#include <linux/smp.h>
#include <linux/anon_inodes.h>
#include <linux/profile.h>
+#include <linux/kvm_para.h>
#include <asm/processor.h>
#include <asm/msr.h>
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);
}
__free_page(free->phys_mem[i]);
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);
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 *));
+ memset(new.rmap, 0, npages * sizeof(*new.rmap));
for (i = 0; i < npages; ++i) {
new.phys_mem[i] = alloc_page(GFP_HIGHUSER
| __GFP_ZERO);
if (!new.phys_mem[i])
goto out_unlock;
- set_page_private(new.phys_mem[i],0);
}
}
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.
*/
return r;
}
-static gfn_t unalias_gfn(struct kvm *kvm, gfn_t gfn)
+gfn_t unalias_gfn(struct kvm *kvm, gfn_t gfn)
{
int i;
struct kvm_mem_alias *alias;
}
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 (!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 (!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 (!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))
+ ret = kvm_write_guest(vcpu->kvm, gpa, val, bytes);
+ if (ret < 0)
return 0;
- page = gfn_to_page(vcpu->kvm, gpa >> PAGE_SHIFT);
- if (!page)
- 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_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;
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.
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;
switch (ext) {
case KVM_CAP_IRQCHIP:
case KVM_CAP_HLT:
+ case KVM_CAP_MMU_SHADOW_CACHE_CONTROL:
r = 1;
break;
default:
}
static struct sysdev_class kvm_sysdev_class = {
- set_kset_name("kvm"),
+ .name = "kvm",
.suspend = kvm_suspend,
.resume = kvm_resume,
};
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);