Merge tag 'kvm-4.9-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM updates from Radim Krčmář:
 "All architectures:
   - move `make kvmconfig` stubs from x86
   - use 64 bits for debugfs stats

  ARM:
   - Important fixes for not using an in-kernel irqchip
   - handle SError exceptions and present them to guests if appropriate
   - proxying of GICV access at EL2 if guest mappings are unsafe
   - GICv3 on AArch32 on ARMv8
   - preparations for GICv3 save/restore, including ABI docs
   - cleanups and a bit of optimizations

  MIPS:
   - A couple of fixes in preparation for supporting MIPS EVA host
     kernels
   - MIPS SMP host & TLB invalidation fixes

  PPC:
   - Fix the bug which caused guests to falsely report lockups
   - other minor fixes
   - a small optimization

  s390:
   - Lazy enablement of runtime instrumentation
   - up to 255 CPUs for nested guests
   - rework of machine check deliver
   - cleanups and fixes

  x86:
   - IOMMU part of AMD's AVIC for vmexit-less interrupt delivery
   - Hyper-V TSC page
   - per-vcpu tsc_offset in debugfs
   - accelerated INS/OUTS in nVMX
   - cleanups and fixes"

* tag 'kvm-4.9-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (140 commits)
  KVM: MIPS: Drop dubious EntryHi optimisation
  KVM: MIPS: Invalidate TLB by regenerating ASIDs
  KVM: MIPS: Split kernel/user ASID regeneration
  KVM: MIPS: Drop other CPU ASIDs on guest MMU changes
  KVM: arm/arm64: vgic: Don't flush/sync without a working vgic
  KVM: arm64: Require in-kernel irqchip for PMU support
  KVM: PPC: Book3s PR: Allow access to unprivileged MMCR2 register
  KVM: PPC: Book3S PR: Support 64kB page size on POWER8E and POWER8NVL
  KVM: PPC: Book3S: Remove duplicate setting of the B field in tlbie
  KVM: PPC: BookE: Fix a sanity check
  KVM: PPC: Book3S HV: Take out virtual core piggybacking code
  KVM: PPC: Book3S: Treat VTB as a per-subcore register, not per-thread
  ARM: gic-v3: Work around definition of gic_write_bpr1
  KVM: nVMX: Fix the NMI IDT-vectoring handling
  KVM: VMX: Enable MSR-BASED TPR shadow even if APICv is inactive
  KVM: nVMX: Fix reload apic access page warning
  kvmconfig: add virtio-gpu to config fragment
  config: move x86 kvm_guest.config to a common location
  arm64: KVM: Remove duplicating init code for setting VMID
  ARM: KVM: Support vgic-v3
  ...

5 files changed, 176 insertions, 39 deletions

diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h
index b54bcadd8aec..07f58cfc1ab9 100644
--- a/arch/mips/include/asm/kvm_host.h
+++ b/arch/mips/include/asm/kvm_host.h
@@ -107,35 +107,49 @@
 #define KVM_INVALID_INST		0xdeadbeef
 #define KVM_INVALID_ADDR		0xdeadbeef
 
+/*
+ * EVA has overlapping user & kernel address spaces, so user VAs may be >
+ * PAGE_OFFSET. For this reason we can't use the default KVM_HVA_ERR_BAD of
+ * PAGE_OFFSET.
+ */
+
+#define KVM_HVA_ERR_BAD			(-1UL)
+#define KVM_HVA_ERR_RO_BAD		(-2UL)
+
+static inline bool kvm_is_error_hva(unsigned long addr)
+{
+	return IS_ERR_VALUE(addr);
+}
+
 extern atomic_t kvm_mips_instance;
 
 struct kvm_vm_stat {
-	u32 remote_tlb_flush;
+	ulong remote_tlb_flush;
 };
 
 struct kvm_vcpu_stat {
-	u32 wait_exits;
-	u32 cache_exits;
-	u32 signal_exits;
-	u32 int_exits;
-	u32 cop_unusable_exits;
-	u32 tlbmod_exits;
-	u32 tlbmiss_ld_exits;
-	u32 tlbmiss_st_exits;
-	u32 addrerr_st_exits;
-	u32 addrerr_ld_exits;
-	u32 syscall_exits;
-	u32 resvd_inst_exits;
-	u32 break_inst_exits;
-	u32 trap_inst_exits;
-	u32 msa_fpe_exits;
-	u32 fpe_exits;
-	u32 msa_disabled_exits;
-	u32 flush_dcache_exits;
-	u32 halt_successful_poll;
-	u32 halt_attempted_poll;
-	u32 halt_poll_invalid;
-	u32 halt_wakeup;
+	u64 wait_exits;
+	u64 cache_exits;
+	u64 signal_exits;
+	u64 int_exits;
+	u64 cop_unusable_exits;
+	u64 tlbmod_exits;
+	u64 tlbmiss_ld_exits;
+	u64 tlbmiss_st_exits;
+	u64 addrerr_st_exits;
+	u64 addrerr_ld_exits;
+	u64 syscall_exits;
+	u64 resvd_inst_exits;
+	u64 break_inst_exits;
+	u64 trap_inst_exits;
+	u64 msa_fpe_exits;
+	u64 fpe_exits;
+	u64 msa_disabled_exits;
+	u64 flush_dcache_exits;
+	u64 halt_successful_poll;
+	u64 halt_attempted_poll;
+	u64 halt_poll_invalid;
+	u64 halt_wakeup;
 };
 
 struct kvm_arch_memory_slot {
@@ -314,6 +328,9 @@ struct kvm_vcpu_arch {
 	u32 guest_kernel_asid[NR_CPUS];
 	struct mm_struct guest_kernel_mm, guest_user_mm;
 
+	/* Guest ASID of last user mode execution */
+	unsigned int last_user_gasid;
+
 	int last_sched_cpu;
 
 	/* WAIT executed */
diff --git a/arch/mips/kvm/emulate.c b/arch/mips/kvm/emulate.c
index e788515f766b..4db4c0370859 100644
--- a/arch/mips/kvm/emulate.c
+++ b/arch/mips/kvm/emulate.c
@@ -846,6 +846,47 @@ enum emulation_result kvm_mips_emul_tlbr(struct kvm_vcpu *vcpu)
 	return EMULATE_FAIL;
 }
 
+/**
+ * kvm_mips_invalidate_guest_tlb() - Indicates a change in guest MMU map.
+ * @vcpu:	VCPU with changed mappings.
+ * @tlb:	TLB entry being removed.
+ *
+ * This is called to indicate a single change in guest MMU mappings, so that we
+ * can arrange TLB flushes on this and other CPUs.
+ */
+static void kvm_mips_invalidate_guest_tlb(struct kvm_vcpu *vcpu,
+					  struct kvm_mips_tlb *tlb)
+{
+	int cpu, i;
+	bool user;
+
+	/* No need to flush for entries which are already invalid */
+	if (!((tlb->tlb_lo[0] | tlb->tlb_lo[1]) & ENTRYLO_V))
+		return;
+	/* User address space doesn't need flushing for KSeg2/3 changes */
+	user = tlb->tlb_hi < KVM_GUEST_KSEG0;
+
+	preempt_disable();
+
+	/*
+	 * Probe the shadow host TLB for the entry being overwritten, if one
+	 * matches, invalidate it
+	 */
+	kvm_mips_host_tlb_inv(vcpu, tlb->tlb_hi);
+
+	/* Invalidate the whole ASID on other CPUs */
+	cpu = smp_processor_id();
+	for_each_possible_cpu(i) {
+		if (i == cpu)
+			continue;
+		if (user)
+			vcpu->arch.guest_user_asid[i] = 0;
+		vcpu->arch.guest_kernel_asid[i] = 0;
+	}
+
+	preempt_enable();
+}
+
 /* Write Guest TLB Entry @ Index */
 enum emulation_result kvm_mips_emul_tlbwi(struct kvm_vcpu *vcpu)
 {
@@ -865,11 +906,8 @@ enum emulation_result kvm_mips_emul_tlbwi(struct kvm_vcpu *vcpu)
 	}
 
 	tlb = &vcpu->arch.guest_tlb[index];
-	/*
-	 * Probe the shadow host TLB for the entry being overwritten, if one
-	 * matches, invalidate it
-	 */
-	kvm_mips_host_tlb_inv(vcpu, tlb->tlb_hi);
+
+	kvm_mips_invalidate_guest_tlb(vcpu, tlb);
 
 	tlb->tlb_mask = kvm_read_c0_guest_pagemask(cop0);
 	tlb->tlb_hi = kvm_read_c0_guest_entryhi(cop0);
@@ -898,11 +936,7 @@ enum emulation_result kvm_mips_emul_tlbwr(struct kvm_vcpu *vcpu)
 
 	tlb = &vcpu->arch.guest_tlb[index];
 
-	/*
-	 * Probe the shadow host TLB for the entry being overwritten, if one
-	 * matches, invalidate it
-	 */
-	kvm_mips_host_tlb_inv(vcpu, tlb->tlb_hi);
+	kvm_mips_invalidate_guest_tlb(vcpu, tlb);
 
 	tlb->tlb_mask = kvm_read_c0_guest_pagemask(cop0);
 	tlb->tlb_hi = kvm_read_c0_guest_entryhi(cop0);
@@ -1026,6 +1060,7 @@ enum emulation_result kvm_mips_emulate_CP0(union mips_instruction inst,
 	enum emulation_result er = EMULATE_DONE;
 	u32 rt, rd, sel;
 	unsigned long curr_pc;
+	int cpu, i;
 
 	/*
 	 * Update PC and hold onto current PC in case there is
@@ -1127,16 +1162,31 @@ enum emulation_result kvm_mips_emulate_CP0(union mips_instruction inst,
 			} else if (rd == MIPS_CP0_TLB_HI && sel == 0) {
 				u32 nasid =
 					vcpu->arch.gprs[rt] & KVM_ENTRYHI_ASID;
-				if ((KSEGX(vcpu->arch.gprs[rt]) != CKSEG0) &&
-				    ((kvm_read_c0_guest_entryhi(cop0) &
+				if (((kvm_read_c0_guest_entryhi(cop0) &
 				      KVM_ENTRYHI_ASID) != nasid)) {
 					trace_kvm_asid_change(vcpu,
 						kvm_read_c0_guest_entryhi(cop0)
 							& KVM_ENTRYHI_ASID,
 						nasid);
 
-					/* Blow away the shadow host TLBs */
-					kvm_mips_flush_host_tlb(1);
+					/*
+					 * Regenerate/invalidate kernel MMU
+					 * context.
+					 * The user MMU context will be
+					 * regenerated lazily on re-entry to
+					 * guest user if the guest ASID actually
+					 * changes.
+					 */
+					preempt_disable();
+					cpu = smp_processor_id();
+					kvm_get_new_mmu_context(&vcpu->arch.guest_kernel_mm,
+								cpu, vcpu);
+					vcpu->arch.guest_kernel_asid[cpu] =
+						vcpu->arch.guest_kernel_mm.context.asid[cpu];
+					for_each_possible_cpu(i)
+						if (i != cpu)
+							vcpu->arch.guest_kernel_asid[i] = 0;
+					preempt_enable();
 				}
 				kvm_write_c0_guest_entryhi(cop0,
 							   vcpu->arch.gprs[rt]);
diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c
index a6ea084b4d9d..ce961495b5e1 100644
--- a/arch/mips/kvm/mips.c
+++ b/arch/mips/kvm/mips.c
@@ -140,6 +140,16 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	return 0;
 }
 
+bool kvm_arch_has_vcpu_debugfs(void)
+{
+	return false;
+}
+
+int kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu)
+{
+	return 0;
+}
+
 void kvm_mips_free_vcpus(struct kvm *kvm)
 {
 	unsigned int i;
@@ -411,6 +421,31 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
 	return -ENOIOCTLCMD;
 }
 
+/* Must be called with preemption disabled, just before entering guest */
+static void kvm_mips_check_asids(struct kvm_vcpu *vcpu)
+{
+	struct mips_coproc *cop0 = vcpu->arch.cop0;
+	int cpu = smp_processor_id();
+	unsigned int gasid;
+
+	/*
+	 * Lazy host ASID regeneration for guest user mode.
+	 * If the guest ASID has changed since the last guest usermode
+	 * execution, regenerate the host ASID so as to invalidate stale TLB
+	 * entries.
+	 */
+	if (!KVM_GUEST_KERNEL_MODE(vcpu)) {
+		gasid = kvm_read_c0_guest_entryhi(cop0) & KVM_ENTRYHI_ASID;
+		if (gasid != vcpu->arch.last_user_gasid) {
+			kvm_get_new_mmu_context(&vcpu->arch.guest_user_mm, cpu,
+						vcpu);
+			vcpu->arch.guest_user_asid[cpu] =
+				vcpu->arch.guest_user_mm.context.asid[cpu];
+			vcpu->arch.last_user_gasid = gasid;
+		}
+	}
+}
+
 int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 {
 	int r = 0;
@@ -438,6 +473,9 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	htw_stop();
 
 	trace_kvm_enter(vcpu);
+
+	kvm_mips_check_asids(vcpu);
+
 	r = vcpu->arch.vcpu_run(run, vcpu);
 	trace_kvm_out(vcpu);
 
@@ -1551,6 +1589,8 @@ skip_emul:
 	if (ret == RESUME_GUEST) {
 		trace_kvm_reenter(vcpu);
 
+		kvm_mips_check_asids(vcpu);
+
 		/*
 		 * If FPU / MSA are enabled (i.e. the guest's FPU / MSA context
 		 * is live), restore FCR31 / MSACSR.
diff --git a/arch/mips/kvm/mmu.c b/arch/mips/kvm/mmu.c
index 121008c0fcc9..03883ba806e2 100644
--- a/arch/mips/kvm/mmu.c
+++ b/arch/mips/kvm/mmu.c
@@ -250,15 +250,27 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 		kvm_get_new_mmu_context(&vcpu->arch.guest_kernel_mm, cpu, vcpu);
 		vcpu->arch.guest_kernel_asid[cpu] =
 		    vcpu->arch.guest_kernel_mm.context.asid[cpu];
+		newasid++;
+
+		kvm_debug("[%d]: cpu_context: %#lx\n", cpu,
+			  cpu_context(cpu, current->mm));
+		kvm_debug("[%d]: Allocated new ASID for Guest Kernel: %#x\n",
+			  cpu, vcpu->arch.guest_kernel_asid[cpu]);
+	}
+
+	if ((vcpu->arch.guest_user_asid[cpu] ^ asid_cache(cpu)) &
+						asid_version_mask(cpu)) {
+		u32 gasid = kvm_read_c0_guest_entryhi(vcpu->arch.cop0) &
+				KVM_ENTRYHI_ASID;
+
 		kvm_get_new_mmu_context(&vcpu->arch.guest_user_mm, cpu, vcpu);
 		vcpu->arch.guest_user_asid[cpu] =
 		    vcpu->arch.guest_user_mm.context.asid[cpu];
+		vcpu->arch.last_user_gasid = gasid;
 		newasid++;
 
 		kvm_debug("[%d]: cpu_context: %#lx\n", cpu,
 			  cpu_context(cpu, current->mm));
-		kvm_debug("[%d]: Allocated new ASID for Guest Kernel: %#x\n",
-			  cpu, vcpu->arch.guest_kernel_asid[cpu]);
 		kvm_debug("[%d]: Allocated new ASID for Guest User: %#x\n", cpu,
 			  vcpu->arch.guest_user_asid[cpu]);
 	}
diff --git a/arch/mips/kvm/trap_emul.c b/arch/mips/kvm/trap_emul.c
index 091553942bcb..3a5484f9aa50 100644
--- a/arch/mips/kvm/trap_emul.c
+++ b/arch/mips/kvm/trap_emul.c
@@ -175,6 +175,24 @@ static int kvm_trap_emul_handle_tlb_miss(struct kvm_vcpu *vcpu, bool store)
 			run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
 			ret = RESUME_HOST;
 		}
+	} else if (KVM_GUEST_KERNEL_MODE(vcpu)
+		   && (KSEGX(badvaddr) == CKSEG0 || KSEGX(badvaddr) == CKSEG1)) {
+		/*
+		 * With EVA we may get a TLB exception instead of an address
+		 * error when the guest performs MMIO to KSeg1 addresses.
+		 */
+		kvm_debug("Emulate %s MMIO space\n",
+			  store ? "Store to" : "Load from");
+		er = kvm_mips_emulate_inst(cause, opc, run, vcpu);
+		if (er == EMULATE_FAIL) {
+			kvm_err("Emulate %s MMIO space failed\n",
+				store ? "Store to" : "Load from");
+			run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
+			ret = RESUME_HOST;
+		} else {
+			run->exit_reason = KVM_EXIT_MMIO;
+			ret = RESUME_HOST;
+		}
 	} else {
 		kvm_err("Illegal TLB %s fault address , cause %#x, PC: %p, BadVaddr: %#lx\n",
 			store ? "ST" : "LD", cause, opc, badvaddr);