public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: guoren@kernel.org
To: guoren@kernel.org, arnd@arndb.de, palmer@dabbelt.com,
	mark.rutland@arm.com, will@kernel.org, peterz@infradead.org,
	boqun.feng@gmail.com
Cc: linux-arch@vger.kernel.org, linux-kernel@vger.kernel.org,
	linux-riscv@lists.infradead.org,
	Guo Ren <guoren@linux.alibaba.com>
Subject: [PATCH V2 3/3] riscv: atomic: Optimize memory barrier semantics of LRSC-pairs
Date: Tue, 12 Apr 2022 11:49:57 +0800	[thread overview]
Message-ID: <20220412034957.1481088-4-guoren@kernel.org> (raw)
In-Reply-To: <20220412034957.1481088-1-guoren@kernel.org>

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
are the reasons for optimization:
 - Reduce one extra fence instruction
 - The "LR/SC" instruction with "acquire and release" operation is
   less cost than ACQUIRE_BARRIER/RELEASE_BARRIER which used
   precedes-loads/subsequent-stores prohibit to protect only LR/SC
   self-instruction.
 - Putting acquire/release barrier into the loop shouldn't cost
   extra performance problems from the micro-arch design view.
   Because LR and SC are sequential in the loop by RVWMO rules.

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>
---
 arch/riscv/include/asm/atomic.h  |  6 ++----
 arch/riscv/include/asm/cmpxchg.h | 18 ++++++------------
 2 files changed, 8 insertions(+), 16 deletions(-)

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..dfb51c98324d 100644
--- a/arch/riscv/include/asm/cmpxchg.h
+++ b/arch/riscv/include/asm/cmpxchg.h
@@ -215,9 +215,8 @@
 		__asm__ __volatile__ (					\
 			"0:	lr.w %0, %2\n"				\
 			"	bne  %0, %z3, 1f\n"			\
-			"	sc.w %1, %z4, %2\n"			\
+			"	sc.w.aq %1, %z4, %2\n"			\
 			"	bnez %1, 0b\n"				\
-			RISCV_ACQUIRE_BARRIER				\
 			"1:\n"						\
 			: "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr)	\
 			: "rJ" ((long)__old), "rJ" (__new)		\
@@ -227,9 +226,8 @@
 		__asm__ __volatile__ (					\
 			"0:	lr.d %0, %2\n"				\
 			"	bne %0, %z3, 1f\n"			\
-			"	sc.d %1, %z4, %2\n"			\
+			"	sc.d.aq %1, %z4, %2\n"			\
 			"	bnez %1, 0b\n"				\
-			RISCV_ACQUIRE_BARRIER				\
 			"1:\n"						\
 			: "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr)	\
 			: "rJ" (__old), "rJ" (__new)			\
@@ -259,8 +257,7 @@
 	switch (size) {							\
 	case 4:								\
 		__asm__ __volatile__ (					\
-			RISCV_RELEASE_BARRIER				\
-			"0:	lr.w %0, %2\n"				\
+			"0:	lr.w.rl %0, %2\n"			\
 			"	bne  %0, %z3, 1f\n"			\
 			"	sc.w %1, %z4, %2\n"			\
 			"	bnez %1, 0b\n"				\
@@ -271,8 +268,7 @@
 		break;							\
 	case 8:								\
 		__asm__ __volatile__ (					\
-			RISCV_RELEASE_BARRIER				\
-			"0:	lr.d %0, %2\n"				\
+			"0:	lr.d.rl %0, %2\n"			\
 			"	bne %0, %z3, 1f\n"			\
 			"	sc.d %1, %z4, %2\n"			\
 			"	bnez %1, 0b\n"				\
@@ -307,9 +303,8 @@
 		__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 +314,8 @@
 		__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)			\
-- 
2.25.1


  parent reply	other threads:[~2022-04-12  3:50 UTC|newest]

Thread overview: 21+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-04-12  3:49 [PATCH V2 0/3] riscv: atomic: Optimize AMO instructions usage guoren
2022-04-12  3:49 ` [PATCH V2 1/3] riscv: atomic: Cleanup unnecessary definition guoren
2022-04-12  3:49 ` [PATCH V2 2/3] riscv: atomic: Optimize acquire and release for AMO operations guoren
2022-04-12  3:49 ` guoren [this message]
2022-04-13 15:46 ` [PATCH V2 0/3] riscv: atomic: Optimize AMO instructions usage Boqun Feng
2022-04-16 16:49   ` Guo Ren
2022-04-17  2:26     ` Boqun Feng
2022-04-17  4:51       ` Guo Ren
2022-04-17  6:30         ` Boqun Feng
2022-04-17  6:45           ` Guo Ren
2022-04-19 17:12         ` Dan Lustig
2022-04-20  5:33           ` Guo Ren
2022-04-20 17:03             ` Dan Lustig
2022-04-21  9:39               ` Guo Ren
2022-04-21 22:56                 ` Boqun Feng
2022-04-22  1:56                   ` Guo Ren
2022-04-22  3:11                     ` Boqun Feng
2022-04-24  7:52                       ` Guo Ren
2022-04-18 23:41     ` Andrea Parri
2022-04-19 17:13       ` Dan Lustig
2022-04-24  8:33       ` Guo Ren

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20220412034957.1481088-4-guoren@kernel.org \
    --to=guoren@kernel.org \
    --cc=arnd@arndb.de \
    --cc=boqun.feng@gmail.com \
    --cc=guoren@linux.alibaba.com \
    --cc=linux-arch@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-riscv@lists.infradead.org \
    --cc=mark.rutland@arm.com \
    --cc=palmer@dabbelt.com \
    --cc=peterz@infradead.org \
    --cc=will@kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox