From fa8259da0e10b189e41ee60907ec2a499bb66019 Mon Sep 17 00:00:00 2001 From: Goldwyn Rodrigues Date: Mon, 2 Mar 2015 10:55:49 -0600 Subject: [PATCH] md: Fix stray --cluster-confirm crash A --cluster-confirm without an --add (by another node) can crash the kernel. Fix it by guarding it using a state. Signed-off-by: Goldwyn Rodrigues Signed-off-by: NeilBrown --- drivers/md/md-cluster.c | 15 ++++++++++++++- drivers/md/md-cluster.h | 2 +- drivers/md/md.c | 8 ++++++-- 3 files changed, 21 insertions(+), 4 deletions(-) diff --git a/drivers/md/md-cluster.c b/drivers/md/md-cluster.c index 03e521a9ca7d..96679b22cfc0 100644 --- a/drivers/md/md-cluster.c +++ b/drivers/md/md-cluster.c @@ -42,6 +42,10 @@ struct resync_info { __le64 hi; }; +/* md_cluster_info flags */ +#define MD_CLUSTER_WAITING_FOR_NEWDISK 1 + + struct md_cluster_info { /* dlm lock space and resources for clustered raid. */ dlm_lockspace_t *lockspace; @@ -61,6 +65,7 @@ struct md_cluster_info { struct dlm_lock_resource *no_new_dev_lockres; struct md_thread *recv_thread; struct completion newdisk_completion; + unsigned long state; }; enum msg_type { @@ -380,9 +385,11 @@ static void process_add_new_disk(struct mddev *mddev, struct cluster_msg *cmsg) snprintf(raid_slot, 16, "RAID_DISK=%d", cmsg->raid_slot); pr_info("%s:%d Sending kobject change with %s and %s\n", __func__, __LINE__, disk_uuid, raid_slot); init_completion(&cinfo->newdisk_completion); + set_bit(MD_CLUSTER_WAITING_FOR_NEWDISK, &cinfo->state); kobject_uevent_env(&disk_to_dev(mddev->gendisk)->kobj, KOBJ_CHANGE, envp); wait_for_completion_timeout(&cinfo->newdisk_completion, NEW_DEV_TIMEOUT); + clear_bit(MD_CLUSTER_WAITING_FOR_NEWDISK, &cinfo->state); } @@ -832,13 +839,19 @@ static int add_new_disk_finish(struct mddev *mddev) return ret; } -static void new_disk_ack(struct mddev *mddev, bool ack) +static int new_disk_ack(struct mddev *mddev, bool ack) { struct md_cluster_info *cinfo = mddev->cluster_info; + if (!test_bit(MD_CLUSTER_WAITING_FOR_NEWDISK, &cinfo->state)) { + pr_warn("md-cluster(%s): Spurious cluster confirmation\n", mdname(mddev)); + return -EINVAL; + } + if (ack) dlm_unlock_sync(cinfo->no_new_dev_lockres); complete(&cinfo->newdisk_completion); + return 0; } static struct md_cluster_operations cluster_ops = { diff --git a/drivers/md/md-cluster.h b/drivers/md/md-cluster.h index 60d7e58964f5..7417133c4295 100644 --- a/drivers/md/md-cluster.h +++ b/drivers/md/md-cluster.h @@ -21,7 +21,7 @@ struct md_cluster_operations { int (*area_resyncing)(struct mddev *mddev, sector_t lo, sector_t hi); int (*add_new_disk_start)(struct mddev *mddev, struct md_rdev *rdev); int (*add_new_disk_finish)(struct mddev *mddev); - void (*new_disk_ack)(struct mddev *mddev, bool ack); + int (*new_disk_ack)(struct mddev *mddev, bool ack); }; #endif /* _MD_CLUSTER_H */ diff --git a/drivers/md/md.c b/drivers/md/md.c index ae3432e57ccb..eb6f92e57ab6 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -5755,7 +5755,7 @@ static int add_new_disk(struct mddev *mddev, mdu_disk_info_t *info) if (mddev_is_clustered(mddev) && !(info->state & ((1 << MD_DISK_CLUSTER_ADD) | (1 << MD_DISK_CANDIDATE)))) { - pr_err("%s: Cannot add to clustered mddev. Try --cluster-add\n", + pr_err("%s: Cannot add to clustered mddev.\n", mdname(mddev)); return -EINVAL; } @@ -5853,7 +5853,11 @@ static int add_new_disk(struct mddev *mddev, mdu_disk_info_t *info) if (info->state & (1 << MD_DISK_CANDIDATE)) { /* Through --cluster-confirm */ set_bit(Candidate, &rdev->flags); - md_cluster_ops->new_disk_ack(mddev, true); + err = md_cluster_ops->new_disk_ack(mddev, true); + if (err) { + export_rdev(rdev); + return err; + } } else if (info->state & (1 << MD_DISK_CLUSTER_ADD)) { /* --add initiated by this node */ err = md_cluster_ops->add_new_disk_start(mddev, rdev);