diff mbox series

[V3,3/5] riscv: atomic: Optimize memory barrier semantics of LRSC-pairs

Message ID 20220420144417.2453958-4-guoren@kernel.org (mailing list archive)
State New, archived
Headers show
Series riscv: atomic: Optimize AMO instructions usage | expand

Commit Message

Guo Ren April 20, 2022, 2:44 p.m. UTC 
From: Guo Ren <guoren@linux.alibaba.com>

The current implementation is the same with 8e86f0b409a4 ("arm64:
atomics: fix use of acquire + release for full barrier semantics").
RISC-V could combine acquire and release into the AMO instructions
and it could reduce the cost of instruction in performance. Here
is RISC-V ISA 10.2 Load-Reserved/Store-Conditional Instructions:

 - .aq:   The LR/SC sequence can be given acquire semantics by
          setting the aq bit on the LR instruction.
 - .rl:   The LR/SC sequence can be given release semantics by
          setting the rl bit on the SC instruction.
 - .aqrl: Setting the aq bit on the LR instruction, and setting
          both the aq and the rl bit on the SC instruction makes the
          LR/SC sequence sequentially consistent, meaning that it
          cannot be reordered with earlier or later memory operations
          from the same hart.

Software should not set the rl bit on an LR instruction unless the
aq bit is also set, nor should software set the aq bit on an SC
instruction unless the rl bit is also set. LR.rl and SC.aq
instructions are not guaranteed to provide any stronger ordering than
those with both bits clear, but may result in lower performance.

Signed-off-by: Guo Ren <guoren@linux.alibaba.com>
Signed-off-by: Guo Ren <guoren@kernel.org>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Dan Lustig <dlustig@nvidia.com>
Cc: Andrea Parri <parri.andrea@gmail.com>
---
 arch/riscv/include/asm/atomic.h  | 6 ++----
 arch/riscv/include/asm/cmpxchg.h | 6 ++----
 2 files changed, 4 insertions(+), 8 deletions(-)
diff mbox series

Patch

diff --git a/arch/riscv/include/asm/atomic.h b/arch/riscv/include/asm/atomic.h
index 20ce8b83bc18..4aaf5b01e7c6 100644
--- a/arch/riscv/include/asm/atomic.h
+++ b/arch/riscv/include/asm/atomic.h
@@ -382,9 +382,8 @@  static __always_inline int arch_atomic_sub_if_positive(atomic_t *v, int offset)
 		"0:	lr.w     %[p],  %[c]\n"
 		"	sub      %[rc], %[p], %[o]\n"
 		"	bltz     %[rc], 1f\n"
-		"	sc.w.rl  %[rc], %[rc], %[c]\n"
+		"	sc.w.aqrl %[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)
@@ -404,9 +403,8 @@  static __always_inline s64 arch_atomic64_sub_if_positive(atomic64_t *v, s64 offs
 		"0:	lr.d     %[p],  %[c]\n"
 		"	sub      %[rc], %[p], %[o]\n"
 		"	bltz     %[rc], 1f\n"
-		"	sc.d.rl  %[rc], %[rc], %[c]\n"
+		"	sc.d.aqrl %[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)
diff --git a/arch/riscv/include/asm/cmpxchg.h b/arch/riscv/include/asm/cmpxchg.h
index 1af8db92250b..9269fceb86e0 100644
--- a/arch/riscv/include/asm/cmpxchg.h
+++ b/arch/riscv/include/asm/cmpxchg.h
@@ -307,9 +307,8 @@ 
 		__asm__ __volatile__ (					\
 			"0:	lr.w %0, %2\n"				\
 			"	bne  %0, %z3, 1f\n"			\
-			"	sc.w.rl %1, %z4, %2\n"			\
+			"	sc.w.aqrl %1, %z4, %2\n"		\
 			"	bnez %1, 0b\n"				\
-			"	fence rw, rw\n"				\
 			"1:\n"						\
 			: "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr)	\
 			: "rJ" ((long)__old), "rJ" (__new)		\
@@ -319,9 +318,8 @@ 
 		__asm__ __volatile__ (					\
 			"0:	lr.d %0, %2\n"				\
 			"	bne %0, %z3, 1f\n"			\
-			"	sc.d.rl %1, %z4, %2\n"			\
+			"	sc.d.aqrl %1, %z4, %2\n"		\
 			"	bnez %1, 0b\n"				\
-			"	fence rw, rw\n"				\
 			"1:\n"						\
 			: "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr)	\
 			: "rJ" (__old), "rJ" (__new)			\