Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   Leonardo Bras <leobras@redhat.com>
To:     Will Deacon <will@kernel.org>,
        Peter Zijlstra <peterz@infradead.org>,
        Boqun Feng <boqun.feng@gmail.com>,
        Mark Rutland <mark.rutland@arm.com>,
        Paul Walmsley <paul.walmsley@sifive.com>,
        Palmer Dabbelt <palmer@dabbelt.com>,
        Albert Ou <aou@eecs.berkeley.edu>,
        Leonardo Bras <leobras@redhat.com>,
        Andrea Parri <parri.andrea@gmail.com>,
        Andrzej Hajda <andrzej.hajda@intel.com>,
        Arnd Bergmann <arnd@arndb.de>,
        Palmer Dabbelt <palmer@rivosinc.com>,
        Guo Ren <guoren@kernel.org>
Cc:     linux-kernel@vger.kernel.org, linux-riscv@lists.infradead.org
Subject: [RFC PATCH v5 5/5] riscv/cmpxchg: Implement xchg for variables of size 1 and 2
Date:   Thu, 10 Aug 2023 01:03:47 -0300
Message-ID: <20230810040349.92279-7-leobras@redhat.com>
In-Reply-To: <20230810040349.92279-2-leobras@redhat.com>
References: <20230810040349.92279-2-leobras@redhat.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

xchg for variables of size 1-byte and 2-bytes is not yet available for
riscv, even though its present in other architectures such as arm64 and
x86. This could lead to not being able to implement some locking mechanisms
or requiring some rework to make it work properly.

Implement 1-byte and 2-bytes xchg in order to achieve parity with other
architectures.

Signed-off-by: Leonardo Bras <leobras@redhat.com>
---
 arch/riscv/include/asm/cmpxchg.h | 31 +++++++++++++++++++++++++++++++
 1 file changed, 31 insertions(+)

diff --git a/arch/riscv/include/asm/cmpxchg.h b/arch/riscv/include/asm/cmpxchg.h
index ac9d0eeb74e6..26cea2395aae 100644
--- a/arch/riscv/include/asm/cmpxchg.h
+++ b/arch/riscv/include/asm/cmpxchg.h
@@ -11,6 +11,31 @@
 #include <asm/barrier.h>
 #include <asm/fence.h>
 
+#define __arch_xchg_masked(prepend, append, r, p, n)			\
+({									\
+	u32 *__ptr32b = (u32 *)((ulong)(p) & ~0x3);			\
+	ulong __s = ((ulong)(p) & (0x4 - sizeof(*p))) * BITS_PER_BYTE;	\
+	ulong __mask = GENMASK(((sizeof(*p)) * BITS_PER_BYTE) - 1, 0)	\
+			<< __s;						\
+	ulong __newx = (ulong)(n) << __s;				\
+	ulong __retx;							\
+	ulong __rc;							\
+									\
+	__asm__ __volatile__ (						\
+	       prepend							\
+	       "0:	lr.w %0, %2\n"					\
+	       "	and  %1, %0, %z4\n"				\
+	       "	or   %1, %1, %z3\n"				\
+	       "	sc.w %1, %1, %2\n"				\
+	       "	bnez %1, 0b\n"					\
+	       append							\
+	       : "=&r" (__retx), "=&r" (__rc), "+A" (*(__ptr32b))	\
+	       : "rJ" (__newx), "rJ" (~__mask)				\
+	       : "memory");						\
+									\
+	r = (__typeof__(*(p)))((__retx & __mask) >> __s);		\
+})
+
 #define __arch_xchg(sfx, prepend, append, r, p, n)			\
 ({									\
 	__asm__ __volatile__ (						\
@@ -27,7 +52,13 @@
 	__typeof__(ptr) __ptr = (ptr);					\
 	__typeof__(*(__ptr)) __new = (new);				\
 	__typeof__(*(__ptr)) __ret;					\
+									\
 	switch (sizeof(*__ptr)) {					\
+	case 1:								\
+	case 2:								\
+		__arch_xchg_masked(prepend, append,			\
+				   __ret, __ptr, __new);		\
+		break;							\
 	case 4:								\
 		__arch_xchg(".w" sfx, prepend, append,			\
 			      __ret, __ptr, __new);			\
-- 
2.41.0