#include "kvm.h"
#include "x86_emulate.h"
#include "segment_descriptor.h"
+#include "irq.h"
#include <linux/kvm.h>
#include <linux/module.h>
static cpumask_t cpus_hardware_enabled;
struct kvm_arch_ops *kvm_arch_ops;
+struct kmem_cache *kvm_vcpu_cache;
+EXPORT_SYMBOL_GPL(kvm_vcpu_cache);
-static void hardware_disable(void *ignored);
+static __read_mostly struct preempt_ops kvm_preempt_ops;
#define STAT_OFFSET(x) offsetof(struct kvm_vcpu, stat.x)
{ "signal_exits", STAT_OFFSET(signal_exits) },
{ "irq_window", STAT_OFFSET(irq_window_exits) },
{ "halt_exits", STAT_OFFSET(halt_exits) },
+ { "halt_wakeup", STAT_OFFSET(halt_wakeup) },
{ "request_irq", STAT_OFFSET(request_irq_exits) },
{ "irq_exits", STAT_OFFSET(irq_exits) },
{ "light_exits", STAT_OFFSET(light_exits) },
#define MAX_IO_MSRS 256
-#define CR0_RESEVED_BITS 0xffffffff1ffaffc0ULL
-#define LMSW_GUEST_MASK 0x0eULL
-#define CR4_RESEVED_BITS (~((1ULL << 11) - 1))
-#define CR8_RESEVED_BITS (~0x0fULL)
+#define CR0_RESERVED_BITS \
+ (~(unsigned long)(X86_CR0_PE | X86_CR0_MP | X86_CR0_EM | X86_CR0_TS \
+ | X86_CR0_ET | X86_CR0_NE | X86_CR0_WP | X86_CR0_AM \
+ | X86_CR0_NW | X86_CR0_CD | X86_CR0_PG))
+#define CR4_RESERVED_BITS \
+ (~(unsigned long)(X86_CR4_VME | X86_CR4_PVI | X86_CR4_TSD | X86_CR4_DE\
+ | X86_CR4_PSE | X86_CR4_PAE | X86_CR4_MCE \
+ | X86_CR4_PGE | X86_CR4_PCE | X86_CR4_OSFXSR \
+ | X86_CR4_OSXMMEXCPT | X86_CR4_VMXE))
+
+#define CR8_RESERVED_BITS (~(unsigned long)X86_CR8_TPR)
#define EFER_RESERVED_BITS 0xfffffffffffff2fe
#ifdef CONFIG_X86_64
return likely(n >= 0 && n < KVM_MAX_VCPUS);
}
-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;
-
- while (size) {
- hpa_t paddr;
- unsigned now;
- unsigned offset;
- hva_t guest_buf;
-
- paddr = gva_to_hpa(vcpu, addr);
-
- if (is_error_hpa(paddr))
- break;
-
- guest_buf = (hva_t)kmap_atomic(
- pfn_to_page(paddr >> PAGE_SHIFT),
- KM_USER0);
- offset = addr & ~PAGE_MASK;
- guest_buf |= offset;
- now = min(size, PAGE_SIZE - offset);
- memcpy(host_buf, (void*)guest_buf, now);
- host_buf += now;
- addr += now;
- size -= now;
- kunmap_atomic((void *)(guest_buf & PAGE_MASK), KM_USER0);
- }
- return req_size - size;
-}
-EXPORT_SYMBOL_GPL(kvm_read_guest);
-
-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;
-
- while (size) {
- hpa_t paddr;
- unsigned now;
- unsigned offset;
- hva_t guest_buf;
- gfn_t gfn;
-
- paddr = gva_to_hpa(vcpu, addr);
-
- if (is_error_hpa(paddr))
- break;
-
- gfn = vcpu->mmu.gva_to_gpa(vcpu, addr) >> PAGE_SHIFT;
- mark_page_dirty(vcpu->kvm, gfn);
- guest_buf = (hva_t)kmap_atomic(
- pfn_to_page(paddr >> PAGE_SHIFT), KM_USER0);
- offset = addr & ~PAGE_MASK;
- guest_buf |= offset;
- now = min(size, PAGE_SIZE - offset);
- memcpy((void*)guest_buf, host_buf, now);
- host_buf += now;
- addr += now;
- size -= now;
- kunmap_atomic((void *)(guest_buf & PAGE_MASK), KM_USER0);
- }
- return req_size - size;
-}
-EXPORT_SYMBOL_GPL(kvm_write_guest);
-
void kvm_load_guest_fpu(struct kvm_vcpu *vcpu)
{
if (!vcpu->fpu_active || vcpu->guest_fpu_loaded)
return;
vcpu->guest_fpu_loaded = 1;
- fx_save(vcpu->host_fx_image);
- fx_restore(vcpu->guest_fx_image);
+ fx_save(&vcpu->host_fx_image);
+ fx_restore(&vcpu->guest_fx_image);
}
EXPORT_SYMBOL_GPL(kvm_load_guest_fpu);
return;
vcpu->guest_fpu_loaded = 0;
- fx_save(vcpu->guest_fx_image);
- fx_restore(vcpu->host_fx_image);
+ fx_save(&vcpu->guest_fx_image);
+ fx_restore(&vcpu->host_fx_image);
}
EXPORT_SYMBOL_GPL(kvm_put_guest_fpu);
*/
static void vcpu_load(struct kvm_vcpu *vcpu)
{
+ int cpu;
+
mutex_lock(&vcpu->mutex);
- kvm_arch_ops->vcpu_load(vcpu);
+ cpu = get_cpu();
+ preempt_notifier_register(&vcpu->preempt_notifier);
+ kvm_arch_ops->vcpu_load(vcpu, cpu);
+ put_cpu();
}
static void vcpu_put(struct kvm_vcpu *vcpu)
{
+ preempt_disable();
kvm_arch_ops->vcpu_put(vcpu);
+ preempt_notifier_unregister(&vcpu->preempt_notifier);
+ preempt_enable();
mutex_unlock(&vcpu->mutex);
}
atomic_set(&completed, 0);
cpus_clear(cpus);
needed = 0;
- for (i = 0; i < kvm->nvcpus; ++i) {
- vcpu = &kvm->vcpus[i];
+ for (i = 0; i < KVM_MAX_VCPUS; ++i) {
+ vcpu = kvm->vcpus[i];
+ if (!vcpu)
+ continue;
if (test_and_set_bit(KVM_TLB_FLUSH, &vcpu->requests))
continue;
cpu = vcpu->cpu;
}
}
+int kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id)
+{
+ struct page *page;
+ int r;
+
+ mutex_init(&vcpu->mutex);
+ vcpu->cpu = -1;
+ vcpu->mmu.root_hpa = INVALID_PAGE;
+ vcpu->kvm = kvm;
+ vcpu->vcpu_id = id;
+ if (!irqchip_in_kernel(kvm) || id == 0)
+ vcpu->mp_state = VCPU_MP_STATE_RUNNABLE;
+ else
+ vcpu->mp_state = VCPU_MP_STATE_UNINITIALIZED;
+ init_waitqueue_head(&vcpu->wq);
+
+ page = alloc_page(GFP_KERNEL | __GFP_ZERO);
+ if (!page) {
+ r = -ENOMEM;
+ goto fail;
+ }
+ vcpu->run = page_address(page);
+
+ page = alloc_page(GFP_KERNEL | __GFP_ZERO);
+ if (!page) {
+ r = -ENOMEM;
+ goto fail_free_run;
+ }
+ vcpu->pio_data = page_address(page);
+
+ r = kvm_mmu_create(vcpu);
+ if (r < 0)
+ goto fail_free_pio_data;
+
+ return 0;
+
+fail_free_pio_data:
+ free_page((unsigned long)vcpu->pio_data);
+fail_free_run:
+ free_page((unsigned long)vcpu->run);
+fail:
+ return -ENOMEM;
+}
+EXPORT_SYMBOL_GPL(kvm_vcpu_init);
+
+void kvm_vcpu_uninit(struct kvm_vcpu *vcpu)
+{
+ kvm_mmu_destroy(vcpu);
+ if (vcpu->apic)
+ hrtimer_cancel(&vcpu->apic->timer.dev);
+ kvm_free_apic(vcpu->apic);
+ free_page((unsigned long)vcpu->pio_data);
+ free_page((unsigned long)vcpu->run);
+}
+EXPORT_SYMBOL_GPL(kvm_vcpu_uninit);
+
static struct kvm *kvm_create_vm(void)
{
struct kvm *kvm = kzalloc(sizeof(struct kvm), GFP_KERNEL);
- int i;
if (!kvm)
return ERR_PTR(-ENOMEM);
kvm_io_bus_init(&kvm->pio_bus);
- spin_lock_init(&kvm->lock);
+ mutex_init(&kvm->lock);
INIT_LIST_HEAD(&kvm->active_mmu_pages);
kvm_io_bus_init(&kvm->mmio_bus);
- for (i = 0; i < KVM_MAX_VCPUS; ++i) {
- struct kvm_vcpu *vcpu = &kvm->vcpus[i];
-
- mutex_init(&vcpu->mutex);
- vcpu->cpu = -1;
- vcpu->kvm = kvm;
- vcpu->mmu.root_hpa = INVALID_PAGE;
- }
spin_lock(&kvm_lock);
list_add(&kvm->vm_list, &vm_list);
spin_unlock(&kvm_lock);
return kvm;
}
-static int kvm_dev_open(struct inode *inode, struct file *filp)
-{
- return 0;
-}
-
/*
* Free any memory in @free but not in @dont.
*/
{
int i;
- for (i = 0; i < 2; ++i)
+ for (i = 0; i < ARRAY_SIZE(vcpu->pio.guest_pages); ++i)
if (vcpu->pio.guest_pages[i]) {
__free_page(vcpu->pio.guest_pages[i]);
vcpu->pio.guest_pages[i] = NULL;
static void kvm_unload_vcpu_mmu(struct kvm_vcpu *vcpu)
{
- if (!vcpu->vmcs)
- return;
-
vcpu_load(vcpu);
kvm_mmu_unload(vcpu);
vcpu_put(vcpu);
}
-static void kvm_free_vcpu(struct kvm_vcpu *vcpu)
-{
- if (!vcpu->vmcs)
- return;
-
- vcpu_load(vcpu);
- kvm_mmu_destroy(vcpu);
- vcpu_put(vcpu);
- kvm_arch_ops->vcpu_free(vcpu);
- free_page((unsigned long)vcpu->run);
- vcpu->run = NULL;
- free_page((unsigned long)vcpu->pio_data);
- vcpu->pio_data = NULL;
- free_pio_guest_pages(vcpu);
-}
-
static void kvm_free_vcpus(struct kvm *kvm)
{
unsigned int i;
* Unpin any mmu pages first.
*/
for (i = 0; i < KVM_MAX_VCPUS; ++i)
- kvm_unload_vcpu_mmu(&kvm->vcpus[i]);
- for (i = 0; i < KVM_MAX_VCPUS; ++i)
- kvm_free_vcpu(&kvm->vcpus[i]);
-}
+ if (kvm->vcpus[i])
+ kvm_unload_vcpu_mmu(kvm->vcpus[i]);
+ for (i = 0; i < KVM_MAX_VCPUS; ++i) {
+ if (kvm->vcpus[i]) {
+ kvm_arch_ops->vcpu_free(kvm->vcpus[i]);
+ kvm->vcpus[i] = NULL;
+ }
+ }
-static int kvm_dev_release(struct inode *inode, struct file *filp)
-{
- return 0;
}
static void kvm_destroy_vm(struct kvm *kvm)
spin_unlock(&kvm_lock);
kvm_io_bus_destroy(&kvm->pio_bus);
kvm_io_bus_destroy(&kvm->mmio_bus);
+ kfree(kvm->vpic);
+ kfree(kvm->vioapic);
kvm_free_vcpus(kvm);
kvm_free_physmem(kvm);
kfree(kvm);
gfn_t pdpt_gfn = cr3 >> PAGE_SHIFT;
unsigned offset = ((cr3 & (PAGE_SIZE-1)) >> 5) << 2;
int i;
- u64 pdpte;
u64 *pdpt;
int ret;
struct page *page;
+ u64 pdpte[ARRAY_SIZE(vcpu->pdptrs)];
- spin_lock(&vcpu->kvm->lock);
+ mutex_lock(&vcpu->kvm->lock);
page = gfn_to_page(vcpu->kvm, pdpt_gfn);
- /* FIXME: !page - emulate? 0xff? */
+ if (!page) {
+ ret = 0;
+ goto out;
+ }
+
pdpt = kmap_atomic(page, KM_USER0);
+ memcpy(pdpte, pdpt+offset, sizeof(pdpte));
+ kunmap_atomic(pdpt, KM_USER0);
- ret = 1;
- for (i = 0; i < 4; ++i) {
- pdpte = pdpt[offset + i];
- if ((pdpte & 1) && (pdpte & 0xfffffff0000001e6ull)) {
+ for (i = 0; i < ARRAY_SIZE(pdpte); ++i) {
+ if ((pdpte[i] & 1) && (pdpte[i] & 0xfffffff0000001e6ull)) {
ret = 0;
goto out;
}
}
+ ret = 1;
- for (i = 0; i < 4; ++i)
- vcpu->pdptrs[i] = pdpt[offset + i];
-
+ memcpy(vcpu->pdptrs, pdpte, sizeof(vcpu->pdptrs));
out:
- kunmap_atomic(pdpt, KM_USER0);
- spin_unlock(&vcpu->kvm->lock);
+ mutex_unlock(&vcpu->kvm->lock);
return ret;
}
void set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
{
- if (cr0 & CR0_RESEVED_BITS) {
+ if (cr0 & CR0_RESERVED_BITS) {
printk(KERN_DEBUG "set_cr0: 0x%lx #GP, reserved bits 0x%lx\n",
cr0, vcpu->cr0);
inject_gp(vcpu);
return;
}
- if ((cr0 & CR0_NW_MASK) && !(cr0 & CR0_CD_MASK)) {
+ if ((cr0 & X86_CR0_NW) && !(cr0 & X86_CR0_CD)) {
printk(KERN_DEBUG "set_cr0: #GP, CD == 0 && NW == 1\n");
inject_gp(vcpu);
return;
}
- if ((cr0 & CR0_PG_MASK) && !(cr0 & CR0_PE_MASK)) {
+ if ((cr0 & X86_CR0_PG) && !(cr0 & X86_CR0_PE)) {
printk(KERN_DEBUG "set_cr0: #GP, set PG flag "
"and a clear PE flag\n");
inject_gp(vcpu);
return;
}
- if (!is_paging(vcpu) && (cr0 & CR0_PG_MASK)) {
+ if (!is_paging(vcpu) && (cr0 & X86_CR0_PG)) {
#ifdef CONFIG_X86_64
if ((vcpu->shadow_efer & EFER_LME)) {
int cs_db, cs_l;
kvm_arch_ops->set_cr0(vcpu, cr0);
vcpu->cr0 = cr0;
- spin_lock(&vcpu->kvm->lock);
+ mutex_lock(&vcpu->kvm->lock);
kvm_mmu_reset_context(vcpu);
- spin_unlock(&vcpu->kvm->lock);
+ mutex_unlock(&vcpu->kvm->lock);
return;
}
EXPORT_SYMBOL_GPL(set_cr0);
void set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
{
- if (cr4 & CR4_RESEVED_BITS) {
+ if (cr4 & CR4_RESERVED_BITS) {
printk(KERN_DEBUG "set_cr4: #GP, reserved bits\n");
inject_gp(vcpu);
return;
}
if (is_long_mode(vcpu)) {
- if (!(cr4 & CR4_PAE_MASK)) {
+ if (!(cr4 & X86_CR4_PAE)) {
printk(KERN_DEBUG "set_cr4: #GP, clearing PAE while "
"in long mode\n");
inject_gp(vcpu);
return;
}
- } else if (is_paging(vcpu) && !is_pae(vcpu) && (cr4 & CR4_PAE_MASK)
+ } else if (is_paging(vcpu) && !is_pae(vcpu) && (cr4 & X86_CR4_PAE)
&& !load_pdptrs(vcpu, vcpu->cr3)) {
printk(KERN_DEBUG "set_cr4: #GP, pdptrs reserved bits\n");
inject_gp(vcpu);
+ return;
}
- if (cr4 & CR4_VMXE_MASK) {
+ if (cr4 & X86_CR4_VMXE) {
printk(KERN_DEBUG "set_cr4: #GP, setting VMXE\n");
inject_gp(vcpu);
return;
}
kvm_arch_ops->set_cr4(vcpu, cr4);
- spin_lock(&vcpu->kvm->lock);
+ vcpu->cr4 = cr4;
+ mutex_lock(&vcpu->kvm->lock);
kvm_mmu_reset_context(vcpu);
- spin_unlock(&vcpu->kvm->lock);
+ mutex_unlock(&vcpu->kvm->lock);
}
EXPORT_SYMBOL_GPL(set_cr4);
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_RESERVED_BITS) {
printk(KERN_DEBUG "set_cr3: #GP, reserved bits\n");
inject_gp(vcpu);
return;
}
} else {
- if (cr3 & CR3_RESEVED_BITS) {
- printk(KERN_DEBUG "set_cr3: #GP, reserved bits\n");
- inject_gp(vcpu);
- return;
- }
- if (is_paging(vcpu) && is_pae(vcpu) &&
- !load_pdptrs(vcpu, cr3)) {
- printk(KERN_DEBUG "set_cr3: #GP, pdptrs "
- "reserved bits\n");
- inject_gp(vcpu);
- return;
+ if (is_pae(vcpu)) {
+ if (cr3 & CR3_PAE_RESERVED_BITS) {
+ printk(KERN_DEBUG
+ "set_cr3: #GP, reserved bits\n");
+ inject_gp(vcpu);
+ return;
+ }
+ if (is_paging(vcpu) && !load_pdptrs(vcpu, cr3)) {
+ printk(KERN_DEBUG "set_cr3: #GP, pdptrs "
+ "reserved bits\n");
+ inject_gp(vcpu);
+ return;
+ }
+ } else {
+ if (cr3 & CR3_NONPAE_RESERVED_BITS) {
+ printk(KERN_DEBUG
+ "set_cr3: #GP, reserved bits\n");
+ inject_gp(vcpu);
+ return;
+ }
}
}
- vcpu->cr3 = cr3;
- spin_lock(&vcpu->kvm->lock);
+ mutex_lock(&vcpu->kvm->lock);
/*
* Does the new cr3 value map to physical memory? (Note, we
* catch an invalid cr3 even in real-mode, because it would
*/
if (unlikely(!gfn_to_memslot(vcpu->kvm, cr3 >> PAGE_SHIFT)))
inject_gp(vcpu);
- else
+ else {
+ vcpu->cr3 = cr3;
vcpu->mmu.new_cr3(vcpu);
- spin_unlock(&vcpu->kvm->lock);
+ }
+ mutex_unlock(&vcpu->kvm->lock);
}
EXPORT_SYMBOL_GPL(set_cr3);
void set_cr8(struct kvm_vcpu *vcpu, unsigned long cr8)
{
- if ( cr8 & CR8_RESEVED_BITS) {
+ if (cr8 & CR8_RESERVED_BITS) {
printk(KERN_DEBUG "set_cr8: #GP, reserved bits 0x%lx\n", cr8);
inject_gp(vcpu);
return;
}
- vcpu->cr8 = cr8;
+ if (irqchip_in_kernel(vcpu->kvm))
+ kvm_lapic_set_tpr(vcpu, cr8);
+ else
+ vcpu->cr8 = cr8;
}
EXPORT_SYMBOL_GPL(set_cr8);
-void fx_init(struct kvm_vcpu *vcpu)
+unsigned long get_cr8(struct kvm_vcpu *vcpu)
+{
+ if (irqchip_in_kernel(vcpu->kvm))
+ return kvm_lapic_get_cr8(vcpu);
+ else
+ return vcpu->cr8;
+}
+EXPORT_SYMBOL_GPL(get_cr8);
+
+u64 kvm_get_apic_base(struct kvm_vcpu *vcpu)
+{
+ if (irqchip_in_kernel(vcpu->kvm))
+ return vcpu->apic_base;
+ else
+ return vcpu->apic_base;
+}
+EXPORT_SYMBOL_GPL(kvm_get_apic_base);
+
+void kvm_set_apic_base(struct kvm_vcpu *vcpu, u64 data)
{
- struct __attribute__ ((__packed__)) fx_image_s {
- u16 control; //fcw
- u16 status; //fsw
- u16 tag; // ftw
- u16 opcode; //fop
- u64 ip; // fpu ip
- u64 operand;// fpu dp
- u32 mxcsr;
- u32 mxcsr_mask;
+ /* TODO: reserve bits check */
+ if (irqchip_in_kernel(vcpu->kvm))
+ kvm_lapic_set_base(vcpu, data);
+ else
+ vcpu->apic_base = data;
+}
+EXPORT_SYMBOL_GPL(kvm_set_apic_base);
- } *fx_image;
+void fx_init(struct kvm_vcpu *vcpu)
+{
+ unsigned after_mxcsr_mask;
- fx_save(vcpu->host_fx_image);
+ /* Initialize guest FPU by resetting ours and saving into guest's */
+ preempt_disable();
+ fx_save(&vcpu->host_fx_image);
fpu_init();
- fx_save(vcpu->guest_fx_image);
- fx_restore(vcpu->host_fx_image);
+ fx_save(&vcpu->guest_fx_image);
+ fx_restore(&vcpu->host_fx_image);
+ preempt_enable();
- fx_image = (struct fx_image_s *)vcpu->guest_fx_image;
- fx_image->mxcsr = 0x1f80;
- memset(vcpu->guest_fx_image + sizeof(struct fx_image_s),
- 0, FX_IMAGE_SIZE - sizeof(struct fx_image_s));
+ vcpu->cr0 |= X86_CR0_ET;
+ after_mxcsr_mask = offsetof(struct i387_fxsave_struct, st_space);
+ vcpu->guest_fx_image.mxcsr = 0x1f80;
+ memset((void *)&vcpu->guest_fx_image + after_mxcsr_mask,
+ 0, sizeof(struct i387_fxsave_struct) - after_mxcsr_mask);
}
EXPORT_SYMBOL_GPL(fx_init);
mem->flags &= ~KVM_MEM_LOG_DIRTY_PAGES;
raced:
- spin_lock(&kvm->lock);
+ mutex_lock(&kvm->lock);
memory_config_version = kvm->memory_config_version;
new = old = *memslot;
* Do memory allocations outside lock. memory_config_version will
* detect any races.
*/
- spin_unlock(&kvm->lock);
+ mutex_unlock(&kvm->lock);
/* Deallocate if slot is being removed */
if (!npages)
memset(new.dirty_bitmap, 0, dirty_bytes);
}
- spin_lock(&kvm->lock);
+ mutex_lock(&kvm->lock);
if (memory_config_version != kvm->memory_config_version) {
- spin_unlock(&kvm->lock);
+ mutex_unlock(&kvm->lock);
kvm_free_physmem_slot(&new, &old);
goto raced;
}
kvm_mmu_slot_remove_write_access(kvm, mem->slot);
kvm_flush_remote_tlbs(kvm);
- spin_unlock(&kvm->lock);
+ mutex_unlock(&kvm->lock);
kvm_free_physmem_slot(&old, &new);
return 0;
out_unlock:
- spin_unlock(&kvm->lock);
+ mutex_unlock(&kvm->lock);
out_free:
kvm_free_physmem_slot(&new, &old);
out:
int n;
unsigned long any = 0;
- spin_lock(&kvm->lock);
+ mutex_lock(&kvm->lock);
/*
* Prevent changes to guest memory configuration even while the lock
* is not taken.
*/
++kvm->busy;
- spin_unlock(&kvm->lock);
+ mutex_unlock(&kvm->lock);
r = -EINVAL;
if (log->slot >= KVM_MEMORY_SLOTS)
goto out;
if (copy_to_user(log->dirty_bitmap, memslot->dirty_bitmap, n))
goto out;
- spin_lock(&kvm->lock);
- kvm_mmu_slot_remove_write_access(kvm, log->slot);
- kvm_flush_remote_tlbs(kvm);
- memset(memslot->dirty_bitmap, 0, n);
- spin_unlock(&kvm->lock);
+ /* If nothing is dirty, don't bother messing with page tables. */
+ if (any) {
+ mutex_lock(&kvm->lock);
+ kvm_mmu_slot_remove_write_access(kvm, log->slot);
+ kvm_flush_remote_tlbs(kvm);
+ memset(memslot->dirty_bitmap, 0, n);
+ mutex_unlock(&kvm->lock);
+ }
r = 0;
out:
- spin_lock(&kvm->lock);
+ mutex_lock(&kvm->lock);
--kvm->busy;
- spin_unlock(&kvm->lock);
+ mutex_unlock(&kvm->lock);
return r;
}
< alias->target_phys_addr)
goto out;
- spin_lock(&kvm->lock);
+ mutex_lock(&kvm->lock);
p = &kvm->aliases[alias->slot];
p->base_gfn = alias->guest_phys_addr >> PAGE_SHIFT;
kvm_mmu_zap_all(kvm);
- spin_unlock(&kvm->lock);
+ mutex_unlock(&kvm->lock);
return 0;
return r;
}
+static int kvm_vm_ioctl_get_irqchip(struct kvm *kvm, struct kvm_irqchip *chip)
+{
+ int r;
+
+ r = 0;
+ switch (chip->chip_id) {
+ case KVM_IRQCHIP_PIC_MASTER:
+ memcpy (&chip->chip.pic,
+ &pic_irqchip(kvm)->pics[0],
+ sizeof(struct kvm_pic_state));
+ break;
+ case KVM_IRQCHIP_PIC_SLAVE:
+ memcpy (&chip->chip.pic,
+ &pic_irqchip(kvm)->pics[1],
+ sizeof(struct kvm_pic_state));
+ break;
+ case KVM_IRQCHIP_IOAPIC:
+ memcpy (&chip->chip.ioapic,
+ ioapic_irqchip(kvm),
+ sizeof(struct kvm_ioapic_state));
+ break;
+ default:
+ r = -EINVAL;
+ break;
+ }
+ return r;
+}
+
+static int kvm_vm_ioctl_set_irqchip(struct kvm *kvm, struct kvm_irqchip *chip)
+{
+ int r;
+
+ r = 0;
+ switch (chip->chip_id) {
+ case KVM_IRQCHIP_PIC_MASTER:
+ memcpy (&pic_irqchip(kvm)->pics[0],
+ &chip->chip.pic,
+ sizeof(struct kvm_pic_state));
+ break;
+ case KVM_IRQCHIP_PIC_SLAVE:
+ memcpy (&pic_irqchip(kvm)->pics[1],
+ &chip->chip.pic,
+ sizeof(struct kvm_pic_state));
+ break;
+ case KVM_IRQCHIP_IOAPIC:
+ memcpy (ioapic_irqchip(kvm),
+ &chip->chip.ioapic,
+ sizeof(struct kvm_ioapic_state));
+ break;
+ default:
+ r = -EINVAL;
+ break;
+ }
+ kvm_pic_update_irq(pic_irqchip(kvm));
+ return r;
+}
+
static gfn_t unalias_gfn(struct kvm *kvm, gfn_t gfn)
{
int i;
}
EXPORT_SYMBOL_GPL(gfn_to_page);
+/* WARNING: Does not work on aliased pages. */
void mark_page_dirty(struct kvm *kvm, gfn_t gfn)
{
- int i;
struct kvm_memory_slot *memslot;
- unsigned long rel_gfn;
- for (i = 0; i < kvm->nmemslots; ++i) {
- memslot = &kvm->memslots[i];
+ memslot = __gfn_to_memslot(kvm, gfn);
+ if (memslot && memslot->dirty_bitmap) {
+ unsigned long rel_gfn = gfn - memslot->base_gfn;
- if (gfn >= memslot->base_gfn
- && gfn < memslot->base_gfn + memslot->npages) {
-
- if (!memslot->dirty_bitmap)
- return;
-
- rel_gfn = gfn - memslot->base_gfn;
-
- /* avoid RMW */
- if (!test_bit(rel_gfn, memslot->dirty_bitmap))
- set_bit(rel_gfn, memslot->dirty_bitmap);
- return;
- }
+ /* avoid RMW */
+ if (!test_bit(rel_gfn, memslot->dirty_bitmap))
+ set_bit(rel_gfn, memslot->dirty_bitmap);
}
}
-static int emulator_read_std(unsigned long addr,
+int emulator_read_std(unsigned long addr,
void *val,
unsigned int bytes,
- struct x86_emulate_ctxt *ctxt)
+ struct kvm_vcpu *vcpu)
{
- struct kvm_vcpu *vcpu = ctxt->vcpu;
void *data = val;
while (bytes) {
return X86EMUL_CONTINUE;
}
+EXPORT_SYMBOL_GPL(emulator_read_std);
static int emulator_write_std(unsigned long addr,
const void *val,
unsigned int bytes,
- struct x86_emulate_ctxt *ctxt)
+ struct kvm_vcpu *vcpu)
{
- printk(KERN_ERR "emulator_write_std: addr %lx n %d\n",
- addr, bytes);
+ pr_unimpl(vcpu, "emulator_write_std: addr %lx n %d\n", addr, bytes);
return X86EMUL_UNHANDLEABLE;
}
+/*
+ * Only apic need an MMIO device hook, so shortcut now..
+ */
+static struct kvm_io_device *vcpu_find_pervcpu_dev(struct kvm_vcpu *vcpu,
+ gpa_t addr)
+{
+ struct kvm_io_device *dev;
+
+ if (vcpu->apic) {
+ dev = &vcpu->apic->dev;
+ if (dev->in_range(dev, addr))
+ return dev;
+ }
+ return NULL;
+}
+
static struct kvm_io_device *vcpu_find_mmio_dev(struct kvm_vcpu *vcpu,
gpa_t addr)
{
- /*
- * Note that its important to have this wrapper function because
- * in the very near future we will be checking for MMIOs against
- * the LAPIC as well as the general MMIO bus
- */
- return kvm_io_bus_find_dev(&vcpu->kvm->mmio_bus, addr);
+ struct kvm_io_device *dev;
+
+ dev = vcpu_find_pervcpu_dev(vcpu, addr);
+ if (dev == NULL)
+ dev = kvm_io_bus_find_dev(&vcpu->kvm->mmio_bus, addr);
+ return dev;
}
static struct kvm_io_device *vcpu_find_pio_dev(struct kvm_vcpu *vcpu,
static int emulator_read_emulated(unsigned long addr,
void *val,
unsigned int bytes,
- struct x86_emulate_ctxt *ctxt)
+ struct kvm_vcpu *vcpu)
{
- struct kvm_vcpu *vcpu = ctxt->vcpu;
struct kvm_io_device *mmio_dev;
gpa_t gpa;
memcpy(val, vcpu->mmio_data, bytes);
vcpu->mmio_read_completed = 0;
return X86EMUL_CONTINUE;
- } else if (emulator_read_std(addr, val, bytes, ctxt)
+ } else if (emulator_read_std(addr, val, bytes, vcpu)
== X86EMUL_CONTINUE)
return X86EMUL_CONTINUE;
{
struct page *page;
void *virt;
- unsigned offset = offset_in_page(gpa);
if (((gpa + bytes - 1) >> PAGE_SHIFT) != (gpa >> PAGE_SHIFT))
return 0;
return 0;
mark_page_dirty(vcpu->kvm, gpa >> PAGE_SHIFT);
virt = kmap_atomic(page, KM_USER0);
- kvm_mmu_pte_write(vcpu, gpa, virt + offset, val, bytes);
+ kvm_mmu_pte_write(vcpu, gpa, val, bytes);
memcpy(virt + offset_in_page(gpa), val, bytes);
kunmap_atomic(virt, KM_USER0);
return 1;
static int emulator_write_emulated_onepage(unsigned long addr,
const void *val,
unsigned int bytes,
- struct x86_emulate_ctxt *ctxt)
+ struct kvm_vcpu *vcpu)
{
- struct kvm_vcpu *vcpu = ctxt->vcpu;
struct kvm_io_device *mmio_dev;
gpa_t gpa = vcpu->mmu.gva_to_gpa(vcpu, addr);
return X86EMUL_CONTINUE;
}
-static int emulator_write_emulated(unsigned long addr,
+int emulator_write_emulated(unsigned long addr,
const void *val,
unsigned int bytes,
- struct x86_emulate_ctxt *ctxt)
+ struct kvm_vcpu *vcpu)
{
/* Crossing a page boundary? */
if (((addr + bytes - 1) ^ addr) & PAGE_MASK) {
int rc, now;
now = -addr & ~PAGE_MASK;
- rc = emulator_write_emulated_onepage(addr, val, now, ctxt);
+ rc = emulator_write_emulated_onepage(addr, val, now, vcpu);
if (rc != X86EMUL_CONTINUE)
return rc;
addr += now;
val += now;
bytes -= now;
}
- return emulator_write_emulated_onepage(addr, val, bytes, ctxt);
+ return emulator_write_emulated_onepage(addr, val, bytes, vcpu);
}
+EXPORT_SYMBOL_GPL(emulator_write_emulated);
static int emulator_cmpxchg_emulated(unsigned long addr,
const void *old,
const void *new,
unsigned int bytes,
- struct x86_emulate_ctxt *ctxt)
+ struct kvm_vcpu *vcpu)
{
static int reported;
reported = 1;
printk(KERN_WARNING "kvm: emulating exchange as write\n");
}
- return emulator_write_emulated(addr, new, bytes, ctxt);
+ return emulator_write_emulated(addr, new, bytes, vcpu);
}
static unsigned long get_segment_base(struct kvm_vcpu *vcpu, int seg)
int emulate_clts(struct kvm_vcpu *vcpu)
{
- unsigned long cr0;
-
- cr0 = vcpu->cr0 & ~CR0_TS_MASK;
- kvm_arch_ops->set_cr0(vcpu, cr0);
+ vcpu->cr0 &= ~X86_CR0_TS;
+ kvm_arch_ops->set_cr0(vcpu, vcpu->cr0);
return X86EMUL_CONTINUE;
}
*dest = kvm_arch_ops->get_dr(vcpu, dr);
return X86EMUL_CONTINUE;
default:
- printk(KERN_DEBUG "%s: unexpected dr %u\n",
- __FUNCTION__, dr);
+ pr_unimpl(vcpu, "%s: unexpected dr %u\n", __FUNCTION__, dr);
return X86EMUL_UNHANDLEABLE;
}
}
if (reported)
return;
- emulator_read_std(rip_linear, (void *)opcodes, 4, ctxt);
+ emulator_read_std(rip_linear, (void *)opcodes, 4, ctxt->vcpu);
printk(KERN_ERR "emulation failed but !mmio_needed?"
" rip %lx %02x %02x %02x %02x\n",
emulate_ctxt.fs_base = get_segment_base(vcpu, VCPU_SREG_FS);
vcpu->mmio_is_write = 0;
+ vcpu->pio.string = 0;
r = x86_emulate_memop(&emulate_ctxt, &emulate_ops);
+ if (vcpu->pio.string)
+ return EMULATE_DO_MMIO;
if ((r || vcpu->mmio_is_write) && run) {
+ run->exit_reason = KVM_EXIT_MMIO;
run->mmio.phys_addr = vcpu->mmio_phys_addr;
memcpy(run->mmio.data, vcpu->mmio_data, 8);
run->mmio.len = vcpu->mmio_size;
}
EXPORT_SYMBOL_GPL(emulate_instruction);
-int kvm_emulate_halt(struct kvm_vcpu *vcpu)
+/*
+ * The vCPU has executed a HLT instruction with in-kernel mode enabled.
+ */
+static void kvm_vcpu_block(struct kvm_vcpu *vcpu)
{
- if (vcpu->irq_summary)
- return 1;
+ DECLARE_WAITQUEUE(wait, current);
+
+ add_wait_queue(&vcpu->wq, &wait);
+
+ /*
+ * We will block until either an interrupt or a signal wakes us up
+ */
+ while (!kvm_cpu_has_interrupt(vcpu)
+ && !signal_pending(current)
+ && vcpu->mp_state != VCPU_MP_STATE_RUNNABLE
+ && vcpu->mp_state != VCPU_MP_STATE_SIPI_RECEIVED) {
+ set_current_state(TASK_INTERRUPTIBLE);
+ vcpu_put(vcpu);
+ schedule();
+ vcpu_load(vcpu);
+ }
+
+ __set_current_state(TASK_RUNNING);
+ remove_wait_queue(&vcpu->wq, &wait);
+}
- vcpu->run->exit_reason = KVM_EXIT_HLT;
+int kvm_emulate_halt(struct kvm_vcpu *vcpu)
+{
++vcpu->stat.halt_exits;
- return 0;
+ if (irqchip_in_kernel(vcpu->kvm)) {
+ vcpu->mp_state = VCPU_MP_STATE_HALTED;
+ kvm_vcpu_block(vcpu);
+ if (vcpu->mp_state != VCPU_MP_STATE_RUNNABLE)
+ return -EINTR;
+ return 1;
+ } else {
+ vcpu->run->exit_reason = KVM_EXIT_HLT;
+ return 0;
+ }
}
EXPORT_SYMBOL_GPL(kvm_emulate_halt);
}
switch (nr) {
default:
+ run->hypercall.nr = nr;
run->hypercall.args[0] = a0;
run->hypercall.args[1] = a1;
run->hypercall.args[2] = a2;
mark_page_dirty(vcpu->kvm, para_state_gpa >> PAGE_SHIFT);
para_state_page = pfn_to_page(para_state_hpa >> PAGE_SHIFT);
- para_state = kmap_atomic(para_state_page, KM_USER0);
+ para_state = kmap(para_state_page);
printk(KERN_DEBUG ".... guest version: %d\n", para_state->guest_version);
printk(KERN_DEBUG ".... size: %d\n", para_state->size);
para_state->ret = 0;
err_kunmap_skip:
- kunmap_atomic(para_state, KM_USER0);
+ kunmap(para_state_page);
return 0;
err_gp:
return 1;
data = 3;
break;
case MSR_IA32_APICBASE:
- data = vcpu->apic_base;
+ data = kvm_get_apic_base(vcpu);
break;
case MSR_IA32_MISC_ENABLE:
data = vcpu->ia32_misc_enable_msr;
break;
#endif
default:
- printk(KERN_ERR "kvm: unhandled rdmsr: 0x%x\n", msr);
+ pr_unimpl(vcpu, "unhandled rdmsr: 0x%x\n", msr);
return 1;
}
*pdata = data;
break;
#endif
case MSR_IA32_MC0_STATUS:
- printk(KERN_WARNING "%s: MSR_IA32_MC0_STATUS 0x%llx, nop\n",
+ pr_unimpl(vcpu, "%s: MSR_IA32_MC0_STATUS 0x%llx, nop\n",
__FUNCTION__, data);
break;
case MSR_IA32_MCG_STATUS:
- printk(KERN_WARNING "%s: MSR_IA32_MCG_STATUS 0x%llx, nop\n",
+ pr_unimpl(vcpu, "%s: MSR_IA32_MCG_STATUS 0x%llx, nop\n",
__FUNCTION__, data);
break;
case MSR_IA32_UCODE_REV:
case 0x200 ... 0x2ff: /* MTRRs */
break;
case MSR_IA32_APICBASE:
- vcpu->apic_base = data;
+ kvm_set_apic_base(vcpu, data);
break;
case MSR_IA32_MISC_ENABLE:
vcpu->ia32_misc_enable_msr = data;
return vcpu_register_para(vcpu, data);
default:
- printk(KERN_ERR "kvm: unhandled wrmsr: 0x%x\n", msr);
+ pr_unimpl(vcpu, "unhandled wrmsr: 0x%x\n", msr);
return 1;
}
return 0;
{
if (!need_resched())
return;
- vcpu_put(vcpu);
cond_resched();
- vcpu_load(vcpu);
}
EXPORT_SYMBOL_GPL(kvm_resched);
-void load_msrs(struct vmx_msr_entry *e, int n)
-{
- int i;
-
- for (i = 0; i < n; ++i)
- wrmsrl(e[i].index, e[i].data);
-}
-EXPORT_SYMBOL_GPL(load_msrs);
-
-void save_msrs(struct vmx_msr_entry *e, int n)
-{
- int i;
-
- for (i = 0; i < n; ++i)
- rdmsrl(e[i].index, e[i].data);
-}
-EXPORT_SYMBOL_GPL(save_msrs);
-
void kvm_emulate_cpuid(struct kvm_vcpu *vcpu)
{
int i;
unsigned bytes;
int nr_pages = vcpu->pio.guest_pages[1] ? 2 : 1;
- kvm_arch_ops->vcpu_put(vcpu);
q = vmap(vcpu->pio.guest_pages, nr_pages, VM_READ|VM_WRITE,
PAGE_KERNEL);
if (!q) {
- kvm_arch_ops->vcpu_load(vcpu);
free_pio_guest_pages(vcpu);
return -ENOMEM;
}
memcpy(p, q, bytes);
q -= vcpu->pio.guest_page_offset;
vunmap(q);
- kvm_arch_ops->vcpu_load(vcpu);
free_pio_guest_pages(vcpu);
return 0;
}
return 0;
}
-void kernel_pio(struct kvm_io_device *pio_dev, struct kvm_vcpu *vcpu)
+static void kernel_pio(struct kvm_io_device *pio_dev,
+ struct kvm_vcpu *vcpu,
+ void *pd)
{
/* TODO: String I/O for in kernel device */
+ mutex_lock(&vcpu->kvm->lock);
if (vcpu->pio.in)
kvm_iodevice_read(pio_dev, vcpu->pio.port,
vcpu->pio.size,
- vcpu->pio_data);
+ pd);
else
kvm_iodevice_write(pio_dev, vcpu->pio.port,
vcpu->pio.size,
- vcpu->pio_data);
+ pd);
+ mutex_unlock(&vcpu->kvm->lock);
+}
+
+static void pio_string_write(struct kvm_io_device *pio_dev,
+ struct kvm_vcpu *vcpu)
+{
+ struct kvm_pio_request *io = &vcpu->pio;
+ void *pd = vcpu->pio_data;
+ int i;
+
+ mutex_lock(&vcpu->kvm->lock);
+ for (i = 0; i < io->cur_count; i++) {
+ kvm_iodevice_write(pio_dev, io->port,
+ io->size,
+ pd);
+ pd += io->size;
+ }
+ mutex_unlock(&vcpu->kvm->lock);
+}
+
+int kvm_emulate_pio (struct kvm_vcpu *vcpu, struct kvm_run *run, int in,
+ int size, unsigned port)
+{
+ struct kvm_io_device *pio_dev;
+
+ vcpu->run->exit_reason = KVM_EXIT_IO;
+ vcpu->run->io.direction = in ? KVM_EXIT_IO_IN : KVM_EXIT_IO_OUT;
+ vcpu->run->io.size = vcpu->pio.size = size;
+ vcpu->run->io.data_offset = KVM_PIO_PAGE_OFFSET * PAGE_SIZE;
+ vcpu->run->io.count = vcpu->pio.count = vcpu->pio.cur_count = 1;
+ vcpu->run->io.port = vcpu->pio.port = port;
+ vcpu->pio.in = in;
+ vcpu->pio.string = 0;
+ vcpu->pio.down = 0;
+ vcpu->pio.guest_page_offset = 0;
+ vcpu->pio.rep = 0;
+
+ kvm_arch_ops->cache_regs(vcpu);
+ memcpy(vcpu->pio_data, &vcpu->regs[VCPU_REGS_RAX], 4);
+ kvm_arch_ops->decache_regs(vcpu);
+
+ pio_dev = vcpu_find_pio_dev(vcpu, port);
+ if (pio_dev) {
+ kernel_pio(pio_dev, vcpu, vcpu->pio_data);
+ complete_pio(vcpu);
+ return 1;
+ }
+ return 0;
}
+EXPORT_SYMBOL_GPL(kvm_emulate_pio);
-int kvm_setup_pio(struct kvm_vcpu *vcpu, struct kvm_run *run, int in,
- int size, unsigned long count, int string, int down,
+int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, struct kvm_run *run, int in,
+ int size, unsigned long count, int down,
gva_t address, int rep, unsigned port)
{
unsigned now, in_page;
- int i;
+ int i, ret = 0;
int nr_pages = 1;
struct page *page;
struct kvm_io_device *pio_dev;
vcpu->run->exit_reason = KVM_EXIT_IO;
vcpu->run->io.direction = in ? KVM_EXIT_IO_IN : KVM_EXIT_IO_OUT;
- vcpu->run->io.size = size;
+ vcpu->run->io.size = vcpu->pio.size = size;
vcpu->run->io.data_offset = KVM_PIO_PAGE_OFFSET * PAGE_SIZE;
- vcpu->run->io.count = count;
- vcpu->run->io.port = port;
- vcpu->pio.count = count;
- vcpu->pio.cur_count = count;
- vcpu->pio.size = size;
+ vcpu->run->io.count = vcpu->pio.count = vcpu->pio.cur_count = count;
+ vcpu->run->io.port = vcpu->pio.port = port;
vcpu->pio.in = in;
- vcpu->pio.port = port;
- vcpu->pio.string = string;
+ vcpu->pio.string = 1;
vcpu->pio.down = down;
vcpu->pio.guest_page_offset = offset_in_page(address);
vcpu->pio.rep = rep;
- pio_dev = vcpu_find_pio_dev(vcpu, port);
- if (!string) {
- kvm_arch_ops->cache_regs(vcpu);
- memcpy(vcpu->pio_data, &vcpu->regs[VCPU_REGS_RAX], 4);
- kvm_arch_ops->decache_regs(vcpu);
- if (pio_dev) {
- kernel_pio(pio_dev, vcpu);
- complete_pio(vcpu);
- return 1;
- }
- return 0;
- }
- /* TODO: String I/O for in kernel device */
- if (pio_dev)
- printk(KERN_ERR "kvm_setup_pio: no string io support\n");
-
if (!count) {
kvm_arch_ops->skip_emulated_instruction(vcpu);
return 1;
}
- now = min(count, PAGE_SIZE / size);
-
if (!down)
in_page = PAGE_SIZE - offset_in_page(address);
else
/*
* String I/O in reverse. Yuck. Kill the guest, fix later.
*/
- printk(KERN_ERR "kvm: guest string pio down\n");
+ pr_unimpl(vcpu, "guest string pio down\n");
inject_gp(vcpu);
return 1;
}
vcpu->pio.cur_count = now;
for (i = 0; i < nr_pages; ++i) {
- spin_lock(&vcpu->kvm->lock);
+ mutex_lock(&vcpu->kvm->lock);
page = gva_to_page(vcpu, address + i * PAGE_SIZE);
if (page)
get_page(page);
vcpu->pio.guest_pages[i] = page;
- spin_unlock(&vcpu->kvm->lock);
+ mutex_unlock(&vcpu->kvm->lock);
if (!page) {
inject_gp(vcpu);
free_pio_guest_pages(vcpu);
}
}
- if (!vcpu->pio.in)
- return pio_copy_data(vcpu);
- return 0;
+ pio_dev = vcpu_find_pio_dev(vcpu, port);
+ if (!vcpu->pio.in) {
+ /* string PIO write */
+ ret = pio_copy_data(vcpu);
+ if (ret >= 0 && pio_dev) {
+ pio_string_write(pio_dev, vcpu);
+ complete_pio(vcpu);
+ if (vcpu->pio.count == 0)
+ ret = 1;
+ }
+ } else if (pio_dev)
+ pr_unimpl(vcpu, "no string pio read support yet, "
+ "port %x size %d count %ld\n",
+ port, size, count);
+
+ return ret;
}
-EXPORT_SYMBOL_GPL(kvm_setup_pio);
+EXPORT_SYMBOL_GPL(kvm_emulate_pio_string);
static int kvm_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
{
vcpu_load(vcpu);
+ if (unlikely(vcpu->mp_state == VCPU_MP_STATE_UNINITIALIZED)) {
+ kvm_vcpu_block(vcpu);
+ vcpu_put(vcpu);
+ return -EAGAIN;
+ }
+
if (vcpu->sigset_active)
sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved);
/* re-sync apic's tpr */
- vcpu->cr8 = kvm_run->cr8;
+ if (!irqchip_in_kernel(vcpu->kvm))
+ set_cr8(vcpu, kvm_run->cr8);
if (vcpu->pio.cur_count) {
r = complete_pio(vcpu);
/*
* Read-modify-write. Back to userspace.
*/
- kvm_run->exit_reason = KVM_EXIT_MMIO;
r = 0;
goto out;
}
struct kvm_sregs *sregs)
{
struct descriptor_table dt;
+ int pending_vec;
vcpu_load(vcpu);
sregs->cr2 = vcpu->cr2;
sregs->cr3 = vcpu->cr3;
sregs->cr4 = vcpu->cr4;
- sregs->cr8 = vcpu->cr8;
+ sregs->cr8 = get_cr8(vcpu);
sregs->efer = vcpu->shadow_efer;
- sregs->apic_base = vcpu->apic_base;
-
- memcpy(sregs->interrupt_bitmap, vcpu->irq_pending,
- sizeof sregs->interrupt_bitmap);
+ sregs->apic_base = kvm_get_apic_base(vcpu);
+
+ if (irqchip_in_kernel(vcpu->kvm)) {
+ memset(sregs->interrupt_bitmap, 0,
+ sizeof sregs->interrupt_bitmap);
+ pending_vec = kvm_arch_ops->get_irq(vcpu);
+ if (pending_vec >= 0)
+ set_bit(pending_vec, (unsigned long *)sregs->interrupt_bitmap);
+ } else
+ memcpy(sregs->interrupt_bitmap, vcpu->irq_pending,
+ sizeof sregs->interrupt_bitmap);
vcpu_put(vcpu);
struct kvm_sregs *sregs)
{
int mmu_reset_needed = 0;
- int i;
+ int i, pending_vec, max_bits;
struct descriptor_table dt;
vcpu_load(vcpu);
mmu_reset_needed |= vcpu->cr3 != sregs->cr3;
vcpu->cr3 = sregs->cr3;
- vcpu->cr8 = sregs->cr8;
+ set_cr8(vcpu, sregs->cr8);
mmu_reset_needed |= vcpu->shadow_efer != sregs->efer;
#ifdef CONFIG_X86_64
kvm_arch_ops->set_efer(vcpu, sregs->efer);
#endif
- vcpu->apic_base = sregs->apic_base;
+ kvm_set_apic_base(vcpu, sregs->apic_base);
kvm_arch_ops->decache_cr4_guest_bits(vcpu);
mmu_reset_needed |= vcpu->cr0 != sregs->cr0;
+ vcpu->cr0 = sregs->cr0;
kvm_arch_ops->set_cr0(vcpu, sregs->cr0);
mmu_reset_needed |= vcpu->cr4 != sregs->cr4;
if (mmu_reset_needed)
kvm_mmu_reset_context(vcpu);
- memcpy(vcpu->irq_pending, sregs->interrupt_bitmap,
- sizeof vcpu->irq_pending);
- vcpu->irq_summary = 0;
- for (i = 0; i < NR_IRQ_WORDS; ++i)
- if (vcpu->irq_pending[i])
- __set_bit(i, &vcpu->irq_summary);
+ if (!irqchip_in_kernel(vcpu->kvm)) {
+ memcpy(vcpu->irq_pending, sregs->interrupt_bitmap,
+ sizeof vcpu->irq_pending);
+ vcpu->irq_summary = 0;
+ for (i = 0; i < ARRAY_SIZE(vcpu->irq_pending); ++i)
+ if (vcpu->irq_pending[i])
+ __set_bit(i, &vcpu->irq_summary);
+ } else {
+ max_bits = (sizeof sregs->interrupt_bitmap) << 3;
+ pending_vec = find_first_bit(
+ (const unsigned long *)sregs->interrupt_bitmap,
+ max_bits);
+ /* Only pending external irq is handled here */
+ if (pending_vec < max_bits) {
+ kvm_arch_ops->set_irq(vcpu, pending_vec);
+ printk("Set back pending irq %d\n", pending_vec);
+ }
+ }
set_segment(vcpu, &sregs->cs, VCPU_SREG_CS);
set_segment(vcpu, &sregs->ds, VCPU_SREG_DS);
return 0;
}
+void kvm_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l)
+{
+ struct kvm_segment cs;
+
+ get_segment(vcpu, &cs, VCPU_SREG_CS);
+ *db = cs.db;
+ *l = cs.l;
+}
+EXPORT_SYMBOL_GPL(kvm_get_cs_db_l_bits);
+
/*
* List of msr numbers which we expose to userspace through KVM_GET_MSRS
* and KVM_SET_MSRS, and KVM_GET_MSR_INDEX_LIST.
gpa_t gpa;
vcpu_load(vcpu);
- spin_lock(&vcpu->kvm->lock);
+ mutex_lock(&vcpu->kvm->lock);
gpa = vcpu->mmu.gva_to_gpa(vcpu, vaddr);
tr->physical_address = gpa;
tr->valid = gpa != UNMAPPED_GVA;
tr->writeable = 1;
tr->usermode = 0;
- spin_unlock(&vcpu->kvm->lock);
+ mutex_unlock(&vcpu->kvm->lock);
vcpu_put(vcpu);
return 0;
{
if (irq->irq < 0 || irq->irq >= 256)
return -EINVAL;
+ if (irqchip_in_kernel(vcpu->kvm))
+ return -ENXIO;
vcpu_load(vcpu);
set_bit(irq->irq, vcpu->irq_pending);
unsigned long pgoff;
struct page *page;
- *type = VM_FAULT_MINOR;
pgoff = ((address - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;
if (pgoff == 0)
page = virt_to_page(vcpu->run);
else
return NOPAGE_SIGBUS;
get_page(page);
+ if (type != NULL)
+ *type = VM_FAULT_MINOR;
+
return page;
}
{
int r;
struct kvm_vcpu *vcpu;
- struct page *page;
- r = -EINVAL;
if (!valid_vcpu(n))
- goto out;
-
- vcpu = &kvm->vcpus[n];
-
- mutex_lock(&vcpu->mutex);
-
- if (vcpu->vmcs) {
- mutex_unlock(&vcpu->mutex);
- return -EEXIST;
- }
-
- page = alloc_page(GFP_KERNEL | __GFP_ZERO);
- r = -ENOMEM;
- if (!page)
- goto out_unlock;
- vcpu->run = page_address(page);
-
- page = alloc_page(GFP_KERNEL | __GFP_ZERO);
- r = -ENOMEM;
- if (!page)
- goto out_free_run;
- vcpu->pio_data = page_address(page);
+ return -EINVAL;
- vcpu->host_fx_image = (char*)ALIGN((hva_t)vcpu->fx_buf,
- FX_IMAGE_ALIGN);
- vcpu->guest_fx_image = vcpu->host_fx_image + FX_IMAGE_SIZE;
- vcpu->cr0 = 0x10;
+ vcpu = kvm_arch_ops->vcpu_create(kvm, n);
+ if (IS_ERR(vcpu))
+ return PTR_ERR(vcpu);
- r = kvm_arch_ops->vcpu_create(vcpu);
- if (r < 0)
- goto out_free_vcpus;
+ preempt_notifier_init(&vcpu->preempt_notifier, &kvm_preempt_ops);
- r = kvm_mmu_create(vcpu);
- if (r < 0)
- goto out_free_vcpus;
+ /* We do fxsave: this must be aligned. */
+ BUG_ON((unsigned long)&vcpu->host_fx_image & 0xF);
- kvm_arch_ops->vcpu_load(vcpu);
+ vcpu_load(vcpu);
r = kvm_mmu_setup(vcpu);
- if (r >= 0)
- r = kvm_arch_ops->vcpu_setup(vcpu);
vcpu_put(vcpu);
-
if (r < 0)
- goto out_free_vcpus;
+ goto free_vcpu;
+
+ mutex_lock(&kvm->lock);
+ if (kvm->vcpus[n]) {
+ r = -EEXIST;
+ mutex_unlock(&kvm->lock);
+ goto mmu_unload;
+ }
+ kvm->vcpus[n] = vcpu;
+ mutex_unlock(&kvm->lock);
+ /* Now it's all set up, let userspace reach it */
r = create_vcpu_fd(vcpu);
if (r < 0)
- goto out_free_vcpus;
+ goto unlink;
+ return r;
- spin_lock(&kvm_lock);
- if (n >= kvm->nvcpus)
- kvm->nvcpus = n + 1;
- spin_unlock(&kvm_lock);
+unlink:
+ mutex_lock(&kvm->lock);
+ kvm->vcpus[n] = NULL;
+ mutex_unlock(&kvm->lock);
- return r;
+mmu_unload:
+ vcpu_load(vcpu);
+ kvm_mmu_unload(vcpu);
+ vcpu_put(vcpu);
-out_free_vcpus:
- kvm_free_vcpu(vcpu);
-out_free_run:
- free_page((unsigned long)vcpu->run);
- vcpu->run = NULL;
-out_unlock:
- mutex_unlock(&vcpu->mutex);
-out:
+free_vcpu:
+ kvm_arch_ops->vcpu_free(vcpu);
return r;
}
static int kvm_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
{
- struct fxsave *fxsave = (struct fxsave *)vcpu->guest_fx_image;
+ struct fxsave *fxsave = (struct fxsave *)&vcpu->guest_fx_image;
vcpu_load(vcpu);
static int kvm_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
{
- struct fxsave *fxsave = (struct fxsave *)vcpu->guest_fx_image;
+ struct fxsave *fxsave = (struct fxsave *)&vcpu->guest_fx_image;
vcpu_load(vcpu);
return 0;
}
+static int kvm_vcpu_ioctl_get_lapic(struct kvm_vcpu *vcpu,
+ struct kvm_lapic_state *s)
+{
+ vcpu_load(vcpu);
+ memcpy(s->regs, vcpu->apic->regs, sizeof *s);
+ vcpu_put(vcpu);
+
+ return 0;
+}
+
+static int kvm_vcpu_ioctl_set_lapic(struct kvm_vcpu *vcpu,
+ struct kvm_lapic_state *s)
+{
+ vcpu_load(vcpu);
+ memcpy(vcpu->apic->regs, s->regs, sizeof *s);
+ kvm_apic_post_state_restore(vcpu);
+ vcpu_put(vcpu);
+
+ return 0;
+}
+
static long kvm_vcpu_ioctl(struct file *filp,
unsigned int ioctl, unsigned long arg)
{
r = 0;
break;
}
+ case KVM_GET_LAPIC: {
+ struct kvm_lapic_state lapic;
+
+ memset(&lapic, 0, sizeof lapic);
+ r = kvm_vcpu_ioctl_get_lapic(vcpu, &lapic);
+ if (r)
+ goto out;
+ r = -EFAULT;
+ if (copy_to_user(argp, &lapic, sizeof lapic))
+ goto out;
+ r = 0;
+ break;
+ }
+ case KVM_SET_LAPIC: {
+ struct kvm_lapic_state lapic;
+
+ r = -EFAULT;
+ if (copy_from_user(&lapic, argp, sizeof lapic))
+ goto out;
+ r = kvm_vcpu_ioctl_set_lapic(vcpu, &lapic);;
+ if (r)
+ goto out;
+ r = 0;
+ break;
+ }
default:
;
}
goto out;
break;
}
+ case KVM_CREATE_IRQCHIP:
+ r = -ENOMEM;
+ kvm->vpic = kvm_create_pic(kvm);
+ if (kvm->vpic) {
+ r = kvm_ioapic_init(kvm);
+ if (r) {
+ kfree(kvm->vpic);
+ kvm->vpic = NULL;
+ goto out;
+ }
+ }
+ else
+ goto out;
+ break;
+ case KVM_IRQ_LINE: {
+ struct kvm_irq_level irq_event;
+
+ r = -EFAULT;
+ if (copy_from_user(&irq_event, argp, sizeof irq_event))
+ goto out;
+ if (irqchip_in_kernel(kvm)) {
+ mutex_lock(&kvm->lock);
+ if (irq_event.irq < 16)
+ kvm_pic_set_irq(pic_irqchip(kvm),
+ irq_event.irq,
+ irq_event.level);
+ kvm_ioapic_set_irq(kvm->vioapic,
+ irq_event.irq,
+ irq_event.level);
+ mutex_unlock(&kvm->lock);
+ r = 0;
+ }
+ break;
+ }
+ case KVM_GET_IRQCHIP: {
+ /* 0: PIC master, 1: PIC slave, 2: IOAPIC */
+ struct kvm_irqchip chip;
+
+ r = -EFAULT;
+ if (copy_from_user(&chip, argp, sizeof chip))
+ goto out;
+ r = -ENXIO;
+ if (!irqchip_in_kernel(kvm))
+ goto out;
+ r = kvm_vm_ioctl_get_irqchip(kvm, &chip);
+ if (r)
+ goto out;
+ r = -EFAULT;
+ if (copy_to_user(argp, &chip, sizeof chip))
+ goto out;
+ r = 0;
+ break;
+ }
+ case KVM_SET_IRQCHIP: {
+ /* 0: PIC master, 1: PIC slave, 2: IOAPIC */
+ struct kvm_irqchip chip;
+
+ r = -EFAULT;
+ if (copy_from_user(&chip, argp, sizeof chip))
+ goto out;
+ r = -ENXIO;
+ if (!irqchip_in_kernel(kvm))
+ goto out;
+ r = kvm_vm_ioctl_set_irqchip(kvm, &chip);
+ if (r)
+ goto out;
+ r = 0;
+ break;
+ }
default:
;
}
unsigned long pgoff;
struct page *page;
- *type = VM_FAULT_MINOR;
pgoff = ((address - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;
page = gfn_to_page(kvm, pgoff);
if (!page)
return NOPAGE_SIGBUS;
get_page(page);
+ if (type != NULL)
+ *type = VM_FAULT_MINOR;
+
return page;
}
r = 0;
break;
}
- case KVM_CHECK_EXTENSION:
- /*
- * No extensions defined at present.
- */
- r = 0;
+ case KVM_CHECK_EXTENSION: {
+ int ext = (long)argp;
+
+ switch (ext) {
+ case KVM_CAP_IRQCHIP:
+ case KVM_CAP_HLT:
+ r = 1;
+ break;
+ default:
+ r = 0;
+ break;
+ }
break;
+ }
case KVM_GET_VCPU_MMAP_SIZE:
r = -EINVAL;
if (arg)
}
static struct file_operations kvm_chardev_ops = {
- .open = kvm_dev_open,
- .release = kvm_dev_release,
.unlocked_ioctl = kvm_dev_ioctl,
.compat_ioctl = kvm_dev_ioctl,
};
&kvm_chardev_ops,
};
-static int kvm_reboot(struct notifier_block *notifier, unsigned long val,
- void *v)
-{
- if (val == SYS_RESTART) {
- /*
- * Some (well, at least mine) BIOSes hang on reboot if
- * in vmx root mode.
- */
- printk(KERN_INFO "kvm: exiting hardware virtualization\n");
- on_each_cpu(hardware_disable, NULL, 0, 1);
- }
- return NOTIFY_OK;
-}
-
-static struct notifier_block kvm_reboot_notifier = {
- .notifier_call = kvm_reboot,
- .priority = 0,
-};
-
/*
* Make sure that a cpu that is being hot-unplugged does not have any vcpus
* cached on it.
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];
+ vcpu = vm->vcpus[i];
+ if (!vcpu)
+ continue;
/*
* If the vcpu is locked, then it is running on some
* other cpu and therefore it is not cached on the
return NOTIFY_OK;
}
+static int kvm_reboot(struct notifier_block *notifier, unsigned long val,
+ void *v)
+{
+ if (val == SYS_RESTART) {
+ /*
+ * Some (well, at least mine) BIOSes hang on reboot if
+ * in vmx root mode.
+ */
+ printk(KERN_INFO "kvm: exiting hardware virtualization\n");
+ on_each_cpu(hardware_disable, NULL, 0, 1);
+ }
+ return NOTIFY_OK;
+}
+
+static struct notifier_block kvm_reboot_notifier = {
+ .notifier_call = kvm_reboot,
+ .priority = 0,
+};
+
void kvm_io_bus_init(struct kvm_io_bus *bus)
{
memset(bus, 0, sizeof(*bus));
spin_lock(&kvm_lock);
list_for_each_entry(kvm, &vm_list, vm_list)
for (i = 0; i < KVM_MAX_VCPUS; ++i) {
- vcpu = &kvm->vcpus[i];
- total += *(u32 *)((void *)vcpu + offset);
+ vcpu = kvm->vcpus[i];
+ if (vcpu)
+ total += *(u32 *)((void *)vcpu + offset);
}
spin_unlock(&kvm_lock);
return total;
}
-static void stat_set(void *offset, u64 val)
-{
-}
-
-DEFINE_SIMPLE_ATTRIBUTE(stat_fops, stat_get, stat_set, "%llu\n");
+DEFINE_SIMPLE_ATTRIBUTE(stat_fops, stat_get, NULL, "%llu\n");
static __init void kvm_init_debug(void)
{
hpa_t bad_page_address;
-int kvm_init_arch(struct kvm_arch_ops *ops, struct module *module)
+static inline
+struct kvm_vcpu *preempt_notifier_to_vcpu(struct preempt_notifier *pn)
+{
+ return container_of(pn, struct kvm_vcpu, preempt_notifier);
+}
+
+static void kvm_sched_in(struct preempt_notifier *pn, int cpu)
+{
+ struct kvm_vcpu *vcpu = preempt_notifier_to_vcpu(pn);
+
+ kvm_arch_ops->vcpu_load(vcpu, cpu);
+}
+
+static void kvm_sched_out(struct preempt_notifier *pn,
+ struct task_struct *next)
+{
+ struct kvm_vcpu *vcpu = preempt_notifier_to_vcpu(pn);
+
+ kvm_arch_ops->vcpu_put(vcpu);
+}
+
+int kvm_init_arch(struct kvm_arch_ops *ops, unsigned int vcpu_size,
+ struct module *module)
{
int r;
+ int cpu;
if (kvm_arch_ops) {
printk(KERN_ERR "kvm: already loaded the other module\n");
if (r < 0)
goto out;
+ for_each_online_cpu(cpu) {
+ smp_call_function_single(cpu,
+ kvm_arch_ops->check_processor_compatibility,
+ &r, 0, 1);
+ if (r < 0)
+ goto out_free_0;
+ }
+
on_each_cpu(hardware_enable, NULL, 0, 1);
r = register_cpu_notifier(&kvm_cpu_notifier);
if (r)
if (r)
goto out_free_3;
+ /* A kmem cache lets us meet the alignment requirements of fx_save. */
+ kvm_vcpu_cache = kmem_cache_create("kvm_vcpu", vcpu_size,
+ __alignof__(struct kvm_vcpu), 0, 0);
+ if (!kvm_vcpu_cache) {
+ r = -ENOMEM;
+ goto out_free_4;
+ }
+
kvm_chardev_ops.owner = module;
r = misc_register(&kvm_dev);
goto out_free;
}
+ kvm_preempt_ops.sched_in = kvm_sched_in;
+ kvm_preempt_ops.sched_out = kvm_sched_out;
+
return r;
out_free:
+ kmem_cache_destroy(kvm_vcpu_cache);
+out_free_4:
sysdev_unregister(&kvm_sysdev);
out_free_3:
sysdev_class_unregister(&kvm_sysdev_class);
unregister_cpu_notifier(&kvm_cpu_notifier);
out_free_1:
on_each_cpu(hardware_disable, NULL, 0, 1);
+out_free_0:
kvm_arch_ops->hardware_unsetup();
out:
kvm_arch_ops = NULL;
void kvm_exit_arch(void)
{
misc_deregister(&kvm_dev);
+ kmem_cache_destroy(kvm_vcpu_cache);
sysdev_unregister(&kvm_sysdev);
sysdev_class_unregister(&kvm_sysdev_class);
unregister_reboot_notifier(&kvm_reboot_notifier);
projects / linux-2.6-omap-h63xx.git / blobdiff