#include <linux/hrtimer.h>
#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/current.h>
#include <asm/apicdef.h>
#include <asm/atomic.h>
-#include <asm/div64.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))
+#else
+#define mod_64(x, y) ((x) % (y))
+#endif
#define PRId64 "d"
#define PRIx64 "llx"
return apic_get_reg(apic, APIC_LVTT) & APIC_LVT_TIMER_PERIODIC;
}
+static inline int apic_lvt_nmi_mode(u32 lvt_val)
+{
+ 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 */
static inline int apic_test_and_set_irr(int vec, struct kvm_lapic *apic)
{
+ apic->irr_pending = true;
return apic_test_and_set_vector(vec, apic->regs + APIC_IRR);
}
-static inline void apic_clear_irr(int vec, struct kvm_lapic *apic)
+static inline int apic_search_irr(struct kvm_lapic *apic)
{
- apic_clear_vector(vec, apic->regs + APIC_IRR);
+ return find_highest_vector(apic->regs + APIC_IRR);
}
static inline int apic_find_highest_irr(struct kvm_lapic *apic)
{
int result;
- result = find_highest_vector(apic->regs + APIC_IRR);
+ if (!apic->irr_pending)
+ return -1;
+
+ result = apic_search_irr(apic);
ASSERT(result == -1 || result >= 16);
return result;
}
+static inline void apic_clear_irr(int vec, struct kvm_lapic *apic)
+{
+ apic->irr_pending = false;
+ apic_clear_vector(vec, apic->regs + APIC_IRR);
+ if (apic_search_irr(apic) != -1)
+ apic->irr_pending = true;
+}
+
int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu)
{
struct kvm_lapic *apic = vcpu->arch.apic;
int highest_irr;
+ /* This may race with setting of irr in __apic_accept_irq() and
+ * value returned may be wrong, but kvm_vcpu_kick() in __apic_accept_irq
+ * will cause vmexit immediately and the value will be recalculated
+ * on the next vmentry.
+ */
if (!apic)
return 0;
highest_irr = apic_find_highest_irr(apic);
return highest_irr;
}
-EXPORT_SYMBOL_GPL(kvm_lapic_find_highest_irr);
-int kvm_apic_set_irq(struct kvm_vcpu *vcpu, u8 vec, u8 trig)
+static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode,
+ int vector, int level, int trig_mode);
+
+int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq)
{
struct kvm_lapic *apic = vcpu->arch.apic;
- if (!apic_test_and_set_irr(vec, apic)) {
- /* a new pending irq is set in IRR */
- if (trig)
- apic_set_vector(vec, apic->regs + APIC_TMR);
- else
- apic_clear_vector(vec, apic->regs + APIC_TMR);
- kvm_vcpu_kick(apic->vcpu);
- return 1;
- }
- return 0;
+ return __apic_accept_irq(apic, irq->delivery_mode, irq->vector,
+ irq->level, irq->trig_mode);
}
static inline int apic_find_highest_isr(struct kvm_lapic *apic)
int kvm_apic_match_physical_addr(struct kvm_lapic *apic, u16 dest)
{
- return kvm_apic_id(apic) == dest;
+ return dest == 0xff || kvm_apic_id(apic) == dest;
}
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));
return result;
}
-static int apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source,
+int kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source,
int short_hand, int dest, int dest_mode)
{
int result = 0;
struct kvm_lapic *target = vcpu->arch.apic;
apic_debug("target %p, source %p, dest 0x%x, "
- "dest_mode 0x%x, short_hand 0x%x",
+ "dest_mode 0x%x, short_hand 0x%x\n",
target, source, dest, dest_mode, short_hand);
ASSERT(!target);
switch (short_hand) {
case APIC_DEST_NOSHORT:
- if (dest_mode == 0) {
+ if (dest_mode == 0)
/* Physical mode. */
- if ((dest == 0xFF) || (dest == kvm_apic_id(target)))
- result = 1;
- } else
+ result = kvm_apic_match_physical_addr(target, dest);
+ else
/* Logical mode. */
result = kvm_apic_match_logical_addr(target, dest);
break;
case APIC_DEST_SELF:
- if (target == source)
- result = 1;
+ result = (target == source);
break;
case APIC_DEST_ALLINC:
result = 1;
break;
case APIC_DEST_ALLBUT:
- if (target != source)
- result = 1;
+ result = (target != source);
break;
default:
printk(KERN_WARNING "Bad dest shorthand value %x\n",
static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode,
int vector, int level, int trig_mode)
{
- int orig_irr, result = 0;
+ int result = 0;
struct kvm_vcpu *vcpu = apic->vcpu;
switch (delivery_mode) {
- case APIC_DM_FIXED:
case APIC_DM_LOWEST:
+ vcpu->arch.apic_arb_prio++;
+ case APIC_DM_FIXED:
/* FIXME add logic for vcpu on reset */
if (unlikely(!apic_enabled(apic)))
break;
- orig_irr = apic_test_and_set_irr(vector, apic);
- if (orig_irr && trig_mode) {
- apic_debug("level trig mode repeatedly for vector %d",
- vector);
- 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);
- if (vcpu->arch.mp_state == VCPU_MP_STATE_RUNNABLE)
- kvm_vcpu_kick(vcpu);
- else if (vcpu->arch.mp_state == VCPU_MP_STATE_HALTED) {
- vcpu->arch.mp_state = VCPU_MP_STATE_RUNNABLE;
- if (waitqueue_active(&vcpu->wq))
- wake_up_interruptible(&vcpu->wq);
+ 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 "
+ "vector %d", vector);
+ break;
}
- result = (orig_irr == 0);
+ kvm_vcpu_kick(vcpu);
break;
case APIC_DM_REMRD:
case APIC_DM_SMI:
printk(KERN_DEBUG "Ignoring guest SMI\n");
break;
+
case APIC_DM_NMI:
- printk(KERN_DEBUG "Ignoring guest NMI\n");
+ result = 1;
+ kvm_inject_nmi(vcpu);
+ kvm_vcpu_kick(vcpu);
break;
case APIC_DM_INIT:
if (level) {
- if (vcpu->arch.mp_state == VCPU_MP_STATE_RUNNABLE)
+ result = 1;
+ if (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE)
printk(KERN_DEBUG
"INIT on a runnable vcpu %d\n",
vcpu->vcpu_id);
- vcpu->arch.mp_state = VCPU_MP_STATE_INIT_RECEIVED;
+ vcpu->arch.mp_state = KVM_MP_STATE_INIT_RECEIVED;
kvm_vcpu_kick(vcpu);
} else {
- printk(KERN_DEBUG
- "Ignoring de-assert INIT to vcpu %d\n",
- vcpu->vcpu_id);
+ apic_debug("Ignoring de-assert INIT to vcpu %d\n",
+ vcpu->vcpu_id);
}
-
break;
case APIC_DM_STARTUP:
- printk(KERN_DEBUG "SIPI to vcpu %d vector 0x%02x\n",
- vcpu->vcpu_id, vector);
- if (vcpu->arch.mp_state == VCPU_MP_STATE_INIT_RECEIVED) {
+ apic_debug("SIPI to vcpu %d vector 0x%02x\n",
+ vcpu->vcpu_id, vector);
+ if (vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED) {
+ result = 1;
vcpu->arch.sipi_vector = vector;
- vcpu->arch.mp_state = VCPU_MP_STATE_SIPI_RECEIVED;
- if (waitqueue_active(&vcpu->wq))
- wake_up_interruptible(&vcpu->wq);
+ vcpu->arch.mp_state = KVM_MP_STATE_SIPI_RECEIVED;
+ kvm_vcpu_kick(vcpu);
}
break;
+ case APIC_DM_EXTINT:
+ /*
+ * Should only be called by kvm_apic_local_deliver() with LVT0,
+ * before NMI watchdog was enabled. Already handled by
+ * kvm_apic_accept_pic_intr().
+ */
+ break;
+
default:
printk(KERN_ERR "TODO: unsupported delivery mode %x\n",
delivery_mode);
return result;
}
-static struct kvm_lapic *kvm_apic_round_robin(struct kvm *kvm, u8 vector,
- unsigned long bitmap)
+int kvm_apic_compare_prio(struct kvm_vcpu *vcpu1, struct kvm_vcpu *vcpu2)
{
- int last;
- int next;
- struct kvm_lapic *apic = NULL;
-
- last = kvm->arch.round_robin_prev_vcpu;
- next = last;
-
- do {
- if (++next == KVM_MAX_VCPUS)
- next = 0;
- if (kvm->vcpus[next] == NULL || !test_bit(next, &bitmap))
- continue;
- apic = kvm->vcpus[next]->arch.apic;
- if (apic && apic_enabled(apic))
- break;
- apic = NULL;
- } while (next != last);
- kvm->arch.round_robin_prev_vcpu = next;
-
- if (!apic)
- printk(KERN_DEBUG "vcpu not ready for apic_round_robin\n");
-
- return apic;
-}
-
-struct kvm_vcpu *kvm_get_lowest_prio_vcpu(struct kvm *kvm, u8 vector,
- unsigned long bitmap)
-{
- struct kvm_lapic *apic;
-
- apic = kvm_apic_round_robin(kvm, vector, bitmap);
- if (apic)
- return apic->vcpu;
- return NULL;
+ return vcpu1->arch.apic_arb_prio - vcpu2->arch.apic_arb_prio;
}
static void apic_set_eoi(struct kvm_lapic *apic)
{
int vector = apic_find_highest_isr(apic);
-
+ int trigger_mode;
/*
* Not every write EOI will has corresponding ISR,
* one example is when Kernel check timer on setup_IO_APIC
apic_update_ppr(apic);
if (apic_test_and_clear_vector(vector, apic->regs + APIC_TMR))
- kvm_ioapic_update_eoi(apic->vcpu->kvm, vector);
+ trigger_mode = IOAPIC_LEVEL_TRIG;
+ else
+ trigger_mode = IOAPIC_EDGE_TRIG;
+ 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)
{
u32 icr_low = apic_get_reg(apic, APIC_ICR);
u32 icr_high = apic_get_reg(apic, APIC_ICR2);
+ struct kvm_lapic_irq irq;
+
+ irq.vector = icr_low & APIC_VECTOR_MASK;
+ irq.delivery_mode = icr_low & APIC_MODE_MASK;
+ irq.dest_mode = icr_low & APIC_DEST_MASK;
+ irq.level = icr_low & APIC_INT_ASSERT;
+ irq.trig_mode = icr_low & APIC_INT_LEVELTRIG;
+ irq.shorthand = icr_low & APIC_SHORT_MASK;
+ if (apic_x2apic_mode(apic))
+ irq.dest_id = icr_high;
+ else
+ irq.dest_id = GET_APIC_DEST_FIELD(icr_high);
- unsigned int dest = GET_APIC_DEST_FIELD(icr_high);
- unsigned int short_hand = icr_low & APIC_SHORT_MASK;
- unsigned int trig_mode = icr_low & APIC_INT_LEVELTRIG;
- unsigned int level = icr_low & APIC_INT_ASSERT;
- unsigned int dest_mode = icr_low & APIC_DEST_MASK;
- unsigned int delivery_mode = icr_low & APIC_MODE_MASK;
- unsigned int vector = icr_low & APIC_VECTOR_MASK;
-
- struct kvm_vcpu *target;
- struct kvm_vcpu *vcpu;
- unsigned long lpr_map = 0;
- int i;
+ 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, "
"dest_mode 0x%x, delivery_mode 0x%x, vector 0x%x\n",
- icr_high, icr_low, short_hand, dest,
- trig_mode, level, dest_mode, delivery_mode, vector);
-
- for (i = 0; i < KVM_MAX_VCPUS; i++) {
- vcpu = apic->vcpu->kvm->vcpus[i];
- if (!vcpu)
- continue;
-
- if (vcpu->arch.apic &&
- apic_match_dest(vcpu, apic, short_hand, dest, dest_mode)) {
- if (delivery_mode == APIC_DM_LOWEST)
- set_bit(vcpu->vcpu_id, &lpr_map);
- else
- __apic_accept_irq(vcpu->arch.apic, delivery_mode,
- vector, level, trig_mode);
- }
- }
+ icr_high, icr_low, irq.shorthand, irq.dest_id,
+ irq.trig_mode, irq.level, irq.dest_mode, irq.delivery_mode,
+ irq.vector);
- if (delivery_mode == APIC_DM_LOWEST) {
- target = kvm_get_lowest_prio_vcpu(vcpu->kvm, vector, lpr_map);
- if (target != NULL)
- __apic_accept_irq(target->arch.apic, delivery_mode,
- vector, level, trig_mode);
- }
+ kvm_irq_delivery_to_apic(apic->vcpu->kvm, apic, &irq);
}
static u32 apic_get_tmcct(struct kvm_lapic *apic)
{
- u64 counter_passed;
- ktime_t passed, now;
+ ktime_t remaining;
+ s64 ns;
u32 tmcct;
ASSERT(apic != NULL);
- now = apic->timer.dev.base->get_time();
- tmcct = apic_get_reg(apic, APIC_TMICT);
-
/* if initial count is 0, current count should also be 0 */
- if (tmcct == 0)
+ if (apic_get_reg(apic, APIC_TMICT) == 0)
return 0;
- if (unlikely(ktime_to_ns(now) <=
- ktime_to_ns(apic->timer.last_update))) {
- /* Wrap around */
- passed = ktime_add(( {
- (ktime_t) {
- .tv64 = KTIME_MAX -
- (apic->timer.last_update).tv64}; }
- ), now);
- apic_debug("time elapsed\n");
- } else
- passed = ktime_sub(now, apic->timer.last_update);
-
- counter_passed = div64_64(ktime_to_ns(passed),
- (APIC_BUS_CYCLE_NS * apic->timer.divide_count));
-
- if (counter_passed > tmcct) {
- if (unlikely(!apic_lvtt_period(apic))) {
- /* one-shot timers stick at 0 until reset */
- tmcct = 0;
- } else {
- /*
- * periodic timers reset to APIC_TMICT when they
- * hit 0. The while loop simulates this happening N
- * times. (counter_passed %= tmcct) would also work,
- * but might be slower or not work on 32-bit??
- */
- while (counter_passed > tmcct)
- counter_passed -= tmcct;
- tmcct -= counter_passed;
- }
- } else {
- tmcct -= counter_passed;
- }
+ remaining = hrtimer_get_remaining(&apic->lapic_timer.timer);
+ if (ktime_to_ns(remaining) < 0)
+ remaining = ktime_set(0, 0);
+
+ ns = mod_64(ktime_to_ns(remaining), apic->lapic_timer.period);
+ tmcct = div64_u64(ns,
+ (APIC_BUS_CYCLE_NS * apic->divide_count));
return tmcct;
}
struct kvm_run *run = vcpu->run;
set_bit(KVM_REQ_REPORT_TPR_ACCESS, &vcpu->requests);
- kvm_x86_ops->cache_regs(vcpu);
- run->tpr_access.rip = vcpu->arch.rip;
+ run->tpr_access.rip = kvm_rip_read(vcpu);
run->tpr_access.is_write = write;
}
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 val;
}
-static void apic_mmio_read(struct kvm_io_device *this,
- gpa_t address, int len, void *data)
+static inline struct kvm_lapic *to_lapic(struct kvm_io_device *dev)
+{
+ return container_of(dev, struct kvm_lapic, dev);
+}
+
+static int apic_reg_read(struct kvm_lapic *apic, u32 offset, int len,
+ void *data)
{
- struct kvm_lapic *apic = (struct kvm_lapic *)this->private;
- 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)
tdcr = apic_get_reg(apic, APIC_TDCR);
tmp1 = tdcr & 0xf;
tmp2 = ((tmp1 & 0x3) | ((tmp1 & 0x8) >> 1)) + 1;
- apic->timer.divide_count = 0x1 << (tmp2 & 0x7);
+ apic->divide_count = 0x1 << (tmp2 & 0x7);
apic_debug("timer divide count is 0x%x\n",
- apic->timer.divide_count);
+ apic->divide_count);
}
static void start_apic_timer(struct kvm_lapic *apic)
{
- ktime_t now = apic->timer.dev.base->get_time();
+ ktime_t now = apic->lapic_timer.timer.base->get_time();
+
+ 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);
- apic->timer.last_update = now;
+ 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;
+ }
- apic->timer.period = apic_get_reg(apic, APIC_TMICT) *
- APIC_BUS_CYCLE_NS * apic->timer.divide_count;
- atomic_set(&apic->timer.pending, 0);
- hrtimer_start(&apic->timer.dev,
- ktime_add_ns(now, apic->timer.period),
+ hrtimer_start(&apic->lapic_timer.timer,
+ ktime_add_ns(now, apic->lapic_timer.period),
HRTIMER_MODE_ABS);
apic_debug("%s: bus cycle is %" PRId64 "ns, now 0x%016"
PRIx64 ", "
"timer initial count 0x%x, period %lldns, "
- "expire @ 0x%016" PRIx64 ".\n", __FUNCTION__,
+ "expire @ 0x%016" PRIx64 ".\n", __func__,
APIC_BUS_CYCLE_NS, ktime_to_ns(now),
apic_get_reg(apic, APIC_TMICT),
- apic->timer.period,
+ apic->lapic_timer.period,
ktime_to_ns(ktime_add_ns(now,
- apic->timer.period)));
+ apic->lapic_timer.period)));
}
-static void apic_mmio_write(struct kvm_io_device *this,
- gpa_t address, int len, const void *data)
+static void apic_manage_nmi_watchdog(struct kvm_lapic *apic, u32 lvt0_val)
{
- struct kvm_lapic *apic = (struct kvm_lapic *)this->private;
- unsigned int offset = address - apic->base_address;
- unsigned char alignment = offset & 0xf;
- u32 val;
+ int nmi_wd_enabled = apic_lvt_nmi_mode(apic_get_reg(apic, APIC_LVT0));
- /*
- * 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) {
- if (printk_ratelimit())
- printk(KERN_ERR "apic write: bad size=%d %lx\n",
- len, (long)address);
- return;
- }
-
- val = *(u32 *) data;
+ if (apic_lvt_nmi_mode(lvt0_val)) {
+ if (!nmi_wd_enabled) {
+ apic_debug("Receive NMI setting on APIC_LVT0 "
+ "for cpu %d\n", apic->vcpu->vcpu_id);
+ apic->vcpu->kvm->arch.vapics_in_nmi_mode++;
+ }
+ } else if (nmi_wd_enabled)
+ apic->vcpu->kvm->arch.vapics_in_nmi_mode--;
+}
- /* too common printing */
- if (offset != APIC_EOI)
- apic_debug("%s: offset 0x%x with length 0x%x, and value is "
- "0x%x\n", __FUNCTION__, offset, len, val);
+static int apic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val)
+{
+ int ret = 0;
- offset &= 0xff0;
+ 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;
apic_set_reg(apic, APIC_LVTT + 0x10 * i,
lvt_val | APIC_LVT_MASKED);
}
- atomic_set(&apic->timer.pending, 0);
+ atomic_set(&apic->lapic_timer.pending, 0);
}
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:
+ apic_manage_nmi_watchdog(apic, val);
case APIC_LVTT:
case APIC_LVTTHMR:
case APIC_LVTPC:
- case APIC_LVT0:
case APIC_LVT1:
case APIC_LVTERR:
/* TODO: Check vector */
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;
case APIC_TMICT:
- hrtimer_cancel(&apic->timer.dev);
+ 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)
+static int apic_mmio_write(struct kvm_io_device *this,
+ gpa_t address, int len, const void *data)
{
- struct kvm_lapic *apic = (struct kvm_lapic *)this->private;
- int ret = 0;
+ struct kvm_lapic *apic = to_lapic(this);
+ 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)
if (!vcpu->arch.apic)
return;
- hrtimer_cancel(&vcpu->arch.apic->timer.dev);
+ hrtimer_cancel(&vcpu->arch.apic->lapic_timer.timer);
if (vcpu->arch.apic->regs_page)
__free_page(vcpu->arch.apic->regs_page);
return (tpr & 0xf0) >> 4;
}
-EXPORT_SYMBOL_GPL(kvm_lapic_get_cr8);
void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value)
{
vcpu->arch.apic_base = value;
return;
}
- if (apic->vcpu->vcpu_id)
+
+ if (!kvm_vcpu_is_bsp(apic->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;
}
-u64 kvm_lapic_get_base(struct kvm_vcpu *vcpu)
-{
- return vcpu->arch.apic_base;
-}
-EXPORT_SYMBOL_GPL(kvm_lapic_get_base);
-
void kvm_lapic_reset(struct kvm_vcpu *vcpu)
{
struct kvm_lapic *apic;
int i;
- apic_debug("%s\n", __FUNCTION__);
+ apic_debug("%s\n", __func__);
ASSERT(vcpu);
apic = vcpu->arch.apic;
ASSERT(apic != NULL);
/* Stop the timer in case it's a reset to an active apic */
- hrtimer_cancel(&apic->timer.dev);
+ 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);
apic_set_reg(apic, APIC_ISR + 0x10 * i, 0);
apic_set_reg(apic, APIC_TMR + 0x10 * i, 0);
}
+ apic->irr_pending = false;
update_divide_count(apic);
- atomic_set(&apic->timer.pending, 0);
- if (vcpu->vcpu_id == 0)
+ atomic_set(&apic->lapic_timer.pending, 0);
+ if (kvm_vcpu_is_bsp(vcpu))
vcpu->arch.apic_base |= MSR_IA32_APICBASE_BSP;
apic_update_ppr(apic);
+ vcpu->arch.apic_arb_prio = 0;
+
apic_debug(KERN_INFO "%s: vcpu=%p, id=%d, base_msr="
- "0x%016" PRIx64 ", base_address=0x%0lx.\n", __FUNCTION__,
+ "0x%016" PRIx64 ", base_address=0x%0lx.\n", __func__,
vcpu, kvm_apic_id(apic),
vcpu->arch.apic_base, apic->base_address);
}
-EXPORT_SYMBOL_GPL(kvm_lapic_reset);
-int kvm_lapic_enabled(struct kvm_vcpu *vcpu)
+bool kvm_apic_present(struct kvm_vcpu *vcpu)
{
- struct kvm_lapic *apic = vcpu->arch.apic;
- int ret = 0;
-
- if (!apic)
- return 0;
- ret = apic_enabled(apic);
+ return vcpu->arch.apic && apic_hw_enabled(vcpu->arch.apic);
+}
- return ret;
+int kvm_lapic_enabled(struct kvm_vcpu *vcpu)
+{
+ return kvm_apic_present(vcpu) && apic_sw_enabled(vcpu->arch.apic);
}
-EXPORT_SYMBOL_GPL(kvm_lapic_enabled);
/*
*----------------------------------------------------------------------
*----------------------------------------------------------------------
*/
-/* TODO: make sure __apic_timer_fn runs in current pCPU */
-static int __apic_timer_fn(struct kvm_lapic *apic)
+static bool lapic_is_periodic(struct kvm_timer *ktimer)
{
- int result = 0;
- wait_queue_head_t *q = &apic->vcpu->wq;
-
- atomic_inc(&apic->timer.pending);
- if (waitqueue_active(q)) {
- apic->vcpu->arch.mp_state = VCPU_MP_STATE_RUNNABLE;
- wake_up_interruptible(q);
- }
- if (apic_lvtt_period(apic)) {
- result = 1;
- apic->timer.dev.expires = ktime_add_ns(
- apic->timer.dev.expires,
- apic->timer.period);
- }
- return result;
+ struct kvm_lapic *apic = container_of(ktimer, struct kvm_lapic,
+ lapic_timer);
+ return apic_lvtt_period(apic);
}
-static int __inject_apic_timer_irq(struct kvm_lapic *apic)
+int apic_has_pending_timer(struct kvm_vcpu *vcpu)
{
- int vector;
+ struct kvm_lapic *lapic = vcpu->arch.apic;
- vector = apic_lvt_vector(apic, APIC_LVTT);
- return __apic_accept_irq(apic, APIC_DM_FIXED, vector, 1, 0);
+ if (lapic && apic_enabled(lapic) && apic_lvt_enabled(lapic, APIC_LVTT))
+ return atomic_read(&lapic->lapic_timer.pending);
+
+ return 0;
}
-static enum hrtimer_restart apic_timer_fn(struct hrtimer *data)
+static int kvm_apic_local_deliver(struct kvm_lapic *apic, int lvt_type)
{
- struct kvm_lapic *apic;
- int restart_timer = 0;
-
- apic = container_of(data, struct kvm_lapic, timer.dev);
+ u32 reg = apic_get_reg(apic, lvt_type);
+ int vector, mode, trig_mode;
+
+ if (apic_hw_enabled(apic) && !(reg & APIC_LVT_MASKED)) {
+ vector = reg & APIC_VECTOR_MASK;
+ mode = reg & APIC_MODE_MASK;
+ trig_mode = reg & APIC_LVT_LEVEL_TRIGGER;
+ return __apic_accept_irq(apic, mode, vector, 1, trig_mode);
+ }
+ return 0;
+}
- restart_timer = __apic_timer_fn(apic);
+void kvm_apic_nmi_wd_deliver(struct kvm_vcpu *vcpu)
+{
+ struct kvm_lapic *apic = vcpu->arch.apic;
- if (restart_timer)
- return HRTIMER_RESTART;
- else
- return HRTIMER_NORESTART;
+ if (apic)
+ kvm_apic_local_deliver(apic, APIC_LVT0);
}
+static struct kvm_timer_ops lapic_timer_ops = {
+ .is_periodic = lapic_is_periodic,
+};
+
+static const struct kvm_io_device_ops apic_mmio_ops = {
+ .read = apic_mmio_read,
+ .write = apic_mmio_write,
+};
+
int kvm_create_lapic(struct kvm_vcpu *vcpu)
{
struct kvm_lapic *apic;
memset(apic->regs, 0, PAGE_SIZE);
apic->vcpu = vcpu;
- hrtimer_init(&apic->timer.dev, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
- apic->timer.dev.function = apic_timer_fn;
+ hrtimer_init(&apic->lapic_timer.timer, CLOCK_MONOTONIC,
+ HRTIMER_MODE_ABS);
+ apic->lapic_timer.timer.function = kvm_timer_fn;
+ apic->lapic_timer.t_ops = &lapic_timer_ops;
+ apic->lapic_timer.kvm = vcpu->kvm;
+ apic->lapic_timer.vcpu = vcpu;
+
apic->base_address = APIC_DEFAULT_PHYS_BASE;
vcpu->arch.apic_base = APIC_DEFAULT_PHYS_BASE;
kvm_lapic_reset(vcpu);
- apic->dev.read = apic_mmio_read;
- apic->dev.write = apic_mmio_write;
- apic->dev.in_range = apic_mmio_range;
- apic->dev.private = apic;
+ kvm_iodevice_init(&apic->dev, &apic_mmio_ops);
return 0;
nomem_free_apic:
nomem:
return -ENOMEM;
}
-EXPORT_SYMBOL_GPL(kvm_create_lapic);
int kvm_apic_has_interrupt(struct kvm_vcpu *vcpu)
{
u32 lvt0 = apic_get_reg(vcpu->arch.apic, APIC_LVT0);
int r = 0;
- if (vcpu->vcpu_id == 0) {
+ if (kvm_vcpu_is_bsp(vcpu)) {
if (!apic_hw_enabled(vcpu->arch.apic))
r = 1;
if ((lvt0 & APIC_LVT_MASKED) == 0 &&
{
struct kvm_lapic *apic = vcpu->arch.apic;
- if (apic && apic_lvt_enabled(apic, APIC_LVTT) &&
- atomic_read(&apic->timer.pending) > 0) {
- if (__inject_apic_timer_irq(apic))
- atomic_dec(&apic->timer.pending);
+ if (apic && atomic_read(&apic->lapic_timer.pending) > 0) {
+ if (kvm_apic_local_deliver(apic, APIC_LVTT))
+ atomic_dec(&apic->lapic_timer.pending);
}
}
-void kvm_apic_timer_intr_post(struct kvm_vcpu *vcpu, int vec)
-{
- struct kvm_lapic *apic = vcpu->arch.apic;
-
- if (apic && apic_lvt_vector(apic, APIC_LVTT) == vec)
- apic->timer.last_update = ktime_add_ns(
- apic->timer.last_update,
- apic->timer.period);
-}
-
int kvm_get_apic_interrupt(struct kvm_vcpu *vcpu)
{
int vector = kvm_apic_has_interrupt(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->timer.dev);
+ 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)
if (!apic)
return;
- timer = &apic->timer.dev;
+ timer = &apic->lapic_timer.timer;
if (hrtimer_cancel(timer))
- hrtimer_start(timer, timer->expires, HRTIMER_MODE_ABS);
+ hrtimer_start_expires(timer, HRTIMER_MODE_ABS);
}
void kvm_lapic_sync_from_vapic(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;
+}