From c38fcb5dc35986b8a93bf2107f800a890e2cea9b Mon Sep 17 00:00:00 2001
From: cinap_lenrek <cinap_lenrek@felloff.net>
Date: Fri, 23 Jul 2021 15:10:01 +0000
Subject: [PATCH] arm64: use generic timer virtual counter for cycles()

We used to use performance cycle counter for cycles(),
but it is kind of useless in userspace as each core
has its own counter and hence not comparable between
cores. Also, the cycle counter stops counting when
the cores are idle.

Most callers expect cycles() to return a high resolution
timestamp instead, so do the best we can do here
and enable the userspace generic timer virtual counter.
---
 sys/man/2/cputime           |  1 +
 sys/src/9/bcm64/clock.c     | 19 ++++++++++++++++---
 sys/src/9/bcm64/sysreg.h    |  2 ++
 sys/src/libc/arm64/cycles.s |  4 ++--
 4 files changed, 21 insertions(+), 5 deletions(-)

diff --git a/sys/man/2/cputime b/sys/man/2/cputime
index 4d6440116..282e93ade 100644
--- a/sys/man/2/cputime
+++ b/sys/man/2/cputime
@@ -39,6 +39,7 @@ if any, and stores it via
 Currently supported architectures are
 .BR 386 ,
 .BR amd64 ,
+.B arm64
 and
 .BR power ;
 on all others,
diff --git a/sys/src/9/bcm64/clock.c b/sys/src/9/bcm64/clock.c
index f7b3e55f7..f5fcc4784 100644
--- a/sys/src/9/bcm64/clock.c
+++ b/sys/src/9/bcm64/clock.c
@@ -2,14 +2,14 @@
  * bcm283[56] timers
  *	System timers run at 1MHz (timers 1 and 2 are used by GPU)
  *	ARM timer usually runs at 250MHz (may be slower in low power modes)
- *	Cycle counter runs at 700MHz (unless overclocked)
  *    All are free-running up-counters
  *
  * Use system timer 3 (64 bits) for hzclock interrupts and fastticks
  *   For smp on bcm2836, use local generic timer for interrupts on cpu1-3
  * Use ARM timer (32 bits) for perfticks
  * Use ARM timer to force immediate interrupt
- * Use cycle counter for cycles()
+ * Use performance cycle counter for lcycles()
+ * Use generic timer virtual counter for cycles()
  */
 
 #include "u.h"
@@ -118,6 +118,7 @@ clockinit(void)
 	syswr(PMCR_EL0, 1<<6 | 7);
 	syswr(PMCNTENSET, 1<<31);
 	syswr(PMUSERENR_EL0, 1<<2);
+	syswr(CNTKCTL_EL1, 1<<1);
 
 	syswr(CNTP_TVAL_EL0, ~0UL);
 	if(m->machno == 0){
@@ -147,7 +148,19 @@ clockinit(void)
 	t1 -= t0;
 	m->cpuhz = 100 * t1;
 	m->cpumhz = (m->cpuhz + Mhz/2 - 1) / Mhz;
-	m->cyclefreq = m->cpuhz;
+
+	/*
+	 * Cyclefreq used to be the same as cpuhz as
+	 * we where using the PMCCNTR_EL0 which counts
+	 * per core cpu cycles. But is is kind of useless
+	 * in userspace because each core has a differnet
+	 * counter and it stops when the core is idle (WFI).
+	 * So we change it to use the generic timer
+	 * virtual counter register CNTVCT_EL0 instead
+	 * running at the same frequency as system timer.
+	 * (CNTFRQ_EL0 is WRONG on raspberry pi).
+	 */
+	m->cyclefreq = SystimerFreq;
 
 	if(m->machno == 0){
 		tn->cs = 1<<3;
diff --git a/sys/src/9/bcm64/sysreg.h b/sys/src/9/bcm64/sysreg.h
index c057bbba8..0d9b1b172 100644
--- a/sys/src/9/bcm64/sysreg.h
+++ b/sys/src/9/bcm64/sysreg.h
@@ -32,6 +32,8 @@
 #define PMUSERENR_EL0			SYSREG(3,3,9,14,0)
 
 #define CNTPCT_EL0			SYSREG(3,3,14,0,1)
+#define CNTVCT_EL0			SYSREG(3,3,14,0,2)
+#define CNTKCTL_EL1			SYSREG(3,0,14,1,0)
 #define CNTP_TVAL_EL0			SYSREG(3,3,14,2,0)
 #define CNTP_CTL_EL0			SYSREG(3,3,14,2,1)
 #define CNTP_CVAL_EL0			SYSREG(3,3,14,2,2)
diff --git a/sys/src/libc/arm64/cycles.s b/sys/src/libc/arm64/cycles.s
index 389ea201f..03955b9ad 100644
--- a/sys/src/libc/arm64/cycles.s
+++ b/sys/src/libc/arm64/cycles.s
@@ -1,7 +1,7 @@
 #define	SYSREG(op0,op1,Cn,Cm,op2)	SPR(((op0)<<19|(op1)<<16|(Cn)<<12|(Cm)<<8|(op2)<<5))
-#define PMCCNTR_EL0			SYSREG(3,3,9,13,0)
+#define CNTVCT_EL0			SYSREG(3,3,14,0,2)
 
 TEXT cycles(SB), 1, $-4
-	MRS	PMCCNTR_EL0, R1
+	MRS	CNTVCT_EL0, R1
 	MOV	R1, (R0)
 	RETURN