*/
#include "kvm.h"
+#include "x86.h"
#include "x86_emulate.h"
#include "segment_descriptor.h"
#include "irq.h"
#include <linux/smp.h>
#include <linux/anon_inodes.h>
#include <linux/profile.h>
+#include <linux/kvm_para.h>
+#include <linux/pagemap.h>
#include <asm/processor.h>
#include <asm/msr.h>
static struct dentry *debugfs_dir;
-#define MAX_IO_MSRS 256
-
#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 \
#define EFER_RESERVED_BITS 0xfffffffffffff2fe
#ifdef CONFIG_X86_64
-// LDT or TSS descriptor in the GDT. 16 bytes.
+/* LDT or TSS descriptor in the GDT. 16 bytes. */
struct segment_descriptor_64 {
struct segment_descriptor s;
u32 base_higher;
struct descriptor_table gdt;
struct segment_descriptor *d;
unsigned long table_base;
- typedef unsigned long ul;
unsigned long v;
if (selector == 0)
return 0;
- asm ("sgdt %0" : "=m"(gdt));
+ asm("sgdt %0" : "=m"(gdt));
table_base = gdt.base;
if (selector & 4) { /* from ldt */
u16 ldt_selector;
- asm ("sldt %0" : "=g"(ldt_selector));
+ asm("sldt %0" : "=g"(ldt_selector));
table_base = segment_base(ldt_selector);
}
d = (struct segment_descriptor *)(table_base + (selector & ~7));
- v = d->base_low | ((ul)d->base_mid << 16) | ((ul)d->base_high << 24);
+ v = d->base_low | ((unsigned long)d->base_mid << 16) |
+ ((unsigned long)d->base_high << 24);
#ifdef CONFIG_X86_64
- if (d->system == 0
- && (d->type == 2 || d->type == 9 || d->type == 11))
- v |= ((ul)((struct segment_descriptor_64 *)d)->base_higher) << 32;
+ if (d->system == 0 && (d->type == 2 || d->type == 9 || d->type == 11))
+ v |= ((unsigned long) \
+ ((struct segment_descriptor_64 *)d)->base_higher) << 32;
#endif
return v;
}
/*
* Switches to specified vcpu, until a matching vcpu_put()
*/
-static void vcpu_load(struct kvm_vcpu *vcpu)
+void vcpu_load(struct kvm_vcpu *vcpu)
{
int cpu;
mutex_lock(&vcpu->mutex);
cpu = get_cpu();
preempt_notifier_register(&vcpu->preempt_notifier);
- kvm_x86_ops->vcpu_load(vcpu, cpu);
+ kvm_arch_vcpu_load(vcpu, cpu);
put_cpu();
}
-static void vcpu_put(struct kvm_vcpu *vcpu)
+void vcpu_put(struct kvm_vcpu *vcpu)
{
preempt_disable();
- kvm_x86_ops->vcpu_put(vcpu);
+ kvm_arch_vcpu_put(vcpu);
preempt_notifier_unregister(&vcpu->preempt_notifier);
preempt_enable();
mutex_unlock(&vcpu->mutex);
static void ack_flush(void *_completed)
{
- atomic_t *completed = _completed;
-
- atomic_inc(completed);
}
void kvm_flush_remote_tlbs(struct kvm *kvm)
{
- int i, cpu, needed;
+ int i, cpu;
cpumask_t cpus;
struct kvm_vcpu *vcpu;
- atomic_t completed;
- atomic_set(&completed, 0);
cpus_clear(cpus);
- needed = 0;
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))
+ if (test_and_set_bit(KVM_REQ_TLB_FLUSH, &vcpu->requests))
continue;
cpu = vcpu->cpu;
if (cpu != -1 && cpu != raw_smp_processor_id())
- if (!cpu_isset(cpu, cpus)) {
- cpu_set(cpu, cpus);
- ++needed;
- }
- }
-
- /*
- * We really want smp_call_function_mask() here. But that's not
- * available, so ipi all cpus in parallel and wait for them
- * to complete.
- */
- for (cpu = first_cpu(cpus); cpu != NR_CPUS; cpu = next_cpu(cpu, cpus))
- smp_call_function_single(cpu, ack_flush, &completed, 1, 0);
- while (atomic_read(&completed) != needed) {
- cpu_relax();
- barrier();
+ cpu_set(cpu, cpus);
}
+ smp_call_function_mask(cpus, ack_flush, NULL, 1);
}
int kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id)
if (r < 0)
goto fail_free_pio_data;
+ if (irqchip_in_kernel(kvm)) {
+ r = kvm_create_lapic(vcpu);
+ if (r < 0)
+ goto fail_mmu_destroy;
+ }
+
return 0;
+fail_mmu_destroy:
+ kvm_mmu_destroy(vcpu);
fail_free_pio_data:
free_page((unsigned long)vcpu->pio_data);
fail_free_run:
free_page((unsigned long)vcpu->run);
fail:
- return -ENOMEM;
+ return r;
}
EXPORT_SYMBOL_GPL(kvm_vcpu_init);
void kvm_vcpu_uninit(struct kvm_vcpu *vcpu)
{
+ kvm_free_lapic(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);
}
return kvm;
}
+static void kvm_free_userspace_physmem(struct kvm_memory_slot *free)
+{
+ int i;
+
+ for (i = 0; i < free->npages; ++i) {
+ if (free->phys_mem[i]) {
+ if (!PageReserved(free->phys_mem[i]))
+ SetPageDirty(free->phys_mem[i]);
+ page_cache_release(free->phys_mem[i]);
+ }
+ }
+}
+
+static void kvm_free_kernel_physmem(struct kvm_memory_slot *free)
+{
+ int i;
+
+ for (i = 0; i < free->npages; ++i)
+ if (free->phys_mem[i])
+ __free_page(free->phys_mem[i]);
+}
+
/*
* Free any memory in @free but not in @dont.
*/
static void kvm_free_physmem_slot(struct kvm_memory_slot *free,
struct kvm_memory_slot *dont)
{
- int i;
-
if (!dont || free->phys_mem != dont->phys_mem)
if (free->phys_mem) {
- for (i = 0; i < free->npages; ++i)
- if (free->phys_mem[i])
- __free_page(free->phys_mem[i]);
+ if (free->user_alloc)
+ kvm_free_userspace_physmem(free);
+ else
+ kvm_free_kernel_physmem(free);
vfree(free->phys_mem);
}
+ if (!dont || free->rmap != dont->rmap)
+ vfree(free->rmap);
if (!dont || free->dirty_bitmap != dont->dirty_bitmap)
vfree(free->dirty_bitmap);
gfn_t pdpt_gfn = cr3 >> PAGE_SHIFT;
unsigned offset = ((cr3 & (PAGE_SIZE-1)) >> 5) << 2;
int i;
- u64 *pdpt;
int ret;
- struct page *page;
u64 pdpte[ARRAY_SIZE(vcpu->pdptrs)];
mutex_lock(&vcpu->kvm->lock);
- page = gfn_to_page(vcpu->kvm, pdpt_gfn);
- if (!page) {
+ ret = kvm_read_guest_page(vcpu->kvm, pdpt_gfn, pdpte,
+ offset * sizeof(u64), sizeof(pdpte));
+ if (ret < 0) {
ret = 0;
goto out;
}
-
- pdpt = kmap_atomic(page, KM_USER0);
- memcpy(pdpte, pdpt+offset, sizeof(pdpte));
- kunmap_atomic(pdpt, KM_USER0);
-
for (i = 0; i < ARRAY_SIZE(pdpte); ++i) {
if ((pdpte[i] & 1) && (pdpte[i] & 0xfffffff0000001e6ull)) {
ret = 0;
inject_gp(vcpu);
return;
}
- } else {
- if (cr3 & CR3_NONPAE_RESERVED_BITS) {
- printk(KERN_DEBUG
- "set_cr3: #GP, reserved bits\n");
- inject_gp(vcpu);
- return;
- }
}
+ /*
+ * We don't check reserved bits in nonpae mode, because
+ * this isn't enforced, and VMware depends on this.
+ */
}
mutex_lock(&vcpu->kvm->lock);
* Discontiguous memory is allowed, mostly for framebuffers.
*/
static int kvm_vm_ioctl_set_memory_region(struct kvm *kvm,
- struct kvm_memory_region *mem)
+ struct
+ kvm_userspace_memory_region *mem,
+ int user_alloc)
{
int r;
gfn_t base_gfn;
if (!new.phys_mem)
goto out_unlock;
+ new.rmap = vmalloc(npages * sizeof(struct page *));
+
+ if (!new.rmap)
+ goto out_unlock;
+
memset(new.phys_mem, 0, npages * sizeof(struct page *));
- for (i = 0; i < npages; ++i) {
- new.phys_mem[i] = alloc_page(GFP_HIGHUSER
- | __GFP_ZERO);
- if (!new.phys_mem[i])
+ memset(new.rmap, 0, npages * sizeof(*new.rmap));
+ if (user_alloc) {
+ unsigned long pages_num;
+
+ new.user_alloc = 1;
+ down_read(¤t->mm->mmap_sem);
+
+ pages_num = get_user_pages(current, current->mm,
+ mem->userspace_addr,
+ npages, 1, 1, new.phys_mem,
+ NULL);
+
+ up_read(¤t->mm->mmap_sem);
+ if (pages_num != npages)
goto out_unlock;
- set_page_private(new.phys_mem[i],0);
+ } else {
+ for (i = 0; i < npages; ++i) {
+ new.phys_mem[i] = alloc_page(GFP_HIGHUSER
+ | __GFP_ZERO);
+ if (!new.phys_mem[i])
+ goto out_unlock;
+ }
}
}
if (mem->slot >= kvm->nmemslots)
kvm->nmemslots = mem->slot + 1;
+ if (!kvm->n_requested_mmu_pages) {
+ unsigned int n_pages;
+
+ if (npages) {
+ n_pages = npages * KVM_PERMILLE_MMU_PAGES / 1000;
+ kvm_mmu_change_mmu_pages(kvm, kvm->n_alloc_mmu_pages +
+ n_pages);
+ } else {
+ unsigned int nr_mmu_pages;
+
+ n_pages = old.npages * KVM_PERMILLE_MMU_PAGES / 1000;
+ nr_mmu_pages = kvm->n_alloc_mmu_pages - n_pages;
+ nr_mmu_pages = max(nr_mmu_pages,
+ (unsigned int) KVM_MIN_ALLOC_MMU_PAGES);
+ kvm_mmu_change_mmu_pages(kvm, nr_mmu_pages);
+ }
+ }
+
*memslot = new;
kvm_mmu_slot_remove_write_access(kvm, mem->slot);
return r;
}
+static int kvm_vm_ioctl_set_nr_mmu_pages(struct kvm *kvm,
+ u32 kvm_nr_mmu_pages)
+{
+ if (kvm_nr_mmu_pages < KVM_MIN_ALLOC_MMU_PAGES)
+ return -EINVAL;
+
+ mutex_lock(&kvm->lock);
+
+ kvm_mmu_change_mmu_pages(kvm, kvm_nr_mmu_pages);
+ kvm->n_requested_mmu_pages = kvm_nr_mmu_pages;
+
+ mutex_unlock(&kvm->lock);
+ return 0;
+}
+
+static int kvm_vm_ioctl_get_nr_mmu_pages(struct kvm *kvm)
+{
+ return kvm->n_alloc_mmu_pages;
+}
+
/*
* Get (and clear) the dirty memory log for a memory slot.
*/
r = 0;
switch (chip->chip_id) {
case KVM_IRQCHIP_PIC_MASTER:
- memcpy (&chip->chip.pic,
+ memcpy(&chip->chip.pic,
&pic_irqchip(kvm)->pics[0],
sizeof(struct kvm_pic_state));
break;
case KVM_IRQCHIP_PIC_SLAVE:
- memcpy (&chip->chip.pic,
+ memcpy(&chip->chip.pic,
&pic_irqchip(kvm)->pics[1],
sizeof(struct kvm_pic_state));
break;
case KVM_IRQCHIP_IOAPIC:
- memcpy (&chip->chip.ioapic,
+ memcpy(&chip->chip.ioapic,
ioapic_irqchip(kvm),
sizeof(struct kvm_ioapic_state));
break;
r = 0;
switch (chip->chip_id) {
case KVM_IRQCHIP_PIC_MASTER:
- memcpy (&pic_irqchip(kvm)->pics[0],
+ 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],
+ memcpy(&pic_irqchip(kvm)->pics[1],
&chip->chip.pic,
sizeof(struct kvm_pic_state));
break;
case KVM_IRQCHIP_IOAPIC:
- memcpy (ioapic_irqchip(kvm),
+ memcpy(ioapic_irqchip(kvm),
&chip->chip.ioapic,
sizeof(struct kvm_ioapic_state));
break;
return r;
}
-static gfn_t unalias_gfn(struct kvm *kvm, gfn_t gfn)
+int is_error_page(struct page *page)
+{
+ return page == bad_page;
+}
+EXPORT_SYMBOL_GPL(is_error_page);
+
+gfn_t unalias_gfn(struct kvm *kvm, gfn_t gfn)
{
int i;
struct kvm_mem_alias *alias;
gfn = unalias_gfn(kvm, gfn);
slot = __gfn_to_memslot(kvm, gfn);
if (!slot)
- return NULL;
+ return bad_page;
return slot->phys_mem[gfn - slot->base_gfn];
}
EXPORT_SYMBOL_GPL(gfn_to_page);
+static int next_segment(unsigned long len, int offset)
+{
+ if (len > PAGE_SIZE - offset)
+ return PAGE_SIZE - offset;
+ else
+ return len;
+}
+
+int kvm_read_guest_page(struct kvm *kvm, gfn_t gfn, void *data, int offset,
+ int len)
+{
+ void *page_virt;
+ struct page *page;
+
+ page = gfn_to_page(kvm, gfn);
+ if (is_error_page(page))
+ return -EFAULT;
+ page_virt = kmap_atomic(page, KM_USER0);
+
+ memcpy(data, page_virt + offset, len);
+
+ kunmap_atomic(page_virt, KM_USER0);
+ return 0;
+}
+EXPORT_SYMBOL_GPL(kvm_read_guest_page);
+
+int kvm_read_guest(struct kvm *kvm, gpa_t gpa, void *data, unsigned long len)
+{
+ gfn_t gfn = gpa >> PAGE_SHIFT;
+ int seg;
+ int offset = offset_in_page(gpa);
+ int ret;
+
+ while ((seg = next_segment(len, offset)) != 0) {
+ ret = kvm_read_guest_page(kvm, gfn, data, offset, seg);
+ if (ret < 0)
+ return ret;
+ offset = 0;
+ len -= seg;
+ data += seg;
+ ++gfn;
+ }
+ return 0;
+}
+EXPORT_SYMBOL_GPL(kvm_read_guest);
+
+int kvm_write_guest_page(struct kvm *kvm, gfn_t gfn, const void *data,
+ int offset, int len)
+{
+ void *page_virt;
+ struct page *page;
+
+ page = gfn_to_page(kvm, gfn);
+ if (is_error_page(page))
+ return -EFAULT;
+ page_virt = kmap_atomic(page, KM_USER0);
+
+ memcpy(page_virt + offset, data, len);
+
+ kunmap_atomic(page_virt, KM_USER0);
+ mark_page_dirty(kvm, gfn);
+ return 0;
+}
+EXPORT_SYMBOL_GPL(kvm_write_guest_page);
+
+int kvm_write_guest(struct kvm *kvm, gpa_t gpa, const void *data,
+ unsigned long len)
+{
+ gfn_t gfn = gpa >> PAGE_SHIFT;
+ int seg;
+ int offset = offset_in_page(gpa);
+ int ret;
+
+ while ((seg = next_segment(len, offset)) != 0) {
+ ret = kvm_write_guest_page(kvm, gfn, data, offset, seg);
+ if (ret < 0)
+ return ret;
+ offset = 0;
+ len -= seg;
+ data += seg;
+ ++gfn;
+ }
+ return 0;
+}
+
+int kvm_clear_guest_page(struct kvm *kvm, gfn_t gfn, int offset, int len)
+{
+ void *page_virt;
+ struct page *page;
+
+ page = gfn_to_page(kvm, gfn);
+ if (is_error_page(page))
+ return -EFAULT;
+ page_virt = kmap_atomic(page, KM_USER0);
+
+ memset(page_virt + offset, 0, len);
+
+ kunmap_atomic(page_virt, KM_USER0);
+ return 0;
+}
+EXPORT_SYMBOL_GPL(kvm_clear_guest_page);
+
+int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len)
+{
+ gfn_t gfn = gpa >> PAGE_SHIFT;
+ int seg;
+ int offset = offset_in_page(gpa);
+ int ret;
+
+ while ((seg = next_segment(len, offset)) != 0) {
+ ret = kvm_clear_guest_page(kvm, gfn, offset, seg);
+ if (ret < 0)
+ return ret;
+ offset = 0;
+ len -= seg;
+ ++gfn;
+ }
+ return 0;
+}
+EXPORT_SYMBOL_GPL(kvm_clear_guest);
+
/* WARNING: Does not work on aliased pages. */
void mark_page_dirty(struct kvm *kvm, gfn_t gfn)
{
gpa_t gpa = vcpu->mmu.gva_to_gpa(vcpu, addr);
unsigned offset = addr & (PAGE_SIZE-1);
unsigned tocopy = min(bytes, (unsigned)PAGE_SIZE - offset);
- unsigned long pfn;
- struct page *page;
- void *page_virt;
+ int ret;
if (gpa == UNMAPPED_GVA)
return X86EMUL_PROPAGATE_FAULT;
- pfn = gpa >> PAGE_SHIFT;
- page = gfn_to_page(vcpu->kvm, pfn);
- if (!page)
+ ret = kvm_read_guest(vcpu->kvm, gpa, data, tocopy);
+ if (ret < 0)
return X86EMUL_UNHANDLEABLE;
- page_virt = kmap_atomic(page, KM_USER0);
-
- memcpy(data, page_virt + offset, tocopy);
-
- kunmap_atomic(page_virt, KM_USER0);
bytes -= tocopy;
data += tocopy;
static int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa,
const void *val, int bytes)
{
- struct page *page;
- void *virt;
+ int ret;
- if (((gpa + bytes - 1) >> PAGE_SHIFT) != (gpa >> PAGE_SHIFT))
- return 0;
- page = gfn_to_page(vcpu->kvm, gpa >> PAGE_SHIFT);
- if (!page)
+ ret = kvm_write_guest(vcpu->kvm, gpa, val, bytes);
+ if (ret < 0)
return 0;
- mark_page_dirty(vcpu->kvm, gpa >> PAGE_SHIFT);
- virt = kmap_atomic(page, KM_USER0);
kvm_mmu_pte_write(vcpu, gpa, val, bytes);
- memcpy(virt + offset_in_page(gpa), val, bytes);
- kunmap_atomic(virt, KM_USER0);
return 1;
}
int emulate_clts(struct kvm_vcpu *vcpu)
{
- vcpu->cr0 &= ~X86_CR0_TS;
- kvm_x86_ops->set_cr0(vcpu, vcpu->cr0);
+ kvm_x86_ops->set_cr0(vcpu, vcpu->cr0 & ~X86_CR0_TS);
return X86EMUL_CONTINUE;
}
-int emulator_get_dr(struct x86_emulate_ctxt* ctxt, int dr, unsigned long *dest)
+int emulator_get_dr(struct x86_emulate_ctxt *ctxt, int dr, unsigned long *dest)
{
struct kvm_vcpu *vcpu = ctxt->vcpu;
int emulate_instruction(struct kvm_vcpu *vcpu,
struct kvm_run *run,
unsigned long cr2,
- u16 error_code)
+ u16 error_code,
+ int no_decode)
{
- struct x86_emulate_ctxt emulate_ctxt;
int r;
- int cs_db, cs_l;
vcpu->mmio_fault_cr2 = cr2;
kvm_x86_ops->cache_regs(vcpu);
- kvm_x86_ops->get_cs_db_l_bits(vcpu, &cs_db, &cs_l);
-
- emulate_ctxt.vcpu = vcpu;
- emulate_ctxt.eflags = kvm_x86_ops->get_rflags(vcpu);
- emulate_ctxt.cr2 = cr2;
- emulate_ctxt.mode = (emulate_ctxt.eflags & X86_EFLAGS_VM)
- ? X86EMUL_MODE_REAL : cs_l
- ? X86EMUL_MODE_PROT64 : cs_db
- ? X86EMUL_MODE_PROT32 : X86EMUL_MODE_PROT16;
-
- if (emulate_ctxt.mode == X86EMUL_MODE_PROT64) {
- emulate_ctxt.cs_base = 0;
- emulate_ctxt.ds_base = 0;
- emulate_ctxt.es_base = 0;
- emulate_ctxt.ss_base = 0;
- } else {
- emulate_ctxt.cs_base = get_segment_base(vcpu, VCPU_SREG_CS);
- emulate_ctxt.ds_base = get_segment_base(vcpu, VCPU_SREG_DS);
- emulate_ctxt.es_base = get_segment_base(vcpu, VCPU_SREG_ES);
- emulate_ctxt.ss_base = get_segment_base(vcpu, VCPU_SREG_SS);
+ vcpu->mmio_is_write = 0;
+ vcpu->pio.string = 0;
+
+ if (!no_decode) {
+ int cs_db, cs_l;
+ kvm_x86_ops->get_cs_db_l_bits(vcpu, &cs_db, &cs_l);
+
+ vcpu->emulate_ctxt.vcpu = vcpu;
+ vcpu->emulate_ctxt.eflags = kvm_x86_ops->get_rflags(vcpu);
+ vcpu->emulate_ctxt.cr2 = cr2;
+ vcpu->emulate_ctxt.mode =
+ (vcpu->emulate_ctxt.eflags & X86_EFLAGS_VM)
+ ? X86EMUL_MODE_REAL : cs_l
+ ? X86EMUL_MODE_PROT64 : cs_db
+ ? X86EMUL_MODE_PROT32 : X86EMUL_MODE_PROT16;
+
+ if (vcpu->emulate_ctxt.mode == X86EMUL_MODE_PROT64) {
+ vcpu->emulate_ctxt.cs_base = 0;
+ vcpu->emulate_ctxt.ds_base = 0;
+ vcpu->emulate_ctxt.es_base = 0;
+ vcpu->emulate_ctxt.ss_base = 0;
+ } else {
+ vcpu->emulate_ctxt.cs_base =
+ get_segment_base(vcpu, VCPU_SREG_CS);
+ vcpu->emulate_ctxt.ds_base =
+ get_segment_base(vcpu, VCPU_SREG_DS);
+ vcpu->emulate_ctxt.es_base =
+ get_segment_base(vcpu, VCPU_SREG_ES);
+ vcpu->emulate_ctxt.ss_base =
+ get_segment_base(vcpu, VCPU_SREG_SS);
+ }
+
+ vcpu->emulate_ctxt.gs_base =
+ get_segment_base(vcpu, VCPU_SREG_GS);
+ vcpu->emulate_ctxt.fs_base =
+ get_segment_base(vcpu, VCPU_SREG_FS);
+
+ r = x86_decode_insn(&vcpu->emulate_ctxt, &emulate_ops);
+ if (r) {
+ if (kvm_mmu_unprotect_page_virt(vcpu, cr2))
+ return EMULATE_DONE;
+ return EMULATE_FAIL;
+ }
}
- emulate_ctxt.gs_base = get_segment_base(vcpu, VCPU_SREG_GS);
- emulate_ctxt.fs_base = get_segment_base(vcpu, VCPU_SREG_FS);
+ r = x86_emulate_insn(&vcpu->emulate_ctxt, &emulate_ops);
- 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;
}
kvm_x86_ops->decache_regs(vcpu);
- kvm_x86_ops->set_rflags(vcpu, emulate_ctxt.eflags);
+ kvm_x86_ops->set_rflags(vcpu, vcpu->emulate_ctxt.eflags);
if (vcpu->mmio_is_write) {
vcpu->mmio_needed = 0;
}
EXPORT_SYMBOL_GPL(kvm_emulate_halt);
-int kvm_hypercall(struct kvm_vcpu *vcpu, struct kvm_run *run)
+int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
{
- unsigned long nr, a0, a1, a2, a3, a4, a5, ret;
+ unsigned long nr, a0, a1, a2, a3, ret;
kvm_x86_ops->cache_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;
+
+ nr = vcpu->regs[VCPU_REGS_RAX];
+ a0 = vcpu->regs[VCPU_REGS_RBX];
+ a1 = vcpu->regs[VCPU_REGS_RCX];
+ a2 = vcpu->regs[VCPU_REGS_RDX];
+ a3 = vcpu->regs[VCPU_REGS_RSI];
+
+ if (!is_long_mode(vcpu)) {
+ nr &= 0xFFFFFFFF;
+ a0 &= 0xFFFFFFFF;
+ a1 &= 0xFFFFFFFF;
+ a2 &= 0xFFFFFFFF;
+ a3 &= 0xFFFFFFFF;
}
+
switch (nr) {
default:
- run->hypercall.nr = nr;
- run->hypercall.args[0] = a0;
- run->hypercall.args[1] = a1;
- run->hypercall.args[2] = a2;
- run->hypercall.args[3] = a3;
- run->hypercall.args[4] = a4;
- run->hypercall.args[5] = a5;
- run->hypercall.ret = ret;
- run->hypercall.longmode = is_long_mode(vcpu);
- kvm_x86_ops->decache_regs(vcpu);
- return 0;
+ ret = -KVM_ENOSYS;
+ break;
}
vcpu->regs[VCPU_REGS_RAX] = ret;
kvm_x86_ops->decache_regs(vcpu);
- return 1;
+ return 0;
+}
+EXPORT_SYMBOL_GPL(kvm_emulate_hypercall);
+
+int kvm_fix_hypercall(struct kvm_vcpu *vcpu)
+{
+ char instruction[3];
+ int ret = 0;
+
+ mutex_lock(&vcpu->kvm->lock);
+
+ /*
+ * Blow out the MMU to ensure that no other VCPU has an active mapping
+ * to ensure that the updated hypercall appears atomically across all
+ * VCPUs.
+ */
+ kvm_mmu_zap_all(vcpu->kvm);
+
+ kvm_x86_ops->cache_regs(vcpu);
+ kvm_x86_ops->patch_hypercall(vcpu, instruction);
+ if (emulator_write_emulated(vcpu->rip, instruction, 3, vcpu)
+ != X86EMUL_CONTINUE)
+ ret = -EFAULT;
+
+ mutex_unlock(&vcpu->kvm->lock);
+
+ return ret;
}
-EXPORT_SYMBOL_GPL(kvm_hypercall);
static u64 mk_cr_64(u64 curr_cr, u32 new_val)
{
}
}
-/*
- * 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;
-
- mark_page_dirty(vcpu->kvm, para_state_gpa >> PAGE_SHIFT);
- para_state_page = pfn_to_page(para_state_hpa >> PAGE_SHIFT);
- 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->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;
-
- mark_page_dirty(vcpu->kvm, hypercall_gpa >> PAGE_SHIFT);
- hypercall = kmap_atomic(pfn_to_page(hypercall_hpa >> PAGE_SHIFT),
- KM_USER1) + (hypercall_hpa & ~PAGE_MASK);
- kvm_x86_ops->patch_hypercall(vcpu, hypercall);
- kunmap_atomic(hypercall, KM_USER1);
-
- para_state->ret = 0;
-err_kunmap_skip:
- kunmap(para_state_page);
- return 0;
-err_gp:
- return 1;
-}
-
int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
{
u64 data;
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:
pr_unimpl(vcpu, "unhandled wrmsr: 0x%x\n", msr);
return 1;
mutex_unlock(&vcpu->kvm->lock);
}
-int kvm_emulate_pio (struct kvm_vcpu *vcpu, struct kvm_run *run, int in,
+int kvm_emulate_pio(struct kvm_vcpu *vcpu, struct kvm_run *run, int in,
int size, unsigned port)
{
struct kvm_io_device *pio_dev;
int r;
if (unlikely(vcpu->mp_state == VCPU_MP_STATE_SIPI_RECEIVED)) {
- printk("vcpu %d received sipi with vector # %x\n",
+ pr_debug("vcpu %d received sipi with vector # %x\n",
vcpu->vcpu_id, vcpu->sipi_vector);
kvm_lapic_reset(vcpu);
kvm_x86_ops->vcpu_reset(vcpu);
if (unlikely(r))
goto out;
+ kvm_inject_pending_timer_irqs(vcpu);
+
preempt_disable();
kvm_x86_ops->prepare_guest_switch(vcpu);
kvm_x86_ops->inject_pending_vectors(vcpu, kvm_run);
vcpu->guest_mode = 1;
+ kvm_guest_enter();
if (vcpu->requests)
- if (test_and_clear_bit(KVM_TLB_FLUSH, &vcpu->requests))
+ if (test_and_clear_bit(KVM_REQ_TLB_FLUSH, &vcpu->requests))
kvm_x86_ops->tlb_flush(vcpu);
kvm_x86_ops->run(vcpu, kvm_run);
++vcpu->stat.exits;
+ /*
+ * We must have an instruction between local_irq_enable() and
+ * kvm_guest_exit(), so the timer interrupt isn't delayed by
+ * the interrupt shadow. The stat.exits increment will do nicely.
+ * But we need to prevent reordering, hence this barrier():
+ */
+ barrier();
+
+ kvm_guest_exit();
+
preempt_enable();
/*
vcpu->mmio_read_completed = 1;
vcpu->mmio_needed = 0;
r = emulate_instruction(vcpu, kvm_run,
- vcpu->mmio_fault_cr2, 0);
+ vcpu->mmio_fault_cr2, 0, 1);
if (r == EMULATE_DO_MMIO) {
/*
* Read-modify-write. Back to userspace.
sizeof sregs->interrupt_bitmap);
pending_vec = kvm_x86_ops->get_irq(vcpu);
if (pending_vec >= 0)
- set_bit(pending_vec, (unsigned long *)sregs->interrupt_bitmap);
+ set_bit(pending_vec,
+ (unsigned long *)sregs->interrupt_bitmap);
} else
memcpy(sregs->interrupt_bitmap, vcpu->irq_pending,
sizeof sregs->interrupt_bitmap);
/* Only pending external irq is handled here */
if (pending_vec < max_bits) {
kvm_x86_ops->set_irq(vcpu, pending_vec);
- printk("Set back pending irq %d\n", pending_vec);
+ pr_debug("Set back pending irq %d\n",
+ pending_vec);
}
}
}
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.
- *
- * This list is modified at module load time to reflect the
- * capabilities of the host cpu.
- */
-static u32 msrs_to_save[] = {
- MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP,
- MSR_K6_STAR,
-#ifdef CONFIG_X86_64
- MSR_CSTAR, MSR_KERNEL_GS_BASE, MSR_SYSCALL_MASK, MSR_LSTAR,
-#endif
- MSR_IA32_TIME_STAMP_COUNTER,
-};
-
-static unsigned num_msrs_to_save;
-
-static u32 emulated_msrs[] = {
- MSR_IA32_MISC_ENABLE,
-};
-
-static __init void kvm_init_msr_list(void)
-{
- u32 dummy[2];
- unsigned i, j;
-
- for (i = j = 0; i < ARRAY_SIZE(msrs_to_save); i++) {
- if (rdmsr_safe(msrs_to_save[i], &dummy[0], &dummy[1]) < 0)
- continue;
- if (j < i)
- msrs_to_save[j] = msrs_to_save[i];
- j++;
- }
- num_msrs_to_save = j;
-}
-
-/*
- * Adapt set_msr() to msr_io()'s calling convention
- */
-static int do_set_msr(struct kvm_vcpu *vcpu, unsigned index, u64 *data)
-{
- return kvm_set_msr(vcpu, index, *data);
-}
-
-/*
- * Read or write a bunch of msrs. All parameters are kernel addresses.
- *
- * @return number of msrs set successfully.
- */
-static int __msr_io(struct kvm_vcpu *vcpu, struct kvm_msrs *msrs,
- struct kvm_msr_entry *entries,
- int (*do_msr)(struct kvm_vcpu *vcpu,
- unsigned index, u64 *data))
-{
- int i;
-
- vcpu_load(vcpu);
-
- for (i = 0; i < msrs->nmsrs; ++i)
- if (do_msr(vcpu, entries[i].index, &entries[i].data))
- break;
-
- vcpu_put(vcpu);
-
- return i;
-}
-
-/*
- * Read or write a bunch of msrs. Parameters are user addresses.
- *
- * @return number of msrs set successfully.
- */
-static int msr_io(struct kvm_vcpu *vcpu, struct kvm_msrs __user *user_msrs,
- int (*do_msr)(struct kvm_vcpu *vcpu,
- unsigned index, u64 *data),
- int writeback)
-{
- struct kvm_msrs msrs;
- struct kvm_msr_entry *entries;
- int r, n;
- unsigned size;
-
- r = -EFAULT;
- if (copy_from_user(&msrs, user_msrs, sizeof msrs))
- goto out;
-
- r = -E2BIG;
- if (msrs.nmsrs >= MAX_IO_MSRS)
- goto out;
-
- r = -ENOMEM;
- size = sizeof(struct kvm_msr_entry) * msrs.nmsrs;
- entries = vmalloc(size);
- if (!entries)
- goto out;
-
- r = -EFAULT;
- if (copy_from_user(entries, user_msrs->entries, size))
- goto out_free;
-
- r = n = __msr_io(vcpu, &msrs, entries, do_msr);
- if (r < 0)
- goto out_free;
-
- r = -EFAULT;
- if (writeback && copy_to_user(user_msrs->entries, entries, size))
- goto out_free;
-
- r = n;
-
-out_free:
- vfree(entries);
-out:
- return r;
-}
-
/*
* Translate a guest virtual address to a guest physical address.
*/
return r;
}
-static void cpuid_fix_nx_cap(struct kvm_vcpu *vcpu)
-{
- u64 efer;
- int i;
- struct kvm_cpuid_entry *e, *entry;
-
- rdmsrl(MSR_EFER, efer);
- entry = NULL;
- for (i = 0; i < vcpu->cpuid_nent; ++i) {
- e = &vcpu->cpuid_entries[i];
- if (e->function == 0x80000001) {
- entry = e;
- break;
- }
- }
- if (entry && (entry->edx & (1 << 20)) && !(efer & EFER_NX)) {
- entry->edx &= ~(1 << 20);
- printk(KERN_INFO "kvm: guest NX capability removed\n");
- }
-}
-
-static int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu,
- struct kvm_cpuid *cpuid,
- struct kvm_cpuid_entry __user *entries)
-{
- int r;
-
- r = -E2BIG;
- if (cpuid->nent > KVM_MAX_CPUID_ENTRIES)
- goto out;
- r = -EFAULT;
- if (copy_from_user(&vcpu->cpuid_entries, entries,
- cpuid->nent * sizeof(struct kvm_cpuid_entry)))
- goto out;
- vcpu->cpuid_nent = cpuid->nent;
- cpuid_fix_nx_cap(vcpu);
- return 0;
-
-out:
- return r;
-}
-
static int kvm_vcpu_ioctl_set_sigmask(struct kvm_vcpu *vcpu, sigset_t *sigset)
{
if (sigset) {
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)
{
struct kvm_vcpu *vcpu = filp->private_data;
void __user *argp = (void __user *)arg;
- int r = -EINVAL;
+ int r;
switch (ioctl) {
case KVM_RUN:
r = 0;
break;
}
- case KVM_GET_MSRS:
- r = msr_io(vcpu, argp, kvm_get_msr, 1);
- break;
- case KVM_SET_MSRS:
- r = msr_io(vcpu, argp, do_set_msr, 0);
- break;
- case KVM_SET_CPUID: {
- struct kvm_cpuid __user *cpuid_arg = argp;
- struct kvm_cpuid cpuid;
-
- r = -EFAULT;
- if (copy_from_user(&cpuid, cpuid_arg, sizeof cpuid))
- goto out;
- r = kvm_vcpu_ioctl_set_cpuid(vcpu, &cpuid, cpuid_arg->entries);
- if (r)
- goto out;
- break;
- }
case KVM_SET_SIGNAL_MASK: {
struct kvm_signal_mask __user *sigmask_arg = argp;
struct kvm_signal_mask kvm_sigmask;
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:
- ;
+ r = kvm_arch_vcpu_ioctl(filp, ioctl, arg);
}
out:
return r;
break;
case KVM_SET_MEMORY_REGION: {
struct kvm_memory_region kvm_mem;
+ struct kvm_userspace_memory_region kvm_userspace_mem;
r = -EFAULT;
if (copy_from_user(&kvm_mem, argp, sizeof kvm_mem))
goto out;
- r = kvm_vm_ioctl_set_memory_region(kvm, &kvm_mem);
+ kvm_userspace_mem.slot = kvm_mem.slot;
+ kvm_userspace_mem.flags = kvm_mem.flags;
+ kvm_userspace_mem.guest_phys_addr = kvm_mem.guest_phys_addr;
+ kvm_userspace_mem.memory_size = kvm_mem.memory_size;
+ r = kvm_vm_ioctl_set_memory_region(kvm, &kvm_userspace_mem, 0);
+ if (r)
+ goto out;
+ break;
+ }
+ case KVM_SET_USER_MEMORY_REGION: {
+ struct kvm_userspace_memory_region kvm_userspace_mem;
+
+ r = -EFAULT;
+ if (copy_from_user(&kvm_userspace_mem, argp,
+ sizeof kvm_userspace_mem))
+ goto out;
+
+ r = kvm_vm_ioctl_set_memory_region(kvm, &kvm_userspace_mem, 1);
if (r)
goto out;
break;
}
+ case KVM_SET_NR_MMU_PAGES:
+ r = kvm_vm_ioctl_set_nr_mmu_pages(kvm, arg);
+ if (r)
+ goto out;
+ break;
+ case KVM_GET_NR_MMU_PAGES:
+ r = kvm_vm_ioctl_get_nr_mmu_pages(kvm);
+ break;
case KVM_GET_DIRTY_LOG: {
struct kvm_dirty_log log;
kvm->vpic = NULL;
goto out;
}
- }
- else
+ } else
goto out;
break;
case KVM_IRQ_LINE: {
pgoff = ((address - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;
page = gfn_to_page(kvm, pgoff);
- if (!page)
+ if (is_error_page(page))
return NOPAGE_SIGBUS;
get_page(page);
if (type != NULL)
goto out;
r = kvm_dev_ioctl_create_vm();
break;
- case KVM_GET_MSR_INDEX_LIST: {
- struct kvm_msr_list __user *user_msr_list = argp;
- struct kvm_msr_list msr_list;
- unsigned n;
-
- r = -EFAULT;
- if (copy_from_user(&msr_list, user_msr_list, sizeof msr_list))
- goto out;
- n = msr_list.nmsrs;
- msr_list.nmsrs = num_msrs_to_save + ARRAY_SIZE(emulated_msrs);
- if (copy_to_user(user_msr_list, &msr_list, sizeof msr_list))
- goto out;
- r = -E2BIG;
- if (n < num_msrs_to_save)
- goto out;
- r = -EFAULT;
- if (copy_to_user(user_msr_list->indices, &msrs_to_save,
- num_msrs_to_save * sizeof(u32)))
- goto out;
- if (copy_to_user(user_msr_list->indices
- + num_msrs_to_save * sizeof(u32),
- &emulated_msrs,
- ARRAY_SIZE(emulated_msrs) * sizeof(u32)))
- goto out;
- r = 0;
- break;
- }
case KVM_CHECK_EXTENSION: {
int ext = (long)argp;
switch (ext) {
case KVM_CAP_IRQCHIP:
case KVM_CAP_HLT:
+ case KVM_CAP_MMU_SHADOW_CACHE_CONTROL:
+ case KVM_CAP_USER_MEMORY:
r = 1;
break;
default:
r = 2 * PAGE_SIZE;
break;
default:
- ;
+ return kvm_arch_dev_ioctl(filp, ioctl, arg);
}
out:
return r;
}
static int kvm_reboot(struct notifier_block *notifier, unsigned long val,
- void *v)
+ void *v)
{
if (val == SYS_RESTART) {
/*
}
static struct sysdev_class kvm_sysdev_class = {
- set_kset_name("kvm"),
+ .name = "kvm",
.suspend = kvm_suspend,
.resume = kvm_resume,
};
.cls = &kvm_sysdev_class,
};
-hpa_t bad_page_address;
+struct page *bad_page;
static inline
struct kvm_vcpu *preempt_notifier_to_vcpu(struct preempt_notifier *pn)
r = misc_register(&kvm_dev);
if (r) {
- printk (KERN_ERR "kvm: misc device register failed\n");
+ printk(KERN_ERR "kvm: misc device register failed\n");
goto out_free;
}
kvm_preempt_ops.sched_in = kvm_sched_in;
kvm_preempt_ops.sched_out = kvm_sched_out;
- return r;
+ kvm_mmu_set_nonpresent_ptes(0ull, 0ull);
+
+ return 0;
out_free:
kmem_cache_destroy(kvm_vcpu_cache);
kvm_x86_ops = NULL;
return r;
}
+EXPORT_SYMBOL_GPL(kvm_init_x86);
void kvm_exit_x86(void)
{
kvm_x86_ops->hardware_unsetup();
kvm_x86_ops = NULL;
}
+EXPORT_SYMBOL_GPL(kvm_exit_x86);
static __init int kvm_init(void)
{
- static struct page *bad_page;
int r;
r = kvm_mmu_module_init();
kvm_init_debug();
- kvm_init_msr_list();
+ kvm_arch_init();
- if ((bad_page = alloc_page(GFP_KERNEL)) == NULL) {
+ bad_page = alloc_page(GFP_KERNEL | __GFP_ZERO);
+
+ if (bad_page == NULL) {
r = -ENOMEM;
goto out;
}
- bad_page_address = page_to_pfn(bad_page) << PAGE_SHIFT;
- memset(__va(bad_page_address), 0, PAGE_SIZE);
-
return 0;
out:
static __exit void kvm_exit(void)
{
kvm_exit_debug();
- __free_page(pfn_to_page(bad_page_address >> PAGE_SHIFT));
+ __free_page(bad_page);
kvm_mmu_module_exit();
}
module_init(kvm_init)
module_exit(kvm_exit)
-
-EXPORT_SYMBOL_GPL(kvm_init_x86);
-EXPORT_SYMBOL_GPL(kvm_exit_x86);