From: Josef Bacik <josef@redhat.com>
Date: Tue, 22 Mar 2011 15:00:46 +0000 (-0400)
Subject: Btrfs: don't allocate dip->csums when doing writes
X-Git-Url: https://git.karo-electronics.de/?a=commitdiff_plain;h=98bc3149fad639c8f50c7110b961a2a2fe085eed;p=linux-beck.git

Btrfs: don't allocate dip->csums when doing writes

When doing direct writes we store the checksums in the ordered sum stuff in the
ordered extent for writing them when the write completes, so we don't even use
the dip->csums array.  So if we're writing, don't bother allocating dip->csums
since we won't use it anyway.  Thanks,

Signed-off-by: Josef Bacik <josef@redhat.com>
---

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index e010000d4bc9..570cd44fe91b 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -5944,6 +5944,7 @@ static int btrfs_submit_direct_hook(int rw, struct btrfs_dio_private *dip,
 	int nr_pages = 0;
 	u32 *csums = dip->csums;
 	int ret = 0;
+	int write = rw & REQ_WRITE;
 
 	bio = btrfs_dio_bio_alloc(orig_bio->bi_bdev, start_sector, GFP_NOFS);
 	if (!bio)
@@ -5980,7 +5981,8 @@ static int btrfs_submit_direct_hook(int rw, struct btrfs_dio_private *dip,
 				goto out_err;
 			}
 
-			if (!skip_sum)
+			/* Write's use the ordered csums */
+			if (!write && !skip_sum)
 				csums = csums + nr_pages;
 			start_sector += submit_len >> 9;
 			file_offset += submit_len;
@@ -6048,7 +6050,8 @@ static void btrfs_submit_direct(int rw, struct bio *bio, struct inode *inode,
 	}
 	dip->csums = NULL;
 
-	if (!skip_sum) {
+	/* Write's use the ordered csum stuff, so we don't need dip->csums */
+	if (!write && !skip_sum) {
 		dip->csums = kmalloc(sizeof(u32) * bio->bi_vcnt, GFP_NOFS);
 		if (!dip->csums) {
 			kfree(dip);