Merge branch 'mpi-master' into wip-k-fmlpwip-k-fmlp

Conflicts:
	litmus/sched_cedf.c

1 files changed, 121 insertions, 46 deletions

diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index ba5f62f45f01..b13ed393dfce 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -148,7 +148,7 @@ static void __cpuinit amd_k7_smp_check(struct cpuinfo_x86 *c)
 {
 #ifdef CONFIG_SMP
         /* calling is from identify_secondary_cpu() ? */
-        if (c->cpu_index == boot_cpu_id)
+        if (!c->cpu_index)
                 return;
 
         /*
@@ -233,18 +233,22 @@ static void __cpuinit init_amd_k7(struct cpuinfo_x86 *c)
 }
 #endif
 
-#if defined(CONFIG_NUMA) && defined(CONFIG_X86_64)
+#ifdef CONFIG_NUMA
+/*
+ * To workaround broken NUMA config.  Read the comment in
+ * srat_detect_node().
+ */
 static int __cpuinit nearby_node(int apicid)
 {
         int i, node;
 
         for (i = apicid - 1; i >= 0; i--) {
-                node = apicid_to_node[i];
+                node = __apicid_to_node[i];
                 if (node != NUMA_NO_NODE && node_online(node))
                         return node;
         }
         for (i = apicid + 1; i < MAX_LOCAL_APIC; i++) {
-                node = apicid_to_node[i];
+                node = __apicid_to_node[i];
                 if (node != NUMA_NO_NODE && node_online(node))
                         return node;
         }
@@ -253,37 +257,55 @@ static int __cpuinit nearby_node(int apicid)
 #endif
 
 /*
- * Fixup core topology information for AMD multi-node processors.
- * Assumption: Number of cores in each internal node is the same.
+ * Fixup core topology information for
+ * (1) AMD multi-node processors
+ *     Assumption: Number of cores in each internal node is the same.
+ * (2) AMD processors supporting compute units
  */
 #ifdef CONFIG_X86_HT
-static void __cpuinit amd_fixup_dcm(struct cpuinfo_x86 *c)
+static void __cpuinit amd_get_topology(struct cpuinfo_x86 *c)
 {
-        unsigned long long value;
-        u32 nodes, cores_per_node;
+        u32 nodes, cores_per_cu = 1;
+        u8 node_id;
         int cpu = smp_processor_id();
 
-        if (!cpu_has(c, X86_FEATURE_NODEID_MSR))
-                return;
-
-        /* fixup topology information only once for a core */
-        if (cpu_has(c, X86_FEATURE_AMD_DCM))
+        /* get information required for multi-node processors */
+        if (cpu_has(c, X86_FEATURE_TOPOEXT)) {
+                u32 eax, ebx, ecx, edx;
+
+                cpuid(0x8000001e, &eax, &ebx, &ecx, &edx);
+                nodes = ((ecx >> 8) & 7) + 1;
+                node_id = ecx & 7;
+
+                /* get compute unit information */
+                smp_num_siblings = ((ebx >> 8) & 3) + 1;
+                c->compute_unit_id = ebx & 0xff;
+                cores_per_cu += ((ebx >> 8) & 3);
+        } else if (cpu_has(c, X86_FEATURE_NODEID_MSR)) {
+                u64 value;
+
+                rdmsrl(MSR_FAM10H_NODE_ID, value);
+                nodes = ((value >> 3) & 7) + 1;
+                node_id = value & 7;
+        } else
                 return;
 
-        rdmsrl(MSR_FAM10H_NODE_ID, value);
-
-        nodes = ((value >> 3) & 7) + 1;
-        if (nodes == 1)
-                return;
+        /* fixup multi-node processor information */
+        if (nodes > 1) {
+                u32 cores_per_node;
+                u32 cus_per_node;
 
-        set_cpu_cap(c, X86_FEATURE_AMD_DCM);
-        cores_per_node = c->x86_max_cores / nodes;
+                set_cpu_cap(c, X86_FEATURE_AMD_DCM);
+                cores_per_node = c->x86_max_cores / nodes;
+                cus_per_node = cores_per_node / cores_per_cu;
 
-        /* store NodeID, use llc_shared_map to store sibling info */
-        per_cpu(cpu_llc_id, cpu) = value & 7;
+                /* store NodeID, use llc_shared_map to store sibling info */
+                per_cpu(cpu_llc_id, cpu) = node_id;
 
-        /* fixup core id to be in range from 0 to (cores_per_node - 1) */
-        c->cpu_core_id = c->cpu_core_id % cores_per_node;
+                /* core id has to be in the [0 .. cores_per_node - 1] range */
+                c->cpu_core_id %= cores_per_node;
+                c->compute_unit_id %= cus_per_node;
+        }
 }
 #endif
 
@@ -304,9 +326,7 @@ static void __cpuinit amd_detect_cmp(struct cpuinfo_x86 *c)
         c->phys_proc_id = c->initial_apicid >> bits;
         /* use socket ID also for last level cache */
         per_cpu(cpu_llc_id, cpu) = c->phys_proc_id;
-        /* fixup topology information on multi-node processors */
-        if ((c->x86 == 0x10) && (c->x86_model == 9))
-                amd_fixup_dcm(c);
+        amd_get_topology(c);
 #endif
 }
 
@@ -322,31 +342,40 @@ EXPORT_SYMBOL_GPL(amd_get_nb_id);
 
 static void __cpuinit srat_detect_node(struct cpuinfo_x86 *c)
 {
-#if defined(CONFIG_NUMA) && defined(CONFIG_X86_64)
+#ifdef CONFIG_NUMA
         int cpu = smp_processor_id();
         int node;
         unsigned apicid = c->apicid;
 
-        node = per_cpu(cpu_llc_id, cpu);
+        node = numa_cpu_node(cpu);
+        if (node == NUMA_NO_NODE)
+                node = per_cpu(cpu_llc_id, cpu);
 
-        if (apicid_to_node[apicid] != NUMA_NO_NODE)
-                node = apicid_to_node[apicid];
         if (!node_online(node)) {
-                /* Two possibilities here:
-                   - The CPU is missing memory and no node was created.
-                   In that case try picking one from a nearby CPU
-                   - The APIC IDs differ from the HyperTransport node IDs
-                   which the K8 northbridge parsing fills in.
-                   Assume they are all increased by a constant offset,
-                   but in the same order as the HT nodeids.
-                   If that doesn't result in a usable node fall back to the
-                   path for the previous case.  */
-
+                /*
+                 * Two possibilities here:
+                 *
+                 * - The CPU is missing memory and no node was created.  In
+                 *   that case try picking one from a nearby CPU.
+                 *
+                 * - The APIC IDs differ from the HyperTransport node IDs
+                 *   which the K8 northbridge parsing fills in.  Assume
+                 *   they are all increased by a constant offset, but in
+                 *   the same order as the HT nodeids.  If that doesn't
+                 *   result in a usable node fall back to the path for the
+                 *   previous case.
+                 *
+                 * This workaround operates directly on the mapping between
+                 * APIC ID and NUMA node, assuming certain relationship
+                 * between APIC ID, HT node ID and NUMA topology.  As going
+                 * through CPU mapping may alter the outcome, directly
+                 * access __apicid_to_node[].
+                 */
                 int ht_nodeid = c->initial_apicid;
 
                 if (ht_nodeid >= 0 &&
-                    apicid_to_node[ht_nodeid] != NUMA_NO_NODE)
-                        node = apicid_to_node[ht_nodeid];
+                    __apicid_to_node[ht_nodeid] != NUMA_NO_NODE)
+                        node = __apicid_to_node[ht_nodeid];
                 /* Pick a nearby node */
                 if (!node_online(node))
                         node = nearby_node(apicid);
@@ -412,6 +441,23 @@ static void __cpuinit early_init_amd(struct cpuinfo_x86 *c)
                         set_cpu_cap(c, X86_FEATURE_EXTD_APICID);
         }
 #endif
+
+        /* We need to do the following only once */
+        if (c != &boot_cpu_data)
+                return;
+
+        if (cpu_has(c, X86_FEATURE_CONSTANT_TSC)) {
+
+                if (c->x86 > 0x10 ||
+                    (c->x86 == 0x10 && c->x86_model >= 0x2)) {
+                        u64 val;
+
+                        rdmsrl(MSR_K7_HWCR, val);
+                        if (!(val & BIT(24)))
+                                printk(KERN_WARNING FW_BUG "TSC doesn't count "
+                                        "with P0 frequency!\n");
+                }
+        }
 }
 
 static void __cpuinit init_amd(struct cpuinfo_x86 *c)
@@ -523,7 +569,7 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
 #endif
 
         if (c->extended_cpuid_level >= 0x80000006) {
-                if ((c->x86 >= 0x0f) && (cpuid_edx(0x80000006) & 0xf000))
+                if (cpuid_edx(0x80000006) & 0xf000)
                         num_cache_leaves = 4;
                 else
                         num_cache_leaves = 3;
@@ -565,6 +611,35 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
                 }
         }
 #endif
+
+        /*
+         * Family 0x12 and above processors have APIC timer
+         * running in deep C states.
+         */
+        if (c->x86 > 0x11)
+                set_cpu_cap(c, X86_FEATURE_ARAT);
+
+        /*
+         * Disable GART TLB Walk Errors on Fam10h. We do this here
+         * because this is always needed when GART is enabled, even in a
+         * kernel which has no MCE support built in.
+         */
+        if (c->x86 == 0x10) {
+                /*
+                 * BIOS should disable GartTlbWlk Errors themself. If
+                 * it doesn't do it here as suggested by the BKDG.
+                 *
+                 * Fixes: https://bugzilla.kernel.org/show_bug.cgi?id=33012
+                 */
+                u64 mask;
+                int err;
+
+                err = rdmsrl_safe(MSR_AMD64_MCx_MASK(4), &mask);
+                if (err == 0) {
+                        mask |= (1 << 10);
+                        checking_wrmsrl(MSR_AMD64_MCx_MASK(4), mask);
+                }
+        }
 }
 
 #ifdef CONFIG_X86_32
@@ -639,7 +714,7 @@ EXPORT_SYMBOL_GPL(amd_erratum_383);
 
 bool cpu_has_amd_erratum(const int *erratum)
 {
-        struct cpuinfo_x86 *cpu = &current_cpu_data;
+        struct cpuinfo_x86 *cpu = __this_cpu_ptr(&cpu_info);
         int osvw_id = *erratum++;
         u32 range;
         u32 ms;