+ arm64-support-wfet-in-smp_cond_load_relaxed_timeout.patch added to mm-new branch

+ arm64-support-wfet-in-smp_cond_load_relaxed_timeout.patch added to mm-new branch

[Andrew Morton]

The patch titled
     Subject: arm64: support WFET in smp_cond_load_relaxed_timeout()
has been added to the -mm mm-new branch.  Its filename is
     arm64-support-wfet-in-smp_cond_load_relaxed_timeout.patch

This patch will shortly appear at
     https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/arm64-support-wfet-in-smp_cond_load_relaxed_timeout.patch

This patch will later appear in the mm-new branch at
    git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Note, mm-new is a provisional staging ground for work-in-progress
patches, and acceptance into mm-new is a notification for others take
notice and to finish up reviews.  Please do not hesitate to respond to
review feedback and post updated versions to replace or incrementally
fixup patches in mm-new.

The mm-new branch of mm.git is not included in linux-next

If a few days of testing in mm-new is successful, the patch will me moved
into mm.git's mm-unstable branch, which is included in linux-next

Before you just go and hit "reply", please:
   a) Consider who else should be cc'ed
   b) Prefer to cc a suitable mailing list as well
   c) Ideally: find the original patch on the mailing list and do a
      reply-to-all to that, adding suitable additional cc's

*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***

The -mm tree is included into linux-next via various
branches at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there most days

------------------------------------------------------
From: Ankur Arora <ankur.a.arora@oracle.com>
Subject: arm64: support WFET in smp_cond_load_relaxed_timeout()
Date: Wed, 8 Apr 2026 17:55:28 +0530

To handle WFET use __cmpwait_timeout() similarly to __cmpwait().  These
call out to the respective __cmpwait_case_timeout_##sz(),
__cmpwait_case_##sz() functions.

Link: https://lore.kernel.org/20260408122538.3610871-5-ankur.a.arora@oracle.com
Signed-off-by: Ankur Arora <ankur.a.arora@oracle.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Will Deacon <will@kernel.org>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Bjorn Andersson <andersson@kernel.org>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Boqun Feng <boqun@kernel.org>
Cc: Christoph Lameter <cl@linux.com>
Cc: Daniel Lezcano <daniel.lezcano@linaro.org>
Cc: David Gow <davidgow@google.com>
Cc: Gary Guo <gary@garyguo.net>
Cc: Haris Okanovic <harisokn@amazon.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Konrad Dybcio <konradybcio@kernel.org>
Cc: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rafael J. Wysocki (Intel) <rafael@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 arch/arm64/include/asm/barrier.h |    8 ++-
 arch/arm64/include/asm/cmpxchg.h |   62 +++++++++++++++++++++++------
 2 files changed, 55 insertions(+), 15 deletions(-)

--- a/arch/arm64/include/asm/barrier.h~arm64-support-wfet-in-smp_cond_load_relaxed_timeout
+++ a/arch/arm64/include/asm/barrier.h
@@ -224,8 +224,8 @@ do {									\
 extern bool arch_timer_evtstrm_available(void);
 
 /*
- * In the common case, cpu_poll_relax() sits waiting in __cmpwait_relaxed()
- * for the ptr value to change.
+ * In the common case, cpu_poll_relax() sits waiting in __cmpwait_relaxed()/
+ * __cmpwait_relaxed_timeout() for the ptr value to change.
  *
  * Since this period is reasonably long, choose SMP_TIMEOUT_POLL_COUNT
  * to be 1, so smp_cond_load_{relaxed,acquire}_timeout() does a
@@ -234,7 +234,9 @@ extern bool arch_timer_evtstrm_available
 #define SMP_TIMEOUT_POLL_COUNT	1
 
 #define cpu_poll_relax(ptr, val, timeout_ns) do {			\
-	if (arch_timer_evtstrm_available())				\
+	if (alternative_has_cap_unlikely(ARM64_HAS_WFXT))		\
+		__cmpwait_relaxed_timeout(ptr, val, timeout_ns);	\
+	else if (arch_timer_evtstrm_available())			\
 		__cmpwait_relaxed(ptr, val);				\
 	else								\
 		cpu_relax();						\
--- a/arch/arm64/include/asm/cmpxchg.h~arm64-support-wfet-in-smp_cond_load_relaxed_timeout
+++ a/arch/arm64/include/asm/cmpxchg.h
@@ -12,6 +12,7 @@
 
 #include <asm/barrier.h>
 #include <asm/lse.h>
+#include <asm/delay-const.h>
 
 /*
  * We need separate acquire parameters for ll/sc and lse, since the full
@@ -212,7 +213,8 @@ __CMPXCHG_GEN(_mb)
 
 #define __CMPWAIT_CASE(w, sfx, sz)					\
 static inline void __cmpwait_case_##sz(volatile void *ptr,		\
-				       unsigned long val)		\
+				       unsigned long val,		\
+				       u64 __maybe_unused timeout_ns)	\
 {									\
 	unsigned long tmp;						\
 									\
@@ -235,20 +237,52 @@ __CMPWAIT_CASE( ,  , 64);
 
 #undef __CMPWAIT_CASE
 
-#define __CMPWAIT_GEN(sfx)						\
-static __always_inline void __cmpwait##sfx(volatile void *ptr,		\
-				  unsigned long val,			\
-				  int size)				\
+#define __CMPWAIT_TIMEOUT_CASE(w, sfx, sz)				\
+static inline void __cmpwait_case_timeout_##sz(volatile void *ptr,	\
+					       unsigned long val,	\
+					       u64 timeout_ns)		\
+{									\
+	unsigned long tmp;						\
+	u64 ecycles = __delay_cycles() +				\
+			NSECS_TO_CYCLES(timeout_ns);			\
+	asm volatile(							\
+	"	sevl\n"							\
+	"	wfe\n"							\
+	"	ldxr" #sfx "\t%" #w "[tmp], %[v]\n"			\
+	"	eor	%" #w "[tmp], %" #w "[tmp], %" #w "[val]\n"	\
+	"	cbnz	%" #w "[tmp], 2f\n"				\
+	"	msr s0_3_c1_c0_0, %[ecycles]\n"				\
+	"2:"								\
+	: [tmp] "=&r" (tmp), [v] "+Q" (*(u##sz *)ptr)			\
+	: [val] "r" (val), [ecycles] "r" (ecycles));			\
+}
+
+__CMPWAIT_TIMEOUT_CASE(w, b, 8);
+__CMPWAIT_TIMEOUT_CASE(w, h, 16);
+__CMPWAIT_TIMEOUT_CASE(w,  , 32);
+__CMPWAIT_TIMEOUT_CASE( ,  , 64);
+
+#undef __CMPWAIT_TIMEOUT_CASE
+
+#define __CMPWAIT_GEN(timeout, sfx)					\
+static __always_inline void __cmpwait##timeout##sfx(volatile void *ptr,	\
+						    unsigned long val,	\
+						    u64 timeout_ns,	\
+						    int size)		\
 {									\
 	switch (size) {							\
 	case 1:								\
-		return __cmpwait_case##sfx##_8(ptr, (u8)val);		\
+		return __cmpwait_case##timeout##sfx##_8(ptr, (u8)val,	\
+							timeout_ns);	\
 	case 2:								\
-		return __cmpwait_case##sfx##_16(ptr, (u16)val);		\
+		return __cmpwait_case##timeout##sfx##_16(ptr, (u16)val,	\
+							 timeout_ns);	\
 	case 4:								\
-		return __cmpwait_case##sfx##_32(ptr, val);		\
+		return __cmpwait_case##timeout##sfx##_32(ptr, val,	\
+							 timeout_ns);	\
 	case 8:								\
-		return __cmpwait_case##sfx##_64(ptr, val);		\
+		return __cmpwait_case##timeout##sfx##_64(ptr, val,	\
+							 timeout_ns);	\
 	default:							\
 		BUILD_BUG();						\
 	}								\
@@ -256,11 +290,15 @@ static __always_inline void __cmpwait##s
 	unreachable();							\
 }
 
-__CMPWAIT_GEN()
+__CMPWAIT_GEN(        , )
+__CMPWAIT_GEN(_timeout, )
 
 #undef __CMPWAIT_GEN
 
-#define __cmpwait_relaxed(ptr, val) \
-	__cmpwait((ptr), (unsigned long)(val), sizeof(*(ptr)))
+#define __cmpwait_relaxed_timeout(ptr, val, timeout_ns)			\
+	__cmpwait_timeout((ptr), (unsigned long)(val), timeout_ns, sizeof(*(ptr)))
+
+#define __cmpwait_relaxed(ptr, val)					\
+	__cmpwait((ptr), (unsigned long)(val), 0, sizeof(*(ptr)))
 
 #endif	/* __ASM_CMPXCHG_H */
_

Patches currently in -mm which might be from ankur.a.arora@oracle.com are

asm-generic-barrier-add-smp_cond_load_relaxed_timeout.patch
arm64-barrier-support-smp_cond_load_relaxed_timeout.patch
arm64-delay-move-some-constants-out-to-a-separate-header.patch
arm64-support-wfet-in-smp_cond_load_relaxed_timeout.patch
arm64-rqspinlock-remove-private-copy-of-smp_cond_load_acquire_timewait.patch
asm-generic-barrier-add-smp_cond_load_acquire_timeout.patch
atomic-add-atomic_cond_read__timeout.patch
locking-atomic-scripts-build-atomic_long_cond_read__timeout.patch
bpf-rqspinlock-switch-check_timeout-to-a-clock-interface.patch
bpf-rqspinlock-use-smp_cond_load_acquire_timeout.patch
sched-add-need-resched-timed-wait-interface.patch
cpuidle-poll_state-wait-for-need-resched-via-tif_need_resched_relaxed_wait.patch
kunit-enable-testing-smp_cond_load_relaxed_timeout.patch
kunit-add-tests-for-smp_cond_load_relaxed_timeout.patch