Merge tag 'for-6.9/dm-vdo' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm

Pull device mapper VDO target from Mike Snitzer:
 "Introduce the DM vdo target which provides block-level deduplication,
  compression, and thin provisioning. Please see:

      Documentation/admin-guide/device-mapper/vdo.rst
      Documentation/admin-guide/device-mapper/vdo-design.rst

  The DM vdo target handles its concurrency by pinning an IO, and
  subsequent stages of handling that IO, to a particular VDO thread.
  This aspect of VDO is "unique" but its overall implementation is very
  tightly coupled to its mostly lockless threading model. As such, VDO
  is not easily changed to use more traditional finer-grained locking
  and Linux workqueues. Please see the "Zones and Threading" section of
  vdo-design.rst

  The DM vdo target has been used in production for many years but has
  seen significant changes over the past ~6 years to prepare it for
  upstream inclusion. The codebase is still large but it is isolated to
  drivers/md/dm-vdo/ and has been made considerably more approachable
  and maintainable.

  Matt Sakai has been added to the MAINTAINERS file to reflect that he
  will send VDO changes upstream through the DM subsystem maintainers"

* tag 'for-6.9/dm-vdo' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm: (142 commits)
  dm vdo: document minimum metadata size requirements
  dm vdo: remove meaningless version number constant
  dm vdo: remove vdo_perform_once
  dm vdo block-map: Remove stray semicolon
  dm vdo string-utils: change from uds_ to vdo_ namespace
  dm vdo logger: change from uds_ to vdo_ namespace
  dm vdo funnel-queue: change from uds_ to vdo_ namespace
  dm vdo indexer: fix use after free
  dm vdo logger: remove log level to string conversion code
  dm vdo: document log_level parameter
  dm vdo: add 'log_level' module parameter
  dm vdo: remove all sysfs interfaces
  dm vdo target: eliminate inappropriate uses of UDS_SUCCESS
  dm vdo indexer: update ASSERT and ASSERT_LOG_ONLY usage
  dm vdo encodings: update some stale comments
  dm vdo permassert: audit all of ASSERT to test for VDO_SUCCESS
  dm-vdo funnel-workqueue: return VDO_SUCCESS from make_simple_work_queue
  dm vdo thread-utils: return VDO_SUCCESS on vdo_create_thread success
  dm vdo int-map: return VDO_SUCCESS on success
  dm vdo: check for VDO_SUCCESS return value from memory-alloc functions
  ...

1 files changed, 115 insertions, 0 deletions

diff --git a/drivers/md/dm-vdo/physical-zone.h b/drivers/md/dm-vdo/physical-zone.h
new file mode 100644
index 000000000000..47d874fd5a0b
--- /dev/null
+++ b/drivers/md/dm-vdo/physical-zone.h
@@ -0,0 +1,115 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright 2023 Red Hat
+ */
+
+#ifndef VDO_PHYSICAL_ZONE_H
+#define VDO_PHYSICAL_ZONE_H
+
+#include <linux/atomic.h>
+
+#include "types.h"
+
+/*
+ * The type of a PBN lock.
+ */
+enum pbn_lock_type {
+	VIO_READ_LOCK,
+	VIO_WRITE_LOCK,
+	VIO_BLOCK_MAP_WRITE_LOCK,
+};
+
+struct pbn_lock_implementation;
+
+/*
+ * A PBN lock.
+ */
+struct pbn_lock {
+	/* The implementation of the lock */
+	const struct pbn_lock_implementation *implementation;
+
+	/* The number of VIOs holding or sharing this lock */
+	data_vio_count_t holder_count;
+	/*
+	 * The number of compressed block writers holding a share of this lock while they are
+	 * acquiring a reference to the PBN.
+	 */
+	u8 fragment_locks;
+
+	/* Whether the locked PBN has been provisionally referenced on behalf of the lock holder. */
+	bool has_provisional_reference;
+
+	/*
+	 * For read locks, the number of references that were known to be available on the locked
+	 * block at the time the lock was acquired.
+	 */
+	u8 increment_limit;
+
+	/*
+	 * For read locks, the number of data_vios that have tried to claim one of the available
+	 * increments during the lifetime of the lock. Each claim will first increment this
+	 * counter, so it can exceed the increment limit.
+	 */
+	atomic_t increments_claimed;
+};
+
+struct physical_zone {
+	/* Which physical zone this is */
+	zone_count_t zone_number;
+	/* The thread ID for this zone */
+	thread_id_t thread_id;
+	/* In progress operations keyed by PBN */
+	struct int_map *pbn_operations;
+	/* Pool of unused pbn_lock instances */
+	struct pbn_lock_pool *lock_pool;
+	/* The block allocator for this zone */
+	struct block_allocator *allocator;
+	/* The next zone from which to attempt an allocation */
+	struct physical_zone *next;
+};
+
+struct physical_zones {
+	/* The number of zones */
+	zone_count_t zone_count;
+	/* The physical zones themselves */
+	struct physical_zone zones[];
+};
+
+bool __must_check vdo_is_pbn_read_lock(const struct pbn_lock *lock);
+void vdo_downgrade_pbn_write_lock(struct pbn_lock *lock, bool compressed_write);
+bool __must_check vdo_claim_pbn_lock_increment(struct pbn_lock *lock);
+
+/**
+ * vdo_pbn_lock_has_provisional_reference() - Check whether a PBN lock has a provisional reference.
+ * @lock: The PBN lock.
+ */
+static inline bool vdo_pbn_lock_has_provisional_reference(struct pbn_lock *lock)
+{
+	return ((lock != NULL) && lock->has_provisional_reference);
+}
+
+void vdo_assign_pbn_lock_provisional_reference(struct pbn_lock *lock);
+void vdo_unassign_pbn_lock_provisional_reference(struct pbn_lock *lock);
+
+int __must_check vdo_make_physical_zones(struct vdo *vdo,
+					 struct physical_zones **zones_ptr);
+
+void vdo_free_physical_zones(struct physical_zones *zones);
+
+struct pbn_lock * __must_check vdo_get_physical_zone_pbn_lock(struct physical_zone *zone,
+							      physical_block_number_t pbn);
+
+int __must_check vdo_attempt_physical_zone_pbn_lock(struct physical_zone *zone,
+						    physical_block_number_t pbn,
+						    enum pbn_lock_type type,
+						    struct pbn_lock **lock_ptr);
+
+bool __must_check vdo_allocate_block_in_zone(struct data_vio *data_vio);
+
+void vdo_release_physical_zone_pbn_lock(struct physical_zone *zone,
+					physical_block_number_t locked_pbn,
+					struct pbn_lock *lock);
+
+void vdo_dump_physical_zone(const struct physical_zone *zone);
+
+#endif /* VDO_PHYSICAL_ZONE_H */