From: Vineet Gupta <Vineet.Gupta1@synopsys.com>
To: linux-snps-arc@lists.infradead.org
Cc: Peter Zijlstra <peterz@infradead.org>,
Will Deacon <will@kernel.org>, Arnd Bergmann <arnd@arndb.de>,
Mark Rutland <mark.rutland@arm.com>,
linux-kernel@vger.kernel.org, linux-arch@vger.kernel.org,
Vladimir Isaev <Vladimir.Isaev@synopsys.com>,
Vineet Gupta <Vineet.Gupta1@synopsys.com>
Subject: [PATCH 05/11] ARC: atomics: implement relaxed variants
Date: Wed, 4 Aug 2021 12:15:48 -0700 [thread overview]
Message-ID: <20210804191554.1252776-6-vgupta@synopsys.com> (raw)
In-Reply-To: <20210804191554.1252776-1-vgupta@synopsys.com>
The current ARC fetch/return atomics provide fully ordered semantics
only with 2 full barriers around the operation.
Instead implement them as relaxed variants without any barriers and
rely on generic code to generate the fully-ordered, acquire and release
varaints by adding the appropriate full barriers.
This helps elide some extra barriers in case of acquire/release/relaxed
calls.
bloat-o-meter for hsdk defconfig shows codegen improvements, although
numbers below inflated due to unrelated inlining heuristic changes
| bloat-o-meter vmlinux-643babe34fd7-non-relaxed vmlinux-45aa05cb44d7-relaxed
| add/remove: 2/5 grow/shrink: 42/1222 up/down: 4158/-14312 (-10154)
| Function old new delta
| ..
| sys_renameat 462 476 +14
| ip_mc_inc_group 424 436 +12
| do_read_cache_page 1882 1894 +12
| ..
| refcount_dec_and_mutex_lock 254 250 -4
| refcount_dec_and_lock_irqsave 258 254 -4
| refcount_dec_and_lock 254 250 -4
| ..
| tcp_v6_route_req 246 238 -8
| tcp_v4_destroy_sock 286 278 -8
| tcp_twsk_unique 352 344 -8
Link: https://lore.kernel.org/r/20180830144344.GW24142@hirez.programming.kicks-ass.net
Suggested-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Vineet Gupta <vgupta@synopsys.com>
---
arch/arc/include/asm/atomic-llsc.h | 32 +++++++++++----------------
arch/arc/include/asm/atomic64-arcv2.h | 24 +++++++++++---------
2 files changed, 26 insertions(+), 30 deletions(-)
diff --git a/arch/arc/include/asm/atomic-llsc.h b/arch/arc/include/asm/atomic-llsc.h
index aab4f2855457..088d348781c1 100644
--- a/arch/arc/include/asm/atomic-llsc.h
+++ b/arch/arc/include/asm/atomic-llsc.h
@@ -22,16 +22,10 @@ static inline void arch_atomic_##op(int i, atomic_t *v) \
} \
#define ATOMIC_OP_RETURN(op, c_op, asm_op) \
-static inline int arch_atomic_##op##_return(int i, atomic_t *v) \
+static inline int arch_atomic_##op##_return_relaxed(int i, atomic_t *v) \
{ \
unsigned int val; \
\
- /* \
- * Explicit full memory barrier needed before/after as \
- * LLOCK/SCOND themselves don't provide any such semantics \
- */ \
- smp_mb(); \
- \
__asm__ __volatile__( \
"1: llock %[val], [%[ctr]] \n" \
" " #asm_op " %[val], %[val], %[i] \n" \
@@ -42,22 +36,17 @@ static inline int arch_atomic_##op##_return(int i, atomic_t *v) \
[i] "ir" (i) \
: "cc"); \
\
- smp_mb(); \
- \
return val; \
}
+#define arch_atomic_add_return_relaxed arch_atomic_add_return_relaxed
+#define arch_atomic_sub_return_relaxed arch_atomic_sub_return_relaxed
+
#define ATOMIC_FETCH_OP(op, c_op, asm_op) \
-static inline int arch_atomic_fetch_##op(int i, atomic_t *v) \
+static inline int arch_atomic_fetch_##op##_relaxed(int i, atomic_t *v) \
{ \
unsigned int val, orig; \
\
- /* \
- * Explicit full memory barrier needed before/after as \
- * LLOCK/SCOND themselves don't provide any such semantics \
- */ \
- smp_mb(); \
- \
__asm__ __volatile__( \
"1: llock %[orig], [%[ctr]] \n" \
" " #asm_op " %[val], %[orig], %[i] \n" \
@@ -69,11 +58,17 @@ static inline int arch_atomic_fetch_##op(int i, atomic_t *v) \
[i] "ir" (i) \
: "cc"); \
\
- smp_mb(); \
- \
return orig; \
}
+#define arch_atomic_fetch_add_relaxed arch_atomic_fetch_add_relaxed
+#define arch_atomic_fetch_sub_relaxed arch_atomic_fetch_sub_relaxed
+
+#define arch_atomic_fetch_and_relaxed arch_atomic_fetch_and_relaxed
+#define arch_atomic_fetch_andnot_relaxed arch_atomic_fetch_andnot_relaxed
+#define arch_atomic_fetch_or_relaxed arch_atomic_fetch_or_relaxed
+#define arch_atomic_fetch_xor_relaxed arch_atomic_fetch_xor_relaxed
+
#define ATOMIC_OPS(op, c_op, asm_op) \
ATOMIC_OP(op, c_op, asm_op) \
ATOMIC_OP_RETURN(op, c_op, asm_op) \
@@ -93,7 +88,6 @@ ATOMIC_OPS(or, |=, or)
ATOMIC_OPS(xor, ^=, xor)
#define arch_atomic_andnot arch_atomic_andnot
-#define arch_atomic_fetch_andnot arch_atomic_fetch_andnot
#undef ATOMIC_OPS
#undef ATOMIC_FETCH_OP
diff --git a/arch/arc/include/asm/atomic64-arcv2.h b/arch/arc/include/asm/atomic64-arcv2.h
index 22ef1cbb94e2..c5a8010fdc97 100644
--- a/arch/arc/include/asm/atomic64-arcv2.h
+++ b/arch/arc/include/asm/atomic64-arcv2.h
@@ -64,12 +64,10 @@ static inline void arch_atomic64_##op(s64 a, atomic64_t *v) \
} \
#define ATOMIC64_OP_RETURN(op, op1, op2) \
-static inline s64 arch_atomic64_##op##_return(s64 a, atomic64_t *v) \
+static inline s64 arch_atomic64_##op##_return_relaxed(s64 a, atomic64_t *v) \
{ \
s64 val; \
\
- smp_mb(); \
- \
__asm__ __volatile__( \
"1: \n" \
" llockd %0, [%1] \n" \
@@ -81,18 +79,17 @@ static inline s64 arch_atomic64_##op##_return(s64 a, atomic64_t *v) \
: "r"(&v->counter), "ir"(a) \
: "cc"); /* memory clobber comes from smp_mb() */ \
\
- smp_mb(); \
- \
return val; \
}
+#define arch_atomic64_add_return_relaxed arch_atomic64_add_return_relaxed
+#define arch_atomic64_sub_return_relaxed arch_atomic64_sub_return_relaxed
+
#define ATOMIC64_FETCH_OP(op, op1, op2) \
-static inline s64 arch_atomic64_fetch_##op(s64 a, atomic64_t *v) \
+static inline s64 arch_atomic64_fetch_##op##_relaxed(s64 a, atomic64_t *v) \
{ \
s64 val, orig; \
\
- smp_mb(); \
- \
__asm__ __volatile__( \
"1: \n" \
" llockd %0, [%2] \n" \
@@ -104,11 +101,17 @@ static inline s64 arch_atomic64_fetch_##op(s64 a, atomic64_t *v) \
: "r"(&v->counter), "ir"(a) \
: "cc"); /* memory clobber comes from smp_mb() */ \
\
- smp_mb(); \
- \
return orig; \
}
+#define arch_atomic64_fetch_add_relaxed arch_atomic64_fetch_add_relaxed
+#define arch_atomic64_fetch_sub_relaxed arch_atomic64_fetch_sub_relaxed
+
+#define arch_atomic64_fetch_and_relaxed arch_atomic64_fetch_and_relaxed
+#define arch_atomic64_fetch_andnot_relaxed arch_atomic64_fetch_andnot_relaxed
+#define arch_atomic64_fetch_or_relaxed arch_atomic64_fetch_or_relaxed
+#define arch_atomic64_fetch_xor_relaxed arch_atomic64_fetch_xor_relaxed
+
#define ATOMIC64_OPS(op, op1, op2) \
ATOMIC64_OP(op, op1, op2) \
ATOMIC64_OP_RETURN(op, op1, op2) \
@@ -128,7 +131,6 @@ ATOMIC64_OPS(or, or, or)
ATOMIC64_OPS(xor, xor, xor)
#define arch_atomic64_andnot arch_atomic64_andnot
-#define arch_atomic64_fetch_andnot arch_atomic64_fetch_andnot
#undef ATOMIC64_OPS
#undef ATOMIC64_FETCH_OP
--
2.25.1
_______________________________________________
linux-snps-arc mailing list
linux-snps-arc@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-snps-arc
next prev parent reply other threads:[~2021-08-04 19:16 UTC|newest]
Thread overview: 19+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-08-04 19:15 [PATCH 00/11] ARC atomics update Vineet Gupta
2021-08-04 19:15 ` [PATCH 01/11] ARC: atomics: disintegrate header Vineet Gupta
2021-08-04 19:15 ` [PATCH 02/11] ARC: atomic: !LLSC: remove hack in atomic_set() for for UP Vineet Gupta
2021-08-04 19:15 ` [PATCH 03/11] ARC: atomic: !LLSC: use int data type consistently Vineet Gupta
2021-08-04 19:15 ` [PATCH 04/11] ARC: atomic64: LLSC: elide unused atomic_{and, or, xor, andnot}_return Vineet Gupta
2021-08-04 19:15 ` Vineet Gupta [this message]
2021-08-04 19:15 ` [PATCH 06/11] ARC: switch to generic bitops Vineet Gupta
2021-08-04 19:15 ` [PATCH 07/11] ARC: bitops: fls/ffs to take int (vs long) per asm-generic defines Vineet Gupta
2021-08-04 19:15 ` [PATCH 08/11] ARC: xchg: !LLSC: remove UP micro-optimization/hack Vineet Gupta
2021-08-04 19:15 ` [PATCH 09/11] ARC: cmpxchg/xchg: rewrite as macros to make type safe Vineet Gupta
2021-08-04 19:15 ` [PATCH 10/11] ARC: cmpxchg/xchg: implement relaxed variants (LLSC config only) Vineet Gupta
2021-08-04 19:15 ` [PATCH 11/11] ARC: atomic_cmpxchg/atomic_xchg: implement relaxed variants Vineet Gupta
2021-08-05 9:02 ` [PATCH 00/11] ARC atomics update Peter Zijlstra
2021-08-05 16:18 ` Vineet Gupta
2021-08-05 17:04 ` Peter Zijlstra
2021-08-05 19:14 ` [RFC] bitops/non-atomic: make @nr unsigned to avoid any DIV Vineet Gupta
2021-08-06 13:42 ` Will Deacon
2021-08-06 19:02 ` Vineet Gupta
2021-08-06 8:41 ` [PATCH 00/11] ARC atomics update Will Deacon
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=20210804191554.1252776-6-vgupta@synopsys.com \
--to=vineet.gupta1@synopsys.com \
--cc=Vladimir.Isaev@synopsys.com \
--cc=arnd@arndb.de \
--cc=linux-arch@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-snps-arc@lists.infradead.org \
--cc=mark.rutland@arm.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;
as well as URLs for NNTP newsgroup(s).