powerpc/64s: Relax PACA address limitations

Book3S PACA memory allocation is restricted by the RMA limit and also
must not take SLB faults when accessed in virtual mode. Currently a
fixed 256MB limit is used for this, which is imprecise and sub-optimal.

Update the paca allocation limits to use use the ppc64_rma_size for RMA
limit, and share the safe_stack_limit() that is currently used for stack
allocations that must not take virtual mode faults.

The safe_stack_limit() name is changed to ppc64_bolted_size() to match
ppc64_rma_size and some comments are updated. We also need to use
early_mmu_has_feature() because we are now calling this function prior
to the jump label patching that enables mmu_has_feature().

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
[mpe: Change mmu_has_feature() to early_mmu_has_feature()]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

arch/powerpc/kernel/paca.c

@@ -18,6 +18,8 @@
 #include <asm/pgtable.h>
 #include <asm/kexec.h>
 
+#include "setup.h"
+
 #ifdef CONFIG_PPC_BOOK3S
 
 /*
@@ -208,15 +210,14 @@ void __init allocate_pacas(void)
 	u64 limit;
 	int cpu;
 
-	limit = ppc64_rma_size;
-
 #ifdef CONFIG_PPC_BOOK3S_64
 	/*
-	 * We can't take SLB misses on the paca, and we want to access them
-	 * in real mode, so allocate them within the RMA and also within
-	 * the first segment.
+	 * We access pacas in real mode, and cannot take SLB faults
+	 * on them when in virtual mode, so allocate them accordingly.
 	 */
-	limit = min(0x10000000ULL, limit);
+	limit = min(ppc64_bolted_size(), ppc64_rma_size);
+#else
+	limit = ppc64_rma_size;
 #endif
 
 	paca_size = PAGE_ALIGN(sizeof(struct paca_struct) * nr_cpu_ids);

arch/powerpc/kernel/setup.h

@@ -51,6 +51,10 @@ void record_spr_defaults(void);
 static inline void record_spr_defaults(void) { };
 #endif
 
+#ifdef CONFIG_PPC64
+u64 ppc64_bolted_size(void);
+#endif
+
 /*
  * Having this in kvm_ppc.h makes include dependencies too
  * tricky to solve for setup-common.c so have it here.

arch/powerpc/kernel/setup_64.c

@@ -565,25 +565,31 @@ void __init initialize_cache_info(void)
 	DBG(" <- initialize_cache_info()\n");
 }
 
-/* This returns the limit below which memory accesses to the linear
- * mapping are guarnateed not to cause a TLB or SLB miss. This is
- * used to allocate interrupt or emergency stacks for which our
- * exception entry path doesn't deal with being interrupted.
+/*
+ * This returns the limit below which memory accesses to the linear
+ * mapping are guarnateed not to cause an architectural exception (e.g.,
+ * TLB or SLB miss fault).
+ *
+ * This is used to allocate PACAs and various interrupt stacks that
+ * that are accessed early in interrupt handlers that must not cause
+ * re-entrant interrupts.
  */
-static __init u64 safe_stack_limit(void)
+__init u64 ppc64_bolted_size(void)
 {
 #ifdef CONFIG_PPC_BOOK3E
 	/* Freescale BookE bolts the entire linear mapping */
-	if (mmu_has_feature(MMU_FTR_TYPE_FSL_E))
+	/* XXX: BookE ppc64_rma_limit setup seems to disagree? */
+	if (early_mmu_has_feature(MMU_FTR_TYPE_FSL_E))
 		return linear_map_top;
 	/* Other BookE, we assume the first GB is bolted */
 	return 1ul << 30;
 #else
+	/* BookS radix, does not take faults on linear mapping */
 	if (early_radix_enabled())
 		return ULONG_MAX;
 
-	/* BookS, the first segment is bolted */
-	if (mmu_has_feature(MMU_FTR_1T_SEGMENT))
+	/* BookS hash, the first segment is bolted */
+	if (early_mmu_has_feature(MMU_FTR_1T_SEGMENT))
 		return 1UL << SID_SHIFT_1T;
 	return 1UL << SID_SHIFT;
 #endif
@@ -591,7 +597,7 @@ static __init u64 safe_stack_limit(void)
 
 void __init irqstack_early_init(void)
 {
-	u64 limit = safe_stack_limit();
+	u64 limit = ppc64_bolted_size();
 	unsigned int i;
 
 	/*
@@ -676,7 +682,7 @@ void __init emergency_stack_init(void)
 	 * initialized in kernel/irq.c. These are initialized here in order
 	 * to have emergency stacks available as early as possible.
 	 */
-	limit = min(safe_stack_limit(), ppc64_rma_size);
+	limit = min(ppc64_bolted_size(), ppc64_rma_size);
 
 	for_each_possible_cpu(i) {
 		struct thread_info *ti;