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

Pull kvm fixes from Paolo Bonzini:
 "Small fixes for x86, slightly larger fixes for PPC, and a forgotten
  s390 patch.  The PPC fixes are important because they fix breakage
  that is new in 3.15"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  KVM: s390: announce irqfd capability
  KVM: x86: disable master clock if TSC is reset during suspend
  KVM: vmx: disable APIC virtualization in nested guests
  KVM guest: Make pv trampoline code executable
  KVM: PPC: Book3S: ifdef on CONFIG_KVM_BOOK3S_32_HANDLER for 32bit
  KVM: PPC: Book3S HV: Add missing code for transaction reclaim on guest exit
  KVM: PPC: Book3S: HV: make _PAGE_NUMA take effect

Documentation/virtual/kvm/api.txt

@@ -2126,7 +2126,7 @@ into the hash PTE second double word).
 4.75 KVM_IRQFD
 
 Capability: KVM_CAP_IRQFD
-Architectures: x86
+Architectures: x86 s390
 Type: vm ioctl
 Parameters: struct kvm_irqfd (in)
 Returns: 0 on success, -1 on error

arch/powerpc/include/asm/sections.h

@@ -39,6 +39,17 @@ static inline int overlaps_kernel_text(unsigned long start, unsigned long end)
 		(unsigned long)_stext < end;
 }
 
+static inline int overlaps_kvm_tmp(unsigned long start, unsigned long end)
+{
+#ifdef CONFIG_KVM_GUEST
+	extern char kvm_tmp[];
+	return start < (unsigned long)kvm_tmp &&
+		(unsigned long)&kvm_tmp[1024 * 1024] < end;
+#else
+	return 0;
+#endif
+}
+
 #undef dereference_function_descriptor
 static inline void *dereference_function_descriptor(void *ptr)
 {

arch/powerpc/kernel/kvm.c

@@ -74,7 +74,7 @@
 #define KVM_INST_MTSRIN		0x7c0001e4
 
 static bool kvm_patching_worked = true;
-static char kvm_tmp[1024 * 1024];
+char kvm_tmp[1024 * 1024];
 static int kvm_tmp_index;
 
 static inline void kvm_patch_ins(u32 *inst, u32 new_inst)

arch/powerpc/kvm/book3s.c

@@ -886,7 +886,7 @@ static int kvmppc_book3s_init(void)
 	r = kvm_init(NULL, sizeof(struct kvm_vcpu), 0, THIS_MODULE);
 	if (r)
 		return r;
-#ifdef CONFIG_KVM_BOOK3S_32
+#ifdef CONFIG_KVM_BOOK3S_32_HANDLER
 	r = kvmppc_book3s_init_pr();
 #endif
 	return r;
@@ -895,7 +895,7 @@ static int kvmppc_book3s_init(void)
 
 static void kvmppc_book3s_exit(void)
 {
-#ifdef CONFIG_KVM_BOOK3S_32
+#ifdef CONFIG_KVM_BOOK3S_32_HANDLER
 	kvmppc_book3s_exit_pr();
 #endif
 	kvm_exit();
@@ -905,7 +905,7 @@ module_init(kvmppc_book3s_init);
 module_exit(kvmppc_book3s_exit);
 
 /* On 32bit this is our one and only kernel module */
-#ifdef CONFIG_KVM_BOOK3S_32
+#ifdef CONFIG_KVM_BOOK3S_32_HANDLER
 MODULE_ALIAS_MISCDEV(KVM_MINOR);
 MODULE_ALIAS("devname:kvm");
 #endif

arch/powerpc/kvm/book3s_hv_rm_mmu.c

@@ -234,7 +234,7 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags,
 		pte_size = psize;
 		pte = lookup_linux_pte_and_update(pgdir, hva, writing,
 						  &pte_size);
-		if (pte_present(pte)) {
+		if (pte_present(pte) && !pte_numa(pte)) {
 			if (writing && !pte_write(pte))
 				/* make the actual HPTE be read-only */
 				ptel = hpte_make_readonly(ptel);

arch/powerpc/kvm/book3s_hv_rmhandlers.S

@@ -1323,6 +1323,110 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
 	mr	r3, r9
 	bl	kvmppc_save_fp
 
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+BEGIN_FTR_SECTION
+	b	2f
+END_FTR_SECTION_IFCLR(CPU_FTR_TM)
+	/* Turn on TM. */
+	mfmsr	r8
+	li	r0, 1
+	rldimi	r8, r0, MSR_TM_LG, 63-MSR_TM_LG
+	mtmsrd	r8
+
+	ld	r5, VCPU_MSR(r9)
+	rldicl. r5, r5, 64 - MSR_TS_S_LG, 62
+	beq	1f	/* TM not active in guest. */
+
+	li	r3, TM_CAUSE_KVM_RESCHED
+
+	/* Clear the MSR RI since r1, r13 are all going to be foobar. */
+	li	r5, 0
+	mtmsrd	r5, 1
+
+	/* All GPRs are volatile at this point. */
+	TRECLAIM(R3)
+
+	/* Temporarily store r13 and r9 so we have some regs to play with */
+	SET_SCRATCH0(r13)
+	GET_PACA(r13)
+	std	r9, PACATMSCRATCH(r13)
+	ld	r9, HSTATE_KVM_VCPU(r13)
+
+	/* Get a few more GPRs free. */
+	std	r29, VCPU_GPRS_TM(29)(r9)
+	std	r30, VCPU_GPRS_TM(30)(r9)
+	std	r31, VCPU_GPRS_TM(31)(r9)
+
+	/* Save away PPR and DSCR soon so don't run with user values. */
+	mfspr	r31, SPRN_PPR
+	HMT_MEDIUM
+	mfspr	r30, SPRN_DSCR
+	ld	r29, HSTATE_DSCR(r13)
+	mtspr	SPRN_DSCR, r29
+
+	/* Save all but r9, r13 & r29-r31 */
+	reg = 0
+	.rept	29
+	.if (reg != 9) && (reg != 13)
+	std	reg, VCPU_GPRS_TM(reg)(r9)
+	.endif
+	reg = reg + 1
+	.endr
+	/* ... now save r13 */
+	GET_SCRATCH0(r4)
+	std	r4, VCPU_GPRS_TM(13)(r9)
+	/* ... and save r9 */
+	ld	r4, PACATMSCRATCH(r13)
+	std	r4, VCPU_GPRS_TM(9)(r9)
+
+	/* Reload stack pointer and TOC. */
+	ld	r1, HSTATE_HOST_R1(r13)
+	ld	r2, PACATOC(r13)
+
+	/* Set MSR RI now we have r1 and r13 back. */
+	li	r5, MSR_RI
+	mtmsrd	r5, 1
+
+	/* Save away checkpinted SPRs. */
+	std	r31, VCPU_PPR_TM(r9)
+	std	r30, VCPU_DSCR_TM(r9)
+	mflr	r5
+	mfcr	r6
+	mfctr	r7
+	mfspr	r8, SPRN_AMR
+	mfspr	r10, SPRN_TAR
+	std	r5, VCPU_LR_TM(r9)
+	stw	r6, VCPU_CR_TM(r9)
+	std	r7, VCPU_CTR_TM(r9)
+	std	r8, VCPU_AMR_TM(r9)
+	std	r10, VCPU_TAR_TM(r9)
+
+	/* Restore r12 as trap number. */
+	lwz	r12, VCPU_TRAP(r9)
+
+	/* Save FP/VSX. */
+	addi	r3, r9, VCPU_FPRS_TM
+	bl	.store_fp_state
+	addi	r3, r9, VCPU_VRS_TM
+	bl	.store_vr_state
+	mfspr	r6, SPRN_VRSAVE
+	stw	r6, VCPU_VRSAVE_TM(r9)
+1:
+	/*
+	 * We need to save these SPRs after the treclaim so that the software
+	 * error code is recorded correctly in the TEXASR.  Also the user may
+	 * change these outside of a transaction, so they must always be
+	 * context switched.
+	 */
+	mfspr	r5, SPRN_TFHAR
+	mfspr	r6, SPRN_TFIAR
+	mfspr	r7, SPRN_TEXASR
+	std	r5, VCPU_TFHAR(r9)
+	std	r6, VCPU_TFIAR(r9)
+	std	r7, VCPU_TEXASR(r9)
+2:
+#endif
+
 	/* Increment yield count if they have a VPA */
 	ld	r8, VCPU_VPA(r9)	/* do they have a VPA? */
 	cmpdi	r8, 0

arch/powerpc/kvm/book3s_pr.c

@@ -1153,7 +1153,7 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_pr(struct kvm *kvm,
 		goto free_vcpu;
 	vcpu->arch.book3s = vcpu_book3s;
 
-#ifdef CONFIG_KVM_BOOK3S_32
+#ifdef CONFIG_KVM_BOOK3S_32_HANDLER
 	vcpu->arch.shadow_vcpu =
 		kzalloc(sizeof(*vcpu->arch.shadow_vcpu), GFP_KERNEL);
 	if (!vcpu->arch.shadow_vcpu)
@@ -1198,7 +1198,7 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_pr(struct kvm *kvm,
 uninit_vcpu:
 	kvm_vcpu_uninit(vcpu);
 free_shadow_vcpu:
-#ifdef CONFIG_KVM_BOOK3S_32
+#ifdef CONFIG_KVM_BOOK3S_32_HANDLER
 	kfree(vcpu->arch.shadow_vcpu);
 free_vcpu3s:
 #endif
@@ -1215,7 +1215,7 @@ static void kvmppc_core_vcpu_free_pr(struct kvm_vcpu *vcpu)
 
 	free_page((unsigned long)vcpu->arch.shared & PAGE_MASK);
 	kvm_vcpu_uninit(vcpu);
-#ifdef CONFIG_KVM_BOOK3S_32
+#ifdef CONFIG_KVM_BOOK3S_32_HANDLER
 	kfree(vcpu->arch.shadow_vcpu);
 #endif
 	vfree(vcpu_book3s);

arch/powerpc/mm/hash_utils_64.c

@@ -207,6 +207,10 @@ int htab_bolt_mapping(unsigned long vstart, unsigned long vend,
 		if (overlaps_kernel_text(vaddr, vaddr + step))
 			tprot &= ~HPTE_R_N;
 
+		/* Make kvm guest trampolines executable */
+		if (overlaps_kvm_tmp(vaddr, vaddr + step))
+			tprot &= ~HPTE_R_N;
+
 		/*
 		 * If relocatable, check if it overlaps interrupt vectors that
 		 * are copied down to real 0. For relocatable kernel

arch/s390/kvm/kvm-s390.c

@@ -158,6 +158,7 @@ int kvm_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_ONE_REG:
 	case KVM_CAP_ENABLE_CAP:
 	case KVM_CAP_S390_CSS_SUPPORT:
+	case KVM_CAP_IRQFD:
 	case KVM_CAP_IOEVENTFD:
 	case KVM_CAP_DEVICE_CTRL:
 	case KVM_CAP_ENABLE_CAP_VM:

arch/x86/kvm/vmx.c

@@ -7778,7 +7778,8 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 
 	exec_control = vmcs12->pin_based_vm_exec_control;
 	exec_control |= vmcs_config.pin_based_exec_ctrl;
-	exec_control &= ~PIN_BASED_VMX_PREEMPTION_TIMER;
+	exec_control &= ~(PIN_BASED_VMX_PREEMPTION_TIMER |
+                          PIN_BASED_POSTED_INTR);
 	vmcs_write32(PIN_BASED_VM_EXEC_CONTROL, exec_control);
 
 	vmx->nested.preemption_timer_expired = false;
@@ -7815,7 +7816,9 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 		if (!vmx->rdtscp_enabled)
 			exec_control &= ~SECONDARY_EXEC_RDTSCP;
 		/* Take the following fields only from vmcs12 */
-		exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
+		exec_control &= ~(SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES |
+				  SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY |
+                                  SECONDARY_EXEC_APIC_REGISTER_VIRT);
 		if (nested_cpu_has(vmcs12,
 				CPU_BASED_ACTIVATE_SECONDARY_CONTROLS))
 			exec_control |= vmcs12->secondary_vm_exec_control;

arch/x86/kvm/x86.c

@@ -106,6 +106,8 @@ EXPORT_SYMBOL_GPL(kvm_max_guest_tsc_khz);
 static u32 tsc_tolerance_ppm = 250;
 module_param(tsc_tolerance_ppm, uint, S_IRUGO | S_IWUSR);
 
+static bool backwards_tsc_observed = false;
+
 #define KVM_NR_SHARED_MSRS 16
 
 struct kvm_shared_msrs_global {
@@ -1486,7 +1488,8 @@ static void pvclock_update_vm_gtod_copy(struct kvm *kvm)
 					&ka->master_kernel_ns,
 					&ka->master_cycle_now);
 
-	ka->use_master_clock = host_tsc_clocksource & vcpus_matched;
+	ka->use_master_clock = host_tsc_clocksource && vcpus_matched
+				&& !backwards_tsc_observed;
 
 	if (ka->use_master_clock)
 		atomic_set(&kvm_guest_has_master_clock, 1);
@@ -6945,6 +6948,7 @@ int kvm_arch_hardware_enable(void *garbage)
 	 */
 	if (backwards_tsc) {
 		u64 delta_cyc = max_tsc - local_tsc;
+		backwards_tsc_observed = true;
 		list_for_each_entry(kvm, &vm_list, vm_list) {
 			kvm_for_each_vcpu(i, vcpu, kvm) {
 				vcpu->arch.tsc_offset_adjustment += delta_cyc;