From: George Guo <guodongtai@kylinos.cn>
Implement 128-bit atomic compare-and-exchange using LoongArch's
LL.D/SC.Q instructions.
At the same time, fix BPF scheduler test failures (scx_central scx_qmap)
caused by kmalloc_nolock_noprof returning NULL due to missing
128-bit atomics. The NULL returns led to -ENOMEM errors during
scheduler initialization, causing test cases to fail.
Verified by testing with the scx_qmap scheduler (located in
tools/sched_ext/). Building with `make` and running
./tools/sched_ext/build/bin/scx_qmap.
Signed-off-by: George Guo <guodongtai@kylinos.cn>
---
arch/loongarch/include/asm/cmpxchg.h | 47 ++++++++++++++++++++++++++++
1 file changed, 47 insertions(+)
diff --git a/arch/loongarch/include/asm/cmpxchg.h b/arch/loongarch/include/asm/cmpxchg.h
index 0494c2ab553e..61ce6a0889f0 100644
--- a/arch/loongarch/include/asm/cmpxchg.h
+++ b/arch/loongarch/include/asm/cmpxchg.h
@@ -137,6 +137,44 @@ __arch_xchg(volatile void *ptr, unsigned long x, int size)
__ret; \
})
+union __u128_halves {
+ u128 full;
+ struct {
+ u64 low;
+ u64 high;
+ };
+};
+
+#define __cmpxchg128_asm(ptr, old, new) \
+({ \
+ union __u128_halves __old, __new, __ret; \
+ volatile u64 *__ptr = (volatile u64 *)(ptr); \
+ \
+ __old.full = (old); \
+ __new.full = (new); \
+ \
+ __asm__ __volatile__( \
+ "1: ll.d %0, %3 # 128-bit cmpxchg low \n" \
+ __WEAK_LLSC_MB \
+ " ld.d %1, %4 # 128-bit cmpxchg high \n" \
+ " bne %0, %z5, 2f \n" \
+ " bne %1, %z6, 2f \n" \
+ " move $t0, %z7 \n" \
+ " move $t1, %z8 \n" \
+ " sc.q $t0, $t1, %2 \n" \
+ " beqz $t0, 1b \n" \
+ "2: \n" \
+ __WEAK_LLSC_MB \
+ : "=&r" (__ret.low), "=&r" (__ret.high) \
+ : "r" (__ptr), \
+ "ZC" (__ptr[0]), "m" (__ptr[1]), \
+ "Jr" (__old.low), "Jr" (__old.high), \
+ "Jr" (__new.low), "Jr" (__new.high) \
+ : "t0", "t1", "memory"); \
+ \
+ __ret.full; \
+})
+
static inline unsigned int __cmpxchg_small(volatile void *ptr, unsigned int old,
unsigned int new, unsigned int size)
{
@@ -224,6 +262,15 @@ __cmpxchg(volatile void *ptr, unsigned long old, unsigned long new, unsigned int
__res; \
})
+/* cmpxchg128 */
+#define system_has_cmpxchg128() 1
+
+#define arch_cmpxchg128(ptr, o, n) \
+({ \
+ BUILD_BUG_ON(sizeof(*(ptr)) != 16); \
+ __cmpxchg128_asm(ptr, o, n); \
+})
+
#ifdef CONFIG_64BIT
#define arch_cmpxchg64_local(ptr, o, n) \
({ \
--
2.49.0On Tue, Dec 30, 2025 at 9:34 AM George Guo <dongtai.guo@linux.dev> wrote:
>
> From: George Guo <guodongtai@kylinos.cn>
>
> Implement 128-bit atomic compare-and-exchange using LoongArch's
> LL.D/SC.Q instructions.
>
> At the same time, fix BPF scheduler test failures (scx_central scx_qmap)
> caused by kmalloc_nolock_noprof returning NULL due to missing
> 128-bit atomics. The NULL returns led to -ENOMEM errors during
> scheduler initialization, causing test cases to fail.
>
> Verified by testing with the scx_qmap scheduler (located in
> tools/sched_ext/). Building with `make` and running
> ./tools/sched_ext/build/bin/scx_qmap.
>
As I mentioned in last cycle, patch 2 and patch 3 can be merged into one.
Please also add a link ([1]) to upstream commit that breaks these tests.
[1]: https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf.git/commit/?id=5fb750e8a9ae
> Signed-off-by: George Guo <guodongtai@kylinos.cn>
> ---
> arch/loongarch/include/asm/cmpxchg.h | 47 ++++++++++++++++++++++++++++
> 1 file changed, 47 insertions(+)
>
> diff --git a/arch/loongarch/include/asm/cmpxchg.h b/arch/loongarch/include/asm/cmpxchg.h
> index 0494c2ab553e..61ce6a0889f0 100644
> --- a/arch/loongarch/include/asm/cmpxchg.h
> +++ b/arch/loongarch/include/asm/cmpxchg.h
> @@ -137,6 +137,44 @@ __arch_xchg(volatile void *ptr, unsigned long x, int size)
> __ret; \
> })
>
> +union __u128_halves {
> + u128 full;
> + struct {
> + u64 low;
> + u64 high;
> + };
> +};
> +
> +#define __cmpxchg128_asm(ptr, old, new) \
> +({ \
> + union __u128_halves __old, __new, __ret; \
> + volatile u64 *__ptr = (volatile u64 *)(ptr); \
> + \
> + __old.full = (old); \
> + __new.full = (new); \
> + \
> + __asm__ __volatile__( \
> + "1: ll.d %0, %3 # 128-bit cmpxchg low \n" \
> + __WEAK_LLSC_MB \
> + " ld.d %1, %4 # 128-bit cmpxchg high \n" \
> + " bne %0, %z5, 2f \n" \
> + " bne %1, %z6, 2f \n" \
> + " move $t0, %z7 \n" \
> + " move $t1, %z8 \n" \
> + " sc.q $t0, $t1, %2 \n" \
> + " beqz $t0, 1b \n" \
> + "2: \n" \
> + __WEAK_LLSC_MB \
> + : "=&r" (__ret.low), "=&r" (__ret.high) \
> + : "r" (__ptr), \
> + "ZC" (__ptr[0]), "m" (__ptr[1]), \
> + "Jr" (__old.low), "Jr" (__old.high), \
> + "Jr" (__new.low), "Jr" (__new.high) \
> + : "t0", "t1", "memory"); \
> + \
> + __ret.full; \
> +})
> +
> static inline unsigned int __cmpxchg_small(volatile void *ptr, unsigned int old,
> unsigned int new, unsigned int size)
> {
> @@ -224,6 +262,15 @@ __cmpxchg(volatile void *ptr, unsigned long old, unsigned long new, unsigned int
> __res; \
> })
>
> +/* cmpxchg128 */
> +#define system_has_cmpxchg128() 1
> +
> +#define arch_cmpxchg128(ptr, o, n) \
> +({ \
> + BUILD_BUG_ON(sizeof(*(ptr)) != 16); \
> + __cmpxchg128_asm(ptr, o, n); \
> +})
> +
> #ifdef CONFIG_64BIT
> #define arch_cmpxchg64_local(ptr, o, n) \
> ({ \
> --
> 2.49.0
>
© 2016 - 2026 Red Hat, Inc.