dm-pcache: add persistent cache target in device-mapper

This patch introduces dm-pcache, a new DM target that places a DAX-
capable persistent-memory device in front of any slower block device and
uses it as a high-throughput, low-latency  cache.

Design highlights
-----------------
- DAX data path – data is copied directly between DRAM and the pmem
  mapping, bypassing the block layer’s overhead.

- Segmented, crash-consistent layout
  - all layout metadata are dual-replicated CRC-protected.
  - atomic kset flushes; key replay on mount guarantees cache integrity
    even after power loss.

- Striped multi-tree index
  - Multi‑tree indexing for high parallelism.
  - overlap-resolution logic ensures non-intersecting cached extents.

- Background services
  - write-back worker flushes dirty keys in order, preserving backing-device
    crash consistency. This is important for checkpoint in cloud storage.
  - garbage collector reclaims clean segments when utilisation exceeds a
    tunable threshold.

- Data integrity – optional CRC32 on cached payload; metadata always protected.

Comparison with existing block-level caches
---------------------------------------------------------------------------------------------------------------------------------
| Feature                          | pcache (this patch)             | bcache                       | dm-writecache             |
|----------------------------------|---------------------------------|------------------------------|---------------------------|
| pmem access method               | DAX                             | bio (block I/O)              | DAX                       |
| Write latency (4 K rand-write)   | ~5 µs                           | ~20 µs                       | ~5 µs                     |
| Concurrency                      | multi subtree index             | global index tree            | single tree + wc_lock     |
| IOPS (4K randwrite, 32 numjobs)  | 2.1 M                           | 352 K                        | 283 K                     |
| Read-cache support               | YES                             | YES                          | NO                        |
| Deployment                       | no re-format of backend         | backend devices must be      | no re-format of backend   |
|                                  |                                 | reformatted                  |                           |
| Write-back ordering              | log-structured;                 | no ordering guarantee        | no ordering guarantee     |
|                                  | preserves app-IO-order          |                              |                           |
| Data integrity checks            | metadata + data CRC(optional)   | metadata CRC only            | none                      |
---------------------------------------------------------------------------------------------------------------------------------

Signed-off-by: Dongsheng Yang <dongsheng.yang@linux.dev>
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>

Documentation/admin-guide/device-mapper/dm-pcache.rst

@@ -0,0 +1,202 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+=================================
+dm-pcache — Persistent Cache
+=================================
+
+*Author: Dongsheng Yang <dongsheng.yang@linux.dev>*
+
+This document describes *dm-pcache*, a Device-Mapper target that lets a
+byte-addressable *DAX* (persistent-memory, “pmem”) region act as a
+high-performance, crash-persistent cache in front of a slower block
+device.  The code lives in `drivers/md/dm-pcache/`.
+
+Quick feature summary
+=====================
+
+* *Write-back* caching (only mode currently supported).
+* *16 MiB segments* allocated on the pmem device.
+* *Data CRC32* verification (optional, per cache).
+* Crash-safe: every metadata structure is duplicated (`PCACHE_META_INDEX_MAX
+  == 2`) and protected with CRC+sequence numbers.
+* *Multi-tree indexing* (indexing trees sharded by logical address) for high PMem parallelism
+* Pure *DAX path* I/O – no extra BIO round-trips
+* *Log-structured write-back* that preserves backend crash-consistency
+
+
+Constructor
+===========
+
+::
+
+    pcache <cache_dev> <backing_dev> [<number_of_optional_arguments> <cache_mode writeback> <data_crc true|false>]
+
+=========================  ====================================================
+``cache_dev``               Any DAX-capable block device (``/dev/pmem0``…).
+                            All metadata *and* cached blocks are stored here.
+
+``backing_dev``             The slow block device to be cached.
+
+``cache_mode``              Optional, Only ``writeback`` is accepted at the
+                            moment.
+
+``data_crc``                Optional, default to ``false``
+
+                            * ``true``  – store CRC32 for every cached entry
+			      and verify on reads
+                            * ``false`` – skip CRC (faster)
+=========================  ====================================================
+
+Example
+-------
+
+.. code-block:: shell
+
+   dmsetup create pcache_sdb --table \
+     "0 $(blockdev --getsz /dev/sdb) pcache /dev/pmem0 /dev/sdb 4 cache_mode writeback data_crc true"
+
+The first time a pmem device is used, dm-pcache formats it automatically
+(super-block, cache_info, etc.).
+
+
+Status line
+===========
+
+``dmsetup status <device>`` (``STATUSTYPE_INFO``) prints:
+
+::
+
+   <sb_flags> <seg_total> <cache_segs> <segs_used> \
+   <gc_percent> <cache_flags> \
+   <key_head_seg>:<key_head_off> \
+   <dirty_tail_seg>:<dirty_tail_off> \
+   <key_tail_seg>:<key_tail_off>
+
+Field meanings
+--------------
+
+===============================  =============================================
+``sb_flags``                     Super-block flags (e.g. endian marker).
+
+``seg_total``                    Number of physical *pmem* segments.
+
+``cache_segs``                   Number of segments used for cache.
+
+``segs_used``                    Segments currently allocated (bitmap weight).
+
+``gc_percent``                   Current GC high-water mark (0-90).
+
+``cache_flags``                  Bit 0 – DATA_CRC enabled
+                                 Bit 1 – INIT_DONE (cache initialised)
+                                 Bits 2-5 – cache mode (0 == WB).
+
+``key_head``                     Where new key-sets are being written.
+
+``dirty_tail``                   First dirty key-set that still needs
+                                 write-back to the backing device.
+
+``key_tail``                     First key-set that may be reclaimed by GC.
+===============================  =============================================
+
+
+Messages
+========
+
+*Change GC trigger*
+
+::
+
+   dmsetup message <dev> 0 gc_percent <0-90>
+
+
+Theory of operation
+===================
+
+Sub-devices
+-----------
+
+====================  =========================================================
+backing_dev             Any block device (SSD/HDD/loop/LVM, etc.).
+cache_dev               DAX device; must expose direct-access memory.
+====================  =========================================================
+
+Segments and key-sets
+---------------------
+
+* The pmem space is divided into *16 MiB segments*.
+* Each write allocates space from a per-CPU *data_head* inside a segment.
+* A *cache-key* records a logical range on the origin and where it lives
+  inside pmem (segment + offset + generation).
+* 128 keys form a *key-set* (kset); ksets are written sequentially in pmem
+  and are themselves crash-safe (CRC).
+* The pair *(key_tail, dirty_tail)* delimit clean/dirty and live/dead ksets.
+
+Write-back
+----------
+
+Dirty keys are queued into a tree; a background worker copies data
+back to the backing_dev and advances *dirty_tail*.  A FLUSH/FUA bio from the
+upper layers forces an immediate metadata commit.
+
+Garbage collection
+------------------
+
+GC starts when ``segs_used >= seg_total * gc_percent / 100``.  It walks
+from *key_tail*, frees segments whose every key has been invalidated, and
+advances *key_tail*.
+
+CRC verification
+----------------
+
+If ``data_crc is enabled`` dm-pcache computes a CRC32 over every cached data
+range when it is inserted and stores it in the on-media key.  Reads
+validate the CRC before copying to the caller.
+
+
+Failure handling
+================
+
+* *pmem media errors* – all metadata copies are read with
+  ``copy_mc_to_kernel``; an uncorrectable error logs and aborts initialisation.
+* *Cache full* – if no free segment can be found, writes return ``-EBUSY``;
+  dm-pcache retries internally (request deferral).
+* *System crash* – on attach, the driver replays ksets from *key_tail* to
+  rebuild the in-core trees; every segment’s generation guards against
+  use-after-free keys.
+
+
+Limitations & TODO
+==================
+
+* Only *write-back* mode; other modes planned.
+* Only FIFO cache invalidate; other (LRU, ARC...) planned.
+* Table reload is not supported currently.
+* Discard planned.
+
+
+Example workflow
+================
+
+.. code-block:: shell
+
+   # 1.  Create devices
+   dmsetup create pcache_sdb --table \
+     "0 $(blockdev --getsz /dev/sdb) pcache /dev/pmem0 /dev/sdb 4 cache_mode writeback data_crc true"
+
+   # 2.  Put a filesystem on top
+   mkfs.ext4 /dev/mapper/pcache_sdb
+   mount /dev/mapper/pcache_sdb /mnt
+
+   # 3.  Tune GC threshold to 80 %
+   dmsetup message pcache_sdb 0 gc_percent 80
+
+   # 4.  Observe status
+   watch -n1 'dmsetup status pcache_sdb'
+
+   # 5.  Shutdown
+   umount /mnt
+   dmsetup remove pcache_sdb
+
+
+``dm-pcache`` is under active development; feedback, bug reports and patches
+are very welcome!

Documentation/admin-guide/device-mapper/index.rst

@@ -18,6 +18,7 @@ Device Mapper
     dm-integrity
     dm-io
     dm-log
+    dm-pcache
     dm-queue-length
     dm-raid
     dm-service-time

MAINTAINERS

@@ -7051,6 +7051,14 @@ S:	Maintained
 F:	Documentation/admin-guide/device-mapper/vdo*.rst
 F:	drivers/md/dm-vdo/
 
+DEVICE-MAPPER PCACHE TARGET
+M:	Dongsheng Yang <dongsheng.yang@linux.dev>
+M:	Zheng Gu <cengku@gmail.com>
+L:	dm-devel@lists.linux.dev
+S:	Maintained
+F:	Documentation/admin-guide/device-mapper/dm-pcache.rst
+F:	drivers/md/dm-pcache/
+
 DEVLINK
 M:	Jiri Pirko <jiri@resnulli.us>
 L:	netdev@vger.kernel.org

drivers/md/Kconfig

@@ -659,4 +659,6 @@ config DM_AUDIT
 
 source "drivers/md/dm-vdo/Kconfig"
 
+source "drivers/md/dm-pcache/Kconfig"
+
 endif # MD

drivers/md/Makefile

@@ -71,6 +71,7 @@ obj-$(CONFIG_DM_RAID)		+= dm-raid.o
 obj-$(CONFIG_DM_THIN_PROVISIONING) += dm-thin-pool.o
 obj-$(CONFIG_DM_VERITY)		+= dm-verity.o
 obj-$(CONFIG_DM_VDO)            += dm-vdo/
+obj-$(CONFIG_DM_PCACHE)		+= dm-pcache/
 obj-$(CONFIG_DM_CACHE)		+= dm-cache.o
 obj-$(CONFIG_DM_CACHE_SMQ)	+= dm-cache-smq.o
 obj-$(CONFIG_DM_EBS)		+= dm-ebs.o

drivers/md/dm-pcache/Kconfig

@@ -0,0 +1,17 @@
+config DM_PCACHE
+	tristate "Persistent cache for Block Device (Experimental)"
+	depends on BLK_DEV_DM
+	depends on DEV_DAX
+	help
+	  PCACHE provides a mechanism to use persistent memory (e.g., CXL persistent memory,
+	  DAX-enabled devices) as a high-performance cache layer in front of
+	  traditional block devices such as SSDs or HDDs.
+
+	  PCACHE is implemented as a kernel module that integrates with the block
+	  layer and supports direct access (DAX) to persistent memory for low-latency,
+	  byte-addressable caching.
+
+	  Note: This feature is experimental and should be tested thoroughly
+	  before use in production environments.
+
+	  If unsure, say 'N'.

drivers/md/dm-pcache/Makefile

@@ -0,0 +1,3 @@
+dm-pcache-y := dm_pcache.o cache_dev.o segment.o backing_dev.o cache.o cache_gc.o cache_writeback.o cache_segment.o cache_key.o cache_req.o
+
+obj-m += dm-pcache.o

drivers/md/dm-pcache/backing_dev.c

@@ -0,0 +1,374 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+#include <linux/blkdev.h>
+
+#include "../dm-core.h"
+#include "pcache_internal.h"
+#include "cache_dev.h"
+#include "backing_dev.h"
+#include "cache.h"
+#include "dm_pcache.h"
+
+static struct kmem_cache *backing_req_cache;
+static struct kmem_cache *backing_bvec_cache;
+
+static void backing_dev_exit(struct pcache_backing_dev *backing_dev)
+{
+	mempool_exit(&backing_dev->req_pool);
+	mempool_exit(&backing_dev->bvec_pool);
+}
+
+static void req_submit_fn(struct work_struct *work);
+static void req_complete_fn(struct work_struct *work);
+static int backing_dev_init(struct dm_pcache *pcache)
+{
+	struct pcache_backing_dev *backing_dev = &pcache->backing_dev;
+	int ret;
+
+	ret = mempool_init_slab_pool(&backing_dev->req_pool, 128, backing_req_cache);
+	if (ret)
+		goto err;
+
+	ret = mempool_init_slab_pool(&backing_dev->bvec_pool, 128, backing_bvec_cache);
+	if (ret)
+		goto req_pool_exit;
+
+	INIT_LIST_HEAD(&backing_dev->submit_list);
+	INIT_LIST_HEAD(&backing_dev->complete_list);
+	spin_lock_init(&backing_dev->submit_lock);
+	spin_lock_init(&backing_dev->complete_lock);
+	INIT_WORK(&backing_dev->req_submit_work, req_submit_fn);
+	INIT_WORK(&backing_dev->req_complete_work, req_complete_fn);
+	atomic_set(&backing_dev->inflight_reqs, 0);
+	init_waitqueue_head(&backing_dev->inflight_wq);
+
+	return 0;
+
+req_pool_exit:
+	mempool_exit(&backing_dev->req_pool);
+err:
+	return ret;
+}
+
+int backing_dev_start(struct dm_pcache *pcache)
+{
+	struct pcache_backing_dev *backing_dev = &pcache->backing_dev;
+	int ret;
+
+	ret = backing_dev_init(pcache);
+	if (ret)
+		return ret;
+
+	backing_dev->dev_size = bdev_nr_sectors(backing_dev->dm_dev->bdev);
+
+	return 0;
+}
+
+void backing_dev_stop(struct dm_pcache *pcache)
+{
+	struct pcache_backing_dev *backing_dev = &pcache->backing_dev;
+
+	/*
+	 * There should not be any new request comming, just wait
+	 * inflight requests done.
+	 */
+	wait_event(backing_dev->inflight_wq,
+			atomic_read(&backing_dev->inflight_reqs) == 0);
+
+	flush_work(&backing_dev->req_submit_work);
+	flush_work(&backing_dev->req_complete_work);
+
+	backing_dev_exit(backing_dev);
+}
+
+/* pcache_backing_dev_req functions */
+void backing_dev_req_end(struct pcache_backing_dev_req *backing_req)
+{
+	struct pcache_backing_dev *backing_dev = backing_req->backing_dev;
+
+	if (backing_req->end_req)
+		backing_req->end_req(backing_req, backing_req->ret);
+
+	switch (backing_req->type) {
+	case BACKING_DEV_REQ_TYPE_REQ:
+		if (backing_req->req.upper_req)
+			pcache_req_put(backing_req->req.upper_req, backing_req->ret);
+		break;
+	case BACKING_DEV_REQ_TYPE_KMEM:
+		if (backing_req->kmem.bvecs != backing_req->kmem.inline_bvecs)
+			mempool_free(backing_req->kmem.bvecs, &backing_dev->bvec_pool);
+		break;
+	default:
+		BUG();
+	}
+
+	mempool_free(backing_req, &backing_dev->req_pool);
+
+	if (atomic_dec_and_test(&backing_dev->inflight_reqs))
+		wake_up(&backing_dev->inflight_wq);
+}
+
+static void req_complete_fn(struct work_struct *work)
+{
+	struct pcache_backing_dev *backing_dev = container_of(work, struct pcache_backing_dev, req_complete_work);
+	struct pcache_backing_dev_req *backing_req;
+	LIST_HEAD(tmp_list);
+
+	spin_lock_irq(&backing_dev->complete_lock);
+	list_splice_init(&backing_dev->complete_list, &tmp_list);
+	spin_unlock_irq(&backing_dev->complete_lock);
+
+	while (!list_empty(&tmp_list)) {
+		backing_req = list_first_entry(&tmp_list,
+					    struct pcache_backing_dev_req, node);
+		list_del_init(&backing_req->node);
+		backing_dev_req_end(backing_req);
+	}
+}
+
+static void backing_dev_bio_end(struct bio *bio)
+{
+	struct pcache_backing_dev_req *backing_req = bio->bi_private;
+	struct pcache_backing_dev *backing_dev = backing_req->backing_dev;
+	unsigned long flags;
+
+	backing_req->ret = blk_status_to_errno(bio->bi_status);
+
+	spin_lock_irqsave(&backing_dev->complete_lock, flags);
+	list_move_tail(&backing_req->node, &backing_dev->complete_list);
+	queue_work(BACKING_DEV_TO_PCACHE(backing_dev)->task_wq, &backing_dev->req_complete_work);
+	spin_unlock_irqrestore(&backing_dev->complete_lock, flags);
+}
+
+static void req_submit_fn(struct work_struct *work)
+{
+	struct pcache_backing_dev *backing_dev = container_of(work, struct pcache_backing_dev, req_submit_work);
+	struct pcache_backing_dev_req *backing_req;
+	LIST_HEAD(tmp_list);
+
+	spin_lock(&backing_dev->submit_lock);
+	list_splice_init(&backing_dev->submit_list, &tmp_list);
+	spin_unlock(&backing_dev->submit_lock);
+
+	while (!list_empty(&tmp_list)) {
+		backing_req = list_first_entry(&tmp_list,
+					    struct pcache_backing_dev_req, node);
+		list_del_init(&backing_req->node);
+		submit_bio_noacct(&backing_req->bio);
+	}
+}
+
+void backing_dev_req_submit(struct pcache_backing_dev_req *backing_req, bool direct)
+{
+	struct pcache_backing_dev *backing_dev = backing_req->backing_dev;
+
+	if (direct) {
+		submit_bio_noacct(&backing_req->bio);
+		return;
+	}
+
+	spin_lock(&backing_dev->submit_lock);
+	list_add_tail(&backing_req->node, &backing_dev->submit_list);
+	queue_work(BACKING_DEV_TO_PCACHE(backing_dev)->task_wq, &backing_dev->req_submit_work);
+	spin_unlock(&backing_dev->submit_lock);
+}
+
+static void bio_map(struct bio *bio, void *base, size_t size)
+{
+	struct page *page;
+	unsigned int offset;
+	unsigned int len;
+
+	if (!is_vmalloc_addr(base)) {
+		page = virt_to_page(base);
+		offset = offset_in_page(base);
+
+		BUG_ON(!bio_add_page(bio, page, size, offset));
+		return;
+	}
+
+	flush_kernel_vmap_range(base, size);
+	while (size) {
+		page = vmalloc_to_page(base);
+		offset = offset_in_page(base);
+		len = min_t(size_t, PAGE_SIZE - offset, size);
+
+		BUG_ON(!bio_add_page(bio, page, len, offset));
+		size -= len;
+		base += len;
+	}
+}
+
+static struct pcache_backing_dev_req *req_type_req_alloc(struct pcache_backing_dev *backing_dev,
+							struct pcache_backing_dev_req_opts *opts)
+{
+	struct pcache_request *pcache_req = opts->req.upper_req;
+	struct pcache_backing_dev_req *backing_req;
+	struct bio *orig = pcache_req->bio;
+
+	backing_req = mempool_alloc(&backing_dev->req_pool, opts->gfp_mask);
+	if (!backing_req)
+		return NULL;
+
+	memset(backing_req, 0, sizeof(struct pcache_backing_dev_req));
+
+	bio_init_clone(backing_dev->dm_dev->bdev, &backing_req->bio, orig, opts->gfp_mask);
+
+	backing_req->type = BACKING_DEV_REQ_TYPE_REQ;
+	backing_req->backing_dev = backing_dev;
+	atomic_inc(&backing_dev->inflight_reqs);
+
+	return backing_req;
+}
+
+static struct pcache_backing_dev_req *kmem_type_req_alloc(struct pcache_backing_dev *backing_dev,
+						struct pcache_backing_dev_req_opts *opts)
+{
+	struct pcache_backing_dev_req *backing_req;
+	u32 n_vecs = bio_add_max_vecs(opts->kmem.data, opts->kmem.len);
+
+	backing_req = mempool_alloc(&backing_dev->req_pool, opts->gfp_mask);
+	if (!backing_req)
+		return NULL;
+
+	memset(backing_req, 0, sizeof(struct pcache_backing_dev_req));
+
+	if (n_vecs > BACKING_DEV_REQ_INLINE_BVECS) {
+		backing_req->kmem.bvecs = mempool_alloc(&backing_dev->bvec_pool, opts->gfp_mask);
+		if (!backing_req->kmem.bvecs)
+			goto free_backing_req;
+	} else {
+		backing_req->kmem.bvecs = backing_req->kmem.inline_bvecs;
+	}
+
+	backing_req->kmem.n_vecs = n_vecs;
+	backing_req->type = BACKING_DEV_REQ_TYPE_KMEM;
+	backing_req->backing_dev = backing_dev;
+	atomic_inc(&backing_dev->inflight_reqs);
+
+	return backing_req;
+
+free_backing_req:
+	mempool_free(backing_req, &backing_dev->req_pool);
+	return NULL;
+}
+
+struct pcache_backing_dev_req *backing_dev_req_alloc(struct pcache_backing_dev *backing_dev,
+						struct pcache_backing_dev_req_opts *opts)
+{
+	if (opts->type == BACKING_DEV_REQ_TYPE_REQ)
+		return req_type_req_alloc(backing_dev, opts);
+
+	if (opts->type == BACKING_DEV_REQ_TYPE_KMEM)
+		return kmem_type_req_alloc(backing_dev, opts);
+
+	BUG();
+}
+
+static void req_type_req_init(struct pcache_backing_dev_req *backing_req,
+			struct pcache_backing_dev_req_opts *opts)
+{
+	struct pcache_request *pcache_req = opts->req.upper_req;
+	struct bio *clone;
+	u32 off = opts->req.req_off;
+	u32 len = opts->req.len;
+
+	clone = &backing_req->bio;
+	BUG_ON(off & SECTOR_MASK);
+	BUG_ON(len & SECTOR_MASK);
+	bio_trim(clone, off >> SECTOR_SHIFT, len >> SECTOR_SHIFT);
+
+	clone->bi_iter.bi_sector = (pcache_req->off + off) >> SECTOR_SHIFT;
+	clone->bi_private = backing_req;
+	clone->bi_end_io = backing_dev_bio_end;
+
+	INIT_LIST_HEAD(&backing_req->node);
+	backing_req->end_req     = opts->end_fn;
+
+	pcache_req_get(pcache_req);
+	backing_req->req.upper_req	= pcache_req;
+	backing_req->req.bio_off	= off;
+}
+
+static void kmem_type_req_init(struct pcache_backing_dev_req *backing_req,
+			struct pcache_backing_dev_req_opts *opts)
+{
+	struct pcache_backing_dev *backing_dev = backing_req->backing_dev;
+	struct bio *backing_bio;
+
+	bio_init(&backing_req->bio, backing_dev->dm_dev->bdev, backing_req->kmem.bvecs,
+			backing_req->kmem.n_vecs, opts->kmem.opf);
+
+	backing_bio = &backing_req->bio;
+	bio_map(backing_bio, opts->kmem.data, opts->kmem.len);
+
+	backing_bio->bi_iter.bi_sector = (opts->kmem.backing_off) >> SECTOR_SHIFT;
+	backing_bio->bi_private = backing_req;
+	backing_bio->bi_end_io = backing_dev_bio_end;
+
+	INIT_LIST_HEAD(&backing_req->node);
+	backing_req->end_req	= opts->end_fn;
+	backing_req->priv_data	= opts->priv_data;
+}
+
+void backing_dev_req_init(struct pcache_backing_dev_req *backing_req,
+			struct pcache_backing_dev_req_opts *opts)
+{
+	if (opts->type == BACKING_DEV_REQ_TYPE_REQ)
+		return req_type_req_init(backing_req, opts);
+
+	if (opts->type == BACKING_DEV_REQ_TYPE_KMEM)
+		return kmem_type_req_init(backing_req, opts);
+
+	BUG();
+}
+
+struct pcache_backing_dev_req *backing_dev_req_create(struct pcache_backing_dev *backing_dev,
+						struct pcache_backing_dev_req_opts *opts)
+{
+	struct pcache_backing_dev_req *backing_req;
+
+	backing_req = backing_dev_req_alloc(backing_dev, opts);
+	if (!backing_req)
+		return NULL;
+
+	backing_dev_req_init(backing_req, opts);
+
+	return backing_req;
+}
+
+void backing_dev_flush(struct pcache_backing_dev *backing_dev)
+{
+	blkdev_issue_flush(backing_dev->dm_dev->bdev);
+}
+
+int pcache_backing_init(void)
+{
+	u32 max_bvecs = (PCACHE_CACHE_SUBTREE_SIZE >> PAGE_SHIFT) + 1;
+	int ret;
+
+	backing_req_cache = KMEM_CACHE(pcache_backing_dev_req, 0);
+	if (!backing_req_cache) {
+		ret = -ENOMEM;
+		goto err;
+	}
+
+	backing_bvec_cache = kmem_cache_create("pcache-bvec-slab",
+					max_bvecs * sizeof(struct bio_vec),
+					0, 0, NULL);
+	if (!backing_bvec_cache) {
+		ret = -ENOMEM;
+		goto destroy_req_cache;
+	}
+
+	return 0;
+destroy_req_cache:
+	kmem_cache_destroy(backing_req_cache);
+err:
+	return ret;
+}
+
+void pcache_backing_exit(void)
+{
+	kmem_cache_destroy(backing_bvec_cache);
+	kmem_cache_destroy(backing_req_cache);
+}

drivers/md/dm-pcache/backing_dev.h

@@ -0,0 +1,127 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#ifndef _BACKING_DEV_H
+#define _BACKING_DEV_H
+
+#include <linux/device-mapper.h>
+
+#include "pcache_internal.h"
+
+struct pcache_backing_dev_req;
+typedef void (*backing_req_end_fn_t)(struct pcache_backing_dev_req *backing_req, int ret);
+
+#define BACKING_DEV_REQ_TYPE_REQ		1
+#define BACKING_DEV_REQ_TYPE_KMEM		2
+
+#define BACKING_DEV_REQ_INLINE_BVECS		4
+
+struct pcache_request;
+struct pcache_backing_dev_req {
+	u8				type;
+	struct bio			bio;
+	struct pcache_backing_dev	*backing_dev;
+
+	void				*priv_data;
+	backing_req_end_fn_t		end_req;
+
+	struct list_head		node;
+	int				ret;
+
+	union {
+		struct {
+			struct pcache_request		*upper_req;
+			u32				bio_off;
+		} req;
+		struct {
+			struct bio_vec	inline_bvecs[BACKING_DEV_REQ_INLINE_BVECS];
+			struct bio_vec	*bvecs;
+			u32		n_vecs;
+		} kmem;
+	};
+};
+
+struct pcache_backing_dev {
+	struct pcache_cache		*cache;
+
+	struct dm_dev			*dm_dev;
+	mempool_t			req_pool;
+	mempool_t			bvec_pool;
+
+	struct list_head		submit_list;
+	spinlock_t			submit_lock;
+	struct work_struct		req_submit_work;
+
+	struct list_head		complete_list;
+	spinlock_t			complete_lock;
+	struct work_struct		req_complete_work;
+
+	atomic_t			inflight_reqs;
+	wait_queue_head_t		inflight_wq;
+
+	u64				dev_size;
+};
+
+struct dm_pcache;
+int backing_dev_start(struct dm_pcache *pcache);
+void backing_dev_stop(struct dm_pcache *pcache);
+
+struct pcache_backing_dev_req_opts {
+	u32 type;
+	union {
+		struct {
+			struct pcache_request *upper_req;
+			u32 req_off;
+			u32 len;
+		} req;
+		struct {
+			void *data;
+			blk_opf_t opf;
+			u32 len;
+			u64 backing_off;
+		} kmem;
+	};
+
+	gfp_t gfp_mask;
+	backing_req_end_fn_t	end_fn;
+	void			*priv_data;
+};
+
+static inline u32 backing_dev_req_coalesced_max_len(const void *data, u32 len)
+{
+	const void *p = data;
+	u32 done = 0, in_page, to_advance;
+	struct page *first_page, *next_page;
+
+	if (!is_vmalloc_addr(data))
+		return len;
+
+	first_page = vmalloc_to_page(p);
+advance:
+	in_page = PAGE_SIZE - offset_in_page(p);
+	to_advance = min_t(u32, in_page, len - done);
+
+	done += to_advance;
+	p += to_advance;
+
+	if (done == len)
+		return done;
+
+	next_page = vmalloc_to_page(p);
+	if (zone_device_pages_have_same_pgmap(first_page, next_page))
+		goto advance;
+
+	return done;
+}
+
+void backing_dev_req_submit(struct pcache_backing_dev_req *backing_req, bool direct);
+void backing_dev_req_end(struct pcache_backing_dev_req *backing_req);
+struct pcache_backing_dev_req *backing_dev_req_create(struct pcache_backing_dev *backing_dev,
+						struct pcache_backing_dev_req_opts *opts);
+struct pcache_backing_dev_req *backing_dev_req_alloc(struct pcache_backing_dev *backing_dev,
+						struct pcache_backing_dev_req_opts *opts);
+void backing_dev_req_init(struct pcache_backing_dev_req *backing_req,
+			struct pcache_backing_dev_req_opts *opts);
+void backing_dev_flush(struct pcache_backing_dev *backing_dev);
+
+int pcache_backing_init(void);
+void pcache_backing_exit(void);
+#endif /* _BACKING_DEV_H */

drivers/md/dm-pcache/cache.c

@@ -0,0 +1,445 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+#include <linux/blk_types.h>
+
+#include "cache.h"
+#include "cache_dev.h"
+#include "backing_dev.h"
+#include "dm_pcache.h"
+
+struct kmem_cache *key_cache;
+
+static inline struct pcache_cache_info *get_cache_info_addr(struct pcache_cache *cache)
+{
+	return cache->cache_info_addr + cache->info_index;
+}
+
+static void cache_info_write(struct pcache_cache *cache)
+{
+	struct pcache_cache_info *cache_info = &cache->cache_info;
+
+	cache_info->header.seq++;
+	cache_info->header.crc = pcache_meta_crc(&cache_info->header,
+						sizeof(struct pcache_cache_info));
+
+	memcpy_flushcache(get_cache_info_addr(cache), cache_info,
+			sizeof(struct pcache_cache_info));
+
+	cache->info_index = (cache->info_index + 1) % PCACHE_META_INDEX_MAX;
+}
+
+static void cache_info_init_default(struct pcache_cache *cache);
+static int cache_info_init(struct pcache_cache *cache, struct pcache_cache_options *opts)
+{
+	struct dm_pcache *pcache = CACHE_TO_PCACHE(cache);
+	struct pcache_cache_info *cache_info_addr;
+
+	cache_info_addr = pcache_meta_find_latest(&cache->cache_info_addr->header,
+						sizeof(struct pcache_cache_info),
+						PCACHE_CACHE_INFO_SIZE,
+						&cache->cache_info);
+	if (IS_ERR(cache_info_addr))
+		return PTR_ERR(cache_info_addr);
+
+	if (cache_info_addr) {
+		if (opts->data_crc !=
+				(cache->cache_info.flags & PCACHE_CACHE_FLAGS_DATA_CRC)) {
+			pcache_dev_err(pcache, "invalid option for data_crc: %s, expected: %s",
+					opts->data_crc ? "true" : "false",
+					cache->cache_info.flags & PCACHE_CACHE_FLAGS_DATA_CRC ? "true" : "false");
+			return -EINVAL;
+		}
+
+		return 0;
+	}
+
+	/* init cache_info for new cache */
+	cache_info_init_default(cache);
+	cache_mode_set(cache, opts->cache_mode);
+	if (opts->data_crc)
+		cache->cache_info.flags |= PCACHE_CACHE_FLAGS_DATA_CRC;
+
+	return 0;
+}
+
+static void cache_info_set_gc_percent(struct pcache_cache_info *cache_info, u8 percent)
+{
+	cache_info->flags &= ~PCACHE_CACHE_FLAGS_GC_PERCENT_MASK;
+	cache_info->flags |= FIELD_PREP(PCACHE_CACHE_FLAGS_GC_PERCENT_MASK, percent);
+}
+
+int pcache_cache_set_gc_percent(struct pcache_cache *cache, u8 percent)
+{
+	if (percent > PCACHE_CACHE_GC_PERCENT_MAX || percent < PCACHE_CACHE_GC_PERCENT_MIN)
+		return -EINVAL;
+
+	mutex_lock(&cache->cache_info_lock);
+	cache_info_set_gc_percent(&cache->cache_info, percent);
+
+	cache_info_write(cache);
+	mutex_unlock(&cache->cache_info_lock);
+
+	return 0;
+}
+
+void cache_pos_encode(struct pcache_cache *cache,
+			     struct pcache_cache_pos_onmedia *pos_onmedia_base,
+			     struct pcache_cache_pos *pos, u64 seq, u32 *index)
+{
+	struct pcache_cache_pos_onmedia pos_onmedia;
+	struct pcache_cache_pos_onmedia *pos_onmedia_addr = pos_onmedia_base + *index;
+
+	pos_onmedia.cache_seg_id = pos->cache_seg->cache_seg_id;
+	pos_onmedia.seg_off = pos->seg_off;
+	pos_onmedia.header.seq = seq;
+	pos_onmedia.header.crc = cache_pos_onmedia_crc(&pos_onmedia);
+
+	memcpy_flushcache(pos_onmedia_addr, &pos_onmedia, sizeof(struct pcache_cache_pos_onmedia));
+	pmem_wmb();
+
+	*index = (*index + 1) % PCACHE_META_INDEX_MAX;
+}
+
+int cache_pos_decode(struct pcache_cache *cache,
+			    struct pcache_cache_pos_onmedia *pos_onmedia,
+			    struct pcache_cache_pos *pos, u64 *seq, u32 *index)
+{
+	struct pcache_cache_pos_onmedia latest, *latest_addr;
+
+	latest_addr = pcache_meta_find_latest(&pos_onmedia->header,
+					sizeof(struct pcache_cache_pos_onmedia),
+					sizeof(struct pcache_cache_pos_onmedia),
+					&latest);
+	if (IS_ERR(latest_addr))
+		return PTR_ERR(latest_addr);
+
+	if (!latest_addr)
+		return -EIO;
+
+	pos->cache_seg = &cache->segments[latest.cache_seg_id];
+	pos->seg_off = latest.seg_off;
+	*seq = latest.header.seq;
+	*index = (latest_addr - pos_onmedia);
+
+	return 0;
+}
+
+static inline void cache_info_set_seg_id(struct pcache_cache *cache, u32 seg_id)
+{
+	cache->cache_info.seg_id = seg_id;
+}
+
+static int cache_init(struct dm_pcache *pcache)
+{
+	struct pcache_cache *cache = &pcache->cache;
+	struct pcache_backing_dev *backing_dev = &pcache->backing_dev;
+	struct pcache_cache_dev *cache_dev = &pcache->cache_dev;
+	int ret;
+
+	cache->segments = kvcalloc(cache_dev->seg_num, sizeof(struct pcache_cache_segment), GFP_KERNEL);
+	if (!cache->segments) {
+		ret = -ENOMEM;
+		goto err;
+	}
+
+	cache->seg_map = kvcalloc(BITS_TO_LONGS(cache_dev->seg_num), sizeof(unsigned long), GFP_KERNEL);
+	if (!cache->seg_map) {
+		ret = -ENOMEM;
+		goto free_segments;
+	}
+
+	cache->backing_dev = backing_dev;
+	cache->cache_dev = &pcache->cache_dev;
+	cache->n_segs = cache_dev->seg_num;
+	atomic_set(&cache->gc_errors, 0);
+	spin_lock_init(&cache->seg_map_lock);
+	spin_lock_init(&cache->key_head_lock);
+
+	mutex_init(&cache->cache_info_lock);
+	mutex_init(&cache->key_tail_lock);
+	mutex_init(&cache->dirty_tail_lock);
+	mutex_init(&cache->writeback_lock);
+
+	INIT_DELAYED_WORK(&cache->writeback_work, cache_writeback_fn);
+	INIT_DELAYED_WORK(&cache->gc_work, pcache_cache_gc_fn);
+	INIT_WORK(&cache->clean_work, clean_fn);
+
+	return 0;
+
+free_segments:
+	kvfree(cache->segments);
+err:
+	return ret;
+}
+
+static void cache_exit(struct pcache_cache *cache)
+{
+	kvfree(cache->seg_map);
+	kvfree(cache->segments);
+}
+
+static void cache_info_init_default(struct pcache_cache *cache)
+{
+	struct pcache_cache_info *cache_info = &cache->cache_info;
+
+	cache_info->header.seq = 0;
+	cache_info->n_segs = cache->cache_dev->seg_num;
+	cache_info_set_gc_percent(cache_info, PCACHE_CACHE_GC_PERCENT_DEFAULT);
+}
+
+static int cache_tail_init(struct pcache_cache *cache)
+{
+	struct dm_pcache *pcache = CACHE_TO_PCACHE(cache);
+	bool new_cache = !(cache->cache_info.flags & PCACHE_CACHE_FLAGS_INIT_DONE);
+
+	if (new_cache) {
+		__set_bit(0, cache->seg_map);
+
+		cache->key_head.cache_seg = &cache->segments[0];
+		cache->key_head.seg_off = 0;
+		cache_pos_copy(&cache->key_tail, &cache->key_head);
+		cache_pos_copy(&cache->dirty_tail, &cache->key_head);
+
+		cache_encode_dirty_tail(cache);
+		cache_encode_key_tail(cache);
+	} else {
+		if (cache_decode_key_tail(cache) || cache_decode_dirty_tail(cache)) {
+			pcache_dev_err(pcache, "Corrupted key tail or dirty tail.\n");
+			return -EIO;
+		}
+	}
+
+	return 0;
+}
+
+static int get_seg_id(struct pcache_cache *cache,
+		      struct pcache_cache_segment *prev_cache_seg,
+		      bool new_cache, u32 *seg_id)
+{
+	struct dm_pcache *pcache = CACHE_TO_PCACHE(cache);
+	struct pcache_cache_dev *cache_dev = cache->cache_dev;
+	int ret;
+
+	if (new_cache) {
+		ret = cache_dev_get_empty_segment_id(cache_dev, seg_id);
+		if (ret) {
+			pcache_dev_err(pcache, "no available segment\n");
+			goto err;
+		}
+
+		if (prev_cache_seg)
+			cache_seg_set_next_seg(prev_cache_seg, *seg_id);
+		else
+			cache_info_set_seg_id(cache, *seg_id);
+	} else {
+		if (prev_cache_seg) {
+			struct pcache_segment_info *prev_seg_info;
+
+			prev_seg_info = &prev_cache_seg->cache_seg_info;
+			if (!segment_info_has_next(prev_seg_info)) {
+				ret = -EFAULT;
+				goto err;
+			}
+			*seg_id = prev_cache_seg->cache_seg_info.next_seg;
+		} else {
+			*seg_id = cache->cache_info.seg_id;
+		}
+	}
+	return 0;
+err:
+	return ret;
+}
+
+static int cache_segs_init(struct pcache_cache *cache)
+{
+	struct pcache_cache_segment *prev_cache_seg = NULL;
+	struct pcache_cache_info *cache_info = &cache->cache_info;
+	bool new_cache = !(cache->cache_info.flags & PCACHE_CACHE_FLAGS_INIT_DONE);
+	u32 seg_id;
+	int ret;
+	u32 i;
+
+	for (i = 0; i < cache_info->n_segs; i++) {
+		ret = get_seg_id(cache, prev_cache_seg, new_cache, &seg_id);
+		if (ret)
+			goto err;
+
+		ret = cache_seg_init(cache, seg_id, i, new_cache);
+		if (ret)
+			goto err;
+
+		prev_cache_seg = &cache->segments[i];
+	}
+	return 0;
+err:
+	return ret;
+}
+
+static int cache_init_req_keys(struct pcache_cache *cache, u32 n_paral)
+{
+	struct dm_pcache *pcache = CACHE_TO_PCACHE(cache);
+	u32 n_subtrees;
+	int ret;
+	u32 i, cpu;
+
+	/* Calculate number of cache trees based on the device size */
+	n_subtrees = DIV_ROUND_UP(cache->dev_size << SECTOR_SHIFT, PCACHE_CACHE_SUBTREE_SIZE);
+	ret = cache_tree_init(cache, &cache->req_key_tree, n_subtrees);
+	if (ret)
+		goto err;
+
+	cache->n_ksets = n_paral;
+	cache->ksets = kvcalloc(cache->n_ksets, PCACHE_KSET_SIZE, GFP_KERNEL);
+	if (!cache->ksets) {
+		ret = -ENOMEM;
+		goto req_tree_exit;
+	}
+
+	/*
+	 * Initialize each kset with a spinlock and delayed work for flushing.
+	 * Each kset is associated with one queue to ensure independent handling
+	 * of cache keys across multiple queues, maximizing multiqueue concurrency.
+	 */
+	for (i = 0; i < cache->n_ksets; i++) {
+		struct pcache_cache_kset *kset = get_kset(cache, i);
+
+		kset->cache = cache;
+		spin_lock_init(&kset->kset_lock);
+		INIT_DELAYED_WORK(&kset->flush_work, kset_flush_fn);
+	}
+
+	cache->data_heads = alloc_percpu(struct pcache_cache_data_head);
+	if (!cache->data_heads) {
+		ret = -ENOMEM;
+		goto free_kset;
+	}
+
+	for_each_possible_cpu(cpu) {
+		struct pcache_cache_data_head *h =
+			per_cpu_ptr(cache->data_heads, cpu);
+		h->head_pos.cache_seg = NULL;
+	}
+
+	/*
+	 * Replay persisted cache keys using cache_replay.
+	 * This function loads and replays cache keys from previously stored
+	 * ksets, allowing the cache to restore its state after a restart.
+	 */
+	ret = cache_replay(cache);
+	if (ret) {
+		pcache_dev_err(pcache, "failed to replay keys\n");
+		goto free_heads;
+	}
+
+	return 0;
+
+free_heads:
+	free_percpu(cache->data_heads);
+free_kset:
+	kvfree(cache->ksets);
+req_tree_exit:
+	cache_tree_exit(&cache->req_key_tree);
+err:
+	return ret;
+}
+
+static void cache_destroy_req_keys(struct pcache_cache *cache)
+{
+	u32 i;
+
+	for (i = 0; i < cache->n_ksets; i++) {
+		struct pcache_cache_kset *kset = get_kset(cache, i);
+
+		cancel_delayed_work_sync(&kset->flush_work);
+	}
+
+	free_percpu(cache->data_heads);
+	kvfree(cache->ksets);
+	cache_tree_exit(&cache->req_key_tree);
+}
+
+int pcache_cache_start(struct dm_pcache *pcache)
+{
+	struct pcache_backing_dev *backing_dev = &pcache->backing_dev;
+	struct pcache_cache *cache = &pcache->cache;
+	struct pcache_cache_options *opts = &pcache->opts;
+	int ret;
+
+	ret = cache_init(pcache);
+	if (ret)
+		return ret;
+
+	cache->cache_info_addr = CACHE_DEV_CACHE_INFO(cache->cache_dev);
+	cache->cache_ctrl = CACHE_DEV_CACHE_CTRL(cache->cache_dev);
+	backing_dev->cache = cache;
+	cache->dev_size = backing_dev->dev_size;
+
+	ret = cache_info_init(cache, opts);
+	if (ret)
+		goto cache_exit;
+
+	ret = cache_segs_init(cache);
+	if (ret)
+		goto cache_exit;
+
+	ret = cache_tail_init(cache);
+	if (ret)
+		goto cache_exit;
+
+	ret = cache_init_req_keys(cache, num_online_cpus());
+	if (ret)
+		goto cache_exit;
+
+	ret = cache_writeback_init(cache);
+	if (ret)
+		goto destroy_keys;
+
+	cache->cache_info.flags |= PCACHE_CACHE_FLAGS_INIT_DONE;
+	cache_info_write(cache);
+	queue_delayed_work(cache_get_wq(cache), &cache->gc_work, 0);
+
+	return 0;
+
+destroy_keys:
+	cache_destroy_req_keys(cache);
+cache_exit:
+	cache_exit(cache);
+
+	return ret;
+}
+
+void pcache_cache_stop(struct dm_pcache *pcache)
+{
+	struct pcache_cache *cache = &pcache->cache;
+
+	cache_flush(cache);
+
+	cancel_delayed_work_sync(&cache->gc_work);
+	flush_work(&cache->clean_work);
+	cache_writeback_exit(cache);
+
+	if (cache->req_key_tree.n_subtrees)
+		cache_destroy_req_keys(cache);
+
+	cache_exit(cache);
+}
+
+struct workqueue_struct *cache_get_wq(struct pcache_cache *cache)
+{
+	struct dm_pcache *pcache = CACHE_TO_PCACHE(cache);
+
+	return pcache->task_wq;
+}
+
+int pcache_cache_init(void)
+{
+	key_cache = KMEM_CACHE(pcache_cache_key, 0);
+	if (!key_cache)
+		return -ENOMEM;
+
+	return 0;
+}
+
+void pcache_cache_exit(void)
+{
+	kmem_cache_destroy(key_cache);
+}

drivers/md/dm-pcache/cache_dev.c

@@ -0,0 +1,303 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <linux/blkdev.h>
+#include <linux/dax.h>
+#include <linux/vmalloc.h>
+#include <linux/parser.h>
+
+#include "cache_dev.h"
+#include "backing_dev.h"
+#include "cache.h"
+#include "dm_pcache.h"
+
+static void cache_dev_dax_exit(struct pcache_cache_dev *cache_dev)
+{
+	if (cache_dev->use_vmap)
+		vunmap(cache_dev->mapping);
+}
+
+static int build_vmap(struct dax_device *dax_dev, long total_pages, void **vaddr)
+{
+	struct page **pages;
+	long i = 0, chunk;
+	unsigned long pfn;
+	int ret;
+
+	pages = vmalloc_array(total_pages, sizeof(struct page *));
+	if (!pages)
+		return -ENOMEM;
+
+	do {
+		chunk = dax_direct_access(dax_dev, i, total_pages - i,
+					  DAX_ACCESS, NULL, &pfn);
+		if (chunk <= 0) {
+			ret = chunk ? chunk : -EINVAL;
+			goto out_free;
+		}
+
+		if (!pfn_valid(pfn)) {
+			ret = -EOPNOTSUPP;
+			goto out_free;
+		}
+
+		while (chunk-- && i < total_pages) {
+			pages[i++] = pfn_to_page(pfn);
+			pfn++;
+			if (!(i & 15))
+				cond_resched();
+		}
+	} while (i < total_pages);
+
+	*vaddr = vmap(pages, total_pages, VM_MAP, PAGE_KERNEL);
+	if (!*vaddr) {
+		ret = -ENOMEM;
+		goto out_free;
+	}
+
+	ret = 0;
+
+out_free:
+	vfree(pages);
+	return ret;
+}
+
+static int cache_dev_dax_init(struct pcache_cache_dev *cache_dev)
+{
+	struct dm_pcache	*pcache = CACHE_DEV_TO_PCACHE(cache_dev);
+	struct dax_device	*dax_dev;
+	long			total_pages, mapped_pages;
+	u64			bdev_size;
+	void			*vaddr;
+	int			ret;
+	int			id;
+	unsigned long		pfn;
+
+	dax_dev	= cache_dev->dm_dev->dax_dev;
+	/* total size check */
+	bdev_size = bdev_nr_bytes(cache_dev->dm_dev->bdev);
+	if (bdev_size < PCACHE_CACHE_DEV_SIZE_MIN) {
+		pcache_dev_err(pcache, "dax device is too small, required at least %llu",
+				PCACHE_CACHE_DEV_SIZE_MIN);
+		ret = -ENOSPC;
+		goto out;
+	}
+
+	total_pages = bdev_size >> PAGE_SHIFT;
+	/* attempt: direct-map the whole range */
+	id = dax_read_lock();
+	mapped_pages = dax_direct_access(dax_dev, 0, total_pages,
+					 DAX_ACCESS, &vaddr, &pfn);
+	if (mapped_pages < 0) {
+		pcache_dev_err(pcache, "dax_direct_access failed: %ld\n", mapped_pages);
+		ret = mapped_pages;
+		goto unlock;
+	}
+
+	if (!pfn_valid(pfn)) {
+		ret = -EOPNOTSUPP;
+		goto unlock;
+	}
+
+	if (mapped_pages == total_pages) {
+		/* success: contiguous direct mapping */
+		cache_dev->mapping = vaddr;
+	} else {
+		/* need vmap fallback */
+		ret = build_vmap(dax_dev, total_pages, &vaddr);
+		if (ret) {
+			pcache_dev_err(pcache, "vmap fallback failed: %d\n", ret);
+			goto unlock;
+		}
+
+		cache_dev->mapping	= vaddr;
+		cache_dev->use_vmap	= true;
+	}
+	dax_read_unlock(id);
+
+	return 0;
+unlock:
+	dax_read_unlock(id);
+out:
+	return ret;
+}
+
+void cache_dev_zero_range(struct pcache_cache_dev *cache_dev, void *pos, u32 size)
+{
+	memset(pos, 0, size);
+	dax_flush(cache_dev->dm_dev->dax_dev, pos, size);
+}
+
+static int sb_read(struct pcache_cache_dev *cache_dev, struct pcache_sb *sb)
+{
+	struct pcache_sb *sb_addr = CACHE_DEV_SB(cache_dev);
+
+	if (copy_mc_to_kernel(sb, sb_addr, sizeof(struct pcache_sb)))
+		return -EIO;
+
+	return 0;
+}
+
+static void sb_write(struct pcache_cache_dev *cache_dev, struct pcache_sb *sb)
+{
+	struct pcache_sb *sb_addr = CACHE_DEV_SB(cache_dev);
+
+	memcpy_flushcache(sb_addr, sb, sizeof(struct pcache_sb));
+	pmem_wmb();
+}
+
+static int sb_init(struct pcache_cache_dev *cache_dev, struct pcache_sb *sb)
+{
+	struct dm_pcache *pcache = CACHE_DEV_TO_PCACHE(cache_dev);
+	u64 nr_segs;
+	u64 cache_dev_size;
+	u64 magic;
+	u32 flags = 0;
+
+	magic = le64_to_cpu(sb->magic);
+	if (magic)
+		return -EEXIST;
+
+	cache_dev_size = bdev_nr_bytes(file_bdev(cache_dev->dm_dev->bdev_file));
+	if (cache_dev_size < PCACHE_CACHE_DEV_SIZE_MIN) {
+		pcache_dev_err(pcache, "dax device is too small, required at least %llu",
+				PCACHE_CACHE_DEV_SIZE_MIN);
+		return -ENOSPC;
+	}
+
+	nr_segs = (cache_dev_size - PCACHE_SEGMENTS_OFF) / ((PCACHE_SEG_SIZE));
+
+#if defined(__BYTE_ORDER) ? (__BIG_ENDIAN == __BYTE_ORDER) : defined(__BIG_ENDIAN)
+	flags |= PCACHE_SB_F_BIGENDIAN;
+#endif
+	sb->flags = cpu_to_le32(flags);
+	sb->magic = cpu_to_le64(PCACHE_MAGIC);
+	sb->seg_num = cpu_to_le32(nr_segs);
+	sb->crc = cpu_to_le32(crc32c(PCACHE_CRC_SEED, (void *)(sb) + 4, sizeof(struct pcache_sb) - 4));
+
+	cache_dev_zero_range(cache_dev, CACHE_DEV_CACHE_INFO(cache_dev),
+			     PCACHE_CACHE_INFO_SIZE * PCACHE_META_INDEX_MAX +
+			     PCACHE_CACHE_CTRL_SIZE);
+
+	return 0;
+}
+
+static int sb_validate(struct pcache_cache_dev *cache_dev, struct pcache_sb *sb)
+{
+	struct dm_pcache *pcache = CACHE_DEV_TO_PCACHE(cache_dev);
+	u32 flags;
+	u32 crc;
+
+	if (le64_to_cpu(sb->magic) != PCACHE_MAGIC) {
+		pcache_dev_err(pcache, "unexpected magic: %llx\n",
+				le64_to_cpu(sb->magic));
+		return -EINVAL;
+	}
+
+	crc = crc32c(PCACHE_CRC_SEED, (void *)(sb) + 4, sizeof(struct pcache_sb) - 4);
+	if (crc != le32_to_cpu(sb->crc)) {
+		pcache_dev_err(pcache, "corrupted sb: %u, expected: %u\n", crc, le32_to_cpu(sb->crc));
+		return -EINVAL;
+	}
+
+	flags = le32_to_cpu(sb->flags);
+#if defined(__BYTE_ORDER) ? (__BIG_ENDIAN == __BYTE_ORDER) : defined(__BIG_ENDIAN)
+	if (!(flags & PCACHE_SB_F_BIGENDIAN)) {
+		pcache_dev_err(pcache, "cache_dev is not big endian\n");
+		return -EINVAL;
+	}
+#else
+	if (flags & PCACHE_SB_F_BIGENDIAN) {
+		pcache_dev_err(pcache, "cache_dev is big endian\n");
+		return -EINVAL;
+	}
+#endif
+	return 0;
+}
+
+static int cache_dev_init(struct pcache_cache_dev *cache_dev, u32 seg_num)
+{
+	cache_dev->seg_num = seg_num;
+	cache_dev->seg_bitmap = kvcalloc(BITS_TO_LONGS(cache_dev->seg_num), sizeof(unsigned long), GFP_KERNEL);
+	if (!cache_dev->seg_bitmap)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static void cache_dev_exit(struct pcache_cache_dev *cache_dev)
+{
+	kvfree(cache_dev->seg_bitmap);
+}
+
+void cache_dev_stop(struct dm_pcache *pcache)
+{
+	struct pcache_cache_dev *cache_dev = &pcache->cache_dev;
+
+	cache_dev_exit(cache_dev);
+	cache_dev_dax_exit(cache_dev);
+}
+
+int cache_dev_start(struct dm_pcache *pcache)
+{
+	struct pcache_cache_dev *cache_dev = &pcache->cache_dev;
+	struct pcache_sb sb;
+	bool format = false;
+	int ret;
+
+	mutex_init(&cache_dev->seg_lock);
+
+	ret = cache_dev_dax_init(cache_dev);
+	if (ret) {
+		pcache_dev_err(pcache, "failed to init cache_dev %s via dax way: %d.",
+			       cache_dev->dm_dev->name, ret);
+		goto err;
+	}
+
+	ret = sb_read(cache_dev, &sb);
+	if (ret)
+		goto dax_release;
+
+	if (le64_to_cpu(sb.magic) == 0) {
+		format = true;
+		ret = sb_init(cache_dev, &sb);
+		if (ret < 0)
+			goto dax_release;
+	}
+
+	ret = sb_validate(cache_dev, &sb);
+	if (ret)
+		goto dax_release;
+
+	cache_dev->sb_flags = le32_to_cpu(sb.flags);
+	ret = cache_dev_init(cache_dev, le32_to_cpu(sb.seg_num));
+	if (ret)
+		goto dax_release;
+
+	if (format)
+		sb_write(cache_dev, &sb);
+
+	return 0;
+
+dax_release:
+	cache_dev_dax_exit(cache_dev);
+err:
+	return ret;
+}
+
+int cache_dev_get_empty_segment_id(struct pcache_cache_dev *cache_dev, u32 *seg_id)
+{
+	int ret;
+
+	mutex_lock(&cache_dev->seg_lock);
+	*seg_id = find_next_zero_bit(cache_dev->seg_bitmap, cache_dev->seg_num, 0);
+	if (*seg_id == cache_dev->seg_num) {
+		ret = -ENOSPC;
+		goto unlock;
+	}
+
+	__set_bit(*seg_id, cache_dev->seg_bitmap);
+	ret = 0;
+unlock:
+	mutex_unlock(&cache_dev->seg_lock);
+	return ret;
+}

drivers/md/dm-pcache/cache_dev.h

@@ -0,0 +1,70 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#ifndef _PCACHE_CACHE_DEV_H
+#define _PCACHE_CACHE_DEV_H
+
+#include <linux/device.h>
+#include <linux/device-mapper.h>
+
+#include "pcache_internal.h"
+
+#define PCACHE_MAGIC				0x65B05EFA96C596EFULL
+
+#define PCACHE_SB_OFF				(4 * PCACHE_KB)
+#define PCACHE_SB_SIZE				(4 * PCACHE_KB)
+
+#define PCACHE_CACHE_INFO_OFF			(PCACHE_SB_OFF + PCACHE_SB_SIZE)
+#define PCACHE_CACHE_INFO_SIZE			(4 * PCACHE_KB)
+
+#define PCACHE_CACHE_CTRL_OFF			(PCACHE_CACHE_INFO_OFF + (PCACHE_CACHE_INFO_SIZE * PCACHE_META_INDEX_MAX))
+#define PCACHE_CACHE_CTRL_SIZE			(4 * PCACHE_KB)
+
+#define PCACHE_SEGMENTS_OFF			(PCACHE_CACHE_CTRL_OFF + PCACHE_CACHE_CTRL_SIZE)
+#define PCACHE_SEG_INFO_SIZE			(4 * PCACHE_KB)
+
+#define PCACHE_CACHE_DEV_SIZE_MIN		(512 * PCACHE_MB)	/* 512 MB */
+#define PCACHE_SEG_SIZE				(16 * PCACHE_MB)	/* Size of each PCACHE segment (16 MB) */
+
+#define CACHE_DEV_SB(cache_dev)			((struct pcache_sb *)(cache_dev->mapping + PCACHE_SB_OFF))
+#define CACHE_DEV_CACHE_INFO(cache_dev)		((void *)cache_dev->mapping + PCACHE_CACHE_INFO_OFF)
+#define CACHE_DEV_CACHE_CTRL(cache_dev)		((void *)cache_dev->mapping + PCACHE_CACHE_CTRL_OFF)
+#define CACHE_DEV_SEGMENTS(cache_dev)		((void *)cache_dev->mapping + PCACHE_SEGMENTS_OFF)
+#define CACHE_DEV_SEGMENT(cache_dev, id)	((void *)CACHE_DEV_SEGMENTS(cache_dev) + (u64)id * PCACHE_SEG_SIZE)
+
+/*
+ * PCACHE SB flags configured during formatting
+ *
+ * The PCACHE_SB_F_xxx flags define registration requirements based on cache_dev
+ * formatting. For a machine to register a cache_dev:
+ * - PCACHE_SB_F_BIGENDIAN: Requires a big-endian machine.
+ */
+#define PCACHE_SB_F_BIGENDIAN			BIT(0)
+
+struct pcache_sb {
+	__le32 crc;
+	__le32 flags;
+	__le64 magic;
+
+	__le32 seg_num;
+};
+
+struct pcache_cache_dev {
+	u32				sb_flags;
+	u32				seg_num;
+	void				*mapping;
+	bool				use_vmap;
+
+	struct dm_dev			*dm_dev;
+
+	struct mutex			seg_lock;
+	unsigned long			*seg_bitmap;
+};
+
+struct dm_pcache;
+int cache_dev_start(struct dm_pcache *pcache);
+void cache_dev_stop(struct dm_pcache *pcache);
+
+void cache_dev_zero_range(struct pcache_cache_dev *cache_dev, void *pos, u32 size);
+
+int cache_dev_get_empty_segment_id(struct pcache_cache_dev *cache_dev, u32 *seg_id);
+
+#endif /* _PCACHE_CACHE_DEV_H */

drivers/md/dm-pcache/cache_gc.c

@@ -0,0 +1,170 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+#include "cache.h"
+#include "backing_dev.h"
+#include "cache_dev.h"
+#include "dm_pcache.h"
+
+/**
+ * cache_key_gc - Releases the reference of a cache key segment.
+ * @cache: Pointer to the pcache_cache structure.
+ * @key: Pointer to the cache key to be garbage collected.
+ *
+ * This function decrements the reference count of the cache segment
+ * associated with the given key. If the reference count drops to zero,
+ * the segment may be invalidated and reused.
+ */
+static void cache_key_gc(struct pcache_cache *cache, struct pcache_cache_key *key)
+{
+	cache_seg_put(key->cache_pos.cache_seg);
+}
+
+static bool need_gc(struct pcache_cache *cache, struct pcache_cache_pos *dirty_tail, struct pcache_cache_pos *key_tail)
+{
+	struct dm_pcache *pcache = CACHE_TO_PCACHE(cache);
+	struct pcache_cache_kset_onmedia *kset_onmedia;
+	void *dirty_addr, *key_addr;
+	u32 segs_used, segs_gc_threshold, to_copy;
+	int ret;
+
+	dirty_addr = cache_pos_addr(dirty_tail);
+	key_addr = cache_pos_addr(key_tail);
+	if (dirty_addr == key_addr) {
+		pcache_dev_debug(pcache, "key tail is equal to dirty tail: %u:%u\n",
+				dirty_tail->cache_seg->cache_seg_id,
+				dirty_tail->seg_off);
+		return false;
+	}
+
+	kset_onmedia = (struct pcache_cache_kset_onmedia *)cache->gc_kset_onmedia_buf;
+
+	to_copy = min(PCACHE_KSET_ONMEDIA_SIZE_MAX, PCACHE_SEG_SIZE - key_tail->seg_off);
+	ret = copy_mc_to_kernel(kset_onmedia, key_addr, to_copy);
+	if (ret) {
+		pcache_dev_err(pcache, "error to read kset: %d", ret);
+		return false;
+	}
+
+	/* Check if kset_onmedia is corrupted */
+	if (kset_onmedia->magic != PCACHE_KSET_MAGIC) {
+		pcache_dev_debug(pcache, "gc error: magic is not as expected. key_tail: %u:%u magic: %llx, expected: %llx\n",
+					key_tail->cache_seg->cache_seg_id, key_tail->seg_off,
+					kset_onmedia->magic, PCACHE_KSET_MAGIC);
+		return false;
+	}
+
+	/* Verify the CRC of the kset_onmedia */
+	if (kset_onmedia->crc != cache_kset_crc(kset_onmedia)) {
+		pcache_dev_debug(pcache, "gc error: crc is not as expected. crc: %x, expected: %x\n",
+					cache_kset_crc(kset_onmedia), kset_onmedia->crc);
+		return false;
+	}
+
+	segs_used = bitmap_weight(cache->seg_map, cache->n_segs);
+	segs_gc_threshold = cache->n_segs * pcache_cache_get_gc_percent(cache) / 100;
+	if (segs_used < segs_gc_threshold) {
+		pcache_dev_debug(pcache, "segs_used: %u, segs_gc_threshold: %u\n", segs_used, segs_gc_threshold);
+		return false;
+	}
+
+	return true;
+}
+
+/**
+ * last_kset_gc - Advances the garbage collection for the last kset.
+ * @cache: Pointer to the pcache_cache structure.
+ * @kset_onmedia: Pointer to the kset_onmedia structure for the last kset.
+ */
+static void last_kset_gc(struct pcache_cache *cache, struct pcache_cache_kset_onmedia *kset_onmedia)
+{
+	struct dm_pcache *pcache = CACHE_TO_PCACHE(cache);
+	struct pcache_cache_segment *cur_seg, *next_seg;
+
+	cur_seg = cache->key_tail.cache_seg;
+
+	next_seg = &cache->segments[kset_onmedia->next_cache_seg_id];
+
+	mutex_lock(&cache->key_tail_lock);
+	cache->key_tail.cache_seg = next_seg;
+	cache->key_tail.seg_off = 0;
+	cache_encode_key_tail(cache);
+	mutex_unlock(&cache->key_tail_lock);
+
+	pcache_dev_debug(pcache, "gc advance kset seg: %u\n", cur_seg->cache_seg_id);
+
+	spin_lock(&cache->seg_map_lock);
+	__clear_bit(cur_seg->cache_seg_id, cache->seg_map);
+	spin_unlock(&cache->seg_map_lock);
+}
+
+void pcache_cache_gc_fn(struct work_struct *work)
+{
+	struct pcache_cache *cache = container_of(work, struct pcache_cache, gc_work.work);
+	struct dm_pcache *pcache = CACHE_TO_PCACHE(cache);
+	struct pcache_cache_pos dirty_tail, key_tail;
+	struct pcache_cache_kset_onmedia *kset_onmedia;
+	struct pcache_cache_key_onmedia *key_onmedia;
+	struct pcache_cache_key *key;
+	int ret;
+	int i;
+
+	kset_onmedia = (struct pcache_cache_kset_onmedia *)cache->gc_kset_onmedia_buf;
+
+	while (true) {
+		if (pcache_is_stopping(pcache) || atomic_read(&cache->gc_errors))
+			return;
+
+		/* Get new tail positions */
+		mutex_lock(&cache->dirty_tail_lock);
+		cache_pos_copy(&dirty_tail, &cache->dirty_tail);
+		mutex_unlock(&cache->dirty_tail_lock);
+
+		mutex_lock(&cache->key_tail_lock);
+		cache_pos_copy(&key_tail, &cache->key_tail);
+		mutex_unlock(&cache->key_tail_lock);
+
+		if (!need_gc(cache, &dirty_tail, &key_tail))
+			break;
+
+		if (kset_onmedia->flags & PCACHE_KSET_FLAGS_LAST) {
+			/* Don't move to the next segment if dirty_tail has not moved */
+			if (dirty_tail.cache_seg == key_tail.cache_seg)
+				break;
+
+			last_kset_gc(cache, kset_onmedia);
+			continue;
+		}
+
+		for (i = 0; i < kset_onmedia->key_num; i++) {
+			struct pcache_cache_key key_tmp = { 0 };
+
+			key_onmedia = &kset_onmedia->data[i];
+
+			key = &key_tmp;
+			cache_key_init(&cache->req_key_tree, key);
+
+			ret = cache_key_decode(cache, key_onmedia, key);
+			if (ret) {
+				/* return without re-arm gc work, and prevent future
+				 * gc, because we can't retry the partial-gc-ed kset
+				 */
+				atomic_inc(&cache->gc_errors);
+				pcache_dev_err(pcache, "failed to decode cache key in gc\n");
+				return;
+			}
+
+			cache_key_gc(cache, key);
+		}
+
+		pcache_dev_debug(pcache, "gc advance: %u:%u %u\n",
+			key_tail.cache_seg->cache_seg_id,
+			key_tail.seg_off,
+			get_kset_onmedia_size(kset_onmedia));
+
+		mutex_lock(&cache->key_tail_lock);
+		cache_pos_advance(&cache->key_tail, get_kset_onmedia_size(kset_onmedia));
+		cache_encode_key_tail(cache);
+		mutex_unlock(&cache->key_tail_lock);
+	}
+
+	queue_delayed_work(cache_get_wq(cache), &cache->gc_work, PCACHE_CACHE_GC_INTERVAL);
+}

drivers/md/dm-pcache/cache_segment.c

@@ -0,0 +1,293 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include "cache_dev.h"
+#include "cache.h"
+#include "backing_dev.h"
+#include "dm_pcache.h"
+
+static inline struct pcache_segment_info *get_seg_info_addr(struct pcache_cache_segment *cache_seg)
+{
+	struct pcache_segment_info *seg_info_addr;
+	u32 seg_id = cache_seg->segment.seg_id;
+	void *seg_addr;
+
+	seg_addr = CACHE_DEV_SEGMENT(cache_seg->cache->cache_dev, seg_id);
+	seg_info_addr = seg_addr + PCACHE_SEG_INFO_SIZE * cache_seg->info_index;
+
+	return seg_info_addr;
+}
+
+static void cache_seg_info_write(struct pcache_cache_segment *cache_seg)
+{
+	struct pcache_segment_info *seg_info_addr;
+	struct pcache_segment_info *seg_info = &cache_seg->cache_seg_info;
+
+	mutex_lock(&cache_seg->info_lock);
+	seg_info->header.seq++;
+	seg_info->header.crc = pcache_meta_crc(&seg_info->header, sizeof(struct pcache_segment_info));
+
+	seg_info_addr = get_seg_info_addr(cache_seg);
+	memcpy_flushcache(seg_info_addr, seg_info, sizeof(struct pcache_segment_info));
+	pmem_wmb();
+
+	cache_seg->info_index = (cache_seg->info_index + 1) % PCACHE_META_INDEX_MAX;
+	mutex_unlock(&cache_seg->info_lock);
+}
+
+static int cache_seg_info_load(struct pcache_cache_segment *cache_seg)
+{
+	struct pcache_segment_info *cache_seg_info_addr_base, *cache_seg_info_addr;
+	struct pcache_cache_dev *cache_dev = cache_seg->cache->cache_dev;
+	struct dm_pcache *pcache = CACHE_DEV_TO_PCACHE(cache_dev);
+	u32 seg_id = cache_seg->segment.seg_id;
+	int ret = 0;
+
+	cache_seg_info_addr_base = CACHE_DEV_SEGMENT(cache_dev, seg_id);
+
+	mutex_lock(&cache_seg->info_lock);
+	cache_seg_info_addr = pcache_meta_find_latest(&cache_seg_info_addr_base->header,
+						sizeof(struct pcache_segment_info),
+						PCACHE_SEG_INFO_SIZE,
+						&cache_seg->cache_seg_info);
+	if (IS_ERR(cache_seg_info_addr)) {
+		ret = PTR_ERR(cache_seg_info_addr);
+		goto out;
+	} else if (!cache_seg_info_addr) {
+		ret = -EIO;
+		goto out;
+	}
+	cache_seg->info_index = cache_seg_info_addr - cache_seg_info_addr_base;
+out:
+	mutex_unlock(&cache_seg->info_lock);
+
+	if (ret)
+		pcache_dev_err(pcache, "can't read segment info of segment: %u, ret: %d\n",
+			      cache_seg->segment.seg_id, ret);
+	return ret;
+}
+
+static int cache_seg_ctrl_load(struct pcache_cache_segment *cache_seg)
+{
+	struct pcache_cache_seg_ctrl *cache_seg_ctrl = cache_seg->cache_seg_ctrl;
+	struct pcache_cache_seg_gen cache_seg_gen, *cache_seg_gen_addr;
+	int ret = 0;
+
+	mutex_lock(&cache_seg->ctrl_lock);
+	cache_seg_gen_addr = pcache_meta_find_latest(&cache_seg_ctrl->gen->header,
+					     sizeof(struct pcache_cache_seg_gen),
+					     sizeof(struct pcache_cache_seg_gen),
+					     &cache_seg_gen);
+	if (IS_ERR(cache_seg_gen_addr)) {
+		ret = PTR_ERR(cache_seg_gen_addr);
+		goto out;
+	}
+
+	if (!cache_seg_gen_addr) {
+		cache_seg->gen = 0;
+		cache_seg->gen_seq = 0;
+		cache_seg->gen_index = 0;
+		goto out;
+	}
+
+	cache_seg->gen = cache_seg_gen.gen;
+	cache_seg->gen_seq = cache_seg_gen.header.seq;
+	cache_seg->gen_index = (cache_seg_gen_addr - cache_seg_ctrl->gen);
+out:
+	mutex_unlock(&cache_seg->ctrl_lock);
+
+	return ret;
+}
+
+static inline struct pcache_cache_seg_gen *get_cache_seg_gen_addr(struct pcache_cache_segment *cache_seg)
+{
+	struct pcache_cache_seg_ctrl *cache_seg_ctrl = cache_seg->cache_seg_ctrl;
+
+	return (cache_seg_ctrl->gen + cache_seg->gen_index);
+}
+
+static void cache_seg_ctrl_write(struct pcache_cache_segment *cache_seg)
+{
+	struct pcache_cache_seg_gen cache_seg_gen;
+
+	mutex_lock(&cache_seg->ctrl_lock);
+	cache_seg_gen.gen = cache_seg->gen;
+	cache_seg_gen.header.seq = ++cache_seg->gen_seq;
+	cache_seg_gen.header.crc = pcache_meta_crc(&cache_seg_gen.header,
+						 sizeof(struct pcache_cache_seg_gen));
+
+	memcpy_flushcache(get_cache_seg_gen_addr(cache_seg), &cache_seg_gen, sizeof(struct pcache_cache_seg_gen));
+	pmem_wmb();
+
+	cache_seg->gen_index = (cache_seg->gen_index + 1) % PCACHE_META_INDEX_MAX;
+	mutex_unlock(&cache_seg->ctrl_lock);
+}
+
+static void cache_seg_ctrl_init(struct pcache_cache_segment *cache_seg)
+{
+	cache_seg->gen = 0;
+	cache_seg->gen_seq = 0;
+	cache_seg->gen_index = 0;
+	cache_seg_ctrl_write(cache_seg);
+}
+
+static int cache_seg_meta_load(struct pcache_cache_segment *cache_seg)
+{
+	int ret;
+
+	ret = cache_seg_info_load(cache_seg);
+	if (ret)
+		goto err;
+
+	ret = cache_seg_ctrl_load(cache_seg);
+	if (ret)
+		goto err;
+
+	return 0;
+err:
+	return ret;
+}
+
+/**
+ * cache_seg_set_next_seg - Sets the ID of the next segment
+ * @cache_seg: Pointer to the cache segment structure.
+ * @seg_id: The segment ID to set as the next segment.
+ *
+ * A pcache_cache allocates multiple cache segments, which are linked together
+ * through next_seg. When loading a pcache_cache, the first cache segment can
+ * be found using cache->seg_id, which allows access to all the cache segments.
+ */
+void cache_seg_set_next_seg(struct pcache_cache_segment *cache_seg, u32 seg_id)
+{
+	cache_seg->cache_seg_info.flags |= PCACHE_SEG_INFO_FLAGS_HAS_NEXT;
+	cache_seg->cache_seg_info.next_seg = seg_id;
+	cache_seg_info_write(cache_seg);
+}
+
+int cache_seg_init(struct pcache_cache *cache, u32 seg_id, u32 cache_seg_id,
+		   bool new_cache)
+{
+	struct pcache_cache_dev *cache_dev = cache->cache_dev;
+	struct pcache_cache_segment *cache_seg = &cache->segments[cache_seg_id];
+	struct pcache_segment_init_options seg_options = { 0 };
+	struct pcache_segment *segment = &cache_seg->segment;
+	int ret;
+
+	cache_seg->cache = cache;
+	cache_seg->cache_seg_id = cache_seg_id;
+	spin_lock_init(&cache_seg->gen_lock);
+	atomic_set(&cache_seg->refs, 0);
+	mutex_init(&cache_seg->info_lock);
+	mutex_init(&cache_seg->ctrl_lock);
+
+	/* init pcache_segment */
+	seg_options.type = PCACHE_SEGMENT_TYPE_CACHE_DATA;
+	seg_options.data_off = PCACHE_CACHE_SEG_CTRL_OFF + PCACHE_CACHE_SEG_CTRL_SIZE;
+	seg_options.seg_id = seg_id;
+	seg_options.seg_info = &cache_seg->cache_seg_info;
+	pcache_segment_init(cache_dev, segment, &seg_options);
+
+	cache_seg->cache_seg_ctrl = CACHE_DEV_SEGMENT(cache_dev, seg_id) + PCACHE_CACHE_SEG_CTRL_OFF;
+
+	if (new_cache) {
+		cache_dev_zero_range(cache_dev, CACHE_DEV_SEGMENT(cache_dev, seg_id),
+				     PCACHE_SEG_INFO_SIZE * PCACHE_META_INDEX_MAX +
+				     PCACHE_CACHE_SEG_CTRL_SIZE);
+
+		cache_seg_ctrl_init(cache_seg);
+
+		cache_seg->info_index = 0;
+		cache_seg_info_write(cache_seg);
+
+		/* clear outdated kset in segment */
+		memcpy_flushcache(segment->data, &pcache_empty_kset, sizeof(struct pcache_cache_kset_onmedia));
+		pmem_wmb();
+	} else {
+		ret = cache_seg_meta_load(cache_seg);
+		if (ret)
+			goto err;
+	}
+
+	return 0;
+err:
+	return ret;
+}
+
+/**
+ * get_cache_segment - Retrieves a free cache segment from the cache.
+ * @cache: Pointer to the cache structure.
+ *
+ * This function attempts to find a free cache segment that can be used.
+ * It locks the segment map and checks for the next available segment ID.
+ * If a free segment is found, it initializes it and returns a pointer to the
+ * cache segment structure. Returns NULL if no segments are available.
+ */
+struct pcache_cache_segment *get_cache_segment(struct pcache_cache *cache)
+{
+	struct pcache_cache_segment *cache_seg;
+	u32 seg_id;
+
+	spin_lock(&cache->seg_map_lock);
+again:
+	seg_id = find_next_zero_bit(cache->seg_map, cache->n_segs, cache->last_cache_seg);
+	if (seg_id == cache->n_segs) {
+		/* reset the hint of ->last_cache_seg and retry */
+		if (cache->last_cache_seg) {
+			cache->last_cache_seg = 0;
+			goto again;
+		}
+		cache->cache_full = true;
+		spin_unlock(&cache->seg_map_lock);
+		return NULL;
+	}
+
+	/*
+	 * found an available cache_seg, mark it used in seg_map
+	 * and update the search hint ->last_cache_seg
+	 */
+	__set_bit(seg_id, cache->seg_map);
+	cache->last_cache_seg = seg_id;
+	spin_unlock(&cache->seg_map_lock);
+
+	cache_seg = &cache->segments[seg_id];
+	cache_seg->cache_seg_id = seg_id;
+
+	return cache_seg;
+}
+
+static void cache_seg_gen_increase(struct pcache_cache_segment *cache_seg)
+{
+	spin_lock(&cache_seg->gen_lock);
+	cache_seg->gen++;
+	spin_unlock(&cache_seg->gen_lock);
+
+	cache_seg_ctrl_write(cache_seg);
+}
+
+void cache_seg_get(struct pcache_cache_segment *cache_seg)
+{
+	atomic_inc(&cache_seg->refs);
+}
+
+static void cache_seg_invalidate(struct pcache_cache_segment *cache_seg)
+{
+	struct pcache_cache *cache;
+
+	cache = cache_seg->cache;
+	cache_seg_gen_increase(cache_seg);
+
+	spin_lock(&cache->seg_map_lock);
+	if (cache->cache_full)
+		cache->cache_full = false;
+	__clear_bit(cache_seg->cache_seg_id, cache->seg_map);
+	spin_unlock(&cache->seg_map_lock);
+
+	pcache_defer_reqs_kick(CACHE_TO_PCACHE(cache));
+	/* clean_work will clean the bad key in key_tree*/
+	queue_work(cache_get_wq(cache), &cache->clean_work);
+}
+
+void cache_seg_put(struct pcache_cache_segment *cache_seg)
+{
+	if (atomic_dec_and_test(&cache_seg->refs))
+		cache_seg_invalidate(cache_seg);
+}

drivers/md/dm-pcache/cache_writeback.c

@@ -0,0 +1,261 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <linux/bio.h>
+
+#include "cache.h"
+#include "backing_dev.h"
+#include "cache_dev.h"
+#include "dm_pcache.h"
+
+static void writeback_ctx_end(struct pcache_cache *cache, int ret)
+{
+	if (ret && !cache->writeback_ctx.ret) {
+		pcache_dev_err(CACHE_TO_PCACHE(cache), "writeback error: %d", ret);
+		cache->writeback_ctx.ret = ret;
+	}
+
+	if (!atomic_dec_and_test(&cache->writeback_ctx.pending))
+		return;
+
+	if (!cache->writeback_ctx.ret) {
+		backing_dev_flush(cache->backing_dev);
+
+		mutex_lock(&cache->dirty_tail_lock);
+		cache_pos_advance(&cache->dirty_tail, cache->writeback_ctx.advance);
+		cache_encode_dirty_tail(cache);
+		mutex_unlock(&cache->dirty_tail_lock);
+	}
+	queue_delayed_work(cache_get_wq(cache), &cache->writeback_work, 0);
+}
+
+static void writeback_end_req(struct pcache_backing_dev_req *backing_req, int ret)
+{
+	struct pcache_cache *cache = backing_req->priv_data;
+
+	mutex_lock(&cache->writeback_lock);
+	writeback_ctx_end(cache, ret);
+	mutex_unlock(&cache->writeback_lock);
+}
+
+static inline bool is_cache_clean(struct pcache_cache *cache, struct pcache_cache_pos *dirty_tail)
+{
+	struct dm_pcache *pcache = CACHE_TO_PCACHE(cache);
+	struct pcache_cache_kset_onmedia *kset_onmedia;
+	u32 to_copy;
+	void *addr;
+	int ret;
+
+	addr = cache_pos_addr(dirty_tail);
+	kset_onmedia = (struct pcache_cache_kset_onmedia *)cache->wb_kset_onmedia_buf;
+
+	to_copy = min(PCACHE_KSET_ONMEDIA_SIZE_MAX, PCACHE_SEG_SIZE - dirty_tail->seg_off);
+	ret = copy_mc_to_kernel(kset_onmedia, addr, to_copy);
+	if (ret) {
+		pcache_dev_err(pcache, "error to read kset: %d", ret);
+		return true;
+	}
+
+	/* Check if the magic number matches the expected value */
+	if (kset_onmedia->magic != PCACHE_KSET_MAGIC) {
+		pcache_dev_debug(pcache, "dirty_tail: %u:%u magic: %llx, not expected: %llx\n",
+				dirty_tail->cache_seg->cache_seg_id, dirty_tail->seg_off,
+				kset_onmedia->magic, PCACHE_KSET_MAGIC);
+		return true;
+	}
+
+	/* Verify the CRC checksum for data integrity */
+	if (kset_onmedia->crc != cache_kset_crc(kset_onmedia)) {
+		pcache_dev_debug(pcache, "dirty_tail: %u:%u crc: %x, not expected: %x\n",
+				dirty_tail->cache_seg->cache_seg_id, dirty_tail->seg_off,
+				cache_kset_crc(kset_onmedia), kset_onmedia->crc);
+		return true;
+	}
+
+	return false;
+}
+
+void cache_writeback_exit(struct pcache_cache *cache)
+{
+	cancel_delayed_work_sync(&cache->writeback_work);
+	backing_dev_flush(cache->backing_dev);
+	cache_tree_exit(&cache->writeback_key_tree);
+}
+
+int cache_writeback_init(struct pcache_cache *cache)
+{
+	int ret;
+
+	ret = cache_tree_init(cache, &cache->writeback_key_tree, 1);
+	if (ret)
+		goto err;
+
+	atomic_set(&cache->writeback_ctx.pending, 0);
+
+	/* Queue delayed work to start writeback handling */
+	queue_delayed_work(cache_get_wq(cache), &cache->writeback_work, 0);
+
+	return 0;
+err:
+	return ret;
+}
+
+static void cache_key_writeback(struct pcache_cache *cache, struct pcache_cache_key *key)
+{
+	struct pcache_backing_dev_req *writeback_req;
+	struct pcache_backing_dev_req_opts writeback_req_opts = { 0 };
+	struct pcache_cache_pos *pos;
+	void *addr;
+	u32 seg_remain, req_len, done = 0;
+
+	if (cache_key_clean(key))
+		return;
+
+	pos = &key->cache_pos;
+
+	seg_remain = cache_seg_remain(pos);
+	BUG_ON(seg_remain < key->len);
+next_req:
+	addr = cache_pos_addr(pos) + done;
+	req_len = backing_dev_req_coalesced_max_len(addr, key->len - done);
+
+	writeback_req_opts.type = BACKING_DEV_REQ_TYPE_KMEM;
+	writeback_req_opts.gfp_mask = GFP_NOIO;
+	writeback_req_opts.end_fn = writeback_end_req;
+	writeback_req_opts.priv_data = cache;
+
+	writeback_req_opts.kmem.data = addr;
+	writeback_req_opts.kmem.opf = REQ_OP_WRITE;
+	writeback_req_opts.kmem.len = req_len;
+	writeback_req_opts.kmem.backing_off = key->off + done;
+
+	writeback_req = backing_dev_req_create(cache->backing_dev, &writeback_req_opts);
+
+	atomic_inc(&cache->writeback_ctx.pending);
+	backing_dev_req_submit(writeback_req, true);
+
+	done += req_len;
+	if (done < key->len)
+		goto next_req;
+}
+
+static void cache_wb_tree_writeback(struct pcache_cache *cache, u32 advance)
+{
+	struct pcache_cache_tree *cache_tree = &cache->writeback_key_tree;
+	struct pcache_cache_subtree *cache_subtree;
+	struct rb_node *node;
+	struct pcache_cache_key *key;
+	u32 i;
+
+	cache->writeback_ctx.ret = 0;
+	cache->writeback_ctx.advance = advance;
+	atomic_set(&cache->writeback_ctx.pending, 1);
+
+	for (i = 0; i < cache_tree->n_subtrees; i++) {
+		cache_subtree = &cache_tree->subtrees[i];
+
+		node = rb_first(&cache_subtree->root);
+		while (node) {
+			key = CACHE_KEY(node);
+			node = rb_next(node);
+
+			cache_key_writeback(cache, key);
+			cache_key_delete(key);
+		}
+	}
+	writeback_ctx_end(cache, 0);
+}
+
+static int cache_kset_insert_tree(struct pcache_cache *cache, struct pcache_cache_kset_onmedia *kset_onmedia)
+{
+	struct pcache_cache_key_onmedia *key_onmedia;
+	struct pcache_cache_subtree *cache_subtree;
+	struct pcache_cache_key *key;
+	int ret;
+	u32 i;
+
+	/* Iterate through all keys in the kset and write each back to storage */
+	for (i = 0; i < kset_onmedia->key_num; i++) {
+		key_onmedia = &kset_onmedia->data[i];
+
+		key = cache_key_alloc(&cache->writeback_key_tree, GFP_NOIO);
+		ret = cache_key_decode(cache, key_onmedia, key);
+		if (ret) {
+			cache_key_put(key);
+			goto clear_tree;
+		}
+
+		cache_subtree = get_subtree(&cache->writeback_key_tree, key->off);
+		spin_lock(&cache_subtree->tree_lock);
+		cache_key_insert(&cache->writeback_key_tree, key, true);
+		spin_unlock(&cache_subtree->tree_lock);
+	}
+
+	return 0;
+clear_tree:
+	cache_tree_clear(&cache->writeback_key_tree);
+	return ret;
+}
+
+static void last_kset_writeback(struct pcache_cache *cache,
+		struct pcache_cache_kset_onmedia *last_kset_onmedia)
+{
+	struct dm_pcache *pcache = CACHE_TO_PCACHE(cache);
+	struct pcache_cache_segment *next_seg;
+
+	pcache_dev_debug(pcache, "last kset, next: %u\n", last_kset_onmedia->next_cache_seg_id);
+
+	next_seg = &cache->segments[last_kset_onmedia->next_cache_seg_id];
+
+	mutex_lock(&cache->dirty_tail_lock);
+	cache->dirty_tail.cache_seg = next_seg;
+	cache->dirty_tail.seg_off = 0;
+	cache_encode_dirty_tail(cache);
+	mutex_unlock(&cache->dirty_tail_lock);
+}
+
+void cache_writeback_fn(struct work_struct *work)
+{
+	struct pcache_cache *cache = container_of(work, struct pcache_cache, writeback_work.work);
+	struct dm_pcache *pcache = CACHE_TO_PCACHE(cache);
+	struct pcache_cache_pos dirty_tail;
+	struct pcache_cache_kset_onmedia *kset_onmedia;
+	u32 delay;
+	int ret;
+
+	mutex_lock(&cache->writeback_lock);
+	if (atomic_read(&cache->writeback_ctx.pending))
+		goto unlock;
+
+	if (pcache_is_stopping(pcache))
+		goto unlock;
+
+	kset_onmedia = (struct pcache_cache_kset_onmedia *)cache->wb_kset_onmedia_buf;
+
+	mutex_lock(&cache->dirty_tail_lock);
+	cache_pos_copy(&dirty_tail, &cache->dirty_tail);
+	mutex_unlock(&cache->dirty_tail_lock);
+
+	if (is_cache_clean(cache, &dirty_tail)) {
+		delay = PCACHE_CACHE_WRITEBACK_INTERVAL;
+		goto queue_work;
+	}
+
+	if (kset_onmedia->flags & PCACHE_KSET_FLAGS_LAST) {
+		last_kset_writeback(cache, kset_onmedia);
+		delay = 0;
+		goto queue_work;
+	}
+
+	ret = cache_kset_insert_tree(cache, kset_onmedia);
+	if (ret) {
+		delay = PCACHE_CACHE_WRITEBACK_INTERVAL;
+		goto queue_work;
+	}
+
+	cache_wb_tree_writeback(cache, get_kset_onmedia_size(kset_onmedia));
+	delay = 0;
+queue_work:
+	queue_delayed_work(cache_get_wq(cache), &cache->writeback_work, delay);
+unlock:
+	mutex_unlock(&cache->writeback_lock);
+}

drivers/md/dm-pcache/dm_pcache.c

@@ -0,0 +1,497 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+#include <linux/module.h>
+#include <linux/blkdev.h>
+#include <linux/bio.h>
+
+#include "../dm-core.h"
+#include "cache_dev.h"
+#include "backing_dev.h"
+#include "cache.h"
+#include "dm_pcache.h"
+
+void pcache_defer_reqs_kick(struct dm_pcache *pcache)
+{
+	struct pcache_cache *cache = &pcache->cache;
+
+	spin_lock(&cache->seg_map_lock);
+	if (!cache->cache_full)
+		queue_work(pcache->task_wq, &pcache->defered_req_work);
+	spin_unlock(&cache->seg_map_lock);
+}
+
+static void defer_req(struct pcache_request *pcache_req)
+{
+	struct dm_pcache *pcache = pcache_req->pcache;
+
+	BUG_ON(!list_empty(&pcache_req->list_node));
+
+	spin_lock(&pcache->defered_req_list_lock);
+	list_add(&pcache_req->list_node, &pcache->defered_req_list);
+	pcache_defer_reqs_kick(pcache);
+	spin_unlock(&pcache->defered_req_list_lock);
+}
+
+static void defered_req_fn(struct work_struct *work)
+{
+	struct dm_pcache *pcache = container_of(work, struct dm_pcache, defered_req_work);
+	struct pcache_request *pcache_req;
+	LIST_HEAD(tmp_list);
+	int ret;
+
+	if (pcache_is_stopping(pcache))
+		return;
+
+	spin_lock(&pcache->defered_req_list_lock);
+	list_splice_init(&pcache->defered_req_list, &tmp_list);
+	spin_unlock(&pcache->defered_req_list_lock);
+
+	while (!list_empty(&tmp_list)) {
+		pcache_req = list_first_entry(&tmp_list,
+					    struct pcache_request, list_node);
+		list_del_init(&pcache_req->list_node);
+		pcache_req->ret = 0;
+		ret = pcache_cache_handle_req(&pcache->cache, pcache_req);
+		if (ret == -EBUSY)
+			defer_req(pcache_req);
+		else
+			pcache_req_put(pcache_req, ret);
+	}
+}
+
+void pcache_req_get(struct pcache_request *pcache_req)
+{
+	kref_get(&pcache_req->ref);
+}
+
+static void end_req(struct kref *ref)
+{
+	struct pcache_request *pcache_req = container_of(ref, struct pcache_request, ref);
+	struct dm_pcache *pcache = pcache_req->pcache;
+	struct bio *bio = pcache_req->bio;
+	int ret = pcache_req->ret;
+
+	if (ret == -EBUSY) {
+		pcache_req_get(pcache_req);
+		defer_req(pcache_req);
+	} else {
+		bio->bi_status = errno_to_blk_status(ret);
+		bio_endio(bio);
+
+		if (atomic_dec_and_test(&pcache->inflight_reqs))
+			wake_up(&pcache->inflight_wq);
+	}
+}
+
+void pcache_req_put(struct pcache_request *pcache_req, int ret)
+{
+	/* Set the return status if it is not already set */
+	if (ret && !pcache_req->ret)
+		pcache_req->ret = ret;
+
+	kref_put(&pcache_req->ref, end_req);
+}
+
+static bool at_least_one_arg(struct dm_arg_set *as, char **error)
+{
+	if (!as->argc) {
+		*error = "Insufficient args";
+		return false;
+	}
+
+	return true;
+}
+
+static int parse_cache_dev(struct dm_pcache *pcache, struct dm_arg_set *as,
+				char **error)
+{
+	int ret;
+
+	if (!at_least_one_arg(as, error))
+		return -EINVAL;
+	ret = dm_get_device(pcache->ti, dm_shift_arg(as),
+			  BLK_OPEN_READ | BLK_OPEN_WRITE,
+			  &pcache->cache_dev.dm_dev);
+	if (ret) {
+		*error = "Error opening cache device";
+		return ret;
+	}
+
+	return 0;
+}
+
+static int parse_backing_dev(struct dm_pcache *pcache, struct dm_arg_set *as,
+				char **error)
+{
+	int ret;
+
+	if (!at_least_one_arg(as, error))
+		return -EINVAL;
+
+	ret = dm_get_device(pcache->ti, dm_shift_arg(as),
+			  BLK_OPEN_READ | BLK_OPEN_WRITE,
+			  &pcache->backing_dev.dm_dev);
+	if (ret) {
+		*error = "Error opening backing device";
+		return ret;
+	}
+
+	return 0;
+}
+
+static void pcache_init_opts(struct pcache_cache_options *opts)
+{
+	opts->cache_mode = PCACHE_CACHE_MODE_WRITEBACK;
+	opts->data_crc = false;
+}
+
+static int parse_cache_opts(struct dm_pcache *pcache, struct dm_arg_set *as,
+			    char **error)
+{
+	struct pcache_cache_options *opts = &pcache->opts;
+	static const struct dm_arg _args[] = {
+		{0, 4, "Invalid number of cache option arguments"},
+	};
+	unsigned int argc;
+	const char *arg;
+	int ret;
+
+	pcache_init_opts(opts);
+	if (!as->argc)
+		return 0;
+
+	ret = dm_read_arg_group(_args, as, &argc, error);
+	if (ret)
+		return -EINVAL;
+
+	while (argc) {
+		arg = dm_shift_arg(as);
+		argc--;
+
+		if (!strcmp(arg, "cache_mode")) {
+			arg = dm_shift_arg(as);
+			if (!strcmp(arg, "writeback")) {
+				opts->cache_mode = PCACHE_CACHE_MODE_WRITEBACK;
+			} else {
+				*error = "Invalid cache mode parameter";
+				return -EINVAL;
+			}
+			argc--;
+		} else if (!strcmp(arg, "data_crc")) {
+			arg = dm_shift_arg(as);
+			if (!strcmp(arg, "true")) {
+				opts->data_crc = true;
+			} else if (!strcmp(arg, "false")) {
+				opts->data_crc = false;
+			} else {
+				*error = "Invalid data crc parameter";
+				return -EINVAL;
+			}
+			argc--;
+		} else {
+			*error = "Unrecognised cache option requested";
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
+static int pcache_start(struct dm_pcache *pcache, char **error)
+{
+	int ret;
+
+	ret = cache_dev_start(pcache);
+	if (ret) {
+		*error = "Failed to start cache dev";
+		return ret;
+	}
+
+	ret = backing_dev_start(pcache);
+	if (ret) {
+		*error = "Failed to start backing dev";
+		goto stop_cache;
+	}
+
+	ret = pcache_cache_start(pcache);
+	if (ret) {
+		*error = "Failed to start pcache";
+		goto stop_backing;
+	}
+
+	return 0;
+stop_backing:
+	backing_dev_stop(pcache);
+stop_cache:
+	cache_dev_stop(pcache);
+
+	return ret;
+}
+
+static void pcache_destroy_args(struct dm_pcache *pcache)
+{
+	if (pcache->cache_dev.dm_dev)
+		dm_put_device(pcache->ti, pcache->cache_dev.dm_dev);
+	if (pcache->backing_dev.dm_dev)
+		dm_put_device(pcache->ti, pcache->backing_dev.dm_dev);
+}
+
+static int pcache_parse_args(struct dm_pcache *pcache, unsigned int argc, char **argv,
+				char **error)
+{
+	struct dm_arg_set as;
+	int ret;
+
+	as.argc = argc;
+	as.argv = argv;
+
+	/*
+	 * Parse cache device
+	 */
+	ret = parse_cache_dev(pcache, &as, error);
+	if (ret)
+		return ret;
+	/*
+	 * Parse backing device
+	 */
+	ret = parse_backing_dev(pcache, &as, error);
+	if (ret)
+		goto out;
+	/*
+	 * Parse optional arguments
+	 */
+	ret = parse_cache_opts(pcache, &as, error);
+	if (ret)
+		goto out;
+
+	return 0;
+out:
+	pcache_destroy_args(pcache);
+	return ret;
+}
+
+static int dm_pcache_ctr(struct dm_target *ti, unsigned int argc, char **argv)
+{
+	struct mapped_device *md = ti->table->md;
+	struct dm_pcache *pcache;
+	int ret;
+
+	if (md->map) {
+		ti->error = "Don't support table loading for live md";
+		return -EOPNOTSUPP;
+	}
+
+	/* Allocate memory for the cache structure */
+	pcache = kzalloc(sizeof(struct dm_pcache), GFP_KERNEL);
+	if (!pcache)
+		return -ENOMEM;
+
+	pcache->task_wq = alloc_workqueue("pcache-%s-wq",  WQ_UNBOUND | WQ_MEM_RECLAIM,
+					  0, md->name);
+	if (!pcache->task_wq) {
+		ret = -ENOMEM;
+		goto free_pcache;
+	}
+
+	spin_lock_init(&pcache->defered_req_list_lock);
+	INIT_LIST_HEAD(&pcache->defered_req_list);
+	INIT_WORK(&pcache->defered_req_work, defered_req_fn);
+	pcache->ti = ti;
+
+	ret = pcache_parse_args(pcache, argc, argv, &ti->error);
+	if (ret)
+		goto destroy_wq;
+
+	ret = pcache_start(pcache, &ti->error);
+	if (ret)
+		goto destroy_args;
+
+	ti->num_flush_bios = 1;
+	ti->flush_supported = true;
+	ti->per_io_data_size = sizeof(struct pcache_request);
+	ti->private = pcache;
+	atomic_set(&pcache->inflight_reqs, 0);
+	atomic_set(&pcache->state, PCACHE_STATE_RUNNING);
+	init_waitqueue_head(&pcache->inflight_wq);
+
+	return 0;
+destroy_args:
+	pcache_destroy_args(pcache);
+destroy_wq:
+	destroy_workqueue(pcache->task_wq);
+free_pcache:
+	kfree(pcache);
+
+	return ret;
+}
+
+static void defer_req_stop(struct dm_pcache *pcache)
+{
+	struct pcache_request *pcache_req;
+	LIST_HEAD(tmp_list);
+
+	flush_work(&pcache->defered_req_work);
+
+	spin_lock(&pcache->defered_req_list_lock);
+	list_splice_init(&pcache->defered_req_list, &tmp_list);
+	spin_unlock(&pcache->defered_req_list_lock);
+
+	while (!list_empty(&tmp_list)) {
+		pcache_req = list_first_entry(&tmp_list,
+					    struct pcache_request, list_node);
+		list_del_init(&pcache_req->list_node);
+		pcache_req_put(pcache_req, -EIO);
+	}
+}
+
+static void dm_pcache_dtr(struct dm_target *ti)
+{
+	struct dm_pcache *pcache;
+
+	pcache = ti->private;
+	atomic_set(&pcache->state, PCACHE_STATE_STOPPING);
+	defer_req_stop(pcache);
+
+	wait_event(pcache->inflight_wq,
+			atomic_read(&pcache->inflight_reqs) == 0);
+
+	pcache_cache_stop(pcache);
+	backing_dev_stop(pcache);
+	cache_dev_stop(pcache);
+
+	pcache_destroy_args(pcache);
+	drain_workqueue(pcache->task_wq);
+	destroy_workqueue(pcache->task_wq);
+
+	kfree(pcache);
+}
+
+static int dm_pcache_map_bio(struct dm_target *ti, struct bio *bio)
+{
+	struct pcache_request *pcache_req = dm_per_bio_data(bio, sizeof(struct pcache_request));
+	struct dm_pcache *pcache = ti->private;
+	int ret;
+
+	pcache_req->pcache = pcache;
+	kref_init(&pcache_req->ref);
+	pcache_req->ret = 0;
+	pcache_req->bio = bio;
+	pcache_req->off = (u64)bio->bi_iter.bi_sector << SECTOR_SHIFT;
+	pcache_req->data_len = bio->bi_iter.bi_size;
+	INIT_LIST_HEAD(&pcache_req->list_node);
+	atomic_inc(&pcache->inflight_reqs);
+
+	ret = pcache_cache_handle_req(&pcache->cache, pcache_req);
+	if (ret == -EBUSY)
+		defer_req(pcache_req);
+	else
+		pcache_req_put(pcache_req, ret);
+
+	return DM_MAPIO_SUBMITTED;
+}
+
+static void dm_pcache_status(struct dm_target *ti, status_type_t type,
+			     unsigned int status_flags, char *result,
+			     unsigned int maxlen)
+{
+	struct dm_pcache *pcache = ti->private;
+	struct pcache_cache_dev *cache_dev = &pcache->cache_dev;
+	struct pcache_backing_dev *backing_dev = &pcache->backing_dev;
+	struct pcache_cache *cache = &pcache->cache;
+	unsigned int sz = 0;
+
+	switch (type) {
+	case STATUSTYPE_INFO:
+		DMEMIT("%x %u %u %u %u %x %u:%u %u:%u %u:%u",
+		       cache_dev->sb_flags,
+		       cache_dev->seg_num,
+		       cache->n_segs,
+		       bitmap_weight(cache->seg_map, cache->n_segs),
+		       pcache_cache_get_gc_percent(cache),
+		       cache->cache_info.flags,
+		       cache->key_head.cache_seg->cache_seg_id,
+		       cache->key_head.seg_off,
+		       cache->dirty_tail.cache_seg->cache_seg_id,
+		       cache->dirty_tail.seg_off,
+		       cache->key_tail.cache_seg->cache_seg_id,
+		       cache->key_tail.seg_off);
+		break;
+	case STATUSTYPE_TABLE:
+		DMEMIT("%s %s 4 cache_mode writeback crc %s",
+		       cache_dev->dm_dev->name,
+		       backing_dev->dm_dev->name,
+		       cache_data_crc_on(cache) ? "true" : "false");
+		break;
+	case STATUSTYPE_IMA:
+		*result = '\0';
+		break;
+	}
+}
+
+static int dm_pcache_message(struct dm_target *ti, unsigned int argc,
+			     char **argv, char *result, unsigned int maxlen)
+{
+	struct dm_pcache *pcache = ti->private;
+	unsigned long val;
+
+	if (argc != 2)
+		goto err;
+
+	if (!strcasecmp(argv[0], "gc_percent")) {
+		if (kstrtoul(argv[1], 10, &val))
+			goto err;
+
+		return pcache_cache_set_gc_percent(&pcache->cache, val);
+	}
+err:
+	return -EINVAL;
+}
+
+static struct target_type dm_pcache_target = {
+	.name		= "pcache",
+	.version	= {0, 1, 0},
+	.module		= THIS_MODULE,
+	.features	= DM_TARGET_SINGLETON,
+	.ctr		= dm_pcache_ctr,
+	.dtr		= dm_pcache_dtr,
+	.map		= dm_pcache_map_bio,
+	.status		= dm_pcache_status,
+	.message	= dm_pcache_message,
+};
+
+static int __init dm_pcache_init(void)
+{
+	int ret;
+
+	ret = pcache_backing_init();
+	if (ret)
+		goto err;
+
+	ret = pcache_cache_init();
+	if (ret)
+		goto backing_exit;
+
+	ret = dm_register_target(&dm_pcache_target);
+	if (ret)
+		goto cache_exit;
+	return 0;
+
+cache_exit:
+	pcache_cache_exit();
+backing_exit:
+	pcache_backing_exit();
+err:
+	return ret;
+}
+module_init(dm_pcache_init);
+
+static void __exit dm_pcache_exit(void)
+{
+	dm_unregister_target(&dm_pcache_target);
+	pcache_cache_exit();
+	pcache_backing_exit();
+}
+module_exit(dm_pcache_exit);
+
+MODULE_DESCRIPTION("dm-pcache Persistent Cache for block device");
+MODULE_AUTHOR("Dongsheng Yang <dongsheng.yang@linux.dev>");
+MODULE_LICENSE("GPL");

drivers/md/dm-pcache/dm_pcache.h

@@ -0,0 +1,67 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#ifndef _DM_PCACHE_H
+#define _DM_PCACHE_H
+#include <linux/device-mapper.h>
+
+#include "../dm-core.h"
+
+#define CACHE_DEV_TO_PCACHE(cache_dev)		(container_of(cache_dev, struct dm_pcache, cache_dev))
+#define BACKING_DEV_TO_PCACHE(backing_dev)	(container_of(backing_dev, struct dm_pcache, backing_dev))
+#define CACHE_TO_PCACHE(cache)			(container_of(cache, struct dm_pcache, cache))
+
+#define PCACHE_STATE_RUNNING			1
+#define PCACHE_STATE_STOPPING			2
+
+struct pcache_cache_dev;
+struct pcache_backing_dev;
+struct pcache_cache;
+struct pcache_cache_options;
+struct dm_pcache {
+	struct dm_target *ti;
+	struct pcache_cache_dev cache_dev;
+	struct pcache_backing_dev backing_dev;
+	struct pcache_cache cache;
+	struct pcache_cache_options opts;
+
+	spinlock_t			defered_req_list_lock;
+	struct list_head		defered_req_list;
+	struct workqueue_struct		*task_wq;
+
+	struct work_struct		defered_req_work;
+
+	atomic_t			state;
+	atomic_t			inflight_reqs;
+	wait_queue_head_t		inflight_wq;
+};
+
+static inline bool pcache_is_stopping(struct dm_pcache *pcache)
+{
+	return (atomic_read(&pcache->state) == PCACHE_STATE_STOPPING);
+}
+
+#define pcache_dev_err(pcache, fmt, ...)							\
+	pcache_err("%s " fmt, pcache->ti->table->md->name, ##__VA_ARGS__)
+#define pcache_dev_info(pcache, fmt, ...)							\
+	pcache_info("%s " fmt, pcache->ti->table->md->name, ##__VA_ARGS__)
+#define pcache_dev_debug(pcache, fmt, ...)							\
+	pcache_debug("%s " fmt, pcache->ti->table->md->name, ##__VA_ARGS__)
+
+struct pcache_request {
+	struct dm_pcache	*pcache;
+	struct bio		*bio;
+
+	u64			off;
+	u32			data_len;
+
+	struct kref		ref;
+	int			ret;
+
+	struct list_head	list_node;
+};
+
+void pcache_req_get(struct pcache_request *pcache_req);
+void pcache_req_put(struct pcache_request *pcache_req, int ret);
+
+void pcache_defer_reqs_kick(struct dm_pcache *pcache);
+
+#endif /* _DM_PCACHE_H */