2021-05-21 20:06:26

by Hugh Dickins

[permalink] [raw]
Subject: config SCHED_CORE

Hi Peter,

make oldconfig gave me no help at all on how to decide whether to choose
SCHED_CORE Y or n, beyond it recommending Y. Maybe you'll delete that
option later, or maybe removing the prompt string would silence it.

I decided that I probably need kernel/sched/core.o, so chose Y :)

Hugh


2021-05-25 08:22:14

by Peter Zijlstra

[permalink] [raw]
Subject: [PATCH] sched: Add CONFIG_SCHED_CORE help text

Subject: sched: Add CONFIG_SCHED_CORE help text
From: Peter Zijlstra <[email protected]>
Date: Tue May 25 08:53:28 CEST 2021

Hugh noted that the SCHED_CORE Kconfig option could do with a help
text.

Requested-by: Hugh Dickins <[email protected]>
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
---
kernel/Kconfig.preempt | 14 ++++++++++++++
1 file changed, 14 insertions(+)

--- a/kernel/Kconfig.preempt
+++ b/kernel/Kconfig.preempt
@@ -104,4 +104,18 @@ config SCHED_CORE
bool "Core Scheduling for SMT"
default y
depends on SCHED_SMT
+ help
+ This option permits Core Scheduling, a means of coordinated task
+ selection across SMT siblings. When enabled -- see
+ prctl(PR_SCHED_CORE) -- task selection ensures that all SMT siblings
+ will execute a task from the same 'core group', forcing idle when no
+ matching task is found.
+
+ Use of this feature includes:
+ - mitigation of some (not all) SMT side channels;
+ - limiting SMT interference to improve determinism and/or performance.
+
+ SCHED_CORE is default enabled when SCHED_SMT is enabled -- when
+ unused there should be no impact on performance.
+

2021-05-25 20:07:29

by Randy Dunlap

[permalink] [raw]
Subject: Re: [PATCH] sched: Add CONFIG_SCHED_CORE help text

On 5/25/21 12:05 AM, Peter Zijlstra wrote:
> Subject: sched: Add CONFIG_SCHED_CORE help text
> From: Peter Zijlstra <[email protected]>
> Date: Tue May 25 08:53:28 CEST 2021
>
> Hugh noted that the SCHED_CORE Kconfig option could do with a help
> text.
>
> Requested-by: Hugh Dickins <[email protected]>
> Signed-off-by: Peter Zijlstra (Intel) <[email protected]>

Reviewed-by: Randy Dunlap <[email protected]>

Thanks.

> ---
> kernel/Kconfig.preempt | 14 ++++++++++++++
> 1 file changed, 14 insertions(+)
>
> --- a/kernel/Kconfig.preempt
> +++ b/kernel/Kconfig.preempt
> @@ -104,4 +104,18 @@ config SCHED_CORE
> bool "Core Scheduling for SMT"
> default y
> depends on SCHED_SMT
> + help
> + This option permits Core Scheduling, a means of coordinated task
> + selection across SMT siblings. When enabled -- see
> + prctl(PR_SCHED_CORE) -- task selection ensures that all SMT siblings
> + will execute a task from the same 'core group', forcing idle when no
> + matching task is found.
> +
> + Use of this feature includes:
> + - mitigation of some (not all) SMT side channels;
> + - limiting SMT interference to improve determinism and/or performance.
> +
> + SCHED_CORE is default enabled when SCHED_SMT is enabled -- when
> + unused there should be no impact on performance.
> +
>
>


--
~Randy

2021-05-25 23:01:03

by Hugh Dickins

[permalink] [raw]
Subject: Re: [PATCH] sched: Add CONFIG_SCHED_CORE help text

On Tue, 25 May 2021, Peter Zijlstra wrote:

> Subject: sched: Add CONFIG_SCHED_CORE help text
> From: Peter Zijlstra <[email protected]>
> Date: Tue May 25 08:53:28 CEST 2021
>
> Hugh noted that the SCHED_CORE Kconfig option could do with a help
> text.
>
> Requested-by: Hugh Dickins <[email protected]>
> Signed-off-by: Peter Zijlstra (Intel) <[email protected]>

Thanks,
Acked-by: Hugh Dickins <[email protected]>
if necessary (but there's more than enough of me there already).

> ---
> kernel/Kconfig.preempt | 14 ++++++++++++++
> 1 file changed, 14 insertions(+)
>
> --- a/kernel/Kconfig.preempt
> +++ b/kernel/Kconfig.preempt
> @@ -104,4 +104,18 @@ config SCHED_CORE
> bool "Core Scheduling for SMT"
> default y
> depends on SCHED_SMT
> + help
> + This option permits Core Scheduling, a means of coordinated task
> + selection across SMT siblings. When enabled -- see
> + prctl(PR_SCHED_CORE) -- task selection ensures that all SMT siblings
> + will execute a task from the same 'core group', forcing idle when no
> + matching task is found.
> +
> + Use of this feature includes:
> + - mitigation of some (not all) SMT side channels;
> + - limiting SMT interference to improve determinism and/or performance.
> +
> + SCHED_CORE is default enabled when SCHED_SMT is enabled -- when
> + unused there should be no impact on performance.
> +

Subject: [tip: sched/core] sched: Add CONFIG_SCHED_CORE help text

The following commit has been merged into the sched/core branch of tip:

Commit-ID: 7b419f47facd286c6723daca6ad69ec355473f78
Gitweb: https://git.kernel.org/tip/7b419f47facd286c6723daca6ad69ec355473f78
Author: Peter Zijlstra <[email protected]>
AuthorDate: Tue, 25 May 2021 08:53:28 +02:00
Committer: Peter Zijlstra <[email protected]>
CommitterDate: Tue, 01 Jun 2021 16:00:10 +02:00

sched: Add CONFIG_SCHED_CORE help text

Hugh noted that the SCHED_CORE Kconfig option could do with a help
text.

Requested-by: Hugh Dickins <[email protected]>
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Reviewed-by: Randy Dunlap <[email protected]>
Acked-by: Hugh Dickins <[email protected]>
Link: https://lkml.kernel.org/r/[email protected]
---
kernel/Kconfig.preempt | 14 ++++++++++++++
1 file changed, 14 insertions(+)

diff --git a/kernel/Kconfig.preempt b/kernel/Kconfig.preempt
index ea1e333..bd7c414 100644
--- a/kernel/Kconfig.preempt
+++ b/kernel/Kconfig.preempt
@@ -104,4 +104,18 @@ config SCHED_CORE
bool "Core Scheduling for SMT"
default y
depends on SCHED_SMT
+ help
+ This option permits Core Scheduling, a means of coordinated task
+ selection across SMT siblings. When enabled -- see
+ prctl(PR_SCHED_CORE) -- task selection ensures that all SMT siblings
+ will execute a task from the same 'core group', forcing idle when no
+ matching task is found.
+
+ Use of this feature includes:
+ - mitigation of some (not all) SMT side channels;
+ - limiting SMT interference to improve determinism and/or performance.
+
+ SCHED_CORE is default enabled when SCHED_SMT is enabled -- when
+ unused there should be no impact on performance.
+