[SPARC64]: Fix endless loop in cheetah_xcall_deliver().

[ Upsteam commit: 0de56d1ab83323d604d95ca193dcbd28388dbabb ]

We need to mask out the proper bits when testing the dispatch status
register else we can see unrelated NACK bits from previous cross call
sends.

Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Adrian Bunk <bunk@kernel.org>

diff --git a/arch/sparc64/kernel/smp.c b/arch/sparc64/kernel/smp.c
index 1f7ad8a690526177bcfc62abe1c7a6f90c4f90b0..39f95217518d9b1ecef59f860242d0ea0e89352f 100644 (file)
--- a/arch/sparc64/kernel/smp.c
+++ b/arch/sparc64/kernel/smp.c
@@ -440,7 +440,7 @@ static __inline__ void spitfire_xcall_deliver(u64 data0, u64 data1, u64 data2, c
  */
 static void cheetah_xcall_deliver(u64 data0, u64 data1, u64 data2, cpumask_t mask)
 {
-       u64 pstate, ver;
+       u64 pstate, ver, busy_mask;
        int nack_busy_id, is_jalapeno;
 
        if (cpus_empty(mask))
@@ -470,14 +470,20 @@ retry:
                               "i" (ASI_INTR_W));
 
        nack_busy_id = 0;
+       busy_mask = 0;
        {
                int i;
 
                for_each_cpu_mask(i, mask) {
                        u64 target = (i << 14) | 0x70;
 
-                       if (!is_jalapeno)
+                       if (is_jalapeno) {
+                               busy_mask |= (0x1UL << (i * 2));
+                       } else {
                                target |= (nack_busy_id << 24);
+                               busy_mask |= (0x1UL <<
+                                             (nack_busy_id * 2));
+                       }
                        __asm__ __volatile__(
                                "stxa   %%g0, [%0] %1\n\t"
                                "membar #Sync\n\t"
@@ -489,27 +495,28 @@ retry:
 
        /* Now, poll for completion. */
        {
-               u64 dispatch_stat;
+               u64 dispatch_stat, nack_mask;
                long stuck;
 
                stuck = 100000 * nack_busy_id;
+               nack_mask = busy_mask << 1;
                do {
                        __asm__ __volatile__("ldxa      [%%g0] %1, %0"
                                             : "=r" (dispatch_stat)
                                             : "i" (ASI_INTR_DISPATCH_STAT));
-                       if (dispatch_stat == 0UL) {
+                       if (!(dispatch_stat & (busy_mask | nack_mask))) {
                                __asm__ __volatile__("wrpr %0, 0x0, %%pstate"
                                                     : : "r" (pstate));
                                return;
                        }
                        if (!--stuck)
                                break;
-               } while (dispatch_stat & 0x5555555555555555UL);
+               } while (dispatch_stat & busy_mask);
 
                __asm__ __volatile__("wrpr %0, 0x0, %%pstate"
                                     : : "r" (pstate));
 
-               if ((dispatch_stat & ~(0x5555555555555555UL)) == 0) {
+               if (dispatch_stat & busy_mask) {
                        /* Busy bits will not clear, continue instead
                         * of freezing up on this cpu.
                         */