Thread (30 messages) 30 messages, 5 authors, 2025-11-06

Re: [RESEND PATCH v7 2/7] arm64: barrier: Support smp_cond_load_relaxed_timeout()

From: "Arnd Bergmann" <arnd@arndb.de>
Date: 2025-10-28 08:43:12
Also in: bpf, linux-arch, linux-pm, lkml

On Tue, Oct 28, 2025, at 06:31, Ankur Arora wrote:
Support waiting in smp_cond_load_relaxed_timeout() via
__cmpwait_relaxed(). Limit this to when the event-stream is enabled,
to ensure that we wake from WFE periodically and don't block forever
if there are no stores to the cacheline.

In the unlikely event that the event-stream is unavailable, fallback
to spin-waiting.

Also set SMP_TIMEOUT_POLL_COUNT to 1 so we do the time-check for each
iteration in smp_cond_load_relaxed_timeout().
After I looked at the entire series again, this one feels like
a missed opportunity. Especially on low-power systems but possibly
on any ARMv9.2+ implementation including Cortex-A320, it would
be nice to be able to both turn off the event stream and also
make this function take fewer wakeups:
+/* Re-declared here to avoid include dependency. */
+extern bool arch_timer_evtstrm_available(void);
+
+#define cpu_poll_relax(ptr, val)					\
+do {									\
+	if (arch_timer_evtstrm_available())				\
+		__cmpwait_relaxed(ptr, val);				\
+	else								\
+		cpu_relax();						\
+} while (0)
+
Since the caller knows exactly how long it wants to wait for,
we should be able to fit a 'wfet' based primitive in here and
pass the timeout as another argument.

    Arnd
Keyboard shortcuts
hback out one level
jnext message in thread
kprevious message in thread
ldrill in
Escclose help / fold thread tree
?toggle this help