arm64: futex: Consolidate 'old == new' check in __lsui_cmpxchg32()

The LSUI futex implementation relies on a cmpxchg() loop to implement
FUTEX_OP_XOR, as the architecture doesn't provide unprivileged *EOR
atomics. Since the unprivileged 'CAST' instructions used to implement
the cmpxchg() can only operate on 64-bit memory locations, the
__lsui_cmpxchg32() helper function performs a song and dance to marshall
the 32-bit futex value into the correct part of a 64-bit register and
fill the remaining bytes with the neighbouring data.

A consequence of this structure is that the 'CAST' failure/success
condition ends up being split into two separate 32-bit checks across
__lsui_cmpxchg32() and its caller. This is a little fiddly to read and
introduces some additional local variables which can be avoided if the
check is done in one place.

Tweak __lsui_cmpxchg32() so that it performs the full 64-bit check on
the value returned from the 'CAST' instruction and returns success to
its caller only in the case that the cmpxchg() operation has succeeded.
With that in place, simplify the outer loop in __lsui_futex_atomic_eor()
to pass 'oldval' by reference and return unless the cmpxchg() operation
returns -EAGAIN. __lsui_futex_cmpxchg() then swallows the -EAGAIN if the
futex word has changed.

Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Yeoreum Yun <yeoreum.yun@arm.com>
Reviewed-by: Yeoreum Yun <yeoreum.yun@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>

1 files changed, 22 insertions, 39 deletions

diff --git a/arch/arm64/include/asm/futex.h b/arch/arm64/include/asm/futex.h
index d1d2ff9d323a..79c6d86c38a9 100644
--- a/arch/arm64/include/asm/futex.h
+++ b/arch/arm64/include/asm/futex.h
@@ -151,42 +151,31 @@ __lsui_cmpxchg64(u64 __user *uaddr, u64 *oldval, u64 newval)
 }
 
 static __always_inline int
-__lsui_cmpxchg32(u32 __user *uaddr, u32 oldval, u32 newval, u32 *oval)
+__lsui_cmpxchg32(u32 __user *uaddr, u32 *oldval, u32 newval)
 {
 	u64 __user *uaddr64;
 	bool futex_pos, other_pos;
-	u32 other, orig_other;
 	union {
 		u32 futex[2];
 		u64 raw;
-	} oval64, orig64, nval64;
+	} orig64, oval64, 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))
+	orig64.futex[futex_pos] = *oldval;
+	if (get_user(orig64.futex[other_pos], (u32 __user *)uaddr64 + other_pos))
 		return -EFAULT;
 
-	orig64.raw = oval64.raw;
-
+	nval64 = oval64 = orig64;
 	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;
+	*oldval = oval64.futex[futex_pos];
+	return oval64.raw == orig64.raw ? 0 : -EAGAIN;
 }
 
 static __always_inline int
@@ -202,7 +191,7 @@ __lsui_futex_atomic_and(int oparg, u32 __user *uaddr, int *oval)
 static __always_inline int
 __lsui_futex_atomic_eor(int oparg, u32 __user *uaddr, int *oval)
 {
-	u32 oldval, newval, val;
+	u32 oldval, newval;
 	int ret, i;
 
 	if (get_user(oldval, uaddr))
@@ -214,33 +203,27 @@ __lsui_futex_atomic_eor(int oparg, u32 __user *uaddr, int *oval)
 	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;
+		ret = __lsui_cmpxchg32(uaddr, &oldval, newval);
+		if (ret != -EAGAIN)
+			break;
 	}
 
-	return -EAGAIN;
+	*oval = oldval;
+	return ret;
 }
 
 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);
+	u32 curval = oldval;
+	int ret;
+
+	ret = __lsui_cmpxchg32(uaddr, &curval, newval);
+	if (ret == -EAGAIN && curval != oldval)
+		ret = 0;
+
+	*oval = curval;
+	return ret;
 }
 #endif	/* CONFIG_ARM64_LSUI */