x86, cpu: Fix cache topology for early P4-SMT

P4 systems with cpuid level < 4 can have SMT, but the cache topology
description available (cpuid2) does not include SMP information.

Now we know that SMT shares all cache levels, and therefore we can
mark all available cache levels as shared.

We do this by setting cpu_llc_id to ->phys_proc_id, since that's
the same for each SMT thread. We can do this unconditional since if
there's no SMT its still true, the one CPU shares cache with only
itself.

This fixes a problem where such CPUs report an incorrect LLC CPU mask.

This in turn fixes a crash in the scheduler where the topology was
build wrong, it assumes the LLC mask to include at least the SMT CPUs.

Cc: Josh Boyer <[e-mail]>
Cc: Dietmar Eggemann <[e-mail]>
Tested-by: Bruno Wolff III <[e-mail]>
Signed-off-by: Peter Zijlstra <[e-mail]>
Link: http://lkml.kernel.org/r/[e-mail]
Signed-off-by: H. Peter Anvin <[e-mail]>

arch/x86/kernel/cpu/intel.c

···
 	 */
 	detect_extended_topology(c);
 
+	if (!cpu_has(c, X86_FEATURE_XTOPOLOGY)) {
+		/*
+		 * let's use the legacy cpuid vector 0x1 and 0x4 for topology
+		 * detection.
+		 */
+		c->x86_max_cores = intel_num_cpu_cores(c);
+#ifdef CONFIG_X86_32
+		detect_ht(c);
+#endif
+	}
+
 	l2 = init_intel_cacheinfo(c);
 	if (c->cpuid_level > 9) {
 		unsigned eax = cpuid_eax(10);
···
 	if (c->x86 == 6)
 		set_cpu_cap(c, X86_FEATURE_P3);
 #endif
-
-	if (!cpu_has(c, X86_FEATURE_XTOPOLOGY)) {
-		/*
-		 * let's use the legacy cpuid vector 0x1 and 0x4 for topology
-		 * detection.
-		 */
-		c->x86_max_cores = intel_num_cpu_cores(c);
-#ifdef CONFIG_X86_32
-		detect_ht(c);
-#endif
-	}
 
 	/* Work around errata */
 	srat_detect_node(c);

arch/x86/kernel/cpu/intel_cacheinfo.c

···
 #endif
 	}
 
+#ifdef CONFIG_X86_HT
+	/*
+	 * If cpu_llc_id is not yet set, this means cpuid_level < 4 which in
+	 * turns means that the only possibility is SMT (as indicated in
+	 * cpuid1). Since cpuid2 doesn't specify shared caches, and we know
+	 * that SMT shares all caches, we can unconditionally set cpu_llc_id to
+	 * c->phys_proc_id.
+	 */
+	if (per_cpu(cpu_llc_id, cpu) == BAD_APICID)
+		per_cpu(cpu_llc_id, cpu) = c->phys_proc_id;
+#endif
+
 	c->x86_cache_size = l3 ? l3 : (l2 ? l2 : (l1i+l1d));
 
 	return l2;