[SPARC64]: Initial LDOM cpu hotplug support.

Only adding cpus is supports at the moment, removal
will come next.

When new cpus are configured, the machine description is
updated.  When we get the configure request we pass in a
cpu mask of to-be-added cpus to the mdesc CPU node parser
so it only fetches information for those cpus.  That code
also proceeds to update the SMT/multi-core scheduling bitmaps.

cpu_up() does all the work and we return the status back
over the DS channel.

CPUs via dr-cpu need to be booted straight out of the
hypervisor, and this requires:

1) A new trampoline mechanism.  CPUs are booted straight
   out of the hypervisor with MMU disabled and running in
   physical addresses with no mappings installed in the TLB.

   The new hvtramp.S code sets up the critical cpu state,
   installs the locked TLB mappings for the kernel, and
   turns the MMU on.  It then proceeds to follow the logic
   of the existing trampoline.S SMP cpu bringup code.

2) All calls into OBP have to be disallowed when domaining
   is enabled.  Since cpus boot straight into the kernel from
   the hypervisor, OBP has no state about that cpu and therefore
   cannot handle being invoked on that cpu.

   Luckily it's only a handful of interfaces which can be called
   after the OBP device tree is obtained.  For example, rebooting,
   halting, powering-off, and setting options node variables.

CPU removal support will require some infrastructure changes
here.  Namely we'll have to process the requests via a true
kernel thread instead of in a workqueue.  workqueues run on
a per-cpu thread, but when unconfiguring we might need to
force the thread to execute on another cpu if the current cpu
is the one being removed.  Removal of a cpu also causes the kernel
to destroy that cpu's workqueue running thread.

Another issue on removal is that we may have interrupts still
pointing to the cpu-to-be-removed.  So new code will be needed
to walk the active INO list and retarget those cpus as-needed.

Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 37 insertions, 18 deletions

diff --git a/arch/sparc64/kernel/smp.c b/arch/sparc64/kernel/smp.c
index 40e40f968d61..315eef0869bd 100644
--- a/arch/sparc64/kernel/smp.c
+++ b/arch/sparc64/kernel/smp.c
@@ -41,6 +41,7 @@
 #include <asm/sections.h>
 #include <asm/prom.h>
 #include <asm/mdesc.h>
+#include <asm/ldc.h>
 
 extern void calibrate_delay(void);
 
@@ -49,12 +50,18 @@ int sparc64_multi_core __read_mostly;
 /* Please don't make this stuff initdata!!!  --DaveM */
 unsigned char boot_cpu_id;
 
+cpumask_t cpu_possible_map __read_mostly = CPU_MASK_NONE;
 cpumask_t cpu_online_map __read_mostly = CPU_MASK_NONE;
-cpumask_t phys_cpu_present_map __read_mostly = CPU_MASK_NONE;
 cpumask_t cpu_sibling_map[NR_CPUS] __read_mostly =
         { [0 ... NR_CPUS-1] = CPU_MASK_NONE };
 cpumask_t cpu_core_map[NR_CPUS] __read_mostly =
         { [0 ... NR_CPUS-1] = CPU_MASK_NONE };
+
+EXPORT_SYMBOL(cpu_possible_map);
+EXPORT_SYMBOL(cpu_online_map);
+EXPORT_SYMBOL(cpu_sibling_map);
+EXPORT_SYMBOL(cpu_core_map);
+
 static cpumask_t smp_commenced_mask;
 static cpumask_t cpu_callout_map;
 
@@ -84,9 +91,10 @@ extern void setup_sparc64_timer(void);
 
 static volatile unsigned long callin_flag = 0;
 
-void __init smp_callin(void)
+void __devinit smp_callin(void)
 {
         int cpuid = hard_smp_processor_id();
+        struct trap_per_cpu *tb = &trap_block[cpuid];;
 
         __local_per_cpu_offset = __per_cpu_offset(cpuid);
 
@@ -117,6 +125,11 @@ void __init smp_callin(void)
         atomic_inc(&init_mm.mm_count);
         current->active_mm = &init_mm;
 
+        if (tb->hdesc) {
+                kfree(tb->hdesc);
+                tb->hdesc = NULL;
+        }
+
         while (!cpu_isset(cpuid, smp_commenced_mask))
                 rmb();
 
@@ -296,14 +309,20 @@ static int __devinit smp_boot_one_cpu(unsigned int cpu)
                 /* Alloc the mondo queues, cpu will load them.  */
                 sun4v_init_mondo_queues(0, cpu, 1, 0);
 
-                prom_startcpu_cpuid(cpu, entry, cookie);
+#ifdef CONFIG_SUN_LDOMS
+                if (ldom_domaining_enabled)
+                        ldom_startcpu_cpuid(cpu,
+                                            (unsigned long) cpu_new_thread);
+                else
+#endif
+                        prom_startcpu_cpuid(cpu, entry, cookie);
         } else {
                 struct device_node *dp = of_find_node_by_cpuid(cpu);
 
                 prom_startcpu(dp->node, entry, cookie);
         }
 
-        for (timeout = 0; timeout < 5000000; timeout++) {
+        for (timeout = 0; timeout < 50000; timeout++) {
                 if (callin_flag)
                         break;
                 udelay(100);
@@ -1163,22 +1182,8 @@ int setup_profiling_timer(unsigned int multiplier)
         return -EINVAL;
 }
 
-/* Constrain the number of cpus to max_cpus.  */
 void __init smp_prepare_cpus(unsigned int max_cpus)
 {
-        int i;
-
-        if (num_possible_cpus() > max_cpus) {
-                for_each_possible_cpu(i) {
-                        if (i != boot_cpu_id) {
-                                cpu_clear(i, phys_cpu_present_map);
-                                cpu_clear(i, cpu_present_map);
-                                if (num_possible_cpus() <= max_cpus)
-                                        break;
-                        }
-                }
-        }
-
         cpu_data(boot_cpu_id).udelay_val = loops_per_jiffy;
 }
 
@@ -1242,6 +1247,20 @@ int __cpuinit __cpu_up(unsigned int cpu)
         return ret;
 }
 
+#ifdef CONFIG_HOTPLUG_CPU
+int __cpu_disable(void)
+{
+        printk(KERN_ERR "SMP: __cpu_disable() on cpu %d\n",
+               smp_processor_id());
+        return -ENODEV;
+}
+
+void __cpu_die(unsigned int cpu)
+{
+        printk(KERN_ERR "SMP: __cpu_die(%u)\n", cpu);
+}
+#endif
+
 void __init smp_cpus_done(unsigned int max_cpus)
 {
         unsigned long bogosum = 0;