[PATCH v15 03/16] arm64/delay: move, fixup usecs_to_cycles()

[Ankur Arora]

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@xxxxxxx>
Cc: Will Deacon <will@xxxxxxxxxx>
Cc: Bjorn Andersson <andersson@xxxxxxxxxx>
Cc: Konrad Dybcio <konradybcio@xxxxxxxxxx>
Cc: linux-arm-kernel@xxxxxxxxxxxxxxxxxxx
Reviewed-by: Christoph Lameter <cl@xxxxxxxxx>
Acked-by: Catalin Marinas <catalin.marinas@xxxxxxx>
Signed-off-by: Ankur Arora <ankur.a.arora@xxxxxxxxxx>
---
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