linux-kernel - [PATCH v5 08/13] riscv: Implement xchg8/16() using Zabha

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <20240818063538.6651-9-alexghiti@rivosinc.com>
Date: Sun, 18 Aug 2024 08:35:33 +0200
From: Alexandre Ghiti <alexghiti@...osinc.com>
To: Jonathan Corbet <corbet@....net>,
	Paul Walmsley <paul.walmsley@...ive.com>,
	Palmer Dabbelt <palmer@...belt.com>,
	Albert Ou <aou@...s.berkeley.edu>,
	Conor Dooley <conor@...nel.org>,
	Rob Herring <robh@...nel.org>,
	Krzysztof Kozlowski <krzk+dt@...nel.org>,
	Andrea Parri <parri.andrea@...il.com>,
	Nathan Chancellor <nathan@...nel.org>,
	Peter Zijlstra <peterz@...radead.org>,
	Ingo Molnar <mingo@...hat.com>,
	Will Deacon <will@...nel.org>,
	Waiman Long <longman@...hat.com>,
	Boqun Feng <boqun.feng@...il.com>,
	Arnd Bergmann <arnd@...db.de>,
	Leonardo Bras <leobras@...hat.com>,
	Guo Ren <guoren@...nel.org>,
	linux-doc@...r.kernel.org,
	devicetree@...r.kernel.org,
	linux-kernel@...r.kernel.org,
	linux-riscv@...ts.infradead.org,
	linux-arch@...r.kernel.org
Cc: Alexandre Ghiti <alexghiti@...osinc.com>,
	Andrew Jones <ajones@...tanamicro.com>
Subject: [PATCH v5 08/13] riscv: Implement xchg8/16() using Zabha

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

Signed-off-by: Alexandre Ghiti <alexghiti@...osinc.com>
Reviewed-by: Andrew Jones <ajones@...tanamicro.com>
---
 arch/riscv/include/asm/cmpxchg.h | 65 ++++++++++++++++++++------------
 1 file changed, 41 insertions(+), 24 deletions(-)

diff --git a/arch/riscv/include/asm/cmpxchg.h b/arch/riscv/include/asm/cmpxchg.h
index 05ba8a8e2ef5..19779d4d134a 100644
--- a/arch/riscv/include/asm/cmpxchg.h
+++ b/arch/riscv/include/asm/cmpxchg.h
@@ -14,29 +14,41 @@
 #include <asm/insn-def.h>
 #include <asm/cpufeature-macros.h>
 
-#define __arch_xchg_masked(sc_sfx, 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" sc_sfx " %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_masked(sc_sfx, swap_sfx, prepend, sc_append,		\
+			   swap_append, r, p, n)				\
+({										\
+	if (IS_ENABLED(CONFIG_RISCV_ISA_ZABHA) &&				\
+	    riscv_has_extension_unlikely(RISCV_ISA_EXT_ZABHA)) {		\
+		__asm__ __volatile__ (						\
+			prepend							\
+			"	amoswap" swap_sfx " %0, %z2, %1\n"		\
+			swap_append						\
+			: "=&r" (r), "+A" (*(p))				\
+			: "rJ" (n)						\
+			: "memory");						\
+	} else {								\
+		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" sc_sfx " %1, %1, %2\n"			\
+		       "	bnez %1, 0b\n"					\
+		       sc_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)			\
@@ -59,8 +71,13 @@
 									\
 	switch (sizeof(*__ptr)) {					\
 	case 1:								\
+		__arch_xchg_masked(sc_sfx, ".b" swap_sfx,		\
+				   prepend, sc_append, swap_append,	\
+				   __ret, __ptr, __new);		\
+		break;							\
 	case 2:								\
-		__arch_xchg_masked(sc_sfx, prepend, sc_append,		\
+		__arch_xchg_masked(sc_sfx, ".h" swap_sfx,		\
+				   prepend, sc_append, swap_append,	\
 				   __ret, __ptr, __new);		\
 		break;							\
 	case 4:								\
-- 
2.39.2