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

Author: torvalds

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

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;

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;