Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6
diff --git a/drivers/kvm/kvm.h b/drivers/kvm/kvm.h
index 3ac9cbc..7bdffe6 100644
--- a/drivers/kvm/kvm.h
+++ b/drivers/kvm/kvm.h
@@ -19,38 +19,20 @@
#include <linux/kvm.h>
#include <linux/kvm_para.h>
-#define CR0_PE_MASK (1ULL << 0)
-#define CR0_MP_MASK (1ULL << 1)
-#define CR0_TS_MASK (1ULL << 3)
-#define CR0_NE_MASK (1ULL << 5)
-#define CR0_WP_MASK (1ULL << 16)
-#define CR0_NW_MASK (1ULL << 29)
-#define CR0_CD_MASK (1ULL << 30)
-#define CR0_PG_MASK (1ULL << 31)
-
-#define CR3_WPT_MASK (1ULL << 3)
-#define CR3_PCD_MASK (1ULL << 4)
-
-#define CR3_RESEVED_BITS 0x07ULL
-#define CR3_L_MODE_RESEVED_BITS (~((1ULL << 40) - 1) | 0x0fe7ULL)
-#define CR3_FLAGS_MASK ((1ULL << 5) - 1)
-
-#define CR4_VME_MASK (1ULL << 0)
-#define CR4_PSE_MASK (1ULL << 4)
-#define CR4_PAE_MASK (1ULL << 5)
-#define CR4_PGE_MASK (1ULL << 7)
-#define CR4_VMXE_MASK (1ULL << 13)
+#define CR3_PAE_RESERVED_BITS ((X86_CR3_PWT | X86_CR3_PCD) - 1)
+#define CR3_NONPAE_RESERVED_BITS ((PAGE_SIZE-1) & ~(X86_CR3_PWT | X86_CR3_PCD))
+#define CR3_L_MODE_RESERVED_BITS (CR3_NONPAE_RESERVED_BITS|0xFFFFFF0000000000ULL)
#define KVM_GUEST_CR0_MASK \
- (CR0_PG_MASK | CR0_PE_MASK | CR0_WP_MASK | CR0_NE_MASK \
- | CR0_NW_MASK | CR0_CD_MASK)
+ (X86_CR0_PG | X86_CR0_PE | X86_CR0_WP | X86_CR0_NE \
+ | X86_CR0_NW | X86_CR0_CD)
#define KVM_VM_CR0_ALWAYS_ON \
- (CR0_PG_MASK | CR0_PE_MASK | CR0_WP_MASK | CR0_NE_MASK | CR0_TS_MASK \
- | CR0_MP_MASK)
+ (X86_CR0_PG | X86_CR0_PE | X86_CR0_WP | X86_CR0_NE | X86_CR0_TS \
+ | X86_CR0_MP)
#define KVM_GUEST_CR4_MASK \
- (CR4_PSE_MASK | CR4_PAE_MASK | CR4_PGE_MASK | CR4_VMXE_MASK | CR4_VME_MASK)
-#define KVM_PMODE_VM_CR4_ALWAYS_ON (CR4_VMXE_MASK | CR4_PAE_MASK)
-#define KVM_RMODE_VM_CR4_ALWAYS_ON (CR4_VMXE_MASK | CR4_PAE_MASK | CR4_VME_MASK)
+ (X86_CR4_VME | X86_CR4_PSE | X86_CR4_PAE | X86_CR4_PGE | X86_CR4_VMXE)
+#define KVM_PMODE_VM_CR4_ALWAYS_ON (X86_CR4_PAE | X86_CR4_VMXE)
+#define KVM_RMODE_VM_CR4_ALWAYS_ON (X86_CR4_VME | X86_CR4_PAE | X86_CR4_VMXE)
#define INVALID_PAGE (~(hpa_t)0)
#define UNMAPPED_GVA (~(gpa_t)0)
@@ -328,6 +310,7 @@
struct kvm_vcpu {
struct kvm *kvm;
+ int vcpu_id;
union {
struct vmcs *vmcs;
struct vcpu_svm *svm;
@@ -341,8 +324,7 @@
int guest_mode;
unsigned long requests;
unsigned long irq_summary; /* bit vector: 1 per word in irq_pending */
-#define NR_IRQ_WORDS KVM_IRQ_BITMAP_SIZE(unsigned long)
- unsigned long irq_pending[NR_IRQ_WORDS];
+ DECLARE_BITMAP(irq_pending, KVM_NR_INTERRUPTS);
unsigned long regs[NR_VCPU_REGS]; /* for rsp: vcpu_load_rsp_rip() */
unsigned long rip; /* needs vcpu_load_rsp_rip() */
@@ -652,17 +634,17 @@
static inline int is_pae(struct kvm_vcpu *vcpu)
{
- return vcpu->cr4 & CR4_PAE_MASK;
+ return vcpu->cr4 & X86_CR4_PAE;
}
static inline int is_pse(struct kvm_vcpu *vcpu)
{
- return vcpu->cr4 & CR4_PSE_MASK;
+ return vcpu->cr4 & X86_CR4_PSE;
}
static inline int is_paging(struct kvm_vcpu *vcpu)
{
- return vcpu->cr0 & CR0_PG_MASK;
+ return vcpu->cr0 & X86_CR0_PG;
}
static inline int memslot_id(struct kvm *kvm, struct kvm_memory_slot *slot)
diff --git a/drivers/kvm/kvm_main.c b/drivers/kvm/kvm_main.c
index bcbe683..7c9bd72 100644
--- a/drivers/kvm/kvm_main.c
+++ b/drivers/kvm/kvm_main.c
@@ -54,8 +54,6 @@
struct kvm_arch_ops *kvm_arch_ops;
-static void hardware_disable(void *ignored);
-
#define STAT_OFFSET(x) offsetof(struct kvm_vcpu, stat.x)
static struct kvm_stats_debugfs_item {
@@ -84,10 +82,17 @@
#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
@@ -297,9 +302,6 @@
kvm_io_bus_init(&kvm->pio_bus);
spin_lock_init(&kvm->lock);
INIT_LIST_HEAD(&kvm->active_mmu_pages);
- 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];
@@ -309,6 +311,9 @@
vcpu->kvm = kvm;
vcpu->mmu.root_hpa = INVALID_PAGE;
}
+ spin_lock(&kvm_lock);
+ list_add(&kvm->vm_list, &vm_list);
+ spin_unlock(&kvm_lock);
return kvm;
}
@@ -468,27 +473,27 @@
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;
@@ -536,26 +541,27 @@
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;
@@ -570,23 +576,32 @@
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;
+ }
}
}
@@ -611,7 +626,7 @@
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;
@@ -1078,10 +1093,10 @@
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;
@@ -1113,6 +1128,26 @@
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,
@@ -1142,7 +1177,7 @@
{
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;
}
@@ -1244,6 +1279,7 @@
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;
@@ -1311,6 +1347,7 @@
}
switch (nr) {
default:
+ run->hypercall.nr = nr;
run->hypercall.args[0] = a0;
run->hypercall.args[1] = a1;
run->hypercall.args[2] = a2;
@@ -1742,18 +1779,35 @@
return 0;
}
-void kernel_pio(struct kvm_io_device *pio_dev, struct kvm_vcpu *vcpu)
+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,
- vcpu->pio_data);
+ pd);
else
kvm_iodevice_write(pio_dev, vcpu->pio.port,
vcpu->pio.size,
- vcpu->pio_data);
+ 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,
@@ -1761,7 +1815,7 @@
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;
@@ -1788,15 +1842,12 @@
memcpy(vcpu->pio_data, &vcpu->regs[VCPU_REGS_RAX], 4);
kvm_arch_ops->decache_regs(vcpu);
if (pio_dev) {
- kernel_pio(pio_dev, vcpu);
+ kernel_pio(pio_dev, vcpu, vcpu->pio_data);
complete_pio(vcpu);
return 1;
}
return 0;
}
- /* TODO: String I/O for in kernel device */
- if (pio_dev)
- printk(KERN_ERR "kvm_setup_pio: no string io support\n");
if (!count) {
kvm_arch_ops->skip_emulated_instruction(vcpu);
@@ -1844,9 +1895,21 @@
}
}
- 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);
@@ -1879,7 +1942,6 @@
/*
* Read-modify-write. Back to userspace.
*/
- kvm_run->exit_reason = KVM_EXIT_MMIO;
r = 0;
goto out;
}
@@ -2072,7 +2134,7 @@
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);
@@ -2267,7 +2329,6 @@
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);
@@ -2276,6 +2337,9 @@
else
return NOPAGE_SIGBUS;
get_page(page);
+ if (type != NULL)
+ *type = VM_FAULT_MINOR;
+
return page;
}
@@ -2335,6 +2399,7 @@
goto out;
vcpu = &kvm->vcpus[n];
+ vcpu->vcpu_id = n;
mutex_lock(&vcpu->mutex);
@@ -2750,12 +2815,14 @@
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;
}
@@ -2875,25 +2942,6 @@
&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(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.
@@ -2972,6 +3020,25 @@
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));
diff --git a/drivers/kvm/mmu.c b/drivers/kvm/mmu.c
index 1a87ba9..a7985b1 100644
--- a/drivers/kvm/mmu.c
+++ b/drivers/kvm/mmu.c
@@ -158,7 +158,7 @@
static int is_write_protection(struct kvm_vcpu *vcpu)
{
- return vcpu->cr0 & CR0_WP_MASK;
+ return vcpu->cr0 & X86_CR0_WP;
}
static int is_cpuid_PSE36(void)
diff --git a/drivers/kvm/paging_tmpl.h b/drivers/kvm/paging_tmpl.h
index 4b5391c..01901ec 100644
--- a/drivers/kvm/paging_tmpl.h
+++ b/drivers/kvm/paging_tmpl.h
@@ -99,7 +99,7 @@
walker->table = kmap_atomic(pfn_to_page(hpa >> PAGE_SHIFT), KM_USER0);
ASSERT((!is_long_mode(vcpu) && is_pae(vcpu)) ||
- (vcpu->cr3 & ~(PAGE_MASK | CR3_FLAGS_MASK)) == 0);
+ (vcpu->cr3 & CR3_NONPAE_RESERVED_BITS) == 0);
walker->inherited_ar = PT_USER_MASK | PT_WRITABLE_MASK;
diff --git a/drivers/kvm/svm.c b/drivers/kvm/svm.c
index bc818cc..850a1b1 100644
--- a/drivers/kvm/svm.c
+++ b/drivers/kvm/svm.c
@@ -38,7 +38,6 @@
#define DR7_GD_MASK (1 << 13)
#define DR6_BD_MASK (1 << 13)
-#define CR4_DE_MASK (1UL << 3)
#define SEG_TYPE_LDT 2
#define SEG_TYPE_BUSY_TSS16 3
@@ -99,7 +98,7 @@
struct vmcb_save_area *sa = &vcpu->svm->vmcb->save;
u16 cs_attrib;
- if (!(sa->cr0 & CR0_PE_MASK) || (sa->rflags & X86_EFLAGS_VM))
+ if (!(sa->cr0 & X86_CR0_PE) || (sa->rflags & X86_EFLAGS_VM))
return 2;
cs_attrib = sa->cs.attrib;
@@ -563,8 +562,8 @@
* cr0 val on cpu init should be 0x60000010, we enable cpu
* cache by default. the orderly way is to enable cache in bios.
*/
- save->cr0 = 0x00000010 | CR0_PG_MASK | CR0_WP_MASK;
- save->cr4 = CR4_PAE_MASK;
+ save->cr0 = 0x00000010 | X86_CR0_PG | X86_CR0_WP;
+ save->cr4 = X86_CR4_PAE;
/* rdx = ?? */
}
@@ -591,7 +590,7 @@
fx_init(vcpu);
vcpu->fpu_active = 1;
vcpu->apic_base = 0xfee00000 | MSR_IA32_APICBASE_ENABLE;
- if (vcpu == &vcpu->kvm->vcpus[0])
+ if (vcpu->vcpu_id == 0)
vcpu->apic_base |= MSR_IA32_APICBASE_BSP;
return 0;
@@ -756,32 +755,32 @@
{
#ifdef CONFIG_X86_64
if (vcpu->shadow_efer & KVM_EFER_LME) {
- if (!is_paging(vcpu) && (cr0 & CR0_PG_MASK)) {
+ if (!is_paging(vcpu) && (cr0 & X86_CR0_PG)) {
vcpu->shadow_efer |= KVM_EFER_LMA;
vcpu->svm->vmcb->save.efer |= KVM_EFER_LMA | KVM_EFER_LME;
}
- if (is_paging(vcpu) && !(cr0 & CR0_PG_MASK) ) {
+ if (is_paging(vcpu) && !(cr0 & X86_CR0_PG) ) {
vcpu->shadow_efer &= ~KVM_EFER_LMA;
vcpu->svm->vmcb->save.efer &= ~(KVM_EFER_LMA | KVM_EFER_LME);
}
}
#endif
- if ((vcpu->cr0 & CR0_TS_MASK) && !(cr0 & CR0_TS_MASK)) {
+ if ((vcpu->cr0 & X86_CR0_TS) && !(cr0 & X86_CR0_TS)) {
vcpu->svm->vmcb->control.intercept_exceptions &= ~(1 << NM_VECTOR);
vcpu->fpu_active = 1;
}
vcpu->cr0 = cr0;
- cr0 |= CR0_PG_MASK | CR0_WP_MASK;
- cr0 &= ~(CR0_CD_MASK | CR0_NW_MASK);
+ cr0 |= X86_CR0_PG | X86_CR0_WP;
+ cr0 &= ~(X86_CR0_CD | X86_CR0_NW);
vcpu->svm->vmcb->save.cr0 = cr0;
}
static void svm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
{
vcpu->cr4 = cr4;
- vcpu->svm->vmcb->save.cr4 = cr4 | CR4_PAE_MASK;
+ vcpu->svm->vmcb->save.cr4 = cr4 | X86_CR4_PAE;
}
static void svm_set_segment(struct kvm_vcpu *vcpu,
@@ -877,7 +876,7 @@
vcpu->svm->db_regs[dr] = value;
return;
case 4 ... 5:
- if (vcpu->cr4 & CR4_DE_MASK) {
+ if (vcpu->cr4 & X86_CR4_DE) {
*exception = UD_VECTOR;
return;
}
@@ -929,7 +928,6 @@
return 1;
case EMULATE_DO_MMIO:
++vcpu->stat.mmio_exits;
- kvm_run->exit_reason = KVM_EXIT_MMIO;
return 0;
case EMULATE_FAIL:
vcpu_printf(vcpu, "%s: emulate fail\n", __FUNCTION__);
@@ -945,8 +943,8 @@
static int nm_interception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
{
vcpu->svm->vmcb->control.intercept_exceptions &= ~(1 << NM_VECTOR);
- if (!(vcpu->cr0 & CR0_TS_MASK))
- vcpu->svm->vmcb->save.cr0 &= ~CR0_TS_MASK;
+ if (!(vcpu->cr0 & X86_CR0_TS))
+ vcpu->svm->vmcb->save.cr0 &= ~X86_CR0_TS;
vcpu->fpu_active = 1;
return 1;
@@ -1702,7 +1700,7 @@
if (vcpu->fpu_active) {
vcpu->svm->vmcb->control.intercept_exceptions |= (1 << NM_VECTOR);
- vcpu->svm->vmcb->save.cr0 |= CR0_TS_MASK;
+ vcpu->svm->vmcb->save.cr0 |= X86_CR0_TS;
vcpu->fpu_active = 0;
}
}
diff --git a/drivers/kvm/vmx.c b/drivers/kvm/vmx.c
index 80628f6..2c4f01be 100644
--- a/drivers/kvm/vmx.c
+++ b/drivers/kvm/vmx.c
@@ -436,9 +436,9 @@
if (vcpu->fpu_active)
return;
vcpu->fpu_active = 1;
- vmcs_clear_bits(GUEST_CR0, CR0_TS_MASK);
- if (vcpu->cr0 & CR0_TS_MASK)
- vmcs_set_bits(GUEST_CR0, CR0_TS_MASK);
+ vmcs_clear_bits(GUEST_CR0, X86_CR0_TS);
+ if (vcpu->cr0 & X86_CR0_TS)
+ vmcs_set_bits(GUEST_CR0, X86_CR0_TS);
update_exception_bitmap(vcpu);
}
@@ -447,7 +447,7 @@
if (!vcpu->fpu_active)
return;
vcpu->fpu_active = 0;
- vmcs_set_bits(GUEST_CR0, CR0_TS_MASK);
+ vmcs_set_bits(GUEST_CR0, X86_CR0_TS);
update_exception_bitmap(vcpu);
}
@@ -764,7 +764,7 @@
if ((old & 5) != 5)
/* enable and lock */
wrmsrl(MSR_IA32_FEATURE_CONTROL, old | 5);
- write_cr4(read_cr4() | CR4_VMXE); /* FIXME: not cpu hotplug safe */
+ write_cr4(read_cr4() | X86_CR4_VMXE); /* FIXME: not cpu hotplug safe */
asm volatile (ASM_VMX_VMXON_RAX : : "a"(&phys_addr), "m"(phys_addr)
: "memory", "cc");
}
@@ -879,8 +879,8 @@
flags |= (vcpu->rmode.save_iopl << IOPL_SHIFT);
vmcs_writel(GUEST_RFLAGS, flags);
- vmcs_writel(GUEST_CR4, (vmcs_readl(GUEST_CR4) & ~CR4_VME_MASK) |
- (vmcs_readl(CR4_READ_SHADOW) & CR4_VME_MASK));
+ vmcs_writel(GUEST_CR4, (vmcs_readl(GUEST_CR4) & ~X86_CR4_VME) |
+ (vmcs_readl(CR4_READ_SHADOW) & X86_CR4_VME));
update_exception_bitmap(vcpu);
@@ -937,7 +937,7 @@
flags |= IOPL_MASK | X86_EFLAGS_VM;
vmcs_writel(GUEST_RFLAGS, flags);
- vmcs_writel(GUEST_CR4, vmcs_readl(GUEST_CR4) | CR4_VME_MASK);
+ vmcs_writel(GUEST_CR4, vmcs_readl(GUEST_CR4) | X86_CR4_VME);
update_exception_bitmap(vcpu);
vmcs_write16(GUEST_SS_SELECTOR, vmcs_readl(GUEST_SS_BASE) >> 4);
@@ -1002,17 +1002,17 @@
{
vmx_fpu_deactivate(vcpu);
- if (vcpu->rmode.active && (cr0 & CR0_PE_MASK))
+ if (vcpu->rmode.active && (cr0 & X86_CR0_PE))
enter_pmode(vcpu);
- if (!vcpu->rmode.active && !(cr0 & CR0_PE_MASK))
+ if (!vcpu->rmode.active && !(cr0 & X86_CR0_PE))
enter_rmode(vcpu);
#ifdef CONFIG_X86_64
if (vcpu->shadow_efer & EFER_LME) {
- if (!is_paging(vcpu) && (cr0 & CR0_PG_MASK))
+ if (!is_paging(vcpu) && (cr0 & X86_CR0_PG))
enter_lmode(vcpu);
- if (is_paging(vcpu) && !(cr0 & CR0_PG_MASK))
+ if (is_paging(vcpu) && !(cr0 & X86_CR0_PG))
exit_lmode(vcpu);
}
#endif
@@ -1022,14 +1022,14 @@
(cr0 & ~KVM_GUEST_CR0_MASK) | KVM_VM_CR0_ALWAYS_ON);
vcpu->cr0 = cr0;
- if (!(cr0 & CR0_TS_MASK) || !(cr0 & CR0_PE_MASK))
+ if (!(cr0 & X86_CR0_TS) || !(cr0 & X86_CR0_PE))
vmx_fpu_activate(vcpu);
}
static void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
{
vmcs_writel(GUEST_CR3, cr3);
- if (vcpu->cr0 & CR0_PE_MASK)
+ if (vcpu->cr0 & X86_CR0_PE)
vmx_fpu_deactivate(vcpu);
}
@@ -1253,7 +1253,7 @@
vcpu->regs[VCPU_REGS_RDX] = get_rdx_init_val();
vcpu->cr8 = 0;
vcpu->apic_base = 0xfee00000 | MSR_IA32_APICBASE_ENABLE;
- if (vcpu == &vcpu->kvm->vcpus[0])
+ if (vcpu->vcpu_id == 0)
vcpu->apic_base |= MSR_IA32_APICBASE_BSP;
fx_init(vcpu);
@@ -1610,7 +1610,6 @@
return 1;
case EMULATE_DO_MMIO:
++vcpu->stat.mmio_exits;
- kvm_run->exit_reason = KVM_EXIT_MMIO;
return 0;
case EMULATE_FAIL:
vcpu_printf(vcpu, "%s: emulate fail\n", __FUNCTION__);
@@ -1778,7 +1777,7 @@
case 2: /* clts */
vcpu_load_rsp_rip(vcpu);
vmx_fpu_deactivate(vcpu);
- vcpu->cr0 &= ~CR0_TS_MASK;
+ vcpu->cr0 &= ~X86_CR0_TS;
vmcs_writel(CR0_READ_SHADOW, vcpu->cr0);
vmx_fpu_activate(vcpu);
skip_emulated_instruction(vcpu);
diff --git a/drivers/kvm/vmx.h b/drivers/kvm/vmx.h
index d0dc93d..76ad793 100644
--- a/drivers/kvm/vmx.h
+++ b/drivers/kvm/vmx.h
@@ -285,8 +285,6 @@
#define AR_RESERVD_MASK 0xfffe0f00
-#define CR4_VMXE 0x2000
-
#define MSR_IA32_VMX_BASIC 0x480
#define MSR_IA32_FEATURE_CONTROL 0x03a
#define MSR_IA32_VMX_PINBASED_CTLS 0x481
diff --git a/drivers/kvm/x86_emulate.c b/drivers/kvm/x86_emulate.c
index 1b800fc..21ce977 100644
--- a/drivers/kvm/x86_emulate.c
+++ b/drivers/kvm/x86_emulate.c
@@ -6,7 +6,7 @@
* Copyright (c) 2005 Keir Fraser
*
* Linux coding style, mod r/m decoder, segment base fixes, real-mode
- * privieged instructions:
+ * privileged instructions:
*
* Copyright (C) 2006 Qumranet
*
@@ -443,8 +443,13 @@
(((reg) + _inc) & ((1UL << (ad_bytes << 3)) - 1)); \
} while (0)
-void *decode_register(u8 modrm_reg, unsigned long *regs,
- int highbyte_regs)
+/*
+ * Given the 'reg' portion of a ModRM byte, and a register block, return a
+ * pointer into the block that addresses the relevant register.
+ * @highbyte_regs specifies whether to decode AH,CH,DH,BH.
+ */
+static void *decode_register(u8 modrm_reg, unsigned long *regs,
+ int highbyte_regs)
{
void *p;
@@ -814,7 +819,7 @@
case DstReg:
dst.type = OP_REG;
if ((d & ByteOp)
- && !(twobyte_table && (b == 0xb6 || b == 0xb7))) {
+ && !(twobyte && (b == 0xb6 || b == 0xb7))) {
dst.ptr = decode_register(modrm_reg, _regs,
(rex_prefix == 0));
dst.val = *(u8 *) dst.ptr;
@@ -1226,40 +1231,40 @@
break;
case 0x40 ... 0x4f: /* cmov */
dst.val = dst.orig_val = src.val;
- d &= ~Mov; /* default to no move */
+ no_wb = 1;
/*
* First, assume we're decoding an even cmov opcode
* (lsb == 0).
*/
switch ((b & 15) >> 1) {
case 0: /* cmovo */
- d |= (_eflags & EFLG_OF) ? Mov : 0;
+ no_wb = (_eflags & EFLG_OF) ? 0 : 1;
break;
case 1: /* cmovb/cmovc/cmovnae */
- d |= (_eflags & EFLG_CF) ? Mov : 0;
+ no_wb = (_eflags & EFLG_CF) ? 0 : 1;
break;
case 2: /* cmovz/cmove */
- d |= (_eflags & EFLG_ZF) ? Mov : 0;
+ no_wb = (_eflags & EFLG_ZF) ? 0 : 1;
break;
case 3: /* cmovbe/cmovna */
- d |= (_eflags & (EFLG_CF | EFLG_ZF)) ? Mov : 0;
+ no_wb = (_eflags & (EFLG_CF | EFLG_ZF)) ? 0 : 1;
break;
case 4: /* cmovs */
- d |= (_eflags & EFLG_SF) ? Mov : 0;
+ no_wb = (_eflags & EFLG_SF) ? 0 : 1;
break;
case 5: /* cmovp/cmovpe */
- d |= (_eflags & EFLG_PF) ? Mov : 0;
+ no_wb = (_eflags & EFLG_PF) ? 0 : 1;
break;
case 7: /* cmovle/cmovng */
- d |= (_eflags & EFLG_ZF) ? Mov : 0;
+ no_wb = (_eflags & EFLG_ZF) ? 0 : 1;
/* fall through */
case 6: /* cmovl/cmovnge */
- d |= (!(_eflags & EFLG_SF) !=
- !(_eflags & EFLG_OF)) ? Mov : 0;
+ no_wb &= (!(_eflags & EFLG_SF) !=
+ !(_eflags & EFLG_OF)) ? 0 : 1;
break;
}
/* Odd cmov opcodes (lsb == 1) have inverted sense. */
- d ^= (b & 1) ? Mov : 0;
+ no_wb ^= b & 1;
break;
case 0xb0 ... 0xb1: /* cmpxchg */
/*
diff --git a/drivers/kvm/x86_emulate.h b/drivers/kvm/x86_emulate.h
index ea3407d..574cca7 100644
--- a/drivers/kvm/x86_emulate.h
+++ b/drivers/kvm/x86_emulate.h
@@ -112,8 +112,6 @@
};
-struct cpu_user_regs;
-
struct x86_emulate_ctxt {
/* Register state before/after emulation. */
struct kvm_vcpu *vcpu;
@@ -154,12 +152,4 @@
int x86_emulate_memop(struct x86_emulate_ctxt *ctxt,
struct x86_emulate_ops *ops);
-/*
- * Given the 'reg' portion of a ModRM byte, and a register block, return a
- * pointer into the block that addresses the relevant register.
- * @highbyte_regs specifies whether to decode AH,CH,DH,BH.
- */
-void *decode_register(u8 modrm_reg, unsigned long *regs,
- int highbyte_regs);
-
#endif /* __X86_EMULATE_H__ */
diff --git a/include/asm-i386/processor-flags.h b/include/asm-i386/processor-flags.h
index 5404e90..199cab10 100644
--- a/include/asm-i386/processor-flags.h
+++ b/include/asm-i386/processor-flags.h
@@ -63,7 +63,7 @@
/*
* x86-64 Task Priority Register, CR8
*/
-#define X86_CR8_TPR 0x00000007 /* task priority register */
+#define X86_CR8_TPR 0x0000000F /* task priority register */
/*
* AMD and Transmeta use MSRs for configuration; see <asm/msr-index.h>
diff --git a/include/linux/kvm.h b/include/linux/kvm.h
index e6edca8..91a446f 100644
--- a/include/linux/kvm.h
+++ b/include/linux/kvm.h
@@ -4,8 +4,7 @@
/*
* Userspace interface for /dev/kvm - kernel based virtual machine
*
- * Note: this interface is considered experimental and may change without
- * notice.
+ * Note: you must update KVM_API_VERSION if you change this interface.
*/
#include <asm/types.h>
@@ -13,14 +12,8 @@
#define KVM_API_VERSION 12
-/*
- * Architectural interrupt line count, and the size of the bitmap needed
- * to hold them.
- */
+/* Architectural interrupt line count. */
#define KVM_NR_INTERRUPTS 256
-#define KVM_IRQ_BITMAP_SIZE_BYTES ((KVM_NR_INTERRUPTS + 7) / 8)
-#define KVM_IRQ_BITMAP_SIZE(type) (KVM_IRQ_BITMAP_SIZE_BYTES / sizeof(type))
-
/* for KVM_CREATE_MEMORY_REGION */
struct kvm_memory_region {
@@ -106,11 +99,14 @@
} mmio;
/* KVM_EXIT_HYPERCALL */
struct {
+ __u64 nr;
__u64 args[6];
__u64 ret;
__u32 longmode;
__u32 pad;
} hypercall;
+ /* Fix the size of the union. */
+ char padding[256];
};
};
@@ -164,7 +160,7 @@
__u64 cr0, cr2, cr3, cr4, cr8;
__u64 efer;
__u64 apic_base;
- __u64 interrupt_bitmap[KVM_IRQ_BITMAP_SIZE(__u64)];
+ __u64 interrupt_bitmap[(KVM_NR_INTERRUPTS + 63) / 64];
};
struct kvm_msr_entry {
