powerpc/64: Use array of paca pointers and allocate pacas individually

Change the paca array into an array of pointers to pacas. Allocate
pacas individually.

This allows flexibility in where the PACAs are allocated. Future work
will allocate them node-local. Platforms that don't have address limits
on PACAs would be able to defer PACA allocations until later in boot
rather than allocate all possible ones up-front then freeing unused.

This is slightly more overhead (one additional indirection) for cross
CPU paca references, but those aren't too common.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

1 files changed, 12 insertions, 11 deletions

diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index c388cc3357fa0e..3ce12af4906f04 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -110,7 +110,7 @@ void __init setup_tlb_core_data(void)
 		if (cpu_first_thread_sibling(boot_cpuid) == first)
 			first = boot_cpuid;
 
-		paca[cpu].tcd_ptr = &paca[first].tcd;
+		paca_ptrs[cpu]->tcd_ptr = &paca_ptrs[first]->tcd;
 
 		/*
 		 * If we have threads, we need either tlbsrx.
@@ -304,7 +304,7 @@ void __init early_setup(unsigned long dt_ptr)
 	early_init_devtree(__va(dt_ptr));
 
 	/* Now we know the logical id of our boot cpu, setup the paca. */
-	setup_paca(&paca[boot_cpuid]);
+	setup_paca(paca_ptrs[boot_cpuid]);
 	fixup_boot_paca();
 
 	/*
@@ -628,15 +628,15 @@ void __init exc_lvl_early_init(void)
 	for_each_possible_cpu(i) {
 		sp = memblock_alloc(THREAD_SIZE, THREAD_SIZE);
 		critirq_ctx[i] = (struct thread_info *)__va(sp);
-		paca[i].crit_kstack = __va(sp + THREAD_SIZE);
+		paca_ptrs[i]->crit_kstack = __va(sp + THREAD_SIZE);
 
 		sp = memblock_alloc(THREAD_SIZE, THREAD_SIZE);
 		dbgirq_ctx[i] = (struct thread_info *)__va(sp);
-		paca[i].dbg_kstack = __va(sp + THREAD_SIZE);
+		paca_ptrs[i]->dbg_kstack = __va(sp + THREAD_SIZE);
 
 		sp = memblock_alloc(THREAD_SIZE, THREAD_SIZE);
 		mcheckirq_ctx[i] = (struct thread_info *)__va(sp);
-		paca[i].mc_kstack = __va(sp + THREAD_SIZE);
+		paca_ptrs[i]->mc_kstack = __va(sp + THREAD_SIZE);
 	}
 
 	if (cpu_has_feature(CPU_FTR_DEBUG_LVL_EXC))
@@ -693,20 +693,20 @@ void __init emergency_stack_init(void)
 		ti = __va(memblock_alloc_base(THREAD_SIZE, THREAD_SIZE, limit));
 		memset(ti, 0, THREAD_SIZE);
 		emerg_stack_init_thread_info(ti, i);
-		paca[i].emergency_sp = (void *)ti + THREAD_SIZE;
+		paca_ptrs[i]->emergency_sp = (void *)ti + THREAD_SIZE;
 
 #ifdef CONFIG_PPC_BOOK3S_64
 		/* emergency stack for NMI exception handling. */
 		ti = __va(memblock_alloc_base(THREAD_SIZE, THREAD_SIZE, limit));
 		memset(ti, 0, THREAD_SIZE);
 		emerg_stack_init_thread_info(ti, i);
-		paca[i].nmi_emergency_sp = (void *)ti + THREAD_SIZE;
+		paca_ptrs[i]->nmi_emergency_sp = (void *)ti + THREAD_SIZE;
 
 		/* emergency stack for machine check exception handling. */
 		ti = __va(memblock_alloc_base(THREAD_SIZE, THREAD_SIZE, limit));
 		memset(ti, 0, THREAD_SIZE);
 		emerg_stack_init_thread_info(ti, i);
-		paca[i].mc_emergency_sp = (void *)ti + THREAD_SIZE;
+		paca_ptrs[i]->mc_emergency_sp = (void *)ti + THREAD_SIZE;
 #endif
 	}
 }
@@ -762,7 +762,7 @@ void __init setup_per_cpu_areas(void)
 	delta = (unsigned long)pcpu_base_addr - (unsigned long)__per_cpu_start;
 	for_each_possible_cpu(cpu) {
                 __per_cpu_offset[cpu] = delta + pcpu_unit_offsets[cpu];
-		paca[cpu].data_offset = __per_cpu_offset[cpu];
+		paca_ptrs[cpu]->data_offset = __per_cpu_offset[cpu];
 	}
 }
 #endif
@@ -875,8 +875,9 @@ static void init_fallback_flush(void)
 	memset(l1d_flush_fallback_area, 0, l1d_size * 2);
 
 	for_each_possible_cpu(cpu) {
-		paca[cpu].rfi_flush_fallback_area = l1d_flush_fallback_area;
-		paca[cpu].l1d_flush_size = l1d_size;
+		struct paca_struct *paca = paca_ptrs[cpu];
+		paca->rfi_flush_fallback_area = l1d_flush_fallback_area;
+		paca->l1d_flush_size = l1d_size;
 	}
 }