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.

Documentation/bcache.txt

+Say you've got a big slow raid 6, and an X-25E or three. Wouldn't it be
+nice if you could use them as cache... Hence bcache.
+
+Wiki and git repositories are at:
+  http://bcache.evilpiepirate.org
+  http://evilpiepirate.org/git/linux-bcache.git
+  http://evilpiepirate.org/git/bcache-tools.git
+
+It's designed around the performance characteristics of SSDs - it only allocates
+in erase block sized buckets, and it uses a hybrid btree/log to track cached
+extants (which can be anywhere from a single sector to the bucket size). It's
+designed to avoid random writes at all costs; it fills up an erase block
+sequentially, then issues a discard before reusing it.
+
+Both writethrough and writeback caching are supported. Writeback defaults to
+off, but can be switched on and off arbitrarily at runtime. Bcache goes to
+great lengths to protect your data - it reliably handles unclean shutdown. (It
+doesn't even have a notion of a clean shutdown; bcache simply doesn't return
+writes as completed until they're on stable storage).
+
+Writeback caching can use most of the cache for buffering writes - writing
+dirty data to the backing device is always done sequentially, scanning from the
+start to the end of the index.
+
+Since random IO is what SSDs excel at, there generally won't be much benefit
+to caching large sequential IO. Bcache detects sequential IO and skips it;
+it also keeps a rolling average of the IO sizes per task, and as long as the
+average is above the cutoff it will skip all IO from that task - instead of
+caching the first 512k after every seek. Backups and large file copies should
+thus entirely bypass the cache.
+
+In the event of a data IO error on the flash it will try to recover by reading
+from disk or invalidating cache entries.  For unrecoverable errors (meta data
+or dirty data), caching is automatically disabled; if dirty data was present
+in the cache it first disables writeback caching and waits for all dirty data
+to be flushed.
+
+Getting started:
+You'll need make-bcache from the bcache-tools repository. Both the cache device
+and backing device must be formatted before use.
+  make-bcache -B /dev/sdb
+  make-bcache -C /dev/sdc
+
+make-bcache has the ability to format multiple devices at the same time - if
+you format your backing devices and cache device at the same time, you won't
+have to manually attach:
+  make-bcache -B /dev/sda /dev/sdb -C /dev/sdc
+
+To make bcache devices known to the kernel, echo them to /sys/fs/bcache/register:
+
+  echo /dev/sdb > /sys/fs/bcache/register
+  echo /dev/sdc > /sys/fs/bcache/register
+
+To register your bcache devices automatically, you could add something like
+this to an init script:
+
+  echo /dev/sd* > /sys/fs/bcache/register_quiet
+
+It'll look for bcache superblocks and ignore everything that doesn't have one.
+
+Registering the backing device makes the bcache show up in /dev; you can now
+format it and use it as normal. But the first time using a new bcache device,
+it'll be running in passthrough mode until you attach it to a cache. See the
+section on attaching.
+
+The devices show up at /dev/bcacheN, and can be controlled via sysfs from
+/sys/block/bcacheN/bcache:
+
+  mkfs.ext4 /dev/bcache0
+  mount /dev/bcache0 /mnt
+
+Cache devices are managed as sets; multiple caches per set isn't supported yet
+but will allow for mirroring of metadata and dirty data in the future. Your new
+cache set shows up as /sys/fs/bcache/<UUID>
+
+ATTACHING:
+
+After your cache device and backing device are registered, the backing device
+must be attached to your cache set to enable caching. Attaching a backing
+device to a cache set is done thusly, with the UUID of the cache set in
+/sys/fs/bcache:
+
+  echo <UUID> > /sys/block/bcache0/bcache/attach
+
+This only has to be done once. The next time you reboot, just reregister all
+your bcache devices. If a backing device has data in a cache somewhere, the
+/dev/bcache# device won't be created until the cache shows up - particularly
+important if you have writeback caching turned on.
+
+If you're booting up and your cache device is gone and never coming back, you
+can force run the backing device:
+
+  echo 1 > /sys/block/sdb/bcache/running
+
+(You need to use /sys/block/sdb (or whatever your backing device is called), not
+/sys/block/bcache0, because bcache0 doesn't exist yet. If you're using a
+partition, the bcache directory would be at /sys/block/sdb/sdb2/bcache)
+
+The backing device will still use that cache set if it shows up in the future,
+but all the cached data will be invalidated. If there was dirty data in the
+cache, don't expect the filesystem to be recoverable - you will have massive
+filesystem corruption, though ext4's fsck does work miracles.
+
+ERROR HANDLING:
+
+Bcache tries to transparently handle IO errors to/from the cache device without
+affecting normal operation; if it sees too many errors (the threshold is
+configurable, and defaults to 0) it shuts down the cache device and switches all
+the backing devices to passthrough mode.
+
+ - For reads from the cache, if they error we just retry the read from the
+   backing device.
+
+ - For writethrough writes, if the write to the cache errors we just switch to
+   invalidating the data at that lba in the cache (i.e. the same thing we do for
+   a write that bypasses the cache)
+
+ - For writeback writes, we currently pass that error back up to the
+   filesystem/userspace. This could be improved - we could retry it as a write
+   that skips the cache so we don't have to error the write.
+
+ - When we detach, we first try to flush any dirty data (if we were running in
+   writeback mode). It currently doesn't do anything intelligent if it fails to
+   read some of the dirty data, though.
+
+TROUBLESHOOTING PERFORMANCE:
+
+Bcache has a bunch of config options and tunables. The defaults are intended to
+be reasonable for typical desktop and server workloads, but they're not what you
+want for getting the best possible numbers when benchmarking.
+
+ - Bad write performance
+
+   If write performance is not what you expected, you probably wanted to be
+   running in writeback mode, which isn't the default (not due to a lack of
+   maturity, but simply because in writeback mode you'll lose data if something
+   happens to your SSD)
+
+   # echo writeback > /sys/block/bcache0/cache_mode
+
+ - Bad performance, or traffic not going to the SSD that you'd expect
+
+   By default, bcache doesn't cache everything. It tries to skip sequential IO -
+   because you really want to be caching the random IO, and if you copy a 10
+   gigabyte file you probably don't want that pushing 10 gigabytes of randomly
+   accessed data out of your cache.
+
+   But if you want to benchmark reads from cache, and you start out with fio
+   writing an 8 gigabyte test file - so you want to disable that.
+
+   # echo 0 > /sys/block/bcache0/bcache/sequential_cutoff
+
+   To set it back to the default (4 mb), do
+
+   # echo 4M > /sys/block/bcache0/bcache/sequential_cutoff
+
+ - Traffic's still going to the spindle/still getting cache misses
+
+   In the real world, SSDs don't always keep up with disks - particularly with
+   slower SSDs, many disks being cached by one SSD, or mostly sequential IO. So
+   you want to avoid being bottlenecked by the SSD and having it slow everything
+   down.
+
+   To avoid that bcache tracks latency to the cache device, and gradually
+   throttles traffic if the latency exceeds a threshold (it does this by
+   cranking down the sequential bypass).
+
+   You can disable this if you need to by setting the thresholds to 0:
+
+   # echo 0 > /sys/fs/bcache/<cache set>/congested_read_threshold_us
+   # echo 0 > /sys/fs/bcache/<cache set>/congested_write_threshold_us
+
+   The default is 2000 us (2 milliseconds) for reads, and 20000 for writes.
+
+ - Still getting cache misses, of the same data
+
+   One last issue that sometimes trips people up is actually an old bug, due to
+   the way cache coherency is handled for cache misses. If a btree node is full,
+   a cache miss won't be able to insert a key for the new data and the data
+   won't be written to the cache.
+
+   In practice this isn't an issue because as soon as a write comes along it'll
+   cause the btree node to be split, and you need almost no write traffic for
+   this to not show up enough to be noticable (especially since bcache's btree
+   nodes are huge and index large regions of the device). But when you're
+   benchmarking, if you're trying to warm the cache by reading a bunch of data
+   and there's no other traffic - that can be a problem.
+
+   Solution: warm the cache by doing writes, or use the testing branch (there's
+   a fix for the issue there).
+
+SYSFS - BACKING DEVICE:
+
+attach
+  Echo the UUID of a cache set to this file to enable caching.
+
+cache_mode
+  Can be one of either writethrough, writeback, writearound or none.
+
+clear_stats
+  Writing to this file resets the running total stats (not the day/hour/5 minute
+  decaying versions).
+
+detach
+  Write to this file to detach from a cache set. If there is dirty data in the
+  cache, it will be flushed first.
+
+dirty_data
+  Amount of dirty data for this backing device in the cache. Continuously
+  updated unlike the cache set's version, but may be slightly off.
+
+label
+  Name of underlying device.
+
+readahead
+  Size of readahead that should be performed.  Defaults to 0.  If set to e.g.
+  1M, it will round cache miss reads up to that size, but without overlapping
+  existing cache entries.
+
+running
+  1 if bcache is running (i.e. whether the /dev/bcache device exists, whether
+  it's in passthrough mode or caching).
+
+sequential_cutoff
+  A sequential IO will bypass the cache once it passes this threshhold; the
+  most recent 128 IOs are tracked so sequential IO can be detected even when
+  it isn't all done at once.
+
+sequential_merge
+  If non zero, bcache keeps a list of the last 128 requests submitted to compare
+  against all new requests to determine which new requests are sequential
+  continuations of previous requests for the purpose of determining sequential
+  cutoff. This is necessary if the sequential cutoff value is greater than the
+  maximum acceptable sequential size for any single request. 
+
+state
+  The backing device can be in one of four different states:
+
+  no cache: Has never been attached to a cache set.
+
+  clean: Part of a cache set, and there is no cached dirty data.
+
+  dirty: Part of a cache set, and there is cached dirty data.
+
+  inconsistent: The backing device was forcibly run by the user when there was
+  dirty data cached but the cache set was unavailable; whatever data was on the
+  backing device has likely been corrupted.
+
+stop
+  Write to this file to shut down the bcache device and close the backing
+  device.
+
+writeback_delay
+  When dirty data is written to the cache and it previously did not contain
+  any, waits some number of seconds before initiating writeback. Defaults to
+  30.
+
+writeback_percent
+  If nonzero, bcache tries to keep around this percentage of the cache dirty by
+  throttling background writeback and using a PD controller to smoothly adjust
+  the rate.
+
+writeback_rate
+  Rate in sectors per second - if writeback_percent is nonzero, background
+  writeback is throttled to this rate. Continuously adjusted by bcache but may
+  also be set by the user.
+
+writeback_running
+  If off, writeback of dirty data will not take place at all. Dirty data will
+  still be added to the cache until it is mostly full; only meant for
+  benchmarking. Defaults to on.
+
+SYSFS - BACKING DEVICE STATS:
+
+There are directories with these numbers for a running total, as well as
+versions that decay over the past day, hour and 5 minutes; they're also
+aggregated in the cache set directory as well.
+
+bypassed
+  Amount of IO (both reads and writes) that has bypassed the cache
+
+cache_hits
+cache_misses
+cache_hit_ratio
+  Hits and misses are counted per individual IO as bcache sees them; a
+  partial hit is counted as a miss.
+
+cache_bypass_hits
+cache_bypass_misses
+  Hits and misses for IO that is intended to skip the cache are still counted,
+  but broken out here.
+
+cache_miss_collisions
+  Counts instances where data was going to be inserted into the cache from a
+  cache miss, but raced with a write and data was already present (usually 0
+  since the synchronization for cache misses was rewritten)
+
+cache_readaheads
+  Count of times readahead occured.
+
+SYSFS - CACHE SET:
+
+average_key_size
+  Average data per key in the btree.
+
+bdev<0..n>
+  Symlink to each of the attached backing devices.
+
+block_size
+  Block size of the cache devices.
+
+btree_cache_size
+  Amount of memory currently used by the btree cache
+
+bucket_size
+  Size of buckets
+
+cache<0..n>
+  Symlink to each of the cache devices comprising this cache set. 
+
+cache_available_percent
+  Percentage of cache device free.
+
+clear_stats
+  Clears the statistics associated with this cache
+
+dirty_data
+  Amount of dirty data is in the cache (updated when garbage collection runs).
+
+flash_vol_create
+  Echoing a size to this file (in human readable units, k/M/G) creates a thinly
+  provisioned volume backed by the cache set.
+
+io_error_halflife
+io_error_limit
+  These determines how many errors we accept before disabling the cache.
+  Each error is decayed by the half life (in # ios).  If the decaying count
+  reaches io_error_limit dirty data is written out and the cache is disabled.
+
+journal_delay_ms
+  Journal writes will delay for up to this many milliseconds, unless a cache
+  flush happens sooner. Defaults to 100.
+
+root_usage_percent
+  Percentage of the root btree node in use.  If this gets too high the node
+  will split, increasing the tree depth.
+
+stop
+  Write to this file to shut down the cache set - waits until all attached
+  backing devices have been shut down.
+
+tree_depth
+  Depth of the btree (A single node btree has depth 0).
+
+unregister
+  Detaches all backing devices and closes the cache devices; if dirty data is
+  present it will disable writeback caching and wait for it to be flushed.
+
+SYSFS - CACHE SET INTERNAL:
+
+This directory also exposes timings for a number of internal operations, with
+separate files for average duration, average frequency, last occurence and max
+duration: garbage collection, btree read, btree node sorts and btree splits.
+
+active_journal_entries
+  Number of journal entries that are newer than the index.
+
+btree_nodes
+  Total nodes in the btree.
+
+btree_used_percent
+  Average fraction of btree in use.
+
+bset_tree_stats
+  Statistics about the auxiliary search trees
+
+btree_cache_max_chain
+  Longest chain in the btree node cache's hash table
+
+cache_read_races
+  Counts instances where while data was being read from the cache, the bucket
+  was reused and invalidated - i.e. where the pointer was stale after the read
+  completed. When this occurs the data is reread from the backing device.
+
+trigger_gc
+  Writing to this file forces garbage collection to run.
+
+SYSFS - CACHE DEVICE:
+
+block_size
+  Minimum granularity of writes - should match hardware sector size.
+
+btree_written
+  Sum of all btree writes, in (kilo/mega/giga) bytes
+
+bucket_size
+  Size of buckets
+
+cache_replacement_policy
+  One of either lru, fifo or random.
+
+discard
+  Boolean; if on a discard/TRIM will be issued to each bucket before it is
+  reused. Defaults to off, since SATA TRIM is an unqueued command (and thus
+  slow).
+
+freelist_percent
+  Size of the freelist as a percentage of nbuckets. Can be written to to
+  increase the number of buckets kept on the freelist, which lets you
+  artificially reduce the size of the cache at runtime. Mostly for testing
+  purposes (i.e. testing how different size caches affect your hit rate), but
+  since buckets are discarded when they move on to the freelist will also make
+  the SSD's garbage collection easier by effectively giving it more reserved
+  space.
+
+io_errors
+  Number of errors that have occured, decayed by io_error_halflife.
+
+metadata_written
+  Sum of all non data writes (btree writes and all other metadata).
+
+nbuckets
+  Total buckets in this cache
+
+priority_stats
+  Statistics about how recently data in the cache has been accessed.  This can
+  reveal your working set size.
+
+written
+  Sum of all data that has been written to the cache; comparison with
+  btree_written gives the amount of write inflation in bcache.

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_actlog.c

@@ -104,7 +104,6 @@ struct update_al_work {
 	int err;
 };
 
-static int al_write_transaction(struct drbd_conf *mdev);
 
 void *drbd_md_get_buffer(struct drbd_conf *mdev)
 {
@@ -168,7 +167,11 @@ static int _drbd_md_sync_page_io(struct drbd_conf *mdev,
 	bio->bi_end_io = drbd_md_io_complete;
 	bio->bi_rw = rw;
 
-	if (!get_ldev_if_state(mdev, D_ATTACHING)) {  /* Corresponding put_ldev in drbd_md_io_complete() */
+	if (!(rw & WRITE) && mdev->state.disk == D_DISKLESS && mdev->ldev == NULL)
+		/* special case, drbd_md_read() during drbd_adm_attach(): no get_ldev */
+		;
+	else if (!get_ldev_if_state(mdev, D_ATTACHING)) {
+		/* Corresponding put_ldev in drbd_md_io_complete() */
 		dev_err(DEV, "ASSERT FAILED: get_ldev_if_state() == 1 in _drbd_md_sync_page_io()\n");
 		err = -ENODEV;
 		goto out;
@@ -199,9 +202,10 @@ int drbd_md_sync_page_io(struct drbd_conf *mdev, struct drbd_backing_dev *bdev,
 
 	BUG_ON(!bdev->md_bdev);
 
-	dev_dbg(DEV, "meta_data io: %s [%d]:%s(,%llus,%s)\n",
+	dev_dbg(DEV, "meta_data io: %s [%d]:%s(,%llus,%s) %pS\n",
 	     current->comm, current->pid, __func__,
-	     (unsigned long long)sector, (rw & WRITE) ? "WRITE" : "READ");
+	     (unsigned long long)sector, (rw & WRITE) ? "WRITE" : "READ",
+	     (void*)_RET_IP_ );
 
 	if (sector < drbd_md_first_sector(bdev) ||
 	    sector + 7 > drbd_md_last_sector(bdev))
@@ -209,7 +213,8 @@ int drbd_md_sync_page_io(struct drbd_conf *mdev, struct drbd_backing_dev *bdev,
 		     current->comm, current->pid, __func__,
 		     (unsigned long long)sector, (rw & WRITE) ? "WRITE" : "READ");
 
-	err = _drbd_md_sync_page_io(mdev, bdev, iop, sector, rw, MD_BLOCK_SIZE);
+	/* we do all our meta data IO in aligned 4k blocks. */
+	err = _drbd_md_sync_page_io(mdev, bdev, iop, sector, rw, 4096);
 	if (err) {
 		dev_err(DEV, "drbd_md_sync_page_io(,%llus,%s) failed with error %d\n",
 		    (unsigned long long)sector, (rw & WRITE) ? "WRITE" : "READ", err);
@@ -217,44 +222,99 @@ int drbd_md_sync_page_io(struct drbd_conf *mdev, struct drbd_backing_dev *bdev,
 	return err;
 }
 
-static struct lc_element *_al_get(struct drbd_conf *mdev, unsigned int enr)
+static struct bm_extent *find_active_resync_extent(struct drbd_conf *mdev, unsigned int enr)
 {
-	struct lc_element *al_ext;
 	struct lc_element *tmp;
-	int wake;
-
-	spin_lock_irq(&mdev->al_lock);
 	tmp = lc_find(mdev->resync, enr/AL_EXT_PER_BM_SECT);
 	if (unlikely(tmp != NULL)) {
 		struct bm_extent  *bm_ext = lc_entry(tmp, struct bm_extent, lce);
-		if (test_bit(BME_NO_WRITES, &bm_ext->flags)) {
-			wake = !test_and_set_bit(BME_PRIORITY, &bm_ext->flags);
-			spin_unlock_irq(&mdev->al_lock);
-			if (wake)
-				wake_up(&mdev->al_wait);
-			return NULL;
-		}
+		if (test_bit(BME_NO_WRITES, &bm_ext->flags))
+			return bm_ext;
+	}
+	return NULL;
+}
+
+static struct lc_element *_al_get(struct drbd_conf *mdev, unsigned int enr, bool nonblock)
+{
+	struct lc_element *al_ext;
+	struct bm_extent *bm_ext;
+	int wake;
+
+	spin_lock_irq(&mdev->al_lock);
+	bm_ext = find_active_resync_extent(mdev, enr);
+	if (bm_ext) {
+		wake = !test_and_set_bit(BME_PRIORITY, &bm_ext->flags);
+		spin_unlock_irq(&mdev->al_lock);
+		if (wake)
+			wake_up(&mdev->al_wait);
+		return NULL;
 	}
-	al_ext = lc_get(mdev->act_log, enr);
+	if (nonblock)
+		al_ext = lc_try_get(mdev->act_log, enr);
+	else
+		al_ext = lc_get(mdev->act_log, enr);
 	spin_unlock_irq(&mdev->al_lock);
 	return al_ext;
 }
 
-void drbd_al_begin_io(struct drbd_conf *mdev, struct drbd_interval *i)
+bool drbd_al_begin_io_fastpath(struct drbd_conf *mdev, struct drbd_interval *i)
 {
 	/* for bios crossing activity log extent boundaries,
 	 * we may need to activate two extents in one go */
 	unsigned first = i->sector >> (AL_EXTENT_SHIFT-9);
 	unsigned last = i->size == 0 ? first : (i->sector + (i->size >> 9) - 1) >> (AL_EXTENT_SHIFT-9);
-	unsigned enr;
-	bool locked = false;
 
+	D_ASSERT((unsigned)(last - first) <= 1);
+	D_ASSERT(atomic_read(&mdev->local_cnt) > 0);
+
+	/* FIXME figure out a fast path for bios crossing AL extent boundaries */
+	if (first != last)
+		return false;
+
+	return _al_get(mdev, first, true);
+}
+
+bool drbd_al_begin_io_prepare(struct drbd_conf *mdev, struct drbd_interval *i)
+{
+	/* for bios crossing activity log extent boundaries,
+	 * we may need to activate two extents in one go */
+	unsigned first = i->sector >> (AL_EXTENT_SHIFT-9);
+	unsigned last = i->size == 0 ? first : (i->sector + (i->size >> 9) - 1) >> (AL_EXTENT_SHIFT-9);
+	unsigned enr;
+	bool need_transaction = false;
 
 	D_ASSERT(first <= last);
 	D_ASSERT(atomic_read(&mdev->local_cnt) > 0);
 
-	for (enr = first; enr <= last; enr++)
-		wait_event(mdev->al_wait, _al_get(mdev, enr) != NULL);
+	for (enr = first; enr <= last; enr++) {
+		struct lc_element *al_ext;
+		wait_event(mdev->al_wait,
+				(al_ext = _al_get(mdev, enr, false)) != NULL);
+		if (al_ext->lc_number != enr)
+			need_transaction = true;
+	}
+	return need_transaction;
+}
+
+static int al_write_transaction(struct drbd_conf *mdev, bool delegate);
+
+/* When called through generic_make_request(), we must delegate
+ * activity log I/O to the worker thread: a further request
+ * submitted via generic_make_request() within the same task
+ * would be queued on current->bio_list, and would only start
+ * after this function returns (see generic_make_request()).
+ *
+ * However, if we *are* the worker, we must not delegate to ourselves.
+ */
+
+/*
+ * @delegate:   delegate activity log I/O to the worker thread
+ */
+void drbd_al_begin_io_commit(struct drbd_conf *mdev, bool delegate)
+{
+	bool locked = false;
+
+	BUG_ON(delegate && current == mdev->tconn->worker.task);
 
 	/* Serialize multiple transactions.
 	 * This uses test_and_set_bit, memory barrier is implicit.
@@ -264,13 +324,6 @@ void drbd_al_begin_io(struct drbd_conf *mdev, struct drbd_interval *i)
 			(locked = lc_try_lock_for_transaction(mdev->act_log)));
 
 	if (locked) {
-		/* drbd_al_write_transaction(mdev,al_ext,enr);
-		 * recurses into generic_make_request(), which
-		 * disallows recursion, bios being serialized on the
-		 * current->bio_tail list now.
-		 * we have to delegate updates to the activity log
-		 * to the worker thread. */
-
 		/* Double check: it may have been committed by someone else,
 		 * while we have been waiting for the lock. */
 		if (mdev->act_log->pending_changes) {
@@ -280,11 +333,8 @@ void drbd_al_begin_io(struct drbd_conf *mdev, struct drbd_interval *i)
 			write_al_updates = rcu_dereference(mdev->ldev->disk_conf)->al_updates;
 			rcu_read_unlock();
 
-			if (write_al_updates) {
-				al_write_transaction(mdev);
-				mdev->al_writ_cnt++;
-			}
-
+			if (write_al_updates)
+				al_write_transaction(mdev, delegate);
 			spin_lock_irq(&mdev->al_lock);
 			/* FIXME
 			if (err)
@@ -298,6 +348,66 @@ void drbd_al_begin_io(struct drbd_conf *mdev, struct drbd_interval *i)
 	}
 }
 
+/*
+ * @delegate:   delegate activity log I/O to the worker thread
+ */
+void drbd_al_begin_io(struct drbd_conf *mdev, struct drbd_interval *i, bool delegate)
+{
+	BUG_ON(delegate && current == mdev->tconn->worker.task);
+
+	if (drbd_al_begin_io_prepare(mdev, i))
+		drbd_al_begin_io_commit(mdev, delegate);
+}
+
+int drbd_al_begin_io_nonblock(struct drbd_conf *mdev, struct drbd_interval *i)
+{
+	struct lru_cache *al = mdev->act_log;
+	/* for bios crossing activity log extent boundaries,
+	 * we may need to activate two extents in one go */
+	unsigned first = i->sector >> (AL_EXTENT_SHIFT-9);
+	unsigned last = i->size == 0 ? first : (i->sector + (i->size >> 9) - 1) >> (AL_EXTENT_SHIFT-9);
+	unsigned nr_al_extents;
+	unsigned available_update_slots;
+	unsigned enr;
+
+	D_ASSERT(first <= last);
+
+	nr_al_extents = 1 + last - first; /* worst case: all touched extends are cold. */
+	available_update_slots = min(al->nr_elements - al->used,
+				al->max_pending_changes - al->pending_changes);
+
+	/* We want all necessary updates for a given request within the same transaction
+	 * We could first check how many updates are *actually* needed,
+	 * and use that instead of the worst-case nr_al_extents */
+	if (available_update_slots < nr_al_extents)
+		return -EWOULDBLOCK;
+
+	/* Is resync active in this area? */
+	for (enr = first; enr <= last; enr++) {
+		struct lc_element *tmp;
+		tmp = lc_find(mdev->resync, enr/AL_EXT_PER_BM_SECT);
+		if (unlikely(tmp != NULL)) {
+			struct bm_extent  *bm_ext = lc_entry(tmp, struct bm_extent, lce);
+			if (test_bit(BME_NO_WRITES, &bm_ext->flags)) {
+				if (!test_and_set_bit(BME_PRIORITY, &bm_ext->flags))
+					return -EBUSY;
+				return -EWOULDBLOCK;
+			}
+		}
+	}
+
+	/* Checkout the refcounts.
+	 * Given that we checked for available elements and update slots above,
+	 * this has to be successful. */
+	for (enr = first; enr <= last; enr++) {
+		struct lc_element *al_ext;
+		al_ext = lc_get_cumulative(mdev->act_log, enr);
+		if (!al_ext)
+			dev_info(DEV, "LOGIC BUG for enr=%u\n", enr);
+	}
+	return 0;
+}
+
 void drbd_al_complete_io(struct drbd_conf *mdev, struct drbd_interval *i)
 {
 	/* for bios crossing activity log extent boundaries,
@@ -350,6 +460,24 @@ static unsigned int rs_extent_to_bm_page(unsigned int rs_enr)
 		 (BM_EXT_SHIFT - BM_BLOCK_SHIFT));
 }
 
+static sector_t al_tr_number_to_on_disk_sector(struct drbd_conf *mdev)
+{
+	const unsigned int stripes = mdev->ldev->md.al_stripes;
+	const unsigned int stripe_size_4kB = mdev->ldev->md.al_stripe_size_4k;
+
+	/* transaction number, modulo on-disk ring buffer wrap around */
+	unsigned int t = mdev->al_tr_number % (mdev->ldev->md.al_size_4k);
+
+	/* ... to aligned 4k on disk block */
+	t = ((t % stripes) * stripe_size_4kB) + t/stripes;
+
+	/* ... to 512 byte sector in activity log */
+	t *= 8;
+
+	/* ... plus offset to the on disk position */
+	return mdev->ldev->md.md_offset + mdev->ldev->md.al_offset + t;
+}
+
 static int
 _al_write_transaction(struct drbd_conf *mdev)
 {
@@ -432,23 +560,27 @@ _al_write_transaction(struct drbd_conf *mdev)
 	if (mdev->al_tr_cycle >= mdev->act_log->nr_elements)
 		mdev->al_tr_cycle = 0;
 
-	sector =  mdev->ldev->md.md_offset
-		+ mdev->ldev->md.al_offset
-		+ mdev->al_tr_pos * (MD_BLOCK_SIZE>>9);
+	sector = al_tr_number_to_on_disk_sector(mdev);
 
 	crc = crc32c(0, buffer, 4096);
 	buffer->crc32c = cpu_to_be32(crc);
 
 	if (drbd_bm_write_hinted(mdev))
 		err = -EIO;
-		/* drbd_chk_io_error done already */
-	else if (drbd_md_sync_page_io(mdev, mdev->ldev, sector, WRITE)) {
-		err = -EIO;
-		drbd_chk_io_error(mdev, 1, DRBD_META_IO_ERROR);
-	} else {
-		/* advance ringbuffer position and transaction counter */
-		mdev->al_tr_pos = (mdev->al_tr_pos + 1) % (MD_AL_SECTORS*512/MD_BLOCK_SIZE);
-		mdev->al_tr_number++;
+	else {
+		bool write_al_updates;
+		rcu_read_lock();
+		write_al_updates = rcu_dereference(mdev->ldev->disk_conf)->al_updates;
+		rcu_read_unlock();
+		if (write_al_updates) {
+			if (drbd_md_sync_page_io(mdev, mdev->ldev, sector, WRITE)) {
+				err = -EIO;
+				drbd_chk_io_error(mdev, 1, DRBD_META_IO_ERROR);
+			} else {
+				mdev->al_tr_number++;
+				mdev->al_writ_cnt++;
+			}
+		}
 	}
 
 	drbd_md_put_buffer(mdev);
@@ -474,20 +606,18 @@ static int w_al_write_transaction(struct drbd_work *w, int unused)
 /* Calls from worker context (see w_restart_disk_io()) need to write the
    transaction directly. Others came through generic_make_request(),
    those need to delegate it to the worker. */
-static int al_write_transaction(struct drbd_conf *mdev)
+static int al_write_transaction(struct drbd_conf *mdev, bool delegate)
 {
-	struct update_al_work al_work;
-
-	if (current == mdev->tconn->worker.task)
+	if (delegate) {
+		struct update_al_work al_work;
+		init_completion(&al_work.event);
+		al_work.w.cb = w_al_write_transaction;
+		al_work.w.mdev = mdev;
+		drbd_queue_work_front(&mdev->tconn->sender_work, &al_work.w);
+		wait_for_completion(&al_work.event);
+		return al_work.err;
+	} else
 		return _al_write_transaction(mdev);
-
-	init_completion(&al_work.event);
-	al_work.w.cb = w_al_write_transaction;
-	al_work.w.mdev = mdev;
-	drbd_queue_work_front(&mdev->tconn->sender_work, &al_work.w);
-	wait_for_completion(&al_work.event);
-
-	return al_work.err;
 }
 
 static int _try_lc_del(struct drbd_conf *mdev, struct lc_element *al_ext)

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_int.h

@@ -753,13 +753,16 @@ struct drbd_md {
 	u32 flags;
 	u32 md_size_sect;
 
-	s32 al_offset;	/* signed relative sector offset to al area */
+	s32 al_offset;	/* signed relative sector offset to activity log */
 	s32 bm_offset;	/* signed relative sector offset to bitmap */
 
-	/* u32 al_nr_extents;	   important for restoring the AL
-	 * is stored into  ldev->dc.al_extents, which in turn
-	 * gets applied to act_log->nr_elements
-	 */
+	/* cached value of bdev->disk_conf->meta_dev_idx (see below) */
+	s32 meta_dev_idx;
+
+	/* see al_tr_number_to_on_disk_sector() */
+	u32 al_stripes;
+	u32 al_stripe_size_4k;
+	u32 al_size_4k; /* cached product of the above */
 };
 
 struct drbd_backing_dev {
@@ -891,6 +894,14 @@ struct drbd_tconn {			/* is a resource from the config file */
 	} send;
 };
 
+struct submit_worker {
+	struct workqueue_struct *wq;
+	struct work_struct worker;
+
+	spinlock_t lock;
+	struct list_head writes;
+};
+
 struct drbd_conf {
 	struct drbd_tconn *tconn;
 	int vnr;			/* volume number within the connection */
@@ -1009,7 +1020,6 @@ struct drbd_conf {
 	struct lru_cache *act_log;	/* activity log */
 	unsigned int al_tr_number;
 	int al_tr_cycle;
-	int al_tr_pos;   /* position of the next transaction in the journal */
 	wait_queue_head_t seq_wait;
 	atomic_t packet_seq;
 	unsigned int peer_seq;
@@ -1032,6 +1042,10 @@ struct drbd_conf {
 	atomic_t ap_in_flight; /* App sectors in flight (waiting for ack) */
 	unsigned int peer_max_bio_size;
 	unsigned int local_max_bio_size;
+
+	/* any requests that would block in drbd_make_request()
+	 * are deferred to this single-threaded work queue */
+	struct submit_worker submit;
 };
 
 static inline struct drbd_conf *minor_to_mdev(unsigned int minor)
@@ -1148,25 +1162,44 @@ extern int drbd_bitmap_io_from_worker(struct drbd_conf *mdev,
 		char *why, enum bm_flag flags);
 extern int drbd_bmio_set_n_write(struct drbd_conf *mdev);
 extern int drbd_bmio_clear_n_write(struct drbd_conf *mdev);
-extern void drbd_go_diskless(struct drbd_conf *mdev);
 extern void drbd_ldev_destroy(struct drbd_conf *mdev);
 
 /* Meta data layout
-   We reserve a 128MB Block (4k aligned)
-   * either at the end of the backing device
-   * or on a separate meta data device. */
+ *
+ * We currently have two possible layouts.
+ * Offsets in (512 byte) sectors.
+ * external:
+ *   |----------- md_size_sect ------------------|
+ *   [ 4k superblock ][ activity log ][  Bitmap  ]
+ *   | al_offset == 8 |
+ *   | bm_offset = al_offset + X      |
+ *  ==> bitmap sectors = md_size_sect - bm_offset
+ *
+ *  Variants:
+ *     old, indexed fixed size meta data:
+ *
+ * internal:
+ *            |----------- md_size_sect ------------------|
+ * [data.....][  Bitmap  ][ activity log ][ 4k superblock ][padding*]
+ *                        | al_offset < 0 |
+ *            | bm_offset = al_offset - Y |
+ *  ==> bitmap sectors = Y = al_offset - bm_offset
+ *
+ *  [padding*] are zero or up to 7 unused 512 Byte sectors to the
+ *  end of the device, so that the [4k superblock] will be 4k aligned.
+ *
+ *  The activity log consists of 4k transaction blocks,
+ *  which are written in a ring-buffer, or striped ring-buffer like fashion,
+ *  which are writtensize used to be fixed 32kB,
+ *  but is about to become configurable.
+ */
 
-/* The following numbers are sectors */
-/* Allows up to about 3.8TB, so if you want more,
+/* Our old fixed size meta data layout
+ * allows up to about 3.8TB, so if you want more,
  * you need to use the "flexible" meta data format. */
-#define MD_RESERVED_SECT (128LU << 11)  /* 128 MB, unit sectors */
-#define MD_AL_OFFSET	8    /* 8 Sectors after start of meta area */
-#define MD_AL_SECTORS	64   /* = 32 kB on disk activity log ring buffer */
-#define MD_BM_OFFSET (MD_AL_OFFSET + MD_AL_SECTORS)
-
-/* we do all meta data IO in 4k blocks */
-#define MD_BLOCK_SHIFT	12
-#define MD_BLOCK_SIZE	(1<<MD_BLOCK_SHIFT)
+#define MD_128MB_SECT (128LLU << 11)  /* 128 MB, unit sectors */
+#define MD_4kB_SECT	 8
+#define MD_32kB_SECT	64
 
 /* One activity log extent represents 4M of storage */
 #define AL_EXTENT_SHIFT 22
@@ -1256,7 +1289,6 @@ struct bm_extent {
 
 /* in one sector of the bitmap, we have this many activity_log extents. */
 #define AL_EXT_PER_BM_SECT  (1 << (BM_EXT_SHIFT - AL_EXTENT_SHIFT))
-#define BM_WORDS_PER_AL_EXT (1 << (AL_EXTENT_SHIFT-BM_BLOCK_SHIFT-LN2_BPL))
 
 #define BM_BLOCKS_PER_BM_EXT_B (BM_EXT_SHIFT - BM_BLOCK_SHIFT)
 #define BM_BLOCKS_PER_BM_EXT_MASK  ((1<<BM_BLOCKS_PER_BM_EXT_B) - 1)
@@ -1276,16 +1308,18 @@ struct bm_extent {
  */
 
 #define DRBD_MAX_SECTORS_32 (0xffffffffLU)
-#define DRBD_MAX_SECTORS_BM \
-	  ((MD_RESERVED_SECT - MD_BM_OFFSET) * (1LL<<(BM_EXT_SHIFT-9)))
-#if DRBD_MAX_SECTORS_BM < DRBD_MAX_SECTORS_32
-#define DRBD_MAX_SECTORS      DRBD_MAX_SECTORS_BM
-#define DRBD_MAX_SECTORS_FLEX DRBD_MAX_SECTORS_BM
-#elif !defined(CONFIG_LBDAF) && BITS_PER_LONG == 32
+/* we have a certain meta data variant that has a fixed on-disk size of 128
+ * MiB, of which 4k are our "superblock", and 32k are the fixed size activity
+ * log, leaving this many sectors for the bitmap.
+ */
+
+#define DRBD_MAX_SECTORS_FIXED_BM \
+	  ((MD_128MB_SECT - MD_32kB_SECT - MD_4kB_SECT) * (1LL<<(BM_EXT_SHIFT-9)))
+#if !defined(CONFIG_LBDAF) && BITS_PER_LONG == 32
 #define DRBD_MAX_SECTORS      DRBD_MAX_SECTORS_32
 #define DRBD_MAX_SECTORS_FLEX DRBD_MAX_SECTORS_32
 #else
-#define DRBD_MAX_SECTORS      DRBD_MAX_SECTORS_BM
+#define DRBD_MAX_SECTORS      DRBD_MAX_SECTORS_FIXED_BM
 /* 16 TB in units of sectors */
 #if BITS_PER_LONG == 32
 /* adjust by one page worth of bitmap,
@@ -1418,6 +1452,7 @@ extern void conn_free_crypto(struct drbd_tconn *tconn);
 extern int proc_details;
 
 /* drbd_req */
+extern void do_submit(struct work_struct *ws);
 extern void __drbd_make_request(struct drbd_conf *, struct bio *, unsigned long);
 extern void drbd_make_request(struct request_queue *q, struct bio *bio);
 extern int drbd_read_remote(struct drbd_conf *mdev, struct drbd_request *req);
@@ -1576,7 +1611,10 @@ extern const char *drbd_conn_str(enum drbd_conns s);
 extern const char *drbd_role_str(enum drbd_role s);
 
 /* drbd_actlog.c */
-extern void drbd_al_begin_io(struct drbd_conf *mdev, struct drbd_interval *i);
+extern int drbd_al_begin_io_nonblock(struct drbd_conf *mdev, struct drbd_interval *i);
+extern void drbd_al_begin_io_commit(struct drbd_conf *mdev, bool delegate);
+extern bool drbd_al_begin_io_fastpath(struct drbd_conf *mdev, struct drbd_interval *i);
+extern void drbd_al_begin_io(struct drbd_conf *mdev, struct drbd_interval *i, bool delegate);
 extern void drbd_al_complete_io(struct drbd_conf *mdev, struct drbd_interval *i);
 extern void drbd_rs_complete_io(struct drbd_conf *mdev, sector_t sector);
 extern int drbd_rs_begin_io(struct drbd_conf *mdev, sector_t sector);
@@ -1755,9 +1793,9 @@ static inline void drbd_chk_io_error_(struct drbd_conf *mdev,
  * BTW, for internal meta data, this happens to be the maximum capacity
  * we could agree upon with our peer node.
  */
-static inline sector_t _drbd_md_first_sector(int meta_dev_idx, struct drbd_backing_dev *bdev)
+static inline sector_t drbd_md_first_sector(struct drbd_backing_dev *bdev)
 {
-	switch (meta_dev_idx) {
+	switch (bdev->md.meta_dev_idx) {
 	case DRBD_MD_INDEX_INTERNAL:
 	case DRBD_MD_INDEX_FLEX_INT:
 		return bdev->md.md_offset + bdev->md.bm_offset;
@@ -1767,36 +1805,19 @@ static inline sector_t _drbd_md_first_sector(int meta_dev_idx, struct drbd_backi
 	}
 }
 
-static inline sector_t drbd_md_first_sector(struct drbd_backing_dev *bdev)
-{
-	int meta_dev_idx;
-
-	rcu_read_lock();
-	meta_dev_idx = rcu_dereference(bdev->disk_conf)->meta_dev_idx;
-	rcu_read_unlock();
-
-	return _drbd_md_first_sector(meta_dev_idx, bdev);
-}
-
 /**
  * drbd_md_last_sector() - Return the last sector number of the meta data area
  * @bdev:	Meta data block device.
  */
 static inline sector_t drbd_md_last_sector(struct drbd_backing_dev *bdev)
 {
-	int meta_dev_idx;
-
-	rcu_read_lock();
-	meta_dev_idx = rcu_dereference(bdev->disk_conf)->meta_dev_idx;
-	rcu_read_unlock();
-
-	switch (meta_dev_idx) {
+	switch (bdev->md.meta_dev_idx) {
 	case DRBD_MD_INDEX_INTERNAL:
 	case DRBD_MD_INDEX_FLEX_INT:
-		return bdev->md.md_offset + MD_AL_OFFSET - 1;
+		return bdev->md.md_offset + MD_4kB_SECT -1;
 	case DRBD_MD_INDEX_FLEX_EXT:
 	default:
-		return bdev->md.md_offset + bdev->md.md_size_sect;
+		return bdev->md.md_offset + bdev->md.md_size_sect -1;
 	}
 }
 
@@ -1818,18 +1839,13 @@ static inline sector_t drbd_get_capacity(struct block_device *bdev)
 static inline sector_t drbd_get_max_capacity(struct drbd_backing_dev *bdev)
 {
 	sector_t s;
-	int meta_dev_idx;
 
-	rcu_read_lock();
-	meta_dev_idx = rcu_dereference(bdev->disk_conf)->meta_dev_idx;
-	rcu_read_unlock();
-
-	switch (meta_dev_idx) {
+	switch (bdev->md.meta_dev_idx) {
 	case DRBD_MD_INDEX_INTERNAL:
 	case DRBD_MD_INDEX_FLEX_INT:
 		s = drbd_get_capacity(bdev->backing_bdev)
 			? min_t(sector_t, DRBD_MAX_SECTORS_FLEX,
-				_drbd_md_first_sector(meta_dev_idx, bdev))
+				drbd_md_first_sector(bdev))
 			: 0;
 		break;
 	case DRBD_MD_INDEX_FLEX_EXT:
@@ -1848,39 +1864,24 @@ static inline sector_t drbd_get_max_capacity(struct drbd_backing_dev *bdev)
 }
 
 /**
- * drbd_md_ss__() - Return the sector number of our meta data super block
- * @mdev:	DRBD device.
+ * drbd_md_ss() - Return the sector number of our meta data super block
  * @bdev:	Meta data block device.
  */
-static inline sector_t drbd_md_ss__(struct drbd_conf *mdev,
-				    struct drbd_backing_dev *bdev)
+static inline sector_t drbd_md_ss(struct drbd_backing_dev *bdev)
 {
-	int meta_dev_idx;
+	const int meta_dev_idx = bdev->md.meta_dev_idx;
 
-	rcu_read_lock();
-	meta_dev_idx = rcu_dereference(bdev->disk_conf)->meta_dev_idx;
-	rcu_read_unlock();
-
-	switch (meta_dev_idx) {
-	default: /* external, some index */
-		return MD_RESERVED_SECT * meta_dev_idx;
-	case DRBD_MD_INDEX_INTERNAL:
-		/* with drbd08, internal meta data is always "flexible" */
-	case DRBD_MD_INDEX_FLEX_INT:
-		/* sizeof(struct md_on_disk_07) == 4k
-		 * position: last 4k aligned block of 4k size */
-		if (!bdev->backing_bdev) {
-			if (__ratelimit(&drbd_ratelimit_state)) {
-				dev_err(DEV, "bdev->backing_bdev==NULL\n");
-				dump_stack();
-			}
-			return 0;
-		}
-		return (drbd_get_capacity(bdev->backing_bdev) & ~7ULL)
-			- MD_AL_OFFSET;
-	case DRBD_MD_INDEX_FLEX_EXT:
+	if (meta_dev_idx == DRBD_MD_INDEX_FLEX_EXT)
 		return 0;
-	}
+
+	/* Since drbd08, internal meta data is always "flexible".
+	 * position: last 4k aligned block of 4k size */
+	if (meta_dev_idx == DRBD_MD_INDEX_INTERNAL ||
+	    meta_dev_idx == DRBD_MD_INDEX_FLEX_INT)
+		return (drbd_get_capacity(bdev->backing_bdev) & ~7ULL) - 8;
+
+	/* external, some index; this is the old fixed size layout */
+	return MD_128MB_SECT * bdev->md.meta_dev_idx;
 }
 
 static inline void
@@ -2053,9 +2054,11 @@ static inline void put_ldev(struct drbd_conf *mdev)
 		if (mdev->state.disk == D_DISKLESS)
 			/* even internal references gone, safe to destroy */
 			drbd_ldev_destroy(mdev);
-		if (mdev->state.disk == D_FAILED)
+		if (mdev->state.disk == D_FAILED) {
 			/* all application IO references gone. */
-			drbd_go_diskless(mdev);
+			if (!test_and_set_bit(GO_DISKLESS, &mdev->flags))
+				drbd_queue_work(&mdev->tconn->sender_work, &mdev->go_diskless);
+		}
 		wake_up(&mdev->misc_wait);
 	}
 }

drivers/block/drbd/drbd_main.c

@@ -45,7 +45,7 @@
 #include <linux/reboot.h>
 #include <linux/notifier.h>
 #include <linux/kthread.h>
-
+#include <linux/workqueue.h>
 #define __KERNEL_SYSCALLS__
 #include <linux/unistd.h>
 #include <linux/vmalloc.h>
@@ -2299,6 +2299,7 @@ static void drbd_cleanup(void)
 	idr_for_each_entry(&minors, mdev, i) {
 		idr_remove(&minors, mdev_to_minor(mdev));
 		idr_remove(&mdev->tconn->volumes, mdev->vnr);
+		destroy_workqueue(mdev->submit.wq);
 		del_gendisk(mdev->vdisk);
 		/* synchronize_rcu(); No other threads running at this point */
 		kref_put(&mdev->kref, &drbd_minor_destroy);
@@ -2588,6 +2589,21 @@ void conn_destroy(struct kref *kref)
 	kfree(tconn);
 }
 
+int init_submitter(struct drbd_conf *mdev)
+{
+	/* opencoded create_singlethread_workqueue(),
+	 * to be able to say "drbd%d", ..., minor */
+	mdev->submit.wq = alloc_workqueue("drbd%u_submit",
+			WQ_UNBOUND | WQ_MEM_RECLAIM, 1, mdev->minor);
+	if (!mdev->submit.wq)
+		return -ENOMEM;
+
+	INIT_WORK(&mdev->submit.worker, do_submit);
+	spin_lock_init(&mdev->submit.lock);
+	INIT_LIST_HEAD(&mdev->submit.writes);
+	return 0;
+}
+
 enum drbd_ret_code conn_new_minor(struct drbd_tconn *tconn, unsigned int minor, int vnr)
 {
 	struct drbd_conf *mdev;
@@ -2677,6 +2693,12 @@ enum drbd_ret_code conn_new_minor(struct drbd_tconn *tconn, unsigned int minor,
 		goto out_idr_remove_minor;
 	}
 
+	if (init_submitter(mdev)) {
+		err = ERR_NOMEM;
+		drbd_msg_put_info("unable to create submit workqueue");
+		goto out_idr_remove_vol;
+	}
+
 	add_disk(disk);
 	kref_init(&mdev->kref); /* one ref for both idrs and the the add_disk */
 
@@ -2687,6 +2709,8 @@ enum drbd_ret_code conn_new_minor(struct drbd_tconn *tconn, unsigned int minor,
 
 	return NO_ERROR;
 
+out_idr_remove_vol:
+	idr_remove(&tconn->volumes, vnr_got);
 out_idr_remove_minor:
 	idr_remove(&minors, minor_got);
 	synchronize_rcu();
@@ -2794,6 +2818,7 @@ void drbd_free_bc(struct drbd_backing_dev *ldev)
 	blkdev_put(ldev->backing_bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL);
 	blkdev_put(ldev->md_bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL);
 
+	kfree(ldev->disk_conf);
 	kfree(ldev);
 }
 
@@ -2833,8 +2858,9 @@ void conn_md_sync(struct drbd_tconn *tconn)
 	rcu_read_unlock();
 }
 
+/* aligned 4kByte */
 struct meta_data_on_disk {
-	u64 la_size;           /* last agreed size. */
+	u64 la_size_sect;      /* last agreed size. */
 	u64 uuid[UI_SIZE];   /* UUIDs. */
 	u64 device_uuid;
 	u64 reserved_u64_1;
@@ -2842,13 +2868,17 @@ struct meta_data_on_disk {
 	u32 magic;
 	u32 md_size_sect;
 	u32 al_offset;         /* offset to this block */
-	u32 al_nr_extents;     /* important for restoring the AL */
+	u32 al_nr_extents;     /* important for restoring the AL (userspace) */
 	      /* `-- act_log->nr_elements <-- ldev->dc.al_extents */
 	u32 bm_offset;         /* offset to the bitmap, from here */
 	u32 bm_bytes_per_bit;  /* BM_BLOCK_SIZE */
 	u32 la_peer_max_bio_size;   /* last peer max_bio_size */
-	u32 reserved_u32[3];
 
+	/* see al_tr_number_to_on_disk_sector() */
+	u32 al_stripes;
+	u32 al_stripe_size_4k;
+
+	u8 reserved_u8[4096 - (7*8 + 10*4)];
 } __packed;
 
 /**
@@ -2861,6 +2891,10 @@ void drbd_md_sync(struct drbd_conf *mdev)
 	sector_t sector;
 	int i;
 
+	/* Don't accidentally change the DRBD meta data layout. */
+	BUILD_BUG_ON(UI_SIZE != 4);
+	BUILD_BUG_ON(sizeof(struct meta_data_on_disk) != 4096);
+
 	del_timer(&mdev->md_sync_timer);
 	/* timer may be rearmed by drbd_md_mark_dirty() now. */
 	if (!test_and_clear_bit(MD_DIRTY, &mdev->flags))
@@ -2875,9 +2909,9 @@ void drbd_md_sync(struct drbd_conf *mdev)
 	if (!buffer)
 		goto out;
 
-	memset(buffer, 0, 512);
+	memset(buffer, 0, sizeof(*buffer));
 
-	buffer->la_size = cpu_to_be64(drbd_get_capacity(mdev->this_bdev));
+	buffer->la_size_sect = cpu_to_be64(drbd_get_capacity(mdev->this_bdev));
 	for (i = UI_CURRENT; i < UI_SIZE; i++)
 		buffer->uuid[i] = cpu_to_be64(mdev->ldev->md.uuid[i]);
 	buffer->flags = cpu_to_be32(mdev->ldev->md.flags);
@@ -2892,7 +2926,10 @@ void drbd_md_sync(struct drbd_conf *mdev)
 	buffer->bm_offset = cpu_to_be32(mdev->ldev->md.bm_offset);
 	buffer->la_peer_max_bio_size = cpu_to_be32(mdev->peer_max_bio_size);
 
-	D_ASSERT(drbd_md_ss__(mdev, mdev->ldev) == mdev->ldev->md.md_offset);
+	buffer->al_stripes = cpu_to_be32(mdev->ldev->md.al_stripes);
+	buffer->al_stripe_size_4k = cpu_to_be32(mdev->ldev->md.al_stripe_size_4k);
+
+	D_ASSERT(drbd_md_ss(mdev->ldev) == mdev->ldev->md.md_offset);
 	sector = mdev->ldev->md.md_offset;
 
 	if (drbd_md_sync_page_io(mdev, mdev->ldev, sector, WRITE)) {
@@ -2910,13 +2947,141 @@ void drbd_md_sync(struct drbd_conf *mdev)
 	put_ldev(mdev);
 }
 
+static int check_activity_log_stripe_size(struct drbd_conf *mdev,
+		struct meta_data_on_disk *on_disk,
+		struct drbd_md *in_core)
+{
+	u32 al_stripes = be32_to_cpu(on_disk->al_stripes);
+	u32 al_stripe_size_4k = be32_to_cpu(on_disk->al_stripe_size_4k);
+	u64 al_size_4k;
+
+	/* both not set: default to old fixed size activity log */
+	if (al_stripes == 0 && al_stripe_size_4k == 0) {
+		al_stripes = 1;
+		al_stripe_size_4k = MD_32kB_SECT/8;
+	}
+
+	/* some paranoia plausibility checks */
+
+	/* we need both values to be set */
+	if (al_stripes == 0 || al_stripe_size_4k == 0)
+		goto err;
+
+	al_size_4k = (u64)al_stripes * al_stripe_size_4k;
+
+	/* Upper limit of activity log area, to avoid potential overflow
+	 * problems in al_tr_number_to_on_disk_sector(). As right now, more
+	 * than 72 * 4k blocks total only increases the amount of history,
+	 * limiting this arbitrarily to 16 GB is not a real limitation ;-)  */
+	if (al_size_4k > (16 * 1024 * 1024/4))
+		goto err;
+
+	/* Lower limit: we need at least 8 transaction slots (32kB)
+	 * to not break existing setups */
+	if (al_size_4k < MD_32kB_SECT/8)
+		goto err;
+
+	in_core->al_stripe_size_4k = al_stripe_size_4k;
+	in_core->al_stripes = al_stripes;
+	in_core->al_size_4k = al_size_4k;
+
+	return 0;
+err:
+	dev_err(DEV, "invalid activity log striping: al_stripes=%u, al_stripe_size_4k=%u\n",
+			al_stripes, al_stripe_size_4k);
+	return -EINVAL;
+}
+
+static int check_offsets_and_sizes(struct drbd_conf *mdev, struct drbd_backing_dev *bdev)
+{
+	sector_t capacity = drbd_get_capacity(bdev->md_bdev);
+	struct drbd_md *in_core = &bdev->md;
+	s32 on_disk_al_sect;
+	s32 on_disk_bm_sect;
+
+	/* The on-disk size of the activity log, calculated from offsets, and
+	 * the size of the activity log calculated from the stripe settings,
+	 * should match.
+	 * Though we could relax this a bit: it is ok, if the striped activity log
+	 * fits in the available on-disk activity log size.
+	 * Right now, that would break how resize is implemented.
+	 * TODO: make drbd_determine_dev_size() (and the drbdmeta tool) aware
+	 * of possible unused padding space in the on disk layout. */
+	if (in_core->al_offset < 0) {
+		if (in_core->bm_offset > in_core->al_offset)
+			goto err;
+		on_disk_al_sect = -in_core->al_offset;
+		on_disk_bm_sect = in_core->al_offset - in_core->bm_offset;
+	} else {
+		if (in_core->al_offset != MD_4kB_SECT)
+			goto err;
+		if (in_core->bm_offset < in_core->al_offset + in_core->al_size_4k * MD_4kB_SECT)
+			goto err;
+
+		on_disk_al_sect = in_core->bm_offset - MD_4kB_SECT;
+		on_disk_bm_sect = in_core->md_size_sect - in_core->bm_offset;
+	}
+
+	/* old fixed size meta data is exactly that: fixed. */
+	if (in_core->meta_dev_idx >= 0) {
+		if (in_core->md_size_sect != MD_128MB_SECT
+		||  in_core->al_offset != MD_4kB_SECT
+		||  in_core->bm_offset != MD_4kB_SECT + MD_32kB_SECT
+		||  in_core->al_stripes != 1
+		||  in_core->al_stripe_size_4k != MD_32kB_SECT/8)
+			goto err;
+	}
+
+	if (capacity < in_core->md_size_sect)
+		goto err;
+	if (capacity - in_core->md_size_sect < drbd_md_first_sector(bdev))
+		goto err;
+
+	/* should be aligned, and at least 32k */
+	if ((on_disk_al_sect & 7) || (on_disk_al_sect < MD_32kB_SECT))
+		goto err;
+
+	/* should fit (for now: exactly) into the available on-disk space;
+	 * overflow prevention is in check_activity_log_stripe_size() above. */
+	if (on_disk_al_sect != in_core->al_size_4k * MD_4kB_SECT)
+		goto err;
+
+	/* again, should be aligned */
+	if (in_core->bm_offset & 7)
+		goto err;
+
+	/* FIXME check for device grow with flex external meta data? */
+
+	/* can the available bitmap space cover the last agreed device size? */
+	if (on_disk_bm_sect < (in_core->la_size_sect+7)/MD_4kB_SECT/8/512)
+		goto err;
+
+	return 0;
+
+err:
+	dev_err(DEV, "meta data offsets don't make sense: idx=%d "
+			"al_s=%u, al_sz4k=%u, al_offset=%d, bm_offset=%d, "
+			"md_size_sect=%u, la_size=%llu, md_capacity=%llu\n",
+			in_core->meta_dev_idx,
+			in_core->al_stripes, in_core->al_stripe_size_4k,
+			in_core->al_offset, in_core->bm_offset, in_core->md_size_sect,
+			(unsigned long long)in_core->la_size_sect,
+			(unsigned long long)capacity);
+
+	return -EINVAL;
+}
+
+
 /**
  * drbd_md_read() - Reads in the meta data super block
  * @mdev:	DRBD device.
  * @bdev:	Device from which the meta data should be read in.
  *
- * Return 0 (NO_ERROR) on success, and an enum drbd_ret_code in case
+ * Return NO_ERROR on success, and an enum drbd_ret_code in case
  * something goes wrong.
+ *
+ * Called exactly once during drbd_adm_attach(), while still being D_DISKLESS,
+ * even before @bdev is assigned to @mdev->ldev.
  */
 int drbd_md_read(struct drbd_conf *mdev, struct drbd_backing_dev *bdev)
 {
@@ -2924,12 +3089,17 @@ int drbd_md_read(struct drbd_conf *mdev, struct drbd_backing_dev *bdev)
 	u32 magic, flags;
 	int i, rv = NO_ERROR;
 
-	if (!get_ldev_if_state(mdev, D_ATTACHING))
-		return ERR_IO_MD_DISK;
+	if (mdev->state.disk != D_DISKLESS)
+		return ERR_DISK_CONFIGURED;
 
 	buffer = drbd_md_get_buffer(mdev);
 	if (!buffer)
-		goto out;
+		return ERR_NOMEM;
+
+	/* First, figure out where our meta data superblock is located,
+	 * and read it. */
+	bdev->md.meta_dev_idx = bdev->disk_conf->meta_dev_idx;
+	bdev->md.md_offset = drbd_md_ss(bdev);
 
 	if (drbd_md_sync_page_io(mdev, bdev, bdev->md.md_offset, READ)) {
 		/* NOTE: can't do normal error processing here as this is
@@ -2948,45 +3118,51 @@ int drbd_md_read(struct drbd_conf *mdev, struct drbd_backing_dev *bdev)
 		rv = ERR_MD_UNCLEAN;
 		goto err;
 	}
+
+	rv = ERR_MD_INVALID;
 	if (magic != DRBD_MD_MAGIC_08) {
 		if (magic == DRBD_MD_MAGIC_07)
 			dev_err(DEV, "Found old (0.7) meta data magic. Did you \"drbdadm create-md\"?\n");
 		else
 			dev_err(DEV, "Meta data magic not found. Did you \"drbdadm create-md\"?\n");
-		rv = ERR_MD_INVALID;
 		goto err;
 	}
-	if (be32_to_cpu(buffer->al_offset) != bdev->md.al_offset) {
-		dev_err(DEV, "unexpected al_offset: %d (expected %d)\n",
-		    be32_to_cpu(buffer->al_offset), bdev->md.al_offset);
-		rv = ERR_MD_INVALID;
+
+	if (be32_to_cpu(buffer->bm_bytes_per_bit) != BM_BLOCK_SIZE) {
+		dev_err(DEV, "unexpected bm_bytes_per_bit: %u (expected %u)\n",
+		    be32_to_cpu(buffer->bm_bytes_per_bit), BM_BLOCK_SIZE);
 		goto err;
 	}
+
+
+	/* convert to in_core endian */
+	bdev->md.la_size_sect = be64_to_cpu(buffer->la_size_sect);
+	for (i = UI_CURRENT; i < UI_SIZE; i++)
+		bdev->md.uuid[i] = be64_to_cpu(buffer->uuid[i]);
+	bdev->md.flags = be32_to_cpu(buffer->flags);
+	bdev->md.device_uuid = be64_to_cpu(buffer->device_uuid);
+
+	bdev->md.md_size_sect = be32_to_cpu(buffer->md_size_sect);
+	bdev->md.al_offset = be32_to_cpu(buffer->al_offset);
+	bdev->md.bm_offset = be32_to_cpu(buffer->bm_offset);
+
+	if (check_activity_log_stripe_size(mdev, buffer, &bdev->md))
+		goto err;
+	if (check_offsets_and_sizes(mdev, bdev))
+		goto err;
+
 	if (be32_to_cpu(buffer->bm_offset) != bdev->md.bm_offset) {
 		dev_err(DEV, "unexpected bm_offset: %d (expected %d)\n",
 		    be32_to_cpu(buffer->bm_offset), bdev->md.bm_offset);
-		rv = ERR_MD_INVALID;
 		goto err;
 	}
 	if (be32_to_cpu(buffer->md_size_sect) != bdev->md.md_size_sect) {
 		dev_err(DEV, "unexpected md_size: %u (expected %u)\n",
 		    be32_to_cpu(buffer->md_size_sect), bdev->md.md_size_sect);
-		rv = ERR_MD_INVALID;
 		goto err;
 	}
 
-	if (be32_to_cpu(buffer->bm_bytes_per_bit) != BM_BLOCK_SIZE) {
-		dev_err(DEV, "unexpected bm_bytes_per_bit: %u (expected %u)\n",
-		    be32_to_cpu(buffer->bm_bytes_per_bit), BM_BLOCK_SIZE);
-		rv = ERR_MD_INVALID;
-		goto err;
-	}
-
-	bdev->md.la_size_sect = be64_to_cpu(buffer->la_size);
-	for (i = UI_CURRENT; i < UI_SIZE; i++)
-		bdev->md.uuid[i] = be64_to_cpu(buffer->uuid[i]);
-	bdev->md.flags = be32_to_cpu(buffer->flags);
-	bdev->md.device_uuid = be64_to_cpu(buffer->device_uuid);
+	rv = NO_ERROR;
 
 	spin_lock_irq(&mdev->tconn->req_lock);
 	if (mdev->state.conn < C_CONNECTED) {
@@ -2999,8 +3175,6 @@ int drbd_md_read(struct drbd_conf *mdev, struct drbd_backing_dev *bdev)
 
  err:
 	drbd_md_put_buffer(mdev);
- out:
-	put_ldev(mdev);
 
 	return rv;
 }
@@ -3238,8 +3412,12 @@ static int w_go_diskless(struct drbd_work *w, int unused)
 	 * end up here after a failed attach, before ldev was even assigned.
 	 */
 	if (mdev->bitmap && mdev->ldev) {
+		/* An interrupted resync or similar is allowed to recounts bits
+		 * while we detach.
+		 * Any modifications would not be expected anymore, though.
+		 */
 		if (drbd_bitmap_io_from_worker(mdev, drbd_bm_write,
-					"detach", BM_LOCKED_MASK)) {
+					"detach", BM_LOCKED_TEST_ALLOWED)) {
 			if (test_bit(WAS_READ_ERROR, &mdev->flags)) {
 				drbd_md_set_flag(mdev, MDF_FULL_SYNC);
 				drbd_md_sync(mdev);
@@ -3251,13 +3429,6 @@ static int w_go_diskless(struct drbd_work *w, int unused)
 	return 0;
 }
 
-void drbd_go_diskless(struct drbd_conf *mdev)
-{
-	D_ASSERT(mdev->state.disk == D_FAILED);
-	if (!test_and_set_bit(GO_DISKLESS, &mdev->flags))
-		drbd_queue_work(&mdev->tconn->sender_work, &mdev->go_diskless);
-}
-
 /**
  * drbd_queue_bitmap_io() - Queues an IO operation on the whole bitmap
  * @mdev:	DRBD device.

drivers/block/drbd/drbd_nl.c

@@ -696,37 +696,52 @@ int drbd_adm_set_role(struct sk_buff *skb, struct genl_info *info)
 	return 0;
 }
 
-/* initializes the md.*_offset members, so we are able to find
- * the on disk meta data */
+/* Initializes the md.*_offset members, so we are able to find
+ * the on disk meta data.
+ *
+ * We currently have two possible layouts:
+ * external:
+ *   |----------- md_size_sect ------------------|
+ *   [ 4k superblock ][ activity log ][  Bitmap  ]
+ *   | al_offset == 8 |
+ *   | bm_offset = al_offset + X      |
+ *  ==> bitmap sectors = md_size_sect - bm_offset
+ *
+ * internal:
+ *            |----------- md_size_sect ------------------|
+ * [data.....][  Bitmap  ][ activity log ][ 4k superblock ]
+ *                        | al_offset < 0 |
+ *            | bm_offset = al_offset - Y |
+ *  ==> bitmap sectors = Y = al_offset - bm_offset
+ *
+ *  Activity log size used to be fixed 32kB,
+ *  but is about to become configurable.
+ */
 static void drbd_md_set_sector_offsets(struct drbd_conf *mdev,
 				       struct drbd_backing_dev *bdev)
 {
 	sector_t md_size_sect = 0;
-	int meta_dev_idx;
+	unsigned int al_size_sect = bdev->md.al_size_4k * 8;
 
-	rcu_read_lock();
-	meta_dev_idx = rcu_dereference(bdev->disk_conf)->meta_dev_idx;
+	bdev->md.md_offset = drbd_md_ss(bdev);
 
-	switch (meta_dev_idx) {
+	switch (bdev->md.meta_dev_idx) {
 	default:
 		/* v07 style fixed size indexed meta data */
-		bdev->md.md_size_sect = MD_RESERVED_SECT;
-		bdev->md.md_offset = drbd_md_ss__(mdev, bdev);
-		bdev->md.al_offset = MD_AL_OFFSET;
-		bdev->md.bm_offset = MD_BM_OFFSET;
+		bdev->md.md_size_sect = MD_128MB_SECT;
+		bdev->md.al_offset = MD_4kB_SECT;
+		bdev->md.bm_offset = MD_4kB_SECT + al_size_sect;
 		break;
 	case DRBD_MD_INDEX_FLEX_EXT:
 		/* just occupy the full device; unit: sectors */
 		bdev->md.md_size_sect = drbd_get_capacity(bdev->md_bdev);
-		bdev->md.md_offset = 0;
-		bdev->md.al_offset = MD_AL_OFFSET;
-		bdev->md.bm_offset = MD_BM_OFFSET;
+		bdev->md.al_offset = MD_4kB_SECT;
+		bdev->md.bm_offset = MD_4kB_SECT + al_size_sect;
 		break;
 	case DRBD_MD_INDEX_INTERNAL:
 	case DRBD_MD_INDEX_FLEX_INT:
-		bdev->md.md_offset = drbd_md_ss__(mdev, bdev);
 		/* al size is still fixed */
-		bdev->md.al_offset = -MD_AL_SECTORS;
+		bdev->md.al_offset = -al_size_sect;
 		/* we need (slightly less than) ~ this much bitmap sectors: */
 		md_size_sect = drbd_get_capacity(bdev->backing_bdev);
 		md_size_sect = ALIGN(md_size_sect, BM_SECT_PER_EXT);
@@ -735,14 +750,13 @@ static void drbd_md_set_sector_offsets(struct drbd_conf *mdev,
 
 		/* plus the "drbd meta data super block",
 		 * and the activity log; */
-		md_size_sect += MD_BM_OFFSET;
+		md_size_sect += MD_4kB_SECT + al_size_sect;
 
 		bdev->md.md_size_sect = md_size_sect;
 		/* bitmap offset is adjusted by 'super' block size */
-		bdev->md.bm_offset   = -md_size_sect + MD_AL_OFFSET;
+		bdev->md.bm_offset   = -md_size_sect + MD_4kB_SECT;
 		break;
 	}
-	rcu_read_unlock();
 }
 
 /* input size is expected to be in KB */
@@ -805,7 +819,7 @@ void drbd_resume_io(struct drbd_conf *mdev)
 enum determine_dev_size drbd_determine_dev_size(struct drbd_conf *mdev, enum dds_flags flags) __must_hold(local)
 {
 	sector_t prev_first_sect, prev_size; /* previous meta location */
-	sector_t la_size, u_size;
+	sector_t la_size_sect, u_size;
 	sector_t size;
 	char ppb[10];
 
@@ -828,7 +842,7 @@ enum determine_dev_size drbd_determine_dev_size(struct drbd_conf *mdev, enum dds
 
 	prev_first_sect = drbd_md_first_sector(mdev->ldev);
 	prev_size = mdev->ldev->md.md_size_sect;
-	la_size = mdev->ldev->md.la_size_sect;
+	la_size_sect = mdev->ldev->md.la_size_sect;
 
 	/* TODO: should only be some assert here, not (re)init... */
 	drbd_md_set_sector_offsets(mdev, mdev->ldev);
@@ -864,7 +878,7 @@ enum determine_dev_size drbd_determine_dev_size(struct drbd_conf *mdev, enum dds
 	if (rv == dev_size_error)
 		goto out;
 
-	la_size_changed = (la_size != mdev->ldev->md.la_size_sect);
+	la_size_changed = (la_size_sect != mdev->ldev->md.la_size_sect);
 
 	md_moved = prev_first_sect != drbd_md_first_sector(mdev->ldev)
 		|| prev_size	   != mdev->ldev->md.md_size_sect;
@@ -886,9 +900,9 @@ enum determine_dev_size drbd_determine_dev_size(struct drbd_conf *mdev, enum dds
 		drbd_md_mark_dirty(mdev);
 	}
 
-	if (size > la_size)
+	if (size > la_size_sect)
 		rv = grew;
-	if (size < la_size)
+	if (size < la_size_sect)
 		rv = shrunk;
 out:
 	lc_unlock(mdev->act_log);
@@ -903,7 +917,7 @@ drbd_new_dev_size(struct drbd_conf *mdev, struct drbd_backing_dev *bdev,
 		  sector_t u_size, int assume_peer_has_space)
 {
 	sector_t p_size = mdev->p_size;   /* partner's disk size. */
-	sector_t la_size = bdev->md.la_size_sect; /* last agreed size. */
+	sector_t la_size_sect = bdev->md.la_size_sect; /* last agreed size. */
 	sector_t m_size; /* my size */
 	sector_t size = 0;
 
@@ -917,8 +931,8 @@ drbd_new_dev_size(struct drbd_conf *mdev, struct drbd_backing_dev *bdev,
 	if (p_size && m_size) {
 		size = min_t(sector_t, p_size, m_size);
 	} else {
-		if (la_size) {
-			size = la_size;
+		if (la_size_sect) {
+			size = la_size_sect;
 			if (m_size && m_size < size)
 				size = m_size;
 			if (p_size && p_size < size)
@@ -1127,15 +1141,32 @@ static bool should_set_defaults(struct genl_info *info)
 	return 0 != (flags & DRBD_GENL_F_SET_DEFAULTS);
 }
 
-static void enforce_disk_conf_limits(struct disk_conf *dc)
+static unsigned int drbd_al_extents_max(struct drbd_backing_dev *bdev)
 {
-	if (dc->al_extents < DRBD_AL_EXTENTS_MIN)
-		dc->al_extents = DRBD_AL_EXTENTS_MIN;
-	if (dc->al_extents > DRBD_AL_EXTENTS_MAX)
-		dc->al_extents = DRBD_AL_EXTENTS_MAX;
+	/* This is limited by 16 bit "slot" numbers,
+	 * and by available on-disk context storage.
+	 *
+	 * Also (u16)~0 is special (denotes a "free" extent).
+	 *
+	 * One transaction occupies one 4kB on-disk block,
+	 * we have n such blocks in the on disk ring buffer,
+	 * the "current" transaction may fail (n-1),
+	 * and there is 919 slot numbers context information per transaction.
+	 *
+	 * 72 transaction blocks amounts to more than 2**16 context slots,
+	 * so cap there first.
+	 */
+	const unsigned int max_al_nr = DRBD_AL_EXTENTS_MAX;
+	const unsigned int sufficient_on_disk =
+		(max_al_nr + AL_CONTEXT_PER_TRANSACTION -1)
+		/AL_CONTEXT_PER_TRANSACTION;
+
+	unsigned int al_size_4k = bdev->md.al_size_4k;
+
+	if (al_size_4k > sufficient_on_disk)
+		return max_al_nr;
 
-	if (dc->c_plan_ahead > DRBD_C_PLAN_AHEAD_MAX)
-		dc->c_plan_ahead = DRBD_C_PLAN_AHEAD_MAX;
+	return (al_size_4k - 1) * AL_CONTEXT_PER_TRANSACTION;
 }
 
 int drbd_adm_disk_opts(struct sk_buff *skb, struct genl_info *info)
@@ -1182,7 +1213,13 @@ int drbd_adm_disk_opts(struct sk_buff *skb, struct genl_info *info)
 	if (!expect(new_disk_conf->resync_rate >= 1))
 		new_disk_conf->resync_rate = 1;
 
-	enforce_disk_conf_limits(new_disk_conf);
+	if (new_disk_conf->al_extents < DRBD_AL_EXTENTS_MIN)
+		new_disk_conf->al_extents = DRBD_AL_EXTENTS_MIN;
+	if (new_disk_conf->al_extents > drbd_al_extents_max(mdev->ldev))
+		new_disk_conf->al_extents = drbd_al_extents_max(mdev->ldev);
+
+	if (new_disk_conf->c_plan_ahead > DRBD_C_PLAN_AHEAD_MAX)
+		new_disk_conf->c_plan_ahead = DRBD_C_PLAN_AHEAD_MAX;
 
 	fifo_size = (new_disk_conf->c_plan_ahead * 10 * SLEEP_TIME) / HZ;
 	if (fifo_size != mdev->rs_plan_s->size) {
@@ -1330,7 +1367,8 @@ int drbd_adm_attach(struct sk_buff *skb, struct genl_info *info)
 		goto fail;
 	}
 
-	enforce_disk_conf_limits(new_disk_conf);
+	if (new_disk_conf->c_plan_ahead > DRBD_C_PLAN_AHEAD_MAX)
+		new_disk_conf->c_plan_ahead = DRBD_C_PLAN_AHEAD_MAX;
 
 	new_plan = fifo_alloc((new_disk_conf->c_plan_ahead * 10 * SLEEP_TIME) / HZ);
 	if (!new_plan) {
@@ -1343,6 +1381,12 @@ int drbd_adm_attach(struct sk_buff *skb, struct genl_info *info)
 		goto fail;
 	}
 
+	write_lock_irq(&global_state_lock);
+	retcode = drbd_resync_after_valid(mdev, new_disk_conf->resync_after);
+	write_unlock_irq(&global_state_lock);
+	if (retcode != NO_ERROR)
+		goto fail;
+
 	rcu_read_lock();
 	nc = rcu_dereference(mdev->tconn->net_conf);
 	if (nc) {
@@ -1399,8 +1443,16 @@ int drbd_adm_attach(struct sk_buff *skb, struct genl_info *info)
 		goto fail;
 	}
 
-	/* RT - for drbd_get_max_capacity() DRBD_MD_INDEX_FLEX_INT */
-	drbd_md_set_sector_offsets(mdev, nbc);
+	/* Read our meta data super block early.
+	 * This also sets other on-disk offsets. */
+	retcode = drbd_md_read(mdev, nbc);
+	if (retcode != NO_ERROR)
+		goto fail;
+
+	if (new_disk_conf->al_extents < DRBD_AL_EXTENTS_MIN)
+		new_disk_conf->al_extents = DRBD_AL_EXTENTS_MIN;
+	if (new_disk_conf->al_extents > drbd_al_extents_max(nbc))
+		new_disk_conf->al_extents = drbd_al_extents_max(nbc);
 
 	if (drbd_get_max_capacity(nbc) < new_disk_conf->disk_size) {
 		dev_err(DEV, "max capacity %llu smaller than disk size %llu\n",
@@ -1416,7 +1468,7 @@ int drbd_adm_attach(struct sk_buff *skb, struct genl_info *info)
 		min_md_device_sectors = (2<<10);
 	} else {
 		max_possible_sectors = DRBD_MAX_SECTORS;
-		min_md_device_sectors = MD_RESERVED_SECT * (new_disk_conf->meta_dev_idx + 1);
+		min_md_device_sectors = MD_128MB_SECT * (new_disk_conf->meta_dev_idx + 1);
 	}
 
 	if (drbd_get_capacity(nbc->md_bdev) < min_md_device_sectors) {
@@ -1467,8 +1519,6 @@ int drbd_adm_attach(struct sk_buff *skb, struct genl_info *info)
 	if (!get_ldev_if_state(mdev, D_ATTACHING))
 		goto force_diskless;
 
-	drbd_md_set_sector_offsets(mdev, nbc);
-
 	if (!mdev->bitmap) {
 		if (drbd_bm_init(mdev)) {
 			retcode = ERR_NOMEM;
@@ -1476,10 +1526,6 @@ int drbd_adm_attach(struct sk_buff *skb, struct genl_info *info)
 		}
 	}
 
-	retcode = drbd_md_read(mdev, nbc);
-	if (retcode != NO_ERROR)
-		goto force_diskless_dec;
-
 	if (mdev->state.conn < C_CONNECTED &&
 	    mdev->state.role == R_PRIMARY &&
 	    (mdev->ed_uuid & ~((u64)1)) != (nbc->md.uuid[UI_CURRENT] & ~((u64)1))) {
@@ -2158,8 +2204,11 @@ static enum drbd_state_rv conn_try_disconnect(struct drbd_tconn *tconn, bool for
 		return SS_SUCCESS;
 	case SS_PRIMARY_NOP:
 		/* Our state checking code wants to see the peer outdated. */
-		rv = conn_request_state(tconn, NS2(conn, C_DISCONNECTING,
-						pdsk, D_OUTDATED), CS_VERBOSE);
+		rv = conn_request_state(tconn, NS2(conn, C_DISCONNECTING, pdsk, D_OUTDATED), 0);
+
+		if (rv == SS_OUTDATE_WO_CONN) /* lost connection before graceful disconnect succeeded */
+			rv = conn_request_state(tconn, NS(conn, C_DISCONNECTING), CS_VERBOSE);
+
 		break;
 	case SS_CW_FAILED_BY_PEER:
 		/* The peer probably wants to see us outdated. */
@@ -2406,22 +2455,19 @@ int drbd_adm_invalidate(struct sk_buff *skb, struct genl_info *info)
 	wait_event(mdev->misc_wait, !test_bit(BITMAP_IO, &mdev->flags));
 	drbd_flush_workqueue(mdev);
 
-	retcode = _drbd_request_state(mdev, NS(conn, C_STARTING_SYNC_T), CS_ORDERED);
-
-	if (retcode < SS_SUCCESS && retcode != SS_NEED_CONNECTION)
-		retcode = drbd_request_state(mdev, NS(conn, C_STARTING_SYNC_T));
-
-	while (retcode == SS_NEED_CONNECTION) {
-		spin_lock_irq(&mdev->tconn->req_lock);
-		if (mdev->state.conn < C_CONNECTED)
-			retcode = _drbd_set_state(_NS(mdev, disk, D_INCONSISTENT), CS_VERBOSE, NULL);
-		spin_unlock_irq(&mdev->tconn->req_lock);
-
-		if (retcode != SS_NEED_CONNECTION)
-			break;
-
+	/* If we happen to be C_STANDALONE R_SECONDARY, just change to
+	 * D_INCONSISTENT, and set all bits in the bitmap.  Otherwise,
+	 * try to start a resync handshake as sync target for full sync.
+	 */
+	if (mdev->state.conn == C_STANDALONE && mdev->state.role == R_SECONDARY) {
+		retcode = drbd_request_state(mdev, NS(disk, D_INCONSISTENT));
+		if (retcode >= SS_SUCCESS) {
+			if (drbd_bitmap_io(mdev, &drbd_bmio_set_n_write,
+				"set_n_write from invalidate", BM_LOCKED_MASK))
+				retcode = ERR_IO_MD_DISK;
+		}
+	} else
 		retcode = drbd_request_state(mdev, NS(conn, C_STARTING_SYNC_T));
-	}
 	drbd_resume_io(mdev);
 
 out:
@@ -2475,21 +2521,22 @@ int drbd_adm_invalidate_peer(struct sk_buff *skb, struct genl_info *info)
 	wait_event(mdev->misc_wait, !test_bit(BITMAP_IO, &mdev->flags));
 	drbd_flush_workqueue(mdev);
 
-	retcode = _drbd_request_state(mdev, NS(conn, C_STARTING_SYNC_S), CS_ORDERED);
-	if (retcode < SS_SUCCESS) {
-		if (retcode == SS_NEED_CONNECTION && mdev->state.role == R_PRIMARY) {
-			/* The peer will get a resync upon connect anyways.
-			 * Just make that into a full resync. */
-			retcode = drbd_request_state(mdev, NS(pdsk, D_INCONSISTENT));
-			if (retcode >= SS_SUCCESS) {
-				if (drbd_bitmap_io(mdev, &drbd_bmio_set_susp_al,
-						   "set_n_write from invalidate_peer",
-						   BM_LOCKED_SET_ALLOWED))
-					retcode = ERR_IO_MD_DISK;
-			}
-		} else
-			retcode = drbd_request_state(mdev, NS(conn, C_STARTING_SYNC_S));
-	}
+	/* If we happen to be C_STANDALONE R_PRIMARY, just set all bits
+	 * in the bitmap.  Otherwise, try to start a resync handshake
+	 * as sync source for full sync.
+	 */
+	if (mdev->state.conn == C_STANDALONE && mdev->state.role == R_PRIMARY) {
+		/* The peer will get a resync upon connect anyways. Just make that
+		   into a full resync. */
+		retcode = drbd_request_state(mdev, NS(pdsk, D_INCONSISTENT));
+		if (retcode >= SS_SUCCESS) {
+			if (drbd_bitmap_io(mdev, &drbd_bmio_set_susp_al,
+				"set_n_write from invalidate_peer",
+				BM_LOCKED_SET_ALLOWED))
+				retcode = ERR_IO_MD_DISK;
+		}
+	} else
+		retcode = drbd_request_state(mdev, NS(conn, C_STARTING_SYNC_S));
 	drbd_resume_io(mdev);
 
 out:
@@ -3162,6 +3209,7 @@ static enum drbd_ret_code adm_delete_minor(struct drbd_conf *mdev)
 				    CS_VERBOSE + CS_WAIT_COMPLETE);
 		idr_remove(&mdev->tconn->volumes, mdev->vnr);
 		idr_remove(&minors, mdev_to_minor(mdev));
+		destroy_workqueue(mdev->submit.wq);
 		del_gendisk(mdev->vdisk);
 		synchronize_rcu();
 		kref_put(&mdev->kref, &drbd_minor_destroy);

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/alloc.c

+/*
+ * Primary bucket allocation code
+ *
+ * Copyright 2012 Google, Inc.
+ *
+ * Allocation in bcache is done in terms of buckets:
+ *
+ * Each bucket has associated an 8 bit gen; this gen corresponds to the gen in
+ * btree pointers - they must match for the pointer to be considered valid.
+ *
+ * Thus (assuming a bucket has no dirty data or metadata in it) we can reuse a
+ * bucket simply by incrementing its gen.
+ *
+ * The gens (along with the priorities; it's really the gens are important but
+ * the code is named as if it's the priorities) are written in an arbitrary list
+ * of buckets on disk, with a pointer to them in the journal header.
+ *
+ * When we invalidate a bucket, we have to write its new gen to disk and wait
+ * for that write to complete before we use it - otherwise after a crash we
+ * could have pointers that appeared to be good but pointed to data that had
+ * been overwritten.
+ *
+ * Since the gens and priorities are all stored contiguously on disk, we can
+ * batch this up: We fill up the free_inc list with freshly invalidated buckets,
+ * call prio_write(), and when prio_write() finishes we pull buckets off the
+ * free_inc list and optionally discard them.
+ *
+ * free_inc isn't the only freelist - if it was, we'd often to sleep while
+ * priorities and gens were being written before we could allocate. c->free is a
+ * smaller freelist, and buckets on that list are always ready to be used.
+ *
+ * If we've got discards enabled, that happens when a bucket moves from the
+ * free_inc list to the free list.
+ *
+ * There is another freelist, because sometimes we have buckets that we know
+ * have nothing pointing into them - these we can reuse without waiting for
+ * priorities to be rewritten. These come from freed btree nodes and buckets
+ * that garbage collection discovered no longer had valid keys pointing into
+ * them (because they were overwritten). That's the unused list - buckets on the
+ * unused list move to the free list, optionally being discarded in the process.
+ *
+ * It's also important to ensure that gens don't wrap around - with respect to
+ * either the oldest gen in the btree or the gen on disk. This is quite
+ * difficult to do in practice, but we explicitly guard against it anyways - if
+ * a bucket is in danger of wrapping around we simply skip invalidating it that
+ * time around, and we garbage collect or rewrite the priorities sooner than we
+ * would have otherwise.
+ *
+ * bch_bucket_alloc() allocates a single bucket from a specific cache.
+ *
+ * bch_bucket_alloc_set() allocates one or more buckets from different caches
+ * out of a cache set.
+ *
+ * free_some_buckets() drives all the processes described above. It's called
+ * from bch_bucket_alloc() and a few other places that need to make sure free
+ * buckets are ready.
+ *
+ * invalidate_buckets_(lru|fifo)() find buckets that are available to be
+ * invalidated, and then invalidate them and stick them on the free_inc list -
+ * in either lru or fifo order.
+ */
+
+#include "bcache.h"
+#include "btree.h"
+
+#include <linux/random.h>
+
+#define MAX_IN_FLIGHT_DISCARDS		8U
+
+/* Bucket heap / gen */
+
+uint8_t bch_inc_gen(struct cache *ca, struct bucket *b)
+{
+	uint8_t ret = ++b->gen;
+
+	ca->set->need_gc = max(ca->set->need_gc, bucket_gc_gen(b));
+	WARN_ON_ONCE(ca->set->need_gc > BUCKET_GC_GEN_MAX);
+
+	if (CACHE_SYNC(&ca->set->sb)) {
+		ca->need_save_prio = max(ca->need_save_prio,
+					 bucket_disk_gen(b));
+		WARN_ON_ONCE(ca->need_save_prio > BUCKET_DISK_GEN_MAX);
+	}
+
+	return ret;
+}
+
+void bch_rescale_priorities(struct cache_set *c, int sectors)
+{
+	struct cache *ca;
+	struct bucket *b;
+	unsigned next = c->nbuckets * c->sb.bucket_size / 1024;
+	unsigned i;
+	int r;
+
+	atomic_sub(sectors, &c->rescale);
+
+	do {
+		r = atomic_read(&c->rescale);
+
+		if (r >= 0)
+			return;
+	} while (atomic_cmpxchg(&c->rescale, r, r + next) != r);
+
+	mutex_lock(&c->bucket_lock);
+
+	c->min_prio = USHRT_MAX;
+
+	for_each_cache(ca, c, i)
+		for_each_bucket(b, ca)
+			if (b->prio &&
+			    b->prio != BTREE_PRIO &&
+			    !atomic_read(&b->pin)) {
+				b->prio--;
+				c->min_prio = min(c->min_prio, b->prio);
+			}
+
+	mutex_unlock(&c->bucket_lock);
+}
+
+/* Discard/TRIM */
+
+struct discard {
+	struct list_head	list;
+	struct work_struct	work;
+	struct cache		*ca;
+	long			bucket;
+
+	struct bio		bio;
+	struct bio_vec		bv;
+};
+
+static void discard_finish(struct work_struct *w)
+{
+	struct discard *d = container_of(w, struct discard, work);
+	struct cache *ca = d->ca;
+	char buf[BDEVNAME_SIZE];
+
+	if (!test_bit(BIO_UPTODATE, &d->bio.bi_flags)) {
+		pr_notice("discard error on %s, disabling",
+			 bdevname(ca->bdev, buf));
+		d->ca->discard = 0;
+	}
+
+	mutex_lock(&ca->set->bucket_lock);
+
+	fifo_push(&ca->free, d->bucket);
+	list_add(&d->list, &ca->discards);
+	atomic_dec(&ca->discards_in_flight);
+
+	mutex_unlock(&ca->set->bucket_lock);
+
+	closure_wake_up(&ca->set->bucket_wait);
+	wake_up(&ca->set->alloc_wait);
+
+	closure_put(&ca->set->cl);
+}
+
+static void discard_endio(struct bio *bio, int error)
+{
+	struct discard *d = container_of(bio, struct discard, bio);
+	schedule_work(&d->work);
+}
+
+static void do_discard(struct cache *ca, long bucket)
+{
+	struct discard *d = list_first_entry(&ca->discards,
+					     struct discard, list);
+
+	list_del(&d->list);
+	d->bucket = bucket;
+
+	atomic_inc(&ca->discards_in_flight);
+	closure_get(&ca->set->cl);
+
+	bio_init(&d->bio);
+
+	d->bio.bi_sector	= bucket_to_sector(ca->set, d->bucket);
+	d->bio.bi_bdev		= ca->bdev;
+	d->bio.bi_rw		= REQ_WRITE|REQ_DISCARD;
+	d->bio.bi_max_vecs	= 1;
+	d->bio.bi_io_vec	= d->bio.bi_inline_vecs;
+	d->bio.bi_size		= bucket_bytes(ca);
+	d->bio.bi_end_io	= discard_endio;
+	bio_set_prio(&d->bio, IOPRIO_PRIO_VALUE(IOPRIO_CLASS_IDLE, 0));
+
+	submit_bio(0, &d->bio);
+}
+
+/* Allocation */
+
+static inline bool can_inc_bucket_gen(struct bucket *b)
+{
+	return bucket_gc_gen(b) < BUCKET_GC_GEN_MAX &&
+		bucket_disk_gen(b) < BUCKET_DISK_GEN_MAX;
+}
+
+bool bch_bucket_add_unused(struct cache *ca, struct bucket *b)
+{
+	BUG_ON(GC_MARK(b) || GC_SECTORS_USED(b));
+
+	if (fifo_used(&ca->free) > ca->watermark[WATERMARK_MOVINGGC] &&
+	    CACHE_REPLACEMENT(&ca->sb) == CACHE_REPLACEMENT_FIFO)
+		return false;
+
+	b->prio = 0;
+
+	if (can_inc_bucket_gen(b) &&
+	    fifo_push(&ca->unused, b - ca->buckets)) {
+		atomic_inc(&b->pin);
+		return true;
+	}
+
+	return false;
+}
+
+static bool can_invalidate_bucket(struct cache *ca, struct bucket *b)
+{
+	return GC_MARK(b) == GC_MARK_RECLAIMABLE &&
+		!atomic_read(&b->pin) &&
+		can_inc_bucket_gen(b);
+}
+
+static void invalidate_one_bucket(struct cache *ca, struct bucket *b)
+{
+	bch_inc_gen(ca, b);
+	b->prio = INITIAL_PRIO;
+	atomic_inc(&b->pin);
+	fifo_push(&ca->free_inc, b - ca->buckets);
+}
+
+#define bucket_prio(b)				\
+	(((unsigned) (b->prio - ca->set->min_prio)) * GC_SECTORS_USED(b))
+
+#define bucket_max_cmp(l, r)	(bucket_prio(l) < bucket_prio(r))
+#define bucket_min_cmp(l, r)	(bucket_prio(l) > bucket_prio(r))
+
+static void invalidate_buckets_lru(struct cache *ca)
+{
+	struct bucket *b;
+	ssize_t i;
+
+	ca->heap.used = 0;
+
+	for_each_bucket(b, ca) {
+		/*
+		 * If we fill up the unused list, if we then return before
+		 * adding anything to the free_inc list we'll skip writing
+		 * prios/gens and just go back to allocating from the unused
+		 * list:
+		 */
+		if (fifo_full(&ca->unused))
+			return;
+
+		if (!can_invalidate_bucket(ca, b))
+			continue;
+
+		if (!GC_SECTORS_USED(b) &&
+		    bch_bucket_add_unused(ca, b))
+			continue;
+
+		if (!heap_full(&ca->heap))
+			heap_add(&ca->heap, b, bucket_max_cmp);
+		else if (bucket_max_cmp(b, heap_peek(&ca->heap))) {
+			ca->heap.data[0] = b;
+			heap_sift(&ca->heap, 0, bucket_max_cmp);
+		}
+	}
+
+	for (i = ca->heap.used / 2 - 1; i >= 0; --i)
+		heap_sift(&ca->heap, i, bucket_min_cmp);
+
+	while (!fifo_full(&ca->free_inc)) {
+		if (!heap_pop(&ca->heap, b, bucket_min_cmp)) {
+			/*
+			 * We don't want to be calling invalidate_buckets()
+			 * multiple times when it can't do anything
+			 */
+			ca->invalidate_needs_gc = 1;
+			bch_queue_gc(ca->set);
+			return;
+		}
+
+		invalidate_one_bucket(ca, b);
+	}
+}
+
+static void invalidate_buckets_fifo(struct cache *ca)
+{
+	struct bucket *b;
+	size_t checked = 0;
+
+	while (!fifo_full(&ca->free_inc)) {
+		if (ca->fifo_last_bucket <  ca->sb.first_bucket ||
+		    ca->fifo_last_bucket >= ca->sb.nbuckets)
+			ca->fifo_last_bucket = ca->sb.first_bucket;
+
+		b = ca->buckets + ca->fifo_last_bucket++;
+
+		if (can_invalidate_bucket(ca, b))
+			invalidate_one_bucket(ca, b);
+
+		if (++checked >= ca->sb.nbuckets) {
+			ca->invalidate_needs_gc = 1;
+			bch_queue_gc(ca->set);
+			return;
+		}
+	}
+}
+
+static void invalidate_buckets_random(struct cache *ca)
+{
+	struct bucket *b;
+	size_t checked = 0;
+
+	while (!fifo_full(&ca->free_inc)) {
+		size_t n;
+		get_random_bytes(&n, sizeof(n));
+
+		n %= (size_t) (ca->sb.nbuckets - ca->sb.first_bucket);
+		n += ca->sb.first_bucket;
+
+		b = ca->buckets + n;
+
+		if (can_invalidate_bucket(ca, b))
+			invalidate_one_bucket(ca, b);
+
+		if (++checked >= ca->sb.nbuckets / 2) {
+			ca->invalidate_needs_gc = 1;
+			bch_queue_gc(ca->set);
+			return;
+		}
+	}
+}
+
+static void invalidate_buckets(struct cache *ca)
+{
+	if (ca->invalidate_needs_gc)
+		return;
+
+	switch (CACHE_REPLACEMENT(&ca->sb)) {
+	case CACHE_REPLACEMENT_LRU:
+		invalidate_buckets_lru(ca);
+		break;
+	case CACHE_REPLACEMENT_FIFO:
+		invalidate_buckets_fifo(ca);
+		break;
+	case CACHE_REPLACEMENT_RANDOM:
+		invalidate_buckets_random(ca);
+		break;
+	}
+
+	pr_debug("free %zu/%zu free_inc %zu/%zu unused %zu/%zu",
+		 fifo_used(&ca->free), ca->free.size,
+		 fifo_used(&ca->free_inc), ca->free_inc.size,
+		 fifo_used(&ca->unused), ca->unused.size);
+}
+
+#define allocator_wait(ca, cond)					\
+do {									\
+	DEFINE_WAIT(__wait);						\
+									\
+	while (1) {							\
+		prepare_to_wait(&ca->set->alloc_wait,			\
+				&__wait, TASK_INTERRUPTIBLE);		\
+		if (cond)						\
+			break;						\
+									\
+		mutex_unlock(&(ca)->set->bucket_lock);			\
+		if (test_bit(CACHE_SET_STOPPING_2, &ca->set->flags)) {	\
+			finish_wait(&ca->set->alloc_wait, &__wait);	\
+			closure_return(cl);				\
+		}							\
+									\
+		schedule();						\
+		mutex_lock(&(ca)->set->bucket_lock);			\
+	}								\
+									\
+	finish_wait(&ca->set->alloc_wait, &__wait);			\
+} while (0)
+
+void bch_allocator_thread(struct closure *cl)
+{
+	struct cache *ca = container_of(cl, struct cache, alloc);
+
+	mutex_lock(&ca->set->bucket_lock);
+
+	while (1) {
+		/*
+		 * First, we pull buckets off of the unused and free_inc lists,
+		 * possibly issue discards to them, then we add the bucket to
+		 * the free list:
+		 */
+		while (1) {
+			long bucket;
+
+			if ((!atomic_read(&ca->set->prio_blocked) ||
+			     !CACHE_SYNC(&ca->set->sb)) &&
+			    !fifo_empty(&ca->unused))
+				fifo_pop(&ca->unused, bucket);
+			else if (!fifo_empty(&ca->free_inc))
+				fifo_pop(&ca->free_inc, bucket);
+			else
+				break;
+
+			allocator_wait(ca, (int) fifo_free(&ca->free) >
+				       atomic_read(&ca->discards_in_flight));
+
+			if (ca->discard) {
+				allocator_wait(ca, !list_empty(&ca->discards));
+				do_discard(ca, bucket);
+			} else {
+				fifo_push(&ca->free, bucket);
+				closure_wake_up(&ca->set->bucket_wait);
+			}
+		}
+
+		/*
+		 * We've run out of free buckets, we need to find some buckets
+		 * we can invalidate. First, invalidate them in memory and add
+		 * them to the free_inc list:
+		 */
+
+		allocator_wait(ca, ca->set->gc_mark_valid &&
+			       (ca->need_save_prio > 64 ||
+				!ca->invalidate_needs_gc));
+		invalidate_buckets(ca);
+
+		/*
+		 * Now, we write their new gens to disk so we can start writing
+		 * new stuff to them:
+		 */
+		allocator_wait(ca, !atomic_read(&ca->set->prio_blocked));
+		if (CACHE_SYNC(&ca->set->sb) &&
+		    (!fifo_empty(&ca->free_inc) ||
+		     ca->need_save_prio > 64))
+			bch_prio_write(ca);
+	}
+}
+
+long bch_bucket_alloc(struct cache *ca, unsigned watermark, struct closure *cl)
+{
+	long r = -1;
+again:
+	wake_up(&ca->set->alloc_wait);
+
+	if (fifo_used(&ca->free) > ca->watermark[watermark] &&
+	    fifo_pop(&ca->free, r)) {
+		struct bucket *b = ca->buckets + r;
+#ifdef CONFIG_BCACHE_EDEBUG
+		size_t iter;
+		long i;
+
+		for (iter = 0; iter < prio_buckets(ca) * 2; iter++)
+			BUG_ON(ca->prio_buckets[iter] == (uint64_t) r);
+
+		fifo_for_each(i, &ca->free, iter)
+			BUG_ON(i == r);
+		fifo_for_each(i, &ca->free_inc, iter)
+			BUG_ON(i == r);
+		fifo_for_each(i, &ca->unused, iter)
+			BUG_ON(i == r);
+#endif
+		BUG_ON(atomic_read(&b->pin) != 1);
+
+		SET_GC_SECTORS_USED(b, ca->sb.bucket_size);
+
+		if (watermark <= WATERMARK_METADATA) {
+			SET_GC_MARK(b, GC_MARK_METADATA);
+			b->prio = BTREE_PRIO;
+		} else {
+			SET_GC_MARK(b, GC_MARK_RECLAIMABLE);
+			b->prio = INITIAL_PRIO;
+		}
+
+		return r;
+	}
+
+	pr_debug("alloc failure: blocked %i free %zu free_inc %zu unused %zu",
+		 atomic_read(&ca->set->prio_blocked), fifo_used(&ca->free),
+		 fifo_used(&ca->free_inc), fifo_used(&ca->unused));
+
+	if (cl) {
+		closure_wait(&ca->set->bucket_wait, cl);
+
+		if (closure_blocking(cl)) {
+			mutex_unlock(&ca->set->bucket_lock);
+			closure_sync(cl);
+			mutex_lock(&ca->set->bucket_lock);
+			goto again;
+		}
+	}
+
+	return -1;
+}
+
+void bch_bucket_free(struct cache_set *c, struct bkey *k)
+{
+	unsigned i;
+
+	for (i = 0; i < KEY_PTRS(k); i++) {
+		struct bucket *b = PTR_BUCKET(c, k, i);
+
+		SET_GC_MARK(b, GC_MARK_RECLAIMABLE);
+		SET_GC_SECTORS_USED(b, 0);
+		bch_bucket_add_unused(PTR_CACHE(c, k, i), b);
+	}
+}
+
+int __bch_bucket_alloc_set(struct cache_set *c, unsigned watermark,
+			   struct bkey *k, int n, struct closure *cl)
+{
+	int i;
+
+	lockdep_assert_held(&c->bucket_lock);
+	BUG_ON(!n || n > c->caches_loaded || n > 8);
+
+	bkey_init(k);
+
+	/* sort by free space/prio of oldest data in caches */
+
+	for (i = 0; i < n; i++) {
+		struct cache *ca = c->cache_by_alloc[i];
+		long b = bch_bucket_alloc(ca, watermark, cl);
+
+		if (b == -1)
+			goto err;
+
+		k->ptr[i] = PTR(ca->buckets[b].gen,
+				bucket_to_sector(c, b),
+				ca->sb.nr_this_dev);
+
+		SET_KEY_PTRS(k, i + 1);
+	}
+
+	return 0;
+err:
+	bch_bucket_free(c, k);
+	__bkey_put(c, k);
+	return -1;
+}
+
+int bch_bucket_alloc_set(struct cache_set *c, unsigned watermark,
+			 struct bkey *k, int n, struct closure *cl)
+{
+	int ret;
+	mutex_lock(&c->bucket_lock);
+	ret = __bch_bucket_alloc_set(c, watermark, k, n, cl);
+	mutex_unlock(&c->bucket_lock);
+	return ret;
+}
+
+/* Init */
+
+void bch_cache_allocator_exit(struct cache *ca)
+{
+	struct discard *d;
+
+	while (!list_empty(&ca->discards)) {
+		d = list_first_entry(&ca->discards, struct discard, list);
+		cancel_work_sync(&d->work);
+		list_del(&d->list);
+		kfree(d);
+	}
+}
+
+int bch_cache_allocator_init(struct cache *ca)
+{
+	unsigned i;
+
+	/*
+	 * Reserve:
+	 * Prio/gen writes first
+	 * Then 8 for btree allocations
+	 * Then half for the moving garbage collector
+	 */
+
+	ca->watermark[WATERMARK_PRIO] = 0;
+
+	ca->watermark[WATERMARK_METADATA] = prio_buckets(ca);
+
+	ca->watermark[WATERMARK_MOVINGGC] = 8 +
+		ca->watermark[WATERMARK_METADATA];
+
+	ca->watermark[WATERMARK_NONE] = ca->free.size / 2 +
+		ca->watermark[WATERMARK_MOVINGGC];
+
+	for (i = 0; i < MAX_IN_FLIGHT_DISCARDS; i++) {
+		struct discard *d = kzalloc(sizeof(*d), GFP_KERNEL);
+		if (!d)
+			return -ENOMEM;
+
+		d->ca = ca;
+		INIT_WORK(&d->work, discard_finish);
+		list_add(&d->list, &ca->discards);
+	}
+
+	return 0;
+}

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);