Merge tag 'for-5.12/dm-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm

Pull device mapper updates from Mike Snitzer:

 - Fix DM integrity's HMAC support to provide enhanced security of
   internal_hash and journal_mac capabilities.

 - Various DM writecache fixes to address performance, fix table output
   to match what was provided at table creation, fix writing beyond end
   of device when shrinking underlying data device, and a couple other
   small cleanups.

 - Add DM crypt support for using trusted keys.

 - Fix deadlock when swapping to DM crypt device by throttling number of
   in-flight REQ_SWAP bios. Implemented in DM core so that other
   bio-based targets can opt-in by setting ti->limit_swap_bios.

 - Fix various inverted logic bugs in the .iterate_devices callout
   functions that are used to assess if specific feature or capability
   is supported across all devices being combined/stacked by DM.

 - Fix DM era target bugs that exposed users to lost writes or memory
   leaks.

 - Add DM core support for passing through inline crypto support of
   underlying devices. Includes block/keyslot-manager changes that
   enable extending this support to DM.

 - Various small fixes and cleanups (spelling fixes, front padding
   calculation cleanup, cleanup conditional zoned support in targets,
   etc).

* tag 'for-5.12/dm-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm: (31 commits)
  dm: fix deadlock when swapping to encrypted device
  dm: simplify target code conditional on CONFIG_BLK_DEV_ZONED
  dm: set DM_TARGET_PASSES_CRYPTO feature for some targets
  dm: support key eviction from keyslot managers of underlying devices
  dm: add support for passing through inline crypto support
  block/keyslot-manager: Introduce functions for device mapper support
  block/keyslot-manager: Introduce passthrough keyslot manager
  dm era: only resize metadata in preresume
  dm era: Use correct value size in equality function of writeset tree
  dm era: Fix bitset memory leaks
  dm era: Verify the data block size hasn't changed
  dm era: Reinitialize bitset cache before digesting a new writeset
  dm era: Update in-core bitset after committing the metadata
  dm era: Recover committed writeset after crash
  dm writecache: use bdev_nr_sectors() instead of open-coded equivalent
  dm writecache: fix writing beyond end of underlying device when shrinking
  dm table: remove needless request_queue NULL pointer checks
  dm table: fix zoned iterate_devices based device capability checks
  dm table: fix DAX iterate_devices based device capability checks
  dm table: fix iterate_devices based device capability checks
  ...

1 files changed, 51 insertions, 29 deletions

diff --git a/drivers/md/dm-writecache.c b/drivers/md/dm-writecache.c
index d5223a0e5cc5..844c4be11768 100644
--- a/drivers/md/dm-writecache.c
+++ b/drivers/md/dm-writecache.c
@@ -148,6 +148,7 @@ struct dm_writecache {
 	size_t metadata_sectors;
 	size_t n_blocks;
 	uint64_t seq_count;
+	sector_t data_device_sectors;
 	void *block_start;
 	struct wc_entry *entries;
 	unsigned block_size;
@@ -159,14 +160,22 @@ struct dm_writecache {
 	bool overwrote_committed:1;
 	bool memory_vmapped:1;
 
+	bool start_sector_set:1;
 	bool high_wm_percent_set:1;
 	bool low_wm_percent_set:1;
 	bool max_writeback_jobs_set:1;
 	bool autocommit_blocks_set:1;
 	bool autocommit_time_set:1;
+	bool max_age_set:1;
 	bool writeback_fua_set:1;
 	bool flush_on_suspend:1;
 	bool cleaner:1;
+	bool cleaner_set:1;
+
+	unsigned high_wm_percent_value;
+	unsigned low_wm_percent_value;
+	unsigned autocommit_time_value;
+	unsigned max_age_value;
 
 	unsigned writeback_all;
 	struct workqueue_struct *writeback_wq;
@@ -523,7 +532,7 @@ static void ssd_commit_superblock(struct dm_writecache *wc)
 
 	region.bdev = wc->ssd_dev->bdev;
 	region.sector = 0;
-	region.count = PAGE_SIZE;
+	region.count = PAGE_SIZE >> SECTOR_SHIFT;
 
 	if (unlikely(region.sector + region.count > wc->metadata_sectors))
 		region.count = wc->metadata_sectors - region.sector;
@@ -969,6 +978,8 @@ static void writecache_resume(struct dm_target *ti)
 
 	wc_lock(wc);
 
+	wc->data_device_sectors = bdev_nr_sectors(wc->dev->bdev);
+
 	if (WC_MODE_PMEM(wc)) {
 		persistent_memory_invalidate_cache(wc->memory_map, wc->memory_map_size);
 	} else {
@@ -1638,6 +1649,10 @@ static bool wc_add_block(struct writeback_struct *wb, struct wc_entry *e, gfp_t
 	void *address = memory_data(wc, e);
 
 	persistent_memory_flush_cache(address, block_size);
+
+	if (unlikely(bio_end_sector(&wb->bio) >= wc->data_device_sectors))
+		return true;
+
 	return bio_add_page(&wb->bio, persistent_memory_page(address),
 			    block_size, persistent_memory_page_offset(address)) != 0;
 }
@@ -1709,6 +1724,9 @@ static void __writecache_writeback_pmem(struct dm_writecache *wc, struct writeba
 		if (writecache_has_error(wc)) {
 			bio->bi_status = BLK_STS_IOERR;
 			bio_endio(bio);
+		} else if (unlikely(!bio_sectors(bio))) {
+			bio->bi_status = BLK_STS_OK;
+			bio_endio(bio);
 		} else {
 			submit_bio(bio);
 		}
@@ -1752,6 +1770,14 @@ static void __writecache_writeback_ssd(struct dm_writecache *wc, struct writebac
 			e = f;
 		}
 
+		if (unlikely(to.sector + to.count > wc->data_device_sectors)) {
+			if (to.sector >= wc->data_device_sectors) {
+				writecache_copy_endio(0, 0, c);
+				continue;
+			}
+			from.count = to.count = wc->data_device_sectors - to.sector;
+		}
+
 		dm_kcopyd_copy(wc->dm_kcopyd, &from, 1, &to, 0, writecache_copy_endio, c);
 
 		__writeback_throttle(wc, wbl);
@@ -2004,8 +2030,7 @@ static void writecache_dtr(struct dm_target *ti)
 	if (wc->ssd_dev)
 		dm_put_device(ti, wc->ssd_dev);
 
-	if (wc->entries)
-		vfree(wc->entries);
+	vfree(wc->entries);
 
 	if (wc->memory_map) {
 		if (WC_MODE_PMEM(wc))
@@ -2020,8 +2045,7 @@ static void writecache_dtr(struct dm_target *ti)
 	if (wc->dm_io)
 		dm_io_client_destroy(wc->dm_io);
 
-	if (wc->dirty_bitmap)
-		vfree(wc->dirty_bitmap);
+	vfree(wc->dirty_bitmap);
 
 	kfree(wc);
 }
@@ -2205,6 +2229,7 @@ static int writecache_ctr(struct dm_target *ti, unsigned argc, char **argv)
 			if (sscanf(string, "%llu%c", &start_sector, &dummy) != 1)
 				goto invalid_optional;
 			wc->start_sector = start_sector;
+			wc->start_sector_set = true;
 			if (wc->start_sector != start_sector ||
 			    wc->start_sector >= wc->memory_map_size >> SECTOR_SHIFT)
 				goto invalid_optional;
@@ -2214,6 +2239,7 @@ static int writecache_ctr(struct dm_target *ti, unsigned argc, char **argv)
 				goto invalid_optional;
 			if (high_wm_percent < 0 || high_wm_percent > 100)
 				goto invalid_optional;
+			wc->high_wm_percent_value = high_wm_percent;
 			wc->high_wm_percent_set = true;
 		} else if (!strcasecmp(string, "low_watermark") && opt_params >= 1) {
 			string = dm_shift_arg(&as), opt_params--;
@@ -2221,6 +2247,7 @@ static int writecache_ctr(struct dm_target *ti, unsigned argc, char **argv)
 				goto invalid_optional;
 			if (low_wm_percent < 0 || low_wm_percent > 100)
 				goto invalid_optional;
+			wc->low_wm_percent_value = low_wm_percent;
 			wc->low_wm_percent_set = true;
 		} else if (!strcasecmp(string, "writeback_jobs") && opt_params >= 1) {
 			string = dm_shift_arg(&as), opt_params--;
@@ -2240,6 +2267,7 @@ static int writecache_ctr(struct dm_target *ti, unsigned argc, char **argv)
 			if (autocommit_msecs > 3600000)
 				goto invalid_optional;
 			wc->autocommit_jiffies = msecs_to_jiffies(autocommit_msecs);
+			wc->autocommit_time_value = autocommit_msecs;
 			wc->autocommit_time_set = true;
 		} else if (!strcasecmp(string, "max_age") && opt_params >= 1) {
 			unsigned max_age_msecs;
@@ -2249,7 +2277,10 @@ static int writecache_ctr(struct dm_target *ti, unsigned argc, char **argv)
 			if (max_age_msecs > 86400000)
 				goto invalid_optional;
 			wc->max_age = msecs_to_jiffies(max_age_msecs);
+			wc->max_age_set = true;
+			wc->max_age_value = max_age_msecs;
 		} else if (!strcasecmp(string, "cleaner")) {
+			wc->cleaner_set = true;
 			wc->cleaner = true;
 		} else if (!strcasecmp(string, "fua")) {
 			if (WC_MODE_PMEM(wc)) {
@@ -2455,7 +2486,6 @@ static void writecache_status(struct dm_target *ti, status_type_t type,
 	struct dm_writecache *wc = ti->private;
 	unsigned extra_args;
 	unsigned sz = 0;
-	uint64_t x;
 
 	switch (type) {
 	case STATUSTYPE_INFO:
@@ -2467,11 +2497,11 @@ static void writecache_status(struct dm_target *ti, status_type_t type,
 		DMEMIT("%c %s %s %u ", WC_MODE_PMEM(wc) ? 'p' : 's',
 				wc->dev->name, wc->ssd_dev->name, wc->block_size);
 		extra_args = 0;
-		if (wc->start_sector)
+		if (wc->start_sector_set)
 			extra_args += 2;
-		if (wc->high_wm_percent_set && !wc->cleaner)
+		if (wc->high_wm_percent_set)
 			extra_args += 2;
-		if (wc->low_wm_percent_set && !wc->cleaner)
+		if (wc->low_wm_percent_set)
 			extra_args += 2;
 		if (wc->max_writeback_jobs_set)
 			extra_args += 2;
@@ -2479,37 +2509,29 @@ static void writecache_status(struct dm_target *ti, status_type_t type,
 			extra_args += 2;
 		if (wc->autocommit_time_set)
 			extra_args += 2;
-		if (wc->max_age != MAX_AGE_UNSPECIFIED)
+		if (wc->max_age_set)
 			extra_args += 2;
-		if (wc->cleaner)
+		if (wc->cleaner_set)
 			extra_args++;
 		if (wc->writeback_fua_set)
 			extra_args++;
 
 		DMEMIT("%u", extra_args);
-		if (wc->start_sector)
+		if (wc->start_sector_set)
 			DMEMIT(" start_sector %llu", (unsigned long long)wc->start_sector);
-		if (wc->high_wm_percent_set && !wc->cleaner) {
-			x = (uint64_t)wc->freelist_high_watermark * 100;
-			x += wc->n_blocks / 2;
-			do_div(x, (size_t)wc->n_blocks);
-			DMEMIT(" high_watermark %u", 100 - (unsigned)x);
-		}
-		if (wc->low_wm_percent_set && !wc->cleaner) {
-			x = (uint64_t)wc->freelist_low_watermark * 100;
-			x += wc->n_blocks / 2;
-			do_div(x, (size_t)wc->n_blocks);
-			DMEMIT(" low_watermark %u", 100 - (unsigned)x);
-		}
+		if (wc->high_wm_percent_set)
+			DMEMIT(" high_watermark %u", wc->high_wm_percent_value);
+		if (wc->low_wm_percent_set)
+			DMEMIT(" low_watermark %u", wc->low_wm_percent_value);
 		if (wc->max_writeback_jobs_set)
 			DMEMIT(" writeback_jobs %u", wc->max_writeback_jobs);
 		if (wc->autocommit_blocks_set)
 			DMEMIT(" autocommit_blocks %u", wc->autocommit_blocks);
 		if (wc->autocommit_time_set)
-			DMEMIT(" autocommit_time %u", jiffies_to_msecs(wc->autocommit_jiffies));
-		if (wc->max_age != MAX_AGE_UNSPECIFIED)
-			DMEMIT(" max_age %u", jiffies_to_msecs(wc->max_age));
-		if (wc->cleaner)
+			DMEMIT(" autocommit_time %u", wc->autocommit_time_value);
+		if (wc->max_age_set)
+			DMEMIT(" max_age %u", wc->max_age_value);
+		if (wc->cleaner_set)
 			DMEMIT(" cleaner");
 		if (wc->writeback_fua_set)
 			DMEMIT(" %sfua", wc->writeback_fua ? "" : "no");
@@ -2519,7 +2541,7 @@ static void writecache_status(struct dm_target *ti, status_type_t type,
 
 static struct target_type writecache_target = {
 	.name			= "writecache",
-	.version		= {1, 3, 0},
+	.version		= {1, 4, 0},
 	.module			= THIS_MODULE,
 	.ctr			= writecache_ctr,
 	.dtr			= writecache_dtr,