Refactor futex atomic operations using ll/sc method with
clearing PSTATE.PAN to prepare to apply FEAT_LSUI on them.
Signed-off-by: Yeoreum Yun <yeoreum.yun@arm.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
---
arch/arm64/include/asm/futex.h | 128 +++++++++++++++++++++------------
1 file changed, 82 insertions(+), 46 deletions(-)
diff --git a/arch/arm64/include/asm/futex.h b/arch/arm64/include/asm/futex.h
index bc06691d2062..f8cb674bdb3f 100644
--- a/arch/arm64/include/asm/futex.h
+++ b/arch/arm64/include/asm/futex.h
@@ -7,17 +7,21 @@
#include <linux/futex.h>
#include <linux/uaccess.h>
+#include <linux/stringify.h>
#include <asm/errno.h>
#define FUTEX_MAX_LOOPS 128 /* What's the largest number you can think of? */
-#define __futex_atomic_op(insn, ret, oldval, uaddr, tmp, oparg) \
-do { \
+#define LLSC_FUTEX_ATOMIC_OP(op, insn) \
+static __always_inline int \
+__llsc_futex_atomic_##op(int oparg, u32 __user *uaddr, int *oval) \
+{ \
unsigned int loops = FUTEX_MAX_LOOPS; \
+ int ret, oldval, tmp; \
\
uaccess_enable_privileged(); \
- asm volatile( \
+ asm volatile("// __llsc_futex_atomic_" #op "\n" \
" prfm pstl1strm, %2\n" \
"1: ldxr %w1, %2\n" \
insn "\n" \
@@ -35,45 +39,103 @@ do { \
: "r" (oparg), "Ir" (-EAGAIN) \
: "memory"); \
uaccess_disable_privileged(); \
-} while (0)
+ \
+ if (!ret) \
+ *oval = oldval; \
+ \
+ return ret; \
+}
+
+LLSC_FUTEX_ATOMIC_OP(add, "add %w3, %w1, %w5")
+LLSC_FUTEX_ATOMIC_OP(or, "orr %w3, %w1, %w5")
+LLSC_FUTEX_ATOMIC_OP(and, "and %w3, %w1, %w5")
+LLSC_FUTEX_ATOMIC_OP(eor, "eor %w3, %w1, %w5")
+LLSC_FUTEX_ATOMIC_OP(set, "mov %w3, %w5")
+
+static __always_inline int
+__llsc_futex_cmpxchg(u32 __user *uaddr, u32 oldval, u32 newval, u32 *oval)
+{
+ int ret = 0;
+ unsigned int loops = FUTEX_MAX_LOOPS;
+ u32 val, tmp;
+
+ uaccess_enable_privileged();
+ asm volatile("//__llsc_futex_cmpxchg\n"
+" prfm pstl1strm, %2\n"
+"1: ldxr %w1, %2\n"
+" eor %w3, %w1, %w5\n"
+" cbnz %w3, 4f\n"
+"2: stlxr %w3, %w6, %2\n"
+" cbz %w3, 3f\n"
+" sub %w4, %w4, %w3\n"
+" cbnz %w4, 1b\n"
+" mov %w0, %w7\n"
+"3:\n"
+" dmb ish\n"
+"4:\n"
+ _ASM_EXTABLE_UACCESS_ERR(1b, 4b, %w0)
+ _ASM_EXTABLE_UACCESS_ERR(2b, 4b, %w0)
+ : "+r" (ret), "=&r" (val), "+Q" (*uaddr), "=&r" (tmp), "+r" (loops)
+ : "r" (oldval), "r" (newval), "Ir" (-EAGAIN)
+ : "memory");
+ uaccess_disable_privileged();
+
+ if (!ret)
+ *oval = val;
+
+ return ret;
+}
+
+#define FUTEX_ATOMIC_OP(op) \
+static __always_inline int \
+__futex_atomic_##op(int oparg, u32 __user *uaddr, int *oval) \
+{ \
+ return __llsc_futex_atomic_##op(oparg, uaddr, oval); \
+}
+
+FUTEX_ATOMIC_OP(add)
+FUTEX_ATOMIC_OP(or)
+FUTEX_ATOMIC_OP(and)
+FUTEX_ATOMIC_OP(eor)
+FUTEX_ATOMIC_OP(set)
+
+static __always_inline int
+__futex_cmpxchg(u32 __user *uaddr, u32 oldval, u32 newval, u32 *oval)
+{
+ return __llsc_futex_cmpxchg(uaddr, oldval, newval, oval);
+}
static inline int
arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *_uaddr)
{
- int oldval = 0, ret, tmp;
- u32 __user *uaddr = __uaccess_mask_ptr(_uaddr);
+ int ret;
+ u32 __user *uaddr;
if (!access_ok(_uaddr, sizeof(u32)))
return -EFAULT;
+ uaddr = __uaccess_mask_ptr(_uaddr);
+
switch (op) {
case FUTEX_OP_SET:
- __futex_atomic_op("mov %w3, %w5",
- ret, oldval, uaddr, tmp, oparg);
+ ret = __futex_atomic_set(oparg, uaddr, oval);
break;
case FUTEX_OP_ADD:
- __futex_atomic_op("add %w3, %w1, %w5",
- ret, oldval, uaddr, tmp, oparg);
+ ret = __futex_atomic_add(oparg, uaddr, oval);
break;
case FUTEX_OP_OR:
- __futex_atomic_op("orr %w3, %w1, %w5",
- ret, oldval, uaddr, tmp, oparg);
+ ret = __futex_atomic_or(oparg, uaddr, oval);
break;
case FUTEX_OP_ANDN:
- __futex_atomic_op("and %w3, %w1, %w5",
- ret, oldval, uaddr, tmp, ~oparg);
+ ret = __futex_atomic_and(~oparg, uaddr, oval);
break;
case FUTEX_OP_XOR:
- __futex_atomic_op("eor %w3, %w1, %w5",
- ret, oldval, uaddr, tmp, oparg);
+ ret = __futex_atomic_eor(oparg, uaddr, oval);
break;
default:
ret = -ENOSYS;
}
- if (!ret)
- *oval = oldval;
-
return ret;
}
@@ -81,40 +143,14 @@ static inline int
futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *_uaddr,
u32 oldval, u32 newval)
{
- int ret = 0;
- unsigned int loops = FUTEX_MAX_LOOPS;
- u32 val, tmp;
u32 __user *uaddr;
if (!access_ok(_uaddr, sizeof(u32)))
return -EFAULT;
uaddr = __uaccess_mask_ptr(_uaddr);
- uaccess_enable_privileged();
- asm volatile("// futex_atomic_cmpxchg_inatomic\n"
-" prfm pstl1strm, %2\n"
-"1: ldxr %w1, %2\n"
-" sub %w3, %w1, %w5\n"
-" cbnz %w3, 4f\n"
-"2: stlxr %w3, %w6, %2\n"
-" cbz %w3, 3f\n"
-" sub %w4, %w4, %w3\n"
-" cbnz %w4, 1b\n"
-" mov %w0, %w7\n"
-"3:\n"
-" dmb ish\n"
-"4:\n"
- _ASM_EXTABLE_UACCESS_ERR(1b, 4b, %w0)
- _ASM_EXTABLE_UACCESS_ERR(2b, 4b, %w0)
- : "+r" (ret), "=&r" (val), "+Q" (*uaddr), "=&r" (tmp), "+r" (loops)
- : "r" (oldval), "r" (newval), "Ir" (-EAGAIN)
- : "memory");
- uaccess_disable_privileged();
-
- if (!ret)
- *uval = val;
- return ret;
+ return __futex_cmpxchg(uaddr, oldval, newval, uval);
}
#endif /* __ASM_FUTEX_H */
--
LEVI:{C3F47F37-75D8-414A-A8BA-3980EC8A46D7}On Sun, Dec 14, 2025 at 11:22:44AM +0000, Yeoreum Yun wrote:
> Refactor futex atomic operations using ll/sc method with
> clearing PSTATE.PAN to prepare to apply FEAT_LSUI on them.
>
> Signed-off-by: Yeoreum Yun <yeoreum.yun@arm.com>
> Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
> ---
> arch/arm64/include/asm/futex.h | 128 +++++++++++++++++++++------------
> 1 file changed, 82 insertions(+), 46 deletions(-)
>
> diff --git a/arch/arm64/include/asm/futex.h b/arch/arm64/include/asm/futex.h
> index bc06691d2062..f8cb674bdb3f 100644
> --- a/arch/arm64/include/asm/futex.h
> +++ b/arch/arm64/include/asm/futex.h
> @@ -7,17 +7,21 @@
>
> #include <linux/futex.h>
> #include <linux/uaccess.h>
> +#include <linux/stringify.h>
>
> #include <asm/errno.h>
>
> #define FUTEX_MAX_LOOPS 128 /* What's the largest number you can think of? */
>
> -#define __futex_atomic_op(insn, ret, oldval, uaddr, tmp, oparg) \
> -do { \
> +#define LLSC_FUTEX_ATOMIC_OP(op, insn) \
> +static __always_inline int \
> +__llsc_futex_atomic_##op(int oparg, u32 __user *uaddr, int *oval) \
> +{ \
> unsigned int loops = FUTEX_MAX_LOOPS; \
> + int ret, oldval, tmp; \
> \
> uaccess_enable_privileged(); \
> - asm volatile( \
> + asm volatile("// __llsc_futex_atomic_" #op "\n" \
> " prfm pstl1strm, %2\n" \
> "1: ldxr %w1, %2\n" \
> insn "\n" \
> @@ -35,45 +39,103 @@ do { \
> : "r" (oparg), "Ir" (-EAGAIN) \
> : "memory"); \
> uaccess_disable_privileged(); \
> -} while (0)
> + \
> + if (!ret) \
> + *oval = oldval; \
> + \
> + return ret; \
> +}
> +
> +LLSC_FUTEX_ATOMIC_OP(add, "add %w3, %w1, %w5")
> +LLSC_FUTEX_ATOMIC_OP(or, "orr %w3, %w1, %w5")
> +LLSC_FUTEX_ATOMIC_OP(and, "and %w3, %w1, %w5")
> +LLSC_FUTEX_ATOMIC_OP(eor, "eor %w3, %w1, %w5")
> +LLSC_FUTEX_ATOMIC_OP(set, "mov %w3, %w5")
Since you're reworking this code, how about we take the opportunity to
use named arguments instead of the numbers?
Will
Hi Will,
> On Sun, Dec 14, 2025 at 11:22:44AM +0000, Yeoreum Yun wrote:
> > Refactor futex atomic operations using ll/sc method with
> > clearing PSTATE.PAN to prepare to apply FEAT_LSUI on them.
> >
> > Signed-off-by: Yeoreum Yun <yeoreum.yun@arm.com>
> > Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
> > ---
> > arch/arm64/include/asm/futex.h | 128 +++++++++++++++++++++------------
> > 1 file changed, 82 insertions(+), 46 deletions(-)
> >
> > diff --git a/arch/arm64/include/asm/futex.h b/arch/arm64/include/asm/futex.h
> > index bc06691d2062..f8cb674bdb3f 100644
> > --- a/arch/arm64/include/asm/futex.h
> > +++ b/arch/arm64/include/asm/futex.h
> > @@ -7,17 +7,21 @@
> >
> > #include <linux/futex.h>
> > #include <linux/uaccess.h>
> > +#include <linux/stringify.h>
> >
> > #include <asm/errno.h>
> >
> > #define FUTEX_MAX_LOOPS 128 /* What's the largest number you can think of? */
> >
> > -#define __futex_atomic_op(insn, ret, oldval, uaddr, tmp, oparg) \
> > -do { \
> > +#define LLSC_FUTEX_ATOMIC_OP(op, insn) \
> > +static __always_inline int \
> > +__llsc_futex_atomic_##op(int oparg, u32 __user *uaddr, int *oval) \
> > +{ \
> > unsigned int loops = FUTEX_MAX_LOOPS; \
> > + int ret, oldval, tmp; \
> > \
> > uaccess_enable_privileged(); \
> > - asm volatile( \
> > + asm volatile("// __llsc_futex_atomic_" #op "\n" \
> > " prfm pstl1strm, %2\n" \
> > "1: ldxr %w1, %2\n" \
> > insn "\n" \
> > @@ -35,45 +39,103 @@ do { \
> > : "r" (oparg), "Ir" (-EAGAIN) \
> > : "memory"); \
> > uaccess_disable_privileged(); \
> > -} while (0)
> > + \
> > + if (!ret) \
> > + *oval = oldval; \
> > + \
> > + return ret; \
> > +}
> > +
> > +LLSC_FUTEX_ATOMIC_OP(add, "add %w3, %w1, %w5")
> > +LLSC_FUTEX_ATOMIC_OP(or, "orr %w3, %w1, %w5")
> > +LLSC_FUTEX_ATOMIC_OP(and, "and %w3, %w1, %w5")
> > +LLSC_FUTEX_ATOMIC_OP(eor, "eor %w3, %w1, %w5")
> > +LLSC_FUTEX_ATOMIC_OP(set, "mov %w3, %w5")
>
> Since you're reworking this code, how about we take the opportunity to
> use named arguments instead of the numbers?
Okay. Let me try this.
--
Sincerely,
Yeoreum Yun
© 2016 - 2026 Red Hat, Inc.