Merge tag 'powerpc-5.18-2' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc fixes from Michael Ellerman:

 - Fix KVM "lost kick" race, where an attempt to pull a vcpu out of the
   guest could be lost (or delayed until the next guest exit).

 - Disable SCV (system call vectored) when PR KVM guests could be run.

 - Fix KVM PR guests using SCV, by disallowing AIL != 0 for KVM PR
   guests.

 - Add a new KVM CAP to indicate if AIL == 3 is supported.

 - Fix a regression when hotplugging a CPU to a memoryless/cpuless node.

 - Make virt_addr_valid() stricter for 64-bit Book3E & 32-bit, which
   fixes crashes seen due to hardened usercopy.

 - Revert a change to max_mapnr which broke HIGHMEM.

Thanks to Christophe Leroy, Fabiano Rosas, Kefeng Wang, Nicholas Piggin,
and Srikar Dronamraju.

* tag 'powerpc-5.18-2' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux:
  Revert "powerpc: Set max_mapnr correctly"
  powerpc: Fix virt_addr_valid() for 64-bit Book3E & 32-bit
  KVM: PPC: Move kvmhv_on_pseries() into kvm_ppc.h
  powerpc/numa: Handle partially initialized numa nodes
  powerpc/64: Fix build failure with allyesconfig in book3s_64_entry.S
  KVM: PPC: Use KVM_CAP_PPC_AIL_MODE_3
  KVM: PPC: Book3S PR: Disallow AIL != 0
  KVM: PPC: Book3S PR: Disable SCV when AIL could be disabled
  KVM: PPC: Book3S HV P9: Fix "lost kick" race

arch/powerpc/include/asm/kvm_book3s_64.h

@@ -16,18 +16,6 @@
 #include <asm/ppc-opcode.h>
 #include <asm/pte-walk.h>
 
-#ifdef CONFIG_PPC_PSERIES
-static inline bool kvmhv_on_pseries(void)
-{
-	return !cpu_has_feature(CPU_FTR_HVMODE);
-}
-#else
-static inline bool kvmhv_on_pseries(void)
-{
-	return false;
-}
-#endif
-
 /*
  * Structure for a nested guest, that is, for a guest that is managed by
  * one of our guests.

arch/powerpc/include/asm/kvm_ppc.h

@@ -586,6 +586,18 @@ static inline bool kvm_hv_mode_active(void)		{ return false; }
 
 #endif
 
+#ifdef CONFIG_PPC_PSERIES
+static inline bool kvmhv_on_pseries(void)
+{
+	return !cpu_has_feature(CPU_FTR_HVMODE);
+}
+#else
+static inline bool kvmhv_on_pseries(void)
+{
+	return false;
+}
+#endif
+
 #ifdef CONFIG_KVM_XICS
 static inline int kvmppc_xics_enabled(struct kvm_vcpu *vcpu)
 {

arch/powerpc/include/asm/page.h

@@ -132,7 +132,11 @@ static inline bool pfn_valid(unsigned long pfn)
 #define virt_to_page(kaddr)	pfn_to_page(virt_to_pfn(kaddr))
 #define pfn_to_kaddr(pfn)	__va((pfn) << PAGE_SHIFT)
 
-#define virt_addr_valid(kaddr)	pfn_valid(virt_to_pfn(kaddr))
+#define virt_addr_valid(vaddr)	({					\
+	unsigned long _addr = (unsigned long)vaddr;			\
+	_addr >= PAGE_OFFSET && _addr < (unsigned long)high_memory &&	\
+	pfn_valid(virt_to_pfn(_addr));					\
+})
 
 /*
  * On Book-E parts we need __va to parse the device tree and we can't

arch/powerpc/include/asm/setup.h

@@ -28,11 +28,13 @@ void setup_panic(void);
 #define ARCH_PANIC_TIMEOUT 180
 
 #ifdef CONFIG_PPC_PSERIES
+extern bool pseries_reloc_on_exception(void);
 extern bool pseries_enable_reloc_on_exc(void);
 extern void pseries_disable_reloc_on_exc(void);
 extern void pseries_big_endian_exceptions(void);
 void __init pseries_little_endian_exceptions(void);
 #else
+static inline bool pseries_reloc_on_exception(void) { return false; }
 static inline bool pseries_enable_reloc_on_exc(void) { return false; }
 static inline void pseries_disable_reloc_on_exc(void) {}
 static inline void pseries_big_endian_exceptions(void) {}

arch/powerpc/kernel/exceptions-64s.S

@@ -809,6 +809,10 @@ __start_interrupts:
  * - MSR_EE|MSR_RI is clear (no reentrant exceptions)
  * - Standard kernel environment is set up (stack, paca, etc)
  *
+ * KVM:
+ * These interrupts do not elevate HV 0->1, so HV is not involved. PR KVM
+ * ensures that FSCR[SCV] is disabled whenever it has to force AIL off.
+ *
  * Call convention:
  *
  * syscall register convention is in Documentation/powerpc/syscall64-abi.rst

arch/powerpc/kernel/setup_64.c

@@ -196,6 +196,34 @@ static void __init configure_exceptions(void)
 
 	/* Under a PAPR hypervisor, we need hypercalls */
 	if (firmware_has_feature(FW_FEATURE_SET_MODE)) {
+		/*
+		 * - PR KVM does not support AIL mode interrupts in the host
+		 *   while a PR guest is running.
+		 *
+		 * - SCV system call interrupt vectors are only implemented for
+		 *   AIL mode interrupts.
+		 *
+		 * - On pseries, AIL mode can only be enabled and disabled
+		 *   system-wide so when a PR VM is created on a pseries host,
+		 *   all CPUs of the host are set to AIL=0 mode.
+		 *
+		 * - Therefore host CPUs must not execute scv while a PR VM
+		 *   exists.
+		 *
+		 * - SCV support can not be disabled dynamically because the
+		 *   feature is advertised to host userspace. Disabling the
+		 *   facility and emulating it would be possible but is not
+		 *   implemented.
+		 *
+		 * - So SCV support is blanket disabled if PR KVM could possibly
+		 *   run. That is, PR support compiled in, booting on pseries
+		 *   with hash MMU.
+		 */
+		if (IS_ENABLED(CONFIG_KVM_BOOK3S_PR_POSSIBLE) && !radix_enabled()) {
+			init_task.thread.fscr &= ~FSCR_SCV;
+			cur_cpu_spec->cpu_user_features2 &= ~PPC_FEATURE2_SCV;
+		}
+
 		/* Enable AIL if possible */
 		if (!pseries_enable_reloc_on_exc()) {
 			init_task.thread.fscr &= ~FSCR_SCV;

arch/powerpc/kvm/Kconfig

@@ -112,12 +112,21 @@ config KVM_BOOK3S_64_PR
 	  guest in user mode (problem state) and emulating all
 	  privileged instructions and registers.
 
+	  This is only available for hash MMU mode and only supports
+	  guests that use hash MMU mode.
+
 	  This is not as fast as using hypervisor mode, but works on
 	  machines where hypervisor mode is not available or not usable,
 	  and can emulate processors that are different from the host
 	  processor, including emulating 32-bit processors on a 64-bit
 	  host.
 
+	  Selecting this option will cause the SCV facility to be
+	  disabled when the kernel is booted on the pseries platform in
+	  hash MMU mode (regardless of PR VMs running). When any PR VMs
+	  are running, "AIL" mode is disabled which may slow interrupts
+	  and system calls on the host.
+
 config KVM_BOOK3S_HV_EXIT_TIMING
 	bool "Detailed timing for hypervisor real-mode code"
 	depends on KVM_BOOK3S_HV_POSSIBLE && DEBUG_FS

arch/powerpc/kvm/book3s_64_entry.S

@@ -414,10 +414,16 @@ END_FTR_SECTION_IFSET(CPU_FTR_DAWR1)
 	 */
 	ld	r10,HSTATE_SCRATCH0(r13)
 	cmpwi	r10,BOOK3S_INTERRUPT_MACHINE_CHECK
-	beq	machine_check_common
+	beq	.Lcall_machine_check_common
 
 	cmpwi	r10,BOOK3S_INTERRUPT_SYSTEM_RESET
-	beq	system_reset_common
+	beq	.Lcall_system_reset_common
 
 	b	.
+
+.Lcall_machine_check_common:
+	b	machine_check_common
+
+.Lcall_system_reset_common:
+	b	system_reset_common
 #endif

arch/powerpc/kvm/book3s_hv.c

@@ -225,6 +225,13 @@ static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu)
 	int cpu;
 	struct rcuwait *waitp;
 
+	/*
+	 * rcuwait_wake_up contains smp_mb() which orders prior stores that
+	 * create pending work vs below loads of cpu fields. The other side
+	 * is the barrier in vcpu run that orders setting the cpu fields vs
+	 * testing for pending work.
+	 */
+
 	waitp = kvm_arch_vcpu_get_wait(vcpu);
 	if (rcuwait_wake_up(waitp))
 		++vcpu->stat.generic.halt_wakeup;
@@ -1089,7 +1096,7 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
 			break;
 		}
 		tvcpu->arch.prodded = 1;
-		smp_mb();
+		smp_mb(); /* This orders prodded store vs ceded load */
 		if (tvcpu->arch.ceded)
 			kvmppc_fast_vcpu_kick_hv(tvcpu);
 		break;
@@ -3766,6 +3773,14 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
 		pvc = core_info.vc[sub];
 		pvc->pcpu = pcpu + thr;
 		for_each_runnable_thread(i, vcpu, pvc) {
+			/*
+			 * XXX: is kvmppc_start_thread called too late here?
+			 * It updates vcpu->cpu and vcpu->arch.thread_cpu
+			 * which are used by kvmppc_fast_vcpu_kick_hv(), but
+			 * kick is called after new exceptions become available
+			 * and exceptions are checked earlier than here, by
+			 * kvmppc_core_prepare_to_enter.
+			 */
 			kvmppc_start_thread(vcpu, pvc);
 			kvmppc_create_dtl_entry(vcpu, pvc);
 			trace_kvm_guest_enter(vcpu);
@@ -4487,6 +4502,21 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit,
 	if (need_resched() || !kvm->arch.mmu_ready)
 		goto out;
 
+	vcpu->cpu = pcpu;
+	vcpu->arch.thread_cpu = pcpu;
+	vc->pcpu = pcpu;
+	local_paca->kvm_hstate.kvm_vcpu = vcpu;
+	local_paca->kvm_hstate.ptid = 0;
+	local_paca->kvm_hstate.fake_suspend = 0;
+
+	/*
+	 * Orders set cpu/thread_cpu vs testing for pending interrupts and
+	 * doorbells below. The other side is when these fields are set vs
+	 * kvmppc_fast_vcpu_kick_hv reading the cpu/thread_cpu fields to
+	 * kick a vCPU to notice the pending interrupt.
+	 */
+	smp_mb();
+
 	if (!nested) {
 		kvmppc_core_prepare_to_enter(vcpu);
 		if (test_bit(BOOK3S_IRQPRIO_EXTERNAL,
@@ -4506,13 +4536,6 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit,
 
 	tb = mftb();
 
-	vcpu->cpu = pcpu;
-	vcpu->arch.thread_cpu = pcpu;
-	vc->pcpu = pcpu;
-	local_paca->kvm_hstate.kvm_vcpu = vcpu;
-	local_paca->kvm_hstate.ptid = 0;
-	local_paca->kvm_hstate.fake_suspend = 0;
-
 	__kvmppc_create_dtl_entry(vcpu, pcpu, tb + vc->tb_offset, 0);
 
 	trace_kvm_guest_enter(vcpu);
@@ -4614,6 +4637,8 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit,
 	run->exit_reason = KVM_EXIT_INTR;
 	vcpu->arch.ret = -EINTR;
  out:
+	vcpu->cpu = -1;
+	vcpu->arch.thread_cpu = -1;
 	powerpc_local_irq_pmu_restore(flags);
 	preempt_enable();
 	goto done;

arch/powerpc/kvm/book3s_pr.c

@@ -137,12 +137,15 @@ static void kvmppc_core_vcpu_load_pr(struct kvm_vcpu *vcpu, int cpu)
 	svcpu->slb_max = to_book3s(vcpu)->slb_shadow_max;
 	svcpu->in_use = 0;
 	svcpu_put(svcpu);
-#endif
 
 	/* Disable AIL if supported */
-	if (cpu_has_feature(CPU_FTR_HVMODE) &&
-	    cpu_has_feature(CPU_FTR_ARCH_207S))
-		mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) & ~LPCR_AIL);
+	if (cpu_has_feature(CPU_FTR_HVMODE)) {
+		if (cpu_has_feature(CPU_FTR_ARCH_207S))
+			mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) & ~LPCR_AIL);
+		if (cpu_has_feature(CPU_FTR_ARCH_300) && (current->thread.fscr & FSCR_SCV))
+			mtspr(SPRN_FSCR, mfspr(SPRN_FSCR) & ~FSCR_SCV);
+	}
+#endif
 
 	vcpu->cpu = smp_processor_id();
 #ifdef CONFIG_PPC_BOOK3S_32
@@ -165,6 +168,14 @@ static void kvmppc_core_vcpu_put_pr(struct kvm_vcpu *vcpu)
 	memcpy(to_book3s(vcpu)->slb_shadow, svcpu->slb, sizeof(svcpu->slb));
 	to_book3s(vcpu)->slb_shadow_max = svcpu->slb_max;
 	svcpu_put(svcpu);
+
+	/* Enable AIL if supported */
+	if (cpu_has_feature(CPU_FTR_HVMODE)) {
+		if (cpu_has_feature(CPU_FTR_ARCH_207S))
+			mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) | LPCR_AIL_3);
+		if (cpu_has_feature(CPU_FTR_ARCH_300) && (current->thread.fscr & FSCR_SCV))
+			mtspr(SPRN_FSCR, mfspr(SPRN_FSCR) | FSCR_SCV);
+	}
 #endif
 
 	if (kvmppc_is_split_real(vcpu))
@@ -174,11 +185,6 @@ static void kvmppc_core_vcpu_put_pr(struct kvm_vcpu *vcpu)
 	kvmppc_giveup_fac(vcpu, FSCR_TAR_LG);
 	kvmppc_save_tm_pr(vcpu);
 
-	/* Enable AIL if supported */
-	if (cpu_has_feature(CPU_FTR_HVMODE) &&
-	    cpu_has_feature(CPU_FTR_ARCH_207S))
-		mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) | LPCR_AIL_3);
-
 	vcpu->cpu = -1;
 }
 
@@ -1037,6 +1043,8 @@ static int kvmppc_handle_fac(struct kvm_vcpu *vcpu, ulong fac)
 
 void kvmppc_set_fscr(struct kvm_vcpu *vcpu, u64 fscr)
 {
+	if (fscr & FSCR_SCV)
+		fscr &= ~FSCR_SCV; /* SCV must not be enabled */
 	if ((vcpu->arch.fscr & FSCR_TAR) && !(fscr & FSCR_TAR)) {
 		/* TAR got dropped, drop it in shadow too */
 		kvmppc_giveup_fac(vcpu, FSCR_TAR_LG);

arch/powerpc/kvm/book3s_pr_papr.c

@@ -281,6 +281,22 @@ static int kvmppc_h_pr_logical_ci_store(struct kvm_vcpu *vcpu)
 	return EMULATE_DONE;
 }
 
+static int kvmppc_h_pr_set_mode(struct kvm_vcpu *vcpu)
+{
+	unsigned long mflags = kvmppc_get_gpr(vcpu, 4);
+	unsigned long resource = kvmppc_get_gpr(vcpu, 5);
+
+	if (resource == H_SET_MODE_RESOURCE_ADDR_TRANS_MODE) {
+		/* KVM PR does not provide AIL!=0 to guests */
+		if (mflags == 0)
+			kvmppc_set_gpr(vcpu, 3, H_SUCCESS);
+		else
+			kvmppc_set_gpr(vcpu, 3, H_UNSUPPORTED_FLAG_START - 63);
+		return EMULATE_DONE;
+	}
+	return EMULATE_FAIL;
+}
+
 #ifdef CONFIG_SPAPR_TCE_IOMMU
 static int kvmppc_h_pr_put_tce(struct kvm_vcpu *vcpu)
 {
@@ -384,6 +400,8 @@ int kvmppc_h_pr(struct kvm_vcpu *vcpu, unsigned long cmd)
 		return kvmppc_h_pr_logical_ci_load(vcpu);
 	case H_LOGICAL_CI_STORE:
 		return kvmppc_h_pr_logical_ci_store(vcpu);
+	case H_SET_MODE:
+		return kvmppc_h_pr_set_mode(vcpu);
 	case H_XIRR:
 	case H_CPPR:
 	case H_EOI:
@@ -421,6 +439,7 @@ int kvmppc_hcall_impl_pr(unsigned long cmd)
 	case H_CEDE:
 	case H_LOGICAL_CI_LOAD:
 	case H_LOGICAL_CI_STORE:
+	case H_SET_MODE:
 #ifdef CONFIG_KVM_XICS
 	case H_XIRR:
 	case H_CPPR:
@@ -447,6 +466,7 @@ static unsigned int default_hcall_list[] = {
 	H_BULK_REMOVE,
 	H_PUT_TCE,
 	H_CEDE,
+	H_SET_MODE,
 #ifdef CONFIG_KVM_XICS
 	H_XIRR,
 	H_CPPR,

arch/powerpc/kvm/powerpc.c

@@ -705,6 +705,23 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		r = 1;
 		break;
 #endif
+	case KVM_CAP_PPC_AIL_MODE_3:
+		r = 0;
+		/*
+		 * KVM PR, POWER7, and some POWER9s don't support AIL=3 mode.
+		 * The POWER9s can support it if the guest runs in hash mode,
+		 * but QEMU doesn't necessarily query the capability in time.
+		 */
+		if (hv_enabled) {
+			if (kvmhv_on_pseries()) {
+				if (pseries_reloc_on_exception())
+					r = 1;
+			} else if (cpu_has_feature(CPU_FTR_ARCH_207S) &&
+				  !cpu_has_feature(CPU_FTR_P9_RADIX_PREFETCH_BUG)) {
+				r = 1;
+			}
+		}
+		break;
 	default:
 		r = 0;
 		break;

arch/powerpc/mm/mem.c

@@ -255,7 +255,7 @@ void __init mem_init(void)
 #endif
 
 	high_memory = (void *) __va(max_low_pfn * PAGE_SIZE);
-	set_max_mapnr(max_low_pfn);
+	set_max_mapnr(max_pfn);
 
 	kasan_late_init();
 

arch/powerpc/mm/numa.c

@@ -1436,7 +1436,7 @@ int find_and_online_cpu_nid(int cpu)
 	if (new_nid < 0 || !node_possible(new_nid))
 		new_nid = first_online_node;
 
-	if (NODE_DATA(new_nid) == NULL) {
+	if (!node_online(new_nid)) {
 #ifdef CONFIG_MEMORY_HOTPLUG
 		/*
 		 * Need to ensure that NODE_DATA is initialized for a node from

arch/powerpc/platforms/pseries/setup.c

@@ -353,6 +353,14 @@ static void pseries_lpar_idle(void)
 	pseries_idle_epilog();
 }
 
+static bool pseries_reloc_on_exception_enabled;
+
+bool pseries_reloc_on_exception(void)
+{
+	return pseries_reloc_on_exception_enabled;
+}
+EXPORT_SYMBOL_GPL(pseries_reloc_on_exception);
+
 /*
  * Enable relocation on during exceptions. This has partition wide scope and
  * may take a while to complete, if it takes longer than one second we will
@@ -377,6 +385,7 @@ bool pseries_enable_reloc_on_exc(void)
 					" on exceptions: %ld\n", rc);
 				return false;
 			}
+			pseries_reloc_on_exception_enabled = true;
 			return true;
 		}
 
@@ -404,7 +413,9 @@ void pseries_disable_reloc_on_exc(void)
 			break;
 		mdelay(get_longbusy_msecs(rc));
 	}
-	if (rc != H_SUCCESS)
+	if (rc == H_SUCCESS)
+		pseries_reloc_on_exception_enabled = false;
+	else
 		pr_warn("Warning: Failed to disable relocation on exceptions: %ld\n",
 			rc);
 }