[PATCH] ARM: futex: add SMP futex support when !CPU_USE_DOMAINS

[will.deacon@arm.com (Will Deacon)]

This patch uses the load/store exclusive instructions to add SMP futex
support for ARM.

Since the ARM architecture does not provide instructions for
unprivileged exclusive memory accesses, we can only provide SMP futexes
when CPU domain support is disabled.

Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm/include/asm/futex.h |  137 +++++++++++++++++++++++++++--------------
 1 files changed, 90 insertions(+), 47 deletions(-)

diff --git a/arch/arm/include/asm/futex.h b/arch/arm/include/asm/futex.h
index 199a6b6..8c73900 100644
--- a/arch/arm/include/asm/futex.h
+++ b/arch/arm/include/asm/futex.h
@@ -3,16 +3,74 @@
 
 #ifdef __KERNEL__
 
+#if defined(CONFIG_CPU_USE_DOMAINS) && defined(CONFIG_SMP)
+/* ARM doesn't provide unprivileged exclusive memory accessors */
+#include <asm-generic/futex.h>
+#else
+
+#include <linux/futex.h>
+#include <linux/uaccess.h>
+#include <asm/errno.h>
+
+#define __futex_atomic_ex_table(err_reg)			\
+	"3:\n"							\
+	"	.pushsection __ex_table,\"a\"\n"		\
+	"	.align	3\n"					\
+	"	.long	1b, 4f, 2b, 4f\n"			\
+	"	.popsection\n"					\
+	"	.pushsection .fixup,\"ax\"\n"			\
+	"4:	mov	%0, " err_reg "\n"			\
+	"	b	3b\n"					\
+	"	.popsection"
+
 #ifdef CONFIG_SMP
 
-#include <asm-generic/futex.h>
+#define __futex_atomic_op(insn, ret, oldval, uaddr, oparg)	\
+	smp_mb();						\
+	__asm__ __volatile__(					\
+	"1:	ldrex	%1, [%2]\n"				\
+	"	" insn "\n"					\
+	"2:	strex	%1, %0, [%2]\n"				\
+	"	teq	%1, #0\n"				\
+	"	bne	1b\n"					\
+	"	mov	%0, #0\n"				\
+	__futex_atomic_ex_table("%4")				\
+	: "=&r" (ret), "=&r" (oldval)				\
+	: "r" (uaddr), "r" (oparg), "Ir" (-EFAULT)		\
+	: "cc", "memory")
+
+static inline int
+futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
+			      u32 oldval, u32 newval)
+{
+	int ret;
+	u32 val;
+
+	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
+		return -EFAULT;
+
+	smp_mb();
+	__asm__ __volatile__("@futex_atomic_cmpxchg_inatomic\n"
+	"1:	ldrex	%1, [%4]\n"
+	"	teq	%1, %2\n"
+	"	ite	eq	@ explicit IT needed for the 2b label\n"
+	"2:	strexeq	%0, %3, [%4]\n"
+	"	movne	%0, #0\n"
+	"	teq	%0, #0\n"
+	"	bne	1b\n"
+	__futex_atomic_ex_table("%5")
+	: "=&r" (ret), "=&r" (val)
+	: "r" (oldval), "r" (newval), "r" (uaddr), "Ir" (-EFAULT)
+	: "cc", "memory");
+	smp_mb();
+
+	*uval = val;
+	return ret;
+}
 
 #else /* !SMP, we can work around lack of atomic ops by disabling preemption */
 
-#include <linux/futex.h>
 #include <linux/preempt.h>
-#include <linux/uaccess.h>
-#include <asm/errno.h>
 #include <asm/domain.h>
 
 #define __futex_atomic_op(insn, ret, oldval, uaddr, oparg)	\
@@ -21,20 +79,38 @@
 	"	" insn "\n"					\
 	"2:	" T(str) "	%0, [%2]\n"			\
 	"	mov	%0, #0\n"				\
-	"3:\n"							\
-	"	.pushsection __ex_table,\"a\"\n"		\
-	"	.align	3\n"					\
-	"	.long	1b, 4f, 2b, 4f\n"			\
-	"	.popsection\n"					\
-	"	.pushsection .fixup,\"ax\"\n"			\
-	"4:	mov	%0, %4\n"				\
-	"	b	3b\n"					\
-	"	.popsection"					\
+	__futex_atomic_ex_table("%4")				\
 	: "=&r" (ret), "=&r" (oldval)				\
 	: "r" (uaddr), "r" (oparg), "Ir" (-EFAULT)		\
 	: "cc", "memory")
 
 static inline int
+futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
+			      u32 oldval, u32 newval)
+{
+	int ret = 0;
+	u32 val;
+
+	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
+		return -EFAULT;
+
+	__asm__ __volatile__("@futex_atomic_cmpxchg_inatomic\n"
+	"1:	" T(ldr) "	%1, [%4]\n"
+	"	teq	%1, %2\n"
+	"	it	eq	@ explicit IT needed for the 2b label\n"
+	"2:	" T(streq) "	%3, [%4]\n"
+	__futex_atomic_ex_table("%5")
+	: "+r" (ret), "=&r" (val)
+	: "r" (oldval), "r" (newval), "r" (uaddr), "Ir" (-EFAULT)
+	: "cc", "memory");
+
+	*uval = val;
+	return ret;
+}
+
+#endif /* !SMP */
+
+static inline int
 futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
 {
 	int op = (encoded_op >> 28) & 7;
@@ -87,39 +163,6 @@ futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
 	return ret;
 }
 
-static inline int
-futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
-			      u32 oldval, u32 newval)
-{
-	int ret = 0;
-	u32 val;
-
-	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
-		return -EFAULT;
-
-	__asm__ __volatile__("@futex_atomic_cmpxchg_inatomic\n"
-	"1:	" T(ldr) "	%1, [%4]\n"
-	"	teq	%1, %2\n"
-	"	it	eq	@ explicit IT needed for the 2b label\n"
-	"2:	" T(streq) "	%3, [%4]\n"
-	"3:\n"
-	"	.pushsection __ex_table,\"a\"\n"
-	"	.align	3\n"
-	"	.long	1b, 4f, 2b, 4f\n"
-	"	.popsection\n"
-	"	.pushsection .fixup,\"ax\"\n"
-	"4:	mov	%0, %5\n"
-	"	b	3b\n"
-	"	.popsection"
-	: "+r" (ret), "=&r" (val)
-	: "r" (oldval), "r" (newval), "r" (uaddr), "Ir" (-EFAULT)
-	: "cc", "memory");
-
-	*uval = val;
-	return ret;
-}
-
-#endif /* !SMP */
-
+#endif /* !(CPU_USE_DOMAINS && SMP) */
 #endif /* __KERNEL__ */
 #endif /* _ASM_ARM_FUTEX_H */
-- 
1.7.0.4