From: Theodore Ts'o <tytso@mit.edu>
To: linux-ext4@vger.kernel.org, linux-kernel@vger.kernel.org
Cc: Josef Bacik <jbacik@redhat.com>, Mark Fasheh <mfasheh@suse.com>,
"Theodore Ts'o" <tytso@mit.edu>,
linux-fsdevel@vger.kernel.org
Subject: [PATCH 38/42] generic block based fiemap implementation
Date: Thu, 9 Oct 2008 00:05:56 -0400 [thread overview]
Message-ID: <1223525160-9887-39-git-send-email-tytso@mit.edu> (raw)
In-Reply-To: <1223525160-9887-38-git-send-email-tytso@mit.edu>
From: Josef Bacik <jbacik@redhat.com>
Any block based fs (this patch includes ext3) just has to declare its own
fiemap() function and then call this generic function with its own
get_block_t. This works well for block based filesystems that will map
multiple contiguous blocks at one time, but will work for filesystems that
only map one block at a time, you will just end up with an "extent" for each
block. One gotcha is this will not play nicely where there is hole+data
after the EOF. This function will assume its hit the end of the data as soon
as it hits a hole after the EOF, so if there is any data past that it will
not pick that up. AFAIK no block based fs does this anyway, but its in the
comments of the function anyway just in case.
Signed-off-by: Josef Bacik <jbacik@redhat.com>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
Cc: linux-fsdevel@vger.kernel.org
---
fs/ext2/ext2.h | 2 +
fs/ext2/file.c | 1 +
fs/ext2/inode.c | 8 +++
fs/ext3/file.c | 1 +
fs/ext3/inode.c | 8 +++
fs/ioctl.c | 118 +++++++++++++++++++++++++++++++++++++++++++++++
include/linux/ext3_fs.h | 2 +
include/linux/fs.h | 3 +
8 files changed, 143 insertions(+), 0 deletions(-)
diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h
index 47d88da..bae998c 100644
--- a/fs/ext2/ext2.h
+++ b/fs/ext2/ext2.h
@@ -133,6 +133,8 @@ extern void ext2_truncate (struct inode *);
extern int ext2_setattr (struct dentry *, struct iattr *);
extern void ext2_set_inode_flags(struct inode *inode);
extern void ext2_get_inode_flags(struct ext2_inode_info *);
+extern int ext2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
+ u64 start, u64 len);
int __ext2_write_begin(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, unsigned flags,
struct page **pagep, void **fsdata);
diff --git a/fs/ext2/file.c b/fs/ext2/file.c
index 5f2fa9c..45ed071 100644
--- a/fs/ext2/file.c
+++ b/fs/ext2/file.c
@@ -86,4 +86,5 @@ const struct inode_operations ext2_file_inode_operations = {
#endif
.setattr = ext2_setattr,
.permission = ext2_permission,
+ .fiemap = ext2_fiemap,
};
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index 991d6df..7658b33 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -31,6 +31,7 @@
#include <linux/writeback.h>
#include <linux/buffer_head.h>
#include <linux/mpage.h>
+#include <linux/fiemap.h>
#include "ext2.h"
#include "acl.h"
#include "xip.h"
@@ -704,6 +705,13 @@ int ext2_get_block(struct inode *inode, sector_t iblock, struct buffer_head *bh_
}
+int ext2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
+ u64 start, u64 len)
+{
+ return generic_block_fiemap(inode, fieinfo, start, len,
+ ext2_get_block);
+}
+
static int ext2_writepage(struct page *page, struct writeback_control *wbc)
{
return block_write_full_page(page, ext2_get_block, wbc);
diff --git a/fs/ext3/file.c b/fs/ext3/file.c
index acc4913..3be1e06 100644
--- a/fs/ext3/file.c
+++ b/fs/ext3/file.c
@@ -134,5 +134,6 @@ const struct inode_operations ext3_file_inode_operations = {
.removexattr = generic_removexattr,
#endif
.permission = ext3_permission,
+ .fiemap = ext3_fiemap,
};
diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c
index 507d868..ebfec4d 100644
--- a/fs/ext3/inode.c
+++ b/fs/ext3/inode.c
@@ -36,6 +36,7 @@
#include <linux/mpage.h>
#include <linux/uio.h>
#include <linux/bio.h>
+#include <linux/fiemap.h>
#include "xattr.h"
#include "acl.h"
@@ -981,6 +982,13 @@ out:
return ret;
}
+int ext3_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
+ u64 start, u64 len)
+{
+ return generic_block_fiemap(inode, fieinfo, start, len,
+ ext3_get_block);
+}
+
/*
* `handle' can be NULL if create is zero
*/
diff --git a/fs/ioctl.c b/fs/ioctl.c
index 045d960..33a6b7e 100644
--- a/fs/ioctl.c
+++ b/fs/ioctl.c
@@ -13,6 +13,8 @@
#include <linux/security.h>
#include <linux/module.h>
#include <linux/uaccess.h>
+#include <linux/writeback.h>
+#include <linux/buffer_head.h>
#include <asm/ioctls.h>
@@ -224,6 +226,122 @@ static int ioctl_fiemap(struct file *filp, unsigned long arg)
return error;
}
+#define blk_to_logical(inode, blk) (blk << (inode)->i_blkbits)
+#define logical_to_blk(inode, offset) (offset >> (inode)->i_blkbits);
+
+/*
+ * @inode - the inode to map
+ * @arg - the pointer to userspace where we copy everything to
+ * @get_block - the fs's get_block function
+ *
+ * This does FIEMAP for block based inodes. Basically it will just loop
+ * through get_block until we hit the number of extents we want to map, or we
+ * go past the end of the file and hit a hole.
+ *
+ * If it is possible to have data blocks beyond a hole past @inode->i_size, then
+ * please do not use this function, it will stop at the first unmapped block
+ * beyond i_size
+ */
+int generic_block_fiemap(struct inode *inode,
+ struct fiemap_extent_info *fieinfo, u64 start,
+ u64 len, get_block_t *get_block)
+{
+ struct buffer_head tmp;
+ unsigned int start_blk;
+ long long length = 0, map_len = 0;
+ u64 logical = 0, phys = 0, size = 0;
+ u32 flags = FIEMAP_EXTENT_MERGED;
+ int ret = 0;
+
+ if ((ret = fiemap_check_flags(fieinfo, FIEMAP_FLAG_SYNC)))
+ return ret;
+
+ start_blk = logical_to_blk(inode, start);
+
+ /* guard against change */
+ mutex_lock(&inode->i_mutex);
+
+ length = (long long)min_t(u64, len, i_size_read(inode));
+ map_len = length;
+
+ do {
+ /*
+ * we set b_size to the total size we want so it will map as
+ * many contiguous blocks as possible at once
+ */
+ memset(&tmp, 0, sizeof(struct buffer_head));
+ tmp.b_size = map_len;
+
+ ret = get_block(inode, start_blk, &tmp, 0);
+ if (ret)
+ break;
+
+ /* HOLE */
+ if (!buffer_mapped(&tmp)) {
+ /*
+ * first hole after going past the EOF, this is our
+ * last extent
+ */
+ if (length <= 0) {
+ flags = FIEMAP_EXTENT_MERGED|FIEMAP_EXTENT_LAST;
+ ret = fiemap_fill_next_extent(fieinfo, logical,
+ phys, size,
+ flags);
+ break;
+ }
+
+ length -= blk_to_logical(inode, 1);
+
+ /* if we have holes up to/past EOF then we're done */
+ if (length <= 0)
+ break;
+
+ start_blk++;
+ } else {
+ if (length <= 0 && size) {
+ ret = fiemap_fill_next_extent(fieinfo, logical,
+ phys, size,
+ flags);
+ if (ret)
+ break;
+ }
+
+ logical = blk_to_logical(inode, start_blk);
+ phys = blk_to_logical(inode, tmp.b_blocknr);
+ size = tmp.b_size;
+ flags = FIEMAP_EXTENT_MERGED;
+
+ length -= tmp.b_size;
+ start_blk += logical_to_blk(inode, size);
+
+ /*
+ * if we are past the EOF we need to loop again to see
+ * if there is a hole so we can mark this extent as the
+ * last one, and if not keep mapping things until we
+ * find a hole, or we run out of slots in the extent
+ * array
+ */
+ if (length <= 0)
+ continue;
+
+ ret = fiemap_fill_next_extent(fieinfo, logical, phys,
+ size, flags);
+ if (ret)
+ break;
+ }
+ cond_resched();
+ } while (1);
+
+ mutex_unlock(&inode->i_mutex);
+
+ /* if ret is 1 then we just hit the end of the extent array */
+ if (ret == 1)
+ ret = 0;
+
+ return ret;
+}
+EXPORT_SYMBOL(generic_block_fiemap);
+
static int file_ioctl(struct file *filp, unsigned int cmd,
unsigned long arg)
{
diff --git a/include/linux/ext3_fs.h b/include/linux/ext3_fs.h
index 80171ee..8120fa1 100644
--- a/include/linux/ext3_fs.h
+++ b/include/linux/ext3_fs.h
@@ -837,6 +837,8 @@ extern void ext3_truncate (struct inode *);
extern void ext3_set_inode_flags(struct inode *);
extern void ext3_get_inode_flags(struct ext3_inode_info *);
extern void ext3_set_aops(struct inode *inode);
+extern int ext3_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
+ u64 start, u64 len);
/* ioctl.c */
extern int ext3_ioctl (struct inode *, struct file *, unsigned int,
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 194fb23..385c9a1 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1998,6 +1998,9 @@ extern int vfs_fstat(unsigned int, struct kstat *);
extern int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd,
unsigned long arg);
+extern int generic_block_fiemap(struct inode *inode,
+ struct fiemap_extent_info *fieinfo, u64 start,
+ u64 len, get_block_t *get_block);
extern void get_filesystem(struct file_system_type *fs);
extern void put_filesystem(struct file_system_type *fs);
--
1.5.6.1.205.ge2c7.dirty
next prev parent reply other threads:[~2008-10-09 4:05 UTC|newest]
Thread overview: 61+ messages / expand[flat|nested] mbox.gz Atom feed top
2008-10-09 4:05 [PATCH 0/42] Ext4 patches queued up for the 2.6.28 merge window Theodore Ts'o
2008-10-09 4:05 ` [PATCH 01/42] percpu counter: clean up percpu_counter_sum_and_set() Theodore Ts'o
2008-10-09 4:05 ` [PATCH 02/42] ext4: Add printk priority levels to clean up checkpatch warnings Theodore Ts'o
2008-10-09 4:05 ` [PATCH 03/42] ext4: Fix long long " Theodore Ts'o
2008-10-09 4:05 ` [PATCH 04/42] ext4: Fix whitespace checkpatch warnings/errors Theodore Ts'o
2008-10-09 4:05 ` [PATCH 05/42] ext4: invalidate pages if delalloc block allocation fails Theodore Ts'o
2008-10-09 4:05 ` [PATCH 06/42] ext4: Make sure all the block allocation paths reserve blocks Theodore Ts'o
2008-10-09 4:05 ` Theodore Ts'o
2008-10-09 4:05 ` [PATCH 07/42] ext4: Retry block reservation Theodore Ts'o
2008-10-09 4:05 ` [PATCH 08/42] ext4: Add percpu dirty block accounting Theodore Ts'o
2008-10-09 4:05 ` [PATCH 09/42] ext4: Switch to non delalloc mode when we are low on free blocks count Theodore Ts'o
2008-10-09 4:05 ` [PATCH 10/42] ext4: Signed arithmetic fix Theodore Ts'o
2008-10-09 4:05 ` [PATCH 11/42] ext4: Fix ext4 nomballoc allocator for ENOSPC Theodore Ts'o
2008-10-09 4:05 ` [PATCH 12/42] ext4: Don't add the inode to journal handle until after the block is allocated Theodore Ts'o
2008-10-09 4:05 ` [PATCH 13/42] ext4: Retry block allocation if we have free blocks left Theodore Ts'o
2008-10-09 4:05 ` Theodore Ts'o
2008-10-09 4:05 ` [PATCH 14/42] ext4: truncate block allocated on a failed ext4_write_begin Theodore Ts'o
2008-10-09 4:05 ` [PATCH 15/42] ext4: Properly update i_disksize Theodore Ts'o
2008-10-09 4:05 ` [PATCH 16/42] ext4: Avoid printk floods in the face of directory corruption Theodore Ts'o
2008-10-09 4:05 ` [PATCH 17/42] Update flex_bg free blocks and free inodes counters when resizing Theodore Ts'o
2008-10-09 4:05 ` [PATCH 18/42] ext4: fix #11321: create /proc/ext4/*/stats more carefully Theodore Ts'o
2008-10-09 4:05 ` [PATCH 19/42] jbd2: clean up how the journal device name is printed Theodore Ts'o
2008-10-09 4:05 ` [PATCH 20/42] ext4: add missing unlock in ext4_check_descriptors() on error path Theodore Ts'o
2008-10-09 4:05 ` [PATCH 21/42] ext4: elevate write count for migrate ioctl Theodore Ts'o
2008-10-09 4:05 ` [PATCH 22/42] ext4: hook the ext3 migration interface to the EXT4_IOC_SETFLAGS ioctl Theodore Ts'o
2008-10-09 4:05 ` [PATCH 23/42] ext4: Renumber EXT4_IOC_MIGRATE Theodore Ts'o
2008-10-09 4:05 ` [PATCH 24/42] ext4: use percpu data structures for lg_prealloc_list Theodore Ts'o
2008-10-09 4:05 ` Theodore Ts'o
2008-10-09 4:05 ` [PATCH 25/42] ext4/jbd2: Avoid WARN() messages when failing to write to the superblock Theodore Ts'o
2008-10-09 4:05 ` [PATCH 26/42] ext4: Don't use 'struct dentry' for internal lookups Theodore Ts'o
2008-10-09 4:05 ` [PATCH 27/42] ext4: move /proc setup and teardown out of mballoc.c Theodore Ts'o
2008-10-09 4:05 ` [PATCH 28/42] ext4: Combine proc file handling into a single set of functions Theodore Ts'o
2008-10-09 4:05 ` [PATCH 29/42] ext4: Use readahead when reading an inode from the inode table Theodore Ts'o
2008-10-09 4:05 ` [PATCH 30/42] ext4: Remove old legacy block allocator Theodore Ts'o
2008-10-09 4:05 ` Theodore Ts'o
2008-10-09 4:05 ` [PATCH 31/42] ext4: fix initialization of UNINIT bitmap blocks Theodore Ts'o
2008-10-09 4:05 ` [PATCH 32/42] jbd2: abort instead of waiting for nonexistent transaction Theodore Ts'o
2008-10-09 4:05 ` [PATCH 33/42] ext4: Add debugging markers that can be used by systemtap Theodore Ts'o
2008-10-09 4:05 ` [PATCH 34/42] jbd2: Fix buffer head leak when writing the commit block Theodore Ts'o
2008-10-09 4:05 ` [PATCH 35/42] ext4: fix xattr deadlock Theodore Ts'o
[not found] ` <1223525160-9887-36-git-send-email-tytso-3s7WtUTddSA@public.gmane.org>
2008-10-09 4:05 ` [PATCH 36/42] vfs: vfs-level fiemap interface Theodore Ts'o
2008-10-09 4:05 ` Theodore Ts'o
2008-10-09 4:05 ` [PATCH 37/42] ocfs2: fiemap support Theodore Ts'o
2008-10-09 4:05 ` [Ocfs2-devel] " Theodore Ts'o
2008-10-09 4:05 ` Theodore Ts'o [this message]
2008-10-09 4:05 ` [PATCH 39/42] Hook ext4 to the vfs fiemap interface Theodore Ts'o
2008-10-09 4:05 ` [PATCH 40/42] Update ext4 MAINTAINERS file Theodore Ts'o
2008-10-09 4:05 ` [PATCH 41/42] ext4: Avoid double dirtying of super block in ext4_put_super() Theodore Ts'o
2008-10-09 4:06 ` [PATCH 42/42] ext4: Rename ext4dev to ext4 Theodore Ts'o
2008-10-11 22:04 ` Jeremy Fitzhardinge
2008-10-11 22:04 ` Jeremy Fitzhardinge
2008-10-11 22:09 ` Eric Sandeen
2008-10-11 22:09 ` Eric Sandeen
2008-10-11 22:54 ` Jeremy Fitzhardinge
2008-10-11 22:54 ` Jeremy Fitzhardinge
2008-10-11 22:58 ` Theodore Tso
2008-10-11 23:08 ` Grant Coady
2008-10-12 1:06 ` Eric Sandeen
2008-10-09 8:18 ` [PATCH 29/42] ext4: Use readahead when reading an inode from the inode table Aneesh Kumar K.V
2008-10-09 8:52 ` [PATCH 01/42] percpu counter: clean up percpu_counter_sum_and_set() Peter Zijlstra
2008-10-09 16:52 ` Theodore Tso
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=1223525160-9887-39-git-send-email-tytso@mit.edu \
--to=tytso@mit.edu \
--cc=jbacik@redhat.com \
--cc=linux-ext4@vger.kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mfasheh@suse.com \
/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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.