arm64: futex: Support futex with FEAT_LSUI

Current futex atomic operations are implemented using LL/SC instructions
while temporarily clearing PSTATE.PAN and setting PSTATE.TCO (if
KASAN_HW_TAGS is enabled). With Armv9.6, FEAT_LSUI provides atomic
instructions for user memory access in the kernel without the need for
PSTATE bits toggling.

Use the FEAT_LSUI instructions to implement the futex atomic operations.
Note that some futex operations do not have a matching LSUI instruction,
(eor or word-sized cmpxchg). For such cases, use cas{al}t to implement
the operation.

Signed-off-by: Yeoreum Yun <yeoreum.yun@arm.com>
[catalin.marinas@arm.com: add comment on -EAGAIN in __lsui_futex_cmpxchg()]
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>

arch/arm64/include/asm/futex.h

@@ -9,6 +9,7 @@
 #include <linux/uaccess.h>
 
 #include <asm/errno.h>
+#include <asm/lsui.h>
 
 #define FUTEX_MAX_LOOPS	128 /* What's the largest number you can think of? */
 
@@ -89,11 +90,166 @@ __llsc_futex_cmpxchg(u32 __user *uaddr, u32 oldval, u32 newval, u32 *oval)
 	return ret;
 }
 
+#ifdef CONFIG_ARM64_LSUI
+
+/*
+ * Wrap LSUI instructions with uaccess_ttbr0_enable()/disable(), as
+ * PAN toggling is not required.
+ */
+
+#define LSUI_FUTEX_ATOMIC_OP(op, asm_op)				\
+static __always_inline int						\
+__lsui_futex_atomic_##op(int oparg, u32 __user *uaddr, int *oval)	\
+{									\
+	int ret = 0;							\
+	int oldval;							\
+									\
+	uaccess_ttbr0_enable();						\
+									\
+	asm volatile("// __lsui_futex_atomic_" #op "\n"			\
+	__LSUI_PREAMBLE							\
+"1:	" #asm_op "al	%w[oparg], %w[oldval], %[uaddr]\n"		\
+"2:\n"									\
+	_ASM_EXTABLE_UACCESS_ERR(1b, 2b, %w[ret])			\
+	: [ret] "+r" (ret), [uaddr] "+Q" (*uaddr),			\
+	  [oldval] "=r" (oldval)					\
+	: [oparg] "r" (oparg)						\
+	: "memory");							\
+									\
+	uaccess_ttbr0_disable();					\
+									\
+	if (!ret)							\
+		*oval = oldval;						\
+	return ret;							\
+}
+
+LSUI_FUTEX_ATOMIC_OP(add, ldtadd)
+LSUI_FUTEX_ATOMIC_OP(or, ldtset)
+LSUI_FUTEX_ATOMIC_OP(andnot, ldtclr)
+LSUI_FUTEX_ATOMIC_OP(set, swpt)
+
+static __always_inline int
+__lsui_cmpxchg64(u64 __user *uaddr, u64 *oldval, u64 newval)
+{
+	int ret = 0;
+
+	uaccess_ttbr0_enable();
+
+	asm volatile("// __lsui_cmpxchg64\n"
+	__LSUI_PREAMBLE
+"1:	casalt	%[oldval], %[newval], %[uaddr]\n"
+"2:\n"
+	_ASM_EXTABLE_UACCESS_ERR(1b, 2b, %w[ret])
+	: [ret] "+r" (ret), [uaddr] "+Q" (*uaddr),
+	  [oldval] "+r" (*oldval)
+	: [newval] "r" (newval)
+	: "memory");
+
+	uaccess_ttbr0_disable();
+
+	return ret;
+}
+
+static __always_inline int
+__lsui_cmpxchg32(u32 __user *uaddr, u32 oldval, u32 newval, u32 *oval)
+{
+	u64 __user *uaddr64;
+	bool futex_pos, other_pos;
+	u32 other, orig_other;
+	union {
+		u32 futex[2];
+		u64 raw;
+	} oval64, orig64, nval64;
+
+	uaddr64 = (u64 __user *)PTR_ALIGN_DOWN(uaddr, sizeof(u64));
+	futex_pos = !IS_ALIGNED((unsigned long)uaddr, sizeof(u64));
+	other_pos = !futex_pos;
+
+	oval64.futex[futex_pos] = oldval;
+	if (get_user(oval64.futex[other_pos], (u32 __user *)uaddr64 + other_pos))
+		return -EFAULT;
+
+	orig64.raw = oval64.raw;
+
+	nval64.futex[futex_pos] = newval;
+	nval64.futex[other_pos] = oval64.futex[other_pos];
+
+	if (__lsui_cmpxchg64(uaddr64, &oval64.raw, nval64.raw))
+		return -EFAULT;
+
+	oldval = oval64.futex[futex_pos];
+	other = oval64.futex[other_pos];
+	orig_other = orig64.futex[other_pos];
+
+	if (other != orig_other)
+		return -EAGAIN;
+
+	*oval = oldval;
+
+	return 0;
+}
+
+static __always_inline int
+__lsui_futex_atomic_and(int oparg, u32 __user *uaddr, int *oval)
+{
+	/*
+	 * Undo the bitwise negation applied to the oparg passed from
+	 * arch_futex_atomic_op_inuser() with FUTEX_OP_ANDN.
+	 */
+	return __lsui_futex_atomic_andnot(~oparg, uaddr, oval);
+}
+
+static __always_inline int
+__lsui_futex_atomic_eor(int oparg, u32 __user *uaddr, int *oval)
+{
+	u32 oldval, newval, val;
+	int ret, i;
+
+	if (get_user(oldval, uaddr))
+		return -EFAULT;
+
+	/*
+	 * there are no ldteor/stteor instructions...
+	 */
+	for (i = 0; i < FUTEX_MAX_LOOPS; i++) {
+		newval = oldval ^ oparg;
+
+		ret = __lsui_cmpxchg32(uaddr, oldval, newval, &val);
+		switch (ret) {
+		case -EFAULT:
+			return ret;
+		case -EAGAIN:
+			continue;
+		}
+
+		if (val == oldval) {
+			*oval = val;
+			return 0;
+		}
+
+		oldval = val;
+	}
+
+	return -EAGAIN;
+}
+
+static __always_inline int
+__lsui_futex_cmpxchg(u32 __user *uaddr, u32 oldval, u32 newval, u32 *oval)
+{
+	/*
+	 * Callers of futex_atomic_cmpxchg_inatomic() already retry on
+	 * -EAGAIN, no need for another loop of max retries.
+	 */
+	return __lsui_cmpxchg32(uaddr, oldval, newval, oval);
+}
+#endif	/* CONFIG_ARM64_LSUI */
+
+
 #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);		\
+	return __lsui_llsc_body(futex_atomic_##op, oparg, uaddr, oval);	\
 }
 
 FUTEX_ATOMIC_OP(add)
@@ -105,7 +261,7 @@ 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);
+	return __lsui_llsc_body(futex_cmpxchg, uaddr, oldval, newval, oval);
 }
 
 static inline int

arch/arm64/include/asm/lsui.h

@@ -0,0 +1,27 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_LSUI_H
+#define __ASM_LSUI_H
+
+#include <linux/compiler_types.h>
+#include <linux/stringify.h>
+#include <asm/alternative.h>
+#include <asm/alternative-macros.h>
+#include <asm/cpucaps.h>
+
+#define __LSUI_PREAMBLE	".arch_extension lsui\n"
+
+#ifdef CONFIG_ARM64_LSUI
+
+#define __lsui_llsc_body(op, ...)					\
+({									\
+	alternative_has_cap_unlikely(ARM64_HAS_LSUI) ?			\
+		__lsui_##op(__VA_ARGS__) : __llsc_##op(__VA_ARGS__);	\
+})
+
+#else	/* CONFIG_ARM64_LSUI */
+
+#define __lsui_llsc_body(op, ...)	__llsc_##op(__VA_ARGS__)
+
+#endif	/* CONFIG_ARM64_LSUI */
+
+#endif	/* __ASM_LSUI_H */