Merge tag 'md-3.9-fixes' of git://neil.brown.name/md

Pull md fixes from NeilBrown:
 "A few bugfixes for md

   - recent regressions in raid5
   - recent regressions in dmraid
   - a few instances of CONFIG_MULTICORE_RAID456 linger

  Several tagged for -stable"

* tag 'md-3.9-fixes' of git://neil.brown.name/md:
  md: remove CONFIG_MULTICORE_RAID456 entirely
  md/raid5: ensure sync and DISCARD don't happen at the same time.
  MD: Prevent sysfs operations on uninitialized kobjects
  MD RAID5: Avoid accessing gendisk or queue structs when not available
  md/raid5: schedule_construction should abort if nothing to do.

6 files changed, 86 insertions, 47 deletions

diff --git a/arch/tile/configs/tilegx_defconfig b/arch/tile/configs/tilegx_defconfig
index 8c5eff6d6df5..47684815e5c8 100644
--- a/arch/tile/configs/tilegx_defconfig
+++ b/arch/tile/configs/tilegx_defconfig
@@ -330,7 +330,6 @@ CONFIG_MD_RAID0=m
 CONFIG_MD_RAID1=m
 CONFIG_MD_RAID10=m
 CONFIG_MD_RAID456=m
-CONFIG_MULTICORE_RAID456=y
 CONFIG_MD_FAULTY=m
 CONFIG_BLK_DEV_DM=m
 CONFIG_DM_DEBUG=y
diff --git a/arch/tile/configs/tilepro_defconfig b/arch/tile/configs/tilepro_defconfig
index e7a3dfcbcda7..dd2b8f0c631f 100644
--- a/arch/tile/configs/tilepro_defconfig
+++ b/arch/tile/configs/tilepro_defconfig
@@ -324,7 +324,6 @@ CONFIG_MD_RAID0=m
 CONFIG_MD_RAID1=m
 CONFIG_MD_RAID10=m
 CONFIG_MD_RAID456=m
-CONFIG_MULTICORE_RAID456=y
 CONFIG_MD_FAULTY=m
 CONFIG_BLK_DEV_DM=m
 CONFIG_DM_DEBUG=y
diff --git a/drivers/md/md.c b/drivers/md/md.c
index fcb878f88796..aeceedfc530b 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -7663,10 +7663,8 @@ static int remove_and_add_spares(struct mddev *mddev)
                                 removed++;
                         }
                 }
-        if (removed)
-                sysfs_notify(&mddev->kobj, NULL,
-                             "degraded");
-
+        if (removed && mddev->kobj.sd)
+                sysfs_notify(&mddev->kobj, NULL, "degraded");
 
         rdev_for_each(rdev, mddev) {
                 if (rdev->raid_disk >= 0 &&
diff --git a/drivers/md/md.h b/drivers/md/md.h
index eca59c3074ef..d90fb1a879e1 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -506,7 +506,7 @@ static inline char * mdname (struct mddev * mddev)
 static inline int sysfs_link_rdev(struct mddev *mddev, struct md_rdev *rdev)
 {
         char nm[20];
-        if (!test_bit(Replacement, &rdev->flags)) {
+        if (!test_bit(Replacement, &rdev->flags) && mddev->kobj.sd) {
                 sprintf(nm, "rd%d", rdev->raid_disk);
                 return sysfs_create_link(&mddev->kobj, &rdev->kobj, nm);
         } else
@@ -516,7 +516,7 @@ static inline int sysfs_link_rdev(struct mddev *mddev, struct md_rdev *rdev)
 static inline void sysfs_unlink_rdev(struct mddev *mddev, struct md_rdev *rdev)
 {
         char nm[20];
-        if (!test_bit(Replacement, &rdev->flags)) {
+        if (!test_bit(Replacement, &rdev->flags) && mddev->kobj.sd) {
                 sprintf(nm, "rd%d", rdev->raid_disk);
                 sysfs_remove_link(&mddev->kobj, nm);
         }
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 3ee2912889e7..24909eb13fec 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -671,9 +671,11 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
                         bi->bi_next = NULL;
                         if (rrdev)
                                 set_bit(R5_DOUBLE_LOCKED, &sh->dev[i].flags);
-                        trace_block_bio_remap(bdev_get_queue(bi->bi_bdev),
-                                              bi, disk_devt(conf->mddev->gendisk),
-                                              sh->dev[i].sector);
+
+                        if (conf->mddev->gendisk)
+                                trace_block_bio_remap(bdev_get_queue(bi->bi_bdev),
+                                                      bi, disk_devt(conf->mddev->gendisk),
+                                                      sh->dev[i].sector);
                         generic_make_request(bi);
                 }
                 if (rrdev) {
@@ -701,9 +703,10 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
                         rbi->bi_io_vec[0].bv_offset = 0;
                         rbi->bi_size = STRIPE_SIZE;
                         rbi->bi_next = NULL;
-                        trace_block_bio_remap(bdev_get_queue(rbi->bi_bdev),
-                                              rbi, disk_devt(conf->mddev->gendisk),
-                                              sh->dev[i].sector);
+                        if (conf->mddev->gendisk)
+                                trace_block_bio_remap(bdev_get_queue(rbi->bi_bdev),
+                                                      rbi, disk_devt(conf->mddev->gendisk),
+                                                      sh->dev[i].sector);
                         generic_make_request(rbi);
                 }
                 if (!rdev && !rrdev) {
@@ -2280,17 +2283,6 @@ schedule_reconstruction(struct stripe_head *sh, struct stripe_head_state *s,
         int level = conf->level;
 
         if (rcw) {
-                /* if we are not expanding this is a proper write request, and
-                 * there will be bios with new data to be drained into the
-                 * stripe cache
-                 */
-                if (!expand) {
-                        sh->reconstruct_state = reconstruct_state_drain_run;
-                        set_bit(STRIPE_OP_BIODRAIN, &s->ops_request);
-                } else
-                        sh->reconstruct_state = reconstruct_state_run;
-
-                set_bit(STRIPE_OP_RECONSTRUCT, &s->ops_request);
 
                 for (i = disks; i--; ) {
                         struct r5dev *dev = &sh->dev[i];
@@ -2303,6 +2295,21 @@ schedule_reconstruction(struct stripe_head *sh, struct stripe_head_state *s,
                                 s->locked++;
                         }
                 }
+                /* if we are not expanding this is a proper write request, and
+                 * there will be bios with new data to be drained into the
+                 * stripe cache
+                 */
+                if (!expand) {
+                        if (!s->locked)
+                                /* False alarm, nothing to do */
+                                return;
+                        sh->reconstruct_state = reconstruct_state_drain_run;
+                        set_bit(STRIPE_OP_BIODRAIN, &s->ops_request);
+                } else
+                        sh->reconstruct_state = reconstruct_state_run;
+
+                set_bit(STRIPE_OP_RECONSTRUCT, &s->ops_request);
+
                 if (s->locked + conf->max_degraded == disks)
                         if (!test_and_set_bit(STRIPE_FULL_WRITE, &sh->state))
                                 atomic_inc(&conf->pending_full_writes);
@@ -2311,11 +2318,6 @@ schedule_reconstruction(struct stripe_head *sh, struct stripe_head_state *s,
                 BUG_ON(!(test_bit(R5_UPTODATE, &sh->dev[pd_idx].flags) ||
                         test_bit(R5_Wantcompute, &sh->dev[pd_idx].flags)));
 
-                sh->reconstruct_state = reconstruct_state_prexor_drain_run;
-                set_bit(STRIPE_OP_PREXOR, &s->ops_request);
-                set_bit(STRIPE_OP_BIODRAIN, &s->ops_request);
-                set_bit(STRIPE_OP_RECONSTRUCT, &s->ops_request);
-
                 for (i = disks; i--; ) {
                         struct r5dev *dev = &sh->dev[i];
                         if (i == pd_idx)
@@ -2330,6 +2332,13 @@ schedule_reconstruction(struct stripe_head *sh, struct stripe_head_state *s,
                                 s->locked++;
                         }
                 }
+                if (!s->locked)
+                        /* False alarm - nothing to do */
+                        return;
+                sh->reconstruct_state = reconstruct_state_prexor_drain_run;
+                set_bit(STRIPE_OP_PREXOR, &s->ops_request);
+                set_bit(STRIPE_OP_BIODRAIN, &s->ops_request);
+                set_bit(STRIPE_OP_RECONSTRUCT, &s->ops_request);
         }
 
         /* keep the parity disk(s) locked while asynchronous operations
@@ -2564,6 +2573,8 @@ handle_failed_sync(struct r5conf *conf, struct stripe_head *sh,
         int i;
 
         clear_bit(STRIPE_SYNCING, &sh->state);
+        if (test_and_clear_bit(R5_Overlap, &sh->dev[sh->pd_idx].flags))
+                wake_up(&conf->wait_for_overlap);
         s->syncing = 0;
         s->replacing = 0;
         /* There is nothing more to do for sync/check/repair.
@@ -2737,6 +2748,7 @@ static void handle_stripe_clean_event(struct r5conf *conf,
 {
         int i;
         struct r5dev *dev;
+        int discard_pending = 0;
 
         for (i = disks; i--; )
                 if (sh->dev[i].written) {
@@ -2765,9 +2777,23 @@ static void handle_stripe_clean_event(struct r5conf *conf,
                                                 STRIPE_SECTORS,
                                          !test_bit(STRIPE_DEGRADED, &sh->state),
                                                 0);
-                        }
-                } else if (test_bit(R5_Discard, &sh->dev[i].flags))
-                        clear_bit(R5_Discard, &sh->dev[i].flags);
+                        } else if (test_bit(R5_Discard, &dev->flags))
+                                discard_pending = 1;
+                }
+        if (!discard_pending &&
+            test_bit(R5_Discard, &sh->dev[sh->pd_idx].flags)) {
+                clear_bit(R5_Discard, &sh->dev[sh->pd_idx].flags);
+                clear_bit(R5_UPTODATE, &sh->dev[sh->pd_idx].flags);
+                if (sh->qd_idx >= 0) {
+                        clear_bit(R5_Discard, &sh->dev[sh->qd_idx].flags);
+                        clear_bit(R5_UPTODATE, &sh->dev[sh->qd_idx].flags);
+                }
+                /* now that discard is done we can proceed with any sync */
+                clear_bit(STRIPE_DISCARD, &sh->state);
+                if (test_bit(STRIPE_SYNC_REQUESTED, &sh->state))
+                        set_bit(STRIPE_HANDLE, &sh->state);
+
+        }
 
         if (test_and_clear_bit(STRIPE_FULL_WRITE, &sh->state))
                 if (atomic_dec_and_test(&conf->pending_full_writes))
@@ -2826,8 +2852,10 @@ static void handle_stripe_dirtying(struct r5conf *conf,
         set_bit(STRIPE_HANDLE, &sh->state);
         if (rmw < rcw && rmw > 0) {
                 /* prefer read-modify-write, but need to get some data */
-                blk_add_trace_msg(conf->mddev->queue, "raid5 rmw %llu %d",
-                                  (unsigned long long)sh->sector, rmw);
+                if (conf->mddev->queue)
+                        blk_add_trace_msg(conf->mddev->queue,
+                                          "raid5 rmw %llu %d",
+                                          (unsigned long long)sh->sector, rmw);
                 for (i = disks; i--; ) {
                         struct r5dev *dev = &sh->dev[i];
                         if ((dev->towrite || i == sh->pd_idx) &&
@@ -2877,7 +2905,7 @@ static void handle_stripe_dirtying(struct r5conf *conf,
                                 }
                         }
                 }
-                if (rcw)
+                if (rcw && conf->mddev->queue)
                         blk_add_trace_msg(conf->mddev->queue, "raid5 rcw %llu %d %d %d",
                                           (unsigned long long)sh->sector,
                                           rcw, qread, test_bit(STRIPE_DELAYED, &sh->state));
@@ -3417,9 +3445,15 @@ static void handle_stripe(struct stripe_head *sh)
                 return;
         }
 
-        if (test_and_clear_bit(STRIPE_SYNC_REQUESTED, &sh->state)) {
-                set_bit(STRIPE_SYNCING, &sh->state);
-                clear_bit(STRIPE_INSYNC, &sh->state);
+        if (test_bit(STRIPE_SYNC_REQUESTED, &sh->state)) {
+                spin_lock(&sh->stripe_lock);
+                /* Cannot process 'sync' concurrently with 'discard' */
+                if (!test_bit(STRIPE_DISCARD, &sh->state) &&
+                    test_and_clear_bit(STRIPE_SYNC_REQUESTED, &sh->state)) {
+                        set_bit(STRIPE_SYNCING, &sh->state);
+                        clear_bit(STRIPE_INSYNC, &sh->state);
+                }
+                spin_unlock(&sh->stripe_lock);
         }
         clear_bit(STRIPE_DELAYED, &sh->state);
 
@@ -3579,6 +3613,8 @@ static void handle_stripe(struct stripe_head *sh)
             test_bit(STRIPE_INSYNC, &sh->state)) {
                 md_done_sync(conf->mddev, STRIPE_SECTORS, 1);
                 clear_bit(STRIPE_SYNCING, &sh->state);
+                if (test_and_clear_bit(R5_Overlap, &sh->dev[sh->pd_idx].flags))
+                        wake_up(&conf->wait_for_overlap);
         }
 
         /* If the failed drives are just a ReadError, then we might need
@@ -3982,9 +4018,10 @@ static int chunk_aligned_read(struct mddev *mddev, struct bio * raid_bio)
                 atomic_inc(&conf->active_aligned_reads);
                 spin_unlock_irq(&conf->device_lock);
 
-                trace_block_bio_remap(bdev_get_queue(align_bi->bi_bdev),
-                                      align_bi, disk_devt(mddev->gendisk),
-                                      raid_bio->bi_sector);
+                if (mddev->gendisk)
+                        trace_block_bio_remap(bdev_get_queue(align_bi->bi_bdev),
+                                              align_bi, disk_devt(mddev->gendisk),
+                                              raid_bio->bi_sector);
                 generic_make_request(align_bi);
                 return 1;
         } else {
@@ -4078,7 +4115,8 @@ static void raid5_unplug(struct blk_plug_cb *blk_cb, bool from_schedule)
                 }
                 spin_unlock_irq(&conf->device_lock);
         }
-        trace_block_unplug(mddev->queue, cnt, !from_schedule);
+        if (mddev->queue)
+                trace_block_unplug(mddev->queue, cnt, !from_schedule);
         kfree(cb);
 }
 
@@ -4141,6 +4179,13 @@ static void make_discard_request(struct mddev *mddev, struct bio *bi)
                 sh = get_active_stripe(conf, logical_sector, 0, 0, 0);
                 prepare_to_wait(&conf->wait_for_overlap, &w,
                                 TASK_UNINTERRUPTIBLE);
+                set_bit(R5_Overlap, &sh->dev[sh->pd_idx].flags);
+                if (test_bit(STRIPE_SYNCING, &sh->state)) {
+                        release_stripe(sh);
+                        schedule();
+                        goto again;
+                }
+                clear_bit(R5_Overlap, &sh->dev[sh->pd_idx].flags);
                 spin_lock_irq(&sh->stripe_lock);
                 for (d = 0; d < conf->raid_disks; d++) {
                         if (d == sh->pd_idx || d == sh->qd_idx)
@@ -4153,6 +4198,7 @@ static void make_discard_request(struct mddev *mddev, struct bio *bi)
                                 goto again;
                         }
                 }
+                set_bit(STRIPE_DISCARD, &sh->state);
                 finish_wait(&conf->wait_for_overlap, &w);
                 for (d = 0; d < conf->raid_disks; d++) {
                         if (d == sh->pd_idx || d == sh->qd_idx)
diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h
index 18b2c4a8a1fd..b0b663b119a8 100644
--- a/drivers/md/raid5.h
+++ b/drivers/md/raid5.h
@@ -221,10 +221,6 @@ struct stripe_head {
         struct stripe_operations {
                 int                  target, target2;
                 enum sum_check_flags zero_sum_result;
-                #ifdef CONFIG_MULTICORE_RAID456
-                unsigned long        request;
-                wait_queue_head_t    wait_for_ops;
-                #endif
         } ops;
         struct r5dev {
                 /* rreq and rvec are used for the replacement device when
@@ -323,6 +319,7 @@ enum {
         STRIPE_COMPUTE_RUN,
         STRIPE_OPS_REQ_PENDING,
         STRIPE_ON_UNPLUG_LIST,
+        STRIPE_DISCARD,
 };
 
 /*