Merge branch 'block-6.15' of git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux-block into xfs-6.16-merge

Merging block tree into XFS because of some dependencies like
bdev_validate_blocksize()

Signed-off-by: Carlos Maiolino <cem@kernel.org>

12 files changed, 148 insertions, 52 deletions

diff --git a/block/bdev.c b/block/bdev.c
index 4844d1e27b6f..520515e4e64e 100644
--- a/block/bdev.c
+++ b/block/bdev.c
@@ -152,27 +152,65 @@ static void set_init_blocksize(struct block_device *bdev)
 				    get_order(bsize));
 }
 
-int set_blocksize(struct file *file, int size)
+/**
+ * bdev_validate_blocksize - check that this block size is acceptable
+ * @bdev:	blockdevice to check
+ * @block_size:	block size to check
+ *
+ * For block device users that do not use buffer heads or the block device
+ * page cache, make sure that this block size can be used with the device.
+ *
+ * Return: On success zero is returned, negative error code on failure.
+ */
+int bdev_validate_blocksize(struct block_device *bdev, int block_size)
 {
-	struct inode *inode = file->f_mapping->host;
-	struct block_device *bdev = I_BDEV(inode);
-
-	if (blk_validate_block_size(size))
+	if (blk_validate_block_size(block_size))
 		return -EINVAL;
 
 	/* Size cannot be smaller than the size supported by the device */
-	if (size < bdev_logical_block_size(bdev))
+	if (block_size < bdev_logical_block_size(bdev))
 		return -EINVAL;
 
+	return 0;
+}
+EXPORT_SYMBOL_GPL(bdev_validate_blocksize);
+
+int set_blocksize(struct file *file, int size)
+{
+	struct inode *inode = file->f_mapping->host;
+	struct block_device *bdev = I_BDEV(inode);
+	int ret;
+
+	ret = bdev_validate_blocksize(bdev, size);
+	if (ret)
+		return ret;
+
 	if (!file->private_data)
 		return -EINVAL;
 
 	/* Don't change the size if it is same as current */
 	if (inode->i_blkbits != blksize_bits(size)) {
+		/*
+		 * Flush and truncate the pagecache before we reconfigure the
+		 * mapping geometry because folio sizes are variable now.  If a
+		 * reader has already allocated a folio whose size is smaller
+		 * than the new min_order but invokes readahead after the new
+		 * min_order becomes visible, readahead will think there are
+		 * "zero" blocks per folio and crash.  Take the inode and
+		 * invalidation locks to avoid racing with
+		 * read/write/fallocate.
+		 */
+		inode_lock(inode);
+		filemap_invalidate_lock(inode->i_mapping);
+
 		sync_blockdev(bdev);
+		kill_bdev(bdev);
+
 		inode->i_blkbits = blksize_bits(size);
 		mapping_set_folio_min_order(inode->i_mapping, get_order(size));
 		kill_bdev(bdev);
+		filemap_invalidate_unlock(inode->i_mapping);
+		inode_unlock(inode);
 	}
 	return 0;
 }
@@ -777,13 +815,13 @@ static void blkdev_put_part(struct block_device *part)
 	blkdev_put_whole(whole);
 }
 
-struct block_device *blkdev_get_no_open(dev_t dev)
+struct block_device *blkdev_get_no_open(dev_t dev, bool autoload)
 {
 	struct block_device *bdev;
 	struct inode *inode;
 
 	inode = ilookup(blockdev_superblock, dev);
-	if (!inode && IS_ENABLED(CONFIG_BLOCK_LEGACY_AUTOLOAD)) {
+	if (!inode && autoload && IS_ENABLED(CONFIG_BLOCK_LEGACY_AUTOLOAD)) {
 		blk_request_module(dev);
 		inode = ilookup(blockdev_superblock, dev);
 		if (inode)
@@ -1005,7 +1043,7 @@ struct file *bdev_file_open_by_dev(dev_t dev, blk_mode_t mode, void *holder,
 	if (ret)
 		return ERR_PTR(ret);
 
-	bdev = blkdev_get_no_open(dev);
+	bdev = blkdev_get_no_open(dev, true);
 	if (!bdev)
 		return ERR_PTR(-ENXIO);
 
@@ -1275,18 +1313,15 @@ void sync_bdevs(bool wait)
 void bdev_statx(struct path *path, struct kstat *stat,
 		u32 request_mask)
 {
-	struct inode *backing_inode;
 	struct block_device *bdev;
 
-	backing_inode = d_backing_inode(path->dentry);
-
 	/*
-	 * Note that backing_inode is the inode of a block device node file,
-	 * not the block device's internal inode.  Therefore it is *not* valid
-	 * to use I_BDEV() here; the block device has to be looked up by i_rdev
+	 * Note that d_backing_inode() returns the block device node inode, not
+	 * the block device's internal inode.  Therefore it is *not* valid to
+	 * use I_BDEV() here; the block device has to be looked up by i_rdev
 	 * instead.
 	 */
-	bdev = blkdev_get_no_open(backing_inode->i_rdev);
+	bdev = blkdev_get_no_open(d_backing_inode(path->dentry)->i_rdev, false);
 	if (!bdev)
 		return;
 
diff --git a/block/bio-integrity-auto.c b/block/bio-integrity-auto.c
index e524c609be50..9c6657664792 100644
--- a/block/bio-integrity-auto.c
+++ b/block/bio-integrity-auto.c
@@ -9,6 +9,7 @@
  * not aware of PI.
  */
 #include <linux/blk-integrity.h>
+#include <linux/t10-pi.h>
 #include <linux/workqueue.h>
 #include "blk.h"
 
@@ -43,6 +44,29 @@ static void bio_integrity_verify_fn(struct work_struct *work)
 	bio_endio(bio);
 }
 
+#define BIP_CHECK_FLAGS (BIP_CHECK_GUARD | BIP_CHECK_REFTAG | BIP_CHECK_APPTAG)
+static bool bip_should_check(struct bio_integrity_payload *bip)
+{
+	return bip->bip_flags & BIP_CHECK_FLAGS;
+}
+
+static bool bi_offload_capable(struct blk_integrity *bi)
+{
+	switch (bi->csum_type) {
+	case BLK_INTEGRITY_CSUM_CRC64:
+		return bi->tuple_size == sizeof(struct crc64_pi_tuple);
+	case BLK_INTEGRITY_CSUM_CRC:
+	case BLK_INTEGRITY_CSUM_IP:
+		return bi->tuple_size == sizeof(struct t10_pi_tuple);
+	default:
+		pr_warn_once("%s: unknown integrity checksum type:%d\n",
+			__func__, bi->csum_type);
+		fallthrough;
+	case BLK_INTEGRITY_CSUM_NONE:
+		return false;
+	}
+}
+
 /**
  * __bio_integrity_endio - Integrity I/O completion function
  * @bio:	Protected bio
@@ -54,12 +78,12 @@ static void bio_integrity_verify_fn(struct work_struct *work)
  */
 bool __bio_integrity_endio(struct bio *bio)
 {
-	struct blk_integrity *bi = blk_get_integrity(bio->bi_bdev->bd_disk);
 	struct bio_integrity_payload *bip = bio_integrity(bio);
 	struct bio_integrity_data *bid =
 		container_of(bip, struct bio_integrity_data, bip);
 
-	if (bio_op(bio) == REQ_OP_READ && !bio->bi_status && bi->csum_type) {
+	if (bio_op(bio) == REQ_OP_READ && !bio->bi_status &&
+	    bip_should_check(bip)) {
 		INIT_WORK(&bid->work, bio_integrity_verify_fn);
 		queue_work(kintegrityd_wq, &bid->work);
 		return false;
@@ -84,6 +108,7 @@ bool bio_integrity_prep(struct bio *bio)
 {
 	struct blk_integrity *bi = blk_get_integrity(bio->bi_bdev->bd_disk);
 	struct bio_integrity_data *bid;
+	bool set_flags = true;
 	gfp_t gfp = GFP_NOIO;
 	unsigned int len;
 	void *buf;
@@ -100,19 +125,24 @@ bool bio_integrity_prep(struct bio *bio)
 
 	switch (bio_op(bio)) {
 	case REQ_OP_READ:
-		if (bi->flags & BLK_INTEGRITY_NOVERIFY)
-			return true;
+		if (bi->flags & BLK_INTEGRITY_NOVERIFY) {
+			if (bi_offload_capable(bi))
+				return true;
+			set_flags = false;
+		}
 		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)
+		if (bi->flags & BLK_INTEGRITY_NOGENERATE) {
+			if (bi_offload_capable(bi))
+				return true;
+			set_flags = false;
+			gfp |= __GFP_ZERO;
+		} else if (bi->csum_type == BLK_INTEGRITY_CSUM_NONE)
 			gfp |= __GFP_ZERO;
 		break;
 	default:
@@ -137,19 +167,21 @@ bool bio_integrity_prep(struct bio *bio)
 	bid->bip.bip_flags |= BIP_BLOCK_INTEGRITY;
 	bip_set_seed(&bid->bip, bio->bi_iter.bi_sector);
 
-	if (bi->csum_type == BLK_INTEGRITY_CSUM_IP)
-		bid->bip.bip_flags |= BIP_IP_CHECKSUM;
-	if (bi->csum_type)
-		bid->bip.bip_flags |= BIP_CHECK_GUARD;
-	if (bi->flags & BLK_INTEGRITY_REF_TAG)
-		bid->bip.bip_flags |= BIP_CHECK_REFTAG;
+	if (set_flags) {
+		if (bi->csum_type == BLK_INTEGRITY_CSUM_IP)
+			bid->bip.bip_flags |= BIP_IP_CHECKSUM;
+		if (bi->csum_type)
+			bid->bip.bip_flags |= BIP_CHECK_GUARD;
+		if (bi->flags & BLK_INTEGRITY_REF_TAG)
+			bid->bip.bip_flags |= BIP_CHECK_REFTAG;
+	}
 
 	if (bio_integrity_add_page(bio, virt_to_page(buf), len,
 			offset_in_page(buf)) < len)
 		goto err_end_io;
 
 	/* Auto-generate integrity metadata if this is a write */
-	if (bio_data_dir(bio) == WRITE)
+	if (bio_data_dir(bio) == WRITE && bip_should_check(&bid->bip))
 		blk_integrity_generate(bio);
 	else
 		bid->saved_bio_iter = bio->bi_iter;
diff --git a/block/bio-integrity.c b/block/bio-integrity.c
index 608594a154a5..43ef6bd06c85 100644
--- a/block/bio-integrity.c
+++ b/block/bio-integrity.c
@@ -66,16 +66,12 @@ struct bio_integrity_payload *bio_integrity_alloc(struct bio *bio,
 }
 EXPORT_SYMBOL(bio_integrity_alloc);
 
-static void bio_integrity_unpin_bvec(struct bio_vec *bv, int nr_vecs,
-				     bool dirty)
+static void bio_integrity_unpin_bvec(struct bio_vec *bv, int nr_vecs)
 {
 	int i;
 
-	for (i = 0; i < nr_vecs; i++) {
-		if (dirty && !PageCompound(bv[i].bv_page))
-			set_page_dirty_lock(bv[i].bv_page);
+	for (i = 0; i < nr_vecs; i++)
 		unpin_user_page(bv[i].bv_page);
-	}
 }
 
 static void bio_integrity_uncopy_user(struct bio_integrity_payload *bip)
@@ -91,7 +87,7 @@ static void bio_integrity_uncopy_user(struct bio_integrity_payload *bip)
 	ret = copy_to_iter(bvec_virt(bounce_bvec), bytes, &orig_iter);
 	WARN_ON_ONCE(ret != bytes);
 
-	bio_integrity_unpin_bvec(orig_bvecs, orig_nr_vecs, true);
+	bio_integrity_unpin_bvec(orig_bvecs, orig_nr_vecs);
 }
 
 /**
@@ -111,8 +107,7 @@ void bio_integrity_unmap_user(struct bio *bio)
 		return;
 	}
 
-	bio_integrity_unpin_bvec(bip->bip_vec, bip->bip_max_vcnt,
-			bio_data_dir(bio) == READ);
+	bio_integrity_unpin_bvec(bip->bip_vec, bip->bip_max_vcnt);
 }
 
 /**
@@ -198,7 +193,7 @@ static int bio_integrity_copy_user(struct bio *bio, struct bio_vec *bvec,
 	}
 
 	if (write)
-		bio_integrity_unpin_bvec(bvec, nr_vecs, false);
+		bio_integrity_unpin_bvec(bvec, nr_vecs);
 	else
 		memcpy(&bip->bip_vec[1], bvec, nr_vecs * sizeof(*bvec));
 
@@ -319,7 +314,7 @@ int bio_integrity_map_user(struct bio *bio, struct iov_iter *iter)
 	return 0;
 
 release_pages:
-	bio_integrity_unpin_bvec(bvec, nr_bvecs, false);
+	bio_integrity_unpin_bvec(bvec, nr_bvecs);
 free_bvec:
 	if (bvec != stack_vec)
 		kfree(bvec);
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 5905f277057b..ce93706555c5 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -797,7 +797,7 @@ int blkg_conf_open_bdev(struct blkg_conf_ctx *ctx)
 		return -EINVAL;
 	input = skip_spaces(input);
 
-	bdev = blkdev_get_no_open(MKDEV(major, minor));
+	bdev = blkdev_get_no_open(MKDEV(major, minor), false);
 	if (!bdev)
 		return -ENODEV;
 	if (bdev_is_partition(bdev)) {
diff --git a/block/blk-settings.c b/block/blk-settings.c
index 6b2dbe645d23..4817e7ca03f8 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -61,8 +61,14 @@ void blk_apply_bdi_limits(struct backing_dev_info *bdi,
 	/*
 	 * For read-ahead of large files to be effective, we need to read ahead
 	 * at least twice the optimal I/O size.
+	 *
+	 * There is no hardware limitation for the read-ahead size and the user
+	 * might have increased the read-ahead size through sysfs, so don't ever
+	 * decrease it.
 	 */
-	bdi->ra_pages = max(lim->io_opt * 2 / PAGE_SIZE, VM_READAHEAD_PAGES);
+	bdi->ra_pages = max3(bdi->ra_pages,
+				lim->io_opt * 2 / PAGE_SIZE,
+				VM_READAHEAD_PAGES);
 	bdi->io_pages = lim->max_sectors >> PAGE_SECTORS_SHIFT;
 }
 
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index a2882751f0d2..1f9b45b0b9ee 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -909,6 +909,8 @@ out_unregister_ia_ranges:
 out_debugfs_remove:
 	blk_debugfs_remove(disk);
 	mutex_unlock(&q->sysfs_lock);
+	if (queue_is_mq(q))
+		blk_mq_sysfs_unregister(disk);
 out_put_queue_kobj:
 	kobject_put(&disk->queue_kobj);
 	return ret;
diff --git a/block/blk-throttle.h b/block/blk-throttle.h
index 7964cc041e06..f9f8666891ab 100644
--- a/block/blk-throttle.h
+++ b/block/blk-throttle.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef BLK_THROTTLE_H
 #define BLK_THROTTLE_H
 
diff --git a/block/blk-zoned.c b/block/blk-zoned.c
index 0c77244a35c9..8f15d1aa6eb8 100644
--- a/block/blk-zoned.c
+++ b/block/blk-zoned.c
@@ -343,6 +343,7 @@ int blkdev_zone_mgmt_ioctl(struct block_device *bdev, blk_mode_t mode,
 		op = REQ_OP_ZONE_RESET;
 
 		/* Invalidate the page cache, including dirty pages. */
+		inode_lock(bdev->bd_mapping->host);
 		filemap_invalidate_lock(bdev->bd_mapping);
 		ret = blkdev_truncate_zone_range(bdev, mode, &zrange);
 		if (ret)
@@ -364,8 +365,10 @@ int blkdev_zone_mgmt_ioctl(struct block_device *bdev, blk_mode_t mode,
 	ret = blkdev_zone_mgmt(bdev, op, zrange.sector, zrange.nr_sectors);
 
 fail:
-	if (cmd == BLKRESETZONE)
+	if (cmd == BLKRESETZONE) {
 		filemap_invalidate_unlock(bdev->bd_mapping);
+		inode_unlock(bdev->bd_mapping->host);
+	}
 
 	return ret;
 }
diff --git a/block/blk.h b/block/blk.h
index 006e3be433d2..594eeba7b949 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -94,6 +94,9 @@ static inline void blk_wait_io(struct completion *done)
 		wait_for_completion_io(done);
 }
 
+struct block_device *blkdev_get_no_open(dev_t dev, bool autoload);
+void blkdev_put_no_open(struct block_device *bdev);
+
 #define BIO_INLINE_VECS 4
 struct bio_vec *bvec_alloc(mempool_t *pool, unsigned short *nr_vecs,
 		gfp_t gfp_mask);
@@ -477,7 +480,8 @@ static inline void blk_zone_update_request_bio(struct request *rq,
 	 * the original BIO sector so that blk_zone_write_plug_bio_endio() can
 	 * lookup the zone write plug.
 	 */
-	if (req_op(rq) == REQ_OP_ZONE_APPEND || bio_zone_write_plugging(bio))
+	if (req_op(rq) == REQ_OP_ZONE_APPEND ||
+	    bio_flagged(bio, BIO_EMULATES_ZONE_APPEND))
 		bio->bi_iter.bi_sector = rq->__sector;
 }
 void blk_zone_write_plug_bio_endio(struct bio *bio);
diff --git a/block/fops.c b/block/fops.c
index be9f1dbea9ce..82b672d15ea4 100644
--- a/block/fops.c
+++ b/block/fops.c
@@ -642,7 +642,7 @@ static int blkdev_open(struct inode *inode, struct file *filp)
 	if (ret)
 		return ret;
 
-	bdev = blkdev_get_no_open(inode->i_rdev);
+	bdev = blkdev_get_no_open(inode->i_rdev, true);
 	if (!bdev)
 		return -ENXIO;
 
@@ -746,7 +746,14 @@ static ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from)
 			ret = direct_write_fallback(iocb, from, ret,
 					blkdev_buffered_write(iocb, from));
 	} else {
+		/*
+		 * Take i_rwsem and invalidate_lock to avoid racing with
+		 * set_blocksize changing i_blkbits/folio order and punching
+		 * out the pagecache.
+		 */
+		inode_lock_shared(bd_inode);
 		ret = blkdev_buffered_write(iocb, from);
+		inode_unlock_shared(bd_inode);
 	}
 
 	if (ret > 0)
@@ -757,6 +764,7 @@ static ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from)
 
 static ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to)
 {
+	struct inode *bd_inode = bdev_file_inode(iocb->ki_filp);
 	struct block_device *bdev = I_BDEV(iocb->ki_filp->f_mapping->host);
 	loff_t size = bdev_nr_bytes(bdev);
 	loff_t pos = iocb->ki_pos;
@@ -793,7 +801,13 @@ static ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to)
 			goto reexpand;
 	}
 
+	/*
+	 * Take i_rwsem and invalidate_lock to avoid racing with set_blocksize
+	 * changing i_blkbits/folio order and punching out the pagecache.
+	 */
+	inode_lock_shared(bd_inode);
 	ret = filemap_read(iocb, to, ret);
+	inode_unlock_shared(bd_inode);
 
 reexpand:
 	if (unlikely(shorted))
@@ -836,6 +850,7 @@ static long blkdev_fallocate(struct file *file, int mode, loff_t start,
 	if ((start | len) & (bdev_logical_block_size(bdev) - 1))
 		return -EINVAL;
 
+	inode_lock(inode);
 	filemap_invalidate_lock(inode->i_mapping);
 
 	/*
@@ -868,6 +883,7 @@ static long blkdev_fallocate(struct file *file, int mode, loff_t start,
 
  fail:
 	filemap_invalidate_unlock(inode->i_mapping);
+	inode_unlock(inode);
 	return error;
 }
 
diff --git a/block/ioctl.c b/block/ioctl.c
index faa40f383e27..e472cc1030c6 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -142,6 +142,7 @@ static int blk_ioctl_discard(struct block_device *bdev, blk_mode_t mode,
 	if (err)
 		return err;
 
+	inode_lock(bdev->bd_mapping->host);
 	filemap_invalidate_lock(bdev->bd_mapping);
 	err = truncate_bdev_range(bdev, mode, start, start + len - 1);
 	if (err)
@@ -174,6 +175,7 @@ out_unplug:
 	blk_finish_plug(&plug);
 fail:
 	filemap_invalidate_unlock(bdev->bd_mapping);
+	inode_unlock(bdev->bd_mapping->host);
 	return err;
 }
 
@@ -199,12 +201,14 @@ static int blk_ioctl_secure_erase(struct block_device *bdev, blk_mode_t mode,
 	    end > bdev_nr_bytes(bdev))
 		return -EINVAL;
 
+	inode_lock(bdev->bd_mapping->host);
 	filemap_invalidate_lock(bdev->bd_mapping);
 	err = truncate_bdev_range(bdev, mode, start, end - 1);
 	if (!err)
 		err = blkdev_issue_secure_erase(bdev, start >> 9, len >> 9,
 						GFP_KERNEL);
 	filemap_invalidate_unlock(bdev->bd_mapping);
+	inode_unlock(bdev->bd_mapping->host);
 	return err;
 }
 
@@ -236,6 +240,7 @@ static int blk_ioctl_zeroout(struct block_device *bdev, blk_mode_t mode,
 		return -EINVAL;
 
 	/* Invalidate the page cache, including dirty pages */
+	inode_lock(bdev->bd_mapping->host);
 	filemap_invalidate_lock(bdev->bd_mapping);
 	err = truncate_bdev_range(bdev, mode, start, end);
 	if (err)
@@ -246,6 +251,7 @@ static int blk_ioctl_zeroout(struct block_device *bdev, blk_mode_t mode,
 
 fail:
 	filemap_invalidate_unlock(bdev->bd_mapping);
+	inode_unlock(bdev->bd_mapping->host);
 	return err;
 }
 
diff --git a/block/ioprio.c b/block/ioprio.c
index 73301a261429..f0ee2798539c 100644
--- a/block/ioprio.c
+++ b/block/ioprio.c
@@ -46,12 +46,8 @@ int ioprio_check_cap(int ioprio)
 			 */
 			if (!capable(CAP_SYS_ADMIN) && !capable(CAP_SYS_NICE))
 				return -EPERM;
-			fallthrough;
-			/* rt has prio field too */
-		case IOPRIO_CLASS_BE:
-			if (level >= IOPRIO_NR_LEVELS)
-				return -EINVAL;
 			break;
+		case IOPRIO_CLASS_BE:
 		case IOPRIO_CLASS_IDLE:
 			break;
 		case IOPRIO_CLASS_NONE: