17 files changed, 217 insertions, 231 deletions

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 09155d6..48e7131 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -500,11 +500,11 @@ struct kvm_vcpu_arch {
 };
 
 struct kvm_lpage_info {
-	unsigned long rmap_pde;
 	int write_count;
 };
 
 struct kvm_arch_memory_slot {
+	unsigned long *rmap_pde[KVM_NR_PAGE_SIZES - 1];
 	struct kvm_lpage_info *lpage_info[KVM_NR_PAGE_SIZES - 1];
 };
 
@@ -957,6 +957,7 @@ extern bool kvm_rebooting;
 
 #define KVM_ARCH_WANT_MMU_NOTIFIER
 int kvm_unmap_hva(struct kvm *kvm, unsigned long hva);
+int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end);
 int kvm_age_hva(struct kvm *kvm, unsigned long hva);
 int kvm_test_age_hva(struct kvm *kvm, unsigned long hva);
 void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte);
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index a28f338..45c044f 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -37,6 +37,7 @@ config KVM
 	select TASK_DELAY_ACCT
 	select PERF_EVENTS
 	select HAVE_KVM_MSI
+	select HAVE_KVM_CPU_RELAX_INTERCEPT
 	---help---
 	  Support hosting fully virtualized guest machines using hardware
 	  virtualization extensions.  You will need a fairly recent
diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile
index 4f579e8..04d3040 100644
--- a/arch/x86/kvm/Makefile
+++ b/arch/x86/kvm/Makefile
@@ -12,7 +12,7 @@ kvm-$(CONFIG_IOMMU_API)	+= $(addprefix ../../../virt/kvm/, iommu.o)
 kvm-$(CONFIG_KVM_ASYNC_PF)	+= $(addprefix ../../../virt/kvm/, async_pf.o)
 
 kvm-y			+= x86.o mmu.o emulate.o i8259.o irq.o lapic.o \
-			   i8254.o timer.o cpuid.o pmu.o
+			   i8254.o cpuid.o pmu.o
 kvm-intel-y		+= vmx.o
 kvm-amd-y		+= svm.o
 
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 0595f13..b496da6 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -316,7 +316,7 @@ static int do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 	}
 	case 7: {
 		entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
-		/* Mask ebx against host capbability word 9 */
+		/* Mask ebx against host capability word 9 */
 		if (index == 0) {
 			entry->ebx &= kvm_supported_word9_x86_features;
 			cpuid_mask(&entry->ebx, 9);
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 97d9a99..10f0136 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -642,7 +642,7 @@ static int __linearize(struct x86_emulate_ctxt *ctxt,
 			if (addr.ea > lim || (u32)(addr.ea + size - 1) > lim)
 				goto bad;
 		} else {
-			/* exapand-down segment */
+			/* expand-down segment */
 			if (addr.ea <= lim || (u32)(addr.ea + size - 1) <= lim)
 				goto bad;
 			lim = desc.d ? 0xffffffff : 0xffff;
@@ -1166,24 +1166,21 @@ static int read_emulated(struct x86_emulate_ctxt *ctxt,
 	int rc;
 	struct read_cache *mc = &ctxt->mem_read;
 
-	while (size) {
-		int n = min(size, 8u);
-		size -= n;
-		if (mc->pos < mc->end)
-			goto read_cached;
+	if (mc->pos < mc->end)
+		goto read_cached;
 
-		rc = ctxt->ops->read_emulated(ctxt, addr, mc->data + mc->end, n,
-					      &ctxt->exception);
-		if (rc != X86EMUL_CONTINUE)
-			return rc;
-		mc->end += n;
+	WARN_ON((mc->end + size) >= sizeof(mc->data));
 
-	read_cached:
-		memcpy(dest, mc->data + mc->pos, n);
-		mc->pos += n;
-		dest += n;
-		addr += n;
-	}
+	rc = ctxt->ops->read_emulated(ctxt, addr, mc->data + mc->end, size,
+				      &ctxt->exception);
+	if (rc != X86EMUL_CONTINUE)
+		return rc;
+
+	mc->end += size;
+
+read_cached:
+	memcpy(dest, mc->data + mc->pos, size);
+	mc->pos += size;
 	return X86EMUL_CONTINUE;
 }
 
@@ -1383,7 +1380,7 @@ static int load_segment_descriptor(struct x86_emulate_ctxt *ctxt,
 	err_code = selector & 0xfffc;
 	err_vec = GP_VECTOR;
 
-	/* can't load system descriptor into segment selecor */
+	/* can't load system descriptor into segment selector */
 	if (seg <= VCPU_SREG_GS && !seg_desc.s)
 		goto exception;
 
@@ -2038,12 +2035,6 @@ static void
 setup_syscalls_segments(struct x86_emulate_ctxt *ctxt,
 			struct desc_struct *cs, struct desc_struct *ss)
 {
-	u16 selector;
-
-	memset(cs, 0, sizeof(struct desc_struct));
-	ctxt->ops->get_segment(ctxt, &selector, cs, NULL, VCPU_SREG_CS);
-	memset(ss, 0, sizeof(struct desc_struct));
-
 	cs->l = 0;		/* will be adjusted later */
 	set_desc_base(cs, 0);	/* flat segment */
 	cs->g = 1;		/* 4kb granularity */
@@ -2053,6 +2044,7 @@ setup_syscalls_segments(struct x86_emulate_ctxt *ctxt,
 	cs->dpl = 0;		/* will be adjusted later */
 	cs->p = 1;
 	cs->d = 1;
+	cs->avl = 0;
 
 	set_desc_base(ss, 0);	/* flat segment */
 	set_desc_limit(ss, 0xfffff);	/* 4GB limit */
@@ -2062,6 +2054,8 @@ setup_syscalls_segments(struct x86_emulate_ctxt *ctxt,
 	ss->d = 1;		/* 32bit stack segment */
 	ss->dpl = 0;
 	ss->p = 1;
+	ss->l = 0;
+	ss->avl = 0;
 }
 
 static bool vendor_intel(struct x86_emulate_ctxt *ctxt)
@@ -2398,7 +2392,7 @@ static int load_state_from_tss16(struct x86_emulate_ctxt *ctxt,
 	set_segment_selector(ctxt, tss->ds, VCPU_SREG_DS);
 
 	/*
-	 * Now load segment descriptors. If fault happenes at this stage
+	 * Now load segment descriptors. If fault happens at this stage
 	 * it is handled in a context of new task
 	 */
 	ret = load_segment_descriptor(ctxt, tss->ldt, VCPU_SREG_LDTR);
@@ -2640,7 +2634,7 @@ static int emulator_do_task_switch(struct x86_emulate_ctxt *ctxt,
 	 *
 	 * 1. jmp/call/int to task gate: Check against DPL of the task gate
 	 * 2. Exception/IRQ/iret: No check is performed
-	 * 3. jmp/call to TSS: Check agains DPL of the TSS
+	 * 3. jmp/call to TSS: Check against DPL of the TSS
 	 */
 	if (reason == TASK_SWITCH_GATE) {
 		if (idt_index != -1) {
@@ -2681,7 +2675,7 @@ static int emulator_do_task_switch(struct x86_emulate_ctxt *ctxt,
 		ctxt->eflags = ctxt->eflags & ~X86_EFLAGS_NT;
 
 	/* set back link to prev task only if NT bit is set in eflags
-	   note that old_tss_sel is not used afetr this point */
+	   note that old_tss_sel is not used after this point */
 	if (reason != TASK_SWITCH_CALL && reason != TASK_SWITCH_GATE)
 		old_tss_sel = 0xffff;
 
diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c
index adba28f..11300d2 100644
--- a/arch/x86/kvm/i8254.c
+++ b/arch/x86/kvm/i8254.c
@@ -108,7 +108,7 @@ static s64 __kpit_elapsed(struct kvm *kvm)
 	ktime_t remaining;
 	struct kvm_kpit_state *ps = &kvm->arch.vpit->pit_state;
 
-	if (!ps->pit_timer.period)
+	if (!ps->period)
 		return 0;
 
 	/*
@@ -120,9 +120,9 @@ static s64 __kpit_elapsed(struct kvm *kvm)
 	 * itself with the initial count and continues counting
 	 * from there.
 	 */
-	remaining = hrtimer_get_remaining(&ps->pit_timer.timer);
-	elapsed = ps->pit_timer.period - ktime_to_ns(remaining);
-	elapsed = mod_64(elapsed, ps->pit_timer.period);
+	remaining = hrtimer_get_remaining(&ps->timer);
+	elapsed = ps->period - ktime_to_ns(remaining);
+	elapsed = mod_64(elapsed, ps->period);
 
 	return elapsed;
 }
@@ -238,12 +238,12 @@ static void kvm_pit_ack_irq(struct kvm_irq_ack_notifier *kian)
 	int value;
 
 	spin_lock(&ps->inject_lock);
-	value = atomic_dec_return(&ps->pit_timer.pending);
+	value = atomic_dec_return(&ps->pending);
 	if (value < 0)
 		/* spurious acks can be generated if, for example, the
 		 * PIC is being reset.  Handle it gracefully here
 		 */
-		atomic_inc(&ps->pit_timer.pending);
+		atomic_inc(&ps->pending);
 	else if (value > 0)
 		/* in this case, we had multiple outstanding pit interrupts
 		 * that we needed to inject.  Reinject
@@ -261,28 +261,17 @@ void __kvm_migrate_pit_timer(struct kvm_vcpu *vcpu)
 	if (!kvm_vcpu_is_bsp(vcpu) || !pit)
 		return;
 
-	timer = &pit->pit_state.pit_timer.timer;
+	timer = &pit->pit_state.timer;
 	if (hrtimer_cancel(timer))
 		hrtimer_start_expires(timer, HRTIMER_MODE_ABS);
 }
 
 static void destroy_pit_timer(struct kvm_pit *pit)
 {
-	hrtimer_cancel(&pit->pit_state.pit_timer.timer);
+	hrtimer_cancel(&pit->pit_state.timer);
 	flush_kthread_work(&pit->expired);
 }
 
-static bool kpit_is_periodic(struct kvm_timer *ktimer)
-{
-	struct kvm_kpit_state *ps = container_of(ktimer, struct kvm_kpit_state,
-						 pit_timer);
-	return ps->is_periodic;
-}
-
-static struct kvm_timer_ops kpit_ops = {
-	.is_periodic = kpit_is_periodic,
-};
-
 static void pit_do_work(struct kthread_work *work)
 {
 	struct kvm_pit *pit = container_of(work, struct kvm_pit, expired);
@@ -322,16 +311,16 @@ static void pit_do_work(struct kthread_work *work)
 
 static enum hrtimer_restart pit_timer_fn(struct hrtimer *data)
 {
-	struct kvm_timer *ktimer = container_of(data, struct kvm_timer, timer);
-	struct kvm_pit *pt = ktimer->kvm->arch.vpit;
+	struct kvm_kpit_state *ps = container_of(data, struct kvm_kpit_state, timer);
+	struct kvm_pit *pt = ps->kvm->arch.vpit;
 
-	if (ktimer->reinject || !atomic_read(&ktimer->pending)) {
-		atomic_inc(&ktimer->pending);
+	if (ps->reinject || !atomic_read(&ps->pending)) {
+		atomic_inc(&ps->pending);
 		queue_kthread_work(&pt->worker, &pt->expired);
 	}
 
-	if (ktimer->t_ops->is_periodic(ktimer)) {
-		hrtimer_add_expires_ns(&ktimer->timer, ktimer->period);
+	if (ps->is_periodic) {
+		hrtimer_add_expires_ns(&ps->timer, ps->period);
 		return HRTIMER_RESTART;
 	} else
 		return HRTIMER_NORESTART;
@@ -340,7 +329,6 @@ static enum hrtimer_restart pit_timer_fn(struct hrtimer *data)
 static void create_pit_timer(struct kvm *kvm, u32 val, int is_period)
 {
 	struct kvm_kpit_state *ps = &kvm->arch.vpit->pit_state;
-	struct kvm_timer *pt = &ps->pit_timer;
 	s64 interval;
 
 	if (!irqchip_in_kernel(kvm) || ps->flags & KVM_PIT_FLAGS_HPET_LEGACY)
@@ -351,19 +339,18 @@ static void create_pit_timer(struct kvm *kvm, u32 val, int is_period)
 	pr_debug("create pit timer, interval is %llu nsec\n", interval);
 
 	/* TODO The new value only affected after the retriggered */
-	hrtimer_cancel(&pt->timer);
+	hrtimer_cancel(&ps->timer);
 	flush_kthread_work(&ps->pit->expired);
-	pt->period = interval;
+	ps->period = interval;
 	ps->is_periodic = is_period;
 
-	pt->timer.function = pit_timer_fn;
-	pt->t_ops = &kpit_ops;
-	pt->kvm = ps->pit->kvm;
+	ps->timer.function = pit_timer_fn;
+	ps->kvm = ps->pit->kvm;
 
-	atomic_set(&pt->pending, 0);
+	atomic_set(&ps->pending, 0);
 	ps->irq_ack = 1;
 
-	hrtimer_start(&pt->timer, ktime_add_ns(ktime_get(), interval),
+	hrtimer_start(&ps->timer, ktime_add_ns(ktime_get(), interval),
 		      HRTIMER_MODE_ABS);
 }
 
@@ -639,7 +626,7 @@ void kvm_pit_reset(struct kvm_pit *pit)
 	}
 	mutex_unlock(&pit->pit_state.lock);
 
-	atomic_set(&pit->pit_state.pit_timer.pending, 0);
+	atomic_set(&pit->pit_state.pending, 0);
 	pit->pit_state.irq_ack = 1;
 }
 
@@ -648,7 +635,7 @@ static void pit_mask_notifer(struct kvm_irq_mask_notifier *kimn, bool mask)
 	struct kvm_pit *pit = container_of(kimn, struct kvm_pit, mask_notifier);
 
 	if (!mask) {
-		atomic_set(&pit->pit_state.pit_timer.pending, 0);
+		atomic_set(&pit->pit_state.pending, 0);
 		pit->pit_state.irq_ack = 1;
 	}
 }
@@ -706,12 +693,11 @@ struct kvm_pit *kvm_create_pit(struct kvm *kvm, u32 flags)
 
 	pit_state = &pit->pit_state;
 	pit_state->pit = pit;
-	hrtimer_init(&pit_state->pit_timer.timer,
-		     CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
+	hrtimer_init(&pit_state->timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
 	pit_state->irq_ack_notifier.gsi = 0;
 	pit_state->irq_ack_notifier.irq_acked = kvm_pit_ack_irq;
 	kvm_register_irq_ack_notifier(kvm, &pit_state->irq_ack_notifier);
-	pit_state->pit_timer.reinject = true;
+	pit_state->reinject = true;
 	mutex_unlock(&pit->pit_state.lock);
 
 	kvm_pit_reset(pit);
@@ -761,7 +747,7 @@ void kvm_free_pit(struct kvm *kvm)
 		kvm_unregister_irq_ack_notifier(kvm,
 				&kvm->arch.vpit->pit_state.irq_ack_notifier);
 		mutex_lock(&kvm->arch.vpit->pit_state.lock);
-		timer = &kvm->arch.vpit->pit_state.pit_timer.timer;
+		timer = &kvm->arch.vpit->pit_state.timer;
 		hrtimer_cancel(timer);
 		flush_kthread_work(&kvm->arch.vpit->expired);
 		kthread_stop(kvm->arch.vpit->worker_task);
diff --git a/arch/x86/kvm/i8254.h b/arch/x86/kvm/i8254.h
index fdf4042..dd1b16b 100644
--- a/arch/x86/kvm/i8254.h
+++ b/arch/x86/kvm/i8254.h
@@ -24,8 +24,12 @@ struct kvm_kpit_channel_state {
 struct kvm_kpit_state {
 	struct kvm_kpit_channel_state channels[3];
 	u32 flags;
-	struct kvm_timer pit_timer;
 	bool is_periodic;
+	s64 period; 				/* unit: ns */
+	struct hrtimer timer;
+	atomic_t pending;			/* accumulated triggered timers */
+	bool reinject;
+	struct kvm *kvm;
 	u32    speaker_data_on;
 	struct mutex lock;
 	struct kvm_pit *pit;
diff --git a/arch/x86/kvm/irq.h b/arch/x86/kvm/irq.h
index 2086f2b..2d03568 100644
--- a/arch/x86/kvm/irq.h
+++ b/arch/x86/kvm/irq.h
@@ -70,7 +70,7 @@ struct kvm_pic {
 	struct kvm_io_device dev_slave;
 	struct kvm_io_device dev_eclr;
 	void (*ack_notifier)(void *opaque, int irq);
-	unsigned long irq_states[16];
+	unsigned long irq_states[PIC_NUM_PINS];
 };
 
 struct kvm_pic *kvm_create_pic(struct kvm *kvm);
diff --git a/arch/x86/kvm/kvm_timer.h b/arch/x86/kvm/kvm_timer.h
deleted file mode 100644
index 497dbaa..0000000
--- a/arch/x86/kvm/kvm_timer.h
+++ /dev/null
@@ -1,18 +0,0 @@
-
-struct kvm_timer {
-	struct hrtimer timer;
-	s64 period; 				/* unit: ns */
-	u32 timer_mode_mask;
-	u64 tscdeadline;
-	atomic_t pending;			/* accumulated triggered timers */
-	bool reinject;
-	struct kvm_timer_ops *t_ops;
-	struct kvm *kvm;
-	struct kvm_vcpu *vcpu;
-};
-
-struct kvm_timer_ops {
-	bool (*is_periodic)(struct kvm_timer *);
-};
-
-enum hrtimer_restart kvm_timer_fn(struct hrtimer *data);
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index ce87878..0cd431c 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -696,12 +696,14 @@ static u32 __apic_read(struct kvm_lapic *apic, unsigned int offset)
 
 		val = apic_get_tmcct(apic);
 		break;
-
+	case APIC_PROCPRI:
+		apic_update_ppr(apic);
+		val = apic_get_reg(apic, offset);
+		break;
 	case APIC_TASKPRI:
 		report_tpr_access(apic, false);
 		/* fall thru */
 	default:
-		apic_update_ppr(apic);
 		val = apic_get_reg(apic, offset);
 		break;
 	}
@@ -719,7 +721,7 @@ static int apic_reg_read(struct kvm_lapic *apic, u32 offset, int len,
 {
 	unsigned char alignment = offset & 0xf;
 	u32 result;
-	/* this bitmask has a bit cleared for each reserver register */
+	/* this bitmask has a bit cleared for each reserved register */
 	static const u64 rmask = 0x43ff01ffffffe70cULL;
 
 	if ((alignment + len) > 4) {
@@ -792,7 +794,7 @@ static void start_apic_timer(struct kvm_lapic *apic)
 	atomic_set(&apic->lapic_timer.pending, 0);
 
 	if (apic_lvtt_period(apic) || apic_lvtt_oneshot(apic)) {
-		/* lapic timer in oneshot or peroidic mode */
+		/* lapic timer in oneshot or periodic mode */
 		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;
@@ -1212,10 +1214,8 @@ int kvm_lapic_enabled(struct kvm_vcpu *vcpu)
  *----------------------------------------------------------------------
  */
 
-static bool lapic_is_periodic(struct kvm_timer *ktimer)
+static bool lapic_is_periodic(struct kvm_lapic *apic)
 {
-	struct kvm_lapic *apic = container_of(ktimer, struct kvm_lapic,
-					      lapic_timer);
 	return apic_lvtt_period(apic);
 }
 
@@ -1251,15 +1251,40 @@ void kvm_apic_nmi_wd_deliver(struct kvm_vcpu *vcpu)
 		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,
 };
 
+static enum hrtimer_restart apic_timer_fn(struct hrtimer *data)
+{
+	struct kvm_timer *ktimer = container_of(data, struct kvm_timer, timer);
+	struct kvm_lapic *apic = container_of(ktimer, struct kvm_lapic, lapic_timer);
+	struct kvm_vcpu *vcpu = apic->vcpu;
+	wait_queue_head_t *q = &vcpu->wq;
+
+	/*
+	 * There is a race window between reading and incrementing, but we do
+	 * not care about potentially losing timer events in the !reinject
+	 * case anyway. Note: KVM_REQ_PENDING_TIMER is implicitly checked
+	 * in vcpu_enter_guest.
+	 */
+	if (!atomic_read(&ktimer->pending)) {
+		atomic_inc(&ktimer->pending);
+		/* FIXME: this code should not know anything about vcpus */
+		kvm_make_request(KVM_REQ_PENDING_TIMER, vcpu);
+	}
+
+	if (waitqueue_active(q))
+		wake_up_interruptible(q);
+
+	if (lapic_is_periodic(apic)) {
+		hrtimer_add_expires_ns(&ktimer->timer, ktimer->period);
+		return HRTIMER_RESTART;
+	} else
+		return HRTIMER_NORESTART;
+}
+
 int kvm_create_lapic(struct kvm_vcpu *vcpu)
 {
 	struct kvm_lapic *apic;
@@ -1283,10 +1308,7 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu)
 
 	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->lapic_timer.timer.function = apic_timer_fn;
 
 	apic->base_address = APIC_DEFAULT_PHYS_BASE;
 	vcpu->arch.apic_base = APIC_DEFAULT_PHYS_BASE;
diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h
index 4af5405..166766f 100644
--- a/arch/x86/kvm/lapic.h
+++ b/arch/x86/kvm/lapic.h
@@ -2,10 +2,17 @@
 #define __KVM_X86_LAPIC_H
 
 #include "iodev.h"
-#include "kvm_timer.h"
 
 #include <linux/kvm_host.h>
 
+struct kvm_timer {
+	struct hrtimer timer;
+	s64 period; 				/* unit: ns */
+	u32 timer_mode_mask;
+	u64 tscdeadline;
+	atomic_t pending;			/* accumulated triggered timers */
+};
+
 struct kvm_lapic {
 	unsigned long base_address;
 	struct kvm_io_device dev;
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 01ca004..a9a2052 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -556,6 +556,14 @@ static int mmu_spte_clear_track_bits(u64 *sptep)
 		return 0;
 
 	pfn = spte_to_pfn(old_spte);
+
+	/*
+	 * KVM does not hold the refcount of the page used by
+	 * kvm mmu, before reclaiming the page, we should
+	 * unmap it from mmu first.
+	 */
+	WARN_ON(!kvm_is_mmio_pfn(pfn) && !page_count(pfn_to_page(pfn)));
+
 	if (!shadow_accessed_mask || old_spte & shadow_accessed_mask)
 		kvm_set_pfn_accessed(pfn);
 	if (!shadow_dirty_mask || (old_spte & shadow_dirty_mask))
@@ -960,13 +968,13 @@ static void pte_list_walk(unsigned long *pte_list, pte_list_walk_fn fn)
 static unsigned long *__gfn_to_rmap(gfn_t gfn, int level,
 				    struct kvm_memory_slot *slot)
 {
-	struct kvm_lpage_info *linfo;
+	unsigned long idx;
 
 	if (likely(level == PT_PAGE_TABLE_LEVEL))
 		return &slot->rmap[gfn - slot->base_gfn];
 
-	linfo = lpage_info_slot(gfn, slot, level);
-	return &linfo->rmap_pde;
+	idx = gfn_to_index(gfn, slot->base_gfn, level);
+	return &slot->arch.rmap_pde[level - PT_DIRECTORY_LEVEL][idx];
 }
 
 /*
@@ -1200,7 +1208,7 @@ static bool rmap_write_protect(struct kvm *kvm, u64 gfn)
 }
 
 static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp,
-			   unsigned long data)
+			   struct kvm_memory_slot *slot, unsigned long data)
 {
 	u64 *sptep;
 	struct rmap_iterator iter;
@@ -1218,7 +1226,7 @@ static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp,
 }
 
 static int kvm_set_pte_rmapp(struct kvm *kvm, unsigned long *rmapp,
-			     unsigned long data)
+			     struct kvm_memory_slot *slot, unsigned long data)
 {
 	u64 *sptep;
 	struct rmap_iterator iter;
@@ -1259,43 +1267,67 @@ static int kvm_set_pte_rmapp(struct kvm *kvm, unsigned long *rmapp,
 	return 0;
 }
 
-static int kvm_handle_hva(struct kvm *kvm, unsigned long hva,
-			  unsigned long data,
-			  int (*handler)(struct kvm *kvm, unsigned long *rmapp,
-					 unsigned long data))
+static int kvm_handle_hva_range(struct kvm *kvm,
+				unsigned long start,
+				unsigned long end,
+				unsigned long data,
+				int (*handler)(struct kvm *kvm,
+					       unsigned long *rmapp,
+					       struct kvm_memory_slot *slot,
+					       unsigned long data))
 {
 	int j;
-	int ret;
-	int retval = 0;
+	int ret = 0;
 	struct kvm_memslots *slots;
 	struct kvm_memory_slot *memslot;
 
 	slots = kvm_memslots(kvm);
 
 	kvm_for_each_memslot(memslot, slots) {
-		unsigned long start = memslot->userspace_addr;
-		unsigned long end;
+		unsigned long hva_start, hva_end;
+		gfn_t gfn_start, gfn_end;
 
-		end = start + (memslot->npages << PAGE_SHIFT);
-		if (hva >= start && hva < end) {
-			gfn_t gfn_offset = (hva - start) >> PAGE_SHIFT;
-			gfn_t gfn = memslot->base_gfn + gfn_offset;
+		hva_start = max(start, memslot->userspace_addr);
+		hva_end = min(end, memslot->userspace_addr +
+					(memslot->npages << PAGE_SHIFT));
+		if (hva_start >= hva_end)
+			continue;
+		/*
+		 * {gfn(page) | page intersects with [hva_start, hva_end)} =
+		 * {gfn_start, gfn_start+1, ..., gfn_end-1}.
+		 */
+		gfn_start = hva_to_gfn_memslot(hva_start, memslot);
+		gfn_end = hva_to_gfn_memslot(hva_end + PAGE_SIZE - 1, memslot);
 
-			ret = handler(kvm, &memslot->rmap[gfn_offset], data);
+		for (j = PT_PAGE_TABLE_LEVEL;
+		     j < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++j) {
+			unsigned long idx, idx_end;
+			unsigned long *rmapp;
 
-			for (j = 0; j < KVM_NR_PAGE_SIZES - 1; ++j) {
-				struct kvm_lpage_info *linfo;
+			/*
+			 * {idx(page_j) | page_j intersects with
+			 *  [hva_start, hva_end)} = {idx, idx+1, ..., idx_end}.
+			 */
+			idx = gfn_to_index(gfn_start, memslot->base_gfn, j);
+			idx_end = gfn_to_index(gfn_end - 1, memslot->base_gfn, j);
 
-				linfo = lpage_info_slot(gfn, memslot,
-							PT_DIRECTORY_LEVEL + j);
-				ret |= handler(kvm, &linfo->rmap_pde, data);
-			}
-			trace_kvm_age_page(hva, memslot, ret);
-			retval |= ret;
+			rmapp = __gfn_to_rmap(gfn_start, j, memslot);
+
+			for (; idx <= idx_end; ++idx)
+				ret |= handler(kvm, rmapp++, memslot, data);
 		}
 	}
 
-	return retval;
+	return ret;
+}
+
+static int kvm_handle_hva(struct kvm *kvm, unsigned long hva,
+			  unsigned long data,
+			  int (*handler)(struct kvm *kvm, unsigned long *rmapp,
+					 struct kvm_memory_slot *slot,
+					 unsigned long data))
+{
+	return kvm_handle_hva_range(kvm, hva, hva + 1, data, handler);
 }
 
 int kvm_unmap_hva(struct kvm *kvm, unsigned long hva)
@@ -1303,13 +1335,18 @@ int kvm_unmap_hva(struct kvm *kvm, unsigned long hva)
 	return kvm_handle_hva(kvm, hva, 0, kvm_unmap_rmapp);
 }
 
+int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end)
+{
+	return kvm_handle_hva_range(kvm, start, end, 0, kvm_unmap_rmapp);
+}
+
 void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte)
 {
 	kvm_handle_hva(kvm, hva, (unsigned long)&pte, kvm_set_pte_rmapp);
 }
 
 static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp,
-			 unsigned long data)
+			 struct kvm_memory_slot *slot, unsigned long data)
 {
 	u64 *sptep;
 	struct rmap_iterator uninitialized_var(iter);
@@ -1323,8 +1360,10 @@ static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp,
 	 * This has some overhead, but not as much as the cost of swapping
 	 * out actively used pages or breaking up actively used hugepages.
 	 */
-	if (!shadow_accessed_mask)
-		return kvm_unmap_rmapp(kvm, rmapp, data);
+	if (!shadow_accessed_mask) {
+		young = kvm_unmap_rmapp(kvm, rmapp, slot, data);
+		goto out;
+	}
 
 	for (sptep = rmap_get_first(*rmapp, &iter); sptep;
 	     sptep = rmap_get_next(&iter)) {
@@ -1336,12 +1375,14 @@ static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp,
 				 (unsigned long *)sptep);
 		}
 	}
-
+out:
+	/* @data has hva passed to kvm_age_hva(). */
+	trace_kvm_age_page(data, slot, young);
 	return young;
 }
 
 static int kvm_test_age_rmapp(struct kvm *kvm, unsigned long *rmapp,
-			      unsigned long data)
+			      struct kvm_memory_slot *slot, unsigned long data)
 {
 	u64 *sptep;
 	struct rmap_iterator iter;
@@ -1379,13 +1420,13 @@ static void rmap_recycle(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn)
 
 	rmapp = gfn_to_rmap(vcpu->kvm, gfn, sp->role.level);
 
-	kvm_unmap_rmapp(vcpu->kvm, rmapp, 0);
+	kvm_unmap_rmapp(vcpu->kvm, rmapp, NULL, 0);
 	kvm_flush_remote_tlbs(vcpu->kvm);
 }
 
 int kvm_age_hva(struct kvm *kvm, unsigned long hva)
 {
-	return kvm_handle_hva(kvm, hva, 0, kvm_age_rmapp);
+	return kvm_handle_hva(kvm, hva, hva, kvm_age_rmapp);
 }
 
 int kvm_test_age_hva(struct kvm *kvm, unsigned long hva)
@@ -2472,14 +2513,12 @@ static pfn_t pte_prefetch_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn,
 	unsigned long hva;
 
 	slot = gfn_to_memslot_dirty_bitmap(vcpu, gfn, no_dirty_log);
-	if (!slot) {
-		get_page(fault_page);
-		return page_to_pfn(fault_page);
-	}
+	if (!slot)
+		return get_fault_pfn();
 
 	hva = gfn_to_hva_memslot(slot, gfn);
 
-	return hva_to_pfn_atomic(vcpu->kvm, hva);
+	return hva_to_pfn_atomic(hva);
 }
 
 static int direct_pte_prefetch_many(struct kvm_vcpu *vcpu,
@@ -3236,7 +3275,7 @@ static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn,
 	if (!async)
 		return false; /* *pfn has correct page already */
 
-	put_page(pfn_to_page(*pfn));
+	kvm_release_pfn_clean(*pfn);
 
 	if (!prefault && can_do_async_pf(vcpu)) {
 		trace_kvm_try_async_get_page(gva, gfn);
diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index 9b7ec11..cfc258a 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -1,5 +1,5 @@
 /*
- * Kernel-based Virtual Machine -- Performane Monitoring Unit support
+ * Kernel-based Virtual Machine -- Performance Monitoring Unit support
  *
  * Copyright 2011 Red Hat, Inc. and/or its affiliates.
  *
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index baead95..687d0c3 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -2063,7 +2063,7 @@ static inline bool nested_svm_intr(struct vcpu_svm *svm)
 	if (svm->nested.intercept & 1ULL) {
 		/*
 		 * The #vmexit can't be emulated here directly because this
-		 * code path runs with irqs and preemtion disabled. A
+		 * code path runs with irqs and preemption disabled. A
 		 * #vmexit emulation might sleep. Only signal request for
 		 * the #vmexit here.
 		 */
@@ -2409,7 +2409,7 @@ static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm)
 {
 	/*
 	 * This function merges the msr permission bitmaps of kvm and the
-	 * nested vmcb. It is omptimized in that it only merges the parts where
+	 * nested vmcb. It is optimized in that it only merges the parts where
 	 * the kvm msr permission bitmap may contain zero bits
 	 */
 	int i;
diff --git a/arch/x86/kvm/timer.c b/arch/x86/kvm/timer.c
deleted file mode 100644
index 6b85cc6..0000000
--- a/arch/x86/kvm/timer.c
+++ /dev/null
@@ -1,47 +0,0 @@
-/*
- * Kernel-based Virtual Machine driver for Linux
- *
- * This module enables machines with Intel VT-x extensions to run virtual
- * machines without emulation or binary translation.
- *
- * timer support
- *
- * Copyright 2010 Red Hat, Inc. and/or its affiliates.
- *
- * This work is licensed under the terms of the GNU GPL, version 2.  See
- * the COPYING file in the top-level directory.
- */
-
-#include <linux/kvm_host.h>
-#include <linux/kvm.h>
-#include <linux/hrtimer.h>
-#include <linux/atomic.h>
-#include "kvm_timer.h"
-
-enum hrtimer_restart kvm_timer_fn(struct hrtimer *data)
-{
-	struct kvm_timer *ktimer = container_of(data, struct kvm_timer, timer);
-	struct kvm_vcpu *vcpu = ktimer->vcpu;
-	wait_queue_head_t *q = &vcpu->wq;
-
-	/*
-	 * There is a race window between reading and incrementing, but we do
-	 * not care about potentially losing timer events in the !reinject
-	 * case anyway. Note: KVM_REQ_PENDING_TIMER is implicitly checked
-	 * in vcpu_enter_guest.
-	 */
-	if (ktimer->reinject || !atomic_read(&ktimer->pending)) {
-		atomic_inc(&ktimer->pending);
-		/* FIXME: this code should not know anything about vcpus */
-		kvm_make_request(KVM_REQ_PENDING_TIMER, vcpu);
-	}
-
-	if (waitqueue_active(q))
-		wake_up_interruptible(q);
-
-	if (ktimer->t_ops->is_periodic(ktimer)) {
-		hrtimer_add_expires_ns(&ktimer->timer, ktimer->period);
-		return HRTIMER_RESTART;
-	} else
-		return HRTIMER_NORESTART;
-}
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index c00f03d..d6e4cbc 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -1343,7 +1343,7 @@ static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset)
 	guest_efer = vmx->vcpu.arch.efer;
 
 	/*
-	 * NX is emulated; LMA and LME handled by hardware; SCE meaninless
+	 * NX is emulated; LMA and LME handled by hardware; SCE meaningless
 	 * outside long mode
 	 */
 	ignore_bits = EFER_NX | EFER_SCE;
@@ -3254,7 +3254,7 @@ static void vmx_set_segment(struct kvm_vcpu *vcpu,
 	 * qemu binaries.
 	 *   IA32 arch specifies that at the time of processor reset the
 	 * "Accessed" bit in the AR field of segment registers is 1. And qemu
-	 * is setting it to 0 in the usedland code. This causes invalid guest
+	 * is setting it to 0 in the userland code. This causes invalid guest
 	 * state vmexit when "unrestricted guest" mode is turned on.
 	 *    Fix for this setup issue in cpu_reset is being pushed in the qemu
 	 * tree. Newer qemu binaries with that qemu fix would not need this
@@ -4439,7 +4439,7 @@ vmx_patch_hypercall(struct kvm_vcpu *vcpu, unsigned char *hypercall)
 	hypercall[2] = 0xc1;
 }
 
-/* called to set cr0 as approriate for a mov-to-cr0 exit. */
+/* called to set cr0 as appropriate for a mov-to-cr0 exit. */
 static int handle_set_cr0(struct kvm_vcpu *vcpu, unsigned long val)
 {
 	if (to_vmx(vcpu)->nested.vmxon &&
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 42bce48..3ca90d7 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -806,7 +806,7 @@ EXPORT_SYMBOL_GPL(kvm_rdpmc);
  * kvm-specific. Those are put in the beginning of the list.
  */
 
-#define KVM_SAVE_MSRS_BEGIN	9
+#define KVM_SAVE_MSRS_BEGIN	10
 static u32 msrs_to_save[] = {
 	MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK,
 	MSR_KVM_SYSTEM_TIME_NEW, MSR_KVM_WALL_CLOCK_NEW,
@@ -1097,7 +1097,7 @@ void kvm_write_tsc(struct kvm_vcpu *vcpu, u64 data)
 		 * For each generation, we track the original measured
 		 * nanosecond time, offset, and write, so if TSCs are in
 		 * sync, we can match exact offset, and if not, we can match
-		 * exact software computaion in compute_guest_tsc()
+		 * exact software computation in compute_guest_tsc()
 		 *
 		 * These values are tracked in kvm->arch.cur_xxx variables.
 		 */
@@ -1504,7 +1504,7 @@ static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data)
 {
 	gpa_t gpa = data & ~0x3f;
 
-	/* Bits 2:5 are resrved, Should be zero */
+	/* Bits 2:5 are reserved, Should be zero */
 	if (data & 0x3c)
 		return 1;
 
@@ -1727,7 +1727,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 		 * Ignore all writes to this no longer documented MSR.
 		 * Writes are only relevant for old K7 processors,
 		 * all pre-dating SVM, but a recommended workaround from
-		 * AMD for these chips. It is possible to speicify the
+		 * AMD for these chips. It is possible to specify the
 		 * affected processor models on the command line, hence
 		 * the need to ignore the workaround.
 		 */
@@ -2636,7 +2636,6 @@ static int kvm_set_guest_paused(struct kvm_vcpu *vcpu)
 	if (!vcpu->arch.time_page)
 		return -EINVAL;
 	src->flags |= PVCLOCK_GUEST_STOPPED;
-	mark_page_dirty(vcpu->kvm, vcpu->arch.time >> PAGE_SHIFT);
 	kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
 	return 0;
 }
@@ -3087,7 +3086,7 @@ static int kvm_vm_ioctl_reinject(struct kvm *kvm,
 	if (!kvm->arch.vpit)
 		return -ENXIO;
 	mutex_lock(&kvm->arch.vpit->pit_state.lock);
-	kvm->arch.vpit->pit_state.pit_timer.reinject = control->pit_reinject;
+	kvm->arch.vpit->pit_state.reinject = control->pit_reinject;
 	mutex_unlock(&kvm->arch.vpit->pit_state.lock);
 	return 0;
 }
@@ -3170,6 +3169,16 @@ out:
 	return r;
 }
 
+int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_event)
+{
+	if (!irqchip_in_kernel(kvm))
+		return -ENXIO;
+
+	irq_event->status = kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID,
+					irq_event->irq, irq_event->level);
+	return 0;
+}
+
 long kvm_arch_vm_ioctl(struct file *filp,
 		       unsigned int ioctl, unsigned long arg)
 {
@@ -3276,29 +3285,6 @@ long kvm_arch_vm_ioctl(struct file *filp,
 	create_pit_unlock:
 		mutex_unlock(&kvm->slots_lock);
 		break;
-	case KVM_IRQ_LINE_STATUS:
-	case KVM_IRQ_LINE: {
-		struct kvm_irq_level irq_event;
-
-		r = -EFAULT;
-		if (copy_from_user(&irq_event, argp, sizeof irq_event))
-			goto out;
-		r = -ENXIO;
-		if (irqchip_in_kernel(kvm)) {
-			__s32 status;
-			status = kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID,
-					irq_event.irq, irq_event.level);
-			if (ioctl == KVM_IRQ_LINE_STATUS) {
-				r = -EFAULT;
-				irq_event.status = status;
-				if (copy_to_user(argp, &irq_event,
-							sizeof irq_event))
-					goto out;
-			}
-			r = 0;
-		}
-		break;
-	}
 	case KVM_GET_IRQCHIP: {
 		/* 0: PIC master, 1: PIC slave, 2: IOAPIC */
 		struct kvm_irqchip *chip;
@@ -4496,7 +4482,7 @@ static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t gva)
 
 	/*
 	 * if emulation was due to access to shadowed page table
-	 * and it failed try to unshadow page and re-entetr the
+	 * and it failed try to unshadow page and re-enter the
 	 * guest to let CPU execute the instruction.
 	 */
 	if (kvm_mmu_unprotect_page_virt(vcpu, gva))
@@ -5592,7 +5578,7 @@ int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 		/*
 		 * We are here if userspace calls get_regs() in the middle of
 		 * instruction emulation. Registers state needs to be copied
-		 * back from emulation context to vcpu. Usrapace shouldn't do
+		 * back from emulation context to vcpu. Userspace shouldn't do
 		 * that usually, but some bad designed PV devices (vmware
 		 * backdoor interface) need this to work
 		 */
@@ -6121,7 +6107,7 @@ int kvm_arch_hardware_enable(void *garbage)
 	 * as we reset last_host_tsc on all VCPUs to stop this from being
 	 * called multiple times (one for each physical CPU bringup).
 	 *
-	 * Platforms with unnreliable TSCs don't have to deal with this, they
+	 * Platforms with unreliable TSCs don't have to deal with this, they
 	 * will be compensated by the logic in vcpu_load, which sets the TSC to
 	 * catchup mode.  This will catchup all VCPUs to real time, but cannot
 	 * guarantee that they stay in perfect synchronization.
@@ -6318,6 +6304,10 @@ void kvm_arch_free_memslot(struct kvm_memory_slot *free,
 	int i;
 
 	for (i = 0; i < KVM_NR_PAGE_SIZES - 1; ++i) {
+		if (!dont || free->arch.rmap_pde[i] != dont->arch.rmap_pde[i]) {
+			kvm_kvfree(free->arch.rmap_pde[i]);
+			free->arch.rmap_pde[i] = NULL;
+		}
 		if (!dont || free->arch.lpage_info[i] != dont->arch.lpage_info[i]) {
 			kvm_kvfree(free->arch.lpage_info[i]);
 			free->arch.lpage_info[i] = NULL;
@@ -6337,6 +6327,11 @@ int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages)
 		lpages = gfn_to_index(slot->base_gfn + npages - 1,
 				      slot->base_gfn, level) + 1;
 
+		slot->arch.rmap_pde[i] =
+			kvm_kvzalloc(lpages * sizeof(*slot->arch.rmap_pde[i]));
+		if (!slot->arch.rmap_pde[i])
+			goto out_free;
+
 		slot->arch.lpage_info[i] =
 			kvm_kvzalloc(lpages * sizeof(*slot->arch.lpage_info[i]));
 		if (!slot->arch.lpage_info[i])
@@ -6365,7 +6360,9 @@ int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages)
 
 out_free:
 	for (i = 0; i < KVM_NR_PAGE_SIZES - 1; ++i) {
+		kvm_kvfree(slot->arch.rmap_pde[i]);
 		kvm_kvfree(slot->arch.lpage_info[i]);
+		slot->arch.rmap_pde[i] = NULL;
 		slot->arch.lpage_info[i] = NULL;
 	}
 	return -ENOMEM;
@@ -6385,7 +6382,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 		map_flags = MAP_SHARED | MAP_ANONYMOUS;
 
 	/*To keep backward compatibility with older userspace,
-	 *x86 needs to hanlde !user_alloc case.
+	 *x86 needs to handle !user_alloc case.
 	 */
 	if (!user_alloc) {
 		if (npages && !old.rmap) {