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, 238 insertions, 0 deletions

diff --git a/drivers/md/dm-cache-background-tracker.c b/drivers/md/dm-cache-background-tracker.c
new file mode 100644
index 000000000000..9b1afdfb13f0
--- /dev/null
+++ b/drivers/md/dm-cache-background-tracker.c
@@ -0,0 +1,238 @@
+/*
+ * Copyright (C) 2017 Red Hat. All rights reserved.
+ *
+ * This file is released under the GPL.
+ */
+
+#include "dm-cache-background-tracker.h"
+
+/*----------------------------------------------------------------*/
+
+#define DM_MSG_PREFIX "dm-background-tracker"
+
+struct bt_work {
+	struct list_head list;
+	struct rb_node node;
+	struct policy_work work;
+};
+
+struct background_tracker {
+	unsigned max_work;
+	atomic_t pending_promotes;
+	atomic_t pending_writebacks;
+	atomic_t pending_demotes;
+
+	struct list_head issued;
+	struct list_head queued;
+	struct rb_root pending;
+
+	struct kmem_cache *work_cache;
+};
+
+struct background_tracker *btracker_create(unsigned max_work)
+{
+	struct background_tracker *b = kmalloc(sizeof(*b), GFP_KERNEL);
+
+	b->max_work = max_work;
+	atomic_set(&b->pending_promotes, 0);
+	atomic_set(&b->pending_writebacks, 0);
+	atomic_set(&b->pending_demotes, 0);
+
+	INIT_LIST_HEAD(&b->issued);
+	INIT_LIST_HEAD(&b->queued);
+
+	b->pending = RB_ROOT;
+	b->work_cache = KMEM_CACHE(bt_work, 0);
+	if (!b->work_cache) {
+		DMERR("couldn't create mempool for background work items");
+		kfree(b);
+		b = NULL;
+	}
+
+	return b;
+}
+EXPORT_SYMBOL_GPL(btracker_create);
+
+void btracker_destroy(struct background_tracker *b)
+{
+	kmem_cache_destroy(b->work_cache);
+	kfree(b);
+}
+EXPORT_SYMBOL_GPL(btracker_destroy);
+
+static int cmp_oblock(dm_oblock_t lhs, dm_oblock_t rhs)
+{
+	if (from_oblock(lhs) < from_oblock(rhs))
+		return -1;
+
+	if (from_oblock(rhs) < from_oblock(lhs))
+		return 1;
+
+	return 0;
+}
+
+static bool __insert_pending(struct background_tracker *b,
+			     struct bt_work *nw)
+{
+	int cmp;
+	struct bt_work *w;
+	struct rb_node **new = &b->pending.rb_node, *parent = NULL;
+
+	while (*new) {
+		w = container_of(*new, struct bt_work, node);
+
+		parent = *new;
+		cmp = cmp_oblock(w->work.oblock, nw->work.oblock);
+		if (cmp < 0)
+			new = &((*new)->rb_left);
+
+		else if (cmp > 0)
+			new = &((*new)->rb_right);
+
+		else
+			/* already present */
+			return false;
+	}
+
+	rb_link_node(&nw->node, parent, new);
+	rb_insert_color(&nw->node, &b->pending);
+
+	return true;
+}
+
+static struct bt_work *__find_pending(struct background_tracker *b,
+				      dm_oblock_t oblock)
+{
+	int cmp;
+	struct bt_work *w;
+	struct rb_node **new = &b->pending.rb_node;
+
+	while (*new) {
+		w = container_of(*new, struct bt_work, node);
+
+		cmp = cmp_oblock(w->work.oblock, oblock);
+		if (cmp < 0)
+			new = &((*new)->rb_left);
+
+		else if (cmp > 0)
+			new = &((*new)->rb_right);
+
+		else
+			break;
+	}
+
+	return *new ? w : NULL;
+}
+
+
+static void update_stats(struct background_tracker *b, struct policy_work *w, int delta)
+{
+	switch (w->op) {
+	case POLICY_PROMOTE:
+		atomic_add(delta, &b->pending_promotes);
+		break;
+
+	case POLICY_DEMOTE:
+		atomic_add(delta, &b->pending_demotes);
+		break;
+
+	case POLICY_WRITEBACK:
+		atomic_add(delta, &b->pending_writebacks);
+		break;
+	}
+}
+
+unsigned btracker_nr_writebacks_queued(struct background_tracker *b)
+{
+	return atomic_read(&b->pending_writebacks);
+}
+EXPORT_SYMBOL_GPL(btracker_nr_writebacks_queued);
+
+unsigned btracker_nr_demotions_queued(struct background_tracker *b)
+{
+	return atomic_read(&b->pending_demotes);
+}
+EXPORT_SYMBOL_GPL(btracker_nr_demotions_queued);
+
+static bool max_work_reached(struct background_tracker *b)
+{
+	// FIXME: finish
+	return false;
+}
+
+int btracker_queue(struct background_tracker *b,
+		   struct policy_work *work,
+		   struct policy_work **pwork)
+{
+	struct bt_work *w;
+
+	if (pwork)
+		*pwork = NULL;
+
+	if (max_work_reached(b))
+		return -ENOMEM;
+
+	w = kmem_cache_alloc(b->work_cache, GFP_NOWAIT);
+	if (!w)
+		return -ENOMEM;
+
+	memcpy(&w->work, work, sizeof(*work));
+
+	if (!__insert_pending(b, w)) {
+		/*
+		 * There was a race, we'll just ignore this second
+		 * bit of work for the same oblock.
+		 */
+		kmem_cache_free(b->work_cache, w);
+		return -EINVAL;
+	}
+
+	if (pwork) {
+		*pwork = &w->work;
+		list_add(&w->list, &b->issued);
+	} else
+		list_add(&w->list, &b->queued);
+	update_stats(b, &w->work, 1);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(btracker_queue);
+
+/*
+ * Returns -ENODATA if there's no work.
+ */
+int btracker_issue(struct background_tracker *b, struct policy_work **work)
+{
+	struct bt_work *w;
+
+	if (list_empty(&b->queued))
+		return -ENODATA;
+
+	w = list_first_entry(&b->queued, struct bt_work, list);
+	list_move(&w->list, &b->issued);
+	*work = &w->work;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(btracker_issue);
+
+void btracker_complete(struct background_tracker *b,
+		       struct policy_work *op)
+{
+	struct bt_work *w = container_of(op, struct bt_work, work);
+
+	update_stats(b, &w->work, -1);
+	rb_erase(&w->node, &b->pending);
+	list_del(&w->list);
+	kmem_cache_free(b->work_cache, w);
+}
+EXPORT_SYMBOL_GPL(btracker_complete);
+
+bool btracker_promotion_already_present(struct background_tracker *b,
+					dm_oblock_t oblock)
+{
+	return __find_pending(b, oblock) != NULL;
+}
+EXPORT_SYMBOL_GPL(btracker_promotion_already_present);
+
+/*----------------------------------------------------------------*/