Merge tag 'for-5.11/dm-fixes-1' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm

Pull device mapper fixes from Mike Snitzer:

 - Fix DM-raid's raid1 discard limits so discards work.

 - Select missing Kconfig dependencies for DM integrity and zoned
   targets.

 - Four fixes for DM crypt target's support to optionally bypass kcryptd
   workqueues.

 - Fix DM snapshot merge supports missing data flushes before committing
   metadata.

 - Fix DM integrity data device flushing when external metadata is used.

 - Fix DM integrity's maximum number of supported constructor arguments
   that user can request when creating an integrity device.

 - Eliminate DM core ioctl logging noise when an ioctl is issued without
   required CAP_SYS_RAWIO permission.

* tag 'for-5.11/dm-fixes-1' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm:
  dm crypt: defer decryption to a tasklet if interrupts disabled
  dm integrity: fix the maximum number of arguments
  dm crypt: do not call bio_endio() from the dm-crypt tasklet
  dm integrity: fix flush with external metadata device
  dm: eliminate potential source of excessive kernel log noise
  dm snapshot: flush merged data before committing metadata
  dm crypt: use GFP_ATOMIC when allocating crypto requests from softirq
  dm crypt: do not wait for backlogged crypto request completion in softirq
  dm zoned: select CONFIG_CRC32
  dm integrity: select CRYPTO_SKCIPHER
  dm raid: fix discard limits for raid1

7 files changed, 238 insertions, 34 deletions

diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig
index b7e2d9666614..9e44c09f6410 100644
--- a/drivers/md/Kconfig
+++ b/drivers/md/Kconfig
@@ -605,6 +605,7 @@ config DM_INTEGRITY
 	select BLK_DEV_INTEGRITY
 	select DM_BUFIO
 	select CRYPTO
+	select CRYPTO_SKCIPHER
 	select ASYNC_XOR
 	help
 	  This device-mapper target emulates a block device that has
@@ -622,6 +623,7 @@ config DM_ZONED
 	tristate "Drive-managed zoned block device target support"
 	depends on BLK_DEV_DM
 	depends on BLK_DEV_ZONED
+	select CRC32
 	help
 	  This device-mapper target takes a host-managed or host-aware zoned
 	  block device and exposes most of its capacity as a regular block
diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c
index 9c1a86bde658..fce4cbf9529d 100644
--- a/drivers/md/dm-bufio.c
+++ b/drivers/md/dm-bufio.c
@@ -1534,6 +1534,12 @@ sector_t dm_bufio_get_device_size(struct dm_bufio_client *c)
 }
 EXPORT_SYMBOL_GPL(dm_bufio_get_device_size);
 
+struct dm_io_client *dm_bufio_get_dm_io_client(struct dm_bufio_client *c)
+{
+	return c->dm_io;
+}
+EXPORT_SYMBOL_GPL(dm_bufio_get_dm_io_client);
+
 sector_t dm_bufio_get_block_number(struct dm_buffer *b)
 {
 	return b->block;
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index 53791138d78b..8c874710f0bc 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -1454,13 +1454,16 @@ static int crypt_convert_block_skcipher(struct crypt_config *cc,
 static void kcryptd_async_done(struct crypto_async_request *async_req,
 			       int error);
 
-static void crypt_alloc_req_skcipher(struct crypt_config *cc,
+static int crypt_alloc_req_skcipher(struct crypt_config *cc,
 				     struct convert_context *ctx)
 {
 	unsigned key_index = ctx->cc_sector & (cc->tfms_count - 1);
 
-	if (!ctx->r.req)
-		ctx->r.req = mempool_alloc(&cc->req_pool, GFP_NOIO);
+	if (!ctx->r.req) {
+		ctx->r.req = mempool_alloc(&cc->req_pool, in_interrupt() ? GFP_ATOMIC : GFP_NOIO);
+		if (!ctx->r.req)
+			return -ENOMEM;
+	}
 
 	skcipher_request_set_tfm(ctx->r.req, cc->cipher_tfm.tfms[key_index]);
 
@@ -1471,13 +1474,18 @@ static void crypt_alloc_req_skcipher(struct crypt_config *cc,
 	skcipher_request_set_callback(ctx->r.req,
 	    CRYPTO_TFM_REQ_MAY_BACKLOG,
 	    kcryptd_async_done, dmreq_of_req(cc, ctx->r.req));
+
+	return 0;
 }
 
-static void crypt_alloc_req_aead(struct crypt_config *cc,
+static int crypt_alloc_req_aead(struct crypt_config *cc,
 				 struct convert_context *ctx)
 {
-	if (!ctx->r.req_aead)
-		ctx->r.req_aead = mempool_alloc(&cc->req_pool, GFP_NOIO);
+	if (!ctx->r.req) {
+		ctx->r.req = mempool_alloc(&cc->req_pool, in_interrupt() ? GFP_ATOMIC : GFP_NOIO);
+		if (!ctx->r.req)
+			return -ENOMEM;
+	}
 
 	aead_request_set_tfm(ctx->r.req_aead, cc->cipher_tfm.tfms_aead[0]);
 
@@ -1488,15 +1496,17 @@ static void crypt_alloc_req_aead(struct crypt_config *cc,
 	aead_request_set_callback(ctx->r.req_aead,
 	    CRYPTO_TFM_REQ_MAY_BACKLOG,
 	    kcryptd_async_done, dmreq_of_req(cc, ctx->r.req_aead));
+
+	return 0;
 }
 
-static void crypt_alloc_req(struct crypt_config *cc,
+static int crypt_alloc_req(struct crypt_config *cc,
 			    struct convert_context *ctx)
 {
 	if (crypt_integrity_aead(cc))
-		crypt_alloc_req_aead(cc, ctx);
+		return crypt_alloc_req_aead(cc, ctx);
 	else
-		crypt_alloc_req_skcipher(cc, ctx);
+		return crypt_alloc_req_skcipher(cc, ctx);
 }
 
 static void crypt_free_req_skcipher(struct crypt_config *cc,
@@ -1529,17 +1539,28 @@ static void crypt_free_req(struct crypt_config *cc, void *req, struct bio *base_
  * Encrypt / decrypt data from one bio to another one (can be the same one)
  */
 static blk_status_t crypt_convert(struct crypt_config *cc,
-			 struct convert_context *ctx, bool atomic)
+			 struct convert_context *ctx, bool atomic, bool reset_pending)
 {
 	unsigned int tag_offset = 0;
 	unsigned int sector_step = cc->sector_size >> SECTOR_SHIFT;
 	int r;
 
-	atomic_set(&ctx->cc_pending, 1);
+	/*
+	 * if reset_pending is set we are dealing with the bio for the first time,
+	 * else we're continuing to work on the previous bio, so don't mess with
+	 * the cc_pending counter
+	 */
+	if (reset_pending)
+		atomic_set(&ctx->cc_pending, 1);
 
 	while (ctx->iter_in.bi_size && ctx->iter_out.bi_size) {
 
-		crypt_alloc_req(cc, ctx);
+		r = crypt_alloc_req(cc, ctx);
+		if (r) {
+			complete(&ctx->restart);
+			return BLK_STS_DEV_RESOURCE;
+		}
+
 		atomic_inc(&ctx->cc_pending);
 
 		if (crypt_integrity_aead(cc))
@@ -1553,7 +1574,25 @@ static blk_status_t crypt_convert(struct crypt_config *cc,
 		 * but the driver request queue is full, let's wait.
 		 */
 		case -EBUSY:
-			wait_for_completion(&ctx->restart);
+			if (in_interrupt()) {
+				if (try_wait_for_completion(&ctx->restart)) {
+					/*
+					 * we don't have to block to wait for completion,
+					 * so proceed
+					 */
+				} else {
+					/*
+					 * we can't wait for completion without blocking
+					 * exit and continue processing in a workqueue
+					 */
+					ctx->r.req = NULL;
+					ctx->cc_sector += sector_step;
+					tag_offset++;
+					return BLK_STS_DEV_RESOURCE;
+				}
+			} else {
+				wait_for_completion(&ctx->restart);
+			}
 			reinit_completion(&ctx->restart);
 			fallthrough;
 		/*
@@ -1691,6 +1730,12 @@ static void crypt_inc_pending(struct dm_crypt_io *io)
 	atomic_inc(&io->io_pending);
 }
 
+static void kcryptd_io_bio_endio(struct work_struct *work)
+{
+	struct dm_crypt_io *io = container_of(work, struct dm_crypt_io, work);
+	bio_endio(io->base_bio);
+}
+
 /*
  * One of the bios was finished. Check for completion of
  * the whole request and correctly clean up the buffer.
@@ -1713,7 +1758,23 @@ static void crypt_dec_pending(struct dm_crypt_io *io)
 		kfree(io->integrity_metadata);
 
 	base_bio->bi_status = error;
-	bio_endio(base_bio);
+
+	/*
+	 * If we are running this function from our tasklet,
+	 * we can't call bio_endio() here, because it will call
+	 * clone_endio() from dm.c, which in turn will
+	 * free the current struct dm_crypt_io structure with
+	 * our tasklet. In this case we need to delay bio_endio()
+	 * execution to after the tasklet is done and dequeued.
+	 */
+	if (tasklet_trylock(&io->tasklet)) {
+		tasklet_unlock(&io->tasklet);
+		bio_endio(base_bio);
+		return;
+	}
+
+	INIT_WORK(&io->work, kcryptd_io_bio_endio);
+	queue_work(cc->io_queue, &io->work);
 }
 
 /*
@@ -1945,6 +2006,37 @@ static bool kcryptd_crypt_write_inline(struct crypt_config *cc,
 	}
 }
 
+static void kcryptd_crypt_write_continue(struct work_struct *work)
+{
+	struct dm_crypt_io *io = container_of(work, struct dm_crypt_io, work);
+	struct crypt_config *cc = io->cc;
+	struct convert_context *ctx = &io->ctx;
+	int crypt_finished;
+	sector_t sector = io->sector;
+	blk_status_t r;
+
+	wait_for_completion(&ctx->restart);
+	reinit_completion(&ctx->restart);
+
+	r = crypt_convert(cc, &io->ctx, true, false);
+	if (r)
+		io->error = r;
+	crypt_finished = atomic_dec_and_test(&ctx->cc_pending);
+	if (!crypt_finished && kcryptd_crypt_write_inline(cc, ctx)) {
+		/* Wait for completion signaled by kcryptd_async_done() */
+		wait_for_completion(&ctx->restart);
+		crypt_finished = 1;
+	}
+
+	/* Encryption was already finished, submit io now */
+	if (crypt_finished) {
+		kcryptd_crypt_write_io_submit(io, 0);
+		io->sector = sector;
+	}
+
+	crypt_dec_pending(io);
+}
+
 static void kcryptd_crypt_write_convert(struct dm_crypt_io *io)
 {
 	struct crypt_config *cc = io->cc;
@@ -1973,7 +2065,17 @@ static void kcryptd_crypt_write_convert(struct dm_crypt_io *io)
 
 	crypt_inc_pending(io);
 	r = crypt_convert(cc, ctx,
-			  test_bit(DM_CRYPT_NO_WRITE_WORKQUEUE, &cc->flags));
+			  test_bit(DM_CRYPT_NO_WRITE_WORKQUEUE, &cc->flags), true);
+	/*
+	 * Crypto API backlogged the request, because its queue was full
+	 * and we're in softirq context, so continue from a workqueue
+	 * (TODO: is it actually possible to be in softirq in the write path?)
+	 */
+	if (r == BLK_STS_DEV_RESOURCE) {
+		INIT_WORK(&io->work, kcryptd_crypt_write_continue);
+		queue_work(cc->crypt_queue, &io->work);
+		return;
+	}
 	if (r)
 		io->error = r;
 	crypt_finished = atomic_dec_and_test(&ctx->cc_pending);
@@ -1998,6 +2100,25 @@ static void kcryptd_crypt_read_done(struct dm_crypt_io *io)
 	crypt_dec_pending(io);
 }
 
+static void kcryptd_crypt_read_continue(struct work_struct *work)
+{
+	struct dm_crypt_io *io = container_of(work, struct dm_crypt_io, work);
+	struct crypt_config *cc = io->cc;
+	blk_status_t r;
+
+	wait_for_completion(&io->ctx.restart);
+	reinit_completion(&io->ctx.restart);
+
+	r = crypt_convert(cc, &io->ctx, true, false);
+	if (r)
+		io->error = r;
+
+	if (atomic_dec_and_test(&io->ctx.cc_pending))
+		kcryptd_crypt_read_done(io);
+
+	crypt_dec_pending(io);
+}
+
 static void kcryptd_crypt_read_convert(struct dm_crypt_io *io)
 {
 	struct crypt_config *cc = io->cc;
@@ -2009,7 +2130,16 @@ static void kcryptd_crypt_read_convert(struct dm_crypt_io *io)
 			   io->sector);
 
 	r = crypt_convert(cc, &io->ctx,
-			  test_bit(DM_CRYPT_NO_READ_WORKQUEUE, &cc->flags));
+			  test_bit(DM_CRYPT_NO_READ_WORKQUEUE, &cc->flags), true);
+	/*
+	 * Crypto API backlogged the request, because its queue was full
+	 * and we're in softirq context, so continue from a workqueue
+	 */
+	if (r == BLK_STS_DEV_RESOURCE) {
+		INIT_WORK(&io->work, kcryptd_crypt_read_continue);
+		queue_work(cc->crypt_queue, &io->work);
+		return;
+	}
 	if (r)
 		io->error = r;
 
@@ -2091,8 +2221,12 @@ static void kcryptd_queue_crypt(struct dm_crypt_io *io)
 
 	if ((bio_data_dir(io->base_bio) == READ && test_bit(DM_CRYPT_NO_READ_WORKQUEUE, &cc->flags)) ||
 	    (bio_data_dir(io->base_bio) == WRITE && test_bit(DM_CRYPT_NO_WRITE_WORKQUEUE, &cc->flags))) {
-		if (in_irq()) {
-			/* Crypto API's "skcipher_walk_first() refuses to work in hard IRQ context */
+		/*
+		 * in_irq(): Crypto API's skcipher_walk_first() refuses to work in hard IRQ context.
+		 * irqs_disabled(): the kernel may run some IO completion from the idle thread, but
+		 * it is being executed with irqs disabled.
+		 */
+		if (in_irq() || irqs_disabled()) {
 			tasklet_init(&io->tasklet, kcryptd_crypt_tasklet, (unsigned long)&io->work);
 			tasklet_schedule(&io->tasklet);
 			return;
diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c
index 5a7a1b90e671..81df019ab284 100644
--- a/drivers/md/dm-integrity.c
+++ b/drivers/md/dm-integrity.c
@@ -1379,12 +1379,52 @@ thorough_test:
 #undef MAY_BE_HASH
 }
 
-static void dm_integrity_flush_buffers(struct dm_integrity_c *ic)
+struct flush_request {
+	struct dm_io_request io_req;
+	struct dm_io_region io_reg;
+	struct dm_integrity_c *ic;
+	struct completion comp;
+};
+
+static void flush_notify(unsigned long error, void *fr_)
+{
+	struct flush_request *fr = fr_;
+	if (unlikely(error != 0))
+		dm_integrity_io_error(fr->ic, "flusing disk cache", -EIO);
+	complete(&fr->comp);
+}
+
+static void dm_integrity_flush_buffers(struct dm_integrity_c *ic, bool flush_data)
 {
 	int r;
+
+	struct flush_request fr;
+
+	if (!ic->meta_dev)
+		flush_data = false;
+	if (flush_data) {
+		fr.io_req.bi_op = REQ_OP_WRITE,
+		fr.io_req.bi_op_flags = REQ_PREFLUSH | REQ_SYNC,
+		fr.io_req.mem.type = DM_IO_KMEM,
+		fr.io_req.mem.ptr.addr = NULL,
+		fr.io_req.notify.fn = flush_notify,
+		fr.io_req.notify.context = &fr;
+		fr.io_req.client = dm_bufio_get_dm_io_client(ic->bufio),
+		fr.io_reg.bdev = ic->dev->bdev,
+		fr.io_reg.sector = 0,
+		fr.io_reg.count = 0,
+		fr.ic = ic;
+		init_completion(&fr.comp);
+		r = dm_io(&fr.io_req, 1, &fr.io_reg, NULL);
+		BUG_ON(r);
+	}
+
 	r = dm_bufio_write_dirty_buffers(ic->bufio);
 	if (unlikely(r))
 		dm_integrity_io_error(ic, "writing tags", r);
+
+	if (flush_data)
+		wait_for_completion(&fr.comp);
 }
 
 static void sleep_on_endio_wait(struct dm_integrity_c *ic)
@@ -2110,7 +2150,7 @@ offload_to_thread:
 
 	if (unlikely(dio->op == REQ_OP_DISCARD) && likely(ic->mode != 'D')) {
 		integrity_metadata(&dio->work);
-		dm_integrity_flush_buffers(ic);
+		dm_integrity_flush_buffers(ic, false);
 
 		dio->in_flight = (atomic_t)ATOMIC_INIT(1);
 		dio->completion = NULL;
@@ -2195,7 +2235,7 @@ static void integrity_commit(struct work_struct *w)
 	flushes = bio_list_get(&ic->flush_bio_list);
 	if (unlikely(ic->mode != 'J')) {
 		spin_unlock_irq(&ic->endio_wait.lock);
-		dm_integrity_flush_buffers(ic);
+		dm_integrity_flush_buffers(ic, true);
 		goto release_flush_bios;
 	}
 
@@ -2409,7 +2449,7 @@ skip_io:
 	complete_journal_op(&comp);
 	wait_for_completion_io(&comp.comp);
 
-	dm_integrity_flush_buffers(ic);
+	dm_integrity_flush_buffers(ic, true);
 }
 
 static void integrity_writer(struct work_struct *w)
@@ -2451,7 +2491,7 @@ static void recalc_write_super(struct dm_integrity_c *ic)
 {
 	int r;
 
-	dm_integrity_flush_buffers(ic);
+	dm_integrity_flush_buffers(ic, false);
 	if (dm_integrity_failed(ic))
 		return;
 
@@ -2654,7 +2694,7 @@ static void bitmap_flush_work(struct work_struct *work)
 	unsigned long limit;
 	struct bio *bio;
 
-	dm_integrity_flush_buffers(ic);
+	dm_integrity_flush_buffers(ic, false);
 
 	range.logical_sector = 0;
 	range.n_sectors = ic->provided_data_sectors;
@@ -2663,9 +2703,7 @@ static void bitmap_flush_work(struct work_struct *work)
 	add_new_range_and_wait(ic, &range);
 	spin_unlock_irq(&ic->endio_wait.lock);
 
-	dm_integrity_flush_buffers(ic);
-	if (ic->meta_dev)
-		blkdev_issue_flush(ic->dev->bdev, GFP_NOIO);
+	dm_integrity_flush_buffers(ic, true);
 
 	limit = ic->provided_data_sectors;
 	if (ic->sb->flags & cpu_to_le32(SB_FLAG_RECALCULATING)) {
@@ -2934,11 +2972,11 @@ static void dm_integrity_postsuspend(struct dm_target *ti)
 		if (ic->meta_dev)
 			queue_work(ic->writer_wq, &ic->writer_work);
 		drain_workqueue(ic->writer_wq);
-		dm_integrity_flush_buffers(ic);
+		dm_integrity_flush_buffers(ic, true);
 	}
 
 	if (ic->mode == 'B') {
-		dm_integrity_flush_buffers(ic);
+		dm_integrity_flush_buffers(ic, true);
 #if 1
 		/* set to 0 to test bitmap replay code */
 		init_journal(ic, 0, ic->journal_sections, 0);
@@ -3754,7 +3792,7 @@ static int dm_integrity_ctr(struct dm_target *ti, unsigned argc, char **argv)
 	unsigned extra_args;
 	struct dm_arg_set as;
 	static const struct dm_arg _args[] = {
-		{0, 9, "Invalid number of feature args"},
+		{0, 15, "Invalid number of feature args"},
 	};
 	unsigned journal_sectors, interleave_sectors, buffer_sectors, journal_watermark, sync_msec;
 	bool should_write_sb;
diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index 23c38777e8f6..cab12b2251ba 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -3729,10 +3729,10 @@ static void raid_io_hints(struct dm_target *ti, struct queue_limits *limits)
 	blk_limits_io_opt(limits, chunk_size_bytes * mddev_data_stripes(rs));
 
 	/*
-	 * RAID1 and RAID10 personalities require bio splitting,
-	 * RAID0/4/5/6 don't and process large discard bios properly.
+	 * RAID0 and RAID10 personalities require bio splitting,
+	 * RAID1/4/5/6 don't and process large discard bios properly.
 	 */
-	if (rs_is_raid1(rs) || rs_is_raid10(rs)) {
+	if (rs_is_raid0(rs) || rs_is_raid10(rs)) {
 		limits->discard_granularity = chunk_size_bytes;
 		limits->max_discard_sectors = rs->md.chunk_sectors;
 	}
diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c
index 4668b2cd98f4..11890db71f3f 100644
--- a/drivers/md/dm-snap.c
+++ b/drivers/md/dm-snap.c
@@ -141,6 +141,11 @@ struct dm_snapshot {
 	 * for them to be committed.
 	 */
 	struct bio_list bios_queued_during_merge;
+
+	/*
+	 * Flush data after merge.
+	 */
+	struct bio flush_bio;
 };
 
 /*
@@ -1121,6 +1126,17 @@ shut:
 
 static void error_bios(struct bio *bio);
 
+static int flush_data(struct dm_snapshot *s)
+{
+	struct bio *flush_bio = &s->flush_bio;
+
+	bio_reset(flush_bio);
+	bio_set_dev(flush_bio, s->origin->bdev);
+	flush_bio->bi_opf = REQ_OP_WRITE | REQ_PREFLUSH;
+
+	return submit_bio_wait(flush_bio);
+}
+
 static void merge_callback(int read_err, unsigned long write_err, void *context)
 {
 	struct dm_snapshot *s = context;
@@ -1134,6 +1150,11 @@ static void merge_callback(int read_err, unsigned long write_err, void *context)
 		goto shut;
 	}
 
+	if (flush_data(s) < 0) {
+		DMERR("Flush after merge failed: shutting down merge");
+		goto shut;
+	}
+
 	if (s->store->type->commit_merge(s->store,
 					 s->num_merging_chunks) < 0) {
 		DMERR("Write error in exception store: shutting down merge");
@@ -1318,6 +1339,7 @@ static int snapshot_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	s->first_merging_chunk = 0;
 	s->num_merging_chunks = 0;
 	bio_list_init(&s->bios_queued_during_merge);
+	bio_init(&s->flush_bio, NULL, 0);
 
 	/* Allocate hash table for COW data */
 	if (init_hash_tables(s)) {
@@ -1504,6 +1526,8 @@ static void snapshot_dtr(struct dm_target *ti)
 
 	dm_exception_store_destroy(s->store);
 
+	bio_uninit(&s->flush_bio);
+
 	dm_put_device(ti, s->cow);
 
 	dm_put_device(ti, s->origin);
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index b3c3c8b4cb42..7bac564f3faa 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -562,7 +562,7 @@ static int dm_blk_ioctl(struct block_device *bdev, fmode_t mode,
 		 * subset of the parent bdev; require extra privileges.
 		 */
 		if (!capable(CAP_SYS_RAWIO)) {
-			DMWARN_LIMIT(
+			DMDEBUG_LIMIT(
 	"%s: sending ioctl %x to DM device without required privilege.",
 				current->comm, cmd);
 			r = -ENOIOCTLCMD;