From: Frederic Weisbecker <frederic@kernel.org>
To: Will Deacon <will@kernel.org>
Cc: LKML <linux-kernel@vger.kernel.org>,
Catalin Marinas <catalin.marinas@arm.com>,
Marc Zyngier <maz@kernel.org>,
Oliver Upton <oliver.upton@linux.dev>,
Ard Biesheuvel <ardb@kernel.org>,
Mark Rutland <mark.rutland@arm.com>,
Andrew Morton <akpm@linux-foundation.org>,
Peter Zijlstra <peterz@infradead.org>,
Thomas Gleixner <tglx@linutronix.de>
Subject: Re: [PATCH 09/19] arm64: Exclude nohz_full CPUs from 32bits el0 support
Date: Sun, 5 Jan 2025 00:18:40 +0100 [thread overview]
Message-ID: <Z3nB0LTdxAp2pPGU@pavilion.home> (raw)
In-Reply-To: <20250103152043.GA3816@willie-the-truck>
Le Fri, Jan 03, 2025 at 03:20:44PM +0000, Will Deacon a écrit :
> On Wed, Dec 11, 2024 at 04:40:22PM +0100, Frederic Weisbecker wrote:
> > +NOHZ FULL
> > +--------
> > +
> > +Nohz full CPUs are not a desirable fallback target to run 32bits el0
> > +applications. If present, a set of housekeeping CPUs that can do
> > +the job instead is preferred. Otherwise 32-bit EL0 is not supported.
> > +Should the need arise, appropriate support can be introduced in the
> > +future.
>
> I think we can probably word this slightly better. How about something
> more along these lines?
>
> To avoid perturbing an adaptive-ticks CPU (specified using
> ``nohz_full=``) when a 32-bit task is forcefully migrated, these CPUs
> are treated as 64-bit-only when support for asymmetric 32-bit systems
> is enabled.
Indeed!
>
> > diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
> > index 6ce71f444ed8..7ce1b8ab417f 100644
> > --- a/arch/arm64/kernel/cpufeature.c
> > +++ b/arch/arm64/kernel/cpufeature.c
> > @@ -75,6 +75,7 @@
> > #include <linux/cpu.h>
> > #include <linux/kasan.h>
> > #include <linux/percpu.h>
> > +#include <linux/sched/isolation.h>
> >
> > #include <asm/cpu.h>
> > #include <asm/cpufeature.h>
> > @@ -3742,7 +3743,10 @@ static int enable_mismatched_32bit_el0(unsigned int cpu)
> > static int lucky_winner = -1;
> >
> > struct cpuinfo_arm64 *info = &per_cpu(cpu_data, cpu);
> > - bool cpu_32bit = id_aa64pfr0_32bit_el0(info->reg_id_aa64pfr0);
> > + bool cpu_32bit = false;
> > +
> > + if (id_aa64pfr0_32bit_el0(info->reg_id_aa64pfr0) && housekeeping_cpu(cpu, HK_TYPE_TICK))
> > + cpu_32bit = true;
>
> I think it would be helpful to emit a diagnostic when a 32-bit CPU is
> ignored because of the housekeeping check. e.g.
>
>
> if (id_aa64pfr0_32bit_el0(info->reg_id_aa64pfr0)) {
> if (!housekeeping_cpu(cpu, HK_TYPE_TICK))
> pr_info("Treating adaptive-ticks CPU %u as 64-bit only\n", cpu);
> else
> cpu_32bit = true;
> }
>
>
> It's a bit of a bummer that this will fire on hardware that isn't
> asymmetric, but I suppose that's easily resolved by not passing the
> 'allow_mismatched_32bit_el0' option in that case.
Right! How is the following updated version?
---
From: Frederic Weisbecker <frederic@kernel.org>
Date: Fri, 25 Oct 2024 00:12:59 +0200
Subject: [PATCH 1/2] arm64: Exclude nohz_full CPUs from 32bits el0 support
Nohz full CPUs are not a desirable fallback target to run 32bits el0
applications. If present, prefer a set of housekeeping CPUs that can do
the job instead. Otherwise just don't support el0 32 bits. Should the
need arise, appropriate support can be introduced in the future.
Suggested-by: Will Deacon <will@kernel.org>
Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
---
Documentation/arch/arm64/asymmetric-32bit.rst | 8 ++++++++
arch/arm64/kernel/cpufeature.c | 10 +++++++++-
2 files changed, 17 insertions(+), 1 deletion(-)
diff --git a/Documentation/arch/arm64/asymmetric-32bit.rst b/Documentation/arch/arm64/asymmetric-32bit.rst
index 64a0b505da7d..1ca2b359a907 100644
--- a/Documentation/arch/arm64/asymmetric-32bit.rst
+++ b/Documentation/arch/arm64/asymmetric-32bit.rst
@@ -153,3 +153,11 @@ asymmetric system, a broken guest at EL1 could still attempt to execute
mode will return to host userspace with an ``exit_reason`` of
``KVM_EXIT_FAIL_ENTRY`` and will remain non-runnable until successfully
re-initialised by a subsequent ``KVM_ARM_VCPU_INIT`` operation.
+
+NOHZ FULL
+---------
+
+To avoid perturbing an adaptive-ticks CPU (specified using
+``nohz_full=``) when a 32-bit task is forcefully migrated, these CPUs
+are treated as 64-bit-only when support for asymmetric 32-bit systems
+is enabled.
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 6ce71f444ed8..3c87659c14db 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -75,6 +75,7 @@
#include <linux/cpu.h>
#include <linux/kasan.h>
#include <linux/percpu.h>
+#include <linux/sched/isolation.h>
#include <asm/cpu.h>
#include <asm/cpufeature.h>
@@ -3742,7 +3743,14 @@ static int enable_mismatched_32bit_el0(unsigned int cpu)
static int lucky_winner = -1;
struct cpuinfo_arm64 *info = &per_cpu(cpu_data, cpu);
- bool cpu_32bit = id_aa64pfr0_32bit_el0(info->reg_id_aa64pfr0);
+ bool cpu_32bit = false;
+
+ if (id_aa64pfr0_32bit_el0(info->reg_id_aa64pfr0)) {
+ if (!housekeeping_cpu(cpu, HK_TYPE_TICK))
+ pr_info("Treating adaptive-ticks CPU %u as 64-bit only\n", cpu);
+ else
+ cpu_32bit = true;
+ }
if (cpu_32bit) {
cpumask_set_cpu(cpu, cpu_32bit_el0_mask);
--
2.46.0
next prev parent reply other threads:[~2025-01-04 23:18 UTC|newest]
Thread overview: 33+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-12-11 15:40 [PATCH 00/19] kthread: Introduce preferred affinity v6 Frederic Weisbecker
2024-12-11 15:40 ` [PATCH 01/19] arm/bL_switcher: Use kthread_run_on_cpu() Frederic Weisbecker
2024-12-11 15:40 ` [PATCH 02/19] firmware: stratix10-svc: " Frederic Weisbecker
2024-12-17 0:37 ` Dinh Nguyen
2024-12-11 15:40 ` [PATCH 03/19] scsi: bnx2fc: Use kthread_create_on_cpu() Frederic Weisbecker
2025-01-02 17:54 ` Martin K. Petersen
2024-12-11 15:40 ` [PATCH 04/19] scsi: bnx2i: " Frederic Weisbecker
2025-01-02 17:55 ` Martin K. Petersen
2024-12-11 15:40 ` [PATCH 05/19] scsi: qedi: " Frederic Weisbecker
2025-01-02 17:55 ` Martin K. Petersen
2024-12-11 15:40 ` [PATCH 06/19] soc/qman: test: Use kthread_run_on_cpu() Frederic Weisbecker
2024-12-13 7:27 ` LEROY Christophe
2024-12-13 11:46 ` Frederic Weisbecker
2024-12-11 15:40 ` [PATCH 07/19] kallsyms: " Frederic Weisbecker
2024-12-11 15:40 ` [PATCH 08/19] lib: test_objpool: " Frederic Weisbecker
2024-12-11 15:40 ` [PATCH 09/19] arm64: Exclude nohz_full CPUs from 32bits el0 support Frederic Weisbecker
2025-01-03 15:20 ` Will Deacon
2025-01-04 23:18 ` Frederic Weisbecker [this message]
2025-01-08 15:49 ` Will Deacon
2024-12-11 15:40 ` [PATCH 10/19] sched,arm64: Handle CPU isolation on last resort fallback rq selection Frederic Weisbecker
2025-01-03 15:27 ` Will Deacon
2025-01-04 23:22 ` Frederic Weisbecker
2025-01-08 15:50 ` Will Deacon
2024-12-11 15:40 ` [PATCH 11/19] kthread: Make sure kthread hasn't started while binding it Frederic Weisbecker
2024-12-11 15:40 ` [PATCH 12/19] kthread: Default affine kthread to its preferred NUMA node Frederic Weisbecker
2024-12-11 15:40 ` [PATCH 13/19] mm: Create/affine kcompactd to its preferred node Frederic Weisbecker
2024-12-11 15:40 ` [PATCH 14/19] mm: Create/affine kswapd " Frederic Weisbecker
2024-12-11 15:40 ` [PATCH 15/19] kthread: Implement preferred affinity Frederic Weisbecker
2024-12-11 15:40 ` [PATCH 16/19] rcu: Use kthread preferred affinity for RCU boost Frederic Weisbecker
2024-12-11 15:40 ` [PATCH 17/19] kthread: Unify kthread_create_on_cpu() and kthread_create_worker_on_cpu() automatic format Frederic Weisbecker
2024-12-11 15:40 ` [PATCH 18/19] treewide: Introduce kthread_run_worker[_on_cpu]() Frederic Weisbecker
2024-12-11 15:40 ` [PATCH 19/19] rcu: Use kthread preferred affinity for RCU exp kworkers Frederic Weisbecker
2025-01-10 21:16 ` (subset) [PATCH 00/19] kthread: Introduce preferred affinity v6 Martin K. Petersen
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=Z3nB0LTdxAp2pPGU@pavilion.home \
--to=frederic@kernel.org \
--cc=akpm@linux-foundation.org \
--cc=ardb@kernel.org \
--cc=catalin.marinas@arm.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mark.rutland@arm.com \
--cc=maz@kernel.org \
--cc=oliver.upton@linux.dev \
--cc=peterz@infradead.org \
--cc=tglx@linutronix.de \
--cc=will@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox