Merge tag 'powerpc-5.10-5' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc fixes from Michael Ellerman:
 "Some more powerpc fixes for 5.10:

   - Three commits fixing possible missed TLB invalidations for
     multi-threaded processes when CPUs are hotplugged in and out.

   - A fix for a host crash triggerable by host userspace (qemu) in KVM
     on Power9.

   - A fix for a host crash in machine check handling when running HPT
     guests on a HPT host.

   - One commit fixing potential missed TLB invalidations when using the
     hash MMU on Power9 or later.

   - A regression fix for machines with CPUs on node 0 but no memory.

  Thanks to Aneesh Kumar K.V, Cédric Le Goater, Greg Kurz, Milan
  Mohanty, Milton Miller, Nicholas Piggin, Paul Mackerras, and Srikar
  Dronamraju"

* tag 'powerpc-5.10-5' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux:
  powerpc/64s/powernv: Fix memory corruption when saving SLB entries on MCE
  KVM: PPC: Book3S HV: XIVE: Fix vCPU id sanity check
  powerpc/numa: Fix a regression on memoryless node 0
  powerpc/64s: Trim offlined CPUs from mm_cpumasks
  kernel/cpu: add arch override for clear_tasks_mm_cpumask() mm handling
  powerpc/64s/pseries: Fix hash tlbiel_all_isa300 for guest kernels
  powerpc/64s: Fix hash ISA v3.0 TLBIEL instruction generation

Author: torvalds

arch/powerpc/include/asm/book3s/64/mmu.h

@@ -242,6 +242,18 @@ extern void radix_init_pseries(void);
 static inline void radix_init_pseries(void) { };
 #endif
 
+#ifdef CONFIG_HOTPLUG_CPU
+#define arch_clear_mm_cpumask_cpu(cpu, mm)				\
+	do {								\
+		if (cpumask_test_cpu(cpu, mm_cpumask(mm))) {		\
+			atomic_dec(&(mm)->context.active_cpus);		\
+			cpumask_clear_cpu(cpu, mm_cpumask(mm));		\
+		}							\
+	} while (0)
+
+void cleanup_cpu_mmu_context(void);
+#endif
+
 static inline int get_user_context(mm_context_t *ctx, unsigned long ea)
 {
 	int index = ea >> MAX_EA_BITS_PER_CONTEXT;

arch/powerpc/kvm/book3s_xive.c

@@ -1214,12 +1214,9 @@ void kvmppc_xive_cleanup_vcpu(struct kvm_vcpu *vcpu)
 static bool kvmppc_xive_vcpu_id_valid(struct kvmppc_xive *xive, u32 cpu)
 {
 	/* We have a block of xive->nr_servers VPs. We just need to check
-	 * raw vCPU ids are below the expected limit for this guest's
-	 * core stride ; kvmppc_pack_vcpu_id() will pack them down to an
-	 * index that can be safely used to compute a VP id that belongs
-	 * to the VP block.
+	 * packed vCPU ids are below that.
 	 */
-	return cpu < xive->nr_servers * xive->kvm->arch.emul_smt_mode;
+	return kvmppc_pack_vcpu_id(xive->kvm, cpu) < xive->nr_servers;
 }
 
 int kvmppc_xive_compute_vp_id(struct kvmppc_xive *xive, u32 cpu, u32 *vp)

arch/powerpc/mm/book3s64/hash_native.c

@@ -68,7 +68,7 @@ static __always_inline void tlbiel_hash_set_isa300(unsigned int set, unsigned in
 	rs = ((unsigned long)pid << PPC_BITLSHIFT(31));
 
 	asm volatile(PPC_TLBIEL(%0, %1, %2, %3, %4)
-		     : : "r"(rb), "r"(rs), "i"(ric), "i"(prs), "r"(r)
+		     : : "r"(rb), "r"(rs), "i"(ric), "i"(prs), "i"(r)
 		     : "memory");
 }
 
@@ -92,16 +92,15 @@ static void tlbiel_all_isa300(unsigned int num_sets, unsigned int is)
 	asm volatile("ptesync": : :"memory");
 
 	/*
-	 * Flush the first set of the TLB, and any caching of partition table
-	 * entries. Then flush the remaining sets of the TLB. Hash mode uses
-	 * partition scoped TLB translations.
+	 * Flush the partition table cache if this is HV mode.
 	 */
-	tlbiel_hash_set_isa300(0, is, 0, 2, 0);
-	for (set = 1; set < num_sets; set++)
-		tlbiel_hash_set_isa300(set, is, 0, 0, 0);
+	if (early_cpu_has_feature(CPU_FTR_HVMODE))
+		tlbiel_hash_set_isa300(0, is, 0, 2, 0);
 
 	/*
-	 * Now invalidate the process table cache.
+	 * Now invalidate the process table cache. UPRT=0 HPT modes (what
+	 * current hardware implements) do not use the process table, but
+	 * add the flushes anyway.
 	 *
 	 * From ISA v3.0B p. 1078:
 	 *     The following forms are invalid.
@@ -110,6 +109,14 @@ static void tlbiel_all_isa300(unsigned int num_sets, unsigned int is)
 	 */
 	tlbiel_hash_set_isa300(0, is, 0, 2, 1);
 
+	/*
+	 * Then flush the sets of the TLB proper. Hash mode uses
+	 * partition scoped TLB translations, which may be flushed
+	 * in !HV mode.
+	 */
+	for (set = 0; set < num_sets; set++)
+		tlbiel_hash_set_isa300(set, is, 0, 0, 0);
+
 	ppc_after_tlbiel_barrier();
 
 	asm volatile(PPC_ISA_3_0_INVALIDATE_ERAT "; isync" : : :"memory");

arch/powerpc/mm/book3s64/mmu_context.c

@@ -17,6 +17,7 @@
 #include <linux/export.h>
 #include <linux/gfp.h>
 #include <linux/slab.h>
+#include <linux/cpu.h>
 
 #include <asm/mmu_context.h>
 #include <asm/pgalloc.h>
@@ -307,3 +308,22 @@ void radix__switch_mmu_context(struct mm_struct *prev, struct mm_struct *next)
 	isync();
 }
 #endif
+
+/**
+ * cleanup_cpu_mmu_context - Clean up MMU details for this CPU (newly offlined)
+ *
+ * This clears the CPU from mm_cpumask for all processes, and then flushes the
+ * local TLB to ensure TLB coherency in case the CPU is onlined again.
+ *
+ * KVM guest translations are not necessarily flushed here. If KVM started
+ * using mm_cpumask or the Linux APIs which do, this would have to be resolved.
+ */
+#ifdef CONFIG_HOTPLUG_CPU
+void cleanup_cpu_mmu_context(void)
+{
+	int cpu = smp_processor_id();
+
+	clear_tasks_mm_cpumask(cpu);
+	tlbiel_all();
+}
+#endif

arch/powerpc/mm/numa.c

@@ -742,8 +742,7 @@ static int __init parse_numa_properties(void)
 			of_node_put(cpu);
 		}
 
-		if (likely(nid > 0))
-			node_set_online(nid);
+		node_set_online(nid);
 	}
 
 	get_n_mem_cells(&n_mem_addr_cells, &n_mem_size_cells);

arch/powerpc/platforms/powermac/smp.c

@@ -911,6 +911,8 @@ static int smp_core99_cpu_disable(void)
 
 	mpic_cpu_set_priority(0xf);
 
+	cleanup_cpu_mmu_context();
+
 	return 0;
 }
 

arch/powerpc/platforms/powernv/setup.c

@@ -211,11 +211,16 @@ static void __init pnv_init(void)
 		add_preferred_console("hvc", 0, NULL);
 
 	if (!radix_enabled()) {
+		size_t size = sizeof(struct slb_entry) * mmu_slb_size;
 		int i;
 
 		/* Allocate per cpu area to save old slb contents during MCE */
-		for_each_possible_cpu(i)
-			paca_ptrs[i]->mce_faulty_slbs = memblock_alloc_node(mmu_slb_size, __alignof__(*paca_ptrs[i]->mce_faulty_slbs), cpu_to_node(i));
+		for_each_possible_cpu(i) {
+			paca_ptrs[i]->mce_faulty_slbs =
+					memblock_alloc_node(size,
+						__alignof__(struct slb_entry),
+						cpu_to_node(i));
+		}
 	}
 }
 

arch/powerpc/platforms/powernv/smp.c

@@ -143,6 +143,9 @@ static int pnv_smp_cpu_disable(void)
 		xive_smp_disable_cpu();
 	else
 		xics_migrate_irqs_away();
+
+	cleanup_cpu_mmu_context();
+
 	return 0;
 }
 

arch/powerpc/platforms/pseries/hotplug-cpu.c

@@ -90,6 +90,9 @@ static int pseries_cpu_disable(void)
 		xive_smp_disable_cpu();
 	else
 		xics_migrate_irqs_away();
+
+	cleanup_cpu_mmu_context();
+
 	return 0;
 }
 

kernel/cpu.c

@@ -815,6 +815,10 @@ void __init cpuhp_threads_init(void)
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
+#ifndef arch_clear_mm_cpumask_cpu
+#define arch_clear_mm_cpumask_cpu(cpu, mm) cpumask_clear_cpu(cpu, mm_cpumask(mm))
+#endif
+
 /**
  * clear_tasks_mm_cpumask - Safely clear tasks' mm_cpumask for a CPU
  * @cpu: a CPU id
@@ -850,7 +854,7 @@ void clear_tasks_mm_cpumask(int cpu)
 		t = find_lock_task_mm(p);
 		if (!t)
 			continue;
-		cpumask_clear_cpu(cpu, mm_cpumask(t->mm));
+		arch_clear_mm_cpumask_cpu(cpu, t->mm);
 		task_unlock(t);
 	}
 	rcu_read_unlock();