvm_run)
{
inject_ud(vcpu);
@@ -1265,7 +1282,7 @@
[SVM_EXIT_TASK_SWITCH] = task_switch_interception,
[SVM_EXIT_SHUTDOWN] = shutdown_interception,
[SVM_EXIT_VMRUN] = invalid_op_interception,
- [SVM_EXIT_VMMCALL] = invalid_op_interception,
+ [SVM_EXIT_VMMCALL] = vmmcall_interception,
[SVM_EXIT_VMLOAD] = invalid_op_interception,
[SVM_EXIT_VMSAVE] = invalid_op_interception,
[SVM_EXIT_STGI] = invalid_op_interception,
@@ -1287,7 +1304,7 @@
__FUNCTION__, vcpu->svm->vmcb->control.exit_int_info,
exit_code);
- if (exit_code >= sizeof(svm_exit_handlers) / sizeof(*svm_exit_handlers)
+ if (exit_code >= ARRAY_SIZE(svm_exit_handlers)
|| svm_exit_handlers[exit_code] == 0) {
kvm_run->exit_reason = KVM_EXIT_UNKNOWN;
printk(KERN_ERR "%s: 0x%x @ 0x%llx cr0 0x%lx rflags 0x%llx\n",
@@ -1658,6 +1675,18 @@
return 0;
}
+static void
+svm_patch_hypercall(struct kvm_vcpu *vcpu, unsigned char *hypercall)
+{
+ /*
+ * Patch in the VMMCALL instruction:
+ */
+ hypercall[0] = 0x0f;
+ hypercall[1] = 0x01;
+ hypercall[2] = 0xd9;
+ hypercall[3] = 0xc3;
+}
+
static struct kvm_arch_ops svm_arch_ops = {
.cpu_has_kvm_support = has_svm,
.disabled_by_bios = is_disabled,
@@ -1671,6 +1700,7 @@
.vcpu_load = svm_vcpu_load,
.vcpu_put = svm_vcpu_put,
+ .vcpu_decache = svm_vcpu_decache,
.set_guest_debug = svm_guest_debug,
.get_msr = svm_get_msr,
@@ -1705,6 +1735,7 @@
.run = svm_vcpu_run,
.skip_emulated_instruction = skip_emulated_instruction,
.vcpu_setup = svm_vcpu_setup,
+ .patch_hypercall = svm_patch_hypercall,
};
static int __init svm_init(void)
Index: linux-2.6.20/drivers/kvm/vmx.c
===================================================================
--- linux-2.6.20.orig/drivers/kvm/vmx.c 2007-02-08 13:43:05.000000000 +0100
+++ linux-2.6.20/drivers/kvm/vmx.c 2007-02-08 13:43:07.000000000 +0100
@@ -19,6 +19,7 @@
#include "vmx.h"
#include "kvm_vmx.h"
#include <linux/module.h>
+#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/highmem.h>
#include <linux/profile.h>
@@ -27,7 +28,6 @@
#include "segment_descriptor.h"
-
MODULE_AUTHOR("Qumranet");
MODULE_LICENSE("GPL");
@@ -76,7 +76,7 @@
#endif
MSR_EFER, MSR_K6_STAR,
};
-#define NR_VMX_MSR (sizeof(vmx_msr_index) / sizeof(*vmx_msr_index))
+#define NR_VMX_MSR ARRAY_SIZE(vmx_msr_index)
static inline int is_page_fault(u32 intr_info)
{
@@ -125,6 +125,15 @@
per_cpu(current_vmcs, cpu) = NULL;
}
+static void vcpu_clear(struct kvm_vcpu *vcpu)
+{
+ if (vcpu->cpu != raw_smp_processor_id() && vcpu->cpu != -1)
+ smp_call_function_single(vcpu->cpu, __vcpu_clear, vcpu, 0, 1);
+ else
+ __vcpu_clear(vcpu);
+ vcpu->launched = 0;
+}
+
static unsigned long vmcs_readl(unsigned long field)
{
unsigned long value;
@@ -202,10 +211,8 @@
cpu = get_cpu();
- if (vcpu->cpu != cpu) {
- smp_call_function(__vcpu_clear, vcpu, 0, 1);
- vcpu->launched = 0;
- }
+ if (vcpu->cpu != cpu)
+ vcpu_clear(vcpu);
if (per_cpu(current_vmcs, cpu) != vcpu->vmcs) {
u8 error;
@@ -243,6 +250,11 @@
put_cpu();
}
+static void vmx_vcpu_decache(struct kvm_vcpu *vcpu)
+{
+ vcpu_clear(vcpu);
+}
+
static unsigned long vmx_get_rflags(struct kvm_vcpu *vcpu)
{
return vmcs_readl(GUEST_RFLAGS);
@@ -406,10 +418,9 @@
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;
- }
default:
msr = find_msr_entry(vcpu, msr_index);
if (msr) {
@@ -502,7 +513,7 @@
return (msr & 5) == 1; /* locked but not enabled */
}
-static __init void hardware_enable(void *garbage)
+static void hardware_enable(void *garbage)
{
int cpu = raw_smp_processor_id();
u64 phys_addr = __pa(per_cpu(vmxarea, cpu));
@@ -781,6 +792,9 @@
*/
static void vmx_set_cr0_no_modeswitch(struct kvm_vcpu *vcpu, unsigned long cr0)
{
+ if (!vcpu->rmode.active && !(cr0 & CR0_PE_MASK))
+ enter_rmode(vcpu);
+
vcpu->rmode.active = ((cr0 & CR0_PE_MASK) == 0);
update_exception_bitmap(vcpu);
vmcs_writel(CR0_READ_SHADOW, cr0);
@@ -1375,6 +1389,11 @@
return 1;
}
+static int handle_triple_fault(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+{
+ kvm_run->exit_reason = KVM_EXIT_SHUTDOWN;
+ return 0;
+}
static int get_io_count(struct kvm_vcpu *vcpu, u64 *count)
{
@@ -1450,6 +1469,18 @@
return 0;
}
+static void
+vmx_patch_hypercall(struct kvm_vcpu *vcpu, unsigned char *hypercall)
+{
+ /*
+ * Patch in the VMCALL instruction:
+ */
+ hypercall[0] = 0x0f;
+ hypercall[1] = 0x01;
+ hypercall[2] = 0xc1;
+ hypercall[3] = 0xc3;
+}
+
static int handle_cr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
{
u64 exit_qualification;
@@ -1626,6 +1657,12 @@
return 0;
}
+static int handle_vmcall(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+{
+ vmcs_writel(GUEST_RIP, vmcs_readl(GUEST_RIP)+3);
+ return kvm_hypercall(vcpu, kvm_run);
+}
+
/*
* The exit handlers return 1 if the exit was handled fully and guest execution
* may resume. Otherwise they set the kvm_run parameter to indicate what needs
@@ -1635,6 +1672,7 @@
struct kvm_run *kvm_run) = {
[EXIT_REASON_EXCEPTION_NMI] = handle_exception,
[EXIT_REASON_EXTERNAL_INTERRUPT] = handle_external_interrupt,
+ [EXIT_REASON_TRIPLE_FAULT] = handle_triple_fault,
[EXIT_REASON_IO_INSTRUCTION] = handle_io,
[EXIT_REASON_CR_ACCESS] = handle_cr,
[EXIT_REASON_DR_ACCESS] = handle_dr,
@@ -1643,6 +1681,7 @@
[EXIT_REASON_MSR_WRITE] = handle_wrmsr,
[EXIT_REASON_PENDING_INTERRUPT] = handle_interrupt_window,
[EXIT_REASON_HLT] = handle_halt,
+ [EXIT_REASON_VMCALL] = handle_vmcall,
};
static const int kvm_vmx_max_exit_handlers =
@@ -1786,10 +1825,10 @@
"kvm_vmx_return: "
/* Save guest registers, load host registers, keep flags */
#ifdef CONFIG_X86_64
- "xchg %3, 0(%%rsp) \n\t"
+ "xchg %3, (%%rsp) \n\t"
"mov %%rax, %c[rax](%3) \n\t"
"mov %%rbx, %c[rbx](%3) \n\t"
- "pushq 0(%%rsp); popq %c[rcx](%3) \n\t"
+ "pushq (%%rsp); popq %c[rcx](%3) \n\t"
"mov %%rdx, %c[rdx](%3) \n\t"
"mov %%rsi, %c[rsi](%3) \n\t"
"mov %%rdi, %c[rdi](%3) \n\t"
@@ -1804,24 +1843,24 @@
"mov %%r15, %c[r15](%3) \n\t"
"mov %%cr2, %%rax \n\t"
"mov %%rax, %c[cr2](%3) \n\t"
- "mov 0(%%rsp), %3 \n\t"
+ "mov (%%rsp), %3 \n\t"
"pop %%rcx; pop %%r15; pop %%r14; pop %%r13; pop %%r12;"
"pop %%r11; pop %%r10; pop %%r9; pop %%r8;"
"pop %%rbp; pop %%rdi; pop %%rsi;"
"pop %%rdx; pop %%rbx; pop %%rax \n\t"
#else
- "xchg %3, 0(%%esp) \n\t"
+ "xchg %3, (%%esp) \n\t"
"mov %%eax, %c[rax](%3) \n\t"
"mov %%ebx, %c[rbx](%3) \n\t"
- "pushl 0(%%esp); popl %c[rcx](%3) \n\t"
+ "pushl (%%esp); popl %c[rcx](%3) \n\t"
"mov %%edx, %c[rdx](%3) \n\t"
"mov %%esi, %c[rsi](%3) \n\t"
"mov %%edi, %c[rdi](%3) \n\t"
"mov %%ebp, %c[rbp](%3) \n\t"
"mov %%cr2, %%eax \n\t"
"mov %%eax, %c[cr2](%3) \n\t"
- "mov 0(%%esp), %3 \n\t"
+ "mov (%%esp), %3 \n\t"
"pop %%ecx; popa \n\t"
#endif
@@ -1859,9 +1898,7 @@
fx_restore(vcpu->host_fx_image);
vcpu->interrupt_window_open = (vmcs_read32(GUEST_INTERRUPTIBILITY_INFO)
& 3) == 0;
-#ifndef CONFIG_X86_64
asm ("mov %0, %%ds; mov %0, %%es" : : "r"(__USER_DS));
-#endif
/*
* Profile KVM exit RIPs:
@@ -2012,6 +2049,7 @@
.vcpu_load = vmx_vcpu_load,
.vcpu_put = vmx_vcpu_put,
+ .vcpu_decache = vmx_vcpu_decache,
.set_guest_debug = set_guest_debug,
.get_msr = vmx_get_msr,
@@ -2045,6 +2083,7 @@
.run = vmx_vcpu_run,
.skip_emulated_instruction = skip_emulated_instruction,
.vcpu_setup = vmx_vcpu_setup,
+ .patch_hypercall = vmx_patch_hypercall,
};
static int __init vmx_init(void)
Index: linux-2.6.20/drivers/kvm/vmx.h
===================================================================
--- linux-2.6.20.orig/drivers/kvm/vmx.h 2007-02-08 13:43:05.000000000 +0100
+++ linux-2.6.20/drivers/kvm/vmx.h 2007-02-08 13:43:07.000000000 +0100
@@ -180,6 +180,7 @@
#define EXIT_REASON_EXCEPTION_NMI 0
#define EXIT_REASON_EXTERNAL_INTERRUPT 1
+#define EXIT_REASON_TRIPLE_FAULT 2
#define EXIT_REASON_PENDING_INTERRUPT 7
Index: linux-2.6.20/include/linux/kvm.h
===================================================================
--- linux-2.6.20.orig/include/linux/kvm.h 2007-02-08 13:43:05.000000000
+0100
+++ linux-2.6.20/include/linux/kvm.h 2007-02-08 13:43:07.000000000 +0100
@@ -11,7 +11,7 @@
#include <asm/types.h>
#include <linux/ioctl.h>
-#define KVM_API_VERSION 2
+#define KVM_API_VERSION 3
/*
* Architectural interrupt line count, and the size of the bitmap needed
@@ -65,6 +65,8 @@
__u8 ready_for_interrupt_injection;
__u8 if_flag;
__u16 padding2;
+
+ /* in (pre_kvm_run), out (post_kvm_run) */
__u64 cr8;
__u64 apic_base;
@@ -185,6 +187,7 @@
__u8 valid;
__u8 writeable;
__u8 usermode;
+ __u8 pad[5];
};
/* for KVM_INTERRUPT */
Index: linux-2.6.20/include/linux/kvm_para.h
===================================================================
--- /dev/null 1970-01-01 00:00:00.000000000 +0000
+++ linux-2.6.20/include/linux/kvm_para.h 2007-02-08 13:43:07.000000000
+0100
@@ -0,0 +1,73 @@
+#ifndef __LINUX_KVM_PARA_H
+#define __LINUX_KVM_PARA_H
+
+/*
+ * Guest OS interface for KVM paravirtualization
+ *
+ * Note: this interface is totally experimental, and is certain to change
+ * as we make progress.
+ */
+
+/*
+ * 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.
+ *
+ * NOTE: all addresses are guest-physical addresses (gpa), to make it
+ * easier for the hypervisor to map between the various addresses.
+ */
+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 hypercall_gpa;
+
+} __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
+
+#define KVM_EINVAL 1
+
+/*
+ * Hypercall calling convention:
+ *
+ * Each hypercall may have 0-6 parameters.
+ *
+ * 64-bit hypercall index is in RAX, goes from 0 to __NR_hypercalls-1
+ *
+ * 64-bit parameters 1-6 are in the standard gcc x86_64 calling convention
+ * order: RDI, RSI, RDX, RCX, R8, R9.
+ *
+ * 32-bit index is EBX, parameters are: EAX, ECX, EDX, ESI, EDI, EBP.
+ * (the first 3 are according to the gcc regparm calling convention)
+ *
+ * No registers are clobbered by the hypercall, except that the
+ * return value is in RAX.
+ */
+#define __NR_hypercalls 0
+
+#endif
signature.asc
Description: OpenPGP digital signature
------------------------------------------------------------------------- Using Tomcat but need to do more? Need to support web services, security? Get stuff done quickly with pre-integrated technology to make your job easier. Download IBM WebSphere Application Server v.1.0.1 based on Apache Geronimo http://sel.as-us.falkag.net/sel?cmd=lnk&kid=120709&bid=263057&dat=121642
_______________________________________________ kvm-devel mailing list [email protected] https://lists.sourceforge.net/lists/listinfo/kvm-devel
