md: handle_stripe5 - add request/completion logic for async read ops

When a read bio is attached to the stripe and the corresponding block is
marked R5_UPTODATE, then a read (biofill) operation is scheduled to copy
the data from the stripe cache to the bio buffer.  handle_stripe flags the
blocks to be operated on with the R5_Wantfill flag.  If new read requests
arrive while raid5_run_ops is running they will not be handled until
handle_stripe is scheduled to run again.

Changelog:
* cleanup to_read and to_fill accounting
* do not fail reads that have reached the cache

Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Acked-By: NeilBrown <neilb@suse.de>

diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 810cf831edda3bc8bdfd703f3b134b5009f37d84..a33dac7c2e2fb143d674a48b8ab19280cdd36dd8 100644 (file)
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -2049,9 +2049,12 @@ handle_requests_to_failed_array(raid5_conf_t *conf, struct stripe_head *sh,
                        bi = bi2;
                }
 
-               /* fail any reads if this device is non-operational */
-               if (!test_bit(R5_Insync, &sh->dev[i].flags) ||
-                   test_bit(R5_ReadError, &sh->dev[i].flags)) {
+               /* fail any reads if this device is non-operational and
+                * the data has not reached the cache yet.
+                */
+               if (!test_bit(R5_Wantfill, &sh->dev[i].flags) &&
+                   (!test_bit(R5_Insync, &sh->dev[i].flags) ||
+                     test_bit(R5_ReadError, &sh->dev[i].flags))) {
                        bi = sh->dev[i].toread;
                        sh->dev[i].toread = NULL;
                        if (test_and_clear_bit(R5_Overlap, &sh->dev[i].flags))
@@ -2740,37 +2743,27 @@ static void handle_stripe5(struct stripe_head *sh)
                struct r5dev *dev = &sh->dev[i];
                clear_bit(R5_Insync, &dev->flags);
 
-               pr_debug("check %d: state 0x%lx read %p write %p written %p\n",
-                       i, dev->flags, dev->toread, dev->towrite, dev->written);
-               /* maybe we can reply to a read */
-               if (test_bit(R5_UPTODATE, &dev->flags) && dev->toread) {
-                       struct bio *rbi, *rbi2;
-                       pr_debug("Return read for disc %d\n", i);
-                       spin_lock_irq(&conf->device_lock);
-                       rbi = dev->toread;
-                       dev->toread = NULL;
-                       if (test_and_clear_bit(R5_Overlap, &dev->flags))
-                               wake_up(&conf->wait_for_overlap);
-                       spin_unlock_irq(&conf->device_lock);
-                       while (rbi && rbi->bi_sector < dev->sector + STRIPE_SECTORS) {
-                               copy_data(0, rbi, dev->page, dev->sector);
-                               rbi2 = r5_next_bio(rbi, dev->sector);
-                               spin_lock_irq(&conf->device_lock);
-                               if (--rbi->bi_phys_segments == 0) {
-                                       rbi->bi_next = return_bi;
-                                       return_bi = rbi;
-                               }
-                               spin_unlock_irq(&conf->device_lock);
-                               rbi = rbi2;
-                       }
-               }
+               pr_debug("check %d: state 0x%lx toread %p read %p write %p "
+                       "written %p\n", i, dev->flags, dev->toread, dev->read,
+                       dev->towrite, dev->written);
+
+               /* maybe we can request a biofill operation
+                *
+                * new wantfill requests are only permitted while
+                * STRIPE_OP_BIOFILL is clear
+                */
+               if (test_bit(R5_UPTODATE, &dev->flags) && dev->toread &&
+                       !test_bit(STRIPE_OP_BIOFILL, &sh->ops.pending))
+                       set_bit(R5_Wantfill, &dev->flags);
 
                /* now count some things */
                if (test_bit(R5_LOCKED, &dev->flags)) s.locked++;
                if (test_bit(R5_UPTODATE, &dev->flags)) s.uptodate++;
                if (test_bit(R5_Wantcompute, &dev->flags)) s.compute++;
 
-               if (dev->toread)
+               if (test_bit(R5_Wantfill, &dev->flags))
+                       s.to_fill++;
+               else if (dev->toread)
                        s.to_read++;
                if (dev->towrite) {
                        s.to_write++;
@@ -2793,6 +2786,10 @@ static void handle_stripe5(struct stripe_head *sh)
                        set_bit(R5_Insync, &dev->flags);
        }
        rcu_read_unlock();
+
+       if (s.to_fill && !test_and_set_bit(STRIPE_OP_BIOFILL, &sh->ops.pending))
+               sh->ops.count++;
+
        pr_debug("locked=%d uptodate=%d to_read=%d"
                " to_write=%d failed=%d failed_num=%d\n",
                s.locked, s.uptodate, s.to_read, s.to_write,

diff --git a/include/linux/raid/raid5.h b/include/linux/raid/raid5.h
index 2293015de1d54747f7d2b4fc09a46071c87f6a46..93678f57ccbe280d3b681aa5c31a2c5049c32a6a 100644 (file)
--- a/include/linux/raid/raid5.h
+++ b/include/linux/raid/raid5.h
@@ -200,7 +200,7 @@ struct stripe_head {
 struct stripe_head_state {
        int syncing, expanding, expanded;
        int locked, uptodate, to_read, to_write, failed, written;
-       int compute, req_compute, non_overwrite;
+       int to_fill, compute, req_compute, non_overwrite;
        int failed_num;
 };