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:   Thu, 23 Jul 2020 10:43:41 -0000
From:   "tip-bot2 for Brian Gerst" <tip-bot2@linutronix.de>
Reply-to: linux-kernel@vger.kernel.org
To:     linux-tip-commits@vger.kernel.org
Subject: [tip: x86/asm] x86/percpu: Clean up percpu_add_return_op()
Cc:     Brian Gerst <brgerst@gmail.com>,
        Nick Desaulniers <ndesaulniers@google.com>,
        Thomas Gleixner <tglx@linutronix.de>,
        Sedat Dilek <sedat.dilek@gmail.com>,
        Linus Torvalds <torvalds@linux-foundation.org>,
        "Peter Zijlstra (Intel)" <peterz@infradead.org>,
        Dennis Zhou <dennis@kernel.org>, x86 <x86@kernel.org>,
        LKML <linux-kernel@vger.kernel.org>
In-Reply-To: <20200720204925.3654302-7-ndesaulniers@google.com>
References: <20200720204925.3654302-7-ndesaulniers@google.com>
MIME-Version: 1.0
Message-ID: <159550102181.4006.3294680559178200499.tip-bot2@tip-bot2>
Robot-ID: <tip-bot2.linutronix.de>
Robot-Unsubscribe: Contact <mailto:tglx@linutronix.de> to get blacklisted from these emails
Content-Type: text/plain; charset="utf-8"
Content-Transfer-Encoding: 7bit
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

The following commit has been merged into the x86/asm branch of tip:

Commit-ID:     bbff583b84a130d4d1234d68906c41690575be36
Gitweb:        https://git.kernel.org/tip/bbff583b84a130d4d1234d68906c41690575be36
Author:        Brian Gerst <brgerst@gmail.com>
AuthorDate:    Mon, 20 Jul 2020 13:49:20 -07:00
Committer:     Thomas Gleixner <tglx@linutronix.de>
CommitterDate: Thu, 23 Jul 2020 11:46:41 +02:00

x86/percpu: Clean up percpu_add_return_op()

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>
Signed-off-by: Nick Desaulniers <ndesaulniers@google.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Nick Desaulniers <ndesaulniers@google.com>
Tested-by: Sedat Dilek <sedat.dilek@gmail.com>
Reviewed-by: Nick Desaulniers <ndesaulniers@google.com>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Dennis Zhou <dennis@kernel.org>
Link: https://lkml.kernel.org/r/20200720204925.3654302-7-ndesaulniers@google.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 9bb5440..0776a11 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)