[RFC PATCH 09/12] powerpc/64: defer paca allocation until memory topology is discovered

[Nicholas Piggin <npiggin@gmail.com>]

---
 arch/powerpc/include/asm/paca.h    |  3 +-
 arch/powerpc/kernel/paca.c         | 80 +++++++++++++-------------------------
 arch/powerpc/kernel/prom.c         |  5 ++-
 arch/powerpc/kernel/setup-common.c |  2 +
 4 files changed, 35 insertions(+), 55 deletions(-)

diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h
index f266b0a7be95..407a8076edd7 100644
--- a/arch/powerpc/include/asm/paca.h
+++ b/arch/powerpc/include/asm/paca.h
@@ -252,7 +252,8 @@ extern void copy_mm_to_paca(struct mm_struct *mm);
 extern struct paca_struct **paca_ptrs;
 extern void initialise_paca(struct paca_struct *new_paca, int cpu);
 extern void setup_paca(struct paca_struct *new_paca);
-extern void allocate_pacas(void);
+extern void allocate_paca_ptrs(void);
+extern void allocate_paca(int cpu);
 extern void free_unused_pacas(void);
 
 #else /* CONFIG_PPC64 */
diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c
index e560072f122b..981886293369 100644
--- a/arch/powerpc/kernel/paca.c
+++ b/arch/powerpc/kernel/paca.c
@@ -169,12 +169,24 @@ void setup_paca(struct paca_struct *new_paca)
 
 static int __initdata paca_nr_cpu_ids;
 static int __initdata paca_ptrs_size;
+static int __initdata paca_struct_size;
 
-void __init allocate_pacas(void)
+void __init allocate_paca_ptrs(void)
+{
+	paca_nr_cpu_ids = nr_cpu_ids;
+
+	paca_ptrs_size = sizeof(struct paca_struct *) * nr_cpu_ids;
+	paca_ptrs = __va(memblock_alloc(paca_ptrs_size, 0));
+	memset(paca_ptrs, 0x88, paca_ptrs_size);
+}
+
+void __init allocate_paca(int cpu)
 {
 	u64 limit;
-	unsigned long size = 0;
-	int cpu;
+	unsigned long pa;
+	struct paca_struct *paca;
+
+	BUG_ON(cpu >= paca_nr_cpu_ids);
 
 #ifdef CONFIG_PPC_BOOK3S_64
 	/*
@@ -186,69 +198,30 @@ void __init allocate_pacas(void)
 	limit = ppc64_rma_size;
 #endif
 
-	paca_nr_cpu_ids = nr_cpu_ids;
-
-	paca_ptrs_size = sizeof(struct paca_struct *) * nr_cpu_ids;
-	paca_ptrs = __va(memblock_alloc_base(paca_ptrs_size, 0, limit));
-	memset(paca_ptrs, 0, paca_ptrs_size);
-
-	size += paca_ptrs_size;
-
-	for (cpu = 0; cpu < nr_cpu_ids; cpu++) {
-		unsigned long pa;
-
-		pa = memblock_alloc_base(sizeof(struct paca_struct),
-						L1_CACHE_BYTES, limit);
-		paca_ptrs[cpu] = __va(pa);
-		memset(paca_ptrs[cpu], 0, sizeof(struct paca_struct));
+	pa = memblock_alloc_base(sizeof(struct paca_struct),
+					L1_CACHE_BYTES, limit);
+	paca = __va(pa);
+	paca_ptrs[cpu] = paca;
+	memset(paca, 0, sizeof(struct paca_struct));
 
-		size += sizeof(struct paca_struct);
-	}
-
-	printk(KERN_DEBUG "Allocated %lu bytes for %u pacas\n",
-			size, nr_cpu_ids);
-
-	/* Can't use for_each_*_cpu, as they aren't functional yet */
-	for (cpu = 0; cpu < nr_cpu_ids; cpu++) {
-		struct paca_struct *paca = paca_ptrs[cpu];
-
-		initialise_paca(paca, cpu);
+	initialise_paca(paca, cpu);
 #ifdef CONFIG_PPC_PSERIES
-		paca->lppaca_ptr = new_lppaca(cpu, limit);
+	paca->lppaca_ptr = new_lppaca(cpu, limit);
 #endif
 #ifdef CONFIG_PPC_BOOK3S_64
-		paca->slb_shadow_ptr = new_slb_shadow(cpu, limit);
+	paca->slb_shadow_ptr = new_slb_shadow(cpu, limit);
 #endif
-	}
+	paca_struct_size += sizeof(struct paca_struct);
 }
 
 void __init free_unused_pacas(void)
 {
-	unsigned long size = 0;
 	int new_ptrs_size;
-	int cpu;
-
-	for (cpu = 0; cpu < paca_nr_cpu_ids; cpu++) {
-		if (!cpu_possible(cpu)) {
-			unsigned long pa = __pa(paca_ptrs[cpu]);
-#ifdef CONFIG_PPC_PSERIES
-			free_lppaca(paca_ptrs[cpu]->lppaca_ptr);
-#endif
-			memblock_free(pa, sizeof(struct paca_struct));
-			paca_ptrs[cpu] = NULL;
-			size += sizeof(struct paca_struct);
-		}
-	}
 
 	new_ptrs_size = sizeof(struct paca_struct *) * nr_cpu_ids;
-	if (new_ptrs_size < paca_ptrs_size) {
+	if (new_ptrs_size < paca_ptrs_size)
 		memblock_free(__pa(paca_ptrs) + new_ptrs_size,
 					paca_ptrs_size - new_ptrs_size);
-		size += paca_ptrs_size - new_ptrs_size;
-	}
-
-	if (size)
-		printk(KERN_DEBUG "Freed %lu bytes for unused pacas\n", size);
 
 	paca_nr_cpu_ids = nr_cpu_ids;
 	paca_ptrs_size = new_ptrs_size;
@@ -261,6 +234,9 @@ void __init free_unused_pacas(void)
 		paca_ptrs[boot_cpuid]->slb_shadow_ptr = NULL;
 	}
 #endif
+
+	printk(KERN_DEBUG "Allocated %u bytes for %u pacas\n",
+			paca_ptrs_size + paca_struct_size, nr_cpu_ids);
 }
 
 void copy_mm_to_paca(struct mm_struct *mm)
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index 6b29eb1d06f4..175bb0bad1d1 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -365,7 +365,6 @@ static int __init early_init_dt_scan_cpus(unsigned long node,
 	DBG("boot cpu: logical %d physical %d\n", found,
 	    be32_to_cpu(intserv[found_thread]));
 	boot_cpuid = found;
-	set_hard_smp_processor_id(found, be32_to_cpu(intserv[found_thread]));
 
 	/*
 	 * PAPR defines "logical" PVR values for cpus that
@@ -403,7 +402,9 @@ static int __init early_init_dt_scan_cpus(unsigned long node,
 		cur_cpu_spec->cpu_features &= ~CPU_FTR_SMT;
 	else if (!dt_cpu_ftrs_in_use())
 		cur_cpu_spec->cpu_features |= CPU_FTR_SMT;
+	allocate_paca(boot_cpuid);
 #endif
+	set_hard_smp_processor_id(found, be32_to_cpu(intserv[found_thread]));
 
 	return 0;
 }
@@ -744,7 +745,7 @@ void __init early_init_devtree(void *params)
 	 * FIXME .. and the initrd too? */
 	move_device_tree();
 
-	allocate_pacas();
+	allocate_paca_ptrs();
 
 	DBG("Scanning CPUs ...\n");
 
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index 169d7e730aa4..5cf6d4d555c4 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -850,6 +850,7 @@ static void smp_setup_pacas(void)
 	for_each_possible_cpu(cpu) {
 		if (cpu == smp_processor_id())
 			continue;
+		allocate_paca(cpu);
 		set_hard_smp_processor_id(cpu, cpu_to_phys_id[cpu]);
 	}
 
@@ -925,6 +926,7 @@ void __init setup_arch(char **cmdline_p)
 	 * so smp_release_cpus() does nothing for them.
 	 */
 #ifdef CONFIG_SMP
+	smp_setup_pacas();
 	smp_release_cpus();
 #endif
 
-- 
2.16.1