aboutsummaryrefslogtreecommitdiff
path: root/arch/x86/kvm
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kvm')
-rw-r--r--arch/x86/kvm/Kconfig2
-rw-r--r--arch/x86/kvm/Makefile13
-rw-r--r--arch/x86/kvm/cpuid.c57
-rw-r--r--arch/x86/kvm/cpuid.h5
-rw-r--r--arch/x86/kvm/mmu.c6
-rw-r--r--arch/x86/kvm/paging_tmpl.h20
-rw-r--r--arch/x86/kvm/svm.c4
-rw-r--r--arch/x86/kvm/vmx.c4
-rw-r--r--arch/x86/kvm/x86.c50
9 files changed, 120 insertions, 41 deletions
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index a47a3e54b964..bdccfb62aa0d 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -27,6 +27,7 @@ config KVM
select MMU_NOTIFIER
select ANON_INODES
select HAVE_KVM_IRQCHIP
+ select HAVE_KVM_IRQFD
select HAVE_KVM_IRQ_ROUTING
select HAVE_KVM_EVENTFD
select KVM_APIC_ARCHITECTURE
@@ -38,6 +39,7 @@ config KVM
select PERF_EVENTS
select HAVE_KVM_MSI
select HAVE_KVM_CPU_RELAX_INTERCEPT
+ select KVM_VFIO
---help---
Support hosting fully virtualized guest machines using hardware
virtualization extensions. You will need a fairly recent
diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile
index d609e1d84048..25d22b2d6509 100644
--- a/arch/x86/kvm/Makefile
+++ b/arch/x86/kvm/Makefile
@@ -5,12 +5,13 @@ CFLAGS_x86.o := -I.
CFLAGS_svm.o := -I.
CFLAGS_vmx.o := -I.
-kvm-y += $(addprefix ../../../virt/kvm/, kvm_main.o ioapic.o \
- coalesced_mmio.o irq_comm.o eventfd.o \
- irqchip.o)
-kvm-$(CONFIG_KVM_DEVICE_ASSIGNMENT) += $(addprefix ../../../virt/kvm/, \
- assigned-dev.o iommu.o)
-kvm-$(CONFIG_KVM_ASYNC_PF) += $(addprefix ../../../virt/kvm/, async_pf.o)
+KVM := ../../../virt/kvm
+
+kvm-y += $(KVM)/kvm_main.o $(KVM)/ioapic.o \
+ $(KVM)/coalesced_mmio.o $(KVM)/irq_comm.o \
+ $(KVM)/eventfd.o $(KVM)/irqchip.o $(KVM)/vfio.o
+kvm-$(CONFIG_KVM_DEVICE_ASSIGNMENT) += $(KVM)/assigned-dev.o $(KVM)/iommu.o
+kvm-$(CONFIG_KVM_ASYNC_PF) += $(KVM)/async_pf.o
kvm-y += x86.o mmu.o emulate.o i8259.o irq.o lapic.o \
i8254.o cpuid.o pmu.o
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index a20ecb5b6cbf..89d288237b9c 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -187,8 +187,14 @@ static bool supported_xcr0_bit(unsigned bit)
#define F(x) bit(X86_FEATURE_##x)
-static int do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
- u32 index, int *nent, int maxnent)
+static int __do_cpuid_ent_emulated(struct kvm_cpuid_entry2 *entry,
+ u32 func, u32 index, int *nent, int maxnent)
+{
+ return 0;
+}
+
+static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
+ u32 index, int *nent, int maxnent)
{
int r;
unsigned f_nx = is_efer_nx() ? F(NX) : 0;
@@ -480,6 +486,15 @@ out:
return r;
}
+static int do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 func,
+ u32 idx, int *nent, int maxnent, unsigned int type)
+{
+ if (type == KVM_GET_EMULATED_CPUID)
+ return __do_cpuid_ent_emulated(entry, func, idx, nent, maxnent);
+
+ return __do_cpuid_ent(entry, func, idx, nent, maxnent);
+}
+
#undef F
struct kvm_cpuid_param {
@@ -494,8 +509,34 @@ static bool is_centaur_cpu(const struct kvm_cpuid_param *param)
return boot_cpu_data.x86_vendor == X86_VENDOR_CENTAUR;
}
-int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid,
- struct kvm_cpuid_entry2 __user *entries)
+static bool sanity_check_entries(struct kvm_cpuid_entry2 __user *entries,
+ __u32 num_entries, unsigned int ioctl_type)
+{
+ int i;
+
+ if (ioctl_type != KVM_GET_EMULATED_CPUID)
+ return false;
+
+ /*
+ * We want to make sure that ->padding is being passed clean from
+ * userspace in case we want to use it for something in the future.
+ *
+ * Sadly, this wasn't enforced for KVM_GET_SUPPORTED_CPUID and so we
+ * have to give ourselves satisfied only with the emulated side. /me
+ * sheds a tear.
+ */
+ for (i = 0; i < num_entries; i++) {
+ if (entries[i].padding[0] ||
+ entries[i].padding[1] ||
+ entries[i].padding[2])
+ return true;
+ }
+ return false;
+}
+
+int kvm_dev_ioctl_get_cpuid(struct kvm_cpuid2 *cpuid,
+ struct kvm_cpuid_entry2 __user *entries,
+ unsigned int type)
{
struct kvm_cpuid_entry2 *cpuid_entries;
int limit, nent = 0, r = -E2BIG, i;
@@ -512,6 +553,10 @@ int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid,
goto out;
if (cpuid->nent > KVM_MAX_CPUID_ENTRIES)
cpuid->nent = KVM_MAX_CPUID_ENTRIES;
+
+ if (sanity_check_entries(entries, cpuid->nent, type))
+ return -EINVAL;
+
r = -ENOMEM;
cpuid_entries = vmalloc(sizeof(struct kvm_cpuid_entry2) * cpuid->nent);
if (!cpuid_entries)
@@ -525,7 +570,7 @@ int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid,
continue;
r = do_cpuid_ent(&cpuid_entries[nent], ent->func, ent->idx,
- &nent, cpuid->nent);
+ &nent, cpuid->nent, type);
if (r)
goto out_free;
@@ -536,7 +581,7 @@ int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid,
limit = cpuid_entries[nent - 1].eax;
for (func = ent->func + 1; func <= limit && nent < cpuid->nent && r == 0; ++func)
r = do_cpuid_ent(&cpuid_entries[nent], func, ent->idx,
- &nent, cpuid->nent);
+ &nent, cpuid->nent, type);
if (r)
goto out_free;
diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h
index b7fd07984888..f1e4895174b2 100644
--- a/arch/x86/kvm/cpuid.h
+++ b/arch/x86/kvm/cpuid.h
@@ -6,8 +6,9 @@
void kvm_update_cpuid(struct kvm_vcpu *vcpu);
struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu,
u32 function, u32 index);
-int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid,
- struct kvm_cpuid_entry2 __user *entries);
+int kvm_dev_ioctl_get_cpuid(struct kvm_cpuid2 *cpuid,
+ struct kvm_cpuid_entry2 __user *entries,
+ unsigned int type);
int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu,
struct kvm_cpuid *cpuid,
struct kvm_cpuid_entry __user *entries);
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index e14b1f8667bb..0cc34f594c2a 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -3241,7 +3241,7 @@ static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn)
arch.direct_map = vcpu->arch.mmu.direct_map;
arch.cr3 = vcpu->arch.mmu.get_cr3(vcpu);
- return kvm_setup_async_pf(vcpu, gva, gfn, &arch);
+ return kvm_setup_async_pf(vcpu, gva, gfn_to_hva(vcpu->kvm, gfn), &arch);
}
static bool can_do_async_pf(struct kvm_vcpu *vcpu)
@@ -4229,7 +4229,7 @@ static int mmu_shrink(struct shrinker *shrink, struct shrink_control *sc)
if (nr_to_scan == 0)
goto out;
- raw_spin_lock(&kvm_lock);
+ spin_lock(&kvm_lock);
list_for_each_entry(kvm, &vm_list, vm_list) {
int idx;
@@ -4265,7 +4265,7 @@ static int mmu_shrink(struct shrinker *shrink, struct shrink_control *sc)
break;
}
- raw_spin_unlock(&kvm_lock);
+ spin_unlock(&kvm_lock);
out:
return percpu_counter_read_positive(&kvm_total_used_mmu_pages);
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index 7e6090e13237..a6a6370c2010 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -69,6 +69,7 @@ struct guest_walker {
pt_element_t prefetch_ptes[PTE_PREFETCH_NUM];
gpa_t pte_gpa[PT_MAX_FULL_LEVELS];
pt_element_t __user *ptep_user[PT_MAX_FULL_LEVELS];
+ bool pte_writable[PT_MAX_FULL_LEVELS];
unsigned pt_access;
unsigned pte_access;
gfn_t gfn;
@@ -130,6 +131,22 @@ static int FNAME(update_accessed_dirty_bits)(struct kvm_vcpu *vcpu,
if (pte == orig_pte)
continue;
+ /*
+ * If the slot is read-only, simply do not process the accessed
+ * and dirty bits. This is the correct thing to do if the slot
+ * is ROM, and page tables in read-as-ROM/write-as-MMIO slots
+ * are only supported if the accessed and dirty bits are already
+ * set in the ROM (so that MMIO writes are never needed).
+ *
+ * Note that NPT does not allow this at all and faults, since
+ * it always wants nested page table entries for the guest
+ * page tables to be writable. And EPT works but will simply
+ * overwrite the read-only memory to set the accessed and dirty
+ * bits.
+ */
+ if (unlikely(!walker->pte_writable[level - 1]))
+ continue;
+
ret = FNAME(cmpxchg_gpte)(vcpu, mmu, ptep_user, index, orig_pte, pte);
if (ret)
return ret;
@@ -204,7 +221,8 @@ retry_walk:
goto error;
real_gfn = gpa_to_gfn(real_gfn);
- host_addr = gfn_to_hva(vcpu->kvm, real_gfn);
+ host_addr = gfn_to_hva_prot(vcpu->kvm, real_gfn,
+ &walker->pte_writable[walker->level - 1]);
if (unlikely(kvm_is_error_hva(host_addr)))
goto error;
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 8bf40a243d75..03f7d03c92a2 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -606,7 +606,7 @@ static int has_svm(void)
return 1;
}
-static void svm_hardware_disable(void *garbage)
+static void svm_hardware_disable(void)
{
/* Make sure we clean up behind us */
if (static_cpu_has(X86_FEATURE_TSCRATEMSR))
@@ -617,7 +617,7 @@ static void svm_hardware_disable(void *garbage)
amd_pmu_disable_virt();
}
-static int svm_hardware_enable(void *garbage)
+static int svm_hardware_enable(void)
{
struct svm_cpu_data *sd;
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 04cc2fa7744f..995fcc40fee9 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2570,7 +2570,7 @@ static void kvm_cpu_vmxon(u64 addr)
: "memory", "cc");
}
-static int hardware_enable(void *garbage)
+static int hardware_enable(void)
{
int cpu = raw_smp_processor_id();
u64 phys_addr = __pa(per_cpu(vmxarea, cpu));
@@ -2634,7 +2634,7 @@ static void kvm_cpu_vmxoff(void)
asm volatile (__ex(ASM_VMX_VMXOFF) : : : "cc");
}
-static void hardware_disable(void *garbage)
+static void hardware_disable(void)
{
if (vmm_exclusive) {
vmclear_local_loaded_vmcss();
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 41ba726c1ce2..88365f2df594 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -247,7 +247,7 @@ int kvm_set_shared_msr(unsigned slot, u64 value, u64 mask)
}
EXPORT_SYMBOL_GPL(kvm_set_shared_msr);
-static void drop_user_return_notifiers(void *ignore)
+static void drop_user_return_notifiers(void)
{
unsigned int cpu = smp_processor_id();
struct kvm_shared_msrs *smsr = per_cpu_ptr(shared_msrs, cpu);
@@ -2551,7 +2551,7 @@ out:
return r;
}
-int kvm_dev_ioctl_check_extension(long ext)
+int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
{
int r;
@@ -2561,6 +2561,7 @@ int kvm_dev_ioctl_check_extension(long ext)
case KVM_CAP_MMU_SHADOW_CACHE_CONTROL:
case KVM_CAP_SET_TSS_ADDR:
case KVM_CAP_EXT_CPUID:
+ case KVM_CAP_EXT_EMUL_CPUID:
case KVM_CAP_CLOCKSOURCE:
case KVM_CAP_PIT:
case KVM_CAP_NOP_IO_DELAY:
@@ -2670,15 +2671,17 @@ long kvm_arch_dev_ioctl(struct file *filp,
r = 0;
break;
}
- case KVM_GET_SUPPORTED_CPUID: {
+ case KVM_GET_SUPPORTED_CPUID:
+ case KVM_GET_EMULATED_CPUID: {
struct kvm_cpuid2 __user *cpuid_arg = argp;
struct kvm_cpuid2 cpuid;
r = -EFAULT;
if (copy_from_user(&cpuid, cpuid_arg, sizeof cpuid))
goto out;
- r = kvm_dev_ioctl_get_supported_cpuid(&cpuid,
- cpuid_arg->entries);
+
+ r = kvm_dev_ioctl_get_cpuid(&cpuid, cpuid_arg->entries,
+ ioctl);
if (r)
goto out;
@@ -5154,7 +5157,7 @@ static int kvmclock_cpufreq_notifier(struct notifier_block *nb, unsigned long va
smp_call_function_single(freq->cpu, tsc_khz_changed, freq, 1);
- raw_spin_lock(&kvm_lock);
+ spin_lock(&kvm_lock);
list_for_each_entry(kvm, &vm_list, vm_list) {
kvm_for_each_vcpu(i, vcpu, kvm) {
if (vcpu->cpu != freq->cpu)
@@ -5164,7 +5167,7 @@ static int kvmclock_cpufreq_notifier(struct notifier_block *nb, unsigned long va
send_ipi = 1;
}
}
- raw_spin_unlock(&kvm_lock);
+ spin_unlock(&kvm_lock);
if (freq->old < freq->new && send_ipi) {
/*
@@ -5311,12 +5314,12 @@ static void pvclock_gtod_update_fn(struct work_struct *work)
struct kvm_vcpu *vcpu;
int i;
- raw_spin_lock(&kvm_lock);
+ spin_lock(&kvm_lock);
list_for_each_entry(kvm, &vm_list, vm_list)
kvm_for_each_vcpu(i, vcpu, kvm)
set_bit(KVM_REQ_MASTERCLOCK_UPDATE, &vcpu->requests);
atomic_set(&kvm_guest_has_master_clock, 0);
- raw_spin_unlock(&kvm_lock);
+ spin_unlock(&kvm_lock);
}
static DECLARE_WORK(pvclock_gtod_work, pvclock_gtod_update_fn);
@@ -5959,7 +5962,7 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
}
if (need_resched()) {
srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx);
- kvm_resched(vcpu);
+ cond_resched();
vcpu->srcu_idx = srcu_read_lock(&kvm->srcu);
}
}
@@ -6613,7 +6616,7 @@ void kvm_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, unsigned int vector)
kvm_rip_write(vcpu, 0);
}
-int kvm_arch_hardware_enable(void *garbage)
+int kvm_arch_hardware_enable(void)
{
struct kvm *kvm;
struct kvm_vcpu *vcpu;
@@ -6624,7 +6627,7 @@ int kvm_arch_hardware_enable(void *garbage)
bool stable, backwards_tsc = false;
kvm_shared_msr_cpu_online();
- ret = kvm_x86_ops->hardware_enable(garbage);
+ ret = kvm_x86_ops->hardware_enable();
if (ret != 0)
return ret;
@@ -6704,10 +6707,10 @@ int kvm_arch_hardware_enable(void *garbage)
return 0;
}
-void kvm_arch_hardware_disable(void *garbage)
+void kvm_arch_hardware_disable(void)
{
- kvm_x86_ops->hardware_disable(garbage);
- drop_user_return_notifiers(garbage);
+ kvm_x86_ops->hardware_disable();
+ drop_user_return_notifiers();
}
int kvm_arch_hardware_setup(void)
@@ -6819,6 +6822,10 @@ void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu)
static_key_slow_dec(&kvm_no_apic_vcpu);
}
+void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu)
+{
+}
+
int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
{
if (type)
@@ -6910,7 +6917,7 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
kfree(rcu_dereference_check(kvm->arch.apic_map, 1));
}
-void kvm_arch_free_memslot(struct kvm_memory_slot *free,
+void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free,
struct kvm_memory_slot *dont)
{
int i;
@@ -6931,7 +6938,8 @@ void kvm_arch_free_memslot(struct kvm_memory_slot *free,
}
}
-int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages)
+int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
+ unsigned long npages)
{
int i;
@@ -6989,6 +6997,10 @@ out_free:
return -ENOMEM;
}
+void kvm_arch_memslots_updated(struct kvm *kvm)
+{
+}
+
int kvm_arch_prepare_memory_region(struct kvm *kvm,
struct kvm_memory_slot *memslot,
struct kvm_userspace_memory_region *mem,
@@ -7127,7 +7139,7 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work)
int r;
if ((vcpu->arch.mmu.direct_map != work->arch.direct_map) ||
- is_error_page(work->page))
+ work->wakeup_all)
return;
r = kvm_mmu_reload(vcpu);
@@ -7237,7 +7249,7 @@ void kvm_arch_async_page_present(struct kvm_vcpu *vcpu,
struct x86_exception fault;
trace_kvm_async_pf_ready(work->arch.token, work->gva);
- if (is_error_page(work->page))
+ if (work->wakeup_all)
work->arch.token = ~0; /* broadcast wakeup */
else
kvm_del_async_pf_gfn(vcpu, work->arch.gfn);
generated by cgit v1.2.3 (git 2.25.1) at 2024-04-27 12:20:34 +0000