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, 10 insertions, 9 deletions

diff --git a/sys/ia64/ia64/mp_machdep.c b/sys/ia64/ia64/mp_machdep.c
index 5804f8c..0153785 100644
--- a/sys/ia64/ia64/mp_machdep.c
+++ b/sys/ia64/ia64/mp_machdep.c
@@ -139,18 +139,18 @@ ia64_ih_rndzvs(struct thread *td, u_int xiv, struct trapframe *tf)
 static u_int
 ia64_ih_stop(struct thread *td, u_int xiv, struct trapframe *tf)
 {
-	cpumask_t mybit;
+	cpuset_t mybit;
 
 	PCPU_INC(md.stats.pcs_nstops);
 	mybit = PCPU_GET(cpumask);
 
 	savectx(PCPU_PTR(md.pcb));
 
-	atomic_set_int(&stopped_cpus, mybit);
-	while ((started_cpus & mybit) == 0)
+	CPU_OR_ATOMIC(&stopped_cpus, &mybit);
+	while (!CPU_OVERLAP(&started_cpus, &mybit))
 		cpu_spinwait();
-	atomic_clear_int(&started_cpus, mybit);
-	atomic_clear_int(&stopped_cpus, mybit);
+	CPU_NAND_ATOMIC(&started_cpus, &mybit);
+	CPU_NAND_ATOMIC(&stopped_cpus, &mybit);
 	return (0);
 }
 
@@ -458,12 +458,12 @@ cpu_mp_unleash(void *dummy)
  * send an IPI to a set of cpus.
  */
 void
-ipi_selected(cpumask_t cpus, int ipi)
+ipi_selected(cpuset_t cpus, int ipi)
 {
 	struct pcpu *pc;
 
 	SLIST_FOREACH(pc, &cpuhead, pc_allcpu) {
-		if (cpus & pc->pc_cpumask)
+		if (CPU_OVERLAP(&cpus, &pc->pc_cpumask))
 			ipi_send(pc, ipi);
 	}
 }
diff --git a/sys/ia64/include/_types.h b/sys/ia64/include/_types.h
index 8fc1be2..0c2f5cc 100644
--- a/sys/ia64/include/_types.h
+++ b/sys/ia64/include/_types.h
@@ -59,7 +59,6 @@ typedef	unsigned long		__uint64_t;
  * Standard type definitions.
  */
 typedef	__int32_t	__clock_t;		/* clock()... */
-typedef	unsigned int	__cpumask_t;
 typedef	__int64_t	__critical_t;
 typedef	double		__double_t;
 typedef	float		__float_t;
diff --git a/sys/ia64/include/smp.h b/sys/ia64/include/smp.h
index 26557a7..d2aff76 100644
--- a/sys/ia64/include/smp.h
+++ b/sys/ia64/include/smp.h
@@ -14,6 +14,8 @@
 
 #ifndef LOCORE
 
+#include <sys/_cpuset.h>
+
 struct pcpu;
 
 struct ia64_ap_state {
@@ -44,7 +46,7 @@ extern int ia64_ipi_wakeup;
 
 void	ipi_all_but_self(int ipi);
 void	ipi_cpu(int cpu, u_int ipi);
-void	ipi_selected(cpumask_t cpus, int ipi);
+void	ipi_selected(cpuset_t cpus, int ipi);
 void	ipi_send(struct pcpu *, int ipi);
 
 #endif /* !LOCORE */