Merge tag 'powerpc-4.15-2' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc fixes from Michael Ellerman:
"A small batch of fixes, about 50% tagged for stable and the rest for
recently merged code.

There's one more fix for the >128T handling on hash. Once a process
had requested a single mmap above 128T we would then always search
above 128T. The correct behaviour is to consider the hint address in
isolation for each mmap request.

Then a couple of fixes for the IMC PMU, a missing EXPORT_SYMBOL in
VAS, a fix for STRICT_KERNEL_RWX on 32-bit, and a fix to correctly
identify P9 DD2.1 but in code that is currently not used by default.

Thanks to: Aneesh Kumar K.V, Christophe Leroy, Madhavan Srinivasan,
Sukadev Bhattiprolu"

* tag 'powerpc-4.15-2' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux:
powerpc/64s: Fix Power9 DD2.1 logic in DT CPU features
powerpc/perf: Fix IMC_MAX_PMU macro
powerpc/perf: Fix pmu_count to count only nest imc pmus
powerpc: Fix boot on BOOK3S_32 with CONFIG_STRICT_KERNEL_RWX
powerpc/perf/imc: Use cpu_to_node() not topology_physical_package_id()
powerpc/vas: Export chip_to_vas_id()
powerpc/64s/slice: Use addr limit when computing slice mask

arch/powerpc/include/asm/imc-pmu.h

···
 #include <asm/opal.h>
 
 /*
- * For static allocation of some of the structures.
- */
-#define IMC_MAX_PMUS			32
-
-/*
  * Compatibility macros for IMC devices
  */
 #define IMC_DTB_COMPAT			"ibm,opal-in-memory-counters"
···
 extern int init_imc_pmu(struct device_node *parent,
 				struct imc_pmu *pmu_ptr, int pmu_id);
 extern void thread_imc_disable(void);
+extern int get_max_nest_dev(void);
 #endif /* __ASM_POWERPC_IMC_PMU_H */

arch/powerpc/kernel/dt_cpu_ftrs.c

···
 	 */
 	if ((version & 0xffffff00) == 0x004e0100)
 		cur_cpu_spec->cpu_features |= CPU_FTR_POWER9_DD1;
-	else if ((version & 0xffffefff) == 0x004e0200)
-		cur_cpu_spec->cpu_features &= ~CPU_FTR_POWER9_DD2_1;
+	else if ((version & 0xffffefff) == 0x004e0201)
+		cur_cpu_spec->cpu_features |= CPU_FTR_POWER9_DD2_1;
 }
 
 static void __init cpufeatures_setup_finished(void)

arch/powerpc/lib/code-patching.c

···
 #include <asm/tlbflush.h>
 #include <asm/page.h>
 #include <asm/code-patching.h>
+#include <asm/setup.h>
 
 static int __patch_instruction(unsigned int *addr, unsigned int instr)
 {
···
 	 * During early early boot patch_instruction is called
 	 * when text_poke_area is not ready, but we still need
 	 * to allow patching. We just do the plain old patching
-	 * We use slab_is_available and per cpu read * via this_cpu_read
-	 * of text_poke_area. Per-CPU areas might not be up early
-	 * this can create problems with just using this_cpu_read()
 	 */
-	if (!slab_is_available() || !this_cpu_read(text_poke_area))
+	if (!this_cpu_read(*PTRRELOC(&text_poke_area)))
 		return __patch_instruction(addr, instr);
 
 	local_irq_save(flags);

arch/powerpc/mm/slice.c

···
 	return !slice_area_is_free(mm, start, end - start);
 }
 
-static void slice_mask_for_free(struct mm_struct *mm, struct slice_mask *ret)
+static void slice_mask_for_free(struct mm_struct *mm, struct slice_mask *ret,
+				unsigned long high_limit)
 {
 	unsigned long i;
 
···
 		if (!slice_low_has_vma(mm, i))
 			ret->low_slices |= 1u << i;
 
-	if (mm->context.slb_addr_limit <= SLICE_LOW_TOP)
+	if (high_limit <= SLICE_LOW_TOP)
 		return;
 
-	for (i = 0; i < GET_HIGH_SLICE_INDEX(mm->context.slb_addr_limit); i++)
+	for (i = 0; i < GET_HIGH_SLICE_INDEX(high_limit); i++)
 		if (!slice_high_has_vma(mm, i))
 			__set_bit(i, ret->high_slices);
 }
 
-static void slice_mask_for_size(struct mm_struct *mm, int psize, struct slice_mask *ret)
+static void slice_mask_for_size(struct mm_struct *mm, int psize, struct slice_mask *ret,
+				unsigned long high_limit)
 {
 	unsigned char *hpsizes;
 	int index, mask_index;
···
 		if (((lpsizes >> (i * 4)) & 0xf) == psize)
 			ret->low_slices |= 1u << i;
 
+	if (high_limit <= SLICE_LOW_TOP)
+		return;
+
 	hpsizes = mm->context.high_slices_psize;
-	for (i = 0; i < GET_HIGH_SLICE_INDEX(mm->context.slb_addr_limit); i++) {
+	for (i = 0; i < GET_HIGH_SLICE_INDEX(high_limit); i++) {
 		mask_index = i & 0x1;
 		index = i >> 1;
 		if (((hpsizes[index] >> (mask_index * 4)) & 0xf) == psize)
···
 			   struct slice_mask mask, struct slice_mask available)
 {
 	DECLARE_BITMAP(result, SLICE_NUM_HIGH);
+	/*
+	 * Make sure we just do bit compare only to the max
+	 * addr limit and not the full bit map size.
+	 */
 	unsigned long slice_count = GET_HIGH_SLICE_INDEX(mm->context.slb_addr_limit);
 
 	bitmap_and(result, mask.high_slices,
···
 	/* First make up a "good" mask of slices that have the right size
 	 * already
 	 */
-	slice_mask_for_size(mm, psize, &good_mask);
+	slice_mask_for_size(mm, psize, &good_mask, high_limit);
 	slice_print_mask(" good_mask", good_mask);
 
 	/*
···
 #ifdef CONFIG_PPC_64K_PAGES
 	/* If we support combo pages, we can allow 64k pages in 4k slices */
 	if (psize == MMU_PAGE_64K) {
-		slice_mask_for_size(mm, MMU_PAGE_4K, &compat_mask);
+		slice_mask_for_size(mm, MMU_PAGE_4K, &compat_mask, high_limit);
 		if (fixed)
 			slice_or_mask(&good_mask, &compat_mask);
 	}
···
 			return newaddr;
 		}
 	}
-
-	/* We don't fit in the good mask, check what other slices are
+	/*
+	 * We don't fit in the good mask, check what other slices are
 	 * empty and thus can be converted
 	 */
-	slice_mask_for_free(mm, &potential_mask);
+	slice_mask_for_free(mm, &potential_mask, high_limit);
 	slice_or_mask(&potential_mask, &good_mask);
 	slice_print_mask(" potential", potential_mask);
 
···
 {
 	struct slice_mask mask, available;
 	unsigned int psize = mm->context.user_psize;
+	unsigned long high_limit = mm->context.slb_addr_limit;
 
 	if (radix_enabled())
 		return 0;
 
 	slice_range_to_mask(addr, len, &mask);
-	slice_mask_for_size(mm, psize, &available);
+	slice_mask_for_size(mm, psize, &available, high_limit);
 #ifdef CONFIG_PPC_64K_PAGES
 	/* We need to account for 4k slices too */
 	if (psize == MMU_PAGE_64K) {
 		struct slice_mask compat_mask;
-		slice_mask_for_size(mm, MMU_PAGE_4K, &compat_mask);
+		slice_mask_for_size(mm, MMU_PAGE_4K, &compat_mask, high_limit);
 		slice_or_mask(&available, &compat_mask);
 	}
 #endif

arch/powerpc/perf/imc-pmu.c

···
  */
 static DEFINE_MUTEX(nest_init_lock);
 static DEFINE_PER_CPU(struct imc_pmu_ref *, local_nest_imc_refc);
-static struct imc_pmu *per_nest_pmu_arr[IMC_MAX_PMUS];
+static struct imc_pmu **per_nest_pmu_arr;
 static cpumask_t nest_imc_cpumask;
 struct imc_pmu_ref *nest_imc_refc;
 static int nest_pmus;
···
 static void nest_change_cpu_context(int old_cpu, int new_cpu)
 {
 	struct imc_pmu **pn = per_nest_pmu_arr;
-	int i;
 
 	if (old_cpu < 0 || new_cpu < 0)
 		return;
 
-	for (i = 0; *pn && i < IMC_MAX_PMUS; i++, pn++)
+	while (*pn) {
 		perf_pmu_migrate_context(&(*pn)->pmu, old_cpu, new_cpu);
+		pn++;
+	}
 }
 
 static int ppc_nest_imc_cpu_offline(unsigned int cpu)
···
 	 * Nest HW counter memory resides in a per-chip reserve-memory (HOMER).
 	 * Get the base memory addresss for this cpu.
 	 */
-	chip_id = topology_physical_package_id(event->cpu);
+	chip_id = cpu_to_chip_id(event->cpu);
 	pcni = pmu->mem_info;
 	do {
 		if (pcni->id == chip_id) {
···
  */
 static int core_imc_mem_init(int cpu, int size)
 {
-	int phys_id, rc = 0, core_id = (cpu / threads_per_core);
+	int nid, rc = 0, core_id = (cpu / threads_per_core);
 	struct imc_mem_info *mem_info;
 
 	/*
 	 * alloc_pages_node() will allocate memory for core in the
 	 * local node only.
 	 */
-	phys_id = topology_physical_package_id(cpu);
+	nid = cpu_to_node(cpu);
 	mem_info = &core_imc_pmu->mem_info[core_id];
 	mem_info->id = core_id;
 
 	/* We need only vbase for core counters */
-	mem_info->vbase = page_address(alloc_pages_node(phys_id,
+	mem_info->vbase = page_address(alloc_pages_node(nid,
 					  GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE |
 					  __GFP_NOWARN, get_order(size)));
 	if (!mem_info->vbase)
···
 static int thread_imc_mem_alloc(int cpu_id, int size)
 {
 	u64 ldbar_value, *local_mem = per_cpu(thread_imc_mem, cpu_id);
-	int phys_id = topology_physical_package_id(cpu_id);
+	int nid = cpu_to_node(cpu_id);
 
 	if (!local_mem) {
 		/*
 		 * This case could happen only once at start, since we dont
 		 * free the memory in cpu offline path.
 		 */
-		local_mem = page_address(alloc_pages_node(phys_id,
+		local_mem = page_address(alloc_pages_node(nid,
 				  GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE |
 				  __GFP_NOWARN, get_order(size)));
 		if (!local_mem)
···
 		kfree(pmu_ptr->attr_groups[IMC_EVENT_ATTR]->attrs);
 	kfree(pmu_ptr->attr_groups[IMC_EVENT_ATTR]);
 	kfree(pmu_ptr);
+	kfree(per_nest_pmu_arr);
 	return;
 }
 
···
 			return -ENOMEM;
 
 		/* Needed for hotplug/migration */
+		if (!per_nest_pmu_arr) {
+			per_nest_pmu_arr = kcalloc(get_max_nest_dev() + 1,
+						sizeof(struct imc_pmu *),
+						GFP_KERNEL);
+			if (!per_nest_pmu_arr)
+				return -ENOMEM;
+		}
 		per_nest_pmu_arr[pmu_index] = pmu_ptr;
 		break;
 	case IMC_DOMAIN_CORE:

arch/powerpc/platforms/powernv/opal-imc.c

···
 	put_online_cpus();
 }
 
+int get_max_nest_dev(void)
+{
+	struct device_node *node;
+	u32 pmu_units = 0, type;
+
+	for_each_compatible_node(node, NULL, IMC_DTB_UNIT_COMPAT) {
+		if (of_property_read_u32(node, "type", &type))
+			continue;
+
+		if (type == IMC_TYPE_CHIP)
+			pmu_units++;
+	}
+
+	return pmu_units;
+}
+
 static int opal_imc_counters_probe(struct platform_device *pdev)
 {
 	struct device_node *imc_dev = pdev->dev.of_node;
···
 			break;
 		}
 
-		if (!imc_pmu_create(imc_dev, pmu_count, domain))
-			pmu_count++;
+		if (!imc_pmu_create(imc_dev, pmu_count, domain)) {
+			if (domain == IMC_DOMAIN_NEST)
+				pmu_count++;
+		}
 	}
 
 	return 0;

arch/powerpc/platforms/powernv/vas.c

···
 	}
 	return -1;
 }
+EXPORT_SYMBOL(chip_to_vas_id);
 
 static int vas_probe(struct platform_device *pdev)
 {