From: Ankur Arora <ankur.a.arora@oracle.com>
To: linux-kernel@vger.kernel.org, linux-arch@vger.kernel.org,
linux-arm-kernel@lists.infradead.org, linux-pm@vger.kernel.org,
bpf@vger.kernel.org
Cc: arnd@arndb.de, catalin.marinas@arm.com, will@kernel.org,
peterz@infradead.org, akpm@linux-foundation.org,
mark.rutland@arm.com, harisokn@amazon.com, cl@gentwo.org,
ast@kernel.org, rafael@kernel.org, daniel.lezcano@linaro.org,
memxor@gmail.com, zhenglifeng1@huawei.com,
xueshuai@linux.alibaba.com, rdunlap@infradead.org,
david.laight.linux@gmail.com, broonie@kernel.org,
joao.m.martins@oracle.com, boris.ostrovsky@oracle.com,
konrad.wilk@oracle.com, ashok.bhat@arm.com,
Ankur Arora <ankur.a.arora@oracle.com>,
Bjorn Andersson <andersson@kernel.org>,
Konrad Dybcio <konradybcio@kernel.org>,
Christoph Lameter <cl@linux.com>
Subject: [PATCH v15 03/16] arm64/delay: move, fixup usecs_to_cycles()
Date: Mon, 31 Aug 2026 13:22:38 -0700 [thread overview]
Message-ID: <20260831202251.305046-4-ankur.a.arora@oracle.com> (raw)
In-Reply-To: <20260831202251.305046-1-ankur.a.arora@oracle.com>
Update xloops_to_cycles() to use mul_u64_u64_shr() instead of 32-bit
fixed point arithmetic to avoid truncation for delay values larger
than ~10s. This adds an extra mul operation but since xloops_to_cycles()
is only used from delay loops so shouldn't matter too much.
Also move some related constants and functions related to the cycles
computation out to a new header (converting some from macros to static
inlines). And finally make __delay_cycles() available outside of
arch/arm64/lib/delay.c.
Rename some macros in qcom/rpmh-rsc.c which were occupying the same
namespace.
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: Bjorn Andersson <andersson@kernel.org>
Cc: Konrad Dybcio <konradybcio@kernel.org>
Cc: linux-arm-kernel@lists.infradead.org
Reviewed-by: Christoph Lameter <cl@linux.com>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Ankur Arora <ankur.a.arora@oracle.com>
---
Notes:
- convert the multiply, shift operation to use mul_u64_u64_shr()
to avoid truncating large delay values.
- makes usecs_to_cycles(), nsecs_to_cycles() static inlines.
arch/arm64/include/asm/delay-const.h | 35 ++++++++++++++++++++++++++++
arch/arm64/lib/delay.c | 17 ++++----------
drivers/soc/qcom/rpmh-rsc.c | 8 +++----
3 files changed, 44 insertions(+), 16 deletions(-)
create mode 100644 arch/arm64/include/asm/delay-const.h
diff --git a/arch/arm64/include/asm/delay-const.h b/arch/arm64/include/asm/delay-const.h
new file mode 100644
index 000000000000..6ccdfe0a4130
--- /dev/null
+++ b/arch/arm64/include/asm/delay-const.h
@@ -0,0 +1,35 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef _ASM_DELAY_CONST_H
+#define _ASM_DELAY_CONST_H
+
+#include <linux/math64.h>
+#include <linux/types.h>
+#include <asm/param.h> /* For HZ */
+
+/* 2**32 / 1000000 (rounded up) */
+#define __usecs_to_xloops_mult 0x10C7UL
+
+/* 2**32 / 1000000000 (rounded up) */
+#define __nsecs_to_xloops_mult 0x5UL
+
+extern unsigned long loops_per_jiffy;
+static inline u64 xloops_to_cycles(u64 xloops)
+{
+ u64 loops_per_sec = (u64)loops_per_jiffy * HZ;
+
+ return mul_u64_u64_shr(xloops, loops_per_sec, 32);
+}
+
+static inline u64 usecs_to_cycles(u64 time_usecs)
+{
+ return xloops_to_cycles(time_usecs * __usecs_to_xloops_mult);
+}
+
+static inline u64 nsecs_to_cycles(u64 time_nsecs)
+{
+ return xloops_to_cycles((time_nsecs) * __nsecs_to_xloops_mult);
+}
+
+u64 notrace __delay_cycles(void);
+
+#endif /* _ASM_DELAY_CONST_H */
diff --git a/arch/arm64/lib/delay.c b/arch/arm64/lib/delay.c
index e278e060e78a..f08eacef2f0a 100644
--- a/arch/arm64/lib/delay.c
+++ b/arch/arm64/lib/delay.c
@@ -12,17 +12,10 @@
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/timex.h>
+#include <asm/delay-const.h>
#include <clocksource/arm_arch_timer.h>
-#define USECS_TO_CYCLES(time_usecs) \
- xloops_to_cycles((time_usecs) * 0x10C7UL)
-
-static inline unsigned long xloops_to_cycles(unsigned long xloops)
-{
- return (xloops * loops_per_jiffy * HZ) >> 32;
-}
-
/*
* Force the use of CNTVCT_EL0 in order to have the same base as WFxT.
* This avoids some annoying issues when CNTVOFF_EL2 is not reset 0 on a
@@ -32,7 +25,7 @@ static inline unsigned long xloops_to_cycles(unsigned long xloops)
* Note that userspace cannot change the offset behind our back either,
* as the vcpu mutex is held as long as KVM_RUN is in progress.
*/
-static cycles_t notrace __delay_cycles(void)
+u64 notrace __delay_cycles(void)
{
guard(preempt_notrace)();
return __arch_counter_get_cntvct_stable();
@@ -54,7 +47,7 @@ void __delay(unsigned long cycles)
wfet(end);
} else if (arch_timer_evtstrm_available()) {
const cycles_t timer_evt_period =
- USECS_TO_CYCLES(ARCH_TIMER_EVT_STREAM_PERIOD_US);
+ usecs_to_cycles(ARCH_TIMER_EVT_STREAM_PERIOD_US);
while ((__delay_cycles() - start + timer_evt_period) < cycles)
wfe();
@@ -73,12 +66,12 @@ EXPORT_SYMBOL(__const_udelay);
void __udelay(unsigned long usecs)
{
- __const_udelay(usecs * 0x10C7UL); /* 2**32 / 1000000 (rounded up) */
+ __const_udelay(usecs * __usecs_to_xloops_mult);
}
EXPORT_SYMBOL(__udelay);
void __ndelay(unsigned long nsecs)
{
- __const_udelay(nsecs * 0x5UL); /* 2**32 / 1000000000 (rounded up) */
+ __const_udelay(nsecs * __nsecs_to_xloops_mult);
}
EXPORT_SYMBOL(__ndelay);
diff --git a/drivers/soc/qcom/rpmh-rsc.c b/drivers/soc/qcom/rpmh-rsc.c
index f881af35ecfc..c9a814d9e06f 100644
--- a/drivers/soc/qcom/rpmh-rsc.c
+++ b/drivers/soc/qcom/rpmh-rsc.c
@@ -146,10 +146,10 @@ enum {
* +---------------------------------------------------+
*/
-#define USECS_TO_CYCLES(time_usecs) \
- xloops_to_cycles((time_usecs) * 0x10C7UL)
+#define RPMH_USECS_TO_CYCLES(time_usecs) \
+ rpmh_xloops_to_cycles((time_usecs) * 0x10C7UL)
-static inline unsigned long xloops_to_cycles(u64 xloops)
+static inline unsigned long rpmh_xloops_to_cycles(u64 xloops)
{
return (xloops * loops_per_jiffy * HZ) >> 32;
}
@@ -828,7 +828,7 @@ void rpmh_rsc_write_next_wakeup(struct rsc_drv *drv)
wakeup_us = ktime_to_us(wakeup);
/* Convert the wakeup to arch timer scale */
- wakeup_cycles = USECS_TO_CYCLES(wakeup_us);
+ wakeup_cycles = RPMH_USECS_TO_CYCLES(wakeup_us);
wakeup_cycles += arch_timer_read_counter();
exit:
--
2.43.7
next prev parent reply other threads:[~2026-08-31 20:23 UTC|newest]
Thread overview: 25+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-08-31 20:22 [PATCH v15 00/16] barrier: Add smp_cond_load_{relaxed,acquire}_timeout() Ankur Arora
2026-08-31 20:22 ` [PATCH v15 01/16] asm-generic: barrier: Add smp_cond_load_relaxed_timeout() Ankur Arora
2026-08-31 20:22 ` [PATCH v15 02/16] arm64: barrier: Support smp_cond_load_relaxed_timeout() Ankur Arora
2026-08-31 20:22 ` Ankur Arora [this message]
2026-08-31 20:22 ` [PATCH v15 04/16] arm64: support WFET in smp_cond_load_relaxed_timeout() Ankur Arora
2026-08-31 21:16 ` bot+bpf-ci
2026-08-31 20:22 ` [PATCH v15 05/16] arm64: rqspinlock: Remove private copy of smp_cond_load_acquire_timewait() Ankur Arora
2026-08-31 20:22 ` [PATCH v15 06/16] asm-generic: barrier: Add smp_cond_load_acquire_timeout() Ankur Arora
2026-08-31 21:17 ` bot+bpf-ci
2026-08-31 20:22 ` [PATCH v15 07/16] atomic: Add atomic_cond_read_*_timeout() Ankur Arora
2026-08-31 21:16 ` bot+bpf-ci
2026-08-31 20:22 ` [PATCH v15 08/16] locking/atomic: scripts: build atomic_long_cond_read_*_timeout() Ankur Arora
2026-08-31 20:22 ` [PATCH v15 09/16] bpf/rqspinlock: switch check_timeout() to a clock interface Ankur Arora
2026-08-31 21:16 ` bot+bpf-ci
2026-08-31 20:22 ` [PATCH v15 10/16] bpf/rqspinlock: Use smp_cond_load_acquire_timeout() Ankur Arora
2026-08-31 21:31 ` bot+bpf-ci
2026-08-31 20:22 ` [PATCH v15 11/16] sched: add need-resched timed wait interface Ankur Arora
2026-08-31 20:22 ` [PATCH v15 12/16] cpuidle/poll_state: Wait for need-resched via tif_need_resched_relaxed_wait() Ankur Arora
2026-08-31 20:22 ` [PATCH v15 13/16] arm64/delay: enable testing smp_cond_load_relaxed_timeout() Ankur Arora
2026-08-31 21:16 ` bot+bpf-ci
2026-08-31 20:22 ` [PATCH v15 14/16] barrier: add tests for smp_cond_load_*_timeout() Ankur Arora
2026-08-31 21:17 ` bot+bpf-ci
2026-08-31 20:22 ` [PATCH v15 15/16] barrier: timeout validity checks for smp_cond_load_relaxed_timeout() Ankur Arora
2026-08-31 21:16 ` bot+bpf-ci
2026-08-31 20:22 ` [PATCH v15 16/16] barrier: timeout validity checks for smp_cond_load_acquire_timeout() Ankur Arora
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=20260831202251.305046-4-ankur.a.arora@oracle.com \
--to=ankur.a.arora@oracle.com \
--cc=akpm@linux-foundation.org \
--cc=andersson@kernel.org \
--cc=arnd@arndb.de \
--cc=ashok.bhat@arm.com \
--cc=ast@kernel.org \
--cc=boris.ostrovsky@oracle.com \
--cc=bpf@vger.kernel.org \
--cc=broonie@kernel.org \
--cc=catalin.marinas@arm.com \
--cc=cl@gentwo.org \
--cc=cl@linux.com \
--cc=daniel.lezcano@linaro.org \
--cc=david.laight.linux@gmail.com \
--cc=harisokn@amazon.com \
--cc=joao.m.martins@oracle.com \
--cc=konrad.wilk@oracle.com \
--cc=konradybcio@kernel.org \
--cc=linux-arch@vger.kernel.org \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-pm@vger.kernel.org \
--cc=mark.rutland@arm.com \
--cc=memxor@gmail.com \
--cc=peterz@infradead.org \
--cc=rafael@kernel.org \
--cc=rdunlap@infradead.org \
--cc=will@kernel.org \
--cc=xueshuai@linux.alibaba.com \
--cc=zhenglifeng1@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