2 files changed, 54 insertions, 17 deletions

diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c
index 3f0c30ae4791..c33d939120c9 100644
--- a/arch/powerpc/mm/hash_native_64.c
+++ b/arch/powerpc/mm/hash_native_64.c
@@ -43,6 +43,7 @@ static inline void __tlbie(unsigned long vpn, int psize, int apsize, int ssize)
 {
         unsigned long va;
         unsigned int penc;
+        unsigned long sllp;
 
         /*
          * We need 14 to 65 bits of va for a tlibe of 4K page
@@ -64,7 +65,9 @@ static inline void __tlbie(unsigned long vpn, int psize, int apsize, int ssize)
                 /* clear out bits after (52) [0....52.....63] */
                 va &= ~((1ul << (64 - 52)) - 1);
                 va |= ssize << 8;
-                va |= mmu_psize_defs[apsize].sllp << 6;
+                sllp = ((mmu_psize_defs[apsize].sllp & SLB_VSID_L) >> 6) |
+                        ((mmu_psize_defs[apsize].sllp & SLB_VSID_LP) >> 4);
+                va |= sllp << 5;
                 asm volatile(ASM_FTR_IFCLR("tlbie %0,0", PPC_TLBIE(%1,%0), %2)
                              : : "r" (va), "r"(0), "i" (CPU_FTR_ARCH_206)
                              : "memory");
@@ -98,6 +101,7 @@ static inline void __tlbiel(unsigned long vpn, int psize, int apsize, int ssize)
 {
         unsigned long va;
         unsigned int penc;
+        unsigned long sllp;
 
         /* VPN_SHIFT can be atmost 12 */
         va = vpn << VPN_SHIFT;
@@ -113,7 +117,9 @@ static inline void __tlbiel(unsigned long vpn, int psize, int apsize, int ssize)
                 /* clear out bits after(52) [0....52.....63] */
                 va &= ~((1ul << (64 - 52)) - 1);
                 va |= ssize << 8;
-                va |= mmu_psize_defs[apsize].sllp << 6;
+                sllp = ((mmu_psize_defs[apsize].sllp & SLB_VSID_L) >> 6) |
+                        ((mmu_psize_defs[apsize].sllp & SLB_VSID_LP) >> 4);
+                va |= sllp << 5;
                 asm volatile(".long 0x7c000224 | (%0 << 11) | (0 << 21)"
                              : : "r"(va) : "memory");
                 break;
@@ -554,6 +560,7 @@ static void hpte_decode(struct hash_pte *hpte, unsigned long slot,
                         seg_off |= vpi << shift;
                 }
                 *vpn = vsid << (SID_SHIFT - VPN_SHIFT) | seg_off >> VPN_SHIFT;
+                break;
         case MMU_SEGSIZE_1T:
                 /* We only have 40 - 23 bits of seg_off in avpn */
                 seg_off = (avpn & 0x1ffff) << 23;
@@ -563,6 +570,7 @@ static void hpte_decode(struct hash_pte *hpte, unsigned long slot,
                         seg_off |= vpi << shift;
                 }
                 *vpn = vsid << (SID_SHIFT_1T - VPN_SHIFT) | seg_off >> VPN_SHIFT;
+                break;
         default:
                 *vpn = size = 0;
         }
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 08397217e8ac..5850798826cd 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -27,6 +27,7 @@
 #include <linux/seq_file.h>
 #include <linux/uaccess.h>
 #include <linux/slab.h>
+#include <asm/cputhreads.h>
 #include <asm/sparsemem.h>
 #include <asm/prom.h>
 #include <asm/smp.h>
@@ -1318,7 +1319,8 @@ static int update_cpu_associativity_changes_mask(void)
                         }
                 }
                 if (changed) {
-                        cpumask_set_cpu(cpu, changes);
+                        cpumask_or(changes, changes, cpu_sibling_mask(cpu));
+                        cpu = cpu_last_thread_sibling(cpu);
                 }
         }
 
@@ -1426,7 +1428,7 @@ static int update_cpu_topology(void *data)
         if (!data)
                 return -EINVAL;
 
-        cpu = get_cpu();
+        cpu = smp_processor_id();
 
         for (update = data; update; update = update->next) {
                 if (cpu != update->cpu)
@@ -1446,12 +1448,12 @@ static int update_cpu_topology(void *data)
  */
 int arch_update_cpu_topology(void)
 {
-        unsigned int cpu, changed = 0;
+        unsigned int cpu, sibling, changed = 0;
         struct topology_update_data *updates, *ud;
         unsigned int associativity[VPHN_ASSOC_BUFSIZE] = {0};
         cpumask_t updated_cpus;
         struct device *dev;
-        int weight, i = 0;
+        int weight, new_nid, i = 0;
 
         weight = cpumask_weight(&cpu_associativity_changes_mask);
         if (!weight)
@@ -1464,19 +1466,46 @@ int arch_update_cpu_topology(void)
         cpumask_clear(&updated_cpus);
 
         for_each_cpu(cpu, &cpu_associativity_changes_mask) {
-                ud = &updates[i++];
-                ud->cpu = cpu;
-                vphn_get_associativity(cpu, associativity);
-                ud->new_nid = associativity_to_nid(associativity);
-
-                if (ud->new_nid < 0 || !node_online(ud->new_nid))
-                        ud->new_nid = first_online_node;
+                /*
+                 * If siblings aren't flagged for changes, updates list
+                 * will be too short. Skip on this update and set for next
+                 * update.
+                 */
+                if (!cpumask_subset(cpu_sibling_mask(cpu),
+                                        &cpu_associativity_changes_mask)) {
+                        pr_info("Sibling bits not set for associativity "
+                                        "change, cpu%d\n", cpu);
+                        cpumask_or(&cpu_associativity_changes_mask,
+                                        &cpu_associativity_changes_mask,
+                                        cpu_sibling_mask(cpu));
+                        cpu = cpu_last_thread_sibling(cpu);
+                        continue;
+                }
 
-                ud->old_nid = numa_cpu_lookup_table[cpu];
-                cpumask_set_cpu(cpu, &updated_cpus);
+                /* Use associativity from first thread for all siblings */
+                vphn_get_associativity(cpu, associativity);
+                new_nid = associativity_to_nid(associativity);
+                if (new_nid < 0 || !node_online(new_nid))
+                        new_nid = first_online_node;
+
+                if (new_nid == numa_cpu_lookup_table[cpu]) {
+                        cpumask_andnot(&cpu_associativity_changes_mask,
+                                        &cpu_associativity_changes_mask,
+                                        cpu_sibling_mask(cpu));
+                        cpu = cpu_last_thread_sibling(cpu);
+                        continue;
+                }
 
-                if (i < weight)
-                        ud->next = &updates[i];
+                for_each_cpu(sibling, cpu_sibling_mask(cpu)) {
+                        ud = &updates[i++];
+                        ud->cpu = sibling;
+                        ud->new_nid = new_nid;
+                        ud->old_nid = numa_cpu_lookup_table[sibling];
+                        cpumask_set_cpu(sibling, &updated_cpus);
+                        if (i < weight)
+                                ud->next = &updates[i];
+                }
+                cpu = cpu_last_thread_sibling(cpu);
         }
 
         stop_machine(update_cpu_topology, &updates[0], &updated_cpus);