[PATCH] md: improve locking on 'safemode' and move superblock writes

When md marks the superblock dirty before a write, it calls
generic_make_request (to write the superblock) from within
generic_make_request (to write the first dirty block), which could cause
problems later.

With this patch, the superblock write is always done by the helper thread, and
write request are delayed until that write completes.

Also, the locking around marking the array dirty and writing the superblock is
improved to avoid possible races.

Signed-off-by: Neil Brown <neilb@cse.unsw.edu.au>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

2 files changed, 8 insertions, 1 deletions

diff --git a/include/linux/raid/md.h b/include/linux/raid/md.h
index a6a67d102bfa..cfde8f497d6d 100644
--- a/include/linux/raid/md.h
+++ b/include/linux/raid/md.h
@@ -69,7 +69,7 @@ extern mdk_thread_t * md_register_thread (void (*run) (mddev_t *mddev),
 extern void md_unregister_thread (mdk_thread_t *thread);
 extern void md_wakeup_thread(mdk_thread_t *thread);
 extern void md_check_recovery(mddev_t *mddev);
-extern void md_write_start(mddev_t *mddev);
+extern int md_write_start(mddev_t *mddev, struct bio *bi);
 extern void md_write_end(mddev_t *mddev);
 extern void md_handle_safemode(mddev_t *mddev);
 extern void md_done_sync(mddev_t *mddev, int blocks, int ok);
diff --git a/include/linux/raid/md_k.h b/include/linux/raid/md_k.h
index c9a0d4013be7..d92db54255a3 100644
--- a/include/linux/raid/md_k.h
+++ b/include/linux/raid/md_k.h
@@ -15,6 +15,9 @@
 #ifndef _MD_K_H
 #define _MD_K_H
 
+/* and dm-bio-list.h is not under include/linux because.... ??? */
+#include "../../../drivers/md/dm-bio-list.h"
+
 #define MD_RESERVED       0UL
 #define LINEAR            1UL
 #define RAID0             2UL
@@ -252,6 +255,10 @@ struct mddev_s
         atomic_t                        recovery_active; /* blocks scheduled, but not written */
         wait_queue_head_t               recovery_wait;
         sector_t                        recovery_cp;
+
+        spinlock_t                      write_lock;
+        struct bio_list                 write_list;
+
         unsigned int                    safemode;       /* if set, update "clean" superblock
                                                          * when no writes pending.
                                                          */