aboutsummaryrefslogtreecommitdiff
path: root/arch/x86/kvm
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kvm')
-rw-r--r--arch/x86/kvm/emulate.c5
-rw-r--r--arch/x86/kvm/i8254.c18
-rw-r--r--arch/x86/kvm/lapic.c48
-rw-r--r--arch/x86/kvm/lapic.h4
-rw-r--r--arch/x86/kvm/mmu.c12
-rw-r--r--arch/x86/kvm/paging_tmpl.h8
-rw-r--r--arch/x86/kvm/svm.c6
-rw-r--r--arch/x86/kvm/vmx.c13
-rw-r--r--arch/x86/kvm/x86.c45
-rw-r--r--arch/x86/kvm/x86.h2
10 files changed, 90 insertions, 71 deletions
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 5953dcea752..5484d54582c 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -4207,7 +4207,10 @@ static int decode_operand(struct x86_emulate_ctxt *ctxt, struct operand *op,
case OpMem8:
ctxt->memop.bytes = 1;
if (ctxt->memop.type == OP_REG) {
- ctxt->memop.addr.reg = decode_register(ctxt, ctxt->modrm_rm, 1);
+ int highbyte_regs = ctxt->rex_prefix == 0;
+
+ ctxt->memop.addr.reg = decode_register(ctxt, ctxt->modrm_rm,
+ highbyte_regs);
fetch_register_operand(&ctxt->memop);
}
goto mem_common;
diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c
index 412a5aa0ef9..518d86471b7 100644
--- a/arch/x86/kvm/i8254.c
+++ b/arch/x86/kvm/i8254.c
@@ -37,6 +37,7 @@
#include "irq.h"
#include "i8254.h"
+#include "x86.h"
#ifndef CONFIG_X86_64
#define mod_64(x, y) ((x) - (y) * div64_u64(x, y))
@@ -349,6 +350,23 @@ static void create_pit_timer(struct kvm *kvm, u32 val, int is_period)
atomic_set(&ps->pending, 0);
ps->irq_ack = 1;
+ /*
+ * Do not allow the guest to program periodic timers with small
+ * interval, since the hrtimers are not throttled by the host
+ * scheduler.
+ */
+ if (ps->is_periodic) {
+ s64 min_period = min_timer_period_us * 1000LL;
+
+ if (ps->period < min_period) {
+ pr_info_ratelimited(
+ "kvm: requested %lld ns "
+ "i8254 timer period limited to %lld ns\n",
+ ps->period, min_period);
+ ps->period = min_period;
+ }
+ }
+
hrtimer_start(&ps->timer, ktime_add_ns(ktime_get(), interval),
HRTIMER_MODE_ABS);
}
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 0eee2c8b64d..61d9fed5eb3 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -71,9 +71,6 @@
#define VEC_POS(v) ((v) & (32 - 1))
#define REG_POS(v) (((v) >> 5) << 4)
-static unsigned int min_timer_period_us = 500;
-module_param(min_timer_period_us, uint, S_IRUGO | S_IWUSR);
-
static inline void apic_set_reg(struct kvm_lapic *apic, int reg_off, u32 val)
{
*((u32 *) (apic->regs + reg_off)) = val;
@@ -153,6 +150,8 @@ static inline int kvm_apic_id(struct kvm_lapic *apic)
return (kvm_apic_get_reg(apic, APIC_ID) >> 24) & 0xff;
}
+#define KVM_X2APIC_CID_BITS 0
+
static void recalculate_apic_map(struct kvm *kvm)
{
struct kvm_apic_map *new, *old = NULL;
@@ -190,7 +189,8 @@ static void recalculate_apic_map(struct kvm *kvm)
if (apic_x2apic_mode(apic)) {
new->ldr_bits = 32;
new->cid_shift = 16;
- new->cid_mask = new->lid_mask = 0xffff;
+ new->cid_mask = (1 << KVM_X2APIC_CID_BITS) - 1;
+ new->lid_mask = 0xffff;
} else if (kvm_apic_sw_enabled(apic) &&
!new->cid_mask /* flat mode */ &&
kvm_apic_get_reg(apic, APIC_DFR) == APIC_DFR_CLUSTER) {
@@ -855,7 +855,8 @@ static u32 apic_get_tmcct(struct kvm_lapic *apic)
ASSERT(apic != NULL);
/* if initial count is 0, current count should also be 0 */
- if (kvm_apic_get_reg(apic, APIC_TMICT) == 0)
+ if (kvm_apic_get_reg(apic, APIC_TMICT) == 0 ||
+ apic->lapic_timer.period == 0)
return 0;
remaining = hrtimer_get_remaining(&apic->lapic_timer.timer);
@@ -1360,8 +1361,12 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value)
return;
}
+ if (!kvm_vcpu_is_bsp(apic->vcpu))
+ value &= ~MSR_IA32_APICBASE_BSP;
+ vcpu->arch.apic_base = value;
+
/* update jump label if enable bit changes */
- if ((vcpu->arch.apic_base ^ value) & MSR_IA32_APICBASE_ENABLE) {
+ if ((old_value ^ value) & MSR_IA32_APICBASE_ENABLE) {
if (value & MSR_IA32_APICBASE_ENABLE)
static_key_slow_dec_deferred(&apic_hw_disabled);
else
@@ -1369,10 +1374,6 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value)
recalculate_apic_map(vcpu->kvm);
}
- if (!kvm_vcpu_is_bsp(apic->vcpu))
- value &= ~MSR_IA32_APICBASE_BSP;
-
- vcpu->arch.apic_base = value;
if ((old_value ^ value) & X2APIC_ENABLE) {
if (value & X2APIC_ENABLE) {
u32 id = kvm_apic_id(apic);
@@ -1705,7 +1706,6 @@ static void apic_sync_pv_eoi_from_guest(struct kvm_vcpu *vcpu,
void kvm_lapic_sync_from_vapic(struct kvm_vcpu *vcpu)
{
u32 data;
- void *vapic;
if (test_bit(KVM_APIC_PV_EOI_PENDING, &vcpu->arch.apic_attention))
apic_sync_pv_eoi_from_guest(vcpu, vcpu->arch.apic);
@@ -1713,9 +1713,8 @@ void kvm_lapic_sync_from_vapic(struct kvm_vcpu *vcpu)
if (!test_bit(KVM_APIC_CHECK_VAPIC, &vcpu->arch.apic_attention))
return;
- vapic = kmap_atomic(vcpu->arch.apic->vapic_page);
- data = *(u32 *)(vapic + offset_in_page(vcpu->arch.apic->vapic_addr));
- kunmap_atomic(vapic);
+ kvm_read_guest_cached(vcpu->kvm, &vcpu->arch.apic->vapic_cache, &data,
+ sizeof(u32));
apic_set_tpr(vcpu->arch.apic, data & 0xff);
}
@@ -1751,7 +1750,6 @@ void kvm_lapic_sync_to_vapic(struct kvm_vcpu *vcpu)
u32 data, tpr;
int max_irr, max_isr;
struct kvm_lapic *apic = vcpu->arch.apic;
- void *vapic;
apic_sync_pv_eoi_to_guest(vcpu, apic);
@@ -1767,18 +1765,24 @@ void kvm_lapic_sync_to_vapic(struct kvm_vcpu *vcpu)
max_isr = 0;
data = (tpr & 0xff) | ((max_isr & 0xf0) << 8) | (max_irr << 24);
- vapic = kmap_atomic(vcpu->arch.apic->vapic_page);
- *(u32 *)(vapic + offset_in_page(vcpu->arch.apic->vapic_addr)) = data;
- kunmap_atomic(vapic);
+ kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.apic->vapic_cache, &data,
+ sizeof(u32));
}
-void kvm_lapic_set_vapic_addr(struct kvm_vcpu *vcpu, gpa_t vapic_addr)
+int kvm_lapic_set_vapic_addr(struct kvm_vcpu *vcpu, gpa_t vapic_addr)
{
- vcpu->arch.apic->vapic_addr = vapic_addr;
- if (vapic_addr)
+ if (vapic_addr) {
+ if (kvm_gfn_to_hva_cache_init(vcpu->kvm,
+ &vcpu->arch.apic->vapic_cache,
+ vapic_addr, sizeof(u32)))
+ return -EINVAL;
__set_bit(KVM_APIC_CHECK_VAPIC, &vcpu->arch.apic_attention);
- else
+ } else {
__clear_bit(KVM_APIC_CHECK_VAPIC, &vcpu->arch.apic_attention);
+ }
+
+ vcpu->arch.apic->vapic_addr = vapic_addr;
+ return 0;
}
int kvm_x2apic_msr_write(struct kvm_vcpu *vcpu, u32 msr, u64 data)
diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h
index c730ac9fe80..c8b0d0d2da5 100644
--- a/arch/x86/kvm/lapic.h
+++ b/arch/x86/kvm/lapic.h
@@ -34,7 +34,7 @@ struct kvm_lapic {
*/
void *regs;
gpa_t vapic_addr;
- struct page *vapic_page;
+ struct gfn_to_hva_cache vapic_cache;
unsigned long pending_events;
unsigned int sipi_vector;
};
@@ -76,7 +76,7 @@ void kvm_set_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu, u64 data);
void kvm_apic_write_nodecode(struct kvm_vcpu *vcpu, u32 offset);
void kvm_apic_set_eoi_accelerated(struct kvm_vcpu *vcpu, int vector);
-void kvm_lapic_set_vapic_addr(struct kvm_vcpu *vcpu, gpa_t vapic_addr);
+int kvm_lapic_set_vapic_addr(struct kvm_vcpu *vcpu, gpa_t vapic_addr);
void kvm_lapic_sync_from_vapic(struct kvm_vcpu *vcpu);
void kvm_lapic_sync_to_vapic(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 004cc87b781..711c649f80b 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -2585,6 +2585,9 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write,
int emulate = 0;
gfn_t pseudo_gfn;
+ if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
+ return 0;
+
for_each_shadow_entry(vcpu, (u64)gfn << PAGE_SHIFT, iterator) {
if (iterator.level == level) {
mmu_set_spte(vcpu, iterator.sptep, ACC_ALL,
@@ -2748,6 +2751,9 @@ static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level,
bool ret = false;
u64 spte = 0ull;
+ if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
+ return false;
+
if (!page_fault_can_be_fast(vcpu, error_code))
return false;
@@ -3139,6 +3145,9 @@ static u64 walk_shadow_page_get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr)
struct kvm_shadow_walk_iterator iterator;
u64 spte = 0ull;
+ if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
+ return spte;
+
walk_shadow_page_lockless_begin(vcpu);
for_each_shadow_entry_lockless(vcpu, addr, iterator, spte)
if (!is_shadow_present_pte(spte))
@@ -4329,6 +4338,9 @@ int kvm_mmu_get_spte_hierarchy(struct kvm_vcpu *vcpu, u64 addr, u64 sptes[4])
u64 spte;
int nr_sptes = 0;
+ if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
+ return nr_sptes;
+
walk_shadow_page_lockless_begin(vcpu);
for_each_shadow_entry_lockless(vcpu, addr, iterator, spte) {
sptes[iterator.level-1] = spte;
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index da20860b457..7e6090e1323 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -423,6 +423,9 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
if (FNAME(gpte_changed)(vcpu, gw, top_level))
goto out_gpte_changed;
+ if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
+ goto out_gpte_changed;
+
for (shadow_walk_init(&it, vcpu, addr);
shadow_walk_okay(&it) && it.level > gw->level;
shadow_walk_next(&it)) {
@@ -671,6 +674,11 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva)
*/
mmu_topup_memory_caches(vcpu);
+ if (!VALID_PAGE(vcpu->arch.mmu.root_hpa)) {
+ WARN_ON(1);
+ return;
+ }
+
spin_lock(&vcpu->kvm->mmu_lock);
for_each_shadow_entry(vcpu, gva, iterator) {
level = iterator.level;
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index a14a6eaf871..765210d4d92 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -2985,10 +2985,8 @@ static int cr8_write_interception(struct vcpu_svm *svm)
u8 cr8_prev = kvm_get_cr8(&svm->vcpu);
/* instruction emulation calls kvm_set_cr8() */
r = cr_interception(svm);
- if (irqchip_in_kernel(svm->vcpu.kvm)) {
- clr_cr_intercept(svm, INTERCEPT_CR8_WRITE);
+ if (irqchip_in_kernel(svm->vcpu.kvm))
return r;
- }
if (cr8_prev <= kvm_get_cr8(&svm->vcpu))
return r;
kvm_run->exit_reason = KVM_EXIT_SET_TPR;
@@ -3550,6 +3548,8 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr)
if (is_guest_mode(vcpu) && (vcpu->arch.hflags & HF_VINTR_MASK))
return;
+ clr_cr_intercept(svm, INTERCEPT_CR8_WRITE);
+
if (irr == -1)
return;
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 260a9193955..7cdafb6dc70 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -3399,15 +3399,22 @@ static void vmx_get_segment(struct kvm_vcpu *vcpu,
var->limit = vmx_read_guest_seg_limit(vmx, seg);
var->selector = vmx_read_guest_seg_selector(vmx, seg);
ar = vmx_read_guest_seg_ar(vmx, seg);
+ var->unusable = (ar >> 16) & 1;
var->type = ar & 15;
var->s = (ar >> 4) & 1;
var->dpl = (ar >> 5) & 3;
- var->present = (ar >> 7) & 1;
+ /*
+ * Some userspaces do not preserve unusable property. Since usable
+ * segment has to be present according to VMX spec we can use present
+ * property to amend userspace bug by making unusable segment always
+ * nonpresent. vmx_segment_access_rights() already marks nonpresent
+ * segment as unusable.
+ */
+ var->present = !var->unusable;
var->avl = (ar >> 12) & 1;
var->l = (ar >> 13) & 1;
var->db = (ar >> 14) & 1;
var->g = (ar >> 15) & 1;
- var->unusable = (ar >> 16) & 1;
}
static u64 vmx_get_segment_base(struct kvm_vcpu *vcpu, int seg)
@@ -7126,8 +7133,8 @@ static void vmx_free_vcpu(struct kvm_vcpu *vcpu)
struct vcpu_vmx *vmx = to_vmx(vcpu);
free_vpid(vmx);
- free_nested(vmx);
free_loaded_vmcs(vmx->loaded_vmcs);
+ free_nested(vmx);
kfree(vmx->guest_msrs);
kvm_vcpu_uninit(vcpu);
kmem_cache_free(kvm_vcpu_cache, vmx);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index e8ba99c3418..1be0a9e75d1 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -94,6 +94,9 @@ EXPORT_SYMBOL_GPL(kvm_x86_ops);
static bool ignore_msrs = 0;
module_param(ignore_msrs, bool, S_IRUGO | S_IWUSR);
+unsigned int min_timer_period_us = 500;
+module_param(min_timer_period_us, uint, S_IRUGO | S_IWUSR);
+
bool kvm_has_tsc_control;
EXPORT_SYMBOL_GPL(kvm_has_tsc_control);
u32 kvm_max_guest_tsc_khz;
@@ -3138,8 +3141,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
r = -EFAULT;
if (copy_from_user(&va, argp, sizeof va))
goto out;
- r = 0;
- kvm_lapic_set_vapic_addr(vcpu, va.vapic_addr);
+ r = kvm_lapic_set_vapic_addr(vcpu, va.vapic_addr);
break;
}
case KVM_X86_SETUP_MCE: {
@@ -5539,36 +5541,6 @@ static void post_kvm_run_save(struct kvm_vcpu *vcpu)
!kvm_event_needs_reinjection(vcpu);
}
-static int vapic_enter(struct kvm_vcpu *vcpu)
-{
- struct kvm_lapic *apic = vcpu->arch.apic;
- struct page *page;
-
- if (!apic || !apic->vapic_addr)
- return 0;
-
- page = gfn_to_page(vcpu->kvm, apic->vapic_addr >> PAGE_SHIFT);
- if (is_error_page(page))
- return -EFAULT;
-
- vcpu->arch.apic->vapic_page = page;
- return 0;
-}
-
-static void vapic_exit(struct kvm_vcpu *vcpu)
-{
- struct kvm_lapic *apic = vcpu->arch.apic;
- int idx;
-
- if (!apic || !apic->vapic_addr)
- return;
-
- idx = srcu_read_lock(&vcpu->kvm->srcu);
- kvm_release_page_dirty(apic->vapic_page);
- mark_page_dirty(vcpu->kvm, apic->vapic_addr >> PAGE_SHIFT);
- srcu_read_unlock(&vcpu->kvm->srcu, idx);
-}
-
static void update_cr8_intercept(struct kvm_vcpu *vcpu)
{
int max_irr, tpr;
@@ -5889,11 +5861,6 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
struct kvm *kvm = vcpu->kvm;
vcpu->srcu_idx = srcu_read_lock(&kvm->srcu);
- r = vapic_enter(vcpu);
- if (r) {
- srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx);
- return r;
- }
r = 1;
while (r > 0) {
@@ -5951,8 +5918,6 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx);
- vapic_exit(vcpu);
-
return r;
}
@@ -6017,7 +5982,7 @@ static int complete_emulated_mmio(struct kvm_vcpu *vcpu)
frag->len -= len;
}
- if (vcpu->mmio_cur_fragment == vcpu->mmio_nr_fragments) {
+ if (vcpu->mmio_cur_fragment >= vcpu->mmio_nr_fragments) {
vcpu->mmio_needed = 0;
if (vcpu->mmio_is_write)
return 1;
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index e224f7a671b..3186542f2fa 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -124,5 +124,7 @@ int kvm_write_guest_virt_system(struct x86_emulate_ctxt *ctxt,
extern u64 host_xcr0;
+extern unsigned int min_timer_period_us;
+
extern struct static_key kvm_no_apic_vcpu;
#endif
generated by cgit v1.2.3 (git 2.25.1) at 2024-04-27 15:48:51 +0000