From: Catalin Marinas <catalin.marinas@arm.com>
To: Jens Axboe <jens.axboe@oracle.com>
Cc: linux-kernel@vger.kernel.org, peterz@infradead.org,
npiggin@suse.de, linux-arch@vger.kernel.org, jeremy@goop.org,
mingo@elte.hu, paulmck@linux.vnet.ibm.com,
Russell King <rmk+lkml@arm.linux.org.uk>
Subject: Re: [PATCH 1/10] Add generic helpers for arch IPI function calls
Date: Tue, 10 Jun 2008 15:51:25 +0100 [thread overview]
Message-ID: <1213109485.24701.107.camel@pc1117.cambridge.arm.com> (raw)
In-Reply-To: <1212051504-12561-2-git-send-email-jens.axboe@oracle.com>
Hi,
On Thu, 2008-05-29 at 10:58 +0200, Jens Axboe wrote:
> This adds kernel/smp.c which contains helpers for IPI function calls. In
> addition to supporting the existing smp_call_function() in a more efficient
> manner, it also adds a more scalable variant called smp_call_function_single()
> for calling a given function on a single CPU only.
[...]
> + * You must not call this function with disabled interrupts or from a
> + * hardware interrupt handler or from a bottom half handler.
> + */
> +int smp_call_function_mask(cpumask_t mask, void (*func)(void *), void *info,
> + int wait)
> +{
> + struct call_function_data d;
> + struct call_function_data *data = NULL;
> + cpumask_t allbutself;
> + unsigned long flags;
> + int cpu, num_cpus;
> +
> + /* Can deadlock when called with interrupts disabled */
> + WARN_ON(irqs_disabled());
I was thinking whether this condition can be removed and allow the
smp_call_function*() to be called with IRQs disabled. At a quick look,
it seems to be possible if the csd_flag_wait() function calls the IPI
handlers directly when the IRQs are disabled (see the patch below).
This would be useful on ARM11MPCore based systems where the cache
maintenance operations are not detected by the snoop control unit and
this affects the DMA calls like dma_map_single(). There doesn't seem to
be any restriction on calls to dma_map_single() and hence we cannot
broadcast the cache operation to the other CPUs. I could implement this
in the ARM specific code using spin_try_lock (on an IPI-specific lock
held during the cross-call) and polling for an IPI if a lock cannot be
acquired (meaning that a different CPU is issuing an IPI) but I was
wondering whether this would be possible in a more generic way.
Please let me know what you think or whether deadlocks are still
possible (or any other solution apart from hardware fixes :-)). Thanks.
diff --git a/kernel/smp.c b/kernel/smp.c
index ef6de3d..2c63e81 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -54,6 +54,10 @@ static void csd_flag_wait(struct call_single_data *data)
smp_mb();
if (!(data->flags & CSD_FLAG_WAIT))
break;
+ if (irqs_disabled()) {
+ generic_smp_call_function_single_interrupt();
+ generic_smp_call_function_interrupt();
+ }
cpu_relax();
} while (1);
}
@@ -208,9 +212,6 @@ int smp_call_function_single(int cpu, void (*func) (void *info), void *info,
/* prevent preemption and reschedule on another processor */
int me = get_cpu();
- /* Can deadlock when called with interrupts disabled */
- WARN_ON(irqs_disabled());
-
if (cpu == me) {
local_irq_save(flags);
func(info);
@@ -250,9 +251,6 @@ EXPORT_SYMBOL(smp_call_function_single);
*/
void __smp_call_function_single(int cpu, struct call_single_data *data)
{
- /* Can deadlock when called with interrupts disabled */
- WARN_ON((data->flags & CSD_FLAG_WAIT) && irqs_disabled());
-
generic_exec_single(cpu, data);
}
@@ -279,9 +277,6 @@ int smp_call_function_mask(cpumask_t mask, void (*func)(void *), void *info,
unsigned long flags;
int cpu, num_cpus;
- /* Can deadlock when called with interrupts disabled */
- WARN_ON(irqs_disabled());
-
cpu = smp_processor_id();
allbutself = cpu_online_map;
cpu_clear(cpu, allbutself);
--
Catalin
next prev parent reply other threads:[~2008-06-10 15:22 UTC|newest]
Thread overview: 75+ messages / expand[flat|nested] mbox.gz Atom feed top
2008-05-29 8:58 [PATCH 0/10] Add generic helpers for arch IPI function calls #4 Jens Axboe
2008-05-29 8:58 ` [PATCH 1/10] Add generic helpers for arch IPI function calls Jens Axboe
2008-05-30 11:24 ` Paul E. McKenney
2008-06-06 8:44 ` Jens Axboe
2008-06-10 14:51 ` Catalin Marinas [this message]
2008-06-10 15:44 ` James Bottomley
2008-06-10 16:04 ` Catalin Marinas
2008-06-10 15:47 ` Paul E. McKenney
2008-06-10 16:53 ` Catalin Marinas
2008-06-11 3:25 ` Nick Piggin
2008-06-11 10:13 ` Catalin Marinas
2008-06-11 10:13 ` Catalin Marinas
2008-07-06 17:21 ` Jeremy Fitzhardinge
2008-05-29 8:58 ` [PATCH 2/10] x86: convert to generic helpers for " Jens Axboe
2008-05-29 12:12 ` Jeremy Fitzhardinge
2008-05-29 12:17 ` Jens Axboe
2008-05-29 13:47 ` Jeremy Fitzhardinge
2008-05-29 8:58 ` [PATCH 3/10] powerpc: " Jens Axboe
2008-05-29 8:58 ` [PATCH 4/10] ia64: " Jens Axboe
2008-05-29 8:58 ` [PATCH 5/10] alpha: " Jens Axboe
2008-05-29 8:58 ` [PATCH 6/10] arm: " Jens Axboe
2008-06-02 12:29 ` Russell King
2008-06-02 12:29 ` Russell King
2008-06-06 8:47 ` Jens Axboe
2008-05-29 8:58 ` [PATCH 7/10] m32r: " Jens Axboe
2008-05-29 8:58 ` [PATCH 8/10] mips: " Jens Axboe
2008-05-29 14:20 ` Ralf Baechle
2008-05-30 7:23 ` Jens Axboe
2008-05-29 8:58 ` [PATCH 9/10] parisc: " Jens Axboe
2008-05-31 7:00 ` Kyle McMartin
2008-05-31 7:00 ` Kyle McMartin
2008-06-02 8:17 ` Jens Axboe
2008-06-02 16:09 ` Kyle McMartin
2008-06-06 8:47 ` Jens Axboe
2008-06-06 21:11 ` Kyle McMartin
2008-06-09 8:47 ` Jens Axboe
2008-05-29 8:58 ` [PATCH 10/10] sh: " Jens Axboe
2008-06-01 8:57 ` [PATCH 0/10] Add generic helpers for arch IPI function calls #4 Andrew Morton
2008-06-01 8:57 ` Andrew Morton
2008-06-01 9:52 ` Jeremy Fitzhardinge
-- strict thread matches above, loose matches on Subject: below --
2008-04-29 7:26 [PATCH 0/10] Add generic helpers for arch IPI function calls #3 Jens Axboe
[not found] ` <1209453990-7735-1-git-send-email-jens.axboe-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org>
2008-04-29 7:26 ` [PATCH 1/10] Add generic helpers for arch IPI function calls Jens Axboe
2008-04-29 7:26 ` Jens Axboe
[not found] ` <1209453990-7735-2-git-send-email-jens.axboe-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org>
2008-04-29 13:59 ` Paul E. McKenney
2008-04-29 13:59 ` Paul E. McKenney
[not found] ` <20080429135936.GC12390-23VcF4HTsmIX0ybBhKVfKdBPR1lH4CV8@public.gmane.org>
2008-04-30 11:29 ` Paul E. McKenney
2008-04-30 11:29 ` Paul E. McKenney
[not found] ` <20080430112934.GA23203-23VcF4HTsmIX0ybBhKVfKdBPR1lH4CV8@public.gmane.org>
2008-04-30 11:34 ` Jens Axboe
2008-04-30 11:34 ` Jens Axboe
[not found] ` <20080430113456.GY12774-tSWWG44O7X1aa/9Udqfwiw@public.gmane.org>
2008-04-30 12:17 ` Paul E. McKenney
2008-04-30 12:17 ` Paul E. McKenney
[not found] ` <20080430121712.GR11126-23VcF4HTsmIX0ybBhKVfKdBPR1lH4CV8@public.gmane.org>
2008-04-30 12:37 ` Jens Axboe
2008-04-30 12:37 ` Jens Axboe
[not found] ` <20080430123717.GC12774-tSWWG44O7X1aa/9Udqfwiw@public.gmane.org>
2008-05-01 2:44 ` Paul E. McKenney
2008-05-01 2:44 ` Paul E. McKenney
2008-05-02 2:02 ` Paul E. McKenney
2008-05-02 2:12 ` Nick Piggin
2008-05-02 12:29 ` Paul E. McKenney
2008-05-02 12:42 ` Paul E. McKenney
2008-05-02 12:59 ` Peter Zijlstra
2008-05-02 12:59 ` Peter Zijlstra
2008-05-02 14:21 ` Paul E. McKenney
2008-05-02 14:21 ` Paul E. McKenney
2008-05-03 2:30 ` Paul E. McKenney
2008-05-03 5:49 ` Nick Piggin
2008-05-03 18:11 ` Paul E. McKenney
2008-05-04 22:04 ` Paul E. McKenney
2008-05-05 4:15 ` Nick Piggin
2008-05-05 4:15 ` Nick Piggin
2008-05-05 17:43 ` Paul E. McKenney
2008-05-07 20:42 ` Jens Axboe
2008-05-08 4:36 ` Paul E. McKenney
2008-05-02 12:50 ` Keith Owens
2008-05-02 13:09 ` Paul E. McKenney
2008-04-30 22:56 ` Jeremy Fitzhardinge
2008-04-30 22:56 ` Jeremy Fitzhardinge
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=1213109485.24701.107.camel@pc1117.cambridge.arm.com \
--to=catalin.marinas@arm.com \
--cc=jens.axboe@oracle.com \
--cc=jeremy@goop.org \
--cc=linux-arch@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@elte.hu \
--cc=npiggin@suse.de \
--cc=paulmck@linux.vnet.ibm.com \
--cc=peterz@infradead.org \
--cc=rmk+lkml@arm.linux.org.uk \
/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).