#include "x86_emulate.h"
#include "segment_descriptor.h"
#include "irq.h"
+#include "mmu.h"
#include <linux/kvm.h>
#include <linux/fs.h>
#include <linux/vmalloc.h>
#include <linux/module.h>
+#include <linux/mman.h>
+#include <linux/highmem.h>
#include <asm/uaccess.h>
#include <asm/msr.h>
{ "mmu_pde_zapped", VM_STAT(mmu_pde_zapped) },
{ "mmu_flooded", VM_STAT(mmu_flooded) },
{ "mmu_recycled", VM_STAT(mmu_recycled) },
+ { "remote_tlb_flush", VM_STAT(remote_tlb_flush) },
{ NULL }
};
u64 kvm_get_apic_base(struct kvm_vcpu *vcpu)
{
if (irqchip_in_kernel(vcpu->kvm))
- return vcpu->apic_base;
+ return vcpu->arch.apic_base;
else
- return vcpu->apic_base;
+ return vcpu->arch.apic_base;
}
EXPORT_SYMBOL_GPL(kvm_get_apic_base);
if (irqchip_in_kernel(vcpu->kvm))
kvm_lapic_set_base(vcpu, data);
else
- vcpu->apic_base = data;
+ vcpu->arch.apic_base = data;
}
EXPORT_SYMBOL_GPL(kvm_set_apic_base);
-static void inject_gp(struct kvm_vcpu *vcpu)
+void kvm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr)
{
- kvm_x86_ops->inject_gp(vcpu, 0);
+ WARN_ON(vcpu->arch.exception.pending);
+ vcpu->arch.exception.pending = true;
+ vcpu->arch.exception.has_error_code = false;
+ vcpu->arch.exception.nr = nr;
+}
+EXPORT_SYMBOL_GPL(kvm_queue_exception);
+
+void kvm_inject_page_fault(struct kvm_vcpu *vcpu, unsigned long addr,
+ u32 error_code)
+{
+ ++vcpu->stat.pf_guest;
+ if (vcpu->arch.exception.pending && vcpu->arch.exception.nr == PF_VECTOR) {
+ printk(KERN_DEBUG "kvm: inject_page_fault:"
+ " double fault 0x%lx\n", addr);
+ vcpu->arch.exception.nr = DF_VECTOR;
+ vcpu->arch.exception.error_code = 0;
+ return;
+ }
+ vcpu->arch.cr2 = addr;
+ kvm_queue_exception_e(vcpu, PF_VECTOR, error_code);
+}
+
+void kvm_queue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code)
+{
+ WARN_ON(vcpu->arch.exception.pending);
+ vcpu->arch.exception.pending = true;
+ vcpu->arch.exception.has_error_code = true;
+ vcpu->arch.exception.nr = nr;
+ vcpu->arch.exception.error_code = error_code;
+}
+EXPORT_SYMBOL_GPL(kvm_queue_exception_e);
+
+static void __queue_exception(struct kvm_vcpu *vcpu)
+{
+ kvm_x86_ops->queue_exception(vcpu, vcpu->arch.exception.nr,
+ vcpu->arch.exception.has_error_code,
+ vcpu->arch.exception.error_code);
}
/*
unsigned offset = ((cr3 & (PAGE_SIZE-1)) >> 5) << 2;
int i;
int ret;
- u64 pdpte[ARRAY_SIZE(vcpu->pdptrs)];
+ u64 pdpte[ARRAY_SIZE(vcpu->arch.pdptrs)];
mutex_lock(&vcpu->kvm->lock);
ret = kvm_read_guest_page(vcpu->kvm, pdpt_gfn, pdpte,
}
ret = 1;
- memcpy(vcpu->pdptrs, pdpte, sizeof(vcpu->pdptrs));
+ memcpy(vcpu->arch.pdptrs, pdpte, sizeof(vcpu->arch.pdptrs));
out:
mutex_unlock(&vcpu->kvm->lock);
return ret;
}
+static bool pdptrs_changed(struct kvm_vcpu *vcpu)
+{
+ u64 pdpte[ARRAY_SIZE(vcpu->arch.pdptrs)];
+ bool changed = true;
+ int r;
+
+ if (is_long_mode(vcpu) || !is_pae(vcpu))
+ return false;
+
+ mutex_lock(&vcpu->kvm->lock);
+ r = kvm_read_guest(vcpu->kvm, vcpu->arch.cr3 & ~31u, pdpte, sizeof(pdpte));
+ if (r < 0)
+ goto out;
+ changed = memcmp(pdpte, vcpu->arch.pdptrs, sizeof(pdpte)) != 0;
+out:
+ mutex_unlock(&vcpu->kvm->lock);
+
+ return changed;
+}
+
void set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
{
if (cr0 & CR0_RESERVED_BITS) {
printk(KERN_DEBUG "set_cr0: 0x%lx #GP, reserved bits 0x%lx\n",
- cr0, vcpu->cr0);
- inject_gp(vcpu);
+ cr0, vcpu->arch.cr0);
+ kvm_inject_gp(vcpu, 0);
return;
}
if ((cr0 & X86_CR0_NW) && !(cr0 & X86_CR0_CD)) {
printk(KERN_DEBUG "set_cr0: #GP, CD == 0 && NW == 1\n");
- inject_gp(vcpu);
+ kvm_inject_gp(vcpu, 0);
return;
}
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);
+ kvm_inject_gp(vcpu, 0);
return;
}
if (!is_paging(vcpu) && (cr0 & X86_CR0_PG)) {
#ifdef CONFIG_X86_64
- if ((vcpu->shadow_efer & EFER_LME)) {
+ if ((vcpu->arch.shadow_efer & EFER_LME)) {
int cs_db, cs_l;
if (!is_pae(vcpu)) {
printk(KERN_DEBUG "set_cr0: #GP, start paging "
"in long mode while PAE is disabled\n");
- inject_gp(vcpu);
+ kvm_inject_gp(vcpu, 0);
return;
}
kvm_x86_ops->get_cs_db_l_bits(vcpu, &cs_db, &cs_l);
if (cs_l) {
printk(KERN_DEBUG "set_cr0: #GP, start paging "
"in long mode while CS.L == 1\n");
- inject_gp(vcpu);
+ kvm_inject_gp(vcpu, 0);
return;
}
} else
#endif
- if (is_pae(vcpu) && !load_pdptrs(vcpu, vcpu->cr3)) {
+ if (is_pae(vcpu) && !load_pdptrs(vcpu, vcpu->arch.cr3)) {
printk(KERN_DEBUG "set_cr0: #GP, pdptrs "
"reserved bits\n");
- inject_gp(vcpu);
+ kvm_inject_gp(vcpu, 0);
return;
}
}
kvm_x86_ops->set_cr0(vcpu, cr0);
- vcpu->cr0 = cr0;
+ vcpu->arch.cr0 = cr0;
mutex_lock(&vcpu->kvm->lock);
kvm_mmu_reset_context(vcpu);
void lmsw(struct kvm_vcpu *vcpu, unsigned long msw)
{
- set_cr0(vcpu, (vcpu->cr0 & ~0x0ful) | (msw & 0x0f));
+ set_cr0(vcpu, (vcpu->arch.cr0 & ~0x0ful) | (msw & 0x0f));
}
EXPORT_SYMBOL_GPL(lmsw);
{
if (cr4 & CR4_RESERVED_BITS) {
printk(KERN_DEBUG "set_cr4: #GP, reserved bits\n");
- inject_gp(vcpu);
+ kvm_inject_gp(vcpu, 0);
return;
}
if (!(cr4 & X86_CR4_PAE)) {
printk(KERN_DEBUG "set_cr4: #GP, clearing PAE while "
"in long mode\n");
- inject_gp(vcpu);
+ kvm_inject_gp(vcpu, 0);
return;
}
} else if (is_paging(vcpu) && !is_pae(vcpu) && (cr4 & X86_CR4_PAE)
- && !load_pdptrs(vcpu, vcpu->cr3)) {
+ && !load_pdptrs(vcpu, vcpu->arch.cr3)) {
printk(KERN_DEBUG "set_cr4: #GP, pdptrs reserved bits\n");
- inject_gp(vcpu);
+ kvm_inject_gp(vcpu, 0);
return;
}
if (cr4 & X86_CR4_VMXE) {
printk(KERN_DEBUG "set_cr4: #GP, setting VMXE\n");
- inject_gp(vcpu);
+ kvm_inject_gp(vcpu, 0);
return;
}
kvm_x86_ops->set_cr4(vcpu, cr4);
- vcpu->cr4 = cr4;
+ vcpu->arch.cr4 = cr4;
mutex_lock(&vcpu->kvm->lock);
kvm_mmu_reset_context(vcpu);
mutex_unlock(&vcpu->kvm->lock);
void set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
{
+ if (cr3 == vcpu->arch.cr3 && !pdptrs_changed(vcpu)) {
+ kvm_mmu_flush_tlb(vcpu);
+ return;
+ }
+
if (is_long_mode(vcpu)) {
if (cr3 & CR3_L_MODE_RESERVED_BITS) {
printk(KERN_DEBUG "set_cr3: #GP, reserved bits\n");
- inject_gp(vcpu);
+ kvm_inject_gp(vcpu, 0);
return;
}
} else {
if (cr3 & CR3_PAE_RESERVED_BITS) {
printk(KERN_DEBUG
"set_cr3: #GP, reserved bits\n");
- inject_gp(vcpu);
+ kvm_inject_gp(vcpu, 0);
return;
}
if (is_paging(vcpu) && !load_pdptrs(vcpu, cr3)) {
printk(KERN_DEBUG "set_cr3: #GP, pdptrs "
"reserved bits\n");
- inject_gp(vcpu);
+ kvm_inject_gp(vcpu, 0);
return;
}
}
* to debug) behavior on the guest side.
*/
if (unlikely(!gfn_to_memslot(vcpu->kvm, cr3 >> PAGE_SHIFT)))
- inject_gp(vcpu);
+ kvm_inject_gp(vcpu, 0);
else {
- vcpu->cr3 = cr3;
- vcpu->mmu.new_cr3(vcpu);
+ vcpu->arch.cr3 = cr3;
+ vcpu->arch.mmu.new_cr3(vcpu);
}
mutex_unlock(&vcpu->kvm->lock);
}
{
if (cr8 & CR8_RESERVED_BITS) {
printk(KERN_DEBUG "set_cr8: #GP, reserved bits 0x%lx\n", cr8);
- inject_gp(vcpu);
+ kvm_inject_gp(vcpu, 0);
return;
}
if (irqchip_in_kernel(vcpu->kvm))
kvm_lapic_set_tpr(vcpu, cr8);
else
- vcpu->cr8 = cr8;
+ vcpu->arch.cr8 = cr8;
}
EXPORT_SYMBOL_GPL(set_cr8);
if (irqchip_in_kernel(vcpu->kvm))
return kvm_lapic_get_cr8(vcpu);
else
- return vcpu->cr8;
+ return vcpu->arch.cr8;
}
EXPORT_SYMBOL_GPL(get_cr8);
if (efer & EFER_RESERVED_BITS) {
printk(KERN_DEBUG "set_efer: 0x%llx #GP, reserved bits\n",
efer);
- inject_gp(vcpu);
+ kvm_inject_gp(vcpu, 0);
return;
}
if (is_paging(vcpu)
- && (vcpu->shadow_efer & EFER_LME) != (efer & EFER_LME)) {
+ && (vcpu->arch.shadow_efer & EFER_LME) != (efer & EFER_LME)) {
printk(KERN_DEBUG "set_efer: #GP, change LME while paging\n");
- inject_gp(vcpu);
+ kvm_inject_gp(vcpu, 0);
return;
}
kvm_x86_ops->set_efer(vcpu, efer);
efer &= ~EFER_LMA;
- efer |= vcpu->shadow_efer & EFER_LMA;
+ efer |= vcpu->arch.shadow_efer & EFER_LMA;
- vcpu->shadow_efer = efer;
+ vcpu->arch.shadow_efer = efer;
}
#endif
kvm_set_apic_base(vcpu, data);
break;
case MSR_IA32_MISC_ENABLE:
- vcpu->ia32_misc_enable_msr = data;
+ vcpu->arch.ia32_misc_enable_msr = data;
break;
default:
pr_unimpl(vcpu, "unhandled wrmsr: 0x%x\n", msr);
data = kvm_get_apic_base(vcpu);
break;
case MSR_IA32_MISC_ENABLE:
- data = vcpu->ia32_misc_enable_msr;
+ data = vcpu->arch.ia32_misc_enable_msr;
break;
#ifdef CONFIG_X86_64
case MSR_EFER:
- data = vcpu->shadow_efer;
+ data = vcpu->arch.shadow_efer;
break;
#endif
default:
case KVM_CAP_MMU_SHADOW_CACHE_CONTROL:
case KVM_CAP_USER_MEMORY:
case KVM_CAP_SET_TSS_ADDR:
+ case KVM_CAP_EXT_CPUID:
r = 1;
break;
default:
kvm_put_guest_fpu(vcpu);
}
-static void cpuid_fix_nx_cap(struct kvm_vcpu *vcpu)
+static int is_efer_nx(void)
{
u64 efer;
- int i;
- struct kvm_cpuid_entry *e, *entry;
rdmsrl(MSR_EFER, efer);
+ return efer & EFER_NX;
+}
+
+static void cpuid_fix_nx_cap(struct kvm_vcpu *vcpu)
+{
+ int i;
+ struct kvm_cpuid_entry2 *e, *entry;
+
entry = NULL;
- for (i = 0; i < vcpu->cpuid_nent; ++i) {
- e = &vcpu->cpuid_entries[i];
+ for (i = 0; i < vcpu->arch.cpuid_nent; ++i) {
+ e = &vcpu->arch.cpuid_entries[i];
if (e->function == 0x80000001) {
entry = e;
break;
}
}
- if (entry && (entry->edx & (1 << 20)) && !(efer & EFER_NX)) {
+ if (entry && (entry->edx & (1 << 20)) && !is_efer_nx()) {
entry->edx &= ~(1 << 20);
printk(KERN_INFO "kvm: guest NX capability removed\n");
}
}
+/* when an old userspace process fills a new kernel module */
static int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu,
struct kvm_cpuid *cpuid,
struct kvm_cpuid_entry __user *entries)
{
- int r;
+ int r, i;
+ struct kvm_cpuid_entry *cpuid_entries;
r = -E2BIG;
if (cpuid->nent > KVM_MAX_CPUID_ENTRIES)
goto out;
+ r = -ENOMEM;
+ cpuid_entries = vmalloc(sizeof(struct kvm_cpuid_entry) * cpuid->nent);
+ if (!cpuid_entries)
+ goto out;
r = -EFAULT;
- if (copy_from_user(&vcpu->cpuid_entries, entries,
+ if (copy_from_user(cpuid_entries, entries,
cpuid->nent * sizeof(struct kvm_cpuid_entry)))
- goto out;
- vcpu->cpuid_nent = cpuid->nent;
+ goto out_free;
+ for (i = 0; i < cpuid->nent; i++) {
+ vcpu->arch.cpuid_entries[i].function = cpuid_entries[i].function;
+ vcpu->arch.cpuid_entries[i].eax = cpuid_entries[i].eax;
+ vcpu->arch.cpuid_entries[i].ebx = cpuid_entries[i].ebx;
+ vcpu->arch.cpuid_entries[i].ecx = cpuid_entries[i].ecx;
+ vcpu->arch.cpuid_entries[i].edx = cpuid_entries[i].edx;
+ vcpu->arch.cpuid_entries[i].index = 0;
+ vcpu->arch.cpuid_entries[i].flags = 0;
+ vcpu->arch.cpuid_entries[i].padding[0] = 0;
+ vcpu->arch.cpuid_entries[i].padding[1] = 0;
+ vcpu->arch.cpuid_entries[i].padding[2] = 0;
+ }
+ vcpu->arch.cpuid_nent = cpuid->nent;
cpuid_fix_nx_cap(vcpu);
+ r = 0;
+
+out_free:
+ vfree(cpuid_entries);
+out:
+ return r;
+}
+
+static int kvm_vcpu_ioctl_set_cpuid2(struct kvm_vcpu *vcpu,
+ struct kvm_cpuid2 *cpuid,
+ struct kvm_cpuid_entry2 __user *entries)
+{
+ int r;
+
+ r = -E2BIG;
+ if (cpuid->nent > KVM_MAX_CPUID_ENTRIES)
+ goto out;
+ r = -EFAULT;
+ if (copy_from_user(&vcpu->arch.cpuid_entries, entries,
+ cpuid->nent * sizeof(struct kvm_cpuid_entry2)))
+ goto out;
+ vcpu->arch.cpuid_nent = cpuid->nent;
+ return 0;
+
+out:
+ return r;
+}
+
+static int kvm_vcpu_ioctl_get_cpuid2(struct kvm_vcpu *vcpu,
+ struct kvm_cpuid2 *cpuid,
+ struct kvm_cpuid_entry2 __user *entries)
+{
+ int r;
+
+ r = -E2BIG;
+ if (cpuid->nent < vcpu->arch.cpuid_nent)
+ goto out;
+ r = -EFAULT;
+ if (copy_to_user(entries, &vcpu->arch.cpuid_entries,
+ vcpu->arch.cpuid_nent * sizeof(struct kvm_cpuid_entry2)))
+ goto out;
return 0;
+out:
+ cpuid->nent = vcpu->arch.cpuid_nent;
+ return r;
+}
+
+static inline u32 bit(int bitno)
+{
+ return 1 << (bitno & 31);
+}
+
+static void do_cpuid_1_ent(struct kvm_cpuid_entry2 *entry, u32 function,
+ u32 index)
+{
+ entry->function = function;
+ entry->index = index;
+ cpuid_count(entry->function, entry->index,
+ &entry->eax, &entry->ebx, &entry->ecx, &entry->edx);
+ entry->flags = 0;
+}
+
+static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
+ u32 index, int *nent, int maxnent)
+{
+ const u32 kvm_supported_word0_x86_features = bit(X86_FEATURE_FPU) |
+ bit(X86_FEATURE_VME) | bit(X86_FEATURE_DE) |
+ bit(X86_FEATURE_PSE) | bit(X86_FEATURE_TSC) |
+ bit(X86_FEATURE_MSR) | bit(X86_FEATURE_PAE) |
+ bit(X86_FEATURE_CX8) | bit(X86_FEATURE_APIC) |
+ bit(X86_FEATURE_SEP) | bit(X86_FEATURE_PGE) |
+ bit(X86_FEATURE_CMOV) | bit(X86_FEATURE_PSE36) |
+ bit(X86_FEATURE_CLFLSH) | bit(X86_FEATURE_MMX) |
+ bit(X86_FEATURE_FXSR) | bit(X86_FEATURE_XMM) |
+ bit(X86_FEATURE_XMM2) | bit(X86_FEATURE_SELFSNOOP);
+ const u32 kvm_supported_word1_x86_features = bit(X86_FEATURE_FPU) |
+ bit(X86_FEATURE_VME) | bit(X86_FEATURE_DE) |
+ bit(X86_FEATURE_PSE) | bit(X86_FEATURE_TSC) |
+ bit(X86_FEATURE_MSR) | bit(X86_FEATURE_PAE) |
+ bit(X86_FEATURE_CX8) | bit(X86_FEATURE_APIC) |
+ bit(X86_FEATURE_PGE) |
+ bit(X86_FEATURE_CMOV) | bit(X86_FEATURE_PSE36) |
+ bit(X86_FEATURE_MMX) | bit(X86_FEATURE_FXSR) |
+ bit(X86_FEATURE_SYSCALL) |
+ (bit(X86_FEATURE_NX) && is_efer_nx()) |
+#ifdef CONFIG_X86_64
+ bit(X86_FEATURE_LM) |
+#endif
+ bit(X86_FEATURE_MMXEXT) |
+ bit(X86_FEATURE_3DNOWEXT) |
+ bit(X86_FEATURE_3DNOW);
+ const u32 kvm_supported_word3_x86_features =
+ bit(X86_FEATURE_XMM3) | bit(X86_FEATURE_CX16);
+ const u32 kvm_supported_word6_x86_features =
+ bit(X86_FEATURE_LAHF_LM) | bit(X86_FEATURE_CMP_LEGACY);
+
+ /* all func 2 cpuid_count() should be called on the same cpu */
+ get_cpu();
+ do_cpuid_1_ent(entry, function, index);
+ ++*nent;
+
+ switch (function) {
+ case 0:
+ entry->eax = min(entry->eax, (u32)0xb);
+ break;
+ case 1:
+ entry->edx &= kvm_supported_word0_x86_features;
+ entry->ecx &= kvm_supported_word3_x86_features;
+ break;
+ /* function 2 entries are STATEFUL. That is, repeated cpuid commands
+ * may return different values. This forces us to get_cpu() before
+ * issuing the first command, and also to emulate this annoying behavior
+ * in kvm_emulate_cpuid() using KVM_CPUID_FLAG_STATE_READ_NEXT */
+ case 2: {
+ int t, times = entry->eax & 0xff;
+
+ entry->flags |= KVM_CPUID_FLAG_STATEFUL_FUNC;
+ for (t = 1; t < times && *nent < maxnent; ++t) {
+ do_cpuid_1_ent(&entry[t], function, 0);
+ entry[t].flags |= KVM_CPUID_FLAG_STATEFUL_FUNC;
+ ++*nent;
+ }
+ break;
+ }
+ /* function 4 and 0xb have additional index. */
+ case 4: {
+ int index, cache_type;
+
+ entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
+ /* read more entries until cache_type is zero */
+ for (index = 1; *nent < maxnent; ++index) {
+ cache_type = entry[index - 1].eax & 0x1f;
+ if (!cache_type)
+ break;
+ do_cpuid_1_ent(&entry[index], function, index);
+ entry[index].flags |=
+ KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
+ ++*nent;
+ }
+ break;
+ }
+ case 0xb: {
+ int index, level_type;
+
+ entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
+ /* read more entries until level_type is zero */
+ for (index = 1; *nent < maxnent; ++index) {
+ level_type = entry[index - 1].ecx & 0xff;
+ if (!level_type)
+ break;
+ do_cpuid_1_ent(&entry[index], function, index);
+ entry[index].flags |=
+ KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
+ ++*nent;
+ }
+ break;
+ }
+ case 0x80000000:
+ entry->eax = min(entry->eax, 0x8000001a);
+ break;
+ case 0x80000001:
+ entry->edx &= kvm_supported_word1_x86_features;
+ entry->ecx &= kvm_supported_word6_x86_features;
+ break;
+ }
+ put_cpu();
+}
+
+static int kvm_vm_ioctl_get_supported_cpuid(struct kvm *kvm,
+ struct kvm_cpuid2 *cpuid,
+ struct kvm_cpuid_entry2 __user *entries)
+{
+ struct kvm_cpuid_entry2 *cpuid_entries;
+ int limit, nent = 0, r = -E2BIG;
+ u32 func;
+
+ if (cpuid->nent < 1)
+ goto out;
+ r = -ENOMEM;
+ cpuid_entries = vmalloc(sizeof(struct kvm_cpuid_entry2) * cpuid->nent);
+ if (!cpuid_entries)
+ goto out;
+
+ do_cpuid_ent(&cpuid_entries[0], 0, 0, &nent, cpuid->nent);
+ limit = cpuid_entries[0].eax;
+ for (func = 1; func <= limit && nent < cpuid->nent; ++func)
+ do_cpuid_ent(&cpuid_entries[nent], func, 0,
+ &nent, cpuid->nent);
+ r = -E2BIG;
+ if (nent >= cpuid->nent)
+ goto out_free;
+
+ do_cpuid_ent(&cpuid_entries[nent], 0x80000000, 0, &nent, cpuid->nent);
+ limit = cpuid_entries[nent - 1].eax;
+ for (func = 0x80000001; func <= limit && nent < cpuid->nent; ++func)
+ do_cpuid_ent(&cpuid_entries[nent], func, 0,
+ &nent, cpuid->nent);
+ r = -EFAULT;
+ if (copy_to_user(entries, cpuid_entries,
+ nent * sizeof(struct kvm_cpuid_entry2)))
+ goto out_free;
+ cpuid->nent = nent;
+ r = 0;
+
+out_free:
+ vfree(cpuid_entries);
out:
return r;
}
struct kvm_lapic_state *s)
{
vcpu_load(vcpu);
- memcpy(s->regs, vcpu->apic->regs, sizeof *s);
+ memcpy(s->regs, vcpu->arch.apic->regs, sizeof *s);
vcpu_put(vcpu);
return 0;
struct kvm_lapic_state *s)
{
vcpu_load(vcpu);
- memcpy(vcpu->apic->regs, s->regs, sizeof *s);
+ memcpy(vcpu->arch.apic->regs, s->regs, sizeof *s);
kvm_apic_post_state_restore(vcpu);
vcpu_put(vcpu);
return 0;
}
+static int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu,
+ struct kvm_interrupt *irq)
+{
+ 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->arch.irq_pending);
+ set_bit(irq->irq / BITS_PER_LONG, &vcpu->arch.irq_summary);
+
+ vcpu_put(vcpu);
+
+ return 0;
+}
+
long kvm_arch_vcpu_ioctl(struct file *filp,
unsigned int ioctl, unsigned long arg)
{
r = 0;
break;
}
+ case KVM_INTERRUPT: {
+ struct kvm_interrupt irq;
+
+ r = -EFAULT;
+ if (copy_from_user(&irq, argp, sizeof irq))
+ goto out;
+ r = kvm_vcpu_ioctl_interrupt(vcpu, &irq);
+ if (r)
+ goto out;
+ r = 0;
+ break;
+ }
case KVM_SET_CPUID: {
struct kvm_cpuid __user *cpuid_arg = argp;
struct kvm_cpuid cpuid;
goto out;
break;
}
+ case KVM_SET_CPUID2: {
+ struct kvm_cpuid2 __user *cpuid_arg = argp;
+ struct kvm_cpuid2 cpuid;
+
+ r = -EFAULT;
+ if (copy_from_user(&cpuid, cpuid_arg, sizeof cpuid))
+ goto out;
+ r = kvm_vcpu_ioctl_set_cpuid2(vcpu, &cpuid,
+ cpuid_arg->entries);
+ if (r)
+ goto out;
+ break;
+ }
+ case KVM_GET_CPUID2: {
+ struct kvm_cpuid2 __user *cpuid_arg = argp;
+ struct kvm_cpuid2 cpuid;
+
+ r = -EFAULT;
+ if (copy_from_user(&cpuid, cpuid_arg, sizeof cpuid))
+ goto out;
+ r = kvm_vcpu_ioctl_get_cpuid2(vcpu, &cpuid,
+ cpuid_arg->entries);
+ if (r)
+ goto out;
+ r = -EFAULT;
+ if (copy_to_user(cpuid_arg, &cpuid, sizeof cpuid))
+ goto out;
+ r = 0;
+ break;
+ }
case KVM_GET_MSRS:
r = msr_io(vcpu, argp, kvm_get_msr, 1);
break;
mutex_lock(&kvm->lock);
kvm_mmu_change_mmu_pages(kvm, kvm_nr_mmu_pages);
- kvm->n_requested_mmu_pages = kvm_nr_mmu_pages;
+ kvm->arch.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;
+ return kvm->arch.n_alloc_mmu_pages;
+}
+
+gfn_t unalias_gfn(struct kvm *kvm, gfn_t gfn)
+{
+ int i;
+ struct kvm_mem_alias *alias;
+
+ for (i = 0; i < kvm->arch.naliases; ++i) {
+ alias = &kvm->arch.aliases[i];
+ if (gfn >= alias->base_gfn
+ && gfn < alias->base_gfn + alias->npages)
+ return alias->target_gfn + gfn - alias->base_gfn;
+ }
+ return gfn;
}
/*
mutex_lock(&kvm->lock);
- p = &kvm->aliases[alias->slot];
+ p = &kvm->arch.aliases[alias->slot];
p->base_gfn = alias->guest_phys_addr >> PAGE_SHIFT;
p->npages = alias->memory_size >> PAGE_SHIFT;
p->target_gfn = alias->target_phys_addr >> PAGE_SHIFT;
for (n = KVM_ALIAS_SLOTS; n > 0; --n)
- if (kvm->aliases[n - 1].npages)
+ if (kvm->arch.aliases[n - 1].npages)
break;
- kvm->naliases = n;
+ kvm->arch.naliases = n;
kvm_mmu_zap_all(kvm);
}
case KVM_CREATE_IRQCHIP:
r = -ENOMEM;
- kvm->vpic = kvm_create_pic(kvm);
- if (kvm->vpic) {
+ kvm->arch.vpic = kvm_create_pic(kvm);
+ if (kvm->arch.vpic) {
r = kvm_ioapic_init(kvm);
if (r) {
- kfree(kvm->vpic);
- kvm->vpic = NULL;
+ kfree(kvm->arch.vpic);
+ kvm->arch.vpic = NULL;
goto out;
}
} else
kvm_pic_set_irq(pic_irqchip(kvm),
irq_event.irq,
irq_event.level);
- kvm_ioapic_set_irq(kvm->vioapic,
+ kvm_ioapic_set_irq(kvm->arch.vioapic,
irq_event.irq,
irq_event.level);
mutex_unlock(&kvm->lock);
r = 0;
break;
}
+ case KVM_GET_SUPPORTED_CPUID: {
+ struct kvm_cpuid2 __user *cpuid_arg = argp;
+ struct kvm_cpuid2 cpuid;
+
+ r = -EFAULT;
+ if (copy_from_user(&cpuid, cpuid_arg, sizeof cpuid))
+ goto out;
+ r = kvm_vm_ioctl_get_supported_cpuid(kvm, &cpuid,
+ cpuid_arg->entries);
+ if (r)
+ goto out;
+
+ r = -EFAULT;
+ if (copy_to_user(cpuid_arg, &cpuid, sizeof cpuid))
+ goto out;
+ r = 0;
+ break;
+ }
default:
;
}
{
struct kvm_io_device *dev;
- if (vcpu->apic) {
- dev = &vcpu->apic->dev;
+ if (vcpu->arch.apic) {
+ dev = &vcpu->arch.apic->dev;
if (dev->in_range(dev, addr))
return dev;
}
void *data = val;
while (bytes) {
- gpa_t gpa = vcpu->mmu.gva_to_gpa(vcpu, addr);
+ gpa_t gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, addr);
unsigned offset = addr & (PAGE_SIZE-1);
unsigned tocopy = min(bytes, (unsigned)PAGE_SIZE - offset);
int ret;
}
EXPORT_SYMBOL_GPL(emulator_read_std);
-static int emulator_write_std(unsigned long addr,
- const void *val,
- unsigned int bytes,
- struct kvm_vcpu *vcpu)
-{
- pr_unimpl(vcpu, "emulator_write_std: addr %lx n %d\n", addr, bytes);
- return X86EMUL_UNHANDLEABLE;
-}
-
static int emulator_read_emulated(unsigned long addr,
void *val,
unsigned int bytes,
return X86EMUL_CONTINUE;
}
- gpa = vcpu->mmu.gva_to_gpa(vcpu, addr);
+ gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, addr);
/* For APIC access vmexit */
if ((gpa & PAGE_MASK) == APIC_DEFAULT_PHYS_BASE)
struct kvm_vcpu *vcpu)
{
struct kvm_io_device *mmio_dev;
- gpa_t gpa = vcpu->mmu.gva_to_gpa(vcpu, addr);
+ gpa_t gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, addr);
if (gpa == UNMAPPED_GVA) {
- kvm_x86_ops->inject_page_fault(vcpu, addr, 2);
+ kvm_inject_page_fault(vcpu, addr, 2);
return X86EMUL_PROPAGATE_FAULT;
}
reported = 1;
printk(KERN_WARNING "kvm: emulating exchange as write\n");
}
+#ifndef CONFIG_X86_64
+ /* guests cmpxchg8b have to be emulated atomically */
+ if (bytes == 8) {
+ gpa_t gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, addr);
+ struct page *page;
+ char *addr;
+ u64 val;
+
+ if (gpa == UNMAPPED_GVA ||
+ (gpa & PAGE_MASK) == APIC_DEFAULT_PHYS_BASE)
+ goto emul_write;
+
+ if (((gpa + bytes - 1) & PAGE_MASK) != (gpa & PAGE_MASK))
+ goto emul_write;
+
+ val = *(u64 *)new;
+ page = gfn_to_page(vcpu->kvm, gpa >> PAGE_SHIFT);
+ addr = kmap_atomic(page, KM_USER0);
+ set_64bit((u64 *)(addr + offset_in_page(gpa)), val);
+ kunmap_atomic(addr, KM_USER0);
+ kvm_release_page_dirty(page);
+ }
+emul_write:
+#endif
+
return emulator_write_emulated(addr, new, bytes, vcpu);
}
int emulate_clts(struct kvm_vcpu *vcpu)
{
- kvm_x86_ops->set_cr0(vcpu, vcpu->cr0 & ~X86_CR0_TS);
+ kvm_x86_ops->set_cr0(vcpu, vcpu->arch.cr0 & ~X86_CR0_TS);
return X86EMUL_CONTINUE;
}
{
static int reported;
u8 opcodes[4];
- unsigned long rip = vcpu->rip;
+ unsigned long rip = vcpu->arch.rip;
unsigned long rip_linear;
rip_linear = rip + get_segment_base(vcpu, VCPU_SREG_CS);
struct x86_emulate_ops emulate_ops = {
.read_std = emulator_read_std,
- .write_std = emulator_write_std,
.read_emulated = emulator_read_emulated,
.write_emulated = emulator_write_emulated,
.cmpxchg_emulated = emulator_cmpxchg_emulated,
{
int r;
- vcpu->mmio_fault_cr2 = cr2;
+ vcpu->arch.mmio_fault_cr2 = cr2;
kvm_x86_ops->cache_regs(vcpu);
vcpu->mmio_is_write = 0;
- vcpu->pio.string = 0;
+ vcpu->arch.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)
+ vcpu->arch.emulate_ctxt.vcpu = vcpu;
+ vcpu->arch.emulate_ctxt.eflags = kvm_x86_ops->get_rflags(vcpu);
+ vcpu->arch.emulate_ctxt.mode =
+ (vcpu->arch.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;
+ if (vcpu->arch.emulate_ctxt.mode == X86EMUL_MODE_PROT64) {
+ vcpu->arch.emulate_ctxt.cs_base = 0;
+ vcpu->arch.emulate_ctxt.ds_base = 0;
+ vcpu->arch.emulate_ctxt.es_base = 0;
+ vcpu->arch.emulate_ctxt.ss_base = 0;
} else {
- vcpu->emulate_ctxt.cs_base =
+ vcpu->arch.emulate_ctxt.cs_base =
get_segment_base(vcpu, VCPU_SREG_CS);
- vcpu->emulate_ctxt.ds_base =
+ vcpu->arch.emulate_ctxt.ds_base =
get_segment_base(vcpu, VCPU_SREG_DS);
- vcpu->emulate_ctxt.es_base =
+ vcpu->arch.emulate_ctxt.es_base =
get_segment_base(vcpu, VCPU_SREG_ES);
- vcpu->emulate_ctxt.ss_base =
+ vcpu->arch.emulate_ctxt.ss_base =
get_segment_base(vcpu, VCPU_SREG_SS);
}
- vcpu->emulate_ctxt.gs_base =
+ vcpu->arch.emulate_ctxt.gs_base =
get_segment_base(vcpu, VCPU_SREG_GS);
- vcpu->emulate_ctxt.fs_base =
+ vcpu->arch.emulate_ctxt.fs_base =
get_segment_base(vcpu, VCPU_SREG_FS);
- r = x86_decode_insn(&vcpu->emulate_ctxt, &emulate_ops);
+ r = x86_decode_insn(&vcpu->arch.emulate_ctxt, &emulate_ops);
++vcpu->stat.insn_emulation;
if (r) {
++vcpu->stat.insn_emulation_fail;
}
}
- r = x86_emulate_insn(&vcpu->emulate_ctxt, &emulate_ops);
+ r = x86_emulate_insn(&vcpu->arch.emulate_ctxt, &emulate_ops);
- if (vcpu->pio.string)
+ if (vcpu->arch.pio.string)
return EMULATE_DO_MMIO;
if ((r || vcpu->mmio_is_write) && run) {
}
kvm_x86_ops->decache_regs(vcpu);
- kvm_x86_ops->set_rflags(vcpu, vcpu->emulate_ctxt.eflags);
+ kvm_x86_ops->set_rflags(vcpu, vcpu->arch.emulate_ctxt.eflags);
if (vcpu->mmio_is_write) {
vcpu->mmio_needed = 0;
{
int i;
- for (i = 0; i < ARRAY_SIZE(vcpu->pio.guest_pages); ++i)
- if (vcpu->pio.guest_pages[i]) {
- kvm_release_page_dirty(vcpu->pio.guest_pages[i]);
- vcpu->pio.guest_pages[i] = NULL;
+ for (i = 0; i < ARRAY_SIZE(vcpu->arch.pio.guest_pages); ++i)
+ if (vcpu->arch.pio.guest_pages[i]) {
+ kvm_release_page_dirty(vcpu->arch.pio.guest_pages[i]);
+ vcpu->arch.pio.guest_pages[i] = NULL;
}
}
static int pio_copy_data(struct kvm_vcpu *vcpu)
{
- void *p = vcpu->pio_data;
+ void *p = vcpu->arch.pio_data;
void *q;
unsigned bytes;
- int nr_pages = vcpu->pio.guest_pages[1] ? 2 : 1;
+ int nr_pages = vcpu->arch.pio.guest_pages[1] ? 2 : 1;
- q = vmap(vcpu->pio.guest_pages, nr_pages, VM_READ|VM_WRITE,
+ q = vmap(vcpu->arch.pio.guest_pages, nr_pages, VM_READ|VM_WRITE,
PAGE_KERNEL);
if (!q) {
free_pio_guest_pages(vcpu);
return -ENOMEM;
}
- q += vcpu->pio.guest_page_offset;
- bytes = vcpu->pio.size * vcpu->pio.cur_count;
- if (vcpu->pio.in)
+ q += vcpu->arch.pio.guest_page_offset;
+ bytes = vcpu->arch.pio.size * vcpu->arch.pio.cur_count;
+ if (vcpu->arch.pio.in)
memcpy(q, p, bytes);
else
memcpy(p, q, bytes);
- q -= vcpu->pio.guest_page_offset;
+ q -= vcpu->arch.pio.guest_page_offset;
vunmap(q);
free_pio_guest_pages(vcpu);
return 0;
int complete_pio(struct kvm_vcpu *vcpu)
{
- struct kvm_pio_request *io = &vcpu->pio;
+ struct kvm_pio_request *io = &vcpu->arch.pio;
long delta;
int r;
if (!io->string) {
if (io->in)
- memcpy(&vcpu->regs[VCPU_REGS_RAX], vcpu->pio_data,
+ memcpy(&vcpu->arch.regs[VCPU_REGS_RAX], vcpu->arch.pio_data,
io->size);
} else {
if (io->in) {
* The size of the register should really depend on
* current address size.
*/
- vcpu->regs[VCPU_REGS_RCX] -= delta;
+ vcpu->arch.regs[VCPU_REGS_RCX] -= delta;
}
if (io->down)
delta = -delta;
delta *= io->size;
if (io->in)
- vcpu->regs[VCPU_REGS_RDI] += delta;
+ vcpu->arch.regs[VCPU_REGS_RDI] += delta;
else
- vcpu->regs[VCPU_REGS_RSI] += delta;
+ vcpu->arch.regs[VCPU_REGS_RSI] += delta;
}
kvm_x86_ops->decache_regs(vcpu);
/* 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,
+ if (vcpu->arch.pio.in)
+ kvm_iodevice_read(pio_dev, vcpu->arch.pio.port,
+ vcpu->arch.pio.size,
pd);
else
- kvm_iodevice_write(pio_dev, vcpu->pio.port,
- vcpu->pio.size,
+ kvm_iodevice_write(pio_dev, vcpu->arch.pio.port,
+ vcpu->arch.pio.size,
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;
+ struct kvm_pio_request *io = &vcpu->arch.pio;
+ void *pd = vcpu->arch.pio_data;
int i;
mutex_lock(&vcpu->kvm->lock);
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.size = vcpu->arch.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;
+ vcpu->run->io.count = vcpu->arch.pio.count = vcpu->arch.pio.cur_count = 1;
+ vcpu->run->io.port = vcpu->arch.pio.port = port;
+ vcpu->arch.pio.in = in;
+ vcpu->arch.pio.string = 0;
+ vcpu->arch.pio.down = 0;
+ vcpu->arch.pio.guest_page_offset = 0;
+ vcpu->arch.pio.rep = 0;
kvm_x86_ops->cache_regs(vcpu);
- memcpy(vcpu->pio_data, &vcpu->regs[VCPU_REGS_RAX], 4);
+ memcpy(vcpu->arch.pio_data, &vcpu->arch.regs[VCPU_REGS_RAX], 4);
kvm_x86_ops->decache_regs(vcpu);
kvm_x86_ops->skip_emulated_instruction(vcpu);
pio_dev = vcpu_find_pio_dev(vcpu, port);
if (pio_dev) {
- kernel_pio(pio_dev, vcpu, vcpu->pio_data);
+ kernel_pio(pio_dev, vcpu, vcpu->arch.pio_data);
complete_pio(vcpu);
return 1;
}
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.size = vcpu->arch.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 = count;
- vcpu->run->io.port = vcpu->pio.port = port;
- vcpu->pio.in = in;
- vcpu->pio.string = 1;
- vcpu->pio.down = down;
- vcpu->pio.guest_page_offset = offset_in_page(address);
- vcpu->pio.rep = rep;
+ vcpu->run->io.count = vcpu->arch.pio.count = vcpu->arch.pio.cur_count = count;
+ vcpu->run->io.port = vcpu->arch.pio.port = port;
+ vcpu->arch.pio.in = in;
+ vcpu->arch.pio.string = 1;
+ vcpu->arch.pio.down = down;
+ vcpu->arch.pio.guest_page_offset = offset_in_page(address);
+ vcpu->arch.pio.rep = rep;
if (!count) {
kvm_x86_ops->skip_emulated_instruction(vcpu);
* String I/O in reverse. Yuck. Kill the guest, fix later.
*/
pr_unimpl(vcpu, "guest string pio down\n");
- inject_gp(vcpu);
+ kvm_inject_gp(vcpu, 0);
return 1;
}
vcpu->run->io.count = now;
- vcpu->pio.cur_count = now;
+ vcpu->arch.pio.cur_count = now;
- if (vcpu->pio.cur_count == vcpu->pio.count)
+ if (vcpu->arch.pio.cur_count == vcpu->arch.pio.count)
kvm_x86_ops->skip_emulated_instruction(vcpu);
for (i = 0; i < nr_pages; ++i) {
mutex_lock(&vcpu->kvm->lock);
page = gva_to_page(vcpu, address + i * PAGE_SIZE);
- vcpu->pio.guest_pages[i] = page;
+ vcpu->arch.pio.guest_pages[i] = page;
mutex_unlock(&vcpu->kvm->lock);
if (!page) {
- inject_gp(vcpu);
+ kvm_inject_gp(vcpu, 0);
free_pio_guest_pages(vcpu);
return 1;
}
}
pio_dev = vcpu_find_pio_dev(vcpu, port);
- if (!vcpu->pio.in) {
+ if (!vcpu->arch.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)
+ if (vcpu->arch.pio.count == 0)
ret = 1;
}
} else if (pio_dev)
{
++vcpu->stat.halt_exits;
if (irqchip_in_kernel(vcpu->kvm)) {
- vcpu->mp_state = VCPU_MP_STATE_HALTED;
+ vcpu->arch.mp_state = VCPU_MP_STATE_HALTED;
kvm_vcpu_block(vcpu);
- if (vcpu->mp_state != VCPU_MP_STATE_RUNNABLE)
+ if (vcpu->arch.mp_state != VCPU_MP_STATE_RUNNABLE)
return -EINTR;
return 1;
} else {
kvm_x86_ops->cache_regs(vcpu);
- 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];
+ nr = vcpu->arch.regs[VCPU_REGS_RAX];
+ a0 = vcpu->arch.regs[VCPU_REGS_RBX];
+ a1 = vcpu->arch.regs[VCPU_REGS_RCX];
+ a2 = vcpu->arch.regs[VCPU_REGS_RDX];
+ a3 = vcpu->arch.regs[VCPU_REGS_RSI];
if (!is_long_mode(vcpu)) {
nr &= 0xFFFFFFFF;
ret = -KVM_ENOSYS;
break;
}
- vcpu->regs[VCPU_REGS_RAX] = ret;
+ vcpu->arch.regs[VCPU_REGS_RAX] = ret;
kvm_x86_ops->decache_regs(vcpu);
return 0;
}
kvm_x86_ops->cache_regs(vcpu);
kvm_x86_ops->patch_hypercall(vcpu, instruction);
- if (emulator_write_emulated(vcpu->rip, instruction, 3, vcpu)
+ if (emulator_write_emulated(vcpu->arch.rip, instruction, 3, vcpu)
!= X86EMUL_CONTINUE)
ret = -EFAULT;
kvm_x86_ops->decache_cr4_guest_bits(vcpu);
switch (cr) {
case 0:
- return vcpu->cr0;
+ return vcpu->arch.cr0;
case 2:
- return vcpu->cr2;
+ return vcpu->arch.cr2;
case 3:
- return vcpu->cr3;
+ return vcpu->arch.cr3;
case 4:
- return vcpu->cr4;
+ return vcpu->arch.cr4;
+ case 8:
+ return get_cr8(vcpu);
default:
vcpu_printf(vcpu, "%s: unexpected cr %u\n", __FUNCTION__, cr);
return 0;
{
switch (cr) {
case 0:
- set_cr0(vcpu, mk_cr_64(vcpu->cr0, val));
+ set_cr0(vcpu, mk_cr_64(vcpu->arch.cr0, val));
*rflags = kvm_x86_ops->get_rflags(vcpu);
break;
case 2:
- vcpu->cr2 = val;
+ vcpu->arch.cr2 = val;
break;
case 3:
set_cr3(vcpu, val);
break;
case 4:
- set_cr4(vcpu, mk_cr_64(vcpu->cr4, val));
+ set_cr4(vcpu, mk_cr_64(vcpu->arch.cr4, val));
+ break;
+ case 8:
+ set_cr8(vcpu, val & 0xfUL);
break;
default:
vcpu_printf(vcpu, "%s: unexpected cr %u\n", __FUNCTION__, cr);
}
}
+static int move_to_next_stateful_cpuid_entry(struct kvm_vcpu *vcpu, int i)
+{
+ struct kvm_cpuid_entry2 *e = &vcpu->arch.cpuid_entries[i];
+ int j, nent = vcpu->arch.cpuid_nent;
+
+ e->flags &= ~KVM_CPUID_FLAG_STATE_READ_NEXT;
+ /* when no next entry is found, the current entry[i] is reselected */
+ for (j = i + 1; j == i; j = (j + 1) % nent) {
+ struct kvm_cpuid_entry2 *ej = &vcpu->arch.cpuid_entries[j];
+ if (ej->function == e->function) {
+ ej->flags |= KVM_CPUID_FLAG_STATE_READ_NEXT;
+ return j;
+ }
+ }
+ return 0; /* silence gcc, even though control never reaches here */
+}
+
+/* find an entry with matching function, matching index (if needed), and that
+ * should be read next (if it's stateful) */
+static int is_matching_cpuid_entry(struct kvm_cpuid_entry2 *e,
+ u32 function, u32 index)
+{
+ if (e->function != function)
+ return 0;
+ if ((e->flags & KVM_CPUID_FLAG_SIGNIFCANT_INDEX) && e->index != index)
+ return 0;
+ if ((e->flags & KVM_CPUID_FLAG_STATEFUL_FUNC) &&
+ !(e->flags & KVM_CPUID_FLAG_STATE_READ_NEXT))
+ return 0;
+ return 1;
+}
+
void kvm_emulate_cpuid(struct kvm_vcpu *vcpu)
{
int i;
- u32 function;
- struct kvm_cpuid_entry *e, *best;
+ u32 function, index;
+ struct kvm_cpuid_entry2 *e, *best;
kvm_x86_ops->cache_regs(vcpu);
- function = vcpu->regs[VCPU_REGS_RAX];
- vcpu->regs[VCPU_REGS_RAX] = 0;
- vcpu->regs[VCPU_REGS_RBX] = 0;
- vcpu->regs[VCPU_REGS_RCX] = 0;
- vcpu->regs[VCPU_REGS_RDX] = 0;
+ function = vcpu->arch.regs[VCPU_REGS_RAX];
+ index = vcpu->arch.regs[VCPU_REGS_RCX];
+ vcpu->arch.regs[VCPU_REGS_RAX] = 0;
+ vcpu->arch.regs[VCPU_REGS_RBX] = 0;
+ vcpu->arch.regs[VCPU_REGS_RCX] = 0;
+ vcpu->arch.regs[VCPU_REGS_RDX] = 0;
best = NULL;
- for (i = 0; i < vcpu->cpuid_nent; ++i) {
- e = &vcpu->cpuid_entries[i];
- if (e->function == function) {
+ for (i = 0; i < vcpu->arch.cpuid_nent; ++i) {
+ e = &vcpu->arch.cpuid_entries[i];
+ if (is_matching_cpuid_entry(e, function, index)) {
+ if (e->flags & KVM_CPUID_FLAG_STATEFUL_FUNC)
+ move_to_next_stateful_cpuid_entry(vcpu, i);
best = e;
break;
}
best = e;
}
if (best) {
- vcpu->regs[VCPU_REGS_RAX] = best->eax;
- vcpu->regs[VCPU_REGS_RBX] = best->ebx;
- vcpu->regs[VCPU_REGS_RCX] = best->ecx;
- vcpu->regs[VCPU_REGS_RDX] = best->edx;
+ vcpu->arch.regs[VCPU_REGS_RAX] = best->eax;
+ vcpu->arch.regs[VCPU_REGS_RBX] = best->ebx;
+ vcpu->arch.regs[VCPU_REGS_RCX] = best->ecx;
+ vcpu->arch.regs[VCPU_REGS_RDX] = best->edx;
}
kvm_x86_ops->decache_regs(vcpu);
kvm_x86_ops->skip_emulated_instruction(vcpu);
static int dm_request_for_irq_injection(struct kvm_vcpu *vcpu,
struct kvm_run *kvm_run)
{
- return (!vcpu->irq_summary &&
+ return (!vcpu->arch.irq_summary &&
kvm_run->request_interrupt_window &&
- vcpu->interrupt_window_open &&
+ vcpu->arch.interrupt_window_open &&
(kvm_x86_ops->get_rflags(vcpu) & X86_EFLAGS_IF));
}
kvm_run->ready_for_interrupt_injection = 1;
else
kvm_run->ready_for_interrupt_injection =
- (vcpu->interrupt_window_open &&
- vcpu->irq_summary == 0);
+ (vcpu->arch.interrupt_window_open &&
+ vcpu->arch.irq_summary == 0);
}
static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
{
int r;
- if (unlikely(vcpu->mp_state == VCPU_MP_STATE_SIPI_RECEIVED)) {
+ if (unlikely(vcpu->arch.mp_state == VCPU_MP_STATE_SIPI_RECEIVED)) {
pr_debug("vcpu %d received sipi with vector # %x\n",
- vcpu->vcpu_id, vcpu->sipi_vector);
+ vcpu->vcpu_id, vcpu->arch.sipi_vector);
kvm_lapic_reset(vcpu);
r = kvm_x86_ops->vcpu_reset(vcpu);
if (r)
return r;
- vcpu->mp_state = VCPU_MP_STATE_RUNNABLE;
+ vcpu->arch.mp_state = VCPU_MP_STATE_RUNNABLE;
}
preempted:
goto out;
}
- if (irqchip_in_kernel(vcpu->kvm))
+ if (vcpu->arch.exception.pending)
+ __queue_exception(vcpu);
+ else if (irqchip_in_kernel(vcpu->kvm))
kvm_x86_ops->inject_pending_irq(vcpu);
- else if (!vcpu->mmio_read_completed)
+ else
kvm_x86_ops->inject_pending_vectors(vcpu, kvm_run);
vcpu->guest_mode = 1;
*/
if (unlikely(prof_on == KVM_PROFILING)) {
kvm_x86_ops->cache_regs(vcpu);
- profile_hit(KVM_PROFILING, (void *)vcpu->rip);
+ profile_hit(KVM_PROFILING, (void *)vcpu->arch.rip);
}
+ if (vcpu->arch.exception.pending && kvm_x86_ops->exception_injected(vcpu))
+ vcpu->arch.exception.pending = false;
+
r = kvm_x86_ops->handle_exit(kvm_run, vcpu);
if (r > 0) {
vcpu_load(vcpu);
- if (unlikely(vcpu->mp_state == VCPU_MP_STATE_UNINITIALIZED)) {
+ if (unlikely(vcpu->arch.mp_state == VCPU_MP_STATE_UNINITIALIZED)) {
kvm_vcpu_block(vcpu);
vcpu_put(vcpu);
return -EAGAIN;
if (!irqchip_in_kernel(vcpu->kvm))
set_cr8(vcpu, kvm_run->cr8);
- if (vcpu->pio.cur_count) {
+ if (vcpu->arch.pio.cur_count) {
r = complete_pio(vcpu);
if (r)
goto out;
vcpu->mmio_read_completed = 1;
vcpu->mmio_needed = 0;
r = emulate_instruction(vcpu, kvm_run,
- vcpu->mmio_fault_cr2, 0, 1);
+ vcpu->arch.mmio_fault_cr2, 0, 1);
if (r == EMULATE_DO_MMIO) {
/*
* Read-modify-write. Back to userspace.
#endif
if (kvm_run->exit_reason == KVM_EXIT_HYPERCALL) {
kvm_x86_ops->cache_regs(vcpu);
- vcpu->regs[VCPU_REGS_RAX] = kvm_run->hypercall.ret;
+ vcpu->arch.regs[VCPU_REGS_RAX] = kvm_run->hypercall.ret;
kvm_x86_ops->decache_regs(vcpu);
}
kvm_x86_ops->cache_regs(vcpu);
- regs->rax = vcpu->regs[VCPU_REGS_RAX];
- regs->rbx = vcpu->regs[VCPU_REGS_RBX];
- regs->rcx = vcpu->regs[VCPU_REGS_RCX];
- regs->rdx = vcpu->regs[VCPU_REGS_RDX];
- regs->rsi = vcpu->regs[VCPU_REGS_RSI];
- regs->rdi = vcpu->regs[VCPU_REGS_RDI];
- regs->rsp = vcpu->regs[VCPU_REGS_RSP];
- regs->rbp = vcpu->regs[VCPU_REGS_RBP];
+ regs->rax = vcpu->arch.regs[VCPU_REGS_RAX];
+ regs->rbx = vcpu->arch.regs[VCPU_REGS_RBX];
+ regs->rcx = vcpu->arch.regs[VCPU_REGS_RCX];
+ regs->rdx = vcpu->arch.regs[VCPU_REGS_RDX];
+ regs->rsi = vcpu->arch.regs[VCPU_REGS_RSI];
+ regs->rdi = vcpu->arch.regs[VCPU_REGS_RDI];
+ regs->rsp = vcpu->arch.regs[VCPU_REGS_RSP];
+ regs->rbp = vcpu->arch.regs[VCPU_REGS_RBP];
#ifdef CONFIG_X86_64
- regs->r8 = vcpu->regs[VCPU_REGS_R8];
- regs->r9 = vcpu->regs[VCPU_REGS_R9];
- regs->r10 = vcpu->regs[VCPU_REGS_R10];
- regs->r11 = vcpu->regs[VCPU_REGS_R11];
- regs->r12 = vcpu->regs[VCPU_REGS_R12];
- regs->r13 = vcpu->regs[VCPU_REGS_R13];
- regs->r14 = vcpu->regs[VCPU_REGS_R14];
- regs->r15 = vcpu->regs[VCPU_REGS_R15];
+ regs->r8 = vcpu->arch.regs[VCPU_REGS_R8];
+ regs->r9 = vcpu->arch.regs[VCPU_REGS_R9];
+ regs->r10 = vcpu->arch.regs[VCPU_REGS_R10];
+ regs->r11 = vcpu->arch.regs[VCPU_REGS_R11];
+ regs->r12 = vcpu->arch.regs[VCPU_REGS_R12];
+ regs->r13 = vcpu->arch.regs[VCPU_REGS_R13];
+ regs->r14 = vcpu->arch.regs[VCPU_REGS_R14];
+ regs->r15 = vcpu->arch.regs[VCPU_REGS_R15];
#endif
- regs->rip = vcpu->rip;
+ regs->rip = vcpu->arch.rip;
regs->rflags = kvm_x86_ops->get_rflags(vcpu);
/*
{
vcpu_load(vcpu);
- vcpu->regs[VCPU_REGS_RAX] = regs->rax;
- vcpu->regs[VCPU_REGS_RBX] = regs->rbx;
- vcpu->regs[VCPU_REGS_RCX] = regs->rcx;
- vcpu->regs[VCPU_REGS_RDX] = regs->rdx;
- vcpu->regs[VCPU_REGS_RSI] = regs->rsi;
- vcpu->regs[VCPU_REGS_RDI] = regs->rdi;
- vcpu->regs[VCPU_REGS_RSP] = regs->rsp;
- vcpu->regs[VCPU_REGS_RBP] = regs->rbp;
+ vcpu->arch.regs[VCPU_REGS_RAX] = regs->rax;
+ vcpu->arch.regs[VCPU_REGS_RBX] = regs->rbx;
+ vcpu->arch.regs[VCPU_REGS_RCX] = regs->rcx;
+ vcpu->arch.regs[VCPU_REGS_RDX] = regs->rdx;
+ vcpu->arch.regs[VCPU_REGS_RSI] = regs->rsi;
+ vcpu->arch.regs[VCPU_REGS_RDI] = regs->rdi;
+ vcpu->arch.regs[VCPU_REGS_RSP] = regs->rsp;
+ vcpu->arch.regs[VCPU_REGS_RBP] = regs->rbp;
#ifdef CONFIG_X86_64
- vcpu->regs[VCPU_REGS_R8] = regs->r8;
- vcpu->regs[VCPU_REGS_R9] = regs->r9;
- vcpu->regs[VCPU_REGS_R10] = regs->r10;
- vcpu->regs[VCPU_REGS_R11] = regs->r11;
- vcpu->regs[VCPU_REGS_R12] = regs->r12;
- vcpu->regs[VCPU_REGS_R13] = regs->r13;
- vcpu->regs[VCPU_REGS_R14] = regs->r14;
- vcpu->regs[VCPU_REGS_R15] = regs->r15;
+ vcpu->arch.regs[VCPU_REGS_R8] = regs->r8;
+ vcpu->arch.regs[VCPU_REGS_R9] = regs->r9;
+ vcpu->arch.regs[VCPU_REGS_R10] = regs->r10;
+ vcpu->arch.regs[VCPU_REGS_R11] = regs->r11;
+ vcpu->arch.regs[VCPU_REGS_R12] = regs->r12;
+ vcpu->arch.regs[VCPU_REGS_R13] = regs->r13;
+ vcpu->arch.regs[VCPU_REGS_R14] = regs->r14;
+ vcpu->arch.regs[VCPU_REGS_R15] = regs->r15;
#endif
- vcpu->rip = regs->rip;
+ vcpu->arch.rip = regs->rip;
kvm_x86_ops->set_rflags(vcpu, regs->rflags);
kvm_x86_ops->decache_regs(vcpu);
sregs->gdt.base = dt.base;
kvm_x86_ops->decache_cr4_guest_bits(vcpu);
- sregs->cr0 = vcpu->cr0;
- sregs->cr2 = vcpu->cr2;
- sregs->cr3 = vcpu->cr3;
- sregs->cr4 = vcpu->cr4;
+ sregs->cr0 = vcpu->arch.cr0;
+ sregs->cr2 = vcpu->arch.cr2;
+ sregs->cr3 = vcpu->arch.cr3;
+ sregs->cr4 = vcpu->arch.cr4;
sregs->cr8 = get_cr8(vcpu);
- sregs->efer = vcpu->shadow_efer;
+ sregs->efer = vcpu->arch.shadow_efer;
sregs->apic_base = kvm_get_apic_base(vcpu);
if (irqchip_in_kernel(vcpu->kvm)) {
set_bit(pending_vec,
(unsigned long *)sregs->interrupt_bitmap);
} else
- memcpy(sregs->interrupt_bitmap, vcpu->irq_pending,
+ memcpy(sregs->interrupt_bitmap, vcpu->arch.irq_pending,
sizeof sregs->interrupt_bitmap);
vcpu_put(vcpu);
dt.base = sregs->gdt.base;
kvm_x86_ops->set_gdt(vcpu, &dt);
- vcpu->cr2 = sregs->cr2;
- mmu_reset_needed |= vcpu->cr3 != sregs->cr3;
- vcpu->cr3 = sregs->cr3;
+ vcpu->arch.cr2 = sregs->cr2;
+ mmu_reset_needed |= vcpu->arch.cr3 != sregs->cr3;
+ vcpu->arch.cr3 = sregs->cr3;
set_cr8(vcpu, sregs->cr8);
- mmu_reset_needed |= vcpu->shadow_efer != sregs->efer;
+ mmu_reset_needed |= vcpu->arch.shadow_efer != sregs->efer;
#ifdef CONFIG_X86_64
kvm_x86_ops->set_efer(vcpu, sregs->efer);
#endif
kvm_x86_ops->decache_cr4_guest_bits(vcpu);
- mmu_reset_needed |= vcpu->cr0 != sregs->cr0;
- vcpu->cr0 = sregs->cr0;
+ mmu_reset_needed |= vcpu->arch.cr0 != sregs->cr0;
+ vcpu->arch.cr0 = sregs->cr0;
kvm_x86_ops->set_cr0(vcpu, sregs->cr0);
- mmu_reset_needed |= vcpu->cr4 != sregs->cr4;
+ mmu_reset_needed |= vcpu->arch.cr4 != sregs->cr4;
kvm_x86_ops->set_cr4(vcpu, sregs->cr4);
if (!is_long_mode(vcpu) && is_pae(vcpu))
- load_pdptrs(vcpu, vcpu->cr3);
+ load_pdptrs(vcpu, vcpu->arch.cr3);
if (mmu_reset_needed)
kvm_mmu_reset_context(vcpu);
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);
+ memcpy(vcpu->arch.irq_pending, sregs->interrupt_bitmap,
+ sizeof vcpu->arch.irq_pending);
+ vcpu->arch.irq_summary = 0;
+ for (i = 0; i < ARRAY_SIZE(vcpu->arch.irq_pending); ++i)
+ if (vcpu->arch.irq_pending[i])
+ __set_bit(i, &vcpu->arch.irq_summary);
} else {
max_bits = (sizeof sregs->interrupt_bitmap) << 3;
pending_vec = find_first_bit(
vcpu_load(vcpu);
mutex_lock(&vcpu->kvm->lock);
- gpa = vcpu->mmu.gva_to_gpa(vcpu, vaddr);
+ gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, vaddr);
tr->physical_address = gpa;
tr->valid = gpa != UNMAPPED_GVA;
tr->writeable = 1;
int kvm_arch_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->arch.guest_fx_image;
vcpu_load(vcpu);
int kvm_arch_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->arch.guest_fx_image;
vcpu_load(vcpu);
/* Initialize guest FPU by resetting ours and saving into guest's */
preempt_disable();
- fx_save(&vcpu->host_fx_image);
+ fx_save(&vcpu->arch.host_fx_image);
fpu_init();
- fx_save(&vcpu->guest_fx_image);
- fx_restore(&vcpu->host_fx_image);
+ fx_save(&vcpu->arch.guest_fx_image);
+ fx_restore(&vcpu->arch.host_fx_image);
preempt_enable();
- vcpu->cr0 |= X86_CR0_ET;
+ vcpu->arch.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,
+ vcpu->arch.guest_fx_image.mxcsr = 0x1f80;
+ memset((void *)&vcpu->arch.guest_fx_image + after_mxcsr_mask,
0, sizeof(struct i387_fxsave_struct) - after_mxcsr_mask);
}
EXPORT_SYMBOL_GPL(fx_init);
return;
vcpu->guest_fpu_loaded = 1;
- fx_save(&vcpu->host_fx_image);
- fx_restore(&vcpu->guest_fx_image);
+ fx_save(&vcpu->arch.host_fx_image);
+ fx_restore(&vcpu->arch.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->arch.guest_fx_image);
+ fx_restore(&vcpu->arch.host_fx_image);
++vcpu->stat.fpu_reload;
}
EXPORT_SYMBOL_GPL(kvm_put_guest_fpu);
struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
unsigned int id)
{
- int r;
- struct kvm_vcpu *vcpu = kvm_x86_ops->vcpu_create(kvm, id);
+ return kvm_x86_ops->vcpu_create(kvm, id);
+}
- if (IS_ERR(vcpu)) {
- r = -ENOMEM;
- goto fail;
- }
+int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
+{
+ int r;
/* We do fxsave: this must be aligned. */
- BUG_ON((unsigned long)&vcpu->host_fx_image & 0xF);
+ BUG_ON((unsigned long)&vcpu->arch.host_fx_image & 0xF);
vcpu_load(vcpu);
r = kvm_arch_vcpu_reset(vcpu);
if (r < 0)
goto free_vcpu;
- return vcpu;
+ return 0;
free_vcpu:
kvm_x86_ops->vcpu_free(vcpu);
-fail:
- return ERR_PTR(r);
+ return r;
}
void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
BUG_ON(vcpu->kvm == NULL);
kvm = vcpu->kvm;
- vcpu->mmu.root_hpa = INVALID_PAGE;
+ vcpu->arch.mmu.root_hpa = INVALID_PAGE;
if (!irqchip_in_kernel(kvm) || vcpu->vcpu_id == 0)
- vcpu->mp_state = VCPU_MP_STATE_RUNNABLE;
+ vcpu->arch.mp_state = VCPU_MP_STATE_RUNNABLE;
else
- vcpu->mp_state = VCPU_MP_STATE_UNINITIALIZED;
+ vcpu->arch.mp_state = VCPU_MP_STATE_UNINITIALIZED;
page = alloc_page(GFP_KERNEL | __GFP_ZERO);
if (!page) {
r = -ENOMEM;
goto fail;
}
- vcpu->pio_data = page_address(page);
+ vcpu->arch.pio_data = page_address(page);
r = kvm_mmu_create(vcpu);
if (r < 0)
fail_mmu_destroy:
kvm_mmu_destroy(vcpu);
fail_free_pio_data:
- free_page((unsigned long)vcpu->pio_data);
+ free_page((unsigned long)vcpu->arch.pio_data);
fail:
return r;
}
{
kvm_free_lapic(vcpu);
kvm_mmu_destroy(vcpu);
- free_page((unsigned long)vcpu->pio_data);
+ free_page((unsigned long)vcpu->arch.pio_data);
}
struct kvm *kvm_arch_create_vm(void)
if (!kvm)
return ERR_PTR(-ENOMEM);
- INIT_LIST_HEAD(&kvm->active_mmu_pages);
+ INIT_LIST_HEAD(&kvm->arch.active_mmu_pages);
return kvm;
}
void kvm_arch_destroy_vm(struct kvm *kvm)
{
- kfree(kvm->vpic);
- kfree(kvm->vioapic);
+ kfree(kvm->arch.vpic);
+ kfree(kvm->arch.vioapic);
kvm_free_vcpus(kvm);
kvm_free_physmem(kvm);
kfree(kvm);
}
+
+int kvm_arch_set_memory_region(struct kvm *kvm,
+ struct kvm_userspace_memory_region *mem,
+ struct kvm_memory_slot old,
+ int user_alloc)
+{
+ int npages = mem->memory_size >> PAGE_SHIFT;
+ struct kvm_memory_slot *memslot = &kvm->memslots[mem->slot];
+
+ /*To keep backward compatibility with older userspace,
+ *x86 needs to hanlde !user_alloc case.
+ */
+ if (!user_alloc) {
+ if (npages && !old.rmap) {
+ down_write(¤t->mm->mmap_sem);
+ memslot->userspace_addr = do_mmap(NULL, 0,
+ npages * PAGE_SIZE,
+ PROT_READ | PROT_WRITE,
+ MAP_SHARED | MAP_ANONYMOUS,
+ 0);
+ up_write(¤t->mm->mmap_sem);
+
+ if (IS_ERR((void *)memslot->userspace_addr))
+ return PTR_ERR((void *)memslot->userspace_addr);
+ } else {
+ if (!old.user_alloc && old.rmap) {
+ int ret;
+
+ down_write(¤t->mm->mmap_sem);
+ ret = do_munmap(current->mm, old.userspace_addr,
+ old.npages * PAGE_SIZE);
+ up_write(¤t->mm->mmap_sem);
+ if (ret < 0)
+ printk(KERN_WARNING
+ "kvm_vm_ioctl_set_memory_region: "
+ "failed to munmap memory\n");
+ }
+ }
+ }
+
+ if (!kvm->arch.n_requested_mmu_pages) {
+ unsigned int nr_mmu_pages = kvm_mmu_calculate_mmu_pages(kvm);
+ kvm_mmu_change_mmu_pages(kvm, nr_mmu_pages);
+ }
+
+ kvm_mmu_slot_remove_write_access(kvm, mem->slot);
+ kvm_flush_remote_tlbs(kvm);
+
+ return 0;
+}
+
+int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
+{
+ return vcpu->arch.mp_state == VCPU_MP_STATE_RUNNABLE
+ || vcpu->arch.mp_state == VCPU_MP_STATE_SIPI_RECEIVED;
+}
projects / linux-2.6-omap-h63xx.git / blobdiff