5 files changed, 44 insertions, 13 deletions

diff --git a/arch/ia64/kernel/head.S b/arch/ia64/kernel/head.S
index 41c712917ff7..8bdea8eb62e3 100644
--- a/arch/ia64/kernel/head.S
+++ b/arch/ia64/kernel/head.S
@@ -359,7 +359,31 @@ start_ap:
         mov ar.rsc=0            // place RSE in enforced lazy mode
         ;;
         loadrs                  // clear the dirty partition
-        mov IA64_KR(PER_CPU_DATA)=r0    // clear physical per-CPU base
+        movl r19=__phys_per_cpu_start
+        mov r18=PERCPU_PAGE_SIZE
+        ;;
+#ifndef CONFIG_SMP
+        add r19=r19,r18
+        ;;
+#else
+(isAP)  br.few 2f
+        mov r20=r19
+        sub r19=r19,r18
+        ;;
+        shr.u r18=r18,3
+1:
+        ld8 r21=[r20],8;;
+        st8[r19]=r21,8
+        adds r18=-1,r18;;
+        cmp4.lt p7,p6=0,r18
+(p7)    br.cond.dptk.few 1b
+2:
+#endif
+        tpa r19=r19
+        ;;
+        .pred.rel.mutex isBP,isAP
+(isBP)  mov IA64_KR(PER_CPU_DATA)=r19   // per-CPU base for cpu0
+(isAP)  mov IA64_KR(PER_CPU_DATA)=r0    // clear physical per-CPU base
         ;;
         mov ar.bspstore=r2      // establish the new RSE stack
         ;;
diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c
index 593279f33e96..c27d5b2c182b 100644
--- a/arch/ia64/kernel/setup.c
+++ b/arch/ia64/kernel/setup.c
@@ -927,17 +927,19 @@ cpu_init (void)
         if (smp_processor_id() == 0) {
                 cpu_set(0, per_cpu(cpu_sibling_map, 0));
                 cpu_set(0, cpu_core_map[0]);
+        } else {
+                /*
+                 * 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
+                 * and the alt-dtlb-miss handler can set per-cpu mapping into
+                 * the TLB when needed. head.S already did this for cpu0.
+                 */
+                ia64_set_kr(IA64_KR_PER_CPU_DATA,
+                            ia64_tpa(cpu_data) - (long) __per_cpu_start);
         }
 #endif
 
-        /*
-         * 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();
 
         /*
diff --git a/arch/ia64/kernel/smp.c b/arch/ia64/kernel/smp.c
index 3676468612b6..da8f020d82c1 100644
--- a/arch/ia64/kernel/smp.c
+++ b/arch/ia64/kernel/smp.c
@@ -58,7 +58,7 @@ static struct local_tlb_flush_counts {
         unsigned int count;
 } __attribute__((__aligned__(32))) local_tlb_flush_counts[NR_CPUS];
 
-static DEFINE_PER_CPU(unsigned int, shadow_flush_counts[NR_CPUS]) ____cacheline_aligned;
+static DEFINE_PER_CPU(unsigned short, shadow_flush_counts[NR_CPUS]) ____cacheline_aligned;
 
 #define IPI_CALL_FUNC           0
 #define IPI_CPU_STOP            1
@@ -254,7 +254,7 @@ smp_local_flush_tlb(void)
 void
 smp_flush_tlb_cpumask(cpumask_t xcpumask)
 {
-        unsigned int *counts = __ia64_per_cpu_var(shadow_flush_counts);
+        unsigned short *counts = __ia64_per_cpu_var(shadow_flush_counts);
         cpumask_t cpumask = xcpumask;
         int mycpu, cpu, flush_mycpu = 0;
 
@@ -262,7 +262,7 @@ smp_flush_tlb_cpumask(cpumask_t xcpumask)
         mycpu = smp_processor_id();
 
         for_each_cpu_mask(cpu, cpumask)
-                counts[cpu] = local_tlb_flush_counts[cpu].count;
+                counts[cpu] = local_tlb_flush_counts[cpu].count & 0xffff;
 
         mb();
         for_each_cpu_mask(cpu, cpumask) {
@@ -276,7 +276,7 @@ smp_flush_tlb_cpumask(cpumask_t xcpumask)
                 smp_local_flush_tlb();
 
         for_each_cpu_mask(cpu, cpumask)
-                while(counts[cpu] == local_tlb_flush_counts[cpu].count)
+                while(counts[cpu] == (local_tlb_flush_counts[cpu].count & 0xffff))
                         udelay(FLUSH_DELAY);
 
         preempt_enable();
diff --git a/arch/ia64/kernel/smpboot.c b/arch/ia64/kernel/smpboot.c
index 03f1a9908afc..b39853a292d5 100644
--- a/arch/ia64/kernel/smpboot.c
+++ b/arch/ia64/kernel/smpboot.c
@@ -467,7 +467,9 @@ start_secondary (void *unused)
 {
         /* Early console may use I/O ports */
         ia64_set_kr(IA64_KR_IO_BASE, __pa(ia64_iobase));
+#ifndef CONFIG_PRINTK_TIME
         Dprintk("start_secondary: starting CPU 0x%x\n", hard_smp_processor_id());
+#endif
         efi_map_pal_code();
         cpu_init();
         preempt_disable();
diff --git a/arch/ia64/kernel/vmlinux.lds.S b/arch/ia64/kernel/vmlinux.lds.S
index 5a77206c2492..de71da811cd6 100644
--- a/arch/ia64/kernel/vmlinux.lds.S
+++ b/arch/ia64/kernel/vmlinux.lds.S
@@ -215,6 +215,9 @@ SECTIONS
   /* Per-cpu data: */
   percpu : { } :percpu
   . = ALIGN(PERCPU_PAGE_SIZE);
+#ifdef  CONFIG_SMP
+  . = . + PERCPU_PAGE_SIZE;     /* cpu0 per-cpu space */
+#endif
   __phys_per_cpu_start = .;
   .data.percpu PERCPU_ADDR : AT(__phys_per_cpu_start - LOAD_OFFSET)
         {