linux-kernel - [PATCH V4 2/5] riscv: atomic: Optimize dec_if

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]

Date:   Thu,  5 May 2022 11:55:23 +0800
From:   guoren@...nel.org
To:     guoren@...nel.org, arnd@...db.de, palmer@...belt.com,
        mark.rutland@....com, will@...nel.org, peterz@...radead.org,
        boqun.feng@...il.com, dlustig@...dia.com, parri.andrea@...il.com
Cc:     linux-arch@...r.kernel.org, linux-kernel@...r.kernel.org,
        linux-riscv@...ts.infradead.org, Guo Ren <guoren@...ux.alibaba.com>
Subject: [PATCH V4 2/5] riscv: atomic: Optimize dec_if_positive functions

From: Guo Ren <guoren@...ux.alibaba.com>

Current implementation wastes another register to pass the
argument, but we only need addi to calculate the result. Optimize
the code with minimize the usage of registers.

Signed-off-by: Guo Ren <guoren@...ux.alibaba.com>
Signed-off-by: Guo Ren <guoren@...nel.org>
Cc: Palmer Dabbelt <palmer@...belt.com>
Cc: Mark Rutland <mark.rutland@....com>
Cc: Dan Lustig <dlustig@...dia.com>
Cc: Andrea Parri <parri.andrea@...il.com>
---
 arch/riscv/include/asm/atomic.h | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/arch/riscv/include/asm/atomic.h b/arch/riscv/include/asm/atomic.h
index ac9bdf4fc404..f3c6a6eac02a 100644
--- a/arch/riscv/include/asm/atomic.h
+++ b/arch/riscv/include/asm/atomic.h
@@ -310,47 +310,47 @@ ATOMIC_OPS()
 #undef ATOMIC_OPS
 #undef ATOMIC_OP
 
-static __always_inline int arch_atomic_sub_if_positive(atomic_t *v, int offset)
+static __always_inline int arch_atomic_dec_if_positive(atomic_t *v)
 {
        int prev, rc;
 
 	__asm__ __volatile__ (
 		"0:	lr.w     %[p],  %[c]\n"
-		"	sub      %[rc], %[p], %[o]\n"
+		"	addi     %[rc], %[p], -1\n"
 		"	bltz     %[rc], 1f\n"
 		"	sc.w.rl  %[rc], %[rc], %[c]\n"
 		"	bnez     %[rc], 0b\n"
 		"	fence    rw, rw\n"
 		"1:\n"
 		: [p]"=&r" (prev), [rc]"=&r" (rc), [c]"+A" (v->counter)
-		: [o]"r" (offset)
+		:
 		: "memory");
-	return prev - offset;
+	return prev - 1;
 }
 
-#define arch_atomic_dec_if_positive(v)	arch_atomic_sub_if_positive(v, 1)
+#define arch_atomic_dec_if_positive arch_atomic_dec_if_positive
 
 #ifndef CONFIG_GENERIC_ATOMIC64
-static __always_inline s64 arch_atomic64_sub_if_positive(atomic64_t *v, s64 offset)
+static __always_inline s64 arch_atomic64_dec_if_positive(atomic64_t *v)
 {
        s64 prev;
        long rc;
 
 	__asm__ __volatile__ (
 		"0:	lr.d     %[p],  %[c]\n"
-		"	sub      %[rc], %[p], %[o]\n"
+		"	addi      %[rc], %[p], -1\n"
 		"	bltz     %[rc], 1f\n"
 		"	sc.d.rl  %[rc], %[rc], %[c]\n"
 		"	bnez     %[rc], 0b\n"
 		"	fence    rw, rw\n"
 		"1:\n"
 		: [p]"=&r" (prev), [rc]"=&r" (rc), [c]"+A" (v->counter)
-		: [o]"r" (offset)
+		:
 		: "memory");
-	return prev - offset;
+	return prev - 1;
 }
 
-#define arch_atomic64_dec_if_positive(v)	arch_atomic64_sub_if_positive(v, 1)
+#define arch_atomic64_dec_if_positive	arch_atomic64_dec_if_positive
 #endif
 
 #endif /* _ASM_RISCV_ATOMIC_H */
-- 
2.25.1