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

Pull KVM fixes from Paolo Bonzini:
"s390 and POWER bug fixes, plus enabling the KVM-VFIO interface on
s390"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
KVM doc: Fix KVM_SMI chapter number
KVM: s390: fix memory overwrites when vx is disabled
KVM: s390: Enable the KVM-VFIO device
KVM: s390: fix guest fprs memory leak
KVM: PPC: Fix ONE_REG AltiVec support
KVM: PPC: Increase memslots to 512
KVM: PPC: Book3S PR: Remove unused variable 'vcpu_book3s'
KVM: PPC: Fix emulation of H_SET_DABR/X on POWER8
KVM: PPC: Book3S HV: Handle unexpected traps in guest entry/exit code better

Documentation/virtual/kvm/api.txt

···
 and it must not exceed (max_vcpus + 32) * sizeof(struct kvm_s390_irq),
 which is the maximum number of possibly pending cpu-local interrupts.
 
-4.90 KVM_SMI
+4.96 KVM_SMI
 
 Capability: KVM_CAP_X86_SMM
 Architectures: x86

arch/powerpc/include/asm/kvm_host.h

···
 
 #define KVM_MAX_VCPUS		NR_CPUS
 #define KVM_MAX_VCORES		NR_CPUS
-#define KVM_USER_MEM_SLOTS 32
-#define KVM_MEM_SLOTS_NUM KVM_USER_MEM_SLOTS
+#define KVM_USER_MEM_SLOTS	512
 
 #ifdef CONFIG_KVM_MMIO
 #define KVM_COALESCED_MMIO_PAGE_OFFSET 1

arch/powerpc/kvm/book3s_64_mmu.c

···
 
 static void kvmppc_mmu_book3s_64_slbmte(struct kvm_vcpu *vcpu, u64 rs, u64 rb)
 {
-	struct kvmppc_vcpu_book3s *vcpu_book3s;
 	u64 esid, esid_1t;
 	int slb_nr;
 	struct kvmppc_slb *slbe;
 
 	dprintk("KVM MMU: slbmte(0x%llx, 0x%llx)\n", rs, rb);
-
-	vcpu_book3s = to_book3s(vcpu);
 
 	esid = GET_ESID(rb);
 	esid_1t = GET_ESID_1T(rb);

arch/powerpc/kvm/book3s_hv.c

···
 
 	vcpu->stat.sum_exits++;
 
+	/*
+	 * This can happen if an interrupt occurs in the last stages
+	 * of guest entry or the first stages of guest exit (i.e. after
+	 * setting paca->kvm_hstate.in_guest to KVM_GUEST_MODE_GUEST_HV
+	 * and before setting it to KVM_GUEST_MODE_HOST_HV).
+	 * That can happen due to a bug, or due to a machine check
+	 * occurring at just the wrong time.
+	 */
+	if (vcpu->arch.shregs.msr & MSR_HV) {
+		printk(KERN_EMERG "KVM trap in HV mode!\n");
+		printk(KERN_EMERG "trap=0x%x | pc=0x%lx | msr=0x%llx\n",
+			vcpu->arch.trap, kvmppc_get_pc(vcpu),
+			vcpu->arch.shregs.msr);
+		kvmppc_dump_regs(vcpu);
+		run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
+		run->hw.hardware_exit_reason = vcpu->arch.trap;
+		return RESUME_HOST;
+	}
 	run->exit_reason = KVM_EXIT_UNKNOWN;
 	run->ready_for_interrupt_injection = 1;
 	switch (vcpu->arch.trap) {

arch/powerpc/kvm/book3s_hv_rmhandlers.S

···
 
 	/* Emulate H_SET_DABR/X on P8 for the sake of compat mode guests */
 2:	rlwimi	r5, r4, 5, DAWRX_DR | DAWRX_DW
-	rlwimi	r5, r4, 1, DAWRX_WT
+	rlwimi	r5, r4, 2, DAWRX_WT
 	clrrdi	r4, r4, 3
 	std	r4, VCPU_DAWR(r3)
 	std	r5, VCPU_DAWRX(r3)
···
 	 * guest as machine check causing guest to crash.
 	 */
 	ld	r11, VCPU_MSR(r9)
+	rldicl.	r0, r11, 64-MSR_HV_LG, 63 /* check if it happened in HV mode */
+	bne	mc_cont			/* if so, exit to host */
 	andi.	r10, r11, MSR_RI	/* check for unrecoverable exception */
 	beq	1f			/* Deliver a machine check to guest */
 	ld	r10, VCPU_PC(r9)

arch/powerpc/kvm/powerpc.c

···
 				r = -ENXIO;
 				break;
 			}
-			vcpu->arch.vr.vr[reg->id - KVM_REG_PPC_VR0] = val.vval;
+			val.vval = vcpu->arch.vr.vr[reg->id - KVM_REG_PPC_VR0];
 			break;
 		case KVM_REG_PPC_VSCR:
 			if (!cpu_has_feature(CPU_FTR_ALTIVEC)) {
 				r = -ENXIO;
 				break;
 			}
-			vcpu->arch.vr.vscr.u[3] = set_reg_val(reg->id, val);
+			val = get_reg_val(reg->id, vcpu->arch.vr.vscr.u[3]);
 			break;
 		case KVM_REG_PPC_VRSAVE:
-			if (!cpu_has_feature(CPU_FTR_ALTIVEC)) {
-				r = -ENXIO;
-				break;
-			}
-			vcpu->arch.vrsave = set_reg_val(reg->id, val);
+			val = get_reg_val(reg->id, vcpu->arch.vrsave);
 			break;
 #endif /* CONFIG_ALTIVEC */
 		default:
···
 				r = -ENXIO;
 				break;
 			}
-			val.vval = vcpu->arch.vr.vr[reg->id - KVM_REG_PPC_VR0];
+			vcpu->arch.vr.vr[reg->id - KVM_REG_PPC_VR0] = val.vval;
 			break;
 		case KVM_REG_PPC_VSCR:
 			if (!cpu_has_feature(CPU_FTR_ALTIVEC)) {
 				r = -ENXIO;
 				break;
 			}
-			val = get_reg_val(reg->id, vcpu->arch.vr.vscr.u[3]);
+			vcpu->arch.vr.vscr.u[3] = set_reg_val(reg->id, val);
 			break;
 		case KVM_REG_PPC_VRSAVE:
-			val = get_reg_val(reg->id, vcpu->arch.vrsave);
+			if (!cpu_has_feature(CPU_FTR_ALTIVEC)) {
+				r = -ENXIO;
+				break;
+			}
+			vcpu->arch.vrsave = set_reg_val(reg->id, val);
 			break;
 #endif /* CONFIG_ALTIVEC */
 		default:

arch/s390/include/asm/kvm_host.h

···
 	struct kvm_s390_sie_block *sie_block;
 	unsigned int      host_acrs[NUM_ACRS];
 	struct fpu	  host_fpregs;
-	struct fpu	  guest_fpregs;
 	struct kvm_s390_local_interrupt local_int;
 	struct hrtimer    ckc_timer;
 	struct kvm_s390_pgm_info pgm;

arch/s390/kvm/Kconfig

···
 	select HAVE_KVM_IRQFD
 	select HAVE_KVM_IRQ_ROUTING
 	select SRCU
+	select KVM_VFIO
 	---help---
 	  Support hosting paravirtualized guest machines using the SIE
 	  virtualization capability on the mainframe. This should work

arch/s390/kvm/Makefile

···
 # as published by the Free Software Foundation.
 
 KVM := ../../../virt/kvm
-common-objs = $(KVM)/kvm_main.o $(KVM)/eventfd.o  $(KVM)/async_pf.o $(KVM)/irqchip.o
+common-objs = $(KVM)/kvm_main.o $(KVM)/eventfd.o  $(KVM)/async_pf.o $(KVM)/irqchip.o $(KVM)/vfio.o
 
 ccflags-y := -Ivirt/kvm -Iarch/s390/kvm
 

arch/s390/kvm/kvm-s390.c

···
 	return 0;
 }
 
-/*
- * Backs up the current FP/VX register save area on a particular
- * destination.  Used to switch between different register save
- * areas.
- */
-static inline void save_fpu_to(struct fpu *dst)
-{
-	dst->fpc = current->thread.fpu.fpc;
-	dst->regs = current->thread.fpu.regs;
-}
-
-/*
- * Switches the FP/VX register save area from which to lazy
- * restore register contents.
- */
-static inline void load_fpu_from(struct fpu *from)
-{
-	current->thread.fpu.fpc = from->fpc;
-	current->thread.fpu.regs = from->regs;
-}
-
 void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
 	/* Save host register state */
 	save_fpu_regs();
-	save_fpu_to(&vcpu->arch.host_fpregs);
+	vcpu->arch.host_fpregs.fpc = current->thread.fpu.fpc;
+	vcpu->arch.host_fpregs.regs = current->thread.fpu.regs;
 
-	if (test_kvm_facility(vcpu->kvm, 129)) {
-		current->thread.fpu.fpc = vcpu->run->s.regs.fpc;
-		/*
-		 * Use the register save area in the SIE-control block
-		 * for register restore and save in kvm_arch_vcpu_put()
-		 */
-		current->thread.fpu.vxrs =
-			(__vector128 *)&vcpu->run->s.regs.vrs;
-	} else
-		load_fpu_from(&vcpu->arch.guest_fpregs);
-
+	/* Depending on MACHINE_HAS_VX, data stored to vrs either
+	 * has vector register or floating point register format.
+	 */
+	current->thread.fpu.regs = vcpu->run->s.regs.vrs;
+	current->thread.fpu.fpc = vcpu->run->s.regs.fpc;
 	if (test_fp_ctl(current->thread.fpu.fpc))
 		/* User space provided an invalid FPC, let's clear it */
 		current->thread.fpu.fpc = 0;
···
 	atomic_andnot(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
 	gmap_disable(vcpu->arch.gmap);
 
+	/* Save guest register state */
 	save_fpu_regs();
+	vcpu->run->s.regs.fpc = current->thread.fpu.fpc;
 
-	if (test_kvm_facility(vcpu->kvm, 129))
-		/*
-		 * kvm_arch_vcpu_load() set up the register save area to
-		 * the &vcpu->run->s.regs.vrs and, thus, the vector registers
-		 * are already saved.  Only the floating-point control must be
-		 * copied.
-		 */
-		vcpu->run->s.regs.fpc = current->thread.fpu.fpc;
-	else
-		save_fpu_to(&vcpu->arch.guest_fpregs);
-	load_fpu_from(&vcpu->arch.host_fpregs);
+	/* Restore host register state */
+	current->thread.fpu.fpc = vcpu->arch.host_fpregs.fpc;
+	current->thread.fpu.regs = vcpu->arch.host_fpregs.regs;
 
 	save_access_regs(vcpu->run->s.regs.acrs);
 	restore_access_regs(vcpu->arch.host_acrs);
···
 	memset(vcpu->arch.sie_block->gcr, 0, 16 * sizeof(__u64));
 	vcpu->arch.sie_block->gcr[0]  = 0xE0UL;
 	vcpu->arch.sie_block->gcr[14] = 0xC2000000UL;
-	vcpu->arch.guest_fpregs.fpc = 0;
-	asm volatile("lfpc %0" : : "Q" (vcpu->arch.guest_fpregs.fpc));
+	/* make sure the new fpc will be lazily loaded */
+	save_fpu_regs();
+	current->thread.fpu.fpc = 0;
 	vcpu->arch.sie_block->gbea = 1;
 	vcpu->arch.sie_block->pp = 0;
 	vcpu->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID;
···
 	vcpu->arch.local_int.float_int = &kvm->arch.float_int;
 	vcpu->arch.local_int.wq = &vcpu->wq;
 	vcpu->arch.local_int.cpuflags = &vcpu->arch.sie_block->cpuflags;
-
-	/*
-	 * Allocate a save area for floating-point registers.  If the vector
-	 * extension is available, register contents are saved in the SIE
-	 * control block.  The allocated save area is still required in
-	 * particular places, for example, in kvm_s390_vcpu_store_status().
-	 */
-	vcpu->arch.guest_fpregs.fprs = kzalloc(sizeof(freg_t) * __NUM_FPRS,
-					       GFP_KERNEL);
-	if (!vcpu->arch.guest_fpregs.fprs)
-		goto out_free_sie_block;
 
 	rc = kvm_vcpu_init(vcpu, kvm, id);
 	if (rc)
···
 
 int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
 {
+	/* make sure the new values will be lazily loaded */
+	save_fpu_regs();
 	if (test_fp_ctl(fpu->fpc))
 		return -EINVAL;
-	memcpy(vcpu->arch.guest_fpregs.fprs, &fpu->fprs, sizeof(fpu->fprs));
-	vcpu->arch.guest_fpregs.fpc = fpu->fpc;
-	save_fpu_regs();
-	load_fpu_from(&vcpu->arch.guest_fpregs);
+	current->thread.fpu.fpc = fpu->fpc;
+	if (MACHINE_HAS_VX)
+		convert_fp_to_vx(current->thread.fpu.vxrs, (freg_t *)fpu->fprs);
+	else
+		memcpy(current->thread.fpu.fprs, &fpu->fprs, sizeof(fpu->fprs));
 	return 0;
 }
 
 int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
 {
-	memcpy(&fpu->fprs, vcpu->arch.guest_fpregs.fprs, sizeof(fpu->fprs));
-	fpu->fpc = vcpu->arch.guest_fpregs.fpc;
+	/* make sure we have the latest values */
+	save_fpu_regs();
+	if (MACHINE_HAS_VX)
+		convert_vx_to_fp((freg_t *)fpu->fprs, current->thread.fpu.vxrs);
+	else
+		memcpy(fpu->fprs, current->thread.fpu.fprs, sizeof(fpu->fprs));
+	fpu->fpc = current->thread.fpu.fpc;
 	return 0;
 }
 
···
 int kvm_s390_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long gpa)
 {
 	unsigned char archmode = 1;
+	freg_t fprs[NUM_FPRS];
 	unsigned int px;
 	u64 clkcomp;
 	int rc;
···
 		gpa = px;
 	} else
 		gpa -= __LC_FPREGS_SAVE_AREA;
-	rc = write_guest_abs(vcpu, gpa + __LC_FPREGS_SAVE_AREA,
-			     vcpu->arch.guest_fpregs.fprs, 128);
+
+	/* manually convert vector registers if necessary */
+	if (MACHINE_HAS_VX) {
+		convert_vx_to_fp(fprs, current->thread.fpu.vxrs);
+		rc = write_guest_abs(vcpu, gpa + __LC_FPREGS_SAVE_AREA,
+				     fprs, 128);
+	} else {
+		rc = write_guest_abs(vcpu, gpa + __LC_FPREGS_SAVE_AREA,
+				     vcpu->run->s.regs.vrs, 128);
+	}
 	rc |= write_guest_abs(vcpu, gpa + __LC_GPREGS_SAVE_AREA,
 			      vcpu->run->s.regs.gprs, 128);
 	rc |= write_guest_abs(vcpu, gpa + __LC_PSW_SAVE_AREA,
···
 	rc |= write_guest_abs(vcpu, gpa + __LC_PREFIX_SAVE_AREA,
 			      &px, 4);
 	rc |= write_guest_abs(vcpu, gpa + __LC_FP_CREG_SAVE_AREA,
-			      &vcpu->arch.guest_fpregs.fpc, 4);
+			      &vcpu->run->s.regs.fpc, 4);
 	rc |= write_guest_abs(vcpu, gpa + __LC_TOD_PROGREG_SAVE_AREA,
 			      &vcpu->arch.sie_block->todpr, 4);
 	rc |= write_guest_abs(vcpu, gpa + __LC_CPU_TIMER_SAVE_AREA,
···
 	 * it into the save area
 	 */
 	save_fpu_regs();
-	if (test_kvm_facility(vcpu->kvm, 129)) {
-		/*
-		 * If the vector extension is available, the vector registers
-		 * which overlaps with floating-point registers are saved in
-		 * the SIE-control block.  Hence, extract the floating-point
-		 * registers and the FPC value and store them in the
-		 * guest_fpregs structure.
-		 */
-		vcpu->arch.guest_fpregs.fpc = current->thread.fpu.fpc;
-		convert_vx_to_fp(vcpu->arch.guest_fpregs.fprs,
-				 current->thread.fpu.vxrs);
-	} else
-		save_fpu_to(&vcpu->arch.guest_fpregs);
+	vcpu->run->s.regs.fpc = current->thread.fpu.fpc;
 	save_access_regs(vcpu->run->s.regs.acrs);
 
 	return kvm_s390_store_status_unloaded(vcpu, addr);