Re: [PATCH v15 12/16] cpuidle/poll_state: Wait for need-resched via tif_need_resched_relaxed_wait()
From: Haris Okanovic <hidden>
Date: 2026-09-10 23:04:49
Also in:
bpf, linux-arch, linux-arm-kernel, lkml
On Mon, 31 Aug 2026 13:22:47 -0700, Ankur Arora [off-list ref] wrote:
quoted hunk ↗ jump to hunk
diff --git a/drivers/cpuidle/poll_state.c b/drivers/cpuidle/poll_state.c index c7524e4c522a2..7443b3e971baf 100644 --- a/drivers/cpuidle/poll_state.c +++ b/drivers/cpuidle/poll_state.c@@ -6,41 +6,22 @@[ ... skip 36 lines ... ] - } - } + dev->poll_time_limit = !tif_need_resched_relaxed_wait(limit); } raw_local_irq_disable();
Tested again on AWS Graviton3/4/5 (ARM Neoverse V1/V2/V3) with haltpoll changes atop latest master 8ab1afb2e: still seeing average 6% improvement across various workloads (mysql, postgresql, cassandra, memcached) in latency sensitive configuration. The new unit tests all pass on both metal and virt variants of the same machines. I hope we can merge this soon. Tested-by: Haris Okanovic <redacted> -- Haris Okanovic AWS Graviton