x86: changed output in /proc/cpuinfo for siblings

x86: changed output in /proc/cpuinfo for siblings

[Andreas Herrmann]

Commit 7ad728f98162cb1af06a85b2a5fc422dddd4fb78
(cpumask: x86: convert cpu_sibling_map/cpu_core_map to cpumask_var_t)
changed the output of /proc/cpuinfo for siblings:

Example on an AMD Phenom:

  physical id   : 0
  siblings : 1
  core id	   : 3
  cpu cores  : 4

Before that commit it was:

  physical id	: 0
  siblings : 4
  core id	   : 3
  cpu cores  : 4

Instead of cpu_core_mask it now uses cpu_sibling_mask to count siblings.
This is due to the following hunk of above commit:

  --- a/arch/x86/kernel/cpu/proc.c
  +++ b/arch/x86/kernel/cpu/proc.c
  @@ -14,7 +14,7 @@ static void show_cpuinfo_core(struct seq_file *m, struct cpuinf
          if (c->x86_max_cores * smp_num_siblings > 1) {
                  seq_printf(m, "physical id\t: %d\n", c->phys_proc_id);
                  seq_printf(m, "siblings\t: %d\n",
  -                          cpus_weight(per_cpu(cpu_core_map, cpu)));
  +                          cpumask_weight(cpu_sibling_mask(cpu)));
                  seq_printf(m, "core id\t\t: %d\n", c->cpu_core_id);
                  seq_printf(m, "cpu cores\t: %d\n", c->booted_cores);
                  seq_printf(m, "apicid\t\t: %d\n", c->apicid);

Was this the intention or just a mistake?
In the latter case attached patch reverts this hunk.


Regards,

Andreas

---
x86: show number of core_siblings instead of thread_siblings in /proc/cpuinfo

Commit 7ad728f98162cb1af06a85b2a5fc422dddd4fb78 (cpumask: x86: convert
cpu_sibling_map/cpu_core_map to cpumask_var_t) changed the value for
siblings in /proc/cpuinfo to be the number of thread_siblings instead
of core_siblings.

Revert the respective hunk to restore the old behavior.

Signed-off-by: Andreas Herrmann <andreas.herrmann3@amd.com>
---
diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c
index f93047f..d5e3039 100644
--- a/arch/x86/kernel/cpu/proc.c
+++ b/arch/x86/kernel/cpu/proc.c
@@ -14,7 +14,7 @@ static void show_cpuinfo_core(struct seq_file *m, struct cpuinfo_x86 *c,
 	if (c->x86_max_cores * smp_num_siblings > 1) {
 		seq_printf(m, "physical id\t: %d\n", c->phys_proc_id);
 		seq_printf(m, "siblings\t: %d\n",
-			   cpumask_weight(cpu_sibling_mask(cpu)));
+			   cpumask_weight(cpu_core_mask(cpu)));
 		seq_printf(m, "core id\t\t: %d\n", c->cpu_core_id);
 		seq_printf(m, "cpu cores\t: %d\n", c->booted_cores);
 		seq_printf(m, "apicid\t\t: %d\n", c->apicid);

Re: x86: changed output in /proc/cpuinfo for siblings

[Ingo Molnar]

* Andreas Herrmann <andreas.herrmann3@amd.com> wrote:

> Commit 7ad728f98162cb1af06a85b2a5fc422dddd4fb78
> (cpumask: x86: convert cpu_sibling_map/cpu_core_map to cpumask_var_t)
> changed the output of /proc/cpuinfo for siblings:
> 
> Example on an AMD Phenom:
> 
>   physical id   : 0
>   siblings : 1
>   core id	   : 3
>   cpu cores  : 4
> 
> Before that commit it was:
> 
>   physical id	: 0
>   siblings : 4
>   core id	   : 3
>   cpu cores  : 4
> 
> Instead of cpu_core_mask it now uses cpu_sibling_mask to count siblings.
> This is due to the following hunk of above commit:
> 
>   --- a/arch/x86/kernel/cpu/proc.c
>   +++ b/arch/x86/kernel/cpu/proc.c
>   @@ -14,7 +14,7 @@ static void show_cpuinfo_core(struct seq_file *m, struct cpuinf
>           if (c->x86_max_cores * smp_num_siblings > 1) {
>                   seq_printf(m, "physical id\t: %d\n", c->phys_proc_id);
>                   seq_printf(m, "siblings\t: %d\n",
>   -                          cpus_weight(per_cpu(cpu_core_map, cpu)));
>   +                          cpumask_weight(cpu_sibling_mask(cpu)));
>                   seq_printf(m, "core id\t\t: %d\n", c->cpu_core_id);
>                   seq_printf(m, "cpu cores\t: %d\n", c->booted_cores);
>                   seq_printf(m, "apicid\t\t: %d\n", c->apicid);
> 
> Was this the intention or just a mistake?

it was a mistake, because the impact-line does not mention this 
side-effect:

  Impact: reduce per-cpu size for CONFIG_CPUMASK_OFFSTACK=y

> In the latter case attached patch reverts this hunk.

applied, thanks!

	Ingo

[tip:x86/urgent] x86: show number of core_siblings instead of thread_siblings in /proc/cpuinfo

[tip-bot for Andreas Herrmann]

Commit-ID:  35d11680a9d82c93eb92f08f9702b72877427b4a
Gitweb:     http://git.kernel.org/tip/35d11680a9d82c93eb92f08f9702b72877427b4a
Author:     Andreas Herrmann <andreas.herrmann3@amd.com>
AuthorDate: Mon, 4 May 2009 20:28:59 +0200
Committer:  Ingo Molnar <mingo@elte.hu>
CommitDate: Mon, 4 May 2009 20:36:49 +0200

x86: show number of core_siblings instead of thread_siblings in /proc/cpuinfo

Commit 7ad728f98162cb1af06a85b2a5fc422dddd4fb78
(cpumask: x86: convert cpu_sibling_map/cpu_core_map to cpumask_var_t)
changed the output of /proc/cpuinfo for siblings:

Example on an AMD Phenom:

  physical id   : 0
  siblings : 1
  core id	   : 3
  cpu cores  : 4

Before that commit it was:

  physical id	: 0
  siblings : 4
  core id	   : 3
  cpu cores  : 4

Instead of cpu_core_mask it now uses cpu_sibling_mask to count siblings.
This is due to the following hunk of above commit:

|  --- a/arch/x86/kernel/cpu/proc.c
|  +++ b/arch/x86/kernel/cpu/proc.c
|  @@ -14,7 +14,7 @@ static void show_cpuinfo_core(struct seq_file *m, struct cpuinf
|          if (c->x86_max_cores * smp_num_siblings > 1) {
|                  seq_printf(m, "physical id\t: %d\n", c->phys_proc_id);
|                  seq_printf(m, "siblings\t: %d\n",
|  -                          cpus_weight(per_cpu(cpu_core_map, cpu)));
|  +                          cpumask_weight(cpu_sibling_mask(cpu)));
|                  seq_printf(m, "core id\t\t: %d\n", c->cpu_core_id);
|                  seq_printf(m, "cpu cores\t: %d\n", c->booted_cores);
|                  seq_printf(m, "apicid\t\t: %d\n", c->apicid);

This was a mistake, because the impact line shows that this side-effect
was not anticipated:

   Impact: reduce per-cpu size for CONFIG_CPUMASK_OFFSTACK=y

So revert the respective hunk to restore the old behavior.

[ Impact: fix sibling-info regression in /proc/cpuinfo ]

Signed-off-by: Andreas Herrmann <andreas.herrmann3@amd.com>
Cc: Rusty Russell <rusty@rustcorp.com.au>
LKML-Reference: <20090504182859.GA29045@alberich.amd.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>


---
 arch/x86/kernel/cpu/proc.c |    2 +-
 1 files changed, 1 insertions(+), 1 deletions(-)

diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c
index f93047f..d5e3039 100644
--- a/arch/x86/kernel/cpu/proc.c
+++ b/arch/x86/kernel/cpu/proc.c
@@ -14,7 +14,7 @@ static void show_cpuinfo_core(struct seq_file *m, struct cpuinfo_x86 *c,
 	if (c->x86_max_cores * smp_num_siblings > 1) {
 		seq_printf(m, "physical id\t: %d\n", c->phys_proc_id);
 		seq_printf(m, "siblings\t: %d\n",
-			   cpumask_weight(cpu_sibling_mask(cpu)));
+			   cpumask_weight(cpu_core_mask(cpu)));
 		seq_printf(m, "core id\t\t: %d\n", c->cpu_core_id);
 		seq_printf(m, "cpu cores\t: %d\n", c->booted_cores);
 		seq_printf(m, "apicid\t\t: %d\n", c->apicid);