From: Malahal Naineni <malahal@us.ibm.com>
Date: Fri, 24 Sep 2010 18:25:49 +0000 (+0200)
Subject: block: set the bounce_pfn to the actual DMA limit rather than to max memory
X-Git-Url: http://git.lede-project.org./?a=commitdiff_plain;h=c49825facfd4969585224a896a5e717f88450cad;p=openwrt%2Fstaging%2Fblogic.git

block: set the bounce_pfn to the actual DMA limit rather than to max memory

The bounce_pfn of the request queue in 64 bit systems is set to the
current max_low_pfn. Adding more memory later makes this incorrect.
Memory allocated beyond this boot time max_low_pfn appear to require
bounce buffers (bounce buffers are actually not allocated but used in
calculating segments that may result in "over max segments limit"
errors).

Signed-off-by: Malahal Naineni <malahal@us.ibm.com>
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
---

diff --git a/block/blk-settings.c b/block/blk-settings.c
index f8f2ddf20613..f47af5031eaa 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -214,16 +214,14 @@ void blk_queue_bounce_limit(struct request_queue *q, u64 dma_mask)
 	 */
 	if (b_pfn < (min_t(u64, 0xffffffffUL, BLK_BOUNCE_HIGH) >> PAGE_SHIFT))
 		dma = 1;
-	q->limits.bounce_pfn = max_low_pfn;
 #else
 	if (b_pfn < blk_max_low_pfn)
 		dma = 1;
-	q->limits.bounce_pfn = b_pfn;
 #endif
+	q->limits.bounce_pfn = b_pfn;
 	if (dma) {
 		init_emergency_isa_pool();
 		q->bounce_gfp = GFP_NOIO | GFP_DMA;
-		q->limits.bounce_pfn = b_pfn;
 	}
 }
 EXPORT_SYMBOL(blk_queue_bounce_limit);