x86/CPU/AMD: Bring back Compute Unit ID

commit 79a8b9aa upstream.

Commit:

  a33d3317 ("x86/CPU/AMD: Fix Bulldozer topology")

restored the initial approach we had with the Fam15h topology of
enumerating CU (Compute Unit) threads as cores. And this is still
correct - they're beefier than HT threads but still have some
shared functionality.

Our current approach has a problem with the Mad Max Steam game, for
example. Yves Dionne reported a certain "choppiness" while playing on
v4.9.5.

That problem stems most likely from the fact that the CU threads share
resources within one CU and when we schedule to a thread of a different
compute unit, this incurs latency due to migrating the working set to a
different CU through the caches.

When the thread siblings mask mirrors that aspect of the CUs and
threads, the scheduler pays attention to it and tries to schedule within
one CU first. Which takes care of the latency, of course.
Reported-by: Yves Dionne <yves.dionne@gmail.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Cc: Brice Goglin <Brice.Goglin@inria.fr>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Yazen Ghannam <yazen.ghannam@amd.com>
Link: http://lkml.kernel.org/r/20170205105022.8705-1-bp@alien8.deSigned-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

arch/x86/include/asm/processor.h

@@ -104,6 +104,7 @@ struct cpuinfo_x86 {
 	__u8			x86_phys_bits;
 	/* CPUID returned core id bits: */
 	__u8			x86_coreid_bits;
+	__u8			cu_id;
 	/* Max extended CPUID function supported: */
 	__u32			extended_cpuid_level;
 	/* Maximum supported CPUID level, -1=no CPUID: */

arch/x86/kernel/cpu/amd.c

@@ -309,8 +309,15 @@ static void amd_get_topology(struct cpuinfo_x86 *c)
 
 	/* get information required for multi-node processors */
 	if (boot_cpu_has(X86_FEATURE_TOPOEXT)) {
+		u32 eax, ebx, ecx, edx;
 
-		node_id = cpuid_ecx(0x8000001e) & 7;
+		cpuid(0x8000001e, &eax, &ebx, &ecx, &edx);
+
+		node_id  = ecx & 0xff;
+		smp_num_siblings = ((ebx >> 8) & 0xff) + 1;
+
+		if (c->x86 == 0x15)
+			c->cu_id = ebx & 0xff;
 
 		/*
 		 * We may have multiple LLCs if L3 caches exist, so check if we

arch/x86/kernel/cpu/common.c

@@ -1015,6 +1015,7 @@ static void identify_cpu(struct cpuinfo_x86 *c)
 	c->x86_model_id[0] = '\0';  /* Unset */
 	c->x86_max_cores = 1;
 	c->x86_coreid_bits = 0;
+	c->cu_id = 0xff;
 #ifdef CONFIG_X86_64
 	c->x86_clflush_size = 64;
 	c->x86_phys_bits = 36;

arch/x86/kernel/smpboot.c

@@ -423,9 +423,15 @@ static bool match_smt(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
 		int cpu1 = c->cpu_index, cpu2 = o->cpu_index;
 
 		if (c->phys_proc_id == o->phys_proc_id &&
-		    per_cpu(cpu_llc_id, cpu1) == per_cpu(cpu_llc_id, cpu2) &&
-		    c->cpu_core_id == o->cpu_core_id)
-			return topology_sane(c, o, "smt");
+		    per_cpu(cpu_llc_id, cpu1) == per_cpu(cpu_llc_id, cpu2)) {
+			if (c->cpu_core_id == o->cpu_core_id)
+				return topology_sane(c, o, "smt");
+
+			if ((c->cu_id != 0xff) &&
+			    (o->cu_id != 0xff) &&
+			    (c->cu_id == o->cu_id))
+				return topology_sane(c, o, "smt");
+		}
 
 	} else if (c->phys_proc_id == o->phys_proc_id &&
 		   c->cpu_core_id == o->cpu_core_id) {