linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Peter Zijlstra <a.p.zijlstra@chello.nl>
To: linux-kernel@vger.kernel.org, linux-mm@kvack.org
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>,
	David Miller <davem@davemloft.net>,
	Andrew Morton <akpm@linux-foundation.org>,
	Daniel Phillips <phillips@google.com>,
	Pekka Enberg <penberg@cs.helsinki.fi>,
	Christoph Lameter <clameter@sgi.com>,
	Matt Mackall <mpm@selenic.com>,
	Lee Schermerhorn <Lee.Schermerhorn@hp.com>,
	Steve Dickson <SteveD@redhat.com>
Subject: [PATCH 05/10] mm: allow mempool to fall back to memalloc reserves
Date: Mon, 06 Aug 2007 12:29:27 +0200	[thread overview]
Message-ID: <20070806103658.869977000@chello.nl> (raw)
In-Reply-To: <20070806102922.907530000@chello.nl>

[-- Attachment #1: mm-mempool_fixup.patch --]
[-- Type: text/plain, Size: 1554 bytes --]

Allow the mempool to use the memalloc reserves when all else fails and
the allocation context would otherwise allow it.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
---
 mm/mempool.c |   12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

Index: linux-2.6-2/mm/mempool.c
===================================================================
--- linux-2.6-2.orig/mm/mempool.c
+++ linux-2.6-2/mm/mempool.c
@@ -14,6 +14,7 @@
 #include <linux/mempool.h>
 #include <linux/blkdev.h>
 #include <linux/writeback.h>
+#include "internal.h"
 
 static void add_element(mempool_t *pool, void *element)
 {
@@ -204,7 +205,7 @@ void * mempool_alloc(mempool_t *pool, gf
 	void *element;
 	unsigned long flags;
 	wait_queue_t wait;
-	gfp_t gfp_temp;
+	gfp_t gfp_temp, gfp_orig = gfp_mask;
 
 	might_sleep_if(gfp_mask & __GFP_WAIT);
 
@@ -228,6 +229,15 @@ repeat_alloc:
 	}
 	spin_unlock_irqrestore(&pool->lock, flags);
 
+	/* if we really had right to the emergency reserves try those */
+	if (gfp_to_alloc_flags(gfp_orig) & ALLOC_NO_WATERMARKS) {
+		if (gfp_temp & __GFP_NOMEMALLOC) {
+			gfp_temp &= ~(__GFP_NOMEMALLOC|__GFP_NOWARN);
+			goto repeat_alloc;
+		} else
+			gfp_temp |= __GFP_NOMEMALLOC|__GFP_NOWARN;
+	}
+
 	/* We must not sleep in the GFP_ATOMIC case */
 	if (!(gfp_mask & __GFP_WAIT))
 		return NULL;

--

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

  parent reply	other threads:[~2007-08-06 10:29 UTC|newest]

Thread overview: 85+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2007-08-06 10:29 [PATCH 00/10] foundations for reserve-based allocation Peter Zijlstra
2007-08-06 10:29 ` [PATCH 01/10] mm: gfp_to_alloc_flags() Peter Zijlstra
2007-08-06 10:29 ` [PATCH 02/10] mm: system wide ALLOC_NO_WATERMARK Peter Zijlstra
2007-08-06 18:11   ` Christoph Lameter
2007-08-06 18:21     ` Daniel Phillips
2007-08-06 18:31       ` Peter Zijlstra
2007-08-06 18:43         ` Daniel Phillips
2007-08-06 19:11         ` Christoph Lameter
2007-08-06 19:31           ` Peter Zijlstra
2007-08-06 20:12             ` Christoph Lameter
2007-08-06 18:42       ` Christoph Lameter
2007-08-06 18:48         ` Daniel Phillips
2007-08-06 18:51           ` Christoph Lameter
2007-08-06 19:15             ` Daniel Phillips
2007-08-06 20:12             ` Matt Mackall
2007-08-06 20:19               ` Christoph Lameter
2007-08-06 20:26                 ` Peter Zijlstra
2007-08-06 21:05                   ` Christoph Lameter
2007-08-06 22:59                     ` Daniel Phillips
2007-08-06 23:14                       ` Christoph Lameter
2007-08-06 23:49                         ` Daniel Phillips
2007-08-07 22:18                           ` Christoph Lameter
2007-08-08  7:24                             ` Peter Zijlstra
2007-08-08 18:06                               ` Christoph Lameter
2007-08-08  7:37                             ` Daniel Phillips
2007-08-08 18:09                               ` Christoph Lameter
2007-08-09 18:41                                 ` Daniel Phillips
2007-08-09 18:49                                   ` Christoph Lameter
2007-08-10  0:17                                     ` Daniel Phillips
2007-08-10  1:48                                       ` Christoph Lameter
2007-08-10  3:34                                         ` Daniel Phillips
2007-08-10  3:48                                           ` Christoph Lameter
2007-08-10  8:15                                             ` Daniel Phillips
2007-08-10 17:46                                               ` Christoph Lameter
2007-08-10 23:25                                                 ` Daniel Phillips
2007-08-13  6:55                                                 ` Daniel Phillips
2007-08-13 23:04                                                   ` Christoph Lameter
2007-08-06 20:27                 ` Andrew Morton
2007-08-06 23:16                   ` Daniel Phillips
2007-08-06 22:47                 ` Daniel Phillips
2007-08-06 10:29 ` [PATCH 03/10] mm: tag reseve pages Peter Zijlstra
2007-08-06 18:11   ` Christoph Lameter
2007-08-06 18:13     ` Daniel Phillips
2007-08-06 18:28     ` Peter Zijlstra
2007-08-06 19:34     ` Andi Kleen
2007-08-06 18:43       ` Christoph Lameter
2007-08-06 18:47         ` Peter Zijlstra
2007-08-06 18:59           ` Andi Kleen
2007-08-06 19:09             ` Christoph Lameter
2007-08-06 19:10             ` Andrew Morton
2007-08-06 19:16               ` Christoph Lameter
2007-08-06 19:38               ` Matt Mackall
2007-08-06 20:18               ` Andi Kleen
2007-08-06 10:29 ` [PATCH 04/10] mm: slub: add knowledge of reserve pages Peter Zijlstra
2007-08-08  0:13   ` Christoph Lameter
2007-08-08  1:44     ` Matt Mackall
2007-08-08 17:13       ` Christoph Lameter
2007-08-08 17:39         ` Andrew Morton
2007-08-08 17:57           ` Christoph Lameter
2007-08-08 18:46             ` Andrew Morton
2007-08-10  1:54               ` Daniel Phillips
2007-08-10  2:01                 ` Christoph Lameter
2007-08-20  7:38   ` Peter Zijlstra
2007-08-20  7:43     ` Peter Zijlstra
2007-08-20  9:12     ` Pekka J Enberg
2007-08-20  9:17       ` Peter Zijlstra
2007-08-20  9:28         ` Pekka Enberg
2007-08-20 19:26           ` Christoph Lameter
2007-08-20 20:08             ` Peter Zijlstra
2007-08-06 10:29 ` Peter Zijlstra [this message]
2007-08-06 10:29 ` [PATCH 06/10] mm: kmem_estimate_pages() Peter Zijlstra
2007-08-06 10:29 ` [PATCH 07/10] mm: allow PF_MEMALLOC from softirq context Peter Zijlstra
2007-08-06 10:29 ` [PATCH 08/10] mm: serialize access to min_free_kbytes Peter Zijlstra
2007-08-06 10:29 ` [PATCH 09/10] mm: emergency pool Peter Zijlstra
2007-08-06 10:29 ` [PATCH 10/10] mm: __GFP_MEMALLOC Peter Zijlstra
2007-08-06 17:35 ` [PATCH 00/10] foundations for reserve-based allocation Daniel Phillips
2007-08-06 18:17   ` Peter Zijlstra
2007-08-06 18:40     ` Daniel Phillips
2007-08-06 19:31     ` Daniel Phillips
2007-08-06 19:36       ` Peter Zijlstra
2007-08-06 19:53         ` Daniel Phillips
2007-08-06 17:56 ` Christoph Lameter
2007-08-06 18:33   ` Peter Zijlstra
2007-08-06 20:23 ` Matt Mackall
2007-08-07  0:09   ` Daniel Phillips

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=20070806103658.869977000@chello.nl \
    --to=a.p.zijlstra@chello.nl \
    --cc=Lee.Schermerhorn@hp.com \
    --cc=SteveD@redhat.com \
    --cc=akpm@linux-foundation.org \
    --cc=clameter@sgi.com \
    --cc=davem@davemloft.net \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mpm@selenic.com \
    --cc=penberg@cs.helsinki.fi \
    --cc=phillips@google.com \
    /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