From 0c3573f19d135d718264e38c46597295bd6154b7 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Fri, 9 Jan 2009 08:31:05 +1100 Subject: md: use sysfs_notify_dirent to notify changes to md/sync_action. There is no compelling need for this, but sysfs_notify_dirent is a nicer interface and the change is good for consistency. Signed-off-by: NeilBrown --- include/linux/raid/md_k.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux/raid/md_k.h') diff --git a/include/linux/raid/md_k.h b/include/linux/raid/md_k.h index 8fc909ef6787..663803eaf0de 100644 --- a/include/linux/raid/md_k.h +++ b/include/linux/raid/md_k.h @@ -244,6 +244,7 @@ struct mddev_s struct sysfs_dirent *sysfs_state; /* handle for 'array_state' * file in sysfs. */ + struct sysfs_dirent *sysfs_action; /* handle for 'sync_action' */ spinlock_t write_lock; wait_queue_head_t sb_wait; /* for waiting on superblock updates */ -- cgit v1.2.3 From 159ec1fc060ab22b157a62364045f5e98749c4d3 Mon Sep 17 00:00:00 2001 From: Cheng Renquan Date: Fri, 9 Jan 2009 08:31:08 +1100 Subject: md: use list_for_each_entry macro directly The rdev_for_each macro defined in is identical to list_for_each_entry_safe, from , it should be defined to use list_for_each_entry_safe, instead of reinventing the wheel. But some calls to each_entry_safe don't really need a safe version, just a direct list_for_each_entry is enough, this could save a temp variable (tmp) in every function that used rdev_for_each. In this patch, most rdev_for_each loops are replaced by list_for_each_entry, totally save many tmp vars; and only in the other situations that will call list_del to delete an entry, the safe version is used. Signed-off-by: Cheng Renquan Signed-off-by: NeilBrown --- include/linux/raid/md_k.h | 11 ++++------- 1 file changed, 4 insertions(+), 7 deletions(-) (limited to 'include/linux/raid/md_k.h') diff --git a/include/linux/raid/md_k.h b/include/linux/raid/md_k.h index 663803eaf0de..8f9a54c1fb0e 100644 --- a/include/linux/raid/md_k.h +++ b/include/linux/raid/md_k.h @@ -335,17 +335,14 @@ static inline char * mdname (mddev_t * mddev) * iterates through some rdev ringlist. It's safe to remove the * current 'rdev'. Dont touch 'tmp' though. */ -#define rdev_for_each_list(rdev, tmp, list) \ - \ - for ((tmp) = (list).next; \ - (rdev) = (list_entry((tmp), mdk_rdev_t, same_set)), \ - (tmp) = (tmp)->next, (tmp)->prev != &(list) \ - ; ) +#define rdev_for_each_list(rdev, tmp, head) \ + list_for_each_entry_safe(rdev, tmp, head, same_set) + /* * iterates through the 'same array disks' ringlist */ #define rdev_for_each(rdev, tmp, mddev) \ - rdev_for_each_list(rdev, tmp, (mddev)->disks) + list_for_each_entry_safe(rdev, tmp, &((mddev)->disks), same_set) #define rdev_for_each_rcu(rdev, mddev) \ list_for_each_entry_rcu(rdev, &((mddev)->disks), same_set) -- cgit v1.2.3 From d3374825ce57ba2214d375023979f6197ccc1385 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Fri, 9 Jan 2009 08:31:10 +1100 Subject: md: make devices disappear when they are no longer needed. Currently md devices, once created, never disappear until the module is unloaded. This is essentially because the gendisk holds a reference to the mddev, and the mddev holds a reference to the gendisk, this a circular reference. If we drop the reference from mddev to gendisk, then we need to ensure that the mddev is destroyed when the gendisk is destroyed. However it is not possible to hook into the gendisk destruction process to enable this. So we drop the reference from the gendisk to the mddev and destroy the gendisk when the mddev gets destroyed. However this has a complication. Between the call __blkdev_get->get_gendisk->kobj_lookup->md_probe and the call __blkdev_get->md_open there is no obvious way to hold a reference on the mddev any more, so unless something is done, it will disappear and gendisk will be destroyed prematurely. Also, once we decide to destroy the mddev, there will be an unlockable moment before the gendisk is unlinked (blk_unregister_region) during which a new reference to the gendisk can be created. We need to ensure that this reference can not be used. i.e. the ->open must fail. So: 1/ in md_probe we set a flag in the mddev (hold_active) which indicates that the array should be treated as active, even though there are no references, and no appearance of activity. This is cleared by md_release when the device is closed if it is no longer needed. This ensures that the gendisk will survive between md_probe and md_open. 2/ In md_open we check if the mddev we expect to open matches the gendisk that we did open. If there is a mismatch we return -ERESTARTSYS and modify __blkdev_get to retry from the top in that case. In the -ERESTARTSYS sys case we make sure to wait until the old gendisk (that we succeeded in opening) is really gone so we loop at most once. Some udev configurations will always open an md device when it first appears. If we allow an md device that was just created by an open to disappear on an immediate close, then this can race with such udev configurations and result in an infinite loop the device being opened and closed, then re-open due to the 'ADD' even from the first open, and then close and so on. So we make sure an md device, once created by an open, remains active at least until some md 'ioctl' has been made on it. This means that all normal usage of md devices will allow them to disappear promptly when not needed, but the worst that an incorrect usage will do it cause an inactive md device to be left in existence (it can easily be removed). As an array can be stopped by writing to a sysfs attribute echo clear > /sys/block/mdXXX/md/array_state we need to use scheduled work for deleting the gendisk and other kobjects. This allows us to wait for any pending gendisk deletion to complete by simply calling flush_scheduled_work(). Signed-off-by: NeilBrown --- include/linux/raid/md_k.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux/raid/md_k.h') diff --git a/include/linux/raid/md_k.h b/include/linux/raid/md_k.h index 8f9a54c1fb0e..e3d17c7f954e 100644 --- a/include/linux/raid/md_k.h +++ b/include/linux/raid/md_k.h @@ -137,6 +137,8 @@ struct mddev_s struct gendisk *gendisk; struct kobject kobj; + int hold_active; +#define UNTIL_IOCTL 1 /* Superblock information */ int major_version, @@ -246,6 +248,8 @@ struct mddev_s */ struct sysfs_dirent *sysfs_action; /* handle for 'sync_action' */ + struct work_struct del_work; /* used for delayed sysfs removal */ + spinlock_t write_lock; wait_queue_head_t sb_wait; /* for waiting on superblock updates */ atomic_t pending_writes; /* number of active superblock writes */ -- cgit v1.2.3 From efeb53c0e57213e843b7ef3cc6ebcdea7d6186ac Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Fri, 9 Jan 2009 08:31:10 +1100 Subject: md: Allow md devices to be created by name. Using sequential numbers to identify md devices is somewhat artificial. Using names can be a lot more user-friendly. Also, creating md devices by opening the device special file is a bit awkward. So this patch provides a new option for creating and naming devices. Writing a name such as "md_home" to /sys/modules/md_mod/parameters/new_array will cause an array with that name to be created. It will appear in /sys/block/ /proc/partitions and /proc/mdstat as 'md_home'. It will have an arbitrary minor number allocated. md devices that a created by an open are destroyed on the last close when the device is inactive. For named md devices, they will not be destroyed until the array is explicitly stopped, either with the STOP_ARRAY ioctl or by writing 'clear' to /sys/block/md_XXXX/md/array_state. The name of the array must start 'md_' to avoid conflict with other devices. Signed-off-by: NeilBrown --- include/linux/raid/md_k.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux/raid/md_k.h') diff --git a/include/linux/raid/md_k.h b/include/linux/raid/md_k.h index e3d17c7f954e..dac4217194b8 100644 --- a/include/linux/raid/md_k.h +++ b/include/linux/raid/md_k.h @@ -139,6 +139,7 @@ struct mddev_s struct kobject kobj; int hold_active; #define UNTIL_IOCTL 1 +#define UNTIL_STOP 2 /* Superblock information */ int major_version, -- cgit v1.2.3 From 4044ba58dd15cb01797c4fd034f39ef4a75f7cc3 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Fri, 9 Jan 2009 08:31:11 +1100 Subject: md: don't retry recovery of raid1 that fails due to error on source drive. If a raid1 has only one working drive and it has a sector which gives an error on read, then an attempt to recover onto a spare will fail, but as the single remaining drive is not removed from the array, the recovery will be immediately re-attempted, resulting in an infinite recovery loop. So detect this situation and don't retry recovery once an error on the lone remaining drive is detected. Allow recovery to be retried once every time a spare is added in case the problem wasn't actually a media error. Signed-off-by: NeilBrown --- include/linux/raid/md_k.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux/raid/md_k.h') diff --git a/include/linux/raid/md_k.h b/include/linux/raid/md_k.h index dac4217194b8..9743e4dbc918 100644 --- a/include/linux/raid/md_k.h +++ b/include/linux/raid/md_k.h @@ -218,6 +218,9 @@ struct mddev_s #define MD_RECOVERY_FROZEN 9 unsigned long recovery; + int recovery_disabled; /* if we detect that recovery + * will always fail, set this + * so we don't loop trying */ int in_sync; /* know to not need resync */ struct mutex reconfig_mutex; -- cgit v1.2.3