*/
#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;
#define STAT_OFFSET(x) offsetof(struct kvm_vcpu, stat.x)
{ "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
-#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;
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)
+static void vcpu_put(struct kvm_vcpu *vcpu)
+{
+ kvm_arch_ops->vcpu_put(vcpu);
+ mutex_unlock(&vcpu->mutex);
+}
+
+static void ack_flush(void *_completed)
{
- struct kvm_vcpu *vcpu = &kvm->vcpus[slot];
+ atomic_t *completed = _completed;
- mutex_lock(&vcpu->mutex);
- if (!vcpu->vmcs) {
- mutex_unlock(&vcpu->mutex);
- return NULL;
- }
- kvm_arch_ops->vcpu_load(vcpu);
- return vcpu;
+ atomic_inc(completed);
}
-static void vcpu_put(struct kvm_vcpu *vcpu)
+void kvm_flush_remote_tlbs(struct kvm *kvm)
{
- kvm_arch_ops->vcpu_put(vcpu);
- mutex_unlock(&vcpu->mutex);
+ 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)
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;
}
}
}
+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)
{
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);
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;
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;
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;
+ }
}
}
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.
*memslot = new;
++kvm->memory_config_version;
- spin_unlock(&kvm->lock);
+ kvm_mmu_slot_remove_write_access(kvm, mem->slot);
+ kvm_flush_remote_tlbs(kvm);
- for (i = 0; i < KVM_MAX_VCPUS; ++i) {
- struct kvm_vcpu *vcpu;
-
- 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;
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]);
return 0;
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;
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,
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,
page = gfn_to_page(vcpu->kvm, gpa >> PAGE_SHIFT);
if (!page)
return 0;
- kvm_mmu_pre_write(vcpu, gpa, bytes);
mark_page_dirty(vcpu->kvm, gpa >> PAGE_SHIFT);
virt = kmap_atomic(page, KM_USER0);
+ kvm_mmu_pte_write(vcpu, gpa, 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,
- 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;
- 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) {
kvm_arch_ops->inject_page_fault(vcpu, addr, 2);
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;
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;
}
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;
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;
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);
}
* 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);
}
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;
}
}
}
- 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);
}
/*
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;
}
/*
goto out;
vcpu = &kvm->vcpus[n];
+ vcpu->vcpu_id = n;
mutex_lock(&vcpu->mutex);
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:
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:
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_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));
+}
+
+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 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;
}
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();
}