#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 <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 "x86_emulate.h"
#include "segment_descriptor.h"
MODULE_AUTHOR("Qumranet");
MODULE_LICENSE("GPL");
+static DEFINE_SPINLOCK(kvm_lock);
+static LIST_HEAD(vm_list);
+
struct kvm_arch_ops *kvm_arch_ops;
struct kvm_stat kvm_stat;
EXPORT_SYMBOL_GPL(kvm_stat);
{ "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 },
- { 0, 0 }
+ { NULL, NULL }
};
static struct dentry *debugfs_dir;
+struct vfsmount *kvmfs_mnt;
+
#define MAX_IO_MSRS 256
#define CR0_RESEVED_BITS 0xffffffff1ffaffc0ULL
#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;
+ 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;
return likely(n >= 0 && n < KVM_MAX_VCPUS);
}
-int kvm_read_guest(struct kvm_vcpu *vcpu,
- gva_t addr,
- unsigned long size,
- void *dest)
+int kvm_read_guest(struct kvm_vcpu *vcpu, gva_t addr, unsigned long size,
+ void *dest)
{
unsigned char *host_buf = dest;
unsigned long req_size = size;
}
EXPORT_SYMBOL_GPL(kvm_read_guest);
-int kvm_write_guest(struct kvm_vcpu *vcpu,
- gva_t addr,
- unsigned long size,
- void *data)
+int kvm_write_guest(struct kvm_vcpu *vcpu, gva_t addr, unsigned long size,
+ void *data)
{
unsigned char *host_buf = data;
unsigned long req_size = size;
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 0;
+ 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)
mutex_unlock(&vcpu->mutex);
}
-static int kvm_dev_open(struct inode *inode, struct file *filp)
+static struct kvm *kvm_create_vm(void)
{
struct kvm *kvm = kzalloc(sizeof(struct kvm), GFP_KERNEL);
int i;
if (!kvm)
- return -ENOMEM;
+ return ERR_PTR(-ENOMEM);
spin_lock_init(&kvm->lock);
INIT_LIST_HEAD(&kvm->active_mmu_pages);
struct kvm_vcpu *vcpu = &kvm->vcpus[i];
mutex_init(&vcpu->mutex);
+ 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);
}
- filp->private_data = kvm;
+ return kvm;
+}
+
+static int kvm_dev_open(struct inode *inode, struct file *filp)
+{
return 0;
}
if (!dont || free->phys_mem != dont->phys_mem)
if (free->phys_mem) {
for (i = 0; i < free->npages; ++i)
- __free_page(free->phys_mem[i]);
+ if (free->phys_mem[i])
+ __free_page(free->phys_mem[i]);
vfree(free->phys_mem);
}
if (!dont || free->dirty_bitmap != dont->dirty_bitmap)
vfree(free->dirty_bitmap);
- free->phys_mem = 0;
+ free->phys_mem = NULL;
free->npages = 0;
- free->dirty_bitmap = 0;
+ free->dirty_bitmap = NULL;
}
static void kvm_free_physmem(struct kvm *kvm)
int i;
for (i = 0; i < kvm->nmemslots; ++i)
- kvm_free_physmem_slot(&kvm->memslots[i], 0);
+ kvm_free_physmem_slot(&kvm->memslots[i], NULL);
}
static void kvm_free_vcpu(struct kvm_vcpu *vcpu)
{
- kvm_arch_ops->vcpu_free(vcpu);
+ if (!vcpu->vmcs)
+ return;
+
+ vcpu_load(vcpu);
kvm_mmu_destroy(vcpu);
+ vcpu_put(vcpu);
+ kvm_arch_ops->vcpu_free(vcpu);
}
static void kvm_free_vcpus(struct kvm *kvm)
static int kvm_dev_release(struct inode *inode, struct file *filp)
{
- struct kvm *kvm = filp->private_data;
+ return 0;
+}
+static void kvm_destroy_vm(struct kvm *kvm)
+{
+ spin_lock(&kvm_lock);
+ list_del(&kvm->vm_list);
+ spin_unlock(&kvm_lock);
kvm_free_vcpus(kvm);
kvm_free_physmem(kvm);
kfree(kvm);
+}
+
+static int kvm_vm_release(struct inode *inode, struct file *filp)
+{
+ struct kvm *kvm = filp->private_data;
+
+ kvm_destroy_vm(kvm);
return 0;
}
kvm_arch_ops->inject_gp(vcpu, 0);
}
-static int pdptrs_have_reserved_bits_set(struct kvm_vcpu *vcpu,
- unsigned long cr3)
+/*
+ * Load the pae pdptrs. Return true is they are all valid.
+ */
+static int load_pdptrs(struct kvm_vcpu *vcpu, unsigned long cr3)
{
gfn_t pdpt_gfn = cr3 >> PAGE_SHIFT;
- unsigned offset = (cr3 & (PAGE_SIZE-1)) >> 5;
+ unsigned offset = ((cr3 & (PAGE_SIZE-1)) >> 5) << 2;
int i;
u64 pdpte;
u64 *pdpt;
+ int ret;
struct kvm_memory_slot *memslot;
spin_lock(&vcpu->kvm->lock);
/* FIXME: !memslot - emulate? 0xff? */
pdpt = kmap_atomic(gfn_to_page(memslot, pdpt_gfn), KM_USER0);
+ ret = 1;
for (i = 0; i < 4; ++i) {
pdpte = pdpt[offset + i];
- if ((pdpte & 1) && (pdpte & 0xfffffff0000001e6ull))
- break;
+ if ((pdpte & 1) && (pdpte & 0xfffffff0000001e6ull)) {
+ ret = 0;
+ goto out;
+ }
}
+ for (i = 0; i < 4; ++i)
+ vcpu->pdptrs[i] = pdpt[offset + i];
+
+out:
kunmap_atomic(pdpt, KM_USER0);
spin_unlock(&vcpu->kvm->lock);
- return i != 4;
+ return ret;
}
void set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
}
} else
#endif
- if (is_pae(vcpu) &&
- pdptrs_have_reserved_bits_set(vcpu, vcpu->cr3)) {
+ if (is_pae(vcpu) && !load_pdptrs(vcpu, vcpu->cr3)) {
printk(KERN_DEBUG "set_cr0: #GP, pdptrs "
"reserved bits\n");
inject_gp(vcpu);
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);
return;
}
- if (kvm_arch_ops->is_long_mode(vcpu)) {
+ if (is_long_mode(vcpu)) {
if (!(cr4 & CR4_PAE_MASK)) {
printk(KERN_DEBUG "set_cr4: #GP, clearing PAE while "
"in long mode\n");
return;
}
} else if (is_paging(vcpu) && !is_pae(vcpu) && (cr4 & CR4_PAE_MASK)
- && pdptrs_have_reserved_bits_set(vcpu, vcpu->cr3)) {
+ && !load_pdptrs(vcpu, vcpu->cr3)) {
printk(KERN_DEBUG "set_cr4: #GP, pdptrs reserved bits\n");
inject_gp(vcpu);
}
void set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
{
- if (kvm_arch_ops->is_long_mode(vcpu)) {
- if ( cr3 & CR3_L_MODE_RESEVED_BITS) {
+ if (is_long_mode(vcpu)) {
+ if (cr3 & CR3_L_MODE_RESEVED_BITS) {
printk(KERN_DEBUG "set_cr3: #GP, reserved bits\n");
inject_gp(vcpu);
return;
return;
}
if (is_paging(vcpu) && is_pae(vcpu) &&
- pdptrs_have_reserved_bits_set(vcpu, cr3)) {
+ !load_pdptrs(vcpu, cr3)) {
printk(KERN_DEBUG "set_cr3: #GP, pdptrs "
"reserved bits\n");
inject_gp(vcpu);
vcpu->cr3 = cr3;
spin_lock(&vcpu->kvm->lock);
- vcpu->mmu.new_cr3(vcpu);
+ /*
+ * Does the new cr3 value map to physical memory? (Note, we
+ * catch an invalid cr3 even in real-mode, because it would
+ * cause trouble later on when we turn on paging anyway.)
+ *
+ * A real CPU would silently accept an invalid cr3 and would
+ * attempt to use it - with largely undefined (and often hard
+ * to debug) behavior on the guest side.
+ */
+ if (unlikely(!gfn_to_memslot(vcpu->kvm, cr3 >> PAGE_SHIFT)))
+ inject_gp(vcpu);
+ else
+ vcpu->mmu.new_cr3(vcpu);
spin_unlock(&vcpu->kvm->lock);
}
EXPORT_SYMBOL_GPL(set_cr3);
}
EXPORT_SYMBOL_GPL(fx_init);
-/*
- * Creates some virtual cpus. Good luck creating more than one.
- */
-static int kvm_dev_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;
-
- vcpu->cpu = -1; /* First load will set up TR */
- vcpu->kvm = kvm;
- r = kvm_arch_ops->vcpu_create(vcpu);
- if (r < 0)
- goto out_free_vcpus;
-
- kvm_arch_ops->vcpu_load(vcpu);
-
- r = kvm_arch_ops->vcpu_setup(vcpu);
- if (r >= 0)
- r = kvm_mmu_init(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);
}
/*
*
* Discontiguous memory is allowed, mostly for framebuffers.
*/
-static int kvm_dev_ioctl_set_memory_region(struct kvm *kvm,
- struct kvm_memory_region *mem)
+static int kvm_vm_ioctl_set_memory_region(struct kvm *kvm,
+ struct kvm_memory_region *mem)
{
int r;
gfn_t base_gfn;
/* Deallocate if slot is being removed */
if (!npages)
- new.phys_mem = 0;
+ new.phys_mem = NULL;
/* Free page dirty bitmap if unneeded */
if (!(new.flags & KVM_MEM_LOG_DIRTY_PAGES))
- new.dirty_bitmap = 0;
+ new.dirty_bitmap = NULL;
r = -ENOMEM;
| __GFP_ZERO);
if (!new.phys_mem[i])
goto out_free;
+ set_page_private(new.phys_mem[i],0);
}
}
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);
}
/*
* Get (and clear) the dirty memory log for a memory slot.
*/
-static int kvm_dev_ioctl_get_dirty_log(struct kvm *kvm,
- struct kvm_dirty_log *log)
+static int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
+ struct kvm_dirty_log *log)
{
struct kvm_memory_slot *memslot;
int r, i;
int n;
+ int cleared;
unsigned long any = 0;
spin_lock(&kvm->lock);
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 (copy_to_user(log->dirty_bitmap, memslot->dirty_bitmap, n))
goto out;
-
if (any) {
- spin_lock(&kvm->lock);
- kvm_mmu_slot_remove_write_access(kvm, log->slot);
- spin_unlock(&kvm->lock);
- memset(memslot->dirty_bitmap, 0, n);
+ 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) {
+ do_remove_write_access(vcpu, log->slot);
+ memset(memslot->dirty_bitmap, 0, n);
+ cleared = 1;
+ }
kvm_arch_ops->tlb_flush(vcpu);
vcpu_put(vcpu);
}
&& gfn < memslot->base_gfn + memslot->npages)
return memslot;
}
- return 0;
+ return NULL;
}
EXPORT_SYMBOL_GPL(gfn_to_memslot);
void mark_page_dirty(struct kvm *kvm, gfn_t gfn)
{
int i;
- struct kvm_memory_slot *memslot = 0;
+ struct kvm_memory_slot *memslot = NULL;
unsigned long rel_gfn;
for (i = 0; i < kvm->nmemslots; ++i) {
return X86EMUL_CONTINUE;
else {
gpa_t gpa = vcpu->mmu.gva_to_gpa(vcpu, addr);
+
if (gpa == UNMAPPED_GVA)
- return vcpu_printf(vcpu, "not present\n"), X86EMUL_PROPAGATE_FAULT;
+ return X86EMUL_PROPAGATE_FAULT;
vcpu->mmio_needed = 1;
vcpu->mmio_phys_addr = gpa;
vcpu->mmio_size = bytes;
}
}
+static int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa,
+ unsigned long val, int bytes)
+{
+ struct kvm_memory_slot *m;
+ struct page *page;
+ void *virt;
+
+ if (((gpa + bytes - 1) >> PAGE_SHIFT) != (gpa >> PAGE_SHIFT))
+ return 0;
+ m = gfn_to_memslot(vcpu->kvm, gpa >> PAGE_SHIFT);
+ if (!m)
+ 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);
+ kvm_mmu_post_write(vcpu, gpa, bytes);
+ return 1;
+}
+
static int emulator_write_emulated(unsigned long addr,
unsigned long val,
unsigned int bytes,
if (gpa == UNMAPPED_GVA)
return X86EMUL_PROPAGATE_FAULT;
+ if (emulator_write_phys(vcpu, gpa, val, bytes))
+ return X86EMUL_CONTINUE;
+
vcpu->mmio_needed = 1;
vcpu->mmio_phys_addr = gpa;
vcpu->mmio_size = bytes;
return emulator_write_emulated(addr, new, 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 reported;
+ int r;
+
+ if (!reported) {
+ reported = 1;
+ printk(KERN_WARNING "kvm: emulating exchange8b 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);
+}
+
+#endif
+
static unsigned long get_segment_base(struct kvm_vcpu *vcpu, int seg)
{
return kvm_arch_ops->get_segment_base(vcpu, seg);
int emulate_invlpg(struct kvm_vcpu *vcpu, gva_t address)
{
- spin_lock(&vcpu->kvm->lock);
- vcpu->mmu.inval_page(vcpu, address);
- spin_unlock(&vcpu->kvm->lock);
- kvm_arch_ops->invlpg(vcpu, address);
return X86EMUL_CONTINUE;
}
int emulate_clts(struct kvm_vcpu *vcpu)
{
- unsigned long cr0 = vcpu->cr0;
+ unsigned long cr0;
- cr0 &= ~CR0_TS_MASK;
+ 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,
}
if (r) {
+ if (kvm_mmu_unprotect_page_virt(vcpu, cr2))
+ return EMULATE_DONE;
if (!vcpu->mmio_needed) {
report_emulation_failure(&emulate_ctxt);
return EMULATE_FAIL;
}
EXPORT_SYMBOL_GPL(emulate_instruction);
+int kvm_hypercall(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+ unsigned long nr, a0, a1, a2, a3, a4, a5, ret;
+
+ kvm_arch_ops->cache_regs(vcpu);
+ ret = -KVM_EINVAL;
+#ifdef CONFIG_X86_64
+ if (is_long_mode(vcpu)) {
+ nr = vcpu->regs[VCPU_REGS_RAX];
+ a0 = vcpu->regs[VCPU_REGS_RDI];
+ a1 = vcpu->regs[VCPU_REGS_RSI];
+ a2 = vcpu->regs[VCPU_REGS_RDX];
+ a3 = vcpu->regs[VCPU_REGS_RCX];
+ a4 = vcpu->regs[VCPU_REGS_R8];
+ a5 = vcpu->regs[VCPU_REGS_R9];
+ } else
+#endif
+ {
+ nr = vcpu->regs[VCPU_REGS_RBX] & -1u;
+ a0 = vcpu->regs[VCPU_REGS_RAX] & -1u;
+ a1 = vcpu->regs[VCPU_REGS_RCX] & -1u;
+ a2 = vcpu->regs[VCPU_REGS_RDX] & -1u;
+ a3 = vcpu->regs[VCPU_REGS_RSI] & -1u;
+ a4 = vcpu->regs[VCPU_REGS_RDI] & -1u;
+ a5 = vcpu->regs[VCPU_REGS_RBP] & -1u;
+ }
+ switch (nr) {
+ default:
+ ;
+ }
+ vcpu->regs[VCPU_REGS_RAX] = ret;
+ kvm_arch_ops->decache_regs(vcpu);
+ return 1;
+}
+EXPORT_SYMBOL_GPL(kvm_hypercall);
+
static u64 mk_cr_64(u64 curr_cr, u32 new_val)
{
return (curr_cr & ~((1ULL << 32) - 1)) | new_val;
unsigned long realmode_get_cr(struct kvm_vcpu *vcpu, int cr)
{
+ kvm_arch_ops->decache_cr0_cr4_guest_bits(vcpu);
switch (cr) {
case 0:
return vcpu->cr0;
}
/*
+ * Register the para guest with the host:
+ */
+static int vcpu_register_para(struct kvm_vcpu *vcpu, gpa_t para_state_gpa)
+{
+ struct kvm_vcpu_para_state *para_state;
+ hpa_t para_state_hpa, hypercall_hpa;
+ struct page *para_state_page;
+ unsigned char *hypercall;
+ gpa_t hypercall_gpa;
+
+ printk(KERN_DEBUG "kvm: guest trying to enter paravirtual mode\n");
+ printk(KERN_DEBUG ".... para_state_gpa: %08Lx\n", para_state_gpa);
+
+ /*
+ * Needs to be page aligned:
+ */
+ if (para_state_gpa != PAGE_ALIGN(para_state_gpa))
+ goto err_gp;
+
+ para_state_hpa = gpa_to_hpa(vcpu, para_state_gpa);
+ printk(KERN_DEBUG ".... para_state_hpa: %08Lx\n", para_state_hpa);
+ if (is_error_hpa(para_state_hpa))
+ goto err_gp;
+
+ mark_page_dirty(vcpu->kvm, para_state_gpa >> PAGE_SHIFT);
+ para_state_page = pfn_to_page(para_state_hpa >> PAGE_SHIFT);
+ para_state = kmap_atomic(para_state_page, KM_USER0);
+
+ printk(KERN_DEBUG ".... guest version: %d\n", para_state->guest_version);
+ printk(KERN_DEBUG ".... size: %d\n", para_state->size);
+
+ para_state->host_version = KVM_PARA_API_VERSION;
+ /*
+ * We cannot support guests that try to register themselves
+ * with a newer API version than the host supports:
+ */
+ if (para_state->guest_version > KVM_PARA_API_VERSION) {
+ para_state->ret = -KVM_EINVAL;
+ goto err_kunmap_skip;
+ }
+
+ hypercall_gpa = para_state->hypercall_gpa;
+ hypercall_hpa = gpa_to_hpa(vcpu, hypercall_gpa);
+ printk(KERN_DEBUG ".... hypercall_hpa: %08Lx\n", hypercall_hpa);
+ if (is_error_hpa(hypercall_hpa)) {
+ para_state->ret = -KVM_EINVAL;
+ goto err_kunmap_skip;
+ }
+
+ printk(KERN_DEBUG "kvm: para guest successfully registered.\n");
+ vcpu->para_state_page = para_state_page;
+ vcpu->para_state_gpa = para_state_gpa;
+ vcpu->hypercall_gpa = hypercall_gpa;
+
+ mark_page_dirty(vcpu->kvm, hypercall_gpa >> PAGE_SHIFT);
+ hypercall = kmap_atomic(pfn_to_page(hypercall_hpa >> PAGE_SHIFT),
+ KM_USER1) + (hypercall_hpa & ~PAGE_MASK);
+ kvm_arch_ops->patch_hypercall(vcpu, hypercall);
+ kunmap_atomic(hypercall, KM_USER1);
+
+ para_state->ret = 0;
+err_kunmap_skip:
+ kunmap_atomic(para_state, KM_USER0);
+ return 0;
+err_gp:
+ return 1;
+}
+
+int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
+{
+ u64 data;
+
+ switch (msr) {
+ case 0xc0010010: /* SYSCFG */
+ case 0xc0010015: /* HWCR */
+ case MSR_IA32_PLATFORM_ID:
+ case MSR_IA32_P5_MC_ADDR:
+ case MSR_IA32_P5_MC_TYPE:
+ case MSR_IA32_MC0_CTL:
+ case MSR_IA32_MCG_STATUS:
+ case MSR_IA32_MCG_CAP:
+ case MSR_IA32_MC0_MISC:
+ case MSR_IA32_MC0_MISC+4:
+ case MSR_IA32_MC0_MISC+8:
+ case MSR_IA32_MC0_MISC+12:
+ case MSR_IA32_MC0_MISC+16:
+ case MSR_IA32_UCODE_REV:
+ case MSR_IA32_PERF_STATUS:
+ /* MTRR registers */
+ case 0xfe:
+ case 0x200 ... 0x2ff:
+ data = 0;
+ break;
+ case 0xcd: /* fsb frequency */
+ data = 3;
+ break;
+ case MSR_IA32_APICBASE:
+ data = vcpu->apic_base;
+ break;
+ case MSR_IA32_MISC_ENABLE:
+ data = vcpu->ia32_misc_enable_msr;
+ break;
+#ifdef CONFIG_X86_64
+ case MSR_EFER:
+ data = vcpu->shadow_efer;
+ break;
+#endif
+ default:
+ printk(KERN_ERR "kvm: unhandled rdmsr: 0x%x\n", msr);
+ return 1;
+ }
+ *pdata = data;
+ return 0;
+}
+EXPORT_SYMBOL_GPL(kvm_get_msr_common);
+
+/*
* Reads an msr value (of 'msr_index') into 'pdata'.
* Returns 0 on success, non-0 otherwise.
* Assumes vcpu_load() was already called.
#ifdef CONFIG_X86_64
-void set_efer(struct kvm_vcpu *vcpu, u64 efer)
+static void set_efer(struct kvm_vcpu *vcpu, u64 efer)
{
if (efer & EFER_RESERVED_BITS) {
printk(KERN_DEBUG "set_efer: 0x%llx #GP, reserved bits\n",
vcpu->shadow_efer = efer;
}
-EXPORT_SYMBOL_GPL(set_efer);
#endif
+int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)
+{
+ switch (msr) {
+#ifdef CONFIG_X86_64
+ case MSR_EFER:
+ set_efer(vcpu, data);
+ break;
+#endif
+ case MSR_IA32_MC0_STATUS:
+ printk(KERN_WARNING "%s: MSR_IA32_MC0_STATUS 0x%llx, nop\n",
+ __FUNCTION__, data);
+ break;
+ case MSR_IA32_UCODE_REV:
+ case MSR_IA32_UCODE_WRITE:
+ case 0x200 ... 0x2ff: /* MTRRs */
+ break;
+ case MSR_IA32_APICBASE:
+ vcpu->apic_base = data;
+ break;
+ case MSR_IA32_MISC_ENABLE:
+ vcpu->ia32_misc_enable_msr = data;
+ break;
+ /*
+ * This is the 'probe whether the host is KVM' logic:
+ */
+ case MSR_KVM_API_MAGIC:
+ return vcpu_register_para(vcpu, data);
+
+ default:
+ printk(KERN_ERR "kvm: unhandled wrmsr: 0x%x\n", msr);
+ return 1;
+ }
+ return 0;
+}
+EXPORT_SYMBOL_GPL(kvm_set_msr_common);
+
/*
* Writes msr value into into the appropriate "register".
* Returns 0 on success, non-0 otherwise.
{
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_dev_ioctl_run(struct kvm *kvm, struct kvm_run *kvm_run)
+static int kvm_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
{
- struct kvm_vcpu *vcpu;
int r;
- if (!valid_vcpu(kvm_run->vcpu))
- return -EINVAL;
+ vcpu_load(vcpu);
- vcpu = vcpu_load(kvm, kvm_run->vcpu);
- if (!vcpu)
- return -ENOENT;
+ /* re-sync apic's tpr */
+ vcpu->cr8 = kvm_run->cr8;
if (kvm_run->emulated) {
kvm_arch_ops->skip_emulated_instruction(vcpu);
return r;
}
-static int kvm_dev_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_dev_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_dev_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);
sregs->gdt.limit = dt.limit;
sregs->gdt.base = dt.base;
+ kvm_arch_ops->decache_cr0_cr4_guest_bits(vcpu);
sregs->cr0 = vcpu->cr0;
sregs->cr2 = vcpu->cr2;
sregs->cr3 = vcpu->cr3;
return kvm_arch_ops->set_segment(vcpu, var, seg);
}
-static int kvm_dev_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;
+ vcpu_load(vcpu);
set_segment(vcpu, &sregs->cs, VCPU_SREG_CS);
set_segment(vcpu, &sregs->ds, VCPU_SREG_DS);
#endif
vcpu->apic_base = sregs->apic_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);
mmu_reset_needed |= vcpu->cr4 != sregs->cr4;
kvm_arch_ops->set_cr4(vcpu, sregs->cr4);
+ if (!is_long_mode(vcpu) && is_pae(vcpu))
+ load_pdptrs(vcpu, vcpu->cr3);
if (mmu_reset_needed)
kvm_mmu_reset_context(vcpu);
static unsigned num_msrs_to_save;
+static u32 emulated_msrs[] = {
+ MSR_IA32_MISC_ENABLE,
+};
+
static __init void kvm_init_msr_list(void)
{
u32 dummy[2];
*
* @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_dev_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_dev_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_dev_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_dev_ioctl(struct file *filp,
- unsigned int ioctl, unsigned long arg)
+static int kvm_vcpu_release(struct inode *inode, struct file *filp)
{
- struct kvm *kvm = filp->private_data;
+ 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,
+};
+
+/*
+ * 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;
+
+ 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;
+
+ r = create_vcpu_fd(vcpu);
+ if (r < 0)
+ goto out_free_vcpus;
+
+ return r;
+
+out_free_vcpus:
+ kvm_free_vcpu(vcpu);
+ mutex_unlock(&vcpu->mutex);
+out:
+ return r;
+}
+
+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_GET_API_VERSION:
- r = KVM_API_VERSION;
- break;
- case KVM_CREATE_VCPU: {
- r = kvm_dev_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, (void *)arg, sizeof kvm_run))
+ if (copy_from_user(&kvm_run, argp, sizeof kvm_run))
goto out;
- r = kvm_dev_ioctl_run(kvm, &kvm_run);
- if (r < 0)
+ r = kvm_vcpu_ioctl_run(vcpu, &kvm_run);
+ if (r < 0 && r != -EINTR)
goto out;
- r = -EFAULT;
- if (copy_to_user((void *)arg, &kvm_run, sizeof kvm_run))
+ if (copy_to_user(argp, &kvm_run, sizeof kvm_run)) {
+ r = -EFAULT;
goto out;
- r = 0;
+ }
break;
}
case KVM_GET_REGS: {
struct kvm_regs kvm_regs;
- r = -EFAULT;
- if (copy_from_user(&kvm_regs, (void *)arg, sizeof kvm_regs))
- goto out;
- r = kvm_dev_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;
- if (copy_to_user((void *)arg, &kvm_regs, sizeof kvm_regs))
+ if (copy_to_user(argp, &kvm_regs, sizeof kvm_regs))
goto out;
r = 0;
break;
struct kvm_regs kvm_regs;
r = -EFAULT;
- if (copy_from_user(&kvm_regs, (void *)arg, sizeof kvm_regs))
+ if (copy_from_user(&kvm_regs, argp, sizeof kvm_regs))
goto out;
- r = kvm_dev_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, (void *)arg, sizeof kvm_sregs))
- goto out;
- r = kvm_dev_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;
- if (copy_to_user((void *)arg, &kvm_sregs, sizeof kvm_sregs))
+ if (copy_to_user(argp, &kvm_sregs, sizeof kvm_sregs))
goto out;
r = 0;
break;
struct kvm_sregs kvm_sregs;
r = -EFAULT;
- if (copy_from_user(&kvm_sregs, (void *)arg, sizeof kvm_sregs))
+ if (copy_from_user(&kvm_sregs, argp, sizeof kvm_sregs))
goto out;
- r = kvm_dev_ioctl_set_sregs(kvm, &kvm_sregs);
+ r = kvm_vcpu_ioctl_set_sregs(vcpu, &kvm_sregs);
if (r)
goto out;
r = 0;
struct kvm_translation tr;
r = -EFAULT;
- if (copy_from_user(&tr, (void *)arg, sizeof tr))
+ if (copy_from_user(&tr, argp, sizeof tr))
goto out;
- r = kvm_dev_ioctl_translate(kvm, &tr);
+ r = kvm_vcpu_ioctl_translate(vcpu, &tr);
if (r)
goto out;
r = -EFAULT;
- if (copy_to_user((void *)arg, &tr, sizeof tr))
+ if (copy_to_user(argp, &tr, sizeof tr))
goto out;
r = 0;
break;
struct kvm_interrupt irq;
r = -EFAULT;
- if (copy_from_user(&irq, (void *)arg, sizeof irq))
+ if (copy_from_user(&irq, argp, sizeof irq))
goto out;
- r = kvm_dev_ioctl_interrupt(kvm, &irq);
+ r = kvm_vcpu_ioctl_interrupt(vcpu, &irq);
if (r)
goto out;
r = 0;
struct kvm_debug_guest dbg;
r = -EFAULT;
- if (copy_from_user(&dbg, (void *)arg, sizeof dbg))
+ if (copy_from_user(&dbg, argp, sizeof dbg))
goto out;
- r = kvm_dev_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;
+ 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;
r = -EFAULT;
- if (copy_from_user(&kvm_mem, (void *)arg, sizeof kvm_mem))
+ if (copy_from_user(&kvm_mem, argp, sizeof kvm_mem))
goto out;
- r = kvm_dev_ioctl_set_memory_region(kvm, &kvm_mem);
+ r = kvm_vm_ioctl_set_memory_region(kvm, &kvm_mem);
if (r)
goto out;
break;
struct kvm_dirty_log log;
r = -EFAULT;
- if (copy_from_user(&log, (void *)arg, sizeof log))
+ if (copy_from_user(&log, argp, sizeof log))
goto out;
- r = kvm_dev_ioctl_get_dirty_log(kvm, &log);
+ r = kvm_vm_ioctl_get_dirty_log(kvm, &log);
if (r)
goto out;
break;
}
- case KVM_GET_MSRS:
- r = msr_io(kvm, (void __user *)arg, get_msr, 1);
- break;
- case KVM_SET_MSRS:
- r = msr_io(kvm, (void __user *)arg, do_set_msr, 0);
- break;
- case KVM_GET_MSR_INDEX_LIST: {
- struct kvm_msr_list __user *user_msr_list = (void __user *)arg;
- struct kvm_msr_list msr_list;
- unsigned n;
-
- r = -EFAULT;
- if (copy_from_user(&msr_list, user_msr_list, sizeof msr_list))
- goto out;
- n = msr_list.nmsrs;
- msr_list.nmsrs = num_msrs_to_save;
- if (copy_to_user(user_msr_list, &msr_list, sizeof msr_list))
- goto out;
- r = -E2BIG;
- if (n < num_msrs_to_save)
- goto out;
- r = -EFAULT;
- if (copy_to_user(user_msr_list->indices, &msrs_to_save,
- num_msrs_to_save * sizeof(u32)))
- goto out;
- r = 0;
- }
default:
;
}
return r;
}
-static struct page *kvm_dev_nopage(struct vm_area_struct *vma,
- unsigned long address,
- int *type)
+static struct page *kvm_vm_nopage(struct vm_area_struct *vma,
+ unsigned long address,
+ int *type)
{
struct kvm *kvm = vma->vm_file->private_data;
unsigned long pgoff;
return page;
}
-static struct vm_operations_struct kvm_dev_vm_ops = {
- .nopage = kvm_dev_nopage,
+static struct vm_operations_struct kvm_vm_vm_ops = {
+ .nopage = kvm_vm_nopage,
};
-static int kvm_dev_mmap(struct file *file, struct vm_area_struct *vma)
+static int kvm_vm_mmap(struct file *file, struct vm_area_struct *vma)
{
- vma->vm_ops = &kvm_dev_vm_ops;
+ vma->vm_ops = &kvm_vm_vm_ops;
return 0;
}
+static struct file_operations kvm_vm_fops = {
+ .release = kvm_vm_release,
+ .unlocked_ioctl = kvm_vm_ioctl,
+ .compat_ioctl = kvm_vm_ioctl,
+ .mmap = kvm_vm_mmap,
+};
+
+static int kvm_dev_ioctl_create_vm(void)
+{
+ int fd, r;
+ struct inode *inode;
+ 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;
+ }
+
+ 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;
+
+ switch (ioctl) {
+ case KVM_GET_API_VERSION:
+ r = KVM_API_VERSION;
+ break;
+ case KVM_CREATE_VM:
+ r = kvm_dev_ioctl_create_vm();
+ break;
+ case KVM_GET_MSR_INDEX_LIST: {
+ struct kvm_msr_list __user *user_msr_list = argp;
+ struct kvm_msr_list msr_list;
+ unsigned n;
+
+ r = -EFAULT;
+ if (copy_from_user(&msr_list, user_msr_list, sizeof msr_list))
+ goto out;
+ n = msr_list.nmsrs;
+ msr_list.nmsrs = num_msrs_to_save + ARRAY_SIZE(emulated_msrs);
+ if (copy_to_user(user_msr_list, &msr_list, sizeof msr_list))
+ goto out;
+ r = -E2BIG;
+ if (n < num_msrs_to_save)
+ goto out;
+ r = -EFAULT;
+ if (copy_to_user(user_msr_list->indices, &msrs_to_save,
+ num_msrs_to_save * sizeof(u32)))
+ goto out;
+ if (copy_to_user(user_msr_list->indices
+ + num_msrs_to_save * sizeof(u32),
+ &emulated_msrs,
+ ARRAY_SIZE(emulated_msrs) * sizeof(u32)))
+ goto out;
+ r = 0;
+ break;
+ }
+ default:
+ ;
+ }
+out:
+ return r;
+}
+
static struct file_operations kvm_chardev_ops = {
.open = kvm_dev_open,
.release = kvm_dev_release,
.unlocked_ioctl = kvm_dev_ioctl,
.compat_ioctl = kvm_dev_ioctl,
- .mmap = kvm_dev_mmap,
};
static struct miscdevice kvm_dev = {
- MISC_DYNAMIC_MINOR,
+ KVM_MINOR,
"kvm",
&kvm_chardev_ops,
};
* in vmx root mode.
*/
printk(KERN_INFO "kvm: exiting hardware virtualization\n");
- on_each_cpu(kvm_arch_ops->hardware_disable, 0, 0, 1);
+ on_each_cpu(kvm_arch_ops->hardware_disable, NULL, 0, 1);
}
return NOTIFY_OK;
}
.priority = 0,
};
+/*
+ * Make sure that a cpu that is being hot-unplugged does not have any vcpus
+ * cached on it.
+ */
+static void decache_vcpus_on_cpu(int cpu)
+{
+ struct kvm *vm;
+ struct kvm_vcpu *vcpu;
+ int i;
+
+ 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];
+ /*
+ * If the vcpu is locked, then it is running on some
+ * other cpu and therefore it is not cached on the
+ * cpu in question.
+ *
+ * If it's not locked, check the last cpu it executed
+ * on.
+ */
+ if (mutex_trylock(&vcpu->mutex)) {
+ if (vcpu->cpu == cpu) {
+ kvm_arch_ops->vcpu_decache(vcpu);
+ vcpu->cpu = -1;
+ }
+ mutex_unlock(&vcpu->mutex);
+ }
+ }
+ spin_unlock(&kvm_lock);
+}
+
+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_UP_CANCELED:
+ 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);
+ break;
+ case CPU_ONLINE:
+ printk(KERN_INFO "kvm: enabling virtualization on CPU%d\n",
+ cpu);
+ smp_call_function_single(cpu, kvm_arch_ops->hardware_enable,
+ NULL, 0, 1);
+ break;
+ }
+ return NOTIFY_OK;
+}
+
+static struct notifier_block kvm_cpu_notifier = {
+ .notifier_call = kvm_cpu_hotplug,
+ .priority = 20, /* must be > scheduler priority */
+};
+
static __init void kvm_init_debug(void)
{
struct kvm_stats_debugfs_item *p;
- debugfs_dir = debugfs_create_dir("kvm", 0);
+ 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);
debugfs_remove(debugfs_dir);
}
+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);
+ return 0;
+}
+
+static int kvm_resume(struct sys_device *dev)
+{
+ on_each_cpu(kvm_arch_ops->hardware_enable, NULL, 0, 1);
+ return 0;
+}
+
+static struct sysdev_class kvm_sysdev_class = {
+ set_kset_name("kvm"),
+ .suspend = kvm_suspend,
+ .resume = kvm_resume,
+};
+
+static struct sys_device kvm_sysdev = {
+ .id = 0,
+ .cls = &kvm_sysdev_class,
+};
+
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;
- kvm_arch_ops = ops;
+ if (kvm_arch_ops) {
+ printk(KERN_ERR "kvm: already loaded the other module\n");
+ return -EEXIST;
+ }
- if (!kvm_arch_ops->cpu_has_kvm_support()) {
+ if (!ops->cpu_has_kvm_support()) {
printk(KERN_ERR "kvm: no hardware support\n");
return -EOPNOTSUPP;
}
- if (kvm_arch_ops->disabled_by_bios()) {
+ if (ops->disabled_by_bios()) {
printk(KERN_ERR "kvm: disabled by bios\n");
return -EOPNOTSUPP;
}
+ kvm_arch_ops = ops;
+
r = kvm_arch_ops->hardware_setup();
if (r < 0)
- return r;
+ goto out;
- on_each_cpu(kvm_arch_ops->hardware_enable, 0, 0, 1);
+ on_each_cpu(kvm_arch_ops->hardware_enable, NULL, 0, 1);
+ r = register_cpu_notifier(&kvm_cpu_notifier);
+ if (r)
+ goto out_free_1;
register_reboot_notifier(&kvm_reboot_notifier);
+ r = sysdev_class_register(&kvm_sysdev_class);
+ if (r)
+ goto out_free_2;
+
+ r = sysdev_register(&kvm_sysdev);
+ if (r)
+ goto out_free_3;
+
kvm_chardev_ops.owner = module;
r = misc_register(&kvm_dev);
return r;
out_free:
+ sysdev_unregister(&kvm_sysdev);
+out_free_3:
+ sysdev_class_unregister(&kvm_sysdev_class);
+out_free_2:
unregister_reboot_notifier(&kvm_reboot_notifier);
- on_each_cpu(kvm_arch_ops->hardware_disable, 0, 0, 1);
+ unregister_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;
}
void kvm_exit_arch(void)
{
misc_deregister(&kvm_dev);
-
+ sysdev_unregister(&kvm_sysdev);
+ sysdev_class_unregister(&kvm_sysdev_class);
unregister_reboot_notifier(&kvm_reboot_notifier);
- on_each_cpu(kvm_arch_ops->hardware_disable, 0, 0, 1);
+ unregister_cpu_notifier(&kvm_cpu_notifier);
+ on_each_cpu(kvm_arch_ops->hardware_disable, NULL, 0, 1);
kvm_arch_ops->hardware_unsetup();
+ kvm_arch_ops = NULL;
}
static __init int kvm_init(void)
{
static struct page *bad_page;
- int r = 0;
+ int r;
+ 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();
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();
+ mntput(kvmfs_mnt);
+out2:
+ unregister_filesystem(&kvm_fs_type);
+out3:
return r;
}
{
kvm_exit_debug();
__free_page(pfn_to_page(bad_page_address >> PAGE_SHIFT));
+ mntput(kvmfs_mnt);
+ unregister_filesystem(&kvm_fs_type);
}
module_init(kvm_init)
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff