#include <linux/kvm.h>
#include <linux/module.h>
#include <linux/errno.h>
+#include <linux/magic.h>
#include <asm/processor.h>
#include <linux/percpu.h>
#include <linux/gfp.h>
static struct dentry *debugfs_dir;
-#define KVMFS_MAGIC 0x19700426
struct vfsmount *kvmfs_mnt;
#define MAX_IO_MSRS 256
#endif
+static long kvm_vcpu_ioctl(struct file *file, unsigned int ioctl,
+ unsigned long arg);
+
static struct inode *kvmfs_inode(struct file_operations *fops)
{
int error = -ENOMEM;
unsigned now;
unsigned offset;
hva_t guest_buf;
+ gfn_t gfn;
paddr = gva_to_hpa(vcpu, addr);
if (is_error_hpa(paddr))
break;
+ gfn = vcpu->mmu.gva_to_gpa(vcpu, addr) >> PAGE_SHIFT;
+ mark_page_dirty(vcpu->kvm, gfn);
guest_buf = (hva_t)kmap_atomic(
pfn_to_page(paddr >> PAGE_SHIFT), KM_USER0);
offset = addr & ~PAGE_MASK;
}
EXPORT_SYMBOL_GPL(kvm_write_guest);
-static int vcpu_slot(struct kvm_vcpu *vcpu)
+/*
+ * Switches to specified vcpu, until a matching vcpu_put()
+ */
+static void vcpu_load(struct kvm_vcpu *vcpu)
{
- return vcpu - vcpu->kvm->vcpus;
+ mutex_lock(&vcpu->mutex);
+ kvm_arch_ops->vcpu_load(vcpu);
}
/*
- * Switches to specified vcpu, until a matching vcpu_put()
+ * Switches to specified vcpu, until a matching vcpu_put(). Will return NULL
+ * if the slot is not populated.
*/
-static struct kvm_vcpu *vcpu_load(struct kvm *kvm, int vcpu_slot)
+static struct kvm_vcpu *vcpu_load_slot(struct kvm *kvm, int slot)
{
- struct kvm_vcpu *vcpu = &kvm->vcpus[vcpu_slot];
+ struct kvm_vcpu *vcpu = &kvm->vcpus[slot];
mutex_lock(&vcpu->mutex);
- if (unlikely(!vcpu->vmcs)) {
+ if (!vcpu->vmcs) {
mutex_unlock(&vcpu->mutex);
return NULL;
}
- return kvm_arch_ops->vcpu_load(vcpu);
+ kvm_arch_ops->vcpu_load(vcpu);
+ return vcpu;
}
static void vcpu_put(struct kvm_vcpu *vcpu)
kvm_free_physmem_slot(&kvm->memslots[i], NULL);
}
+static void free_pio_guest_pages(struct kvm_vcpu *vcpu)
+{
+ int i;
+
+ for (i = 0; i < 2; ++i)
+ if (vcpu->pio.guest_pages[i]) {
+ __free_page(vcpu->pio.guest_pages[i]);
+ vcpu->pio.guest_pages[i] = NULL;
+ }
+}
+
static void kvm_free_vcpu(struct kvm_vcpu *vcpu)
{
- if (!vcpu_load(vcpu->kvm, vcpu_slot(vcpu)))
+ if (!vcpu->vmcs)
return;
+ vcpu_load(vcpu);
kvm_mmu_destroy(vcpu);
vcpu_put(vcpu);
kvm_arch_ops->vcpu_free(vcpu);
+ free_page((unsigned long)vcpu->run);
+ vcpu->run = NULL;
+ free_page((unsigned long)vcpu->pio_data);
+ vcpu->pio_data = NULL;
+ free_pio_guest_pages(vcpu);
}
static void kvm_free_vcpus(struct kvm *kvm)
}
EXPORT_SYMBOL_GPL(fx_init);
-/*
- * Creates some virtual cpus. Good luck creating more than one.
- */
-static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, int n)
+static void do_remove_write_access(struct kvm_vcpu *vcpu, int slot)
{
- int r;
- struct kvm_vcpu *vcpu;
-
- r = -EINVAL;
- if (!valid_vcpu(n))
- goto out;
-
- vcpu = &kvm->vcpus[n];
-
- mutex_lock(&vcpu->mutex);
-
- if (vcpu->vmcs) {
- mutex_unlock(&vcpu->mutex);
- return -EEXIST;
- }
-
- vcpu->host_fx_image = (char*)ALIGN((hva_t)vcpu->fx_buf,
- FX_IMAGE_ALIGN);
- vcpu->guest_fx_image = vcpu->host_fx_image + FX_IMAGE_SIZE;
-
- r = kvm_arch_ops->vcpu_create(vcpu);
- if (r < 0)
- goto out_free_vcpus;
-
- r = kvm_mmu_create(vcpu);
- if (r < 0)
- goto out_free_vcpus;
-
- kvm_arch_ops->vcpu_load(vcpu);
- r = kvm_mmu_setup(vcpu);
- if (r >= 0)
- r = kvm_arch_ops->vcpu_setup(vcpu);
- vcpu_put(vcpu);
-
- if (r < 0)
- goto out_free_vcpus;
-
- return 0;
-
-out_free_vcpus:
- kvm_free_vcpu(vcpu);
- mutex_unlock(&vcpu->mutex);
-out:
- return r;
+ spin_lock(&vcpu->kvm->lock);
+ kvm_mmu_slot_remove_write_access(vcpu, slot);
+ spin_unlock(&vcpu->kvm->lock);
}
/*
for (i = 0; i < KVM_MAX_VCPUS; ++i) {
struct kvm_vcpu *vcpu;
- vcpu = vcpu_load(kvm, i);
+ vcpu = vcpu_load_slot(kvm, i);
if (!vcpu)
continue;
+ if (new.flags & KVM_MEM_LOG_DIRTY_PAGES)
+ do_remove_write_access(vcpu, mem->slot);
kvm_mmu_reset_context(vcpu);
vcpu_put(vcpu);
}
return r;
}
-static void do_remove_write_access(struct kvm_vcpu *vcpu, int slot)
-{
- spin_lock(&vcpu->kvm->lock);
- kvm_mmu_slot_remove_write_access(vcpu, slot);
- spin_unlock(&vcpu->kvm->lock);
-}
-
/*
* Get (and clear) the dirty memory log for a memory slot.
*/
if (!memslot->dirty_bitmap)
goto out;
- n = ALIGN(memslot->npages, 8) / 8;
+ n = ALIGN(memslot->npages, BITS_PER_LONG) / 8;
- for (i = 0; !any && i < n; ++i)
+ for (i = 0; !any && i < n/sizeof(long); ++i)
any = memslot->dirty_bitmap[i];
r = -EFAULT;
if (any) {
cleared = 0;
for (i = 0; i < KVM_MAX_VCPUS; ++i) {
- struct kvm_vcpu *vcpu = vcpu_load(kvm, i);
+ struct kvm_vcpu *vcpu;
+ vcpu = vcpu_load_slot(kvm, i);
if (!vcpu)
continue;
if (!cleared) {
return 0;
page = gfn_to_page(m, gpa >> PAGE_SHIFT);
kvm_mmu_pre_write(vcpu, gpa, bytes);
+ mark_page_dirty(vcpu->kvm, gpa >> PAGE_SHIFT);
virt = kmap_atomic(page, KM_USER0);
memcpy(virt + offset_in_page(gpa), &val, bytes);
kunmap_atomic(virt, KM_USER0);
{
unsigned long nr, a0, a1, a2, a3, a4, a5, ret;
- kvm_arch_ops->decache_regs(vcpu);
+ kvm_arch_ops->cache_regs(vcpu);
ret = -KVM_EINVAL;
#ifdef CONFIG_X86_64
if (is_long_mode(vcpu)) {
}
switch (nr) {
default:
- ;
+ 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_arch_ops->decache_regs(vcpu);
+ return 0;
}
vcpu->regs[VCPU_REGS_RAX] = ret;
- kvm_arch_ops->cache_regs(vcpu);
+ kvm_arch_ops->decache_regs(vcpu);
return 1;
}
EXPORT_SYMBOL_GPL(kvm_hypercall);
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_atomic(para_state_page, KM_USER0);
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_arch_ops->patch_hypercall(vcpu, hypercall);
printk(KERN_WARNING "%s: MSR_IA32_MC0_STATUS 0x%llx, nop\n",
__FUNCTION__, data);
break;
+ case MSR_IA32_MCG_STATUS:
+ printk(KERN_WARNING "%s: MSR_IA32_MCG_STATUS 0x%llx, nop\n",
+ __FUNCTION__, data);
+ break;
case MSR_IA32_UCODE_REV:
case MSR_IA32_UCODE_WRITE:
case 0x200 ... 0x2ff: /* MTRRs */
{
vcpu_put(vcpu);
cond_resched();
- /* Cannot fail - no vcpu unplug yet. */
- vcpu_load(vcpu->kvm, vcpu_slot(vcpu));
+ vcpu_load(vcpu);
}
EXPORT_SYMBOL_GPL(kvm_resched);
}
EXPORT_SYMBOL_GPL(save_msrs);
-static int kvm_vm_ioctl_run(struct kvm *kvm, struct kvm_run *kvm_run)
+void kvm_emulate_cpuid(struct kvm_vcpu *vcpu)
{
- struct kvm_vcpu *vcpu;
+ int i;
+ u32 function;
+ struct kvm_cpuid_entry *e, *best;
+
+ kvm_arch_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;
+ best = NULL;
+ for (i = 0; i < vcpu->cpuid_nent; ++i) {
+ e = &vcpu->cpuid_entries[i];
+ if (e->function == function) {
+ best = e;
+ break;
+ }
+ /*
+ * Both basic or both extended?
+ */
+ if (((e->function ^ function) & 0x80000000) == 0)
+ if (!best || e->function > best->function)
+ 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;
+ }
+ kvm_arch_ops->decache_regs(vcpu);
+ kvm_arch_ops->skip_emulated_instruction(vcpu);
+}
+EXPORT_SYMBOL_GPL(kvm_emulate_cpuid);
+
+static int pio_copy_data(struct kvm_vcpu *vcpu)
+{
+ void *p = vcpu->pio_data;
+ void *q;
+ unsigned bytes;
+ int nr_pages = vcpu->pio.guest_pages[1] ? 2 : 1;
+
+ kvm_arch_ops->vcpu_put(vcpu);
+ q = vmap(vcpu->pio.guest_pages, nr_pages, VM_READ|VM_WRITE,
+ PAGE_KERNEL);
+ if (!q) {
+ kvm_arch_ops->vcpu_load(vcpu);
+ free_pio_guest_pages(vcpu);
+ return -ENOMEM;
+ }
+ q += vcpu->pio.guest_page_offset;
+ bytes = vcpu->pio.size * vcpu->pio.cur_count;
+ if (vcpu->pio.in)
+ memcpy(q, p, bytes);
+ else
+ memcpy(p, q, bytes);
+ q -= vcpu->pio.guest_page_offset;
+ vunmap(q);
+ kvm_arch_ops->vcpu_load(vcpu);
+ free_pio_guest_pages(vcpu);
+ return 0;
+}
+
+static int complete_pio(struct kvm_vcpu *vcpu)
+{
+ struct kvm_pio_request *io = &vcpu->pio;
+ long delta;
int r;
- if (!valid_vcpu(kvm_run->vcpu))
- return -EINVAL;
+ kvm_arch_ops->cache_regs(vcpu);
- vcpu = vcpu_load(kvm, kvm_run->vcpu);
- if (!vcpu)
- return -ENOENT;
+ if (!io->string) {
+ if (io->in)
+ memcpy(&vcpu->regs[VCPU_REGS_RAX], vcpu->pio_data,
+ io->size);
+ } else {
+ if (io->in) {
+ r = pio_copy_data(vcpu);
+ if (r) {
+ kvm_arch_ops->cache_regs(vcpu);
+ return r;
+ }
+ }
- /* re-sync apic's tpr */
- vcpu->cr8 = kvm_run->cr8;
+ delta = 1;
+ if (io->rep) {
+ delta *= io->cur_count;
+ /*
+ * The size of the register should really depend on
+ * current address size.
+ */
+ vcpu->regs[VCPU_REGS_RCX] -= delta;
+ }
+ if (io->down)
+ delta = -delta;
+ delta *= io->size;
+ if (io->in)
+ vcpu->regs[VCPU_REGS_RDI] += delta;
+ else
+ vcpu->regs[VCPU_REGS_RSI] += delta;
+ }
+
+ vcpu->run->io_completed = 0;
+
+ kvm_arch_ops->decache_regs(vcpu);
+
+ io->count -= io->cur_count;
+ io->cur_count = 0;
- if (kvm_run->emulated) {
+ if (!io->count)
kvm_arch_ops->skip_emulated_instruction(vcpu);
- kvm_run->emulated = 0;
+ return 0;
+}
+
+int kvm_setup_pio(struct kvm_vcpu *vcpu, struct kvm_run *run, int in,
+ int size, unsigned long count, int string, int down,
+ gva_t address, int rep, unsigned port)
+{
+ unsigned now, in_page;
+ int i;
+ int nr_pages = 1;
+ struct page *page;
+
+ vcpu->run->exit_reason = KVM_EXIT_IO;
+ vcpu->run->io.direction = in ? KVM_EXIT_IO_IN : KVM_EXIT_IO_OUT;
+ vcpu->run->io.size = size;
+ vcpu->run->io.data_offset = KVM_PIO_PAGE_OFFSET * PAGE_SIZE;
+ vcpu->run->io.count = count;
+ vcpu->run->io.port = port;
+ vcpu->pio.count = count;
+ vcpu->pio.cur_count = count;
+ vcpu->pio.size = size;
+ vcpu->pio.in = in;
+ vcpu->pio.string = string;
+ vcpu->pio.down = down;
+ vcpu->pio.guest_page_offset = offset_in_page(address);
+ vcpu->pio.rep = rep;
+
+ if (!string) {
+ kvm_arch_ops->cache_regs(vcpu);
+ memcpy(vcpu->pio_data, &vcpu->regs[VCPU_REGS_RAX], 4);
+ kvm_arch_ops->decache_regs(vcpu);
+ return 0;
+ }
+
+ if (!count) {
+ kvm_arch_ops->skip_emulated_instruction(vcpu);
+ return 1;
+ }
+
+ now = min(count, PAGE_SIZE / size);
+
+ if (!down)
+ in_page = PAGE_SIZE - offset_in_page(address);
+ else
+ in_page = offset_in_page(address) + size;
+ now = min(count, (unsigned long)in_page / size);
+ if (!now) {
+ /*
+ * String I/O straddles page boundary. Pin two guest pages
+ * so that we satisfy atomicity constraints. Do just one
+ * transaction to avoid complexity.
+ */
+ nr_pages = 2;
+ now = 1;
+ }
+ if (down) {
+ /*
+ * String I/O in reverse. Yuck. Kill the guest, fix later.
+ */
+ printk(KERN_ERR "kvm: guest string pio down\n");
+ inject_gp(vcpu);
+ return 1;
+ }
+ vcpu->run->io.count = now;
+ vcpu->pio.cur_count = now;
+
+ for (i = 0; i < nr_pages; ++i) {
+ spin_lock(&vcpu->kvm->lock);
+ page = gva_to_page(vcpu, address + i * PAGE_SIZE);
+ if (page)
+ get_page(page);
+ vcpu->pio.guest_pages[i] = page;
+ spin_unlock(&vcpu->kvm->lock);
+ if (!page) {
+ inject_gp(vcpu);
+ free_pio_guest_pages(vcpu);
+ return 1;
+ }
}
- if (kvm_run->mmio_completed) {
- memcpy(vcpu->mmio_data, kvm_run->mmio.data, 8);
- vcpu->mmio_read_completed = 1;
+ if (!vcpu->pio.in)
+ return pio_copy_data(vcpu);
+ return 0;
+}
+EXPORT_SYMBOL_GPL(kvm_setup_pio);
+
+static int kvm_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+{
+ int r;
+ sigset_t sigsaved;
+
+ vcpu_load(vcpu);
+
+ if (vcpu->sigset_active)
+ sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved);
+
+ /* re-sync apic's tpr */
+ vcpu->cr8 = kvm_run->cr8;
+
+ if (kvm_run->io_completed) {
+ if (vcpu->pio.cur_count) {
+ r = complete_pio(vcpu);
+ if (r)
+ goto out;
+ } else {
+ memcpy(vcpu->mmio_data, kvm_run->mmio.data, 8);
+ vcpu->mmio_read_completed = 1;
+ }
}
vcpu->mmio_needed = 0;
+ if (kvm_run->exit_reason == KVM_EXIT_HYPERCALL) {
+ kvm_arch_ops->cache_regs(vcpu);
+ vcpu->regs[VCPU_REGS_RAX] = kvm_run->hypercall.ret;
+ kvm_arch_ops->decache_regs(vcpu);
+ }
+
r = kvm_arch_ops->run(vcpu, kvm_run);
+out:
+ if (vcpu->sigset_active)
+ sigprocmask(SIG_SETMASK, &sigsaved, NULL);
+
vcpu_put(vcpu);
return r;
}
-static int kvm_vm_ioctl_get_regs(struct kvm *kvm, struct kvm_regs *regs)
+static int kvm_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu,
+ struct kvm_regs *regs)
{
- struct kvm_vcpu *vcpu;
-
- if (!valid_vcpu(regs->vcpu))
- return -EINVAL;
-
- vcpu = vcpu_load(kvm, regs->vcpu);
- if (!vcpu)
- return -ENOENT;
+ vcpu_load(vcpu);
kvm_arch_ops->cache_regs(vcpu);
return 0;
}
-static int kvm_vm_ioctl_set_regs(struct kvm *kvm, struct kvm_regs *regs)
+static int kvm_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu,
+ struct kvm_regs *regs)
{
- struct kvm_vcpu *vcpu;
-
- if (!valid_vcpu(regs->vcpu))
- return -EINVAL;
-
- vcpu = vcpu_load(kvm, regs->vcpu);
- if (!vcpu)
- return -ENOENT;
+ vcpu_load(vcpu);
vcpu->regs[VCPU_REGS_RAX] = regs->rax;
vcpu->regs[VCPU_REGS_RBX] = regs->rbx;
return kvm_arch_ops->get_segment(vcpu, var, seg);
}
-static int kvm_vm_ioctl_get_sregs(struct kvm *kvm, struct kvm_sregs *sregs)
+static int kvm_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
+ struct kvm_sregs *sregs)
{
- struct kvm_vcpu *vcpu;
struct descriptor_table dt;
- if (!valid_vcpu(sregs->vcpu))
- return -EINVAL;
- vcpu = vcpu_load(kvm, sregs->vcpu);
- if (!vcpu)
- return -ENOENT;
+ vcpu_load(vcpu);
get_segment(vcpu, &sregs->cs, VCPU_SREG_CS);
get_segment(vcpu, &sregs->ds, VCPU_SREG_DS);
return kvm_arch_ops->set_segment(vcpu, var, seg);
}
-static int kvm_vm_ioctl_set_sregs(struct kvm *kvm, struct kvm_sregs *sregs)
+static int kvm_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
+ struct kvm_sregs *sregs)
{
- struct kvm_vcpu *vcpu;
int mmu_reset_needed = 0;
int i;
struct descriptor_table dt;
- if (!valid_vcpu(sregs->vcpu))
- return -EINVAL;
- vcpu = vcpu_load(kvm, sregs->vcpu);
- if (!vcpu)
- return -ENOENT;
-
- set_segment(vcpu, &sregs->cs, VCPU_SREG_CS);
- set_segment(vcpu, &sregs->ds, VCPU_SREG_DS);
- set_segment(vcpu, &sregs->es, VCPU_SREG_ES);
- set_segment(vcpu, &sregs->fs, VCPU_SREG_FS);
- set_segment(vcpu, &sregs->gs, VCPU_SREG_GS);
- set_segment(vcpu, &sregs->ss, VCPU_SREG_SS);
-
- set_segment(vcpu, &sregs->tr, VCPU_SREG_TR);
- set_segment(vcpu, &sregs->ldt, VCPU_SREG_LDTR);
+ vcpu_load(vcpu);
dt.limit = sregs->idt.limit;
dt.base = sregs->idt.base;
kvm_arch_ops->decache_cr0_cr4_guest_bits(vcpu);
mmu_reset_needed |= vcpu->cr0 != sregs->cr0;
- kvm_arch_ops->set_cr0_no_modeswitch(vcpu, sregs->cr0);
+ kvm_arch_ops->set_cr0(vcpu, sregs->cr0);
mmu_reset_needed |= vcpu->cr4 != sregs->cr4;
kvm_arch_ops->set_cr4(vcpu, sregs->cr4);
if (vcpu->irq_pending[i])
__set_bit(i, &vcpu->irq_summary);
+ set_segment(vcpu, &sregs->cs, VCPU_SREG_CS);
+ set_segment(vcpu, &sregs->ds, VCPU_SREG_DS);
+ set_segment(vcpu, &sregs->es, VCPU_SREG_ES);
+ set_segment(vcpu, &sregs->fs, VCPU_SREG_FS);
+ set_segment(vcpu, &sregs->gs, VCPU_SREG_GS);
+ set_segment(vcpu, &sregs->ss, VCPU_SREG_SS);
+
+ set_segment(vcpu, &sregs->tr, VCPU_SREG_TR);
+ set_segment(vcpu, &sregs->ldt, VCPU_SREG_LDTR);
+
vcpu_put(vcpu);
return 0;
*
* @return number of msrs set successfully.
*/
-static int __msr_io(struct kvm *kvm, struct kvm_msrs *msrs,
+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))
{
- struct kvm_vcpu *vcpu;
int i;
- if (!valid_vcpu(msrs->vcpu))
- return -EINVAL;
-
- vcpu = vcpu_load(kvm, msrs->vcpu);
- if (!vcpu)
- return -ENOENT;
+ vcpu_load(vcpu);
for (i = 0; i < msrs->nmsrs; ++i)
if (do_msr(vcpu, entries[i].index, &entries[i].data))
*
* @return number of msrs set successfully.
*/
-static int msr_io(struct kvm *kvm, struct kvm_msrs __user *user_msrs,
+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)
if (copy_from_user(entries, user_msrs->entries, size))
goto out_free;
- r = n = __msr_io(kvm, &msrs, entries, do_msr);
+ r = n = __msr_io(vcpu, &msrs, entries, do_msr);
if (r < 0)
goto out_free;
/*
* Translate a guest virtual address to a guest physical address.
*/
-static int kvm_vm_ioctl_translate(struct kvm *kvm, struct kvm_translation *tr)
+static int kvm_vcpu_ioctl_translate(struct kvm_vcpu *vcpu,
+ struct kvm_translation *tr)
{
unsigned long vaddr = tr->linear_address;
- struct kvm_vcpu *vcpu;
gpa_t gpa;
- vcpu = vcpu_load(kvm, tr->vcpu);
- if (!vcpu)
- return -ENOENT;
- spin_lock(&kvm->lock);
+ vcpu_load(vcpu);
+ spin_lock(&vcpu->kvm->lock);
gpa = vcpu->mmu.gva_to_gpa(vcpu, vaddr);
tr->physical_address = gpa;
tr->valid = gpa != UNMAPPED_GVA;
tr->writeable = 1;
tr->usermode = 0;
- spin_unlock(&kvm->lock);
+ spin_unlock(&vcpu->kvm->lock);
vcpu_put(vcpu);
return 0;
}
-static int kvm_vm_ioctl_interrupt(struct kvm *kvm, struct kvm_interrupt *irq)
+static int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu,
+ struct kvm_interrupt *irq)
{
- struct kvm_vcpu *vcpu;
-
- if (!valid_vcpu(irq->vcpu))
- return -EINVAL;
if (irq->irq < 0 || irq->irq >= 256)
return -EINVAL;
- vcpu = vcpu_load(kvm, irq->vcpu);
- if (!vcpu)
- return -ENOENT;
+ vcpu_load(vcpu);
set_bit(irq->irq, vcpu->irq_pending);
set_bit(irq->irq / BITS_PER_LONG, &vcpu->irq_summary);
return 0;
}
-static int kvm_vm_ioctl_debug_guest(struct kvm *kvm,
- struct kvm_debug_guest *dbg)
+static int kvm_vcpu_ioctl_debug_guest(struct kvm_vcpu *vcpu,
+ struct kvm_debug_guest *dbg)
{
- struct kvm_vcpu *vcpu;
int r;
- if (!valid_vcpu(dbg->vcpu))
- return -EINVAL;
- vcpu = vcpu_load(kvm, dbg->vcpu);
- if (!vcpu)
- return -ENOENT;
+ vcpu_load(vcpu);
r = kvm_arch_ops->set_guest_debug(vcpu, dbg);
return r;
}
-static long kvm_vm_ioctl(struct file *filp,
- unsigned int ioctl, unsigned long arg)
+static struct page *kvm_vcpu_nopage(struct vm_area_struct *vma,
+ unsigned long address,
+ int *type)
{
- struct kvm *kvm = filp->private_data;
+ struct kvm_vcpu *vcpu = vma->vm_file->private_data;
+ unsigned long pgoff;
+ struct page *page;
+
+ *type = VM_FAULT_MINOR;
+ pgoff = ((address - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;
+ if (pgoff == 0)
+ page = virt_to_page(vcpu->run);
+ else if (pgoff == KVM_PIO_PAGE_OFFSET)
+ page = virt_to_page(vcpu->pio_data);
+ else
+ return NOPAGE_SIGBUS;
+ get_page(page);
+ return page;
+}
+
+static struct vm_operations_struct kvm_vcpu_vm_ops = {
+ .nopage = kvm_vcpu_nopage,
+};
+
+static int kvm_vcpu_mmap(struct file *file, struct vm_area_struct *vma)
+{
+ vma->vm_ops = &kvm_vcpu_vm_ops;
+ return 0;
+}
+
+static int kvm_vcpu_release(struct inode *inode, struct file *filp)
+{
+ struct kvm_vcpu *vcpu = filp->private_data;
+
+ fput(vcpu->kvm->filp);
+ return 0;
+}
+
+static struct file_operations kvm_vcpu_fops = {
+ .release = kvm_vcpu_release,
+ .unlocked_ioctl = kvm_vcpu_ioctl,
+ .compat_ioctl = kvm_vcpu_ioctl,
+ .mmap = kvm_vcpu_mmap,
+};
+
+/*
+ * Allocates an inode for the vcpu.
+ */
+static int create_vcpu_fd(struct kvm_vcpu *vcpu)
+{
+ int fd, r;
+ struct inode *inode;
+ struct file *file;
+
+ atomic_inc(&vcpu->kvm->filp->f_count);
+ inode = kvmfs_inode(&kvm_vcpu_fops);
+ if (IS_ERR(inode)) {
+ r = PTR_ERR(inode);
+ goto out1;
+ }
+
+ file = kvmfs_file(inode, vcpu);
+ if (IS_ERR(file)) {
+ r = PTR_ERR(file);
+ goto out2;
+ }
+
+ r = get_unused_fd();
+ if (r < 0)
+ goto out3;
+ fd = r;
+ fd_install(fd, file);
+
+ return fd;
+
+out3:
+ fput(file);
+out2:
+ iput(inode);
+out1:
+ fput(vcpu->kvm->filp);
+ return r;
+}
+
+/*
+ * Creates some virtual cpus. Good luck creating more than one.
+ */
+static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, int n)
+{
+ int r;
+ struct kvm_vcpu *vcpu;
+ struct page *page;
+
+ r = -EINVAL;
+ if (!valid_vcpu(n))
+ goto out;
+
+ vcpu = &kvm->vcpus[n];
+
+ mutex_lock(&vcpu->mutex);
+
+ if (vcpu->vmcs) {
+ mutex_unlock(&vcpu->mutex);
+ return -EEXIST;
+ }
+
+ page = alloc_page(GFP_KERNEL | __GFP_ZERO);
+ r = -ENOMEM;
+ if (!page)
+ goto out_unlock;
+ vcpu->run = page_address(page);
+
+ page = alloc_page(GFP_KERNEL | __GFP_ZERO);
+ r = -ENOMEM;
+ if (!page)
+ goto out_free_run;
+ vcpu->pio_data = page_address(page);
+
+ vcpu->host_fx_image = (char*)ALIGN((hva_t)vcpu->fx_buf,
+ FX_IMAGE_ALIGN);
+ vcpu->guest_fx_image = vcpu->host_fx_image + FX_IMAGE_SIZE;
+
+ r = kvm_arch_ops->vcpu_create(vcpu);
+ if (r < 0)
+ goto out_free_vcpus;
+
+ r = kvm_mmu_create(vcpu);
+ if (r < 0)
+ goto out_free_vcpus;
+
+ kvm_arch_ops->vcpu_load(vcpu);
+ r = kvm_mmu_setup(vcpu);
+ if (r >= 0)
+ r = kvm_arch_ops->vcpu_setup(vcpu);
+ vcpu_put(vcpu);
+
+ if (r < 0)
+ goto out_free_vcpus;
+
+ r = create_vcpu_fd(vcpu);
+ if (r < 0)
+ goto out_free_vcpus;
+
+ return r;
+
+out_free_vcpus:
+ kvm_free_vcpu(vcpu);
+out_free_run:
+ free_page((unsigned long)vcpu->run);
+ vcpu->run = NULL;
+out_unlock:
+ mutex_unlock(&vcpu->mutex);
+out:
+ return r;
+}
+
+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;
+ return 0;
+
+out:
+ return r;
+}
+
+static int kvm_vcpu_ioctl_set_sigmask(struct kvm_vcpu *vcpu, sigset_t *sigset)
+{
+ if (sigset) {
+ sigdelsetmask(sigset, sigmask(SIGKILL)|sigmask(SIGSTOP));
+ vcpu->sigset_active = 1;
+ vcpu->sigset = *sigset;
+ } else
+ vcpu->sigset_active = 0;
+ 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;
switch (ioctl) {
- case KVM_CREATE_VCPU:
- r = kvm_vm_ioctl_create_vcpu(kvm, arg);
- if (r)
- goto out;
- break;
- case KVM_RUN: {
- struct kvm_run kvm_run;
-
- r = -EFAULT;
- if (copy_from_user(&kvm_run, argp, sizeof kvm_run))
- goto out;
- r = kvm_vm_ioctl_run(kvm, &kvm_run);
- if (r < 0 && r != -EINTR)
- goto out;
- if (copy_to_user(argp, &kvm_run, sizeof kvm_run)) {
- r = -EFAULT;
+ case KVM_RUN:
+ r = -EINVAL;
+ if (arg)
goto out;
- }
+ r = kvm_vcpu_ioctl_run(vcpu, vcpu->run);
break;
- }
case KVM_GET_REGS: {
struct kvm_regs kvm_regs;
- r = -EFAULT;
- if (copy_from_user(&kvm_regs, argp, sizeof kvm_regs))
- goto out;
- r = kvm_vm_ioctl_get_regs(kvm, &kvm_regs);
+ memset(&kvm_regs, 0, sizeof kvm_regs);
+ r = kvm_vcpu_ioctl_get_regs(vcpu, &kvm_regs);
if (r)
goto out;
r = -EFAULT;
r = -EFAULT;
if (copy_from_user(&kvm_regs, argp, sizeof kvm_regs))
goto out;
- r = kvm_vm_ioctl_set_regs(kvm, &kvm_regs);
+ r = kvm_vcpu_ioctl_set_regs(vcpu, &kvm_regs);
if (r)
goto out;
r = 0;
case KVM_GET_SREGS: {
struct kvm_sregs kvm_sregs;
- r = -EFAULT;
- if (copy_from_user(&kvm_sregs, argp, sizeof kvm_sregs))
- goto out;
- r = kvm_vm_ioctl_get_sregs(kvm, &kvm_sregs);
+ memset(&kvm_sregs, 0, sizeof kvm_sregs);
+ r = kvm_vcpu_ioctl_get_sregs(vcpu, &kvm_sregs);
if (r)
goto out;
r = -EFAULT;
r = -EFAULT;
if (copy_from_user(&kvm_sregs, argp, sizeof kvm_sregs))
goto out;
- r = kvm_vm_ioctl_set_sregs(kvm, &kvm_sregs);
+ r = kvm_vcpu_ioctl_set_sregs(vcpu, &kvm_sregs);
if (r)
goto out;
r = 0;
r = -EFAULT;
if (copy_from_user(&tr, argp, sizeof tr))
goto out;
- r = kvm_vm_ioctl_translate(kvm, &tr);
+ r = kvm_vcpu_ioctl_translate(vcpu, &tr);
if (r)
goto out;
r = -EFAULT;
r = -EFAULT;
if (copy_from_user(&irq, argp, sizeof irq))
goto out;
- r = kvm_vm_ioctl_interrupt(kvm, &irq);
+ r = kvm_vcpu_ioctl_interrupt(vcpu, &irq);
if (r)
goto out;
r = 0;
r = -EFAULT;
if (copy_from_user(&dbg, argp, sizeof dbg))
goto out;
- r = kvm_vm_ioctl_debug_guest(kvm, &dbg);
+ r = kvm_vcpu_ioctl_debug_guest(vcpu, &dbg);
if (r)
goto out;
r = 0;
break;
}
+ case KVM_GET_MSRS:
+ r = msr_io(vcpu, argp, 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;
+ sigset_t sigset, *p;
+
+ p = NULL;
+ if (argp) {
+ r = -EFAULT;
+ if (copy_from_user(&kvm_sigmask, argp,
+ sizeof kvm_sigmask))
+ goto out;
+ r = -EINVAL;
+ if (kvm_sigmask.len != sizeof sigset)
+ goto out;
+ r = -EFAULT;
+ if (copy_from_user(&sigset, sigmask_arg->sigset,
+ sizeof sigset))
+ goto out;
+ p = &sigset;
+ }
+ r = kvm_vcpu_ioctl_set_sigmask(vcpu, &sigset);
+ break;
+ }
+ default:
+ ;
+ }
+out:
+ return r;
+}
+
+static long kvm_vm_ioctl(struct file *filp,
+ unsigned int ioctl, unsigned long arg)
+{
+ struct kvm *kvm = filp->private_data;
+ void __user *argp = (void __user *)arg;
+ int r = -EINVAL;
+
+ switch (ioctl) {
+ case KVM_CREATE_VCPU:
+ r = kvm_vm_ioctl_create_vcpu(kvm, arg);
+ if (r < 0)
+ goto out;
+ break;
case KVM_SET_MEMORY_REGION: {
struct kvm_memory_region kvm_mem;
goto out;
break;
}
- case KVM_GET_MSRS:
- r = msr_io(kvm, argp, get_msr, 1);
- break;
- case KVM_SET_MSRS:
- r = msr_io(kvm, argp, do_set_msr, 0);
- break;
default:
;
}
r = PTR_ERR(file);
goto out3;
}
+ kvm->filp = file;
r = get_unused_fd();
if (r < 0)
unsigned int ioctl, unsigned long arg)
{
void __user *argp = (void __user *)arg;
- int r = -EINVAL;
+ long r = -EINVAL;
switch (ioctl) {
case KVM_GET_API_VERSION:
+ r = -EINVAL;
+ if (arg)
+ goto out;
r = KVM_API_VERSION;
break;
case KVM_CREATE_VM:
+ r = -EINVAL;
+ if (arg)
+ goto out;
r = kvm_dev_ioctl_create_vm();
break;
case KVM_GET_MSR_INDEX_LIST: {
r = 0;
break;
}
+ case KVM_CHECK_EXTENSION:
+ /*
+ * No extensions defined at present.
+ */
+ r = 0;
+ break;
+ case KVM_GET_VCPU_MMAP_SIZE:
+ r = -EINVAL;
+ if (arg)
+ goto out;
+ r = 2 * PAGE_SIZE;
+ break;
default:
;
}
};
static struct miscdevice kvm_dev = {
- MISC_DYNAMIC_MINOR,
+ KVM_MINOR,
"kvm",
&kvm_chardev_ops,
};
static int kvmfs_get_sb(struct file_system_type *fs_type, int flags,
const char *dev_name, void *data, struct vfsmount *mnt)
{
- return get_sb_pseudo(fs_type, "kvm:", NULL, KVMFS_MAGIC, mnt);
+ return get_sb_pseudo(fs_type, "kvm:", NULL, KVMFS_SUPER_MAGIC, mnt);
}
static struct file_system_type kvm_fs_type = {
r = kvm_arch_ops->hardware_setup();
if (r < 0)
- return r;
+ goto out;
on_each_cpu(kvm_arch_ops->hardware_enable, NULL, 0, 1);
r = register_cpu_notifier(&kvm_cpu_notifier);
out_free_1:
on_each_cpu(kvm_arch_ops->hardware_disable, NULL, 0, 1);
kvm_arch_ops->hardware_unsetup();
+out:
+ kvm_arch_ops = NULL;
return r;
}
bad_page_address = page_to_pfn(bad_page) << PAGE_SHIFT;
memset(__va(bad_page_address), 0, PAGE_SIZE);
- return r;
+ return 0;
out:
kvm_exit_debug();
projects / linux-2.6-omap-h63xx.git / blobdiff