summaryrefslogtreecommitdiff
path: root/arch/x86/kvm
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kvm')
-rw-r--r--arch/x86/kvm/Kconfig1
-rw-r--r--arch/x86/kvm/emulate.c6
-rw-r--r--arch/x86/kvm/i8254.c8
-rw-r--r--arch/x86/kvm/i8259.c4
-rw-r--r--arch/x86/kvm/kvm_cache_regs.h24
-rw-r--r--arch/x86/kvm/lapic.c31
-rw-r--r--arch/x86/kvm/lapic.h8
-rw-r--r--arch/x86/kvm/mmu.c53
-rw-r--r--arch/x86/kvm/mmu.h11
-rw-r--r--arch/x86/kvm/svm.c126
-rw-r--r--arch/x86/kvm/trace.h32
-rw-r--r--arch/x86/kvm/vmx.c283
-rw-r--r--arch/x86/kvm/x86.c692
13 files changed, 968 insertions, 311 deletions
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index 4cd498332466..06871111bf54 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -29,6 +29,7 @@ config KVM
select HAVE_KVM_EVENTFD
select KVM_APIC_ARCHITECTURE
select USER_RETURN_NOTIFIER
+ select KVM_MMIO
---help---
Support hosting fully virtualized guest machines using hardware
virtualization extensions. You will need a fairly recent
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 7e8faea4651e..0f89e320bc96 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -1515,7 +1515,7 @@ emulate_syscall(struct x86_emulate_ctxt *ctxt)
/* syscall is not available in real mode */
if (c->lock_prefix || ctxt->mode == X86EMUL_MODE_REAL
- || !(ctxt->vcpu->arch.cr0 & X86_CR0_PE))
+ || !kvm_read_cr0_bits(ctxt->vcpu, X86_CR0_PE))
return -1;
setup_syscalls_segments(ctxt, &cs, &ss);
@@ -1569,7 +1569,7 @@ emulate_sysenter(struct x86_emulate_ctxt *ctxt)
/* inject #GP if in real mode or paging is disabled */
if (ctxt->mode == X86EMUL_MODE_REAL ||
- !(ctxt->vcpu->arch.cr0 & X86_CR0_PE)) {
+ !kvm_read_cr0_bits(ctxt->vcpu, X86_CR0_PE)) {
kvm_inject_gp(ctxt->vcpu, 0);
return -1;
}
@@ -1635,7 +1635,7 @@ emulate_sysexit(struct x86_emulate_ctxt *ctxt)
/* inject #GP if in real mode or paging is disabled */
if (ctxt->mode == X86EMUL_MODE_REAL
- || !(ctxt->vcpu->arch.cr0 & X86_CR0_PE)) {
+ || !kvm_read_cr0_bits(ctxt->vcpu, X86_CR0_PE)) {
kvm_inject_gp(ctxt->vcpu, 0);
return -1;
}
diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c
index 296aba49472a..caad18954ed3 100644
--- a/arch/x86/kvm/i8254.c
+++ b/arch/x86/kvm/i8254.c
@@ -602,7 +602,7 @@ static const struct kvm_io_device_ops speaker_dev_ops = {
.write = speaker_ioport_write,
};
-/* Caller must have writers lock on slots_lock */
+/* Caller must hold slots_lock */
struct kvm_pit *kvm_create_pit(struct kvm *kvm, u32 flags)
{
struct kvm_pit *pit;
@@ -642,13 +642,13 @@ struct kvm_pit *kvm_create_pit(struct kvm *kvm, u32 flags)
kvm_register_irq_mask_notifier(kvm, 0, &pit->mask_notifier);
kvm_iodevice_init(&pit->dev, &pit_dev_ops);
- ret = __kvm_io_bus_register_dev(&kvm->pio_bus, &pit->dev);
+ ret = kvm_io_bus_register_dev(kvm, KVM_PIO_BUS, &pit->dev);
if (ret < 0)
goto fail;
if (flags & KVM_PIT_SPEAKER_DUMMY) {
kvm_iodevice_init(&pit->speaker_dev, &speaker_dev_ops);
- ret = __kvm_io_bus_register_dev(&kvm->pio_bus,
+ ret = kvm_io_bus_register_dev(kvm, KVM_PIO_BUS,
&pit->speaker_dev);
if (ret < 0)
goto fail_unregister;
@@ -657,7 +657,7 @@ struct kvm_pit *kvm_create_pit(struct kvm *kvm, u32 flags)
return pit;
fail_unregister:
- __kvm_io_bus_unregister_dev(&kvm->pio_bus, &pit->dev);
+ kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, &pit->dev);
fail:
if (pit->irq_source_id >= 0)
diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c
index d057c0cbd245..d5753a75d58c 100644
--- a/arch/x86/kvm/i8259.c
+++ b/arch/x86/kvm/i8259.c
@@ -533,7 +533,9 @@ struct kvm_pic *kvm_create_pic(struct kvm *kvm)
* Initialize PIO device
*/
kvm_iodevice_init(&s->dev, &picdev_ops);
- ret = kvm_io_bus_register_dev(kvm, &kvm->pio_bus, &s->dev);
+ mutex_lock(&kvm->slots_lock);
+ ret = kvm_io_bus_register_dev(kvm, KVM_PIO_BUS, &s->dev);
+ mutex_unlock(&kvm->slots_lock);
if (ret < 0) {
kfree(s);
return NULL;
diff --git a/arch/x86/kvm/kvm_cache_regs.h b/arch/x86/kvm/kvm_cache_regs.h
index 7bcc5b6a4403..6b419a36cbd9 100644
--- a/arch/x86/kvm/kvm_cache_regs.h
+++ b/arch/x86/kvm/kvm_cache_regs.h
@@ -38,4 +38,28 @@ static inline u64 kvm_pdptr_read(struct kvm_vcpu *vcpu, int index)
return vcpu->arch.pdptrs[index];
}
+static inline ulong kvm_read_cr0_bits(struct kvm_vcpu *vcpu, ulong mask)
+{
+ if (mask & vcpu->arch.cr0_guest_owned_bits)
+ kvm_x86_ops->decache_cr0_guest_bits(vcpu);
+ return vcpu->arch.cr0 & mask;
+}
+
+static inline ulong kvm_read_cr0(struct kvm_vcpu *vcpu)
+{
+ return kvm_read_cr0_bits(vcpu, ~0UL);
+}
+
+static inline ulong kvm_read_cr4_bits(struct kvm_vcpu *vcpu, ulong mask)
+{
+ if (mask & vcpu->arch.cr4_guest_owned_bits)
+ kvm_x86_ops->decache_cr4_guest_bits(vcpu);
+ return vcpu->arch.cr4 & mask;
+}
+
+static inline ulong kvm_read_cr4(struct kvm_vcpu *vcpu)
+{
+ return kvm_read_cr4_bits(vcpu, ~0UL);
+}
+
#endif
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index ba8c045da782..4b224f90087b 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1246,3 +1246,34 @@ int kvm_x2apic_msr_read(struct kvm_vcpu *vcpu, u32 msr, u64 *data)
return 0;
}
+
+int kvm_hv_vapic_msr_write(struct kvm_vcpu *vcpu, u32 reg, u64 data)
+{
+ struct kvm_lapic *apic = vcpu->arch.apic;
+
+ if (!irqchip_in_kernel(vcpu->kvm))
+ return 1;
+
+ /* if this is ICR write vector before command */
+ if (reg == APIC_ICR)
+ apic_reg_write(apic, APIC_ICR2, (u32)(data >> 32));
+ return apic_reg_write(apic, reg, (u32)data);
+}
+
+int kvm_hv_vapic_msr_read(struct kvm_vcpu *vcpu, u32 reg, u64 *data)
+{
+ struct kvm_lapic *apic = vcpu->arch.apic;
+ u32 low, high = 0;
+
+ if (!irqchip_in_kernel(vcpu->kvm))
+ return 1;
+
+ if (apic_reg_read(apic, reg, 4, &low))
+ return 1;
+ if (reg == APIC_ICR)
+ apic_reg_read(apic, APIC_ICR2, 4, &high);
+
+ *data = (((u64)high) << 32) | low;
+
+ return 0;
+}
diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h
index 40010b09c4aa..f5fe32c5edad 100644
--- a/arch/x86/kvm/lapic.h
+++ b/arch/x86/kvm/lapic.h
@@ -48,4 +48,12 @@ void kvm_lapic_sync_to_vapic(struct kvm_vcpu *vcpu);
int kvm_x2apic_msr_write(struct kvm_vcpu *vcpu, u32 msr, u64 data);
int kvm_x2apic_msr_read(struct kvm_vcpu *vcpu, u32 msr, u64 *data);
+
+int kvm_hv_vapic_msr_write(struct kvm_vcpu *vcpu, u32 msr, u64 data);
+int kvm_hv_vapic_msr_read(struct kvm_vcpu *vcpu, u32 msr, u64 *data);
+
+static inline bool kvm_hv_vapic_assist_page_enabled(struct kvm_vcpu *vcpu)
+{
+ return vcpu->arch.hv_vapic & HV_X64_MSR_APIC_ASSIST_PAGE_ENABLE;
+}
#endif
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 89a49fb46a27..276bf7497c36 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -29,6 +29,7 @@
#include <linux/swap.h>
#include <linux/hugetlb.h>
#include <linux/compiler.h>
+#include <linux/srcu.h>
#include <asm/page.h>
#include <asm/cmpxchg.h>
@@ -142,10 +143,6 @@ module_param(oos_shadow, bool, 0644);
#define PFERR_RSVD_MASK (1U << 3)
#define PFERR_FETCH_MASK (1U << 4)
-#define PT_PDPE_LEVEL 3
-#define PT_DIRECTORY_LEVEL 2
-#define PT_PAGE_TABLE_LEVEL 1
-
#define RMAP_EXT 4
#define ACC_EXEC_MASK 1
@@ -229,7 +226,7 @@ EXPORT_SYMBOL_GPL(kvm_mmu_set_mask_ptes);
static int is_write_protection(struct kvm_vcpu *vcpu)
{
- return vcpu->arch.cr0 & X86_CR0_WP;
+ return kvm_read_cr0_bits(vcpu, X86_CR0_WP);
}
static int is_cpuid_PSE36(void)
@@ -503,8 +500,7 @@ out:
static int mapping_level(struct kvm_vcpu *vcpu, gfn_t large_gfn)
{
struct kvm_memory_slot *slot;
- int host_level;
- int level = PT_PAGE_TABLE_LEVEL;
+ int host_level, level, max_level;
slot = gfn_to_memslot(vcpu->kvm, large_gfn);
if (slot && slot->dirty_bitmap)
@@ -515,7 +511,10 @@ static int mapping_level(struct kvm_vcpu *vcpu, gfn_t large_gfn)
if (host_level == PT_PAGE_TABLE_LEVEL)
return host_level;
- for (level = PT_DIRECTORY_LEVEL; level <= host_level; ++level)
+ max_level = kvm_x86_ops->get_lpage_level() < host_level ?
+ kvm_x86_ops->get_lpage_level() : host_level;
+
+ for (level = PT_DIRECTORY_LEVEL; level <= max_level; ++level)
if (has_wrprotected_page(vcpu->kvm, large_gfn, level))
break;
@@ -662,6 +661,7 @@ static void rmap_remove(struct kvm *kvm, u64 *spte)
prev_desc = desc;
desc = desc->more;
}
+ pr_err("rmap_remove: %p %llx many->many\n", spte, *spte);
BUG();
}
}
@@ -806,20 +806,15 @@ static int kvm_handle_hva(struct kvm *kvm, unsigned long hva,
{
int i, j;
int retval = 0;
+ struct kvm_memslots *slots;
- /*
- * If mmap_sem isn't taken, we can look the memslots with only
- * the mmu_lock by skipping over the slots with userspace_addr == 0.
- */
- for (i = 0; i < kvm->nmemslots; i++) {
- struct kvm_memory_slot *memslot = &kvm->memslots[i];
+ slots = rcu_dereference(kvm->memslots);
+
+ for (i = 0; i < slots->nmemslots; i++) {
+ struct kvm_memory_slot *memslot = &slots->memslots[i];
unsigned long start = memslot->userspace_addr;
unsigned long end;
- /* mmu_lock protects userspace_addr */
- if (!start)
- continue;
-
end = start + (memslot->npages << PAGE_SHIFT);
if (hva >= start && hva < end) {
gfn_t gfn_offset = (hva - start) >> PAGE_SHIFT;
@@ -1615,7 +1610,7 @@ static void mmu_unshadow(struct kvm *kvm, gfn_t gfn)
static void page_header_update_slot(struct kvm *kvm, void *pte, gfn_t gfn)
{
- int slot = memslot_id(kvm, gfn_to_memslot(kvm, gfn));
+ int slot = memslot_id(kvm, gfn);
struct kvm_mmu_page *sp = page_header(__pa(pte));
__set_bit(slot, sp->slot_bitmap);
@@ -2936,10 +2931,9 @@ static int mmu_shrink(int nr_to_scan, gfp_t gfp_mask)
spin_lock(&kvm_lock);
list_for_each_entry(kvm, &vm_list, vm_list) {
- int npages;
+ int npages, idx;
- if (!down_read_trylock(&kvm->slots_lock))
- continue;
+ idx = srcu_read_lock(&kvm->srcu);
spin_lock(&kvm->mmu_lock);
npages = kvm->arch.n_alloc_mmu_pages -
kvm->arch.n_free_mmu_pages;
@@ -2952,7 +2946,7 @@ static int mmu_shrink(int nr_to_scan, gfp_t gfp_mask)
nr_to_scan--;
spin_unlock(&kvm->mmu_lock);
- up_read(&kvm->slots_lock);
+ srcu_read_unlock(&kvm->srcu, idx);
}
if (kvm_freed)
list_move_tail(&kvm_freed->vm_list, &vm_list);
@@ -3019,9 +3013,11 @@ unsigned int kvm_mmu_calculate_mmu_pages(struct kvm *kvm)
int i;
unsigned int nr_mmu_pages;
unsigned int nr_pages = 0;
+ struct kvm_memslots *slots;
- for (i = 0; i < kvm->nmemslots; i++)
- nr_pages += kvm->memslots[i].npages;
+ slots = rcu_dereference(kvm->memslots);
+ for (i = 0; i < slots->nmemslots; i++)
+ nr_pages += slots->memslots[i].npages;
nr_mmu_pages = nr_pages * KVM_PERMILLE_MMU_PAGES / 1000;
nr_mmu_pages = max(nr_mmu_pages,
@@ -3291,10 +3287,12 @@ static void audit_mappings(struct kvm_vcpu *vcpu)
static int count_rmaps(struct kvm_vcpu *vcpu)
{
int nmaps = 0;
- int i, j, k;
+ int i, j, k, idx;
+ idx = srcu_read_lock(&kvm->srcu);
+ slots = rcu_dereference(kvm->memslots);
for (i = 0; i < KVM_MEMORY_SLOTS; ++i) {
- struct kvm_memory_slot *m = &vcpu->kvm->memslots[i];
+ struct kvm_memory_slot *m = &slots->memslots[i];
struct kvm_rmap_desc *d;
for (j = 0; j < m->npages; ++j) {
@@ -3317,6 +3315,7 @@ static int count_rmaps(struct kvm_vcpu *vcpu)
}
}
}
+ srcu_read_unlock(&kvm->srcu, idx);
return nmaps;
}
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index 61a1b3884b49..599159f728b9 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -2,6 +2,7 @@
#define __KVM_X86_MMU_H
#include <linux/kvm_host.h>
+#include "kvm_cache_regs.h"
#define PT64_PT_BITS 9
#define PT64_ENT_PER_PAGE (1 << PT64_PT_BITS)
@@ -37,6 +38,10 @@
#define PT32_ROOT_LEVEL 2
#define PT32E_ROOT_LEVEL 3
+#define PT_PDPE_LEVEL 3
+#define PT_DIRECTORY_LEVEL 2
+#define PT_PAGE_TABLE_LEVEL 1
+
int kvm_mmu_get_spte_hierarchy(struct kvm_vcpu *vcpu, u64 addr, u64 sptes[4]);
static inline void kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu)
@@ -64,17 +69,17 @@ static inline int is_long_mode(struct kvm_vcpu *vcpu)
static inline int is_pae(struct kvm_vcpu *vcpu)
{
- return vcpu->arch.cr4 & X86_CR4_PAE;
+ return kvm_read_cr4_bits(vcpu, X86_CR4_PAE);
}
static inline int is_pse(struct kvm_vcpu *vcpu)
{
- return vcpu->arch.cr4 & X86_CR4_PSE;
+ return kvm_read_cr4_bits(vcpu, X86_CR4_PSE);
}
static inline int is_paging(struct kvm_vcpu *vcpu)
{
- return vcpu->arch.cr0 & X86_CR0_PG;
+ return kvm_read_cr0_bits(vcpu, X86_CR0_PG);
}
static inline int is_present_gpte(unsigned long pte)
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 1d9b33843c80..8d7cb62ebef6 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -540,6 +540,8 @@ static void init_vmcb(struct vcpu_svm *svm)
struct vmcb_control_area *control = &svm->vmcb->control;
struct vmcb_save_area *save = &svm->vmcb->save;
+ svm->vcpu.fpu_active = 1;
+
control->intercept_cr_read = INTERCEPT_CR0_MASK |
INTERCEPT_CR3_MASK |
INTERCEPT_CR4_MASK;
@@ -569,6 +571,7 @@ static void init_vmcb(struct vcpu_svm *svm)
control->intercept = (1ULL << INTERCEPT_INTR) |
(1ULL << INTERCEPT_NMI) |
(1ULL << INTERCEPT_SMI) |
+ (1ULL << INTERCEPT_SELECTIVE_CR0) |
(1ULL << INTERCEPT_CPUID) |
(1ULL << INTERCEPT_INVD) |
(1ULL << INTERCEPT_HLT) |
@@ -641,10 +644,8 @@ static void init_vmcb(struct vcpu_svm *svm)
control->intercept &= ~((1ULL << INTERCEPT_TASK_SWITCH) |
(1ULL << INTERCEPT_INVLPG));
control->intercept_exceptions &= ~(1 << PF_VECTOR);
- control->intercept_cr_read &= ~(INTERCEPT_CR0_MASK|
- INTERCEPT_CR3_MASK);
- control->intercept_cr_write &= ~(INTERCEPT_CR0_MASK|
- INTERCEPT_CR3_MASK);
+ control->intercept_cr_read &= ~INTERCEPT_CR3_MASK;
+ control->intercept_cr_write &= ~INTERCEPT_CR3_MASK;
save->g_pat = 0x0007040600070406ULL;
save->cr3 = 0;
save->cr4 = 0;
@@ -730,7 +731,6 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id)
init_vmcb(svm);
fx_init(&svm->vcpu);
- svm->vcpu.fpu_active = 1;
svm->vcpu.arch.apic_base = 0xfee00000 | MSR_IA32_APICBASE_ENABLE;
if (kvm_vcpu_is_bsp(&svm->vcpu))
svm->vcpu.arch.apic_base |= MSR_IA32_APICBASE_BSP;
@@ -765,14 +765,16 @@ static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
if (unlikely(cpu != vcpu->cpu)) {
u64 delta;
- /*
- * Make sure that the guest sees a monotonically
- * increasing TSC.
- */
- delta = vcpu->arch.host_tsc - native_read_tsc();
- svm->vmcb->control.tsc_offset += delta;
- if (is_nested(svm))
- svm->nested.hsave->control.tsc_offset += delta;
+ if (check_tsc_unstable()) {
+ /*
+ * Make sure that the guest sees a monotonically
+ * increasing TSC.
+ */
+ delta = vcpu->arch.host_tsc - native_read_tsc();
+ svm->vmcb->control.tsc_offset += delta;
+ if (is_nested(svm))
+ svm->nested.hsave->control.tsc_offset += delta;
+ }
vcpu->cpu = cpu;
kvm_migrate_timers(vcpu);
svm->asid_generation = 0;
@@ -954,10 +956,35 @@ static void svm_set_gdt(struct kvm_vcpu *vcpu, struct descriptor_table *dt)
svm->vmcb->save.gdtr.base = dt->base ;
}
+static void svm_decache_cr0_guest_bits(struct kvm_vcpu *vcpu)
+{
+}
+
static void svm_decache_cr4_guest_bits(struct kvm_vcpu *vcpu)
{
}
+static void update_cr0_intercept(struct vcpu_svm *svm)
+{
+ ulong gcr0 = svm->vcpu.arch.cr0;
+ u64 *hcr0 = &svm->vmcb->save.cr0;
+
+ if (!svm->vcpu.fpu_active)
+ *hcr0 |= SVM_CR0_SELECTIVE_MASK;
+ else
+ *hcr0 = (*hcr0 & ~SVM_CR0_SELECTIVE_MASK)
+ | (gcr0 & SVM_CR0_SELECTIVE_MASK);
+
+
+ if (gcr0 == *hcr0 && svm->vcpu.fpu_active) {
+ svm->vmcb->control.intercept_cr_read &= ~INTERCEPT_CR0_MASK;
+ svm->vmcb->control.intercept_cr_write &= ~INTERCEPT_CR0_MASK;
+ } else {
+ svm->vmcb->control.intercept_cr_read |= INTERCEPT_CR0_MASK;
+ svm->vmcb->control.intercept_cr_write |= INTERCEPT_CR0_MASK;
+ }
+}
+
static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
{
struct vcpu_svm *svm = to_svm(vcpu);
@@ -975,21 +1002,13 @@ static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
}
}
#endif
- if (npt_enabled)
- goto set;
+ vcpu->arch.cr0 = cr0;
- if ((vcpu->arch.cr0 & X86_CR0_TS) && !(cr0 & X86_CR0_TS)) {
- svm->vmcb->control.intercept_exceptions &= ~(1 << NM_VECTOR);
- vcpu->fpu_active = 1;
- }
+ if (!npt_enabled)
+ cr0 |= X86_CR0_PG | X86_CR0_WP;
- vcpu->arch.cr0 = cr0;
- cr0 |= X86_CR0_PG | X86_CR0_WP;
- if (!vcpu->fpu_active) {
- svm->vmcb->control.intercept_exceptions |= (1 << NM_VECTOR);
+ if (!vcpu->fpu_active)
cr0 |= X86_CR0_TS;
- }
-set:
/*
* re-enable caching here because the QEMU bios
* does not do it - this results in some delay at
@@ -997,6 +1016,7 @@ set:
*/
cr0 &= ~(X86_CR0_CD | X86_CR0_NW);
svm->vmcb->save.cr0 = cr0;
+ update_cr0_intercept(svm);
}
static void svm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
@@ -1242,9 +1262,8 @@ static int ud_interception(struct vcpu_svm *svm)
static int nm_interception(struct vcpu_svm *svm)
{
svm->vmcb->control.intercept_exceptions &= ~(1 << NM_VECTOR);
- if (!(svm->vcpu.arch.cr0 & X86_CR0_TS))
- svm->vmcb->save.cr0 &= ~X86_CR0_TS;
svm->vcpu.fpu_active = 1;
+ update_cr0_intercept(svm);
return 1;
}
@@ -1741,7 +1760,7 @@ static bool nested_svm_vmrun(struct vcpu_svm *svm)
hsave->save.gdtr = vmcb->save.gdtr;
hsave->save.idtr = vmcb->save.idtr;
hsave->save.efer = svm->vcpu.arch.shadow_efer;
- hsave->save.cr0 = svm->vcpu.arch.cr0;
+ hsave->save.cr0 = kvm_read_cr0(&svm->vcpu);
hsave->save.cr4 = svm->vcpu.arch.cr4;
hsave->save.rflags = vmcb->save.rflags;
hsave->save.rip = svm->next_rip;
@@ -2297,7 +2316,7 @@ static int (*svm_exit_handlers[])(struct vcpu_svm *svm) = {
[SVM_EXIT_READ_CR3] = emulate_on_interception,
[SVM_EXIT_READ_CR4] = emulate_on_interception,
[SVM_EXIT_READ_CR8] = emulate_on_interception,
- /* for now: */
+ [SVM_EXIT_CR0_SEL_WRITE] = emulate_on_interception,
[SVM_EXIT_WRITE_CR0] = emulate_on_interception,
[SVM_EXIT_WRITE_CR3] = emulate_on_interception,
[SVM_EXIT_WRITE_CR4] = emulate_on_interception,
@@ -2383,20 +2402,10 @@ static int handle_exit(struct kvm_vcpu *vcpu)
svm_complete_interrupts(svm);
- if (npt_enabled) {
- int mmu_reload = 0;
- if ((vcpu->arch.cr0 ^ svm->vmcb->save.cr0) & X86_CR0_PG) {
- svm_set_cr0(vcpu, svm->vmcb->save.cr0);
- mmu_reload = 1;
- }
+ if (!(svm->vmcb->control.intercept_cr_write & INTERCEPT_CR0_MASK))
vcpu->arch.cr0 = svm->vmcb->save.cr0;
+ if (npt_enabled)
vcpu->arch.cr3 = svm->vmcb->save.cr3;
- if (mmu_reload) {
- kvm_mmu_reset_context(vcpu);
- kvm_mmu_load(vcpu);
- }
- }
-
if (svm->vmcb->control.exit_code == SVM_EXIT_ERR) {
kvm_run->exit_reason = KVM_EXIT_FAIL_ENTRY;
@@ -2798,12 +2807,6 @@ static void svm_set_cr3(struct kvm_vcpu *vcpu, unsigned long root)
svm->vmcb->save.cr3 = root;
force_new_asid(vcpu);
-
- if (vcpu->fpu_active) {
- svm->vmcb->control.intercept_exceptions |= (1 << NM_VECTOR);
- svm->vmcb->save.cr0 |= X86_CR0_TS;
- vcpu->fpu_active = 0;
- }
}
static int is_disabled(void)
@@ -2852,6 +2855,10 @@ static u64 svm_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio)
return 0;
}
+static void svm_cpuid_update(struct kvm_vcpu *vcpu)
+{
+}
+
static const struct trace_print_flags svm_exit_reasons_str[] = {
{ SVM_EXIT_READ_CR0, "read_cr0" },
{ SVM_EXIT_READ_CR3, "read_cr3" },
@@ -2905,9 +2912,22 @@ static const struct trace_print_flags svm_exit_reasons_str[] = {
{ -1, NULL }
};
-static bool svm_gb_page_enable(void)
+static int svm_get_lpage_level(void)
{
- return true;
+ return PT_PDPE_LEVEL;
+}
+
+static bool svm_rdtscp_supported(void)
+{
+ return false;
+}
+
+static void svm_fpu_deactivate(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_svm *svm = to_svm(vcpu);
+
+ update_cr0_intercept(svm);
+ svm->vmcb->control.intercept_exceptions |= 1 << NM_VECTOR;
}
static struct kvm_x86_ops svm_x86_ops = {
@@ -2936,6 +2956,7 @@ static struct kvm_x86_ops svm_x86_ops = {
.set_segment = svm_set_segment,
.get_cpl = svm_get_cpl,
.get_cs_db_l_bits = kvm_get_cs_db_l_bits,
+ .decache_cr0_guest_bits = svm_decache_cr0_guest_bits,
.decache_cr4_guest_bits = svm_decache_cr4_guest_bits,
.set_cr0 = svm_set_cr0,
.set_cr3 = svm_set_cr3,
@@ -2950,6 +2971,7 @@ static struct kvm_x86_ops svm_x86_ops = {
.cache_reg = svm_cache_reg,
.get_rflags = svm_get_rflags,
.set_rflags = svm_set_rflags,
+ .fpu_deactivate = svm_fpu_deactivate,
.tlb_flush = svm_flush_tlb,
@@ -2975,7 +2997,11 @@ static struct kvm_x86_ops svm_x86_ops = {
.get_mt_mask = svm_get_mt_mask,
.exit_reasons_str = svm_exit_reasons_str,
- .gb_page_enable = svm_gb_page_enable,
+ .get_lpage_level = svm_get_lpage_level,
+
+ .cpuid_update = svm_cpuid_update,
+
+ .rdtscp_supported = svm_rdtscp_supported,
};
static int __init svm_init(void)
diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h
index 816e0449db0b..1cb3d0e990f3 100644
--- a/arch/x86/kvm/trace.h
+++ b/arch/x86/kvm/trace.h
@@ -56,6 +56,38 @@ TRACE_EVENT(kvm_hypercall,
);
/*
+ * Tracepoint for hypercall.
+ */
+TRACE_EVENT(kvm_hv_hypercall,
+ TP_PROTO(__u16 code, bool fast, __u16 rep_cnt, __u16 rep_idx,
+ __u64 ingpa, __u64 outgpa),
+ TP_ARGS(code, fast, rep_cnt, rep_idx, ingpa, outgpa),
+
+ TP_STRUCT__entry(
+ __field( __u16, code )
+ __field( bool, fast )
+ __field( __u16, rep_cnt )
+ __field( __u16, rep_idx )
+ __field( __u64, ingpa )
+ __field( __u64, outgpa )
+ ),
+
+ TP_fast_assign(
+ __entry->code = code;
+ __entry->fast = fast;
+ __entry->rep_cnt = rep_cnt;
+ __entry->rep_idx = rep_idx;
+ __entry->ingpa = ingpa;
+ __entry->outgpa = outgpa;
+ ),
+
+ TP_printk("code 0x%x %s cnt 0x%x idx 0x%x in 0x%llx out 0x%llx",
+ __entry->code, __entry->fast ? "fast" : "slow",
+ __entry->rep_cnt, __entry->rep_idx, __entry->ingpa,
+ __entry->outgpa)
+);
+
+/*
* Tracepoint for PIO.
*/
TRACE_EVENT(kvm_pio,
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index d4918d6fc924..7375ae1682ed 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -61,6 +61,21 @@ module_param_named(unrestricted_guest,
static int __read_mostly emulate_invalid_guest_state = 0;
module_param(emulate_invalid_guest_state, bool, S_IRUGO);
+#define KVM_GUEST_CR0_MASK_UNRESTRICTED_GUEST \
+ (X86_CR0_WP | X86_CR0_NE | X86_CR0_NW | X86_CR0_CD)
+#define KVM_GUEST_CR0_MASK \
+ (KVM_GUEST_CR0_MASK_UNRESTRICTED_GUEST | X86_CR0_PG | X86_CR0_PE)
+#define KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST \
+ (X86_CR0_WP | X86_CR0_NE | X86_CR0_MP)
+#define KVM_VM_CR0_ALWAYS_ON \
+ (KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST | X86_CR0_PG | X86_CR0_PE)
+#define KVM_CR4_GUEST_OWNED_BITS \
+ (X86_CR4_PVI | X86_CR4_DE | X86_CR4_PCE | X86_CR4_OSFXSR \
+ | X86_CR4_OSXMMEXCPT)
+
+#define KVM_PMODE_VM_CR4_ALWAYS_ON (X86_CR4_PAE | X86_CR4_VMXE)
+#define KVM_RMODE_VM_CR4_ALWAYS_ON (X86_CR4_VME | X86_CR4_PAE | X86_CR4_VMXE)
+
/*
* These 2 parameters are used to config the controls for Pause-Loop Exiting:
* ple_gap: upper bound on the amount of time between two successive
@@ -136,6 +151,8 @@ struct vcpu_vmx {
ktime_t entry_time;
s64 vnmi_blocked_time;
u32 exit_reason;
+
+ bool rdtscp_enabled;
};
static inline struct vcpu_vmx *to_vmx(struct kvm_vcpu *vcpu)
@@ -210,7 +227,7 @@ static const u32 vmx_msr_index[] = {
#ifdef CONFIG_X86_64
MSR_SYSCALL_MASK, MSR_LSTAR, MSR_CSTAR,
#endif
- MSR_EFER, MSR_K6_STAR,
+ MSR_EFER, MSR_TSC_AUX, MSR_K6_STAR,
};
#define NR_VMX_MSR ARRAY_SIZE(vmx_msr_index)
@@ -301,6 +318,11 @@ static inline bool cpu_has_vmx_ept_2m_page(void)
return !!(vmx_capability.ept & VMX_EPT_2MB_PAGE_BIT);
}
+static inline bool cpu_has_vmx_ept_1g_page(void)
+{
+ return !!(vmx_capability.ept & VMX_EPT_1GB_PAGE_BIT);
+}
+
static inline int cpu_has_vmx_invept_individual_addr(void)
{
return !!(vmx_capability.ept & VMX_EPT_EXTENT_INDIVIDUAL_BIT);
@@ -347,6 +369,12 @@ static inline int cpu_has_vmx_vpid(void)
SECONDARY_EXEC_ENABLE_VPID;
}
+static inline int cpu_has_vmx_rdtscp(void)
+{
+ return vmcs_config.cpu_based_2nd_exec_ctrl &
+ SECONDARY_EXEC_RDTSCP;
+}
+
static inline int cpu_has_virtual_nmis(void)
{
return vmcs_config.pin_based_exec_ctrl & PIN_BASED_VIRTUAL_NMIS;
@@ -551,9 +579,8 @@ static void update_exception_bitmap(struct kvm_vcpu *vcpu)
{
u32 eb;
- eb = (1u << PF_VECTOR) | (1u << UD_VECTOR) | (1u << MC_VECTOR);
- if (!vcpu->fpu_active)
- eb |= 1u << NM_VECTOR;
+ eb = (1u << PF_VECTOR) | (1u << UD_VECTOR) | (1u << MC_VECTOR)
+ | (1u << NM_VECTOR);
/*
* Unconditionally intercept #DB so we can maintain dr6 without
* reading it every exit.
@@ -567,6 +594,8 @@ static void update_exception_bitmap(struct kvm_vcpu *vcpu)
eb = ~0;
if (enable_ept)
eb &= ~(1u << PF_VECTOR); /* bypass_guest_pf = 0 */
+ if (vcpu->fpu_active)
+ eb &= ~(1u << NM_VECTOR);
vmcs_write32(EXCEPTION_BITMAP, eb);
}
@@ -771,18 +800,26 @@ static void vmx_fpu_activate(struct kvm_vcpu *vcpu)
return;
vcpu->fpu_active = 1;
vmcs_clear_bits(GUEST_CR0, X86_CR0_TS);
- if (vcpu->arch.cr0 & X86_CR0_TS)
+ if (kvm_read_cr0_bits(vcpu, X86_CR0_TS))
vmcs_set_bits(GUEST_CR0, X86_CR0_TS);
update_exception_bitmap(vcpu);
+ vcpu->arch.cr0_guest_owned_bits = X86_CR0_TS;
+ vmcs_writel(CR0_GUEST_HOST_MASK, ~vcpu->arch.cr0_guest_owned_bits);
}
static void vmx_fpu_deactivate(struct kvm_vcpu *vcpu)
{
- if (!vcpu->fpu_active)
- return;
- vcpu->fpu_active = 0;
+ ulong old_ts, old_cr0;
+
+ old_ts = kvm_read_cr0_bits(vcpu, X86_CR0_TS);
vmcs_set_bits(GUEST_CR0, X86_CR0_TS);
update_exception_bitmap(vcpu);
+ vcpu->arch.cr0_guest_owned_bits = 0;
+ vmcs_writel(CR0_GUEST_HOST_MASK, ~vcpu->arch.cr0_guest_owned_bits);
+ old_cr0 = vcpu->arch.cr0;
+ vcpu->arch.cr0 = (vcpu->arch.cr0 & ~X86_CR0_TS) | old_ts;
+ if (vcpu->arch.cr0 != old_cr0)
+ vmcs_writel(CR0_READ_SHADOW, vcpu->arch.cr0);
}
static unsigned long vmx_get_rflags(struct kvm_vcpu *vcpu)
@@ -878,6 +915,11 @@ static void vmx_queue_exception(struct kvm_vcpu *vcpu, unsigned nr,
vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, intr_info);
}
+static bool vmx_rdtscp_supported(void)
+{
+ return cpu_has_vmx_rdtscp();
+}
+
/*
* Swap MSR entry in host/guest MSR entry array.
*/
@@ -913,6 +955,9 @@ static void setup_msrs(struct vcpu_vmx *vmx)
index = __find_msr_index(vmx, MSR_CSTAR);
if (index >= 0)
move_msr_up(vmx, index, save_nmsrs++);
+ index = __find_msr_index(vmx, MSR_TSC_AUX);
+ if (index >= 0 && vmx->rdtscp_enabled)
+ move_msr_up(vmx, index, save_nmsrs++);
/*
* MSR_K6_STAR is only needed on long mode guests, and only
* if efer.sce is enabled.
@@ -1002,6 +1047,10 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata)
case MSR_IA32_SYSENTER_ESP:
data = vmcs_readl(GUEST_SYSENTER_ESP);
break;
+ case MSR_TSC_AUX:
+ if (!to_vmx(vcpu)->rdtscp_enabled)
+ return 1;
+ /* Otherwise falls through */
default:
vmx_load_host_state(to_vmx(vcpu));
msr = find_msr_entry(to_vmx(vcpu), msr_index);
@@ -1065,7 +1114,15 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data)
vcpu->arch.pat = data;
break;
}
- /* Otherwise falls through to kvm_set_msr_common */
+ ret = kvm_set_msr_common(vcpu, msr_index, data);
+ break;
+ case MSR_TSC_AUX:
+ if (!vmx->rdtscp_enabled)
+ return 1;
+ /* Check reserved bit, higher 32 bits should be zero */
+ if ((data >> 32) != 0)
+ return 1;
+ /* Otherwise falls through */
default:
msr = find_msr_entry(vmx, msr_index);
if (msr) {
@@ -1224,6 +1281,8 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf)
CPU_BASED_USE_IO_BITMAPS |
CPU_BASED_MOV_DR_EXITING |
CPU_BASED_USE_TSC_OFFSETING |
+ CPU_BASED_MWAIT_EXITING |
+ CPU_BASED_MONITOR_EXITING |
CPU_BASED_INVLPG_EXITING;
opt = CPU_BASED_TPR_SHADOW |
CPU_BASED_USE_MSR_BITMAPS |
@@ -1243,7 +1302,8 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf)
SECONDARY_EXEC_ENABLE_VPID |
SECONDARY_EXEC_ENABLE_EPT |
SECONDARY_EXEC_UNRESTRICTED_GUEST |
- SECONDARY_EXEC_PAUSE_LOOP_EXITING;
+ SECONDARY_EXEC_PAUSE_LOOP_EXITING |
+ SECONDARY_EXEC_RDTSCP;
if (adjust_vmx_controls(min2, opt2,
MSR_IA32_VMX_PROCBASED_CTLS2,
&_cpu_based_2nd_exec_control) < 0)
@@ -1457,8 +1517,12 @@ static void enter_pmode(struct kvm_vcpu *vcpu)
static gva_t rmode_tss_base(struct kvm *kvm)
{
if (!kvm->arch.tss_addr) {
- gfn_t base_gfn = kvm->memslots[0].base_gfn +
- kvm->memslots[0].npages - 3;
+ struct kvm_memslots *slots;
+ gfn_t base_gfn;
+
+ slots = rcu_dereference(kvm->memslots);
+ base_gfn = kvm->memslots->memslots[0].base_gfn +
+ kvm->memslots->memslots[0].npages - 3;
return base_gfn << PAGE_SHIFT;
}
return kvm->arch.tss_addr;
@@ -1598,10 +1662,20 @@ static void vmx_flush_tlb(struct kvm_vcpu *vcpu)
ept_sync_context(construct_eptp(vcpu->arch.mmu.root_hpa));
}
+static void vmx_decache_cr0_guest_bits(struct kvm_vcpu *vcpu)
+{
+ ulong cr0_guest_owned_bits = vcpu->arch.cr0_guest_owned_bits;
+
+ vcpu->arch.cr0 &= ~cr0_guest_owned_bits;
+ vcpu->arch.cr0 |= vmcs_readl(GUEST_CR0) & cr0_guest_owned_bits;
+}
+
static void vmx_decache_cr4_guest_bits(struct kvm_vcpu *vcpu)
{
- vcpu->arch.cr4 &= KVM_GUEST_CR4_MASK;
- vcpu->arch.cr4 |= vmcs_readl(GUEST_CR4) & ~KVM_GUEST_CR4_MASK;
+ ulong cr4_guest_owned_bits = vcpu->arch.cr4_guest_owned_bits;
+
+ vcpu->arch.cr4 &= ~cr4_guest_owned_bits;
+ vcpu->arch.cr4 |= vmcs_readl(GUEST_CR4) & cr4_guest_owned_bits;
}
static void ept_load_pdptrs(struct kvm_vcpu *vcpu)
@@ -1646,7 +1720,7 @@ static void ept_update_paging_mode_cr0(unsigned long *hw_cr0,
(CPU_BASED_CR3_LOAD_EXITING |
CPU_BASED_CR3_STORE_EXITING));
vcpu->arch.cr0 = cr0;
- vmx_set_cr4(vcpu, vcpu->arch.cr4);
+ vmx_set_cr4(vcpu, kvm_read_cr4(vcpu));
} else if (!is_paging(vcpu)) {
/* From nonpaging to paging */
vmcs_write32(CPU_BASED_VM_EXEC_CONTROL,
@@ -1654,23 +1728,13 @@ static void ept_update_paging_mode_cr0(unsigned long *hw_cr0,
~(CPU_BASED_CR3_LOAD_EXITING |
CPU_BASED_CR3_STORE_EXITING));
vcpu->arch.cr0 = cr0;
- vmx_set_cr4(vcpu, vcpu->arch.cr4);
+ vmx_set_cr4(vcpu, kvm_read_cr4(vcpu));
}
if (!(cr0 & X86_CR0_WP))
*hw_cr0 &= ~X86_CR0_WP;
}
-static void ept_update_paging_mode_cr4(unsigned long *hw_cr4,
- struct kvm_vcpu *vcpu)
-{
- if (!is_paging(vcpu)) {
- *hw_cr4 &= ~X86_CR4_PAE;
- *hw_cr4 |= X86_CR4_PSE;
- } else if (!(vcpu->arch.cr4 & X86_CR4_PAE))
- *hw_cr4 &= ~X86_CR4_PAE;
-}
-
static void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -1682,8 +1746,6 @@ static void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
else
hw_cr0 = (cr0 & ~KVM_GUEST_CR0_MASK) | KVM_VM_CR0_ALWAYS_ON;
- vmx_fpu_deactivate(vcpu);
-
if (vmx->rmode.vm86_active && (cr0 & X86_CR0_PE))
enter_pmode(vcpu);
@@ -1702,12 +1764,12 @@ static void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
if (enable_ept)
ept_update_paging_mode_cr0(&hw_cr0, cr0, vcpu);
+ if (!vcpu->fpu_active)
+ hw_cr0 |= X86_CR0_TS;
+
vmcs_writel(CR0_READ_SHADOW, cr0);
vmcs_writel(GUEST_CR0, hw_cr0);
vcpu->arch.cr0 = cr0;
-
- if (!(cr0 & X86_CR0_TS) || !(cr0 & X86_CR0_PE))
- vmx_fpu_activate(vcpu);
}
static u64 construct_eptp(unsigned long root_hpa)
@@ -1738,8 +1800,6 @@ static void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
vmx_flush_tlb(vcpu);
vmcs_writel(GUEST_CR3, guest_cr3);
- if (vcpu->arch.cr0 & X86_CR0_PE)
- vmx_fpu_deactivate(vcpu);
}
static void vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
@@ -1748,8 +1808,14 @@ static void vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
KVM_RMODE_VM_CR4_ALWAYS_ON : KVM_PMODE_VM_CR4_ALWAYS_ON);
vcpu->arch.cr4 = cr4;
- if (enable_ept)
- ept_update_paging_mode_cr4(&hw_cr4, vcpu);
+ if (enable_ept) {
+ if (!is_paging(vcpu)) {
+ hw_cr4 &= ~X86_CR4_PAE;
+ hw_cr4 |= X86_CR4_PSE;
+ } else if (!(cr4 & X86_CR4_PAE)) {
+ hw_cr4 &= ~X86_CR4_PAE;
+ }
+ }
vmcs_writel(CR4_READ_SHADOW, cr4);
vmcs_writel(GUEST_CR4, hw_cr4);
@@ -1787,7 +1853,7 @@ static void vmx_get_segment(struct kvm_vcpu *vcpu,
static int vmx_get_cpl(struct kvm_vcpu *vcpu)
{
- if (!(vcpu->arch.cr0 & X86_CR0_PE)) /* if real mode */
+ if (!kvm_read_cr0_bits(vcpu, X86_CR0_PE)) /* if real mode */
return 0;
if (vmx_get_rflags(vcpu) & X86_EFLAGS_VM) /* if virtual 8086 */
@@ -2042,7 +2108,7 @@ static bool cs_ss_rpl_check(struct kvm_vcpu *vcpu)
static bool guest_state_valid(struct kvm_vcpu *vcpu)
{
/* real mode guest state checks */
- if (!(vcpu->arch.cr0 & X86_CR0_PE)) {
+ if (!kvm_read_cr0_bits(vcpu, X86_CR0_PE)) {
if (!rmode_segment_valid(vcpu, VCPU_SREG_CS))
return false;
if (!rmode_segment_valid(vcpu, VCPU_SREG_SS))
@@ -2175,7 +2241,7 @@ static int alloc_apic_access_page(struct kvm *kvm)
struct kvm_userspace_memory_region kvm_userspace_mem;
int r = 0;
- down_write(&kvm->slots_lock);
+ mutex_lock(&kvm->slots_lock);
if (kvm->arch.apic_access_page)
goto out;
kvm_userspace_mem.slot = APIC_ACCESS_PAGE_PRIVATE_MEMSLOT;
@@ -2188,7 +2254,7 @@ static int alloc_apic_access_page(struct kvm *kvm)
kvm->arch.apic_access_page = gfn_to_page(kvm, 0xfee00);
out:
- up_write(&kvm->slots_lock);
+ mutex_unlock(&kvm->slots_lock);
return r;
}
@@ -2197,7 +2263,7 @@ static int alloc_identity_pagetable(struct kvm *kvm)
struct kvm_userspace_memory_region kvm_userspace_mem;
int r = 0;
- down_write(&kvm->slots_lock);
+ mutex_lock(&kvm->slots_lock);
if (kvm->arch.ept_identity_pagetable)
goto out;
kvm_userspace_mem.slot = IDENTITY_PAGETABLE_PRIVATE_MEMSLOT;
@@ -2212,7 +2278,7 @@ static int alloc_identity_pagetable(struct kvm *kvm)
kvm->arch.ept_identity_pagetable = gfn_to_page(kvm,
kvm->arch.ept_identity_map_addr >> PAGE_SHIFT);
out:
- up_write(&kvm->slots_lock);
+ mutex_unlock(&kvm->slots_lock);
return r;
}
@@ -2384,14 +2450,12 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx)
for (i = 0; i < NR_VMX_MSR; ++i) {
u32 index = vmx_msr_index[i];
u32 data_low, data_high;
- u64 data;
int j = vmx->nmsrs;
if (rdmsr_safe(index, &data_low, &data_high) < 0)
continue;
if (wrmsr_safe(index, data_low, data_high) < 0)
continue;
- data = data_low | ((u64)data_high << 32);
vmx->guest_msrs[j].index = i;
vmx->guest_msrs[j].data = 0;
vmx->guest_msrs[j].mask = -1ull;
@@ -2404,7 +2468,10 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx)
vmcs_write32(VM_ENTRY_CONTROLS, vmcs_config.vmentry_ctrl);
vmcs_writel(CR0_GUEST_HOST_MASK, ~0UL);
- vmcs_writel(CR4_GUEST_HOST_MASK, KVM_GUEST_CR4_MASK);
+ vmx->vcpu.arch.cr4_guest_owned_bits = KVM_CR4_GUEST_OWNED_BITS;
+ if (enable_ept)
+ vmx->vcpu.arch.cr4_guest_owned_bits |= X86_CR4_PGE;
+ vmcs_writel(CR4_GUEST_HOST_MASK, ~vmx->vcpu.arch.cr4_guest_owned_bits);
tsc_base = vmx->vcpu.kvm->arch.vm_init_tsc;
rdtscll(tsc_this);
@@ -2429,10 +2496,10 @@ static int vmx_vcpu_reset(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
u64 msr;
- int ret;
+ int ret, idx;
vcpu->arch.regs_avail = ~((1 << VCPU_REGS_RIP) | (1 << VCPU_REGS_RSP));
- down_read(&vcpu->kvm->slots_lock);
+ idx = srcu_read_lock(&vcpu->kvm->srcu);
if (!init_rmode(vmx->vcpu.kvm)) {
ret = -ENOMEM;
goto out;
@@ -2526,7 +2593,7 @@ static int vmx_vcpu_reset(struct kvm_vcpu *vcpu)
vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid);
vmx->vcpu.arch.cr0 = X86_CR0_NW | X86_CR0_CD | X86_CR0_ET;
- vmx_set_cr0(&vmx->vcpu, vmx->vcpu.arch.cr0); /* enter rmode */
+ vmx_set_cr0(&vmx->vcpu, kvm_read_cr0(vcpu)); /* enter rmode */
vmx_set_cr4(&vmx->vcpu, 0);
vmx_set_efer(&vmx->vcpu, 0);
vmx_fpu_activate(&vmx->vcpu);
@@ -2540,7 +2607,7 @@ static int vmx_vcpu_reset(struct kvm_vcpu *vcpu)
vmx->emulation_required = 0;
out:
- up_read(&vcpu->kvm->slots_lock);
+ srcu_read_unlock(&vcpu->kvm->srcu, idx);
return ret;
}
@@ -2940,10 +3007,9 @@ static int handle_cr(struct kvm_vcpu *vcpu)
};
break;
case 2: /* clts */
- vmx_fpu_deactivate(vcpu);
vcpu->arch.cr0 &= ~X86_CR0_TS;
- vmcs_writel(CR0_READ_SHADOW, vcpu->arch.cr0);
- vmx_fpu_activate(vcpu);
+ vmcs_writel(CR0_READ_SHADOW, kvm_read_cr0(vcpu));
+ trace_kvm_cr_write(0, kvm_read_cr0(vcpu));
skip_emulated_instruction(vcpu);
return 1;
case 1: /*mov from cr*/
@@ -2962,7 +3028,9 @@ static int handle_cr(struct kvm_vcpu *vcpu)
}
break;
case 3: /* lmsw */
- kvm_lmsw(vcpu, (exit_qualification >> LMSW_SOURCE_DATA_SHIFT) & 0x0f);
+ val = (exit_qualification >> LMSW_SOURCE_DATA_SHIFT) & 0x0f;
+ trace_kvm_cr_write(0, (kvm_read_cr0(vcpu) & ~0xful) | val);
+ kvm_lmsw(vcpu, val);
skip_emulated_instruction(vcpu);
return 1;
@@ -3035,7 +3103,7 @@ static int handle_dr(struct kvm_vcpu *vcpu)
vcpu->arch.eff_db[dr] = val;
break;
case 4 ... 5:
- if (vcpu->arch.cr4 & X86_CR4_DE)
+ if (kvm_read_cr4_bits(vcpu, X86_CR4_DE))
kvm_queue_exception(vcpu, UD_VECTOR);
break;
case 6:
@@ -3416,6 +3484,12 @@ static int handle_pause(struct kvm_vcpu *vcpu)
return 1;
}
+static int handle_invalid_op(struct kvm_vcpu *vcpu)
+{
+ kvm_queue_exception(vcpu, UD_VECTOR);
+ return 1;
+}
+
/*
* The exit handlers return 1 if the exit was handled fully and guest execution
* may resume. Otherwise they set the kvm_run parameter to indicate what needs
@@ -3453,6 +3527,8 @@ static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = {
[EXIT_REASON_EPT_VIOLATION] = handle_ept_violation,
[EXIT_REASON_EPT_MISCONFIG] = handle_ept_misconfig,
[EXIT_REASON_PAUSE_INSTRUCTION] = handle_pause,
+ [EXIT_REASON_MWAIT_INSTRUCTION] = handle_invalid_op,
+ [EXIT_REASON_MONITOR_INSTRUCTION] = handle_invalid_op,
};
static const int kvm_vmx_max_exit_handlers =
@@ -3936,32 +4012,83 @@ static u64 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio)
return ret;
}
+#define _ER(x) { EXIT_REASON_##x, #x }
+
static const struct trace_print_flags vmx_exit_reasons_str[] = {
- { EXIT_REASON_EXCEPTION_NMI, "exception" },
- { EXIT_REASON_EXTERNAL_INTERRUPT, "ext_irq" },
- { EXIT_REASON_TRIPLE_FAULT, "triple_fault" },
- { EXIT_REASON_NMI_WINDOW, "nmi_window" },
- { EXIT_REASON_IO_INSTRUCTION, "io_instruction" },
- { EXIT_REASON_CR_ACCESS, "cr_access" },
- { EXIT_REASON_DR_ACCESS, "dr_access" },
- { EXIT_REASON_CPUID, "cpuid" },
- { EXIT_REASON_MSR_READ, "rdmsr" },
- { EXIT_REASON_MSR_WRITE, "wrmsr" },
- { EXIT_REASON_PENDING_INTERRUPT, "interrupt_window" },
- { EXIT_REASON_HLT, "halt" },
- { EXIT_REASON_INVLPG, "invlpg" },
- { EXIT_REASON_VMCALL, "hypercall" },
- { EXIT_REASON_TPR_BELOW_THRESHOLD, "tpr_below_thres" },
- { EXIT_REASON_APIC_ACCESS, "apic_access" },
- { EXIT_REASON_WBINVD, "wbinvd" },
- { EXIT_REASON_TASK_SWITCH, "task_switch" },
- { EXIT_REASON_EPT_VIOLATION, "ept_violation" },
+ _ER(EXCEPTION_NMI),
+ _ER(EXTERNAL_INTERRUPT),
+ _ER(TRIPLE_FAULT),
+ _ER(PENDING_INTERRUPT),
+ _ER(NMI_WINDOW),
+ _ER(TASK_SWITCH),
+ _ER(CPUID),
+ _ER(HLT),
+ _ER(INVLPG),
+ _ER(RDPMC),
+ _ER(RDTSC),
+ _ER(VMCALL),
+ _ER(VMCLEAR),
+ _ER(VMLAUNCH),
+ _ER(VMPTRLD),
+ _ER(VMPTRST),
+ _ER(VMREAD),
+ _ER(VMRESUME),
+ _ER(VMWRITE),
+ _ER(VMOFF),
+ _ER(VMON),
+ _ER(CR_ACCESS),
+ _ER(DR_ACCESS),
+ _ER(IO_INSTRUCTION),
+ _ER(MSR_READ),
+ _ER(MSR_WRITE),
+ _ER(MWAIT_INSTRUCTION),
+ _ER(MONITOR_INSTRUCTION),
+ _ER(PAUSE_INSTRUCTION),
+ _ER(MCE_DURING_VMENTRY),
+ _ER(TPR_BELOW_THRESHOLD),
+ _ER(APIC_ACCESS),
+ _ER(EPT_VIOLATION),
+ _ER(EPT_MISCONFIG),
+ _ER(WBINVD),
{ -1, NULL }
};
-static bool vmx_gb_page_enable(void)
+#undef _ER
+
+static int vmx_get_lpage_level(void)
{
- return false;
+ if (enable_ept && !cpu_has_vmx_ept_1g_page())
+ return PT_DIRECTORY_LEVEL;
+ else
+ /* For shadow and EPT supported 1GB page */
+ return PT_PDPE_LEVEL;
+}
+
+static inline u32 bit(int bitno)
+{
+ return 1 << (bitno & 31);
+}
+
+static void vmx_cpuid_update(struct kvm_vcpu *vcpu)
+{
+ struct kvm_cpuid_entry2 *best;
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+ u32 exec_control;
+
+ vmx->rdtscp_enabled = false;
+ if (vmx_rdtscp_supported()) {
+ exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL);
+ if (exec_control & SECONDARY_EXEC_RDTSCP) {
+ best = kvm_find_cpuid_entry(vcpu, 0x80000001, 0);
+ if (best && (best->edx & bit(X86_FEATURE_RDTSCP)))
+ vmx->rdtscp_enabled = true;
+ else {
+ exec_control &= ~SECONDARY_EXEC_RDTSCP;
+ vmcs_write32(SECONDARY_VM_EXEC_CONTROL,
+ exec_control);
+ }
+ }
+ }
}
static struct kvm_x86_ops vmx_x86_ops = {
@@ -3990,6 +4117,7 @@ static struct kvm_x86_ops vmx_x86_ops = {
.set_segment = vmx_set_segment,
.get_cpl = vmx_get_cpl,
.get_cs_db_l_bits = vmx_get_cs_db_l_bits,
+ .decache_cr0_guest_bits = vmx_decache_cr0_guest_bits,
.decache_cr4_guest_bits = vmx_decache_cr4_guest_bits,
.set_cr0 = vmx_set_cr0,
.set_cr3 = vmx_set_cr3,
@@ -4002,6 +4130,7 @@ static struct kvm_x86_ops vmx_x86_ops = {
.cache_reg = vmx_cache_reg,
.get_rflags = vmx_get_rflags,
.set_rflags = vmx_set_rflags,
+ .fpu_deactivate = vmx_fpu_deactivate,
.tlb_flush = vmx_flush_tlb,
@@ -4027,7 +4156,11 @@ static struct kvm_x86_ops vmx_x86_ops = {
.get_mt_mask = vmx_get_mt_mask,
.exit_reasons_str = vmx_exit_reasons_str,
- .gb_page_enable = vmx_gb_page_enable,
+ .get_lpage_level = vmx_get_lpage_level,
+
+ .cpuid_update = vmx_cpuid_update,
+
+ .rdtscp_supported = vmx_rdtscp_supported,
};
static int __init vmx_init(void)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 1ddcad452add..5b05f4df0ae7 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -38,6 +38,7 @@
#include <linux/intel-iommu.h>
#include <linux/cpufreq.h>
#include <linux/user-return-notifier.h>
+#include <linux/srcu.h>
#include <trace/events/kvm.h>
#undef TRACE_INCLUDE_FILE
#define CREATE_TRACE_POINTS
@@ -93,16 +94,16 @@ module_param_named(ignore_msrs, ignore_msrs, bool, S_IRUGO | S_IWUSR);
struct kvm_shared_msrs_global {
int nr;
- struct kvm_shared_msr {
- u32 msr;
- u64 value;
- } msrs[KVM_NR_SHARED_MSRS];
+ u32 msrs[KVM_NR_SHARED_MSRS];
};
struct kvm_shared_msrs {
struct user_return_notifier urn;
bool registered;
- u64 current_value[KVM_NR_SHARED_MSRS];
+ struct kvm_shared_msr_values {
+ u64 host;
+ u64 curr;
+ } values[KVM_NR_SHARED_MSRS];
};
static struct kvm_shared_msrs_global __read_mostly shared_msrs_global;
@@ -147,53 +148,64 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
static void kvm_on_user_return(struct user_return_notifier *urn)
{
unsigned slot;
- struct kvm_shared_msr *global;
struct kvm_shared_msrs *locals
= container_of(urn, struct kvm_shared_msrs, urn);
+ struct kvm_shared_msr_values *values;
for (slot = 0; slot < shared_msrs_global.nr; ++slot) {
- global = &shared_msrs_global.msrs[slot];
- if (global->value != locals->current_value[slot]) {
- wrmsrl(global->msr, global->value);
- locals->current_value[slot] = global->value;
+ values = &locals->values[slot];
+ if (values->host != values->curr) {
+ wrmsrl(shared_msrs_global.msrs[slot], values->host);
+ values->curr = values->host;
}
}
locals->registered = false;
user_return_notifier_unregister(urn);
}
-void kvm_define_shared_msr(unsigned slot, u32 msr)
+static void shared_msr_update(unsigned slot, u32 msr)
{
- int cpu;
+ struct kvm_shared_msrs *smsr;
u64 value;
+ smsr = &__get_cpu_var(shared_msrs);
+ /* only read, and nobody should modify it at this time,
+ * so don't need lock */
+ if (slot >= shared_msrs_global.nr) {
+ printk(KERN_ERR "kvm: invalid MSR slot!");
+ return;
+ }
+ rdmsrl_safe(msr, &value);
+ smsr->values[slot].host = value;
+ smsr->values[slot].curr = value;
+}
+
+void kvm_define_shared_msr(unsigned slot, u32 msr)
+{
if (slot >= shared_msrs_global.nr)
shared_msrs_global.nr = slot + 1;
- shared_msrs_global.msrs[slot].msr = msr;
- rdmsrl_safe(msr, &value);
- shared_msrs_global.msrs[slot].value = value;
- for_each_online_cpu(cpu)
- per_cpu(shared_msrs, cpu).current_value[slot] = value;
+ shared_msrs_global.msrs[slot] = msr;
+ /* we need ensured the shared_msr_global have been updated */
+ smp_wmb();
}
EXPORT_SYMBOL_GPL(kvm_define_shared_msr);
static void kvm_shared_msr_cpu_online(void)
{
unsigned i;
- struct kvm_shared_msrs *locals = &__get_cpu_var(shared_msrs);
for (i = 0; i < shared_msrs_global.nr; ++i)
- locals->current_value[i] = shared_msrs_global.msrs[i].value;
+ shared_msr_update(i, shared_msrs_global.msrs[i]);
}
void kvm_set_shared_msr(unsigned slot, u64 value, u64 mask)
{
struct kvm_shared_msrs *smsr = &__get_cpu_var(shared_msrs);
- if (((value ^ smsr->current_value[slot]) & mask) == 0)
+ if (((value ^ smsr->values[slot].curr) & mask) == 0)
return;
- smsr->current_value[slot] = value;
- wrmsrl(shared_msrs_global.msrs[slot].msr, value);
+ smsr->values[slot].curr = value;
+ wrmsrl(shared_msrs_global.msrs[slot], value);
if (!smsr->registered) {
smsr->urn.on_user_return = kvm_on_user_return;
user_return_notifier_register(&smsr->urn);
@@ -257,12 +269,68 @@ void kvm_set_apic_base(struct kvm_vcpu *vcpu, u64 data)
}
EXPORT_SYMBOL_GPL(kvm_set_apic_base);
+#define EXCPT_BENIGN 0
+#define EXCPT_CONTRIBUTORY 1
+#define EXCPT_PF 2
+
+static int exception_class(int vector)
+{
+ switch (vector) {
+ case PF_VECTOR:
+ return EXCPT_PF;
+ case DE_VECTOR:
+ case TS_VECTOR:
+ case NP_VECTOR:
+ case SS_VECTOR:
+ case GP_VECTOR:
+ return EXCPT_CONTRIBUTORY;
+ default:
+ break;
+ }
+ return EXCPT_BENIGN;
+}
+
+static void kvm_multiple_exception(struct kvm_vcpu *vcpu,
+ unsigned nr, bool has_error, u32 error_code)
+{
+ u32 prev_nr;
+ int class1, class2;
+
+ if (!vcpu->arch.exception.pending) {
+ queue:
+ vcpu->arch.exception.pending = true;
+ vcpu->arch.exception.has_error_code = has_error;
+ vcpu->arch.exception.nr = nr;
+ vcpu->arch.exception.error_code = error_code;
+ return;
+ }
+
+ /* to check exception */
+ prev_nr = vcpu->arch.exception.nr;
+ if (prev_nr == DF_VECTOR) {
+ /* triple fault -> shutdown */
+ set_bit(KVM_REQ_TRIPLE_FAULT, &vcpu->requests);
+ return;
+ }
+ class1 = exception_class(prev_nr);
+ class2 = exception_class(nr);
+ if ((class1 == EXCPT_CONTRIBUTORY && class2 == EXCPT_CONTRIBUTORY)
+ || (class1 == EXCPT_PF && class2 != EXCPT_BENIGN)) {
+ /* generate double fault per SDM Table 5-5 */
+ vcpu->arch.exception.pending = true;
+ vcpu->arch.exception.has_error_code = true;
+ vcpu->arch.exception.nr = DF_VECTOR;
+ vcpu->arch.exception.error_code = 0;
+ } else
+ /* replace previous exception with a new one in a hope
+ that instruction re-execution will regenerate lost
+ exception */
+ goto queue;
+}
+
void kvm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr)
{
- WARN_ON(vcpu->arch.exception.pending);
- vcpu->arch.exception.pending = true;
- vcpu->arch.exception.has_error_code = false;
- vcpu->arch.exception.nr = nr;
+ kvm_multiple_exception(vcpu, nr, false, 0);
}
EXPORT_SYMBOL_GPL(kvm_queue_exception);
@@ -270,25 +338,6 @@ void kvm_inject_page_fault(struct kvm_vcpu *vcpu, unsigned long addr,
u32 error_code)
{
++vcpu->stat.pf_guest;
-
- if (vcpu->arch.exception.pending) {
- switch(vcpu->arch.exception.nr) {
- case DF_VECTOR:
- /* triple fault -> shutdown */
- set_bit(KVM_REQ_TRIPLE_FAULT, &vcpu->requests);
- return;
- case PF_VECTOR:
- vcpu->arch.exception.nr = DF_VECTOR;
- vcpu->arch.exception.error_code = 0;
- return;
- default:
- /* replace previous exception with a new one in a hope
- that instruction re-execution will regenerate lost
- exception */
- vcpu->arch.exception.pending = false;
- break;
- }
- }
vcpu->arch.cr2 = addr;
kvm_queue_exception_e(vcpu, PF_VECTOR, error_code);
}
@@ -301,11 +350,7 @@ EXPORT_SYMBOL_GPL(kvm_inject_nmi);
void kvm_queue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code)
{
- WARN_ON(vcpu->arch.exception.pending);
- vcpu->arch.exception.pending = true;
- vcpu->arch.exception.has_error_code = true;
- vcpu->arch.exception.nr = nr;
- vcpu->arch.exception.error_code = error_code;
+ kvm_multiple_exception(vcpu, nr, true, error_code);
}
EXPORT_SYMBOL_GPL(kvm_queue_exception_e);
@@ -383,9 +428,11 @@ out:
void kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
{
+ cr0 |= X86_CR0_ET;
+
if (cr0 & CR0_RESERVED_BITS) {
printk(KERN_DEBUG "set_cr0: 0x%lx #GP, reserved bits 0x%lx\n",
- cr0, vcpu->arch.cr0);
+ cr0, kvm_read_cr0(vcpu));
kvm_inject_gp(vcpu, 0);
return;
}
@@ -443,13 +490,13 @@ EXPORT_SYMBOL_GPL(kvm_set_cr0);
void kvm_lmsw(struct kvm_vcpu *vcpu, unsigned long msw)
{
- kvm_set_cr0(vcpu, (vcpu->arch.cr0 & ~0x0ful) | (msw & 0x0f));
+ kvm_set_cr0(vcpu, kvm_read_cr0_bits(vcpu, ~0x0ful) | (msw & 0x0f));
}
EXPORT_SYMBOL_GPL(kvm_lmsw);
void kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
{
- unsigned long old_cr4 = vcpu->arch.cr4;
+ unsigned long old_cr4 = kvm_read_cr4(vcpu);
unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE;
if (cr4 & CR4_RESERVED_BITS) {
@@ -575,9 +622,11 @@ static inline u32 bit(int bitno)
* kvm-specific. Those are put in the beginning of the list.
*/
-#define KVM_SAVE_MSRS_BEGIN 2
+#define KVM_SAVE_MSRS_BEGIN 5
static u32 msrs_to_save[] = {
MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK,
+ HV_X64_MSR_GUEST_OS_ID, HV_X64_MSR_HYPERCALL,
+ HV_X64_MSR_APIC_ASSIST_PAGE,
MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP,
MSR_K6_STAR,
#ifdef CONFIG_X86_64
@@ -958,6 +1007,100 @@ out:
return r;
}
+static bool kvm_hv_hypercall_enabled(struct kvm *kvm)
+{
+ return kvm->arch.hv_hypercall & HV_X64_MSR_HYPERCALL_ENABLE;
+}
+
+static bool kvm_hv_msr_partition_wide(u32 msr)
+{
+ bool r = false;
+ switch (msr) {
+ case HV_X64_MSR_GUEST_OS_ID:
+ case HV_X64_MSR_HYPERCALL:
+ r = true;
+ break;
+ }
+
+ return r;
+}
+
+static int set_msr_hyperv_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data)
+{
+ struct kvm *kvm = vcpu->kvm;
+
+ switch (msr) {
+ case HV_X64_MSR_GUEST_OS_ID:
+ kvm->arch.hv_guest_os_id = data;
+ /* setting guest os id to zero disables hypercall page */
+ if (!kvm->arch.hv_guest_os_id)
+ kvm->arch.hv_hypercall &= ~HV_X64_MSR_HYPERCALL_ENABLE;
+ break;
+ case HV_X64_MSR_HYPERCALL: {
+ u64 gfn;
+ unsigned long addr;
+ u8 instructions[4];
+
+ /* if guest os id is not set hypercall should remain disabled */
+ if (!kvm->arch.hv_guest_os_id)
+ break;
+ if (!(data & HV_X64_MSR_HYPERCALL_ENABLE)) {
+ kvm->arch.hv_hypercall = data;
+ break;
+ }
+ gfn = data >> HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_SHIFT;
+ addr = gfn_to_hva(kvm, gfn);
+ if (kvm_is_error_hva(addr))
+ return 1;
+ kvm_x86_ops->patch_hypercall(vcpu, instructions);
+ ((unsigned char *)instructions)[3] = 0xc3; /* ret */
+ if (copy_to_user((void __user *)addr, instructions, 4))
+ return 1;
+ kvm->arch.hv_hypercall = data;
+ break;
+ }
+ default:
+ pr_unimpl(vcpu, "HYPER-V unimplemented wrmsr: 0x%x "
+ "data 0x%llx\n", msr, data);
+ return 1;
+ }
+ return 0;
+}
+
+static int set_msr_hyperv(struct kvm_vcpu *vcpu, u32 msr, u64 data)
+{
+ switch (msr) {
+ case HV_X64_MSR_APIC_ASSIST_PAGE: {
+ unsigned long addr;
+
+ if (!(data & HV_X64_MSR_APIC_ASSIST_PAGE_ENABLE)) {
+ vcpu->arch.hv_vapic = data;
+ break;
+ }
+ addr = gfn_to_hva(vcpu->kvm, data >>
+ HV_X64_MSR_APIC_ASSIST_PAGE_ADDRESS_SHIFT);
+ if (kvm_is_error_hva(addr))
+ return 1;
+ if (clear_user((void __user *)addr, PAGE_SIZE))
+ return 1;
+ vcpu->arch.hv_vapic = data;
+ break;
+ }
+ case HV_X64_MSR_EOI:
+ return kvm_hv_vapic_msr_write(vcpu, APIC_EOI, data);
+ case HV_X64_MSR_ICR:
+ return kvm_hv_vapic_msr_write(vcpu, APIC_ICR, data);
+ case HV_X64_MSR_TPR:
+ return kvm_hv_vapic_msr_write(vcpu, APIC_TASKPRI, data);
+ default:
+ pr_unimpl(vcpu, "HYPER-V unimplemented wrmsr: 0x%x "
+ "data 0x%llx\n", msr, data);
+ return 1;
+ }
+
+ return 0;
+}
+
int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)
{
switch (msr) {
@@ -1072,6 +1215,16 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)
pr_unimpl(vcpu, "unimplemented perfctr wrmsr: "
"0x%x data 0x%llx\n", msr, data);
break;
+ case HV_X64_MSR_GUEST_OS_ID ... HV_X64_MSR_SINT15:
+ if (kvm_hv_msr_partition_wide(msr)) {
+ int r;
+ mutex_lock(&vcpu->kvm->lock);
+ r = set_msr_hyperv_pw(vcpu, msr, data);
+ mutex_unlock(&vcpu->kvm->lock);
+ return r;
+ } else
+ return set_msr_hyperv(vcpu, msr, data);
+ break;
default:
if (msr && (msr == vcpu->kvm->arch.xen_hvm_config.msr))
return xen_hvm_config(vcpu, data);
@@ -1171,6 +1324,54 @@ static int get_msr_mce(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
return 0;
}
+static int get_msr_hyperv_pw(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
+{
+ u64 data = 0;
+ struct kvm *kvm = vcpu->kvm;
+
+ switch (msr) {
+ case HV_X64_MSR_GUEST_OS_ID:
+ data = kvm->arch.hv_guest_os_id;
+ break;
+ case HV_X64_MSR_HYPERCALL:
+ data = kvm->arch.hv_hypercall;
+ break;
+ default:
+ pr_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr);
+ return 1;
+ }
+
+ *pdata = data;
+ return 0;
+}
+
+static int get_msr_hyperv(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
+{
+ u64 data = 0;
+
+ switch (msr) {
+ case HV_X64_MSR_VP_INDEX: {
+ int r;
+ struct kvm_vcpu *v;
+ kvm_for_each_vcpu(r, v, vcpu->kvm)
+ if (v == vcpu)
+ data = r;
+ break;
+ }
+ case HV_X64_MSR_EOI:
+ return kvm_hv_vapic_msr_read(vcpu, APIC_EOI, pdata);
+ case HV_X64_MSR_ICR:
+ return kvm_hv_vapic_msr_read(vcpu, APIC_ICR, pdata);
+ case HV_X64_MSR_TPR:
+ return kvm_hv_vapic_msr_read(vcpu, APIC_TASKPRI, pdata);
+ default:
+ pr_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr);
+ return 1;
+ }
+ *pdata = data;
+ return 0;
+}
+
int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
{
u64 data;
@@ -1237,6 +1438,16 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
case MSR_IA32_MCG_STATUS:
case MSR_IA32_MC0_CTL ... MSR_IA32_MC0_CTL + 4 * KVM_MAX_MCE_BANKS - 1:
return get_msr_mce(vcpu, msr, pdata);
+ case HV_X64_MSR_GUEST_OS_ID ... HV_X64_MSR_SINT15:
+ if (kvm_hv_msr_partition_wide(msr)) {
+ int r;
+ mutex_lock(&vcpu->kvm->lock);
+ r = get_msr_hyperv_pw(vcpu, msr, pdata);
+ mutex_unlock(&vcpu->kvm->lock);
+ return r;
+ } else
+ return get_msr_hyperv(vcpu, msr, pdata);
+ break;
default:
if (!ignore_msrs) {
pr_unimpl(vcpu, "unhandled rdmsr: 0x%x\n", msr);
@@ -1262,15 +1473,15 @@ static int __msr_io(struct kvm_vcpu *vcpu, struct kvm_msrs *msrs,
int (*do_msr)(struct kvm_vcpu *vcpu,
unsigned index, u64 *data))
{
- int i;
+ int i, idx;
vcpu_load(vcpu);
- down_read(&vcpu->kvm->slots_lock);
+ idx = srcu_read_lock(&vcpu->kvm->srcu);
for (i = 0; i < msrs->nmsrs; ++i)
if (do_msr(vcpu, entries[i].index, &entries[i].data))
break;
- up_read(&vcpu->kvm->slots_lock);
+ srcu_read_unlock(&vcpu->kvm->srcu, idx);
vcpu_put(vcpu);
@@ -1352,6 +1563,9 @@ int kvm_dev_ioctl_check_extension(long ext)
case KVM_CAP_XEN_HVM:
case KVM_CAP_ADJUST_CLOCK:
case KVM_CAP_VCPU_EVENTS:
+ case KVM_CAP_HYPERV:
+ case KVM_CAP_HYPERV_VAPIC:
+ case KVM_CAP_HYPERV_SPIN:
r = 1;
break;
case KVM_CAP_COALESCED_MMIO:
@@ -1465,8 +1679,8 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
{
- kvm_x86_ops->vcpu_put(vcpu);
kvm_put_guest_fpu(vcpu);
+ kvm_x86_ops->vcpu_put(vcpu);
}
static int is_efer_nx(void)
@@ -1531,6 +1745,7 @@ static int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu,
cpuid_fix_nx_cap(vcpu);
r = 0;
kvm_apic_set_version(vcpu);
+ kvm_x86_ops->cpuid_update(vcpu);
out_free:
vfree(cpuid_entries);
@@ -1553,6 +1768,7 @@ static int kvm_vcpu_ioctl_set_cpuid2(struct kvm_vcpu *vcpu,
goto out;
vcpu->arch.cpuid_nent = cpuid->nent;
kvm_apic_set_version(vcpu);
+ kvm_x86_ops->cpuid_update(vcpu);
return 0;
out:
@@ -1595,12 +1811,15 @@ static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
u32 index, int *nent, int maxnent)
{
unsigned f_nx = is_efer_nx() ? F(NX) : 0;
- unsigned f_gbpages = kvm_x86_ops->gb_page_enable() ? F(GBPAGES) : 0;
#ifdef CONFIG_X86_64
+ unsigned f_gbpages = (kvm_x86_ops->get_lpage_level() == PT_PDPE_LEVEL)
+ ? F(GBPAGES) : 0;
unsigned f_lm = F(LM);
#else
+ unsigned f_gbpages = 0;
unsigned f_lm = 0;
#endif
+ unsigned f_rdtscp = kvm_x86_ops->rdtscp_supported() ? F(RDTSCP) : 0;
/* cpuid 1.edx */
const u32 kvm_supported_word0_x86_features =
@@ -1620,7 +1839,7 @@ static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
F(MTRR) | F(PGE) | F(MCA) | F(CMOV) |
F(PAT) | F(PSE36) | 0 /* Reserved */ |
f_nx | 0 /* Reserved */ | F(MMXEXT) | F(MMX) |
- F(FXSR) | F(FXSR_OPT) | f_gbpages | 0 /* RDTSCP */ |
+ F(FXSR) | F(FXSR_OPT) | f_gbpages | f_rdtscp |
0 /* Reserved */ | f_lm | F(3DNOWEXT) | F(3DNOW);
/* cpuid 1.ecx */
const u32 kvm_supported_word4_x86_features =
@@ -1867,7 +2086,7 @@ static int kvm_vcpu_ioctl_x86_set_mce(struct kvm_vcpu *vcpu,
return 0;
if (mce->status & MCI_STATUS_UC) {
if ((vcpu->arch.mcg_status & MCG_STATUS_MCIP) ||
- !(vcpu->arch.cr4 & X86_CR4_MCE)) {
+ !kvm_read_cr4_bits(vcpu, X86_CR4_MCE)) {
printk(KERN_DEBUG "kvm: set_mce: "
"injects mce exception while "
"previous one is in progress!\n");
@@ -2161,14 +2380,14 @@ static int kvm_vm_ioctl_set_nr_mmu_pages(struct kvm *kvm,
if (kvm_nr_mmu_pages < KVM_MIN_ALLOC_MMU_PAGES)
return -EINVAL;
- down_write(&kvm->slots_lock);
+ mutex_lock(&kvm->slots_lock);
spin_lock(&kvm->mmu_lock);
kvm_mmu_change_mmu_pages(kvm, kvm_nr_mmu_pages);
kvm->arch.n_requested_mmu_pages = kvm_nr_mmu_pages;
spin_unlock(&kvm->mmu_lock);
- up_write(&kvm->slots_lock);
+ mutex_unlock(&kvm->slots_lock);
return 0;
}
@@ -2177,13 +2396,35 @@ static int kvm_vm_ioctl_get_nr_mmu_pages(struct kvm *kvm)
return kvm->arch.n_alloc_mmu_pages;
}
+gfn_t unalias_gfn_instantiation(struct kvm *kvm, gfn_t gfn)
+{
+ int i;
+ struct kvm_mem_alias *alias;
+ struct kvm_mem_aliases *aliases;
+
+ aliases = rcu_dereference(kvm->arch.aliases);
+
+ for (i = 0; i < aliases->naliases; ++i) {
+ alias = &aliases->aliases[i];
+ if (alias->flags & KVM_ALIAS_INVALID)
+ continue;
+ if (gfn >= alias->base_gfn
+ && gfn < alias->base_gfn + alias->npages)
+ return alias->target_gfn + gfn - alias->base_gfn;
+ }
+ return gfn;
+}
+
gfn_t unalias_gfn(struct kvm *kvm, gfn_t gfn)
{
int i;
struct kvm_mem_alias *alias;
+ struct kvm_mem_aliases *aliases;
+
+ aliases = rcu_dereference(kvm->arch.aliases);
- for (i = 0; i < kvm->arch.naliases; ++i) {
- alias = &kvm->arch.aliases[i];
+ for (i = 0; i < aliases->naliases; ++i) {
+ alias = &aliases->aliases[i];
if (gfn >= alias->base_gfn
&& gfn < alias->base_gfn + alias->npages)
return alias->target_gfn + gfn - alias->base_gfn;
@@ -2201,6 +2442,7 @@ static int kvm_vm_ioctl_set_memory_alias(struct kvm *kvm,
{
int r, n;
struct kvm_mem_alias *p;
+ struct kvm_mem_aliases *aliases, *old_aliases;
r = -EINVAL;
/* General sanity checks */
@@ -2217,26 +2459,48 @@ static int kvm_vm_ioctl_set_memory_alias(struct kvm *kvm,
< alias->target_phys_addr)
goto out;
- down_write(&kvm->slots_lock);
- spin_lock(&kvm->mmu_lock);
+ r = -ENOMEM;
+ aliases = kzalloc(sizeof(struct kvm_mem_aliases), GFP_KERNEL);
+ if (!aliases)
+ goto out;
- p = &kvm->arch.aliases[alias->slot];
+ mutex_lock(&kvm->slots_lock);
+
+ /* invalidate any gfn reference in case of deletion/shrinking */
+ memcpy(aliases, kvm->arch.aliases, sizeof(struct kvm_mem_aliases));
+ aliases->aliases[alias->slot].flags |= KVM_ALIAS_INVALID;
+ old_aliases = kvm->arch.aliases;
+ rcu_assign_pointer(kvm->arch.aliases, aliases);
+ synchronize_srcu_expedited(&kvm->srcu);
+ kvm_mmu_zap_all(kvm);
+ kfree(old_aliases);
+
+ r = -ENOMEM;
+ aliases = kzalloc(sizeof(struct kvm_mem_aliases), GFP_KERNEL);
+ if (!aliases)
+ goto out_unlock;
+
+ memcpy(aliases, kvm->arch.aliases, sizeof(struct kvm_mem_aliases));
+
+ p = &aliases->aliases[alias->slot];
p->base_gfn = alias->guest_phys_addr >> PAGE_SHIFT;
p->npages = alias->memory_size >> PAGE_SHIFT;
p->target_gfn = alias->target_phys_addr >> PAGE_SHIFT;
+ p->flags &= ~(KVM_ALIAS_INVALID);
for (n = KVM_ALIAS_SLOTS; n > 0; --n)
- if (kvm->arch.aliases[n - 1].npages)
+ if (aliases->aliases[n - 1].npages)
break;
- kvm->arch.naliases = n;
-
- spin_unlock(&kvm->mmu_lock);
- kvm_mmu_zap_all(kvm);
+ aliases->naliases = n;
- up_write(&kvm->slots_lock);
-
- return 0;
+ old_aliases = kvm->arch.aliases;
+ rcu_assign_pointer(kvm->arch.aliases, aliases);
+ synchronize_srcu_expedited(&kvm->srcu);
+ kfree(old_aliases);
+ r = 0;
+out_unlock:
+ mutex_unlock(&kvm->slots_lock);
out:
return r;
}
@@ -2365,29 +2629,62 @@ static int kvm_vm_ioctl_reinject(struct kvm *kvm,
int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
struct kvm_dirty_log *log)
{
- int r;
- int n;
+ int r, n, i;
struct kvm_memory_slot *memslot;
- int is_dirty = 0;
+ unsigned long is_dirty = 0;
+ unsigned long *dirty_bitmap = NULL;
- down_write(&kvm->slots_lock);
+ mutex_lock(&kvm->slots_lock);
- r = kvm_get_dirty_log(kvm, log, &is_dirty);
- if (r)
+ r = -EINVAL;
+ if (log->slot >= KVM_MEMORY_SLOTS)
+ goto out;
+
+ memslot = &kvm->memslots->memslots[log->slot];
+ r = -ENOENT;
+ if (!memslot->dirty_bitmap)
+ goto out;
+
+ n = ALIGN(memslot->npages, BITS_PER_LONG) / 8;
+
+ r = -ENOMEM;
+ dirty_bitmap = vmalloc(n);
+ if (!dirty_bitmap)
goto out;
+ memset(dirty_bitmap, 0, n);
+
+ for (i = 0; !is_dirty && i < n/sizeof(long); i++)
+ is_dirty = memslot->dirty_bitmap[i];
/* If nothing is dirty, don't bother messing with page tables. */
if (is_dirty) {
+ struct kvm_memslots *slots, *old_slots;
+
spin_lock(&kvm->mmu_lock);
kvm_mmu_slot_remove_write_access(kvm, log->slot);
spin_unlock(&kvm->mmu_lock);
- memslot = &kvm->memslots[log->slot];
- n = ALIGN(memslot->npages, BITS_PER_LONG) / 8;
- memset(memslot->dirty_bitmap, 0, n);
+
+ slots = kzalloc(sizeof(struct kvm_memslots), GFP_KERNEL);
+ if (!slots)
+ goto out_free;
+
+ memcpy(slots, kvm->memslots, sizeof(struct kvm_memslots));
+ slots->memslots[log->slot].dirty_bitmap = dirty_bitmap;
+
+ old_slots = kvm->memslots;
+ rcu_assign_pointer(kvm->memslots, slots);
+ synchronize_srcu_expedited(&kvm->srcu);
+ dirty_bitmap = old_slots->memslots[log->slot].dirty_bitmap;
+ kfree(old_slots);
}
+
r = 0;
+ if (copy_to_user(log->dirty_bitmap, dirty_bitmap, n))
+ r = -EFAULT;
+out_free:
+ vfree(dirty_bitmap);
out:
- up_write(&kvm->slots_lock);
+ mutex_unlock(&kvm->slots_lock);
return r;
}
@@ -2500,7 +2797,7 @@ long kvm_arch_vm_ioctl(struct file *filp,
sizeof(struct kvm_pit_config)))
goto out;
create_pit:
- down_write(&kvm->slots_lock);
+ mutex_lock(&kvm->slots_lock);
r = -EEXIST;
if (kvm->arch.vpit)
goto create_pit_unlock;
@@ -2509,7 +2806,7 @@ long kvm_arch_vm_ioctl(struct file *filp,
if (kvm->arch.vpit)
r = 0;
create_pit_unlock:
- up_write(&kvm->slots_lock);
+ mutex_unlock(&kvm->slots_lock);
break;
case KVM_IRQ_LINE_STATUS:
case KVM_IRQ_LINE: {
@@ -2726,7 +3023,7 @@ static int vcpu_mmio_write(struct kvm_vcpu *vcpu, gpa_t addr, int len,
!kvm_iodevice_write(&vcpu->arch.apic->dev, addr, len, v))
return 0;
- return kvm_io_bus_write(&vcpu->kvm->mmio_bus, addr, len, v);
+ return kvm_io_bus_write(vcpu->kvm, KVM_MMIO_BUS, addr, len, v);
}
static int vcpu_mmio_read(struct kvm_vcpu *vcpu, gpa_t addr, int len, void *v)
@@ -2735,7 +3032,7 @@ static int vcpu_mmio_read(struct kvm_vcpu *vcpu, gpa_t addr, int len, void *v)
!kvm_iodevice_read(&vcpu->arch.apic->dev, addr, len, v))
return 0;
- return kvm_io_bus_read(&vcpu->kvm->mmio_bus, addr, len, v);
+ return kvm_io_bus_read(vcpu->kvm, KVM_MMIO_BUS, addr, len, v);
}
static int kvm_read_guest_virt(gva_t addr, void *val, unsigned int bytes,
@@ -2968,7 +3265,7 @@ int emulate_invlpg(struct kvm_vcpu *vcpu, gva_t address)
int emulate_clts(struct kvm_vcpu *vcpu)
{
- kvm_x86_ops->set_cr0(vcpu, vcpu->arch.cr0 & ~X86_CR0_TS);
+ kvm_x86_ops->set_cr0(vcpu, kvm_read_cr0_bits(vcpu, ~X86_CR0_TS));
return X86EMUL_CONTINUE;
}
@@ -3220,11 +3517,12 @@ static int kernel_pio(struct kvm_vcpu *vcpu, void *pd)
int r;
if (vcpu->arch.pio.in)
- r = kvm_io_bus_read(&vcpu->kvm->pio_bus, vcpu->arch.pio.port,
+ r = kvm_io_bus_read(vcpu->kvm, KVM_PIO_BUS, vcpu->arch.pio.port,
vcpu->arch.pio.size, pd);
else
- r = kvm_io_bus_write(&vcpu->kvm->pio_bus, vcpu->arch.pio.port,
- vcpu->arch.pio.size, pd);
+ r = kvm_io_bus_write(vcpu->kvm, KVM_PIO_BUS,
+ vcpu->arch.pio.port, vcpu->arch.pio.size,
+ pd);
return r;
}
@@ -3235,7 +3533,7 @@ static int pio_string_write(struct kvm_vcpu *vcpu)
int i, r = 0;
for (i = 0; i < io->cur_count; i++) {
- if (kvm_io_bus_write(&vcpu->kvm->pio_bus,
+ if (kvm_io_bus_write(vcpu->kvm, KVM_PIO_BUS,
io->port, io->size, pd)) {
r = -EOPNOTSUPP;
break;
@@ -3488,11 +3786,77 @@ static inline gpa_t hc_gpa(struct kvm_vcpu *vcpu, unsigned long a0,
return a0 | ((gpa_t)a1 << 32);
}
+int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
+{
+ u64 param, ingpa, outgpa, ret;
+ uint16_t code, rep_idx, rep_cnt, res = HV_STATUS_SUCCESS, rep_done = 0;
+ bool fast, longmode;
+ int cs_db, cs_l;
+
+ /*
+ * hypercall generates UD from non zero cpl and real mode
+ * per HYPER-V spec
+ */
+ if (kvm_x86_ops->get_cpl(vcpu) != 0 ||
+ !kvm_read_cr0_bits(vcpu, X86_CR0_PE)) {
+ kvm_queue_exception(vcpu, UD_VECTOR);
+ return 0;
+ }
+
+ kvm_x86_ops->get_cs_db_l_bits(vcpu, &cs_db, &cs_l);
+ longmode = is_long_mode(vcpu) && cs_l == 1;
+
+ if (!longmode) {
+ param = ((u64)kvm_register_read(vcpu, VCPU_REGS_RDX) << 32) |
+ (kvm_register_read(vcpu, VCPU_REGS_RAX) & 0xffffffff);
+ ingpa = ((u64)kvm_register_read(vcpu, VCPU_REGS_RBX) << 32) |
+ (kvm_register_read(vcpu, VCPU_REGS_RCX) & 0xffffffff);
+ outgpa = ((u64)kvm_register_read(vcpu, VCPU_REGS_RDI) << 32) |
+ (kvm_register_read(vcpu, VCPU_REGS_RSI) & 0xffffffff);
+ }
+#ifdef CONFIG_X86_64
+ else {
+ param = kvm_register_read(vcpu, VCPU_REGS_RCX);
+ ingpa = kvm_register_read(vcpu, VCPU_REGS_RDX);
+ outgpa = kvm_register_read(vcpu, VCPU_REGS_R8);
+ }
+#endif
+
+ code = param & 0xffff;
+ fast = (param >> 16) & 0x1;
+ rep_cnt = (param >> 32) & 0xfff;
+ rep_idx = (param >> 48) & 0xfff;
+
+ trace_kvm_hv_hypercall(code, fast, rep_cnt, rep_idx, ingpa, outgpa);
+
+ switch (code) {
+ case HV_X64_HV_NOTIFY_LONG_SPIN_WAIT:
+ kvm_vcpu_on_spin(vcpu);
+ break;
+ default:
+ res = HV_STATUS_INVALID_HYPERCALL_CODE;
+ break;
+ }
+
+ ret = res | (((u64)rep_done & 0xfff) << 32);
+ if (longmode) {
+ kvm_register_write(vcpu, VCPU_REGS_RAX, ret);
+ } else {
+ kvm_register_write(vcpu, VCPU_REGS_RDX, ret >> 32);
+ kvm_register_write(vcpu, VCPU_REGS_RAX, ret & 0xffffffff);
+ }
+
+ return 1;
+}
+
int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
{
unsigned long nr, a0, a1, a2, a3, ret;
int r = 1;
+ if (kvm_hv_hypercall_enabled(vcpu->kvm))
+ return kvm_hv_hypercall(vcpu);
+
nr = kvm_register_read(vcpu, VCPU_REGS_RAX);
a0 = kvm_register_read(vcpu, VCPU_REGS_RBX);
a1 = kvm_register_read(vcpu, VCPU_REGS_RCX);
@@ -3584,10 +3948,9 @@ unsigned long realmode_get_cr(struct kvm_vcpu *vcpu, int cr)
{
unsigned long value;
- kvm_x86_ops->decache_cr4_guest_bits(vcpu);
switch (cr) {
case 0:
- value = vcpu->arch.cr0;
+ value = kvm_read_cr0(vcpu);
break;
case 2:
value = vcpu->arch.cr2;
@@ -3596,7 +3959,7 @@ unsigned long realmode_get_cr(struct kvm_vcpu *vcpu, int cr)
value = vcpu->arch.cr3;
break;
case 4:
- value = vcpu->arch.cr4;
+ value = kvm_read_cr4(vcpu);
break;
case 8:
value = kvm_get_cr8(vcpu);
@@ -3614,7 +3977,7 @@ void realmode_set_cr(struct kvm_vcpu *vcpu, int cr, unsigned long val,
{
switch (cr) {
case 0:
- kvm_set_cr0(vcpu, mk_cr_64(vcpu->arch.cr0, val));
+ kvm_set_cr0(vcpu, mk_cr_64(kvm_read_cr0(vcpu), val));
*rflags = kvm_get_rflags(vcpu);
break;
case 2:
@@ -3624,7 +3987,7 @@ void realmode_set_cr(struct kvm_vcpu *vcpu, int cr, unsigned long val,
kvm_set_cr3(vcpu, val);
break;
case 4:
- kvm_set_cr4(vcpu, mk_cr_64(vcpu->arch.cr4, val));
+ kvm_set_cr4(vcpu, mk_cr_64(kvm_read_cr4(vcpu), val));
break;
case 8:
kvm_set_cr8(vcpu, val & 0xfUL);
@@ -3691,6 +4054,7 @@ struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu,
}
return best;
}
+EXPORT_SYMBOL_GPL(kvm_find_cpuid_entry);
int cpuid_maxphyaddr(struct kvm_vcpu *vcpu)
{
@@ -3774,14 +4138,15 @@ static void vapic_enter(struct kvm_vcpu *vcpu)
static void vapic_exit(struct kvm_vcpu *vcpu)
{
struct kvm_lapic *apic = vcpu->arch.apic;
+ int idx;
if (!apic || !apic->vapic_addr)
return;
- down_read(&vcpu->kvm->slots_lock);
+ idx = srcu_read_lock(&vcpu->kvm->srcu);
kvm_release_page_dirty(apic->vapic_page);
mark_page_dirty(vcpu->kvm, apic->vapic_addr >> PAGE_SHIFT);
- up_read(&vcpu->kvm->slots_lock);
+ srcu_read_unlock(&vcpu->kvm->srcu, idx);
}
static void update_cr8_intercept(struct kvm_vcpu *vcpu)
@@ -3877,6 +4242,10 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
r = 0;
goto out;
}
+ if (test_and_clear_bit(KVM_REQ_DEACTIVATE_FPU, &vcpu->requests)) {
+ vcpu->fpu_active = 0;
+ kvm_x86_ops->fpu_deactivate(vcpu);
+ }
}
preempt_disable();
@@ -3910,7 +4279,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
kvm_lapic_sync_to_vapic(vcpu);
}
- up_read(&vcpu->kvm->slots_lock);
+ srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
kvm_guest_enter();
@@ -3952,7 +4321,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
preempt_enable();
- down_read(&vcpu->kvm->slots_lock);
+ vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
/*
* Profile KVM exit RIPs:
@@ -3974,6 +4343,7 @@ out:
static int __vcpu_run(struct kvm_vcpu *vcpu)
{
int r;
+ struct kvm *kvm = vcpu->kvm;
if (unlikely(vcpu->arch.mp_state == KVM_MP_STATE_SIPI_RECEIVED)) {
pr_debug("vcpu %d received sipi with vector # %x\n",
@@ -3985,7 +4355,7 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
}
- down_read(&vcpu->kvm->slots_lock);
+ vcpu->srcu_idx = srcu_read_lock(&kvm->srcu);
vapic_enter(vcpu);
r = 1;
@@ -3993,9 +4363,9 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
if (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE)
r = vcpu_enter_guest(vcpu);
else {
- up_read(&vcpu->kvm->slots_lock);
+ srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx);
kvm_vcpu_block(vcpu);
- down_read(&vcpu->kvm->slots_lock);
+ vcpu->srcu_idx = srcu_read_lock(&kvm->srcu);
if (test_and_clear_bit(KVM_REQ_UNHALT, &vcpu->requests))
{
switch(vcpu->arch.mp_state) {
@@ -4030,13 +4400,13 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
++vcpu->stat.signal_exits;
}
if (need_resched()) {
- up_read(&vcpu->kvm->slots_lock);
+ srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx);
kvm_resched(vcpu);
- down_read(&vcpu->kvm->slots_lock);
+ vcpu->srcu_idx = srcu_read_lock(&kvm->srcu);
}
}
- up_read(&vcpu->kvm->slots_lock);
+ srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx);
post_kvm_run_save(vcpu);
vapic_exit(vcpu);
@@ -4075,10 +4445,10 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
vcpu->mmio_read_completed = 1;
vcpu->mmio_needed = 0;
- down_read(&vcpu->kvm->slots_lock);
+ vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
r = emulate_instruction(vcpu, vcpu->arch.mmio_fault_cr2, 0,
EMULTYPE_NO_DECODE);
- up_read(&vcpu->kvm->slots_lock);
+ srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
if (r == EMULATE_DO_MMIO) {
/*
* Read-modify-write. Back to userspace.
@@ -4205,11 +4575,10 @@ int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
sregs->gdt.limit = dt.limit;
sregs->gdt.base = dt.base;
- kvm_x86_ops->decache_cr4_guest_bits(vcpu);
- sregs->cr0 = vcpu->arch.cr0;
+ sregs->cr0 = kvm_read_cr0(vcpu);
sregs->cr2 = vcpu->arch.cr2;
sregs->cr3 = vcpu->arch.cr3;
- sregs->cr4 = vcpu->arch.cr4;
+ sregs->cr4 = kvm_read_cr4(vcpu);
sregs->cr8 = kvm_get_cr8(vcpu);
sregs->efer = vcpu->arch.shadow_efer;
sregs->apic_base = kvm_get_apic_base(vcpu);
@@ -4378,15 +4747,26 @@ static int is_vm86_segment(struct kvm_vcpu *vcpu, int seg)
(kvm_get_rflags(vcpu) & X86_EFLAGS_VM);
}
+static void kvm_check_segment_descriptor(struct kvm_vcpu *vcpu, int seg,
+ u16 selector)
+{
+ /* NULL selector is not valid for CS and SS */
+ if (seg == VCPU_SREG_CS || seg == VCPU_SREG_SS)
+ if (!selector)
+ kvm_queue_exception_e(vcpu, TS_VECTOR, selector >> 3);
+}
+
int kvm_load_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector,
int type_bits, int seg)
{
struct kvm_segment kvm_seg;
- if (is_vm86_segment(vcpu, seg) || !(vcpu->arch.cr0 & X86_CR0_PE))
+ if (is_vm86_segment(vcpu, seg) || !(kvm_read_cr0_bits(vcpu, X86_CR0_PE)))
return kvm_load_realmode_segment(vcpu, selector, seg);
if (load_segment_descriptor_to_kvm_desct(vcpu, selector, &kvm_seg))
return 1;
+
+ kvm_check_segment_descriptor(vcpu, seg, selector);
kvm_seg.type |= type_bits;
if (seg != VCPU_SREG_SS && seg != VCPU_SREG_CS &&
@@ -4659,7 +5039,7 @@ int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason)
&nseg_desc);
}
- kvm_x86_ops->set_cr0(vcpu, vcpu->arch.cr0 | X86_CR0_TS);
+ kvm_x86_ops->set_cr0(vcpu, kvm_read_cr0(vcpu) | X86_CR0_TS);
seg_desct_to_kvm_desct(&nseg_desc, tss_selector, &tr_seg);
tr_seg.type = 11;
kvm_set_segment(vcpu, &tr_seg, VCPU_SREG_TR);
@@ -4694,13 +5074,11 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
kvm_x86_ops->set_efer(vcpu, sregs->efer);
kvm_set_apic_base(vcpu, sregs->apic_base);
- kvm_x86_ops->decache_cr4_guest_bits(vcpu);
-
- mmu_reset_needed |= vcpu->arch.cr0 != sregs->cr0;
+ mmu_reset_needed |= kvm_read_cr0(vcpu) != sregs->cr0;
kvm_x86_ops->set_cr0(vcpu, sregs->cr0);
vcpu->arch.cr0 = sregs->cr0;
- mmu_reset_needed |= vcpu->arch.cr4 != sregs->cr4;
+ mmu_reset_needed |= kvm_read_cr4(vcpu) != sregs->cr4;
kvm_x86_ops->set_cr4(vcpu, sregs->cr4);
if (!is_long_mode(vcpu) && is_pae(vcpu)) {
load_pdptrs(vcpu, vcpu->arch.cr3);
@@ -4735,7 +5113,7 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
/* Older userspace won't unhalt the vcpu on reset. */
if (kvm_vcpu_is_bsp(vcpu) && kvm_rip_read(vcpu) == 0xfff0 &&
sregs->cs.selector == 0xf000 && sregs->cs.base == 0xffff0000 &&
- !(vcpu->arch.cr0 & X86_CR0_PE))
+ !(kvm_read_cr0_bits(vcpu, X86_CR0_PE)))
vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
vcpu_put(vcpu);
@@ -4833,11 +5211,12 @@ int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu,
{
unsigned long vaddr = tr->linear_address;
gpa_t gpa;
+ int idx;
vcpu_load(vcpu);
- down_read(&vcpu->kvm->slots_lock);
+ idx = srcu_read_lock(&vcpu->kvm->srcu);
gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, vaddr);
- up_read(&vcpu->kvm->slots_lock);
+ srcu_read_unlock(&vcpu->kvm->srcu, idx);
tr->physical_address = gpa;
tr->valid = gpa != UNMAPPED_GVA;
tr->writeable = 1;
@@ -4936,6 +5315,7 @@ void kvm_put_guest_fpu(struct kvm_vcpu *vcpu)
kvm_fx_save(&vcpu->arch.guest_fx_image);
kvm_fx_restore(&vcpu->arch.host_fx_image);
++vcpu->stat.fpu_reload;
+ set_bit(KVM_REQ_DEACTIVATE_FPU, &vcpu->requests);
}
EXPORT_SYMBOL_GPL(kvm_put_guest_fpu);
@@ -5089,11 +5469,13 @@ fail:
void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu)
{
+ int idx;
+
kfree(vcpu->arch.mce_banks);
kvm_free_lapic(vcpu);
- down_read(&vcpu->kvm->slots_lock);
+ idx = srcu_read_lock(&vcpu->kvm->srcu);
kvm_mmu_destroy(vcpu);
- up_read(&vcpu->kvm->slots_lock);
+ srcu_read_unlock(&vcpu->kvm->srcu, idx);
free_page((unsigned long)vcpu->arch.pio_data);
}
@@ -5104,6 +5486,12 @@ struct kvm *kvm_arch_create_vm(void)
if (!kvm)
return ERR_PTR(-ENOMEM);
+ kvm->arch.aliases = kzalloc(sizeof(struct kvm_mem_aliases), GFP_KERNEL);
+ if (!kvm->arch.aliases) {
+ kfree(kvm);
+ return ERR_PTR(-ENOMEM);
+ }
+
INIT_LIST_HEAD(&kvm->arch.active_mmu_pages);
INIT_LIST_HEAD(&kvm->arch.assigned_dev_head);
@@ -5160,16 +5548,17 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
put_page(kvm->arch.apic_access_page);
if (kvm->arch.ept_identity_pagetable)
put_page(kvm->arch.ept_identity_pagetable);
+ kfree(kvm->arch.aliases);
kfree(kvm);
}
-int kvm_arch_set_memory_region(struct kvm *kvm,
- struct kvm_userspace_memory_region *mem,
+int kvm_arch_prepare_memory_region(struct kvm *kvm,
+ struct kvm_memory_slot *memslot,
struct kvm_memory_slot old,
+ struct kvm_userspace_memory_region *mem,
int user_alloc)
{
- int npages = mem->memory_size >> PAGE_SHIFT;
- struct kvm_memory_slot *memslot = &kvm->memslots[mem->slot];
+ int npages = memslot->npages;
/*To keep backward compatibility with older userspace,
*x86 needs to hanlde !user_alloc case.
@@ -5189,26 +5578,35 @@ int kvm_arch_set_memory_region(struct kvm *kvm,
if (IS_ERR((void *)userspace_addr))
return PTR_ERR((void *)userspace_addr);
- /* set userspace_addr atomically for kvm_hva_to_rmapp */
- spin_lock(&kvm->mmu_lock);
memslot->userspace_addr = userspace_addr;
- spin_unlock(&kvm->mmu_lock);
- } else {
- if (!old.user_alloc && old.rmap) {
- int ret;
-
- down_write(&current->mm->mmap_sem);
- ret = do_munmap(current->mm, old.userspace_addr,
- old.npages * PAGE_SIZE);
- up_write(&current->mm->mmap_sem);
- if (ret < 0)
- printk(KERN_WARNING
- "kvm_vm_ioctl_set_memory_region: "
- "failed to munmap memory\n");
- }
}
}
+
+ return 0;
+}
+
+void kvm_arch_commit_memory_region(struct kvm *kvm,
+ struct kvm_userspace_memory_region *mem,
+ struct kvm_memory_slot old,
+ int user_alloc)
+{
+
+ int npages = mem->memory_size >> PAGE_SHIFT;
+
+ if (!user_alloc && !old.user_alloc && old.rmap && !npages) {
+ int ret;
+
+ down_write(&current->mm->mmap_sem);
+ ret = do_munmap(current->mm, old.userspace_addr,
+ old.npages * PAGE_SIZE);
+ up_write(&current->mm->mmap_sem);
+ if (ret < 0)
+ printk(KERN_WARNING
+ "kvm_vm_ioctl_set_memory_region: "
+ "failed to munmap memory\n");
+ }
+
spin_lock(&kvm->mmu_lock);
if (!kvm->arch.n_requested_mmu_pages) {
unsigned int nr_mmu_pages = kvm_mmu_calculate_mmu_pages(kvm);
@@ -5217,8 +5615,6 @@ int kvm_arch_set_memory_region(struct kvm *kvm,
kvm_mmu_slot_remove_write_access(kvm, mem->slot);
spin_unlock(&kvm->mmu_lock);
-
- return 0;
}
void kvm_arch_flush_shadow(struct kvm *kvm)
generated by cgit v1.2.3 (git 2.39.1) at 2024-06-30 15:37:54 +0000