From: Peter Zijlstra <peterz@infradead.org>
To: Vineet Gupta <Vineet.Gupta1@synopsys.com>
Cc: "torvalds@linux-foundation.org" <torvalds@linux-foundation.org>,
"mingo@kernel.org" <mingo@kernel.org>,
"tglx@linutronix.de" <tglx@linutronix.de>,
"will.deacon@arm.com" <will.deacon@arm.com>,
"paulmck@linux.vnet.ibm.com" <paulmck@linux.vnet.ibm.com>,
"boqun.feng@gmail.com" <boqun.feng@gmail.com>,
"waiman.long@hpe.com" <waiman.long@hpe.com>,
"fweisbec@gmail.com" <fweisbec@gmail.com>,
"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
"linux-arch@vger.kernel.org" <linux-arch@vger.kernel.org>,
"rth@twiddle.net" <rth@twiddle.net>,
"linux@arm.linux.org.uk" <linux@arm.linux.org.uk>,
"egtvedt@samfundet.no" <egtvedt@samfundet.no>,
"realmz6@gmail.com" <realmz6@gmail.com>,
"ysato@users.sourceforge.jp" <ysato@users.sourceforge.jp>,
"rkuo@codeaurora.org" <rkuo@codeaurora.org>,
"tony.luck@intel.com" <tony.luck@intel.com>,
"geert@linux-m68k.org" <geert@linux-m68k.org>,
"james.hogan@imgtec.com" <james.hogan@imgtec.com>,
"ralf@linux-mips.org" <ralf@linux-mips.org>,
"dhowells@redhat.com" <dhowells@redhat.com>,
"jejb@parisc-linux.org" <jejb@parisc-linux.org>,
"mpe@ellerman.id.au" <mpe@ellerman.id.au>,
"schwidefsky@de.ibm.com" <schwidefsky@de.ibm.com>,
"dalias@libc.org" <dalias@libc.org>,
"davem@davemloft.net" <davem@davemloft.net>,
"cmetcalf@mellanox.com" <cmetcalf@mellanox.com>,
"jcmvbkbc@gmail.com" <jcmvbkbc@gmail.com>,
"arnd@arndb.de" <arnd@arndb.de>,
"dbueso@suse.de" <dbueso@suse.de>,
"fengguang.wu@intel.com" <fengguang.wu@intel.com>
Subject: Re: [RFC][PATCH 03/31] locking,arc: Implement atomic_fetch_{add,sub,and,andnot,or,xor}()
Date: Fri, 22 Apr 2016 16:16:14 +0200 [thread overview]
Message-ID: <20160422141614.GP3430@twins.programming.kicks-ass.net> (raw)
In-Reply-To: <C2D7FE5348E1B147BCA15975FBA23075F4E9EF11@us01wembx1.internal.synopsys.com>
On Fri, Apr 22, 2016 at 10:50:41AM +0000, Vineet Gupta wrote:
> > +#define ATOMIC_FETCH_OP(op, c_op, asm_op) \
> > +static inline int atomic_fetch_##op(int i, atomic_t *v) \
> > +{ \
> > + unsigned int val, result; \
> > + SCOND_FAIL_RETRY_VAR_DEF \
> > + \
> > + /* \
> > + * Explicit full memory barrier needed before/after as \
> > + * LLOCK/SCOND thmeselves don't provide any such semantics \
> > + */ \
> > + smp_mb(); \
> > + \
> > + __asm__ __volatile__( \
> > + "1: llock %[val], [%[ctr]] \n" \
> > + " mov %[result], %[val] \n" \
>
> Calling it result could be a bit confusing, this is meant to be the "orig" value.
> So it indeed "result" of the API, but for atomic operation it is pristine value.
>
> Also we can optimize away that MOV - given there are plenty of regs, so
>
> > + " " #asm_op " %[val], %[val], %[i] \n" \
> > + " scond %[val], [%[ctr]] \n" \
>
> Instead have
>
> + " " #asm_op " %[result], %[val], %[i] \n" \
> + " scond %[result], [%[ctr]] \n" \
>
>
Indeed, how about something like so?
---
Subject: locking,arc: Implement atomic_fetch_{add,sub,and,andnot,or,xor}()
From: Peter Zijlstra <peterz@infradead.org>
Date: Mon Apr 18 01:16:09 CEST 2016
Implement FETCH-OP atomic primitives, these are very similar to the
existing OP-RETURN primitives we already have, except they return the
value of the atomic variable _before_ modification.
This is especially useful for irreversible operations -- such as
bitops (because it becomes impossible to reconstruct the state prior
to modification).
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
arch/arc/include/asm/atomic.h | 69 ++++++++++++++++++++++++++++++++++++++----
1 file changed, 64 insertions(+), 5 deletions(-)
--- a/arch/arc/include/asm/atomic.h
+++ b/arch/arc/include/asm/atomic.h
@@ -102,6 +102,37 @@ static inline int atomic_##op##_return(i
return val; \
}
+#define ATOMIC_FETCH_OP(op, c_op, asm_op) \
+static inline int atomic_fetch_##op(int i, atomic_t *v) \
+{ \
+ unsigned int val, orig; \
+ SCOND_FAIL_RETRY_VAR_DEF \
+ \
+ /* \
+ * Explicit full memory barrier needed before/after as \
+ * LLOCK/SCOND thmeselves don't provide any such semantics \
+ */ \
+ smp_mb(); \
+ \
+ __asm__ __volatile__( \
+ "1: llock %[orig], [%[ctr]] \n" \
+ " " #asm_op " %[val], %[orig], %[i] \n" \
+ " scond %[val], [%[ctr]] \n" \
+ " \n" \
+ SCOND_FAIL_RETRY_ASM \
+ \
+ : [val] "=&r" (val), \
+ [orig] "=&r" (orig) \
+ SCOND_FAIL_RETRY_VARS \
+ : [ctr] "r" (&v->counter), \
+ [i] "ir" (i) \
+ : "cc"); \
+ \
+ smp_mb(); \
+ \
+ return orig; \
+}
+
#else /* !CONFIG_ARC_HAS_LLSC */
#ifndef CONFIG_SMP
@@ -164,23 +196,49 @@ static inline int atomic_##op##_return(i
return temp; \
}
+#define ATOMIC_FETCH_OP(op, c_op, asm_op) \
+static inline int atomic_fetch_##op(int i, atomic_t *v) \
+{ \
+ unsigned long flags; \
+ unsigned long orig; \
+ \
+ /* \
+ * spin lock/unlock provides the needed smp_mb() before/after \
+ */ \
+ atomic_ops_lock(flags); \
+ orig = v->counter; \
+ v->counter c_op i; \
+ atomic_ops_unlock(flags); \
+ \
+ return orig; \
+}
+
#endif /* !CONFIG_ARC_HAS_LLSC */
#define ATOMIC_OPS(op, c_op, asm_op) \
ATOMIC_OP(op, c_op, asm_op) \
- ATOMIC_OP_RETURN(op, c_op, asm_op)
+ ATOMIC_OP_RETURN(op, c_op, asm_op) \
+ ATOMIC_FETCH_OP(op, c_op, asm_op)
ATOMIC_OPS(add, +=, add)
ATOMIC_OPS(sub, -=, sub)
#define atomic_andnot atomic_andnot
-ATOMIC_OP(and, &=, and)
-ATOMIC_OP(andnot, &= ~, bic)
-ATOMIC_OP(or, |=, or)
-ATOMIC_OP(xor, ^=, xor)
+#define atomic_fetch_or atomic_fetch_or
+
+#undef ATOMIC_OPS
+#define ATOMIC_OPS(op, c_op, asm_op) \
+ ATOMIC_OP(op, c_op, asm_op) \
+ ATOMIC_FETCH_OP(op, c_op, asm_op)
+
+ATOMIC_OPS(and, &=, and)
+ATOMIC_OPS(andnot, &= ~, bic)
+ATOMIC_OPS(or, |=, or)
+ATOMIC_OPS(xor, ^=, xor)
#undef ATOMIC_OPS
+#undef ATOMIC_FETCH_OP
#undef ATOMIC_OP_RETURN
#undef ATOMIC_OP
#undef SCOND_FAIL_RETRY_VAR_DEF
next prev parent reply other threads:[~2016-04-22 14:16 UTC|newest]
Thread overview: 67+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-04-22 9:04 [RFC][PATCH 00/31] implement atomic_fetch_$op Peter Zijlstra
2016-04-22 9:04 ` [RFC][PATCH 01/31] locking: Flip arguments to atomic_fetch_or Peter Zijlstra
2016-04-22 10:54 ` Will Deacon
2016-04-22 11:09 ` Geert Uytterhoeven
2016-04-22 14:18 ` Peter Zijlstra
2016-04-22 9:04 ` [RFC][PATCH 02/31] locking,alpha: Implement atomic{,64}_fetch_{add,sub,and,andnot,or,xor}() Peter Zijlstra
2016-04-22 16:57 ` Richard Henderson
2016-04-23 1:55 ` Peter Zijlstra
2016-04-22 9:04 ` [RFC][PATCH 03/31] locking,arc: Implement atomic_fetch_{add,sub,and,andnot,or,xor}() Peter Zijlstra
2016-04-22 10:50 ` Vineet Gupta
2016-04-22 14:16 ` Peter Zijlstra [this message]
2016-04-25 4:26 ` Vineet Gupta
2016-04-22 14:26 ` Peter Zijlstra
2016-04-22 9:04 ` [RFC][PATCH 04/31] locking,arm: Implement atomic{,64}_fetch_{add,sub,and,andnot,or,xor}{,_relaxed,_acquire,_release}() Peter Zijlstra
2016-04-22 11:35 ` Will Deacon
2016-04-22 9:04 ` [RFC][PATCH 05/31] locking,arm64: " Peter Zijlstra
2016-04-22 11:08 ` Will Deacon
2016-04-22 14:23 ` Will Deacon
2016-04-22 9:04 ` [RFC][PATCH 06/31] locking,avr32: Implement atomic_fetch_{add,sub,and,or,xor}() Peter Zijlstra
2016-04-22 11:58 ` Hans-Christian Noren Egtvedt
2016-04-22 9:04 ` [RFC][PATCH 07/31] locking,blackfin: " Peter Zijlstra
2016-04-22 9:04 ` [RFC][PATCH 08/31] locking,frv: Implement atomic{,64}_fetch_{add,sub,and,or,xor}() Peter Zijlstra
2016-04-22 9:04 ` [RFC][PATCH 09/31] locking,h8300: Implement atomic_fetch_{add,sub,and,or,xor}() Peter Zijlstra
2016-04-22 9:04 ` [RFC][PATCH 10/31] locking,hexagon: " Peter Zijlstra
2016-04-23 2:16 ` Peter Zijlstra
2016-04-26 0:39 ` Richard Kuo
2016-04-22 9:04 ` [RFC][PATCH 11/31] locking,ia64: Implement atomic{,64}_fetch_{add,sub,and,or,xor}() Peter Zijlstra
2016-04-22 9:04 ` [RFC][PATCH 12/31] locking,m32r: Implement atomic_fetch_{add,sub,and,or,xor}() Peter Zijlstra
2016-04-22 9:04 ` [RFC][PATCH 13/31] locking,m68k: " Peter Zijlstra
2016-04-22 9:04 ` [RFC][PATCH 14/31] locking,metag: " Peter Zijlstra
2016-04-30 0:20 ` James Hogan
2016-05-02 8:15 ` Peter Zijlstra
2016-04-22 9:04 ` [RFC][PATCH 15/31] locking,mips: Implement atomic{,64}_fetch_{add,sub,and,or,xor}() Peter Zijlstra
2016-04-22 9:04 ` [RFC][PATCH 16/31] locking,mn10300: Implement atomic_fetch_{add,sub,and,or,xor}() Peter Zijlstra
2016-04-22 9:04 ` [RFC][PATCH 17/31] locking,parisc: Implement atomic{,64}_fetch_{add,sub,and,or,xor}() Peter Zijlstra
2016-04-22 9:04 ` [RFC][PATCH 18/31] locking,powerpc: Implement atomic{,64}_fetch_{add,sub,and,or,xor}{,_relaxed,_acquire,_release}() Peter Zijlstra
2016-04-22 16:41 ` Boqun Feng
2016-04-23 2:31 ` Peter Zijlstra
2016-04-22 9:04 ` [RFC][PATCH 19/31] locking,s390: Implement atomic{,64}_fetch_{add,sub,and,or,xor}() Peter Zijlstra
2016-04-25 8:06 ` Martin Schwidefsky
2016-04-25 8:26 ` Peter Zijlstra
2016-04-22 9:04 ` [RFC][PATCH 20/31] locking,sh: Implement atomic_fetch_{add,sub,and,or,xor}() Peter Zijlstra
2016-04-22 9:04 ` [RFC][PATCH 21/31] locking,sparc: Implement atomic{,64}_fetch_{add,sub,and,or,xor}() Peter Zijlstra
2016-04-22 9:04 ` [RFC][PATCH 22/31] locking,tile: " Peter Zijlstra
2016-04-25 21:10 ` Chris Metcalf
2016-04-26 14:00 ` [PATCH] tile: clarify barrier semantics of atomic_add_return Chris Metcalf
[not found] ` <571E840A.8090703@mellanox.com>
2016-04-26 15:28 ` [RFC][PATCH 22/31] locking,tile: Implement atomic{,64}_fetch_{add,sub,and,or,xor}() Peter Zijlstra
2016-04-26 15:32 ` Chris Metcalf
2016-04-22 9:04 ` [RFC][PATCH 23/31] locking,x86: " Peter Zijlstra
2016-04-22 9:04 ` [RFC][PATCH 24/31] locking,xtensa: Implement atomic_fetch_{add,sub,and,or,xor}() Peter Zijlstra
2016-04-22 9:04 ` [RFC][PATCH 25/31] locking: Fix atomic64_relaxed bits Peter Zijlstra
2016-04-22 9:04 ` [RFC][PATCH 26/31] locking: Implement atomic{,64,_long}_fetch_{add,sub,and,andnot,or,xor}{,_relaxed,_acquire,_release}() Peter Zijlstra
2016-04-22 9:04 ` [RFC][PATCH 27/31] locking: Remove linux/atomic.h:atomic_fetch_or Peter Zijlstra
2016-04-22 13:02 ` Will Deacon
2016-04-22 14:21 ` Peter Zijlstra
2016-04-22 9:04 ` [RFC][PATCH 28/31] locking: Remove the deprecated atomic_{set,clear}_mask() functions Peter Zijlstra
2016-04-22 9:04 ` [RFC][PATCH 29/31] locking,alpha: Convert to _relaxed atomics Peter Zijlstra
2016-04-22 9:04 ` [RFC][PATCH 30/31] locking,mips: " Peter Zijlstra
2016-04-22 9:04 ` [RFC][PATCH 31/31] locking,qrwlock: Employ atomic_fetch_add_acquire() Peter Zijlstra
2016-04-22 14:25 ` Waiman Long
2016-04-22 9:44 ` [RFC][PATCH 00/31] implement atomic_fetch_$op Peter Zijlstra
2016-04-22 12:56 ` Fengguang Wu
2016-04-22 13:03 ` Will Deacon
2016-04-22 14:23 ` Peter Zijlstra
2016-04-23 1:59 ` Fengguang Wu
2016-04-22 18:35 ` Kalle Valo
2016-04-23 3:23 ` Fengguang Wu
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=20160422141614.GP3430@twins.programming.kicks-ass.net \
--to=peterz@infradead.org \
--cc=Vineet.Gupta1@synopsys.com \
--cc=arnd@arndb.de \
--cc=boqun.feng@gmail.com \
--cc=cmetcalf@mellanox.com \
--cc=dalias@libc.org \
--cc=davem@davemloft.net \
--cc=dbueso@suse.de \
--cc=dhowells@redhat.com \
--cc=egtvedt@samfundet.no \
--cc=fengguang.wu@intel.com \
--cc=fweisbec@gmail.com \
--cc=geert@linux-m68k.org \
--cc=james.hogan@imgtec.com \
--cc=jcmvbkbc@gmail.com \
--cc=jejb@parisc-linux.org \
--cc=linux-arch@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux@arm.linux.org.uk \
--cc=mingo@kernel.org \
--cc=mpe@ellerman.id.au \
--cc=paulmck@linux.vnet.ibm.com \
--cc=ralf@linux-mips.org \
--cc=realmz6@gmail.com \
--cc=rkuo@codeaurora.org \
--cc=rth@twiddle.net \
--cc=schwidefsky@de.ibm.com \
--cc=tglx@linutronix.de \
--cc=tony.luck@intel.com \
--cc=torvalds@linux-foundation.org \
--cc=waiman.long@hpe.com \
--cc=will.deacon@arm.com \
--cc=ysato@users.sourceforge.jp \
/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).