};
#endif
+extern void (*crash_vmclear_loaded_vmcss)(void);
+
#endif /* __ASSEMBLY__ */
#endif /* _ASM_X86_KEXEC_H */
#define VMX_EPTP_WB_BIT (1ull << 14)
#define VMX_EPT_2MB_PAGE_BIT (1ull << 16)
#define VMX_EPT_1GB_PAGE_BIT (1ull << 17)
-#define VMX_EPT_AD_BIT (1ull << 21)
-#define VMX_EPT_EXTENT_INDIVIDUAL_BIT (1ull << 24)
+#define VMX_EPT_AD_BIT (1ull << 21)
#define VMX_EPT_EXTENT_CONTEXT_BIT (1ull << 25)
#define VMX_EPT_EXTENT_GLOBAL_BIT (1ull << 26)
#include <linux/delay.h>
#include <linux/elf.h>
#include <linux/elfcore.h>
+#include <linux/module.h>
#include <asm/processor.h>
#include <asm/hardirq.h>
int in_crash_kexec;
+/*
+ * This is used to VMCLEAR all VMCSs loaded on the
+ * processor. And when loading kvm_intel module, the
+ * callback function pointer will be assigned.
+ *
+ * protected by rcu.
+ */
+void (*crash_vmclear_loaded_vmcss)(void) = NULL;
+EXPORT_SYMBOL_GPL(crash_vmclear_loaded_vmcss);
+
+static inline void cpu_crash_vmclear_loaded_vmcss(void)
+{
+ void (*do_vmclear_operation)(void) = NULL;
+
+ rcu_read_lock();
+ do_vmclear_operation = rcu_dereference(crash_vmclear_loaded_vmcss);
+ if (do_vmclear_operation)
+ do_vmclear_operation();
+ rcu_read_unlock();
+}
+
#if defined(CONFIG_SMP) && defined(CONFIG_X86_LOCAL_APIC)
static void kdump_nmi_callback(int cpu, struct pt_regs *regs)
#endif
crash_save_cpu(regs, cpu);
+ /*
+ * VMCLEAR VMCSs loaded on all cpus if needed.
+ */
+ cpu_crash_vmclear_loaded_vmcss();
+
/* Disable VMX or SVM if needed.
*
* We need to disable virtualization on all CPUs.
kdump_nmi_shootdown_cpus();
+ /*
+ * VMCLEAR VMCSs loaded on this cpu if needed.
+ */
+ cpu_crash_vmclear_loaded_vmcss();
+
/* Booting kdump kernel with VMX or SVM enabled won't work,
* because (among other limitations) we can't disable paging
* with the virt flags.
} else
*eax = *ebx = *ecx = *edx = 0;
}
+EXPORT_SYMBOL_GPL(kvm_cpuid);
void kvm_emulate_cpuid(struct kvm_vcpu *vcpu)
{
|| (!vcpu->arch.mmu.direct_map && write_fault
&& !is_write_protection(vcpu) && !user_fault)) {
+ /*
+ * There are two cases:
+ * - the one is other vcpu creates new sp in the window
+ * between mapping_level() and acquiring mmu-lock.
+ * - the another case is the new sp is created by itself
+ * (page-fault path) when guest uses the target gfn as
+ * its page table.
+ * Both of these cases can be fixed by allowing guest to
+ * retry the access, it will refault, then we can establish
+ * the mapping by using small page.
+ */
if (level > PT_PAGE_TABLE_LEVEL &&
- has_wrprotected_page(vcpu->kvm, gfn, level)) {
- ret = 1;
- drop_spte(vcpu->kvm, sptep);
+ has_wrprotected_page(vcpu->kvm, gfn, level))
goto done;
- }
spte |= PT_WRITABLE_MASK | SPTE_MMU_WRITEABLE;
#include "mmu.h"
#include "kvm_cache_regs.h"
#include "x86.h"
+#include "cpuid.h"
#include <linux/module.h>
#include <linux/mod_devicetable.h>
static int svm_vcpu_reset(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
+ u32 dummy;
+ u32 eax = 1;
init_vmcb(svm);
svm->vmcb->save.cs.base = svm->vcpu.arch.sipi_vector << 12;
svm->vmcb->save.cs.selector = svm->vcpu.arch.sipi_vector << 8;
}
- vcpu->arch.regs_avail = ~0;
- vcpu->arch.regs_dirty = ~0;
+
+ kvm_cpuid(vcpu, &eax, &dummy, &dummy, &dummy);
+ kvm_register_write(vcpu, VCPU_REGS_RDX, eax);
return 0;
}
svm->asid_generation = 0;
init_vmcb(svm);
- err = fx_init(&svm->vcpu);
- if (err)
- goto free_page4;
-
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;
return &svm->vcpu;
-free_page4:
- __free_page(hsave_page);
free_page3:
__free_pages(nested_msrpm_pages, MSRPM_ALLOC_ORDER);
free_page2:
#include <asm/i387.h>
#include <asm/xcr.h>
#include <asm/perf_event.h>
+#include <asm/kexec.h>
#include "trace.h"
return vmx_capability.ept & VMX_EPT_AD_BIT;
}
-static inline bool cpu_has_vmx_invept_individual_addr(void)
-{
- return vmx_capability.ept & VMX_EPT_EXTENT_INDIVIDUAL_BIT;
-}
-
static inline bool cpu_has_vmx_invept_context(void)
{
return vmx_capability.ept & VMX_EPT_EXTENT_CONTEXT_BIT;
vmcs, phys_addr);
}
+#ifdef CONFIG_KEXEC
+/*
+ * This bitmap is used to indicate whether the vmclear
+ * operation is enabled on all cpus. All disabled by
+ * default.
+ */
+static cpumask_t crash_vmclear_enabled_bitmap = CPU_MASK_NONE;
+
+static inline void crash_enable_local_vmclear(int cpu)
+{
+ cpumask_set_cpu(cpu, &crash_vmclear_enabled_bitmap);
+}
+
+static inline void crash_disable_local_vmclear(int cpu)
+{
+ cpumask_clear_cpu(cpu, &crash_vmclear_enabled_bitmap);
+}
+
+static inline int crash_local_vmclear_enabled(int cpu)
+{
+ return cpumask_test_cpu(cpu, &crash_vmclear_enabled_bitmap);
+}
+
+static void crash_vmclear_local_loaded_vmcss(void)
+{
+ int cpu = raw_smp_processor_id();
+ struct loaded_vmcs *v;
+
+ if (!crash_local_vmclear_enabled(cpu))
+ return;
+
+ list_for_each_entry(v, &per_cpu(loaded_vmcss_on_cpu, cpu),
+ loaded_vmcss_on_cpu_link)
+ vmcs_clear(v->vmcs);
+}
+#else
+static inline void crash_enable_local_vmclear(int cpu) { }
+static inline void crash_disable_local_vmclear(int cpu) { }
+#endif /* CONFIG_KEXEC */
+
static void __loaded_vmcs_clear(void *arg)
{
struct loaded_vmcs *loaded_vmcs = arg;
return; /* vcpu migration can race with cpu offline */
if (per_cpu(current_vmcs, cpu) == loaded_vmcs->vmcs)
per_cpu(current_vmcs, cpu) = NULL;
+ crash_disable_local_vmclear(cpu);
list_del(&loaded_vmcs->loaded_vmcss_on_cpu_link);
/*
smp_wmb();
loaded_vmcs_init(loaded_vmcs);
+ crash_enable_local_vmclear(cpu);
}
static void loaded_vmcs_clear(struct loaded_vmcs *loaded_vmcs)
}
}
-static inline void ept_sync_individual_addr(u64 eptp, gpa_t gpa)
-{
- if (enable_ept) {
- if (cpu_has_vmx_invept_individual_addr())
- __invept(VMX_EPT_EXTENT_INDIVIDUAL_ADDR,
- eptp, gpa);
- else
- ept_sync_context(eptp);
- }
-}
-
static __always_inline unsigned long vmcs_readl(unsigned long field)
{
unsigned long value;
kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
local_irq_disable();
+ crash_disable_local_vmclear(cpu);
/*
* Read loaded_vmcs->cpu should be before fetching
list_add(&vmx->loaded_vmcs->loaded_vmcss_on_cpu_link,
&per_cpu(loaded_vmcss_on_cpu, cpu));
+ crash_enable_local_vmclear(cpu);
local_irq_enable();
/*
return -EBUSY;
INIT_LIST_HEAD(&per_cpu(loaded_vmcss_on_cpu, cpu));
+
+ /*
+ * Now we can enable the vmclear operation in kdump
+ * since the loaded_vmcss_on_cpu list on this cpu
+ * has been initialized.
+ *
+ * Though the cpu is not in VMX operation now, there
+ * is no problem to enable the vmclear operation
+ * for the loaded_vmcss_on_cpu list is empty!
+ */
+ crash_enable_local_vmclear(cpu);
+
rdmsrl(MSR_IA32_FEATURE_CONTROL, old);
test_bits = FEATURE_CONTROL_LOCKED;
u64 msr;
int ret;
- vcpu->arch.regs_avail = ~((1 << VCPU_REGS_RIP) | (1 << VCPU_REGS_RSP));
-
vmx->rmode.vm86_active = 0;
vmx->soft_vnmi_blocked = 0;
msr |= MSR_IA32_APICBASE_BSP;
kvm_set_apic_base(&vmx->vcpu, msr);
- ret = fx_init(&vmx->vcpu);
- if (ret != 0)
- goto out;
-
vmx_segment_cache_clear(vmx);
seg_setup(VCPU_SREG_CS);
kvm_rip_write(vcpu, 0xfff0);
else
kvm_rip_write(vcpu, 0);
- kvm_register_write(vcpu, VCPU_REGS_RSP, 0);
vmcs_writel(GUEST_GDTR_BASE, 0);
vmcs_write32(GUEST_GDTR_LIMIT, 0xffff);
/* HACK: Don't enable emulation on guest boot/reset */
vmx->emulation_required = 0;
-out:
return ret;
}
exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
- if (exit_qualification & (1 << 6)) {
- printk(KERN_ERR "EPT: GPA exceeds GAW!\n");
- return -EINVAL;
- }
-
gla_validity = (exit_qualification >> 7) & 0x3;
if (gla_validity != 0x3 && gla_validity != 0x1 && gla_validity != 0) {
printk(KERN_ERR "EPT: Handling EPT violation failed!\n");
if (r)
goto out3;
+#ifdef CONFIG_KEXEC
+ rcu_assign_pointer(crash_vmclear_loaded_vmcss,
+ crash_vmclear_local_loaded_vmcss);
+#endif
+
vmx_disable_intercept_for_msr(MSR_FS_BASE, false);
vmx_disable_intercept_for_msr(MSR_GS_BASE, false);
vmx_disable_intercept_for_msr(MSR_KERNEL_GS_BASE, true);
free_page((unsigned long)vmx_io_bitmap_b);
free_page((unsigned long)vmx_io_bitmap_a);
+#ifdef CONFIG_KEXEC
+ rcu_assign_pointer(crash_vmclear_loaded_vmcss, NULL);
+ synchronize_rcu();
+#endif
+
kvm_exit();
}
kvm_pmu_reset(vcpu);
+ memset(vcpu->arch.regs, 0, sizeof(vcpu->arch.regs));
+ vcpu->arch.regs_avail = ~0;
+ vcpu->arch.regs_dirty = ~0;
+
return kvm_x86_ops->vcpu_reset(vcpu);
}
if (!zalloc_cpumask_var(&vcpu->arch.wbinvd_dirty_mask, GFP_KERNEL))
goto fail_free_mce_banks;
+ r = fx_init(vcpu);
+ if (r)
+ goto fail_free_wbinvd_dirty_mask;
+
vcpu->arch.ia32_tsc_adjust_msr = 0x0;
kvm_async_pf_hash_reset(vcpu);
kvm_pmu_init(vcpu);
return 0;
+fail_free_wbinvd_dirty_mask:
+ free_cpumask_var(vcpu->arch.wbinvd_dirty_mask);
fail_free_mce_banks:
kfree(vcpu->arch.mce_banks);
fail_free_lapic:
unsigned long *deliver_bitmask);
#endif
int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level);
+int kvm_set_irq_inatomic(struct kvm *kvm, int irq_source_id, u32 irq, int level);
int kvm_set_msi(struct kvm_kernel_irq_routing_entry *irq_entry, struct kvm *kvm,
int irq_source_id, int level);
void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin);
}
#ifdef __KVM_HAVE_MSI
+static irqreturn_t kvm_assigned_dev_msi(int irq, void *dev_id)
+{
+ struct kvm_assigned_dev_kernel *assigned_dev = dev_id;
+ int ret = kvm_set_irq_inatomic(assigned_dev->kvm,
+ assigned_dev->irq_source_id,
+ assigned_dev->guest_irq, 1);
+ return unlikely(ret == -EWOULDBLOCK) ? IRQ_WAKE_THREAD : IRQ_HANDLED;
+}
+
static irqreturn_t kvm_assigned_dev_thread_msi(int irq, void *dev_id)
{
struct kvm_assigned_dev_kernel *assigned_dev = dev_id;
#endif
#ifdef __KVM_HAVE_MSIX
+static irqreturn_t kvm_assigned_dev_msix(int irq, void *dev_id)
+{
+ struct kvm_assigned_dev_kernel *assigned_dev = dev_id;
+ int index = find_index_from_host_irq(assigned_dev, irq);
+ u32 vector;
+ int ret = 0;
+
+ if (index >= 0) {
+ vector = assigned_dev->guest_msix_entries[index].vector;
+ ret = kvm_set_irq_inatomic(assigned_dev->kvm,
+ assigned_dev->irq_source_id,
+ vector, 1);
+ }
+
+ return unlikely(ret == -EWOULDBLOCK) ? IRQ_WAKE_THREAD : IRQ_HANDLED;
+}
+
static irqreturn_t kvm_assigned_dev_thread_msix(int irq, void *dev_id)
{
struct kvm_assigned_dev_kernel *assigned_dev = dev_id;
}
#ifdef __KVM_HAVE_MSI
-static irqreturn_t kvm_assigned_dev_msi(int irq, void *dev_id)
-{
- return IRQ_WAKE_THREAD;
-}
-
static int assigned_device_enable_host_msi(struct kvm *kvm,
struct kvm_assigned_dev_kernel *dev)
{
#endif
#ifdef __KVM_HAVE_MSIX
-static irqreturn_t kvm_assigned_dev_msix(int irq, void *dev_id)
-{
- return IRQ_WAKE_THREAD;
-}
-
static int assigned_device_enable_host_msix(struct kvm *kvm,
struct kvm_assigned_dev_kernel *dev)
{
return r;
}
+static inline void kvm_set_msi_irq(struct kvm_kernel_irq_routing_entry *e,
+ struct kvm_lapic_irq *irq)
+{
+ trace_kvm_msi_set_irq(e->msi.address_lo, e->msi.data);
+
+ irq->dest_id = (e->msi.address_lo &
+ MSI_ADDR_DEST_ID_MASK) >> MSI_ADDR_DEST_ID_SHIFT;
+ irq->vector = (e->msi.data &
+ MSI_DATA_VECTOR_MASK) >> MSI_DATA_VECTOR_SHIFT;
+ irq->dest_mode = (1 << MSI_ADDR_DEST_MODE_SHIFT) & e->msi.address_lo;
+ irq->trig_mode = (1 << MSI_DATA_TRIGGER_SHIFT) & e->msi.data;
+ irq->delivery_mode = e->msi.data & 0x700;
+ irq->level = 1;
+ irq->shorthand = 0;
+ /* TODO Deal with RH bit of MSI message address */
+}
+
int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e,
struct kvm *kvm, int irq_source_id, int level)
{
if (!level)
return -1;
- trace_kvm_msi_set_irq(e->msi.address_lo, e->msi.data);
+ kvm_set_msi_irq(e, &irq);
- irq.dest_id = (e->msi.address_lo &
- MSI_ADDR_DEST_ID_MASK) >> MSI_ADDR_DEST_ID_SHIFT;
- irq.vector = (e->msi.data &
- MSI_DATA_VECTOR_MASK) >> MSI_DATA_VECTOR_SHIFT;
- irq.dest_mode = (1 << MSI_ADDR_DEST_MODE_SHIFT) & e->msi.address_lo;
- irq.trig_mode = (1 << MSI_DATA_TRIGGER_SHIFT) & e->msi.data;
- irq.delivery_mode = e->msi.data & 0x700;
- irq.level = 1;
- irq.shorthand = 0;
-
- /* TODO Deal with RH bit of MSI message address */
return kvm_irq_delivery_to_apic(kvm, NULL, &irq);
}
+
+static int kvm_set_msi_inatomic(struct kvm_kernel_irq_routing_entry *e,
+ struct kvm *kvm)
+{
+ struct kvm_lapic_irq irq;
+ int r;
+
+ kvm_set_msi_irq(e, &irq);
+
+ if (kvm_irq_delivery_to_apic_fast(kvm, NULL, &irq, &r))
+ return r;
+ else
+ return -EWOULDBLOCK;
+}
+
int kvm_send_userspace_msi(struct kvm *kvm, struct kvm_msi *msi)
{
struct kvm_kernel_irq_routing_entry route;
return ret;
}
+/*
+ * Deliver an IRQ in an atomic context if we can, or return a failure,
+ * user can retry in a process context.
+ * Return value:
+ * -EWOULDBLOCK - Can't deliver in atomic context: retry in a process context.
+ * Other values - No need to retry.
+ */
+int kvm_set_irq_inatomic(struct kvm *kvm, int irq_source_id, u32 irq, int level)
+{
+ struct kvm_kernel_irq_routing_entry *e;
+ int ret = -EINVAL;
+ struct kvm_irq_routing_table *irq_rt;
+ struct hlist_node *n;
+
+ trace_kvm_set_irq(irq, level, irq_source_id);
+
+ /*
+ * Injection into either PIC or IOAPIC might need to scan all CPUs,
+ * which would need to be retried from thread context; when same GSI
+ * is connected to both PIC and IOAPIC, we'd have to report a
+ * partial failure here.
+ * Since there's no easy way to do this, we only support injecting MSI
+ * which is limited to 1:1 GSI mapping.
+ */
+ rcu_read_lock();
+ irq_rt = rcu_dereference(kvm->irq_routing);
+ if (irq < irq_rt->nr_rt_entries)
+ hlist_for_each_entry(e, n, &irq_rt->map[irq], link) {
+ if (likely(e->type == KVM_IRQ_ROUTING_MSI))
+ ret = kvm_set_msi_inatomic(e, kvm);
+ else
+ ret = -EWOULDBLOCK;
+ break;
+ }
+ rcu_read_unlock();
+ return ret;
+}
+
void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin)
{
struct kvm_irq_ack_notifier *kian;
Code Review / linux-3.10.git / commitdiff