[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <1338589841-9568-18-git-send-email-jack@suse.cz>
Date: Sat, 2 Jun 2012 00:30:31 +0200
From: Jan Kara <jack@...e.cz>
To: linux-fsdevel@...r.kernel.org
Cc: Al Viro <viro@...IV.linux.org.uk>, dchinner@...hat.com,
Jan Kara <jack@...e.cz>, linux-ext4@...r.kernel.org,
"Theodore Ts'o" <tytso@....edu>
Subject: [PATCH 17/27] ext4: Convert to new freezing mechanism
We remove most of frozen checks since upper layer takes care of blocking all
writes. We have to handle protection in ext4_page_mkwrite() in a special way
because we cannot use generic block_page_mkwrite(). Also we add a freeze
protection to ext4_evict_inode() so that iput() of unlinked inode cannot modify
a frozen filesystem (we cannot easily instrument ext4_journal_start() /
ext4_journal_stop() with freeze protection because we are missing the
superblock pointer in ext4_journal_stop() in nojournal mode).
CC: linux-ext4@...r.kernel.org
CC: "Theodore Ts'o" <tytso@....edu>
BugLink: https://bugs.launchpad.net/bugs/897421
Tested-by: Kamal Mostafa <kamal@...onical.com>
Tested-by: Peter M. Petrakis <peter.petrakis@...onical.com>
Tested-by: Dann Frazier <dann.frazier@...onical.com>
Tested-by: Massimo Morana <massimo.morana@...onical.com>
Signed-off-by: Jan Kara <jack@...e.cz>
---
fs/ext4/inode.c | 15 ++++++++++-----
fs/ext4/mmp.c | 14 ++++++++++----
fs/ext4/super.c | 31 +++++++------------------------
3 files changed, 27 insertions(+), 33 deletions(-)
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 07eaf56..4884127 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -166,6 +166,11 @@ void ext4_evict_inode(struct inode *inode)
if (is_bad_inode(inode))
goto no_delete;
+ /*
+ * Protect us against freezing - iput() caller didn't have to have any
+ * protection against it
+ */
+ sb_start_intwrite(inode->i_sb);
handle = ext4_journal_start(inode, ext4_blocks_for_truncate(inode)+3);
if (IS_ERR(handle)) {
ext4_std_error(inode->i_sb, PTR_ERR(handle));
@@ -175,6 +180,7 @@ void ext4_evict_inode(struct inode *inode)
* cleaned up.
*/
ext4_orphan_del(NULL, inode);
+ sb_end_intwrite(inode->i_sb);
goto no_delete;
}
@@ -206,6 +212,7 @@ void ext4_evict_inode(struct inode *inode)
stop_handle:
ext4_journal_stop(handle);
ext4_orphan_del(NULL, inode);
+ sb_end_intwrite(inode->i_sb);
goto no_delete;
}
}
@@ -234,6 +241,7 @@ void ext4_evict_inode(struct inode *inode)
else
ext4_free_inode(handle, inode);
ext4_journal_stop(handle);
+ sb_end_intwrite(inode->i_sb);
return;
no_delete:
ext4_clear_inode(inode); /* We must guarantee clearing of inode... */
@@ -4606,11 +4614,7 @@ int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
get_block_t *get_block;
int retries = 0;
- /*
- * This check is racy but catches the common case. We rely on
- * __block_page_mkwrite() to do a reliable check.
- */
- vfs_check_frozen(inode->i_sb, SB_FREEZE_WRITE);
+ sb_start_pagefault(inode->i_sb);
/* Delalloc case is easy... */
if (test_opt(inode->i_sb, DELALLOC) &&
!ext4_should_journal_data(inode) &&
@@ -4678,5 +4682,6 @@ retry_alloc:
out_ret:
ret = block_page_mkwrite_return(ret);
out:
+ sb_end_pagefault(inode->i_sb);
return ret;
}
diff --git a/fs/ext4/mmp.c b/fs/ext4/mmp.c
index ed6548d..4f63f90 100644
--- a/fs/ext4/mmp.c
+++ b/fs/ext4/mmp.c
@@ -10,14 +10,20 @@
* Write the MMP block using WRITE_SYNC to try to get the block on-disk
* faster.
*/
-static int write_mmp_block(struct buffer_head *bh)
+static int write_mmp_block(struct super_block *sb, struct buffer_head *bh)
{
+ /*
+ * We protect against freezing so that we don't create dirty buffers
+ * on frozen filesystem.
+ */
+ sb_start_write(sb);
mark_buffer_dirty(bh);
lock_buffer(bh);
bh->b_end_io = end_buffer_write_sync;
get_bh(bh);
submit_bh(WRITE_SYNC, bh);
wait_on_buffer(bh);
+ sb_end_write(sb);
if (unlikely(!buffer_uptodate(bh)))
return 1;
@@ -120,7 +126,7 @@ static int kmmpd(void *data)
mmp->mmp_time = cpu_to_le64(get_seconds());
last_update_time = jiffies;
- retval = write_mmp_block(bh);
+ retval = write_mmp_block(sb, bh);
/*
* Don't spew too many error messages. Print one every
* (s_mmp_update_interval * 60) seconds.
@@ -200,7 +206,7 @@ static int kmmpd(void *data)
mmp->mmp_seq = cpu_to_le32(EXT4_MMP_SEQ_CLEAN);
mmp->mmp_time = cpu_to_le64(get_seconds());
- retval = write_mmp_block(bh);
+ retval = write_mmp_block(sb, bh);
failed:
kfree(data);
@@ -299,7 +305,7 @@ skip:
seq = mmp_new_seq();
mmp->mmp_seq = cpu_to_le32(seq);
- retval = write_mmp_block(bh);
+ retval = write_mmp_block(sb, bh);
if (retval)
goto failed;
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 35b5954..cd6a516 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -290,33 +290,17 @@ static void ext4_put_nojournal(handle_t *handle)
* journal_end calls result in the superblock being marked dirty, so
* that sync() will call the filesystem's write_super callback if
* appropriate.
- *
- * To avoid j_barrier hold in userspace when a user calls freeze(),
- * ext4 prevents a new handle from being started by s_frozen, which
- * is in an upper layer.
*/
handle_t *ext4_journal_start_sb(struct super_block *sb, int nblocks)
{
journal_t *journal;
- handle_t *handle;
trace_ext4_journal_start(sb, nblocks, _RET_IP_);
if (sb->s_flags & MS_RDONLY)
return ERR_PTR(-EROFS);
+ WARN_ON(sb->s_writers.frozen == SB_FREEZE_COMPLETE);
journal = EXT4_SB(sb)->s_journal;
- handle = ext4_journal_current_handle();
-
- /*
- * If a handle has been started, it should be allowed to
- * finish, otherwise deadlock could happen between freeze
- * and others(e.g. truncate) due to the restart of the
- * journal handle if the filesystem is forzen and active
- * handles are not stopped.
- */
- if (!handle)
- vfs_check_frozen(sb, SB_FREEZE_TRANS);
-
if (!journal)
return ext4_get_nojournal();
/*
@@ -2633,6 +2617,7 @@ static int ext4_run_li_request(struct ext4_li_request *elr)
sb = elr->lr_super;
ngroups = EXT4_SB(sb)->s_groups_count;
+ sb_start_write(sb);
for (group = elr->lr_next_group; group < ngroups; group++) {
gdp = ext4_get_group_desc(sb, group, NULL);
if (!gdp) {
@@ -2659,6 +2644,7 @@ static int ext4_run_li_request(struct ext4_li_request *elr)
elr->lr_next_sched = jiffies + elr->lr_timeout;
elr->lr_next_group = group + 1;
}
+ sb_end_write(sb);
return ret;
}
@@ -4135,10 +4121,8 @@ int ext4_force_commit(struct super_block *sb)
return 0;
journal = EXT4_SB(sb)->s_journal;
- if (journal) {
- vfs_check_frozen(sb, SB_FREEZE_TRANS);
+ if (journal)
ret = ext4_journal_force_commit(journal);
- }
return ret;
}
@@ -4170,9 +4154,8 @@ static int ext4_sync_fs(struct super_block *sb, int wait)
* gives us a chance to flush the journal completely and mark the fs clean.
*
* Note that only this function cannot bring a filesystem to be in a clean
- * state independently, because ext4 prevents a new handle from being started
- * by @sb->s_frozen, which stays in an upper layer. It thus needs help from
- * the upper layer.
+ * state independently. It relies on upper layer to stop all data & metadata
+ * modifications.
*/
static int ext4_freeze(struct super_block *sb)
{
@@ -4199,7 +4182,7 @@ static int ext4_freeze(struct super_block *sb)
EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
error = ext4_commit_super(sb, 1);
out:
- /* we rely on s_frozen to stop further updates */
+ /* we rely on upper layer to stop further updates */
jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
return error;
}
--
1.7.1
--
To unsubscribe from this list: send the line "unsubscribe linux-ext4" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Powered by blists - more mailing lists