lkml.org 
[lkml]   [2012]   [Aug]   [24]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
From
Subject[PATCH 3/5] mm/memblock: reduce overhead in binary search
Date
From: Wanpeng Li <liwanp@linux.vnet.ibm.com>

When checking the indicated address belongs to the memory
or reserved region, the memory or reserved regions are checked
one by one through binary search, which would be a little
time consuming. If the indicated address isn't in memory
region, then we needn't do the time-sonsuming search. The
patch adds more check on the indicated address for that purpose.

Signed-off-by: Wanpeng Li <liwanp@linux.vnet.ibm.com>
---
mm/memblock.c | 4 ++++
1 files changed, 4 insertions(+), 0 deletions(-)

diff --git a/mm/memblock.c b/mm/memblock.c
index 2feff8d..880e461 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -871,6 +871,10 @@ static int __init_memblock memblock_search(struct memblock_type *type, phys_addr
{
unsigned int left = 0, right = type->cnt;

+ if (unlikely(addr < memblock_start_of_DRAM() ||
+ addr >= memblock_end_of_DRAM()))
+ return 0;
+
do {
unsigned int mid = (right + left) / 2;

--
1.7.5.4


\
 
 \ /
  Last update: 2012-08-24 17:21    [W:0.090 / U:1.304 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site