#include <linux/io.h>
#include <linux/module.h>
#include <linux/math64.h>
+#include <linux/slab.h>
#include <asm/processor.h>
#include <asm/msr.h>
#include <asm/page.h>
#include <asm/atomic.h>
#include "kvm_cache_regs.h"
#include "irq.h"
+#include "trace.h"
+#include "x86.h"
#ifndef CONFIG_X86_64
#define mod_64(x, y) ((x) - (y) * div64_u64(x, y))
return (lvt_val & (APIC_MODE_MASK | APIC_LVT_MASKED)) == APIC_DM_NMI;
}
+void kvm_apic_set_version(struct kvm_vcpu *vcpu)
+{
+ struct kvm_lapic *apic = vcpu->arch.apic;
+ struct kvm_cpuid_entry2 *feat;
+ u32 v = APIC_VERSION;
+
+ if (!irqchip_in_kernel(vcpu->kvm))
+ return;
+
+ feat = kvm_find_cpuid_entry(apic->vcpu, 0x1, 0);
+ if (feat && (feat->ecx & (1 << (X86_FEATURE_X2APIC & 31))))
+ v |= APIC_LVR_DIRECTED_EOI;
+ apic_set_reg(apic, APIC_LVR, v);
+}
+
+static inline int apic_x2apic_mode(struct kvm_lapic *apic)
+{
+ return apic->vcpu->arch.apic_base & X2APIC_ENABLE;
+}
+
static unsigned int apic_lvt_mask[APIC_LVT_NUM] = {
LVT_MASK | APIC_LVT_TIMER_PERIODIC, /* LVTT */
LVT_MASK | APIC_MODE_MASK, /* LVTTHMR */
int kvm_apic_match_logical_addr(struct kvm_lapic *apic, u8 mda)
{
int result = 0;
- u8 logical_id;
+ u32 logical_id;
+
+ if (apic_x2apic_mode(apic)) {
+ logical_id = apic_get_reg(apic, APIC_LDR);
+ return logical_id & mda;
+ }
logical_id = GET_APIC_LOGICAL_ID(apic_get_reg(apic, APIC_LDR));
if (unlikely(!apic_enabled(apic)))
break;
+ if (trig_mode) {
+ apic_debug("level trig mode for vector %d", vector);
+ apic_set_vector(vector, apic->regs + APIC_TMR);
+ } else
+ apic_clear_vector(vector, apic->regs + APIC_TMR);
+
result = !apic_test_and_set_irr(vector, apic);
+ trace_kvm_apic_accept_irq(vcpu->vcpu_id, delivery_mode,
+ trig_mode, vector, !result);
if (!result) {
if (trig_mode)
apic_debug("level trig mode repeatedly for "
break;
}
- if (trig_mode) {
- apic_debug("level trig mode for vector %d", vector);
- apic_set_vector(vector, apic->regs + APIC_TMR);
- } else
- apic_clear_vector(vector, apic->regs + APIC_TMR);
kvm_vcpu_kick(vcpu);
break;
trigger_mode = IOAPIC_LEVEL_TRIG;
else
trigger_mode = IOAPIC_EDGE_TRIG;
- mutex_lock(&apic->vcpu->kvm->irq_lock);
- kvm_ioapic_update_eoi(apic->vcpu->kvm, vector, trigger_mode);
- mutex_unlock(&apic->vcpu->kvm->irq_lock);
+ if (!(apic_get_reg(apic, APIC_SPIV) & APIC_SPIV_DIRECTED_EOI))
+ kvm_ioapic_update_eoi(apic->vcpu->kvm, vector, trigger_mode);
}
static void apic_send_ipi(struct kvm_lapic *apic)
irq.level = icr_low & APIC_INT_ASSERT;
irq.trig_mode = icr_low & APIC_INT_LEVELTRIG;
irq.shorthand = icr_low & APIC_SHORT_MASK;
- irq.dest_id = GET_APIC_DEST_FIELD(icr_high);
+ if (apic_x2apic_mode(apic))
+ irq.dest_id = icr_high;
+ else
+ irq.dest_id = GET_APIC_DEST_FIELD(icr_high);
+
+ trace_kvm_apic_ipi(icr_low, irq.dest_id);
apic_debug("icr_high 0x%x, icr_low 0x%x, "
"short_hand 0x%x, dest 0x%x, trig_mode 0x%x, level 0x%x, "
irq.trig_mode, irq.level, irq.dest_mode, irq.delivery_mode,
irq.vector);
- mutex_lock(&apic->vcpu->kvm->irq_lock);
kvm_irq_delivery_to_apic(apic->vcpu->kvm, apic, &irq);
- mutex_unlock(&apic->vcpu->kvm->irq_lock);
}
static u32 apic_get_tmcct(struct kvm_lapic *apic)
if (apic_get_reg(apic, APIC_TMICT) == 0)
return 0;
- remaining = hrtimer_expires_remaining(&apic->lapic_timer.timer);
+ remaining = hrtimer_get_remaining(&apic->lapic_timer.timer);
if (ktime_to_ns(remaining) < 0)
remaining = ktime_set(0, 0);
{
u32 val = 0;
- KVMTRACE_1D(APIC_ACCESS, apic->vcpu, (u32)offset, handler);
-
if (offset >= LAPIC_MMIO_LENGTH)
return 0;
switch (offset) {
+ case APIC_ID:
+ if (apic_x2apic_mode(apic))
+ val = kvm_apic_id(apic);
+ else
+ val = kvm_apic_id(apic) << 24;
+ break;
case APIC_ARBPRI:
printk(KERN_WARNING "Access APIC ARBPRI register "
"which is for P6\n");
return container_of(dev, struct kvm_lapic, dev);
}
-static void apic_mmio_read(struct kvm_io_device *this,
- gpa_t address, int len, void *data)
+static int apic_reg_read(struct kvm_lapic *apic, u32 offset, int len,
+ void *data)
{
- struct kvm_lapic *apic = to_lapic(this);
- unsigned int offset = address - apic->base_address;
unsigned char alignment = offset & 0xf;
u32 result;
+ /* this bitmask has a bit cleared for each reserver register */
+ static const u64 rmask = 0x43ff01ffffffe70cULL;
if ((alignment + len) > 4) {
- printk(KERN_ERR "KVM_APIC_READ: alignment error %lx %d",
- (unsigned long)address, len);
- return;
+ apic_debug("KVM_APIC_READ: alignment error %x %d\n",
+ offset, len);
+ return 1;
}
+
+ if (offset > 0x3f0 || !(rmask & (1ULL << (offset >> 4)))) {
+ apic_debug("KVM_APIC_READ: read reserved register %x\n",
+ offset);
+ return 1;
+ }
+
result = __apic_read(apic, offset & ~0xf);
+ trace_kvm_apic_read(offset, result);
+
switch (len) {
case 1:
case 2:
"should be 1,2, or 4 instead\n", len);
break;
}
+ return 0;
+}
+
+static int apic_mmio_in_range(struct kvm_lapic *apic, gpa_t addr)
+{
+ return apic_hw_enabled(apic) &&
+ addr >= apic->base_address &&
+ addr < apic->base_address + LAPIC_MMIO_LENGTH;
+}
+
+static int apic_mmio_read(struct kvm_io_device *this,
+ gpa_t address, int len, void *data)
+{
+ struct kvm_lapic *apic = to_lapic(this);
+ u32 offset = address - apic->base_address;
+
+ if (!apic_mmio_in_range(apic, address))
+ return -EOPNOTSUPP;
+
+ apic_reg_read(apic, offset, len, data);
+
+ return 0;
}
static void update_divide_count(struct kvm_lapic *apic)
{
ktime_t now = apic->lapic_timer.timer.base->get_time();
- apic->lapic_timer.period = apic_get_reg(apic, APIC_TMICT) *
+ apic->lapic_timer.period = (u64)apic_get_reg(apic, APIC_TMICT) *
APIC_BUS_CYCLE_NS * apic->divide_count;
atomic_set(&apic->lapic_timer.pending, 0);
if (!apic->lapic_timer.period)
return;
+ /*
+ * Do not allow the guest to program periodic timers with small
+ * interval, since the hrtimers are not throttled by the host
+ * scheduler.
+ */
+ if (apic_lvtt_period(apic)) {
+ if (apic->lapic_timer.period < NSEC_PER_MSEC/2)
+ apic->lapic_timer.period = NSEC_PER_MSEC/2;
+ }
hrtimer_start(&apic->lapic_timer.timer,
ktime_add_ns(now, apic->lapic_timer.period),
apic->vcpu->kvm->arch.vapics_in_nmi_mode--;
}
-static void apic_mmio_write(struct kvm_io_device *this,
- gpa_t address, int len, const void *data)
+static int apic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val)
{
- struct kvm_lapic *apic = to_lapic(this);
- unsigned int offset = address - apic->base_address;
- unsigned char alignment = offset & 0xf;
- u32 val;
-
- /*
- * APIC register must be aligned on 128-bits boundary.
- * 32/64/128 bits registers must be accessed thru 32 bits.
- * Refer SDM 8.4.1
- */
- if (len != 4 || alignment) {
- /* Don't shout loud, $infamous_os would cause only noise. */
- apic_debug("apic write: bad size=%d %lx\n",
- len, (long)address);
- return;
- }
-
- val = *(u32 *) data;
-
- /* too common printing */
- if (offset != APIC_EOI)
- apic_debug("%s: offset 0x%x with length 0x%x, and value is "
- "0x%x\n", __func__, offset, len, val);
-
- offset &= 0xff0;
+ int ret = 0;
- KVMTRACE_1D(APIC_ACCESS, apic->vcpu, (u32)offset, handler);
+ trace_kvm_apic_write(reg, val);
- switch (offset) {
+ switch (reg) {
case APIC_ID: /* Local APIC ID */
- apic_set_reg(apic, APIC_ID, val);
+ if (!apic_x2apic_mode(apic))
+ apic_set_reg(apic, APIC_ID, val);
+ else
+ ret = 1;
break;
case APIC_TASKPRI:
break;
case APIC_LDR:
- apic_set_reg(apic, APIC_LDR, val & APIC_LDR_MASK);
+ if (!apic_x2apic_mode(apic))
+ apic_set_reg(apic, APIC_LDR, val & APIC_LDR_MASK);
+ else
+ ret = 1;
break;
case APIC_DFR:
- apic_set_reg(apic, APIC_DFR, val | 0x0FFFFFFF);
+ if (!apic_x2apic_mode(apic))
+ apic_set_reg(apic, APIC_DFR, val | 0x0FFFFFFF);
+ else
+ ret = 1;
break;
- case APIC_SPIV:
- apic_set_reg(apic, APIC_SPIV, val & 0x3ff);
+ case APIC_SPIV: {
+ u32 mask = 0x3ff;
+ if (apic_get_reg(apic, APIC_LVR) & APIC_LVR_DIRECTED_EOI)
+ mask |= APIC_SPIV_DIRECTED_EOI;
+ apic_set_reg(apic, APIC_SPIV, val & mask);
if (!(val & APIC_SPIV_APIC_ENABLED)) {
int i;
u32 lvt_val;
}
break;
-
+ }
case APIC_ICR:
/* No delay here, so we always clear the pending bit */
apic_set_reg(apic, APIC_ICR, val & ~(1 << 12));
break;
case APIC_ICR2:
- apic_set_reg(apic, APIC_ICR2, val & 0xff000000);
+ if (!apic_x2apic_mode(apic))
+ val &= 0xff000000;
+ apic_set_reg(apic, APIC_ICR2, val);
break;
case APIC_LVT0:
if (!apic_sw_enabled(apic))
val |= APIC_LVT_MASKED;
- val &= apic_lvt_mask[(offset - APIC_LVTT) >> 4];
- apic_set_reg(apic, offset, val);
+ val &= apic_lvt_mask[(reg - APIC_LVTT) >> 4];
+ apic_set_reg(apic, reg, val);
break;
hrtimer_cancel(&apic->lapic_timer.timer);
apic_set_reg(apic, APIC_TMICT, val);
start_apic_timer(apic);
- return;
+ break;
case APIC_TDCR:
if (val & 4)
update_divide_count(apic);
break;
+ case APIC_ESR:
+ if (apic_x2apic_mode(apic) && val != 0) {
+ printk(KERN_ERR "KVM_WRITE:ESR not zero %x\n", val);
+ ret = 1;
+ }
+ break;
+
+ case APIC_SELF_IPI:
+ if (apic_x2apic_mode(apic)) {
+ apic_reg_write(apic, APIC_ICR, 0x40000 | (val & 0xff));
+ } else
+ ret = 1;
+ break;
default:
- apic_debug("Local APIC Write to read-only register %x\n",
- offset);
+ ret = 1;
break;
}
-
+ if (ret)
+ apic_debug("Local APIC Write to read-only register %x\n", reg);
+ return ret;
}
-static int apic_mmio_range(struct kvm_io_device *this, gpa_t addr,
- int len, int size)
+static int apic_mmio_write(struct kvm_io_device *this,
+ gpa_t address, int len, const void *data)
{
struct kvm_lapic *apic = to_lapic(this);
- int ret = 0;
+ unsigned int offset = address - apic->base_address;
+ u32 val;
+ if (!apic_mmio_in_range(apic, address))
+ return -EOPNOTSUPP;
- if (apic_hw_enabled(apic) &&
- (addr >= apic->base_address) &&
- (addr < (apic->base_address + LAPIC_MMIO_LENGTH)))
- ret = 1;
+ /*
+ * APIC register must be aligned on 128-bits boundary.
+ * 32/64/128 bits registers must be accessed thru 32 bits.
+ * Refer SDM 8.4.1
+ */
+ if (len != 4 || (offset & 0xf)) {
+ /* Don't shout loud, $infamous_os would cause only noise. */
+ apic_debug("apic write: bad size=%d %lx\n", len, (long)address);
+ return 0;
+ }
- return ret;
+ val = *(u32*)data;
+
+ /* too common printing */
+ if (offset != APIC_EOI)
+ apic_debug("%s: offset 0x%x with length 0x%x, and value is "
+ "0x%x\n", __func__, offset, len, val);
+
+ apic_reg_write(apic, offset & 0xff0, val);
+
+ return 0;
}
void kvm_free_lapic(struct kvm_vcpu *vcpu)
value &= ~MSR_IA32_APICBASE_BSP;
vcpu->arch.apic_base = value;
+ if (apic_x2apic_mode(apic)) {
+ u32 id = kvm_apic_id(apic);
+ u32 ldr = ((id & ~0xf) << 16) | (1 << (id & 0xf));
+ apic_set_reg(apic, APIC_LDR, ldr);
+ }
apic->base_address = apic->vcpu->arch.apic_base &
MSR_IA32_APICBASE_BASE;
hrtimer_cancel(&apic->lapic_timer.timer);
apic_set_reg(apic, APIC_ID, vcpu->vcpu_id << 24);
- apic_set_reg(apic, APIC_LVR, APIC_VERSION);
+ kvm_apic_set_version(apic->vcpu);
for (i = 0; i < APIC_LVT_NUM; i++)
apic_set_reg(apic, APIC_LVTT + 0x10 * i, APIC_LVT_MASKED);
static const struct kvm_io_device_ops apic_mmio_ops = {
.read = apic_mmio_read,
.write = apic_mmio_write,
- .in_range = apic_mmio_range,
};
int kvm_create_lapic(struct kvm_vcpu *vcpu)
apic->base_address = vcpu->arch.apic_base &
MSR_IA32_APICBASE_BASE;
- apic_set_reg(apic, APIC_LVR, APIC_VERSION);
+ kvm_apic_set_version(vcpu);
+
apic_update_ppr(apic);
hrtimer_cancel(&apic->lapic_timer.timer);
update_divide_count(apic);
start_apic_timer(apic);
+ apic->irr_pending = true;
}
void __kvm_migrate_apic_timer(struct kvm_vcpu *vcpu)
vcpu->arch.apic->vapic_addr = vapic_addr;
}
+
+int kvm_x2apic_msr_write(struct kvm_vcpu *vcpu, u32 msr, u64 data)
+{
+ struct kvm_lapic *apic = vcpu->arch.apic;
+ u32 reg = (msr - APIC_BASE_MSR) << 4;
+
+ if (!irqchip_in_kernel(vcpu->kvm) || !apic_x2apic_mode(apic))
+ return 1;
+
+ /* if this is ICR write vector before command */
+ if (msr == 0x830)
+ apic_reg_write(apic, APIC_ICR2, (u32)(data >> 32));
+ return apic_reg_write(apic, reg, (u32)data);
+}
+
+int kvm_x2apic_msr_read(struct kvm_vcpu *vcpu, u32 msr, u64 *data)
+{
+ struct kvm_lapic *apic = vcpu->arch.apic;
+ u32 reg = (msr - APIC_BASE_MSR) << 4, low, high = 0;
+
+ if (!irqchip_in_kernel(vcpu->kvm) || !apic_x2apic_mode(apic))
+ return 1;
+
+ if (apic_reg_read(apic, reg, 4, &low))
+ return 1;
+ if (msr == 0x830)
+ apic_reg_read(apic, APIC_ICR2, 4, &high);
+
+ *data = (((u64)high) << 32) | low;
+
+ return 0;
+}
+
+int kvm_hv_vapic_msr_write(struct kvm_vcpu *vcpu, u32 reg, u64 data)
+{
+ struct kvm_lapic *apic = vcpu->arch.apic;
+
+ if (!irqchip_in_kernel(vcpu->kvm))
+ return 1;
+
+ /* if this is ICR write vector before command */
+ if (reg == APIC_ICR)
+ apic_reg_write(apic, APIC_ICR2, (u32)(data >> 32));
+ return apic_reg_write(apic, reg, (u32)data);
+}
+
+int kvm_hv_vapic_msr_read(struct kvm_vcpu *vcpu, u32 reg, u64 *data)
+{
+ struct kvm_lapic *apic = vcpu->arch.apic;
+ u32 low, high = 0;
+
+ if (!irqchip_in_kernel(vcpu->kvm))
+ return 1;
+
+ if (apic_reg_read(apic, reg, 4, &low))
+ return 1;
+ if (reg == APIC_ICR)
+ apic_reg_read(apic, APIC_ICR2, 4, &high);
+
+ *data = (((u64)high) << 32) | low;
+
+ return 0;
+}