linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Christoph Lameter <cl@linux.com>
To: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: David Rientjes <rientjes@google.com>,
	Eric Dumazet <eric.dumazet@gmail.com>,
	"H. Peter Anvin" <hpa@zytor.com>,
	linux-mm@kvack.org, Thomas Gleixner <tglx@linutronix.de>
Subject: [slubllv5 15/25] slub: Avoid disabling interrupts in free slowpath
Date: Mon, 16 May 2011 15:26:20 -0500	[thread overview]
Message-ID: <20110516202629.872677981@linux.com> (raw)
In-Reply-To: 20110516202605.274023469@linux.com

[-- Attachment #1: slab_free_without_irqoff --]
[-- Type: text/plain, Size: 2507 bytes --]

Disabling interrupts can be avoided now. However, list operation still require
disabling interrupts since allocations can occur from interrupt
contexts and there is no way to perform atomic list operations. So
acquire the list lock opportunistically if there is a chance
that list operations would be needed. This may result in
needless synchronizations but allows the avoidance of synchronization
in the majority of the cases.

Dropping interrupt handling significantly simplifies the slowpath.

Signed-off-by: Christoph Lameter <cl@linux.com>

---
 mm/slub.c |   16 +++++-----------
 1 file changed, 5 insertions(+), 11 deletions(-)

Index: linux-2.6/mm/slub.c
===================================================================
--- linux-2.6.orig/mm/slub.c	2011-05-16 12:45:42.741458944 -0500
+++ linux-2.6/mm/slub.c	2011-05-16 12:45:44.211458942 -0500
@@ -2182,11 +2182,10 @@ static void __slab_free(struct kmem_cach
 	struct kmem_cache_node *n = NULL;
 	unsigned long flags;
 
-	local_irq_save(flags);
 	stat(s, FREE_SLOWPATH);
 
 	if (kmem_cache_debug(s) && !free_debug_processing(s, page, x, addr))
-		goto out_unlock;
+		return;
 
 	do {
 		prior = page->freelist;
@@ -2205,7 +2204,7 @@ static void __slab_free(struct kmem_cach
 			 * Otherwise the list_lock will synchronize with
 			 * other processors updating the list of slabs.
 			 */
-                        spin_lock(&n->list_lock);
+                        spin_lock_irqsave(&n->list_lock, flags);
 		}
 		inuse = new.inuse;
 
@@ -2221,7 +2220,7 @@ static void __slab_free(struct kmem_cach
 		 */
                 if (was_frozen)
                         stat(s, FREE_FROZEN);
-                goto out_unlock;
+                return;
         }
 
 	/*
@@ -2244,11 +2243,7 @@ static void __slab_free(struct kmem_cach
 			stat(s, FREE_ADD_PARTIAL);
 		}
 	}
-
-	spin_unlock(&n->list_lock);
-
-out_unlock:
-	local_irq_restore(flags);
+	spin_unlock_irqrestore(&n->list_lock, flags);
 	return;
 
 slab_empty:
@@ -2260,8 +2255,7 @@ slab_empty:
 		stat(s, FREE_REMOVE_PARTIAL);
 	}
 
-	spin_unlock(&n->list_lock);
-	local_irq_restore(flags);
+	spin_unlock_irqrestore(&n->list_lock, flags);
 	stat(s, FREE_SLAB);
 	discard_slab(s, page);
 }

--
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/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

  parent reply	other threads:[~2011-05-16 20:26 UTC|newest]

Thread overview: 54+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2011-05-16 20:26 [slubllv5 00/25] SLUB: Lockless freelists for objects V5 Christoph Lameter
2011-05-16 20:26 ` [slubllv5 01/25] slub: Avoid warning for !CONFIG_SLUB_DEBUG Christoph Lameter
2011-05-16 20:26 ` [slubllv5 02/25] slub: Fix control flow in slab_alloc Christoph Lameter
2011-05-16 20:26 ` [slubllv5 03/25] slub: Make CONFIG_PAGE_ALLOC work with new fastpath Christoph Lameter
2011-05-17  4:52   ` Eric Dumazet
2011-05-17 13:46     ` Christoph Lameter
2011-05-17 19:22       ` Pekka Enberg
2011-05-16 20:26 ` [slubllv5 04/25] slub: Push irq disable into allocate_slab() Christoph Lameter
2011-05-16 20:26 ` [slubllv5 05/25] slub: Do not use frozen page flag but a bit in the page counters Christoph Lameter
2011-05-16 20:26 ` [slubllv5 06/25] slub: Move page->frozen handling near where the page->freelist handling occurs Christoph Lameter
2011-05-16 20:26 ` [slubllv5 07/25] x86: Add support for cmpxchg_double Christoph Lameter
2011-05-26 17:57   ` Pekka Enberg
2011-05-26 18:02     ` Christoph Lameter
2011-05-26 18:05   ` H. Peter Anvin
2011-05-26 18:17     ` Christoph Lameter
2011-05-26 18:29       ` H. Peter Anvin
2011-05-26 18:42         ` Christoph Lameter
2011-05-26 21:16         ` Christoph Lameter
2011-05-26 21:21           ` H. Peter Anvin
2011-05-26 21:25           ` Eric Dumazet
2011-05-26 21:31             ` H. Peter Anvin
2011-05-26 21:45               ` Eric Dumazet
2011-05-27  0:49                 ` H. Peter Anvin
2011-05-31 15:13             ` Christoph Lameter
2011-05-31 15:16               ` H. Peter Anvin
2011-05-31 16:53                 ` Christoph Lameter
2011-05-31 23:16                   ` H. Peter Anvin
2011-05-31 23:49                     ` Christoph Lameter
2011-05-31 23:54                       ` H. Peter Anvin
2011-06-01 14:13                         ` Christoph Lameter
2011-06-01 14:46                           ` Christoph Lameter
2011-06-01 15:42                             ` H. Peter Anvin
2011-06-01 16:08                               ` Christoph Lameter
2011-06-01 15:41                           ` H. Peter Anvin
2011-05-27  0:50           ` H. Peter Anvin
2011-05-31 15:10             ` Christoph Lameter
2011-05-16 20:26 ` [slubllv5 08/25] mm: Rearrange struct page Christoph Lameter
2011-05-16 20:26 ` [slubllv5 09/25] slub: Add cmpxchg_double_slab() Christoph Lameter
2011-05-16 20:26 ` [slubllv5 10/25] slub: explicit list_lock taking Christoph Lameter
2011-05-16 20:26 ` [slubllv5 11/25] slub: Pass kmem_cache struct to lock and freeze slab Christoph Lameter
2011-05-16 20:26 ` [slubllv5 12/25] slub: Rework allocator fastpaths Christoph Lameter
2011-05-16 20:26 ` [slubllv5 13/25] slub: Invert locking and avoid slab lock Christoph Lameter
2011-05-16 20:26 ` [slubllv5 14/25] slub: Disable interrupts in free_debug processing Christoph Lameter
2011-05-16 20:26 ` Christoph Lameter [this message]
2011-05-16 20:26 ` [slubllv5 16/25] slub: Get rid of the another_slab label Christoph Lameter
2011-05-16 20:26 ` [slubllv5 17/25] slub: Add statistics for the case that the current slab does not match the node Christoph Lameter
2011-05-16 20:26 ` [slubllv5 18/25] slub: fast release on full slab Christoph Lameter
2011-05-16 20:26 ` [slubllv5 19/25] slub: Not necessary to check for empty slab on load_freelist Christoph Lameter
2011-05-16 20:26 ` [slubllv5 20/25] slub: slabinfo update for cmpxchg handling Christoph Lameter
2011-05-16 20:26 ` [slubllv5 21/25] slub: Prepare inuse field in new_slab() Christoph Lameter
2011-05-16 20:26 ` [slubllv5 22/25] slub: pass kmem_cache_cpu pointer to get_partial() Christoph Lameter
2011-05-16 20:26 ` [slubllv5 23/25] slub: return object pointer from get_partial() / new_slab() Christoph Lameter
2011-05-16 20:26 ` [slubllv5 24/25] slub: Remove gotos from __slab_free() Christoph Lameter
2011-05-16 20:26 ` [slubllv5 25/25] slub: Remove gotos from __slab_alloc() Christoph Lameter

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=20110516202629.872677981@linux.com \
    --to=cl@linux.com \
    --cc=eric.dumazet@gmail.com \
    --cc=hpa@zytor.com \
    --cc=linux-mm@kvack.org \
    --cc=penberg@cs.helsinki.fi \
    --cc=rientjes@google.com \
    --cc=tglx@linutronix.de \
    /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).