Merge tag 'for-4.12/dm-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm

Pull device mapper updates from Mike Snitzer:

 - A major update for DM cache that reduces the latency for deciding
   whether blocks should migrate to/from the cache. The bio-prison-v2
   interface supports this improvement by enabling direct dispatch of
   work to workqueues rather than having to delay the actual work
   dispatch to the DM cache core. So the dm-cache policies are much more
   nimble by being able to drive IO as they see fit. One immediate
   benefit from the improved latency is a cache that should be much more
   adaptive to changing workloads.

 - Add a new DM integrity target that emulates a block device that has
   additional per-sector tags that can be used for storing integrity
   information.

 - Add a new authenticated encryption feature to the DM crypt target
   that builds on the capabilities provided by the DM integrity target.

 - Add MD interface for switching the raid4/5/6 journal mode and update
   the DM raid target to use it to enable aid4/5/6 journal write-back
   support.

 - Switch the DM verity target over to using the asynchronous hash
   crypto API (this helps work better with architectures that have
   access to off-CPU algorithm providers, which should reduce CPU
   utilization).

 - Various request-based DM and DM multipath fixes and improvements from
   Bart and Christoph.

 - A DM thinp target fix for a bio structure leak that occurs for each
   discard IFF discard passdown is enabled.

 - A fix for a possible deadlock in DM bufio and a fix to re-check the
   new buffer allocation watermark in the face of competing admin
   changes to the 'max_cache_size_bytes' tunable.

 - A couple DM core cleanups.

* tag 'for-4.12/dm-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm: (50 commits)
  dm bufio: check new buffer allocation watermark every 30 seconds
  dm bufio: avoid a possible ABBA deadlock
  dm mpath: make it easier to detect unintended I/O request flushes
  dm mpath: cleanup QUEUE_IF_NO_PATH bit manipulation by introducing assign_bit()
  dm mpath: micro-optimize the hot path relative to MPATHF_QUEUE_IF_NO_PATH
  dm: introduce enum dm_queue_mode to cleanup related code
  dm mpath: verify __pg_init_all_paths locking assumptions at runtime
  dm: verify suspend_locking assumptions at runtime
  dm block manager: remove an unused argument from dm_block_manager_create()
  dm rq: check blk_mq_register_dev() return value in dm_mq_init_request_queue()
  dm mpath: delay requeuing while path initialization is in progress
  dm mpath: avoid that path removal can trigger an infinite loop
  dm mpath: split and rename activate_path() to prepare for its expanded use
  dm ioctl: prevent stack leak in dm ioctl call
  dm integrity: use previously calculated log2 of sectors_per_block
  dm integrity: use hex2bin instead of open-coded variant
  dm crypt: replace custom implementation of hex2bin()
  dm crypt: remove obsolete references to per-CPU state
  dm verity: switch to using asynchronous hash crypto API
  dm crypt: use WQ_HIGHPRI for the IO and crypt workqueues
  ...

1 files changed, 54 insertions, 133 deletions

diff --git a/drivers/md/dm-cache-policy.h b/drivers/md/dm-cache-policy.h
index aa10b1493f34..c05fc3436cef 100644
--- a/drivers/md/dm-cache-policy.h
+++ b/drivers/md/dm-cache-policy.h
@@ -13,183 +13,100 @@
 
 /*----------------------------------------------------------------*/
 
-/* FIXME: make it clear which methods are optional.  Get debug policy to
- * double check this at start.
- */
-
 /*
  * The cache policy makes the important decisions about which blocks get to
  * live on the faster cache device.
- *
- * When the core target has to remap a bio it calls the 'map' method of the
- * policy.  This returns an instruction telling the core target what to do.
- *
- * POLICY_HIT:
- *   That block is in the cache.  Remap to the cache and carry on.
- *
- * POLICY_MISS:
- *   This block is on the origin device.  Remap and carry on.
- *
- * POLICY_NEW:
- *   This block is currently on the origin device, but the policy wants to
- *   move it.  The core should:
- *
- *   - hold any further io to this origin block
- *   - copy the origin to the given cache block
- *   - release all the held blocks
- *   - remap the original block to the cache
- *
- * POLICY_REPLACE:
- *   This block is currently on the origin device.  The policy wants to
- *   move it to the cache, with the added complication that the destination
- *   cache block needs a writeback first.  The core should:
- *
- *   - hold any further io to this origin block
- *   - hold any further io to the origin block that's being written back
- *   - writeback
- *   - copy new block to cache
- *   - release held blocks
- *   - remap bio to cache and reissue.
- *
- * Should the core run into trouble while processing a POLICY_NEW or
- * POLICY_REPLACE instruction it will roll back the policies mapping using
- * remove_mapping() or force_mapping().  These methods must not fail.  This
- * approach avoids having transactional semantics in the policy (ie, the
- * core informing the policy when a migration is complete), and hence makes
- * it easier to write new policies.
- *
- * In general policy methods should never block, except in the case of the
- * map function when can_migrate is set.  So be careful to implement using
- * bounded, preallocated memory.
  */
 enum policy_operation {
-	POLICY_HIT,
-	POLICY_MISS,
-	POLICY_NEW,
-	POLICY_REPLACE
-};
-
-/*
- * When issuing a POLICY_REPLACE the policy needs to make a callback to
- * lock the block being demoted.  This doesn't need to occur during a
- * writeback operation since the block remains in the cache.
- */
-struct policy_locker;
-typedef int (*policy_lock_fn)(struct policy_locker *l, dm_oblock_t oblock);
-
-struct policy_locker {
-	policy_lock_fn fn;
+	POLICY_PROMOTE,
+	POLICY_DEMOTE,
+	POLICY_WRITEBACK
 };
 
 /*
  * This is the instruction passed back to the core target.
  */
-struct policy_result {
+struct policy_work {
 	enum policy_operation op;
-	dm_oblock_t old_oblock;	/* POLICY_REPLACE */
-	dm_cblock_t cblock;	/* POLICY_HIT, POLICY_NEW, POLICY_REPLACE */
+	dm_oblock_t oblock;
+	dm_cblock_t cblock;
 };
 
 /*
- * The cache policy object.  Just a bunch of methods.  It is envisaged that
- * this structure will be embedded in a bigger, policy specific structure
- * (ie. use container_of()).
+ * The cache policy object.  It is envisaged that this structure will be
+ * embedded in a bigger, policy specific structure (ie. use container_of()).
  */
 struct dm_cache_policy {
-
-	/*
-	 * FIXME: make it clear which methods are optional, and which may
-	 * block.
-	 */
-
 	/*
 	 * Destroys this object.
 	 */
 	void (*destroy)(struct dm_cache_policy *p);
 
 	/*
-	 * See large comment above.
-	 *
-	 * oblock      - the origin block we're interested in.
-	 *
-	 * can_block - indicates whether the current thread is allowed to
-	 *             block.  -EWOULDBLOCK returned if it can't and would.
-	 *
-	 * can_migrate - gives permission for POLICY_NEW or POLICY_REPLACE
-	 *               instructions.  If denied and the policy would have
-	 *               returned one of these instructions it should
-	 *               return -EWOULDBLOCK.
+	 * Find the location of a block.
 	 *
-	 * discarded_oblock - indicates whether the whole origin block is
-	 *               in a discarded state (FIXME: better to tell the
-	 *               policy about this sooner, so it can recycle that
-	 *               cache block if it wants.)
-	 * bio         - the bio that triggered this call.
-	 * result      - gets filled in with the instruction.
+	 * Must not block.
 	 *
-	 * May only return 0, or -EWOULDBLOCK (if !can_migrate)
+	 * Returns 0 if in cache (cblock will be set), -ENOENT if not, < 0 for
+	 * other errors (-EWOULDBLOCK would be typical).  data_dir should be
+	 * READ or WRITE. fast_copy should be set if migrating this block would
+	 * be 'cheap' somehow (eg, discarded data). background_queued will be set
+	 * if a migration has just been queued.
 	 */
-	int (*map)(struct dm_cache_policy *p, dm_oblock_t oblock,
-		   bool can_block, bool can_migrate, bool discarded_oblock,
-		   struct bio *bio, struct policy_locker *locker,
-		   struct policy_result *result);
+	int (*lookup)(struct dm_cache_policy *p, dm_oblock_t oblock, dm_cblock_t *cblock,
+		      int data_dir, bool fast_copy, bool *background_queued);
 
 	/*
-	 * Sometimes we want to see if a block is in the cache, without
-	 * triggering any update of stats.  (ie. it's not a real hit).
-	 *
-	 * Must not block.
+	 * Sometimes the core target can optimise a migration, eg, the
+	 * block may be discarded, or the bio may cover an entire block.
+	 * In order to optimise it needs the migration immediately though
+	 * so it knows to do something different with the bio.
 	 *
-	 * Returns 0 if in cache, -ENOENT if not, < 0 for other errors
-	 * (-EWOULDBLOCK would be typical).
+	 * This method is optional (policy-internal will fallback to using
+	 * lookup).
 	 */
-	int (*lookup)(struct dm_cache_policy *p, dm_oblock_t oblock, dm_cblock_t *cblock);
-
-	void (*set_dirty)(struct dm_cache_policy *p, dm_oblock_t oblock);
-	void (*clear_dirty)(struct dm_cache_policy *p, dm_oblock_t oblock);
+	int (*lookup_with_work)(struct dm_cache_policy *p,
+				dm_oblock_t oblock, dm_cblock_t *cblock,
+				int data_dir, bool fast_copy,
+				struct policy_work **work);
 
 	/*
-	 * Called when a cache target is first created.  Used to load a
-	 * mapping from the metadata device into the policy.
+	 * Retrieves background work.  Returns -ENODATA when there's no
+	 * background work.
 	 */
-	int (*load_mapping)(struct dm_cache_policy *p, dm_oblock_t oblock,
-			    dm_cblock_t cblock, uint32_t hint, bool hint_valid);
+	int (*get_background_work)(struct dm_cache_policy *p, bool idle,
+			           struct policy_work **result);
 
 	/*
-	 * Gets the hint for a given cblock.  Called in a single threaded
-	 * context.  So no locking required.
+	 * You must pass in the same work pointer that you were given, not
+	 * a copy.
 	 */
-	uint32_t (*get_hint)(struct dm_cache_policy *p, dm_cblock_t cblock);
+	void (*complete_background_work)(struct dm_cache_policy *p,
+					 struct policy_work *work,
+					 bool success);
+
+	void (*set_dirty)(struct dm_cache_policy *p, dm_cblock_t cblock);
+	void (*clear_dirty)(struct dm_cache_policy *p, dm_cblock_t cblock);
 
 	/*
-	 * Override functions used on the error paths of the core target.
-	 * They must succeed.
+	 * Called when a cache target is first created.  Used to load a
+	 * mapping from the metadata device into the policy.
 	 */
-	void (*remove_mapping)(struct dm_cache_policy *p, dm_oblock_t oblock);
-	void (*force_mapping)(struct dm_cache_policy *p, dm_oblock_t current_oblock,
-			      dm_oblock_t new_oblock);
+	int (*load_mapping)(struct dm_cache_policy *p, dm_oblock_t oblock,
+			    dm_cblock_t cblock, bool dirty,
+			    uint32_t hint, bool hint_valid);
 
 	/*
-	 * This is called via the invalidate_cblocks message.  It is
-	 * possible the particular cblock has already been removed due to a
-	 * write io in passthrough mode.  In which case this should return
-	 * -ENODATA.
+	 * Drops the mapping, irrespective of whether it's clean or dirty.
+	 * Returns -ENODATA if cblock is not mapped.
 	 */
-	int (*remove_cblock)(struct dm_cache_policy *p, dm_cblock_t cblock);
+	int (*invalidate_mapping)(struct dm_cache_policy *p, dm_cblock_t cblock);
 
 	/*
-	 * Provide a dirty block to be written back by the core target.  If
-	 * critical_only is set then the policy should only provide work if
-	 * it urgently needs it.
-	 *
-	 * Returns:
-	 *
-	 * 0 and @cblock,@oblock: block to write back provided
-	 *
-	 * -ENODATA: no dirty blocks available
+	 * Gets the hint for a given cblock.  Called in a single threaded
+	 * context.  So no locking required.
 	 */
-	int (*writeback_work)(struct dm_cache_policy *p, dm_oblock_t *oblock, dm_cblock_t *cblock,
-			      bool critical_only);
+	uint32_t (*get_hint)(struct dm_cache_policy *p, dm_cblock_t cblock);
 
 	/*
 	 * How full is the cache?
@@ -202,6 +119,8 @@ struct dm_cache_policy {
 	 * queue merging has occurred).  To stop the policy being fooled by
 	 * these, the core target sends regular tick() calls to the policy.
 	 * The policy should only count an entry as hit once per tick.
+	 *
+	 * This method is optional.
 	 */
 	void (*tick)(struct dm_cache_policy *p, bool can_block);
 
@@ -213,6 +132,8 @@ struct dm_cache_policy {
 	int (*set_config_value)(struct dm_cache_policy *p,
 				const char *key, const char *value);
 
+	void (*allow_migrations)(struct dm_cache_policy *p, bool allow);
+
 	/*
 	 * Book keeping ptr for the policy register, not for general use.
 	 */