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>
  ...

Documentation/ABI/testing/sysfs-block-bcache

+What:		/sys/block/<disk>/bcache/unregister
+Date:		November 2010
+Contact:	Kent Overstreet <kent.overstreet@gmail.com>
+Description:
+		A write to this file causes the backing device or cache to be
+		unregistered. If a backing device had dirty data in the cache,
+		writeback mode is automatically disabled and all dirty data is
+		flushed before the device is unregistered. Caches unregister
+		all associated backing devices before unregistering themselves.
+
+What:		/sys/block/<disk>/bcache/clear_stats
+Date:		November 2010
+Contact:	Kent Overstreet <kent.overstreet@gmail.com>
+Description:
+		Writing to this file resets all the statistics for the device.
+
+What:		/sys/block/<disk>/bcache/cache
+Date:		November 2010
+Contact:	Kent Overstreet <kent.overstreet@gmail.com>
+Description:
+		For a backing device that has cache, a symlink to
+		the bcache/ dir of that cache.
+
+What:		/sys/block/<disk>/bcache/cache_hits
+Date:		November 2010
+Contact:	Kent Overstreet <kent.overstreet@gmail.com>
+Description:
+		For backing devices: integer number of full cache hits,
+		counted per bio. A partial cache hit counts as a miss.
+
+What:		/sys/block/<disk>/bcache/cache_misses
+Date:		November 2010
+Contact:	Kent Overstreet <kent.overstreet@gmail.com>
+Description:
+		For backing devices: integer number of cache misses.
+
+What:		/sys/block/<disk>/bcache/cache_hit_ratio
+Date:		November 2010
+Contact:	Kent Overstreet <kent.overstreet@gmail.com>
+Description:
+		For backing devices: cache hits as a percentage.
+
+What:		/sys/block/<disk>/bcache/sequential_cutoff
+Date:		November 2010
+Contact:	Kent Overstreet <kent.overstreet@gmail.com>
+Description:
+		For backing devices: Threshold past which sequential IO will
+		skip the cache. Read and written as bytes in human readable
+		units (i.e. echo 10M > sequntial_cutoff).
+
+What:		/sys/block/<disk>/bcache/bypassed
+Date:		November 2010
+Contact:	Kent Overstreet <kent.overstreet@gmail.com>
+Description:
+		Sum of all reads and writes that have bypassed the cache (due
+		to the sequential cutoff).  Expressed as bytes in human
+		readable units.
+
+What:		/sys/block/<disk>/bcache/writeback
+Date:		November 2010
+Contact:	Kent Overstreet <kent.overstreet@gmail.com>
+Description:
+		For backing devices: When on, writeback caching is enabled and
+		writes will be buffered in the cache. When off, caching is in
+		writethrough mode; reads and writes will be added to the
+		cache but no write buffering will take place.
+
+What:		/sys/block/<disk>/bcache/writeback_running
+Date:		November 2010
+Contact:	Kent Overstreet <kent.overstreet@gmail.com>
+Description:
+		For backing devices: when off, dirty data will not be written
+		from the cache to the backing device. The cache will still be
+		used to buffer writes until it is mostly full, at which point
+		writes transparently revert to writethrough mode. Intended only
+		for benchmarking/testing.
+
+What:		/sys/block/<disk>/bcache/writeback_delay
+Date:		November 2010
+Contact:	Kent Overstreet <kent.overstreet@gmail.com>
+Description:
+		For backing devices: In writeback mode, when dirty data is
+		written to the cache and the cache held no dirty data for that
+		backing device, writeback from cache to backing device starts
+		after this delay, expressed as an integer number of seconds.
+
+What:		/sys/block/<disk>/bcache/writeback_percent
+Date:		November 2010
+Contact:	Kent Overstreet <kent.overstreet@gmail.com>
+Description:
+		For backing devices: If nonzero, writeback from cache to
+		backing device only takes place when more than this percentage
+		of the cache is used, allowing more write coalescing to take
+		place and reducing total number of writes sent to the backing
+		device. Integer between 0 and 40.
+
+What:		/sys/block/<disk>/bcache/synchronous
+Date:		November 2010
+Contact:	Kent Overstreet <kent.overstreet@gmail.com>
+Description:
+		For a cache, a boolean that allows synchronous mode to be
+		switched on and off. In synchronous mode all writes are ordered
+		such that the cache can reliably recover from unclean shutdown;
+		if disabled bcache will not generally wait for writes to
+		complete but if the cache is not shut down cleanly all data
+		will be discarded from the cache. Should not be turned off with
+		writeback caching enabled.
+
+What:		/sys/block/<disk>/bcache/discard
+Date:		November 2010
+Contact:	Kent Overstreet <kent.overstreet@gmail.com>
+Description:
+		For a cache, a boolean allowing discard/TRIM to be turned off
+		or back on if the device supports it.
+
+What:		/sys/block/<disk>/bcache/bucket_size
+Date:		November 2010
+Contact:	Kent Overstreet <kent.overstreet@gmail.com>
+Description:
+		For a cache, bucket size in human readable units, as set at
+		cache creation time; should match the erase block size of the
+		SSD for optimal performance.
+
+What:		/sys/block/<disk>/bcache/nbuckets
+Date:		November 2010
+Contact:	Kent Overstreet <kent.overstreet@gmail.com>
+Description:
+		For a cache, the number of usable buckets.
+
+What:		/sys/block/<disk>/bcache/tree_depth
+Date:		November 2010
+Contact:	Kent Overstreet <kent.overstreet@gmail.com>
+Description:
+		For a cache, height of the btree excluding leaf nodes (i.e. a
+		one node tree will have a depth of 0).
+
+What:		/sys/block/<disk>/bcache/btree_cache_size
+Date:		November 2010
+Contact:	Kent Overstreet <kent.overstreet@gmail.com>
+Description:
+		Number of btree buckets/nodes that are currently cached in
+		memory; cache dynamically grows and shrinks in response to
+		memory pressure from the rest of the system.
+
+What:		/sys/block/<disk>/bcache/written
+Date:		November 2010
+Contact:	Kent Overstreet <kent.overstreet@gmail.com>
+Description:
+		For a cache, total amount of data in human readable units
+		written to the cache, excluding all metadata.
+
+What:		/sys/block/<disk>/bcache/btree_written
+Date:		November 2010
+Contact:	Kent Overstreet <kent.overstreet@gmail.com>
+Description:
+		For a cache, sum of all btree writes in human readable units.

MAINTAINERS

@@ -1620,6 +1620,13 @@ W:	http://www.baycom.org/~tom/ham/ham.html
 S:	Maintained
 F:	drivers/net/hamradio/baycom*
 
+BCACHE (BLOCK LAYER CACHE)
+M:	Kent Overstreet <koverstreet@google.com>
+L:	linux-bcache@vger.kernel.org
+W:	http://bcache.evilpiepirate.org
+S:	Maintained:
+F:	drivers/md/bcache/
+
 BEFS FILE SYSTEM
 S:	Orphan
 F:	Documentation/filesystems/befs.txt

drivers/block/aoe/aoecmd.c

@@ -920,16 +920,14 @@ bio_pagedec(struct bio *bio)
 static void
 bufinit(struct buf *buf, struct request *rq, struct bio *bio)
 {
-	struct bio_vec *bv;
-
 	memset(buf, 0, sizeof(*buf));
 	buf->rq = rq;
 	buf->bio = bio;
 	buf->resid = bio->bi_size;
 	buf->sector = bio->bi_sector;
 	bio_pageinc(bio);
-	buf->bv = bv = bio_iovec(bio);
-	buf->bv_resid = bv->bv_len;
+	buf->bv = bio_iovec(bio);
+	buf->bv_resid = buf->bv->bv_len;
 	WARN_ON(buf->bv_resid == 0);
 }
 

drivers/block/cciss.c

@@ -75,6 +75,12 @@ module_param(cciss_simple_mode, int, S_IRUGO|S_IWUSR);
 MODULE_PARM_DESC(cciss_simple_mode,
 	"Use 'simple mode' rather than 'performant mode'");
 
+static int cciss_allow_hpsa;
+module_param(cciss_allow_hpsa, int, S_IRUGO|S_IWUSR);
+MODULE_PARM_DESC(cciss_allow_hpsa,
+	"Prevent cciss driver from accessing hardware known to be "
+	" supported by the hpsa driver");
+
 static DEFINE_MUTEX(cciss_mutex);
 static struct proc_dir_entry *proc_cciss;
 
@@ -4115,9 +4121,13 @@ static int cciss_lookup_board_id(struct pci_dev *pdev, u32 *board_id)
 	*board_id = ((subsystem_device_id << 16) & 0xffff0000) |
 			subsystem_vendor_id;
 
-	for (i = 0; i < ARRAY_SIZE(products); i++)
+	for (i = 0; i < ARRAY_SIZE(products); i++) {
+		/* Stand aside for hpsa driver on request */
+		if (cciss_allow_hpsa)
+			return -ENODEV;
 		if (*board_id == products[i].board_id)
 			return i;
+	}
 	dev_warn(&pdev->dev, "unrecognized board ID: 0x%08x, ignoring.\n",
 		*board_id);
 	return -ENODEV;
@@ -4959,6 +4969,16 @@ static int cciss_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	ctlr_info_t *h;
 	unsigned long flags;
 
+	/*
+	 * By default the cciss driver is used for all older HP Smart Array
+	 * controllers. There are module paramaters that allow a user to
+	 * override this behavior and instead use the hpsa SCSI driver. If
+	 * this is the case cciss may be loaded first from the kdump initrd
+	 * image and cause a kernel panic. So if reset_devices is true and
+	 * cciss_allow_hpsa is set just bail.
+	 */
+	if ((reset_devices) && (cciss_allow_hpsa == 1))
+		return -ENODEV;
 	rc = cciss_init_reset_devices(pdev);
 	if (rc) {
 		if (rc != -ENOTSUPP)

drivers/block/drbd/drbd_bitmap.c

@@ -612,6 +612,17 @@ static void bm_memset(struct drbd_bitmap *b, size_t offset, int c, size_t len)
 	}
 }
 
+/* For the layout, see comment above drbd_md_set_sector_offsets(). */
+static u64 drbd_md_on_disk_bits(struct drbd_backing_dev *ldev)
+{
+	u64 bitmap_sectors;
+	if (ldev->md.al_offset == 8)
+		bitmap_sectors = ldev->md.md_size_sect - ldev->md.bm_offset;
+	else
+		bitmap_sectors = ldev->md.al_offset - ldev->md.bm_offset;
+	return bitmap_sectors << (9 + 3);
+}
+
 /*
  * make sure the bitmap has enough room for the attached storage,
  * if necessary, resize.
@@ -668,7 +679,7 @@ int drbd_bm_resize(struct drbd_conf *mdev, sector_t capacity, int set_new_bits)
 	words = ALIGN(bits, 64) >> LN2_BPL;
 
 	if (get_ldev(mdev)) {
-		u64 bits_on_disk = ((u64)mdev->ldev->md.md_size_sect-MD_BM_OFFSET) << 12;
+		u64 bits_on_disk = drbd_md_on_disk_bits(mdev->ldev);
 		put_ldev(mdev);
 		if (bits > bits_on_disk) {
 			dev_info(DEV, "bits = %lu\n", bits);

drivers/block/drbd/drbd_proc.c

@@ -313,8 +313,14 @@ static int drbd_seq_show(struct seq_file *seq, void *v)
 
 static int drbd_proc_open(struct inode *inode, struct file *file)
 {
-	if (try_module_get(THIS_MODULE))
-		return single_open(file, drbd_seq_show, PDE_DATA(inode));
+	int err;
+
+	if (try_module_get(THIS_MODULE)) {
+		err = single_open(file, drbd_seq_show, PDE_DATA(inode));
+		if (err)
+			module_put(THIS_MODULE);
+		return err;
+	}
 	return -ENODEV;
 }
 

drivers/block/drbd/drbd_receiver.c

@@ -850,6 +850,7 @@ int drbd_connected(struct drbd_conf *mdev)
 		err = drbd_send_current_state(mdev);
 	clear_bit(USE_DEGR_WFC_T, &mdev->flags);
 	clear_bit(RESIZE_PENDING, &mdev->flags);
+	atomic_set(&mdev->ap_in_flight, 0);
 	mod_timer(&mdev->request_timer, jiffies + HZ); /* just start it here. */
 	return err;
 }
@@ -2266,7 +2267,7 @@ static int receive_Data(struct drbd_tconn *tconn, struct packet_info *pi)
 		drbd_set_out_of_sync(mdev, peer_req->i.sector, peer_req->i.size);
 		peer_req->flags |= EE_CALL_AL_COMPLETE_IO;
 		peer_req->flags &= ~EE_MAY_SET_IN_SYNC;
-		drbd_al_begin_io(mdev, &peer_req->i);
+		drbd_al_begin_io(mdev, &peer_req->i, true);
 	}
 
 	err = drbd_submit_peer_request(mdev, peer_req, rw, DRBD_FAULT_DT_WR);
@@ -2662,7 +2663,6 @@ static int drbd_asb_recover_1p(struct drbd_conf *mdev) __must_hold(local)
 		if (hg == -1 && mdev->state.role == R_PRIMARY) {
 			enum drbd_state_rv rv2;
 
-			drbd_set_role(mdev, R_SECONDARY, 0);
 			 /* drbd_change_state() does not sleep while in SS_IN_TRANSIENT_STATE,
 			  * we might be here in C_WF_REPORT_PARAMS which is transient.
 			  * we do not need to wait for the after state change work either. */
@@ -3993,7 +3993,7 @@ static int receive_state(struct drbd_tconn *tconn, struct packet_info *pi)
 
 	clear_bit(DISCARD_MY_DATA, &mdev->flags);
 
-	drbd_md_sync(mdev); /* update connected indicator, la_size, ... */
+	drbd_md_sync(mdev); /* update connected indicator, la_size_sect, ... */
 
 	return 0;
 }
@@ -4660,8 +4660,8 @@ static int drbd_do_features(struct drbd_tconn *tconn)
 #if !defined(CONFIG_CRYPTO_HMAC) && !defined(CONFIG_CRYPTO_HMAC_MODULE)
 static int drbd_do_auth(struct drbd_tconn *tconn)
 {
-	dev_err(DEV, "This kernel was build without CONFIG_CRYPTO_HMAC.\n");
-	dev_err(DEV, "You need to disable 'cram-hmac-alg' in drbd.conf.\n");
+	conn_err(tconn, "This kernel was build without CONFIG_CRYPTO_HMAC.\n");
+	conn_err(tconn, "You need to disable 'cram-hmac-alg' in drbd.conf.\n");
 	return -1;
 }
 #else
@@ -5258,9 +5258,11 @@ int drbd_asender(struct drbd_thread *thi)
 	bool ping_timeout_active = false;
 	struct net_conf *nc;
 	int ping_timeo, tcp_cork, ping_int;
+	struct sched_param param = { .sched_priority = 2 };
 
-	current->policy = SCHED_RR;  /* Make this a realtime task! */
-	current->rt_priority = 2;    /* more important than all other tasks */
+	rv = sched_setscheduler(current, SCHED_RR, &param);
+	if (rv < 0)
+		conn_err(tconn, "drbd_asender: ERROR set priority, ret=%d\n", rv);
 
 	while (get_t_state(thi) == RUNNING) {
 		drbd_thread_current_set_cpu(thi);

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 @@ void __drbd_make_request(struct drbd_conf *mdev, struct bio *bio, unsigned long
 
 	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)

drivers/block/drbd/drbd_req.h

@@ -88,6 +88,14 @@ enum drbd_req_event {
 	QUEUE_FOR_NET_READ,
 	QUEUE_FOR_SEND_OOS,
 
+	/* An empty flush is queued as P_BARRIER,
+	 * which will cause it to complete "successfully",
+	 * even if the local disk flush failed.
+	 *
+	 * Just like "real" requests, empty flushes (blkdev_issue_flush()) will
+	 * only see an error if neither local nor remote data is reachable. */
+	QUEUE_AS_DRBD_BARRIER,
+
 	SEND_CANCELED,
 	SEND_FAILED,
 	HANDED_OVER_TO_NETWORK,

drivers/block/drbd/drbd_state.c

@@ -570,6 +570,13 @@ is_valid_state(struct drbd_conf *mdev, union drbd_state ns)
 		  mdev->tconn->agreed_pro_version < 88)
 		rv = SS_NOT_SUPPORTED;
 
+	else if (ns.role == R_PRIMARY && ns.disk < D_UP_TO_DATE && ns.pdsk < D_UP_TO_DATE)
+		rv = SS_NO_UP_TO_DATE_DISK;
+
+	else if ((ns.conn == C_STARTING_SYNC_S || ns.conn == C_STARTING_SYNC_T) &&
+                 ns.pdsk == D_UNKNOWN)
+		rv = SS_NEED_CONNECTION;
+
 	else if (ns.conn >= C_CONNECTED && ns.pdsk == D_UNKNOWN)
 		rv = SS_CONNECTED_OUTDATES;
 
@@ -635,6 +642,10 @@ is_valid_soft_transition(union drbd_state os, union drbd_state ns, struct drbd_t
 	    && os.conn < C_WF_REPORT_PARAMS)
 		rv = SS_NEED_CONNECTION; /* No NetworkFailure -> SyncTarget etc... */
 
+	if (ns.conn == C_DISCONNECTING && ns.pdsk == D_OUTDATED &&
+	    os.conn < C_CONNECTED && os.pdsk > D_OUTDATED)
+		rv = SS_OUTDATE_WO_CONN;
+
 	return rv;
 }
 
@@ -1377,13 +1388,6 @@ static void after_state_ch(struct drbd_conf *mdev, union drbd_state os,
 			&drbd_bmio_set_n_write, &abw_start_sync,
 			"set_n_write from StartingSync", BM_LOCKED_TEST_ALLOWED);
 
-	/* We are invalidating our self... */
-	if (os.conn < C_CONNECTED && ns.conn < C_CONNECTED &&
-	    os.disk > D_INCONSISTENT && ns.disk == D_INCONSISTENT)
-		/* other bitmap operation expected during this phase */
-		drbd_queue_bitmap_io(mdev, &drbd_bmio_set_n_write, NULL,
-			"set_n_write from invalidate", BM_LOCKED_MASK);
-
 	/* first half of local IO error, failure to attach,
 	 * or administrative detach */
 	if (os.disk != D_FAILED && ns.disk == D_FAILED) {
@@ -1748,13 +1752,9 @@ _conn_rq_cond(struct drbd_tconn *tconn, union drbd_state mask, union drbd_state
 	if (test_and_clear_bit(CONN_WD_ST_CHG_FAIL, &tconn->flags))
 		return SS_CW_FAILED_BY_PEER;
 
-	rv = tconn->cstate != C_WF_REPORT_PARAMS ? SS_CW_NO_NEED : SS_UNKNOWN_ERROR;
-
-	if (rv == SS_UNKNOWN_ERROR)
-		rv = conn_is_valid_transition(tconn, mask, val, 0);
-
-	if (rv == SS_SUCCESS)
-		rv = SS_UNKNOWN_ERROR; /* cont waiting, otherwise fail. */
+	rv = conn_is_valid_transition(tconn, mask, val, 0);
+	if (rv == SS_SUCCESS && tconn->cstate == C_WF_REPORT_PARAMS)
+		rv = SS_UNKNOWN_ERROR; /* continue waiting */
 
 	return rv;
 }

drivers/block/drbd/drbd_strings.c

@@ -89,6 +89,7 @@ static const char *drbd_state_sw_errors[] = {
 	[-SS_LOWER_THAN_OUTDATED] = "Disk state is lower than outdated",
 	[-SS_IN_TRANSIENT_STATE] = "In transient state, retry after next state change",
 	[-SS_CONCURRENT_ST_CHG] = "Concurrent state changes detected and aborted",
+	[-SS_OUTDATE_WO_CONN] = "Need a connection for a graceful disconnect/outdate peer",
 	[-SS_O_VOL_PEER_PRI] = "Other vol primary on peer not allowed by config",
 };
 

drivers/block/drbd/drbd_worker.c

@@ -89,7 +89,8 @@ void drbd_md_io_complete(struct bio *bio, int error)
 	md_io->done = 1;
 	wake_up(&mdev->misc_wait);
 	bio_put(bio);
-	put_ldev(mdev);
+	if (mdev->ldev) /* special case: drbd_md_read() during drbd_adm_attach() */
+		put_ldev(mdev);
 }
 
 /* reads on behalf of the partner,
@@ -1410,7 +1411,7 @@ int w_restart_disk_io(struct drbd_work *w, int cancel)
 	struct drbd_conf *mdev = w->mdev;
 
 	if (bio_data_dir(req->master_bio) == WRITE && req->rq_state & RQ_IN_ACT_LOG)
-		drbd_al_begin_io(mdev, &req->i);
+		drbd_al_begin_io(mdev, &req->i, false);
 
 	drbd_req_make_private_bio(req, req->master_bio);
 	req->private_bio->bi_bdev = mdev->ldev->backing_bdev;
@@ -1425,7 +1426,7 @@ static int _drbd_may_sync_now(struct drbd_conf *mdev)
 	int resync_after;
 
 	while (1) {
-		if (!odev->ldev)
+		if (!odev->ldev || odev->state.disk == D_DISKLESS)
 			return 1;
 		rcu_read_lock();
 		resync_after = rcu_dereference(odev->ldev->disk_conf)->resync_after;
@@ -1433,7 +1434,7 @@ static int _drbd_may_sync_now(struct drbd_conf *mdev)
 		if (resync_after == -1)
 			return 1;
 		odev = minor_to_mdev(resync_after);
-		if (!expect(odev))
+		if (!odev)
 			return 1;
 		if ((odev->state.conn >= C_SYNC_SOURCE &&
 		     odev->state.conn <= C_PAUSED_SYNC_T) ||
@@ -1515,7 +1516,7 @@ enum drbd_ret_code drbd_resync_after_valid(struct drbd_conf *mdev, int o_minor)
 
 	if (o_minor == -1)
 		return NO_ERROR;
-	if (o_minor < -1 || minor_to_mdev(o_minor) == NULL)
+	if (o_minor < -1 || o_minor > MINORMASK)
 		return ERR_RESYNC_AFTER;
 
 	/* check for loops */
@@ -1524,6 +1525,15 @@ enum drbd_ret_code drbd_resync_after_valid(struct drbd_conf *mdev, int o_minor)
 		if (odev == mdev)
 			return ERR_RESYNC_AFTER_CYCLE;
 
+		/* You are free to depend on diskless, non-existing,
+		 * or not yet/no longer existing minors.
+		 * We only reject dependency loops.
+		 * We cannot follow the dependency chain beyond a detached or
+		 * missing minor.
+		 */
+		if (!odev || !odev->ldev || odev->state.disk == D_DISKLESS)
+			return NO_ERROR;
+
 		rcu_read_lock();
 		resync_after = rcu_dereference(odev->ldev->disk_conf)->resync_after;
 		rcu_read_unlock();
@@ -1652,7 +1662,9 @@ void drbd_start_resync(struct drbd_conf *mdev, enum drbd_conns side)
 	clear_bit(B_RS_H_DONE, &mdev->flags);
 
 	write_lock_irq(&global_state_lock);
-	if (!get_ldev_if_state(mdev, D_NEGOTIATING)) {
+	/* Did some connection breakage or IO error race with us? */
+	if (mdev->state.conn < C_CONNECTED
+	|| !get_ldev_if_state(mdev, D_NEGOTIATING)) {
 		write_unlock_irq(&global_state_lock);
 		mutex_unlock(mdev->state_mutex);
 		return;

drivers/block/mg_disk.c

@@ -780,6 +780,7 @@ static const struct block_device_operations mg_disk_ops = {
 	.getgeo = mg_getgeo
 };
 
+#ifdef CONFIG_PM_SLEEP
 static int mg_suspend(struct device *dev)
 {
 	struct mg_drv_data *prv_data = dev->platform_data;
@@ -824,6 +825,7 @@ static int mg_resume(struct device *dev)
 
 	return 0;
 }
+#endif
 
 static SIMPLE_DEV_PM_OPS(mg_pm, mg_suspend, mg_resume);
 

drivers/block/mtip32xx/mtip32xx.c

@@ -728,7 +728,10 @@ static void mtip_async_complete(struct mtip_port *port,
 	atomic_set(&port->commands[tag].active, 0);
 	release_slot(port, tag);
 
-	up(&port->cmd_slot);
+	if (unlikely(command->unaligned))
+		up(&port->cmd_slot_unal);
+	else
+		up(&port->cmd_slot);
 }
 
 /*
@@ -1560,10 +1563,12 @@ static int mtip_get_identify(struct mtip_port *port, void __user *user_buffer)
 	}
 #endif
 
+#ifdef MTIP_TRIM /* Disabling TRIM support temporarily */
 	/* Demux ID.DRAT & ID.RZAT to determine trim support */
 	if (port->identify[69] & (1 << 14) && port->identify[69] & (1 << 5))
 		port->dd->trim_supp = true;
 	else
+#endif
 		port->dd->trim_supp = false;
 
 	/* Set the identify buffer as valid. */
@@ -2557,7 +2562,7 @@ static int mtip_hw_ioctl(struct driver_data *dd, unsigned int cmd,
  */
 static void mtip_hw_submit_io(struct driver_data *dd, sector_t sector,
 			      int nsect, int nents, int tag, void *callback,
-			      void *data, int dir)
+			      void *data, int dir, int unaligned)
 {
 	struct host_to_dev_fis	*fis;
 	struct mtip_port *port = dd->port;
@@ -2570,6 +2575,7 @@ static void mtip_hw_submit_io(struct driver_data *dd, sector_t sector,
 
 	command->scatter_ents = nents;
 
+	command->unaligned = unaligned;
 	/*
 	 * The number of retries for this command before it is
 	 * reported as a failure to the upper layers.
@@ -2598,6 +2604,9 @@ static void mtip_hw_submit_io(struct driver_data *dd, sector_t sector,
 	fis->res3        = 0;
 	fill_command_sg(dd, command, nents);
 
+	if (unaligned)
+		fis->device |= 1 << 7;
+
 	/* Populate the command header */
 	command->command_header->opts =
 			__force_bit2int cpu_to_le32(
@@ -2644,9 +2653,13 @@ static void mtip_hw_submit_io(struct driver_data *dd, sector_t sector,
  * return value
  *      None
  */
-static void mtip_hw_release_scatterlist(struct driver_data *dd, int tag)
+static void mtip_hw_release_scatterlist(struct driver_data *dd, int tag,
+								int unaligned)
 {
+	struct semaphore *sem = unaligned ? &dd->port->cmd_slot_unal :
+							&dd->port->cmd_slot;
 	release_slot(dd->port, tag);
+	up(sem);
 }
 
 /*
@@ -2661,22 +2674,25 @@ static void mtip_hw_release_scatterlist(struct driver_data *dd, int tag)
  *	or NULL if no command slots are available.
  */
 static struct scatterlist *mtip_hw_get_scatterlist(struct driver_data *dd,
-						   int *tag)
+						   int *tag, int unaligned)
 {
+	struct semaphore *sem = unaligned ? &dd->port->cmd_slot_unal :
+							&dd->port->cmd_slot;
+
 	/*
 	 * It is possible that, even with this semaphore, a thread
 	 * may think that no command slots are available. Therefore, we
 	 * need to make an attempt to get_slot().
 	 */
-	down(&dd->port->cmd_slot);
+	down(sem);
 	*tag = get_slot(dd->port);
 
 	if (unlikely(test_bit(MTIP_DDF_REMOVE_PENDING_BIT, &dd->dd_flag))) {
-		up(&dd->port->cmd_slot);
+		up(sem);
 		return NULL;
 	}
 	if (unlikely(*tag < 0)) {
-		up(&dd->port->cmd_slot);
+		up(sem);
 		return NULL;
 	}
 
@@ -3010,6 +3026,11 @@ static inline void hba_setup(struct driver_data *dd)
 		dd->mmio + HOST_HSORG);
 }
 
+static int mtip_device_unaligned_constrained(struct driver_data *dd)
+{
+	return (dd->pdev->device == P420M_DEVICE_ID ? 1 : 0);
+}
+
 /*
  * Detect the details of the product, and store anything needed
  * into the driver data structure.  This includes product type and
@@ -3232,8 +3253,15 @@ static int mtip_hw_init(struct driver_data *dd)
 	for (i = 0; i < MTIP_MAX_SLOT_GROUPS; i++)
 		dd->work[i].port = dd->port;
 
+	/* Enable unaligned IO constraints for some devices */
+	if (mtip_device_unaligned_constrained(dd))
+		dd->unal_qdepth = MTIP_MAX_UNALIGNED_SLOTS;
+	else
+		dd->unal_qdepth = 0;
+
 	/* Counting semaphore to track command slot usage */
-	sema_init(&dd->port->cmd_slot, num_command_slots - 1);
+	sema_init(&dd->port->cmd_slot, num_command_slots - 1 - dd->unal_qdepth);
+	sema_init(&dd->port->cmd_slot_unal, dd->unal_qdepth);
 
 	/* Spinlock to prevent concurrent issue */
 	for (i = 0; i < MTIP_MAX_SLOT_GROUPS; i++)
@@ -3836,7 +3864,7 @@ static void mtip_make_request(struct request_queue *queue, struct bio *bio)
 	struct scatterlist *sg;
 	struct bio_vec *bvec;
 	int nents = 0;
-	int tag = 0;
+	int tag = 0, unaligned = 0;
 
 	if (unlikely(dd->dd_flag & MTIP_DDF_STOP_IO)) {
 		if (unlikely(test_bit(MTIP_DDF_REMOVE_PENDING_BIT,
@@ -3872,7 +3900,15 @@ static void mtip_make_request(struct request_queue *queue, struct bio *bio)
 		return;
 	}
 
-	sg = mtip_hw_get_scatterlist(dd, &tag);
+	if (bio_data_dir(bio) == WRITE && bio_sectors(bio) <= 64 &&
+							dd->unal_qdepth) {
+		if (bio->bi_sector % 8 != 0) /* Unaligned on 4k boundaries */
+			unaligned = 1;
+		else if (bio_sectors(bio) % 8 != 0) /* Aligned but not 4k/8k */
+			unaligned = 1;
+	}
+
+	sg = mtip_hw_get_scatterlist(dd, &tag, unaligned);
 	if (likely(sg != NULL)) {
 		blk_queue_bounce(queue, &bio);
 
@@ -3880,7 +3916,7 @@ static void mtip_make_request(struct request_queue *queue, struct bio *bio)
 			dev_warn(&dd->pdev->dev,
 				"Maximum number of SGL entries exceeded\n");
 			bio_io_error(bio);
-			mtip_hw_release_scatterlist(dd, tag);
+			mtip_hw_release_scatterlist(dd, tag, unaligned);
 			return;
 		}
 
@@ -3900,7 +3936,8 @@ static void mtip_make_request(struct request_queue *queue, struct bio *bio)
 				tag,
 				bio_endio,
 				bio,
-				bio_data_dir(bio));
+				bio_data_dir(bio),
+				unaligned);
 	} else
 		bio_io_error(bio);
 }
@@ -4156,26 +4193,24 @@ static int mtip_block_remove(struct driver_data *dd)
  */
 static int mtip_block_shutdown(struct driver_data *dd)
 {
-	dev_info(&dd->pdev->dev,
-		"Shutting down %s ...\n", dd->disk->disk_name);
-
 	/* Delete our gendisk structure, and cleanup the blk queue. */
 	if (dd->disk) {
-		if (dd->disk->queue)
+		dev_info(&dd->pdev->dev,
+			"Shutting down %s ...\n", dd->disk->disk_name);
+
+		if (dd->disk->queue) {
 			del_gendisk(dd->disk);
-		else
+			blk_cleanup_queue(dd->queue);
+		} else
 			put_disk(dd->disk);
+		dd->disk  = NULL;
+		dd->queue = NULL;
 	}
 
-
 	spin_lock(&rssd_index_lock);
 	ida_remove(&rssd_index_ida, dd->index);
 	spin_unlock(&rssd_index_lock);
 
-	blk_cleanup_queue(dd->queue);
-	dd->disk  = NULL;
-	dd->queue = NULL;
-
 	mtip_hw_shutdown(dd);
 	return 0;
 }

drivers/block/mtip32xx/mtip32xx.h

@@ -52,6 +52,9 @@
 #define MTIP_FTL_REBUILD_MAGIC		0xED51
 #define MTIP_FTL_REBUILD_TIMEOUT_MS	2400000
 
+/* unaligned IO handling */
+#define MTIP_MAX_UNALIGNED_SLOTS	8
+
 /* Macro to extract the tag bit number from a tag value. */
 #define MTIP_TAG_BIT(tag)	(tag & 0x1F)
 
@@ -333,6 +336,8 @@ struct mtip_cmd {
 
 	int scatter_ents; /* Number of scatter list entries used */
 
+	int unaligned; /* command is unaligned on 4k boundary */
+
 	struct scatterlist sg[MTIP_MAX_SG]; /* Scatter list entries */
 
 	int retries; /* The number of retries left for this command. */
@@ -452,6 +457,10 @@ struct mtip_port {
 	 * command slots available.
 	 */
 	struct semaphore cmd_slot;
+
+	/* Semaphore to control queue depth of unaligned IOs */
+	struct semaphore cmd_slot_unal;
+
 	/* Spinlock for working around command-issue bug. */
 	spinlock_t cmd_issue_lock[MTIP_MAX_SLOT_GROUPS];
 };
@@ -502,6 +511,8 @@ struct driver_data {
 
 	int isr_binding;
 
+	int unal_qdepth; /* qdepth of unaligned IO queue */
+
 	struct list_head online_list; /* linkage for online list */
 
 	struct list_head remove_list; /* linkage for removing list */

drivers/md/Kconfig

@@ -174,6 +174,8 @@ config MD_FAULTY
 
 	  In unsure, say N.
 
+source "drivers/md/bcache/Kconfig"
+
 config BLK_DEV_DM
 	tristate "Device mapper support"
 	---help---

drivers/md/Makefile

@@ -29,6 +29,7 @@ obj-$(CONFIG_MD_RAID10)		+= raid10.o
 obj-$(CONFIG_MD_RAID456)	+= raid456.o
 obj-$(CONFIG_MD_MULTIPATH)	+= multipath.o
 obj-$(CONFIG_MD_FAULTY)		+= faulty.o
+obj-$(CONFIG_BCACHE)		+= bcache/
 obj-$(CONFIG_BLK_DEV_MD)	+= md-mod.o
 obj-$(CONFIG_BLK_DEV_DM)	+= dm-mod.o
 obj-$(CONFIG_DM_BUFIO)		+= dm-bufio.o

drivers/md/bcache/Kconfig

+
+config BCACHE
+	tristate "Block device as cache"
+	select CLOSURES
+	---help---
+	Allows a block device to be used as cache for other devices; uses
+	a btree for indexing and the layout is optimized for SSDs.
+
+	See Documentation/bcache.txt for details.
+
+config BCACHE_DEBUG
+	bool "Bcache debugging"
+	depends on BCACHE
+	---help---
+	Don't select this option unless you're a developer
+
+	Enables extra debugging tools (primarily a fuzz tester)
+
+config BCACHE_EDEBUG
+	bool "Extended runtime checks"
+	depends on BCACHE
+	---help---
+	Don't select this option unless you're a developer
+
+	Enables extra runtime checks which significantly affect performance
+
+config BCACHE_CLOSURES_DEBUG
+	bool "Debug closures"
+	depends on BCACHE
+	select DEBUG_FS
+	---help---
+	Keeps all active closures in a linked list and provides a debugfs
+	interface to list them, which makes it possible to see asynchronous
+	operations that get stuck.
+
+# cgroup code needs to be updated:
+#
+#config CGROUP_BCACHE
+#	bool "Cgroup controls for bcache"
+#	depends on BCACHE && BLK_CGROUP
+#	---help---
+#	TODO

drivers/md/bcache/Makefile

+
+obj-$(CONFIG_BCACHE)	+= bcache.o
+
+bcache-y		:= alloc.o btree.o bset.o io.o journal.o writeback.o\
+	movinggc.o request.o super.o sysfs.o debug.o util.o trace.o stats.o closure.o
+
+CFLAGS_request.o	+= -Iblock

drivers/md/bcache/debug.h

+#ifndef _BCACHE_DEBUG_H
+#define _BCACHE_DEBUG_H
+
+/* Btree/bkey debug printing */
+
+#define KEYHACK_SIZE 80
+struct keyprint_hack {
+	char s[KEYHACK_SIZE];
+};
+
+struct keyprint_hack bch_pkey(const struct bkey *k);
+struct keyprint_hack bch_pbtree(const struct btree *b);
+#define pkey(k)		(&bch_pkey(k).s[0])
+#define pbtree(b)	(&bch_pbtree(b).s[0])
+
+#ifdef CONFIG_BCACHE_EDEBUG
+
+unsigned bch_count_data(struct btree *);
+void bch_check_key_order_msg(struct btree *, struct bset *, const char *, ...);
+void bch_check_keys(struct btree *, const char *, ...);
+
+#define bch_check_key_order(b, i)			\
+	bch_check_key_order_msg(b, i, "keys out of order")
+#define EBUG_ON(cond)		BUG_ON(cond)
+
+#else /* EDEBUG */
+
+#define bch_count_data(b)				0
+#define bch_check_key_order(b, i)			do {} while (0)
+#define bch_check_key_order_msg(b, i, ...)		do {} while (0)
+#define bch_check_keys(b, ...)				do {} while (0)
+#define EBUG_ON(cond)					do {} while (0)
+
+#endif
+
+#ifdef CONFIG_BCACHE_DEBUG
+
+void bch_btree_verify(struct btree *, struct bset *);
+void bch_data_verify(struct search *);
+
+#else /* DEBUG */
+
+static inline void bch_btree_verify(struct btree *b, struct bset *i) {}
+static inline void bch_data_verify(struct search *s) {};
+
+#endif
+
+#ifdef CONFIG_DEBUG_FS
+void bch_debug_init_cache_set(struct cache_set *);
+#else
+static inline void bch_debug_init_cache_set(struct cache_set *c) {}
+#endif
+
+#endif

drivers/md/bcache/journal.h

+#ifndef _BCACHE_JOURNAL_H
+#define _BCACHE_JOURNAL_H
+
+/*
+ * THE JOURNAL:
+ *
+ * The journal is treated as a circular buffer of buckets - a journal entry
+ * never spans two buckets. This means (not implemented yet) we can resize the
+ * journal at runtime, and will be needed for bcache on raw flash support.
+ *
+ * Journal entries contain a list of keys, ordered by the time they were
+ * inserted; thus journal replay just has to reinsert the keys.
+ *
+ * We also keep some things in the journal header that are logically part of the
+ * superblock - all the things that are frequently updated. This is for future
+ * bcache on raw flash support; the superblock (which will become another
+ * journal) can't be moved or wear leveled, so it contains just enough
+ * information to find the main journal, and the superblock only has to be
+ * rewritten when we want to move/wear level the main journal.
+ *
+ * Currently, we don't journal BTREE_REPLACE operations - this will hopefully be
+ * fixed eventually. This isn't a bug - BTREE_REPLACE is used for insertions
+ * from cache misses, which don't have to be journaled, and for writeback and
+ * moving gc we work around it by flushing the btree to disk before updating the
+ * gc information. But it is a potential issue with incremental garbage
+ * collection, and it's fragile.
+ *
+ * OPEN JOURNAL ENTRIES:
+ *
+ * Each journal entry contains, in the header, the sequence number of the last
+ * journal entry still open - i.e. that has keys that haven't been flushed to
+ * disk in the btree.
+ *
+ * We track this by maintaining a refcount for every open journal entry, in a
+ * fifo; each entry in the fifo corresponds to a particular journal
+ * entry/sequence number. When the refcount at the tail of the fifo goes to
+ * zero, we pop it off - thus, the size of the fifo tells us the number of open
+ * journal entries
+ *
+ * We take a refcount on a journal entry when we add some keys to a journal
+ * entry that we're going to insert (held by struct btree_op), and then when we
+ * insert those keys into the btree the btree write we're setting up takes a
+ * copy of that refcount (held by struct btree_write). That refcount is dropped
+ * when the btree write completes.
+ *
+ * A struct btree_write can only hold a refcount on a single journal entry, but
+ * might contain keys for many journal entries - we handle this by making sure
+ * it always has a refcount on the _oldest_ journal entry of all the journal
+ * entries it has keys for.
+ *
+ * JOURNAL RECLAIM:
+ *
+ * As mentioned previously, our fifo of refcounts tells us the number of open
+ * journal entries; from that and the current journal sequence number we compute
+ * last_seq - the oldest journal entry we still need. We write last_seq in each
+ * journal entry, and we also have to keep track of where it exists on disk so
+ * we don't overwrite it when we loop around the journal.
+ *
+ * To do that we track, for each journal bucket, the sequence number of the
+ * newest journal entry it contains - if we don't need that journal entry we
+ * don't need anything in that bucket anymore. From that we track the last
+ * journal bucket we still need; all this is tracked in struct journal_device
+ * and updated by journal_reclaim().
+ *
+ * JOURNAL FILLING UP:
+ *
+ * There are two ways the journal could fill up; either we could run out of
+ * space to write to, or we could have too many open journal entries and run out
+ * of room in the fifo of refcounts. Since those refcounts are decremented
+ * without any locking we can't safely resize that fifo, so we handle it the
+ * same way.
+ *
+ * If the journal fills up, we start flushing dirty btree nodes until we can
+ * allocate space for a journal write again - preferentially flushing btree
+ * nodes that are pinning the oldest journal entries first.
+ */
+
+#define BCACHE_JSET_VERSION_UUIDv1	1
+/* Always latest UUID format */
+#define BCACHE_JSET_VERSION_UUID	1
+#define BCACHE_JSET_VERSION		1
+
+/*
+ * On disk format for a journal entry:
+ * seq is monotonically increasing; every journal entry has its own unique
+ * sequence number.
+ *
+ * last_seq is the oldest journal entry that still has keys the btree hasn't
+ * flushed to disk yet.
+ *
+ * version is for on disk format changes.
+ */
+struct jset {
+	uint64_t		csum;
+	uint64_t		magic;
+	uint64_t		seq;
+	uint32_t		version;
+	uint32_t		keys;
+
+	uint64_t		last_seq;
+
+	BKEY_PADDED(uuid_bucket);
+	BKEY_PADDED(btree_root);
+	uint16_t		btree_level;
+	uint16_t		pad[3];
+
+	uint64_t		prio_bucket[MAX_CACHES_PER_SET];
+
+	union {
+		struct bkey	start[0];
+		uint64_t	d[0];
+	};
+};
+
+/*
+ * Only used for holding the journal entries we read in btree_journal_read()
+ * during cache_registration
+ */
+struct journal_replay {
+	struct list_head	list;
+	atomic_t		*pin;
+	struct jset		j;
+};
+
+/*
+ * We put two of these in struct journal; we used them for writes to the
+ * journal that are being staged or in flight.
+ */
+struct journal_write {
+	struct jset		*data;
+#define JSET_BITS		3
+
+	struct cache_set	*c;
+	struct closure_waitlist	wait;
+	bool			need_write;
+};
+
+/* Embedded in struct cache_set */
+struct journal {
+	spinlock_t		lock;
+	/* used when waiting because the journal was full */
+	struct closure_waitlist	wait;
+	struct closure_with_timer io;
+
+	/* Number of blocks free in the bucket(s) we're currently writing to */
+	unsigned		blocks_free;
+	uint64_t		seq;
+	DECLARE_FIFO(atomic_t, pin);
+
+	BKEY_PADDED(key);
+
+	struct journal_write	w[2], *cur;
+};
+
+/*
+ * Embedded in struct cache. First three fields refer to the array of journal
+ * buckets, in cache_sb.
+ */
+struct journal_device {
+	/*
+	 * For each journal bucket, contains the max sequence number of the
+	 * journal writes it contains - so we know when a bucket can be reused.
+	 */
+	uint64_t		seq[SB_JOURNAL_BUCKETS];
+
+	/* Journal bucket we're currently writing to */
+	unsigned		cur_idx;
+
+	/* Last journal bucket that still contains an open journal entry */
+	unsigned		last_idx;
+
+	/* Next journal bucket to be discarded */
+	unsigned		discard_idx;
+
+#define DISCARD_READY		0
+#define DISCARD_IN_FLIGHT	1
+#define DISCARD_DONE		2
+	/* 1 - discard in flight, -1 - discard completed */
+	atomic_t		discard_in_flight;
+
+	struct work_struct	discard_work;
+	struct bio		discard_bio;
+	struct bio_vec		discard_bv;
+
+	/* Bio for journal reads/writes to this device */
+	struct bio		bio;
+	struct bio_vec		bv[8];
+};
+
+#define journal_pin_cmp(c, l, r)				\
+	(fifo_idx(&(c)->journal.pin, (l)->journal) >		\
+	 fifo_idx(&(c)->journal.pin, (r)->journal))
+
+#define JOURNAL_PIN	20000
+
+#define journal_full(j)						\
+	(!(j)->blocks_free || fifo_free(&(j)->pin) <= 1)
+
+struct closure;
+struct cache_set;
+struct btree_op;
+
+void bch_journal(struct closure *);
+void bch_journal_next(struct journal *);
+void bch_journal_mark(struct cache_set *, struct list_head *);
+void bch_journal_meta(struct cache_set *, struct closure *);
+int bch_journal_read(struct cache_set *, struct list_head *,
+			struct btree_op *);
+int bch_journal_replay(struct cache_set *, struct list_head *,
+			  struct btree_op *);
+
+void bch_journal_free(struct cache_set *);
+int bch_journal_alloc(struct cache_set *);
+
+#endif /* _BCACHE_JOURNAL_H */

include/linux/cgroup_subsys.h

@@ -78,3 +78,9 @@ SUBSYS(hugetlb)
 #endif
 
 /* */
+
+#ifdef CONFIG_CGROUP_BCACHE
+SUBSYS(bcache)
+#endif
+
+/* */

include/linux/lru_cache.h

@@ -256,6 +256,7 @@ extern void lc_destroy(struct lru_cache *lc);
 extern void lc_set(struct lru_cache *lc, unsigned int enr, int index);
 extern void lc_del(struct lru_cache *lc, struct lc_element *element);
 
+extern struct lc_element *lc_get_cumulative(struct lru_cache *lc, unsigned int enr);
 extern struct lc_element *lc_try_get(struct lru_cache *lc, unsigned int enr);
 extern struct lc_element *lc_find(struct lru_cache *lc, unsigned int enr);
 extern struct lc_element *lc_get(struct lru_cache *lc, unsigned int enr);