[tip:,sched/core] arm64/arch_timer: Provide noinstr sched_clock_read() functions
Commit Message
The following commit has been merged into the sched/core branch of tip:
Commit-ID: 24ee7607b286b44a5112ced38652df14cd80d5e2
Gitweb: https://git.kernel.org/tip/24ee7607b286b44a5112ced38652df14cd80d5e2
Author: Peter Zijlstra <peterz@infradead.org>
AuthorDate: Fri, 19 May 2023 12:21:02 +02:00
Committer: Peter Zijlstra <peterz@infradead.org>
CommitterDate: Mon, 05 Jun 2023 21:11:05 +02:00
arm64/arch_timer: Provide noinstr sched_clock_read() functions
With the intent to provide local_clock_noinstr(), a variant of
local_clock() that's safe to be called from noinstr code (with the
assumption that any such code will already be non-preemptible),
prepare for things by providing a noinstr sched_clock_read() function.
Specifically, preempt_enable_*() calls out to schedule(), which upsets
noinstr validation efforts.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Michael Kelley <mikelley@microsoft.com> # Hyper-V
Link: https://lore.kernel.org/r/20230519102715.435618812@infradead.org
---
arch/arm64/include/asm/arch_timer.h | 8 +----
drivers/clocksource/arm_arch_timer.c | 54 ++++++++++++++++++++-------
2 files changed, 41 insertions(+), 21 deletions(-)
Comments
On Mon, Jun 05, 2023 at 07:16:18PM -0000, tip-bot2 for Peter Zijlstra wrote:
> @@ -753,14 +771,14 @@ static int arch_timer_set_next_event_phys(unsigned long evt,
> return 0;
> }
>
> -static u64 arch_counter_get_cnt_mem(struct arch_timer *t, int offset_lo)
> +static noinstr u64 arch_counter_get_cnt_mem(struct arch_timer *t, int offset_lo)
> {
> u32 cnt_lo, cnt_hi, tmp_hi;
>
> do {
> - cnt_hi = readl_relaxed(t->base + offset_lo + 4);
> - cnt_lo = readl_relaxed(t->base + offset_lo);
> - tmp_hi = readl_relaxed(t->base + offset_lo + 4);
> + cnt_hi = __raw_readl(t->base + offset_lo + 4);
> + cnt_lo = __raw_readl(t->base + offset_lo);
> + tmp_hi = __raw_readl(t->base + offset_lo + 4);
> } while (cnt_hi != tmp_hi);
>
> return ((u64) cnt_hi << 32) | cnt_lo;
Mark noted that this looses the byteswap :/
---
Subject: arm64/arch_timer: Fix MMIO byteswap
The readl_relaxed() to __raw_readl() change meant to loose the
instrumentation, but also (inadvertently) lost the byteswap.
Fixes: 24ee7607b286 ("arm64/arch_timer: Provide noinstr sched_clock_read() functions")
Reported-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
diff --git a/drivers/clocksource/arm_arch_timer.c b/drivers/clocksource/arm_arch_timer.c
index b23d23b033cc..e733a2a1927a 100644
--- a/drivers/clocksource/arm_arch_timer.c
+++ b/drivers/clocksource/arm_arch_timer.c
@@ -776,9 +776,9 @@ static noinstr u64 arch_counter_get_cnt_mem(struct arch_timer *t, int offset_lo)
u32 cnt_lo, cnt_hi, tmp_hi;
do {
- cnt_hi = __raw_readl(t->base + offset_lo + 4);
- cnt_lo = __raw_readl(t->base + offset_lo);
- tmp_hi = __raw_readl(t->base + offset_lo + 4);
+ cnt_hi = __le32_to_cpu((__le32 __force)__raw_readl(t->base + offset_lo + 4));
+ cnt_lo = __le32_to_cpu((__le32 __force)__raw_readl(t->base + offset_lo));
+ tmp_hi = __le32_to_cpu((__le32 __force)__raw_readl(t->base + offset_lo + 4));
} while (cnt_hi != tmp_hi);
return ((u64) cnt_hi << 32) | cnt_lo;
On Tue, Jun 06, 2023 at 10:06:14AM +0200, Peter Zijlstra wrote:
> On Mon, Jun 05, 2023 at 07:16:18PM -0000, tip-bot2 for Peter Zijlstra wrote:
> > @@ -753,14 +771,14 @@ static int arch_timer_set_next_event_phys(unsigned long evt,
> > return 0;
> > }
> >
> > -static u64 arch_counter_get_cnt_mem(struct arch_timer *t, int offset_lo)
> > +static noinstr u64 arch_counter_get_cnt_mem(struct arch_timer *t, int offset_lo)
> > {
> > u32 cnt_lo, cnt_hi, tmp_hi;
> >
> > do {
> > - cnt_hi = readl_relaxed(t->base + offset_lo + 4);
> > - cnt_lo = readl_relaxed(t->base + offset_lo);
> > - tmp_hi = readl_relaxed(t->base + offset_lo + 4);
> > + cnt_hi = __raw_readl(t->base + offset_lo + 4);
> > + cnt_lo = __raw_readl(t->base + offset_lo);
> > + tmp_hi = __raw_readl(t->base + offset_lo + 4);
> > } while (cnt_hi != tmp_hi);
> >
> > return ((u64) cnt_hi << 32) | cnt_lo;
>
> Mark noted that this looses the byteswap :/
>
>
> ---
> Subject: arm64/arch_timer: Fix MMIO byteswap
>
> The readl_relaxed() to __raw_readl() change meant to loose the
> instrumentation, but also (inadvertently) lost the byteswap.
>
> Fixes: 24ee7607b286 ("arm64/arch_timer: Provide noinstr sched_clock_read() functions")
> Reported-by: Mark Rutland <mark.rutland@arm.com>
> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
> ---
> diff --git a/drivers/clocksource/arm_arch_timer.c b/drivers/clocksource/arm_arch_timer.c
> index b23d23b033cc..e733a2a1927a 100644
> --- a/drivers/clocksource/arm_arch_timer.c
> +++ b/drivers/clocksource/arm_arch_timer.c
> @@ -776,9 +776,9 @@ static noinstr u64 arch_counter_get_cnt_mem(struct arch_timer *t, int offset_lo)
> u32 cnt_lo, cnt_hi, tmp_hi;
>
> do {
> - cnt_hi = __raw_readl(t->base + offset_lo + 4);
> - cnt_lo = __raw_readl(t->base + offset_lo);
> - tmp_hi = __raw_readl(t->base + offset_lo + 4);
> + cnt_hi = __le32_to_cpu((__le32 __force)__raw_readl(t->base + offset_lo + 4));
> + cnt_lo = __le32_to_cpu((__le32 __force)__raw_readl(t->base + offset_lo));
> + tmp_hi = __le32_to_cpu((__le32 __force)__raw_readl(t->base + offset_lo + 4));
> } while (cnt_hi != tmp_hi);
This LGTM, so FWIW:
Acked-by: Mark Rutland <mark.rutland@arm.com>
Longer term it'd be good to have noistr-safe forms of the MMIO accessors, but
from a quick play that's a much bigger piece of work, and I think this is fine
for now!
Thanks,
Mark.
@@ -88,13 +88,7 @@ static inline notrace u64 arch_timer_read_cntvct_el0(void)
#define arch_timer_reg_read_stable(reg) \
({ \
- u64 _val; \
- \
- preempt_disable_notrace(); \
- _val = erratum_handler(read_ ## reg)(); \
- preempt_enable_notrace(); \
- \
- _val; \
+ erratum_handler(read_ ## reg)(); \
})
/*
@@ -191,22 +191,40 @@ u32 arch_timer_reg_read(int access, enum arch_timer_reg reg,
return val;
}
-static notrace u64 arch_counter_get_cntpct_stable(void)
+static noinstr u64 raw_counter_get_cntpct_stable(void)
{
return __arch_counter_get_cntpct_stable();
}
-static notrace u64 arch_counter_get_cntpct(void)
+static notrace u64 arch_counter_get_cntpct_stable(void)
+{
+ u64 val;
+ preempt_disable_notrace();
+ val = __arch_counter_get_cntpct_stable();
+ preempt_enable_notrace();
+ return val;
+}
+
+static noinstr u64 arch_counter_get_cntpct(void)
{
return __arch_counter_get_cntpct();
}
-static notrace u64 arch_counter_get_cntvct_stable(void)
+static noinstr u64 raw_counter_get_cntvct_stable(void)
{
return __arch_counter_get_cntvct_stable();
}
-static notrace u64 arch_counter_get_cntvct(void)
+static notrace u64 arch_counter_get_cntvct_stable(void)
+{
+ u64 val;
+ preempt_disable_notrace();
+ val = __arch_counter_get_cntvct_stable();
+ preempt_enable_notrace();
+ return val;
+}
+
+static noinstr u64 arch_counter_get_cntvct(void)
{
return __arch_counter_get_cntvct();
}
@@ -753,14 +771,14 @@ static int arch_timer_set_next_event_phys(unsigned long evt,
return 0;
}
-static u64 arch_counter_get_cnt_mem(struct arch_timer *t, int offset_lo)
+static noinstr u64 arch_counter_get_cnt_mem(struct arch_timer *t, int offset_lo)
{
u32 cnt_lo, cnt_hi, tmp_hi;
do {
- cnt_hi = readl_relaxed(t->base + offset_lo + 4);
- cnt_lo = readl_relaxed(t->base + offset_lo);
- tmp_hi = readl_relaxed(t->base + offset_lo + 4);
+ cnt_hi = __raw_readl(t->base + offset_lo + 4);
+ cnt_lo = __raw_readl(t->base + offset_lo);
+ tmp_hi = __raw_readl(t->base + offset_lo + 4);
} while (cnt_hi != tmp_hi);
return ((u64) cnt_hi << 32) | cnt_lo;
@@ -1060,7 +1078,7 @@ bool arch_timer_evtstrm_available(void)
return cpumask_test_cpu(raw_smp_processor_id(), &evtstrm_available);
}
-static u64 arch_counter_get_cntvct_mem(void)
+static noinstr u64 arch_counter_get_cntvct_mem(void)
{
return arch_counter_get_cnt_mem(arch_timer_mem, CNTVCT_LO);
}
@@ -1074,6 +1092,7 @@ struct arch_timer_kvm_info *arch_timer_get_kvm_info(void)
static void __init arch_counter_register(unsigned type)
{
+ u64 (*scr)(void);
u64 start_count;
int width;
@@ -1083,21 +1102,28 @@ static void __init arch_counter_register(unsigned type)
if ((IS_ENABLED(CONFIG_ARM64) && !is_hyp_mode_available()) ||
arch_timer_uses_ppi == ARCH_TIMER_VIRT_PPI) {
- if (arch_timer_counter_has_wa())
+ if (arch_timer_counter_has_wa()) {
rd = arch_counter_get_cntvct_stable;
- else
+ scr = raw_counter_get_cntvct_stable;
+ } else {
rd = arch_counter_get_cntvct;
+ scr = arch_counter_get_cntvct;
+ }
} else {
- if (arch_timer_counter_has_wa())
+ if (arch_timer_counter_has_wa()) {
rd = arch_counter_get_cntpct_stable;
- else
+ scr = raw_counter_get_cntpct_stable;
+ } else {
rd = arch_counter_get_cntpct;
+ scr = arch_counter_get_cntpct;
+ }
}
arch_timer_read_counter = rd;
clocksource_counter.vdso_clock_mode = vdso_default;
} else {
arch_timer_read_counter = arch_counter_get_cntvct_mem;
+ scr = arch_counter_get_cntvct_mem;
}
width = arch_counter_get_width();
@@ -1113,7 +1139,7 @@ static void __init arch_counter_register(unsigned type)
timecounter_init(&arch_timer_kvm_info.timecounter,
&cyclecounter, start_count);
- sched_clock_register(arch_timer_read_counter, width, arch_timer_rate);
+ sched_clock_register(scr, width, arch_timer_rate);
}
static void arch_timer_stop(struct clock_event_device *clk)