md: use separate bio pool for each md device.

[pandora-kernel.git] / drivers / md / raid5.c

diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 69b0a16..dc574f3 100644 (file)
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -506,9 +506,12 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
                int rw;
                struct bio *bi;
                mdk_rdev_t *rdev;
-               if (test_and_clear_bit(R5_Wantwrite, &sh->dev[i].flags))
-                       rw = WRITE;
-               else if (test_and_clear_bit(R5_Wantread, &sh->dev[i].flags))
+               if (test_and_clear_bit(R5_Wantwrite, &sh->dev[i].flags)) {
+                       if (test_and_clear_bit(R5_WantFUA, &sh->dev[i].flags))
+                               rw = WRITE_FUA;
+                       else
+                               rw = WRITE;
+               } else if (test_and_clear_bit(R5_Wantread, &sh->dev[i].flags))
                        rw = READ;
                else
                        continue;
@@ -1031,6 +1034,8 @@ ops_run_biodrain(struct stripe_head *sh, struct dma_async_tx_descriptor *tx)
 
                        while (wbi && wbi->bi_sector <
                                dev->sector + STRIPE_SECTORS) {
+                               if (wbi->bi_rw & REQ_FUA)
+                                       set_bit(R5_WantFUA, &dev->flags);
                                tx = async_copy_data(1, wbi, dev->page,
                                        dev->sector, tx);
                                wbi = r5_next_bio(wbi, dev->sector);
@@ -1048,15 +1053,22 @@ static void ops_complete_reconstruct(void *stripe_head_ref)
        int pd_idx = sh->pd_idx;
        int qd_idx = sh->qd_idx;
        int i;
+       bool fua = false;
 
        pr_debug("%s: stripe %llu\n", __func__,
                (unsigned long long)sh->sector);
 
+       for (i = disks; i--; )
+               fua |= test_bit(R5_WantFUA, &sh->dev[i].flags);
+
        for (i = disks; i--; ) {
                struct r5dev *dev = &sh->dev[i];
 
-               if (dev->written || i == pd_idx || i == qd_idx)
+               if (dev->written || i == pd_idx || i == qd_idx) {
                        set_bit(R5_UPTODATE, &dev->flags);
+                       if (fua)
+                               set_bit(R5_WantFUA, &dev->flags);
+               }
        }
 
        if (sh->reconstruct_state == reconstruct_state_drain_run)
@@ -3281,7 +3293,7 @@ static void handle_stripe5(struct stripe_head *sh)
 
        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
+                * is waiting on a flush, it won't continue until the writes
                 * have actually been submitted.
                 */
                atomic_dec(&conf->preread_active_stripes);
@@ -3583,7 +3595,7 @@ static void handle_stripe6(struct stripe_head *sh)
 
        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
+                * is waiting on a flush, it won't continue until the writes
                 * have actually been submitted.
                 */
                atomic_dec(&conf->preread_active_stripes);
@@ -3864,9 +3876,9 @@ static int chunk_aligned_read(mddev_t *mddev, struct bio * raid_bio)
                return 0;
        }
        /*
-        * use bio_clone to make a copy of the bio
+        * use bio_clone_mddev to make a copy of the bio
         */
-       align_bi = bio_clone(raid_bio, GFP_NOIO);
+       align_bi = bio_clone_mddev(raid_bio, GFP_NOIO, mddev);
        if (!align_bi)
                return 0;
        /*
@@ -3978,14 +3990,8 @@ static int make_request(mddev_t *mddev, struct bio * bi)
        const int rw = bio_data_dir(bi);
        int remaining;
 
-       if (unlikely(bi->bi_rw & REQ_HARDBARRIER)) {
-               /* Drain all pending writes.  We only really need
-                * to ensure they have been submitted, but this is
-                * easier.
-                */
-               mddev->pers->quiesce(mddev, 1);
-               mddev->pers->quiesce(mddev, 0);
-               md_barrier_request(mddev, bi);
+       if (unlikely(bi->bi_rw & REQ_FLUSH)) {
+               md_flush_request(mddev, bi);
                return 0;
        }
 
@@ -4103,7 +4109,7 @@ static int make_request(mddev_t *mddev, 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 && 
+                       if ((bi->bi_rw & REQ_SYNC) &&
                            !test_and_set_bit(STRIPE_PREREAD_ACTIVE, &sh->state))
                                atomic_inc(&conf->preread_active_stripes);
                        release_stripe(sh);
@@ -4126,13 +4132,6 @@ static int make_request(mddev_t *mddev, 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;
 }
 
@@ -4361,7 +4360,7 @@ static inline sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *ski
        raid5_conf_t *conf = mddev->private;
        struct stripe_head *sh;
        sector_t max_sector = mddev->dev_sectors;
-       int sync_blocks;
+       sector_t sync_blocks;
        int still_degraded = 0;
        int i;