Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM updates from Paolo Bonzini:
 "First batch of KVM changes for 4.1

  The most interesting bit here is irqfd/ioeventfd support for ARM and
  ARM64.

  Summary:

  ARM/ARM64:
     fixes for live migration, irqfd and ioeventfd support (enabling
     vhost, too), page aging

  s390:
     interrupt handling rework, allowing to inject all local interrupts
     via new ioctl and to get/set the full local irq state for migration
     and introspection.  New ioctls to access memory by virtual address,
     and to get/set the guest storage keys.  SIMD support.

  MIPS:
     FPU and MIPS SIMD Architecture (MSA) support.  Includes some
     patches from Ralf Baechle's MIPS tree.

  x86:
     bugfixes (notably for pvclock, the others are small) and cleanups.
     Another small latency improvement for the TSC deadline timer"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (146 commits)
  KVM: use slowpath for cross page cached accesses
  kvm: mmu: lazy collapse small sptes into large sptes
  KVM: x86: Clear CR2 on VCPU reset
  KVM: x86: DR0-DR3 are not clear on reset
  KVM: x86: BSP in MSR_IA32_APICBASE is writable
  KVM: x86: simplify kvm_apic_map
  KVM: x86: avoid logical_map when it is invalid
  KVM: x86: fix mixed APIC mode broadcast
  KVM: x86: use MDA for interrupt matching
  kvm/ppc/mpic: drop unused IRQ_testbit
  KVM: nVMX: remove unnecessary double caching of MAXPHYADDR
  KVM: nVMX: checks for address bits beyond MAXPHYADDR on VM-entry
  KVM: x86: cache maxphyaddr CPUID leaf in struct kvm_vcpu
  KVM: vmx: pass error code with internal error #2
  x86: vdso: fix pvclock races with task migration
  KVM: remove kvm_read_hva and kvm_read_hva_atomic
  KVM: x86: optimize delivery of TSC deadline timer interrupt
  KVM: x86: extract blocking logic from __vcpu_run
  kvm: x86: fix x86 eflags fixed bit
  KVM: s390: migrate vcpu interrupt state
  ...

1 files changed, 25 insertions, 18 deletions

diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index cc618c882f90..ce741b8650f6 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -1261,7 +1261,7 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id)
 
 	svm->vcpu.arch.apic_base = APIC_DEFAULT_PHYS_BASE |
 				   MSR_IA32_APICBASE_ENABLE;
-	if (kvm_vcpu_is_bsp(&svm->vcpu))
+	if (kvm_vcpu_is_reset_bsp(&svm->vcpu))
 		svm->vcpu.arch.apic_base |= MSR_IA32_APICBASE_BSP;
 
 	svm_init_osvw(&svm->vcpu);
@@ -1929,14 +1929,12 @@ static int nop_on_interception(struct vcpu_svm *svm)
 static int halt_interception(struct vcpu_svm *svm)
 {
 	svm->next_rip = kvm_rip_read(&svm->vcpu) + 1;
-	skip_emulated_instruction(&svm->vcpu);
 	return kvm_emulate_halt(&svm->vcpu);
 }
 
 static int vmmcall_interception(struct vcpu_svm *svm)
 {
 	svm->next_rip = kvm_rip_read(&svm->vcpu) + 3;
-	skip_emulated_instruction(&svm->vcpu);
 	kvm_emulate_hypercall(&svm->vcpu);
 	return 1;
 }
@@ -2757,11 +2755,11 @@ static int invlpga_interception(struct vcpu_svm *svm)
 {
 	struct kvm_vcpu *vcpu = &svm->vcpu;
 
-	trace_kvm_invlpga(svm->vmcb->save.rip, vcpu->arch.regs[VCPU_REGS_RCX],
-			  vcpu->arch.regs[VCPU_REGS_RAX]);
+	trace_kvm_invlpga(svm->vmcb->save.rip, kvm_register_read(&svm->vcpu, VCPU_REGS_RCX),
+			  kvm_register_read(&svm->vcpu, VCPU_REGS_RAX));
 
 	/* Let's treat INVLPGA the same as INVLPG (can be optimized!) */
-	kvm_mmu_invlpg(vcpu, vcpu->arch.regs[VCPU_REGS_RAX]);
+	kvm_mmu_invlpg(vcpu, kvm_register_read(&svm->vcpu, VCPU_REGS_RAX));
 
 	svm->next_rip = kvm_rip_read(&svm->vcpu) + 3;
 	skip_emulated_instruction(&svm->vcpu);
@@ -2770,12 +2768,18 @@ static int invlpga_interception(struct vcpu_svm *svm)
 
 static int skinit_interception(struct vcpu_svm *svm)
 {
-	trace_kvm_skinit(svm->vmcb->save.rip, svm->vcpu.arch.regs[VCPU_REGS_RAX]);
+	trace_kvm_skinit(svm->vmcb->save.rip, kvm_register_read(&svm->vcpu, VCPU_REGS_RAX));
 
 	kvm_queue_exception(&svm->vcpu, UD_VECTOR);
 	return 1;
 }
 
+static int wbinvd_interception(struct vcpu_svm *svm)
+{
+	kvm_emulate_wbinvd(&svm->vcpu);
+	return 1;
+}
+
 static int xsetbv_interception(struct vcpu_svm *svm)
 {
 	u64 new_bv = kvm_read_edx_eax(&svm->vcpu);
@@ -2902,7 +2906,8 @@ static int rdpmc_interception(struct vcpu_svm *svm)
 	return 1;
 }
 
-bool check_selective_cr0_intercepted(struct vcpu_svm *svm, unsigned long val)
+static bool check_selective_cr0_intercepted(struct vcpu_svm *svm,
+					    unsigned long val)
 {
 	unsigned long cr0 = svm->vcpu.arch.cr0;
 	bool ret = false;
@@ -2940,7 +2945,10 @@ static int cr_interception(struct vcpu_svm *svm)
 		return emulate_on_interception(svm);
 
 	reg = svm->vmcb->control.exit_info_1 & SVM_EXITINFO_REG_MASK;
-	cr = svm->vmcb->control.exit_code - SVM_EXIT_READ_CR0;
+	if (svm->vmcb->control.exit_code == SVM_EXIT_CR0_SEL_WRITE)
+		cr = SVM_EXIT_WRITE_CR0 - SVM_EXIT_READ_CR0;
+	else
+		cr = svm->vmcb->control.exit_code - SVM_EXIT_READ_CR0;
 
 	err = 0;
 	if (cr >= 16) { /* mov to cr */
@@ -3133,7 +3141,7 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 *data)
 
 static int rdmsr_interception(struct vcpu_svm *svm)
 {
-	u32 ecx = svm->vcpu.arch.regs[VCPU_REGS_RCX];
+	u32 ecx = kvm_register_read(&svm->vcpu, VCPU_REGS_RCX);
 	u64 data;
 
 	if (svm_get_msr(&svm->vcpu, ecx, &data)) {
@@ -3142,8 +3150,8 @@ static int rdmsr_interception(struct vcpu_svm *svm)
 	} else {
 		trace_kvm_msr_read(ecx, data);
 
-		svm->vcpu.arch.regs[VCPU_REGS_RAX] = data & 0xffffffff;
-		svm->vcpu.arch.regs[VCPU_REGS_RDX] = data >> 32;
+		kvm_register_write(&svm->vcpu, VCPU_REGS_RAX, data & 0xffffffff);
+		kvm_register_write(&svm->vcpu, VCPU_REGS_RDX, data >> 32);
 		svm->next_rip = kvm_rip_read(&svm->vcpu) + 2;
 		skip_emulated_instruction(&svm->vcpu);
 	}
@@ -3246,9 +3254,8 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 static int wrmsr_interception(struct vcpu_svm *svm)
 {
 	struct msr_data msr;
-	u32 ecx = svm->vcpu.arch.regs[VCPU_REGS_RCX];
-	u64 data = (svm->vcpu.arch.regs[VCPU_REGS_RAX] & -1u)
-		| ((u64)(svm->vcpu.arch.regs[VCPU_REGS_RDX] & -1u) << 32);
+	u32 ecx = kvm_register_read(&svm->vcpu, VCPU_REGS_RCX);
+	u64 data = kvm_read_edx_eax(&svm->vcpu);
 
 	msr.data = data;
 	msr.index = ecx;
@@ -3325,7 +3332,7 @@ static int (*const svm_exit_handlers[])(struct vcpu_svm *svm) = {
 	[SVM_EXIT_READ_CR3]			= cr_interception,
 	[SVM_EXIT_READ_CR4]			= cr_interception,
 	[SVM_EXIT_READ_CR8]			= cr_interception,
-	[SVM_EXIT_CR0_SEL_WRITE]		= emulate_on_interception,
+	[SVM_EXIT_CR0_SEL_WRITE]		= cr_interception,
 	[SVM_EXIT_WRITE_CR0]			= cr_interception,
 	[SVM_EXIT_WRITE_CR3]			= cr_interception,
 	[SVM_EXIT_WRITE_CR4]			= cr_interception,
@@ -3376,7 +3383,7 @@ static int (*const svm_exit_handlers[])(struct vcpu_svm *svm) = {
 	[SVM_EXIT_STGI]				= stgi_interception,
 	[SVM_EXIT_CLGI]				= clgi_interception,
 	[SVM_EXIT_SKINIT]			= skinit_interception,
-	[SVM_EXIT_WBINVD]                       = emulate_on_interception,
+	[SVM_EXIT_WBINVD]                       = wbinvd_interception,
 	[SVM_EXIT_MONITOR]			= monitor_interception,
 	[SVM_EXIT_MWAIT]			= mwait_interception,
 	[SVM_EXIT_XSETBV]			= xsetbv_interception,
@@ -3555,7 +3562,7 @@ static int handle_exit(struct kvm_vcpu *vcpu)
 
 	if (exit_code >= ARRAY_SIZE(svm_exit_handlers)
 	    || !svm_exit_handlers[exit_code]) {
-		WARN_ONCE(1, "vmx: unexpected exit reason 0x%x\n", exit_code);
+		WARN_ONCE(1, "svm: unexpected exit reason 0x%x\n", exit_code);
 		kvm_queue_exception(vcpu, UD_VECTOR);
 		return 1;
 	}