[RFC][PATCH] sched: Rename DIE domain

[RFC][PATCH] sched: Rename DIE domain

[Peter Zijlstra]

Hi

Thomas just tripped over the x86 topology setup creating a 'DIE' domain
for the package mask :-)

Since these names are SCHED_DEBUG only, rename them.
I don't think anybody *should* be relying on this, but who knows.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
 arch/powerpc/kernel/smp.c   | 2 +-
 arch/s390/kernel/topology.c | 2 +-
 arch/x86/kernel/smpboot.c   | 2 +-
 kernel/sched/topology.c     | 2 +-
 4 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index fbbb695bae3d..5ed6b9fe5094 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -1050,7 +1050,7 @@ static struct sched_domain_topology_level powerpc_topology[] = {
 #endif
 	{ shared_cache_mask, powerpc_shared_cache_flags, SD_INIT_NAME(CACHE) },
 	{ cpu_mc_mask, SD_INIT_NAME(MC) },
-	{ cpu_cpu_mask, SD_INIT_NAME(DIE) },
+	{ cpu_cpu_mask, SD_INIT_NAME(PKG) },
 	{ NULL, },
 };
 
diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c
index 68adf1de8888..c803f5e6ab46 100644
--- a/arch/s390/kernel/topology.c
+++ b/arch/s390/kernel/topology.c
@@ -522,7 +522,7 @@ static struct sched_domain_topology_level s390_topology[] = {
 	{ cpu_coregroup_mask, cpu_core_flags, SD_INIT_NAME(MC) },
 	{ cpu_book_mask, SD_INIT_NAME(BOOK) },
 	{ cpu_drawer_mask, SD_INIT_NAME(DRAWER) },
-	{ cpu_cpu_mask, SD_INIT_NAME(DIE) },
+	{ cpu_cpu_mask, SD_INIT_NAME(PKG) },
 	{ NULL, },
 };
 
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index e1aa2cd7734b..09cc9d0aa358 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -653,7 +653,7 @@ static void __init build_sched_topology(void)
 	 */
 	if (!x86_has_numa_in_package) {
 		x86_topology[i++] = (struct sched_domain_topology_level){
-			cpu_cpu_mask, SD_INIT_NAME(DIE)
+			cpu_cpu_mask, SD_INIT_NAME(PKG)
 		};
 	}
 
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index d3a3b2646ec4..e9d9cf776b7a 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -1670,7 +1670,7 @@ static struct sched_domain_topology_level default_topology[] = {
 #ifdef CONFIG_SCHED_MC
 	{ cpu_coregroup_mask, cpu_core_flags, SD_INIT_NAME(MC) },
 #endif
-	{ cpu_cpu_mask, SD_INIT_NAME(DIE) },
+	{ cpu_cpu_mask, SD_INIT_NAME(PKG) },
 	{ NULL, },
 };
 

Re: [RFC][PATCH] sched: Rename DIE domain

[Valentin Schneider]

On 12/07/23 16:10, Peter Zijlstra wrote:
> Hi
>
> Thomas just tripped over the x86 topology setup creating a 'DIE' domain
> for the package mask :-)
>
> Since these names are SCHED_DEBUG only, rename them.
> I don't think anybody *should* be relying on this, but who knows.
>

FWIW I don't care much about the actual name.

There are some stray references to DIE in comments - see below. Bit funny
to see:
- *  - Package (DIE)
+ *  - Package (PKG)

With that:
Acked-by: Valentin Schneider <vschneid@redhat.com>

---
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index a80a73909dc2a..190a647534984 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -9439,7 +9439,7 @@ static bool sched_use_asym_prio(struct sched_domain *sd, int cpu)
  * can only do it if @group is an SMT group and has exactly on busy CPU. Larger
  * imbalances in the number of CPUS are dealt with in find_busiest_group().
  *
- * If we are balancing load within an SMT core, or at DIE domain level, always
+ * If we are balancing load within an SMT core, or at PKG domain level, always
  * proceed.
  *
  * Return: true if @env::dst_cpu can do with asym_packing load balance. False
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index e9d9cf776b7ab..2cdcfec1d1c89 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -1118,7 +1118,7 @@ build_overlap_sched_groups(struct sched_domain *sd, int cpu)
  *
  *  - Simultaneous multithreading (SMT)
  *  - Multi-Core Cache (MC)
- *  - Package (DIE)
+ *  - Package (PKG)
  *
  * Where the last one more or less denotes everything up to a NUMA node.
  *
@@ -1140,13 +1140,13 @@ build_overlap_sched_groups(struct sched_domain *sd, int cpu)
  *
  * CPU   0   1   2   3   4   5   6   7
  *
- * DIE  [                             ]
+ * PKG  [                             ]
  * MC   [             ] [             ]
  * SMT  [     ] [     ] [     ] [     ]
  *
  *  - or -
  *
- * DIE  0-7 0-7 0-7 0-7 0-7 0-7 0-7 0-7
+ * PKG  0-7 0-7 0-7 0-7 0-7 0-7 0-7 0-7
  * MC	0-3 0-3 0-3 0-3 4-7 4-7 4-7 4-7
  * SMT  0-1 0-1 2-3 2-3 4-5 4-5 6-7 6-7
  *

Re: [RFC][PATCH] sched: Rename DIE domain

[Peter Zijlstra]

On Wed, Jul 12, 2023 at 04:02:38PM +0100, Valentin Schneider wrote:
> On 12/07/23 16:10, Peter Zijlstra wrote:
> > Hi
> >
> > Thomas just tripped over the x86 topology setup creating a 'DIE' domain
> > for the package mask :-)
> >
> > Since these names are SCHED_DEBUG only, rename them.
> > I don't think anybody *should* be relying on this, but who knows.
> >
> 
> FWIW I don't care much about the actual name.

Confusion is due to x86 growing an actual die topology and this not
being it.

Other than that, I can't be bothered too much about the silly name
either.

> There are some stray references to DIE in comments - see below. Bit funny
> to see:
> - *  - Package (DIE)
> + *  - Package (PKG)
> 
> With that:
> Acked-by: Valentin Schneider <vschneid@redhat.com>

Durr, I did a git-grep SD_INIT_NAME().. Thanks!

Re: [RFC][PATCH] sched: Rename DIE domain

[Mel Gorman]

On Wed, Jul 12, 2023 at 04:02:38PM +0100, Valentin Schneider wrote:
> On 12/07/23 16:10, Peter Zijlstra wrote:
> > Hi
> >
> > Thomas just tripped over the x86 topology setup creating a 'DIE' domain
> > for the package mask :-)
> >
> > Since these names are SCHED_DEBUG only, rename them.
> > I don't think anybody *should* be relying on this, but who knows.
> >
> 
> FWIW I don't care much about the actual name.
> 
> There are some stray references to DIE in comments - see below. Bit funny
> to see:
> - *  - Package (DIE)
> + *  - Package (PKG)
> 
> With that:
> Acked-by: Valentin Schneider <vschneid@redhat.com>
> 

No objection either, PKG is less ambiguous than DIE

Acked-by: Mel Gorman <mgorman@suse.de>

-- 
Mel Gorman
SUSE Labs

Re: [RFC][PATCH] sched: Rename DIE domain

[Heiko Carstens]

On Wed, Jul 12, 2023 at 04:10:56PM +0200, Peter Zijlstra wrote:
> Hi
> 
> Thomas just tripped over the x86 topology setup creating a 'DIE' domain
> for the package mask :-)
> 
> Since these names are SCHED_DEBUG only, rename them.
> I don't think anybody *should* be relying on this, but who knows.
> 
> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
> ---
>  arch/powerpc/kernel/smp.c   | 2 +-
>  arch/s390/kernel/topology.c | 2 +-
>  arch/x86/kernel/smpboot.c   | 2 +-
>  kernel/sched/topology.c     | 2 +-
>  4 files changed, 4 insertions(+), 4 deletions(-)

For s390:
Acked-by: Heiko Carstens <hca@linux.ibm.com>

Re: [RFC][PATCH] sched: Rename DIE domain

[Shrikanth Hegde]

On 7/12/23 8:32 PM, Valentin Schneider wrote:
> On 12/07/23 16:10, Peter Zijlstra wrote:
>> Hi
>>
>> Thomas just tripped over the x86 topology setup creating a 'DIE' domain
>> for the package mask :-)
>>
>> Since these names are SCHED_DEBUG only, rename them.
>> I don't think anybody *should* be relying on this, but who knows.
>>
> 
> FWIW I don't care much about the actual name.
> 
> There are some stray references to DIE in comments - see below. Bit funny
> to see:
> - *  - Package (DIE)
> + *  - Package (PKG)
> 
> With that:
> Acked-by: Valentin Schneider <vschneid@redhat.com>
> 
> ---
> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index a80a73909dc2a..190a647534984 100644
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -9439,7 +9439,7 @@ static bool sched_use_asym_prio(struct sched_domain *sd, int cpu)
>   * can only do it if @group is an SMT group and has exactly on busy CPU. Larger
>   * imbalances in the number of CPUS are dealt with in find_busiest_group().
>   *
> - * If we are balancing load within an SMT core, or at DIE domain level, always
> + * If we are balancing load within an SMT core, or at PKG domain level, always
>   * proceed.
>   *
>   * Return: true if @env::dst_cpu can do with asym_packing load balance. False
> diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
> index e9d9cf776b7ab..2cdcfec1d1c89 100644
> --- a/kernel/sched/topology.c
> +++ b/kernel/sched/topology.c
> @@ -1118,7 +1118,7 @@ build_overlap_sched_groups(struct sched_domain *sd, int cpu)
>   *
>   *  - Simultaneous multithreading (SMT)
>   *  - Multi-Core Cache (MC)
> - *  - Package (DIE)
> + *  - Package (PKG)
>   *
>   * Where the last one more or less denotes everything up to a NUMA node.
>   *
> @@ -1140,13 +1140,13 @@ build_overlap_sched_groups(struct sched_domain *sd, int cpu)
>   *
>   * CPU   0   1   2   3   4   5   6   7
>   *
> - * DIE  [                             ]
> + * PKG  [                             ]
>   * MC   [             ] [             ]
>   * SMT  [     ] [     ] [     ] [     ]
>   *
>   *  - or -
>   *
> - * DIE  0-7 0-7 0-7 0-7 0-7 0-7 0-7 0-7
> + * PKG  0-7 0-7 0-7 0-7 0-7 0-7 0-7 0-7
>   * MC	0-3 0-3 0-3 0-3 4-7 4-7 4-7 4-7
>   * SMT  0-1 0-1 2-3 2-3 4-5 4-5 6-7 6-7
>   *
> 

A couple of comments missing the change still? Not sure if it taken care already.

---
 arch/powerpc/kernel/smp.c | 2 +-
 arch/x86/kernel/smpboot.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index fbbb695bae3d..9b1853bf6b1d 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -1588,7 +1588,7 @@ static void add_cpu_to_masks(int cpu)
 	/* Skip all CPUs already part of current CPU core mask */
 	cpumask_andnot(mask, cpu_online_mask, cpu_core_mask(cpu));
 
-	/* If chip_id is -1; limit the cpu_core_mask to within DIE*/
+	/* If chip_id is -1; limit the cpu_core_mask to within PKG*/
 	if (chip_id == -1)
 		cpumask_and(mask, mask, cpu_cpu_mask(cpu));
 
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index e1aa2cd7734b..3f175e70eb7a 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -647,7 +647,7 @@ static void __init build_sched_topology(void)
 	};
 #endif
 	/*
-	 * When there is NUMA topology inside the package skip the DIE domain
+	 * When there is NUMA topology inside the package skip the PKG domain
 	 * since the NUMA domains will auto-magically create the right spanning
 	 * domains based on the SLIT.
 	 */

Re: [RFC][PATCH] sched: Rename DIE domain

[Gautham R. Shenoy]

On Wed, Jul 12, 2023 at 04:10:56PM +0200, Peter Zijlstra wrote:
> Hi
> 
> Thomas just tripped over the x86 topology setup creating a 'DIE' domain
> for the package mask :-)
> 
> Since these names are SCHED_DEBUG only, rename them.
> I don't think anybody *should* be relying on this, but who knows.
> 
> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>

This naming makes sense.
Acked-by: Gautham R. Shenoy <gautham.shenoy@amd.com>

--
Thanks and Regards
gautham.

Re: [RFC][PATCH] sched: Rename DIE domain

[Vincent Guittot]

On Wed, 12 Jul 2023 at 16:11, Peter Zijlstra <peterz@infradead.org> wrote:
>
> Hi
>
> Thomas just tripped over the x86 topology setup creating a 'DIE' domain
> for the package mask :-)

May be a link to the change that triggers this patch could be useful

>
> Since these names are SCHED_DEBUG only, rename them.
> I don't think anybody *should* be relying on this, but who knows.

Apart the remaining reference to DIE already mentioned by others,
looks good to me

>
> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
> ---
>  arch/powerpc/kernel/smp.c   | 2 +-
>  arch/s390/kernel/topology.c | 2 +-
>  arch/x86/kernel/smpboot.c   | 2 +-
>  kernel/sched/topology.c     | 2 +-
>  4 files changed, 4 insertions(+), 4 deletions(-)
>
> diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
> index fbbb695bae3d..5ed6b9fe5094 100644
> --- a/arch/powerpc/kernel/smp.c
> +++ b/arch/powerpc/kernel/smp.c
> @@ -1050,7 +1050,7 @@ static struct sched_domain_topology_level powerpc_topology[] = {
>  #endif
>         { shared_cache_mask, powerpc_shared_cache_flags, SD_INIT_NAME(CACHE) },
>         { cpu_mc_mask, SD_INIT_NAME(MC) },
> -       { cpu_cpu_mask, SD_INIT_NAME(DIE) },
> +       { cpu_cpu_mask, SD_INIT_NAME(PKG) },
>         { NULL, },
>  };
>
> diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c
> index 68adf1de8888..c803f5e6ab46 100644
> --- a/arch/s390/kernel/topology.c
> +++ b/arch/s390/kernel/topology.c
> @@ -522,7 +522,7 @@ static struct sched_domain_topology_level s390_topology[] = {
>         { cpu_coregroup_mask, cpu_core_flags, SD_INIT_NAME(MC) },
>         { cpu_book_mask, SD_INIT_NAME(BOOK) },
>         { cpu_drawer_mask, SD_INIT_NAME(DRAWER) },
> -       { cpu_cpu_mask, SD_INIT_NAME(DIE) },
> +       { cpu_cpu_mask, SD_INIT_NAME(PKG) },
>         { NULL, },
>  };
>
> diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
> index e1aa2cd7734b..09cc9d0aa358 100644
> --- a/arch/x86/kernel/smpboot.c
> +++ b/arch/x86/kernel/smpboot.c
> @@ -653,7 +653,7 @@ static void __init build_sched_topology(void)
>          */
>         if (!x86_has_numa_in_package) {
>                 x86_topology[i++] = (struct sched_domain_topology_level){
> -                       cpu_cpu_mask, SD_INIT_NAME(DIE)
> +                       cpu_cpu_mask, SD_INIT_NAME(PKG)
>                 };
>         }
>
> diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
> index d3a3b2646ec4..e9d9cf776b7a 100644
> --- a/kernel/sched/topology.c
> +++ b/kernel/sched/topology.c
> @@ -1670,7 +1670,7 @@ static struct sched_domain_topology_level default_topology[] = {
>  #ifdef CONFIG_SCHED_MC
>         { cpu_coregroup_mask, cpu_core_flags, SD_INIT_NAME(MC) },
>  #endif
> -       { cpu_cpu_mask, SD_INIT_NAME(DIE) },
> +       { cpu_cpu_mask, SD_INIT_NAME(PKG) },
>         { NULL, },
>  };
>
>

Re: [RFC][PATCH] sched: Rename DIE domain

[Peter Zijlstra]

On Mon, Jul 17, 2023 at 03:51:25PM +0200, Vincent Guittot wrote:
> On Wed, 12 Jul 2023 at 16:11, Peter Zijlstra <peterz@infradead.org> wrote:
> >
> > Hi
> >
> > Thomas just tripped over the x86 topology setup creating a 'DIE' domain
> > for the package mask :-)
> 
> May be a link to the change that triggers this patch could be useful

Thomas should post soonish..