aboutsummaryrefslogtreecommitdiffstats
path: root/fs
Commit message (Collapse)AuthorAge
* ceph: decode v5 of osdmap (pool names) [protocol change]Sage Weil2010-04-09
| | | | | | | | Teach the client to decode an updated format for the osdmap. The new format includes pool names, which will be useful shortly. Get this change in earlier rather than later. Signed-off-by: Sage Weil <sage@newdream.net>
* ceph: fix ack counter reset on connection resetSage Weil2010-04-02
| | | | | | | | | If in_seq_acked isn't reset along with in_seq, we don't ack received messages until we reach the old count, consuming gobs memory on the other end of the connection and introducing a large delay when those messages are eventually deleted. Signed-off-by: Sage Weil <sage@newdream.net>
* ceph: fix leaked inode ref due to snap metadata writeback raceSage Weil2010-04-01
| | | | | | | | | | | | | | | | | | We create a ceph_cap_snap if there is dirty cap metadata (for writeback to mds) OR dirty pages (for writeback to osd). It is thus possible that the metadata has been written back to the MDS but the OSD data has not when the cap_snap is created. This results in a cap_snap with dirty(caps) == 0. The problem is that cap writeback to the MDS isn't necessary, and a FLUSHSNAP cap op gets no ack from the MDS. This leaves the cap_snap attached to the inode along with its inode reference. Fix the problem by dropping the cap_snap if it becomes 'complete' (all pages written out) and dirty(caps) == 0 in ceph_put_wrbuffer_cap_refs(). Also, BUG() in __ceph_flush_snaps() if we encounter a cap_snap with dirty(caps) == 0. Signed-off-by: Sage Weil <sage@newdream.net>
* ceph: fix snap context reference leaksSage Weil2010-04-01
| | | | | | | | | The get_oldest_context() helper takes a reference to the returned snap context, but most callers weren't dropping that reference. Fix them. Also drop the unused locked __get_oldest_context() variant. Signed-off-by: Sage Weil <sage@newdream.net>
* ceph: allow writeback of snapped pages older than 'oldest' snapcSage Weil2010-04-01
| | | | | | | | | | | | | | | | | | | | | | | On snap deletion, we don't regenerate ceph_cap_snaps for inodes with dirty pages because deletion does not affect metadata writeback. However, we did run into problems when we went to write back the pages because the 'oldest' snapc is determined by the oldest cap_snap, and that may be the newer snapc that reflects the deletion. This caused confusion and an infinite loop in ceph_update_writeable_page(). Change the snapc checks to allow writeback of any snapc that is equal to OR older than the 'oldest' snapc. When there are no cap_snaps, we were also using the realm's latest snapc for writeback, which complicates ceph_put_wrbufffer_cap_refs(). Instead, use i_head_snapc, the most snapc used for the most recent ('head') data. This makes the writeback snapc (ceph_osd_request.r_snapc) _always_ match a capsnap or i_head_snapc. Also, in writepags_finish(), drop the snapc referenced by the _page_ and do not assume it matches the request snapc (it may not anymore). Signed-off-by: Sage Weil <sage@newdream.net>
* ceph: fix dentry rehashing on virtual .snap dirSage Weil2010-03-30
| | | | | | | | | | | | | | | | | | | If a lookup fails on the magic .snap directory, we bind it to a magic snap directory inode in ceph_lookup_finish(). That code assumes the dentry is unhashed, but a recent server-side change started returning NULL leases on lookup failure, causing the .snap dentry to be hashed and NULL by ceph_fill_trace(). This causes dentry hash chain corruption, or a dies when d_rehash() includes BUG_ON(!d_unhashed(entry)); So, avoid processing the NULL dentry lease if it the dentry matches the snapdir name in ceph_fill_trace(). That allows the lookup completion to properly bind it to the snapdir inode. BUG there if dentry is hashed to be sure. Signed-off-by: Sage Weil <sage@newdream.net>
* Merge git://git.kernel.org/pub/scm/linux/kernel/git/joern/logfsLinus Torvalds2010-03-30
|\ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | * git://git.kernel.org/pub/scm/linux/kernel/git/joern/logfs: [LogFS] Erase new journal segments [LogFS] Move reserved segments with journal [LogFS] Clear PagePrivate when moving journal Simplify and fix pad_wbuf Prevent data corruption in logfs_rewrite_block() Use deactivate_locked_super Fix logfs_get_sb_final error path Write out both superblocks on mismatch Prevent schedule while atomic in __logfs_readdir Plug memory leak in writeseg_end_io Limit max_pages for insane devices Open segment file before using it
| * [LogFS] Erase new journal segmentsJoern Engel2010-03-29
| | | | | | | | | | | | | | | | | | | | If the device contains on old logfs image and the journal is moved to segment that have never been used by the current logfs and not all journal segments are erased before the next mount, the old content can confuse mount code. To prevent this, always erase the new journal segments. Signed-off-by: Joern Engel <joern@logfs.org>
| * [LogFS] Move reserved segments with journalJoern Engel2010-03-29
| | | | | | | | | | | | Fixes a GC livelock. Signed-off-by: Joern Engel <joern@logfs.org>
| * [LogFS] Clear PagePrivate when moving journalJoern Engel2010-03-28
| | | | | | | | | | | | | | do_logfs_journal_wl_pass() must call freeseg(), thereby clear PagePrivate on all pages of the current journal segment. Signed-off-by: Joern Engel <joern@logfs.org>
| * Simplify and fix pad_wbufJoern Engel2010-03-28
| | | | | | | | | | | | | | | | | | | | | | A comment in the old code read: /* The math in this function can surely use some love */ And indeed it did. In the case that area->a_used_bytes is exactly 4096 bytes below segment size it fell apart. pad_wbuf is now split into two helpers that are significantly less complicated. Signed-off-by: Joern Engel <joern@logfs.org>
| * Prevent data corruption in logfs_rewrite_block()Joern Engel2010-03-28
| | | | | | | | | | | | | | | | The comment was correct, so make the code match the comment. As the new comment indicates, we might be able to do a little less work. But for the current -rc series let's keep it simple and just fix the bug. Signed-off-by: Joern Engel <joern@logfs.org>
| * Use deactivate_locked_superJoern Engel2010-03-27
| | | | | | | | | | | | Found by Al Viro. Signed-off-by: Joern Engel <joern@logfs.org>
| * Fix logfs_get_sb_final error pathJoern Engel2010-03-27
| | | | | | | | | | | | | | rootdir was already allocated, so we must iput it again. Found by Al Viro. Signed-off-by: Joern Engel <joern@logfs.org>
| * Write out both superblocks on mismatchJoern Engel2010-03-27
| | | | | | | | | | | | | | | | If the first superblock is wrong and the second gets written, there will still be a mismatch on next mount. Write both to make sure they match. Signed-off-by: Joern Engel <joern@logfs.org>
| * Prevent schedule while atomic in __logfs_readdirJoern Engel2010-03-27
| | | | | | | | | | | | Apparently filldir can sleep, which forbids kmap_atomic. Signed-off-by: Joern Engel <joern@logfs.org>
| * Plug memory leak in writeseg_end_ioJoern Engel2010-03-27
| | | | | | | | Signed-off-by: Joern Engel <joern@logfs.org>
| * Limit max_pages for insane devicesJoern Engel2010-03-27
| | | | | | | | | | | | | | | | Intel SSDs have a limit of 0xffff as queue_max_hw_sectors(q). Such a limit may make sense from a hardware pov, but it causes bio_alloc() to return NULL. Signed-off-by: Joern Engel <joern@logfs.org>
| * Open segment file before using itJoern Engel2010-03-27
| | | | | | | | | | | | logfs_recover_sb() needs it open. Signed-off-by: Joern Engel <joern@logfs.org>
* | Merge branch 'upstream-linus' of ↵Linus Torvalds2010-03-29
|\ \ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | git://git.kernel.org/pub/scm/linux/kernel/git/jlbec/ocfs2 * 'upstream-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jlbec/ocfs2: ocfs2: Fix a race in o2dlm lockres mastery Ocfs2: Handle deletion of reflinked oprhan inodes correctly. Ocfs2: Journaling i_flags and i_orphaned_slot when adding inode to orphan dir. ocfs2: Clear undo bits when local alloc is freed ocfs2: Init meta_ac properly in ocfs2_create_empty_xattr_block. ocfs2: Fix the update of name_offset when removing xattrs ocfs2: Always try for maximum bits with new local alloc windows ocfs2: set i_mode on disk during acl operations ocfs2: Update i_blocks in reflink operations. ocfs2: Change bg_chain check for ocfs2_validate_gd_parent. [PATCH] Skip check for mandatory locks when unlocking
| * | ocfs2: Fix a race in o2dlm lockres masterySrinivas Eeda2010-03-23
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | In o2dlm, the master of a lock resource keeps a map of all interested nodes. This prevents the master from purging the resource before an interested node can create a lock. A race between the mastery thread and the mastery handler allowed an interested node to discover who the master is without informing the master directly. This is easily fixed by holding the dlm spinlock a little longer in the mastery handler. Signed-off-by: Srinivas Eeda <srinivas.eeda@oracle.com> Signed-off-by: Joel Becker <joel.becker@oracle.com>
| * | Ocfs2: Handle deletion of reflinked oprhan inodes correctly.Tristan Ye2010-03-23
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The rule is that all inodes in the orphan dir have ORPHANED_FL, otherwise we treated it as an ERROR. This rule works well except for some rare cases of reflink operation: http://oss.oracle.com/bugzilla/show_bug.cgi?id=1215 The problem is caused by how reflink and our orphan_scan thread interact. * The orphan scan pulls the orphans into a queue first, then runs the queue at a later time. We only hold the orphan_dir's lock during scanning. * Reflink create a oprhaned target in orphan_dir as its first step. It removes the target and clears the flag as the final step. These two steps take the orphan_dir's lock, but it is not held for the duration. Based on the above semantics, a reflink inode can be moved out of the orphan dir and have its ORPHANED_FL cleared before the queue of orphans is run. This leads to a ERROR in ocfs2_query_wipde_inode(). This patch teaches ocfs2_query_wipe_inode() to detect previously orphaned reflink targets. If a reflink fails or a crash occurs during the relfink operation, the inode will retain ORPHANED_FL and will be properly wiped. Signed-off-by: Tristan Ye <tristan.ye@oracle.com> Signed-off-by: Joel Becker <joel.becker@oracle.com>
| * | Ocfs2: Journaling i_flags and i_orphaned_slot when adding inode to orphan dir.Tristan Ye2010-03-23
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Currently, some callers were missing to journal the dirty inode after adding it to orphan dir. Now we're going to journal such modifications within the ocfs2_orphan_add() itself, It's safe to do so, though some existing caller may duplicate this, and it makes the logic look more straightforward anyway. Signed-off-by: Tristan Ye <tristan.ye@oracle.com> Signed-off-by: Joel Becker <joel.becker@oracle.com>
| * | ocfs2: Clear undo bits when local alloc is freedMark Fasheh2010-03-23
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | When the local alloc file changes windows, unused bits are freed back to the global bitmap. By defnition, those bits can not be in use by any file. Also, the local alloc will never have been able to allocate those bits if they were part of a previous truncate. Therefore it makes sense that we should clear unused local alloc bits in the undo buffer so that they can be used immediatly. [ Modified to call it ocfs2_release_clusters() -- Joel ] Signed-off-by: Mark Fasheh <mfasheh@suse.com> Signed-off-by: Joel Becker <joel.becker@oracle.com>
| * | ocfs2: Init meta_ac properly in ocfs2_create_empty_xattr_block.Tao Ma2010-03-19
| | | | | | | | | | | | | | | | | | | | | | | | You can't store a pointer that you haven't filled in yet and expect it to work. Signed-off-by: Tao Ma <tao.ma@oracle.com> Signed-off-by: Joel Becker <joel.becker@oracle.com>
| * | ocfs2: Fix the update of name_offset when removing xattrsTao Ma2010-03-19
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | When replacing a xattr's value, in some case we wipe its name/value first and then re-add it. The wipe is done by ocfs2_xa_block_wipe_namevalue() when the xattr is in the inode or block. We currently adjust name_offset for all the entries which have (offset < name_offset). This does not adjust the entrie we're replacing. Since we are replacing the entry, we don't adjust the total entry count. When we calculate a new namevalue location, we trust the entries now-wrong offset in ocfs2_xa_get_free_start(). The solution is to also adjust the name_offset for the replaced entry, allowing ocfs2_xa_get_free_start() to calculate the new namevalue location correctly. The following script can trigger a kernel panic easily. echo 'y'|mkfs.ocfs2 --fs-features=local,xattr -b 4K $DEVICE mount -t ocfs2 $DEVICE $MNT_DIR FILE=$MNT_DIR/$RANDOM for((i=0;i<76;i++)) do string_76="a$string_76" done string_78="aa$string_76" string_82="aaaa$string_78" touch $FILE setfattr -n 'user.test1234567890' -v $string_76 $FILE setfattr -n 'user.test1234567890' -v $string_78 $FILE setfattr -n 'user.test1234567890' -v $string_82 $FILE Signed-off-by: Tao Ma <tao.ma@oracle.com> Signed-off-by: Joel Becker <joel.becker@oracle.com>
| * | ocfs2: Always try for maximum bits with new local alloc windowsMark Fasheh2010-03-18
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | What we were doing before was to ask for the current window size as the maximum allocation. This had the effect of limiting the amount of allocation we could get for the local alloc during times when the window size was shrunk due to fragmentation. In some cases, that could actually *increase* fragmentation by artificially limiting the number of bits we can accept. So while we still want to ask for a minimum number of bits equal to window size, there is no reason why we should limit the number of bits the local alloc should accept. Hence always allow the maximum number of local alloc bits. Signed-off-by: Mark Fasheh <mfasheh@suse.com> Signed-off-by: Joel Becker <joel.becker@oracle.com>
| * | ocfs2: set i_mode on disk during acl operationsMark Fasheh2010-03-17
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ocfs2_set_acl() and ocfs2_init_acl() were setting i_mode on the in-memory inode, but never setting it on the disk copy. Thus, acls were some times not getting propagated between nodes. This patch fixes the issue by adding a helper function ocfs2_acl_set_mode() which does this the right way. ocfs2_set_acl() and ocfs2_init_acl() are then updated to call ocfs2_acl_set_mode(). Signed-off-by: Mark Fasheh <mfasheh@suse.com> Signed-off-by: Joel Becker <joel.becker@oracle.com>
| * | ocfs2: Update i_blocks in reflink operations.Tao Ma2010-03-17
| | | | | | | | | | | | | | | | | | | | | | | | In reflink, we need to upate i_blocks for the target inode. Reported-by: Jie Liu <jeff.liu@oracle.com> Signed-off-by: Tao Ma <tao.ma@oracle.com> Signed-off-by: Joel Becker <joel.becker@oracle.com>
| * | ocfs2: Change bg_chain check for ocfs2_validate_gd_parent.Tao Ma2010-03-17
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | In ocfs2_validate_gd_parent, we check bg_chain against the cl_next_free_rec of the dinode. Actually in resize, we have the chance of bg_chain == cl_next_free_rec. So add some additional condition check for it. I also rename paramter "clean_error" to "resize", since the old one is not clearly enough to indicate that we should only meet with this case in resize. btw, the correpsonding bug is http://oss.oracle.com/bugzilla/show_bug.cgi?id=1230. Signed-off-by: Tao Ma <tao.ma@oracle.com> Signed-off-by: Joel Becker <joel.becker@oracle.com>
| * | [PATCH] Skip check for mandatory locks when unlockingSachin Prabhu2010-03-17
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ocfs2_lock() will skip locks on file which has mode set to 02666. This is a problem in cases where the mode of the file is changed after a process has obtained a lock on the file. ocfs2_lock() should skip the check for mandatory locks when unlocking a file. Signed-off-by: Sachin Prabhu <sprabhu@redhat.com> Signed-off-by: Joel Becker <joel.becker@oracle.com>
* | | Merge branch 'for-linus' of ↵Linus Torvalds2010-03-29
|\ \ \ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client * 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client: (28 commits) ceph: update discussion list address in MAINTAINERS ceph: some documentations fixes ceph: fix use after free on mds __unregister_request ceph: avoid loaded term 'OSD' in documention ceph: fix possible double-free of mds request reference ceph: fix session check on mds reply ceph: handle kmalloc() failure ceph: propagate mds session allocation failures to caller ceph: make write_begin wait propagate ERESTARTSYS ceph: fix snap rebuild condition ceph: avoid reopening osd connections when address hasn't changed ceph: rename r_sent_stamp r_stamp ceph: fix connection fault con_work reentrancy problem ceph: prevent dup stale messages to console for restarting mds ceph: fix pg pool decoding from incremental osdmap update ceph: fix mds sync() race with completing requests ceph: only release unused caps with mds requests ceph: clean up handle_cap_grant, handle_caps wrt session mutex ceph: fix session locking in handle_caps, ceph_check_caps ceph: drop unnecessary WARN_ON in caps migration ...
| * | | ceph: fix use after free on mds __unregister_requestSage Weil2010-03-29
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | There was a use after free in __unregister_request that would trigger whenever the request map held the last reference. This appears to have triggered an oops during 'umount -f' when requests are being torn down. Signed-off-by: Sage Weil <sage@newdream.net>
| * | | ceph: fix possible double-free of mds request referenceSage Weil2010-03-23
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Clear pointer to mds request after dropping the reference to ensure we don't drop it again, as there is at least one error path through this function that does not reset fi->last_readdir to a new value. Signed-off-by: Sage Weil <sage@newdream.net>
| * | | ceph: fix session check on mds replySage Weil2010-03-23
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Fix a broken check that a reply came back from the same MDS we sent the request to. I don't think a case that actually triggers this would ever come up in practice, but it's clearly wrong and easy to fix. Reported-by: Dan Carpenter <error27@gmail.com> Signed-off-by: Sage Weil <sage@newdream.net>
| * | | ceph: handle kmalloc() failureDan Carpenter2010-03-23
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Return ERR_PTR(-ENOMEM) if kmalloc() fails. We handle allocation failures the same way later in the function. Signed-off-by: Dan Carpenter <error27@gmail.com> Signed-off-by: Sage Weil <sage@newdream.net>
| * | | ceph: propagate mds session allocation failures to callerSage Weil2010-03-23
| | | | | | | | | | | | | | | | | | | | | | | | Return error to original caller if register_session() fails. Signed-off-by: Sage Weil <sage@newdream.net>
| * | | ceph: make write_begin wait propagate ERESTARTSYSSage Weil2010-03-23
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Currently, if the wait_event_interruptible is interrupted, we return EAGAIN unconditionally and loop, such that we aren't, in fact, interruptible. So, propagate ERESTARTSYS if we get it. Signed-off-by: Sage Weil <sage@newdream.net>
| * | | ceph: fix snap rebuild conditionSage Weil2010-03-23
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | We were rebuilding the snap context when it was not necessary (i.e. when the realm seq hadn't changed _and_ the parent seq was still older), which caused page snapc pointers to not match the realm's snapc pointer (even though the snap context itself was identical). This confused begin_write and put it into an endless loop. The correct logic is: rebuild snapc if _my_ realm seq changed, or if my parent realm's seq is newer than mine (and thus mine needs to be rebuilt too). Signed-off-by: Sage Weil <sage@newdream.net>
| * | | ceph: avoid reopening osd connections when address hasn't changedSage Weil2010-03-23
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | We get a fault callback on _every_ tcp connection fault. Normally, we want to reopen the connection when that happens. If the address we have is bad, however, and connection attempts always result in a connection refused or similar error, explicitly closing and reopening the msgr connection just prevents the messenger's backoff logic from kicking in. The result can be a console full of [ 3974.417106] ceph: osd11 10.3.14.138:6800 connection failed [ 3974.423295] ceph: osd11 10.3.14.138:6800 connection failed [ 3974.429709] ceph: osd11 10.3.14.138:6800 connection failed Instead, if we get a fault, and have outstanding requests, but the osd address hasn't changed and the connection never successfully connected in the first place, do nothing to the osd connection. The messenger layer will back off and retry periodically, because we never connected and thus the lossy bit is not set. Instead, touch each request's r_stamp so that handle_timeout can tell the request is still alive and kicking. Signed-off-by: Sage Weil <sage@newdream.net>
| * | | ceph: rename r_sent_stamp r_stampSage Weil2010-03-23
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Make variable name slightly more generic, since it will (soon) reflect either the time the request was sent OR the time it was last determined to be still retrying. Signed-off-by: Sage Weil <sage@newdream.net>
| * | | ceph: fix connection fault con_work reentrancy problemSage Weil2010-03-23
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The messenger fault was clearing the BUSY bit, for reasons unclear. This made it possible for the con->ops->fault function to reopen the connection, and requeue work in the workqueue--even though the current thread was already in con_work. This avoids a problem where the client busy loops with connection failures on an unreachable OSD, but doesn't address the root cause of that problem. Signed-off-by: Sage Weil <sage@newdream.net>
| * | | ceph: prevent dup stale messages to console for restarting mdsSage Weil2010-03-23
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Prevent duplicate 'mds0 caps stale' message from spamming the console every few seconds while the MDS restarts. Set s_renew_requested earlier, so that we only print the message once, even if we don't send an actual request. Signed-off-by: Sage Weil <sage@newdream.net>
| * | | ceph: fix pg pool decoding from incremental osdmap updateSage Weil2010-03-23
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The incremental map decoding of pg pool updates wasn't skipping the snaps and removed_snaps vectors. This caused osd requests to stall when pool snapshots were created or fs snapshots were deleted. Use a common helper for full and incremental map decoders that decodes pools properly. Signed-off-by: Sage Weil <sage@newdream.net>
| * | | ceph: fix mds sync() race with completing requestsSage Weil2010-03-23
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The wait_unsafe_requests() helper dropped the mdsc mutex to wait for each request to complete, and then examined r_node to get the next request after retaking the lock. But the request completion removes the request from the tree, so r_node was always undefined at this point. Since it's a small race, it usually led to a valid request, but not always. The result was an occasional crash in rb_next() while dereferencing node->rb_left. Fix this by clearing the rb_node when removing the request from the request tree, and not walking off into the weeds when we are done waiting for a request. Since the request we waited on will _always_ be out of the request tree, take a ref on the next request, in the hopes that it won't be. But if it is, it's ok: we can start over from the beginning (and traverse over older read requests again). Signed-off-by: Sage Weil <sage@newdream.net>
| * | | ceph: only release unused caps with mds requestsSage Weil2010-03-23
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | We were releasing used caps (e.g. FILE_CACHE) from encode_inode_release with MDS requests (e.g. setattr). We don't carry refs on most caps, so this code worked most of the time, but for setattr (utimes) we try to drop Fscr. This causes cap state to get slightly out of sync with reality, and may result in subsequent mds revoke messages getting ignored. Fix by only releasing unused caps. Signed-off-by: Sage Weil <sage@newdream.net>
| * | | ceph: clean up handle_cap_grant, handle_caps wrt session mutexSage Weil2010-03-23
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Drop session mutex unconditionally in handle_cap_grant, and do the check_caps from the handle_cap_grant helper. This avoids using a magic return value. Also avoid using a flag variable in the IMPORT case and call check_caps at the appropriate point. Signed-off-by: Sage Weil <sage@newdream.net>
| * | | ceph: fix session locking in handle_caps, ceph_check_capsSage Weil2010-03-23
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Passing a session pointer to ceph_check_caps() used to mean it would leave the session mutex locked. That wasn't always possible if it wasn't passed CHECK_CAPS_AUTHONLY. If could unlock the passed session and lock a differet session mutex, which was clearly wrong, and also emitted a warning when it a racing CPU retook it and we did an unlock from the wrong context. This was only a problem when there was more than one MDS. First, make ceph_check_caps unconditionally drop the session mutex, so that it is free to lock other sessions as needed. Then adjust the one caller that passes in a session (handle_cap_grant) accordingly. Signed-off-by: Sage Weil <sage@newdream.net>
| * | | ceph: drop unnecessary WARN_ON in caps migrationSage Weil2010-03-23
| | | | | | | | | | | | | | | | | | | | | | | | | | | | If we don't have the exported cap it's because we already released it. No need to WARN. Signed-off-by: Sage Weil <sage@newdream.net>
| * | | ceph: fix null pointer deref of r_osd in debug outputSage Weil2010-03-23
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This causes an oops when debug output is enabled and we kick an osd request with no current r_osd (sometime after an osd failure). Check the pointer before dereferencing. Signed-off-by: Sage Weil <sage@newdream.net>
generated by cgit v1.2.2 (git 2.25.0) at 2025-02-11 07:31:59 -0500