From: Peter Zijlstra <peterz@infradead•org>
To: Torsten Duwe <duwe@lst•de>
Cc: Tom Musta <tommusta@gmail•com>,
linux-kernel@vger•kernel.org, Paul Mackerras <paulus@samba•org>,
Anton Blanchard <anton@samba•org>,
Scott Wood <scottwood@freescale•com>,
"Paul E. McKenney" <paulmck@linux•vnet.ibm.com>,
linuxppc-dev@lists•ozlabs.org, Ingo Molnar <mingo@kernel•org>
Subject: Re: [PATCH v2] powerpc ticket locks
Date: Fri, 7 Feb 2014 18:12:24 +0100 [thread overview]
Message-ID: <20140207171224.GR5002@laptop.programming.kicks-ass.net> (raw)
In-Reply-To: <20140207165801.GC2107@lst.de>
On Fri, Feb 07, 2014 at 05:58:01PM +0100, Torsten Duwe wrote:
> +static __always_inline void arch_spin_lock(arch_spinlock_t *lock)
> {
> + register struct __raw_tickets old, tmp,
> + inc = { .tail = TICKET_LOCK_INC };
> +
> CLEAR_IO_SYNC;
> + __asm__ __volatile__(
> +"1: lwarx %0,0,%4 # arch_spin_lock\n"
> +" add %1,%3,%0\n"
> + PPC405_ERR77(0, "%4")
> +" stwcx. %1,0,%4\n"
> +" bne- 1b"
> + : "=&r" (old), "=&r" (tmp), "+m" (lock->tickets)
> + : "r" (inc), "r" (&lock->tickets)
> + : "cc");
> +
> + if (likely(old.head == old.tail))
> + goto out;
I would have expected an lwsync someplace hereabouts.
> + for (;;) {
> + unsigned count = 100;
> +
> do {
> + if (ACCESS_ONCE(lock->tickets.head) == old.tail)
> + goto out;
> HMT_low();
> if (SHARED_PROCESSOR)
> __spin_yield(lock);
> + } while (--count);
> HMT_medium();
> }
> +out:
> +#if defined(CONFIG_PPC_SPLPAR)
> + lock->holder = LOCK_TOKEN;
> +#endif
> + barrier(); /* make sure nothing creeps before the lock is taken */
> }
>
> static inline
> @@ -147,10 +220,21 @@ void arch_spin_lock_flags(arch_spinlock_t *lock, unsigned long flags)
>
> static inline void arch_spin_unlock(arch_spinlock_t *lock)
> {
> + arch_spinlock_t old, new;
> +
> +#if defined(CONFIG_PPC_SPLPAR)
> + lock->holder = 0;
> +#endif
> + do {
> + old.tickets = ACCESS_ONCE(lock->tickets);
> + new.tickets.head = old.tickets.head + TICKET_LOCK_INC;
> + new.tickets.tail = old.tickets.tail;
> + } while (unlikely(__arch_spin_cmpxchg_eq(lock,
> + old.head_tail,
> + new.head_tail)));
> SYNC_IO;
> __asm__ __volatile__("# arch_spin_unlock\n\t"
> PPC_RELEASE_BARRIER: : :"memory");
Doens't your cmpxchg_eq not already imply a lwsync?
> - lock->slock = 0;
> }
I'm still failing to see why you need an ll/sc pair for unlock.
next prev parent reply other threads:[~2014-02-07 17:12 UTC|newest]
Thread overview: 14+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-02-07 16:58 [PATCH v2] powerpc ticket locks Torsten Duwe
2014-02-07 17:12 ` Peter Zijlstra [this message]
2014-02-07 17:55 ` Torsten Duwe
2014-02-10 3:10 ` Benjamin Herrenschmidt
2014-02-10 15:52 ` Torsten Duwe
2014-02-10 17:53 ` Peter Zijlstra
2014-02-11 2:44 ` Benjamin Herrenschmidt
2014-02-11 2:56 ` Al Viro
2014-02-11 3:38 ` Benjamin Herrenschmidt
2014-02-11 9:53 ` Raghavendra KT
2014-02-11 10:40 ` Torsten Duwe
2014-02-11 18:30 ` Scott Wood
2014-02-11 19:34 ` Benjamin Herrenschmidt
2014-02-11 9:39 ` Raghavendra KT
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=20140207171224.GR5002@laptop.programming.kicks-ass.net \
--to=peterz@infradead$(echo .)org \
--cc=anton@samba$(echo .)org \
--cc=duwe@lst$(echo .)de \
--cc=linux-kernel@vger$(echo .)kernel.org \
--cc=linuxppc-dev@lists$(echo .)ozlabs.org \
--cc=mingo@kernel$(echo .)org \
--cc=paulmck@linux$(echo .)vnet.ibm.com \
--cc=paulus@samba$(echo .)org \
--cc=scottwood@freescale$(echo .)com \
--cc=tommusta@gmail$(echo .)com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
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