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;
Date:   Mon, 20 Jul 2020 13:49:21 -0700
In-Reply-To: <20200720204925.3654302-1-ndesaulniers@google.com>
Message-Id: <20200720204925.3654302-8-ndesaulniers@google.com>
Mime-Version: 1.0
References: <20200720204925.3654302-1-ndesaulniers@google.com>
Subject: [PATCH v3 07/11] x86/percpu: Clean up percpu_xchg_op()
From:   Nick Desaulniers <ndesaulniers@google.com>
To:     Thomas Gleixner <tglx@linutronix.de>,
        Ingo Molnar <mingo@redhat.com>, Borislav Petkov <bp@alien8.de>
Cc:     Dennis Zhou <dennis@kernel.org>, Tejun Heo <tj@kernel.org>,
        Christoph Lameter <cl@linux.com>, x86@kernel.org,
        "H. Peter Anvin" <hpa@zytor.com>,
        Al Viro <viro@zeniv.linux.org.uk>,
        Andrew Morton <akpm@linux-foundation.org>,
        Peter Zijlstra <peterz@infradead.org>,
        linux-kernel@vger.kernel.org, clang-built-linux@googlegroups.com,
        Brian Gerst <brgerst@gmail.com>,
        Nick Desaulniers <ndesaulniers@google.com>,
        Linus Torvalds <torvalds@linux-foundation.org>
Content-Type: text/plain; charset="UTF-8"
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

From: Brian Gerst <brgerst@gmail.com>

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.

Tested-by: Nick Desaulniers <ndesaulniers@google.com>
Reviewed-by: Nick Desaulniers <ndesaulniers@google.com>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Brian Gerst <brgerst@gmail.com>
Signed-off-by: Nick Desaulniers <ndesaulniers@google.com>
---
 arch/x86/include/asm/percpu.h | 61 +++++++++++------------------------
 1 file changed, 18 insertions(+), 43 deletions(-)

diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index 0776a11e7e11..ac6d7e76c0d4 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -215,46 +215,21 @@ do {									\
  * expensive due to the implied lock prefix.  The processor cannot prefetch
  * cachelines if xchg is used.
  */
-#define percpu_xchg_op(qual, var, nval)					\
+#define percpu_xchg_op(size, qual, _var, _nval)				\
 ({									\
-	typeof(var) pxo_ret__;						\
-	typeof(var) pxo_new__ = (nval);					\
-	switch (sizeof(var)) {						\
-	case 1:								\
-		asm qual ("\n\tmov "__percpu_arg(1)",%%al"		\
-		    "\n1:\tcmpxchgb %2, "__percpu_arg(1)		\
-		    "\n\tjnz 1b"					\
-			    : "=&a" (pxo_ret__), "+m" (var)		\
-			    : "q" (pxo_new__)				\
-			    : "memory");				\
-		break;							\
-	case 2:								\
-		asm qual ("\n\tmov "__percpu_arg(1)",%%ax"		\
-		    "\n1:\tcmpxchgw %2, "__percpu_arg(1)		\
-		    "\n\tjnz 1b"					\
-			    : "=&a" (pxo_ret__), "+m" (var)		\
-			    : "r" (pxo_new__)				\
-			    : "memory");				\
-		break;							\
-	case 4:								\
-		asm qual ("\n\tmov "__percpu_arg(1)",%%eax"		\
-		    "\n1:\tcmpxchgl %2, "__percpu_arg(1)		\
-		    "\n\tjnz 1b"					\
-			    : "=&a" (pxo_ret__), "+m" (var)		\
-			    : "r" (pxo_new__)				\
-			    : "memory");				\
-		break;							\
-	case 8:								\
-		asm qual ("\n\tmov "__percpu_arg(1)",%%rax"		\
-		    "\n1:\tcmpxchgq %2, "__percpu_arg(1)		\
-		    "\n\tjnz 1b"					\
-			    : "=&a" (pxo_ret__), "+m" (var)		\
-			    : "r" (pxo_new__)				\
-			    : "memory");				\
-		break;							\
-	default: __bad_percpu_size();					\
-	}								\
-	pxo_ret__;							\
+	__pcpu_type_##size pxo_old__;					\
+	__pcpu_type_##size pxo_new__ = __pcpu_cast_##size(_nval);	\
+	asm qual (__pcpu_op2_##size("mov", __percpu_arg([var]),		\
+				    "%[oval]")				\
+		  "\n1:\t"						\
+		  __pcpu_op2_##size("cmpxchg", "%[nval]",		\
+				    __percpu_arg([var]))		\
+		  "\n\tjnz 1b"						\
+		  : [oval] "=&a" (pxo_old__),				\
+		    [var] "+m" (_var)					\
+		  : [nval] __pcpu_reg_##size(, pxo_new__)		\
+		  : "memory");						\
+	(typeof(_var))(unsigned long) pxo_old__;			\
 })
 
 /*
@@ -354,9 +329,9 @@ do {									\
 #define this_cpu_or_1(pcp, val)		percpu_to_op(1, volatile, "or", (pcp), val)
 #define this_cpu_or_2(pcp, val)		percpu_to_op(2, volatile, "or", (pcp), val)
 #define this_cpu_or_4(pcp, val)		percpu_to_op(4, volatile, "or", (pcp), val)
-#define this_cpu_xchg_1(pcp, nval)	percpu_xchg_op(volatile, pcp, nval)
-#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 this_cpu_xchg_1(pcp, nval)	percpu_xchg_op(1, volatile, pcp, nval)
+#define this_cpu_xchg_2(pcp, nval)	percpu_xchg_op(2, volatile, pcp, nval)
+#define this_cpu_xchg_4(pcp, nval)	percpu_xchg_op(4, volatile, pcp, nval)
 
 #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)
@@ -409,7 +384,7 @@ do {									\
 #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(8, volatile, pcp, val)
-#define this_cpu_xchg_8(pcp, nval)		percpu_xchg_op(volatile, pcp, nval)
+#define this_cpu_xchg_8(pcp, nval)		percpu_xchg_op(8, volatile, pcp, nval)
 #define this_cpu_cmpxchg_8(pcp, oval, nval)	percpu_cmpxchg_op(volatile, pcp, oval, nval)
 
 /*
-- 
2.28.0.rc0.105.gf9edc3c819-goog