MIPS: Build uasm-generated code only once to avoid CPU Hotplug problem

This and the next patch resolve memory corruption problems while CPU
hotplug. Without these patches, memory corruption can triggered easily
as below:

On a quad-core MIPS platform, use "spawn" of UnixBench-5.1.3 (http://
code.google.com/p/byte-unixbench/) and a CPU hotplug script like this
(hotplug.sh):
while true; do
echo 0 >/sys/devices/system/cpu/cpu1/online
echo 0 >/sys/devices/system/cpu/cpu2/online
echo 0 >/sys/devices/system/cpu/cpu3/online
sleep 1
echo 1 >/sys/devices/system/cpu/cpu1/online
echo 1 >/sys/devices/system/cpu/cpu2/online
echo 1 >/sys/devices/system/cpu/cpu3/online
sleep 1
done

Run "hotplug.sh" and then run "spawn 10000", spawn will get segfault
after a few minutes.

This patch:
Currently, clear_page()/copy_page() are generated by Micro-assembler
dynamically. But they are unavailable until uasm_resolve_relocs() has
finished because jump labels are illegal before that. Since these
functions are shared by every CPU, we only call build_clear_page()/
build_copy_page() only once at boot time. Without this patch, programs
will get random memory corruption (segmentation fault, bus error, etc.)
while CPU Hotplug (e.g. one CPU is using clear_page() while another is
generating it in cpu_cache_init()).

For similar reasons we modify build_tlb_refill_handler()'s invocation.

V2:
1, Rework the code to make CPU#0 can be online/offline.
2, Introduce cpu_has_local_ebase feature since some types of MIPS CPU
   need a per-CPU tlb_refill_handler().

Signed-off-by: Huacai Chen <chenhc@lemote.com>
Signed-off-by: Hongbing Hu <huhb@lemote.com>
Acked-by: David Daney <david.daney@cavium.com>
Patchwork: http://patchwork.linux-mips.org/patch/4994/
Acked-by: John Crispin <blogic@openwrt.org>

arch/mips/include/asm/cpu-features.h

@@ -113,6 +113,9 @@
 #ifndef cpu_has_pindexed_dcache
 #define cpu_has_pindexed_dcache (cpu_data[0].dcache.flags & MIPS_CACHE_PINDEX)
 #endif
+#ifndef cpu_has_local_ebase
+#define cpu_has_local_ebase	1
+#endif
 
 /*
  * I-Cache snoops remote store.	 This only matters on SMP.  Some multiprocessors

arch/mips/include/asm/mach-loongson/cpu-feature-overrides.h

@@ -57,5 +57,6 @@
 #define cpu_has_vint		0
 #define cpu_has_vtag_icache	0
 #define cpu_has_watch		1
+#define cpu_has_local_ebase	0
 
 #endif /* __ASM_MACH_LOONGSON_CPU_FEATURE_OVERRIDES_H */

arch/mips/mm/page.c

@@ -247,6 +247,11 @@ void __cpuinit build_clear_page(void)
 	struct uasm_label *l = labels;
 	struct uasm_reloc *r = relocs;
 	int i;
+	static atomic_t run_once = ATOMIC_INIT(0);
+
+	if (atomic_xchg(&run_once, 1)) {
+		return;
+	}
 
 	memset(labels, 0, sizeof(labels));
 	memset(relocs, 0, sizeof(relocs));
@@ -389,6 +394,11 @@ void __cpuinit build_copy_page(void)
 	struct uasm_label *l = labels;
 	struct uasm_reloc *r = relocs;
 	int i;
+	static atomic_t run_once = ATOMIC_INIT(0);
+
+	if (atomic_xchg(&run_once, 1)) {
+		return;
+	}
 
 	memset(labels, 0, sizeof(labels));
 	memset(relocs, 0, sizeof(relocs));

arch/mips/mm/tlbex.c

@@ -2162,8 +2162,11 @@ void __cpuinit build_tlb_refill_handler(void)
 	case CPU_TX3922:
 	case CPU_TX3927:
 #ifndef CONFIG_MIPS_PGD_C0_CONTEXT
-		build_r3000_tlb_refill_handler();
+		if (cpu_has_local_ebase)
+			build_r3000_tlb_refill_handler();
 		if (!run_once) {
+			if (!cpu_has_local_ebase)
+				build_r3000_tlb_refill_handler();
 			build_r3000_tlb_load_handler();
 			build_r3000_tlb_store_handler();
 			build_r3000_tlb_modify_handler();
@@ -2192,9 +2195,12 @@ void __cpuinit build_tlb_refill_handler(void)
 			build_r4000_tlb_load_handler();
 			build_r4000_tlb_store_handler();
 			build_r4000_tlb_modify_handler();
+			if (!cpu_has_local_ebase)
+				build_r4000_tlb_refill_handler();
 			run_once++;
 		}
-		build_r4000_tlb_refill_handler();
+		if (cpu_has_local_ebase)
+			build_r4000_tlb_refill_handler();
 	}
 }