summaryrefslogtreecommitdiff
path: root/fs/xfs
diff options
context:
space:
mode:
authorDave Chinner <dchinner@redhat.com>2013-04-03 14:09:21 +1100
committerBen Myers <bpm@sgi.com>2013-04-05 13:25:35 -0500
commit666d644cd72a9ec58b353209ff191d7430f3b357 (patch)
treeeb6918c1d053b8f55a33f57575906acf7beea8b9 /fs/xfs
parent3d6e036193bfa67a8a1cc1908fe910c7a014d183 (diff)
xfs: don't free EFIs before the EFDs are committed
Filesystems are occasionally being shut down with this error: xfs_trans_ail_delete_bulk: attempting to delete a log item that is not in the AIL. It was diagnosed to be related to the EFI/EFD commit order when the EFI and EFD are in different checkpoints and the EFD is committed before the EFI here: http://oss.sgi.com/archives/xfs/2013-01/msg00082.html The real problem is that a single bit cannot fully describe the states that the EFI/EFD processing can be in. These completion states are: EFI EFI in AIL EFD Result committed/unpinned Yes committed OK committed/pinned No committed Shutdown uncommitted No committed Shutdown Note that the "result" field is what should happen, not what does happen. The current logic is broken and handles the first two cases correctly by luck. That is, the code will free the EFI if the XFS_EFI_COMMITTED bit is *not* set, rather than if it is set. The inverted logic "works" because if both EFI and EFD are committed, then the first __xfs_efi_release() call clears the XFS_EFI_COMMITTED bit, and the second frees the EFI item. Hence as long as xfs_efi_item_committed() has been called, everything appears to be fine. It is the third case where the logic fails - where xfs_efd_item_committed() is called before xfs_efi_item_committed(), and that results in the EFI being freed before it has been committed. That is the bug that triggered the shutdown, and hence keeping track of whether the EFI has been committed or not is insufficient to correctly order the EFI/EFD operations w.r.t. the AIL. What we really want is this: the EFI is always placed into the AIL before the last reference goes away. The only way to guarantee that is that the EFI is not freed until after it has been unpinned *and* the EFD has been committed. That is, restructure the logic so that the only case that can occur is the first case. This can be done easily by replacing the XFS_EFI_COMMITTED with an EFI reference count. The EFI is initialised with it's own count, and that is not released until it is unpinned. However, there is a complication to this method - the high level EFI/EFD code in xfs_bmap_finish() does not hold direct references to the EFI structure, and runs a transaction commit between the EFI and EFD processing. Hence the EFI can be freed even before the EFD is created using such a method. Further, log recovery uses the AIL for tracking EFI/EFDs that need to be recovered, but it uses the AIL *differently* to the EFI transaction commit. Hence log recovery never pins or unpins EFIs, so we can't drop the EFI reference count indirectly to free the EFI. However, this doesn't prevent us from using a reference count here. There is a 1:1 relationship between EFIs and EFDs, so when we initialise the EFI we can take a reference count for the EFD as well. This solves the xfs_bmap_finish() issue - the EFI will never be freed until the EFD is processed. In terms of log recovery, during the committing of the EFD we can look for the XFS_EFI_RECOVERED bit being set and drop the EFI reference as well, thereby ensuring everything works correctly there as well. Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Mark Tinguely <tinguely@sgi.com> Signed-off-by: Ben Myers <bpm@sgi.com>
Diffstat (limited to 'fs/xfs')
-rw-r--r--fs/xfs/xfs_extfree_item.c27
-rw-r--r--fs/xfs/xfs_extfree_item.h14
-rw-r--r--fs/xfs/xfs_log_recover.c1
3 files changed, 23 insertions, 19 deletions
diff --git a/fs/xfs/xfs_extfree_item.c b/fs/xfs/xfs_extfree_item.c
index feb36d7551ae..c0f375087efc 100644
--- a/fs/xfs/xfs_extfree_item.c
+++ b/fs/xfs/xfs_extfree_item.c
@@ -50,9 +50,8 @@ xfs_efi_item_free(
* Freeing the efi requires that we remove it from the AIL if it has already
* been placed there. However, the EFI may not yet have been placed in the AIL
* when called by xfs_efi_release() from EFD processing due to the ordering of
- * committed vs unpin operations in bulk insert operations. Hence the
- * test_and_clear_bit(XFS_EFI_COMMITTED) to ensure only the last caller frees
- * the EFI.
+ * committed vs unpin operations in bulk insert operations. Hence the reference
+ * count to ensure only the last caller frees the EFI.
*/
STATIC void
__xfs_efi_release(
@@ -60,7 +59,7 @@ __xfs_efi_release(
{
struct xfs_ail *ailp = efip->efi_item.li_ailp;
- if (!test_and_clear_bit(XFS_EFI_COMMITTED, &efip->efi_flags)) {
+ if (atomic_dec_and_test(&efip->efi_refcount)) {
spin_lock(&ailp->xa_lock);
/* xfs_trans_ail_delete() drops the AIL lock. */
xfs_trans_ail_delete(ailp, &efip->efi_item,
@@ -126,8 +125,8 @@ xfs_efi_item_pin(
* which the EFI is manipulated during a transaction. If we are being asked to
* remove the EFI it's because the transaction has been cancelled and by
* definition that means the EFI cannot be in the AIL so remove it from the
- * transaction and free it. Otherwise coordinate with xfs_efi_release() (via
- * XFS_EFI_COMMITTED) to determine who gets to free the EFI.
+ * transaction and free it. Otherwise coordinate with xfs_efi_release()
+ * to determine who gets to free the EFI.
*/
STATIC void
xfs_efi_item_unpin(
@@ -171,19 +170,13 @@ xfs_efi_item_unlock(
/*
* The EFI is logged only once and cannot be moved in the log, so simply return
- * the lsn at which it's been logged. For bulk transaction committed
- * processing, the EFI may be processed but not yet unpinned prior to the EFD
- * being processed. Set the XFS_EFI_COMMITTED flag so this case can be detected
- * when processing the EFD.
+ * the lsn at which it's been logged.
*/
STATIC xfs_lsn_t
xfs_efi_item_committed(
struct xfs_log_item *lip,
xfs_lsn_t lsn)
{
- struct xfs_efi_log_item *efip = EFI_ITEM(lip);
-
- set_bit(XFS_EFI_COMMITTED, &efip->efi_flags);
return lsn;
}
@@ -241,6 +234,7 @@ xfs_efi_init(
efip->efi_format.efi_nextents = nextents;
efip->efi_format.efi_id = (__psint_t)(void*)efip;
atomic_set(&efip->efi_next_extent, 0);
+ atomic_set(&efip->efi_refcount, 2);
return efip;
}
@@ -310,8 +304,13 @@ xfs_efi_release(xfs_efi_log_item_t *efip,
uint nextents)
{
ASSERT(atomic_read(&efip->efi_next_extent) >= nextents);
- if (atomic_sub_and_test(nextents, &efip->efi_next_extent))
+ if (atomic_sub_and_test(nextents, &efip->efi_next_extent)) {
__xfs_efi_release(efip);
+
+ /* recovery needs us to drop the EFI reference, too */
+ if (test_bit(XFS_EFI_RECOVERED, &efip->efi_flags))
+ __xfs_efi_release(efip);
+ }
}
static inline struct xfs_efd_log_item *EFD_ITEM(struct xfs_log_item *lip)
diff --git a/fs/xfs/xfs_extfree_item.h b/fs/xfs/xfs_extfree_item.h
index 375f68e42531..432222418c56 100644
--- a/fs/xfs/xfs_extfree_item.h
+++ b/fs/xfs/xfs_extfree_item.h
@@ -114,16 +114,20 @@ typedef struct xfs_efd_log_format_64 {
* Define EFI flag bits. Manipulated by set/clear/test_bit operators.
*/
#define XFS_EFI_RECOVERED 1
-#define XFS_EFI_COMMITTED 2
/*
- * This is the "extent free intention" log item. It is used
- * to log the fact that some extents need to be free. It is
- * used in conjunction with the "extent free done" log item
- * described below.
+ * This is the "extent free intention" log item. It is used to log the fact
+ * that some extents need to be free. It is used in conjunction with the
+ * "extent free done" log item described below.
+ *
+ * The EFI is reference counted so that it is not freed prior to both the EFI
+ * and EFD being committed and unpinned. This ensures that when the last
+ * reference goes away the EFI will always be in the AIL as it has been
+ * unpinned, regardless of whether the EFD is processed before or after the EFI.
*/
typedef struct xfs_efi_log_item {
xfs_log_item_t efi_item;
+ atomic_t efi_refcount;
atomic_t efi_next_extent;
unsigned long efi_flags; /* misc flags */
xfs_efi_log_format_t efi_format;
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index d1dba7ce75ae..3ca3380c3afe 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -2948,6 +2948,7 @@ xlog_recover_process_efi(
* This will pull the EFI from the AIL and
* free the memory associated with it.
*/
+ set_bit(XFS_EFI_RECOVERED, &efip->efi_flags);
xfs_efi_release(efip, efip->efi_format.efi_nextents);
return XFS_ERROR(EIO);
}