Merge tag 'for-6.11/block-20240710' of git://git.kernel.dk/linux

Pull block updates from Jens Axboe:

 - NVMe updates via Keith:
     - Device initialization memory leak fixes (Keith)
     - More constants defined (Weiwen)
     - Target debugfs support (Hannes)
     - PCIe subsystem reset enhancements (Keith)
     - Queue-depth multipath policy (Redhat and PureStorage)
     - Implement get_unique_id (Christoph)
     - Authentication error fixes (Gaosheng)

 - MD updates via Song
     - sync_action fix and refactoring (Yu Kuai)
     - Various small fixes (Christoph Hellwig, Li Nan, and Ofir Gal, Yu
       Kuai, Benjamin Marzinski, Christophe JAILLET, Yang Li)

 - Fix loop detach/open race (Gulam)

 - Fix lower control limit for blk-throttle (Yu)

 - Add module descriptions to various drivers (Jeff)

 - Add support for atomic writes for block devices, and statx reporting
   for same. Includes SCSI and NVMe (John, Prasad, Alan)

 - Add IO priority information to block trace points (Dongliang)

 - Various zone improvements and tweaks (Damien)

 - mq-deadline tag reservation improvements (Bart)

 - Ignore direct reclaim swap writes in writeback throttling (Baokun)

 - Block integrity improvements and fixes (Anuj)

 - Add basic support for rust based block drivers. Has a dummy null_blk
   variant for now (Andreas)

 - Series converting driver settings to queue limits, and cleanups and
   fixes related to that (Christoph)

 - Cleanup for poking too deeply into the bvec internals, in preparation
   for DMA mapping API changes (Christoph)

 - Various minor tweaks and fixes (Jiapeng, John, Kanchan, Mikulas,
   Ming, Zhu, Damien, Christophe, Chaitanya)

* tag 'for-6.11/block-20240710' of git://git.kernel.dk/linux: (206 commits)
  floppy: add missing MODULE_DESCRIPTION() macro
  loop: add missing MODULE_DESCRIPTION() macro
  ublk_drv: add missing MODULE_DESCRIPTION() macro
  xen/blkback: add missing MODULE_DESCRIPTION() macro
  block/rnbd: Constify struct kobj_type
  block: take offset into account in blk_bvec_map_sg again
  block: fix get_max_segment_size() warning
  loop: Don't bother validating blocksize
  virtio_blk: Don't bother validating blocksize
  null_blk: Don't bother validating blocksize
  block: Validate logical block size in blk_validate_limits()
  virtio_blk: Fix default logical block size fallback
  nvmet-auth: fix nvmet_auth hash error handling
  nvme: implement ->get_unique_id
  block: pass a phys_addr_t to get_max_segment_size
  block: add a bvec_phys helper
  blk-lib: check for kill signal in ioctl BLKZEROOUT
  block: limit the Write Zeroes to manually writing zeroes fallback
  block: refacto blkdev_issue_zeroout
  block: move read-only and supported checks into (__)blkdev_issue_zeroout
  ...

1 files changed, 37 insertions, 98 deletions

diff --git a/block/bio-integrity.c b/block/bio-integrity.c
index 8b528e12136f..b78c145eb026 100644
--- a/block/bio-integrity.c
+++ b/block/bio-integrity.c
@@ -76,7 +76,7 @@ struct bio_integrity_payload *bio_integrity_alloc(struct bio *bio,
 					  &bip->bip_max_vcnt, gfp_mask);
 		if (!bip->bip_vec)
 			goto err;
-	} else {
+	} else if (nr_vecs) {
 		bip->bip_vec = bip->bip_inline_vecs;
 	}
 
@@ -276,6 +276,7 @@ static int bio_integrity_copy_user(struct bio *bio, struct bio_vec *bvec,
 
 	bip->bip_flags |= BIP_INTEGRITY_USER | BIP_COPY_USER;
 	bip->bip_iter.bi_sector = seed;
+	bip->bip_vcnt = nr_vecs;
 	return 0;
 free_bip:
 	bio_integrity_free(bio);
@@ -297,6 +298,7 @@ static int bio_integrity_init_user(struct bio *bio, struct bio_vec *bvec,
 	bip->bip_flags |= BIP_INTEGRITY_USER;
 	bip->bip_iter.bi_sector = seed;
 	bip->bip_iter.bi_size = len;
+	bip->bip_vcnt = nr_vecs;
 	return 0;
 }
 
@@ -334,7 +336,7 @@ int bio_integrity_map_user(struct bio *bio, void __user *ubuf, ssize_t bytes,
 			   u32 seed)
 {
 	struct request_queue *q = bdev_get_queue(bio->bi_bdev);
-	unsigned int align = q->dma_pad_mask | queue_dma_alignment(q);
+	unsigned int align = blk_lim_dma_alignment_and_pad(&q->limits);
 	struct page *stack_pages[UIO_FASTIOV], **pages = stack_pages;
 	struct bio_vec stack_vec[UIO_FASTIOV], *bvec = stack_vec;
 	unsigned int direction, nr_bvecs;
@@ -397,44 +399,6 @@ free_bvec:
 EXPORT_SYMBOL_GPL(bio_integrity_map_user);
 
 /**
- * bio_integrity_process - Process integrity metadata for a bio
- * @bio:	bio to generate/verify integrity metadata for
- * @proc_iter:  iterator to process
- * @proc_fn:	Pointer to the relevant processing function
- */
-static blk_status_t bio_integrity_process(struct bio *bio,
-		struct bvec_iter *proc_iter, integrity_processing_fn *proc_fn)
-{
-	struct blk_integrity *bi = blk_get_integrity(bio->bi_bdev->bd_disk);
-	struct blk_integrity_iter iter;
-	struct bvec_iter bviter;
-	struct bio_vec bv;
-	struct bio_integrity_payload *bip = bio_integrity(bio);
-	blk_status_t ret = BLK_STS_OK;
-
-	iter.disk_name = bio->bi_bdev->bd_disk->disk_name;
-	iter.interval = 1 << bi->interval_exp;
-	iter.tuple_size = bi->tuple_size;
-	iter.seed = proc_iter->bi_sector;
-	iter.prot_buf = bvec_virt(bip->bip_vec);
-	iter.pi_offset = bi->pi_offset;
-
-	__bio_for_each_segment(bv, bio, bviter, *proc_iter) {
-		void *kaddr = bvec_kmap_local(&bv);
-
-		iter.data_buf = kaddr;
-		iter.data_size = bv.bv_len;
-		ret = proc_fn(&iter);
-		kunmap_local(kaddr);
-
-		if (ret)
-			break;
-
-	}
-	return ret;
-}
-
-/**
  * bio_integrity_prep - Prepare bio for integrity I/O
  * @bio:	bio to prepare
  *
@@ -450,17 +414,13 @@ bool bio_integrity_prep(struct bio *bio)
 {
 	struct bio_integrity_payload *bip;
 	struct blk_integrity *bi = blk_get_integrity(bio->bi_bdev->bd_disk);
+	unsigned int len;
 	void *buf;
-	unsigned long start, end;
-	unsigned int len, nr_pages;
-	unsigned int bytes, offset, i;
+	gfp_t gfp = GFP_NOIO;
 
 	if (!bi)
 		return true;
 
-	if (bio_op(bio) != REQ_OP_READ && bio_op(bio) != REQ_OP_WRITE)
-		return true;
-
 	if (!bio_sectors(bio))
 		return true;
 
@@ -468,32 +428,36 @@ bool bio_integrity_prep(struct bio *bio)
 	if (bio_integrity(bio))
 		return true;
 
-	if (bio_data_dir(bio) == READ) {
-		if (!bi->profile->verify_fn ||
-		    !(bi->flags & BLK_INTEGRITY_VERIFY))
+	switch (bio_op(bio)) {
+	case REQ_OP_READ:
+		if (bi->flags & BLK_INTEGRITY_NOVERIFY)
 			return true;
-	} else {
-		if (!bi->profile->generate_fn ||
-		    !(bi->flags & BLK_INTEGRITY_GENERATE))
+		break;
+	case REQ_OP_WRITE:
+		if (bi->flags & BLK_INTEGRITY_NOGENERATE)
 			return true;
+
+		/*
+		 * Zero the memory allocated to not leak uninitialized kernel
+		 * memory to disk for non-integrity metadata where nothing else
+		 * initializes the memory.
+		 */
+		if (bi->csum_type == BLK_INTEGRITY_CSUM_NONE)
+			gfp |= __GFP_ZERO;
+		break;
+	default:
+		return true;
 	}
 
 	/* Allocate kernel buffer for protection data */
 	len = bio_integrity_bytes(bi, bio_sectors(bio));
-	buf = kmalloc(len, GFP_NOIO);
+	buf = kmalloc(len, gfp);
 	if (unlikely(buf == NULL)) {
-		printk(KERN_ERR "could not allocate integrity buffer\n");
 		goto err_end_io;
 	}
 
-	end = (((unsigned long) buf) + len + PAGE_SIZE - 1) >> PAGE_SHIFT;
-	start = ((unsigned long) buf) >> PAGE_SHIFT;
-	nr_pages = end - start;
-
-	/* Allocate bio integrity payload and integrity vectors */
-	bip = bio_integrity_alloc(bio, GFP_NOIO, nr_pages);
+	bip = bio_integrity_alloc(bio, GFP_NOIO, 1);
 	if (IS_ERR(bip)) {
-		printk(KERN_ERR "could not allocate data integrity bioset\n");
 		kfree(buf);
 		goto err_end_io;
 	}
@@ -501,35 +465,20 @@ bool bio_integrity_prep(struct bio *bio)
 	bip->bip_flags |= BIP_BLOCK_INTEGRITY;
 	bip_set_seed(bip, bio->bi_iter.bi_sector);
 
-	if (bi->flags & BLK_INTEGRITY_IP_CHECKSUM)
+	if (bi->csum_type == BLK_INTEGRITY_CSUM_IP)
 		bip->bip_flags |= BIP_IP_CHECKSUM;
 
-	/* Map it */
-	offset = offset_in_page(buf);
-	for (i = 0; i < nr_pages && len > 0; i++) {
-		bytes = PAGE_SIZE - offset;
-
-		if (bytes > len)
-			bytes = len;
-
-		if (bio_integrity_add_page(bio, virt_to_page(buf),
-					   bytes, offset) < bytes) {
-			printk(KERN_ERR "could not attach integrity payload\n");
-			goto err_end_io;
-		}
-
-		buf += bytes;
-		len -= bytes;
-		offset = 0;
+	if (bio_integrity_add_page(bio, virt_to_page(buf), len,
+			offset_in_page(buf)) < len) {
+		printk(KERN_ERR "could not attach integrity payload\n");
+		goto err_end_io;
 	}
 
 	/* Auto-generate integrity metadata if this is a write */
-	if (bio_data_dir(bio) == WRITE) {
-		bio_integrity_process(bio, &bio->bi_iter,
-				      bi->profile->generate_fn);
-	} else {
+	if (bio_data_dir(bio) == WRITE)
+		blk_integrity_generate(bio);
+	else
 		bip->bio_iter = bio->bi_iter;
-	}
 	return true;
 
 err_end_io:
@@ -552,15 +501,8 @@ static void bio_integrity_verify_fn(struct work_struct *work)
 	struct bio_integrity_payload *bip =
 		container_of(work, struct bio_integrity_payload, bip_work);
 	struct bio *bio = bip->bip_bio;
-	struct blk_integrity *bi = blk_get_integrity(bio->bi_bdev->bd_disk);
 
-	/*
-	 * At the moment verify is called bio's iterator was advanced
-	 * during split and completion, we need to rewind iterator to
-	 * it's original position.
-	 */
-	bio->bi_status = bio_integrity_process(bio, &bip->bio_iter,
-						bi->profile->verify_fn);
+	blk_integrity_verify(bio);
 	bio_integrity_free(bio);
 	bio_endio(bio);
 }
@@ -582,7 +524,7 @@ bool __bio_integrity_endio(struct bio *bio)
 	struct bio_integrity_payload *bip = bio_integrity(bio);
 
 	if (bio_op(bio) == REQ_OP_READ && !bio->bi_status &&
-	    (bip->bip_flags & BIP_BLOCK_INTEGRITY) && bi->profile->verify_fn) {
+	    (bip->bip_flags & BIP_BLOCK_INTEGRITY) && bi->csum_type) {
 		INIT_WORK(&bip->bip_work, bio_integrity_verify_fn);
 		queue_work(kintegrityd_wq, &bip->bip_work);
 		return false;
@@ -642,14 +584,11 @@ int bio_integrity_clone(struct bio *bio, struct bio *bio_src,
 
 	BUG_ON(bip_src == NULL);
 
-	bip = bio_integrity_alloc(bio, gfp_mask, bip_src->bip_vcnt);
+	bip = bio_integrity_alloc(bio, gfp_mask, 0);
 	if (IS_ERR(bip))
 		return PTR_ERR(bip);
 
-	memcpy(bip->bip_vec, bip_src->bip_vec,
-	       bip_src->bip_vcnt * sizeof(struct bio_vec));
-
-	bip->bip_vcnt = bip_src->bip_vcnt;
+	bip->bip_vec = bip_src->bip_vec;
 	bip->bip_iter = bip_src->bip_iter;
 	bip->bip_flags = bip_src->bip_flags & ~BIP_BLOCK_INTEGRITY;