From: Chandan Rajendra <chandan@linux.vnet.ibm.com>
To: clm@fb.com, jbacik@fb.com, bo.li.liu@oracle.com, dsterba@suse.cz
Cc: Chandan Rajendra <chandan@linux.vnet.ibm.com>,
aneesh.kumar@linux.vnet.ibm.com, linux-btrfs@vger.kernel.org
Subject: [RFC PATCH V6 08/15] Btrfs: subpagesize-blocksize: Compute and look up csums based on sectorsized blocks.
Date: Mon, 8 Sep 2014 19:44:19 +0530 [thread overview]
Message-ID: <1410185666-23308-9-git-send-email-chandan@linux.vnet.ibm.com> (raw)
In-Reply-To: <1410185666-23308-1-git-send-email-chandan@linux.vnet.ibm.com>
Checksums are applicable to sectorsize units. The current code uses
bio->bv_len units to compute and look up checksums. This works on machines
where sectorsize == PAGE_CACHE_SIZE. This patch makes the checksum
computation and look up code to work with sectorsize units.
Signed-off-by: Chandan Rajendra <chandan@linux.vnet.ibm.com>
---
fs/btrfs/file-item.c | 87 ++++++++++++++++++++++++++++++++--------------------
fs/btrfs/inode.c | 53 +++++++++++++++++++++-----------
2 files changed, 89 insertions(+), 51 deletions(-)
diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c
index 54c84da..000418a 100644
--- a/fs/btrfs/file-item.c
+++ b/fs/btrfs/file-item.c
@@ -172,6 +172,7 @@ static int __btrfs_lookup_bio_sums(struct btrfs_root *root,
u64 item_start_offset = 0;
u64 item_last_offset = 0;
u64 disk_bytenr;
+ u64 page_bytes_left;
u32 diff;
int nblocks;
int bio_index = 0;
@@ -220,6 +221,8 @@ static int __btrfs_lookup_bio_sums(struct btrfs_root *root,
disk_bytenr = (u64)bio->bi_iter.bi_sector << 9;
if (dio)
offset = logical_offset;
+
+ page_bytes_left = bvec->bv_len;
while (bio_index < bio->bi_vcnt) {
if (!dio)
offset = page_offset(bvec->bv_page) + bvec->bv_offset;
@@ -243,7 +246,7 @@ static int __btrfs_lookup_bio_sums(struct btrfs_root *root,
if (BTRFS_I(inode)->root->root_key.objectid ==
BTRFS_DATA_RELOC_TREE_OBJECTID) {
set_extent_bits(io_tree, offset,
- offset + bvec->bv_len - 1,
+ offset + root->sectorsize - 1,
EXTENT_NODATASUM, GFP_NOFS);
} else {
btrfs_info(BTRFS_I(inode)->root->fs_info,
@@ -281,11 +284,17 @@ static int __btrfs_lookup_bio_sums(struct btrfs_root *root,
found:
csum += count * csum_size;
nblocks -= count;
- bio_index += count;
+
while (count--) {
- disk_bytenr += bvec->bv_len;
- offset += bvec->bv_len;
- bvec++;
+ disk_bytenr += root->sectorsize;
+ offset += root->sectorsize;
+ page_bytes_left -= root->sectorsize;
+ if (!page_bytes_left) {
+ bio_index++;
+ bvec++;
+ page_bytes_left = bvec->bv_len;
+ }
+
}
}
btrfs_free_path(path);
@@ -442,6 +451,8 @@ int btrfs_csum_one_bio(struct btrfs_root *root, struct inode *inode,
struct bio_vec *bvec = bio->bi_io_vec;
int bio_index = 0;
int index;
+ int nr_sectors;
+ int i;
unsigned long total_bytes = 0;
unsigned long this_sum_bytes = 0;
u64 offset;
@@ -469,41 +480,51 @@ int btrfs_csum_one_bio(struct btrfs_root *root, struct inode *inode,
if (!contig)
offset = page_offset(bvec->bv_page) + bvec->bv_offset;
- if (offset >= ordered->file_offset + ordered->len ||
- offset < ordered->file_offset) {
- unsigned long bytes_left;
- sums->len = this_sum_bytes;
- this_sum_bytes = 0;
- btrfs_add_ordered_sum(inode, ordered, sums);
- btrfs_put_ordered_extent(ordered);
+ data = kmap_atomic(bvec->bv_page);
- bytes_left = bio->bi_iter.bi_size - total_bytes;
- sums = kzalloc(btrfs_ordered_sum_size(root, bytes_left),
- GFP_NOFS);
- BUG_ON(!sums); /* -ENOMEM */
- sums->len = bytes_left;
- ordered = btrfs_lookup_ordered_extent(inode, offset);
- BUG_ON(!ordered); /* Logic error */
- sums->bytenr = ((u64)bio->bi_iter.bi_sector << 9) +
- total_bytes;
- index = 0;
+ nr_sectors = (bvec->bv_len + root->sectorsize - 1)
+ >> root->fs_info->sb->s_blocksize_bits;
+
+
+ for (i = 0; i < nr_sectors; i++) {
+ if (offset >= ordered->file_offset + ordered->len ||
+ offset < ordered->file_offset) {
+ unsigned long bytes_left;
+ sums->len = this_sum_bytes;
+ this_sum_bytes = 0;
+ btrfs_add_ordered_sum(inode, ordered, sums);
+ btrfs_put_ordered_extent(ordered);
+
+ bytes_left = bio->bi_iter.bi_size - total_bytes;
+
+ sums = kzalloc(btrfs_ordered_sum_size(root, bytes_left),
+ GFP_NOFS);
+ BUG_ON(!sums); /* -ENOMEM */
+ sums->len = bytes_left;
+ ordered = btrfs_lookup_ordered_extent(inode, offset);
+ BUG_ON(!ordered); /* Logic error */
+ sums->bytenr = ((u64)bio->bi_iter.bi_sector << 9) +
+ total_bytes;
+ index = 0;
+ }
+
+ sums->sums[index] = ~(u32)0;
+ sums->sums[index]
+ = btrfs_csum_data(data + bvec->bv_offset + (i * root->sectorsize),
+ sums->sums[index],
+ root->sectorsize);
+ btrfs_csum_final(sums->sums[index],
+ (char *)(sums->sums + index));
+ index++;
+ offset += root->sectorsize;
+ this_sum_bytes += root->sectorsize;
+ total_bytes += root->sectorsize;
}
- data = kmap_atomic(bvec->bv_page);
- sums->sums[index] = ~(u32)0;
- sums->sums[index] = btrfs_csum_data(data + bvec->bv_offset,
- sums->sums[index],
- bvec->bv_len);
kunmap_atomic(data);
- btrfs_csum_final(sums->sums[index],
- (char *)(sums->sums + index));
bio_index++;
- index++;
- total_bytes += bvec->bv_len;
- this_sum_bytes += bvec->bv_len;
- offset += bvec->bv_len;
bvec++;
}
this_sum_bytes = 0;
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 2ffb4df..ae5d459 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -7116,37 +7116,54 @@ static void btrfs_endio_direct_read(struct bio *bio, int err)
struct btrfs_root *root = BTRFS_I(inode)->root;
struct bio *dio_bio;
u32 *csums = (u32 *)dip->csum;
+ int index = 0;
+ int nr_sectors;
u64 start;
- int i;
+ int i, j;
+
+ if (err || !(BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM))
+ goto unlock;
start = dip->logical_offset;
bio_for_each_segment_all(bvec, bio, i) {
- if (!(BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM)) {
- struct page *page = bvec->bv_page;
- char *kaddr;
- u32 csum = ~(u32)0;
- unsigned long flags;
+ struct page *page = bvec->bv_page;
+ char *kaddr;
+ u32 csum;
+ unsigned long flags;
+
+ local_irq_save(flags);
+ kaddr = kmap_atomic(page);
+
+ nr_sectors = bvec->bv_len >> inode->i_sb->s_blocksize_bits;
- local_irq_save(flags);
- kaddr = kmap_atomic(page);
- csum = btrfs_csum_data(kaddr + bvec->bv_offset,
- csum, bvec->bv_len);
+ for (j = 0; j < nr_sectors; j++) {
+ csum = ~(u32)0;
+ csum = btrfs_csum_data(kaddr + bvec->bv_offset
+ + (root->sectorsize * j),
+ csum, root->sectorsize);
btrfs_csum_final(csum, (char *)&csum);
- kunmap_atomic(kaddr);
- local_irq_restore(flags);
- flush_dcache_page(bvec->bv_page);
- if (csum != csums[i]) {
- btrfs_err(root->fs_info, "csum failed ino %llu off %llu csum %u expected csum %u",
- btrfs_ino(inode), start, csum,
- csums[i]);
+ if (csum != csums[index]) {
+ btrfs_err(root->fs_info,
+ "csum failed ino %llu off %llu csum %u expected csum %u",
+ btrfs_ino(inode), start, csum,
+ csums[index]);
err = -EIO;
+ break;
}
+
+ start += root->sectorsize;
+ index++;
}
- start += bvec->bv_len;
+ kunmap_atomic(kaddr);
+ local_irq_restore(flags);
+ flush_dcache_page(bvec->bv_page);
+ if (err)
+ break;
}
+unlock:
unlock_extent(&BTRFS_I(inode)->io_tree, dip->logical_offset,
dip->logical_offset + dip->bytes - 1);
dio_bio = dip->dio_bio;
--
1.8.3.1
next prev parent reply other threads:[~2014-09-08 14:15 UTC|newest]
Thread overview: 16+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-09-08 14:14 [RFC PATCH V6 00/15] ] Btrfs: Subpagesize-blocksize: Get rid of whole page I/O Chandan Rajendra
2014-09-08 14:14 ` [RFC PATCH V6 01/15] Btrfs: subpagesize-blocksize: Get rid of whole page reads Chandan Rajendra
2014-09-08 14:14 ` [RFC PATCH V6 02/15] Btrfs: subpagesize-blocksize: Get rid of whole page writes Chandan Rajendra
2014-09-08 14:14 ` [RFC PATCH V6 03/15] Btrfs: subpagesize-blocksize: __btrfs_buffered_write: Reserve/release extents aligned to block size Chandan Rajendra
2014-09-08 14:14 ` [RFC PATCH V6 04/15] Btrfs: subpagesize-blocksize: Define extent_buffer_head Chandan Rajendra
2014-09-08 14:14 ` [RFC PATCH V6 05/15] Btrfs: subpagesize-blocksize: Read tree blocks whose size is <PAGE_CACHE_SIZE Chandan Rajendra
2014-09-08 14:14 ` [RFC PATCH V6 06/15] Btrfs: subpagesize-blocksize: Write only dirty extent buffers belonging to a page Chandan Rajendra
2014-09-08 14:14 ` [RFC PATCH V6 07/15] Btrfs: subpagesize-blocksize: Allow mounting filesystems where sectorsize != PAGE_SIZE Chandan Rajendra
2014-09-08 14:14 ` Chandan Rajendra [this message]
2014-09-08 14:14 ` [RFC PATCH V6 09/15] Btrfs: subpagesize-blocksize: __extent_writepage: Write only dirty blocks of a page Chandan Rajendra
2014-09-08 14:14 ` [RFC PATCH V6 10/15] Btrfs: subpagesize-blocksize: fallocate: Work with sectorsized units Chandan Rajendra
2014-09-08 14:14 ` [RFC PATCH V6 11/15] Btrfs: subpagesize-blocksize: btrfs_page_mkwrite: Reserve space in " Chandan Rajendra
2014-09-08 14:14 ` [RFC PATCH V6 12/15] Btrfs: subpagesize-blocksize: Search for all ordered extents that could span across a page Chandan Rajendra
2014-09-08 14:14 ` [RFC PATCH V6 13/15] Btrfs: subpagesize-blocksize: Deal with partial ordered extent allocations Chandan Rajendra
2014-09-08 14:14 ` [RFC PATCH V6 14/15] Btrfs: subpagesize-blocksize: Explicitly Track I/O status of blocks of an ordered extent Chandan Rajendra
2014-09-08 14:14 ` [RFC PATCH V6 15/15] Btrfs: subpagesize-blocksize: Revert commit fc4adbff823f76577ece26dcb88bf6f8392dbd43 Chandan Rajendra
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=1410185666-23308-9-git-send-email-chandan@linux.vnet.ibm.com \
--to=chandan@linux.vnet.ibm.com \
--cc=aneesh.kumar@linux.vnet.ibm.com \
--cc=bo.li.liu@oracle.com \
--cc=clm@fb.com \
--cc=dsterba@suse.cz \
--cc=jbacik@fb.com \
--cc=linux-btrfs@vger.kernel.org \
/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).