*/
#include "kvm.h"
+#include "x86_emulate.h"
+#include "segment_descriptor.h"
#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>
-#include <asm/msr.h>
#include <linux/mm.h>
#include <linux/miscdevice.h>
#include <linux/vmalloc.h>
-#include <asm/uaccess.h>
#include <linux/reboot.h>
-#include <asm/io.h>
#include <linux/debugfs.h>
#include <linux/highmem.h>
#include <linux/file.h>
-#include <asm/desc.h>
#include <linux/sysdev.h>
#include <linux/cpu.h>
-#include <linux/file.h>
-#include <linux/fs.h>
-#include <linux/mount.h>
+#include <linux/sched.h>
+#include <linux/cpumask.h>
+#include <linux/smp.h>
+#include <linux/anon_inodes.h>
-#include "x86_emulate.h"
-#include "segment_descriptor.h"
+#include <asm/processor.h>
+#include <asm/msr.h>
+#include <asm/io.h>
+#include <asm/uaccess.h>
+#include <asm/desc.h>
MODULE_AUTHOR("Qumranet");
MODULE_LICENSE("GPL");
static DEFINE_SPINLOCK(kvm_lock);
static LIST_HEAD(vm_list);
+static cpumask_t cpus_hardware_enabled;
+
struct kvm_arch_ops *kvm_arch_ops;
-struct kvm_stat kvm_stat;
-EXPORT_SYMBOL_GPL(kvm_stat);
+
+static void hardware_disable(void *ignored);
+
+#define STAT_OFFSET(x) offsetof(struct kvm_vcpu, stat.x)
static struct kvm_stats_debugfs_item {
const char *name;
- u32 *data;
+ int offset;
struct dentry *dentry;
} debugfs_entries[] = {
- { "pf_fixed", &kvm_stat.pf_fixed },
- { "pf_guest", &kvm_stat.pf_guest },
- { "tlb_flush", &kvm_stat.tlb_flush },
- { "invlpg", &kvm_stat.invlpg },
- { "exits", &kvm_stat.exits },
- { "io_exits", &kvm_stat.io_exits },
- { "mmio_exits", &kvm_stat.mmio_exits },
- { "signal_exits", &kvm_stat.signal_exits },
- { "irq_window", &kvm_stat.irq_window_exits },
- { "halt_exits", &kvm_stat.halt_exits },
- { "request_irq", &kvm_stat.request_irq_exits },
- { "irq_exits", &kvm_stat.irq_exits },
- { NULL, NULL }
+ { "pf_fixed", STAT_OFFSET(pf_fixed) },
+ { "pf_guest", STAT_OFFSET(pf_guest) },
+ { "tlb_flush", STAT_OFFSET(tlb_flush) },
+ { "invlpg", STAT_OFFSET(invlpg) },
+ { "exits", STAT_OFFSET(exits) },
+ { "io_exits", STAT_OFFSET(io_exits) },
+ { "mmio_exits", STAT_OFFSET(mmio_exits) },
+ { "signal_exits", STAT_OFFSET(signal_exits) },
+ { "irq_window", STAT_OFFSET(irq_window_exits) },
+ { "halt_exits", STAT_OFFSET(halt_exits) },
+ { "request_irq", STAT_OFFSET(request_irq_exits) },
+ { "irq_exits", STAT_OFFSET(irq_exits) },
+ { "light_exits", STAT_OFFSET(light_exits) },
+ { "efer_reload", STAT_OFFSET(efer_reload) },
+ { NULL }
};
static struct dentry *debugfs_dir;
-struct vfsmount *kvmfs_mnt;
-
#define MAX_IO_MSRS 256
#define CR0_RESEVED_BITS 0xffffffff1ffaffc0ULL
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;
- struct inode *inode = new_inode(kvmfs_mnt->mnt_sb);
-
- if (!inode)
- goto eexit_1;
-
- inode->i_fop = fops;
-
- /*
- * Mark the inode dirty from the very beginning,
- * that way it will never be moved to the dirty
- * list because mark_inode_dirty() will think
- * that it already _is_ on the dirty list.
- */
- inode->i_state = I_DIRTY;
- inode->i_mode = S_IRUSR | S_IWUSR;
- inode->i_uid = current->fsuid;
- inode->i_gid = current->fsgid;
- inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
- return inode;
-
-eexit_1:
- return ERR_PTR(error);
-}
-
-static struct file *kvmfs_file(struct inode *inode, void *private_data)
-{
- struct file *file = get_empty_filp();
-
- if (!file)
- return ERR_PTR(-ENFILE);
-
- file->f_path.mnt = mntget(kvmfs_mnt);
- file->f_path.dentry = d_alloc_anon(inode);
- if (!file->f_path.dentry)
- return ERR_PTR(-ENOMEM);
- file->f_mapping = inode->i_mapping;
-
- file->f_pos = 0;
- file->f_flags = O_RDWR;
- file->f_op = inode->i_fop;
- file->f_mode = FMODE_READ | FMODE_WRITE;
- file->f_version = 0;
- file->private_data = private_data;
- return file;
-}
-
unsigned long segment_base(u16 selector)
{
struct descriptor_table gdt;
}
EXPORT_SYMBOL_GPL(kvm_write_guest);
-/*
- * Switches to specified vcpu, until a matching vcpu_put()
- */
-static void vcpu_load(struct kvm_vcpu *vcpu)
+void kvm_load_guest_fpu(struct kvm_vcpu *vcpu)
{
- mutex_lock(&vcpu->mutex);
- kvm_arch_ops->vcpu_load(vcpu);
+ if (!vcpu->fpu_active || vcpu->guest_fpu_loaded)
+ return;
+
+ vcpu->guest_fpu_loaded = 1;
+ fx_save(vcpu->host_fx_image);
+ fx_restore(vcpu->guest_fx_image);
+}
+EXPORT_SYMBOL_GPL(kvm_load_guest_fpu);
+
+void kvm_put_guest_fpu(struct kvm_vcpu *vcpu)
+{
+ if (!vcpu->guest_fpu_loaded)
+ return;
+
+ vcpu->guest_fpu_loaded = 0;
+ fx_save(vcpu->guest_fx_image);
+ fx_restore(vcpu->host_fx_image);
}
+EXPORT_SYMBOL_GPL(kvm_put_guest_fpu);
/*
- * Switches to specified vcpu, until a matching vcpu_put(). Will return NULL
- * if the slot is not populated.
+ * Switches to specified vcpu, until a matching vcpu_put()
*/
-static struct kvm_vcpu *vcpu_load_slot(struct kvm *kvm, int slot)
+static void vcpu_load(struct kvm_vcpu *vcpu)
{
- struct kvm_vcpu *vcpu = &kvm->vcpus[slot];
-
mutex_lock(&vcpu->mutex);
- if (!vcpu->vmcs) {
- mutex_unlock(&vcpu->mutex);
- return NULL;
- }
kvm_arch_ops->vcpu_load(vcpu);
- return vcpu;
}
static void vcpu_put(struct kvm_vcpu *vcpu)
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;
+ cpumask_t cpus;
+ struct kvm_vcpu *vcpu;
+ atomic_t completed;
+
+ atomic_set(&completed, 0);
+ cpus_clear(cpus);
+ needed = 0;
+ for (i = 0; i < kvm->nvcpus; ++i) {
+ vcpu = &kvm->vcpus[i];
+ if (test_and_set_bit(KVM_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();
+ }
+}
+
static struct kvm *kvm_create_vm(void)
{
struct kvm *kvm = kzalloc(sizeof(struct kvm), GFP_KERNEL);
if (!kvm)
return ERR_PTR(-ENOMEM);
+ kvm_io_bus_init(&kvm->pio_bus);
spin_lock_init(&kvm->lock);
INIT_LIST_HEAD(&kvm->active_mmu_pages);
+ kvm_io_bus_init(&kvm->mmio_bus);
for (i = 0; i < KVM_MAX_VCPUS; ++i) {
struct kvm_vcpu *vcpu = &kvm->vcpus[i];
vcpu->cpu = -1;
vcpu->kvm = kvm;
vcpu->mmu.root_hpa = INVALID_PAGE;
- INIT_LIST_HEAD(&vcpu->free_pages);
- spin_lock(&kvm_lock);
- list_add(&kvm->vm_list, &vm_list);
- spin_unlock(&kvm_lock);
}
+ spin_lock(&kvm_lock);
+ list_add(&kvm->vm_list, &vm_list);
+ spin_unlock(&kvm_lock);
return kvm;
}
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_unload_vcpu_mmu(struct kvm_vcpu *vcpu)
+{
+ if (!vcpu->vmcs)
+ return;
+
+ vcpu_load(vcpu);
+ kvm_mmu_unload(vcpu);
+ vcpu_put(vcpu);
+}
+
static void kvm_free_vcpu(struct kvm_vcpu *vcpu)
{
if (!vcpu->vmcs)
kvm_arch_ops->vcpu_free(vcpu);
free_page((unsigned long)vcpu->run);
vcpu->run = NULL;
+ free_page((unsigned long)vcpu->pio_data);
+ vcpu->pio_data = NULL;
+ free_pio_guest_pages(vcpu);
}
static void kvm_free_vcpus(struct kvm *kvm)
{
unsigned int i;
+ /*
+ * Unpin any mmu pages first.
+ */
+ for (i = 0; i < KVM_MAX_VCPUS; ++i)
+ kvm_unload_vcpu_mmu(&kvm->vcpus[i]);
for (i = 0; i < KVM_MAX_VCPUS; ++i)
kvm_free_vcpu(&kvm->vcpus[i]);
}
spin_lock(&kvm_lock);
list_del(&kvm->vm_list);
spin_unlock(&kvm_lock);
+ kvm_io_bus_destroy(&kvm->pio_bus);
+ kvm_io_bus_destroy(&kvm->mmio_bus);
kvm_free_vcpus(kvm);
kvm_free_physmem(kvm);
kfree(kvm);
u64 pdpte;
u64 *pdpt;
int ret;
- struct kvm_memory_slot *memslot;
+ struct page *page;
spin_lock(&vcpu->kvm->lock);
- memslot = gfn_to_memslot(vcpu->kvm, pdpt_gfn);
- /* FIXME: !memslot - emulate? 0xff? */
- pdpt = kmap_atomic(gfn_to_page(memslot, pdpt_gfn), KM_USER0);
+ page = gfn_to_page(vcpu->kvm, pdpt_gfn);
+ /* FIXME: !page - emulate? 0xff? */
+ pdpt = kmap_atomic(page, KM_USER0);
ret = 1;
for (i = 0; i < 4; ++i) {
void lmsw(struct kvm_vcpu *vcpu, unsigned long msw)
{
- kvm_arch_ops->decache_cr0_cr4_guest_bits(vcpu);
set_cr0(vcpu, (vcpu->cr0 & ~0x0ful) | (msw & 0x0f));
}
EXPORT_SYMBOL_GPL(lmsw);
}
EXPORT_SYMBOL_GPL(fx_init);
-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);
-}
-
/*
* Allocate some memory and give it an address in the guest physical address
* space.
*memslot = new;
++kvm->memory_config_version;
- spin_unlock(&kvm->lock);
-
- for (i = 0; i < KVM_MAX_VCPUS; ++i) {
- struct kvm_vcpu *vcpu;
+ kvm_mmu_slot_remove_write_access(kvm, mem->slot);
+ kvm_flush_remote_tlbs(kvm);
- 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);
- }
+ spin_unlock(&kvm->lock);
kvm_free_physmem_slot(&old, &new);
return 0;
struct kvm_memory_slot *memslot;
int r, i;
int n;
- int cleared;
unsigned long any = 0;
spin_lock(&kvm->lock);
if (copy_to_user(log->dirty_bitmap, memslot->dirty_bitmap, n))
goto out;
- if (any) {
- cleared = 0;
- for (i = 0; i < KVM_MAX_VCPUS; ++i) {
- struct kvm_vcpu *vcpu;
-
- vcpu = vcpu_load_slot(kvm, i);
- if (!vcpu)
- continue;
- if (!cleared) {
- do_remove_write_access(vcpu, log->slot);
- memset(memslot->dirty_bitmap, 0, n);
- cleared = 1;
- }
- kvm_arch_ops->tlb_flush(vcpu);
- vcpu_put(vcpu);
- }
- }
+ spin_lock(&kvm->lock);
+ kvm_mmu_slot_remove_write_access(kvm, log->slot);
+ kvm_flush_remote_tlbs(kvm);
+ memset(memslot->dirty_bitmap, 0, n);
+ spin_unlock(&kvm->lock);
r = 0;
return r;
}
-struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn)
+/*
+ * Set a new alias region. Aliases map a portion of physical memory into
+ * another portion. This is useful for memory windows, for example the PC
+ * VGA region.
+ */
+static int kvm_vm_ioctl_set_memory_alias(struct kvm *kvm,
+ struct kvm_memory_alias *alias)
+{
+ int r, n;
+ struct kvm_mem_alias *p;
+
+ r = -EINVAL;
+ /* General sanity checks */
+ if (alias->memory_size & (PAGE_SIZE - 1))
+ goto out;
+ if (alias->guest_phys_addr & (PAGE_SIZE - 1))
+ goto out;
+ if (alias->slot >= KVM_ALIAS_SLOTS)
+ goto out;
+ if (alias->guest_phys_addr + alias->memory_size
+ < alias->guest_phys_addr)
+ goto out;
+ if (alias->target_phys_addr + alias->memory_size
+ < alias->target_phys_addr)
+ goto out;
+
+ spin_lock(&kvm->lock);
+
+ p = &kvm->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)
+ break;
+ kvm->naliases = n;
+
+ kvm_mmu_zap_all(kvm);
+
+ spin_unlock(&kvm->lock);
+
+ return 0;
+
+out:
+ return r;
+}
+
+static gfn_t unalias_gfn(struct kvm *kvm, gfn_t gfn)
+{
+ int i;
+ struct kvm_mem_alias *alias;
+
+ for (i = 0; i < kvm->naliases; ++i) {
+ alias = &kvm->aliases[i];
+ if (gfn >= alias->base_gfn
+ && gfn < alias->base_gfn + alias->npages)
+ return alias->target_gfn + gfn - alias->base_gfn;
+ }
+ return gfn;
+}
+
+static struct kvm_memory_slot *__gfn_to_memslot(struct kvm *kvm, gfn_t gfn)
{
int i;
}
return NULL;
}
-EXPORT_SYMBOL_GPL(gfn_to_memslot);
+
+struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn)
+{
+ gfn = unalias_gfn(kvm, gfn);
+ return __gfn_to_memslot(kvm, gfn);
+}
+
+struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn)
+{
+ struct kvm_memory_slot *slot;
+
+ gfn = unalias_gfn(kvm, gfn);
+ slot = __gfn_to_memslot(kvm, gfn);
+ if (!slot)
+ return NULL;
+ return slot->phys_mem[gfn - slot->base_gfn];
+}
+EXPORT_SYMBOL_GPL(gfn_to_page);
void mark_page_dirty(struct kvm *kvm, gfn_t gfn)
{
int i;
- struct kvm_memory_slot *memslot = NULL;
+ struct kvm_memory_slot *memslot;
unsigned long rel_gfn;
for (i = 0; i < kvm->nmemslots; ++i) {
if (gfn >= memslot->base_gfn
&& gfn < memslot->base_gfn + memslot->npages) {
- if (!memslot || !memslot->dirty_bitmap)
+ if (!memslot->dirty_bitmap)
return;
rel_gfn = gfn - memslot->base_gfn;
}
static int emulator_read_std(unsigned long addr,
- unsigned long *val,
+ void *val,
unsigned int bytes,
struct x86_emulate_ctxt *ctxt)
{
unsigned offset = addr & (PAGE_SIZE-1);
unsigned tocopy = min(bytes, (unsigned)PAGE_SIZE - offset);
unsigned long pfn;
- struct kvm_memory_slot *memslot;
- void *page;
+ struct page *page;
+ void *page_virt;
if (gpa == UNMAPPED_GVA)
return X86EMUL_PROPAGATE_FAULT;
pfn = gpa >> PAGE_SHIFT;
- memslot = gfn_to_memslot(vcpu->kvm, pfn);
- if (!memslot)
+ page = gfn_to_page(vcpu->kvm, pfn);
+ if (!page)
return X86EMUL_UNHANDLEABLE;
- page = kmap_atomic(gfn_to_page(memslot, pfn), KM_USER0);
+ page_virt = kmap_atomic(page, KM_USER0);
- memcpy(data, page + offset, tocopy);
+ memcpy(data, page_virt + offset, tocopy);
- kunmap_atomic(page, KM_USER0);
+ kunmap_atomic(page_virt, KM_USER0);
bytes -= tocopy;
data += tocopy;
}
static int emulator_write_std(unsigned long addr,
- unsigned long val,
+ const void *val,
unsigned int bytes,
struct x86_emulate_ctxt *ctxt)
{
return X86EMUL_UNHANDLEABLE;
}
+static struct kvm_io_device *vcpu_find_mmio_dev(struct kvm_vcpu *vcpu,
+ gpa_t addr)
+{
+ /*
+ * Note that its important to have this wrapper function because
+ * in the very near future we will be checking for MMIOs against
+ * the LAPIC as well as the general MMIO bus
+ */
+ return kvm_io_bus_find_dev(&vcpu->kvm->mmio_bus, addr);
+}
+
+static struct kvm_io_device *vcpu_find_pio_dev(struct kvm_vcpu *vcpu,
+ gpa_t addr)
+{
+ return kvm_io_bus_find_dev(&vcpu->kvm->pio_bus, addr);
+}
+
static int emulator_read_emulated(unsigned long addr,
- unsigned long *val,
+ void *val,
unsigned int bytes,
struct x86_emulate_ctxt *ctxt)
{
- struct kvm_vcpu *vcpu = ctxt->vcpu;
+ struct kvm_vcpu *vcpu = ctxt->vcpu;
+ struct kvm_io_device *mmio_dev;
+ gpa_t gpa;
if (vcpu->mmio_read_completed) {
memcpy(val, vcpu->mmio_data, bytes);
} else if (emulator_read_std(addr, val, bytes, ctxt)
== X86EMUL_CONTINUE)
return X86EMUL_CONTINUE;
- else {
- gpa_t gpa = vcpu->mmu.gva_to_gpa(vcpu, addr);
- if (gpa == UNMAPPED_GVA)
- return X86EMUL_PROPAGATE_FAULT;
- vcpu->mmio_needed = 1;
- vcpu->mmio_phys_addr = gpa;
- vcpu->mmio_size = bytes;
- vcpu->mmio_is_write = 0;
+ gpa = vcpu->mmu.gva_to_gpa(vcpu, addr);
+ if (gpa == UNMAPPED_GVA)
+ return X86EMUL_PROPAGATE_FAULT;
- return X86EMUL_UNHANDLEABLE;
+ /*
+ * Is this MMIO handled locally?
+ */
+ mmio_dev = vcpu_find_mmio_dev(vcpu, gpa);
+ if (mmio_dev) {
+ kvm_iodevice_read(mmio_dev, gpa, bytes, val);
+ return X86EMUL_CONTINUE;
}
+
+ vcpu->mmio_needed = 1;
+ vcpu->mmio_phys_addr = gpa;
+ vcpu->mmio_size = bytes;
+ vcpu->mmio_is_write = 0;
+
+ return X86EMUL_UNHANDLEABLE;
}
static int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa,
- unsigned long val, int bytes)
+ const void *val, int bytes)
{
- struct kvm_memory_slot *m;
struct page *page;
void *virt;
+ unsigned offset = offset_in_page(gpa);
if (((gpa + bytes - 1) >> PAGE_SHIFT) != (gpa >> PAGE_SHIFT))
return 0;
- m = gfn_to_memslot(vcpu->kvm, gpa >> PAGE_SHIFT);
- if (!m)
+ page = gfn_to_page(vcpu->kvm, gpa >> PAGE_SHIFT);
+ if (!page)
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);
+ kvm_mmu_pte_write(vcpu, gpa, virt + offset, val, bytes);
+ memcpy(virt + offset_in_page(gpa), val, bytes);
kunmap_atomic(virt, KM_USER0);
- kvm_mmu_post_write(vcpu, gpa, bytes);
return 1;
}
-static int emulator_write_emulated(unsigned long addr,
- unsigned long val,
- unsigned int bytes,
- struct x86_emulate_ctxt *ctxt)
+static int emulator_write_emulated_onepage(unsigned long addr,
+ const void *val,
+ unsigned int bytes,
+ struct x86_emulate_ctxt *ctxt)
{
- struct kvm_vcpu *vcpu = ctxt->vcpu;
- gpa_t gpa = vcpu->mmu.gva_to_gpa(vcpu, addr);
+ struct kvm_vcpu *vcpu = ctxt->vcpu;
+ struct kvm_io_device *mmio_dev;
+ gpa_t gpa = vcpu->mmu.gva_to_gpa(vcpu, addr);
- if (gpa == UNMAPPED_GVA)
+ if (gpa == UNMAPPED_GVA) {
+ kvm_arch_ops->inject_page_fault(vcpu, addr, 2);
return X86EMUL_PROPAGATE_FAULT;
+ }
if (emulator_write_phys(vcpu, gpa, val, bytes))
return X86EMUL_CONTINUE;
+ /*
+ * Is this MMIO handled locally?
+ */
+ mmio_dev = vcpu_find_mmio_dev(vcpu, gpa);
+ if (mmio_dev) {
+ kvm_iodevice_write(mmio_dev, gpa, bytes, val);
+ return X86EMUL_CONTINUE;
+ }
+
vcpu->mmio_needed = 1;
vcpu->mmio_phys_addr = gpa;
vcpu->mmio_size = bytes;
vcpu->mmio_is_write = 1;
- memcpy(vcpu->mmio_data, &val, bytes);
+ memcpy(vcpu->mmio_data, val, bytes);
return X86EMUL_CONTINUE;
}
-static int emulator_cmpxchg_emulated(unsigned long addr,
- unsigned long old,
- unsigned long new,
- unsigned int bytes,
- struct x86_emulate_ctxt *ctxt)
+static int emulator_write_emulated(unsigned long addr,
+ const void *val,
+ unsigned int bytes,
+ struct x86_emulate_ctxt *ctxt)
{
- static int reported;
+ /* Crossing a page boundary? */
+ if (((addr + bytes - 1) ^ addr) & PAGE_MASK) {
+ int rc, now;
- if (!reported) {
- reported = 1;
- printk(KERN_WARNING "kvm: emulating exchange as write\n");
+ now = -addr & ~PAGE_MASK;
+ rc = emulator_write_emulated_onepage(addr, val, now, ctxt);
+ if (rc != X86EMUL_CONTINUE)
+ return rc;
+ addr += now;
+ val += now;
+ bytes -= now;
}
- return emulator_write_emulated(addr, new, bytes, ctxt);
+ return emulator_write_emulated_onepage(addr, val, bytes, ctxt);
}
-#ifdef CONFIG_X86_32
-
-static int emulator_cmpxchg8b_emulated(unsigned long addr,
- unsigned long old_lo,
- unsigned long old_hi,
- unsigned long new_lo,
- unsigned long new_hi,
- struct x86_emulate_ctxt *ctxt)
+static int emulator_cmpxchg_emulated(unsigned long addr,
+ const void *old,
+ const void *new,
+ unsigned int bytes,
+ struct x86_emulate_ctxt *ctxt)
{
static int reported;
- int r;
if (!reported) {
reported = 1;
- printk(KERN_WARNING "kvm: emulating exchange8b as write\n");
+ printk(KERN_WARNING "kvm: emulating exchange as write\n");
}
- r = emulator_write_emulated(addr, new_lo, 4, ctxt);
- if (r != X86EMUL_CONTINUE)
- return r;
- return emulator_write_emulated(addr+4, new_hi, 4, ctxt);
+ return emulator_write_emulated(addr, new, bytes, ctxt);
}
-#endif
-
static unsigned long get_segment_base(struct kvm_vcpu *vcpu, int seg)
{
return kvm_arch_ops->get_segment_base(vcpu, seg);
{
unsigned long cr0;
- kvm_arch_ops->decache_cr0_cr4_guest_bits(vcpu);
cr0 = vcpu->cr0 & ~CR0_TS_MASK;
kvm_arch_ops->set_cr0(vcpu, cr0);
return X86EMUL_CONTINUE;
.read_emulated = emulator_read_emulated,
.write_emulated = emulator_write_emulated,
.cmpxchg_emulated = emulator_cmpxchg_emulated,
-#ifdef CONFIG_X86_32
- .cmpxchg8b_emulated = emulator_cmpxchg8b_emulated,
-#endif
};
int emulate_instruction(struct kvm_vcpu *vcpu,
int r;
int cs_db, cs_l;
+ vcpu->mmio_fault_cr2 = cr2;
kvm_arch_ops->cache_regs(vcpu);
kvm_arch_ops->get_cs_db_l_bits(vcpu, &cs_db, &cs_l);
kvm_arch_ops->decache_regs(vcpu);
kvm_arch_ops->set_rflags(vcpu, emulate_ctxt.eflags);
- if (vcpu->mmio_is_write)
+ if (vcpu->mmio_is_write) {
+ vcpu->mmio_needed = 0;
return EMULATE_DO_MMIO;
+ }
return EMULATE_DONE;
}
EXPORT_SYMBOL_GPL(emulate_instruction);
+int kvm_emulate_halt(struct kvm_vcpu *vcpu)
+{
+ if (vcpu->irq_summary)
+ return 1;
+
+ vcpu->run->exit_reason = KVM_EXIT_HLT;
+ ++vcpu->stat.halt_exits;
+ return 0;
+}
+EXPORT_SYMBOL_GPL(kvm_emulate_halt);
+
int kvm_hypercall(struct kvm_vcpu *vcpu, struct kvm_run *run)
{
unsigned long nr, a0, a1, a2, a3, a4, a5, ret;
unsigned long realmode_get_cr(struct kvm_vcpu *vcpu, int cr)
{
- kvm_arch_ops->decache_cr0_cr4_guest_bits(vcpu);
+ kvm_arch_ops->decache_cr4_guest_bits(vcpu);
switch (cr) {
case 0:
return vcpu->cr0;
case MSR_IA32_MC0_MISC+16:
case MSR_IA32_UCODE_REV:
case MSR_IA32_PERF_STATUS:
+ case MSR_IA32_EBL_CR_POWERON:
/* MTRR registers */
case 0xfe:
case 0x200 ... 0x2ff:
* Returns 0 on success, non-0 otherwise.
* Assumes vcpu_load() was already called.
*/
-static int get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata)
+int kvm_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata)
{
return kvm_arch_ops->get_msr(vcpu, msr_index, pdata);
}
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 */
* Returns 0 on success, non-0 otherwise.
* Assumes vcpu_load() was already called.
*/
-static int set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data)
+int kvm_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data)
{
return kvm_arch_ops->set_msr(vcpu, msr_index, data);
}
void kvm_resched(struct kvm_vcpu *vcpu)
{
+ if (!need_resched())
+ return;
vcpu_put(vcpu);
cond_resched();
vcpu_load(vcpu);
}
EXPORT_SYMBOL_GPL(kvm_emulate_cpuid);
-static void complete_pio(struct kvm_vcpu *vcpu)
+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_io *io = &vcpu->run->io;
+ struct kvm_pio_request *io = &vcpu->pio;
long delta;
+ int r;
kvm_arch_ops->cache_regs(vcpu);
if (!io->string) {
- if (io->direction == KVM_EXIT_IO_IN)
- memcpy(&vcpu->regs[VCPU_REGS_RAX], &io->value,
+ 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;
+ }
+ }
+
delta = 1;
if (io->rep) {
- delta *= io->count;
+ delta *= io->cur_count;
/*
* The size of the register should really depend on
* current address size.
*/
vcpu->regs[VCPU_REGS_RCX] -= delta;
}
- if (io->string_down)
+ if (io->down)
delta = -delta;
delta *= io->size;
- if (io->direction == KVM_EXIT_IO_IN)
+ if (io->in)
vcpu->regs[VCPU_REGS_RDI] += delta;
else
vcpu->regs[VCPU_REGS_RSI] += delta;
}
- vcpu->pio_pending = 0;
- vcpu->run->io_completed = 0;
-
kvm_arch_ops->decache_regs(vcpu);
- kvm_arch_ops->skip_emulated_instruction(vcpu);
+ io->count -= io->cur_count;
+ io->cur_count = 0;
+
+ if (!io->count)
+ kvm_arch_ops->skip_emulated_instruction(vcpu);
+ return 0;
+}
+
+void kernel_pio(struct kvm_io_device *pio_dev, struct kvm_vcpu *vcpu)
+{
+ /* TODO: String I/O for in kernel device */
+
+ if (vcpu->pio.in)
+ kvm_iodevice_read(pio_dev, vcpu->pio.port,
+ vcpu->pio.size,
+ vcpu->pio_data);
+ else
+ kvm_iodevice_write(pio_dev, vcpu->pio.port,
+ vcpu->pio.size,
+ vcpu->pio_data);
+}
+
+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;
+ struct kvm_io_device *pio_dev;
+
+ vcpu->run->exit_reason = KVM_EXIT_IO;
+ vcpu->run->io.direction = in ? KVM_EXIT_IO_IN : KVM_EXIT_IO_OUT;
+ vcpu->run->io.size = size;
+ vcpu->run->io.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.port = port;
+ vcpu->pio.string = string;
+ vcpu->pio.down = down;
+ vcpu->pio.guest_page_offset = offset_in_page(address);
+ vcpu->pio.rep = rep;
+
+ pio_dev = vcpu_find_pio_dev(vcpu, port);
+ if (!string) {
+ kvm_arch_ops->cache_regs(vcpu);
+ memcpy(vcpu->pio_data, &vcpu->regs[VCPU_REGS_RAX], 4);
+ kvm_arch_ops->decache_regs(vcpu);
+ if (pio_dev) {
+ kernel_pio(pio_dev, vcpu);
+ complete_pio(vcpu);
+ return 1;
+ }
+ return 0;
+ }
+ /* TODO: String I/O for in kernel device */
+ if (pio_dev)
+ printk(KERN_ERR "kvm_setup_pio: no string io support\n");
+
+ if (!count) {
+ kvm_arch_ops->skip_emulated_instruction(vcpu);
+ return 1;
+ }
+
+ now = min(count, PAGE_SIZE / size);
+
+ if (!down)
+ in_page = PAGE_SIZE - offset_in_page(address);
+ else
+ 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 (!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_pending)
- complete_pio(vcpu);
- else {
- memcpy(vcpu->mmio_data, kvm_run->mmio.data, 8);
- vcpu->mmio_read_completed = 1;
- }
+ if (vcpu->pio.cur_count) {
+ r = complete_pio(vcpu);
+ if (r)
+ goto out;
}
- vcpu->mmio_needed = 0;
+ if (vcpu->mmio_needed) {
+ memcpy(vcpu->mmio_data, kvm_run->mmio.data, 8);
+ vcpu->mmio_read_completed = 1;
+ vcpu->mmio_needed = 0;
+ r = emulate_instruction(vcpu, kvm_run,
+ vcpu->mmio_fault_cr2, 0);
+ if (r == EMULATE_DO_MMIO) {
+ /*
+ * Read-modify-write. Back to userspace.
+ */
+ kvm_run->exit_reason = KVM_EXIT_MMIO;
+ r = 0;
+ goto out;
+ }
+ }
- if (kvm_run->exit_type == KVM_EXIT_TYPE_VM_EXIT
- && kvm_run->exit_reason == KVM_EXIT_HYPERCALL) {
+ 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;
}
sregs->gdt.limit = dt.limit;
sregs->gdt.base = dt.base;
- kvm_arch_ops->decache_cr0_cr4_guest_bits(vcpu);
+ kvm_arch_ops->decache_cr4_guest_bits(vcpu);
sregs->cr0 = vcpu->cr0;
sregs->cr2 = vcpu->cr2;
sregs->cr3 = vcpu->cr3;
vcpu_load(vcpu);
- 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);
-
dt.limit = sregs->idt.limit;
dt.base = sregs->idt.base;
kvm_arch_ops->set_idt(vcpu, &dt);
#endif
vcpu->apic_base = sregs->apic_base;
- kvm_arch_ops->decache_cr0_cr4_guest_bits(vcpu);
+ kvm_arch_ops->decache_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;
*/
static int do_set_msr(struct kvm_vcpu *vcpu, unsigned index, u64 *data)
{
- return set_msr(vcpu, index, *data);
+ return kvm_set_msr(vcpu, index, *data);
}
/*
*type = VM_FAULT_MINOR;
pgoff = ((address - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;
- if (pgoff != 0)
+ 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;
- page = virt_to_page(vcpu->run);
get_page(page);
return page;
}
struct inode *inode;
struct file *file;
+ r = anon_inode_getfd(&fd, &inode, &file,
+ "kvm-vcpu", &kvm_vcpu_fops, vcpu);
+ if (r)
+ return r;
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;
}
/*
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;
+ vcpu->cr0 = 0x10;
r = kvm_arch_ops->vcpu_create(vcpu);
if (r < 0)
if (r < 0)
goto out_free_vcpus;
+ spin_lock(&kvm_lock);
+ if (n >= kvm->nvcpus)
+ kvm->nvcpus = n + 1;
+ spin_unlock(&kvm_lock);
+
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 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)
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) {
+ sigdelsetmask(sigset, sigmask(SIGKILL)|sigmask(SIGSTOP));
+ vcpu->sigset_active = 1;
+ vcpu->sigset = *sigset;
+ } else
+ vcpu->sigset_active = 0;
+ return 0;
+}
+
+/*
+ * fxsave fpu state. Taken from x86_64/processor.h. To be killed when
+ * we have asm/x86/processor.h
+ */
+struct fxsave {
+ u16 cwd;
+ u16 swd;
+ u16 twd;
+ u16 fop;
+ u64 rip;
+ u64 rdp;
+ u32 mxcsr;
+ u32 mxcsr_mask;
+ u32 st_space[32]; /* 8*16 bytes for each FP-reg = 128 bytes */
+#ifdef CONFIG_X86_64
+ u32 xmm_space[64]; /* 16*16 bytes for each XMM-reg = 256 bytes */
+#else
+ u32 xmm_space[32]; /* 8*16 bytes for each XMM-reg = 128 bytes */
+#endif
+};
+
+static int kvm_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
+{
+ struct fxsave *fxsave = (struct fxsave *)vcpu->guest_fx_image;
+
+ vcpu_load(vcpu);
+
+ memcpy(fpu->fpr, fxsave->st_space, 128);
+ fpu->fcw = fxsave->cwd;
+ fpu->fsw = fxsave->swd;
+ fpu->ftwx = fxsave->twd;
+ fpu->last_opcode = fxsave->fop;
+ fpu->last_ip = fxsave->rip;
+ fpu->last_dp = fxsave->rdp;
+ memcpy(fpu->xmm, fxsave->xmm_space, sizeof fxsave->xmm_space);
+
+ vcpu_put(vcpu);
+
+ return 0;
+}
+
+static int kvm_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
+{
+ struct fxsave *fxsave = (struct fxsave *)vcpu->guest_fx_image;
+
+ vcpu_load(vcpu);
+
+ memcpy(fxsave->st_space, fpu->fpr, 128);
+ fxsave->cwd = fpu->fcw;
+ fxsave->swd = fpu->fsw;
+ fxsave->twd = fpu->ftwx;
+ fxsave->fop = fpu->last_opcode;
+ fxsave->rip = fpu->last_ip;
+ fxsave->rdp = fpu->last_dp;
+ memcpy(fxsave->xmm_space, fpu->xmm, sizeof fxsave->xmm_space);
+
+ vcpu_put(vcpu);
+
+ return 0;
+}
+
static long kvm_vcpu_ioctl(struct file *filp,
unsigned int ioctl, unsigned long arg)
{
switch (ioctl) {
case KVM_RUN:
+ r = -EINVAL;
+ if (arg)
+ goto out;
r = kvm_vcpu_ioctl_run(vcpu, vcpu->run);
break;
case KVM_GET_REGS: {
break;
}
case KVM_GET_MSRS:
- r = msr_io(vcpu, argp, get_msr, 1);
+ r = msr_io(vcpu, argp, kvm_get_msr, 1);
break;
case KVM_SET_MSRS:
r = msr_io(vcpu, argp, do_set_msr, 0);
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;
+ }
+ case KVM_GET_FPU: {
+ struct kvm_fpu fpu;
+
+ memset(&fpu, 0, sizeof fpu);
+ r = kvm_vcpu_ioctl_get_fpu(vcpu, &fpu);
+ if (r)
+ goto out;
+ r = -EFAULT;
+ if (copy_to_user(argp, &fpu, sizeof fpu))
+ goto out;
+ r = 0;
+ break;
+ }
+ case KVM_SET_FPU: {
+ struct kvm_fpu fpu;
+
+ r = -EFAULT;
+ if (copy_from_user(&fpu, argp, sizeof fpu))
+ goto out;
+ r = kvm_vcpu_ioctl_set_fpu(vcpu, &fpu);
+ if (r)
+ goto out;
+ r = 0;
+ break;
+ }
default:
;
}
goto out;
break;
}
+ case KVM_SET_MEMORY_ALIAS: {
+ struct kvm_memory_alias alias;
+
+ r = -EFAULT;
+ if (copy_from_user(&alias, argp, sizeof alias))
+ goto out;
+ r = kvm_vm_ioctl_set_memory_alias(kvm, &alias);
+ if (r)
+ goto out;
+ break;
+ }
default:
;
}
{
struct kvm *kvm = vma->vm_file->private_data;
unsigned long pgoff;
- struct kvm_memory_slot *slot;
struct page *page;
*type = VM_FAULT_MINOR;
pgoff = ((address - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;
- slot = gfn_to_memslot(kvm, pgoff);
- if (!slot)
- return NOPAGE_SIGBUS;
- page = gfn_to_page(slot, pgoff);
+ page = gfn_to_page(kvm, pgoff);
if (!page)
return NOPAGE_SIGBUS;
get_page(page);
struct file *file;
struct kvm *kvm;
- inode = kvmfs_inode(&kvm_vm_fops);
- if (IS_ERR(inode)) {
- r = PTR_ERR(inode);
- goto out1;
- }
-
kvm = kvm_create_vm();
- if (IS_ERR(kvm)) {
- r = PTR_ERR(kvm);
- goto out2;
+ if (IS_ERR(kvm))
+ return PTR_ERR(kvm);
+ r = anon_inode_getfd(&fd, &inode, &file, "kvm-vm", &kvm_vm_fops, kvm);
+ if (r) {
+ kvm_destroy_vm(kvm);
+ return r;
}
- file = kvmfs_file(inode, kvm);
- if (IS_ERR(file)) {
- r = PTR_ERR(file);
- goto out3;
- }
kvm->filp = file;
- r = get_unused_fd();
- if (r < 0)
- goto out4;
- fd = r;
- fd_install(fd, file);
-
return fd;
-
-out4:
- fput(file);
-out3:
- kvm_destroy_vm(kvm);
-out2:
- iput(inode);
-out1:
- return r;
}
static long kvm_dev_ioctl(struct file *filp,
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_GET_VCPU_MMAP_SIZE:
+ r = -EINVAL;
+ if (arg)
+ goto out;
+ r = 2 * PAGE_SIZE;
+ break;
default:
;
}
* in vmx root mode.
*/
printk(KERN_INFO "kvm: exiting hardware virtualization\n");
- on_each_cpu(kvm_arch_ops->hardware_disable, NULL, 0, 1);
+ on_each_cpu(hardware_disable, NULL, 0, 1);
}
return NOTIFY_OK;
}
spin_unlock(&kvm_lock);
}
+static void hardware_enable(void *junk)
+{
+ int cpu = raw_smp_processor_id();
+
+ if (cpu_isset(cpu, cpus_hardware_enabled))
+ return;
+ cpu_set(cpu, cpus_hardware_enabled);
+ kvm_arch_ops->hardware_enable(NULL);
+}
+
+static void hardware_disable(void *junk)
+{
+ int cpu = raw_smp_processor_id();
+
+ if (!cpu_isset(cpu, cpus_hardware_enabled))
+ return;
+ cpu_clear(cpu, cpus_hardware_enabled);
+ decache_vcpus_on_cpu(cpu);
+ kvm_arch_ops->hardware_disable(NULL);
+}
+
static int kvm_cpu_hotplug(struct notifier_block *notifier, unsigned long val,
void *v)
{
int cpu = (long)v;
switch (val) {
- case CPU_DOWN_PREPARE:
+ case CPU_DYING:
+ case CPU_DYING_FROZEN:
case CPU_UP_CANCELED:
+ case CPU_UP_CANCELED_FROZEN:
printk(KERN_INFO "kvm: disabling virtualization on CPU%d\n",
cpu);
- decache_vcpus_on_cpu(cpu);
- smp_call_function_single(cpu, kvm_arch_ops->hardware_disable,
- NULL, 0, 1);
+ smp_call_function_single(cpu, hardware_disable, NULL, 0, 1);
break;
case CPU_ONLINE:
+ case CPU_ONLINE_FROZEN:
printk(KERN_INFO "kvm: enabling virtualization on CPU%d\n",
cpu);
- smp_call_function_single(cpu, kvm_arch_ops->hardware_enable,
- NULL, 0, 1);
+ smp_call_function_single(cpu, hardware_enable, NULL, 0, 1);
break;
}
return NOTIFY_OK;
}
+void kvm_io_bus_init(struct kvm_io_bus *bus)
+{
+ memset(bus, 0, sizeof(*bus));
+}
+
+void kvm_io_bus_destroy(struct kvm_io_bus *bus)
+{
+ int i;
+
+ for (i = 0; i < bus->dev_count; i++) {
+ struct kvm_io_device *pos = bus->devs[i];
+
+ kvm_iodevice_destructor(pos);
+ }
+}
+
+struct kvm_io_device *kvm_io_bus_find_dev(struct kvm_io_bus *bus, gpa_t addr)
+{
+ int i;
+
+ for (i = 0; i < bus->dev_count; i++) {
+ struct kvm_io_device *pos = bus->devs[i];
+
+ if (pos->in_range(pos, addr))
+ return pos;
+ }
+
+ return NULL;
+}
+
+void kvm_io_bus_register_dev(struct kvm_io_bus *bus, struct kvm_io_device *dev)
+{
+ BUG_ON(bus->dev_count > (NR_IOBUS_DEVS-1));
+
+ bus->devs[bus->dev_count++] = dev;
+}
+
static struct notifier_block kvm_cpu_notifier = {
.notifier_call = kvm_cpu_hotplug,
.priority = 20, /* must be > scheduler priority */
};
+static u64 stat_get(void *_offset)
+{
+ unsigned offset = (long)_offset;
+ u64 total = 0;
+ struct kvm *kvm;
+ struct kvm_vcpu *vcpu;
+ int i;
+
+ spin_lock(&kvm_lock);
+ list_for_each_entry(kvm, &vm_list, vm_list)
+ for (i = 0; i < KVM_MAX_VCPUS; ++i) {
+ vcpu = &kvm->vcpus[i];
+ total += *(u32 *)((void *)vcpu + offset);
+ }
+ spin_unlock(&kvm_lock);
+ return total;
+}
+
+static void stat_set(void *offset, u64 val)
+{
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(stat_fops, stat_get, stat_set, "%llu\n");
+
static __init void kvm_init_debug(void)
{
struct kvm_stats_debugfs_item *p;
debugfs_dir = debugfs_create_dir("kvm", NULL);
for (p = debugfs_entries; p->name; ++p)
- p->dentry = debugfs_create_u32(p->name, 0444, debugfs_dir,
- p->data);
+ p->dentry = debugfs_create_file(p->name, 0444, debugfs_dir,
+ (void *)(long)p->offset,
+ &stat_fops);
}
static void kvm_exit_debug(void)
static int kvm_suspend(struct sys_device *dev, pm_message_t state)
{
- decache_vcpus_on_cpu(raw_smp_processor_id());
- on_each_cpu(kvm_arch_ops->hardware_disable, NULL, 0, 1);
+ hardware_disable(NULL);
return 0;
}
static int kvm_resume(struct sys_device *dev)
{
- on_each_cpu(kvm_arch_ops->hardware_enable, NULL, 0, 1);
+ hardware_enable(NULL);
return 0;
}
hpa_t bad_page_address;
-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_SUPER_MAGIC, mnt);
-}
-
-static struct file_system_type kvm_fs_type = {
- .name = "kvmfs",
- .get_sb = kvmfs_get_sb,
- .kill_sb = kill_anon_super,
-};
-
int kvm_init_arch(struct kvm_arch_ops *ops, struct module *module)
{
int r;
if (r < 0)
goto out;
- on_each_cpu(kvm_arch_ops->hardware_enable, NULL, 0, 1);
+ on_each_cpu(hardware_enable, NULL, 0, 1);
r = register_cpu_notifier(&kvm_cpu_notifier);
if (r)
goto out_free_1;
unregister_reboot_notifier(&kvm_reboot_notifier);
unregister_cpu_notifier(&kvm_cpu_notifier);
out_free_1:
- on_each_cpu(kvm_arch_ops->hardware_disable, NULL, 0, 1);
+ on_each_cpu(hardware_disable, NULL, 0, 1);
kvm_arch_ops->hardware_unsetup();
out:
kvm_arch_ops = NULL;
sysdev_class_unregister(&kvm_sysdev_class);
unregister_reboot_notifier(&kvm_reboot_notifier);
unregister_cpu_notifier(&kvm_cpu_notifier);
- on_each_cpu(kvm_arch_ops->hardware_disable, NULL, 0, 1);
+ on_each_cpu(hardware_disable, NULL, 0, 1);
kvm_arch_ops->hardware_unsetup();
kvm_arch_ops = NULL;
}
static struct page *bad_page;
int r;
- r = register_filesystem(&kvm_fs_type);
+ r = kvm_mmu_module_init();
if (r)
- goto out3;
+ goto out4;
- kvmfs_mnt = kern_mount(&kvm_fs_type);
- r = PTR_ERR(kvmfs_mnt);
- if (IS_ERR(kvmfs_mnt))
- goto out2;
kvm_init_debug();
kvm_init_msr_list();
out:
kvm_exit_debug();
- mntput(kvmfs_mnt);
-out2:
- unregister_filesystem(&kvm_fs_type);
-out3:
+ kvm_mmu_module_exit();
+out4:
return r;
}
{
kvm_exit_debug();
__free_page(pfn_to_page(bad_page_address >> PAGE_SHIFT));
- mntput(kvmfs_mnt);
- unregister_filesystem(&kvm_fs_type);
+ kvm_mmu_module_exit();
}
module_init(kvm_init)
projects / linux-2.6-omap-h63xx.git / blobdiff