[IA64] Ensure cpu0 can access per-cpu variables in early boot code

ia64 handles per-cpu variables a litle differently from other architectures
in that it maps the physical memory allocated for each cpu at a constant
virtual address (0xffffffffffff0000). This mapping is not enabled until
the architecture specific cpu_init() function is run, which causes problems
since some generic code is run before this point. In particular when
CONFIG_PRINTK_TIME is enabled, the boot cpu will trap on the access to
per-cpu memory at the first printk() call so the boot will fail without
the kernel printing anything to the console.

Fix this by allocating percpu memory for cpu0 in the kernel data section
and doing all initialization to enable percpu access in head.S before
calling any generic code.

Other cpus must take care not to access per-cpu variables too early, but
their code path from start_secondary() to cpu_init() is all in arch/ia64

Signed-off-by: Tony Luck <tony.luck@intel.com>

2 files changed, 13 insertions, 3 deletions

diff --git a/arch/ia64/mm/contig.c b/arch/ia64/mm/contig.c
index 798bf9835a51..e566ff43884a 100644
--- a/arch/ia64/mm/contig.c
+++ b/arch/ia64/mm/contig.c
@@ -163,8 +163,14 @@ per_cpu_init (void)
          * get_zeroed_page().
          */
         if (first_time) {
+                void *cpu0_data = __phys_per_cpu_start - PERCPU_PAGE_SIZE;
+
                 first_time=0;
-                for (cpu = 0; cpu < NR_CPUS; cpu++) {
+
+                __per_cpu_offset[0] = (char *) cpu0_data - __per_cpu_start;
+                per_cpu(local_per_cpu_offset, 0) = __per_cpu_offset[0];
+
+                for (cpu = 1; cpu < NR_CPUS; cpu++) {
                         memcpy(cpu_data, __phys_per_cpu_start, __per_cpu_end - __per_cpu_start);
                         __per_cpu_offset[cpu] = (char *) cpu_data - __per_cpu_start;
                         cpu_data += PERCPU_PAGE_SIZE;
@@ -177,7 +183,7 @@ per_cpu_init (void)
 static inline void
 alloc_per_cpu_data(void)
 {
-        cpu_data = __alloc_bootmem(PERCPU_PAGE_SIZE * NR_CPUS,
+        cpu_data = __alloc_bootmem(PERCPU_PAGE_SIZE * NR_CPUS-1,
                                    PERCPU_PAGE_SIZE, __pa(MAX_DMA_ADDRESS));
 }
 #else
diff --git a/arch/ia64/mm/discontig.c b/arch/ia64/mm/discontig.c
index d83125e1ed27..78026aabaa7f 100644
--- a/arch/ia64/mm/discontig.c
+++ b/arch/ia64/mm/discontig.c
@@ -143,7 +143,11 @@ static void *per_cpu_node_setup(void *cpu_data, int node)
         int cpu;
 
         for_each_possible_early_cpu(cpu) {
-                if (node == node_cpuid[cpu].nid) {
+                if (cpu == 0) {
+                        void *cpu0_data = __phys_per_cpu_start - PERCPU_PAGE_SIZE;
+                        __per_cpu_offset[cpu] = (char*)cpu0_data -
+                                __per_cpu_start;
+                } else if (node == node_cpuid[cpu].nid) {
                         memcpy(__va(cpu_data), __phys_per_cpu_start,
                                __per_cpu_end - __per_cpu_start);
                         __per_cpu_offset[cpu] = (char*)__va(cpu_data) -