summaryrefslogtreecommitdiffstats
path: root/arch/x86/kvm
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2009-01-02 11:41:11 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2009-01-02 11:41:11 -0800
commit597b0d21626da4e6f09f132442caf0cc2b0eb47c (patch)
tree13c0074bb20f7b05a471e78d4ff52c665a10266a /arch/x86/kvm
parent2640c9a90fa596871e142f42052608864335f102 (diff)
parent87917239204d67a316cb89751750f86c9ed3640b (diff)
Merge branch 'kvm-updates/2.6.29' of git://git.kernel.org/pub/scm/linux/kernel/git/avi/kvm
* 'kvm-updates/2.6.29' of git://git.kernel.org/pub/scm/linux/kernel/git/avi/kvm: (140 commits) KVM: MMU: handle large host sptes on invlpg/resync KVM: Add locking to virtual i8259 interrupt controller KVM: MMU: Don't treat a global pte as such if cr4.pge is cleared MAINTAINERS: Maintainership changes for kvm/ia64 KVM: ia64: Fix kvm_arch_vcpu_ioctl_[gs]et_regs() KVM: x86: Rework user space NMI injection as KVM_CAP_USER_NMI KVM: VMX: Fix pending NMI-vs.-IRQ race for user space irqchip KVM: fix handling of ACK from shared guest IRQ KVM: MMU: check for present pdptr shadow page in walk_shadow KVM: Consolidate userspace memory capability reporting into common code KVM: Advertise the bug in memory region destruction as fixed KVM: use cpumask_var_t for cpus_hardware_enabled KVM: use modern cpumask primitives, no cpumask_t on stack KVM: Extract core of kvm_flush_remote_tlbs/kvm_reload_remote_mmus KVM: set owner of cpu and vm file operations anon_inodes: use fops->owner for module refcount x86: KVM guest: kvm_get_tsc_khz: return khz, not lpj KVM: MMU: prepopulate the shadow on invlpg KVM: MMU: skip global pgtables on sync due to cr3 switch KVM: MMU: collapse remote TLB flushes on root sync ...
Diffstat (limited to 'arch/x86/kvm')
-rw-r--r--arch/x86/kvm/i8254.c19
-rw-r--r--arch/x86/kvm/i8259.c52
-rw-r--r--arch/x86/kvm/irq.h6
-rw-r--r--arch/x86/kvm/kvm_svm.h2
-rw-r--r--arch/x86/kvm/lapic.c58
-rw-r--r--arch/x86/kvm/mmu.c444
-rw-r--r--arch/x86/kvm/paging_tmpl.h44
-rw-r--r--arch/x86/kvm/svm.c48
-rw-r--r--arch/x86/kvm/svm.h328
-rw-r--r--arch/x86/kvm/vmx.c350
-rw-r--r--arch/x86/kvm/vmx.h359
-rw-r--r--arch/x86/kvm/x86.c117
-rw-r--r--arch/x86/kvm/x86_emulate.c297
13 files changed, 1055 insertions, 1069 deletions
diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c
index 59ebd37ad79..e665d1c623c 100644
--- a/arch/x86/kvm/i8254.c
+++ b/arch/x86/kvm/i8254.c
@@ -603,10 +603,29 @@ void kvm_free_pit(struct kvm *kvm)
static void __inject_pit_timer_intr(struct kvm *kvm)
{
+ struct kvm_vcpu *vcpu;
+ int i;
+
mutex_lock(&kvm->lock);
kvm_set_irq(kvm, kvm->arch.vpit->irq_source_id, 0, 1);
kvm_set_irq(kvm, kvm->arch.vpit->irq_source_id, 0, 0);
mutex_unlock(&kvm->lock);
+
+ /*
+ * Provides NMI watchdog support via Virtual Wire mode.
+ * The route is: PIT -> PIC -> LVT0 in NMI mode.
+ *
+ * Note: Our Virtual Wire implementation is simplified, only
+ * propagating PIT interrupts to all VCPUs when they have set
+ * LVT0 to NMI delivery. Other PIC interrupts are just sent to
+ * VCPU0, and only if its LVT0 is in EXTINT mode.
+ */
+ if (kvm->arch.vapics_in_nmi_mode > 0)
+ for (i = 0; i < KVM_MAX_VCPUS; ++i) {
+ vcpu = kvm->vcpus[i];
+ if (vcpu)
+ kvm_apic_nmi_wd_deliver(vcpu);
+ }
}
void kvm_inject_pit_timer_irqs(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c
index 17e41e165f1..179dcb0103f 100644
--- a/arch/x86/kvm/i8259.c
+++ b/arch/x86/kvm/i8259.c
@@ -26,10 +26,40 @@
* Port from Qemu.
*/
#include <linux/mm.h>
+#include <linux/bitops.h>
#include "irq.h"
#include <linux/kvm_host.h>
+static void pic_lock(struct kvm_pic *s)
+{
+ spin_lock(&s->lock);
+}
+
+static void pic_unlock(struct kvm_pic *s)
+{
+ struct kvm *kvm = s->kvm;
+ unsigned acks = s->pending_acks;
+ bool wakeup = s->wakeup_needed;
+ struct kvm_vcpu *vcpu;
+
+ s->pending_acks = 0;
+ s->wakeup_needed = false;
+
+ spin_unlock(&s->lock);
+
+ while (acks) {
+ kvm_notify_acked_irq(kvm, __ffs(acks));
+ acks &= acks - 1;
+ }
+
+ if (wakeup) {
+ vcpu = s->kvm->vcpus[0];
+ if (vcpu)
+ kvm_vcpu_kick(vcpu);
+ }
+}
+
static void pic_clear_isr(struct kvm_kpic_state *s, int irq)
{
s->isr &= ~(1 << irq);
@@ -136,17 +166,21 @@ static void pic_update_irq(struct kvm_pic *s)
void kvm_pic_update_irq(struct kvm_pic *s)
{
+ pic_lock(s);
pic_update_irq(s);
+ pic_unlock(s);
}
void kvm_pic_set_irq(void *opaque, int irq, int level)
{
struct kvm_pic *s = opaque;
+ pic_lock(s);
if (irq >= 0 && irq < PIC_NUM_PINS) {
pic_set_irq1(&s->pics[irq >> 3], irq & 7, level);
pic_update_irq(s);
}
+ pic_unlock(s);
}
/*
@@ -172,6 +206,7 @@ int kvm_pic_read_irq(struct kvm *kvm)
int irq, irq2, intno;
struct kvm_pic *s = pic_irqchip(kvm);
+ pic_lock(s);
irq = pic_get_irq(&s->pics[0]);
if (irq >= 0) {
pic_intack(&s->pics[0], irq);
@@ -196,6 +231,7 @@ int kvm_pic_read_irq(struct kvm *kvm)
intno = s->pics[0].irq_base + irq;
}
pic_update_irq(s);
+ pic_unlock(s);
kvm_notify_acked_irq(kvm, irq);
return intno;
@@ -203,7 +239,7 @@ int kvm_pic_read_irq(struct kvm *kvm)
void kvm_pic_reset(struct kvm_kpic_state *s)
{
- int irq, irqbase;
+ int irq, irqbase, n;
struct kvm *kvm = s->pics_state->irq_request_opaque;
struct kvm_vcpu *vcpu0 = kvm->vcpus[0];
@@ -214,8 +250,10 @@ void kvm_pic_reset(struct kvm_kpic_state *s)
for (irq = 0; irq < PIC_NUM_PINS/2; irq++) {
if (vcpu0 && kvm_apic_accept_pic_intr(vcpu0))
- if (s->irr & (1 << irq) || s->isr & (1 << irq))
- kvm_notify_acked_irq(kvm, irq+irqbase);
+ if (s->irr & (1 << irq) || s->isr & (1 << irq)) {
+ n = irq + irqbase;
+ s->pics_state->pending_acks |= 1 << n;
+ }
}
s->last_irr = 0;
s->irr = 0;
@@ -406,6 +444,7 @@ static void picdev_write(struct kvm_io_device *this,
printk(KERN_ERR "PIC: non byte write\n");
return;
}
+ pic_lock(s);
switch (addr) {
case 0x20:
case 0x21:
@@ -418,6 +457,7 @@ static void picdev_write(struct kvm_io_device *this,
elcr_ioport_write(&s->pics[addr & 1], addr, data);
break;
}
+ pic_unlock(s);
}
static void picdev_read(struct kvm_io_device *this,
@@ -431,6 +471,7 @@ static void picdev_read(struct kvm_io_device *this,
printk(KERN_ERR "PIC: non byte read\n");
return;
}
+ pic_lock(s);
switch (addr) {
case 0x20:
case 0x21:
@@ -444,6 +485,7 @@ static void picdev_read(struct kvm_io_device *this,
break;
}
*(unsigned char *)val = data;
+ pic_unlock(s);
}
/*
@@ -459,7 +501,7 @@ static void pic_irq_request(void *opaque, int level)
s->output = level;
if (vcpu && level && (s->pics[0].isr_ack & (1 << irq))) {
s->pics[0].isr_ack &= ~(1 << irq);
- kvm_vcpu_kick(vcpu);
+ s->wakeup_needed = true;
}
}
@@ -469,6 +511,8 @@ struct kvm_pic *kvm_create_pic(struct kvm *kvm)
s = kzalloc(sizeof(struct kvm_pic), GFP_KERNEL);
if (!s)
return NULL;
+ spin_lock_init(&s->lock);
+ s->kvm = kvm;
s->pics[0].elcr_mask = 0xf8;
s->pics[1].elcr_mask = 0xde;
s->irq_request = pic_irq_request;
diff --git a/arch/x86/kvm/irq.h b/arch/x86/kvm/irq.h
index f17c8f5bbf3..2bf32a03cee 100644
--- a/arch/x86/kvm/irq.h
+++ b/arch/x86/kvm/irq.h
@@ -25,6 +25,7 @@
#include <linux/mm_types.h>
#include <linux/hrtimer.h>
#include <linux/kvm_host.h>
+#include <linux/spinlock.h>
#include "iodev.h"
#include "ioapic.h"
@@ -59,6 +60,10 @@ struct kvm_kpic_state {
};
struct kvm_pic {
+ spinlock_t lock;
+ bool wakeup_needed;
+ unsigned pending_acks;
+ struct kvm *kvm;
struct kvm_kpic_state pics[2]; /* 0 is master pic, 1 is slave pic */
irq_request_func *irq_request;
void *irq_request_opaque;
@@ -87,6 +92,7 @@ void kvm_pic_reset(struct kvm_kpic_state *s);
void kvm_timer_intr_post(struct kvm_vcpu *vcpu, int vec);
void kvm_inject_pending_timer_irqs(struct kvm_vcpu *vcpu);
void kvm_inject_apic_timer_irqs(struct kvm_vcpu *vcpu);
+void kvm_apic_nmi_wd_deliver(struct kvm_vcpu *vcpu);
void __kvm_migrate_apic_timer(struct kvm_vcpu *vcpu);
void __kvm_migrate_pit_timer(struct kvm_vcpu *vcpu);
void __kvm_migrate_timers(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/kvm/kvm_svm.h b/arch/x86/kvm/kvm_svm.h
index 65ef0fc2c03..8e5ee99551f 100644
--- a/arch/x86/kvm/kvm_svm.h
+++ b/arch/x86/kvm/kvm_svm.h
@@ -7,7 +7,7 @@
#include <linux/kvm_host.h>
#include <asm/msr.h>
-#include "svm.h"
+#include <asm/svm.h>
static const u32 host_save_user_msrs[] = {
#ifdef CONFIG_X86_64
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 0fc3cab4894..afac68c0815 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -130,6 +130,11 @@ static inline int apic_lvtt_period(struct kvm_lapic *apic)
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;
+}
+
static unsigned int apic_lvt_mask[APIC_LVT_NUM] = {
LVT_MASK | APIC_LVT_TIMER_PERIODIC, /* LVTT */
LVT_MASK | APIC_MODE_MASK, /* LVTTHMR */
@@ -354,6 +359,7 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode,
case APIC_DM_NMI:
kvm_inject_nmi(vcpu);
+ kvm_vcpu_kick(vcpu);
break;
case APIC_DM_INIT:
@@ -380,6 +386,14 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode,
}
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);
@@ -663,6 +677,20 @@ static void start_apic_timer(struct kvm_lapic *apic)
apic->timer.period)));
}
+static void apic_manage_nmi_watchdog(struct kvm_lapic *apic, u32 lvt0_val)
+{
+ int nmi_wd_enabled = apic_lvt_nmi_mode(apic_get_reg(apic, APIC_LVT0));
+
+ 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--;
+}
+
static void apic_mmio_write(struct kvm_io_device *this,
gpa_t address, int len, const void *data)
{
@@ -743,10 +771,11 @@ static void apic_mmio_write(struct kvm_io_device *this,
apic_set_reg(apic, APIC_ICR2, val & 0xff000000);
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 */
@@ -961,12 +990,26 @@ int apic_has_pending_timer(struct kvm_vcpu *vcpu)
return 0;
}
-static int __inject_apic_timer_irq(struct kvm_lapic *apic)
+static int kvm_apic_local_deliver(struct kvm_lapic *apic, int lvt_type)
+{
+ 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;
+}
+
+void kvm_apic_nmi_wd_deliver(struct kvm_vcpu *vcpu)
{
- int vector;
+ struct kvm_lapic *apic = vcpu->arch.apic;
- vector = apic_lvt_vector(apic, APIC_LVTT);
- return __apic_accept_irq(apic, APIC_DM_FIXED, vector, 1, 0);
+ if (apic)
+ kvm_apic_local_deliver(apic, APIC_LVT0);
}
static enum hrtimer_restart apic_timer_fn(struct hrtimer *data)
@@ -1061,9 +1104,8 @@ void kvm_inject_apic_timer_irqs(struct kvm_vcpu *vcpu)
{
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))
+ if (apic && atomic_read(&apic->timer.pending) > 0) {
+ if (kvm_apic_local_deliver(apic, APIC_LVTT))
atomic_dec(&apic->timer.pending);
}
}
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 410ddbc1aa2..83f11c7474a 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -17,7 +17,6 @@
*
*/
-#include "vmx.h"
#include "mmu.h"
#include <linux/kvm_host.h>
@@ -33,6 +32,7 @@
#include <asm/page.h>
#include <asm/cmpxchg.h>
#include <asm/io.h>
+#include <asm/vmx.h>
/*
* When setting this variable to true it enables Two-Dimensional-Paging
@@ -168,6 +168,7 @@ static u64 __read_mostly shadow_x_mask; /* mutual exclusive with nx_mask */
static u64 __read_mostly shadow_user_mask;
static u64 __read_mostly shadow_accessed_mask;
static u64 __read_mostly shadow_dirty_mask;
+static u64 __read_mostly shadow_mt_mask;
void kvm_mmu_set_nonpresent_ptes(u64 trap_pte, u64 notrap_pte)
{
@@ -183,13 +184,14 @@ void kvm_mmu_set_base_ptes(u64 base_pte)
EXPORT_SYMBOL_GPL(kvm_mmu_set_base_ptes);
void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask,
- u64 dirty_mask, u64 nx_mask, u64 x_mask)
+ u64 dirty_mask, u64 nx_mask, u64 x_mask, u64 mt_mask)
{
shadow_user_mask = user_mask;
shadow_accessed_mask = accessed_mask;
shadow_dirty_mask = dirty_mask;
shadow_nx_mask = nx_mask;
shadow_x_mask = x_mask;
+ shadow_mt_mask = mt_mask;
}
EXPORT_SYMBOL_GPL(kvm_mmu_set_mask_ptes);
@@ -384,7 +386,9 @@ static void account_shadowed(struct kvm *kvm, gfn_t gfn)
{
int *write_count;
- write_count = slot_largepage_idx(gfn, gfn_to_memslot(kvm, gfn));
+ gfn = unalias_gfn(kvm, gfn);
+ write_count = slot_largepage_idx(gfn,
+ gfn_to_memslot_unaliased(kvm, gfn));
*write_count += 1;
}
@@ -392,16 +396,20 @@ static void unaccount_shadowed(struct kvm *kvm, gfn_t gfn)
{
int *write_count;
- write_count = slot_largepage_idx(gfn, gfn_to_memslot(kvm, gfn));
+ gfn = unalias_gfn(kvm, gfn);
+ write_count = slot_largepage_idx(gfn,
+ gfn_to_memslot_unaliased(kvm, gfn));
*write_count -= 1;
WARN_ON(*write_count < 0);
}
static int has_wrprotected_page(struct kvm *kvm, gfn_t gfn)
{
- struct kvm_memory_slot *slot = gfn_to_memslot(kvm, gfn);
+ struct kvm_memory_slot *slot;
int *largepage_idx;
+ gfn = unalias_gfn(kvm, gfn);
+ slot = gfn_to_memslot_unaliased(kvm, gfn);
if (slot) {
largepage_idx = slot_largepage_idx(gfn, slot);
return *largepage_idx;
@@ -613,7 +621,7 @@ static u64 *rmap_next(struct kvm *kvm, unsigned long *rmapp, u64 *spte)
return NULL;
}
-static void rmap_write_protect(struct kvm *kvm, u64 gfn)
+static int rmap_write_protect(struct kvm *kvm, u64 gfn)
{
unsigned long *rmapp;
u64 *spte;
@@ -659,8 +667,7 @@ static void rmap_write_protect(struct kvm *kvm, u64 gfn)
spte = rmap_next(kvm, rmapp, spte);
}
- if (write_protected)
- kvm_flush_remote_tlbs(kvm);
+ return write_protected;
}
static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp)
@@ -786,9 +793,11 @@ static struct kvm_mmu_page *kvm_mmu_alloc_page(struct kvm_vcpu *vcpu,
sp->gfns = mmu_memory_cache_alloc(&vcpu->arch.mmu_page_cache, PAGE_SIZE);
set_page_private(virt_to_page(sp->spt), (unsigned long)sp);
list_add(&sp->link, &vcpu->kvm->arch.active_mmu_pages);
+ INIT_LIST_HEAD(&sp->oos_link);
ASSERT(is_empty_shadow_page(sp->spt));
- sp->slot_bitmap = 0;
+ bitmap_zero(sp->slot_bitmap, KVM_MEMORY_SLOTS + KVM_PRIVATE_MEM_SLOTS);
sp->multimapped = 0;
+ sp->global = 1;
sp->parent_pte = parent_pte;
--vcpu->kvm->arch.n_free_mmu_pages;
return sp;
@@ -900,8 +909,9 @@ static void kvm_mmu_update_unsync_bitmap(u64 *spte)
struct kvm_mmu_page *sp = page_header(__pa(spte));
index = spte - sp->spt;
- __set_bit(index, sp->unsync_child_bitmap);
- sp->unsync_children = 1;
+ if (!__test_and_set_bit(index, sp->unsync_child_bitmap))
+ sp->unsync_children++;
+ WARN_ON(!sp->unsync_children);
}
static void kvm_mmu_update_parents_unsync(struct kvm_mmu_page *sp)
@@ -928,7 +938,6 @@ static void kvm_mmu_update_parents_unsync(struct kvm_mmu_page *sp)
static int unsync_walk_fn(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
{
- sp->unsync_children = 1;
kvm_mmu_update_parents_unsync(sp);
return 1;
}
@@ -959,38 +968,66 @@ static void nonpaging_invlpg(struct kvm_vcpu *vcpu, gva_t gva)
{
}
+#define KVM_PAGE_ARRAY_NR 16
+
+struct kvm_mmu_pages {
+ struct mmu_page_and_offset {
+ struct kvm_mmu_page *sp;
+ unsigned int idx;
+ } page[KVM_PAGE_ARRAY_NR];
+ unsigned int nr;
+};
+
#define for_each_unsync_children(bitmap, idx) \
for (idx = find_first_bit(bitmap, 512); \
idx < 512; \
idx = find_next_bit(bitmap, 512, idx+1))
-static int mmu_unsync_walk(struct kvm_mmu_page *sp,
- struct kvm_unsync_walk *walker)
+int mmu_pages_add(struct kvm_mmu_pages *pvec, struct kvm_mmu_page *sp,
+ int idx)
{
- int i, ret;
+ int i;
- if (!sp->unsync_children)
- return 0;
+ if (sp->unsync)
+ for (i=0; i < pvec->nr; i++)
+ if (pvec->page[i].sp == sp)
+ return 0;
+
+ pvec->page[pvec->nr].sp = sp;
+ pvec->page[pvec->nr].idx = idx;
+ pvec->nr++;
+ return (pvec->nr == KVM_PAGE_ARRAY_NR);
+}
+
+static int __mmu_unsync_walk(struct kvm_mmu_page *sp,
+ struct kvm_mmu_pages *pvec)
+{
+ int i, ret, nr_unsync_leaf = 0;
for_each_unsync_children(sp->unsync_child_bitmap, i) {
u64 ent = sp->spt[i];
- if (is_shadow_present_pte(ent)) {
+ if (is_shadow_present_pte(ent) && !is_large_pte(ent)) {
struct kvm_mmu_page *child;
child = page_header(ent & PT64_BASE_ADDR_MASK);
if (child->unsync_children) {
- ret = mmu_unsync_walk(child, walker);
- if (ret)
+ if (mmu_pages_add(pvec, child, i))
+ return -ENOSPC;
+
+ ret = __mmu_unsync_walk(child, pvec);
+ if (!ret)
+ __clear_bit(i, sp->unsync_child_bitmap);
+ else if (ret > 0)
+ nr_unsync_leaf += ret;
+ else
return ret;
- __clear_bit(i, sp->unsync_child_bitmap);
}
if (child->unsync) {
- ret = walker->entry(child, walker);
- __clear_bit(i, sp->unsync_child_bitmap);
- if (ret)
- return ret;
+ nr_unsync_leaf++;
+ if (mmu_pages_add(pvec, child, i))
+ return -ENOSPC;
}
}
}
@@ -998,7 +1035,17 @@ static int mmu_unsync_walk(struct kvm_mmu_page *sp,
if (find_first_bit(sp->unsync_child_bitmap, 512) == 512)
sp->unsync_children = 0;
- return 0;
+ return nr_unsync_leaf;
+}
+
+static int mmu_unsync_walk(struct kvm_mmu_page *sp,
+ struct kvm_mmu_pages *pvec)
+{
+ if (!sp->unsync_children)
+ return 0;
+
+ mmu_pages_add(pvec, sp, 0);
+ return __mmu_unsync_walk(sp, pvec);
}
static struct kvm_mmu_page *kvm_mmu_lookup_page(struct kvm *kvm, gfn_t gfn)
@@ -1021,10 +1068,18 @@ static struct kvm_mmu_page *kvm_mmu_lookup_page(struct kvm *kvm, gfn_t gfn)
return NULL;
}
+static void kvm_unlink_unsync_global(struct kvm *kvm, struct kvm_mmu_page *sp)
+{
+ list_del(&sp->oos_link);
+ --kvm->stat.mmu_unsync_global;
+}
+
static void kvm_unlink_unsync_page(struct kvm *kvm, struct kvm_mmu_page *sp)
{
WARN_ON(!sp->unsync);
sp->unsync = 0;
+ if (sp->global)
+ kvm_unlink_unsync_global(kvm, sp);
--kvm->stat.mmu_unsync;
}
@@ -1037,7 +1092,8 @@ static int kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
return 1;
}
- rmap_write_protect(vcpu->kvm, sp->gfn);
+ if (rmap_write_protect(vcpu->kvm, sp->gfn))
+ kvm_flush_remote_tlbs(vcpu->kvm);
kvm_unlink_unsync_page(vcpu->kvm, sp);
if (vcpu->arch.mmu.sync_page(vcpu, sp)) {
kvm_mmu_zap_page(vcpu->kvm, sp);
@@ -1048,30 +1104,89 @@ static int kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
return 0;
}
-struct sync_walker {
- struct kvm_vcpu *vcpu;
- struct kvm_unsync_walk walker;
+struct mmu_page_path {
+ struct kvm_mmu_page *parent[PT64_ROOT_LEVEL-1];
+ unsigned int idx[PT64_ROOT_LEVEL-1];
};
-static int mmu_sync_fn(struct kvm_mmu_page *sp, struct kvm_unsync_walk *walk)
+#define for_each_sp(pvec, sp, parents, i) \
+ for (i = mmu_pages_next(&pvec, &parents, -1), \
+ sp = pvec.page[i].sp; \
+ i < pvec.nr && ({ sp = pvec.page[i].sp; 1;}); \
+ i = mmu_pages_next(&pvec, &parents, i))
+
+int mmu_pages_next(struct kvm_mmu_pages *pvec, struct mmu_page_path *parents,
+ int i)
{
- struct sync_walker *sync_walk = container_of(walk, struct sync_walker,
- walker);
- struct kvm_vcpu *vcpu = sync_walk->vcpu;
+ int n;
- kvm_sync_page(vcpu, sp);
- return (need_resched() || spin_needbreak(&vcpu->kvm->mmu_lock));
+ for (n = i+1; n < pvec->nr; n++) {
+ struct kvm_mmu_page *sp = pvec->page[n].sp;
+
+ if (sp->role.level == PT_PAGE_TABLE_LEVEL) {
+ parents->idx[0] = pvec->page[n].idx;
+ return n;
+ }
+
+ parents->parent[sp->role.level-2] = sp;
+ parents->idx[sp->role.level-1] = pvec->page[n].idx;
+ }
+
+ return n;
}
-static void mmu_sync_children(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
+void mmu_pages_clear_parents(struct mmu_page_path *parents)
{
- struct sync_walker walker = {
- .walker = { .entry = mmu_sync_fn, },
- .vcpu = vcpu,
- };
+ struct kvm_mmu_page *sp;
+ unsigned int level = 0;
+
+ do {
+ unsigned int idx = parents->idx[level];
+
+ sp = parents->parent[level];
+ if (!sp)
+ return;
+
+ --sp->unsync_children;
+ WARN_ON((int)sp->unsync_children < 0);
+ __clear_bit(idx, sp->unsync_child_bitmap);
+ level++;
+ } while (level < PT64_ROOT_LEVEL-1 && !sp->unsync_children);
+}
+
+static void kvm_mmu_pages_init(struct kvm_mmu_page *parent,
+ struct mmu_page_path *parents,
+ struct kvm_mmu_pages *pvec)
+{
+ parents->parent[parent->role.level-1] = NULL;
+ pvec->nr = 0;
+}
+
+static void mmu_sync_children(struct kvm_vcpu *vcpu,
+ struct kvm_mmu_page *parent)
+{
+ int i;
+ struct kvm_mmu_page *sp;
+ struct mmu_page_path parents;
+ struct kvm_mmu_pages pages;
+
+ kvm_mmu_pages_init(parent, &parents, &pages);
+ while (mmu_unsync_walk(parent, &pages)) {
+ int protected = 0;
- while (mmu_unsync_walk(sp, &walker.walker))
+ for_each_sp(pages, sp, parents, i)
+ protected |= rmap_write_protect(vcpu->kvm, sp->gfn);
+
+ if (protected)
+ kvm_flush_remote_tlbs(vcpu->kvm);
+
+ for_each_sp(pages, sp, parents, i) {
+ kvm_sync_page(vcpu, sp);
+ mmu_pages_clear_parents(&parents);
+ }
cond_resched_lock(&vcpu->kvm->mmu_lock);
+ kvm_mmu_pages_init(parent, &parents, &pages);
+ }
}
static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu,
@@ -1129,7 +1244,8 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu,
sp->role = role;
hlist_add_head(&sp->hash_link, bucket);
if (!metaphysical) {
- rmap_write_protect(vcpu->kvm, gfn);
+ if (rmap_write_protect(vcpu->kvm, gfn))
+ kvm_flush_remote_tlbs(vcpu->kvm);
account_shadowed(vcpu->kvm, gfn);
}
if (shadow_trap_nonpresent_pte != shadow_notrap_nonpresent_pte)
@@ -1153,6 +1269,8 @@ static int walk_shadow(struct kvm_shadow_walk *walker,
if (level == PT32E_ROOT_LEVEL) {
shadow_addr = vcpu->arch.mmu.pae_root[(addr >> 30) & 3];
shadow_addr &= PT64_BASE_ADDR_MASK;
+ if (!shadow_addr)
+ return 1;
--level;
}
@@ -1237,33 +1355,29 @@ static void kvm_mmu_unlink_parents(struct kvm *kvm, struct kvm_mmu_page *sp)
}
}
-struct zap_walker {
- struct kvm_unsync_walk walker;
- struct kvm *kvm;
- int zapped;
-};
-
-static int mmu_zap_fn(struct kvm_mmu_page *sp, struct kvm_unsync_walk *walk)
+static int mmu_zap_unsync_children(struct kvm *kvm,
+ struct kvm_mmu_page *parent)
{
- struct zap_walker *zap_walk = container_of(walk, struct zap_walker,
- walker);
- kvm_mmu_zap_page(zap_walk->kvm, sp);
- zap_walk->zapped = 1;
- return 0;
-}
+ int i, zapped = 0;
+ struct mmu_page_path parents;
+ struct kvm_mmu_pages pages;
-static int mmu_zap_unsync_children(struct kvm *kvm, struct kvm_mmu_page *sp)
-{
- struct zap_walker walker = {
- .walker = { .entry = mmu_zap_fn, },
- .kvm = kvm,
- .zapped = 0,
- };
-
- if (sp->role.level == PT_PAGE_TABLE_LEVEL)
+ if (parent->role.level == PT_PAGE_TABLE_LEVEL)
return 0;
- mmu_unsync_walk(sp, &walker.walker);
- return walker.zapped;
+
+ kvm_mmu_pages_init(parent, &parents, &pages);
+ while (mmu_unsync_walk(parent, &pages)) {
+ struct kvm_mmu_page *sp;
+
+ for_each_sp(pages, sp, parents, i) {
+ kvm_mmu_zap_page(kvm, sp);
+ mmu_pages_clear_parents(&parents);
+ }
+ zapped += pages.nr;
+ kvm_mmu_pages_init(parent, &parents, &pages);
+ }
+
+ return zapped;
}
static int kvm_mmu_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp)
@@ -1362,7 +1476,7 @@ static void page_header_update_slot(struct kvm *kvm, void *pte, gfn_t gfn)
int slot = memslot_id(kvm, gfn_to_memslot(kvm, gfn));
struct kvm_mmu_page *sp = page_header(__pa(pte));
- __set_bit(slot, &sp->slot_bitmap);
+ __set_bit(slot, sp->slot_bitmap);
}
static void mmu_convert_notrap(struct kvm_mmu_page *sp)
@@ -1393,6 +1507,110 @@ struct page *gva_to_page(struct kvm_vcpu *vcpu, gva_t gva)
return page;
}
+/*
+ * The function is based on mtrr_type_lookup() in
+ * arch/x86/kernel/cpu/mtrr/generic.c
+ */
+static int get_mtrr_type(struct mtrr_state_type *mtrr_state,
+ u64 start, u64 end)
+{
+ int i;
+ u64 base, mask;
+ u8 prev_match, curr_match;
+ int num_var_ranges = KVM_NR_VAR_MTRR;
+
+ if (!mtrr_state->enabled)
+ return 0xFF;
+
+ /* Make end inclusive end, instead of exclusive */
+ end--;
+
+ /* Look in fixed ranges. Just return the type as per start */
+ if (mtrr_state->have_fixed && (start < 0x100000)) {
+ int idx;
+
+ if (start < 0x80000) {
+ idx = 0;
+ idx += (start >> 16);
+ return mtrr_state->fixed_ranges[idx];
+ } else if (start < 0xC0000) {
+ idx = 1 * 8;
+ idx += ((start - 0x80000) >> 14);
+ return mtrr_state->fixed_ranges[idx];
+ } else if (start < 0x1000000) {
+ idx = 3 * 8;
+ idx += ((start - 0xC0000) >> 12);
+ return mtrr_state->fixed_ranges[idx];
+ }
+ }
+
+ /*
+ * Look in variable ranges
+ * Look of multiple ranges matching this address and pick type
+ * as per MTRR precedence
+ */
+ if (!(mtrr_state->enabled & 2))
+ return mtrr_state->def_type;
+
+ prev_match = 0xFF;
+ for (i = 0; i < num_var_ranges; ++i) {
+ unsigned short start_state, end_state;
+
+ if (!(mtrr_state->var_ranges[i].mask_lo & (1 << 11)))
+ continue;
+
+ base = (((u64)mtrr_state->var_ranges[i].base_hi) << 32) +
+ (mtrr_state->var_ranges[i].base_lo & PAGE_MASK);
+ mask = (((u64)mtrr_state->var_ranges[i].mask_hi) << 32) +
+ (mtrr_state->var_ranges[i].mask_lo & PAGE_MASK);
+
+ start_state = ((start & mask) == (base & mask));
+ end_state = ((end & mask) == (base & mask));
+ if (start_state != end_state)
+ return 0xFE;
+
+ if ((start & mask) != (base & mask))
+ continue;
+
+ curr_match = mtrr_state->var_ranges[i].base_lo & 0xff;
+ if (prev_match == 0xFF) {
+ prev_match = curr_match;
+ continue;
+ }
+
+ if (prev_match == MTRR_TYPE_UNCACHABLE ||
+ curr_match == MTRR_TYPE_UNCACHABLE)
+ return MTRR_TYPE_UNCACHABLE;
+
+ if ((prev_match == MTRR_TYPE_WRBACK &&
+ curr_match == MTRR_TYPE_WRTHROUGH) ||
+ (prev_match == MTRR_TYPE_WRTHROUGH &&
+ curr_match == MTRR_TYPE_WRBACK)) {
+ prev_match = MTRR_TYPE_WRTHROUGH;
+ curr_match = MTRR_TYPE_WRTHROUGH;
+ }
+
+ if (prev_match != curr_match)
+ return MTRR_TYPE_UNCACHABLE;
+ }
+
+ if (prev_match != 0xFF)
+ return prev_match;
+
+ return mtrr_state->def_type;
+}
+
+static u8 get_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn)
+{
+ u8 mtrr;
+
+ mtrr = get_mtrr_type(&vcpu->arch.mtrr_state, gfn << PAGE_SHIFT,
+ (gfn << PAGE_SHIFT) + PAGE_SIZE);
+ if (mtrr == 0xfe || mtrr == 0xff)
+ mtrr = MTRR_TYPE_WRBACK;
+ return mtrr;
+}
+
static int kvm_unsync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
{
unsigned index;
@@ -1409,9 +1627,15 @@ static int kvm_unsync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
if (s->role.word != sp->role.word)
return 1;
}
- kvm_mmu_mark_parents_unsync(vcpu, sp);
++vcpu->kvm->stat.mmu_unsync;
sp->unsync = 1;
+
+ if (sp->global) {
+ list_add(&sp->oos_link, &vcpu->kvm->arch.oos_global_pages);
+ ++vcpu->kvm->stat.mmu_unsync_global;
+ } else
+ kvm_mmu_mark_parents_unsync(vcpu, sp);
+
mmu_convert_notrap(sp);
return 0;
}
@@ -1437,11 +1661,24 @@ static int mmu_need_write_protect(struct kvm_vcpu *vcpu, gfn_t gfn,
static int set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte,
unsigned pte_access, int user_fault,
int write_fault, int dirty, int largepage,
- gfn_t gfn, pfn_t pfn, bool speculative,
+ int global, gfn_t gfn, pfn_t pfn, bool speculative,
bool can_unsync)
{
u64 spte;
int ret = 0;
+ u64 mt_mask = shadow_mt_mask;
+ struct kvm_mmu_page *sp = page_header(__pa(shadow_pte));
+
+ if (!(vcpu->arch.cr4 & X86_CR4_PGE))
+ global = 0;
+ if (!global && sp->global) {
+ sp->global = 0;
+ if (sp->unsync) {
+ kvm_unlink_unsync_global(vcpu->kvm, sp);
+ kvm_mmu_mark_parents_unsync(vcpu, sp);
+ }
+ }
+
/*
* We don't set the accessed bit, since we sometimes want to see
* whether the guest actually used the pte (in order to detect
@@ -1460,6 +1697,11 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte,
spte |= shadow_user_mask;
if (largepage)
spte |= PT_PAGE_SIZE_MASK;
+ if (mt_mask) {
+ mt_mask = get_memory_type(vcpu, gfn) <<
+ kvm_x86_ops->get_mt_mask_shift();
+ spte |= mt_mask;
+ }
spte |= (u64)pfn << PAGE_SHIFT;
@@ -1474,6 +1716,15 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte,
spte |= PT_WRITABLE_MASK;
+ /*
+ * Optimization: for pte sync, if spte was writable the hash
+ * lookup is unnecessary (and expensive). Write protection
+ * is responsibility of mmu_get_page / kvm_sync_page.
+ * Same reasoning can be applied to dirty page accounting.
+ */
+ if (!can_unsync && is_writeble_pte(*shadow_pte))
+ goto set_pte;
+
if (mmu_need_write_protect(vcpu, gfn, can_unsync)) {
pgprintk("%s: found shadow page for %lx, marking ro\n",
__func__, gfn);
@@ -1495,8 +1746,8 @@ set_pte:
static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte,
unsigned pt_access, unsigned pte_access,
int user_fault, int write_fault, int dirty,
- int *ptwrite, int largepage, gfn_t gfn,
- pfn_t pfn, bool speculative)
+ int *ptwrite, int largepage, int global,
+ gfn_t gfn, pfn_t pfn, bool speculative)
{
int was_rmapped = 0;
int was_writeble = is_writeble_pte(*shadow_pte);
@@ -1529,7 +1780,7 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte,
}
}
if (set_spte(vcpu, shadow_pte, pte_access, user_fault, write_fault,
- dirty, largepage, gfn, pfn, speculative, true)) {
+ dirty, largepage, global, gfn, pfn, speculative, true)) {
if (write_fault)
*ptwrite = 1;
kvm_x86_ops->tlb_flush(vcpu);
@@ -1586,7 +1837,7 @@ static int direct_map_entry(struct kvm_shadow_walk *_walk,
|| (walk->largepage && level == PT_DIRECTORY_LEVEL)) {
mmu_set_spte(vcpu, sptep, ACC_ALL, ACC_ALL,
0, walk->write, 1, &walk->pt_write,
- walk->largepage, gfn, walk->pfn, false);
+ walk->largepage, 0, gfn, walk->pfn, false);
++vcpu->stat.pf_fixed;
return 1;
}
@@ -1773,6 +2024,15 @@ static void mmu_sync_roots(struct kvm_vcpu *vcpu)
}
}
+static void mmu_sync_global(struct kvm_vcpu *vcpu)
+{
+ struct kvm *kvm = vcpu->kvm;
+ struct kvm_mmu_page *sp, *n;
+
+ list_for_each_entry_safe(sp, n, &kvm->arch.oos_global_pages, oos_link)
+ kvm_sync_page(vcpu, sp);
+}
+
void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu)
{
spin_lock(&vcpu->kvm->mmu_lock);
@@ -1780,6 +2040,13 @@ void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu)
spin_unlock(&vcpu->kvm->mmu_lock);
}
+void kvm_mmu_sync_global(struct kvm_vcpu *vcpu)
+{
+ spin_lock(&vcpu->kvm->mmu_lock);
+ mmu_sync_global(vcpu);
+ spin_unlock(&vcpu->kvm->mmu_lock);
+}
+
static gpa_t nonpaging_gva_to_gpa(struct kvm_vcpu *vcpu, gva_t vaddr)
{
return vaddr;
@@ -2178,7 +2445,8 @@ static void kvm_mmu_access_page(struct kvm_vcpu *vcpu, gfn_t gfn)
}
void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
- const u8 *new, int bytes)
+ const u8 *new, int bytes,
+ bool guest_initiated)
{
gfn_t gfn = gpa >> PAGE_SHIFT;
struct kvm_mmu_page *sp;
@@ -2204,15 +2472,17 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
kvm_mmu_free_some_pages(vcpu);
++vcpu->kvm->stat.mmu_pte_write;
kvm_mmu_audit(vcpu, "pre pte write");
- if (gfn == vcpu->arch.last_pt_write_gfn
- && !last_updated_pte_accessed(vcpu)) {
- ++vcpu->arch.last_pt_write_count;
- if (vcpu->arch.last_pt_write_count >= 3)
- flooded = 1;
- } else {
- vcpu->arch.last_pt_write_gfn = gfn;
- vcpu->arch.last_pt_write_count = 1;
- vcpu->arch.last_pte_updated = NULL;
+ if (guest_initiated) {
+ if (gfn == vcpu->arch.last_pt_write_gfn
+ && !last_updated_pte_accessed(vcpu)) {
+ ++vcpu->arch.last_pt_write_count;
+ if (vcpu->arch.last_pt_write_count >= 3)
+ flooded = 1;
+ } else {
+ vcpu->arch.last_pt_write_gfn = gfn;
+ vcpu->arch.last_pt_write_count = 1;
+ vcpu->arch.last_pte_updated = NULL;
+ }
}
index = kvm_page_table_hashfn(gfn);
bucket = &vcpu->kvm->arch.mmu_page_hash[index];
@@ -2352,9 +2622,7 @@ EXPORT_SYMBOL_GPL(kvm_mmu_page_fault);
void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva)
{
- spin_lock(&vcpu->kvm->mmu_lock);
vcpu->arch.mmu.invlpg(vcpu, gva);
- spin_unlock(&vcpu->kvm->mmu_lock);
kvm_mmu_flush_tlb(vcpu);
++vcpu->stat.invlpg;
}
@@ -2451,7 +2719,7 @@ void kvm_mmu_slot_remove_write_access(struct kvm *kvm, int slot)
int i;
u64 *pt;
- if (!test_bit(slot, &sp->slot_bitmap))
+ if (!test_bit(slot, sp->slot_bitmap))
continue;
pt = sp->spt;
@@ -2860,8 +3128,8 @@ static void audit_write_protection(struct kvm_vcpu *vcpu)
if (sp->role.metaphysical)
continue;
- slot = gfn_to_memslot(vcpu->kvm, sp->gfn);
gfn = unalias_gfn(vcpu->kvm, sp->gfn);
+ slot = gfn_to_memslot_unaliased(vcpu->kvm, sp->gfn);
rmapp = &slot->rmap[gfn - slot->base_gfn];
if (*rmapp)
printk(KERN_ERR "%s: (%s) shadow page has writable"
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index 84eee43bbe7..9fd78b6e17a 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -82,6 +82,7 @@ struct shadow_walker {
int *ptwrite;
pfn_t pfn;
u64 *sptep;
+ gpa_t pte_gpa;
};
static gfn_t gpte_to_gfn(pt_element_t gpte)
@@ -222,7 +223,7 @@ walk:
if (ret)
goto walk;
pte |= PT_DIRTY_MASK;
- kvm_mmu_pte_write(vcpu, pte_gpa, (u8 *)&pte, sizeof(pte));
+ kvm_mmu_pte_write(vcpu, pte_gpa, (u8 *)&pte, sizeof(pte), 0);
walker->ptes[walker->level - 1] = pte;
}
@@ -274,7 +275,8 @@ static void FNAME(update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *page,
return;
kvm_get_pfn(pfn);
mmu_set_spte(vcpu, spte, page->role.access, pte_access, 0, 0,
- gpte & PT_DIRTY_MASK, NULL, largepage, gpte_to_gfn(gpte),
+ gpte & PT_DIRTY_MASK, NULL, largepage,
+ gpte & PT_GLOBAL_MASK, gpte_to_gfn(gpte),
pfn, true);
}
@@ -301,8 +303,9 @@ static int FNAME(shadow_walk_entry)(struct kvm_shadow_walk *_sw,
mmu_set_spte(vcpu, sptep, access, gw->pte_access & access,
sw->user_fault, sw->write_fault,
gw->ptes[gw->level-1] & PT_DIRTY_MASK,
- sw->ptwrite, sw->largepage, gw->gfn, sw->pfn,
- false);
+ sw->ptwrite, sw->largepage,
+ gw->ptes[gw->level-1] & PT_GLOBAL_MASK,
+ gw->gfn, sw->pfn, false);
sw->sptep = sptep;
return 1;
}
@@ -466,10 +469,22 @@ static int FNAME(shadow_invlpg_entry)(struct kvm_shadow_walk *_sw,
struct kvm_vcpu *vcpu, u64 addr,
u64 *sptep, int level)
{
+ struct shadow_walker *sw =
+ container_of(_sw, struct shadow_walker, walker);
- if (level == PT_PAGE_TABLE_LEVEL) {
- if (is_shadow_present_pte(*sptep))
+ /* FIXME: properly handle invlpg on large guest pages */
+ if (level == PT_PAGE_TABLE_LEVEL ||
+ ((level == PT_DIRECTORY_LEVEL) && is_large_pte(*sptep))) {
+ struct kvm_mmu_page *sp = page_header(__pa(sptep));
+
+ sw->pte_gpa = (sp->gfn << PAGE_SHIFT);
+ sw->pte_gpa += (sptep - sp->spt) * sizeof(pt_element_t);
+
+ if (is_shadow_present_pte(*sptep)) {
rmap_remove(vcpu->kvm, sptep);
+ if (is_large_pte(*sptep))
+ --vcpu->kvm->stat.lpages;
+ }
set_shadow_pte(sptep, shadow_trap_nonpresent_pte);
return 1;
}
@@ -480,11 +495,26 @@ static int FNAME(shadow_invlpg_entry)(struct kvm_shadow_walk *_sw,
static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva)
{
+ pt_element_t gpte;
struct shadow_walker walker = {
.walker = { .entry = FNAME(shadow_invlpg_entry), },
+ .pte_gpa = -1,
};
+ spin_lock(&vcpu->kvm->mmu_lock);
walk_shadow(&walker.walker, vcpu, gva);
+ spin_unlock(&vcpu->kvm->mmu_lock);
+ if (walker.pte_gpa == -1)
+ return;
+ if (kvm_read_guest_atomic(vcpu->kvm, walker.pte_gpa, &gpte,
+ sizeof(pt_element_t)))
+ return;
+ if (is_present_pte(gpte) && (gpte & PT_ACCESSED_MASK)) {
+ if (mmu_topup_memory_caches(vcpu))
+ return;
+ kvm_mmu_pte_write(vcpu, walker.pte_gpa, (const u8 *)&gpte,
+ sizeof(pt_element_t), 0);
+ }
}
static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t vaddr)
@@ -580,7 +610,7 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
nr_present++;
pte_access = sp->role.access & FNAME(gpte_access)(vcpu, gpte);
set_spte(vcpu, &sp->spt[i], pte_access, 0, 0,
- is_dirty_pte(gpte), 0, gfn,
+ is_dirty_pte(gpte), 0, gpte & PT_GLOBAL_MASK, gfn,
spte_to_pfn(sp->spt[i]), true, false);
}
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 9c4ce657d96..1452851ae25 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -28,6 +28,8 @@
#include <asm/desc.h>
+#include <asm/virtext.h>
+
#define __ex(x) __kvm_handle_fault_on_reboot(x)
MODULE_AUTHOR("Qumranet");
@@ -245,34 +247,19 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu)
static int has_svm(void)
{
- uint32_t eax, ebx, ecx, edx;
-
- if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD) {
- printk(KERN_INFO "has_svm: not amd\n");
- return 0;
- }
+ const char *msg;
- cpuid(0x80000000, &eax, &ebx, &ecx, &edx);
- if (eax < SVM_CPUID_FUNC) {
- printk(KERN_INFO "has_svm: can't execute cpuid_8000000a\n");
+ if (!cpu_has_svm(&msg)) {
+ printk(KERN_INFO "has_svn: %s\n", msg);
return 0;
}
- cpuid(0x80000001, &eax, &ebx, &ecx, &edx);
- if (!(ecx & (1 << SVM_CPUID_FEATURE_SHIFT))) {
- printk(KERN_DEBUG "has_svm: svm not available\n");
- return 0;
- }
return 1;
}
static void svm_hardware_disable(void *garbage)
{
- uint64_t efer;
-
- wrmsrl(MSR_VM_HSAVE_PA, 0);
- rdmsrl(MSR_EFER, efer);
- wrmsrl(MSR_EFER, efer & ~MSR_EFER_SVME_MASK);
+ cpu_svm_disable();
}
static void svm_hardware_enable(void *garbage)
@@ -772,6 +759,22 @@ static void svm_get_segment(struct kvm_vcpu *vcpu,
var->l = (s->attrib >> SVM_SELECTOR_L_SHIFT) & 1;
var->db = (s->attrib >> SVM_SELECTOR_DB_SHIFT) & 1;
var->g = (s->attrib >> SVM_SELECTOR_G_SHIFT) & 1;
+
+ /*
+ * SVM always stores 0 for the 'G' bit in the CS selector in
+ * the VMCB on a VMEXIT. This hurts cross-vendor migration:
+ * Intel's VMENTRY has a check on the 'G' bit.
+ */
+ if (seg == VCPU_SREG_CS)
+ var->g = s->limit > 0xfffff;
+
+ /*
+ * Work around a bug where the busy flag in the tr selector
+ * isn't exposed
+ */
+ if (seg == VCPU_SREG_TR)
+ var->type |= 0x2;
+
var->unusable = !var->present;
}
@@ -1099,6 +1102,7 @@ static int io_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
rep = (io_info & SVM_IOIO_REP_MASK) != 0;
down = (svm->vmcb->save.rflags & X86_EFLAGS_DF) != 0;
+ skip_emulated_instruction(&svm->vcpu);
return kvm_emulate_pio(&svm->vcpu, kvm_run, in, size, port);
}
@@ -1912,6 +1916,11 @@ static int get_npt_level(void)
#endif
}
+static int svm_get_mt_mask_shift(void)
+{
+ return 0;
+}
+
static struct kvm_x86_ops svm_x86_ops = {
.cpu_has_kvm_support = has_svm,
.disabled_by_bios = is_disabled,
@@ -1967,6 +1976,7 @@ static struct kvm_x86_ops svm_x86_ops = {
.set_tss_addr = svm_set_tss_addr,
.get_tdp_level = get_npt_level,
+ .get_mt_mask_shift = svm_get_mt_mask_shift,
};
static int __init svm_init(void)
diff --git a/arch/x86/kvm/svm.h b/arch/x86/kvm/svm.h
deleted file mode 100644
index 1b8afa78e86..00000000000
--- a/arch/x86/kvm/svm.h
+++ /dev/null
@@ -1,328 +0,0 @@
-#ifndef __SVM_H
-#define __SVM_H
-
-enum {
- INTERCEPT_INTR,
- INTERCEPT_NMI,
- INTERCEPT_SMI,
- INTERCEPT_INIT,
- INTERCEPT_VINTR,
- INTERCEPT_SELECTIVE_CR0,
- INTERCEPT_STORE_IDTR,
- INTERCEPT_STORE_GDTR,
- INTERCEPT_STORE_LDTR,
- INTERCEPT_STORE_TR,
- INTERCEPT_LOAD_IDTR,
- INTERCEPT_LOAD_GDTR,
- INTERCEPT_LOAD_LDTR,
- INTERCEPT_LOAD_TR,
- INTERCEPT_RDTSC,
- INTERCEPT_RDPMC,
- INTERCEPT_PUSHF,
- INTERCEPT_POPF,
- INTERCEPT_CPUID,
- INTERCEPT_RSM,
- INTERCEPT_IRET,
- INTERCEPT_INTn,
- INTERCEPT_INVD,
- INTERCEPT_PAUSE,
- INTERCEPT_HLT,
- INTERCEPT_INVLPG,
- INTERCEPT_INVLPGA,
- INTERCEPT_IOIO_PROT,
- INTERCEPT_MSR_PROT,
- INTERCEPT_TASK_SWITCH,
- INTERCEPT_FERR_FREEZE,
- INTERCEPT_SHUTDOWN,
- INTERCEPT_VMRUN,
- INTERCEPT_VMMCALL,
- INTERCEPT_VMLOAD,
- INTERCEPT_VMSAVE,
- INTERCEPT_STGI,
- INTERCEPT_CLGI,
- INTERCEPT_SKINIT,
- INTERCEPT_RDTSCP,
- INTERCEPT_ICEBP,
- INTERCEPT_WBINVD,
- INTERCEPT_MONITOR,
- INTERCEPT_MWAIT,
- INTERCEPT_MWAIT_COND,
-};
-
-
-struct __attribute__ ((__packed__)) vmcb_control_area {
- u16 intercept_cr_read;
- u16 intercept_cr_write;
- u16 intercept_dr_read;
- u16 intercept_dr_write;
- u32 intercept_exceptions;
- u64 intercept;
- u8 reserved_1[44];
- u64 iopm_base_pa;
- u64 msrpm_base_pa;
- u64 tsc_offset;
- u32 asid;
- u8 tlb_ctl;
- u8 reserved_2[3];
- u32 int_ctl;
- u32 int_vector;
- u32 int_state;
- u8 reserved_3[4];
- u32 exit_code;
- u32 exit_code_hi;
- u64 exit_info_1;
- u64 exit_info_2;
- u32 exit_int_info;
- u32 exit_int_info_err;
- u64 nested_ctl;
- u8 reserved_4[16];
- u32 event_inj;
- u32 event_inj_err;
- u64 nested_cr3;
- u64 lbr_ctl;
- u8 reserved_5[832];
-};
-
-
-#define TLB_CONTROL_DO_NOTHING 0
-#define TLB_CONTROL_FLUSH_ALL_ASID 1
-
-#define V_TPR_MASK 0x0f
-
-#define V_IRQ_SHIFT 8
-#define V_IRQ_MASK (1 << V_IRQ_SHIFT)
-
-#define V_INTR_PRIO_SHIFT 16
-#define V_INTR_PRIO_MASK (0x0f << V_INTR_PRIO_SHIFT)
-
-#define V_IGN_TPR_SHIFT 20
-#define V_IGN_TPR_MASK (1 << V_IGN_TPR_SHIFT)
-
-#define V_INTR_MASKING_SHIFT 24
-#define V_INTR_MASKING_MASK (1 << V_INTR_MASKING_SHIFT)
-
-#define SVM_INTERRUPT_SHADOW_MASK 1
-
-#define SVM_IOIO_STR_SHIFT 2
-#define SVM_IOIO_REP_SHIFT 3
-#define SVM_IOIO_SIZE_SHIFT 4
-#define SVM_IOIO_ASIZE_SHIFT 7
-
-#define SVM_IOIO_TYPE_MASK 1
-#define SVM_IOIO_STR_MASK (1 << SVM_IOIO_STR_SHIFT)
-#define SVM_IOIO_REP_MASK (1 << SVM_IOIO_REP_SHIFT)
-#define SVM_IOIO_SIZE_MASK (7 << SVM_IOIO_SIZE_SHIFT)
-#define SVM_IOIO_ASIZE_MASK (7 << SVM_IOIO_ASIZE_SHIFT)
-
-struct __attribute__ ((__packed__)) vmcb_seg {
- u16 selector;
- u16 attrib;
- u32 limit;
- u64 base;
-};
-
-struct __attribute__ ((__packed__)) vmcb_save_area {
- struct vmcb_seg es;
- struct vmcb_seg cs;
- struct vmcb_seg ss;
- struct vmcb_seg ds;
- struct vmcb_seg fs;
- struct vmcb_seg gs;
- struct vmcb_seg gdtr;
- struct vmcb_seg ldtr;
- struct vmcb_seg idtr;
- struct vmcb_seg tr;
- u8 reserved_1[43];
- u8 cpl;
- u8 reserved_2[4];
- u64 efer;
- u8 reserved_3[112];
- u64 cr4;
- u64 cr3;
- u64 cr0;
- u64 dr7;
- u64 dr6;
- u64 rflags;
- u64 rip;
- u8 reserved_4[88];
- u64 rsp;
- u8 reserved_5[24];
- u64 rax;
- u64 star;
- u64 lstar;
- u64 cstar;
- u64 sfmask;
- u64 kernel_gs_base;
- u64 sysenter_cs;
- u64 sysenter_esp;
- u64 sysenter_eip;
- u64 cr2;
- u8 reserved_6[32];
- u64 g_pat;
- u64 dbgctl;
- u64 br_from;
- u64 br_to;
- u64 last_excp_from;
- u64 last_excp_to;
-};
-
-struct __attribute__ ((__packed__)) vmcb {
- struct vmcb_control_area control;
- struct vmcb_save_area save;
-};
-
-#define SVM_CPUID_FEATURE_SHIFT 2
-#define SVM_CPUID_FUNC 0x8000000a
-
-#define MSR_EFER_SVME_MASK (1ULL << 12)
-#define MSR_VM_CR 0xc0010114
-#define MSR_VM_HSAVE_PA 0xc0010117ULL
-
-#define SVM_VM_CR_SVM_DISABLE 4
-
-#define SVM_SELECTOR_S_SHIFT 4
-#define SVM_SELECTOR_DPL_SHIFT 5
-#define SVM_SELECTOR_P_SHIFT 7
-#define SVM_SELECTOR_AVL_SHIFT 8
-#define SVM_SELECTOR_L_SHIFT 9
-#define SVM_SELECTOR_DB_SHIFT 10
-#define SVM_SELECTOR_G_SHIFT 11
-
-#define SVM_SELECTOR_TYPE_MASK (0xf)
-#define SVM_SELECTOR_S_MASK (1 << SVM_SELECTOR_S_SHIFT)
-#define SVM_SELECTOR_DPL_MASK (3 << SVM_SELECTOR_DPL_SHIFT)
-#define SVM_SELECTOR_P_MASK (1 << SVM_SELECTOR_P_SHIFT)
-#define SVM_SELECTOR_AVL_MASK (1 << SVM_SELECTOR_AVL_SHIFT)
-#define SVM_SELECTOR_L_MASK (1 << SVM_SELECTOR_L_SHIFT)
-#define SVM_SELECTOR_DB_MASK (1 << SVM_SELECTOR_DB_SHIFT)
-#define SVM_SELECTOR_G_MASK (1 << SVM_SELECTOR_G_SHIFT)
-
-#define SVM_SELECTOR_WRITE_MASK (1 << 1)
-#define SVM_SELECTOR_READ_MASK SVM_SELECTOR_WRITE_MASK
-#define SVM_SELECTOR_CODE_MASK (1 << 3)
-
-#define INTERCEPT_CR0_MASK 1
-#define INTERCEPT_CR3_MASK (1 << 3)
-#define INTERCEPT_CR4_MASK (1 << 4)
-#define INTERCEPT_CR8_MASK (1 << 8)
-
-#define INTERCEPT_DR0_MASK 1
-#define INTERCEPT_DR1_MASK (1 << 1)
-#define INTERCEPT_DR2_MASK (1 << 2)
-#define INTERCEPT_DR3_MASK (1 << 3)
-#define INTERCEPT_DR4_MASK (1 << 4)
-#define INTERCEPT_DR5_MASK (1 << 5)
-#define INTERCEPT_DR6_MASK (1 << 6)
-#define INTERCEPT_DR7_MASK (1 << 7)
-
-#define SVM_EVTINJ_VEC_MASK 0xff
-
-#define SVM_EVTINJ_TYPE_SHIFT 8
-#define SVM_EVTINJ_TYPE_MASK (7 << SVM_EVTINJ_TYPE_SHIFT)
-
-#define SVM_EVTINJ_TYPE_INTR (0 << SVM_EVTINJ_TYPE_SHIFT)
-#define SVM_EVTINJ_TYPE_NMI (2 << SVM_EVTINJ_TYPE_SHIFT)
-#define SVM_EVTINJ_TYPE_EXEPT (3 << SVM_EVTINJ_TYPE_SHIFT)
-#define SVM_EVTINJ_TYPE_SOFT (4 << SVM_EVTINJ_TYPE_SHIFT)
-
-#define SVM_EVTINJ_VALID (1 << 31)
-#define SVM_EVTINJ_VALID_ERR (1 << 11)
-
-#define SVM_EXITINTINFO_VEC_MASK SVM_EVTINJ_VEC_MASK
-
-#define SVM_EXITINTINFO_TYPE_INTR SVM_EVTINJ_TYPE_INTR
-#define SVM_EXITINTINFO_TYPE_NMI SVM_EVTINJ_TYPE_NMI
-#define SVM_EXITINTINFO_TYPE_EXEPT SVM_EVTINJ_TYPE_EXEPT
-#define SVM_EXITINTINFO_TYPE_SOFT SVM_EVTINJ_TYPE_SOFT
-
-#define SVM_EXITINTINFO_VALID SVM_EVTINJ_VALID
-#define SVM_EXITINTINFO_VALID_ERR SVM_EVTINJ_VALID_ERR
-
-#define SVM_EXITINFOSHIFT_TS_REASON_IRET 36
-#define SVM_EXITINFOSHIFT_TS_REASON_JMP 38
-
-#define SVM_EXIT_READ_CR0 0x000
-#define SVM_EXIT_READ_CR3 0x003
-#define SVM_EXIT_READ_CR4 0x004
-#define SVM_EXIT_READ_CR8 0x008
-#define SVM_EXIT_WRITE_CR0 0x010
-#define SVM_EXIT_WRITE_CR3 0x013
-#define SVM_EXIT_WRITE_CR4 0x014
-#define SVM_EXIT_WRITE_CR8 0x018
-#define SVM_EXIT_READ_DR0 0x020
-#define SVM_EXIT_READ_DR1 0x021
-#define SVM_EXIT_READ_DR2 0x022
-#define SVM_EXIT_READ_DR3 0x023
-#define SVM_EXIT_READ_DR4 0x024
-#define SVM_EXIT_READ_DR5 0x025
-#define SVM_EXIT_READ_DR6 0x026
-#define SVM_EXIT_READ_DR7 0x027
-#define SVM_EXIT_WRITE_DR0 0x030
-#define SVM_EXIT_WRITE_DR1 0x031
-#define SVM_EXIT_WRITE_DR2 0x032
-#define SVM_EXIT_WRITE_DR3 0x033
-#define SVM_EXIT_WRITE_DR4 0x034
-#define SVM_EXIT_WRITE_DR5 0x035
-#define SVM_EXIT_WRITE_DR6 0x036
-#define SVM_EXIT_WRITE_DR7 0x037
-#define SVM_EXIT_EXCP_BASE 0x040
-#define SVM_EXIT_INTR 0x060
-#define SVM_EXIT_NMI 0x061
-#define SVM_EXIT_SMI 0x062
-#define SVM_EXIT_INIT 0x063
-#define SVM_EXIT_VINTR 0x064
-#define SVM_EXIT_CR0_SEL_WRITE 0x065
-#define SVM_EXIT_IDTR_READ 0x066
-#define SVM_EXIT_GDTR_READ 0x067
-#define SVM_EXIT_LDTR_READ 0x068
-#define SVM_EXIT_TR_READ 0x069
-#define SVM_EXIT_IDTR_WRITE 0x06a
-#define SVM_EXIT_GDTR_WRITE 0x06b
-#define SVM_EXIT_LDTR_WRITE 0x06c
-#define SVM_EXIT_TR_WRITE 0x06d
-#define SVM_EXIT_RDTSC 0x06e
-#define SVM_EXIT_RDPMC 0x06f
-#define SVM_EXIT_PUSHF 0x070
-#define SVM_EXIT_POPF 0x071
-#define SVM_EXIT_CPUID 0x072
-#define SVM_EXIT_RSM 0x073
-#define SVM_EXIT_IRET 0x074
-#define SVM_EXIT_SWINT 0x075
-#define SVM_EXIT_INVD 0x076
-#define SVM_EXIT_PAUSE 0x077
-#define SVM_EXIT_HLT 0x078
-#define SVM_EXIT_INVLPG 0x079
-#define SVM_EXIT_INVLPGA 0x07a
-#define SVM_EXIT_IOIO 0x07b
-#define SVM_EXIT_MSR 0x07c
-#define SVM_EXIT_TASK_SWITCH 0x07d
-#define SVM_EXIT_FERR_FREEZE 0x07e
-#define SVM_EXIT_SHUTDOWN 0x07f
-#define SVM_EXIT_VMRUN 0x080
-#define SVM_EXIT_VMMCALL 0x081
-#define SVM_EXIT_VMLOAD 0x082
-#define SVM_EXIT_VMSAVE 0x083
-#define SVM_EXIT_STGI 0x084
-#define SVM_EXIT_CLGI 0x085
-#define SVM_EXIT_SKINIT 0x086
-#define SVM_EXIT_RDTSCP 0x087
-#define SVM_EXIT_ICEBP 0x088
-#define SVM_EXIT_WBINVD 0x089
-#define SVM_EXIT_MONITOR 0x08a
-#define SVM_EXIT_MWAIT 0x08b
-#define SVM_EXIT_MWAIT_COND 0x08c
-#define SVM_EXIT_NPF 0x400
-
-#define SVM_EXIT_ERR -1
-
-#define SVM_CR0_SELECTIVE_MASK (1 << 3 | 1) /* TS and MP */
-
-#define SVM_VMLOAD ".byte 0x0f, 0x01, 0xda"
-#define SVM_VMRUN ".byte 0x0f, 0x01, 0xd8"
-#define SVM_VMSAVE ".byte 0x0f, 0x01, 0xdb"
-#define SVM_CLGI ".byte 0x0f, 0x01, 0xdd"
-#define SVM_STGI ".byte 0x0f, 0x01, 0xdc"
-#define SVM_INVLPGA ".byte 0x0f, 0x01, 0xdf"
-
-#endif
-
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index a4018b01e1f..6259d746764 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -16,7 +16,6 @@
*/
#include "irq.h"
-#include "vmx.h"
#include "mmu.h"
#include <linux/kvm_host.h>
@@ -31,6 +30,8 @@
#include <asm/io.h>
#include <asm/desc.h>
+#include <asm/vmx.h>
+#include <asm/virtext.h>
#define __ex(x) __kvm_handle_fault_on_reboot(x)
@@ -90,6 +91,11 @@ struct vcpu_vmx {
} rmode;
int vpid;
bool emulation_required;
+
+ /* Support for vnmi-less CPUs */
+ int soft_vnmi_blocked;
+ ktime_t entry_time;
+ s64 vnmi_blocked_time;
};
static inline struct vcpu_vmx *to_vmx(struct kvm_vcpu *vcpu)
@@ -122,7 +128,7 @@ static struct vmcs_config {
u32 vmentry_ctrl;
} vmcs_config;
-struct vmx_capability {
+static struct vmx_capability {
u32 ept;
u32 vpid;
} vmx_capability;
@@ -957,6 +963,13 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data)
pr_unimpl(vcpu, "unimplemented perfctr wrmsr: 0x%x data 0x%llx\n", msr_index, data);
break;
+ case MSR_IA32_CR_PAT:
+ if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) {
+ vmcs_write64(GUEST_IA32_PAT, data);
+ vcpu->arch.pat = data;
+ break;
+ }
+ /* Otherwise falls through to kvm_set_msr_common */
default:
vmx_load_host_state(vmx);
msr = find_msr_entry(vmx, msr_index);
@@ -1032,8 +1045,7 @@ static int vmx_get_irq(struct kvm_vcpu *vcpu)
static __init int cpu_has_kvm_support(void)
{
- unsigned long ecx = cpuid_ecx(1);
- return test_bit(5, &ecx); /* CPUID.1:ECX.VMX[bit 5] -> VT */
+ return cpu_has_vmx();
}
static __init int vmx_disabled_by_bios(void)
@@ -1079,13 +1091,22 @@ static void vmclear_local_vcpus(void)
__vcpu_clear(vmx);
}
-static void hardware_disable(void *garbage)
+
+/* Just like cpu_vmxoff(), but with the __kvm_handle_fault_on_reboot()
+ * tricks.
+ */
+static void kvm_cpu_vmxoff(void)
{
- vmclear_local_vcpus();
asm volatile (__ex(ASM_VMX_VMXOFF) : : : "cc");
write_cr4(read_cr4() & ~X86_CR4_VMXE);
}
+static void hardware_disable(void *garbage)
+{
+ vmclear_local_vcpus();
+ kvm_cpu_vmxoff();
+}
+
static __init int adjust_vmx_controls(u32 ctl_min, u32 ctl_opt,
u32 msr, u32 *result)
{
@@ -1176,12 +1197,13 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf)
#ifdef CONFIG_X86_64
min |= VM_EXIT_HOST_ADDR_SPACE_SIZE;
#endif
- opt = 0;
+ opt = VM_EXIT_SAVE_IA32_PAT | VM_EXIT_LOAD_IA32_PAT;
if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_EXIT_CTLS,
&_vmexit_control) < 0)
return -EIO;
- min = opt = 0;
+ min = 0;
+ opt = VM_ENTRY_LOAD_IA32_PAT;
if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_ENTRY_CTLS,
&_vmentry_control) < 0)
return -EIO;
@@ -2087,8 +2109,9 @@ static void vmx_disable_intercept_for_msr(struct page *msr_bitmap, u32 msr)
*/
static int vmx_vcpu_setup(struct vcpu_vmx *vmx)
{
- u32 host_sysenter_cs;
+ u32 host_sysenter_cs, msr_low, msr_high;
u32 junk;
+ u64 host_pat;
unsigned long a;
struct descriptor_table dt;
int i;
@@ -2176,6 +2199,20 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx)
rdmsrl(MSR_IA32_SYSENTER_EIP, a);
vmcs_writel(HOST_IA32_SYSENTER_EIP, a); /* 22.2.3 */
+ if (vmcs_config.vmexit_ctrl & VM_EXIT_LOAD_IA32_PAT) {
+ rdmsr(MSR_IA32_CR_PAT, msr_low, msr_high);
+ host_pat = msr_low | ((u64) msr_high << 32);
+ vmcs_write64(HOST_IA32_PAT, host_pat);
+ }
+ if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) {
+ rdmsr(MSR_IA32_CR_PAT, msr_low, msr_high);
+ host_pat = msr_low | ((u64) msr_high << 32);
+ /* Write the default value follow host pat */
+ vmcs_write64(GUEST_IA32_PAT, host_pat);
+ /* Keep arch.pat sync with GUEST_IA32_PAT */
+ vmx->vcpu.arch.pat = host_pat;
+ }
+
for (i = 0; i < NR_VMX_MSR; ++i) {
u32 index = vmx_msr_index[i];
u32 data_low, data_high;
@@ -2230,6 +2267,8 @@ static int vmx_vcpu_reset(struct kvm_vcpu *vcpu)
vmx->vcpu.arch.rmode.active = 0;
+ vmx->soft_vnmi_blocked = 0;
+
vmx->vcpu.arch.regs[VCPU_REGS_RDX] = get_rdx_init_val();
kvm_set_cr8(&vmx->vcpu, 0);
msr = 0xfee00000 | MSR_IA32_APICBASE_ENABLE;
@@ -2335,6 +2374,29 @@ out:
return ret;
}
+static void enable_irq_window(struct kvm_vcpu *vcpu)
+{
+ u32 cpu_based_vm_exec_control;
+
+ cpu_based_vm_exec_control = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL);
+ cpu_based_vm_exec_control |= CPU_BASED_VIRTUAL_INTR_PENDING;
+ vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control);
+}
+
+static void enable_nmi_window(struct kvm_vcpu *vcpu)
+{
+ u32 cpu_based_vm_exec_control;
+
+ if (!cpu_has_virtual_nmis()) {
+ enable_irq_window(vcpu);
+ return;
+ }
+
+ cpu_based_vm_exec_control = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL);
+ cpu_based_vm_exec_control |= CPU_BASED_VIRTUAL_NMI_PENDING;
+ vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control);
+}
+
static void vmx_inject_irq(struct kvm_vcpu *vcpu, int irq)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -2358,10 +2420,54 @@ static void vmx_inject_irq(struct kvm_vcpu *vcpu, int irq)
static void vmx_inject_nmi(struct kvm_vcpu *vcpu)
{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+ if (!cpu_has_virtual_nmis()) {
+ /*
+ * Tracking the NMI-blocked state in software is built upon
+ * finding the next open IRQ window. This, in turn, depends on
+ * well-behaving guests: They have to keep IRQs disabled at
+ * least as long as the NMI handler runs. Otherwise we may
+ * cause NMI nesting, maybe breaking the guest. But as this is
+ * highly unlikely, we can live with the residual risk.
+ */
+ vmx->soft_vnmi_blocked = 1;
+ vmx->vnmi_blocked_time = 0;
+ }
+
+ ++vcpu->stat.nmi_injections;
+ if (vcpu->arch.rmode.active) {
+ vmx->rmode.irq.pending = true;
+ vmx->rmode.irq.vector = NMI_VECTOR;
+ vmx->rmode.irq.rip = kvm_rip_read(vcpu);
+ vmcs_write32(VM_ENTRY_INTR_INFO_FIELD,
+ NMI_VECTOR | INTR_TYPE_SOFT_INTR |
+ INTR_INFO_VALID_MASK);
+ vmcs_write32(VM_ENTRY_INSTRUCTION_LEN, 1);
+ kvm_rip_write(vcpu, vmx->rmode.irq.rip - 1);
+ return;
+ }
vmcs_write32(VM_ENTRY_INTR_INFO_FIELD,
INTR_TYPE_NMI_INTR | INTR_INFO_VALID_MASK | NMI_VECTOR);
}
+static void vmx_update_window_states(struct kvm_vcpu *vcpu)
+{
+ u32 guest_intr = vmcs_read32(GUEST_INTERRUPTIBILITY_INFO);
+
+ vcpu->arch.nmi_window_open =
+ !(guest_intr & (GUEST_INTR_STATE_STI |
+ GUEST_INTR_STATE_MOV_SS |
+ GUEST_INTR_STATE_NMI));
+ if (!cpu_has_virtual_nmis() && to_vmx(vcpu)->soft_vnmi_blocked)
+ vcpu->arch.nmi_window_open = 0;
+
+ vcpu->arch.interrupt_window_open =
+ ((vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_IF) &&
+ !(guest_intr & (GUEST_INTR_STATE_STI |
+ GUEST_INTR_STATE_MOV_SS)));
+}
+
static void kvm_do_inject_irq(struct kvm_vcpu *vcpu)
{
int word_index = __ffs(vcpu->arch.irq_summary);
@@ -2374,40 +2480,49 @@ static void kvm_do_inject_irq(struct kvm_vcpu *vcpu)
kvm_queue_interrupt(vcpu, irq);
}
-
static void do_interrupt_requests(struct kvm_vcpu *vcpu,
struct kvm_run *kvm_run)
{
- u32 cpu_based_vm_exec_control;
-
- vcpu->arch.interrupt_window_open =
- ((vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_IF) &&
- (vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & 3) == 0);
+ vmx_update_window_states(vcpu);
- if (vcpu->arch.interrupt_window_open &&
- vcpu->arch.irq_summary && !vcpu->arch.interrupt.pending)
- kvm_do_inject_irq(vcpu);
+ if (vcpu->arch.nmi_pending && !vcpu->arch.nmi_injected) {
+ if (vcpu->arch.interrupt.pending) {
+ enable_nmi_window(vcpu);
+ } else if (vcpu->arch.nmi_window_open) {
+ vcpu->arch.nmi_pending = false;
+ vcpu->arch.nmi_injected = true;
+ } else {
+ enable_nmi_window(vcpu);
+ return;
+ }
+ }
+ if (vcpu->arch.nmi_injected) {
+ vmx_inject_nmi(vcpu);
+ if (vcpu->arch.nmi_pending)
+ enable_nmi_window(vcpu);
+ else if (vcpu->arch.irq_summary
+ || kvm_run->request_interrupt_window)
+ enable_irq_window(vcpu);
+ return;
+ }
- if (vcpu->arch.interrupt_window_open && vcpu->arch.interrupt.pending)
- vmx_inject_irq(vcpu, vcpu->arch.interrupt.nr);
+ if (vcpu->arch.interrupt_window_open) {
+ if (vcpu->arch.irq_summary && !vcpu->arch.interrupt.pending)
+ kvm_do_inject_irq(vcpu);
- cpu_based_vm_exec_control = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL);
+ if (vcpu->arch.interrupt.pending)
+ vmx_inject_irq(vcpu, vcpu->arch.interrupt.nr);
+ }
if (!vcpu->arch.interrupt_window_open &&
(vcpu->arch.irq_summary || kvm_run->request_interrupt_window))
- /*
- * Interrupts blocked. Wait for unblock.
- */
- cpu_based_vm_exec_control |= CPU_BASED_VIRTUAL_INTR_PENDING;
- else
- cpu_based_vm_exec_control &= ~CPU_BASED_VIRTUAL_INTR_PENDING;
- vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control);
+ enable_irq_window(vcpu);
}
static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr)
{
int ret;
struct kvm_userspace_memory_region tss_mem = {
- .slot = 8,
+ .slot = TSS_PRIVATE_MEMSLOT,
.guest_phys_addr = addr,
.memory_size = PAGE_SIZE * 3,
.flags = 0,
@@ -2492,7 +2607,7 @@ static int handle_exception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
set_bit(irq / BITS_PER_LONG, &vcpu->arch.irq_summary);
}
- if ((intr_info & INTR_INFO_INTR_TYPE_MASK) == 0x200) /* nmi */
+ if ((intr_info & INTR_INFO_INTR_TYPE_MASK) == INTR_TYPE_NMI_INTR)
return 1; /* already handled by vmx_vcpu_run() */
if (is_no_device(intr_info)) {
@@ -2581,6 +2696,7 @@ static int handle_io(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
rep = (exit_qualification & 32) != 0;
port = exit_qualification >> 16;
+ skip_emulated_instruction(vcpu);
return kvm_emulate_pio(vcpu, kvm_run, in, size, port);
}
@@ -2767,6 +2883,7 @@ static int handle_interrupt_window(struct kvm_vcpu *vcpu,
vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control);
KVMTRACE_0D(PEND_INTR, vcpu, handler);
+ ++vcpu->stat.irq_window_exits;
/*
* If the user space waits to inject interrupts, exit as soon as
@@ -2775,7 +2892,6 @@ static int handle_interrupt_window(struct kvm_vcpu *vcpu,
if (kvm_run->request_interrupt_window &&
!vcpu->arch.irq_summary) {
kvm_run->exit_reason = KVM_EXIT_IRQ_WINDOW_OPEN;
- ++vcpu->stat.irq_window_exits;
return 0;
}
return 1;
@@ -2832,6 +2948,7 @@ static int handle_apic_access(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
static int handle_task_switch(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
unsigned long exit_qualification;
u16 tss_selector;
int reason;
@@ -2839,6 +2956,15 @@ static int handle_task_switch(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
reason = (u32)exit_qualification >> 30;
+ if (reason == TASK_SWITCH_GATE && vmx->vcpu.arch.nmi_injected &&
+ (vmx->idt_vectoring_info & VECTORING_INFO_VALID_MASK) &&
+ (vmx->idt_vectoring_info & VECTORING_INFO_TYPE_MASK)
+ == INTR_TYPE_NMI_INTR) {
+ vcpu->arch.nmi_injected = false;
+ if (cpu_has_virtual_nmis())
+ vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO,
+ GUEST_INTR_STATE_NMI);
+ }
tss_selector = exit_qualification;
return kvm_task_switch(vcpu, tss_selector, reason);
@@ -2927,16 +3053,12 @@ static void handle_invalid_guest_state(struct kvm_vcpu *vcpu,
while (!guest_state_valid(vcpu)) {
err = emulate_instruction(vcpu, kvm_run, 0, 0, 0);
- switch (err) {
- case EMULATE_DONE:
- break;
- case EMULATE_DO_MMIO:
- kvm_report_emulation_failure(vcpu, "mmio");
- /* TODO: Handle MMIO */
- return;
- default:
- kvm_report_emulation_failure(vcpu, "emulation failure");
- return;
+ if (err == EMULATE_DO_MMIO)
+ break;
+
+ if (err != EMULATE_DONE) {
+ kvm_report_emulation_failure(vcpu, "emulation failure");
+ return;
}
if (signal_pending(current))
@@ -2948,8 +3070,10 @@ static void handle_invalid_guest_state(struct kvm_vcpu *vcpu,
local_irq_disable();
preempt_disable();
- /* Guest state should be valid now, no more emulation should be needed */
- vmx->emulation_required = 0;
+ /* Guest state should be valid now except if we need to
+ * emulate an MMIO */
+ if (guest_state_valid(vcpu))
+ vmx->emulation_required = 0;
}
/*
@@ -2996,6 +3120,11 @@ static int kvm_handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
KVMTRACE_3D(VMEXIT, vcpu, exit_reason, (u32)kvm_rip_read(vcpu),
(u32)((u64)kvm_rip_read(vcpu) >> 32), entryexit);
+ /* If we need to emulate an MMIO from handle_invalid_guest_state
+ * we just return 0 */
+ if (vmx->emulation_required && emulate_invalid_guest_state)
+ return 0;
+
/* Access CR3 don't cause VMExit in paging mode, so we need
* to sync with guest real CR3. */
if (vm_need_ept() && is_paging(vcpu)) {
@@ -3012,9 +3141,32 @@ static int kvm_handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
if ((vectoring_info & VECTORING_INFO_VALID_MASK) &&
(exit_reason != EXIT_REASON_EXCEPTION_NMI &&
- exit_reason != EXIT_REASON_EPT_VIOLATION))
- printk(KERN_WARNING "%s: unexpected, valid vectoring info and "
- "exit reason is 0x%x\n", __func__, exit_reason);
+ exit_reason != EXIT_REASON_EPT_VIOLATION &&
+ exit_reason != EXIT_REASON_TASK_SWITCH))
+ printk(KERN_WARNING "%s: unexpected, valid vectoring info "
+ "(0x%x) and exit reason is 0x%x\n",
+ __func__, vectoring_info, exit_reason);
+
+ if (unlikely(!cpu_has_virtual_nmis() && vmx->soft_vnmi_blocked)) {
+ if (vcpu->arch.interrupt_window_open) {
+ vmx->soft_vnmi_blocked = 0;
+ vcpu->arch.nmi_window_open = 1;
+ } else if (vmx->vnmi_blocked_time > 1000000000LL &&
+ vcpu->arch.nmi_pending) {
+ /*
+ * This CPU don't support us in finding the end of an
+ * NMI-blocked window if the guest runs with IRQs
+ * disabled. So we pull the trigger after 1 s of
+ * futile waiting, but inform the user about this.
+ */
+ printk(KERN_WARNING "%s: Breaking out of NMI-blocked "
+ "state on VCPU %d after 1 s timeout\n",
+ __func__, vcpu->vcpu_id);
+ vmx->soft_vnmi_blocked = 0;
+ vmx->vcpu.arch.nmi_window_open = 1;
+ }
+ }
+
if (exit_reason < kvm_vmx_max_exit_handlers
&& kvm_vmx_exit_handlers[exit_reason])
return kvm_vmx_exit_handlers[exit_reason](vcpu, kvm_run);
@@ -3042,51 +3194,6 @@ static void update_tpr_threshold(struct kvm_vcpu *vcpu)
vmcs_write32(TPR_THRESHOLD, (max_irr > tpr) ? tpr >> 4 : max_irr >> 4);
}
-static void enable_irq_window(struct kvm_vcpu *vcpu)
-{
- u32 cpu_based_vm_exec_control;
-
- cpu_based_vm_exec_control = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL);
- cpu_based_vm_exec_control |= CPU_BASED_VIRTUAL_INTR_PENDING;
- vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control);
-}
-
-static void enable_nmi_window(struct kvm_vcpu *vcpu)
-{
- u32 cpu_based_vm_exec_control;
-
- if (!cpu_has_virtual_nmis())
- return;
-
- cpu_based_vm_exec_control = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL);
- cpu_based_vm_exec_control |= CPU_BASED_VIRTUAL_NMI_PENDING;
- vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control);
-}
-
-static int vmx_nmi_enabled(struct kvm_vcpu *vcpu)
-{
- u32 guest_intr = vmcs_read32(GUEST_INTERRUPTIBILITY_INFO);
- return !(guest_intr & (GUEST_INTR_STATE_NMI |
- GUEST_INTR_STATE_MOV_SS |
- GUEST_INTR_STATE_STI));
-}
-
-static int vmx_irq_enabled(struct kvm_vcpu *vcpu)
-{
- u32 guest_intr = vmcs_read32(GUEST_INTERRUPTIBILITY_INFO);
- return (!(guest_intr & (GUEST_INTR_STATE_MOV_SS |
- GUEST_INTR_STATE_STI)) &&
- (vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_IF));
-}
-
-static void enable_intr_window(struct kvm_vcpu *vcpu)
-{
- if (vcpu->arch.nmi_pending)
- enable_nmi_window(vcpu);
- else if (kvm_cpu_has_interrupt(vcpu))
- enable_irq_window(vcpu);
-}
-
static void vmx_complete_interrupts(struct vcpu_vmx *vmx)
{
u32 exit_intr_info;
@@ -3109,7 +3216,9 @@ static void vmx_complete_interrupts(struct vcpu_vmx *vmx)
if (unblock_nmi && vector != DF_VECTOR)
vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO,
GUEST_INTR_STATE_NMI);
- }
+ } else if (unlikely(vmx->soft_vnmi_blocked))
+ vmx->vnmi_blocked_time +=
+ ktime_to_ns(ktime_sub(ktime_get(), vmx->entry_time));
idt_vectoring_info = vmx->idt_vectoring_info;
idtv_info_valid = idt_vectoring_info & VECTORING_INFO_VALID_MASK;
@@ -3147,26 +3256,29 @@ static void vmx_intr_assist(struct kvm_vcpu *vcpu)
{
update_tpr_threshold(vcpu);
- if (cpu_has_virtual_nmis()) {
- if (vcpu->arch.nmi_pending && !vcpu->arch.nmi_injected) {
- if (vcpu->arch.interrupt.pending) {
- enable_nmi_window(vcpu);
- } else if (vmx_nmi_enabled(vcpu)) {
- vcpu->arch.nmi_pending = false;
- vcpu->arch.nmi_injected = true;
- } else {
- enable_intr_window(vcpu);
- return;
- }
- }
- if (vcpu->arch.nmi_injected) {
- vmx_inject_nmi(vcpu);
- enable_intr_window(vcpu);
+ vmx_update_window_states(vcpu);
+
+ if (vcpu->arch.nmi_pending && !vcpu->arch.nmi_injected) {
+ if (vcpu->arch.interrupt.pending) {
+ enable_nmi_window(vcpu);
+ } else if (vcpu->arch.nmi_window_open) {
+ vcpu->arch.nmi_pending = false;
+ vcpu->arch.nmi_injected = true;
+ } else {
+ enable_nmi_window(vcpu);
return;
}
}
+ if (vcpu->arch.nmi_injected) {
+ vmx_inject_nmi(vcpu);
+ if (vcpu->arch.nmi_pending)
+ enable_nmi_window(vcpu);
+ else if (kvm_cpu_has_interrupt(vcpu))
+ enable_irq_window(vcpu);
+ return;
+ }
if (!vcpu->arch.interrupt.pending && kvm_cpu_has_interrupt(vcpu)) {
- if (vmx_irq_enabled(vcpu))
+ if (vcpu->arch.interrupt_window_open)
kvm_queue_interrupt(vcpu, kvm_cpu_get_interrupt(vcpu));
else
enable_irq_window(vcpu);
@@ -3174,6 +3286,8 @@ static void vmx_intr_assist(struct kvm_vcpu *vcpu)
if (vcpu->arch.interrupt.pending) {
vmx_inject_irq(vcpu, vcpu->arch.interrupt.nr);
kvm_timer_intr_post(vcpu, vcpu->arch.interrupt.nr);
+ if (kvm_cpu_has_interrupt(vcpu))
+ enable_irq_window(vcpu);
}
}
@@ -3213,6 +3327,10 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
struct vcpu_vmx *vmx = to_vmx(vcpu);
u32 intr_info;
+ /* Record the guest's net vcpu time for enforced NMI injections. */
+ if (unlikely(!cpu_has_virtual_nmis() && vmx->soft_vnmi_blocked))
+ vmx->entry_time = ktime_get();
+
/* Handle invalid guest state instead of entering VMX */
if (vmx->emulation_required && emulate_invalid_guest_state) {
handle_invalid_guest_state(vcpu, kvm_run);
@@ -3327,9 +3445,7 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
if (vmx->rmode.irq.pending)
fixup_rmode_irq(vmx);
- vcpu->arch.interrupt_window_open =
- (vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) &
- (GUEST_INTR_STATE_STI | GUEST_INTR_STATE_MOV_SS)) == 0;
+ vmx_update_window_states(vcpu);
asm("mov %0, %%ds; mov %0, %%es" : : "r"(__USER_DS));
vmx->launched = 1;
@@ -3337,7 +3453,7 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
intr_info = vmcs_read32(VM_EXIT_INTR_INFO);
/* We need to handle NMIs before interrupts are enabled */
- if ((intr_info & INTR_INFO_INTR_TYPE_MASK) == 0x200 &&
+ if ((intr_info & INTR_INFO_INTR_TYPE_MASK) == INTR_TYPE_NMI_INTR &&
(intr_info & INTR_INFO_VALID_MASK)) {
KVMTRACE_0D(NMI, vcpu, handler);
asm("int $2");
@@ -3455,6 +3571,11 @@ static int get_ept_level(void)
return VMX_EPT_DEFAULT_GAW + 1;
}
+static int vmx_get_mt_mask_shift(void)
+{
+ return VMX_EPT_MT_EPTE_SHIFT;
+}
+
static struct kvm_x86_ops vmx_x86_ops = {
.cpu_has_kvm_support = cpu_has_kvm_support,
.disabled_by_bios = vmx_disabled_by_bios,
@@ -3510,6 +3631,7 @@ static struct kvm_x86_ops vmx_x86_ops = {
.set_tss_addr = vmx_set_tss_addr,
.get_tdp_level = get_ept_level,
+ .get_mt_mask_shift = vmx_get_mt_mask_shift,
};
static int __init vmx_init(void)
@@ -3566,10 +3688,10 @@ static int __init vmx_init(void)
bypass_guest_pf = 0;
kvm_mmu_set_base_ptes(VMX_EPT_READABLE_MASK |
VMX_EPT_WRITABLE_MASK |
- VMX_EPT_DEFAULT_MT << VMX_EPT_MT_EPTE_SHIFT |
VMX_EPT_IGMT_BIT);
kvm_mmu_set_mask_ptes(0ull, 0ull, 0ull, 0ull,
- VMX_EPT_EXECUTABLE_MASK);
+ VMX_EPT_EXECUTABLE_MASK,
+ VMX_EPT_DEFAULT_MT << VMX_EPT_MT_EPTE_SHIFT);
kvm_enable_tdp();
} else
kvm_disable_tdp();
diff --git a/arch/x86/kvm/vmx.h b/arch/x86/kvm/vmx.h
deleted file mode 100644
index ec5edc339da..00000000000
--- a/arch/x86/kvm/vmx.h
+++ /dev/null
@@ -1,359 +0,0 @@
-#ifndef VMX_H
-#define VMX_H
-
-/*
- * vmx.h: VMX Architecture related definitions
- * Copyright (c) 2004, Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, write to the Free Software Foundation, Inc., 59 Temple
- * Place - Suite 330, Boston, MA 02111-1307 USA.
- *
- * A few random additions are:
- * Copyright (C) 2006 Qumranet
- * Avi Kivity <avi@qumranet.com>
- * Yaniv Kamay <yaniv@qumranet.com>
- *
- */
-
-/*
- * Definitions of Primary Processor-Based VM-Execution Controls.
- */
-#define CPU_BASED_VIRTUAL_INTR_PENDING 0x00000004
-#define CPU_BASED_USE_TSC_OFFSETING 0x00000008
-#define CPU_BASED_HLT_EXITING 0x00000080
-#define CPU_BASED_INVLPG_EXITING 0x00000200
-#define CPU_BASED_MWAIT_EXITING 0x00000400
-#define CPU_BASED_RDPMC_EXITING 0x00000800
-#define CPU_BASED_RDTSC_EXITING 0x00001000
-#define CPU_BASED_CR3_LOAD_EXITING 0x00008000
-#define CPU_BASED_CR3_STORE_EXITING 0x00010000
-#define CPU_BASED_CR8_LOAD_EXITING 0x00080000
-#define CPU_BASED_CR8_STORE_EXITING 0x00100000
-#define CPU_BASED_TPR_SHADOW 0x00200000
-#define CPU_BASED_VIRTUAL_NMI_PENDING 0x00400000
-#define CPU_BASED_MOV_DR_EXITING 0x00800000
-#define CPU_BASED_UNCOND_IO_EXITING 0x01000000
-#define CPU_BASED_USE_IO_BITMAPS 0x02000000
-#define CPU_BASED_USE_MSR_BITMAPS 0x10000000
-#define CPU_BASED_MONITOR_EXITING 0x20000000
-#define CPU_BASED_PAUSE_EXITING 0x40000000
-#define CPU_BASED_ACTIVATE_SECONDARY_CONTROLS 0x80000000
-/*
- * Definitions of Secondary Processor-Based VM-Execution Controls.
- */
-#define SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES 0x00000001
-#define SECONDARY_EXEC_ENABLE_EPT 0x00000002
-#define SECONDARY_EXEC_ENABLE_VPID 0x00000020
-#define SECONDARY_EXEC_WBINVD_EXITING 0x00000040
-
-
-#define PIN_BASED_EXT_INTR_MASK 0x00000001
-#define PIN_BASED_NMI_EXITING 0x00000008
-#define PIN_BASED_VIRTUAL_NMIS 0x00000020
-
-#define VM_EXIT_HOST_ADDR_SPACE_SIZE 0x00000200
-#define VM_EXIT_ACK_INTR_ON_EXIT 0x00008000
-
-#define VM_ENTRY_IA32E_MODE 0x00000200
-#define VM_ENTRY_SMM 0x00000400
-#define VM_ENTRY_DEACT_DUAL_MONITOR 0x00000800
-
-/* VMCS Encodings */
-enum vmcs_field {
- VIRTUAL_PROCESSOR_ID = 0x00000000,
- GUEST_ES_SELECTOR = 0x00000800,
- GUEST_CS_SELECTOR = 0x00000802,
- GUEST_SS_SELECTOR = 0x00000804,
- GUEST_DS_SELECTOR = 0x00000806,
- GUEST_FS_SELECTOR = 0x00000808,
- GUEST_GS_SELECTOR = 0x0000080a,
- GUEST_LDTR_SELECTOR = 0x0000080c,
- GUEST_TR_SELECTOR = 0x0000080e,
- HOST_ES_SELECTOR = 0x00000c00,
- HOST_CS_SELECTOR = 0x00000c02,
- HOST_SS_SELECTOR = 0x00000c04,
- HOST_DS_SELECTOR = 0x00000c06,
- HOST_FS_SELECTOR = 0x00000c08,
- HOST_GS_SELECTOR = 0x00000c0a,
- HOST_TR_SELECTOR = 0x00000c0c,
- IO_BITMAP_A = 0x00002000,
- IO_BITMAP_A_HIGH = 0x00002001,
- IO_BITMAP_B = 0x00002002,
- IO_BITMAP_B_HIGH = 0x00002003,
- MSR_BITMAP = 0x00002004,
- MSR_BITMAP_HIGH = 0x00002005,
- VM_EXIT_MSR_STORE_ADDR = 0x00002006,
- VM_EXIT_MSR_STORE_ADDR_HIGH = 0x00002007,
- VM_EXIT_MSR_LOAD_ADDR = 0x00002008,
- VM_EXIT_MSR_LOAD_ADDR_HIGH = 0x00002009,
- VM_ENTRY_MSR_LOAD_ADDR = 0x0000200a,
- VM_ENTRY_MSR_LOAD_ADDR_HIGH = 0x0000200b,
- TSC_OFFSET = 0x00002010,
- TSC_OFFSET_HIGH = 0x00002011,
- VIRTUAL_APIC_PAGE_ADDR = 0x00002012,
- VIRTUAL_APIC_PAGE_ADDR_HIGH = 0x00002013,
- APIC_ACCESS_ADDR = 0x00002014,
- APIC_ACCESS_ADDR_HIGH = 0x00002015,
- EPT_POINTER = 0x0000201a,
- EPT_POINTER_HIGH = 0x0000201b,
- GUEST_PHYSICAL_ADDRESS = 0x00002400,
- GUEST_PHYSICAL_ADDRESS_HIGH = 0x00002401,
- VMCS_LINK_POINTER = 0x00002800,
- VMCS_LINK_POINTER_HIGH = 0x00002801,
- GUEST_IA32_DEBUGCTL = 0x00002802,
- GUEST_IA32_DEBUGCTL_HIGH = 0x00002803,
- GUEST_PDPTR0 = 0x0000280a,
- GUEST_PDPTR0_HIGH = 0x0000280b,
- GUEST_PDPTR1 = 0x0000280c,
- GUEST_PDPTR1_HIGH = 0x0000280d,
- GUEST_PDPTR2 = 0x0000280e,
- GUEST_PDPTR2_HIGH = 0x0000280f,
- GUEST_PDPTR3 = 0x00002810,
- GUEST_PDPTR3_HIGH = 0x00002811,
- PIN_BASED_VM_EXEC_CONTROL = 0x00004000,
- CPU_BASED_VM_EXEC_CONTROL = 0x00004002,
- EXCEPTION_BITMAP = 0x00004004,
- PAGE_FAULT_ERROR_CODE_MASK = 0x00004006,
- PAGE_FAULT_ERROR_CODE_MATCH = 0x00004008,
- CR3_TARGET_COUNT = 0x0000400a,
- VM_EXIT_CONTROLS = 0x0000400c,
- VM_EXIT_MSR_STORE_COUNT = 0x0000400e,
- VM_EXIT_MSR_LOAD_COUNT = 0x00004010,
- VM_ENTRY_CONTROLS = 0x00004012,
- VM_ENTRY_MSR_LOAD_COUNT = 0x00004014,
- VM_ENTRY_INTR_INFO_FIELD = 0x00004016,
- VM_ENTRY_EXCEPTION_ERROR_CODE = 0x00004018,
- VM_ENTRY_INSTRUCTION_LEN = 0x0000401a,
- TPR_THRESHOLD = 0x0000401c,
- SECONDARY_VM_EXEC_CONTROL = 0x0000401e,
- VM_INSTRUCTION_ERROR = 0x00004400,
- VM_EXIT_REASON = 0x00004402,
- VM_EXIT_INTR_INFO = 0x00004404,
- VM_EXIT_INTR_ERROR_CODE = 0x00004406,
- IDT_VECTORING_INFO_FIELD = 0x00004408,
- IDT_VECTORING_ERROR_CODE = 0x0000440a,
- VM_EXIT_INSTRUCTION_LEN = 0x0000440c,
- VMX_INSTRUCTION_INFO = 0x0000440e,
- GUEST_ES_LIMIT = 0x00004800,
- GUEST_CS_LIMIT = 0x00004802,
- GUEST_SS_LIMIT = 0x00004804,
- GUEST_DS_LIMIT = 0x00004806,
- GUEST_FS_LIMIT = 0x00004808,
- GUEST_GS_LIMIT = 0x0000480a,
- GUEST_LDTR_LIMIT = 0x0000480c,
- GUEST_TR_LIMIT = 0x0000480e,
- GUEST_GDTR_LIMIT = 0x00004810,
- GUEST_IDTR_LIMIT = 0x00004812,
- GUEST_ES_AR_BYTES = 0x00004814,
- GUEST_CS_AR_BYTES = 0x00004816,
- GUEST_SS_AR_BYTES = 0x00004818,
- GUEST_DS_AR_BYTES = 0x0000481a,
- GUEST_FS_AR_BYTES = 0x0000481c,
- GUEST_GS_AR_BYTES = 0x0000481e,
- GUEST_LDTR_AR_BYTES = 0x00004820,
- GUEST_TR_AR_BYTES = 0x00004822,
- GUEST_INTERRUPTIBILITY_INFO = 0x00004824,
- GUEST_ACTIVITY_STATE = 0X00004826,
- GUEST_SYSENTER_CS = 0x0000482A,
- HOST_IA32_SYSENTER_CS = 0x00004c00,
- CR0_GUEST_HOST_MASK = 0x00006000,
- CR4_GUEST_HOST_MASK = 0x00006002,
- CR0_READ_SHADOW = 0x00006004,
- CR4_READ_SHADOW = 0x00006006,
- CR3_TARGET_VALUE0 = 0x00006008,
- CR3_TARGET_VALUE1 = 0x0000600a,
- CR3_TARGET_VALUE2 = 0x0000600c,
- CR3_TARGET_VALUE3 = 0x0000600e,
- EXIT_QUALIFICATION = 0x00006400,
- GUEST_LINEAR_ADDRESS = 0x0000640a,
- GUEST_CR0 = 0x00006800,
- GUEST_CR3 = 0x00006802,
- GUEST_CR4 = 0x00006804,
- GUEST_ES_BASE = 0x00006806,
- GUEST_CS_BASE = 0x00006808,
- GUEST_SS_BASE = 0x0000680a,
- GUEST_DS_BASE = 0x0000680c,
- GUEST_FS_BASE = 0x0000680e,
- GUEST_GS_BASE = 0x00006810,
- GUEST_LDTR_BASE = 0x00006812,
- GUEST_TR_BASE = 0x00006814,
- GUEST_GDTR_BASE = 0x00006816,
- GUEST_IDTR_BASE = 0x00006818,
- GUEST_DR7 = 0x0000681a,
- GUEST_RSP = 0x0000681c,
- GUEST_RIP = 0x0000681e,
- GUEST_RFLAGS = 0x00006820,
- GUEST_PENDING_DBG_EXCEPTIONS = 0x00006822,
- GUEST_SYSENTER_ESP = 0x00006824,
- GUEST_SYSENTER_EIP = 0x00006826,
- HOST_CR0 = 0x00006c00,
- HOST_CR3 = 0x00006c02,
- HOST_CR4 = 0x00006c04,
- HOST_FS_BASE = 0x00006c06,
- HOST_GS_BASE = 0x00006c08,
- HOST_TR_BASE = 0x00006c0a,
- HOST_GDTR_BASE = 0x00006c0c,
- HOST_IDTR_BASE = 0x00006c0e,
- HOST_IA32_SYSENTER_ESP = 0x00006c10,
- HOST_IA32_SYSENTER_EIP = 0x00006c12,
- HOST_RSP = 0x00006c14,
- HOST_RIP = 0x00006c16,
-};
-
-#define VMX_EXIT_REASONS_FAILED_VMENTRY 0x80000000
-
-#define EXIT_REASON_EXCEPTION_NMI 0
-#define EXIT_REASON_EXTERNAL_INTERRUPT 1
-#define EXIT_REASON_TRIPLE_FAULT 2
-
-#define EXIT_REASON_PENDING_INTERRUPT 7
-#define EXIT_REASON_NMI_WINDOW 8
-#define EXIT_REASON_TASK_SWITCH 9
-#define EXIT_REASON_CPUID 10
-#define EXIT_REASON_HLT 12
-#define EXIT_REASON_INVLPG 14
-#define EXIT_REASON_RDPMC 15
-#define EXIT_REASON_RDTSC 16
-#define EXIT_REASON_VMCALL 18
-#define EXIT_REASON_VMCLEAR 19
-#define EXIT_REASON_VMLAUNCH 20
-#define EXIT_REASON_VMPTRLD 21
-#define EXIT_REASON_VMPTRST 22
-#define EXIT_REASON_VMREAD 23
-#define EXIT_REASON_VMRESUME 24
-#define EXIT_REASON_VMWRITE 25
-#define EXIT_REASON_VMOFF 26
-#define EXIT_REASON_VMON 27
-#define EXIT_REASON_CR_ACCESS 28
-#define EXIT_REASON_DR_ACCESS 29
-#define EXIT_REASON_IO_INSTRUCTION 30
-#define EXIT_REASON_MSR_READ 31
-#define EXIT_REASON_MSR_WRITE 32
-#define EXIT_REASON_MWAIT_INSTRUCTION 36
-#define EXIT_REASON_TPR_BELOW_THRESHOLD 43
-#define EXIT_REASON_APIC_ACCESS 44
-#define EXIT_REASON_EPT_VIOLATION 48
-#define EXIT_REASON_EPT_MISCONFIG 49
-#define EXIT_REASON_WBINVD 54
-
-/*
- * Interruption-information format
- */
-#define INTR_INFO_VECTOR_MASK 0xff /* 7:0 */
-#define INTR_INFO_INTR_TYPE_MASK 0x700 /* 10:8 */
-#define INTR_INFO_DELIVER_CODE_MASK 0x800 /* 11 */
-#define INTR_INFO_UNBLOCK_NMI 0x1000 /* 12 */
-#define INTR_INFO_VALID_MASK 0x80000000 /* 31 */
-#define INTR_INFO_RESVD_BITS_MASK 0x7ffff000
-
-#define VECTORING_INFO_VECTOR_MASK INTR_INFO_VECTOR_MASK
-#define VECTORING_INFO_TYPE_MASK INTR_INFO_INTR_TYPE_MASK
-#define VECTORING_INFO_DELIVER_CODE_MASK INTR_INFO_DELIVER_CODE_MASK
-#define VECTORING_INFO_VALID_MASK INTR_INFO_VALID_MASK
-
-#define INTR_TYPE_EXT_INTR (0 << 8) /* external interrupt */
-#define INTR_TYPE_NMI_INTR (2 << 8) /* NMI */
-#define INTR_TYPE_EXCEPTION (3 << 8) /* processor exception */
-#define INTR_TYPE_SOFT_INTR (4 << 8) /* software interrupt */
-
-/* GUEST_INTERRUPTIBILITY_INFO flags. */
-#define GUEST_INTR_STATE_STI 0x00000001
-#define GUEST_INTR_STATE_MOV_SS 0x00000002
-#define GUEST_INTR_STATE_SMI 0x00000004
-#define GUEST_INTR_STATE_NMI 0x00000008
-
-/*
- * Exit Qualifications for MOV for Control Register Access
- */
-#define CONTROL_REG_ACCESS_NUM 0x7 /* 2:0, number of control reg.*/
-#define CONTROL_REG_ACCESS_TYPE 0x30 /* 5:4, access type */
-#define CONTROL_REG_ACCESS_REG 0xf00 /* 10:8, general purpose reg. */
-#define LMSW_SOURCE_DATA_SHIFT 16
-#define LMSW_SOURCE_DATA (0xFFFF << LMSW_SOURCE_DATA_SHIFT) /* 16:31 lmsw source */
-#define REG_EAX (0 << 8)
-#define REG_ECX (1 << 8)
-#define REG_EDX (2 << 8)
-#define REG_EBX (3 << 8)
-#define REG_ESP (4 << 8)
-#define REG_EBP (5 << 8)
-#define REG_ESI (6 << 8)
-#define REG_EDI (7 << 8)
-#define REG_R8 (8 << 8)
-#define REG_R9 (9 << 8)
-#define REG_R10 (10 << 8)
-#define REG_R11 (11 << 8)
-#define REG_R12 (12 << 8)
-#define REG_R13 (13 << 8)
-#define REG_R14 (14 << 8)
-#define REG_R15 (15 << 8)
-
-/*
- * Exit Qualifications for MOV for Debug Register Access
- */
-#define DEBUG_REG_ACCESS_NUM 0x7 /* 2:0, number of debug reg. */
-#define DEBUG_REG_ACCESS_TYPE 0x10 /* 4, direction of access */
-#define TYPE_MOV_TO_DR (0 << 4)
-#define TYPE_MOV_FROM_DR (1 << 4)
-#define DEBUG_REG_ACCESS_REG 0xf00 /* 11:8, general purpose reg. */
-
-
-/* segment AR */
-#define SEGMENT_AR_L_MASK (1 << 13)
-
-#define AR_TYPE_ACCESSES_MASK 1
-#define AR_TYPE_READABLE_MASK (1 << 1)
-#define AR_TYPE_WRITEABLE_MASK (1 << 2)
-#define AR_TYPE_CODE_MASK (1 << 3)
-#define AR_TYPE_MASK 0x0f
-#define AR_TYPE_BUSY_64_TSS 11
-#define AR_TYPE_BUSY_32_TSS 11
-#define AR_TYPE_BUSY_16_TSS 3
-#define AR_TYPE_LDT 2
-
-#define AR_UNUSABLE_MASK (1 << 16)
-#define AR_S_MASK (1 << 4)
-#define AR_P_MASK (1 << 7)
-#define AR_L_MASK (1 << 13)
-#define AR_DB_MASK (1 << 14)
-#define AR_G_MASK (1 << 15)
-#define AR_DPL_SHIFT 5
-#define AR_DPL(ar) (((ar) >> AR_DPL_SHIFT) & 3)
-
-#define AR_RESERVD_MASK 0xfffe0f00
-
-#define APIC_ACCESS_PAGE_PRIVATE_MEMSLOT 9
-#define IDENTITY_PAGETABLE_PRIVATE_MEMSLOT 10
-
-#define VMX_NR_VPIDS (1 << 16)
-#define VMX_VPID_EXTENT_SINGLE_CONTEXT 1
-#define VMX_VPID_EXTENT_ALL_CONTEXT 2
-
-#define VMX_EPT_EXTENT_INDIVIDUAL_ADDR 0
-#define VMX_EPT_EXTENT_CONTEXT 1
-#define VMX_EPT_EXTENT_GLOBAL 2
-#define VMX_EPT_EXTENT_INDIVIDUAL_BIT (1ull << 24)
-#define VMX_EPT_EXTENT_CONTEXT_BIT (1ull << 25)
-#define VMX_EPT_EXTENT_GLOBAL_BIT (1ull << 26)
-#define VMX_EPT_DEFAULT_GAW 3
-#define VMX_EPT_MAX_GAW 0x4
-#define VMX_EPT_MT_EPTE_SHIFT 3
-#define VMX_EPT_GAW_EPTP_SHIFT 3
-#define VMX_EPT_DEFAULT_MT 0x6ull
-#define VMX_EPT_READABLE_MASK 0x1ull
-#define VMX_EPT_WRITABLE_MASK 0x2ull
-#define VMX_EPT_EXECUTABLE_MASK 0x4ull
-#define VMX_EPT_IGMT_BIT (1ull << 6)
-
-#define VMX_EPT_IDENTITY_PAGETABLE_ADDR 0xfffbc000ul
-
-#endif
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index f1f8ff2f1fa..0e6aa8141dc 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -39,6 +39,7 @@
#include <asm/uaccess.h>
#include <asm/msr.h>
#include <asm/desc.h>
+#include <asm/mtrr.h>
#define MAX_IO_MSRS 256
#define CR0_RESERVED_BITS \
@@ -86,6 +87,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
{ "halt_wakeup", VCPU_STAT(halt_wakeup) },
{ "hypercalls", VCPU_STAT(hypercalls) },
{ "request_irq", VCPU_STAT(request_irq_exits) },
+ { "request_nmi", VCPU_STAT(request_nmi_exits) },
{ "irq_exits", VCPU_STAT(irq_exits) },
{ "host_state_reload", VCPU_STAT(host_state_reload) },
{ "efer_reload", VCPU_STAT(efer_reload) },
@@ -93,6 +95,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
{ "insn_emulation", VCPU_STAT(insn_emulation) },
{ "insn_emulation_fail", VCPU_STAT(insn_emulation_fail) },
{ "irq_injections", VCPU_STAT(irq_injections) },
+ { "nmi_injections", VCPU_STAT(nmi_injections) },
{ "mmu_shadow_zapped", VM_STAT(mmu_shadow_zapped) },
{ "mmu_pte_write", VM_STAT(mmu_pte_write) },
{ "mmu_pte_updated", VM_STAT(mmu_pte_updated) },
@@ -101,6 +104,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
{ "mmu_recycled", VM_STAT(mmu_recycled) },
{ "mmu_cache_miss", VM_STAT(mmu_cache_miss) },
{ "mmu_unsync", VM_STAT(mmu_unsync) },
+ { "mmu_unsync_global", VM_STAT(mmu_unsync_global) },
{ "remote_tlb_flush", VM_STAT(remote_tlb_flush) },
{ "largepages", VM_STAT(lpages) },
{ NULL }
@@ -312,6 +316,7 @@ void kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
kvm_x86_ops->set_cr0(vcpu, cr0);
vcpu->arch.cr0 = cr0;
+ kvm_mmu_sync_global(vcpu);
kvm_mmu_reset_context(vcpu);
return;
}
@@ -355,6 +360,7 @@ void kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
}
kvm_x86_ops->set_cr4(vcpu, cr4);
vcpu->arch.cr4 = cr4;
+ kvm_mmu_sync_global(vcpu);
kvm_mmu_reset_context(vcpu);
}
EXPORT_SYMBOL_GPL(kvm_set_cr4);
@@ -449,7 +455,7 @@ static u32 msrs_to_save[] = {
MSR_CSTAR, MSR_KERNEL_GS_BASE, MSR_SYSCALL_MASK, MSR_LSTAR,
#endif
MSR_IA32_TIME_STAMP_COUNTER, MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK,
- MSR_IA32_PERF_STATUS,
+ MSR_IA32_PERF_STATUS, MSR_IA32_CR_PAT
};
static unsigned num_msrs_to_save;
@@ -648,10 +654,38 @@ static bool msr_mtrr_valid(unsigned msr)
static int set_msr_mtrr(struct kvm_vcpu *vcpu, u32 msr, u64 data)
{
+ u64 *p = (u64 *)&vcpu->arch.mtrr_state.fixed_ranges;
+
if (!msr_mtrr_valid(msr))
return 1;
- vcpu->arch.mtrr[msr - 0x200] = data;
+ if (msr == MSR_MTRRdefType) {
+ vcpu->arch.mtrr_state.def_type = data;
+ vcpu->arch.mtrr_state.enabled = (data & 0xc00) >> 10;
+ } else if (msr == MSR_MTRRfix64K_00000)
+ p[0] = data;
+ else if (msr == MSR_MTRRfix16K_80000 || msr == MSR_MTRRfix16K_A0000)
+ p[1 + msr - MSR_MTRRfix16K_80000] = data;
+ else if (msr >= MSR_MTRRfix4K_C0000 && msr <= MSR_MTRRfix4K_F8000)
+ p[3 + msr - MSR_MTRRfix4K_C0000] = data;
+ else if (msr == MSR_IA32_CR_PAT)
+ vcpu->arch.pat = data;
+ else { /* Variable MTRRs */
+ int idx, is_mtrr_mask;
+ u64 *pt;
+
+ idx = (msr - 0x200) / 2;
+ is_mtrr_mask = msr - 0x200 - 2 * idx;
+ if (!is_mtrr_mask)
+ pt =
+ (u64 *)&vcpu->arch.mtrr_state.var_ranges[idx].base_lo;
+ else
+ pt =
+ (u64 *)&vcpu->arch.mtrr_state.var_ranges[idx].mask_lo;
+ *pt = data;
+ }
+
+ kvm_mmu_reset_context(vcpu);
return 0;
}
@@ -747,10 +781,37 @@ int kvm_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata)
static int get_msr_mtrr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
{
+ u64 *p = (u64 *)&vcpu->arch.mtrr_state.fixed_ranges;
+
if (!msr_mtrr_valid(msr))
return 1;
- *pdata = vcpu->arch.mtrr[msr - 0x200];
+ if (msr == MSR_MTRRdefType)
+ *pdata = vcpu->arch.mtrr_state.def_type +
+ (vcpu->arch.mtrr_state.enabled << 10);
+ else if (msr == MSR_MTRRfix64K_00000)
+ *pdata = p[0];
+ else if (msr == MSR_MTRRfix16K_80000 || msr == MSR_MTRRfix16K_A0000)
+ *pdata = p[1 + msr - MSR_MTRRfix16K_80000];
+ else if (msr >= MSR_MTRRfix4K_C0000 && msr <= MSR_MTRRfix4K_F8000)
+ *pdata = p[3 + msr - MSR_MTRRfix4K_C0000];
+ else if (msr == MSR_IA32_CR_PAT)
+ *pdata = vcpu->arch.pat;
+ else { /* Variable MTRRs */
+ int idx, is_mtrr_mask;
+ u64 *pt;
+
+ idx = (msr - 0x200) / 2;
+ is_mtrr_mask = msr - 0x200 - 2 * idx;
+ if (!is_mtrr_mask)
+ pt =
+ (u64 *)&vcpu->arch.mtrr_state.var_ranges[idx].base_lo;
+ else
+ pt =
+ (u64 *)&vcpu->arch.mtrr_state.var_ranges[idx].mask_lo;
+ *pdata = *pt;
+ }
+
return 0;
}
@@ -903,7 +964,6 @@ int kvm_dev_ioctl_check_extension(long ext)
case KVM_CAP_IRQCHIP:
case KVM_CAP_HLT:
case KVM_CAP_MMU_SHADOW_CACHE_CONTROL:
- case KVM_CAP_USER_MEMORY:
case KVM_CAP_SET_TSS_ADDR:
case KVM_CAP_EXT_CPUID:
case KVM_CAP_CLOCKSOURCE:
@@ -1188,6 +1248,7 @@ static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
int t, times = entry->eax & 0xff;
entry->flags |= KVM_CPUID_FLAG_STATEFUL_FUNC;
+ entry->flags |= KVM_CPUID_FLAG_STATE_READ_NEXT;
for (t = 1; t < times && *nent < maxnent; ++t) {
do_cpuid_1_ent(&entry[t], function, 0);
entry[t].flags |= KVM_CPUID_FLAG_STATEFUL_FUNC;
@@ -1218,7 +1279,7 @@ static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
/* read more entries until level_type is zero */
for (i = 1; *nent < maxnent; ++i) {
- level_type = entry[i - 1].ecx & 0xff;
+ level_type = entry[i - 1].ecx & 0xff00;
if (!level_type)
break;
do_cpuid_1_ent(&entry[i], function, i);
@@ -1318,6 +1379,15 @@ static int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu,
return 0;
}
+static int kvm_vcpu_ioctl_nmi(struct kvm_vcpu *vcpu)
+{
+ vcpu_load(vcpu);
+ kvm_inject_nmi(vcpu);
+ vcpu_put(vcpu);
+
+ return 0;
+}
+
static int vcpu_ioctl_tpr_access_reporting(struct kvm_vcpu *vcpu,
struct kvm_tpr_access_ctl *tac)
{
@@ -1377,6 +1447,13 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
r = 0;
break;
}
+ case KVM_NMI: {
+ r = kvm_vcpu_ioctl_nmi(vcpu);
+ if (r)
+ goto out;
+ r = 0;
+ break;
+ }
case KVM_SET_CPUID: {
struct kvm_cpuid __user *cpuid_arg = argp;
struct kvm_cpuid cpuid;
@@ -1968,7 +2045,7 @@ int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa,
ret = kvm_write_guest(vcpu->kvm, gpa, val, bytes);
if (ret < 0)
return 0;
- kvm_mmu_pte_write(vcpu, gpa, val, bytes);
+ kvm_mmu_pte_write(vcpu, gpa, val, bytes, 1);
return 1;
}
@@ -2404,8 +2481,6 @@ int kvm_emulate_pio(struct kvm_vcpu *vcpu, struct kvm_run *run, int in,
val = kvm_register_read(vcpu, VCPU_REGS_RAX);
memcpy(vcpu->arch.pio_data, &val, 4);
- kvm_x86_ops->skip_emulated_instruction(vcpu);
-
pio_dev = vcpu_find_pio_dev(vcpu, port, size, !in);
if (pio_dev) {
kernel_pio(pio_dev, vcpu, vcpu->arch.pio_data);
@@ -2541,7 +2616,7 @@ int kvm_arch_init(void *opaque)
kvm_mmu_set_nonpresent_ptes(0ull, 0ull);
kvm_mmu_set_base_ptes(PT_PRESENT_MASK);
kvm_mmu_set_mask_ptes(PT_USER_MASK, PT_ACCESSED_MASK,
- PT_DIRTY_MASK, PT64_NX_MASK, 0);
+ PT_DIRTY_MASK, PT64_NX_MASK, 0, 0);
return 0;
out:
@@ -2729,7 +2804,7 @@ static int move_to_next_stateful_cpuid_entry(struct kvm_vcpu *vcpu, int i)
e->flags &= ~KVM_CPUID_FLAG_STATE_READ_NEXT;
/* when no next entry is found, the current entry[i] is reselected */
- for (j = i + 1; j == i; j = (j + 1) % nent) {
+ for (j = i + 1; ; j = (j + 1) % nent) {
struct kvm_cpuid_entry2 *ej = &vcpu->arch.cpuid_entries[j];
if (ej->function == e->function) {
ej->flags |= KVM_CPUID_FLAG_STATE_READ_NEXT;
@@ -2973,7 +3048,7 @@ static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
pr_debug("vcpu %d received sipi with vector # %x\n",
vcpu->vcpu_id, vcpu->arch.sipi_vector);
kvm_lapic_reset(vcpu);
- r = kvm_x86_ops->vcpu_reset(vcpu);
+ r = kvm_arch_vcpu_reset(vcpu);
if (r)
return r;
vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
@@ -3275,9 +3350,9 @@ static void seg_desct_to_kvm_desct(struct desc_struct *seg_desc, u16 selector,
kvm_desct->padding = 0;
}
-static void get_segment_descritptor_dtable(struct kvm_vcpu *vcpu,
- u16 selector,
- struct descriptor_table *dtable)
+static void get_segment_descriptor_dtable(struct kvm_vcpu *vcpu,
+ u16 selector,
+ struct descriptor_table *dtable)
{
if (selector & 1 << 2) {
struct kvm_segment kvm_seg;
@@ -3302,7 +3377,7 @@ static int load_guest_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector,
struct descriptor_table dtable;
u16 index = selector >> 3;
- get_segment_descritptor_dtable(vcpu, selector, &dtable);
+ get_segment_descriptor_dtable(vcpu, selector, &dtable);
if (dtable.limit < index * 8 + 7) {
kvm_queue_exception_e(vcpu, GP_VECTOR, selector & 0xfffc);
@@ -3321,7 +3396,7 @@ static int save_guest_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector,
struct descriptor_table dtable;
u16 index = selector >> 3;
- get_segment_descritptor_dtable(vcpu, selector, &dtable);
+ get_segment_descriptor_dtable(vcpu, selector, &dtable);
if (dtable.limit < index * 8 + 7)
return 1;
@@ -3900,6 +3975,7 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
/* We do fxsave: this must be aligned. */
BUG_ON((unsigned long)&vcpu->arch.host_fx_image & 0xF);
+ vcpu->arch.mtrr_state.have_fixed = 1;
vcpu_load(vcpu);
r = kvm_arch_vcpu_reset(vcpu);
if (r == 0)
@@ -3925,6 +4001,9 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
int kvm_arch_vcpu_reset(struct kvm_vcpu *vcpu)
{
+ vcpu->arch.nmi_pending = false;
+ vcpu->arch.nmi_injected = false;
+
return kvm_x86_ops->vcpu_reset(vcpu);
}
@@ -4012,6 +4091,7 @@ struct kvm *kvm_arch_create_vm(void)
return ERR_PTR(-ENOMEM);
INIT_LIST_HEAD(&kvm->arch.active_mmu_pages);
+ INIT_LIST_HEAD(&kvm->arch.oos_global_pages);
INIT_LIST_HEAD(&kvm->arch.assigned_dev_head);
/* Reserve bit 0 of irq_sources_bitmap for userspace irq source */
@@ -4048,8 +4128,8 @@ static void kvm_free_vcpus(struct kvm *kvm)
void kvm_arch_destroy_vm(struct kvm *kvm)
{
- kvm_iommu_unmap_guest(kvm);
kvm_free_all_assigned_devices(kvm);
+ kvm_iommu_unmap_guest(kvm);
kvm_free_pit(kvm);
kfree(kvm->arch.vpic);
kfree(kvm->arch.vioapic);
@@ -4127,7 +4207,8 @@ void kvm_arch_flush_shadow(struct kvm *kvm)
int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
{
return vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE
- || vcpu->arch.mp_state == KVM_MP_STATE_SIPI_RECEIVED;
+ || vcpu->arch.mp_state == KVM_MP_STATE_SIPI_RECEIVED
+ || vcpu->arch.nmi_pending;
}
static void vcpu_kick_intr(void *info)
diff --git a/arch/x86/kvm/x86_emulate.c b/arch/x86/kvm/x86_emulate.c
index ea051173b0d..d174db7a337 100644
--- a/arch/x86/kvm/x86_emulate.c
+++ b/arch/x86/kvm/x86_emulate.c
@@ -58,6 +58,7 @@
#define SrcMem32 (4<<4) /* Memory operand (32-bit). */
#define SrcImm (5<<4) /* Immediate operand. */
#define SrcImmByte (6<<4) /* 8-bit sign-extended immediate operand. */
+#define SrcOne (7<<4) /* Implied '1' */
#define SrcMask (7<<4)
/* Generic ModRM decode. */
#define ModRM (1<<7)
@@ -70,17 +71,23 @@
#define Group (1<<14) /* Bits 3:5 of modrm byte extend opcode */
#define GroupDual (1<<15) /* Alternate decoding of mod == 3 */
#define GroupMask 0xff /* Group number stored in bits 0:7 */
+/* Source 2 operand type */
+#define Src2None (0<<29)
+#define Src2CL (1<<29)
+#define Src2ImmByte (2<<29)
+#define Src2One (3<<29)
+#define Src2Mask (7<<29)
enum {
Group1_80, Group1_81, Group1_82, Group1_83,
Group1A, Group3_Byte, Group3, Group4, Group5, Group7,
};
-static u16 opcode_table[256] = {
+static u32 opcode_table[256] = {
/* 0x00 - 0x07 */
ByteOp | DstMem | SrcReg | ModRM, DstMem | SrcReg | ModRM,
ByteOp | DstReg | SrcMem | ModRM, DstReg | SrcMem | ModRM,
- 0, 0, 0, 0,
+ ByteOp | DstAcc | SrcImm, DstAcc | SrcImm, 0, 0,
/* 0x08 - 0x0F */
ByteOp | DstMem | SrcReg | ModRM, DstMem | SrcReg | ModRM,
ByteOp | DstReg | SrcMem | ModRM, DstReg | SrcMem | ModRM,
@@ -195,7 +202,7 @@ static u16 opcode_table[256] = {
ImplicitOps, ImplicitOps, Group | Group4, Group | Group5,
};
-static u16 twobyte_table[256] = {
+static u32 twobyte_table[256] = {
/* 0x00 - 0x0F */
0, Group | GroupDual | Group7, 0, 0, 0, 0, ImplicitOps, 0,
ImplicitOps, ImplicitOps, 0, 0, 0, ImplicitOps | ModRM, 0, 0,
@@ -230,9 +237,14 @@ static u16 twobyte_table[256] = {
/* 0x90 - 0x9F */
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
/* 0xA0 - 0xA7 */
- 0, 0, 0, DstMem | SrcReg | ModRM | BitOp, 0, 0, 0, 0,
+ 0, 0, 0, DstMem | SrcReg | ModRM | BitOp,
+ DstMem | SrcReg | Src2ImmByte | ModRM,
+ DstMem | SrcReg | Src2CL | ModRM, 0, 0,
/* 0xA8 - 0xAF */
- 0, 0, 0, DstMem | SrcReg | ModRM | BitOp, 0, 0, ModRM, 0,
+ 0, 0, 0, DstMem | SrcReg | ModRM | BitOp,
+ DstMem | SrcReg | Src2ImmByte | ModRM,
+ DstMem | SrcReg | Src2CL | ModRM,
+ ModRM, 0,
/* 0xB0 - 0xB7 */
ByteOp | DstMem | SrcReg | ModRM, DstMem | SrcReg | ModRM, 0,
DstMem | SrcReg | ModRM | BitOp,
@@ -253,7 +265,7 @@ static u16 twobyte_table[256] = {
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
};
-static u16 group_table[] = {
+static u32 group_table[] = {
[Group1_80*8] =
ByteOp | DstMem | SrcImm | ModRM, ByteOp | DstMem | SrcImm | ModRM,
ByteOp | DstMem | SrcImm | ModRM, ByteOp | DstMem | SrcImm | ModRM,
@@ -297,9 +309,9 @@ static u16 group_table[] = {
SrcMem16 | ModRM | Mov, SrcMem | ModRM | ByteOp,
};
-static u16 group2_table[] = {
+static u32 group2_table[] = {
[Group7*8] =
- SrcNone | ModRM, 0, 0, 0,
+ SrcNone | ModRM, 0, 0, SrcNone | ModRM,
SrcNone | ModRM | DstMem | Mov, 0,
SrcMem16 | ModRM | Mov, 0,
};
@@ -359,49 +371,48 @@ static u16 group2_table[] = {
"andl %"_msk",%"_LO32 _tmp"; " \
"orl %"_LO32 _tmp",%"_sav"; "
+#ifdef CONFIG_X86_64
+#define ON64(x) x
+#else
+#define ON64(x)
+#endif
+
+#define ____emulate_2op(_op, _src, _dst, _eflags, _x, _y, _suffix) \
+ do { \
+ __asm__ __volatile__ ( \
+ _PRE_EFLAGS("0", "4", "2") \
+ _op _suffix " %"_x"3,%1; " \
+ _POST_EFLAGS("0", "4", "2") \
+ : "=m" (_eflags), "=m" ((_dst).val), \
+ "=&r" (_tmp) \
+ : _y ((_src).val), "i" (EFLAGS_MASK)); \
+ } while (0)
+
+
/* Raw emulation: instruction has two explicit operands. */
#define __emulate_2op_nobyte(_op,_src,_dst,_eflags,_wx,_wy,_lx,_ly,_qx,_qy) \
- do { \
- unsigned long _tmp; \
- \
- switch ((_dst).bytes) { \
- case 2: \
- __asm__ __volatile__ ( \
- _PRE_EFLAGS("0", "4", "2") \
- _op"w %"_wx"3,%1; " \
- _POST_EFLAGS("0", "4", "2") \
- : "=m" (_eflags), "=m" ((_dst).val), \
- "=&r" (_tmp) \
- : _wy ((_src).val), "i" (EFLAGS_MASK)); \
- break; \
- case 4: \
- __asm__ __volatile__ ( \
- _PRE_EFLAGS("0", "4", "2") \
- _op"l %"_lx"3,%1; " \
- _POST_EFLAGS("0", "4", "2") \
- : "=m" (_eflags), "=m" ((_dst).val), \
- "=&r" (_tmp) \
- : _ly ((_src).val), "i" (EFLAGS_MASK)); \
- break; \
- case 8: \
- __emulate_2op_8byte(_op, _src, _dst, \
- _eflags, _qx, _qy); \
- break; \
- } \
+ do { \
+ unsigned long _tmp; \
+ \
+ switch ((_dst).bytes) { \
+ case 2: \
+ ____emulate_2op(_op,_src,_dst,_eflags,_wx,_wy,"w"); \
+ break; \
+ case 4: \
+ ____emulate_2op(_op,_src,_dst,_eflags,_lx,_ly,"l"); \
+ break; \
+ case 8: \
+ ON64(____emulate_2op(_op,_src,_dst,_eflags,_qx,_qy,"q")); \
+ break; \
+ } \
} while (0)
#define __emulate_2op(_op,_src,_dst,_eflags,_bx,_by,_wx,_wy,_lx,_ly,_qx,_qy) \
do { \
- unsigned long __tmp; \
+ unsigned long _tmp; \
switch ((_dst).bytes) { \
case 1: \
- __asm__ __volatile__ ( \
- _PRE_EFLAGS("0", "4", "2") \
- _op"b %"_bx"3,%1; " \
- _POST_EFLAGS("0", "4", "2") \
- : "=m" (_eflags), "=m" ((_dst).val), \
- "=&r" (__tmp) \
- : _by ((_src).val), "i" (EFLAGS_MASK)); \
+ ____emulate_2op(_op,_src,_dst,_eflags,_bx,_by,"b"); \
break; \
default: \
__emulate_2op_nobyte(_op, _src, _dst, _eflags, \
@@ -425,71 +436,68 @@ static u16 group2_table[] = {
__emulate_2op_nobyte(_op, _src, _dst, _eflags, \
"w", "r", _LO32, "r", "", "r")
-/* Instruction has only one explicit operand (no source operand). */
-#define emulate_1op(_op, _dst, _eflags) \
- do { \
- unsigned long _tmp; \
- \
- switch ((_dst).bytes) { \
- case 1: \
- __asm__ __volatile__ ( \
- _PRE_EFLAGS("0", "3", "2") \
- _op"b %1; " \
- _POST_EFLAGS("0", "3", "2") \
- : "=m" (_eflags), "=m" ((_dst).val), \
- "=&r" (_tmp) \
- : "i" (EFLAGS_MASK)); \
- break; \
- case 2: \
- __asm__ __volatile__ ( \
- _PRE_EFLAGS("0", "3", "2") \
- _op"w %1; " \
- _POST_EFLAGS("0", "3", "2") \
- : "=m" (_eflags), "=m" ((_dst).val), \
- "=&r" (_tmp) \
- : "i" (EFLAGS_MASK)); \
- break; \
- case 4: \
- __asm__ __volatile__ ( \
- _PRE_EFLAGS("0", "3", "2") \
- _op"l %1; " \
- _POST_EFLAGS("0", "3", "2") \
- : "=m" (_eflags), "=m" ((_dst).val), \
- "=&r" (_tmp) \
- : "i" (EFLAGS_MASK)); \
- break; \
- case 8: \
- __emulate_1op_8byte(_op, _dst, _eflags); \
- break; \
- } \
+/* Instruction has three operands and one operand is stored in ECX register */
+#define __emulate_2op_cl(_op, _cl, _src, _dst, _eflags, _suffix, _type) \
+ do { \
+ unsigned long _tmp; \
+ _type _clv = (_cl).val; \
+ _type _srcv = (_src).val; \
+ _type _dstv = (_dst).val; \
+ \
+ __asm__ __volatile__ ( \
+ _PRE_EFLAGS("0", "5", "2") \
+ _op _suffix " %4,%1 \n" \
+ _POST_EFLAGS("0", "5", "2") \
+ : "=m" (_eflags), "+r" (_dstv), "=&r" (_tmp) \
+ : "c" (_clv) , "r" (_srcv), "i" (EFLAGS_MASK) \
+ ); \
+ \
+ (_cl).val = (unsigned long) _clv; \
+ (_src).val = (unsigned long) _srcv; \
+ (_dst).val = (unsigned long) _dstv; \
} while (0)
-/* Emulate an instruction with quadword operands (x86/64 only). */
-#if defined(CONFIG_X86_64)
-#define __emulate_2op_8byte(_op, _src, _dst, _eflags, _qx, _qy) \
- do { \
- __asm__ __volatile__ ( \
- _PRE_EFLAGS("0", "4", "2") \
- _op"q %"_qx"3,%1; " \
- _POST_EFLAGS("0", "4", "2") \
- : "=m" (_eflags), "=m" ((_dst).val), "=&r" (_tmp) \
- : _qy ((_src).val), "i" (EFLAGS_MASK)); \
+#define emulate_2op_cl(_op, _cl, _src, _dst, _eflags) \
+ do { \
+ switch ((_dst).bytes) { \
+ case 2: \
+ __emulate_2op_cl(_op, _cl, _src, _dst, _eflags, \
+ "w", unsigned short); \
+ break; \
+ case 4: \
+ __emulate_2op_cl(_op, _cl, _src, _dst, _eflags, \
+ "l", unsigned int); \
+ break; \
+ case 8: \
+ ON64(__emulate_2op_cl(_op, _cl, _src, _dst, _eflags, \
+ "q", unsigned long)); \
+ break; \
+ } \
} while (0)
-#define __emulate_1op_8byte(_op, _dst, _eflags) \
- do { \
- __asm__ __volatile__ ( \
- _PRE_EFLAGS("0", "3", "2") \
- _op"q %1; " \
- _POST_EFLAGS("0", "3", "2") \
- : "=m" (_eflags), "=m" ((_dst).val), "=&r" (_tmp) \
- : "i" (EFLAGS_MASK)); \
+#define __emulate_1op(_op, _dst, _eflags, _suffix) \
+ do { \
+ unsigned long _tmp; \
+ \
+ __asm__ __volatile__ ( \
+ _PRE_EFLAGS("0", "3", "2") \
+ _op _suffix " %1; " \
+ _POST_EFLAGS("0", "3", "2") \
+ : "=m" (_eflags), "+m" ((_dst).val), \
+ "=&r" (_tmp) \
+ : "i" (EFLAGS_MASK)); \
} while (0)
-#elif defined(__i386__)
-#define __emulate_2op_8byte(_op, _src, _dst, _eflags, _qx, _qy)
-#define __emulate_1op_8byte(_op, _dst, _eflags)
-#endif /* __i386__ */
+/* Instruction has only one explicit operand (no source operand). */
+#define emulate_1op(_op, _dst, _eflags) \
+ do { \
+ switch ((_dst).bytes) { \
+ case 1: __emulate_1op(_op, _dst, _eflags, "b"); break; \
+ case 2: __emulate_1op(_op, _dst, _eflags, "w"); break; \
+ case 4: __emulate_1op(_op, _dst, _eflags, "l"); break; \
+ case 8: ON64(__emulate_1op(_op, _dst, _eflags, "q")); break; \
+ } \
+ } while (0)
/* Fetch next part of the instruction being emulated. */
#define insn_fetch(_type, _size, _eip) \
@@ -1041,6 +1049,33 @@ done_prefixes:
c->src.bytes = 1;
c->src.val = insn_fetch(s8, 1, c->eip);
break;
+ case SrcOne:
+ c->src.bytes = 1;
+ c->src.val = 1;
+ break;
+ }
+
+ /*
+ * Decode and fetch the second source operand: register, memory
+ * or immediate.
+ */
+ switch (c->d & Src2Mask) {
+ case Src2None:
+ break;
+ case Src2CL:
+ c->src2.bytes = 1;
+ c->src2.val = c->regs[VCPU_REGS_RCX] & 0x8;
+ break;
+ case Src2ImmByte:
+ c->src2.type = OP_IMM;
+ c->src2.ptr = (unsigned long *)c->eip;
+ c->src2.bytes = 1;
+ c->src2.val = insn_fetch(u8, 1, c->eip);
+ break;
+ case Src2One:
+ c->src2.bytes = 1;
+ c->src2.val = 1;
+ break;
}
/* Decode and fetch the destination operand: register or memory. */
@@ -1100,20 +1135,33 @@ static inline void emulate_push(struct x86_emulate_ctxt *ctxt)
c->regs[VCPU_REGS_RSP]);
}
-static inline int emulate_grp1a(struct x86_emulate_ctxt *ctxt,
- struct x86_emulate_ops *ops)
+static int emulate_pop(struct x86_emulate_ctxt *ctxt,
+ struct x86_emulate_ops *ops)
{
struct decode_cache *c = &ctxt->decode;
int rc;
- rc = ops->read_std(register_address(c, ss_base(ctxt),
- c->regs[VCPU_REGS_RSP]),
- &c->dst.val, c->dst.bytes, ctxt->vcpu);
+ rc = ops->read_emulated(register_address(c, ss_base(ctxt),
+ c->regs[VCPU_REGS_RSP]),
+ &c->src.val, c->src.bytes, ctxt->vcpu);
if (rc != 0)
return rc;
- register_address_increment(c, &c->regs[VCPU_REGS_RSP], c->dst.bytes);
+ register_address_increment(c, &c->regs[VCPU_REGS_RSP], c->src.bytes);
+ return rc;
+}
+
+static inline int emulate_grp1a(struct x86_emulate_ctxt *ctxt,
+ struct x86_emulate_ops *ops)
+{
+ struct decode_cache *c = &ctxt->decode;
+ int rc;
+ c->src.bytes = c->dst.bytes;
+ rc = emulate_pop(ctxt, ops);
+ if (rc != 0)
+ return rc;
+ c->dst.val = c->src.val;
return 0;
}
@@ -1415,24 +1463,15 @@ special_insn:
emulate_1op("dec", c->dst, ctxt->eflags);
break;
case 0x50 ... 0x57: /* push reg */
- c->dst.type = OP_MEM;
- c->dst.bytes = c->op_bytes;
- c->dst.val = c->src.val;
- register_address_increment(c, &c->regs[VCPU_REGS_RSP],
- -c->op_bytes);
- c->dst.ptr = (void *) register_address(
- c, ss_base(ctxt), c->regs[VCPU_REGS_RSP]);
+ emulate_push(ctxt);
break;
case 0x58 ... 0x5f: /* pop reg */
pop_instruction:
- if ((rc = ops->read_std(register_address(c, ss_base(ctxt),
- c->regs[VCPU_REGS_RSP]), c->dst.ptr,
- c->op_bytes, ctxt->vcpu)) != 0)
+ c->src.bytes = c->op_bytes;
+ rc = emulate_pop(ctxt, ops);
+ if (rc != 0)
goto done;
-
- register_address_increment(c, &c->regs[VCPU_REGS_RSP],
- c->op_bytes);
- c->dst.type = OP_NONE; /* Disable writeback. */
+ c->dst.val = c->src.val;
break;
case 0x63: /* movsxd */
if (ctxt->mode != X86EMUL_MODE_PROT64)
@@ -1591,7 +1630,9 @@ special_insn:
emulate_push(ctxt);
break;
case 0x9d: /* popf */
+ c->dst.type = OP_REG;
c->dst.ptr = (unsigned long *) &ctxt->eflags;
+ c->dst.bytes = c->op_bytes;
goto pop_instruction;
case 0xa0 ... 0xa1: /* mov */
c->dst.ptr = (unsigned long *)&c->regs[VCPU_REGS_RAX];
@@ -1689,7 +1730,9 @@ special_insn:
emulate_grp2(ctxt);
break;
case 0xc3: /* ret */
+ c->dst.type = OP_REG;
c->dst.ptr = &c->eip;
+ c->dst.bytes = c->op_bytes;
goto pop_instruction;
case 0xc6 ... 0xc7: /* mov (sole member of Grp11) */
mov:
@@ -1778,7 +1821,7 @@ special_insn:
c->eip = saved_eip;
goto cannot_emulate;
}
- return 0;
+ break;
case 0xf4: /* hlt */
ctxt->vcpu->arch.halt_request = 1;
break;
@@ -1999,12 +2042,20 @@ twobyte_insn:
c->src.val &= (c->dst.bytes << 3) - 1;
emulate_2op_SrcV_nobyte("bt", c->src, c->dst, ctxt->eflags);
break;
+ case 0xa4: /* shld imm8, r, r/m */
+ case 0xa5: /* shld cl, r, r/m */
+ emulate_2op_cl("shld", c->src2, c->src, c->dst, ctxt->eflags);
+ break;
case 0xab:
bts: /* bts */
/* only subword offset */
c->src.val &= (c->dst.bytes << 3) - 1;
emulate_2op_SrcV_nobyte("bts", c->src, c->dst, ctxt->eflags);
break;
+ case 0xac: /* shrd imm8, r, r/m */
+ case 0xad: /* shrd cl, r, r/m */
+ emulate_2op_cl("shrd", c->src2, c->src, c->dst, ctxt->eflags);
+ break;
case 0xae: /* clflush */
break;
case 0xb0 ... 0xb1: /* cmpxchg */
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2024-12-22 20:31:37 +0000