[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/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;
