[SPARC64]: Eliminate NR_CPUS limitations.

Cheetah systems can have cpuids as large as 1023, although physical
systems don't have that many cpus.

Only three limitations existed in the kernel preventing arbitrary
NR_CPUS values:

1) dcache dirty cpu state stored in page->flags on
   D-cache aliasing platforms.  With some build time
   calculations and some build-time BUG checks on
   page->flags layout, this one was easily solved.

2) The cheetah XCALL delivery code could only handle
   a cpumask with up to 32 cpus set.  Some simple looping
   logic clears that up too.

3) thread_info->cpu was a u8, easily changed to a u16.

There are a few spots in the kernel that still put NR_CPUS
sized arrays on the kernel stack, but that's not a sparc64
specific problem.

Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/arch/sparc64/Kconfig b/arch/sparc64/Kconfig
index 831781c..bd00f89 100644
--- a/arch/sparc64/Kconfig
+++ b/arch/sparc64/Kconfig
@@ -147,10 +147,10 @@
 	  If you don't know what to do here, say N.
 
 config NR_CPUS
-	int "Maximum number of CPUs (2-64)"
-	range 2 64
+	int "Maximum number of CPUs (2-1024)"
+	range 2 1024
 	depends on SMP
-	default "32"
+	default "64"
 
 source "drivers/cpufreq/Kconfig"
 
diff --git a/arch/sparc64/kernel/head.S b/arch/sparc64/kernel/head.S
index baea10a..5c11529 100644
--- a/arch/sparc64/kernel/head.S
+++ b/arch/sparc64/kernel/head.S
@@ -523,7 +523,7 @@
 #else
 	mov	0, %o0
 #endif
-	stb	%o0, [%g6 + TI_CPU]
+	sth	%o0, [%g6 + TI_CPU]
 
 	/* Off we go.... */
 	call	start_kernel
diff --git a/arch/sparc64/kernel/smp.c b/arch/sparc64/kernel/smp.c
index f7fa873..c550bba 100644
--- a/arch/sparc64/kernel/smp.c
+++ b/arch/sparc64/kernel/smp.c
@@ -400,7 +400,7 @@
 static void cheetah_xcall_deliver(u64 data0, u64 data1, u64 data2, cpumask_t mask)
 {
 	u64 pstate, ver;
-	int nack_busy_id, is_jbus;
+	int nack_busy_id, is_jbus, need_more;
 
 	if (cpus_empty(mask))
 		return;
@@ -416,6 +416,7 @@
 	__asm__ __volatile__("rdpr %%pstate, %0" : "=r" (pstate));
 
 retry:
+	need_more = 0;
 	__asm__ __volatile__("wrpr %0, %1, %%pstate\n\t"
 			     : : "r" (pstate), "i" (PSTATE_IE));
 
@@ -444,6 +445,10 @@
 				: /* no outputs */
 				: "r" (target), "i" (ASI_INTR_W));
 			nack_busy_id++;
+			if (nack_busy_id == 32) {
+				need_more = 1;
+				break;
+			}
 		}
 	}
 
@@ -460,6 +465,16 @@
 			if (dispatch_stat == 0UL) {
 				__asm__ __volatile__("wrpr %0, 0x0, %%pstate"
 						     : : "r" (pstate));
+				if (unlikely(need_more)) {
+					int i, cnt = 0;
+					for_each_cpu_mask(i, mask) {
+						cpu_clear(i, mask);
+						cnt++;
+						if (cnt == 32)
+							break;
+					}
+					goto retry;
+				}
 				return;
 			}
 			if (!--stuck)
@@ -497,6 +512,8 @@
 				if ((dispatch_stat & check_mask) == 0)
 					cpu_clear(i, mask);
 				this_busy_nack += 2;
+				if (this_busy_nack == 64)
+					break;
 			}
 
 			goto retry;
diff --git a/arch/sparc64/mm/init.c b/arch/sparc64/mm/init.c
index 9776982..087cbf0 100644
--- a/arch/sparc64/mm/init.c
+++ b/arch/sparc64/mm/init.c
@@ -191,12 +191,9 @@
 }
 
 #define PG_dcache_dirty		PG_arch_1
-#define PG_dcache_cpu_shift	24UL
-#define PG_dcache_cpu_mask	(256UL - 1UL)
-
-#if NR_CPUS > 256
-#error D-cache dirty tracking and thread_info->cpu need fixing for > 256 cpus
-#endif
+#define PG_dcache_cpu_shift	32UL
+#define PG_dcache_cpu_mask	\
+	((1UL<<ilog2(roundup_pow_of_two(NR_CPUS)))-1UL)
 
 #define dcache_dirty_cpu(page) \
 	(((page)->flags >> PG_dcache_cpu_shift) & PG_dcache_cpu_mask)
@@ -1349,6 +1346,19 @@
 	unsigned long end_pfn, pages_avail, shift, phys_base;
 	unsigned long real_end, i;
 
+	/* These build time checkes make sure that the dcache_dirty_cpu()
+	 * page->flags usage will work.
+	 *
+	 * When a page gets marked as dcache-dirty, we store the
+	 * cpu number starting at bit 32 in the page->flags.  Also,
+	 * functions like clear_dcache_dirty_cpu use the cpu mask
+	 * in 13-bit signed-immediate instruction fields.
+	 */
+	BUILD_BUG_ON(FLAGS_RESERVED != 32);
+	BUILD_BUG_ON(SECTIONS_WIDTH + NODES_WIDTH + ZONES_WIDTH +
+		     ilog2(roundup_pow_of_two(NR_CPUS)) > FLAGS_RESERVED);
+	BUILD_BUG_ON(NR_CPUS > 4096);
+
 	kern_base = (prom_boot_mapping_phys_low >> 22UL) << 22UL;
 	kern_size = (unsigned long)&_end - (unsigned long)KERNBASE;