Merge tag 'for-6.18/dm-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm

Pull device mapper updates from Mikulas Patocka:

 - a new dm-pcache target for read/write caching on persistent memory

 - fix typos in docs

 - misc small refactoring

 - mark dm-error with DM_TARGET_PASSES_INTEGRITY

 - dm-request-based: fix NULL pointer dereference and quiesce_depth out of sync

 - dm-linear: optimize REQ_PREFLUSH

 - dm-vdo: return error on corrupted metadata

 - dm-integrity: support asynchronous hash interface

* tag 'for-6.18/dm-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm: (27 commits)
  dm raid: use proper md_ro_state enumerators
  dm-integrity: prefer synchronous hash interface
  dm-integrity: enable asynchronous hash interface
  dm-integrity: rename internal_hash
  dm-integrity: add the "offset" argument
  dm-integrity: allocate the recalculate buffer with kmalloc
  dm-integrity: introduce integrity_kmap and integrity_kunmap
  dm-integrity: replace bvec_kmap_local with kmap_local_page
  dm-integrity: use internal variable for digestsize
  dm vdo: return error on corrupted metadata in start_restoring_volume functions
  dm vdo: Update code to use mem_is_zero
  dm: optimize REQ_PREFLUSH with data when using the linear target
  dm-pcache: use int type to store negative error codes
  dm: fix "writen"->"written"
  dm-pcache: cleanup: fix coding style report by checkpatch.pl
  dm-pcache: remove ctrl_lock for pcache_cache_segment
  dm: fix NULL pointer dereference in __dm_suspend()
  dm: fix queue start/stop imbalance under suspend/load/resume races
  dm-pcache: add persistent cache target in device-mapper
  dm error: mark as DM_TARGET_PASSES_INTEGRITY
  ...

Author: torvalds

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

@@ -3,7 +3,7 @@ dm-delay
 ========
 
 Device-Mapper's "delay" target delays reads and/or writes
-and/or flushs and optionally maps them to different devices.
+and/or flushes and optionally maps them to different devices.
 
 Arguments::
 
@@ -18,7 +18,7 @@ Table line has to either have 3, 6 or 9 arguments:
    to write and flush operations on optionally different write_device with
    optionally different sector offset
 
-9: same as 6 arguments plus define flush_offset and flush_delay explicitely
+9: same as 6 arguments plus define flush_offset and flush_delay explicitly
    on/with optionally different flush_device/flush_offset.
 
 Offsets are specified in sectors.
@@ -40,15 +40,15 @@ Example scripts
 	#!/bin/sh
 	#
 	# Create mapped device delaying write and flush operations for 400ms and
-	# splitting reads to device $1 but writes and flushs to different device $2
+	# splitting reads to device $1 but writes and flushes to different device $2
 	# to different offsets of 2048 and 4096 sectors respectively.
 	#
 	dmsetup create delayed --table "0 `blockdev --getsz $1` delay $1 2048 0 $2 4096 400"
 
 ::
 	#!/bin/sh
 	#
-	# Create mapped device delaying reads for 50ms, writes for 100ms and flushs for 333ms
+	# Create mapped device delaying reads for 50ms, writes for 100ms and flushes for 333ms
 	# onto the same backing device at offset 0 sectors.
 	#
 	dmsetup create delayed --table "0 `blockdev --getsz $1` delay $1 0 50 $2 0 100 $1 0 333"

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 <[email protected]>*
+
+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

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

@@ -1,5 +1,6 @@
 .. SPDX-License-Identifier: GPL-2.0-only
 
+======
 dm-vdo
 ======
 

MAINTAINERS

@@ -7133,6 +7133,14 @@ S:	Maintained
 F:	Documentation/admin-guide/device-mapper/vdo*.rst
 F:	drivers/md/dm-vdo/
 
+DEVICE-MAPPER PCACHE TARGET
+M:	Dongsheng Yang <[email protected]>
+M:	Zheng Gu <[email protected]>
+L:	[email protected]
+S:	Maintained
+F:	Documentation/admin-guide/device-mapper/dm-pcache.rst
+F:	drivers/md/dm-pcache/
+
 DEVLINK
 M:	Jiri Pirko <[email protected]>
 L:	[email protected]

drivers/md/Kconfig

@@ -688,4 +688,6 @@ config DM_AUDIT
 
 source "drivers/md/dm-vdo/Kconfig"
 
+source "drivers/md/dm-pcache/Kconfig"
+
 endif # MD

drivers/md/Makefile

@@ -73,6 +73,7 @@ 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-bufio.c

@@ -1337,7 +1337,7 @@ static void use_bio(struct dm_buffer *b, enum req_op op, sector_t sector,
 	char *ptr;
 	unsigned int len;
 
-	bio = bio_kmalloc(1, GFP_NOWAIT | __GFP_NORETRY | __GFP_NOWARN);
+	bio = bio_kmalloc(1, GFP_NOWAIT);
 	if (!bio) {
 		use_dmio(b, op, sector, n_sectors, offset, ioprio);
 		return;
@@ -1601,18 +1601,18 @@ static struct dm_buffer *__alloc_buffer_wait_no_callback(struct dm_bufio_client
 	 * dm-bufio is resistant to allocation failures (it just keeps
 	 * one buffer reserved in cases all the allocations fail).
 	 * So set flags to not try too hard:
-	 *	GFP_NOWAIT: don't wait; if we need to sleep we'll release our
-	 *		    mutex and wait ourselves.
+	 *	GFP_NOWAIT: don't wait and don't print a warning in case of
+	 *		    failure; if we need to sleep we'll release our mutex
+	 *		    and wait ourselves.
 	 *	__GFP_NORETRY: don't retry and rather return failure
 	 *	__GFP_NOMEMALLOC: don't use emergency reserves
-	 *	__GFP_NOWARN: don't print a warning in case of failure
 	 *
 	 * For debugging, if we set the cache size to 1, no new buffers will
 	 * be allocated.
 	 */
 	while (1) {
 		if (dm_bufio_cache_size_latch != 1) {
-			b = alloc_buffer(c, GFP_NOWAIT | __GFP_NORETRY | __GFP_NOMEMALLOC | __GFP_NOWARN);
+			b = alloc_buffer(c, GFP_NOWAIT | __GFP_NORETRY | __GFP_NOMEMALLOC);
 			if (b)
 				return b;
 		}

drivers/md/dm-cache-policy-smq.c

@@ -590,7 +590,7 @@ static int h_init(struct smq_hash_table *ht, struct entry_space *es, unsigned in
 	nr_buckets = roundup_pow_of_two(max(nr_entries / 4u, 16u));
 	ht->hash_bits = __ffs(nr_buckets);
 
-	ht->buckets = vmalloc(array_size(nr_buckets, sizeof(*ht->buckets)));
+	ht->buckets = vmalloc_array(nr_buckets, sizeof(*ht->buckets));
 	if (!ht->buckets)
 		return -ENOMEM;
 

drivers/md/dm-core.h

@@ -162,6 +162,7 @@ struct mapped_device {
 #define DMF_SUSPENDED_INTERNALLY 7
 #define DMF_POST_SUSPENDING 8
 #define DMF_EMULATE_ZONE_APPEND 9
+#define DMF_QUEUE_STOPPED 10
 
 static inline sector_t dm_get_size(struct mapped_device *md)
 {
@@ -291,6 +292,7 @@ struct dm_io {
 	struct dm_io *next;
 	struct dm_stats_aux stats_aux;
 	blk_status_t status;
+	bool requeue_flush_with_data;
 	atomic_t io_count;
 	struct mapped_device *md;