md: fix 'degraded' calculation when starting a reshape.

[safe/jmp/linux-2.6] / drivers / md / raid5.c

diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 8c9395f..b5629c3 100644 (file)
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -2947,6 +2947,7 @@ static void handle_stripe5(struct stripe_head *sh)
        struct r5dev *dev;
        mdk_rdev_t *blocked_rdev = NULL;
        int prexor;
+       int dec_preread_active = 0;
 
        memset(&s, 0, sizeof(s));
        pr_debug("handling stripe %llu, state=%#lx cnt=%d, pd_idx=%d check:%d "
@@ -3096,12 +3097,8 @@ static void handle_stripe5(struct stripe_head *sh)
                                        set_bit(STRIPE_INSYNC, &sh->state);
                        }
                }
-               if (test_and_clear_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) {
-                       atomic_dec(&conf->preread_active_stripes);
-                       if (atomic_read(&conf->preread_active_stripes) <
-                               IO_THRESHOLD)
-                               md_wakeup_thread(conf->mddev->thread);
-               }
+               if (test_and_clear_bit(STRIPE_PREREAD_ACTIVE, &sh->state))
+                       dec_preread_active = 1;
        }
 
        /* Now to consider new write requests and what else, if anything
@@ -3208,6 +3205,16 @@ static void handle_stripe5(struct stripe_head *sh)
 
        ops_run_io(sh, &s);
 
+       if (dec_preread_active) {
+               /* We delay this until after ops_run_io so that if make_request
+                * is waiting on a barrier, it won't continue until the writes
+                * have actually been submitted.
+                */
+               atomic_dec(&conf->preread_active_stripes);
+               if (atomic_read(&conf->preread_active_stripes) <
+                   IO_THRESHOLD)
+                       md_wakeup_thread(conf->mddev->thread);
+       }
        return_io(return_bi);
 }
 
@@ -3221,6 +3228,7 @@ static void handle_stripe6(struct stripe_head *sh)
        struct r6_state r6s;
        struct r5dev *dev, *pdev, *qdev;
        mdk_rdev_t *blocked_rdev = NULL;
+       int dec_preread_active = 0;
 
        pr_debug("handling stripe %llu, state=%#lx cnt=%d, "
                "pd_idx=%d, qd_idx=%d\n, check:%d, reconstruct:%d\n",
@@ -3379,12 +3387,8 @@ static void handle_stripe6(struct stripe_head *sh)
                                        set_bit(STRIPE_INSYNC, &sh->state);
                        }
                }
-               if (test_and_clear_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) {
-                       atomic_dec(&conf->preread_active_stripes);
-                       if (atomic_read(&conf->preread_active_stripes) <
-                               IO_THRESHOLD)
-                               md_wakeup_thread(conf->mddev->thread);
-               }
+               if (test_and_clear_bit(STRIPE_PREREAD_ACTIVE, &sh->state))
+                       dec_preread_active = 1;
        }
 
        /* Now to consider new write requests and what else, if anything
@@ -3493,6 +3497,18 @@ static void handle_stripe6(struct stripe_head *sh)
 
        ops_run_io(sh, &s);
 
+
+       if (dec_preread_active) {
+               /* We delay this until after ops_run_io so that if make_request
+                * is waiting on a barrier, it won't continue until the writes
+                * have actually been submitted.
+                */
+               atomic_dec(&conf->preread_active_stripes);
+               if (atomic_read(&conf->preread_active_stripes) <
+                   IO_THRESHOLD)
+                       md_wakeup_thread(conf->mddev->thread);
+       }
+
        return_io(return_bi);
 }
 
@@ -3995,6 +4011,9 @@ static int make_request(struct request_queue *q, struct bio * bi)
                        finish_wait(&conf->wait_for_overlap, &w);
                        set_bit(STRIPE_HANDLE, &sh->state);
                        clear_bit(STRIPE_DELAYED, &sh->state);
+                       if (mddev->barrier && 
+                           !test_and_set_bit(STRIPE_PREREAD_ACTIVE, &sh->state))
+                               atomic_inc(&conf->preread_active_stripes);
                        release_stripe(sh);
                } else {
                        /* cannot get stripe for read-ahead, just give-up */
@@ -4014,6 +4033,14 @@ static int make_request(struct request_queue *q, struct bio * bi)
 
                bio_endio(bi, 0);
        }
+
+       if (mddev->barrier) {
+               /* We need to wait for the stripes to all be handled.
+                * So: wait for preread_active_stripes to drop to 0.
+                */
+               wait_event(mddev->thread->wqueue,
+                          atomic_read(&conf->preread_active_stripes) == 0);
+       }
        return 0;
 }
 
@@ -5437,11 +5464,11 @@ static int raid5_start_reshape(mddev_t *mddev)
                    !test_bit(Faulty, &rdev->flags)) {
                        if (raid5_add_disk(mddev, rdev) == 0) {
                                char nm[20];
-                               if (rdev->raid_disk >= conf->previous_raid_disks)
+                               if (rdev->raid_disk >= conf->previous_raid_disks) {
                                        set_bit(In_sync, &rdev->flags);
-                               else
+                                       added_devices++;
+                               } else
                                        rdev->recovery_offset = 0;
-                               added_devices++;
                                sprintf(nm, "rd%d", rdev->raid_disk);
                                if (sysfs_create_link(&mddev->kobj,
                                                      &rdev->kobj, nm))
@@ -5453,9 +5480,12 @@ static int raid5_start_reshape(mddev_t *mddev)
                                break;
                }
 
+       /* When a reshape changes the number of devices, ->degraded
+        * is measured against the large of the pre and post number of
+        * devices.*/
        if (mddev->delta_disks > 0) {
                spin_lock_irqsave(&conf->device_lock, flags);
-               mddev->degraded = (conf->raid_disks - conf->previous_raid_disks)
+               mddev->degraded += (conf->raid_disks - conf->previous_raid_disks)
                        - added_devices;
                spin_unlock_irqrestore(&conf->device_lock, flags);
        }
@@ -5865,6 +5895,7 @@ static void raid5_exit(void)
 module_init(raid5_init);
 module_exit(raid5_exit);
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("RAID4/5/6 (striping with parity) personality for MD");
 MODULE_ALIAS("md-personality-4"); /* RAID5 */
 MODULE_ALIAS("md-raid5");
 MODULE_ALIAS("md-raid4");