From: Joseph Qi <joseph.qi@huawei.com>
To: ocfs2-devel@oss.oracle.com
Subject: [Ocfs2-devel] [PATCH 2/7 v5] ocfs2: add functions to add and remove inode in orphan dir
Date: Tue, 28 Oct 2014 21:13:47 +0800 [thread overview]
Message-ID: <544F968B.2030900@huawei.com> (raw)
From: Weiwei Wang <wangww631@huawei.com>
Add functions to add inode to orphan dir and remove inode in orphan dir.
Here we do not call ocfs2_prepare_orphan_dir and ocfs2_orphan_add
directly. Because append O_DIRECT will add inode to orphan two and
may result in more than one orphan entry for the same inode.
Signed-off-by: Weiwei Wang <wangww631@huawei.com>
Signed-off-by: Joseph Qi <joseph.qi@huawei.com>
---
fs/ocfs2/journal.h | 5 +
fs/ocfs2/namei.c | 315 +++++++++++++++++++++++++++++++++++++++++++++++++
fs/ocfs2/namei.h | 5 +
fs/ocfs2/ocfs2_fs.h | 5 +-
fs/ocfs2/ocfs2_trace.h | 3 +
5 files changed, 332 insertions(+), 1 deletion(-)
diff --git a/fs/ocfs2/journal.h b/fs/ocfs2/journal.h
index 7f8cde9..f4cd3c3 100644
--- a/fs/ocfs2/journal.h
+++ b/fs/ocfs2/journal.h
@@ -472,6 +472,11 @@ static inline int ocfs2_unlink_credits(struct super_block *sb)
* orphan dir index leaf */
#define OCFS2_DELETE_INODE_CREDITS (3 * OCFS2_INODE_UPDATE_CREDITS + 4)
+/* dinode + orphan dir dinode + extent tree leaf block + orphan dir entry +
+ * orphan dir index root + orphan dir index leaf */
+#define OCFS2_INODE_ADD_TO_ORPHAN_CREDITS (2 * OCFS2_INODE_UPDATE_CREDITS + 4)
+#define OCFS2_INODE_DEL_FROM_ORPHAN_CREDITS OCFS2_INODE_ADD_TO_ORPHAN_CREDITS
+
/* dinode update, old dir dinode update, new dir dinode update, old
* dir dir entry, new dir dir entry, dir entry update for renaming
* directory + target unlink + 3 x dir index leaves */
diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c
index 8add6f1..3b74f58 100644
--- a/fs/ocfs2/namei.c
+++ b/fs/ocfs2/namei.c
@@ -81,6 +81,12 @@ static int ocfs2_prepare_orphan_dir(struct ocfs2_super *osb,
char *name,
struct ocfs2_dir_lookup_result *lookup);
+static int ocfs2_dio_prepare_orphan_dir(struct ocfs2_super *osb,
+ struct inode **ret_orphan_dir,
+ u64 blkno,
+ char *name,
+ struct ocfs2_dir_lookup_result *lookup);
+
static int ocfs2_orphan_add(struct ocfs2_super *osb,
handle_t *handle,
struct inode *inode,
@@ -89,6 +95,15 @@ static int ocfs2_orphan_add(struct ocfs2_super *osb,
struct ocfs2_dir_lookup_result *lookup,
struct inode *orphan_dir_inode);
+static int ocfs2_dio_orphan_add(struct ocfs2_super *osb,
+ handle_t *handle,
+ struct inode *inode,
+ struct buffer_head *fe_bh,
+ char *name,
+ struct ocfs2_dir_lookup_result *lookup,
+ struct inode *orphan_dir_inode,
+ bool orphaned);
+
static int ocfs2_create_symlink_data(struct ocfs2_super *osb,
handle_t *handle,
struct inode *inode,
@@ -2137,6 +2152,51 @@ out:
return ret;
}
+/**
+ * Copy from ocfs2_prepare_orphan_dir(). The difference:
+ * It will still lock orphan dir if entry exists.
+ * Caller must take care of -EEXIST and responsible for unlock.
+*/
+static int ocfs2_dio_prepare_orphan_dir(struct ocfs2_super *osb,
+ struct inode **ret_orphan_dir,
+ u64 blkno,
+ char *name,
+ struct ocfs2_dir_lookup_result *lookup)
+{
+ struct inode *orphan_dir_inode = NULL;
+ struct buffer_head *orphan_dir_bh = NULL;
+ int ret = 0;
+
+ ret = ocfs2_lookup_lock_orphan_dir(osb, &orphan_dir_inode,
+ &orphan_dir_bh);
+ if (ret < 0) {
+ mlog_errno(ret);
+ return ret;
+ }
+
+ ret = __ocfs2_prepare_orphan_dir(orphan_dir_inode, orphan_dir_bh,
+ blkno, name, lookup);
+ if (ret < 0 && ret != -EEXIST) {
+ mlog_errno(ret);
+ goto out;
+ }
+
+ *ret_orphan_dir = orphan_dir_inode;
+
+out:
+ brelse(orphan_dir_bh);
+
+ if (ret && ret != -EEXIST) {
+ ocfs2_inode_unlock(orphan_dir_inode, 1);
+ mutex_unlock(&orphan_dir_inode->i_mutex);
+ iput(orphan_dir_inode);
+ }
+
+ if (ret && ret != -EEXIST)
+ mlog_errno(ret);
+ return ret;
+}
+
static int ocfs2_orphan_add(struct ocfs2_super *osb,
handle_t *handle,
struct inode *inode,
@@ -2226,6 +2286,100 @@ leave:
return status;
}
+/**
+ * Copy from ocfs2_orphan_add, the difference:
+ * 1. Do not add entry if already added.
+ * 2. Update di flags OCFS2_DIO_ORPHANED_FL and record the
+ * orphan slot.
+*/
+static int ocfs2_dio_orphan_add(struct ocfs2_super *osb,
+ handle_t *handle,
+ struct inode *inode,
+ struct buffer_head *fe_bh,
+ char *name,
+ struct ocfs2_dir_lookup_result *lookup,
+ struct inode *orphan_dir_inode,
+ bool orphaned)
+{
+ struct buffer_head *orphan_dir_bh = NULL;
+ int status = 0;
+ struct ocfs2_dinode *orphan_fe;
+ struct ocfs2_dinode *fe = (struct ocfs2_dinode *) fe_bh->b_data;
+
+ trace_ocfs2_dio_orphan_add_begin(
+ (unsigned long long)OCFS2_I(inode)->ip_blkno);
+
+ status = ocfs2_read_inode_block(orphan_dir_inode, &orphan_dir_bh);
+ if (status < 0) {
+ mlog_errno(status);
+ goto leave;
+ }
+
+ status = ocfs2_journal_access_di(handle,
+ INODE_CACHE(orphan_dir_inode),
+ orphan_dir_bh,
+ OCFS2_JOURNAL_ACCESS_WRITE);
+ if (status < 0) {
+ mlog_errno(status);
+ goto leave;
+ }
+
+ /*
+ * We're going to journal the change of i_flags and i_dio_orphaned_slot.
+ * It's safe anyway, though some callers may duplicate the journaling.
+ * Journaling within the func just make the logic look more
+ * straightforward.
+ */
+ status = ocfs2_journal_access_di(handle,
+ INODE_CACHE(inode),
+ fe_bh,
+ OCFS2_JOURNAL_ACCESS_WRITE);
+ if (status < 0) {
+ mlog_errno(status);
+ goto leave;
+ }
+
+ /* we're a cluster, and nlink can change on disk from
+ * underneath us... */
+ orphan_fe = (struct ocfs2_dinode *) orphan_dir_bh->b_data;
+ if (S_ISDIR(inode->i_mode))
+ ocfs2_add_links_count(orphan_fe, 1);
+ set_nlink(orphan_dir_inode, ocfs2_read_links_count(orphan_fe));
+ ocfs2_journal_dirty(handle, orphan_dir_bh);
+
+ /* It may already be orphaned by ocfs2_unlink/ocfs2_rename */
+ if (!orphaned) {
+ status = __ocfs2_add_entry(handle, orphan_dir_inode, name,
+ OCFS2_ORPHAN_NAMELEN, inode,
+ OCFS2_I(inode)->ip_blkno,
+ orphan_dir_bh, lookup);
+ if (status < 0) {
+ mlog_errno(status);
+ goto rollback;
+ }
+ }
+
+ /* Update flag OCFS2_DIO_ORPHANED_FL and record the orphan slot */
+ fe->i_flags |= cpu_to_le32(OCFS2_DIO_ORPHANED_FL);
+ fe->i_dio_orphaned_slot = cpu_to_le16(osb->slot_num);
+
+ ocfs2_journal_dirty(handle, fe_bh);
+
+ trace_ocfs2_dio_orphan_add_end((unsigned long long)OCFS2_I(inode)->ip_blkno,
+ osb->slot_num);
+
+rollback:
+ if (status < 0) {
+ if (S_ISDIR(inode->i_mode))
+ ocfs2_add_links_count(orphan_fe, -1);
+ set_nlink(orphan_dir_inode, ocfs2_read_links_count(orphan_fe));
+ }
+
+leave:
+ brelse(orphan_dir_bh);
+
+ return status;
+}
/* unlike orphan_add, we expect the orphan dir to already be locked here. */
int ocfs2_orphan_del(struct ocfs2_super *osb,
handle_t *handle,
@@ -2500,6 +2654,167 @@ leave:
return status;
}
+int ocfs2_add_inode_to_orphan(struct ocfs2_super *osb,
+ struct inode *inode)
+{
+ char orphan_name[OCFS2_ORPHAN_NAMELEN + 1];
+ struct inode *orphan_dir_inode = NULL;
+ struct ocfs2_dir_lookup_result orphan_insert = { NULL, };
+ struct buffer_head *di_bh = NULL;
+ int status = 0;
+ handle_t *handle = NULL;
+ struct ocfs2_dinode *di = NULL;
+ bool orphaned = false;
+
+ status = ocfs2_inode_lock(inode, &di_bh, 1);
+ if (status < 0) {
+ mlog_errno(status);
+ goto bail;
+ }
+
+ status = ocfs2_dio_prepare_orphan_dir(osb, &orphan_dir_inode,
+ OCFS2_I(inode)->ip_blkno,
+ orphan_name,
+ &orphan_insert);
+ if (status < 0 && status != -EEXIST) {
+ mlog_errno(status);
+ goto bail_unlock_inode;
+ } else if (status == -EEXIST) {
+ mlog(ML_NOTICE, "inode %llu already added to "
+ "orphan dir %llu.\n",
+ OCFS2_I(inode)->ip_blkno,
+ OCFS2_I(orphan_dir_inode)->ip_blkno);
+ di = (struct ocfs2_dinode *) di_bh->b_data;
+ if (!(di->i_flags & le32_to_cpu(OCFS2_ORPHANED_FL))) {
+ mlog_errno(status);
+ goto bail_unlock_orphan;
+ }
+ orphaned = true;
+ }
+
+ handle = ocfs2_start_trans(osb,
+ OCFS2_INODE_ADD_TO_ORPHAN_CREDITS);
+ if (IS_ERR(handle)) {
+ status = PTR_ERR(handle);
+ goto bail_unlock_orphan;
+ }
+
+ status = ocfs2_dio_orphan_add(osb, handle, inode, di_bh, orphan_name,
+ &orphan_insert, orphan_dir_inode, orphaned);
+ if (status)
+ mlog_errno(status);
+
+ ocfs2_commit_trans(osb, handle);
+
+bail_unlock_orphan:
+ ocfs2_inode_unlock(orphan_dir_inode, 1);
+ mutex_unlock(&orphan_dir_inode->i_mutex);
+ iput(orphan_dir_inode);
+
+ ocfs2_free_dir_lookup_result(&orphan_insert);
+
+bail_unlock_inode:
+ ocfs2_inode_unlock(inode, 1);
+ brelse(di_bh);
+
+bail:
+ return status;
+}
+
+int ocfs2_del_inode_from_orphan(struct ocfs2_super *osb,
+ struct inode *inode, int update_isize,
+ loff_t end)
+{
+ struct inode *orphan_dir_inode = NULL;
+ struct buffer_head *orphan_dir_bh = NULL;
+ struct buffer_head *di_bh = NULL;
+ struct ocfs2_dinode *di = NULL;
+ handle_t *handle = NULL;
+ int status = 0;
+
+ status = ocfs2_inode_lock(inode, &di_bh, 1);
+ if (status < 0) {
+ mlog_errno(status);
+ goto bail;
+ }
+ di = (struct ocfs2_dinode *) di_bh->b_data;
+
+ orphan_dir_inode = ocfs2_get_system_file_inode(osb,
+ ORPHAN_DIR_SYSTEM_INODE,
+ le16_to_cpu(di->i_dio_orphaned_slot));
+ if (!orphan_dir_inode) {
+ status = -EEXIST;
+ mlog_errno(status);
+ goto bail_unlock_inode;
+ }
+
+ mutex_lock(&orphan_dir_inode->i_mutex);
+ status = ocfs2_inode_lock(orphan_dir_inode, &orphan_dir_bh, 1);
+ if (status < 0) {
+ mutex_unlock(&orphan_dir_inode->i_mutex);
+ iput(orphan_dir_inode);
+ mlog_errno(status);
+ goto bail_unlock_inode;
+ }
+
+ handle = ocfs2_start_trans(osb,
+ OCFS2_INODE_DEL_FROM_ORPHAN_CREDITS);
+ if (IS_ERR(handle)) {
+ status = PTR_ERR(handle);
+ goto bail_unlock_orphan;
+ }
+
+ BUG_ON(!di->i_flags & cpu_to_le32(OCFS2_DIO_ORPHANED_FL));
+
+ /* Only delete entry if OCFS2_ORPHANED_FL not set, or
+ * there are two entries added */
+ if (!(di->i_flags & cpu_to_le32(OCFS2_ORPHANED_FL)) ||
+ (di->i_flags & cpu_to_le32(OCFS2_ORPHANED_FL) &&
+ (di->i_orphaned_slot != di->i_dio_orphaned_slot))) {
+ status = ocfs2_orphan_del(osb, handle, orphan_dir_inode,
+ inode, orphan_dir_bh);
+ if (status < 0) {
+ mlog_errno(status);
+ goto bail_commit;
+ }
+ }
+
+ status = ocfs2_journal_access_di(handle,
+ INODE_CACHE(inode),
+ di_bh,
+ OCFS2_JOURNAL_ACCESS_WRITE);
+ if (status < 0) {
+ mlog_errno(status);
+ goto bail_commit;
+ }
+
+ di->i_flags &= ~cpu_to_le32(OCFS2_DIO_ORPHANED_FL);
+ di->i_dio_orphaned_slot = 0;
+
+ if (update_isize) {
+ status = ocfs2_set_inode_size(handle, inode, di_bh, end);
+ if (status)
+ mlog_errno(status);
+ } else
+ ocfs2_journal_dirty(handle, di_bh);
+
+bail_commit:
+ ocfs2_commit_trans(osb, handle);
+
+bail_unlock_orphan:
+ ocfs2_inode_unlock(orphan_dir_inode, 1);
+ mutex_unlock(&orphan_dir_inode->i_mutex);
+ brelse(orphan_dir_bh);
+ iput(orphan_dir_inode);
+
+bail_unlock_inode:
+ ocfs2_inode_unlock(inode, 1);
+ brelse(di_bh);
+
+bail:
+ return status;
+}
+
int ocfs2_mv_orphaned_inode_to_new(struct inode *dir,
struct inode *inode,
struct dentry *dentry)
diff --git a/fs/ocfs2/namei.h b/fs/ocfs2/namei.h
index e5d059d..5625540 100644
--- a/fs/ocfs2/namei.h
+++ b/fs/ocfs2/namei.h
@@ -38,6 +38,11 @@ int ocfs2_orphan_del(struct ocfs2_super *osb,
int ocfs2_create_inode_in_orphan(struct inode *dir,
int mode,
struct inode **new_inode);
+int ocfs2_add_inode_to_orphan(struct ocfs2_super *osb,
+ struct inode *inode);
+int ocfs2_del_inode_from_orphan(struct ocfs2_super *osb,
+ struct inode *inode, int update_isize,
+ loff_t end);
int ocfs2_mv_orphaned_inode_to_new(struct inode *dir,
struct inode *new_inode,
struct dentry *new_dentry);
diff --git a/fs/ocfs2/ocfs2_fs.h b/fs/ocfs2/ocfs2_fs.h
index 938387a..e933ea2 100644
--- a/fs/ocfs2/ocfs2_fs.h
+++ b/fs/ocfs2/ocfs2_fs.h
@@ -229,6 +229,7 @@
#define OCFS2_CHAIN_FL (0x00000400) /* Chain allocator */
#define OCFS2_DEALLOC_FL (0x00000800) /* Truncate log */
#define OCFS2_QUOTA_FL (0x00001000) /* Quota file */
+#define OCFS2_DIO_ORPHANED_FL (0X00002000) /* On the orphan list especially for dio */
/*
* Flags on ocfs2_dinode.i_dyn_features
@@ -729,7 +730,9 @@ struct ocfs2_dinode {
inode belongs to. Only valid
if allocated from a
discontiguous block group */
-/*A0*/ __le64 i_reserved2[3];
+/*A0*/ __le16 i_dio_orphaned_slot; /* only used for append dio write */
+ __le16 i_reserved1[3];
+ __le64 i_reserved2[2];
/*B8*/ union {
__le64 i_pad1; /* Generic way to refer to this
64bit union */
diff --git a/fs/ocfs2/ocfs2_trace.h b/fs/ocfs2/ocfs2_trace.h
index 6cb019b..2d471cc 100644
--- a/fs/ocfs2/ocfs2_trace.h
+++ b/fs/ocfs2/ocfs2_trace.h
@@ -2373,6 +2373,9 @@ DEFINE_OCFS2_ULL_EVENT(ocfs2_orphan_add_begin);
DEFINE_OCFS2_ULL_UINT_EVENT(ocfs2_orphan_add_end);
+DEFINE_OCFS2_ULL_EVENT(ocfs2_dio_orphan_add_begin);
+DEFINE_OCFS2_ULL_UINT_EVENT(ocfs2_dio_orphan_add_end);
+
TRACE_EVENT(ocfs2_orphan_del,
TP_PROTO(unsigned long long dir, const char *name, int namelen),
TP_ARGS(dir, name, namelen),
--
1.8.4.3
reply other threads:[~2014-10-28 13:13 UTC|newest]
Thread overview: [no followups] expand[flat|nested] mbox.gz Atom feed
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=544F968B.2030900@huawei.com \
--to=joseph.qi@huawei.com \
--cc=ocfs2-devel@oss.oracle.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.