From: "Darrick J. Wong" <djwong@kernel.org>
To: tytso@mit.edu
Cc: John@groves.net, bernd@bsbernd.com,
linux-fsdevel@vger.kernel.org, linux-ext4@vger.kernel.org,
miklos@szeredi.hu, amir73il@gmail.com, joannelkoong@gmail.com,
neal@gompa.dev
Subject: [PATCH 18/20] fuse4fs: use the orphaned inode list
Date: Wed, 20 Aug 2025 18:12:34 -0700 [thread overview]
Message-ID: <175573713131.20753.249562496853950632.stgit@frogsfrogsfrogs> (raw)
In-Reply-To: <175573712721.20753.5223489399594191991.stgit@frogsfrogsfrogs>
From: Darrick J. Wong <djwong@kernel.org>
Put open but unlinked files on the orphan list, and remove them when the
last open fd releases the inode.
Signed-off-by: "Darrick J. Wong" <djwong@kernel.org>
---
misc/fuse4fs.c | 181 +++++++++++++++++++++++++++++++++++++++++++++++++++++++-
1 file changed, 178 insertions(+), 3 deletions(-)
diff --git a/misc/fuse4fs.c b/misc/fuse4fs.c
index e2a9e7bfe54b00..1d1797a483a139 100644
--- a/misc/fuse4fs.c
+++ b/misc/fuse4fs.c
@@ -955,6 +955,13 @@ static int fuse4fs_inum_access(struct fuse4fs *ff, const struct fuse_ctx *ctxt,
inode_uid(inode), inode_gid(inode),
ctxt->uid, ctxt->gid);
+ /* linked files cannot be on the unlinked list or deleted */
+ if (inode.i_dtime != 0) {
+ dbg_printf(ff, "%s: unlinked ino=%d dtime=0x%x\n",
+ __func__, ino, inode.i_dtime);
+ return -ENOENT;
+ }
+
/* existence check */
if (mask == 0)
return 0;
@@ -2140,9 +2147,80 @@ static int fuse4fs_remove_ea_inodes(struct fuse4fs *ff, ext2_ino_t ino,
return 0;
}
+static int fuse4fs_add_to_orphans(struct fuse4fs *ff, ext2_ino_t ino,
+ struct ext2_inode_large *inode)
+{
+ ext2_filsys fs = ff->fs;
+
+ dbg_printf(ff, "%s: orphan ino=%d dtime=%d next=%d\n",
+ __func__, ino, inode->i_dtime, fs->super->s_last_orphan);
+
+ inode->i_dtime = fs->super->s_last_orphan;
+ fs->super->s_last_orphan = ino;
+ ext2fs_mark_super_dirty(fs);
+
+ return 0;
+}
+
+static int fuse4fs_remove_from_orphans(struct fuse4fs *ff, ext2_ino_t ino,
+ struct ext2_inode_large *inode)
+{
+ ext2_filsys fs = ff->fs;
+ ext2_ino_t prev_orphan;
+ errcode_t err;
+
+ dbg_printf(ff, "%s: super=%d ino=%d next=%d\n",
+ __func__, fs->super->s_last_orphan, ino, inode->i_dtime);
+
+ /* If we're lucky, the ondisk superblock points to us */
+ if (fs->super->s_last_orphan == ino) {
+ dbg_printf(ff, "%s: superblock\n", __func__);
+
+ fs->super->s_last_orphan = inode->i_dtime;
+ inode->i_dtime = 0;
+ ext2fs_mark_super_dirty(fs);
+ return 0;
+ }
+
+ /* Otherwise walk the ondisk orphan list. */
+ prev_orphan = fs->super->s_last_orphan;
+ while (prev_orphan != 0) {
+ struct ext2_inode_large orphan;
+
+ err = fuse4fs_read_inode(fs, prev_orphan, &orphan);
+ if (err)
+ return translate_error(fs, prev_orphan, err);
+
+ if (orphan.i_dtime == prev_orphan)
+ return translate_error(fs, prev_orphan,
+ EXT2_ET_FILESYSTEM_CORRUPTED);
+
+ if (orphan.i_dtime == ino) {
+ dbg_printf(ff, "%s: prev=%d\n",
+ __func__, prev_orphan);
+
+ orphan.i_dtime = inode->i_dtime;
+ inode->i_dtime = 0;
+
+ err = fuse4fs_write_inode(fs, prev_orphan, &orphan);
+ if (err)
+ return translate_error(fs, prev_orphan, err);
+
+ return 0;
+ }
+
+ dbg_printf(ff, "%s: orphan=%d next=%d\n",
+ __func__, prev_orphan, orphan.i_dtime);
+ prev_orphan = orphan.i_dtime;
+ }
+
+ return translate_error(fs, ino, EXT2_ET_FILESYSTEM_CORRUPTED);
+}
+
static int fuse4fs_remove_inode(struct fuse4fs *ff, ext2_ino_t ino)
{
ext2_filsys fs = ff->fs;
+ struct fuse4fs_inode *fi;
errcode_t err;
struct ext2_inode_large inode;
int ret = 0;
@@ -2159,7 +2237,6 @@ static int fuse4fs_remove_inode(struct fuse4fs *ff, ext2_ino_t ino)
return 0; /* XXX: already done? */
case 1:
inode.i_links_count--;
- ext2fs_set_dtime(fs, EXT2_INODE(&inode));
break;
default:
inode.i_links_count--;
@@ -2172,6 +2249,26 @@ static int fuse4fs_remove_inode(struct fuse4fs *ff, ext2_ino_t ino)
if (inode.i_links_count)
goto write_out;
+ err = fuse4fs_iget(ff, ino, &fi);
+ if (err)
+ return translate_error(fs, ino, err);
+
+ dbg_printf(ff, "%s: put ino=%d opencount=%d\n", __func__, ino,
+ fi->i_open_count);
+
+ /*
+ * The file is unlinked but still open; add it to the orphan list and
+ * free it later.
+ */
+ if (fi->i_open_count > 0) {
+ fuse4fs_iput(ff, fi);
+ ret = fuse4fs_add_to_orphans(ff, ino, &inode);
+ if (ret)
+ return ret;
+
+ goto write_out;
+ }
+ fuse4fs_iput(ff, fi);
if (ext2fs_has_feature_ea_inode(fs->super)) {
ret = fuse4fs_remove_ea_inodes(ff, ino, &inode);
@@ -2191,6 +2288,7 @@ static int fuse4fs_remove_inode(struct fuse4fs *ff, ext2_ino_t ino)
return translate_error(fs, ino, err);
}
+ ext2fs_set_dtime(fs, EXT2_INODE(&inode));
ext2fs_inode_alloc_stats2(fs, ino, -1,
LINUX_S_ISDIR(inode.i_mode));
@@ -2735,6 +2833,16 @@ static void op_link(fuse_req_t req, fuse_ino_t child_fino,
if (ret)
goto out2;
+ /*
+ * Linking a file back into the filesystem requires removing it from
+ * the orphan list.
+ */
+ if (inode.i_links_count == 0) {
+ ret = fuse4fs_remove_from_orphans(ff, child, &inode);
+ if (ret)
+ goto out2;
+ }
+
inode.i_links_count++;
ret = update_ctime(fs, child, &inode);
if (ret)
@@ -3015,7 +3123,8 @@ static void detect_linux_executable_open(int kernel_flags, int *access_check,
#endif /* __linux__ */
static int fuse4fs_open_file(struct fuse4fs *ff, const struct fuse_ctx *ctxt,
- ext2_ino_t ino, struct fuse_file_info *fp)
+ ext2_ino_t ino,
+ struct fuse_file_info *fp)
{
ext2_filsys fs = ff->fs;
errcode_t err;
@@ -3089,6 +3198,8 @@ static int fuse4fs_open_file(struct fuse4fs *ff, const struct fuse_ctx *ctxt,
file->fi->i_open_count++;
fuse4fs_set_handle(fp, file);
+ dbg_printf(ff, "%s: ino=%d fh=%p opencount=%d\n", __func__, ino, file,
+ file->fi->i_open_count);
out:
if (ret)
@@ -3105,6 +3216,8 @@ static void op_open(fuse_req_t req, fuse_ino_t fino, struct fuse_file_info *fp)
FUSE4FS_CHECK_CONTEXT(req);
FUSE4FS_CONVERT_FINO(req, &ino, fino);
+ dbg_printf(ff, "%s: ino=%d\n", __func__, ino);
+
fuse4fs_start(ff);
ret = fuse4fs_open_file(ff, ctxt, ino, fp);
fuse4fs_finish(ff, ret);
@@ -3253,6 +3366,55 @@ static void op_write(fuse_req_t req, fuse_ino_t fino EXT2FS_ATTR((unused)),
fuse_reply_err(req, -ret);
}
+static int fuse4fs_free_unlinked(struct fuse4fs *ff, ext2_ino_t ino)
+{
+ struct ext2_inode_large inode;
+ ext2_filsys fs = ff->fs;
+ errcode_t err;
+ int ret = 0;
+
+ err = fuse4fs_read_inode(fs, ino, &inode);
+ if (err)
+ return translate_error(fs, ino, err);
+
+ if (inode.i_links_count > 0)
+ return 0;
+
+ dbg_printf(ff, "%s: ino=%d links=%d\n", __func__, ino,
+ inode.i_links_count);
+
+ if (ext2fs_has_feature_ea_inode(fs->super)) {
+ ret = fuse4fs_remove_ea_inodes(ff, ino, &inode);
+ if (ret)
+ return ret;
+ }
+
+ /* Nobody holds this file; free its blocks! */
+ err = ext2fs_free_ext_attr(fs, ino, &inode);
+ if (err)
+ return translate_error(fs, ino, err);
+
+ if (ext2fs_inode_has_valid_blocks2(fs, EXT2_INODE(&inode))) {
+ err = ext2fs_punch(fs, ino, EXT2_INODE(&inode), NULL,
+ 0, ~0ULL);
+ if (err)
+ return translate_error(fs, ino, err);
+ }
+
+ ret = fuse4fs_remove_from_orphans(ff, ino, &inode);
+ if (ret)
+ return ret;
+
+ ext2fs_set_dtime(fs, EXT2_INODE(&inode));
+ ext2fs_inode_alloc_stats2(fs, ino, -1, LINUX_S_ISDIR(inode.i_mode));
+
+ err = fuse4fs_write_inode(fs, ino, &inode);
+ if (err)
+ return translate_error(fs, ino, err);
+
+ return 0;
+}
+
static void op_release(fuse_req_t req, fuse_ino_t fino EXT2FS_ATTR((unused)),
struct fuse_file_info *fp)
{
@@ -3264,9 +3426,21 @@ static void op_release(fuse_req_t req, fuse_ino_t fino EXT2FS_ATTR((unused)),
FUSE4FS_CHECK_CONTEXT(req);
FUSE4FS_CHECK_HANDLE(req, fh);
- dbg_printf(ff, "%s: ino=%d\n", __func__, fh->ino);
+ dbg_printf(ff, "%s: ino=%d fh=%p opencount=%u\n",
+ __func__, fh->ino, fh, fh->fi->i_open_count);
+
fs = fuse4fs_start(ff);
+ /*
+ * If the file is no longer open and is unlinked, free it, which
+ * removes it from the ondisk list.
+ */
+ if (--fh->fi->i_open_count == 0) {
+ ret = fuse4fs_free_unlinked(ff, fh->ino);
+ if (ret)
+ goto out_iput;
+ }
+
if ((fp->flags & O_SYNC) &&
fuse4fs_is_writeable(ff) &&
(fh->open_flags & EXT2_FILE_WRITE)) {
@@ -3275,6 +3449,7 @@ static void op_release(fuse_req_t req, fuse_ino_t fino EXT2FS_ATTR((unused)),
ret = translate_error(fs, fh->ino, err);
}
+out_iput:
fuse4fs_iput(ff, fh->fi);
fp->fh = 0;
fuse4fs_finish(ff, ret);
next prev parent reply other threads:[~2025-08-21 1:12 UTC|newest]
Thread overview: 72+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-08-21 0:37 [RFC v4] fuse: use fs-iomap for better performance so we can containerize ext4 Darrick J. Wong
2025-08-21 0:49 ` [PATCHSET RFC v4 1/6] fuse4fs: fork a low level fuse server Darrick J. Wong
2025-08-21 1:08 ` [PATCH 01/20] fuse2fs: port fuse2fs to lowlevel libfuse API Darrick J. Wong
2025-08-21 1:08 ` [PATCH 02/20] fuse4fs: drop fuse 2.x support code Darrick J. Wong
2025-08-21 1:08 ` [PATCH 03/20] fuse4fs: namespace some helpers Darrick J. Wong
2025-08-21 1:08 ` [PATCH 04/20] fuse4fs: convert to low level API Darrick J. Wong
2025-08-21 1:09 ` [PATCH 05/20] libsupport: port the kernel list.h to libsupport Darrick J. Wong
2025-08-21 1:09 ` [PATCH 06/20] libsupport: add a cache Darrick J. Wong
2025-08-21 1:09 ` [PATCH 07/20] cache: disable debugging Darrick J. Wong
2025-08-21 1:09 ` [PATCH 08/20] cache: use modern list iterator macros Darrick J. Wong
2025-08-21 1:10 ` [PATCH 09/20] cache: embed struct cache in the owner Darrick J. Wong
2025-08-21 1:10 ` [PATCH 10/20] cache: pass cache pointer to callbacks Darrick J. Wong
2025-08-21 1:10 ` [PATCH 11/20] cache: pass a private data pointer through cache_walk Darrick J. Wong
2025-08-21 1:11 ` [PATCH 12/20] cache: add a helper to grab a new refcount for a cache_node Darrick J. Wong
2025-08-21 1:11 ` [PATCH 13/20] cache: return results of a cache flush Darrick J. Wong
2025-08-21 1:11 ` [PATCH 14/20] cache: add a "get only if incore" flag to cache_node_get Darrick J. Wong
2025-08-21 1:11 ` [PATCH 15/20] cache: support gradual expansion Darrick J. Wong
2025-08-21 1:12 ` [PATCH 16/20] cache: implement automatic shrinking Darrick J. Wong
2025-08-21 1:12 ` [PATCH 17/20] fuse4fs: add cache to track open files Darrick J. Wong
2025-08-21 1:12 ` Darrick J. Wong [this message]
2025-08-21 1:12 ` [PATCH 19/20] fuse4fs: implement FUSE_TMPFILE Darrick J. Wong
2025-08-21 1:13 ` [PATCH 20/20] fuse4fs: create incore reverse orphan list Darrick J. Wong
2025-08-21 0:49 ` [PATCHSET RFC v4 2/6] libext2fs: refactoring for fuse2fs iomap support Darrick J. Wong
2025-08-21 1:13 ` [PATCH 01/10] libext2fs: make it possible to extract the fd from an IO manager Darrick J. Wong
2025-08-21 1:13 ` [PATCH 02/10] libext2fs: always fsync the device when flushing the cache Darrick J. Wong
2025-08-21 1:13 ` [PATCH 03/10] libext2fs: always fsync the device when closing the unix IO manager Darrick J. Wong
2025-08-21 1:14 ` [PATCH 04/10] libext2fs: only fsync the unix fd if we wrote to the device Darrick J. Wong
2025-08-21 1:14 ` [PATCH 05/10] libext2fs: invalidate cached blocks when freeing them Darrick J. Wong
2025-08-21 1:14 ` [PATCH 06/10] libext2fs: only flush affected blocks in unix_write_byte Darrick J. Wong
2025-08-21 1:14 ` [PATCH 07/10] libext2fs: allow unix_write_byte when the write would be aligned Darrick J. Wong
2025-08-21 1:15 ` [PATCH 08/10] libext2fs: allow clients to ask to write full superblocks Darrick J. Wong
2025-08-21 1:15 ` [PATCH 09/10] libext2fs: allow callers to disallow I/O to file data blocks Darrick J. Wong
2025-08-21 1:15 ` [PATCH 10/10] libext2fs: add posix advisory locking to the unix IO manager Darrick J. Wong
2025-08-21 0:49 ` [PATCHSET RFC v4 3/6] fuse2fs: use fuse iomap data paths for better file I/O performance Darrick J. Wong
2025-08-21 1:15 ` [PATCH 01/19] fuse2fs: implement bare minimum iomap for file mapping reporting Darrick J. Wong
2025-08-21 1:16 ` [PATCH 02/19] fuse2fs: add iomap= mount option Darrick J. Wong
2025-08-21 1:16 ` [PATCH 03/19] fuse2fs: implement iomap configuration Darrick J. Wong
2025-08-21 1:16 ` [PATCH 04/19] fuse2fs: register block devices for use with iomap Darrick J. Wong
2025-08-21 1:17 ` [PATCH 05/19] fuse2fs: implement directio file reads Darrick J. Wong
2025-08-21 1:17 ` [PATCH 06/19] fuse2fs: add extent dump function for debugging Darrick J. Wong
2025-08-21 1:17 ` [PATCH 07/19] fuse2fs: implement direct write support Darrick J. Wong
2025-08-21 1:17 ` [PATCH 08/19] fuse2fs: turn on iomap for pagecache IO Darrick J. Wong
2025-08-21 1:18 ` [PATCH 09/19] fuse2fs: don't zero bytes in punch hole Darrick J. Wong
2025-08-21 1:18 ` [PATCH 10/19] fuse2fs: don't do file data block IO when iomap is enabled Darrick J. Wong
2025-08-21 1:18 ` [PATCH 11/19] fuse2fs: avoid fuseblk mode if fuse-iomap support is likely Darrick J. Wong
2025-08-21 1:18 ` [PATCH 12/19] fuse2fs: enable file IO to inline data files Darrick J. Wong
2025-08-21 1:19 ` [PATCH 13/19] fuse2fs: set iomap-related inode flags Darrick J. Wong
2025-08-21 1:19 ` [PATCH 14/19] fuse2fs: add strictatime/lazytime mount options Darrick J. Wong
2025-08-21 1:19 ` [PATCH 15/19] fuse2fs: configure block device block size Darrick J. Wong
2025-08-21 1:19 ` [PATCH 16/19] fuse4fs: don't use inode number translation when possible Darrick J. Wong
2025-08-21 1:20 ` [PATCH 17/19] fuse4fs: separate invalidation Darrick J. Wong
2025-08-21 1:20 ` [PATCH 18/19] fuse2fs: implement statx Darrick J. Wong
2025-08-21 1:20 ` [PATCH 19/19] fuse2fs: enable atomic writes Darrick J. Wong
2025-08-21 0:50 ` [PATCHSET RFC v4 4/6] fuse2fs: use fuse iomap data paths for better file I/O performance Darrick J. Wong
2025-08-21 1:20 ` [PATCH 1/2] fuse2fs: enable caching of iomaps Darrick J. Wong
2025-08-21 1:21 ` [PATCH 2/2] fuse2fs: be smarter about caching iomaps Darrick J. Wong
2025-08-21 0:50 ` [PATCHSET RFC v4 5/6] fuse2fs: handle timestamps and ACLs correctly when iomap is enabled Darrick J. Wong
2025-08-21 1:21 ` [PATCH 1/8] fuse2fs: skip permission checking on utimens " Darrick J. Wong
2025-08-21 1:21 ` [PATCH 2/8] fuse2fs: let the kernel tell us about acl/mode updates Darrick J. Wong
2025-08-21 1:21 ` [PATCH 3/8] fuse2fs: better debugging for file mode updates Darrick J. Wong
2025-08-21 1:22 ` [PATCH 4/8] fuse2fs: debug timestamp updates Darrick J. Wong
2025-08-21 1:22 ` [PATCH 5/8] fuse2fs: use coarse timestamps for iomap mode Darrick J. Wong
2025-08-21 1:22 ` [PATCH 6/8] fuse2fs: add tracing for retrieving timestamps Darrick J. Wong
2025-08-21 1:23 ` [PATCH 7/8] fuse2fs: enable syncfs Darrick J. Wong
2025-08-21 1:23 ` [PATCH 8/8] fuse2fs: skip the gdt write in op_destroy if syncfs is working Darrick J. Wong
2025-08-21 0:50 ` [PATCHSET RFC v4 6/6] fuse2fs: improve block and inode caching Darrick J. Wong
2025-08-21 1:23 ` [PATCH 1/6] libsupport: add caching IO manager Darrick J. Wong
2025-08-21 1:23 ` [PATCH 2/6] iocache: add the actual buffer cache Darrick J. Wong
2025-08-21 1:24 ` [PATCH 3/6] iocache: bump buffer mru priority every 50 accesses Darrick J. Wong
2025-08-21 1:24 ` [PATCH 4/6] fuse2fs: enable caching IO manager Darrick J. Wong
2025-08-21 1:24 ` [PATCH 5/6] fuse2fs: increase inode cache size Darrick J. Wong
2025-08-21 1:24 ` [PATCH 6/6] libext2fs: improve caching for inodes Darrick J. Wong
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=175573713131.20753.249562496853950632.stgit@frogsfrogsfrogs \
--to=djwong@kernel.org \
--cc=John@groves.net \
--cc=amir73il@gmail.com \
--cc=bernd@bsbernd.com \
--cc=joannelkoong@gmail.com \
--cc=linux-ext4@vger.kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=miklos@szeredi.hu \
--cc=neal@gompa.dev \
--cc=tytso@mit.edu \
/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