[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <tip-5c1eb08936693cd78c71164c8bea0b086ae72c67@git.kernel.org>
Date: Fri, 29 Oct 2010 06:43:02 GMT
From: tip-bot for Eric Dumazet <eric.dumazet@...il.com>
To: linux-tip-commits@...r.kernel.org
Cc: linux-kernel@...r.kernel.org, hpa@...or.com, mingo@...hat.com,
eric.dumazet@...il.com, brgerst@...il.com, peterz@...radead.org,
tglx@...utronix.de, mingo@...e.hu
Subject: [tip:x86/urgent] x86-32: Restore irq stacks NUMA-aware allocations
Commit-ID: 5c1eb08936693cd78c71164c8bea0b086ae72c67
Gitweb: http://git.kernel.org/tip/5c1eb08936693cd78c71164c8bea0b086ae72c67
Author: Eric Dumazet <eric.dumazet@...il.com>
AuthorDate: Thu, 28 Oct 2010 16:40:54 +0200
Committer: Ingo Molnar <mingo@...e.hu>
CommitDate: Fri, 29 Oct 2010 08:17:07 +0200
x86-32: Restore irq stacks NUMA-aware allocations
Commit 22d4cd4c4d ("Allocate irq stacks seperate from percpu
area") removed NUMA affinity of IRQ stacks as side-effect of
the fix.
Using alloc_pages_node() instead of __get_free_pages() is safe,
even if the target node has no available LOWMEM pages :
alloc_pages_node() fallbacks to another node.
Signed-off-by: Eric Dumazet <eric.dumazet@...il.com>
Acked-by: Brian Gerst <brgerst@...il.com>
Cc: tj@...nel.org
Cc: torvalds@...ux-foundation.org
Cc: Peter Zijlstra <peterz@...radead.org>
LKML-Reference: <1288276854.2649.607.camel@...mazet-laptop>
Signed-off-by: Ingo Molnar <mingo@...e.hu>
---
arch/x86/kernel/irq_32.c | 9 +++++++--
1 files changed, 7 insertions(+), 2 deletions(-)
diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index 64668db..96656f2 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -17,6 +17,7 @@
#include <linux/delay.h>
#include <linux/uaccess.h>
#include <linux/percpu.h>
+#include <linux/mm.h>
#include <asm/apic.h>
@@ -125,7 +126,9 @@ void __cpuinit irq_ctx_init(int cpu)
if (per_cpu(hardirq_ctx, cpu))
return;
- irqctx = (union irq_ctx *)__get_free_pages(THREAD_FLAGS, THREAD_ORDER);
+ irqctx = page_address(alloc_pages_node(cpu_to_node(cpu),
+ THREAD_FLAGS,
+ THREAD_ORDER));
irqctx->tinfo.task = NULL;
irqctx->tinfo.exec_domain = NULL;
irqctx->tinfo.cpu = cpu;
@@ -134,7 +137,9 @@ void __cpuinit irq_ctx_init(int cpu)
per_cpu(hardirq_ctx, cpu) = irqctx;
- irqctx = (union irq_ctx *)__get_free_pages(THREAD_FLAGS, THREAD_ORDER);
+ irqctx = page_address(alloc_pages_node(cpu_to_node(cpu),
+ THREAD_FLAGS,
+ THREAD_ORDER));
irqctx->tinfo.task = NULL;
irqctx->tinfo.exec_domain = NULL;
irqctx->tinfo.cpu = cpu;
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists