Merge branch 'i2c-for-linus' of git://jdelvare.pck.nerim.net/jdelvare-2.6

[firefly-linux-kernel-4.4.55.git] / drivers / md / raid10.c

diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 5de42d87bf4ed23d17a8762609140f01c536779b..32389d2f18fcdfcadc87137936441e6d51560c05 100644 (file)
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -537,7 +537,8 @@ static int read_balance(conf_t *conf, r10bio_t *r10_bio)
        current_distance = abs(r10_bio->devs[slot].addr -
                               conf->mirrors[disk].head_position);
 
-       /* Find the disk whose head is closest */
+       /* Find the disk whose head is closest,
+        * or - for far > 1 - find the closest to partition beginning */
 
        for (nslot = slot; nslot < conf->copies; nslot++) {
                int ndisk = r10_bio->devs[nslot].devnum;
@@ -557,8 +558,13 @@ static int read_balance(conf_t *conf, r10bio_t *r10_bio)
                        slot = nslot;
                        break;
                }
-               new_distance = abs(r10_bio->devs[nslot].addr -
-                                  conf->mirrors[ndisk].head_position);
+
+               /* for far > 1 always use the lowest address */
+               if (conf->far_copies > 1)
+                       new_distance = r10_bio->devs[nslot].addr;
+               else
+                       new_distance = abs(r10_bio->devs[nslot].addr -
+                                          conf->mirrors[ndisk].head_position);
                if (new_distance < current_distance) {
                        current_distance = new_distance;
                        disk = ndisk;
@@ -741,13 +747,20 @@ static void freeze_array(conf_t *conf)
        /* stop syncio and normal IO and wait for everything to
         * go quiet.
         * We increment barrier and nr_waiting, and then
-        * wait until barrier+nr_pending match nr_queued+2
+        * wait until nr_pending match nr_queued+1
+        * This is called in the context of one normal IO request
+        * that has failed. Thus any sync request that might be pending
+        * will be blocked by nr_pending, and we need to wait for
+        * pending IO requests to complete or be queued for re-try.
+        * Thus the number queued (nr_queued) plus this request (1)
+        * must match the number of pending IOs (nr_pending) before
+        * we continue.
         */
        spin_lock_irq(&conf->resync_lock);
        conf->barrier++;
        conf->nr_waiting++;
        wait_event_lock_irq(conf->wait_barrier,
-                           conf->barrier+conf->nr_pending == conf->nr_queued+2,
+                           conf->nr_pending == conf->nr_queued+1,
                            conf->resync_lock,
                            ({ flush_pending_writes(conf);
                               raid10_unplug(conf->mddev->queue); }));
@@ -1805,6 +1818,8 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, i
                                if (j == conf->copies) {
                                        /* Cannot recover, so abort the recovery */
                                        put_buf(r10_bio);
+                                       if (rb2)
+                                               atomic_dec(&rb2->remaining);
                                        r10_bio = rb2;
                                        if (!test_and_set_bit(MD_RECOVERY_ERR, &mddev->recovery))
                                                printk(KERN_INFO "raid10: %s: insufficient working devices for recovery.\n",