summaryrefslogtreecommitdiff
path: root/drivers/md/md-cluster.c
AgeCommit message (Collapse)Author
2018-06-12treewide: kzalloc() -> kcalloc()Kees Cook
The kzalloc() function has a 2-factor argument form, kcalloc(). This patch replaces cases of: kzalloc(a * b, gfp) with: kcalloc(a * b, gfp) as well as handling cases of: kzalloc(a * b * c, gfp) with: kzalloc(array3_size(a, b, c), gfp) as it's slightly less ugly than: kzalloc_array(array_size(a, b), c, gfp) This does, however, attempt to ignore constant size factors like: kzalloc(4 * 1024, gfp) though any constants defined via macros get caught up in the conversion. Any factors with a sizeof() of "unsigned char", "char", and "u8" were dropped, since they're redundant. The Coccinelle script used for this was: // Fix redundant parens around sizeof(). @@ type TYPE; expression THING, E; @@ ( kzalloc( - (sizeof(TYPE)) * E + sizeof(TYPE) * E , ...) | kzalloc( - (sizeof(THING)) * E + sizeof(THING) * E , ...) ) // Drop single-byte sizes and redundant parens. @@ expression COUNT; typedef u8; typedef __u8; @@ ( kzalloc( - sizeof(u8) * (COUNT) + COUNT , ...) | kzalloc( - sizeof(__u8) * (COUNT) + COUNT , ...) | kzalloc( - sizeof(char) * (COUNT) + COUNT , ...) | kzalloc( - sizeof(unsigned char) * (COUNT) + COUNT , ...) | kzalloc( - sizeof(u8) * COUNT + COUNT , ...) | kzalloc( - sizeof(__u8) * COUNT + COUNT , ...) | kzalloc( - sizeof(char) * COUNT + COUNT , ...) | kzalloc( - sizeof(unsigned char) * COUNT + COUNT , ...) ) // 2-factor product with sizeof(type/expression) and identifier or constant. @@ type TYPE; expression THING; identifier COUNT_ID; constant COUNT_CONST; @@ ( - kzalloc + kcalloc ( - sizeof(TYPE) * (COUNT_ID) + COUNT_ID, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * COUNT_ID + COUNT_ID, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * (COUNT_CONST) + COUNT_CONST, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * COUNT_CONST + COUNT_CONST, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * (COUNT_ID) + COUNT_ID, sizeof(THING) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * COUNT_ID + COUNT_ID, sizeof(THING) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * (COUNT_CONST) + COUNT_CONST, sizeof(THING) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * COUNT_CONST + COUNT_CONST, sizeof(THING) , ...) ) // 2-factor product, only identifiers. @@ identifier SIZE, COUNT; @@ - kzalloc + kcalloc ( - SIZE * COUNT + COUNT, SIZE , ...) // 3-factor product with 1 sizeof(type) or sizeof(expression), with // redundant parens removed. @@ expression THING; identifier STRIDE, COUNT; type TYPE; @@ ( kzalloc( - sizeof(TYPE) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc( - sizeof(TYPE) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc( - sizeof(TYPE) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc( - sizeof(TYPE) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc( - sizeof(THING) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kzalloc( - sizeof(THING) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kzalloc( - sizeof(THING) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kzalloc( - sizeof(THING) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) ) // 3-factor product with 2 sizeof(variable), with redundant parens removed. @@ expression THING1, THING2; identifier COUNT; type TYPE1, TYPE2; @@ ( kzalloc( - sizeof(TYPE1) * sizeof(TYPE2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | kzalloc( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | kzalloc( - sizeof(THING1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | kzalloc( - sizeof(THING1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | kzalloc( - sizeof(TYPE1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) | kzalloc( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) ) // 3-factor product, only identifiers, with redundant parens removed. @@ identifier STRIDE, SIZE, COUNT; @@ ( kzalloc( - (COUNT) * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - COUNT * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - COUNT * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - (COUNT) * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - COUNT * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - (COUNT) * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - (COUNT) * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - COUNT * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) ) // Any remaining multi-factor products, first at least 3-factor products, // when they're not all constants... @@ expression E1, E2, E3; constant C1, C2, C3; @@ ( kzalloc(C1 * C2 * C3, ...) | kzalloc( - (E1) * E2 * E3 + array3_size(E1, E2, E3) , ...) | kzalloc( - (E1) * (E2) * E3 + array3_size(E1, E2, E3) , ...) | kzalloc( - (E1) * (E2) * (E3) + array3_size(E1, E2, E3) , ...) | kzalloc( - E1 * E2 * E3 + array3_size(E1, E2, E3) , ...) ) // And then all remaining 2 factors products when they're not all constants, // keeping sizeof() as the second factor argument. @@ expression THING, E1, E2; type TYPE; constant C1, C2, C3; @@ ( kzalloc(sizeof(THING) * C2, ...) | kzalloc(sizeof(TYPE) * C2, ...) | kzalloc(C1 * C2 * C3, ...) | kzalloc(C1 * C2, ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * (E2) + E2, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * E2 + E2, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * (E2) + E2, sizeof(THING) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * E2 + E2, sizeof(THING) , ...) | - kzalloc + kcalloc ( - (E1) * E2 + E1, E2 , ...) | - kzalloc + kcalloc ( - (E1) * (E2) + E1, E2 , ...) | - kzalloc + kcalloc ( - E1 * E2 + E1, E2 , ...) ) Signed-off-by: Kees Cook <keescook@chromium.org>
2017-11-01md-cluster: update document for raid10Guoqing Jiang
Signed-off-by: Guoqing Jiang <gqjiang@suse.com> Signed-off-by: Shaohua Li <shli@fb.com>
2017-11-01md: remove special meaning of ->quiesce(.., 2)NeilBrown
The '2' argument means "wake up anything that is waiting". This is an inelegant part of the design and was added to help support management of suspend_lo/suspend_hi setting. Now that suspend_lo/hi is managed in mddev_suspend/resume, that need is gone. These is still a couple of places where we call 'quiesce' with an argument of '2', but they can safely be changed to call ->quiesce(.., 1); ->quiesce(.., 0) which achieve the same result at the small cost of pausing IO briefly. This removes a small "optimization" from suspend_{hi,lo}_store, but it isn't clear that optimization served a useful purpose. The code now is a lot clearer. Suggested-by: Shaohua Li <shli@kernel.org> Signed-off-by: NeilBrown <neilb@suse.com> Signed-off-by: Shaohua Li <shli@fb.com>
2017-10-16md: rename some drivers/md/ files to have an "md-" prefixMike Snitzer
Motivated by the desire to illiminate the imprecise nature of DM-specific patches being unnecessarily sent to both the MD maintainer and mailing-list. Which is born out of the fact that DM files also reside in drivers/md/ Now all MD-specific files in drivers/md/ start with either "raid" or "md-" and the MAINTAINERS file has been updated accordingly. Shaohua: don't change module name Signed-off-by: Mike Snitzer <snitzer@redhat.com> Signed-off-by: Shaohua Li <shli@fb.com>
2017-10-16md-cluster: make function cluster_check_sync_size staticColin Ian King
The function cluster_check_sync_size is local to the source and does not need to be in global scope, so make it static. Cleans up sparse warning: symbol 'cluster_check_sync_size' was not declared. Should it be static? Signed-off-by: Colin Ian King <colin.king@canonical.com> Signed-off-by: Shaohua Li <shli@fb.com>
2017-05-21md-cluster: fix potential lock issue in add_new_diskGuoqing Jiang
The add_new_disk returns with communication locked if __sendmsg returns failure, fix it with call unlock_comm before return. Reported-by: Dan Carpenter <dan.carpenter@oracle.com> CC: Goldwyn Rodrigues <rgoldwyn@suse.com> Signed-off-by: Guoqing Jiang <gqjiang@suse.com> Signed-off-by: Shaohua Li <shli@fb.com>
2017-04-14md-cluster: Fix a memleak in an error handling pathChristophe JAILLET
We know that 'bm_lockres' is NULL here, so 'lockres_free(bm_lockres)' is a no-op. According to resource handling in case of error a few lines below, it is likely that 'bitmap_free(bitmap)' was expected instead. Fixes: b98938d16a10 ("md-cluster: introduce cluster_check_sync_size") Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr> Reviewed-by: Guoqing Jiang <gqjiang@suse.com> Signed-off-by: Shaohua Li <shli@fb.com>
2017-03-16md-cluster: add the support for resizeGuoqing Jiang
To update size for cluster raid, we need to make sure all nodes can perform the change successfully. However, it is possible that some of them can't do it due to failure (bitmap_resize could fail). So we need to consider the issue before we set the capacity unconditionally, and we use below steps to perform sanity check. 1. A change the size, then broadcast METADATA_UPDATED msg. 2. B and C receive METADATA_UPDATED change the size excepts call set_capacity, sync_size is not update if the change failed. Also call bitmap_update_sb to sync sb to disk. 3. A checks other node's sync_size, if sync_size has been updated in all nodes, then send CHANGE_CAPACITY msg otherwise send msg to revert previous change. 4. B and C call set_capacity if receive CHANGE_CAPACITY msg, otherwise pers->resize will be called to restore the old value. Reviewed-by: NeilBrown <neilb@suse.com> Signed-off-by: Guoqing Jiang <gqjiang@suse.com> Signed-off-by: Shaohua Li <shli@fb.com>
2017-03-16md-cluster: introduce cluster_check_sync_sizeGuoqing Jiang
Support resize is a little complex for clustered raid, since we need to ensure all the nodes share the same knowledge about the size of raid. We achieve the goal by check the sync_size which is in each node's bitmap, we can only change the capacity after cluster_check_sync_size returns 0. Also, get_bitmap_from_slot is added to get a slot's bitmap. And we exported some funcs since they are used in cluster_check_sync_size(). We can also reuse get_bitmap_from_slot to remove redundant code existed in bitmap_copy_from_slot. Reviewed-by: NeilBrown <neilb@suse.com> Signed-off-by: Guoqing Jiang <gqjiang@suse.com> Signed-off-by: Shaohua Li <shli@fb.com>
2017-03-16md-cluster: add CHANGE_CAPACITY message typeGuoqing Jiang
The msg type CHANGE_CAPACITY is introduced to support resize clustered raid in later patch, and it is sent after all the nodes have the same sync_size, receiver node just need to set new capacity once received this msg. Reviewed-by: NeilBrown <neilb@suse.com> Signed-off-by: Guoqing Jiang <gqjiang@suse.com> Signed-off-by: Shaohua Li <shli@fb.com>
2017-03-16md-cluster: use sync way to handle METADATA_UPDATED msgGuoqing Jiang
Previously, when node received METADATA_UPDATED msg, it just need to wakeup mddev->thread, then md_reload_sb will be called eventually. We taken the asynchronous way to avoid a deadlock issue, the deadlock issue could happen when one node is receiving the METADATA_UPDATED msg (wants reconfig_mutex) and trying to run the path: md_check_recovery -> mddev_trylock(hold reconfig_mutex) -> md_update_sb-metadata_update_start (want EX on token however token is got by the sending node) Since we will support resizing for clustered raid, and we need the metadata update handling to be synchronous so that the initiating node can detect failure, so we need to change the way for handling METADATA_UPDATED msg. But, we obviously need to avoid above deadlock with the sync way. To make this happen, we considered to not hold reconfig_mutex to call md_reload_sb, if some other thread has already taken reconfig_mutex and waiting for the 'token', then process_recvd_msg() can safely call md_reload_sb() without taking the mutex. This is because we can be certain that no other thread will take the mutex, and we also certain that the actions performed by md_reload_sb() won't interfere with anything that the other thread is in the middle of. To make this more concrete, we added a new cinfo->state bit MD_CLUSTER_HOLDING_MUTEX_FOR_RECVD Which is set in lock_token() just before dlm_lock_sync() is called, and cleared just after. As lock_token() is always called with reconfig_mutex() held (the specific case is the resync_info_update which is distinguished well in previous patch), if process_recvd_msg() finds that the new bit is set, then the mutex must be held by some other thread, and it will keep waiting. So process_metadata_update() can call md_reload_sb() if either mddev_trylock() succeeds, or if MD_CLUSTER_HOLDING_MUTEX_FOR_RECVD is set. The tricky bit is what to do if neither of these apply. We need to wait. Fortunately mddev_unlock() always calls wake_up() on mddev->thread->wqueue. So we can get lock_token() to call wake_up() on that when it sets the bit. There are also some related changes inside this commit: 1. remove RELOAD_SB related codes since there are not valid anymore. 2. mddev is added into md_cluster_info then we can get mddev inside lock_token. 3. add new parameter for lock_token to distinguish reconfig_mutex is held or not. And, we need to set MD_CLUSTER_HOLDING_MUTEX_FOR_RECVD in below: 1. set it before unregister thread, otherwise a deadlock could appear if stop a resyncing array. This is because md_unregister_thread(&cinfo->recv_thread) is blocked by recv_daemon -> process_recvd_msg -> process_metadata_update. To resolve the issue, MD_CLUSTER_HOLDING_MUTEX_FOR_RECVD is also need to be set before unregister thread. 2. set it in metadata_update_start to fix another deadlock. a. Node A sends METADATA_UPDATED msg (held Token lock). b. Node B wants to do resync, and is blocked since it can't get Token lock, but MD_CLUSTER_HOLDING_MUTEX_FOR_RECVD is not set since the callchain (md_do_sync -> sync_request -> resync_info_update -> sendmsg -> lock_comm -> lock_token) doesn't hold reconfig_mutex. c. Node B trys to update sb (held reconfig_mutex), but stopped at wait_event() in metadata_update_start since we have set MD_CLUSTER_SEND_LOCK flag in lock_comm (step 2). d. Then Node B receives METADATA_UPDATED msg from A, of course recv_daemon is blocked forever. Since metadata_update_start always calls lock_token with reconfig_mutex, we need to set MD_CLUSTER_HOLDING_MUTEX_FOR_RECVD here as well, and lock_token don't need to set it twice unless lock_token is invoked from lock_comm. Finally, thanks to Neil for his great idea and help! Reviewed-by: NeilBrown <neilb@suse.com> Signed-off-by: Guoqing Jiang <gqjiang@suse.com> Signed-off-by: Shaohua Li <shli@fb.com>
2017-03-09md-cluster: remove useless memset from gather_all_resync_infoGuoqing Jiang
This memset is not needed. The lvb is already zeroed because it was recently allocated by lockres_init, which uses kzalloc(), and read_resync_info() doesn't need it to be zero anyway. Reviewed-by: NeilBrown <neilb@suse.com> Signed-off-by: Guoqing Jiang <gqjiang@suse.com> Signed-off-by: Shaohua Li <shli@fb.com>
2017-03-09md-cluster: free md_cluster_info if node leave clusterGuoqing Jiang
To avoid memory leak, we need to free the cinfo which is allocated when node join cluster. Reviewed-by: NeilBrown <neilb@suse.com> Signed-off-by: Guoqing Jiang <gqjiang@suse.com> Signed-off-by: Shaohua Li <shli@fb.com>
2016-09-21md-cluster: make resync lock also could be interrupttedGuoqing Jiang
When one node is perform resync or recovery, other nodes can't get resync lock and could block for a while before it holds the lock, so we can't stop array immediately for this scenario. To make array could be stop quickly, we check MD_CLOSING in dlm_lock_sync_interruptible to make us can interrupt the lock request. Reviewed-by: NeilBrown <neilb@suse.com> Signed-off-by: Guoqing Jiang <gqjiang@suse.com> Signed-off-by: Shaohua Li <shli@fb.com>
2016-09-21md-cluster: introduce dlm_lock_sync_interruptible to fix tasks hangGuoqing Jiang
When some node leaves cluster, then it's bitmap need to be synced by another node, so "md*_recover" thread is triggered for the purpose. However, with below steps. we can find tasks hang happened either in B or C. 1. Node A create a resyncing cluster raid1, assemble it in other two nodes (B and C). 2. stop array in B and C. 3. stop array in A. linux44:~ # ps aux|grep md|grep D root 5938 0.0 0.1 19852 1964 pts/0 D+ 14:52 0:00 mdadm -S md0 root 5939 0.0 0.0 0 0 ? D 14:52 0:00 [md0_recover] linux44:~ # cat /proc/5939/stack [<ffffffffa04cf321>] dlm_lock_sync+0x71/0x90 [md_cluster] [<ffffffffa04d0705>] recover_bitmaps+0x125/0x220 [md_cluster] [<ffffffffa052105d>] md_thread+0x16d/0x180 [md_mod] [<ffffffff8107ad94>] kthread+0xb4/0xc0 [<ffffffff8152a518>] ret_from_fork+0x58/0x90 linux44:~ # cat /proc/5938/stack [<ffffffff8107afde>] kthread_stop+0x6e/0x120 [<ffffffffa0519da0>] md_unregister_thread+0x40/0x80 [md_mod] [<ffffffffa04cfd20>] leave+0x70/0x120 [md_cluster] [<ffffffffa0525e24>] md_cluster_stop+0x14/0x30 [md_mod] [<ffffffffa05269ab>] bitmap_free+0x14b/0x150 [md_mod] [<ffffffffa0523f3b>] do_md_stop+0x35b/0x5a0 [md_mod] [<ffffffffa0524e83>] md_ioctl+0x873/0x1590 [md_mod] [<ffffffff81288464>] blkdev_ioctl+0x214/0x7d0 [<ffffffff811dd3dd>] block_ioctl+0x3d/0x40 [<ffffffff811b92d4>] do_vfs_ioctl+0x2d4/0x4b0 [<ffffffff811b9538>] SyS_ioctl+0x88/0xa0 [<ffffffff8152a5c9>] system_call_fastpath+0x16/0x1b The problem is caused by recover_bitmaps can't reliably abort when the thread is unregistered. So dlm_lock_sync_interruptible is introduced to detect the thread's situation to fix the problem. Reviewed-by: NeilBrown <neilb@suse.com> Signed-off-by: Guoqing Jiang <gqjiang@suse.com> Signed-off-by: Shaohua Li <shli@fb.com>
2016-09-21md-cluster: convert the completion to wait queueGuoqing Jiang
Previously, we used completion to sync between require dlm lock and sync_ast, however we will have to expose completion.wait and completion.done in dlm_lock_sync_interruptible (introduced later), it is not a common usage for completion, so convert related things to wait queue. Reviewed-by: NeilBrown <neilb@suse.com> Signed-off-by: Guoqing Jiang <gqjiang@suse.com> Signed-off-by: Shaohua Li <shli@fb.com>
2016-09-21md-cluster: protect md_find_rdev_nr_rcu with rcu lockGuoqing Jiang
We need to use rcu_read_lock/unlock to avoid potential race. Reported-by: Shaohua Li <shli@fb.com> Reviewed-by: NeilBrown <neilb@suse.com> Signed-off-by: Guoqing Jiang <gqjiang@suse.com> Signed-off-by: Shaohua Li <shli@fb.com>
2016-09-21md-cluster: remove some unnecessary dlm_unlock_syncGuoqing Jiang
Since DLM_LKF_FORCEUNLOCK is used in lockres_free, we don't need to call dlm_unlock_sync before free lock resource. Reviewed-by: NeilBrown <neilb@suse.com> Signed-off-by: Guoqing Jiang <gqjiang@suse.com> Signed-off-by: Shaohua Li <shli@fb.com>
2016-09-21md-cluster: use FORCEUNLOCK in lockres_freeGuoqing Jiang
For dlm_unlock, we need to pass flag to dlm_unlock as the third parameter instead of set res->flags. Also, DLM_LKF_FORCEUNLOCK is more suitable for dlm_unlock since it works even the lock is on waiting or convert queue. Acked-by: NeilBrown <neilb@suse.com> Signed-off-by: Guoqing Jiang <gqjiang@suse.com> Signed-off-by: Shaohua Li <shli@fb.com>
2016-08-24md-cluster: fix error return code in join()Wei Yongjun
Fix to return error code -ENOMEM from the lockres_init() error handling case instead of 0, as done elsewhere in this function. Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com> Signed-off-by: Shaohua Li <shli@fb.com>
2016-05-09md-cluster: check the return value of process_recvd_msgGuoqing Jiang
We don't need to run the full path of recv_daemon if process_recvd_msg doesn't return 0. Reviewed-by: NeilBrown <neilb@suse.com> Signed-off-by: Guoqing Jiang <gqjiang@suse.com> Signed-off-by: Shaohua Li <shli@fb.com>
2016-05-09md-cluster: gather resync infos and enable recv_thread after bitmap is readyGuoqing Jiang
The in-memory bitmap is not ready when node joins cluster, so it doesn't make sense to make gather_all_resync_info() called so earlier, we need to call it after the node's bitmap is setup. Also, recv_thread could be wake up after node joins cluster, but it could cause problem if node receives RESYNCING message without persionality since mddev->pers->quiesce is called in process_suspend_info. This commit introduces a new cluster interface load_bitmaps to fix above problems, load_bitmaps is called in bitmap_load where bitmap and persionality are ready, and load_bitmaps does the following tasks: 1. call gather_all_resync_info to load all the node's bitmap info. 2. set MD_CLUSTER_ALREADY_IN_CLUSTER bit to recv_thread could be wake up, and wake up recv_thread if there is pending recv event. Then ack_bast only wakes up recv_thread after IN_CLUSTER bit is ready otherwise MD_CLUSTER_PENDING_RESYNC_EVENT is set. Reviewed-by: NeilBrown <neilb@suse.com> Signed-off-by: Guoqing Jiang <gqjiang@suse.com> Signed-off-by: Shaohua Li <shli@fb.com>
2016-05-04md-cluster: sync bitmap when node received RESYNCING msgGuoqing Jiang
If the node received RESYNCING message which means another node will perform resync with the area, then we don't want to do it again in another node. Let's set RESYNC_MASK and clear NEEDED_MASK for the region from old-low to new-low which has finished syncing, and the region from old-hi to new-hi is about to syncing, bitmap_sync_with_cluste is introduced for the purpose. Reviewed-by: NeilBrown <neilb@suse.com> Signed-off-by: Guoqing Jiang <gqjiang@suse.com> Signed-off-by: Shaohua Li <shli@fb.com>
2016-05-04md-cluster: fix locking when node joins cluster during message broadcastGuoqing Jiang
If a node joins the cluster while a message broadcast is under way, a lock issue could happen as follows. For a cluster which included two nodes, if node A is calling __sendmsg before up-convert CR to EX on ack, and node B released CR on ack. But if a new node C joins the cluster and it doesn't receive the message which A sent before, so it could hold CR on ack before A up-convert CR to EX on ack. So a node joining the cluster should get an EX lock on the "token" first to ensure no broadcast is ongoing, then release it after held CR on ack. Reviewed-by: NeilBrown <neilb@suse.com> Signed-off-by: Guoqing Jiang <gqjiang@suse.com> Signed-off-by: Shaohua Li <shli@fb.com>
2016-05-04md-cluster: unregister thread if err happenedGuoqing Jiang
The two threads need to be unregistered if a node can't join cluster successfully. Reviewed-by: NeilBrown <neilb@suse.com> Signed-off-by: Guoqing Jiang <gqjiang@suse.com> Signed-off-by: Shaohua Li <shli@fb.com>
2016-05-04md-cluster: wake up thread to continue recoveryGuoqing Jiang
In recovery case, we need to set MD_RECOVERY_NEEDED and wake up thread only if recover is not finished. Reviewed-by: NeilBrown <neilb@suse.com> Signed-off-by: Guoqing Jiang <gqjiang@suse.com> Signed-off-by: Shaohua Li <shli@fb.com>
2016-05-04md-cluster: change resync lock from asynchronous to synchronousGuoqing Jiang
If multiple nodes choose to attempt do resync at the same time they need to be serialized so they don't duplicate effort. This serialization is done by locking the 'resync' DLM lock. Currently if a node cannot get the lock immediately it doesn't request notification when the lock becomes available (i.e. DLM_LKF_NOQUEUE is set), so it may not reliably find out when it is safe to try again. Rather than trying to arrange an async wake-up when the lock becomes available, switch to using synchronous locking - this is a lot easier to think about. As it is not permitted to block in the 'raid1d' thread, move the locking to the resync thread. So the rsync thread is forked immediately, but it blocks until the resync lock is available. Once the lock is locked it checks again if any resync action is needed. A particular symptom of the current problem is that a node can get stuck with "resync=pending" indefinitely. Reviewed-by: NeilBrown <neilb@suse.com> Signed-off-by: Guoqing Jiang <gqjiang@suse.com> Signed-off-by: Shaohua Li <shli@fb.com>
2016-01-24md-cluster: fix missing memory freeShaohua Li
There are several places we allocate dlm_lock_resource, but not free it. leave() need free a lock resource too (from Guoqing) Cc: Goldwyn Rodrigues <rgoldwyn@suse.com> Cc: Guoqing Jiang <gqjiang@suse.com> Cc: NeilBrown <neilb@suse.com> Signed-off-by: Shaohua Li <shli@fb.com>
2016-01-06md-cluster: update comments for MD_CLUSTER_SEND_LOCKED_ALREADYGuoqing Jiang
1. fix unbalanced parentheses. 2. add more description about that MD_CLUSTER_SEND_LOCKED_ALREADY will be cleared after set it in add_new_disk. Signed-off-by: Guoqing Jiang <gqjiang@suse.com> Signed-off-by: NeilBrown <neilb@suse.com>
2016-01-06md-cluster: Protect communication with mutexesGuoqing Jiang
Communication can happen through multiple threads. It is possible that one thread steps over another threads sequence. So, we use mutexes to protect both the send and receive sequences. Send communication is locked through state bit, MD_CLUSTER_SEND_LOCK. Communication is locked with bit manipulation in order to allow "lock and hold" for the add operation. In case of an add operation, if the lock is held, MD_CLUSTER_SEND_LOCKED_ALREADY is set. When md_update_sb() calls metadata_update_start(), it checks (in a single statement to avoid races), if the communication is already locked. If yes, it merely returns zero, else it locks the token lockresource. Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com> Signed-off-by: NeilBrown <neilb@suse.com>
2016-01-06md-cluster: Defer MD reloading to mddev->threadGuoqing Jiang
Reloading of superblock must be performed under reconfig_mutex. However, this cannot be done with md_reload_sb because it would deadlock with the message DLM lock. So, we defer it in md_check_recovery() which is executed by mddev->thread. This introduces a new flag, MD_RELOAD_SB, which if set, will reload the superblock. And good_device_nr is also added to 'struct mddev' which is used to get the num of the good device within cluster raid. Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com> Signed-off-by: Guoqing Jiang <gqjiang@suse.com> Signed-off-by: NeilBrown <neilb@suse.com>
2016-01-06md-cluster: append some actions when change bitmap from clustered to noneGuoqing Jiang
For clustered raid, we need to do extra actions when change bitmap to none. 1. check if all the bitmap lock could be get or not, if yes then we can continue the change since cluster raid is only active in current node. Otherwise return fail and unlock the related bitmap locks 2. set nodes to 0 and then leave cluster environment. 3. release other nodes's bitmap lock. Signed-off-by: Guoqing Jiang <gqjiang@suse.com> Signed-off-by: NeilBrown <neilb@suse.com>
2016-01-06md-cluster: Fix the remove sequence with the new MD reload codeGoldwyn Rodrigues
The remove disk message does not need metadata_update_start(), but can be an independent message. Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com> Signed-off-by: Guoqing Jiang <gqjiang@suse.com> Signed-off-by: NeilBrown <neilb@suse.com>
2016-01-06md-cluster: remove a disk asynchronously from cluster environmentGuoqing Jiang
For cluster raid, if one disk couldn't be reach in one node, then other nodes would receive the REMOVE message for the disk. In receiving node, we can't call md_kick_rdev_from_array to remove the disk from array synchronously since the disk might still be busy in this node. So let's set a ClusterRemove flag on the disk, then let the thread to do the removal job eventually. Signed-off-by: Guoqing Jiang <gqjiang@suse.com> Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com> Signed-off-by: NeilBrown <neilb@suse.com>
2016-01-06md-cluster: Avoid the resync ping-pongGoldwyn Rodrigues
If a RESYNCING message with (0,0) has been sent before, do not send it again. This avoids a resync ping pong between the nodes. We read the bitmap lockresource's LVB to figure out the previous value of the RESYNCING message. Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com> Signed-off-by: NeilBrown <neilb@suse.com>
2015-10-24md-cluster: remove mddev arg from add_resync_info()NeilBrown
The arg isn't used, so its presence is only confusing. Signed-off-by: NeilBrown <neilb@suse.com>
2015-10-24md-cluster: don't cast void pointers when assigning them.NeilBrown
It is common practice in the kernel to leave out this case. It isn't needed and adds little if any value. Signed-off-by: NeilBrown <neilb@suse.com>
2015-10-24md-cluster: discard unused sb_mutex.NeilBrown
Signed-off-by: NeilBrown <neilb@suse.com>
2015-10-24md-cluster: Fix warnings when build with CF=-D__CHECK_ENDIAN__Guoqing Jiang
This patches fixes sparse warnings like incorrect type in assignment (different base types), cast to restricted __le64. Reported-by: kbuild test robot <fengguang.wu@intel.com> Signed-off-by: Guoqing Jiang <gqjiang@suse.com> Signed-off-by: NeilBrown <neilb@suse.com>
2015-10-16md-cluster: metadata_update_finish: consistently use cmsg.raid_slot as le32NeilBrown
As cmsg.raid_slot is le32, comparing for >0 is not meaningful. So introduce cpu-endian 'raid_slot' and only assign to cmsg.raid_slot when we know value is valid. Reported-by: kbuild test robot <fengguang.wu@intel.com> Signed-off-by: NeilBrown <neilb@suse.com>
2015-10-12md-cluster: Add 'SUSE' as author for md-cluster.cGuoqing Jiang
Signed-off-by: Guoqing Jiang <gqjiang@suse.com>
2015-10-12md-cluster: zero cmsg before it was sentGuoqing Jiang
Signed-off-by: Guoqing Jiang <gqjiang@suse.com>
2015-10-12md-cluster: make sure the node do not receive it's own msgGuoqing Jiang
During the past test, the node occasionally received the msg which is sent from itself, this case should not happen in theory, but it is better to avoid it in case something wrong happened. Signed-off-by: Guoqing Jiang <gqjiang@suse.com> Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
2015-10-12md-cluster: remove unnecessary setting for slotGuoqing Jiang
Since slot will be set within _sendmsg, we can remove the redundant code in resync_info_update. Signed-off-by: Guoqing Jiang <gqjiang@suse.com>
2015-10-12md-cluster: make other members of cluster_msg is handled by little endian funcsGuoqing Jiang
Signed-off-by: Guoqing Jiang <gqjiang@suse.com>
2015-10-12md-cluster: Do not printk() every received messageGoldwyn Rodrigues
The receive daemon prints kernel messages for every network message received. This would fill the kernel message log with unnecessary messages. Remove the pr_info() messages. Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
2015-10-12md-cluster: Fix adding of new disk with new reload codeGoldwyn Rodrigues
Adding the disk worked incorrectly with the new reload code. Fix it: - No operation should be performed on rdev marked as Candidate - After a metadata update operation, kick disk if role is 0xfffe else clear Candidate bit and continue with the regular change check. - Saving the mode of the lock resource to check if token lock is already locked, because it can be called twice while adding a disk. However, unlock_comm() must be called only once. - add_new_disk() is called by the node initiating the --add operation. If it needs to be canceled, call add_new_disk_cancel(). The operation is completed by md_update_sb() which will write and unlock the communication. Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
2015-10-12md-cluster: Perform resync/recovery under a DLM lockGoldwyn Rodrigues
Resync or recovery must be performed by only one node at a time. A DLM lock resource, resync_lockres provides the mutual exclusion so that only one node performs the recovery/resync at a time. If a node is unable to get the resync_lockres, because recovery is being performed by another node, it set MD_RECOVER_NEEDED so as to schedule recovery in the future. Remove the debug message in resync_info_update() used during development. Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
2015-10-12md-cluster: Improve md_reload_sb to be less error proneGoldwyn Rodrigues
md_reload_sb is too simplistic and it explicitly needs to determine the changes made by the writing node. However, there are multiple areas where a simple reload could fail. Instead, read the superblock of one of the "good" rdevs and update the necessary information: - read the superblock into a newly allocated page, by temporarily swapping out rdev->sb_page and calling ->load_super. - if that fails return - if it succeeds, call check_sb_changes 1. iterates over list of active devices and checks the matching dev_roles[] value. If that is 'faulty', the device must be marked as faulty - call md_error to mark the device as faulty. Make sure not to set CHANGE_DEVS and wakeup mddev->thread or else it would initiate a resync process, which is the responsibility of the "primary" node. - clear the Blocked bit - Call remove_and_add_spares() to hot remove the device. If the device is 'spare': - call remove_and_add_spares() to get the number of spares added in this operation. - Reduce mddev->degraded to mark the array as not degraded. 2. reset recovery_cp - read the rest of the rdevs to update recovery_offset. If recovery_offset is equal to MaxSector, call spare_active() to set it In_sync This required that recovery_offset be initialized to MaxSector, as opposed to zero so as to communicate the end of sync for a rdev. Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
2015-10-12md-cluster: Wake up suspended processGoldwyn Rodrigues
When the suspended_area is deleted, the suspended processes must be woken up in order to complete their I/O. Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>