Fix problem with waiting while holding rcu read lock in md/bitmap.c

A recent patch to protect the rdev list with rcu locking leaves us
with a problem because we can sleep on memalloc while holding the
rcu lock.

The rcu lock is only needed while walking the linked list as
uninteresting devices (failed or spares) can be removed at any time.

So only take the rcu lock while actually walking the linked list.
Take a refcount on the rdev during the time when we drop the lock
and do the memalloc to start IO.
When we return to the locked code, all the interesting devices
on the list will not have moved, so we can simply use
list_for_each_continue_rcu to pick up where we left off.

Signed-off-by: NeilBrown <neilb@suse.de>

1 files changed, 38 insertions, 7 deletions

diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c
index 7e65bad522cb..ac89a5deaca2 100644
--- a/drivers/md/bitmap.c
+++ b/drivers/md/bitmap.c
@@ -238,15 +238,47 @@ static struct page *read_sb_page(mddev_t *mddev, long offset, unsigned long inde
 
 }
 
+static mdk_rdev_t *next_active_rdev(mdk_rdev_t *rdev, mddev_t *mddev)
+{
+        /* Iterate the disks of an mddev, using rcu to protect access to the
+         * linked list, and raising the refcount of devices we return to ensure
+         * they don't disappear while in use.
+         * As devices are only added or removed when raid_disk is < 0 and
+         * nr_pending is 0 and In_sync is clear, the entries we return will
+         * still be in the same position on the list when we re-enter
+         * list_for_each_continue_rcu.
+         */
+        struct list_head *pos;
+        rcu_read_lock();
+        if (rdev == NULL)
+                /* start at the beginning */
+                pos = &mddev->disks;
+        else {
+                /* release the previous rdev and start from there. */
+                rdev_dec_pending(rdev, mddev);
+                pos = &rdev->same_set;
+        }
+        list_for_each_continue_rcu(pos, &mddev->disks) {
+                rdev = list_entry(pos, mdk_rdev_t, same_set);
+                if (rdev->raid_disk >= 0 &&
+                    test_bit(In_sync, &rdev->flags) &&
+                    !test_bit(Faulty, &rdev->flags)) {
+                        /* this is a usable devices */
+                        atomic_inc(&rdev->nr_pending);
+                        rcu_read_unlock();
+                        return rdev;
+                }
+        }
+        rcu_read_unlock();
+        return NULL;
+}
+
 static int write_sb_page(struct bitmap *bitmap, struct page *page, int wait)
 {
-        mdk_rdev_t *rdev;
+        mdk_rdev_t *rdev = NULL;
         mddev_t *mddev = bitmap->mddev;
 
-        rcu_read_lock();
-        rdev_for_each_rcu(rdev, mddev)
-                if (test_bit(In_sync, &rdev->flags)
-                    && !test_bit(Faulty, &rdev->flags)) {
+        while ((rdev = next_active_rdev(rdev, mddev)) != NULL) {
                         int size = PAGE_SIZE;
                         if (page->index == bitmap->file_pages-1)
                                 size = roundup(bitmap->last_page_size,
@@ -281,8 +313,7 @@ static int write_sb_page(struct bitmap *bitmap, struct page *page, int wait)
                                        + page->index * (PAGE_SIZE/512),
                                        size,
                                        page);
-                }
-        rcu_read_unlock();
+        }
 
         if (wait)
                 md_super_wait(mddev);