public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Peter Zijlstra <peterz@infradead.org>
To: mingo@kernel.org
Cc: peterz@infradead.org, juri.lelli@redhat.com,
	vincent.guittot@linaro.org, dietmar.eggemann@arm.com,
	rostedt@goodmis.org, bsegall@google.com, mgorman@suse.de,
	vschneid@redhat.com, linux-kernel@vger.kernel.org,
	wangtao554@huawei.com, quzicheng@huawei.com,
	kprateek.nayak@amd.com, dsmythies@telus.net,
	shubhang@os.amperecomputing.com
Subject: [PATCH v2 7/7] sched/fair: Use full weight to __calc_delta()
Date: Thu, 19 Feb 2026 08:58:47 +0100	[thread overview]
Message-ID: <20260219080625.183283814@infradead.org> (raw)
In-Reply-To: 20260219075840.162631716@infradead.org

Since we now use the full weight for avg_vruntime(), also make
__calc_delta() use the full value.

Since weight is effectively NICE_0_LOAD, this is 20 bits on 64bit.
This leaves 44 bits for delta_exec, which is ~16k seconds, way longer
than any one tick would ever be, so no worry about overflow.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: K Prateek Nayak <kprateek.nayak@amd.com>
Tested-by: Shubhang Kaushik <shubhang@os.amperecomputing.com>
---
 kernel/sched/fair.c |    7 +++++++
 1 file changed, 7 insertions(+)

--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -225,6 +225,7 @@ void __init sched_init_granularity(void)
 	update_sysctl();
 }
 
+#ifndef CONFIG_64BIT
 #define WMULT_CONST	(~0U)
 #define WMULT_SHIFT	32
 
@@ -283,6 +284,12 @@ static u64 __calc_delta(u64 delta_exec,
 
 	return mul_u64_u32_shr(delta_exec, fact, shift);
 }
+#else
+static u64 __calc_delta(u64 delta_exec, unsigned long weight, struct load_weight *lw)
+{
+	return (delta_exec * weight) / lw->weight;
+}
+#endif
 
 /*
  * delta /= w



  parent reply	other threads:[~2026-02-19  8:11 UTC|newest]

Thread overview: 55+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-02-19  7:58 [PATCH v2 0/7] sched: Various reweight_entity() fixes Peter Zijlstra
2026-02-19  7:58 ` [PATCH v2 1/7] sched/fair: Fix zero_vruntime tracking Peter Zijlstra
2026-02-23 10:56   ` Vincent Guittot
2026-02-23 13:09   ` Dietmar Eggemann
2026-02-23 14:15     ` Peter Zijlstra
2026-02-24  8:53       ` Dietmar Eggemann
2026-02-24  9:02         ` Peter Zijlstra
2026-03-28  5:44   ` John Stultz
2026-03-28 17:04     ` Steven Rostedt
2026-03-30 17:58       ` John Stultz
2026-03-30 18:27         ` Steven Rostedt
2026-03-30  9:43     ` Peter Zijlstra
2026-03-30 17:49       ` John Stultz
2026-03-30 10:10     ` Peter Zijlstra
2026-03-30 14:37       ` K Prateek Nayak
2026-03-30 14:40         ` Peter Zijlstra
2026-03-30 15:50           ` K Prateek Nayak
2026-03-30 19:11             ` Peter Zijlstra
2026-03-31  0:38               ` K Prateek Nayak
2026-03-31  4:58                 ` K Prateek Nayak
2026-03-31  7:08                 ` Peter Zijlstra
2026-03-31  7:14                   ` Peter Zijlstra
2026-03-31  8:49                     ` K Prateek Nayak
2026-03-31  9:29                       ` Peter Zijlstra
2026-03-31 12:20                         ` Peter Zijlstra
2026-03-31 16:14                           ` Peter Zijlstra
2026-03-31 17:02                             ` K Prateek Nayak
2026-03-31 22:40                             ` John Stultz
2026-03-30 19:40       ` John Stultz
2026-03-30 19:43         ` Peter Zijlstra
2026-03-30 21:45           ` John Stultz
2026-02-19  7:58 ` [PATCH v2 2/7] sched/fair: Only set slice protection at pick time Peter Zijlstra
2026-02-19  7:58 ` [PATCH v2 3/7] sched/eevdf: Update se->vprot in reweight_entity() Peter Zijlstra
2026-02-19  7:58 ` [PATCH v2 4/7] sched/fair: Fix lag clamp Peter Zijlstra
2026-02-23 10:23   ` Dietmar Eggemann
2026-02-23 10:57   ` Vincent Guittot
2026-02-19  7:58 ` [PATCH v2 5/7] sched/fair: Increase weight bits for avg_vruntime Peter Zijlstra
2026-02-23 10:56   ` Vincent Guittot
2026-02-23 11:51     ` Peter Zijlstra
2026-02-23 12:36       ` Peter Zijlstra
2026-02-23 13:06       ` Vincent Guittot
2026-03-30  7:55       ` K Prateek Nayak
2026-03-30  9:27         ` Peter Zijlstra
2026-04-02  5:28         ` K Prateek Nayak
2026-04-02 10:22           ` Peter Zijlstra
2026-04-02 10:56             ` K Prateek Nayak
2026-04-03  4:02               ` K Prateek Nayak
2026-04-07 12:00                 ` Peter Zijlstra
2026-04-07 13:42                   ` [tip: sched/core] sched/fair: Avoid overflow in enqueue_entity() tip-bot2 for K Prateek Nayak
2026-02-19  7:58 ` [PATCH v2 6/7] sched/fair: Revert 6d71a9c61604 ("sched/fair: Fix EEVDF entity placement bug causing scheduling lag") Peter Zijlstra
2026-02-23 10:57   ` Vincent Guittot
2026-03-24 10:01     ` William Montaz
2026-04-07 13:45       ` Peter Zijlstra
2026-02-19  7:58 ` Peter Zijlstra [this message]
2026-02-23 10:57   ` [PATCH v2 7/7] sched/fair: Use full weight to __calc_delta() Vincent Guittot

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=20260219080625.183283814@infradead.org \
    --to=peterz@infradead.org \
    --cc=bsegall@google.com \
    --cc=dietmar.eggemann@arm.com \
    --cc=dsmythies@telus.net \
    --cc=juri.lelli@redhat.com \
    --cc=kprateek.nayak@amd.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mgorman@suse.de \
    --cc=mingo@kernel.org \
    --cc=quzicheng@huawei.com \
    --cc=rostedt@goodmis.org \
    --cc=shubhang@os.amperecomputing.com \
    --cc=vincent.guittot@linaro.org \
    --cc=vschneid@redhat.com \
    --cc=wangtao554@huawei.com \
    /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