---

yaml
---
r: 343591
b: refs/heads/master
c: d2ff4fc
h: refs/heads/master
i:
  343589: 1f1aa8c
  343587: 4a06977
  343583: 882a261
v: v3

[refs]

@@ -1,2 +1,2 @@
 ---
-refs/heads/master: 352df1deb2e3c40e65ff94c8d7c62d9144446b1c
+refs/heads/master: d2ff4fc557a4c5248b2d99b0d48e47a246d994b2

trunk/arch/x86/include/asm/kexec.h

@@ -163,6 +163,8 @@ struct kimage_arch {
 };
 #endif
 
+extern void (*crash_vmclear_loaded_vmcss)(void);
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* _ASM_X86_KEXEC_H */

trunk/arch/x86/include/asm/vmx.h

@@ -445,8 +445,7 @@ enum vmcs_field {
 #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)
 

trunk/arch/x86/kernel/crash.c

@@ -16,6 +16,7 @@
 #include <linux/delay.h>
 #include <linux/elf.h>
 #include <linux/elfcore.h>
+#include <linux/module.h>
 
 #include <asm/processor.h>
 #include <asm/hardirq.h>
@@ -30,6 +31,27 @@
 
 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)
@@ -46,6 +68,11 @@ 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.
@@ -88,6 +115,11 @@ void native_machine_crash_shutdown(struct pt_regs *regs)
 
 	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.

trunk/arch/x86/kvm/cpuid.c

@@ -661,6 +661,7 @@ void kvm_cpuid(struct kvm_vcpu *vcpu, u32 *eax, u32 *ebx, u32 *ecx, u32 *edx)
 	} else
 		*eax = *ebx = *ecx = *edx = 0;
 }
+EXPORT_SYMBOL_GPL(kvm_cpuid);
 
 void kvm_emulate_cpuid(struct kvm_vcpu *vcpu)
 {

trunk/arch/x86/kvm/mmu.c

@@ -2382,12 +2382,20 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 	    || (!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;
 

trunk/arch/x86/kvm/svm.c

@@ -20,6 +20,7 @@
 #include "mmu.h"
 #include "kvm_cache_regs.h"
 #include "x86.h"
+#include "cpuid.h"
 
 #include <linux/module.h>
 #include <linux/mod_devicetable.h>
@@ -1193,6 +1194,8 @@ static void init_vmcb(struct vcpu_svm *svm)
 static int svm_vcpu_reset(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
+	u32 dummy;
+	u32 eax = 1;
 
 	init_vmcb(svm);
 
@@ -1201,8 +1204,9 @@ static int svm_vcpu_reset(struct kvm_vcpu *vcpu)
 		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;
 }
@@ -1259,10 +1263,6 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id)
 	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;
@@ -1271,8 +1271,6 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id)
 
 	return &svm->vcpu;
 
-free_page4:
-	__free_page(hsave_page);
 free_page3:
 	__free_pages(nested_msrpm_pages, MSRPM_ALLOC_ORDER);
 free_page2:

trunk/arch/x86/kvm/vmx.c

@@ -42,6 +42,7 @@
 #include <asm/i387.h>
 #include <asm/xcr.h>
 #include <asm/perf_event.h>
+#include <asm/kexec.h>
 
 #include "trace.h"
 
@@ -802,11 +803,6 @@ static inline bool cpu_has_vmx_ept_ad_bits(void)
 	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;
@@ -992,6 +988,46 @@ static void vmcs_load(struct vmcs *vmcs)
 		       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;
@@ -1001,6 +1037,7 @@ static void __loaded_vmcs_clear(void *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);
 
 	/*
@@ -1012,6 +1049,7 @@ static void __loaded_vmcs_clear(void *arg)
 	smp_wmb();
 
 	loaded_vmcs_init(loaded_vmcs);
+	crash_enable_local_vmclear(cpu);
 }
 
 static void loaded_vmcs_clear(struct loaded_vmcs *loaded_vmcs)
@@ -1062,17 +1100,6 @@ static inline void ept_sync_context(u64 eptp)
 	}
 }
 
-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;
@@ -1546,6 +1573,7 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 
 		kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
 		local_irq_disable();
+		crash_disable_local_vmclear(cpu);
 
 		/*
 		 * Read loaded_vmcs->cpu should be before fetching
@@ -1556,6 +1584,7 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 
 		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();
 
 		/*
@@ -2369,6 +2398,18 @@ static int hardware_enable(void *garbage)
 		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;
@@ -3934,8 +3975,6 @@ static int vmx_vcpu_reset(struct kvm_vcpu *vcpu)
 	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;
@@ -3947,10 +3986,6 @@ static int vmx_vcpu_reset(struct kvm_vcpu *vcpu)
 		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);
@@ -3991,7 +4026,6 @@ static int vmx_vcpu_reset(struct kvm_vcpu *vcpu)
 		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);
@@ -4041,7 +4075,6 @@ static int vmx_vcpu_reset(struct kvm_vcpu *vcpu)
 	/* HACK: Don't enable emulation on guest boot/reset */
 	vmx->emulation_required = 0;
 
-out:
 	return ret;
 }
 
@@ -4863,11 +4896,6 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu)
 
 	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");
@@ -7412,6 +7440,11 @@ static int __init vmx_init(void)
 	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);
@@ -7449,6 +7482,11 @@ static void __exit vmx_exit(void)
 	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();
 }