* [PATCHv3 1/4] ARM: Translate delay.S into (mostly) C
2010-12-08 4:38 [PATCHv3 0/4] ARM: Fixing udelay() for SMP and non-SMP systems Stephen Boyd
@ 2010-12-08 4:38 ` Stephen Boyd
2010-12-08 4:38 ` [PATCHv3 2/4] ARM: Allow machines to override __delay() Stephen Boyd
` (2 subsequent siblings)
3 siblings, 0 replies; 10+ messages in thread
From: Stephen Boyd @ 2010-12-08 4:38 UTC (permalink / raw)
To: linux-arm-kernel
We want to allow machines to override the __delay() implementation
at runtime so they can use a timer based __delay() routine. It's
easier to do this using C, so let's write udelay and friends in C.
We lose the #if 0 code, which according to Russell is used "to
make the delay loop more stable and predictable on older CPUs"
(see http://article.gmane.org/gmane.linux.kernel/888867 for more
info). We shouldn't be too worried though, since we'll soon add
functionality allowing a machine to set the __delay() loop
themselves, thus allowing machines to resurrect the commented out
code should they need it.
Nico expressed concern that fixed lpj cmdlines will break due to
compiler optimizations. That doesn't seem to be the case since
before and after this patch I get the same lpj value when running
my CPU at 19.2 MHz. That should be sufficiently slow enough to
cover any machine running Linux.
Signed-off-by: Stephen Boyd <sboyd@codeaurora.org>
Reviewed-by: Saravana Kannan <skannan@codeaurora.org>
Acked-by: Nicolas Pitre <nicolas.pitre@linaro.org>
---
arch/arm/include/asm/delay.h | 2 +-
arch/arm/kernel/armksyms.c | 4 --
arch/arm/lib/delay.S | 65 ------------------------------------------
arch/arm/lib/delay.c | 56 ++++++++++++++++++++++++++++++++++++
4 files changed, 57 insertions(+), 70 deletions(-)
delete mode 100644 arch/arm/lib/delay.S
create mode 100644 arch/arm/lib/delay.c
diff --git a/arch/arm/include/asm/delay.h b/arch/arm/include/asm/delay.h
index b2deda1..ccc5ed5 100644
--- a/arch/arm/include/asm/delay.h
+++ b/arch/arm/include/asm/delay.h
@@ -8,7 +8,7 @@
#include <asm/param.h> /* HZ */
-extern void __delay(int loops);
+extern void __delay(unsigned long loops);
/*
* This function intentionally does not exist; if you see references to
diff --git a/arch/arm/kernel/armksyms.c b/arch/arm/kernel/armksyms.c
index e5e1e538..220dce6 100644
--- a/arch/arm/kernel/armksyms.c
+++ b/arch/arm/kernel/armksyms.c
@@ -52,10 +52,6 @@ extern void fpundefinstr(void);
EXPORT_SYMBOL(__backtrace);
- /* platform dependent support */
-EXPORT_SYMBOL(__udelay);
-EXPORT_SYMBOL(__const_udelay);
-
/* networking */
EXPORT_SYMBOL(csum_partial);
EXPORT_SYMBOL(csum_partial_copy_from_user);
diff --git a/arch/arm/lib/delay.S b/arch/arm/lib/delay.S
deleted file mode 100644
index 8d6a876..0000000
--- a/arch/arm/lib/delay.S
+++ /dev/null
@@ -1,65 +0,0 @@
-/*
- * linux/arch/arm/lib/delay.S
- *
- * Copyright (C) 1995, 1996 Russell King
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/linkage.h>
-#include <asm/assembler.h>
-#include <asm/param.h>
- .text
-
-.LC0: .word loops_per_jiffy
-.LC1: .word (2199023*HZ)>>11
-
-/*
- * r0 <= 2000
- * lpj <= 0x01ffffff (max. 3355 bogomips)
- * HZ <= 1000
- */
-
-ENTRY(__udelay)
- ldr r2, .LC1
- mul r0, r2, r0
-ENTRY(__const_udelay) @ 0 <= r0 <= 0x7fffff06
- ldr r2, .LC0
- ldr r2, [r2] @ max = 0x01ffffff
- mov r0, r0, lsr #14 @ max = 0x0001ffff
- mov r2, r2, lsr #10 @ max = 0x00007fff
- mul r0, r2, r0 @ max = 2^32-1
- movs r0, r0, lsr #6
- moveq pc, lr
-
-/*
- * loops = r0 * HZ * loops_per_jiffy / 1000000
- *
- * Oh, if only we had a cycle counter...
- */
-
-@ Delay routine
-ENTRY(__delay)
- subs r0, r0, #1
-#if 0
- movls pc, lr
- subs r0, r0, #1
- movls pc, lr
- subs r0, r0, #1
- movls pc, lr
- subs r0, r0, #1
- movls pc, lr
- subs r0, r0, #1
- movls pc, lr
- subs r0, r0, #1
- movls pc, lr
- subs r0, r0, #1
- movls pc, lr
- subs r0, r0, #1
-#endif
- bhi __delay
- mov pc, lr
-ENDPROC(__udelay)
-ENDPROC(__const_udelay)
-ENDPROC(__delay)
diff --git a/arch/arm/lib/delay.c b/arch/arm/lib/delay.c
new file mode 100644
index 0000000..f92aca0
--- /dev/null
+++ b/arch/arm/lib/delay.c
@@ -0,0 +1,56 @@
+/*
+ * Originally from linux/arch/arm/lib/delay.S
+ *
+ * Copyright (C) 1995, 1996 Russell King
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/module.h>
+#include <linux/delay.h>
+
+/*
+ * loops = usecs * HZ * loops_per_jiffy / 1000000
+ *
+ * Oh, if only we had a cycle counter...
+ */
+void __delay(unsigned long loops)
+{
+ asm volatile(
+ "1: subs %0, %0, #1 \n"
+ " bhi 1b \n"
+ : /* No output */
+ : "r" (loops)
+ );
+}
+EXPORT_SYMBOL(__delay);
+
+/*
+ * 0 <= xloops <= 0x7fffff06
+ * loops_per_jiffy <= 0x01ffffff (max. 3355 bogomips)
+ */
+void __const_udelay(unsigned long xloops)
+{
+ unsigned long lpj;
+ unsigned long loops;
+
+ xloops >>= 14; /* max = 0x01ffffff */
+ lpj = loops_per_jiffy >> 10; /* max = 0x0001ffff */
+ loops = lpj * xloops; /* max = 0x00007fff */
+ loops >>= 6; /* max = 2^32-1 */
+
+ if (likely(loops))
+ __delay(loops);
+}
+EXPORT_SYMBOL(__const_udelay);
+
+/*
+ * usecs <= 2000
+ * HZ <= 1000
+ */
+void __udelay(unsigned long usecs)
+{
+ __const_udelay(usecs * ((2199023*HZ)>>11));
+}
+EXPORT_SYMBOL(__udelay);
--
Sent by an employee of the Qualcomm Innovation Center, Inc.
The Qualcomm Innovation Center, Inc. is a member of the Code Aurora Forum.
^ permalink raw reply related [flat|nested] 10+ messages in thread* [PATCHv3 2/4] ARM: Allow machines to override __delay()
2010-12-08 4:38 [PATCHv3 0/4] ARM: Fixing udelay() for SMP and non-SMP systems Stephen Boyd
2010-12-08 4:38 ` [PATCHv3 1/4] ARM: Translate delay.S into (mostly) C Stephen Boyd
@ 2010-12-08 4:38 ` Stephen Boyd
2010-12-08 19:22 ` Daniel Walker
2010-12-08 4:38 ` [PATCHv3 3/4] ARM: Implement a timer based __delay() loop Stephen Boyd
2010-12-08 4:38 ` [PATCHv3 4/4] msm: timer: Migrate to timer based __delay() Stephen Boyd
3 siblings, 1 reply; 10+ messages in thread
From: Stephen Boyd @ 2010-12-08 4:38 UTC (permalink / raw)
To: linux-arm-kernel
Some machines want to implement their own __delay() routine based
on fixed rate timers. Expose functionality to set the __delay()
routine at runtime. This should allow two machines with different
__delay() routines to happily co-exist within the same kernel
with minimal overhead.
Russell expressed concern that using a timer based __delay()
would cause problems when an iomapped device isn't mapped in
prior to a delay call being made (see
http://article.gmane.org/gmane.linux.ports.arm.kernel/78543 for
more info). We can sidestep that issue with this approach since
the __delay() routine _should_ only be pointed to a timer based
delay once the timer has been properly mapped. Up until that
point __delay() and udelay() will use delay_loop() which is
always safe to call.
This patch is inspired by x86's delay.c
Signed-off-by: Stephen Boyd <sboyd@codeaurora.org>
---
arch/arm/include/asm/delay.h | 2 ++
arch/arm/lib/delay.c | 19 ++++++++++++++++---
2 files changed, 18 insertions(+), 3 deletions(-)
diff --git a/arch/arm/include/asm/delay.h b/arch/arm/include/asm/delay.h
index ccc5ed5..7c732b5 100644
--- a/arch/arm/include/asm/delay.h
+++ b/arch/arm/include/asm/delay.h
@@ -40,5 +40,7 @@ extern void __const_udelay(unsigned long);
__const_udelay((n) * ((2199023U*HZ)>>11))) : \
__udelay(n))
+extern void set_delay_fn(void (*fn)(unsigned long));
+
#endif /* defined(_ARM_DELAY_H) */
diff --git a/arch/arm/lib/delay.c b/arch/arm/lib/delay.c
index f92aca0..b38f7c0 100644
--- a/arch/arm/lib/delay.c
+++ b/arch/arm/lib/delay.c
@@ -11,11 +11,9 @@
#include <linux/delay.h>
/*
- * loops = usecs * HZ * loops_per_jiffy / 1000000
- *
* Oh, if only we had a cycle counter...
*/
-void __delay(unsigned long loops)
+void delay_loop(unsigned long loops)
{
asm volatile(
"1: subs %0, %0, #1 \n"
@@ -24,6 +22,21 @@ void __delay(unsigned long loops)
: "r" (loops)
);
}
+
+static void (*delay_fn)(unsigned long) = delay_loop;
+
+void set_delay_fn(void (*fn)(unsigned long))
+{
+ delay_fn = fn;
+}
+
+/*
+ * loops = usecs * HZ * loops_per_jiffy / 1000000
+ */
+void __delay(unsigned long loops)
+{
+ delay_fn(loops);
+}
EXPORT_SYMBOL(__delay);
/*
--
Sent by an employee of the Qualcomm Innovation Center, Inc.
The Qualcomm Innovation Center, Inc. is a member of the Code Aurora Forum.
^ permalink raw reply related [flat|nested] 10+ messages in thread* [PATCHv3 3/4] ARM: Implement a timer based __delay() loop
2010-12-08 4:38 [PATCHv3 0/4] ARM: Fixing udelay() for SMP and non-SMP systems Stephen Boyd
2010-12-08 4:38 ` [PATCHv3 1/4] ARM: Translate delay.S into (mostly) C Stephen Boyd
2010-12-08 4:38 ` [PATCHv3 2/4] ARM: Allow machines to override __delay() Stephen Boyd
@ 2010-12-08 4:38 ` Stephen Boyd
2010-12-08 4:38 ` [PATCHv3 4/4] msm: timer: Migrate to timer based __delay() Stephen Boyd
3 siblings, 0 replies; 10+ messages in thread
From: Stephen Boyd @ 2010-12-08 4:38 UTC (permalink / raw)
To: linux-arm-kernel
udelay() can be incorrect on SMP machines that scale their CPU
frequencies independently of one another (as pointed out here
http://article.gmane.org/gmane.linux.kernel/977567). The delay
loop can either be too fast or too slow depending on which CPU the
loops_per_jiffy counter is calibrated on and which CPU the delay
loop is running on. udelay() can also be incorrect if the
CPU frequency switches during the __delay() loop, causing the loop
to either terminate too early, or too late.
Forcing udelay() to run on one CPU is unreasonable and taking the
penalty of a rather large loops_per_jiffy in udelay() when the
CPU is actually running slower is bad for performance. Solve the
problem by adding a timer based__delay() loop unaffected by CPU
frequency scaling. Machines should set this loop as their
__delay() implementation by calling set_timer_fn() during their
timer initialization.
The kernel is already prepared for a timer based approach
(evident by the read_current_timer() function). If an arch
implements read_current_timer(), calibrate_delay() will use
calibrate_delay_direct() to calculate loops_per_jiffy (in which
case loops_per_jiffy should really be renamed to
timer_ticks_per_jiffy). Since the loops_per_jiffy will be based
on timer ticks, __delay() should be implemented as a loop around
read_current_timer().
Doing this makes the expensive loops_per_jiffy calculation go
away (saving ~150ms on boot time on my machine) and fixes
udelay() by making it safe in the face of independently scaling
CPUs. The only prerequisite is that read_current_timer() is
monotonically increasing across calls (and doesn't overflow
within ~2000us).
There is a downside to this approach though. BogoMIPS is no
longer "accurate" in that it reflects the BogoMIPS of the timer
and not the CPU. On most SoC's the timer isn't running anywhere
near as fast as the CPU so BogoMIPS will be ridiculously low (my
timer runs at 4.8 MHz and thus my BogoMIPS is 9.6 compared to my
CPU's 800). This shouldn't be too much of a concern though since
BogoMIPS are bogus anyway (hence the name).
This loop is pretty much a copy of AVR's version.
Reported-by: Saravana Kannan <skannan@codeaurora.org>
Signed-off-by: Stephen Boyd <sboyd@codeaurora.org>
Reviewed-by: Saravana Kannan <skannan@codeaurora.org>
---
arch/arm/include/asm/delay.h | 1 +
arch/arm/lib/delay.c | 17 +++++++++++++++++
2 files changed, 18 insertions(+), 0 deletions(-)
diff --git a/arch/arm/include/asm/delay.h b/arch/arm/include/asm/delay.h
index 7c732b5..5c6b9a3 100644
--- a/arch/arm/include/asm/delay.h
+++ b/arch/arm/include/asm/delay.h
@@ -41,6 +41,7 @@ extern void __const_udelay(unsigned long);
__udelay(n))
extern void set_delay_fn(void (*fn)(unsigned long));
+extern void read_current_timer_delay_loop(unsigned long loops);
#endif /* defined(_ARM_DELAY_H) */
diff --git a/arch/arm/lib/delay.c b/arch/arm/lib/delay.c
index b38f7c0..c590b8a 100644
--- a/arch/arm/lib/delay.c
+++ b/arch/arm/lib/delay.c
@@ -9,6 +9,7 @@
*/
#include <linux/module.h>
#include <linux/delay.h>
+#include <linux/timex.h>
/*
* Oh, if only we had a cycle counter...
@@ -23,6 +24,22 @@ void delay_loop(unsigned long loops)
);
}
+#ifdef ARCH_HAS_READ_CURRENT_TIMER
+/*
+ * Assumes read_current_timer() is monotonically increasing
+ * across calls and wraps at most once within MAX_UDELAY_MS.
+ */
+void read_current_timer_delay_loop(unsigned long loops)
+{
+ unsigned long bclock, now;
+
+ read_current_timer(&bclock);
+ do {
+ read_current_timer(&now);
+ } while ((now - bclock) < loops);
+}
+#endif
+
static void (*delay_fn)(unsigned long) = delay_loop;
void set_delay_fn(void (*fn)(unsigned long))
--
Sent by an employee of the Qualcomm Innovation Center, Inc.
The Qualcomm Innovation Center, Inc. is a member of the Code Aurora Forum.
^ permalink raw reply related [flat|nested] 10+ messages in thread* [PATCHv3 4/4] msm: timer: Migrate to timer based __delay()
2010-12-08 4:38 [PATCHv3 0/4] ARM: Fixing udelay() for SMP and non-SMP systems Stephen Boyd
` (2 preceding siblings ...)
2010-12-08 4:38 ` [PATCHv3 3/4] ARM: Implement a timer based __delay() loop Stephen Boyd
@ 2010-12-08 4:38 ` Stephen Boyd
3 siblings, 0 replies; 10+ messages in thread
From: Stephen Boyd @ 2010-12-08 4:38 UTC (permalink / raw)
To: linux-arm-kernel
We have to provide a dummy set_mode for the DGT since we don't
want it to ever turn off.
Signed-off-by: Stephen Boyd <sboyd@codeaurora.org>
---
arch/arm/mach-msm/include/mach/timex.h | 1 +
arch/arm/mach-msm/timer.c | 16 +++++++++++++++-
2 files changed, 16 insertions(+), 1 deletions(-)
diff --git a/arch/arm/mach-msm/include/mach/timex.h b/arch/arm/mach-msm/include/mach/timex.h
index a62e6b2..52b602b 100644
--- a/arch/arm/mach-msm/include/mach/timex.h
+++ b/arch/arm/mach-msm/include/mach/timex.h
@@ -17,5 +17,6 @@
#define __ASM_ARCH_MSM_TIMEX_H
#define CLOCK_TICK_RATE 1000000
+#define ARCH_HAS_READ_CURRENT_TIMER
#endif
diff --git a/arch/arm/mach-msm/timer.c b/arch/arm/mach-msm/timer.c
index 950100f..3e4c205 100644
--- a/arch/arm/mach-msm/timer.c
+++ b/arch/arm/mach-msm/timer.c
@@ -84,6 +84,12 @@ static cycle_t msm_dgt_read(struct clocksource *cs)
return readl(MSM_DGT_BASE + TIMER_COUNT_VAL) >> MSM_DGT_SHIFT;
}
+int read_current_timer(unsigned long *timer_val)
+{
+ *timer_val = readl(MSM_DGT_BASE + TIMER_COUNT_VAL);
+ return 0;
+}
+
static int msm_timer_set_next_event(unsigned long cycles,
struct clock_event_device *evt)
{
@@ -122,6 +128,12 @@ static void msm_timer_set_mode(enum clock_event_mode mode,
}
}
+static void msm_timer_set_mode_nop(enum clock_event_mode mode,
+ struct clock_event_device *evt)
+{
+ /* The timer is always ticking so do nothing */
+}
+
static struct msm_clock msm_clocks[] = {
{
.clockevent = {
@@ -157,7 +169,7 @@ static struct msm_clock msm_clocks[] = {
.shift = 32 + MSM_DGT_SHIFT,
.rating = 300,
.set_next_event = msm_timer_set_next_event,
- .set_mode = msm_timer_set_mode,
+ .set_mode = msm_timer_set_mode_nop,
},
.clocksource = {
.name = "dg_timer",
@@ -218,6 +230,8 @@ static void __init msm_timer_init(void)
clockevents_register_device(ce);
}
+ writel(1, MSM_DGT_BASE + TIMER_ENABLE);
+ set_delay_fn(read_current_timer_delay_loop);
}
struct sys_timer msm_timer = {
--
Sent by an employee of the Qualcomm Innovation Center, Inc.
The Qualcomm Innovation Center, Inc. is a member of the Code Aurora Forum.
^ permalink raw reply related [flat|nested] 10+ messages in thread