Skip to contentSkip to conversation

x86/centaur: report correct CPU/cache topology

PATCH David Wang 1 participant 1 message Apr 25, 2018

lore
Share & tools
lore

David Wang

author
#0 lore raw
Quoted 12 lines

-----Original Mail-----
Sender: Thomas Gleixner [mailto:[email protected]]
Time: 2018年4月17日 18:16
Receiver: David Wang <[email protected]>
CC: [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; brucechang@via- alliance.com; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]
Subject: Re: [PATCH] x86/centaur: report correct CPU/cache topology

Quoted 6 lines
Quoted 2 lines · David Wang

This patch is used to support multi-core Centaur CPU. After using this patch, we can get correct CPU topology and correct cache topology.

David. This changelog is pretty useless. First of all, please do not use

'This

Quoted 9 lines

patch ..'. We all know already that this is a patch. Documentation/process/submitting-patches.rst has a good explanation about writing changelogs.

The changelog should explain why it does something. Let me give you an example:

Centaur CPUs enumerate the cache topology in the same way as Intel CPUs, but the functionality is unused so far. The Centaur init code also

misses

Quoted 7 lines

to initialize x86_cpuinfo::max_cores so the CPU topology cannot be desribed correctly,

Initialize x86_cpuinfo::max_cores and invoke init_intel_cacheinfo() to make CPU and cache topology information available and correct.

See? I'm neither using 'this patch' nor 'We/I' as I'm not impersonatimg

the

Quoted 1 line

code. It's all factual instead.

OK. I got it.

Quoted 14 lines

arch/x86/kernel/cpu/centaur.c static void early_init_centaur(struct cpuinfo_x86

Quoted 10 lines
---
 arch/x86/kernel/cpu/centaur.c | 20 ++++++++++++++++++++
 1 file changed, 20 insertions(+)
(quoted diff) +0 -0

b/arch/x86/kernel/cpu/centaur.c index e5ec0f1..713e4db 100644

arch/x86/kernel/cpu/centaur.c +0 -0
@@ -112,6 +112,19 @@ static void early_init_centaur(struct cpuinfo_x86

*c)

Quoted 3 lines
arch/x86/kernel/cpu/centaur.c +0 -0
 	}
 }
 
Quoted 12 lines

arch/x86/kernel/cpu/centaur.c static void early_init_centaur(struct cpuinfo_x86 · line 124

Quoted 10 lines
arch/x86/kernel/cpu/centaur.c +10 -0
+static int centaur_num_cpu_cores(struct cpuinfo_x86 *c) {
+	unsigned int eax, ebx, ecx, edx;
+
+	if (c->cpuid_level < 4)
+		return 1;
+	cpuid_count(4, 0, &eax, &ebx, &ecx, &edx);
+	if (eax & 0x1f)
+		return (eax >> 26) + 1;
+	else
+		return 1;

This is a bad copy of intel_num_cpu_cores(). See for the subtle

difference.

Quoted 2 lines

Please rename the intel function and move it to common.c

OK. I will adjust.

Quoted 10 lines

arch/x86/kernel/cpu/centaur.c

Quoted 9 lines
arch/x86/kernel/cpu/centaur.c +0 -0
 static void init_centaur(struct cpuinfo_x86 *c)  {  #ifdef

CONFIG_X86_32 @@ -128,6 +141,13 @@ static void init_centaur(struct cpuinfo_x86 *c)

arch/x86/kernel/cpu/centaur.c +3 -0
 	clear_cpu_cap(c, 0*32+31);
 #endif
 	early_init_centaur(c);
+
+	init_intel_cacheinfo(c);
+	c->x86_max_cores = centaur_num_cpu_cores(c); #ifdef

CONFIG_X86_32

Quoted 4 lines

arch/x86/kernel/cpu/centaur.c

Quoted 2 lines
arch/x86/kernel/cpu/centaur.c +2 -0
+	detect_ht(c);
+#endif

Can you please create a stub inline of detect_ht() for the !32bit case and

get

Quoted 1 line

rid of these #ifdefs in the code. That wants to be a separate patch which

also

Quoted 1 line

cleans up the existing call sites.

The detect_ht() function will also be called by identify_cpu()
function for
!32bit case. So, I think it means that all 64-bit CPUs can use
detect_ht(),
but only some 32-bit CPUs can use detect_ht(). Please correct me, if I'm wrong.

Quoted 4 lines

Thanks,

tglx

Thanks,

---
David