Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
From:   Brian Gerst <brgerst@gmail.com>
To:     linux-kernel@vger.kernel.org, x86@kernel.org
Cc:     Thomas Gleixner <tglx@linutronix.de>,
        Ingo Molnar <mingo@kernel.org>, Borislav Petkov <bp@alien8.de>,
        "H . Peter Anvin" <hpa@zytor.com>,
        Andy Lutomirski <luto@kernel.org>,
        Peter Zijlstra <peterz@infradead.org>,
        Nick Desaulniers <ndesaulniers@google.com>,
        Brian Gerst <brgerst@gmail.com>
Subject: [PATCH v2 06/10] x86/percpu: Clean up percpu_add_return_op()
Date:   Sat, 30 May 2020 18:11:23 -0400
Message-Id: <20200530221127.459704-7-brgerst@gmail.com>
In-Reply-To: <20200530221127.459704-1-brgerst@gmail.com>
References: <20200530221127.459704-1-brgerst@gmail.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

The core percpu macros already have a switch on the data size, so the switch
in the x86 code is redundant and produces more dead code.

Also use appropriate types for the width of the instructions.  This avoids
errors when compiling with Clang.

Signed-off-by: Brian Gerst <brgerst@gmail.com>
---
 arch/x86/include/asm/percpu.h | 51 +++++++++++------------------------
 1 file changed, 16 insertions(+), 35 deletions(-)

diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index 9bb5440d98d3..0776a11e7e11 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -199,34 +199,15 @@ do {									\
 /*
  * Add return operation
  */
-#define percpu_add_return_op(qual, var, val)				\
+#define percpu_add_return_op(size, qual, _var, _val)			\
 ({									\
-	typeof(var) paro_ret__ = val;					\
-	switch (sizeof(var)) {						\
-	case 1:								\
-		asm qual ("xaddb %0, "__percpu_arg(1)			\
-			    : "+q" (paro_ret__), "+m" (var)		\
-			    : : "memory");				\
-		break;							\
-	case 2:								\
-		asm qual ("xaddw %0, "__percpu_arg(1)			\
-			    : "+r" (paro_ret__), "+m" (var)		\
-			    : : "memory");				\
-		break;							\
-	case 4:								\
-		asm qual ("xaddl %0, "__percpu_arg(1)			\
-			    : "+r" (paro_ret__), "+m" (var)		\
-			    : : "memory");				\
-		break;							\
-	case 8:								\
-		asm qual ("xaddq %0, "__percpu_arg(1)			\
-			    : "+r" (paro_ret__), "+m" (var)		\
-			    : : "memory");				\
-		break;							\
-	default: __bad_percpu_size();					\
-	}								\
-	paro_ret__ += val;						\
-	paro_ret__;							\
+	__pcpu_type_##size paro_tmp__ = __pcpu_cast_##size(_val);	\
+	asm qual (__pcpu_op2_##size("xadd", "%[tmp]",			\
+				     __percpu_arg([var]))		\
+		  : [tmp] __pcpu_reg_##size("+", paro_tmp__),		\
+		    [var] "+m" (_var)					\
+		  : : "memory");					\
+	(typeof(_var))(unsigned long) (paro_tmp__ + _val);		\
 })
 
 /*
@@ -377,16 +358,16 @@ do {									\
 #define this_cpu_xchg_2(pcp, nval)	percpu_xchg_op(volatile, pcp, nval)
 #define this_cpu_xchg_4(pcp, nval)	percpu_xchg_op(volatile, pcp, nval)
 
-#define raw_cpu_add_return_1(pcp, val)		percpu_add_return_op(, pcp, val)
-#define raw_cpu_add_return_2(pcp, val)		percpu_add_return_op(, pcp, val)
-#define raw_cpu_add_return_4(pcp, val)		percpu_add_return_op(, pcp, val)
+#define raw_cpu_add_return_1(pcp, val)		percpu_add_return_op(1, , pcp, val)
+#define raw_cpu_add_return_2(pcp, val)		percpu_add_return_op(2, , pcp, val)
+#define raw_cpu_add_return_4(pcp, val)		percpu_add_return_op(4, , pcp, val)
 #define raw_cpu_cmpxchg_1(pcp, oval, nval)	percpu_cmpxchg_op(, pcp, oval, nval)
 #define raw_cpu_cmpxchg_2(pcp, oval, nval)	percpu_cmpxchg_op(, pcp, oval, nval)
 #define raw_cpu_cmpxchg_4(pcp, oval, nval)	percpu_cmpxchg_op(, pcp, oval, nval)
 
-#define this_cpu_add_return_1(pcp, val)		percpu_add_return_op(volatile, pcp, val)
-#define this_cpu_add_return_2(pcp, val)		percpu_add_return_op(volatile, pcp, val)
-#define this_cpu_add_return_4(pcp, val)		percpu_add_return_op(volatile, pcp, val)
+#define this_cpu_add_return_1(pcp, val)		percpu_add_return_op(1, volatile, pcp, val)
+#define this_cpu_add_return_2(pcp, val)		percpu_add_return_op(2, volatile, pcp, val)
+#define this_cpu_add_return_4(pcp, val)		percpu_add_return_op(4, volatile, pcp, val)
 #define this_cpu_cmpxchg_1(pcp, oval, nval)	percpu_cmpxchg_op(volatile, pcp, oval, nval)
 #define this_cpu_cmpxchg_2(pcp, oval, nval)	percpu_cmpxchg_op(volatile, pcp, oval, nval)
 #define this_cpu_cmpxchg_4(pcp, oval, nval)	percpu_cmpxchg_op(volatile, pcp, oval, nval)
@@ -418,7 +399,7 @@ do {									\
 #define raw_cpu_add_8(pcp, val)			percpu_add_op(8, , (pcp), val)
 #define raw_cpu_and_8(pcp, val)			percpu_to_op(8, , "and", (pcp), val)
 #define raw_cpu_or_8(pcp, val)			percpu_to_op(8, , "or", (pcp), val)
-#define raw_cpu_add_return_8(pcp, val)		percpu_add_return_op(, pcp, val)
+#define raw_cpu_add_return_8(pcp, val)		percpu_add_return_op(8, , pcp, val)
 #define raw_cpu_xchg_8(pcp, nval)		raw_percpu_xchg_op(pcp, nval)
 #define raw_cpu_cmpxchg_8(pcp, oval, nval)	percpu_cmpxchg_op(, pcp, oval, nval)
 
@@ -427,7 +408,7 @@ do {									\
 #define this_cpu_add_8(pcp, val)		percpu_add_op(8, volatile, (pcp), val)
 #define this_cpu_and_8(pcp, val)		percpu_to_op(8, volatile, "and", (pcp), val)
 #define this_cpu_or_8(pcp, val)			percpu_to_op(8, volatile, "or", (pcp), val)
-#define this_cpu_add_return_8(pcp, val)		percpu_add_return_op(volatile, pcp, val)
+#define this_cpu_add_return_8(pcp, val)		percpu_add_return_op(8, volatile, pcp, val)
 #define this_cpu_xchg_8(pcp, nval)		percpu_xchg_op(volatile, pcp, nval)
 #define this_cpu_cmpxchg_8(pcp, oval, nval)	percpu_cmpxchg_op(volatile, pcp, oval, nval)
 
-- 
2.25.4