[IA64] Move allocation of per-CPU MCA data out of per_cpu_init()

This patch moves the per-CPU MCA data allocation out of per_cpu_init()
so the code can be shared for contig and discontig memory
architectures.  Also, it means we can revert back to the old way
of doing per_cpu_init() on UP.

Also cleanup initialization of ar.k3 in setup.c.  Need to use
ia64_tpa() rather than __pa() because address will be in region 5
on UP build.
Signed-off-by: David Mosberger-Tang <davidm@hpl.hp.com>
Signed-off-by: Tony Luck <tony.luck@intel.com>

arch/ia64/kernel/mca.c

@@ -1209,6 +1209,18 @@ ia64_mca_cpu_init(void *cpu_data)
 {
 	void *pal_vaddr;
 
+	if (smp_processor_id() == 0) {
+		void *mca_data;
+		int cpu;
+
+		mca_data = alloc_bootmem(sizeof(struct ia64_mca_cpu)
+					 * NR_CPUS);
+		for (cpu = 0; cpu < NR_CPUS; cpu++) {
+			__per_cpu_mca[cpu] = __pa(mca_data);
+			mca_data += sizeof(struct ia64_mca_cpu);
+		}
+	}
+
         /*
          * The MCA info structure was allocated earlier and its
          * physical address saved in __per_cpu_mca[cpu].  Copy that

arch/ia64/kernel/setup.c

@@ -609,7 +609,13 @@ cpu_init (void)
 
 	cpu_data = per_cpu_init();
 
-	ia64_set_kr(IA64_KR_PER_CPU_DATA, __pa(cpu_data - (void *) __per_cpu_start));
+	/*
+	 * We set ar.k3 so that assembly code in MCA handler can compute
+	 * physical addresses of per cpu variables with a simple:
+	 *   phys = ar.k3 + &per_cpu_var
+	 */
+	ia64_set_kr(IA64_KR_PER_CPU_DATA,
+		    ia64_tpa(cpu_data) - (long) __per_cpu_start);
 
 	get_max_cacheline_size();
 

arch/ia64/mm/contig.c

@@ -169,6 +169,7 @@ find_memory (void)
 	find_initrd();
 }
 
+#ifdef CONFIG_SMP
 /**
  * per_cpu_init - setup per-cpu variables
  *
@@ -177,18 +178,15 @@ find_memory (void)
 void *
 per_cpu_init (void)
 {
-	void *mca_data, *my_data;
+	void *cpu_data;
 	int cpu;
 
-#ifdef CONFIG_SMP
 	/*
 	 * get_free_pages() cannot be used before cpu_init() done.  BSP
 	 * allocates "NR_CPUS" pages for all CPUs to avoid that AP calls
 	 * get_zeroed_page().
 	 */
 	if (smp_processor_id() == 0) {
-		void *cpu_data;
-
 		cpu_data = __alloc_bootmem(PERCPU_PAGE_SIZE * NR_CPUS,
 					   PERCPU_PAGE_SIZE, __pa(MAX_DMA_ADDRESS));
 		for (cpu = 0; cpu < NR_CPUS; cpu++) {
@@ -198,20 +196,9 @@ per_cpu_init (void)
 			per_cpu(local_per_cpu_offset, cpu) = __per_cpu_offset[cpu];
 		}
 	}
-	my_data = __per_cpu_start + __per_cpu_offset[smp_processor_id()];
-#else
-	my_data = (void *) __phys_per_cpu_start;
-#endif
-
-	if (smp_processor_id() == 0) {
-		mca_data = alloc_bootmem(sizeof (struct ia64_mca_cpu) * NR_CPUS);
-		for (cpu = 0; cpu < NR_CPUS; cpu++) {
-			__per_cpu_mca[cpu] = __pa(mca_data);
-			mca_data += sizeof (struct ia64_mca_cpu);
-		}
-	}
-	return my_data;
+	return __per_cpu_start + __per_cpu_offset[smp_processor_id()];
 }
+#endif /* CONFIG_SMP */
 
 static int
 count_pages (u64 start, u64 end, void *arg)

arch/ia64/mm/discontig.c

@@ -26,7 +26,6 @@
 #include <asm/meminit.h>
 #include <asm/numa.h>
 #include <asm/sections.h>
-#include <asm/mca.h>
 
 /*
  * Track per-node information needed to setup the boot memory allocator, the
@@ -294,9 +293,6 @@ static int early_nr_cpus_node(int node)
  *   |------------------------|
  *   |  local ia64_node_data  |
  *   |------------------------|
- *   |    MCA/INIT data *     |
- *   |    cpus_on_this_node   |
- *   |------------------------|
  *   |          ???           |
  *   |________________________|
  *
@@ -310,7 +306,7 @@ static int __init find_pernode_space(unsigned long start, unsigned long len,
 {
 	unsigned long epfn, cpu, cpus, phys_cpus;
 	unsigned long pernodesize = 0, pernode, pages, mapsize;
-	void *cpu_data, *mca_data_phys;
+	void *cpu_data;
 	struct bootmem_data *bdp = &mem_data[node].bootmem_data;
 
 	epfn = (start + len) >> PAGE_SHIFT;
@@ -339,7 +335,6 @@ static int __init find_pernode_space(unsigned long start, unsigned long len,
 	pernodesize += node * L1_CACHE_BYTES;
 	pernodesize += L1_CACHE_ALIGN(sizeof(pg_data_t));
 	pernodesize += L1_CACHE_ALIGN(sizeof(struct ia64_node_data));
-	pernodesize += L1_CACHE_ALIGN(sizeof(struct ia64_mca_cpu)) * phys_cpus;
 	pernodesize = PAGE_ALIGN(pernodesize);
 	pernode = NODEDATA_ALIGN(start, node);
 
@@ -362,9 +357,6 @@ static int __init find_pernode_space(unsigned long start, unsigned long len,
 		mem_data[node].pgdat->bdata = bdp;
 		pernode += L1_CACHE_ALIGN(sizeof(pg_data_t));
 
-		mca_data_phys = (void *)pernode;
-		pernode += L1_CACHE_ALIGN(sizeof(struct ia64_mca_cpu)) * phys_cpus;
-
 		/*
 		 * Copy the static per-cpu data into the region we
 		 * just set aside and then setup __per_cpu_offset
@@ -374,18 +366,6 @@ static int __init find_pernode_space(unsigned long start, unsigned long len,
 			if (node == node_cpuid[cpu].nid) {
 				memcpy(__va(cpu_data), __phys_per_cpu_start,
 				       __per_cpu_end - __per_cpu_start);
-				if ((cpu == 0) || (node_cpuid[cpu].phys_id > 0)) {
-					/* 
-					 * The memory for the cpuinfo structure is allocated
-					 * here, but the data in the structure is initialized
-					 * later.  Save the physical address of the MCA save
-					 * area in __per_cpu_mca[cpu].  When the cpuinfo struct 
-					 * is initialized, the value in __per_cpu_mca[cpu]
-					 * will be put in the cpuinfo structure.
-					 */
-					__per_cpu_mca[cpu] = __pa(mca_data_phys);
-					mca_data_phys += L1_CACHE_ALIGN(sizeof(struct ia64_mca_cpu));
-				}
 				__per_cpu_offset[cpu] = (char*)__va(cpu_data) -
 					__per_cpu_start;
 				cpu_data += PERCPU_PAGE_SIZE;

include/asm-ia64/percpu.h

@@ -46,11 +46,13 @@ DECLARE_PER_CPU(unsigned long, local_per_cpu_offset);
 
 extern void percpu_modcopy(void *pcpudst, const void *src, unsigned long size);
 extern void setup_per_cpu_areas (void);
+extern void *per_cpu_init(void);
 
 #else /* ! SMP */
 
 #define per_cpu(var, cpu)			(*((void)cpu, &per_cpu__##var))
 #define __get_cpu_var(var)			per_cpu__##var
+#define per_cpu_init()				(__phys_per_cpu_start)
 
 #endif	/* SMP */
 
@@ -65,8 +67,6 @@ extern void setup_per_cpu_areas (void);
  */
 #define __ia64_per_cpu_var(var)	(per_cpu__##var)
 
-extern void *per_cpu_init(void);
-
 #endif /* !__ASSEMBLY__ */
 
 #endif /* _ASM_IA64_PERCPU_H */