*/
#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;
+static __read_mostly struct preempt_ops kvm_preempt_ops;
+
#define STAT_OFFSET(x) offsetof(struct kvm_vcpu, stat.x)
static struct kvm_stats_debugfs_item {
static struct dentry *debugfs_dir;
-struct vfsmount *kvmfs_mnt;
-
#define MAX_IO_MSRS 256
-#define CR0_RESEVED_BITS 0xffffffff1ffaffc0ULL
-#define LMSW_GUEST_MASK 0x0eULL
-#define CR4_RESEVED_BITS (~((1ULL << 11) - 1))
-#define CR8_RESEVED_BITS (~0x0fULL)
+#define CR0_RESERVED_BITS \
+ (~(unsigned long)(X86_CR0_PE | X86_CR0_MP | X86_CR0_EM | X86_CR0_TS \
+ | X86_CR0_ET | X86_CR0_NE | X86_CR0_WP | X86_CR0_AM \
+ | X86_CR0_NW | X86_CR0_CD | X86_CR0_PG))
+#define CR4_RESERVED_BITS \
+ (~(unsigned long)(X86_CR4_VME | X86_CR4_PVI | X86_CR4_TSD | X86_CR4_DE\
+ | X86_CR4_PSE | X86_CR4_PAE | X86_CR4_MCE \
+ | X86_CR4_PGE | X86_CR4_PCE | X86_CR4_OSFXSR \
+ | X86_CR4_OSXMMEXCPT | X86_CR4_VMXE))
+
+#define CR8_RESERVED_BITS (~(unsigned long)X86_CR8_TPR)
#define EFER_RESERVED_BITS 0xfffffffffffff2fe
#ifdef CONFIG_X86_64
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;
*/
static void vcpu_load(struct kvm_vcpu *vcpu)
{
- mutex_lock(&vcpu->mutex);
- kvm_arch_ops->vcpu_load(vcpu);
-}
-
-/*
- * Switches to specified vcpu, until a matching vcpu_put(). Will return NULL
- * if the slot is not populated.
- */
-static struct kvm_vcpu *vcpu_load_slot(struct kvm *kvm, int slot)
-{
- struct kvm_vcpu *vcpu = &kvm->vcpus[slot];
+ int cpu;
mutex_lock(&vcpu->mutex);
- if (!vcpu->vmcs) {
- mutex_unlock(&vcpu->mutex);
- return NULL;
- }
- kvm_arch_ops->vcpu_load(vcpu);
- return vcpu;
+ cpu = get_cpu();
+ preempt_notifier_register(&vcpu->preempt_notifier);
+ kvm_arch_ops->vcpu_load(vcpu, cpu);
+ put_cpu();
}
static void vcpu_put(struct kvm_vcpu *vcpu)
{
+ preempt_disable();
kvm_arch_ops->vcpu_put(vcpu);
+ preempt_notifier_unregister(&vcpu->preempt_notifier);
+ preempt_enable();
mutex_unlock(&vcpu->mutex);
}
atomic_set(&completed, 0);
cpus_clear(cpus);
needed = 0;
- for (i = 0; i < kvm->nvcpus; ++i) {
- vcpu = &kvm->vcpus[i];
+ for (i = 0; i < KVM_MAX_VCPUS; ++i) {
+ vcpu = kvm->vcpus[i];
+ if (!vcpu)
+ continue;
if (test_and_set_bit(KVM_TLB_FLUSH, &vcpu->requests))
continue;
cpu = vcpu->cpu;
}
}
+int kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id)
+{
+ struct page *page;
+ int r;
+
+ mutex_init(&vcpu->mutex);
+ vcpu->cpu = -1;
+ vcpu->mmu.root_hpa = INVALID_PAGE;
+ vcpu->kvm = kvm;
+ vcpu->vcpu_id = id;
+
+ page = alloc_page(GFP_KERNEL | __GFP_ZERO);
+ if (!page) {
+ r = -ENOMEM;
+ goto fail;
+ }
+ vcpu->run = page_address(page);
+
+ page = alloc_page(GFP_KERNEL | __GFP_ZERO);
+ if (!page) {
+ r = -ENOMEM;
+ goto fail_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_mmu_create(vcpu);
+ if (r < 0)
+ goto fail_free_pio_data;
+
+ return 0;
+
+fail_free_pio_data:
+ free_page((unsigned long)vcpu->pio_data);
+fail_free_run:
+ free_page((unsigned long)vcpu->run);
+fail:
+ return -ENOMEM;
+}
+EXPORT_SYMBOL_GPL(kvm_vcpu_init);
+
+void kvm_vcpu_uninit(struct kvm_vcpu *vcpu)
+{
+ kvm_mmu_destroy(vcpu);
+ free_page((unsigned long)vcpu->pio_data);
+ free_page((unsigned long)vcpu->run);
+}
+EXPORT_SYMBOL_GPL(kvm_vcpu_uninit);
+
static struct kvm *kvm_create_vm(void)
{
struct kvm *kvm = kzalloc(sizeof(struct kvm), GFP_KERNEL);
- int i;
if (!kvm)
return ERR_PTR(-ENOMEM);
- spin_lock_init(&kvm->lock);
+ kvm_io_bus_init(&kvm->pio_bus);
+ mutex_init(&kvm->lock);
INIT_LIST_HEAD(&kvm->active_mmu_pages);
+ kvm_io_bus_init(&kvm->mmio_bus);
spin_lock(&kvm_lock);
list_add(&kvm->vm_list, &vm_list);
spin_unlock(&kvm_lock);
- kvm_io_bus_init(&kvm->mmio_bus);
- for (i = 0; i < KVM_MAX_VCPUS; ++i) {
- struct kvm_vcpu *vcpu = &kvm->vcpus[i];
-
- mutex_init(&vcpu->mutex);
- vcpu->cpu = -1;
- vcpu->kvm = kvm;
- vcpu->mmu.root_hpa = INVALID_PAGE;
- }
return kvm;
}
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)
- 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)
{
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]);
+ if (kvm->vcpus[i])
+ kvm_unload_vcpu_mmu(kvm->vcpus[i]);
+ for (i = 0; i < KVM_MAX_VCPUS; ++i) {
+ if (kvm->vcpus[i]) {
+ kvm_arch_ops->vcpu_free(kvm->vcpus[i]);
+ kvm->vcpus[i] = NULL;
+ }
+ }
+
}
static int kvm_dev_release(struct inode *inode, struct file *filp)
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);
gfn_t pdpt_gfn = cr3 >> PAGE_SHIFT;
unsigned offset = ((cr3 & (PAGE_SIZE-1)) >> 5) << 2;
int i;
- u64 pdpte;
u64 *pdpt;
int ret;
struct page *page;
+ u64 pdpte[ARRAY_SIZE(vcpu->pdptrs)];
- spin_lock(&vcpu->kvm->lock);
+ mutex_lock(&vcpu->kvm->lock);
page = gfn_to_page(vcpu->kvm, pdpt_gfn);
- /* FIXME: !page - emulate? 0xff? */
+ if (!page) {
+ ret = 0;
+ goto out;
+ }
+
pdpt = kmap_atomic(page, KM_USER0);
+ memcpy(pdpte, pdpt+offset, sizeof(pdpte));
+ kunmap_atomic(pdpt, KM_USER0);
- ret = 1;
- for (i = 0; i < 4; ++i) {
- pdpte = pdpt[offset + i];
- if ((pdpte & 1) && (pdpte & 0xfffffff0000001e6ull)) {
+ for (i = 0; i < ARRAY_SIZE(pdpte); ++i) {
+ if ((pdpte[i] & 1) && (pdpte[i] & 0xfffffff0000001e6ull)) {
ret = 0;
goto out;
}
}
+ ret = 1;
- for (i = 0; i < 4; ++i)
- vcpu->pdptrs[i] = pdpt[offset + i];
-
+ memcpy(vcpu->pdptrs, pdpte, sizeof(vcpu->pdptrs));
out:
- kunmap_atomic(pdpt, KM_USER0);
- spin_unlock(&vcpu->kvm->lock);
+ mutex_unlock(&vcpu->kvm->lock);
return ret;
}
void set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
{
- if (cr0 & CR0_RESEVED_BITS) {
+ if (cr0 & CR0_RESERVED_BITS) {
printk(KERN_DEBUG "set_cr0: 0x%lx #GP, reserved bits 0x%lx\n",
cr0, vcpu->cr0);
inject_gp(vcpu);
return;
}
- if ((cr0 & CR0_NW_MASK) && !(cr0 & CR0_CD_MASK)) {
+ if ((cr0 & X86_CR0_NW) && !(cr0 & X86_CR0_CD)) {
printk(KERN_DEBUG "set_cr0: #GP, CD == 0 && NW == 1\n");
inject_gp(vcpu);
return;
}
- if ((cr0 & CR0_PG_MASK) && !(cr0 & CR0_PE_MASK)) {
+ 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);
return;
}
- if (!is_paging(vcpu) && (cr0 & CR0_PG_MASK)) {
+ if (!is_paging(vcpu) && (cr0 & X86_CR0_PG)) {
#ifdef CONFIG_X86_64
if ((vcpu->shadow_efer & EFER_LME)) {
int cs_db, cs_l;
kvm_arch_ops->set_cr0(vcpu, cr0);
vcpu->cr0 = cr0;
- spin_lock(&vcpu->kvm->lock);
+ mutex_lock(&vcpu->kvm->lock);
kvm_mmu_reset_context(vcpu);
- spin_unlock(&vcpu->kvm->lock);
+ mutex_unlock(&vcpu->kvm->lock);
return;
}
EXPORT_SYMBOL_GPL(set_cr0);
void set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
{
- if (cr4 & CR4_RESEVED_BITS) {
+ if (cr4 & CR4_RESERVED_BITS) {
printk(KERN_DEBUG "set_cr4: #GP, reserved bits\n");
inject_gp(vcpu);
return;
}
if (is_long_mode(vcpu)) {
- if (!(cr4 & CR4_PAE_MASK)) {
+ if (!(cr4 & X86_CR4_PAE)) {
printk(KERN_DEBUG "set_cr4: #GP, clearing PAE while "
"in long mode\n");
inject_gp(vcpu);
return;
}
- } else if (is_paging(vcpu) && !is_pae(vcpu) && (cr4 & CR4_PAE_MASK)
+ } else if (is_paging(vcpu) && !is_pae(vcpu) && (cr4 & X86_CR4_PAE)
&& !load_pdptrs(vcpu, vcpu->cr3)) {
printk(KERN_DEBUG "set_cr4: #GP, pdptrs reserved bits\n");
inject_gp(vcpu);
+ return;
}
- if (cr4 & CR4_VMXE_MASK) {
+ if (cr4 & X86_CR4_VMXE) {
printk(KERN_DEBUG "set_cr4: #GP, setting VMXE\n");
inject_gp(vcpu);
return;
}
kvm_arch_ops->set_cr4(vcpu, cr4);
- spin_lock(&vcpu->kvm->lock);
+ mutex_lock(&vcpu->kvm->lock);
kvm_mmu_reset_context(vcpu);
- spin_unlock(&vcpu->kvm->lock);
+ mutex_unlock(&vcpu->kvm->lock);
}
EXPORT_SYMBOL_GPL(set_cr4);
void set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
{
if (is_long_mode(vcpu)) {
- if (cr3 & CR3_L_MODE_RESEVED_BITS) {
+ if (cr3 & CR3_L_MODE_RESERVED_BITS) {
printk(KERN_DEBUG "set_cr3: #GP, reserved bits\n");
inject_gp(vcpu);
return;
}
} else {
- if (cr3 & CR3_RESEVED_BITS) {
- printk(KERN_DEBUG "set_cr3: #GP, reserved bits\n");
- inject_gp(vcpu);
- return;
- }
- if (is_paging(vcpu) && is_pae(vcpu) &&
- !load_pdptrs(vcpu, cr3)) {
- printk(KERN_DEBUG "set_cr3: #GP, pdptrs "
- "reserved bits\n");
- inject_gp(vcpu);
- return;
+ if (is_pae(vcpu)) {
+ if (cr3 & CR3_PAE_RESERVED_BITS) {
+ printk(KERN_DEBUG
+ "set_cr3: #GP, reserved bits\n");
+ inject_gp(vcpu);
+ return;
+ }
+ if (is_paging(vcpu) && !load_pdptrs(vcpu, cr3)) {
+ printk(KERN_DEBUG "set_cr3: #GP, pdptrs "
+ "reserved bits\n");
+ inject_gp(vcpu);
+ return;
+ }
+ } else {
+ if (cr3 & CR3_NONPAE_RESERVED_BITS) {
+ printk(KERN_DEBUG
+ "set_cr3: #GP, reserved bits\n");
+ inject_gp(vcpu);
+ return;
+ }
}
}
vcpu->cr3 = cr3;
- spin_lock(&vcpu->kvm->lock);
+ mutex_lock(&vcpu->kvm->lock);
/*
* Does the new cr3 value map to physical memory? (Note, we
* catch an invalid cr3 even in real-mode, because it would
inject_gp(vcpu);
else
vcpu->mmu.new_cr3(vcpu);
- spin_unlock(&vcpu->kvm->lock);
+ mutex_unlock(&vcpu->kvm->lock);
}
EXPORT_SYMBOL_GPL(set_cr3);
void set_cr8(struct kvm_vcpu *vcpu, unsigned long cr8)
{
- if ( cr8 & CR8_RESEVED_BITS) {
+ if (cr8 & CR8_RESERVED_BITS) {
printk(KERN_DEBUG "set_cr8: #GP, reserved bits 0x%lx\n", cr8);
inject_gp(vcpu);
return;
}
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.
mem->flags &= ~KVM_MEM_LOG_DIRTY_PAGES;
raced:
- spin_lock(&kvm->lock);
+ mutex_lock(&kvm->lock);
memory_config_version = kvm->memory_config_version;
new = old = *memslot;
* Do memory allocations outside lock. memory_config_version will
* detect any races.
*/
- spin_unlock(&kvm->lock);
+ mutex_unlock(&kvm->lock);
/* Deallocate if slot is being removed */
if (!npages)
memset(new.dirty_bitmap, 0, dirty_bytes);
}
- spin_lock(&kvm->lock);
+ mutex_lock(&kvm->lock);
if (memory_config_version != kvm->memory_config_version) {
- spin_unlock(&kvm->lock);
+ mutex_unlock(&kvm->lock);
kvm_free_physmem_slot(&new, &old);
goto raced;
}
*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);
- }
+ mutex_unlock(&kvm->lock);
kvm_free_physmem_slot(&old, &new);
return 0;
out_unlock:
- spin_unlock(&kvm->lock);
+ mutex_unlock(&kvm->lock);
out_free:
kvm_free_physmem_slot(&new, &old);
out:
struct kvm_memory_slot *memslot;
int r, i;
int n;
- int cleared;
unsigned long any = 0;
- spin_lock(&kvm->lock);
+ mutex_lock(&kvm->lock);
/*
* Prevent changes to guest memory configuration even while the lock
* is not taken.
*/
++kvm->busy;
- spin_unlock(&kvm->lock);
+ mutex_unlock(&kvm->lock);
r = -EINVAL;
if (log->slot >= KVM_MEMORY_SLOTS)
goto out;
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);
- }
- }
+ mutex_lock(&kvm->lock);
+ kvm_mmu_slot_remove_write_access(kvm, log->slot);
+ kvm_flush_remote_tlbs(kvm);
+ memset(memslot->dirty_bitmap, 0, n);
+ mutex_unlock(&kvm->lock);
r = 0;
out:
- spin_lock(&kvm->lock);
+ mutex_lock(&kvm->lock);
--kvm->busy;
- spin_unlock(&kvm->lock);
+ mutex_unlock(&kvm->lock);
return r;
}
< alias->target_phys_addr)
goto out;
- spin_lock(&kvm->lock);
+ mutex_lock(&kvm->lock);
p = &kvm->aliases[alias->slot];
p->base_gfn = alias->guest_phys_addr >> PAGE_SHIFT;
break;
kvm->naliases = n;
- spin_unlock(&kvm->lock);
+ kvm_mmu_zap_all(kvm);
- vcpu_load(&kvm->vcpus[0]);
- spin_lock(&kvm->lock);
- kvm_mmu_zap_all(&kvm->vcpus[0]);
- spin_unlock(&kvm->lock);
- vcpu_put(&kvm->vcpus[0]);
+ mutex_unlock(&kvm->lock);
return 0;
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,
void *val,
unsigned int bytes,
{
struct page *page;
void *virt;
- unsigned offset = offset_in_page(gpa);
if (((gpa + bytes - 1) >> PAGE_SHIFT) != (gpa >> PAGE_SHIFT))
return 0;
return 0;
mark_page_dirty(vcpu->kvm, gpa >> PAGE_SHIFT);
virt = kmap_atomic(page, KM_USER0);
- kvm_mmu_pte_write(vcpu, gpa, virt + offset, val, bytes);
+ kvm_mmu_pte_write(vcpu, gpa, val, bytes);
memcpy(virt + offset_in_page(gpa), val, bytes);
kunmap_atomic(virt, KM_USER0);
return 1;
}
-static int emulator_write_emulated(unsigned long addr,
- const void *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;
struct kvm_io_device *mmio_dev;
return X86EMUL_CONTINUE;
}
+static int emulator_write_emulated(unsigned long addr,
+ const void *val,
+ unsigned int bytes,
+ struct x86_emulate_ctxt *ctxt)
+{
+ /* Crossing a page boundary? */
+ if (((addr + bytes - 1) ^ addr) & PAGE_MASK) {
+ int rc, now;
+
+ 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_onepage(addr, val, bytes, ctxt);
+}
+
static int emulator_cmpxchg_emulated(unsigned long addr,
const void *old,
const void *new,
{
unsigned long cr0;
- cr0 = vcpu->cr0 & ~CR0_TS_MASK;
+ cr0 = vcpu->cr0 & ~X86_CR0_TS;
kvm_arch_ops->set_cr0(vcpu, cr0);
return X86EMUL_CONTINUE;
}
r = x86_emulate_memop(&emulate_ctxt, &emulate_ops);
if ((r || vcpu->mmio_is_write) && run) {
+ run->exit_reason = KVM_EXIT_MMIO;
run->mmio.phys_addr = vcpu->mmio_phys_addr;
memcpy(run->mmio.data, vcpu->mmio_data, 8);
run->mmio.len = vcpu->mmio_size;
}
switch (nr) {
default:
+ run->hypercall.nr = nr;
run->hypercall.args[0] = a0;
run->hypercall.args[1] = a1;
run->hypercall.args[2] = a2;
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);
+ para_state = kmap(para_state_page);
printk(KERN_DEBUG ".... guest version: %d\n", para_state->guest_version);
printk(KERN_DEBUG ".... size: %d\n", para_state->size);
para_state->ret = 0;
err_kunmap_skip:
- kunmap_atomic(para_state, KM_USER0);
+ kunmap(para_state_page);
return 0;
err_gp:
return 1;
* 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);
}
* 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);
}
{
if (!need_resched())
return;
- vcpu_put(vcpu);
cond_resched();
- vcpu_load(vcpu);
}
EXPORT_SYMBOL_GPL(kvm_resched);
-void load_msrs(struct vmx_msr_entry *e, int n)
-{
- int i;
-
- for (i = 0; i < n; ++i)
- wrmsrl(e[i].index, e[i].data);
-}
-EXPORT_SYMBOL_GPL(load_msrs);
-
-void save_msrs(struct vmx_msr_entry *e, int n)
-{
- int i;
-
- for (i = 0; i < n; ++i)
- rdmsrl(e[i].index, e[i].data);
-}
-EXPORT_SYMBOL_GPL(save_msrs);
-
void kvm_emulate_cpuid(struct kvm_vcpu *vcpu)
{
int i;
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;
}
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;
}
return 0;
}
+static void kernel_pio(struct kvm_io_device *pio_dev,
+ struct kvm_vcpu *vcpu,
+ void *pd)
+{
+ /* TODO: String I/O for in kernel device */
+
+ if (vcpu->pio.in)
+ kvm_iodevice_read(pio_dev, vcpu->pio.port,
+ vcpu->pio.size,
+ pd);
+ else
+ kvm_iodevice_write(pio_dev, vcpu->pio.port,
+ vcpu->pio.size,
+ pd);
+}
+
+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;
+ int i;
+
+ for (i = 0; i < io->cur_count; i++) {
+ kvm_iodevice_write(pio_dev, io->port,
+ io->size,
+ pd);
+ pd += io->size;
+ }
+}
+
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 i, ret = 0;
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->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, vcpu->pio_data);
+ complete_pio(vcpu);
+ return 1;
+ }
return 0;
}
vcpu->pio.cur_count = now;
for (i = 0; i < nr_pages; ++i) {
- spin_lock(&vcpu->kvm->lock);
+ mutex_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);
+ mutex_unlock(&vcpu->kvm->lock);
if (!page) {
inject_gp(vcpu);
free_pio_guest_pages(vcpu);
}
}
- if (!vcpu->pio.in)
- return pio_copy_data(vcpu);
- return 0;
+ if (!vcpu->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)
+ ret = 1;
+ }
+ } else if (pio_dev)
+ printk(KERN_ERR "no string pio read support yet, "
+ "port %x size %d count %ld\n",
+ port, size, count);
+
+ return ret;
}
EXPORT_SYMBOL_GPL(kvm_setup_pio);
/*
* Read-modify-write. Back to userspace.
*/
- kvm_run->exit_reason = KVM_EXIT_MMIO;
r = 0;
goto out;
}
memcpy(vcpu->irq_pending, sregs->interrupt_bitmap,
sizeof vcpu->irq_pending);
vcpu->irq_summary = 0;
- for (i = 0; i < NR_IRQ_WORDS; ++i)
+ for (i = 0; i < ARRAY_SIZE(vcpu->irq_pending); ++i)
if (vcpu->irq_pending[i])
__set_bit(i, &vcpu->irq_summary);
*/
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);
}
/*
gpa_t gpa;
vcpu_load(vcpu);
- spin_lock(&vcpu->kvm->lock);
+ mutex_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(&vcpu->kvm->lock);
+ mutex_unlock(&vcpu->kvm->lock);
vcpu_put(vcpu);
return 0;
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
return NOPAGE_SIGBUS;
get_page(page);
+ if (type != NULL)
+ *type = VM_FAULT_MINOR;
+
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;
}
/*
{
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;
- vcpu->cr0 = 0x10;
+ return -EINVAL;
- r = kvm_arch_ops->vcpu_create(vcpu);
- if (r < 0)
- goto out_free_vcpus;
+ vcpu = kvm_arch_ops->vcpu_create(kvm, n);
+ if (IS_ERR(vcpu))
+ return PTR_ERR(vcpu);
- r = kvm_mmu_create(vcpu);
- if (r < 0)
- goto out_free_vcpus;
+ preempt_notifier_init(&vcpu->preempt_notifier, &kvm_preempt_ops);
- kvm_arch_ops->vcpu_load(vcpu);
+ 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;
+ goto free_vcpu;
+ mutex_lock(&kvm->lock);
+ if (kvm->vcpus[n]) {
+ r = -EEXIST;
+ mutex_unlock(&kvm->lock);
+ goto mmu_unload;
+ }
+ kvm->vcpus[n] = vcpu;
+ mutex_unlock(&kvm->lock);
+
+ /* Now it's all set up, let userspace reach it */
r = create_vcpu_fd(vcpu);
if (r < 0)
- goto out_free_vcpus;
+ goto unlink;
+ return r;
- spin_lock(&kvm_lock);
- if (n >= kvm->nvcpus)
- kvm->nvcpus = n + 1;
- spin_unlock(&kvm_lock);
+unlink:
+ mutex_lock(&kvm->lock);
+ kvm->vcpus[n] = NULL;
+ mutex_unlock(&kvm->lock);
- return r;
+mmu_unload:
+ vcpu_load(vcpu);
+ kvm_mmu_unload(vcpu);
+ vcpu_put(vcpu);
-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:
+free_vcpu:
+ kvm_arch_ops->vcpu_free(vcpu);
return r;
}
break;
}
}
- if (entry && (entry->edx & EFER_NX) && !(efer & EFER_NX)) {
+ if (entry && (entry->edx & (1 << 20)) && !(efer & EFER_NX)) {
entry->edx &= ~(1 << 20);
- printk(KERN_INFO ": guest NX capability removed\n");
+ printk(KERN_INFO "kvm: guest NX capability removed\n");
}
}
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);
unsigned long pgoff;
struct page *page;
- *type = VM_FAULT_MINOR;
pgoff = ((address - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;
page = gfn_to_page(kvm, pgoff);
if (!page)
return NOPAGE_SIGBUS;
get_page(page);
+ if (type != NULL)
+ *type = VM_FAULT_MINOR;
+
return 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,
&kvm_chardev_ops,
};
-static int kvm_reboot(struct notifier_block *notifier, unsigned long val,
- void *v)
-{
- if (val == SYS_RESTART) {
- /*
- * Some (well, at least mine) BIOSes hang on reboot if
- * in vmx root mode.
- */
- printk(KERN_INFO "kvm: exiting hardware virtualization\n");
- on_each_cpu(kvm_arch_ops->hardware_disable, NULL, 0, 1);
- }
- return NOTIFY_OK;
-}
-
-static struct notifier_block kvm_reboot_notifier = {
- .notifier_call = kvm_reboot,
- .priority = 0,
-};
-
/*
* Make sure that a cpu that is being hot-unplugged does not have any vcpus
* cached on it.
spin_lock(&kvm_lock);
list_for_each_entry(vm, &vm_list, vm_list)
for (i = 0; i < KVM_MAX_VCPUS; ++i) {
- vcpu = &vm->vcpus[i];
+ vcpu = vm->vcpus[i];
+ if (!vcpu)
+ continue;
/*
* If the vcpu is locked, then it is running on some
* other cpu and therefore it is not cached on the
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_DOWN_PREPARE_FROZEN:
+ case CPU_DYING:
+ case CPU_DYING_FROZEN:
+ printk(KERN_INFO "kvm: disabling virtualization on CPU%d\n",
+ cpu);
+ hardware_disable(NULL);
+ break;
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;
}
+static int kvm_reboot(struct notifier_block *notifier, unsigned long val,
+ void *v)
+{
+ if (val == SYS_RESTART) {
+ /*
+ * Some (well, at least mine) BIOSes hang on reboot if
+ * in vmx root mode.
+ */
+ printk(KERN_INFO "kvm: exiting hardware virtualization\n");
+ on_each_cpu(hardware_disable, NULL, 0, 1);
+ }
+ return NOTIFY_OK;
+}
+
+static struct notifier_block kvm_reboot_notifier = {
+ .notifier_call = kvm_reboot,
+ .priority = 0,
+};
+
void kvm_io_bus_init(struct kvm_io_bus *bus)
{
memset(bus, 0, sizeof(*bus));
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);
+ vcpu = kvm->vcpus[i];
+ if (vcpu)
+ total += *(u32 *)((void *)vcpu + offset);
}
spin_unlock(&kvm_lock);
return total;
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)
+static inline
+struct kvm_vcpu *preempt_notifier_to_vcpu(struct preempt_notifier *pn)
{
- return get_sb_pseudo(fs_type, "kvm:", NULL, KVMFS_SUPER_MAGIC, mnt);
+ return container_of(pn, struct kvm_vcpu, preempt_notifier);
}
-static struct file_system_type kvm_fs_type = {
- .name = "kvmfs",
- .get_sb = kvmfs_get_sb,
- .kill_sb = kill_anon_super,
-};
+static void kvm_sched_in(struct preempt_notifier *pn, int cpu)
+{
+ struct kvm_vcpu *vcpu = preempt_notifier_to_vcpu(pn);
+
+ kvm_arch_ops->vcpu_load(vcpu, cpu);
+}
+
+static void kvm_sched_out(struct preempt_notifier *pn,
+ struct task_struct *next)
+{
+ struct kvm_vcpu *vcpu = preempt_notifier_to_vcpu(pn);
+
+ kvm_arch_ops->vcpu_put(vcpu);
+}
int kvm_init_arch(struct kvm_arch_ops *ops, struct module *module)
{
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;
goto out_free;
}
+ kvm_preempt_ops.sched_in = kvm_sched_in;
+ kvm_preempt_ops.sched_out = kvm_sched_out;
+
return r;
out_free:
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;
}
if (r)
goto out4;
- r = register_filesystem(&kvm_fs_type);
- if (r)
- goto out3;
-
- 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();
}
projects / linux-2.6 / blobdiff