Commit the support for removing cpumask_t and replacing it directly with

cpuset_t objects.
That is going to offer the underlying support for a simple bump of
MAXCPU and then support for number of cpus > 32 (as it is today).

Right now, cpumask_t is an int, 32 bits on all our supported architecture.
cpumask_t on the other side is implemented as an array of longs, and
easilly extendible by definition.

The architectures touched by this commit are the following:
- amd64
- i386
- pc98
- arm
- ia64
- XEN

while the others are still missing.
Userland is believed to be fully converted with the changes contained
here.

Some technical notes:
- This commit may be considered an ABI nop for all the architectures
  different from amd64 and ia64 (and sparc64 in the future)
- per-cpu members, which are now converted to cpuset_t, needs to be
  accessed avoiding migration, because the size of cpuset_t should be
  considered unknown
- size of cpuset_t objects is different from kernel and userland (this is
  primirally done in order to leave some more space in userland to cope
  with KBI extensions). If you need to access kernel cpuset_t from the
  userland please refer to example in this patch on how to do that
  correctly (kgdb may be a good source, for example).
- Support for other architectures is going to be added soon
- Only MAXCPU for amd64 is bumped now

The patch has been tested by sbruno and Nicholas Esborn on opteron
4 x 12 pack CPUs. More testing on big SMP is expected to came soon.
pluknet tested the patch with his 8-ways on both amd64 and i386.

Tested by:	pluknet, sbruno, gianni, Nicholas Esborn
Reviewed by:	jeff, jhb, sbruno

3 files changed, 14 insertions, 9 deletions

diff --git a/sys/cddl/dev/cyclic/i386/cyclic_machdep.c b/sys/cddl/dev/cyclic/i386/cyclic_machdep.c
index 1c18fc1..dc6cb71 100644
--- a/sys/cddl/dev/cyclic/i386/cyclic_machdep.c
+++ b/sys/cddl/dev/cyclic/i386/cyclic_machdep.c
@@ -121,7 +121,9 @@ static void reprogram(cyb_arg_t arg, hrtime_t exp)
 
 static void xcall(cyb_arg_t arg, cpu_t *c, cyc_func_t func, void *param)
 {
+	cpuset_t cpus;
 
-	smp_rendezvous_cpus((cpumask_t) (1 << c->cpuid),
+	CPU_SETOF(c->cpuid, &cpus);
+	smp_rendezvous_cpus(cpus,
 	    smp_no_rendevous_barrier, func, smp_no_rendevous_barrier, param);
 }
diff --git a/sys/cddl/dev/dtrace/amd64/dtrace_subr.c b/sys/cddl/dev/dtrace/amd64/dtrace_subr.c
index 102ea04..bc4b8b6 100644
--- a/sys/cddl/dev/dtrace/amd64/dtrace_subr.c
+++ b/sys/cddl/dev/dtrace/amd64/dtrace_subr.c
@@ -113,12 +113,12 @@ dtrace_toxic_ranges(void (*func)(uintptr_t base, uintptr_t limit))
 void
 dtrace_xcall(processorid_t cpu, dtrace_xcall_t func, void *arg)
 {
-	cpumask_t cpus;
+	cpuset_t cpus;
 
 	if (cpu == DTRACE_CPUALL)
 		cpus = all_cpus;
 	else
-		cpus = (cpumask_t)1 << cpu;
+		CPU_SETOF(cpu, &cpus);
 
 	smp_rendezvous_cpus(cpus, smp_no_rendevous_barrier, func,
 	    smp_no_rendevous_barrier, arg);
@@ -394,7 +394,7 @@ dtrace_gethrtime_init(void *arg)
 {
 	struct pcpu *pc;
 	uint64_t tsc_f;
-	cpumask_t map;
+	cpuset_t map;
 	int i;
 
 	/*
@@ -432,7 +432,8 @@ dtrace_gethrtime_init(void *arg)
 			continue;
 
 		pc = pcpu_find(i);
-		map = PCPU_GET(cpumask) | pc->pc_cpumask;
+		map = PCPU_GET(cpumask);
+		CPU_OR(&map, &pc->pc_cpumask);
 
 		smp_rendezvous_cpus(map, dtrace_gethrtime_init_sync,
 		    dtrace_gethrtime_init_cpu,
diff --git a/sys/cddl/dev/dtrace/i386/dtrace_subr.c b/sys/cddl/dev/dtrace/i386/dtrace_subr.c
index 50793c4..7d460bc 100644
--- a/sys/cddl/dev/dtrace/i386/dtrace_subr.c
+++ b/sys/cddl/dev/dtrace/i386/dtrace_subr.c
@@ -30,6 +30,7 @@
 #include <sys/param.h>
 #include <sys/systm.h>
 #include <sys/types.h>
+#include <sys/cpuset.h>
 #include <sys/kernel.h>
 #include <sys/malloc.h>
 #include <sys/kmem.h>
@@ -113,12 +114,12 @@ dtrace_toxic_ranges(void (*func)(uintptr_t base, uintptr_t limit))
 void
 dtrace_xcall(processorid_t cpu, dtrace_xcall_t func, void *arg)
 {
-	cpumask_t cpus;
+	cpuset_t cpus;
 
 	if (cpu == DTRACE_CPUALL)
 		cpus = all_cpus;
 	else
-		cpus = (cpumask_t)1 << cpu;
+		CPU_SETOF(cpu, &cpus);
 
 	smp_rendezvous_cpus(cpus, smp_no_rendevous_barrier, func,
 	    smp_no_rendevous_barrier, arg);
@@ -392,9 +393,9 @@ dtrace_gethrtime_init_cpu(void *arg)
 static void
 dtrace_gethrtime_init(void *arg)
 {
+	cpuset_t map;
 	struct pcpu *pc;
 	uint64_t tsc_f;
-	cpumask_t map;
 	int i;
 
 	/*
@@ -432,7 +433,8 @@ dtrace_gethrtime_init(void *arg)
 			continue;
 
 		pc = pcpu_find(i);
-		map = PCPU_GET(cpumask) | pc->pc_cpumask;
+		map = PCPU_GET(cpumask);
+		CPU_OR(&map, &pc->pc_cpumask);
 
 		smp_rendezvous_cpus(map, dtrace_gethrtime_init_sync,
 		    dtrace_gethrtime_init_cpu,