Received-SPF: pass (google.com: domain of linux-kernel+bounces-192643-linux.lists.archive=gmail.com@vger.kernel.org designates 147.75.80.249 as permitted sender) client-ip=147.75.80.249;
From: Alexandre Ghiti <alexghiti@rivosinc.com>
To: Jonathan Corbet <corbet@lwn.net>,
	Paul Walmsley <paul.walmsley@sifive.com>,
	Palmer Dabbelt <palmer@dabbelt.com>,
	Albert Ou <aou@eecs.berkeley.edu>,
	Peter Zijlstra <peterz@infradead.org>,
	Ingo Molnar <mingo@redhat.com>,
	Will Deacon <will@kernel.org>,
	Waiman Long <longman@redhat.com>,
	Boqun Feng <boqun.feng@gmail.com>,
	Arnd Bergmann <arnd@arndb.de>,
	Leonardo Bras <leobras@redhat.com>,
	Guo Ren <guoren@kernel.org>,
	linux-doc@vger.kernel.org,
	linux-kernel@vger.kernel.org,
	linux-riscv@lists.infradead.org,
	linux-arch@vger.kernel.org
Cc: Alexandre Ghiti <alexghiti@rivosinc.com>
Subject: [PATCH 4/7] riscv: Implement xchg8/16() using Zabha
Date: Tue, 28 May 2024 17:10:49 +0200
Message-Id: <20240528151052.313031-5-alexghiti@rivosinc.com>
In-Reply-To: <20240528151052.313031-1-alexghiti@rivosinc.com>
References: <20240528151052.313031-1-alexghiti@rivosinc.com>
Precedence: bulk
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit

This adds runtime support for Zabha in xchg8/16() operations.

Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
---
 arch/riscv/include/asm/cmpxchg.h | 24 ++++++++++++++++++++++--
 arch/riscv/include/asm/hwcap.h   |  1 +
 arch/riscv/kernel/cpufeature.c   |  1 +
 3 files changed, 24 insertions(+), 2 deletions(-)

diff --git a/arch/riscv/include/asm/cmpxchg.h b/arch/riscv/include/asm/cmpxchg.h
index 0789fbe38b23..43696d9e13aa 100644
--- a/arch/riscv/include/asm/cmpxchg.h
+++ b/arch/riscv/include/asm/cmpxchg.h
@@ -11,8 +11,14 @@
 #include <asm/fence.h>
 #include <asm/alternative.h>
 
-#define __arch_xchg_masked(prepend, append, r, p, n)			\
+#define __arch_xchg_masked(swap_sfx, prepend, append, r, p, n)		\
 ({									\
+	__label__ zabha, end;						\
+									\
+	asm goto(ALTERNATIVE("nop", "j %[zabha]", 0,			\
+			     RISCV_ISA_EXT_ZABHA, 1)			\
+			: : : : zabha);					\
+									\
 	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)	\
@@ -34,6 +40,17 @@
 	       : "memory");						\
 									\
 	r = (__typeof__(*(p)))((__retx & __mask) >> __s);		\
+	goto end;							\
+									\
+zabha:									\
+	__asm__ __volatile__ (						\
+		prepend							\
+		"	amoswap" swap_sfx " %0, %z2, %1\n"		\
+		append							\
+		: "=&r" (r), "+A" (*(p))				\
+		: "rJ" (n)						\
+		: "memory");						\
+end:									\
 })
 
 #define __arch_xchg(sfx, prepend, append, r, p, n)			\
@@ -55,8 +72,11 @@
 									\
 	switch (sizeof(*__ptr)) {					\
 	case 1:								\
+		__arch_xchg_masked(".b" sfx, prepend, append,		\
+				   __ret, __ptr, __new);		\
+		break;							\
 	case 2:								\
-		__arch_xchg_masked(prepend, append,			\
+		__arch_xchg_masked(".h" sfx, prepend, append,		\
 				   __ret, __ptr, __new);		\
 		break;							\
 	case 4:								\
diff --git a/arch/riscv/include/asm/hwcap.h b/arch/riscv/include/asm/hwcap.h
index e17d0078a651..f71ddd2ca163 100644
--- a/arch/riscv/include/asm/hwcap.h
+++ b/arch/riscv/include/asm/hwcap.h
@@ -81,6 +81,7 @@
 #define RISCV_ISA_EXT_ZTSO		72
 #define RISCV_ISA_EXT_ZACAS		73
 #define RISCV_ISA_EXT_XANDESPMU		74
+#define RISCV_ISA_EXT_ZABHA		75
 
 #define RISCV_ISA_EXT_XLINUXENVCFG	127
 
diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c
index 3ed2359eae35..8d0f56dd2f53 100644
--- a/arch/riscv/kernel/cpufeature.c
+++ b/arch/riscv/kernel/cpufeature.c
@@ -257,6 +257,7 @@ const struct riscv_isa_ext_data riscv_isa_ext[] = {
 	__RISCV_ISA_EXT_DATA(zihintpause, RISCV_ISA_EXT_ZIHINTPAUSE),
 	__RISCV_ISA_EXT_DATA(zihpm, RISCV_ISA_EXT_ZIHPM),
 	__RISCV_ISA_EXT_DATA(zacas, RISCV_ISA_EXT_ZACAS),
+	__RISCV_ISA_EXT_DATA(zabha, RISCV_ISA_EXT_ZABHA),
 	__RISCV_ISA_EXT_DATA(zfa, RISCV_ISA_EXT_ZFA),
 	__RISCV_ISA_EXT_DATA(zfh, RISCV_ISA_EXT_ZFH),
 	__RISCV_ISA_EXT_DATA(zfhmin, RISCV_ISA_EXT_ZFHMIN),
-- 
2.39.2