1 files changed, 48 insertions, 15 deletions

diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index d29215d966da..e84204eb12df 100644
--- 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",
@@ -3358,7 +3366,6 @@ static void handle_stripe6(struct stripe_head *sh)
          * completed
          */
         if (sh->reconstruct_state == reconstruct_state_drain_result) {
-                int qd_idx = sh->qd_idx;
 
                 sh->reconstruct_state = reconstruct_state_idle;
                 /* All the 'written' buffers and the parity blocks are ready to
@@ -3380,12 +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
@@ -3494,6 +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);
 }
 
@@ -3741,7 +3756,7 @@ static int chunk_aligned_read(struct request_queue *q, struct bio * raid_bio)
 {
         mddev_t *mddev = q->queuedata;
         raid5_conf_t *conf = mddev->private;
-        unsigned int dd_idx;
+        int dd_idx;
         struct bio* align_bi;
         mdk_rdev_t *rdev;
 
@@ -3866,7 +3881,13 @@ static int make_request(struct request_queue *q, struct bio * bi)
         int cpu, remaining;
 
         if (unlikely(bio_rw_flagged(bi, BIO_RW_BARRIER))) {
-                bio_endio(bi, -EOPNOTSUPP);
+                /* 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);
                 return 0;
         }
 
@@ -3990,6 +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 */
@@ -4009,6 +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;
 }
 
@@ -5860,6 +5892,7 @@ 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");