Merge tag 'jg-20061012-00' of git://electric-eye.fr.zoreil.com/home/romieu/linux...

[~andy/linux] / drivers / md / raid5.c

diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 1c8ab340a11dc15799a460c13061e7f33562eda8..e14f4578072006e3b464668d3c8500187df76453 100644 (file)
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -636,7 +636,6 @@ static int raid5_end_write_request (struct bio *bi, unsigned int bytes_done,
        struct stripe_head *sh = bi->bi_private;
        raid5_conf_t *conf = sh->raid_conf;
        int disks = sh->disks, i;
-       unsigned long flags;
        int uptodate = test_bit(BIO_UPTODATE, &bi->bi_flags);
 
        if (bi->bi_size)
@@ -654,7 +653,6 @@ static int raid5_end_write_request (struct bio *bi, unsigned int bytes_done,
                return 0;
        }
 
-       spin_lock_irqsave(&conf->device_lock, flags);
        if (!uptodate)
                md_error(conf->mddev, conf->disks[i].rdev);
 
@@ -662,8 +660,7 @@ static int raid5_end_write_request (struct bio *bi, unsigned int bytes_done,
        
        clear_bit(R5_LOCKED, &sh->dev[i].flags);
        set_bit(STRIPE_HANDLE, &sh->state);
-       __release_stripe(conf, sh);
-       spin_unlock_irqrestore(&conf->device_lock, flags);
+       release_stripe(sh);
        return 0;
 }
 
@@ -697,9 +694,11 @@ static void error(mddev_t *mddev, mdk_rdev_t *rdev)
 
        if (!test_bit(Faulty, &rdev->flags)) {
                set_bit(MD_CHANGE_DEVS, &mddev->flags);
-               if (test_bit(In_sync, &rdev->flags)) {
+               if (test_and_clear_bit(In_sync, &rdev->flags)) {
+                       unsigned long flags;
+                       spin_lock_irqsave(&conf->device_lock, flags);
                        mddev->degraded++;
-                       clear_bit(In_sync, &rdev->flags);
+                       spin_unlock_irqrestore(&conf->device_lock, flags);
                        /*
                         * if recovery was running, make sure it aborts.
                         */
@@ -1106,7 +1105,7 @@ static void compute_parity6(struct stripe_head *sh, int method)
                                if (test_and_clear_bit(R5_Overlap, &sh->dev[i].flags))
                                        wake_up(&conf->wait_for_overlap);
 
-                               if (sh->dev[i].written) BUG();
+                               BUG_ON(sh->dev[i].written);
                                sh->dev[i].written = chosen;
                        }
                break;
@@ -1351,10 +1350,9 @@ static int page_is_zero(struct page *p)
 static int stripe_to_pdidx(sector_t stripe, raid5_conf_t *conf, int disks)
 {
        int sectors_per_chunk = conf->chunk_size >> 9;
-       sector_t x = stripe;
        int pd_idx, dd_idx;
-       int chunk_offset = sector_div(x, sectors_per_chunk);
-       stripe = x;
+       int chunk_offset = sector_div(stripe, sectors_per_chunk);
+
        raid5_compute_sector(stripe*(disks-1)*sectors_per_chunk
                             + chunk_offset, disks, disks-1, &dd_idx, &pd_idx, conf);
        return pd_idx;
@@ -2595,6 +2593,24 @@ static int raid5_issue_flush(request_queue_t *q, struct gendisk *disk,
        return ret;
 }
 
+static int raid5_congested(void *data, int bits)
+{
+       mddev_t *mddev = data;
+       raid5_conf_t *conf = mddev_to_conf(mddev);
+
+       /* No difference between reads and writes.  Just check
+        * how busy the stripe_cache is
+        */
+       if (conf->inactive_blocked)
+               return 1;
+       if (conf->quiesce)
+               return 1;
+       if (list_empty_careful(&conf->inactive_list))
+               return 1;
+
+       return 0;
+}
+
 static int make_request(request_queue_t *q, struct bio * bi)
 {
        mddev_t *mddev = q->queuedata;
@@ -3298,6 +3314,9 @@ static int run(mddev_t *mddev)
 
        mddev->queue->unplug_fn = raid5_unplug_device;
        mddev->queue->issue_flush_fn = raid5_issue_flush;
+       mddev->queue->backing_dev_info.congested_fn = raid5_congested;
+       mddev->queue->backing_dev_info.congested_data = mddev;
+
        mddev->array_size =  mddev->size * (conf->previous_raid_disks -
                                            conf->max_degraded);
 
@@ -3419,9 +3438,11 @@ static int raid5_spare_active(mddev_t *mddev)
                tmp = conf->disks + i;
                if (tmp->rdev
                    && !test_bit(Faulty, &tmp->rdev->flags)
-                   && !test_bit(In_sync, &tmp->rdev->flags)) {
+                   && !test_and_set_bit(In_sync, &tmp->rdev->flags)) {
+                       unsigned long flags;
+                       spin_lock_irqsave(&conf->device_lock, flags);
                        mddev->degraded--;
-                       set_bit(In_sync, &tmp->rdev->flags);
+                       spin_unlock_irqrestore(&conf->device_lock, flags);
                }
        }
        print_raid5_conf(conf);
@@ -3557,6 +3578,7 @@ static int raid5_start_reshape(mddev_t *mddev)
        struct list_head *rtmp;
        int spares = 0;
        int added_devices = 0;
+       unsigned long flags;
 
        if (mddev->degraded ||
            test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
@@ -3598,7 +3620,9 @@ static int raid5_start_reshape(mddev_t *mddev)
                                break;
                }
 
+       spin_lock_irqsave(&conf->device_lock, flags);
        mddev->degraded = (conf->raid_disks - conf->previous_raid_disks) - added_devices;
+       spin_unlock_irqrestore(&conf->device_lock, flags);
        mddev->raid_disks = conf->raid_disks;
        mddev->reshape_position = 0;
        set_bit(MD_CHANGE_DEVS, &mddev->flags);