Currently all functions which call vfs_dq_release_reservation_block()
call it without i_block_reservation_lock. This result in
ext4_reservation vs quota_reservation inconsistency which provoke
incorrect reservation transfer and incorrect quota.
Task 1 (chown) Task 2 (truncate)
dquot_transfer
->down_write(dqptr_sem) ext4_da_release_spac
->dquot_get_reserved_space ->lock(i_block_reservation_lock)
->get_reserved_space /* decrement reservation */
->ext4_get_reserved_spac ->unlock(i_block_reservation_lock)
lock(i_block_rsv_lock) ---- /* During this time window
Read incorrect value * fs's reservation not equals
* to quota's */
->vfs_dq_release_reservation_block()
In fact i_block_reservation_lock is held by ext4_da_reserve_space()
while calling vfs_dq_reserve_block(). This may result in deadlock:
because of different lock ordering:
ext4_da_reserve_space() dquot_transfer()
lock(i_block_reservation_lock) down_write(dqptr_sem)
down_write(dqptr_sem) lock(i_block_reservation_lock)
But this not happens only because both callers must have i_mutex so
serialization happens on i_mutex.
To prevent ext4_reservation vs dquot_reservation inconsistency, we have
to reorganize locking ordering like follows:
i_block_reservation_lock > dqptr_sem
This means what all functions which changes ext4 or quota reservation have
to hold i_block_reservation_lock.
Signed-off-by: Dmitry Monakhov <dmonakhov@xxxxxxxxxx>
---
fs/ext4/inode.c | 23 +++++++++++++++++------
1 files changed, 17 insertions(+), 6 deletions(-)
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index e642cdb..979362d 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -1047,16 +1047,23 @@ cleanup:
out:
return err;
}
+/*
+ * Quota_transfer callback.
+ * During quota transfer we have to transfer rsv-blocks from one dquot to
+ * another. inode must be protected from concurrent reservation/reclamation.
+ * Locking ordering for all space reservation code:
+ * i_block_reservation_lock > dqptr_sem
+ * This is differ from i_block,i_lock locking ordering, but this is the
+ * only possible way.
+ * NOTE: Caller must hold i_block_reservation_lock.
+ */
qsize_t ext4_get_reserved_space(struct inode *inode)
{
unsigned long long total;
- spin_lock(&EXT4_I(inode)->i_block_reservation_lock);
total = EXT4_I(inode)->i_reserved_data_blocks +
EXT4_I(inode)->i_reserved_meta_blocks;
- spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
-
return (total << inode->i_blkbits);
}
/*
@@ -1124,13 +1131,13 @@ static void ext4_da_update_reserve_space(struct inode *inode, int used)
EXT4_I(inode)->i_reserved_data_blocks -= used;
percpu_counter_sub(&sbi->s_dirtyblocks_counter, used + mdb_claim);
vfs_dq_claim_block(inode, used + mdb_claim);
- spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
/*
* free those over-booking quota for metadata blocks
*/
if (mdb_free)
vfs_dq_release_reservation_block(inode, mdb_free);
+ spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
/*
* If we have done all the pending block allocations and if
@@ -1867,8 +1874,8 @@ repeat:
}
if (ext4_claim_free_blocks(sbi, total)) {
- spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
vfs_dq_release_reservation_block(inode, total);
+ spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
if (ext4_should_retry_alloc(inode->i_sb, &retries)) {
yield();
goto repeat;
@@ -1925,9 +1932,9 @@ static void ext4_da_release_space(struct inode *inode, int to_free)
BUG_ON(mdb > EXT4_I(inode)->i_reserved_meta_blocks);
EXT4_I(inode)->i_reserved_meta_blocks = mdb;
- spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
vfs_dq_release_reservation_block(inode, release);
+ spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
}
static void ext4_da_page_release_reservation(struct page *page,
@@ -5437,7 +5444,11 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
error = PTR_ERR(handle);
goto err_out;
}
+ /* i_block_reservation must being held in order to avoid races
+ * with concurent block reservation. */
+ spin_lock(&EXT4_I(inode)->i_block_reservation_lock);
error = vfs_dq_transfer(inode, attr) ? -EDQUOT : 0;
+ spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
if (error) {
ext4_journal_stop(handle);
return error;
--
1.6.0.4
--
To unsubscribe from this list: send the line "unsubscribe linux-ext4" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
