[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, 38 insertions, 15 deletions

diff --git a/arch/sparc64/kernel/mdesc.c b/arch/sparc64/kernel/mdesc.c
index 9e5088d563c..3f79940a293 100644
--- a/arch/sparc64/kernel/mdesc.c
+++ b/arch/sparc64/kernel/mdesc.c
@@ -434,6 +434,22 @@ static void __init report_platform_properties(void)
 	if (v)
 		printk("PLATFORM: max-cpus [%lu]\n", *v);
 
+#ifdef CONFIG_SMP
+	{
+		int max_cpu, i;
+
+		if (v) {
+			max_cpu = *v;
+			if (max_cpu > NR_CPUS)
+				max_cpu = NR_CPUS;
+		} else {
+			max_cpu = NR_CPUS;
+		}
+		for (i = 0; i < max_cpu; i++)
+			cpu_set(i, cpu_possible_map);
+	}
+#endif
+
 	mdesc_release(hp);
 }
 
@@ -451,9 +467,9 @@ static int inline find_in_proplist(const char *list, const char *match, int len)
 	return 0;
 }
 
-static void __init fill_in_one_cache(cpuinfo_sparc *c,
-				     struct mdesc_handle *hp,
-				     u64 mp)
+static void __devinit fill_in_one_cache(cpuinfo_sparc *c,
+					struct mdesc_handle *hp,
+					u64 mp)
 {
 	const u64 *level = mdesc_get_property(hp, mp, "level", NULL);
 	const u64 *size = mdesc_get_property(hp, mp, "size", NULL);
@@ -496,7 +512,8 @@ static void __init fill_in_one_cache(cpuinfo_sparc *c,
 	}
 }
 
-static void __init mark_core_ids(struct mdesc_handle *hp, u64 mp, int core_id)
+static void __devinit mark_core_ids(struct mdesc_handle *hp, u64 mp,
+				    int core_id)
 {
 	u64 a;
 
@@ -529,7 +546,7 @@ static void __init mark_core_ids(struct mdesc_handle *hp, u64 mp, int core_id)
 	}
 }
 
-static void __init set_core_ids(struct mdesc_handle *hp)
+static void __devinit set_core_ids(struct mdesc_handle *hp)
 {
 	int idx;
 	u64 mp;
@@ -554,7 +571,8 @@ static void __init set_core_ids(struct mdesc_handle *hp)
 	}
 }
 
-static void __init mark_proc_ids(struct mdesc_handle *hp, u64 mp, int proc_id)
+static void __devinit mark_proc_ids(struct mdesc_handle *hp, u64 mp,
+				    int proc_id)
 {
 	u64 a;
 
@@ -573,8 +591,8 @@ static void __init mark_proc_ids(struct mdesc_handle *hp, u64 mp, int proc_id)
 	}
 }
 
-static void __init __set_proc_ids(struct mdesc_handle *hp,
-				  const char *exec_unit_name)
+static void __devinit __set_proc_ids(struct mdesc_handle *hp,
+				     const char *exec_unit_name)
 {
 	int idx;
 	u64 mp;
@@ -595,13 +613,14 @@ static void __init __set_proc_ids(struct mdesc_handle *hp,
 	}
 }
 
-static void __init set_proc_ids(struct mdesc_handle *hp)
+static void __devinit set_proc_ids(struct mdesc_handle *hp)
 {
 	__set_proc_ids(hp, "exec_unit");
 	__set_proc_ids(hp, "exec-unit");
 }
 
-static void __init get_one_mondo_bits(const u64 *p, unsigned int *mask, unsigned char def)
+static void __devinit get_one_mondo_bits(const u64 *p, unsigned int *mask,
+					 unsigned char def)
 {
 	u64 val;
 
@@ -619,8 +638,8 @@ use_default:
 	*mask = ((1U << def) * 64U) - 1U;
 }
 
-static void __init get_mondo_data(struct mdesc_handle *hp, u64 mp,
-				  struct trap_per_cpu *tb)
+static void __devinit get_mondo_data(struct mdesc_handle *hp, u64 mp,
+				     struct trap_per_cpu *tb)
 {
 	const u64 *val;
 
@@ -637,7 +656,7 @@ static void __init get_mondo_data(struct mdesc_handle *hp, u64 mp,
 	get_one_mondo_bits(val, &tb->nonresum_qmask, 2);
 }
 
-static void __init mdesc_fill_in_cpu_data(void)
+void __devinit mdesc_fill_in_cpu_data(cpumask_t mask)
 {
 	struct mdesc_handle *hp = mdesc_grab();
 	u64 mp;
@@ -658,6 +677,8 @@ static void __init mdesc_fill_in_cpu_data(void)
 #ifdef CONFIG_SMP
 		if (cpuid >= NR_CPUS)
 			continue;
+		if (!cpu_isset(cpuid, mask))
+			continue;
 #else
 		/* On uniprocessor we only want the values for the
 		 * real physical cpu the kernel booted onto, however
@@ -696,7 +717,6 @@ static void __init mdesc_fill_in_cpu_data(void)
 
 #ifdef CONFIG_SMP
 		cpu_set(cpuid, cpu_present_map);
-		cpu_set(cpuid, phys_cpu_present_map);
 #endif
 
 		c->core_id = 0;
@@ -719,6 +739,7 @@ void __init sun4v_mdesc_init(void)
 {
 	struct mdesc_handle *hp;
 	unsigned long len, real_len, status;
+	cpumask_t mask;
 
 	(void) sun4v_mach_desc(0UL, 0UL, &len);
 
@@ -742,5 +763,7 @@ void __init sun4v_mdesc_init(void)
 	cur_mdesc = hp;
 
 	report_platform_properties();
-	mdesc_fill_in_cpu_data();
+
+	cpus_setall(mask);
+	mdesc_fill_in_cpu_data(mask);
 }