Merge branch 'for-3.10/drivers' of git://git.kernel.dk/linux-block

Pull block driver updates from Jens Axboe:
 "It might look big in volume, but when categorized, not a lot of
  drivers are touched.  The pull request contains:

   - mtip32xx fixes from Micron.

   - A slew of drbd updates, this time in a nicer series.

   - bcache, a flash/ssd caching framework from Kent.

   - Fixes for cciss"

* 'for-3.10/drivers' of git://git.kernel.dk/linux-block: (66 commits)
  bcache: Use bd_link_disk_holder()
  bcache: Allocator cleanup/fixes
  cciss: bug fix to prevent cciss from loading in kdump crash kernel
  cciss: add cciss_allow_hpsa module parameter
  drivers/block/mg_disk.c: add CONFIG_PM_SLEEP to suspend/resume functions
  mtip32xx: Workaround for unaligned writes
  bcache: Make sure blocksize isn't smaller than device blocksize
  bcache: Fix merge_bvec_fn usage for when it modifies the bvm
  bcache: Correctly check against BIO_MAX_PAGES
  bcache: Hack around stuff that clones up to bi_max_vecs
  bcache: Set ra_pages based on backing device's ra_pages
  bcache: Take data offset from the bdev superblock.
  mtip32xx: mtip32xx: Disable TRIM support
  mtip32xx: fix a smatch warning
  bcache: Disable broken btree fuzz tester
  bcache: Fix a format string overflow
  bcache: Fix a minor memory leak on device teardown
  bcache: Documentation updates
  bcache: Use WARN_ONCE() instead of __WARN()
  bcache: Add missing #include <linux/prefetch.h>
  ...

1 files changed, 161 insertions, 31 deletions

diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c
index 2b8303ad63c9..c24379ffd4e3 100644
--- a/drivers/block/drbd/drbd_req.c
+++ b/drivers/block/drbd/drbd_req.c
@@ -34,14 +34,14 @@
 static bool drbd_may_do_local_read(struct drbd_conf *mdev, sector_t sector, int size);
 
 /* Update disk stats at start of I/O request */
-static void _drbd_start_io_acct(struct drbd_conf *mdev, struct drbd_request *req, struct bio *bio)
+static void _drbd_start_io_acct(struct drbd_conf *mdev, struct drbd_request *req)
 {
-        const int rw = bio_data_dir(bio);
+        const int rw = bio_data_dir(req->master_bio);
         int cpu;
         cpu = part_stat_lock();
         part_round_stats(cpu, &mdev->vdisk->part0);
         part_stat_inc(cpu, &mdev->vdisk->part0, ios[rw]);
-        part_stat_add(cpu, &mdev->vdisk->part0, sectors[rw], bio_sectors(bio));
+        part_stat_add(cpu, &mdev->vdisk->part0, sectors[rw], req->i.size >> 9);
         (void) cpu; /* The macro invocations above want the cpu argument, I do not like
                        the compiler warning about cpu only assigned but never used... */
         part_inc_in_flight(&mdev->vdisk->part0, rw);
@@ -263,8 +263,7 @@ void drbd_req_complete(struct drbd_request *req, struct bio_and_error *m)
                 else
                         root = &mdev->read_requests;
                 drbd_remove_request_interval(root, req);
-        } else if (!(s & RQ_POSTPONED))
-                D_ASSERT((s & (RQ_NET_MASK & ~RQ_NET_DONE)) == 0);
+        }
 
         /* Before we can signal completion to the upper layers,
          * we may need to close the current transfer log epoch.
@@ -755,6 +754,11 @@ int __req_mod(struct drbd_request *req, enum drbd_req_event what,
                 D_ASSERT(req->rq_state & RQ_NET_PENDING);
                 mod_rq_state(req, m, RQ_NET_PENDING, RQ_NET_OK|RQ_NET_DONE);
                 break;
+
+        case QUEUE_AS_DRBD_BARRIER:
+                start_new_tl_epoch(mdev->tconn);
+                mod_rq_state(req, m, 0, RQ_NET_OK|RQ_NET_DONE);
+                break;
         };
 
         return rv;
@@ -861,8 +865,10 @@ static void maybe_pull_ahead(struct drbd_conf *mdev)
         bool congested = false;
         enum drbd_on_congestion on_congestion;
 
+        rcu_read_lock();
         nc = rcu_dereference(tconn->net_conf);
         on_congestion = nc ? nc->on_congestion : OC_BLOCK;
+        rcu_read_unlock();
         if (on_congestion == OC_BLOCK ||
             tconn->agreed_pro_version < 96)
                 return;
@@ -956,14 +962,8 @@ static int drbd_process_write_request(struct drbd_request *req)
         struct drbd_conf *mdev = req->w.mdev;
         int remote, send_oos;
 
-        rcu_read_lock();
         remote = drbd_should_do_remote(mdev->state);
-        if (remote) {
-                maybe_pull_ahead(mdev);
-                remote = drbd_should_do_remote(mdev->state);
-        }
         send_oos = drbd_should_send_out_of_sync(mdev->state);
-        rcu_read_unlock();
 
         /* Need to replicate writes.  Unless it is an empty flush,
          * which is better mapped to a DRBD P_BARRIER packet,
@@ -975,8 +975,8 @@ static int drbd_process_write_request(struct drbd_request *req)
                 /* The only size==0 bios we expect are empty flushes. */
                 D_ASSERT(req->master_bio->bi_rw & REQ_FLUSH);
                 if (remote)
-                        start_new_tl_epoch(mdev->tconn);
-                return 0;
+                        _req_mod(req, QUEUE_AS_DRBD_BARRIER);
+                return remote;
         }
 
         if (!remote && !send_oos)
@@ -1020,12 +1020,24 @@ drbd_submit_req_private_bio(struct drbd_request *req)
                 bio_endio(bio, -EIO);
 }
 
-void __drbd_make_request(struct drbd_conf *mdev, struct bio *bio, unsigned long start_time)
+static void drbd_queue_write(struct drbd_conf *mdev, struct drbd_request *req)
 {
-        const int rw = bio_rw(bio);
-        struct bio_and_error m = { NULL, };
+        spin_lock(&mdev->submit.lock);
+        list_add_tail(&req->tl_requests, &mdev->submit.writes);
+        spin_unlock(&mdev->submit.lock);
+        queue_work(mdev->submit.wq, &mdev->submit.worker);
+}
+
+/* returns the new drbd_request pointer, if the caller is expected to
+ * drbd_send_and_submit() it (to save latency), or NULL if we queued the
+ * request on the submitter thread.
+ * Returns ERR_PTR(-ENOMEM) if we cannot allocate a drbd_request.
+ */
+struct drbd_request *
+drbd_request_prepare(struct drbd_conf *mdev, struct bio *bio, unsigned long start_time)
+{
+        const int rw = bio_data_dir(bio);
         struct drbd_request *req;
-        bool no_remote = false;
 
         /* allocate outside of all locks; */
         req = drbd_req_new(mdev, bio);
@@ -1035,7 +1047,7 @@ void __drbd_make_request(struct drbd_conf *mdev, struct bio *bio, unsigned long
                  * if user cannot handle io errors, that's not our business. */
                 dev_err(DEV, "could not kmalloc() req\n");
                 bio_endio(bio, -ENOMEM);
-                return;
+                return ERR_PTR(-ENOMEM);
         }
         req->start_time = start_time;
 
@@ -1044,28 +1056,40 @@ void __drbd_make_request(struct drbd_conf *mdev, struct bio *bio, unsigned long
                 req->private_bio = NULL;
         }
 
-        /* For WRITES going to the local disk, grab a reference on the target
-         * extent.  This waits for any resync activity in the corresponding
-         * resync extent to finish, and, if necessary, pulls in the target
-         * extent into the activity log, which involves further disk io because
-         * of transactional on-disk meta data updates.
-         * Empty flushes don't need to go into the activity log, they can only
-         * flush data for pending writes which are already in there. */
+        /* Update disk stats */
+        _drbd_start_io_acct(mdev, req);
+
         if (rw == WRITE && req->private_bio && req->i.size
         && !test_bit(AL_SUSPENDED, &mdev->flags)) {
+                if (!drbd_al_begin_io_fastpath(mdev, &req->i)) {
+                        drbd_queue_write(mdev, req);
+                        return NULL;
+                }
                 req->rq_state |= RQ_IN_ACT_LOG;
-                drbd_al_begin_io(mdev, &req->i);
         }
 
+        return req;
+}
+
+static void drbd_send_and_submit(struct drbd_conf *mdev, struct drbd_request *req)
+{
+        const int rw = bio_rw(req->master_bio);
+        struct bio_and_error m = { NULL, };
+        bool no_remote = false;
+
         spin_lock_irq(&mdev->tconn->req_lock);
         if (rw == WRITE) {
                 /* This may temporarily give up the req_lock,
                  * but will re-aquire it before it returns here.
                  * Needs to be before the check on drbd_suspended() */
                 complete_conflicting_writes(req);
+                /* no more giving up req_lock from now on! */
+
+                /* check for congestion, and potentially stop sending
+                 * full data updates, but start sending "dirty bits" only. */
+                maybe_pull_ahead(mdev);
         }
 
-        /* no more giving up req_lock from now on! */
 
         if (drbd_suspended(mdev)) {
                 /* push back and retry: */
@@ -1078,9 +1102,6 @@ void __drbd_make_request(struct drbd_conf *mdev, struct bio *bio, unsigned long
                 goto out;
         }
 
-        /* Update disk stats */
-        _drbd_start_io_acct(mdev, req, bio);
-
         /* We fail READ/READA early, if we can not serve it.
          * We must do this before req is registered on any lists.
          * Otherwise, drbd_req_complete() will queue failed READ for retry. */
@@ -1137,7 +1158,116 @@ out:
 
         if (m.bio)
                 complete_master_bio(mdev, &m);
-        return;
+}
+
+void __drbd_make_request(struct drbd_conf *mdev, struct bio *bio, unsigned long start_time)
+{
+        struct drbd_request *req = drbd_request_prepare(mdev, bio, start_time);
+        if (IS_ERR_OR_NULL(req))
+                return;
+        drbd_send_and_submit(mdev, req);
+}
+
+static void submit_fast_path(struct drbd_conf *mdev, struct list_head *incoming)
+{
+        struct drbd_request *req, *tmp;
+        list_for_each_entry_safe(req, tmp, incoming, tl_requests) {
+                const int rw = bio_data_dir(req->master_bio);
+
+                if (rw == WRITE /* rw != WRITE should not even end up here! */
+                && req->private_bio && req->i.size
+                && !test_bit(AL_SUSPENDED, &mdev->flags)) {
+                        if (!drbd_al_begin_io_fastpath(mdev, &req->i))
+                                continue;
+
+                        req->rq_state |= RQ_IN_ACT_LOG;
+                }
+
+                list_del_init(&req->tl_requests);
+                drbd_send_and_submit(mdev, req);
+        }
+}
+
+static bool prepare_al_transaction_nonblock(struct drbd_conf *mdev,
+                                            struct list_head *incoming,
+                                            struct list_head *pending)
+{
+        struct drbd_request *req, *tmp;
+        int wake = 0;
+        int err;
+
+        spin_lock_irq(&mdev->al_lock);
+        list_for_each_entry_safe(req, tmp, incoming, tl_requests) {
+                err = drbd_al_begin_io_nonblock(mdev, &req->i);
+                if (err == -EBUSY)
+                        wake = 1;
+                if (err)
+                        continue;
+                req->rq_state |= RQ_IN_ACT_LOG;
+                list_move_tail(&req->tl_requests, pending);
+        }
+        spin_unlock_irq(&mdev->al_lock);
+        if (wake)
+                wake_up(&mdev->al_wait);
+
+        return !list_empty(pending);
+}
+
+void do_submit(struct work_struct *ws)
+{
+        struct drbd_conf *mdev = container_of(ws, struct drbd_conf, submit.worker);
+        LIST_HEAD(incoming);
+        LIST_HEAD(pending);
+        struct drbd_request *req, *tmp;
+
+        for (;;) {
+                spin_lock(&mdev->submit.lock);
+                list_splice_tail_init(&mdev->submit.writes, &incoming);
+                spin_unlock(&mdev->submit.lock);
+
+                submit_fast_path(mdev, &incoming);
+                if (list_empty(&incoming))
+                        break;
+
+                wait_event(mdev->al_wait, prepare_al_transaction_nonblock(mdev, &incoming, &pending));
+                /* Maybe more was queued, while we prepared the transaction?
+                 * Try to stuff them into this transaction as well.
+                 * Be strictly non-blocking here, no wait_event, we already
+                 * have something to commit.
+                 * Stop if we don't make any more progres.
+                 */
+                for (;;) {
+                        LIST_HEAD(more_pending);
+                        LIST_HEAD(more_incoming);
+                        bool made_progress;
+
+                        /* It is ok to look outside the lock,
+                         * it's only an optimization anyways */
+                        if (list_empty(&mdev->submit.writes))
+                                break;
+
+                        spin_lock(&mdev->submit.lock);
+                        list_splice_tail_init(&mdev->submit.writes, &more_incoming);
+                        spin_unlock(&mdev->submit.lock);
+
+                        if (list_empty(&more_incoming))
+                                break;
+
+                        made_progress = prepare_al_transaction_nonblock(mdev, &more_incoming, &more_pending);
+
+                        list_splice_tail_init(&more_pending, &pending);
+                        list_splice_tail_init(&more_incoming, &incoming);
+
+                        if (!made_progress)
+                                break;
+                }
+                drbd_al_begin_io_commit(mdev, false);
+
+                list_for_each_entry_safe(req, tmp, &pending, tl_requests) {
+                        list_del_init(&req->tl_requests);
+                        drbd_send_and_submit(mdev, req);
+                }
+        }
 }
 
 void drbd_make_request(struct request_queue *q, struct bio *bio)