Merge tag 'for-6.14/io_uring-20250119' of git://git.kernel.dk/linux

Pull io_uring updates from Jens Axboe:
 "Not a lot in terms of features this time around, mostly just cleanups
  and code consolidation:

   - Support for PI meta data read/write via io_uring, with NVMe and
     SCSI covered

   - Cleanup the per-op structure caching, making it consistent across
     various command types

   - Consolidate the various user mapped features into a concept called
     regions, making the various users of that consistent

   - Various cleanups and fixes"

* tag 'for-6.14/io_uring-20250119' of git://git.kernel.dk/linux: (56 commits)
  io_uring/fdinfo: fix io_uring_show_fdinfo() misuse of ->d_iname
  io_uring: reuse io_should_terminate_tw() for cmds
  io_uring: Factor out a function to parse restrictions
  io_uring/rsrc: require cloned buffers to share accounting contexts
  io_uring: simplify the SQPOLL thread check when cancelling requests
  io_uring: expose read/write attribute capability
  io_uring/rw: don't gate retry on completion context
  io_uring/rw: handle -EAGAIN retry at IO completion time
  io_uring/rw: use io_rw_recycle() from cleanup path
  io_uring/rsrc: simplify the bvec iter count calculation
  io_uring: ensure io_queue_deferred() is out-of-line
  io_uring/rw: always clear ->bytes_done on io_async_rw setup
  io_uring/rw: use NULL for rw->free_iovec assigment
  io_uring/rw: don't mask in f_iocb_flags
  io_uring/msg_ring: Drop custom destructor
  io_uring: Move old async data allocation helper to header
  io_uring/rw: Allocate async data through helper
  io_uring/net: Allocate msghdr async data through helper
  io_uring/uring_cmd: Allocate async data through generic helper
  io_uring/poll: Allocate apoll with generic alloc_cache helper
  ...

Author: torvalds

block/bio-integrity.c

@@ -118,17 +118,18 @@ static void bio_integrity_unpin_bvec(struct bio_vec *bv, int nr_vecs,
 
 static void bio_integrity_uncopy_user(struct bio_integrity_payload *bip)
 {
-	unsigned short nr_vecs = bip->bip_max_vcnt - 1;
-	struct bio_vec *copy = &bip->bip_vec[1];
-	size_t bytes = bip->bip_iter.bi_size;
-	struct iov_iter iter;
+	unsigned short orig_nr_vecs = bip->bip_max_vcnt - 1;
+	struct bio_vec *orig_bvecs = &bip->bip_vec[1];
+	struct bio_vec *bounce_bvec = &bip->bip_vec[0];
+	size_t bytes = bounce_bvec->bv_len;
+	struct iov_iter orig_iter;
 	int ret;
 
-	iov_iter_bvec(&iter, ITER_DEST, copy, nr_vecs, bytes);
-	ret = copy_to_iter(bvec_virt(bip->bip_vec), bytes, &iter);
+	iov_iter_bvec(&orig_iter, ITER_DEST, orig_bvecs, orig_nr_vecs, bytes);
+	ret = copy_to_iter(bvec_virt(bounce_bvec), bytes, &orig_iter);
 	WARN_ON_ONCE(ret != bytes);
 
-	bio_integrity_unpin_bvec(copy, nr_vecs, true);
+	bio_integrity_unpin_bvec(orig_bvecs, orig_nr_vecs, true);
 }
 
 /**
@@ -301,16 +302,15 @@ static unsigned int bvec_from_pages(struct bio_vec *bvec, struct page **pages,
 	return nr_bvecs;
 }
 
-int bio_integrity_map_user(struct bio *bio, void __user *ubuf, ssize_t bytes)
+int bio_integrity_map_user(struct bio *bio, struct iov_iter *iter)
 {
 	struct request_queue *q = bdev_get_queue(bio->bi_bdev);
 	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;
+	size_t offset, bytes = iter->count;
 	unsigned int direction, nr_bvecs;
-	struct iov_iter iter;
 	int ret, nr_vecs;
-	size_t offset;
 	bool copy;
 
 	if (bio_integrity(bio))
@@ -323,8 +323,7 @@ int bio_integrity_map_user(struct bio *bio, void __user *ubuf, ssize_t bytes)
 	else
 		direction = ITER_SOURCE;
 
-	iov_iter_ubuf(&iter, direction, ubuf, bytes);
-	nr_vecs = iov_iter_npages(&iter, BIO_MAX_VECS + 1);
+	nr_vecs = iov_iter_npages(iter, BIO_MAX_VECS + 1);
 	if (nr_vecs > BIO_MAX_VECS)
 		return -E2BIG;
 	if (nr_vecs > UIO_FASTIOV) {
@@ -334,8 +333,8 @@ int bio_integrity_map_user(struct bio *bio, void __user *ubuf, ssize_t bytes)
 		pages = NULL;
 	}
 
-	copy = !iov_iter_is_aligned(&iter, align, align);
-	ret = iov_iter_extract_pages(&iter, &pages, bytes, nr_vecs, 0, &offset);
+	copy = !iov_iter_is_aligned(iter, align, align);
+	ret = iov_iter_extract_pages(iter, &pages, bytes, nr_vecs, 0, &offset);
 	if (unlikely(ret < 0))
 		goto free_bvec;
 
@@ -365,6 +364,55 @@ int bio_integrity_map_user(struct bio *bio, void __user *ubuf, ssize_t bytes)
 	return ret;
 }
 
+static void bio_uio_meta_to_bip(struct bio *bio, struct uio_meta *meta)
+{
+	struct bio_integrity_payload *bip = bio_integrity(bio);
+
+	if (meta->flags & IO_INTEGRITY_CHK_GUARD)
+		bip->bip_flags |= BIP_CHECK_GUARD;
+	if (meta->flags & IO_INTEGRITY_CHK_APPTAG)
+		bip->bip_flags |= BIP_CHECK_APPTAG;
+	if (meta->flags & IO_INTEGRITY_CHK_REFTAG)
+		bip->bip_flags |= BIP_CHECK_REFTAG;
+
+	bip->app_tag = meta->app_tag;
+}
+
+int bio_integrity_map_iter(struct bio *bio, struct uio_meta *meta)
+{
+	struct blk_integrity *bi = blk_get_integrity(bio->bi_bdev->bd_disk);
+	unsigned int integrity_bytes;
+	int ret;
+	struct iov_iter it;
+
+	if (!bi)
+		return -EINVAL;
+	/*
+	 * original meta iterator can be bigger.
+	 * process integrity info corresponding to current data buffer only.
+	 */
+	it = meta->iter;
+	integrity_bytes = bio_integrity_bytes(bi, bio_sectors(bio));
+	if (it.count < integrity_bytes)
+		return -EINVAL;
+
+	/* should fit into two bytes */
+	BUILD_BUG_ON(IO_INTEGRITY_VALID_FLAGS >= (1 << 16));
+
+	if (meta->flags && (meta->flags & ~IO_INTEGRITY_VALID_FLAGS))
+		return -EINVAL;
+
+	it.count = integrity_bytes;
+	ret = bio_integrity_map_user(bio, &it);
+	if (!ret) {
+		bio_uio_meta_to_bip(bio, meta);
+		bip_set_seed(bio_integrity(bio), meta->seed);
+		iov_iter_advance(&meta->iter, integrity_bytes);
+		meta->seed += bio_integrity_intervals(bi, bio_sectors(bio));
+	}
+	return ret;
+}
+
 /**
  * bio_integrity_prep - Prepare bio for integrity I/O
  * @bio:	bio to prepare
@@ -435,6 +483,11 @@ bool bio_integrity_prep(struct bio *bio)
 	if (bi->csum_type == BLK_INTEGRITY_CSUM_IP)
 		bip->bip_flags |= BIP_IP_CHECKSUM;
 
+	/* describe what tags to check in payload */
+	if (bi->csum_type)
+		bip->bip_flags |= BIP_CHECK_GUARD;
+	if (bi->flags & BLK_INTEGRITY_REF_TAG)
+		bip->bip_flags |= BIP_CHECK_REFTAG;
 	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");
@@ -559,7 +612,8 @@ int bio_integrity_clone(struct bio *bio, struct bio *bio_src,
 
 	bip->bip_vec = bip_src->bip_vec;
 	bip->bip_iter = bip_src->bip_iter;
-	bip->bip_flags = bip_src->bip_flags & ~BIP_BLOCK_INTEGRITY;
+	bip->bip_flags = bip_src->bip_flags & BIP_CLONE_FLAGS;
+	bip->app_tag = bip_src->app_tag;
 
 	return 0;
 }

block/blk-integrity.c

@@ -115,8 +115,16 @@ EXPORT_SYMBOL(blk_rq_map_integrity_sg);
 int blk_rq_integrity_map_user(struct request *rq, void __user *ubuf,
 			      ssize_t bytes)
 {
-	int ret = bio_integrity_map_user(rq->bio, ubuf, bytes);
+	int ret;
+	struct iov_iter iter;
+	unsigned int direction;
 
+	if (op_is_write(req_op(rq)))
+		direction = ITER_DEST;
+	else
+		direction = ITER_SOURCE;
+	iov_iter_ubuf(&iter, direction, ubuf, bytes);
+	ret = bio_integrity_map_user(rq->bio, &iter);
 	if (ret)
 		return ret;
 

block/fops.c

@@ -54,6 +54,7 @@ static ssize_t __blkdev_direct_IO_simple(struct kiocb *iocb,
 	struct bio bio;
 	ssize_t ret;
 
+	WARN_ON_ONCE(iocb->ki_flags & IOCB_HAS_METADATA);
 	if (nr_pages <= DIO_INLINE_BIO_VECS)
 		vecs = inline_vecs;
 	else {
@@ -124,12 +125,16 @@ static void blkdev_bio_end_io(struct bio *bio)
 {
 	struct blkdev_dio *dio = bio->bi_private;
 	bool should_dirty = dio->flags & DIO_SHOULD_DIRTY;
+	bool is_sync = dio->flags & DIO_IS_SYNC;
 
 	if (bio->bi_status && !dio->bio.bi_status)
 		dio->bio.bi_status = bio->bi_status;
 
+	if (!is_sync && (dio->iocb->ki_flags & IOCB_HAS_METADATA))
+		bio_integrity_unmap_user(bio);
+
 	if (atomic_dec_and_test(&dio->ref)) {
-		if (!(dio->flags & DIO_IS_SYNC)) {
+		if (!is_sync) {
 			struct kiocb *iocb = dio->iocb;
 			ssize_t ret;
 
@@ -221,14 +226,16 @@ static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 			 * a retry of this from blocking context.
 			 */
 			if (unlikely(iov_iter_count(iter))) {
-				bio_release_pages(bio, false);
-				bio_clear_flag(bio, BIO_REFFED);
-				bio_put(bio);
-				blk_finish_plug(&plug);
-				return -EAGAIN;
+				ret = -EAGAIN;
+				goto fail;
 			}
 			bio->bi_opf |= REQ_NOWAIT;
 		}
+		if (!is_sync && (iocb->ki_flags & IOCB_HAS_METADATA)) {
+			ret = bio_integrity_map_iter(bio, iocb->private);
+			if (unlikely(ret))
+				goto fail;
+		}
 
 		if (is_read) {
 			if (dio->flags & DIO_SHOULD_DIRTY)
@@ -269,6 +276,12 @@ static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 
 	bio_put(&dio->bio);
 	return ret;
+fail:
+	bio_release_pages(bio, false);
+	bio_clear_flag(bio, BIO_REFFED);
+	bio_put(bio);
+	blk_finish_plug(&plug);
+	return ret;
 }
 
 static void blkdev_bio_end_io_async(struct bio *bio)
@@ -286,6 +299,9 @@ static void blkdev_bio_end_io_async(struct bio *bio)
 		ret = blk_status_to_errno(bio->bi_status);
 	}
 
+	if (iocb->ki_flags & IOCB_HAS_METADATA)
+		bio_integrity_unmap_user(bio);
+
 	iocb->ki_complete(iocb, ret);
 
 	if (dio->flags & DIO_SHOULD_DIRTY) {
@@ -330,10 +346,8 @@ static ssize_t __blkdev_direct_IO_async(struct kiocb *iocb,
 		bio_iov_bvec_set(bio, iter);
 	} else {
 		ret = bio_iov_iter_get_pages(bio, iter);
-		if (unlikely(ret)) {
-			bio_put(bio);
-			return ret;
-		}
+		if (unlikely(ret))
+			goto out_bio_put;
 	}
 	dio->size = bio->bi_iter.bi_size;
 
@@ -346,6 +360,13 @@ static ssize_t __blkdev_direct_IO_async(struct kiocb *iocb,
 		task_io_account_write(bio->bi_iter.bi_size);
 	}
 
+	if (iocb->ki_flags & IOCB_HAS_METADATA) {
+		ret = bio_integrity_map_iter(bio, iocb->private);
+		WRITE_ONCE(iocb->private, NULL);
+		if (unlikely(ret))
+			goto out_bio_put;
+	}
+
 	if (iocb->ki_flags & IOCB_ATOMIC)
 		bio->bi_opf |= REQ_ATOMIC;
 
@@ -360,6 +381,10 @@ static ssize_t __blkdev_direct_IO_async(struct kiocb *iocb,
 		submit_bio(bio);
 	}
 	return -EIOCBQUEUED;
+
+out_bio_put:
+	bio_put(bio);
+	return ret;
 }
 
 static ssize_t blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter)

drivers/nvme/host/core.c

@@ -885,6 +885,12 @@ static blk_status_t nvme_setup_discard(struct nvme_ns *ns, struct request *req,
 	return BLK_STS_OK;
 }
 
+static void nvme_set_app_tag(struct request *req, struct nvme_command *cmnd)
+{
+	cmnd->rw.lbat = cpu_to_le16(bio_integrity(req->bio)->app_tag);
+	cmnd->rw.lbatm = cpu_to_le16(0xffff);
+}
+
 static void nvme_set_ref_tag(struct nvme_ns *ns, struct nvme_command *cmnd,
 			      struct request *req)
 {
@@ -1017,18 +1023,17 @@ static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns,
 			control |= NVME_RW_PRINFO_PRACT;
 		}
 
-		switch (ns->head->pi_type) {
-		case NVME_NS_DPS_PI_TYPE3:
+		if (bio_integrity_flagged(req->bio, BIP_CHECK_GUARD))
 			control |= NVME_RW_PRINFO_PRCHK_GUARD;
-			break;
-		case NVME_NS_DPS_PI_TYPE1:
-		case NVME_NS_DPS_PI_TYPE2:
-			control |= NVME_RW_PRINFO_PRCHK_GUARD |
-					NVME_RW_PRINFO_PRCHK_REF;
+		if (bio_integrity_flagged(req->bio, BIP_CHECK_REFTAG)) {
+			control |= NVME_RW_PRINFO_PRCHK_REF;
 			if (op == nvme_cmd_zone_append)
 				control |= NVME_RW_APPEND_PIREMAP;
 			nvme_set_ref_tag(ns, cmnd, req);
-			break;
+		}
+		if (bio_integrity_flagged(req->bio, BIP_CHECK_APPTAG)) {
+			control |= NVME_RW_PRINFO_PRCHK_APP;
+			nvme_set_app_tag(req, cmnd);
 		}
 	}
 

drivers/scsi/sd.c

@@ -809,14 +809,14 @@ static unsigned char sd_setup_protect_cmnd(struct scsi_cmnd *scmd,
 		if (bio_integrity_flagged(bio, BIP_IP_CHECKSUM))
 			scmd->prot_flags |= SCSI_PROT_IP_CHECKSUM;
 
-		if (bio_integrity_flagged(bio, BIP_CTRL_NOCHECK) == false)
+		if (bio_integrity_flagged(bio, BIP_CHECK_GUARD))
 			scmd->prot_flags |= SCSI_PROT_GUARD_CHECK;
 	}
 
 	if (dif != T10_PI_TYPE3_PROTECTION) {	/* DIX/DIF Type 0, 1, 2 */
 		scmd->prot_flags |= SCSI_PROT_REF_INCREMENT;
 
-		if (bio_integrity_flagged(bio, BIP_CTRL_NOCHECK) == false)
+		if (bio_integrity_flagged(bio, BIP_CHECK_REFTAG))
 			scmd->prot_flags |= SCSI_PROT_REF_CHECK;
 	}
 

include/linux/bio-integrity.h

@@ -7,10 +7,12 @@
 enum bip_flags {
 	BIP_BLOCK_INTEGRITY	= 1 << 0, /* block layer owns integrity data */
 	BIP_MAPPED_INTEGRITY	= 1 << 1, /* ref tag has been remapped */
-	BIP_CTRL_NOCHECK	= 1 << 2, /* disable HBA integrity checking */
-	BIP_DISK_NOCHECK	= 1 << 3, /* disable disk integrity checking */
-	BIP_IP_CHECKSUM		= 1 << 4, /* IP checksum */
-	BIP_COPY_USER		= 1 << 5, /* Kernel bounce buffer in use */
+	BIP_DISK_NOCHECK	= 1 << 2, /* disable disk integrity checking */
+	BIP_IP_CHECKSUM		= 1 << 3, /* IP checksum */
+	BIP_COPY_USER		= 1 << 4, /* Kernel bounce buffer in use */
+	BIP_CHECK_GUARD		= 1 << 5, /* guard check */
+	BIP_CHECK_REFTAG	= 1 << 6, /* reftag check */
+	BIP_CHECK_APPTAG	= 1 << 7, /* apptag check */
 };
 
 struct bio_integrity_payload {
@@ -21,6 +23,7 @@ struct bio_integrity_payload {
 	unsigned short		bip_vcnt;	/* # of integrity bio_vecs */
 	unsigned short		bip_max_vcnt;	/* integrity bio_vec slots */
 	unsigned short		bip_flags;	/* control flags */
+	u16			app_tag;	/* application tag value */
 
 	struct bvec_iter	bio_iter;	/* for rewinding parent bio */
 
@@ -30,6 +33,9 @@ struct bio_integrity_payload {
 	struct bio_vec		bip_inline_vecs[];/* embedded bvec array */
 };
 
+#define BIP_CLONE_FLAGS (BIP_MAPPED_INTEGRITY | BIP_IP_CHECKSUM | \
+			 BIP_CHECK_GUARD | BIP_CHECK_REFTAG | BIP_CHECK_APPTAG)
+
 #ifdef CONFIG_BLK_DEV_INTEGRITY
 
 #define bip_for_each_vec(bvl, bip, iter)				\
@@ -72,7 +78,8 @@ struct bio_integrity_payload *bio_integrity_alloc(struct bio *bio, gfp_t gfp,
 		unsigned int nr);
 int bio_integrity_add_page(struct bio *bio, struct page *page, unsigned int len,
 		unsigned int offset);
-int bio_integrity_map_user(struct bio *bio, void __user *ubuf, ssize_t len);
+int bio_integrity_map_user(struct bio *bio, struct iov_iter *iter);
+int bio_integrity_map_iter(struct bio *bio, struct uio_meta *meta);
 void bio_integrity_unmap_user(struct bio *bio);
 bool bio_integrity_prep(struct bio *bio);
 void bio_integrity_advance(struct bio *bio, unsigned int bytes_done);
@@ -98,8 +105,12 @@ static inline void bioset_integrity_free(struct bio_set *bs)
 {
 }
 
-static inline int bio_integrity_map_user(struct bio *bio, void __user *ubuf,
-					 ssize_t len)
+static inline int bio_integrity_map_user(struct bio *bio, struct iov_iter *iter)
+{
+	return -EINVAL;
+}
+
+static inline int bio_integrity_map_iter(struct bio *bio, struct uio_meta *meta)
 {
 	return -EINVAL;
 }

include/linux/fs.h

@@ -349,6 +349,7 @@ struct readahead_control;
 #define IOCB_DIO_CALLER_COMP	(1 << 22)
 /* kiocb is a read or write operation submitted by fs/aio.c. */
 #define IOCB_AIO_RW		(1 << 23)
+#define IOCB_HAS_METADATA	(1 << 24)
 
 /* for use in trace events */
 #define TRACE_IOCB_STRINGS \