Merge tag 'for-4.18/dm-changes-v2' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm

Pull device mapper updates from Mike Snitzer:

 - Adjust various DM structure members to improve alignment relative to
   4.18 block's mempool_t and bioset changes.

 - Add DM writecache target that offers writeback caching to persistent
   memory or SSD.

 - Small DM core error message change to give context for why a DM table
   type transition wasn't allowed.

* tag 'for-4.18/dm-changes-v2' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm:
  dm: add writecache target
  dm: adjust structure members to improve alignment
  dm: report which conflicting type caused error during table_load()

14 files changed, 2466 insertions, 74 deletions

diff --git a/Documentation/device-mapper/writecache.txt b/Documentation/device-mapper/writecache.txt
new file mode 100644
index 000000000000..4424fa2c67d7
--- /dev/null
+++ b/Documentation/device-mapper/writecache.txt
@@ -0,0 +1,68 @@
+The writecache target caches writes on persistent memory or on SSD. It
+doesn't cache reads because reads are supposed to be cached in page cache
+in normal RAM.
+
+When the device is constructed, the first sector should be zeroed or the
+first sector should contain valid superblock from previous invocation.
+
+Constructor parameters:
+1. type of the cache device - "p" or "s"
+        p - persistent memory
+        s - SSD
+2. the underlying device that will be cached
+3. the cache device
+4. block size (4096 is recommended; the maximum block size is the page
+   size)
+5. the number of optional parameters (the parameters with an argument
+   count as two)
+        high_watermark n        (default: 50)
+                start writeback when the number of used blocks reach this
+                watermark
+        low_watermark x         (default: 45)
+                stop writeback when the number of used blocks drops below
+                this watermark
+        writeback_jobs n        (default: unlimited)
+                limit the number of blocks that are in flight during
+                writeback. Setting this value reduces writeback
+                throughput, but it may improve latency of read requests
+        autocommit_blocks n     (default: 64 for pmem, 65536 for ssd)
+                when the application writes this amount of blocks without
+                issuing the FLUSH request, the blocks are automatically
+                commited
+        autocommit_time ms      (default: 1000)
+                autocommit time in milliseconds. The data is automatically
+                commited if this time passes and no FLUSH request is
+                received
+        fua                     (by default on)
+                applicable only to persistent memory - use the FUA flag
+                when writing data from persistent memory back to the
+                underlying device
+        nofua
+                applicable only to persistent memory - don't use the FUA
+                flag when writing back data and send the FLUSH request
+                afterwards
+                - some underlying devices perform better with fua, some
+                  with nofua. The user should test it
+
+Status:
+1. error indicator - 0 if there was no error, otherwise error number
+2. the number of blocks
+3. the number of free blocks
+4. the number of blocks under writeback
+
+Messages:
+        flush
+                flush the cache device. The message returns successfully
+                if the cache device was flushed without an error
+        flush_on_suspend
+                flush the cache device on next suspend. Use this message
+                when you are going to remove the cache device. The proper
+                sequence for removing the cache device is:
+                1. send the "flush_on_suspend" message
+                2. load an inactive table with a linear target that maps
+                   to the underlying device
+                3. suspend the device
+                4. ask for status and verify that there are no errors
+                5. resume the device, so that it will use the linear
+                   target
+                6. the cache device is now inactive and it can be deleted
diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig
index edff083f7c4e..8b8c123cae66 100644
--- a/drivers/md/Kconfig
+++ b/drivers/md/Kconfig
@@ -334,6 +334,17 @@ config DM_CACHE_SMQ
          of less memory utilization, improved performance and increased
          adaptability in the face of changing workloads.
 
+config DM_WRITECACHE
+        tristate "Writecache target"
+        depends on BLK_DEV_DM
+        ---help---
+           The writecache target caches writes on persistent memory or SSD.
+           It is intended for databases or other programs that need extremely
+           low commit latency.
+
+           The writecache target doesn't cache reads because reads are supposed
+           to be cached in standard RAM.
+
 config DM_ERA
        tristate "Era target (EXPERIMENTAL)"
        depends on BLK_DEV_DM
diff --git a/drivers/md/Makefile b/drivers/md/Makefile
index 63255f3ebd97..822f4e8753bc 100644
--- a/drivers/md/Makefile
+++ b/drivers/md/Makefile
@@ -67,6 +67,7 @@ obj-$(CONFIG_DM_ERA)		+= dm-era.o
 obj-$(CONFIG_DM_LOG_WRITES)     += dm-log-writes.o
 obj-$(CONFIG_DM_INTEGRITY)      += dm-integrity.o
 obj-$(CONFIG_DM_ZONED)          += dm-zoned.o
+obj-$(CONFIG_DM_WRITECACHE)     += dm-writecache.o
 
 ifeq ($(CONFIG_DM_UEVENT),y)
 dm-mod-objs                     += dm-uevent.o
diff --git a/drivers/md/dm-bio-prison-v1.c b/drivers/md/dm-bio-prison-v1.c
index e794e3662fdd..b5389890bbc3 100644
--- a/drivers/md/dm-bio-prison-v1.c
+++ b/drivers/md/dm-bio-prison-v1.c
@@ -19,8 +19,8 @@
 
 struct dm_bio_prison {
         spinlock_t lock;
-        mempool_t cell_pool;
         struct rb_root cells;
+        mempool_t cell_pool;
 };
 
 static struct kmem_cache *_cell_cache;
diff --git a/drivers/md/dm-bio-prison-v2.c b/drivers/md/dm-bio-prison-v2.c
index f866bc97b032..b092cdc8e1ae 100644
--- a/drivers/md/dm-bio-prison-v2.c
+++ b/drivers/md/dm-bio-prison-v2.c
@@ -21,8 +21,8 @@ struct dm_bio_prison_v2 {
         struct workqueue_struct *wq;
 
         spinlock_t lock;
-        mempool_t cell_pool;
         struct rb_root cells;
+        mempool_t cell_pool;
 };
 
 static struct kmem_cache *_cell_cache;
diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c
index 001c71248246..ce14a3d1f609 100644
--- a/drivers/md/dm-cache-target.c
+++ b/drivers/md/dm-cache-target.c
@@ -371,7 +371,13 @@ struct cache_stats {
 
 struct cache {
         struct dm_target *ti;
-        struct dm_target_callbacks callbacks;
+        spinlock_t lock;
+
+        /*
+         * Fields for converting from sectors to blocks.
+         */
+        int sectors_per_block_shift;
+        sector_t sectors_per_block;
 
         struct dm_cache_metadata *cmd;
 
@@ -402,13 +408,11 @@ struct cache {
         dm_cblock_t cache_size;
 
         /*
-         * Fields for converting from sectors to blocks.
+         * Invalidation fields.
          */
-        sector_t sectors_per_block;
-        int sectors_per_block_shift;
+        spinlock_t invalidation_lock;
+        struct list_head invalidation_requests;
 
-        spinlock_t lock;
-        struct bio_list deferred_bios;
         sector_t migration_threshold;
         wait_queue_head_t migration_wait;
         atomic_t nr_allocated_migrations;
@@ -419,13 +423,11 @@ struct cache {
          */
         atomic_t nr_io_migrations;
 
+        struct bio_list deferred_bios;