From 79478bf9ea9fa48d30836afa796ac13d8a0f320b Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 17 Nov 2021 07:13:54 +0100
Subject: block: move blk_rq_err_bytes to scsi

blk_rq_err_bytes is only used by the scsi midlayer, so move it there.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Link: https://lore.kernel.org/r/20211117061404.331732-2-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/blk-mq.h | 3 ---
 1 file changed, 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 2949d9ac7484..a78d9a0f2a1b 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -947,7 +947,6 @@ struct req_iterator {
  * blk_rq_pos()			: the current sector
  * blk_rq_bytes()		: bytes left in the entire request
  * blk_rq_cur_bytes()		: bytes left in the current segment
- * blk_rq_err_bytes()		: bytes left till the next error boundary
  * blk_rq_sectors()		: sectors left in the entire request
  * blk_rq_cur_sectors()		: sectors left in the current segment
  * blk_rq_stats_sectors()	: sectors of the entire request used for stats
@@ -971,8 +970,6 @@ static inline int blk_rq_cur_bytes(const struct request *rq)
 	return bio_iovec(rq->bio).bv_len;
 }
 
-unsigned int blk_rq_err_bytes(const struct request *rq);
-
 static inline unsigned int blk_rq_sectors(const struct request *rq)
 {
 	return blk_rq_bytes(rq) >> SECTOR_SHIFT;
-- 
cgit v1.2.3


From 786d4e01c550e8bb7c9f9f23bca0596a2a33483c Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 17 Nov 2021 07:13:55 +0100
Subject: block: remove rq_flush_dcache_pages

This function is trivial, and flush_dcache_page is always defined, so
just open code it in the 2.5 callers.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Link: https://lore.kernel.org/r/20211117061404.331732-3-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-core.c          | 19 -------------------
 drivers/mtd/mtd_blkdevs.c | 10 ++++++++--
 drivers/mtd/ubi/block.c   |  6 +++++-
 include/linux/blk-mq.h    | 10 ----------
 4 files changed, 13 insertions(+), 32 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-core.c b/block/blk-core.c
index 682b112f513f..039e28509f59 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1300,25 +1300,6 @@ void blk_steal_bios(struct bio_list *list, struct request *rq)
 }
 EXPORT_SYMBOL_GPL(blk_steal_bios);
 
-#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE
-/**
- * rq_flush_dcache_pages - Helper function to flush all pages in a request
- * @rq: the request to be flushed
- *
- * Description:
- *     Flush all pages in @rq.
- */
-void rq_flush_dcache_pages(struct request *rq)
-{
-	struct req_iterator iter;
-	struct bio_vec bvec;
-
-	rq_for_each_segment(bvec, rq, iter)
-		flush_dcache_page(bvec.bv_page);
-}
-EXPORT_SYMBOL_GPL(rq_flush_dcache_pages);
-#endif
-
 /**
  * blk_lld_busy - Check if underlying low-level drivers of a device are busy
  * @q : the queue of the device being checked
diff --git a/drivers/mtd/mtd_blkdevs.c b/drivers/mtd/mtd_blkdevs.c
index 4eaba6f4ec68..66f81d42fe77 100644
--- a/drivers/mtd/mtd_blkdevs.c
+++ b/drivers/mtd/mtd_blkdevs.c
@@ -46,6 +46,8 @@ static blk_status_t do_blktrans_request(struct mtd_blktrans_ops *tr,
 			       struct mtd_blktrans_dev *dev,
 			       struct request *req)
 {
+	struct req_iterator iter;
+	struct bio_vec bvec;
 	unsigned long block, nsect;
 	char *buf;
 
@@ -76,13 +78,17 @@ static blk_status_t do_blktrans_request(struct mtd_blktrans_ops *tr,
 			}
 		}
 		kunmap(bio_page(req->bio));
-		rq_flush_dcache_pages(req);
+
+		rq_for_each_segment(bvec, req, iter)
+			flush_dcache_page(bvec.bv_page);
 		return BLK_STS_OK;
 	case REQ_OP_WRITE:
 		if (!tr->writesect)
 			return BLK_STS_IOERR;
 
-		rq_flush_dcache_pages(req);
+		rq_for_each_segment(bvec, req, iter)
+			flush_dcache_page(bvec.bv_page);
+
 		buf = kmap(bio_page(req->bio)) + bio_offset(req->bio);
 		for (; nsect > 0; nsect--, block++, buf += tr->blksize) {
 			if (tr->writesect(dev, block, buf)) {
diff --git a/drivers/mtd/ubi/block.c b/drivers/mtd/ubi/block.c
index 062e6c2c45f5..302426ab30f8 100644
--- a/drivers/mtd/ubi/block.c
+++ b/drivers/mtd/ubi/block.c
@@ -294,6 +294,8 @@ static void ubiblock_do_work(struct work_struct *work)
 	int ret;
 	struct ubiblock_pdu *pdu = container_of(work, struct ubiblock_pdu, work);
 	struct request *req = blk_mq_rq_from_pdu(pdu);
+	struct req_iterator iter;
+	struct bio_vec bvec;
 
 	blk_mq_start_request(req);
 
@@ -305,7 +307,9 @@ static void ubiblock_do_work(struct work_struct *work)
 	blk_rq_map_sg(req->q, req, pdu->usgl.sg);
 
 	ret = ubiblock_read(pdu);
-	rq_flush_dcache_pages(req);
+
+	rq_for_each_segment(bvec, req, iter)
+		flush_dcache_page(bvec.bv_page);
 
 	blk_mq_end_request(req, errno_to_blk_status(ret));
 }
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index a78d9a0f2a1b..308edc2a4925 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -1132,14 +1132,4 @@ static inline bool blk_req_can_dispatch_to_zone(struct request *rq)
 }
 #endif /* CONFIG_BLK_DEV_ZONED */
 
-#ifndef ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE
-# error	"You should define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE for your platform"
-#endif
-#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE
-void rq_flush_dcache_pages(struct request *rq);
-#else
-static inline void rq_flush_dcache_pages(struct request *rq)
-{
-}
-#endif /* ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE */
 #endif /* BLK_MQ_H */
-- 
cgit v1.2.3


From 86416916466514e4ae0b7296d20133b6427c4c1f Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 22 Nov 2021 14:06:12 +0100
Subject: block: move GENHD_FL_NATIVE_CAPACITY to disk->state

The flag to indicate an unlocked native capacity is dynamic state,
not a driver capability flag, so move it to disk->state.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20211122130625.1136848-2-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/partitions/core.c | 15 ++++++---------
 include/linux/genhd.h   |  8 +-------
 2 files changed, 7 insertions(+), 16 deletions(-)

(limited to 'include/linux')

diff --git a/block/partitions/core.c b/block/partitions/core.c
index 334b72ef1d73..520292fee933 100644
--- a/block/partitions/core.c
+++ b/block/partitions/core.c
@@ -527,18 +527,15 @@ out_unlock:
 
 static bool disk_unlock_native_capacity(struct gendisk *disk)
 {
-	const struct block_device_operations *bdops = disk->fops;
-
-	if (bdops->unlock_native_capacity &&
-	    !(disk->flags & GENHD_FL_NATIVE_CAPACITY)) {
-		printk(KERN_CONT "enabling native capacity\n");
-		bdops->unlock_native_capacity(disk);
-		disk->flags |= GENHD_FL_NATIVE_CAPACITY;
-		return true;
-	} else {
+	if (!disk->fops->unlock_native_capacity ||
+	    test_and_set_bit(GD_NATIVE_CAPACITY, &disk->state)) {
 		printk(KERN_CONT "truncated\n");
 		return false;
 	}
+
+	printk(KERN_CONT "enabling native capacity\n");
+	disk->fops->unlock_native_capacity(disk);
+	return true;
 }
 
 void blk_drop_partitions(struct gendisk *disk)
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 74c410263113..e490a71e5e9d 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -60,12 +60,6 @@ struct partition_meta_info {
  * (``BLOCK_EXT_MAJOR``).
  * This affects the maximum number of partitions.
  *
- * ``GENHD_FL_NATIVE_CAPACITY`` (0x0080): based on information in the
- * partition table, the device's capacity has been extended to its
- * native capacity; i.e. the device has hidden capacity used by one
- * of the partitions (this is a flag used so that native capacity is
- * only ever unlocked once).
- *
  * ``GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE`` (0x0100): event polling is
  * blocked whenever a writer holds an exclusive lock.
  *
@@ -86,7 +80,6 @@ struct partition_meta_info {
 #define GENHD_FL_CD				0x0008
 #define GENHD_FL_SUPPRESS_PARTITION_INFO	0x0020
 #define GENHD_FL_EXT_DEVT			0x0040
-#define GENHD_FL_NATIVE_CAPACITY		0x0080
 #define GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE	0x0100
 #define GENHD_FL_NO_PART_SCAN			0x0200
 #define GENHD_FL_HIDDEN				0x0400
@@ -140,6 +133,7 @@ struct gendisk {
 #define GD_NEED_PART_SCAN		0
 #define GD_READ_ONLY			1
 #define GD_DEAD				2
+#define GD_NATIVE_CAPACITY		3
 
 	struct mutex open_mutex;	/* open/close mutex */
 	unsigned open_partitions;	/* number of open partitions */
-- 
cgit v1.2.3


From 1545e0b419ba1d9b9bee4061d4826340afe6b0aa Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 22 Nov 2021 14:06:13 +0100
Subject: block: move GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE to disk->event_flags

GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE is all about the event reporting
mechanism, so move it to the event_flags field.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20211122130625.1136848-3-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/bdev.c               | 2 +-
 drivers/block/paride/pcd.c | 2 +-
 drivers/scsi/sr.c          | 5 +++--
 include/linux/genhd.h      | 6 ++----
 4 files changed, 7 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/block/bdev.c b/block/bdev.c
index b1d087e5e205..dd84961bed7e 100644
--- a/block/bdev.c
+++ b/block/bdev.c
@@ -837,7 +837,7 @@ struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder)
 		 * used in blkdev_get/put().
 		 */
 		if ((mode & FMODE_WRITE) && !bdev->bd_write_holder &&
-		    (disk->flags & GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE)) {
+		    (disk->event_flags & DISK_EVENT_FLAG_BLOCK_ON_EXCL_WRITE)) {
 			bdev->bd_write_holder = true;
 			unblock_events = false;
 		}
diff --git a/drivers/block/paride/pcd.c b/drivers/block/paride/pcd.c
index f6b1d63e96e1..430ee8004a51 100644
--- a/drivers/block/paride/pcd.c
+++ b/drivers/block/paride/pcd.c
@@ -928,8 +928,8 @@ static int pcd_init_unit(struct pcd_unit *cd, bool autoprobe, int port,
 	disk->minors = 1;
 	strcpy(disk->disk_name, cd->name);	/* umm... */
 	disk->fops = &pcd_bdops;
-	disk->flags = GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE;
 	disk->events = DISK_EVENT_MEDIA_CHANGE;
+	disk->event_flags = DISK_EVENT_FLAG_BLOCK_ON_EXCL_WRITE;
 
 	if (!pi_init(cd->pi, autoprobe, port, mode, unit, protocol, delay,
 			pcd_buffer, PI_PCD, verbose, cd->name)) {
diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c
index 8e4af111c078..be445dc35f2c 100644
--- a/drivers/scsi/sr.c
+++ b/drivers/scsi/sr.c
@@ -684,9 +684,10 @@ static int sr_probe(struct device *dev)
 	disk->minors = 1;
 	sprintf(disk->disk_name, "sr%d", minor);
 	disk->fops = &sr_bdops;
-	disk->flags = GENHD_FL_CD | GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE;
+	disk->flags = GENHD_FL_CD;
 	disk->events = DISK_EVENT_MEDIA_CHANGE | DISK_EVENT_EJECT_REQUEST;
-	disk->event_flags = DISK_EVENT_FLAG_POLL | DISK_EVENT_FLAG_UEVENT;
+	disk->event_flags = DISK_EVENT_FLAG_POLL | DISK_EVENT_FLAG_UEVENT |
+				DISK_EVENT_FLAG_BLOCK_ON_EXCL_WRITE;
 
 	blk_queue_rq_timeout(sdev->request_queue, SR_TIMEOUT);
 
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index e490a71e5e9d..c1136ff3c91f 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -60,9 +60,6 @@ struct partition_meta_info {
  * (``BLOCK_EXT_MAJOR``).
  * This affects the maximum number of partitions.
  *
- * ``GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE`` (0x0100): event polling is
- * blocked whenever a writer holds an exclusive lock.
- *
  * ``GENHD_FL_NO_PART_SCAN`` (0x0200): partition scanning is disabled.
  * Used for loop devices in their default settings and some MMC
  * devices.
@@ -80,7 +77,6 @@ struct partition_meta_info {
 #define GENHD_FL_CD				0x0008
 #define GENHD_FL_SUPPRESS_PARTITION_INFO	0x0020
 #define GENHD_FL_EXT_DEVT			0x0040
-#define GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE	0x0100
 #define GENHD_FL_NO_PART_SCAN			0x0200
 #define GENHD_FL_HIDDEN				0x0400
 
@@ -94,6 +90,8 @@ enum {
 	DISK_EVENT_FLAG_POLL			= 1 << 0,
 	/* Forward events to udev */
 	DISK_EVENT_FLAG_UEVENT			= 1 << 1,
+	/* Block event polling when open for exclusive write */
+	DISK_EVENT_FLAG_BLOCK_ON_EXCL_WRITE	= 1 << 2,
 };
 
 struct disk_events;
-- 
cgit v1.2.3


From 1a827ce1b9f2c740d2c6a228afd972970c18bc21 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 22 Nov 2021 14:06:14 +0100
Subject: block: remove GENHD_FL_CD

GENHD_FL_CD marks a gendisk as a vaguely CD-ROM like device.
Besides being used internally inside of sunvdc.c an xen-blkfront it
is used by xen-blkback as a hint to claim a device exported to a
guest is a CD-ROM like device.  Just check for disk->cdi instead
which is the right indicator for "real" CD-ROM or DVD drivers.  This
will miss the paravirtualized guest drivers, but those make little
sense to report anyway.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20211122130625.1136848-4-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/sunvdc.c             | 17 +++++++++--------
 drivers/block/xen-blkback/xenbus.c |  2 +-
 drivers/block/xen-blkfront.c       | 26 +++++++++++---------------
 drivers/scsi/sr.c                  |  1 -
 include/linux/genhd.h              |  5 -----
 5 files changed, 21 insertions(+), 30 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/block/sunvdc.c b/drivers/block/sunvdc.c
index 6f45a53f7cbf..2157936de623 100644
--- a/drivers/block/sunvdc.c
+++ b/drivers/block/sunvdc.c
@@ -143,8 +143,8 @@ static int vdc_getgeo(struct block_device *bdev, struct hd_geometry *geo)
 static int vdc_ioctl(struct block_device *bdev, fmode_t mode,
 		     unsigned command, unsigned long argument)
 {
+	struct vdc_port *port = bdev->bd_disk->private_data;
 	int i;
-	struct gendisk *disk;
 
 	switch (command) {
 	case CDROMMULTISESSION:
@@ -155,12 +155,15 @@ static int vdc_ioctl(struct block_device *bdev, fmode_t mode,
 		return 0;
 
 	case CDROM_GET_CAPABILITY:
-		disk = bdev->bd_disk;
-
-		if (bdev->bd_disk && (disk->flags & GENHD_FL_CD))
+		if (!vdc_version_supported(port, 1, 1))
+			return -EINVAL;
+		switch (port->vdisk_mtype) {
+		case VD_MEDIA_TYPE_CD:
+		case VD_MEDIA_TYPE_DVD:
 			return 0;
-		return -EINVAL;
-
+		default:
+			return -EINVAL;
+		}
 	default:
 		pr_debug(PFX "ioctl %08x not supported\n", command);
 		return -EINVAL;
@@ -854,14 +857,12 @@ static int probe_disk(struct vdc_port *port)
 		switch (port->vdisk_mtype) {
 		case VD_MEDIA_TYPE_CD:
 			pr_info(PFX "Virtual CDROM %s\n", port->disk_name);
-			g->flags |= GENHD_FL_CD;
 			g->flags |= GENHD_FL_REMOVABLE;
 			set_disk_ro(g, 1);
 			break;
 
 		case VD_MEDIA_TYPE_DVD:
 			pr_info(PFX "Virtual DVD %s\n", port->disk_name);
-			g->flags |= GENHD_FL_CD;
 			g->flags |= GENHD_FL_REMOVABLE;
 			set_disk_ro(g, 1);
 			break;
diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c
index 914587aabca0..62125fd4af4a 100644
--- a/drivers/block/xen-blkback/xenbus.c
+++ b/drivers/block/xen-blkback/xenbus.c
@@ -510,7 +510,7 @@ static int xen_vbd_create(struct xen_blkif *blkif, blkif_vdev_t handle,
 	}
 	vbd->size = vbd_sz(vbd);
 
-	if (vbd->bdev->bd_disk->flags & GENHD_FL_CD || cdrom)
+	if (cdrom || disk_to_cdi(vbd->bdev->bd_disk))
 		vbd->type |= VDISK_CDROM;
 	if (vbd->bdev->bd_disk->flags & GENHD_FL_REMOVABLE)
 		vbd->type |= VDISK_REMOVABLE;
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index 8e3983e456f3..700c765a759a 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -198,6 +198,7 @@ struct blkfront_info
 	struct gendisk *gd;
 	u16 sector_size;
 	unsigned int physical_sector_size;
+	unsigned long vdisk_info;
 	int vdevice;
 	blkif_vdev_t handle;
 	enum blkif_state connected;
@@ -505,6 +506,7 @@ static int blkif_getgeo(struct block_device *bd, struct hd_geometry *hg)
 static int blkif_ioctl(struct block_device *bdev, fmode_t mode,
 		       unsigned command, unsigned long argument)
 {
+	struct blkfront_info *info = bdev->bd_disk->private_data;
 	int i;
 
 	switch (command) {
@@ -514,9 +516,9 @@ static int blkif_ioctl(struct block_device *bdev, fmode_t mode,
 				return -EFAULT;
 		return 0;
 	case CDROM_GET_CAPABILITY:
-		if (bdev->bd_disk->flags & GENHD_FL_CD)
-			return 0;
-		return -EINVAL;
+		if (!(info->vdisk_info & VDISK_CDROM))
+			return -EINVAL;
+		return 0;
 	default:
 		return -EINVAL;
 	}
@@ -1057,9 +1059,8 @@ static char *encode_disk_name(char *ptr, unsigned int n)
 }
 
 static int xlvbd_alloc_gendisk(blkif_sector_t capacity,
-			       struct blkfront_info *info,
-			       u16 vdisk_info, u16 sector_size,
-			       unsigned int physical_sector_size)
+		struct blkfront_info *info, u16 sector_size,
+		unsigned int physical_sector_size)
 {
 	struct gendisk *gd;
 	int nr_minors = 1;
@@ -1157,15 +1158,11 @@ static int xlvbd_alloc_gendisk(blkif_sector_t capacity,
 
 	xlvbd_flush(info);
 
-	if (vdisk_info & VDISK_READONLY)
+	if (info->vdisk_info & VDISK_READONLY)
 		set_disk_ro(gd, 1);
-
-	if (vdisk_info & VDISK_REMOVABLE)
+	if (info->vdisk_info & VDISK_REMOVABLE)
 		gd->flags |= GENHD_FL_REMOVABLE;
 
-	if (vdisk_info & VDISK_CDROM)
-		gd->flags |= GENHD_FL_CD;
-
 	return 0;
 
 out_free_tag_set:
@@ -2304,7 +2301,6 @@ static void blkfront_connect(struct blkfront_info *info)
 	unsigned long long sectors;
 	unsigned long sector_size;
 	unsigned int physical_sector_size;
-	unsigned int binfo;
 	int err, i;
 	struct blkfront_ring_info *rinfo;
 
@@ -2342,7 +2338,7 @@ static void blkfront_connect(struct blkfront_info *info)
 
 	err = xenbus_gather(XBT_NIL, info->xbdev->otherend,
 			    "sectors", "%llu", &sectors,
-			    "info", "%u", &binfo,
+			    "info", "%u", &info->vdisk_info,
 			    "sector-size", "%lu", &sector_size,
 			    NULL);
 	if (err) {
@@ -2371,7 +2367,7 @@ static void blkfront_connect(struct blkfront_info *info)
 		}
 	}
 
-	err = xlvbd_alloc_gendisk(sectors, info, binfo, sector_size,
+	err = xlvbd_alloc_gendisk(sectors, info, sector_size,
 				  physical_sector_size);
 	if (err) {
 		xenbus_dev_fatal(info->xbdev, err, "xlvbd_add at %s",
diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c
index be445dc35f2c..6646797a7756 100644
--- a/drivers/scsi/sr.c
+++ b/drivers/scsi/sr.c
@@ -684,7 +684,6 @@ static int sr_probe(struct device *dev)
 	disk->minors = 1;
 	sprintf(disk->disk_name, "sr%d", minor);
 	disk->fops = &sr_bdops;
-	disk->flags = GENHD_FL_CD;
 	disk->events = DISK_EVENT_MEDIA_CHANGE | DISK_EVENT_EJECT_REQUEST;
 	disk->event_flags = DISK_EVENT_FLAG_POLL | DISK_EVENT_FLAG_UEVENT |
 				DISK_EVENT_FLAG_BLOCK_ON_EXCL_WRITE;
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index c1136ff3c91f..74518c576fbb 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -46,10 +46,6 @@ struct partition_meta_info {
  * Must not be set for devices which are removed entirely when the
  * media is removed.
  *
- * ``GENHD_FL_CD`` (0x0008): the block device is a CD-ROM-style
- * device.
- * Affects responses to the ``CDROM_GET_CAPABILITY`` ioctl.
- *
  * ``GENHD_FL_SUPPRESS_PARTITION_INFO`` (0x0020): don't include
  * partition information in ``/proc/partitions`` or in the output of
  * printk_all_partitions().
@@ -74,7 +70,6 @@ struct partition_meta_info {
 #define GENHD_FL_REMOVABLE			0x0001
 /* 2 is unused (used to be GENHD_FL_DRIVERFS) */
 /* 4 is unused (used to be GENHD_FL_MEDIA_CHANGE_NOTIFY) */
-#define GENHD_FL_CD				0x0008
 #define GENHD_FL_SUPPRESS_PARTITION_INFO	0x0020
 #define GENHD_FL_EXT_DEVT			0x0040
 #define GENHD_FL_NO_PART_SCAN			0x0200
-- 
cgit v1.2.3


From 46e7eac647b34ed4106a8262f8bedbb90801fadd Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 22 Nov 2021 14:06:17 +0100
Subject: block: rename GENHD_FL_NO_PART_SCAN to GENHD_FL_NO_PART

The GENHD_FL_NO_PART_SCAN controls more than just partitions canning,
so rename it to GENHD_FL_NO_PART.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Ulf Hansson <ulf.hansson@linaro.org>
Link: https://lore.kernel.org/r/20211122130625.1136848-7-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/genhd.c            |  2 +-
 drivers/block/loop.c     |  8 ++++----
 drivers/block/n64cart.c  |  2 +-
 drivers/mmc/core/block.c |  4 ++--
 include/linux/genhd.h    | 13 ++++++-------
 5 files changed, 14 insertions(+), 15 deletions(-)

(limited to 'include/linux')

diff --git a/block/genhd.c b/block/genhd.c
index 94f39c4333b8..685794a2ebb0 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -500,7 +500,7 @@ int __must_check device_add_disk(struct device *parent, struct gendisk *disk,
 		 * and don't bother scanning for partitions either.
 		 */
 		disk->flags |= GENHD_FL_SUPPRESS_PARTITION_INFO;
-		disk->flags |= GENHD_FL_NO_PART_SCAN;
+		disk->flags |= GENHD_FL_NO_PART;
 	} else {
 		ret = bdi_register(disk->bdi, "%u:%u",
 				   disk->major, disk->first_minor);
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index a154cab6cd98..7219d98c6fb8 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -1061,7 +1061,7 @@ static int loop_configure(struct loop_device *lo, fmode_t mode,
 		lo->lo_flags |= LO_FLAGS_PARTSCAN;
 	partscan = lo->lo_flags & LO_FLAGS_PARTSCAN;
 	if (partscan)
-		lo->lo_disk->flags &= ~GENHD_FL_NO_PART_SCAN;
+		lo->lo_disk->flags &= ~GENHD_FL_NO_PART;
 
 	loop_global_unlock(lo, is_loop);
 	if (partscan)
@@ -1191,7 +1191,7 @@ out_unlock:
 	mutex_lock(&lo->lo_mutex);
 	lo->lo_flags = 0;
 	if (!part_shift)
-		lo->lo_disk->flags |= GENHD_FL_NO_PART_SCAN;
+		lo->lo_disk->flags |= GENHD_FL_NO_PART;
 	lo->lo_state = Lo_unbound;
 	mutex_unlock(&lo->lo_mutex);
 
@@ -1301,7 +1301,7 @@ out_unfreeze:
 
 	if (!err && (lo->lo_flags & LO_FLAGS_PARTSCAN) &&
 	     !(prev_lo_flags & LO_FLAGS_PARTSCAN)) {
-		lo->lo_disk->flags &= ~GENHD_FL_NO_PART_SCAN;
+		lo->lo_disk->flags &= ~GENHD_FL_NO_PART;
 		partscan = true;
 	}
 out_unlock:
@@ -2032,7 +2032,7 @@ static int loop_add(int i)
 	 * userspace tools. Parameters like this in general should be avoided.
 	 */
 	if (!part_shift)
-		disk->flags |= GENHD_FL_NO_PART_SCAN;
+		disk->flags |= GENHD_FL_NO_PART;
 	disk->flags |= GENHD_FL_EXT_DEVT;
 	atomic_set(&lo->lo_refcnt, 0);
 	mutex_init(&lo->lo_mutex);
diff --git a/drivers/block/n64cart.c b/drivers/block/n64cart.c
index 78282f01f581..4db9a8c244af 100644
--- a/drivers/block/n64cart.c
+++ b/drivers/block/n64cart.c
@@ -136,7 +136,7 @@ static int __init n64cart_probe(struct platform_device *pdev)
 		goto out;
 
 	disk->first_minor = 0;
-	disk->flags = GENHD_FL_NO_PART_SCAN;
+	disk->flags = GENHD_FL_NO_PART;
 	disk->fops = &n64cart_fops;
 	disk->private_data = &pdev->dev;
 	strcpy(disk->disk_name, "n64cart");
diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c
index 90e1bcd03b46..a71b3512c877 100644
--- a/drivers/mmc/core/block.c
+++ b/drivers/mmc/core/block.c
@@ -2397,8 +2397,8 @@ static struct mmc_blk_data *mmc_blk_alloc_req(struct mmc_card *card,
 	set_disk_ro(md->disk, md->read_only || default_ro);
 	md->disk->flags = GENHD_FL_EXT_DEVT;
 	if (area_type & (MMC_BLK_DATA_AREA_RPMB | MMC_BLK_DATA_AREA_BOOT))
-		md->disk->flags |= GENHD_FL_NO_PART_SCAN
-				   | GENHD_FL_SUPPRESS_PARTITION_INFO;
+		md->disk->flags |= GENHD_FL_NO_PART |
+				   GENHD_FL_SUPPRESS_PARTITION_INFO;
 
 	/*
 	 * As discussed on lkml, GENHD_FL_REMOVABLE should:
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 74518c576fbb..0b9be3df9489 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -56,15 +56,15 @@ struct partition_meta_info {
  * (``BLOCK_EXT_MAJOR``).
  * This affects the maximum number of partitions.
  *
- * ``GENHD_FL_NO_PART_SCAN`` (0x0200): partition scanning is disabled.
- * Used for loop devices in their default settings and some MMC
- * devices.
+ * ``GENHD_FL_NO_PART`` (0x0200): partition support is disabled.
+ * The kernel will not scan for partitions from add_disk, and users
+ * can't add partitions manually.
  *
  * ``GENHD_FL_HIDDEN`` (0x0400): the block device is hidden; it
  * doesn't produce events, doesn't appear in sysfs, and doesn't have
  * an associated ``bdev``.
  * Implies ``GENHD_FL_SUPPRESS_PARTITION_INFO`` and
- * ``GENHD_FL_NO_PART_SCAN``.
+ * ``GENHD_FL_NO_PART``.
  * Used for multipath devices.
  */
 #define GENHD_FL_REMOVABLE			0x0001
@@ -72,7 +72,7 @@ struct partition_meta_info {
 /* 4 is unused (used to be GENHD_FL_MEDIA_CHANGE_NOTIFY) */
 #define GENHD_FL_SUPPRESS_PARTITION_INFO	0x0020
 #define GENHD_FL_EXT_DEVT			0x0040
-#define GENHD_FL_NO_PART_SCAN			0x0200
+#define GENHD_FL_NO_PART			0x0200
 #define GENHD_FL_HIDDEN				0x0400
 
 enum {
@@ -180,8 +180,7 @@ static inline int disk_max_parts(struct gendisk *disk)
 
 static inline bool disk_part_scan_enabled(struct gendisk *disk)
 {
-	return disk_max_parts(disk) > 1 &&
-		!(disk->flags & GENHD_FL_NO_PART_SCAN);
+	return disk_max_parts(disk) > 1 && !(disk->flags & GENHD_FL_NO_PART);
 }
 
 static inline dev_t disk_devt(struct gendisk *disk)
-- 
cgit v1.2.3


From 3b5149ac50970669ee0ddb9629ec77ffd5c0622d Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 22 Nov 2021 14:06:21 +0100
Subject: block: remove GENHD_FL_SUPPRESS_PARTITION_INFO

This flag is not set directly anywhere and only inherited from
GENHD_FL_HIDDEN.  Just check for GENHD_FL_HIDDEN instead.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20211122130625.1136848-11-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/genhd.c         | 11 +++--------
 include/linux/genhd.h |  9 +--------
 2 files changed, 4 insertions(+), 16 deletions(-)

(limited to 'include/linux')

diff --git a/block/genhd.c b/block/genhd.c
index 685794a2ebb0..50a843ee18f6 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -496,10 +496,8 @@ int __must_check device_add_disk(struct device *parent, struct gendisk *disk,
 
 	if (disk->flags & GENHD_FL_HIDDEN) {
 		/*
-		 * Don't let hidden disks show up in /proc/partitions,
-		 * and don't bother scanning for partitions either.
+		 * Don't bother scanning for partitions.
 		 */
-		disk->flags |= GENHD_FL_SUPPRESS_PARTITION_INFO;
 		disk->flags |= GENHD_FL_NO_PART;
 	} else {
 		ret = bdi_register(disk->bdi, "%u:%u",
@@ -725,8 +723,7 @@ void __init printk_all_partitions(void)
 		 * Don't show empty devices or things that have been
 		 * suppressed
 		 */
-		if (get_capacity(disk) == 0 ||
-		    (disk->flags & GENHD_FL_SUPPRESS_PARTITION_INFO))
+		if (get_capacity(disk) == 0 || (disk->flags & GENHD_FL_HIDDEN))
 			continue;
 
 		/*
@@ -819,9 +816,7 @@ static int show_partition(struct seq_file *seqf, void *v)
 	struct block_device *part;
 	unsigned long idx;
 
-	if (!get_capacity(sgp))
-		return 0;
-	if (sgp->flags & GENHD_FL_SUPPRESS_PARTITION_INFO)
+	if (!get_capacity(sgp) || (sgp->flags & GENHD_FL_HIDDEN))
 		return 0;
 
 	rcu_read_lock();
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 0b9be3df9489..64a2f33ae9ea 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -46,11 +46,6 @@ struct partition_meta_info {
  * Must not be set for devices which are removed entirely when the
  * media is removed.
  *
- * ``GENHD_FL_SUPPRESS_PARTITION_INFO`` (0x0020): don't include
- * partition information in ``/proc/partitions`` or in the output of
- * printk_all_partitions().
- * Used for the null block device and some MMC devices.
- *
  * ``GENHD_FL_EXT_DEVT`` (0x0040): the driver supports extended
  * dynamic ``dev_t``, i.e. it wants extended device numbers
  * (``BLOCK_EXT_MAJOR``).
@@ -63,14 +58,12 @@ struct partition_meta_info {
  * ``GENHD_FL_HIDDEN`` (0x0400): the block device is hidden; it
  * doesn't produce events, doesn't appear in sysfs, and doesn't have
  * an associated ``bdev``.
- * Implies ``GENHD_FL_SUPPRESS_PARTITION_INFO`` and
- * ``GENHD_FL_NO_PART``.
+ * Implies ``GENHD_FL_NO_PART``.
  * Used for multipath devices.
  */
 #define GENHD_FL_REMOVABLE			0x0001
 /* 2 is unused (used to be GENHD_FL_DRIVERFS) */
 /* 4 is unused (used to be GENHD_FL_MEDIA_CHANGE_NOTIFY) */
-#define GENHD_FL_SUPPRESS_PARTITION_INFO	0x0020
 #define GENHD_FL_EXT_DEVT			0x0040
 #define GENHD_FL_NO_PART			0x0200
 #define GENHD_FL_HIDDEN				0x0400
-- 
cgit v1.2.3


From 1ebe2e5f9d68e94c524aba876f27b945669a7879 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 22 Nov 2021 14:06:22 +0100
Subject: block: remove GENHD_FL_EXT_DEVT

All modern drivers can support extra partitions using the extended
dev_t.  In fact except for the ioctl method drivers never even see
partitions in normal operation.

So remove the GENHD_FL_EXT_DEVT and allow extra partitions for all
block devices that do support partitions, and require those that
do not support partitions to explicit disallow them using
GENHD_FL_NO_PART.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20211122130625.1136848-12-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/genhd.c                  |  6 +++---
 block/partitions/core.c        |  9 ++++-----
 drivers/block/amiflop.c        |  1 +
 drivers/block/ataflop.c        |  1 +
 drivers/block/brd.c            |  1 -
 drivers/block/drbd/drbd_main.c |  1 +
 drivers/block/floppy.c         |  1 +
 drivers/block/loop.c           |  1 -
 drivers/block/null_blk/main.c  |  1 -
 drivers/block/paride/pcd.c     |  1 +
 drivers/block/paride/pf.c      |  1 +
 drivers/block/pktcdvd.c        |  2 +-
 drivers/block/ps3vram.c        |  1 +
 drivers/block/rbd.c            |  6 ++----
 drivers/block/swim.c           |  1 +
 drivers/block/swim3.c          |  2 +-
 drivers/block/virtio_blk.c     |  1 -
 drivers/block/z2ram.c          |  1 +
 drivers/block/zram/zram_drv.c  |  1 +
 drivers/cdrom/gdrom.c          |  1 +
 drivers/md/dm.c                |  1 +
 drivers/md/md.c                |  5 -----
 drivers/mmc/core/block.c       |  1 -
 drivers/mtd/ubi/block.c        |  1 +
 drivers/scsi/sd.c              |  1 -
 drivers/scsi/sr.c              |  1 +
 include/linux/genhd.h          | 28 +++++-----------------------
 27 files changed, 30 insertions(+), 48 deletions(-)

(limited to 'include/linux')

diff --git a/block/genhd.c b/block/genhd.c
index 50a843ee18f6..628632537129 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -376,7 +376,7 @@ int disk_scan_partitions(struct gendisk *disk, fmode_t mode)
 {
 	struct block_device *bdev;
 
-	if (!disk_part_scan_enabled(disk))
+	if (disk->flags & GENHD_FL_NO_PART)
 		return -EINVAL;
 	if (disk->open_partitions)
 		return -EBUSY;
@@ -438,7 +438,6 @@ int __must_check device_add_disk(struct device *parent, struct gendisk *disk,
 			return ret;
 		disk->major = BLOCK_EXT_MAJOR;
 		disk->first_minor = ret;
-		disk->flags |= GENHD_FL_EXT_DEVT;
 	}
 
 	ret = disk_alloc_events(disk);
@@ -872,7 +871,8 @@ static ssize_t disk_ext_range_show(struct device *dev,
 {
 	struct gendisk *disk = dev_to_disk(dev);
 
-	return sprintf(buf, "%d\n", disk_max_parts(disk));
+	return sprintf(buf, "%d\n",
+		(disk->flags & GENHD_FL_NO_PART) ? 1 : DISK_MAX_PARTS);
 }
 
 static ssize_t disk_removable_show(struct device *dev,
diff --git a/block/partitions/core.c b/block/partitions/core.c
index 520292fee933..c2a1635922b1 100644
--- a/block/partitions/core.c
+++ b/block/partitions/core.c
@@ -98,13 +98,12 @@ static void bdev_set_nr_sectors(struct block_device *bdev, sector_t sectors)
 static struct parsed_partitions *allocate_partitions(struct gendisk *hd)
 {
 	struct parsed_partitions *state;
-	int nr;
+	int nr = DISK_MAX_PARTS;
 
 	state = kzalloc(sizeof(*state), GFP_KERNEL);
 	if (!state)
 		return NULL;
 
-	nr = disk_max_parts(hd);
 	state->parts = vzalloc(array_size(nr, sizeof(state->parts[0])));
 	if (!state->parts) {
 		kfree(state);
@@ -326,7 +325,7 @@ static struct block_device *add_partition(struct gendisk *disk, int partno,
 
 	lockdep_assert_held(&disk->open_mutex);
 
-	if (partno >= disk_max_parts(disk))
+	if (partno >= DISK_MAX_PARTS)
 		return ERR_PTR(-EINVAL);
 
 	/*
@@ -604,7 +603,7 @@ static int blk_add_partitions(struct gendisk *disk)
 	struct parsed_partitions *state;
 	int ret = -EAGAIN, p;
 
-	if (!disk_part_scan_enabled(disk))
+	if (disk->flags & GENHD_FL_NO_PART)
 		return 0;
 
 	state = check_partition(disk);
@@ -687,7 +686,7 @@ rescan:
 	 * userspace for this particular setup.
 	 */
 	if (invalidate) {
-		if (disk_part_scan_enabled(disk) ||
+		if (!(disk->flags & GENHD_FL_NO_PART) ||
 		    !(disk->flags & GENHD_FL_REMOVABLE))
 			set_capacity(disk, 0);
 	}
diff --git a/drivers/block/amiflop.c b/drivers/block/amiflop.c
index bf5c124c5452..1eec5113d0b5 100644
--- a/drivers/block/amiflop.c
+++ b/drivers/block/amiflop.c
@@ -1790,6 +1790,7 @@ static int fd_alloc_disk(int drive, int system)
 	disk->first_minor = drive + system;
 	disk->minors = 1;
 	disk->fops = &floppy_fops;
+	disk->flags |= GENHD_FL_NO_PART;
 	disk->events = DISK_EVENT_MEDIA_CHANGE;
 	if (system)
 		sprintf(disk->disk_name, "fd%d_msdos", drive);
diff --git a/drivers/block/ataflop.c b/drivers/block/ataflop.c
index bf769e6e32fe..f3ff9babdb5c 100644
--- a/drivers/block/ataflop.c
+++ b/drivers/block/ataflop.c
@@ -2000,6 +2000,7 @@ static int ataflop_alloc_disk(unsigned int drive, unsigned int type)
 	disk->minors = 1;
 	sprintf(disk->disk_name, "fd%d", drive);
 	disk->fops = &floppy_fops;
+	disk->flags |= GENHD_FL_NO_PART;
 	disk->events = DISK_EVENT_MEDIA_CHANGE;
 	disk->private_data = &unit[drive];
 	set_capacity(disk, MAX_DISK_SIZE * 2);
diff --git a/drivers/block/brd.c b/drivers/block/brd.c
index a896ee175d86..8fe2e4289dae 100644
--- a/drivers/block/brd.c
+++ b/drivers/block/brd.c
@@ -405,7 +405,6 @@ static int brd_alloc(int i)
 	disk->minors		= max_part;
 	disk->fops		= &brd_fops;
 	disk->private_data	= brd;
-	disk->flags		= GENHD_FL_EXT_DEVT;
 	strlcpy(disk->disk_name, buf, DISK_NAME_LEN);
 	set_capacity(disk, rd_size * 2);
 	
diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index 53ba2dddba6e..07b3c6093e7d 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -2734,6 +2734,7 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig
 	disk->first_minor = minor;
 	disk->minors = 1;
 	disk->fops = &drbd_ops;
+	disk->flags |= GENHD_FL_NO_PART;
 	sprintf(disk->disk_name, "drbd%d", minor);
 	disk->private_data = device;
 
diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c
index c4267da716fe..7f0a60c4079f 100644
--- a/drivers/block/floppy.c
+++ b/drivers/block/floppy.c
@@ -4503,6 +4503,7 @@ static int floppy_alloc_disk(unsigned int drive, unsigned int type)
 	disk->first_minor = TOMINOR(drive) | (type << 2);
 	disk->minors = 1;
 	disk->fops = &floppy_fops;
+	disk->flags |= GENHD_FL_NO_PART;
 	disk->events = DISK_EVENT_MEDIA_CHANGE;
 	if (type)
 		sprintf(disk->disk_name, "fd%d_type%d", drive, type);
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 7219d98c6fb8..0954ea8cf9e3 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -2033,7 +2033,6 @@ static int loop_add(int i)
 	 */
 	if (!part_shift)
 		disk->flags |= GENHD_FL_NO_PART;
-	disk->flags |= GENHD_FL_EXT_DEVT;
 	atomic_set(&lo->lo_refcnt, 0);
 	mutex_init(&lo->lo_mutex);
 	lo->lo_number		= i;
diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c
index eb17def1f265..54f7d490f8eb 100644
--- a/drivers/block/null_blk/main.c
+++ b/drivers/block/null_blk/main.c
@@ -1850,7 +1850,6 @@ static int null_gendisk_register(struct nullb *nullb)
 
 	set_capacity(disk, size);
 
-	disk->flags |= GENHD_FL_EXT_DEVT;
 	disk->major		= null_major;
 	disk->first_minor	= nullb->index;
 	disk->minors		= 1;
diff --git a/drivers/block/paride/pcd.c b/drivers/block/paride/pcd.c
index 430ee8004a51..255fd3d4b8a8 100644
--- a/drivers/block/paride/pcd.c
+++ b/drivers/block/paride/pcd.c
@@ -928,6 +928,7 @@ static int pcd_init_unit(struct pcd_unit *cd, bool autoprobe, int port,
 	disk->minors = 1;
 	strcpy(disk->disk_name, cd->name);	/* umm... */
 	disk->fops = &pcd_bdops;
+	disk->flags |= GENHD_FL_NO_PART;
 	disk->events = DISK_EVENT_MEDIA_CHANGE;
 	disk->event_flags = DISK_EVENT_FLAG_BLOCK_ON_EXCL_WRITE;
 
diff --git a/drivers/block/paride/pf.c b/drivers/block/paride/pf.c
index bf8d0ef41a0a..b84a6448a4f7 100644
--- a/drivers/block/paride/pf.c
+++ b/drivers/block/paride/pf.c
@@ -942,6 +942,7 @@ static int __init pf_init_unit(struct pf_unit *pf, bool autoprobe, int port,
 	disk->minors = 1;
 	strcpy(disk->disk_name, pf->name);
 	disk->fops = &pf_fops;
+	disk->flags |= GENHD_FL_NO_PART;
 	disk->events = DISK_EVENT_MEDIA_CHANGE;
 	disk->private_data = pf;
 
diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c
index b53f648302c1..3af0499857ec 100644
--- a/drivers/block/pktcdvd.c
+++ b/drivers/block/pktcdvd.c
@@ -2719,7 +2719,7 @@ static int pkt_setup_dev(dev_t dev, dev_t* pkt_dev)
 	disk->first_minor = idx;
 	disk->minors = 1;
 	disk->fops = &pktcdvd_ops;
-	disk->flags = GENHD_FL_REMOVABLE;
+	disk->flags = GENHD_FL_REMOVABLE | GENHD_FL_NO_PART;
 	strcpy(disk->disk_name, pd->name);
 	disk->private_data = pd;
 
diff --git a/drivers/block/ps3vram.c b/drivers/block/ps3vram.c
index c1876646a4cb..4f90819e245e 100644
--- a/drivers/block/ps3vram.c
+++ b/drivers/block/ps3vram.c
@@ -742,6 +742,7 @@ static int ps3vram_probe(struct ps3_system_bus_device *dev)
 	priv->gendisk = gendisk;
 	gendisk->major = ps3vram_major;
 	gendisk->minors = 1;
+	gendisk->flags |= GENHD_FL_NO_PART;
 	gendisk->fops = &ps3vram_fops;
 	gendisk->private_data = dev;
 	strlcpy(gendisk->disk_name, DEVICE_NAME, sizeof(gendisk->disk_name));
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index 953fa134cd3d..8f140da1efe3 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -4924,12 +4924,10 @@ static int rbd_init_disk(struct rbd_device *rbd_dev)
 		 rbd_dev->dev_id);
 	disk->major = rbd_dev->major;
 	disk->first_minor = rbd_dev->minor;
-	if (single_major) {
+	if (single_major)
 		disk->minors = (1 << RBD_SINGLE_MAJOR_PART_SHIFT);
-		disk->flags |= GENHD_FL_EXT_DEVT;
-	} else {
+	else
 		disk->minors = RBD_MINORS_PER_MAJOR;
-	}
 	disk->fops = &rbd_bd_ops;
 	disk->private_data = rbd_dev;
 
diff --git a/drivers/block/swim.c b/drivers/block/swim.c
index 821594cd1315..fef65a18d56f 100644
--- a/drivers/block/swim.c
+++ b/drivers/block/swim.c
@@ -840,6 +840,7 @@ static int swim_floppy_init(struct swim_priv *swd)
 		swd->unit[drive].disk->minors = 1;
 		sprintf(swd->unit[drive].disk->disk_name, "fd%d", drive);
 		swd->unit[drive].disk->fops = &floppy_fops;
+		swd->unit[drive].disk->flags |= GENHD_FL_NO_PART;
 		swd->unit[drive].disk->events = DISK_EVENT_MEDIA_CHANGE;
 		swd->unit[drive].disk->private_data = &swd->unit[drive];
 		set_capacity(swd->unit[drive].disk, 2880);
diff --git a/drivers/block/swim3.c b/drivers/block/swim3.c
index 4b91c9aa5892..6c39f2c9f806 100644
--- a/drivers/block/swim3.c
+++ b/drivers/block/swim3.c
@@ -1227,7 +1227,7 @@ static int swim3_attach(struct macio_dev *mdev,
 	disk->fops = &floppy_fops;
 	disk->private_data = fs;
 	disk->events = DISK_EVENT_MEDIA_CHANGE;
-	disk->flags |= GENHD_FL_REMOVABLE;
+	disk->flags |= GENHD_FL_REMOVABLE | GENHD_FL_NO_PART;
 	sprintf(disk->disk_name, "fd%d", floppy_count);
 	set_capacity(disk, 2880);
 	rc = add_disk(disk);
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 6ae38776e30e..cfa303fa7318 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -843,7 +843,6 @@ static int virtblk_probe(struct virtio_device *vdev)
 	vblk->disk->minors = 1 << PART_BITS;
 	vblk->disk->private_data = vblk;
 	vblk->disk->fops = &virtblk_fops;
-	vblk->disk->flags |= GENHD_FL_EXT_DEVT;
 	vblk->index = index;
 
 	/* configure queue flush support */
diff --git a/drivers/block/z2ram.c b/drivers/block/z2ram.c
index ccc52c935faf..7a6ed83481b8 100644
--- a/drivers/block/z2ram.c
+++ b/drivers/block/z2ram.c
@@ -327,6 +327,7 @@ static int z2ram_register_disk(int minor)
 	disk->major = Z2RAM_MAJOR;
 	disk->first_minor = minor;
 	disk->minors = 1;
+	disk->flags |= GENHD_FL_NO_PART;
 	disk->fops = &z2_fops;
 	if (minor)
 		sprintf(disk->disk_name, "z2ram%d", minor);
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index 25071126995b..f6da5293b913 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -1947,6 +1947,7 @@ static int zram_add(void)
 	zram->disk->major = zram_major;
 	zram->disk->first_minor = device_id;
 	zram->disk->minors = 1;
+	zram->disk->flags |= GENHD_FL_NO_PART;
 	zram->disk->fops = &zram_devops;
 	zram->disk->private_data = zram;
 	snprintf(zram->disk->disk_name, 16, "zram%d", device_id);
diff --git a/drivers/cdrom/gdrom.c b/drivers/cdrom/gdrom.c
index d50cc1fd34d5..faead41709bc 100644
--- a/drivers/cdrom/gdrom.c
+++ b/drivers/cdrom/gdrom.c
@@ -719,6 +719,7 @@ static void probe_gdrom_setupdisk(void)
 	gd.disk->major = gdrom_major;
 	gd.disk->first_minor = 1;
 	gd.disk->minors = 1;
+	gd.disk->flags |= GENHD_FL_NO_PART;
 	strcpy(gd.disk->disk_name, GDROM_DEV_NAME);
 }
 
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 662742a310cb..280918cdcabd 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1778,6 +1778,7 @@ static struct mapped_device *alloc_dev(int minor)
 	md->disk->major = _major;
 	md->disk->first_minor = minor;
 	md->disk->minors = 1;
+	md->disk->flags |= GENHD_FL_NO_PART;
 	md->disk->fops = &dm_blk_dops;
 	md->disk->queue = md->queue;
 	md->disk->private_data = md;
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 5111ed966947..7fbf6f0ac01b 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -5707,11 +5707,6 @@ static int md_alloc(dev_t dev, char *name)
 	mddev->queue = disk->queue;
 	blk_set_stacking_limits(&mddev->queue->limits);
 	blk_queue_write_cache(mddev->queue, true, true);
-	/* Allow extended partitions.  This makes the
-	 * 'mdp' device redundant, but we can't really
-	 * remove it now.
-	 */
-	disk->flags |= GENHD_FL_EXT_DEVT;
 	disk->events |= DISK_EVENT_MEDIA_CHANGE;
 	mddev->gendisk = disk;
 	error = add_disk(disk);
diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c
index 2dd93d49d822..5e0960560eab 100644
--- a/drivers/mmc/core/block.c
+++ b/drivers/mmc/core/block.c
@@ -2395,7 +2395,6 @@ static struct mmc_blk_data *mmc_blk_alloc_req(struct mmc_card *card,
 	md->disk->private_data = md;
 	md->parent = parent;
 	set_disk_ro(md->disk, md->read_only || default_ro);
-	md->disk->flags = GENHD_FL_EXT_DEVT;
 	if (area_type & (MMC_BLK_DATA_AREA_RPMB | MMC_BLK_DATA_AREA_BOOT))
 		md->disk->flags |= GENHD_FL_NO_PART;
 
diff --git a/drivers/mtd/ubi/block.c b/drivers/mtd/ubi/block.c
index 302426ab30f8..a78fdf3b30f7 100644
--- a/drivers/mtd/ubi/block.c
+++ b/drivers/mtd/ubi/block.c
@@ -430,6 +430,7 @@ int ubiblock_create(struct ubi_volume_info *vi)
 		ret = -ENODEV;
 		goto out_cleanup_disk;
 	}
+	gd->flags |= GENHD_FL_NO_PART;
 	gd->private_data = dev;
 	sprintf(gd->disk_name, "ubiblock%d_%d", dev->ubi_num, dev->vol_id);
 	set_capacity(gd, disk_capacity);
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 65875a598d62..bba1f5dafd38 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -3566,7 +3566,6 @@ static int sd_probe(struct device *dev)
 
 	sd_revalidate_disk(gd);
 
-	gd->flags = GENHD_FL_EXT_DEVT;
 	if (sdp->removable) {
 		gd->flags |= GENHD_FL_REMOVABLE;
 		gd->events |= DISK_EVENT_MEDIA_CHANGE;
diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c
index 6646797a7756..cf093387e42a 100644
--- a/drivers/scsi/sr.c
+++ b/drivers/scsi/sr.c
@@ -684,6 +684,7 @@ static int sr_probe(struct device *dev)
 	disk->minors = 1;
 	sprintf(disk->disk_name, "sr%d", minor);
 	disk->fops = &sr_bdops;
+	disk->flags |= GENHD_FL_NO_PART;
 	disk->events = DISK_EVENT_MEDIA_CHANGE | DISK_EVENT_EJECT_REQUEST;
 	disk->event_flags = DISK_EVENT_FLAG_POLL | DISK_EVENT_FLAG_UEVENT |
 				DISK_EVENT_FLAG_BLOCK_ON_EXCL_WRITE;
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 64a2f33ae9ea..b8ced80178d6 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -46,11 +46,6 @@ struct partition_meta_info {
  * Must not be set for devices which are removed entirely when the
  * media is removed.
  *
- * ``GENHD_FL_EXT_DEVT`` (0x0040): the driver supports extended
- * dynamic ``dev_t``, i.e. it wants extended device numbers
- * (``BLOCK_EXT_MAJOR``).
- * This affects the maximum number of partitions.
- *
  * ``GENHD_FL_NO_PART`` (0x0200): partition support is disabled.
  * The kernel will not scan for partitions from add_disk, and users
  * can't add partitions manually.
@@ -64,7 +59,6 @@ struct partition_meta_info {
 #define GENHD_FL_REMOVABLE			0x0001
 /* 2 is unused (used to be GENHD_FL_DRIVERFS) */
 /* 4 is unused (used to be GENHD_FL_MEDIA_CHANGE_NOTIFY) */
-#define GENHD_FL_EXT_DEVT			0x0040
 #define GENHD_FL_NO_PART			0x0200
 #define GENHD_FL_HIDDEN				0x0400
 
@@ -94,13 +88,13 @@ struct blk_integrity {
 };
 
 struct gendisk {
-	/* major, first_minor and minors are input parameters only,
-	 * don't use directly.  Use disk_devt() and disk_max_parts().
+	/*
+	 * major/first_minor/minors should not be set by any new driver, the
+	 * block core will take care of allocating them automatically.
 	 */
-	int major;			/* major number of driver */
+	int major;
 	int first_minor;
-	int minors;                     /* maximum number of minors, =1 for
-                                         * disks that can't be partitioned. */
+	int minors;
 
 	char disk_name[DISK_NAME_LEN];	/* name of major driver */
 
@@ -164,18 +158,6 @@ static inline bool disk_live(struct gendisk *disk)
 #define disk_to_cdi(disk)	NULL
 #endif
 
-static inline int disk_max_parts(struct gendisk *disk)
-{
-	if (disk->flags & GENHD_FL_EXT_DEVT)
-		return DISK_MAX_PARTS;
-	return disk->minors;
-}
-
-static inline bool disk_part_scan_enabled(struct gendisk *disk)
-{
-	return disk_max_parts(disk) > 1 && !(disk->flags & GENHD_FL_NO_PART);
-}
-
 static inline dev_t disk_devt(struct gendisk *disk)
 {
 	return MKDEV(disk->major, disk->first_minor);
-- 
cgit v1.2.3


From 430cc5d3ab4d0ba0bd011cfbb0035e46ba92920c Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 22 Nov 2021 14:06:24 +0100
Subject: block: cleanup the GENHD_FL_* definitions

Switch to an enum and tidy up the documentation.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20211122130625.1136848-14-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/genhd.h | 32 ++++++++++++++------------------
 1 file changed, 14 insertions(+), 18 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index b8ced80178d6..6906a45bc761 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -39,28 +39,24 @@ struct partition_meta_info {
 /**
  * DOC: genhd capability flags
  *
- * ``GENHD_FL_REMOVABLE`` (0x0001): indicates that the block device
- * gives access to removable media.
- * When set, the device remains present even when media is not
- * inserted.
- * Must not be set for devices which are removed entirely when the
+ * ``GENHD_FL_REMOVABLE``: indicates that the block device gives access to
+ * removable media.  When set, the device remains present even when media is not
+ * inserted.  Shall not be set for devices which are removed entirely when the
  * media is removed.
  *
- * ``GENHD_FL_NO_PART`` (0x0200): partition support is disabled.
- * The kernel will not scan for partitions from add_disk, and users
- * can't add partitions manually.
+ * ``GENHD_FL_HIDDEN``: the block device is hidden; it doesn't produce events,
+ * doesn't appear in sysfs, and can't be opened from userspace or using
+ * blkdev_get*. Used for the underlying components of multipath devices.
+ *
+ * ``GENHD_FL_NO_PART``: partition support is disabled.  The kernel will not
+ * scan for partitions from add_disk, and users can't add partitions manually.
  *
- * ``GENHD_FL_HIDDEN`` (0x0400): the block device is hidden; it
- * doesn't produce events, doesn't appear in sysfs, and doesn't have
- * an associated ``bdev``.
- * Implies ``GENHD_FL_NO_PART``.
- * Used for multipath devices.
  */
-#define GENHD_FL_REMOVABLE			0x0001
-/* 2 is unused (used to be GENHD_FL_DRIVERFS) */
-/* 4 is unused (used to be GENHD_FL_MEDIA_CHANGE_NOTIFY) */
-#define GENHD_FL_NO_PART			0x0200
-#define GENHD_FL_HIDDEN				0x0400
+enum {
+	GENHD_FL_REMOVABLE			= 1 << 0,
+	GENHD_FL_HIDDEN				= 1 << 1,
+	GENHD_FL_NO_PART			= 1 << 2,
+};
 
 enum {
 	DISK_EVENT_MEDIA_CHANGE			= 1 << 0, /* media changed */
-- 
cgit v1.2.3


From 48b5c1fbcd8c5bc6b91a56399a5257b801391dd8 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Sat, 13 Nov 2021 14:03:26 -0700
Subject: block: only allocate poll_stats if there's a user of them

This is essentially never used, yet it's about 1/3rd of the total
queue size. Allocate it when needed, and don't embed it in the queue.

Kill the queue flag for this while at it, since we can just check the
assigned pointer now.

Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-mq-debugfs.c |  1 -
 block/blk-mq.c         | 10 ++++------
 block/blk-stat.c       | 18 ++++++++++++++++++
 block/blk-stat.h       |  1 +
 block/blk-sysfs.c      |  3 ++-
 include/linux/blkdev.h |  3 +--
 6 files changed, 26 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c
index 4f2cf8399f3d..f4022b198580 100644
--- a/block/blk-mq-debugfs.c
+++ b/block/blk-mq-debugfs.c
@@ -122,7 +122,6 @@ static const char *const blk_queue_flag_name[] = {
 	QUEUE_FLAG_NAME(FUA),
 	QUEUE_FLAG_NAME(DAX),
 	QUEUE_FLAG_NAME(STATS),
-	QUEUE_FLAG_NAME(POLL_STATS),
 	QUEUE_FLAG_NAME(REGISTERED),
 	QUEUE_FLAG_NAME(QUIESCED),
 	QUEUE_FLAG_NAME(PCI_P2PDMA),
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 3af88ffc9e2c..7cd408408a37 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -4581,11 +4581,10 @@ EXPORT_SYMBOL_GPL(blk_mq_update_nr_hw_queues);
 /* Enable polling stats and return whether they were already enabled. */
 static bool blk_poll_stats_enable(struct request_queue *q)
 {
-	if (test_bit(QUEUE_FLAG_POLL_STATS, &q->queue_flags) ||
-	    blk_queue_flag_test_and_set(QUEUE_FLAG_POLL_STATS, q))
+	if (q->poll_stat)
 		return true;
-	blk_stat_add_callback(q, q->poll_cb);
-	return false;
+
+	return blk_stats_alloc_enable(q);
 }
 
 static void blk_mq_poll_stats_start(struct request_queue *q)
@@ -4594,8 +4593,7 @@ static void blk_mq_poll_stats_start(struct request_queue *q)
 	 * We don't arm the callback if polling stats are not enabled or the
 	 * callback is already active.
 	 */
-	if (!test_bit(QUEUE_FLAG_POLL_STATS, &q->queue_flags) ||
-	    blk_stat_is_active(q->poll_cb))
+	if (!q->poll_stat || blk_stat_is_active(q->poll_cb))
 		return;
 
 	blk_stat_activate_msecs(q->poll_cb, 100);
diff --git a/block/blk-stat.c b/block/blk-stat.c
index ae3dd1fb8e61..efb2a80db906 100644
--- a/block/blk-stat.c
+++ b/block/blk-stat.c
@@ -219,3 +219,21 @@ void blk_free_queue_stats(struct blk_queue_stats *stats)
 
 	kfree(stats);
 }
+
+bool blk_stats_alloc_enable(struct request_queue *q)
+{
+	struct blk_rq_stat *poll_stat;
+
+	poll_stat = kcalloc(BLK_MQ_POLL_STATS_BKTS, sizeof(*poll_stat),
+				GFP_ATOMIC);
+	if (!poll_stat)
+		return false;
+
+	if (cmpxchg(&q->poll_stat, NULL, poll_stat) != NULL) {
+		kfree(poll_stat);
+		return true;
+	}
+
+	blk_stat_add_callback(q, q->poll_cb);
+	return false;
+}
diff --git a/block/blk-stat.h b/block/blk-stat.h
index 17b47a86eefb..58f029af49e5 100644
--- a/block/blk-stat.h
+++ b/block/blk-stat.h
@@ -64,6 +64,7 @@ struct blk_stat_callback {
 
 struct blk_queue_stats *blk_alloc_queue_stats(void);
 void blk_free_queue_stats(struct blk_queue_stats *);
+bool blk_stats_alloc_enable(struct request_queue *q);
 
 void blk_stat_add(struct request *rq, u64 now);
 
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index cd75b0f73dc6..c079be1c58a3 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -785,11 +785,12 @@ static void blk_release_queue(struct kobject *kobj)
 
 	might_sleep();
 
-	if (test_bit(QUEUE_FLAG_POLL_STATS, &q->queue_flags))
+	if (q->poll_stat)
 		blk_stat_remove_callback(q, q->poll_cb);
 	blk_stat_free_callback(q->poll_cb);
 
 	blk_free_queue_stats(q->stats);
+	kfree(q->poll_stat);
 
 	blk_exit_queue(q);
 
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index bd4370baccca..74118e67f649 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -267,7 +267,7 @@ struct request_queue {
 	int			poll_nsec;
 
 	struct blk_stat_callback	*poll_cb;
-	struct blk_rq_stat	poll_stat[BLK_MQ_POLL_STATS_BKTS];
+	struct blk_rq_stat	*poll_stat;
 
 	struct timer_list	timeout;
 	struct work_struct	timeout_work;
@@ -397,7 +397,6 @@ struct request_queue {
 #define QUEUE_FLAG_FUA		18	/* device supports FUA writes */
 #define QUEUE_FLAG_DAX		19	/* device supports DAX */
 #define QUEUE_FLAG_STATS	20	/* track IO start and completion times */
-#define QUEUE_FLAG_POLL_STATS	21	/* collecting stats for hybrid polling */
 #define QUEUE_FLAG_REGISTERED	22	/* queue has been registered to a disk */
 #define QUEUE_FLAG_QUIESCED	24	/* queue has been quiesced */
 #define QUEUE_FLAG_PCI_P2PDMA	25	/* device supports PCI p2p requests */
-- 
cgit v1.2.3


From 72cd9df2ef788d88c138d51223a01ca6281f232d Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Tue, 23 Nov 2021 17:37:33 -0800
Subject: blk-crypto: remove blk_crypto_unregister()

This function is trivial and is only used in one place.  Having this
function is misleading because it implies that blk_crypto_register()
needs to be paired with blk_crypto_unregister(), which is not the case.
Just set disk->queue->crypto_profile to NULL directly.

Signed-off-by: Eric Biggers <ebiggers@google.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20211124013733.347612-1-ebiggers@kernel.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-crypto-profile.c | 5 -----
 block/blk-integrity.c      | 2 +-
 include/linux/blkdev.h     | 4 ----
 3 files changed, 1 insertion(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-crypto-profile.c b/block/blk-crypto-profile.c
index 605ba0626a5c..96c511967386 100644
--- a/block/blk-crypto-profile.c
+++ b/block/blk-crypto-profile.c
@@ -463,11 +463,6 @@ bool blk_crypto_register(struct blk_crypto_profile *profile,
 }
 EXPORT_SYMBOL_GPL(blk_crypto_register);
 
-void blk_crypto_unregister(struct request_queue *q)
-{
-	q->crypto_profile = NULL;
-}
-
 /**
  * blk_crypto_intersect_capabilities() - restrict supported crypto capabilities
  *					 by child device
diff --git a/block/blk-integrity.c b/block/blk-integrity.c
index d670d54e5f7a..69eed260a823 100644
--- a/block/blk-integrity.c
+++ b/block/blk-integrity.c
@@ -411,7 +411,7 @@ void blk_integrity_register(struct gendisk *disk, struct blk_integrity *template
 #ifdef CONFIG_BLK_INLINE_ENCRYPTION
 	if (disk->queue->crypto_profile) {
 		pr_warn("blk-integrity: Integrity and hardware inline encryption are not supported together. Disabling hardware inline encryption.\n");
-		blk_crypto_unregister(disk->queue);
+		disk->queue->crypto_profile = NULL;
 	}
 #endif
 }
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 74118e67f649..0a4416ef4fbf 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1170,8 +1170,6 @@ int kblockd_mod_delayed_work_on(int cpu, struct delayed_work *dwork, unsigned lo
 bool blk_crypto_register(struct blk_crypto_profile *profile,
 			 struct request_queue *q);
 
-void blk_crypto_unregister(struct request_queue *q);
-
 #else /* CONFIG_BLK_INLINE_ENCRYPTION */
 
 static inline bool blk_crypto_register(struct blk_crypto_profile *profile,
@@ -1180,8 +1178,6 @@ static inline bool blk_crypto_register(struct blk_crypto_profile *profile,
 	return true;
 }
 
-static inline void blk_crypto_unregister(struct request_queue *q) { }
-
 #endif /* CONFIG_BLK_INLINE_ENCRYPTION */
 
 enum blk_unique_id {
-- 
cgit v1.2.3


From e8dc17e2893b4107366004810ca2a4acf1fc8563 Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Mon, 25 Oct 2021 09:06:57 +0200
Subject: blk-mq: Add blk_mq_complete_request_direct()

Add blk_mq_complete_request_direct() which completes the block request
directly instead deferring it to softirq for single queue devices.

This is useful for devices which complete the requests in preemptible
context and raising softirq from means scheduling ksoftirqd.

Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20211025070658.1565848-2-bigeasy@linutronix.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/blk-mq.h | 11 +++++++++++
 1 file changed, 11 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 308edc2a4925..d952c3442261 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -752,6 +752,17 @@ static inline void blk_mq_set_request_complete(struct request *rq)
 	WRITE_ONCE(rq->state, MQ_RQ_COMPLETE);
 }
 
+/*
+ * Complete the request directly instead of deferring it to softirq or
+ * completing it another CPU. Useful in preemptible instead of an interrupt.
+ */
+static inline void blk_mq_complete_request_direct(struct request *rq,
+		   void (*complete)(struct request *rq))
+{
+	WRITE_ONCE(rq->state, MQ_RQ_COMPLETE);
+	complete(rq);
+}
+
 void blk_mq_start_request(struct request *rq);
 void blk_mq_end_request(struct request *rq, blk_status_t error);
 void __blk_mq_end_request(struct request *rq, blk_status_t error);
-- 
cgit v1.2.3


From 88c9a2ce520ba381bb70658c80ec704f4d60f728 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 26 Nov 2021 12:58:05 +0100
Subject: fork: move copy_io to block/blk-ioc.c

Move the copying of the I/O context to the block layer as that is where
we can use the proper low-level interfaces.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20211126115817.2087431-3-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-ioc.c           | 27 +++++++++++++++++++++++++++
 include/linux/iocontext.h | 23 +++++++++++++----------
 kernel/fork.c             | 26 --------------------------
 3 files changed, 40 insertions(+), 36 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-ioc.c b/block/blk-ioc.c
index 70c99e85aee5..3b31cfad4b75 100644
--- a/block/blk-ioc.c
+++ b/block/blk-ioc.c
@@ -322,6 +322,33 @@ struct io_context *get_task_io_context(struct task_struct *task,
 	return NULL;
 }
 
+int __copy_io(unsigned long clone_flags, struct task_struct *tsk)
+{
+	struct io_context *ioc = current->io_context;
+	struct io_context *new_ioc;
+
+	/*
+	 * Share io context with parent, if CLONE_IO is set
+	 */
+	if (clone_flags & CLONE_IO) {
+		get_io_context_active(ioc);
+
+		WARN_ON_ONCE(atomic_read(&ioc->nr_tasks) <= 0);
+		atomic_inc(&ioc->nr_tasks);
+
+		tsk->io_context = ioc;
+	} else if (ioprio_valid(ioc->ioprio)) {
+		new_ioc = get_task_io_context(tsk, GFP_KERNEL, NUMA_NO_NODE);
+		if (unlikely(!new_ioc))
+			return -ENOMEM;
+
+		new_ioc->ioprio = ioc->ioprio;
+		put_io_context(new_ioc);
+	}
+
+	return 0;
+}
+
 /**
  * ioc_lookup_icq - lookup io_cq from ioc
  * @ioc: the associated io_context
diff --git a/include/linux/iocontext.h b/include/linux/iocontext.h
index 0a9dc40b7be8..bcd47d104d8e 100644
--- a/include/linux/iocontext.h
+++ b/include/linux/iocontext.h
@@ -129,14 +129,6 @@ static inline void get_io_context_active(struct io_context *ioc)
 	atomic_inc(&ioc->active_ref);
 }
 
-static inline void ioc_task_link(struct io_context *ioc)
-{
-	get_io_context_active(ioc);
-
-	WARN_ON_ONCE(atomic_read(&ioc->nr_tasks) <= 0);
-	atomic_inc(&ioc->nr_tasks);
-}
-
 struct task_struct;
 #ifdef CONFIG_BLOCK
 void put_io_context(struct io_context *ioc);
@@ -144,10 +136,21 @@ void put_io_context_active(struct io_context *ioc);
 void exit_io_context(struct task_struct *task);
 struct io_context *get_task_io_context(struct task_struct *task,
 				       gfp_t gfp_flags, int node);
+int __copy_io(unsigned long clone_flags, struct task_struct *tsk);
+static inline int copy_io(unsigned long clone_flags, struct task_struct *tsk)
+{
+	if (!current->io_context)
+		return 0;
+	return __copy_io(clone_flags, tsk);
+}
 #else
 struct io_context;
 static inline void put_io_context(struct io_context *ioc) { }
 static inline void exit_io_context(struct task_struct *task) { }
-#endif
+static inline int copy_io(unsigned long clone_flags, struct task_struct *tsk)
+{
+	return 0;
+}
+#endif /* CONFIG_BLOCK */
 
-#endif
+#endif /* IOCONTEXT_H */
diff --git a/kernel/fork.c b/kernel/fork.c
index 3244cc56b697..3161d7980155 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1556,32 +1556,6 @@ out:
 	return error;
 }
 
-static int copy_io(unsigned long clone_flags, struct task_struct *tsk)
-{
-#ifdef CONFIG_BLOCK
-	struct io_context *ioc = current->io_context;
-	struct io_context *new_ioc;
-
-	if (!ioc)
-		return 0;
-	/*
-	 * Share io context with parent, if CLONE_IO is set
-	 */
-	if (clone_flags & CLONE_IO) {
-		ioc_task_link(ioc);
-		tsk->io_context = ioc;
-	} else if (ioprio_valid(ioc->ioprio)) {
-		new_ioc = get_task_io_context(tsk, GFP_KERNEL, NUMA_NO_NODE);
-		if (unlikely(!new_ioc))
-			return -ENOMEM;
-
-		new_ioc->ioprio = ioc->ioprio;
-		put_io_context(new_ioc);
-	}
-#endif
-	return 0;
-}
-
 static int copy_sighand(unsigned long clone_flags, struct task_struct *tsk)
 {
 	struct sighand_struct *sig;
-- 
cgit v1.2.3


From 3304742562d27fb87a6d8291cc48824dd20f6964 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 26 Nov 2021 12:58:09 +0100
Subject: block: mark put_io_context_active static

Signed-off-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20211126115817.2087431-7-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-ioc.c           | 2 +-
 include/linux/iocontext.h | 1 -
 2 files changed, 1 insertion(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-ioc.c b/block/blk-ioc.c
index 3b31cfad4b75..f3ff495756cb 100644
--- a/block/blk-ioc.c
+++ b/block/blk-ioc.c
@@ -175,7 +175,7 @@ void put_io_context(struct io_context *ioc)
  * Undo get_io_context_active().  If active reference reaches zero after
  * put, @ioc can never issue further IOs and ioscheds are notified.
  */
-void put_io_context_active(struct io_context *ioc)
+static void put_io_context_active(struct io_context *ioc)
 {
 	struct io_cq *icq;
 
diff --git a/include/linux/iocontext.h b/include/linux/iocontext.h
index bcd47d104d8e..3ba45953d522 100644
--- a/include/linux/iocontext.h
+++ b/include/linux/iocontext.h
@@ -132,7 +132,6 @@ static inline void get_io_context_active(struct io_context *ioc)
 struct task_struct;
 #ifdef CONFIG_BLOCK
 void put_io_context(struct io_context *ioc);
-void put_io_context_active(struct io_context *ioc);
 void exit_io_context(struct task_struct *task);
 struct io_context *get_task_io_context(struct task_struct *task,
 				       gfp_t gfp_flags, int node);
-- 
cgit v1.2.3


From 50569c24be61eafb3efa06e2a3ccd447f75ae1b0 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 26 Nov 2021 12:58:12 +0100
Subject: block: remove get_io_context_active

Fold it into it's only caller, and remove a lof of the debug checks
that are not needed.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20211126115817.2087431-10-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-ioc.c           |  8 +++-----
 include/linux/iocontext.h | 16 ----------------
 2 files changed, 3 insertions(+), 21 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-ioc.c b/block/blk-ioc.c
index 3ba15c867dfa..cc4eb2ba87f7 100644
--- a/block/blk-ioc.c
+++ b/block/blk-ioc.c
@@ -173,7 +173,7 @@ EXPORT_SYMBOL_GPL(put_io_context);
  * put_io_context_active - put active reference on ioc
  * @ioc: ioc of interest
  *
- * Undo get_io_context_active().  If active reference reaches zero after
+ * Put an active reference to an ioc.  If active reference reaches zero after
  * put, @ioc can never issue further IOs and ioscheds are notified.
  */
 static void put_io_context_active(struct io_context *ioc)
@@ -333,11 +333,9 @@ int __copy_io(unsigned long clone_flags, struct task_struct *tsk)
 	 * Share io context with parent, if CLONE_IO is set
 	 */
 	if (clone_flags & CLONE_IO) {
-		get_io_context_active(ioc);
-
-		WARN_ON_ONCE(atomic_read(&ioc->nr_tasks) <= 0);
+		atomic_long_inc(&ioc->refcount);
+		atomic_inc(&ioc->active_ref);
 		atomic_inc(&ioc->nr_tasks);
-
 		tsk->io_context = ioc;
 	} else if (ioprio_valid(ioc->ioprio)) {
 		new_ioc = get_task_io_context(tsk, GFP_KERNEL, NUMA_NO_NODE);
diff --git a/include/linux/iocontext.h b/include/linux/iocontext.h
index 3ba45953d522..c1229fbd6691 100644
--- a/include/linux/iocontext.h
+++ b/include/linux/iocontext.h
@@ -113,22 +113,6 @@ struct io_context {
 	struct work_struct release_work;
 };
 
-/**
- * get_io_context_active - get active reference on ioc
- * @ioc: ioc of interest
- *
- * Only iocs with active reference can issue new IOs.  This function
- * acquires an active reference on @ioc.  The caller must already have an
- * active reference on @ioc.
- */
-static inline void get_io_context_active(struct io_context *ioc)
-{
-	WARN_ON_ONCE(atomic_long_read(&ioc->refcount) <= 0);
-	WARN_ON_ONCE(atomic_read(&ioc->active_ref) <= 0);
-	atomic_long_inc(&ioc->refcount);
-	atomic_inc(&ioc->active_ref);
-}
-
 struct task_struct;
 #ifdef CONFIG_BLOCK
 void put_io_context(struct io_context *ioc);
-- 
cgit v1.2.3


From f3fa33acca9f0058157214800f68b10d8e71ab7a Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 26 Nov 2021 13:18:00 +0100
Subject: block: remove the ->rq_disk field in struct request

Just use the disk attached to the request_queue instead.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Link: https://lore.kernel.org/r/20211126121802.2090656-4-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-flush.c                |  3 +--
 block/blk-mq.c                   | 14 ++++++--------
 block/blk.h                      |  2 +-
 drivers/block/amiflop.c          |  2 +-
 drivers/block/ataflop.c          |  6 +++---
 drivers/block/floppy.c           |  6 +++---
 drivers/block/null_blk/trace.h   |  2 +-
 drivers/block/paride/pcd.c       |  2 +-
 drivers/block/paride/pd.c        |  4 ++--
 drivers/block/paride/pf.c        |  4 ++--
 drivers/block/rnbd/rnbd-clt.c    |  4 ++--
 drivers/block/sunvdc.c           |  2 +-
 drivers/md/dm-mpath.c            |  1 -
 drivers/mmc/core/block.c         |  2 +-
 drivers/nvme/host/fault_inject.c |  2 +-
 drivers/nvme/host/trace.h        |  6 +++---
 drivers/scsi/scsi_lib.c          |  3 ++-
 drivers/scsi/scsi_logging.c      |  4 +++-
 drivers/scsi/sd.c                | 24 ++++++++++++------------
 drivers/scsi/sd_zbc.c            |  8 ++++----
 drivers/scsi/sr.c                |  4 ++--
 drivers/scsi/virtio_scsi.c       |  2 +-
 drivers/usb/storage/transport.c  |  2 +-
 include/linux/blk-mq.h           |  4 ----
 include/scsi/scsi_cmnd.h         |  2 +-
 include/scsi/scsi_device.h       |  4 ++--
 include/trace/events/block.h     |  8 ++++----
 kernel/trace/blktrace.c          |  2 +-
 28 files changed, 62 insertions(+), 67 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-flush.c b/block/blk-flush.c
index 902e80e48e4a..fd5187a0898d 100644
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@@ -145,7 +145,7 @@ static void blk_flush_queue_rq(struct request *rq, bool add_front)
 
 static void blk_account_io_flush(struct request *rq)
 {
-	struct block_device *part = rq->rq_disk->part0;
+	struct block_device *part = rq->q->disk->part0;
 
 	part_stat_lock();
 	part_stat_inc(part, ios[STAT_FLUSH]);
@@ -339,7 +339,6 @@ static void blk_kick_flush(struct request_queue *q, struct blk_flush_queue *fq,
 	flush_rq->cmd_flags = REQ_OP_FLUSH | REQ_PREFLUSH;
 	flush_rq->cmd_flags |= (flags & REQ_DRV) | (flags & REQ_FAILFAST_MASK);
 	flush_rq->rq_flags |= RQF_FLUSH_SEQ;
-	flush_rq->rq_disk = first_rq->rq_disk;
 	flush_rq->end_io = flush_end_io;
 	/*
 	 * Order WRITE ->end_io and WRITE rq->ref, and its pair is the one
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 3e67662f7801..f1abfd2e24f7 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -377,7 +377,6 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data,
 		rq->start_time_ns = ktime_get_ns();
 	else
 		rq->start_time_ns = 0;
-	rq->rq_disk = NULL;
 	rq->part = NULL;
 #ifdef CONFIG_BLK_RQ_ALLOC_TIME
 	rq->alloc_time_ns = alloc_time_ns;
@@ -659,7 +658,7 @@ void blk_mq_free_plug_rqs(struct blk_plug *plug)
 void blk_dump_rq_flags(struct request *rq, char *msg)
 {
 	printk(KERN_INFO "%s: dev %s: flags=%llx\n", msg,
-		rq->rq_disk ? rq->rq_disk->disk_name : "?",
+		rq->q->disk ? rq->q->disk->disk_name : "?",
 		(unsigned long long) rq->cmd_flags);
 
 	printk(KERN_INFO "  sector %llu, nr/cnr %u/%u\n",
@@ -712,7 +711,7 @@ static void blk_print_req_error(struct request *req, blk_status_t status)
 		"%s error, dev %s, sector %llu op 0x%x:(%s) flags 0x%x "
 		"phys_seg %u prio class %u\n",
 		blk_status_to_str(status),
-		req->rq_disk ? req->rq_disk->disk_name : "?",
+		req->q->disk ? req->q->disk->disk_name : "?",
 		blk_rq_pos(req), req_op(req), blk_op_str(req_op(req)),
 		req->cmd_flags & ~REQ_OP_MASK,
 		req->nr_phys_segments,
@@ -853,8 +852,8 @@ static void __blk_account_io_start(struct request *rq)
 	/* passthrough requests can hold bios that do not have ->bi_bdev set */
 	if (rq->bio && rq->bio->bi_bdev)
 		rq->part = rq->bio->bi_bdev;
-	else
-		rq->part = rq->rq_disk->part0;
+	else if (rq->q->disk)
+		rq->part = rq->q->disk->part0;
 
 	part_stat_lock();
 	update_io_ticks(rq->part, jiffies, false);
@@ -1172,7 +1171,6 @@ void blk_execute_rq_nowait(struct gendisk *bd_disk, struct request *rq,
 	WARN_ON(irqs_disabled());
 	WARN_ON(!blk_rq_is_passthrough(rq));
 
-	rq->rq_disk = bd_disk;
 	rq->end_io = done;
 
 	blk_account_io_start(rq);
@@ -2902,8 +2900,8 @@ blk_status_t blk_insert_cloned_request(struct request_queue *q, struct request *
 	if (ret != BLK_STS_OK)
 		return ret;
 
-	if (rq->rq_disk &&
-	    should_fail_request(rq->rq_disk->part0, blk_rq_bytes(rq)))
+	if (rq->q->disk &&
+	    should_fail_request(rq->q->disk->part0, blk_rq_bytes(rq)))
 		return BLK_STS_IOERR;
 
 	if (blk_crypto_insert_cloned_request(rq))
diff --git a/block/blk.h b/block/blk.h
index 3be0fdf76c9a..a55d82c3d1c2 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -324,7 +324,7 @@ int blk_dev_init(void);
  */
 static inline bool blk_do_io_stat(struct request *rq)
 {
-	return (rq->rq_flags & RQF_IO_STAT) && rq->rq_disk;
+	return (rq->rq_flags & RQF_IO_STAT) && rq->q->disk;
 }
 
 void update_io_ticks(struct block_device *part, unsigned long now, bool end);
diff --git a/drivers/block/amiflop.c b/drivers/block/amiflop.c
index 1eec5113d0b5..5a566f2fd533 100644
--- a/drivers/block/amiflop.c
+++ b/drivers/block/amiflop.c
@@ -1505,7 +1505,7 @@ static blk_status_t amiflop_queue_rq(struct blk_mq_hw_ctx *hctx,
 				     const struct blk_mq_queue_data *bd)
 {
 	struct request *rq = bd->rq;
-	struct amiga_floppy_struct *floppy = rq->rq_disk->private_data;
+	struct amiga_floppy_struct *floppy = rq->q->disk->private_data;
 	blk_status_t err;
 
 	if (!spin_trylock_irq(&amiflop_lock))
diff --git a/drivers/block/ataflop.c b/drivers/block/ataflop.c
index f3ff9babdb5c..5d819a466e2f 100644
--- a/drivers/block/ataflop.c
+++ b/drivers/block/ataflop.c
@@ -1502,7 +1502,7 @@ static void setup_req_params( int drive )
 static blk_status_t ataflop_queue_rq(struct blk_mq_hw_ctx *hctx,
 				     const struct blk_mq_queue_data *bd)
 {
-	struct atari_floppy_struct *floppy = bd->rq->rq_disk->private_data;
+	struct atari_floppy_struct *floppy = bd->rq->q->disk->private_data;
 	int drive = floppy - unit;
 	int type = floppy->type;
 
@@ -1538,7 +1538,7 @@ static blk_status_t ataflop_queue_rq(struct blk_mq_hw_ctx *hctx,
 		if (!UDT) {
 			Probing = 1;
 			UDT = atari_disk_type + StartDiskType[DriveType];
-			set_capacity(bd->rq->rq_disk, UDT->blocks);
+			set_capacity(bd->rq->q->disk, UDT->blocks);
 			UD.autoprobe = 1;
 		}
 	} 
@@ -1558,7 +1558,7 @@ static blk_status_t ataflop_queue_rq(struct blk_mq_hw_ctx *hctx,
 		}
 		type = minor2disktype[type].index;
 		UDT = &atari_disk_type[type];
-		set_capacity(bd->rq->rq_disk, UDT->blocks);
+		set_capacity(bd->rq->q->disk, UDT->blocks);
 		UD.autoprobe = 0;
 	}
 
diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c
index 7f0a60c4079f..0c638de25023 100644
--- a/drivers/block/floppy.c
+++ b/drivers/block/floppy.c
@@ -2259,7 +2259,7 @@ static int do_format(int drive, struct format_descr *tmp_format_req)
 static void floppy_end_request(struct request *req, blk_status_t error)
 {
 	unsigned int nr_sectors = current_count_sectors;
-	unsigned int drive = (unsigned long)req->rq_disk->private_data;
+	unsigned int drive = (unsigned long)req->q->disk->private_data;
 
 	/* current_count_sectors can be zero if transfer failed */
 	if (error)
@@ -2550,7 +2550,7 @@ static int make_raw_rw_request(void)
 	if (WARN(max_buffer_sectors == 0, "VFS: Block I/O scheduled on unopened device\n"))
 		return 0;
 
-	set_fdc((long)current_req->rq_disk->private_data);
+	set_fdc((long)current_req->q->disk->private_data);
 
 	raw_cmd = &default_raw_cmd;
 	raw_cmd->flags = FD_RAW_SPIN | FD_RAW_NEED_DISK | FD_RAW_NEED_SEEK;
@@ -2792,7 +2792,7 @@ do_request:
 			return;
 		}
 	}
-	drive = (long)current_req->rq_disk->private_data;
+	drive = (long)current_req->q->disk->private_data;
 	set_fdc(drive);
 	reschedule_timeout(current_drive, "redo fd request");
 
diff --git a/drivers/block/null_blk/trace.h b/drivers/block/null_blk/trace.h
index ce3b430e88c5..86d6c12c603c 100644
--- a/drivers/block/null_blk/trace.h
+++ b/drivers/block/null_blk/trace.h
@@ -44,7 +44,7 @@ TRACE_EVENT(nullb_zone_op,
 		__entry->op = req_op(cmd->rq);
 		__entry->zone_no = zone_no;
 		__entry->zone_cond = zone_cond;
-		__assign_disk_name(__entry->disk, cmd->rq->rq_disk);
+		__assign_disk_name(__entry->disk, cmd->rq->q->disk);
 	    ),
 	    TP_printk("%s req=%-15s zone_no=%u zone_cond=%-10s",
 		      __print_disk_name(__entry->disk),
diff --git a/drivers/block/paride/pcd.c b/drivers/block/paride/pcd.c
index 255fd3d4b8a8..f462ad67931a 100644
--- a/drivers/block/paride/pcd.c
+++ b/drivers/block/paride/pcd.c
@@ -690,7 +690,7 @@ static void pcd_request(void)
 	if (!pcd_req && !set_next_request())
 		return;
 
-	cd = pcd_req->rq_disk->private_data;
+	cd = pcd_req->q->disk->private_data;
 	if (cd != pcd_current)
 		pcd_bufblk = -1;
 	pcd_current = cd;
diff --git a/drivers/block/paride/pd.c b/drivers/block/paride/pd.c
index fba865058a17..4f8cce510562 100644
--- a/drivers/block/paride/pd.c
+++ b/drivers/block/paride/pd.c
@@ -430,7 +430,7 @@ static void run_fsm(void)
 		int stop = 0;
 
 		if (!phase) {
-			pd_current = pd_req->rq_disk->private_data;
+			pd_current = pd_req->q->disk->private_data;
 			pi_current = pd_current->pi;
 			phase = do_pd_io_start;
 		}
@@ -492,7 +492,7 @@ static enum action do_pd_io_start(void)
 	case REQ_OP_WRITE:
 		pd_block = blk_rq_pos(pd_req);
 		pd_count = blk_rq_cur_sectors(pd_req);
-		if (pd_block + pd_count > get_capacity(pd_req->rq_disk))
+		if (pd_block + pd_count > get_capacity(pd_req->q->disk))
 			return Fail;
 		pd_run = blk_rq_sectors(pd_req);
 		pd_buf = bio_data(pd_req->bio);
diff --git a/drivers/block/paride/pf.c b/drivers/block/paride/pf.c
index b84a6448a4f7..292e9a4ce1b9 100644
--- a/drivers/block/paride/pf.c
+++ b/drivers/block/paride/pf.c
@@ -746,12 +746,12 @@ repeat:
 	if (!pf_req && !set_next_request())
 		return;
 
-	pf_current = pf_req->rq_disk->private_data;
+	pf_current = pf_req->q->disk->private_data;
 	pf_block = blk_rq_pos(pf_req);
 	pf_run = blk_rq_sectors(pf_req);
 	pf_count = blk_rq_cur_sectors(pf_req);
 
-	if (pf_block + pf_count > get_capacity(pf_req->rq_disk)) {
+	if (pf_block + pf_count > get_capacity(pf_req->q->disk)) {
 		pf_end_request(BLK_STS_IOERR);
 		goto repeat;
 	}
diff --git a/drivers/block/rnbd/rnbd-clt.c b/drivers/block/rnbd/rnbd-clt.c
index 2df0657cdf00..67a8edbaa1fd 100644
--- a/drivers/block/rnbd/rnbd-clt.c
+++ b/drivers/block/rnbd/rnbd-clt.c
@@ -393,7 +393,7 @@ static void rnbd_put_iu(struct rnbd_clt_session *sess, struct rnbd_iu *iu)
 
 static void rnbd_softirq_done_fn(struct request *rq)
 {
-	struct rnbd_clt_dev *dev	= rq->rq_disk->private_data;
+	struct rnbd_clt_dev *dev	= rq->q->disk->private_data;
 	struct rnbd_clt_session *sess	= dev->sess;
 	struct rnbd_iu *iu;
 
@@ -1133,7 +1133,7 @@ static blk_status_t rnbd_queue_rq(struct blk_mq_hw_ctx *hctx,
 				   const struct blk_mq_queue_data *bd)
 {
 	struct request *rq = bd->rq;
-	struct rnbd_clt_dev *dev = rq->rq_disk->private_data;
+	struct rnbd_clt_dev *dev = rq->q->disk->private_data;
 	struct rnbd_iu *iu = blk_mq_rq_to_pdu(rq);
 	int err;
 	blk_status_t ret = BLK_STS_IOERR;
diff --git a/drivers/block/sunvdc.c b/drivers/block/sunvdc.c
index 2157936de623..146d85d80e0e 100644
--- a/drivers/block/sunvdc.c
+++ b/drivers/block/sunvdc.c
@@ -462,7 +462,7 @@ static int __vdc_tx_trigger(struct vdc_port *port)
 
 static int __send_request(struct request *req)
 {
-	struct vdc_port *port = req->rq_disk->private_data;
+	struct vdc_port *port = req->q->disk->private_data;
 	struct vio_dring_state *dr = &port->vio.drings[VIO_DRIVER_TX_RING];
 	struct scatterlist sg[MAX_RING_COOKIES];
 	struct vdc_req_entry *rqe;
diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index 90dc9cc48881..f4719b65e5e3 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -550,7 +550,6 @@ static int multipath_clone_and_map(struct dm_target *ti, struct request *rq,
 		return DM_MAPIO_REQUEUE;
 	}
 	clone->bio = clone->biotail = NULL;
-	clone->rq_disk = bdev->bd_disk;
 	clone->cmd_flags |= REQ_FAILFAST_TRANSPORT;
 	*__clone = clone;
 
diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c
index 635b79899b9f..dc094f73d335 100644
--- a/drivers/mmc/core/block.c
+++ b/drivers/mmc/core/block.c
@@ -1837,7 +1837,7 @@ static void mmc_blk_mq_rw_recovery(struct mmc_queue *mq, struct request *req)
 	/* Reset if the card is in a bad state */
 	if (!mmc_host_is_spi(mq->card->host) &&
 	    err && mmc_blk_reset(md, card->host, type)) {
-		pr_err("%s: recovery failed!\n", req->rq_disk->disk_name);
+		pr_err("%s: recovery failed!\n", req->q->disk->disk_name);
 		mqrq->retries = MMC_NO_RETRIES;
 		return;
 	}
diff --git a/drivers/nvme/host/fault_inject.c b/drivers/nvme/host/fault_inject.c
index 1352159733b0..83d2e6860d38 100644
--- a/drivers/nvme/host/fault_inject.c
+++ b/drivers/nvme/host/fault_inject.c
@@ -56,7 +56,7 @@ void nvme_fault_inject_fini(struct nvme_fault_inject *fault_inject)
 
 void nvme_should_fail(struct request *req)
 {
-	struct gendisk *disk = req->rq_disk;
+	struct gendisk *disk = req->q->disk;
 	struct nvme_fault_inject *fault_inject = NULL;
 	u16 status;
 
diff --git a/drivers/nvme/host/trace.h b/drivers/nvme/host/trace.h
index 35bac7a25422..b5f85259461a 100644
--- a/drivers/nvme/host/trace.h
+++ b/drivers/nvme/host/trace.h
@@ -68,7 +68,7 @@ TRACE_EVENT(nvme_setup_cmd,
 		__entry->nsid = le32_to_cpu(cmd->common.nsid);
 		__entry->metadata = !!blk_integrity_rq(req);
 		__entry->fctype = cmd->fabrics.fctype;
-		__assign_disk_name(__entry->disk, req->rq_disk);
+		__assign_disk_name(__entry->disk, req->q->disk);
 		memcpy(__entry->cdw10, &cmd->common.cdw10,
 			sizeof(__entry->cdw10));
 	    ),
@@ -103,7 +103,7 @@ TRACE_EVENT(nvme_complete_rq,
 		__entry->retries = nvme_req(req)->retries;
 		__entry->flags = nvme_req(req)->flags;
 		__entry->status = nvme_req(req)->status;
-		__assign_disk_name(__entry->disk, req->rq_disk);
+		__assign_disk_name(__entry->disk, req->q->disk);
 	    ),
 	    TP_printk("nvme%d: %sqid=%d, cmdid=%u, res=%#llx, retries=%u, flags=0x%x, status=%#x",
 		      __entry->ctrl_id, __print_disk_name(__entry->disk),
@@ -153,7 +153,7 @@ TRACE_EVENT(nvme_sq,
 	),
 	TP_fast_assign(
 		__entry->ctrl_id = nvme_req(req)->ctrl->instance;
-		__assign_disk_name(__entry->disk, req->rq_disk);
+		__assign_disk_name(__entry->disk, req->q->disk);
 		__entry->qid = nvme_req_qid(req);
 		__entry->sq_head = le16_to_cpu(sq_head);
 		__entry->sq_tail = sq_tail;
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 5e8b5ecb3245..c23cf8e7b3c3 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -543,8 +543,9 @@ static bool scsi_end_request(struct request *req, blk_status_t error,
 	if (blk_update_request(req, error, bytes))
 		return true;
 
+	// XXX:
 	if (blk_queue_add_random(q))
-		add_disk_randomness(req->rq_disk);
+		add_disk_randomness(req->q->disk);
 
 	if (!blk_rq_is_passthrough(req)) {
 		WARN_ON_ONCE(!(cmd->flags & SCMD_INITIALIZED));
diff --git a/drivers/scsi/scsi_logging.c b/drivers/scsi/scsi_logging.c
index ed9572252a42..1f8f80b2dbfc 100644
--- a/drivers/scsi/scsi_logging.c
+++ b/drivers/scsi/scsi_logging.c
@@ -30,7 +30,9 @@ static inline const char *scmd_name(const struct scsi_cmnd *scmd)
 {
 	struct request *rq = scsi_cmd_to_rq((struct scsi_cmnd *)scmd);
 
-	return rq->rq_disk ? rq->rq_disk->disk_name : NULL;
+	if (!rq->q->disk)
+		return NULL;
+	return rq->q->disk->disk_name;
 }
 
 static size_t sdev_format_header(char *logbuf, size_t logbuf_len,
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index bba1f5dafd38..8181857ddf53 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -872,7 +872,7 @@ static blk_status_t sd_setup_unmap_cmnd(struct scsi_cmnd *cmd)
 {
 	struct scsi_device *sdp = cmd->device;
 	struct request *rq = scsi_cmd_to_rq(cmd);
-	struct scsi_disk *sdkp = scsi_disk(rq->rq_disk);
+	struct scsi_disk *sdkp = scsi_disk(rq->q->disk);
 	u64 lba = sectors_to_logical(sdp, blk_rq_pos(rq));
 	u32 nr_blocks = sectors_to_logical(sdp, blk_rq_sectors(rq));
 	unsigned int data_len = 24;
@@ -908,7 +908,7 @@ static blk_status_t sd_setup_write_same16_cmnd(struct scsi_cmnd *cmd,
 {
 	struct scsi_device *sdp = cmd->device;
 	struct request *rq = scsi_cmd_to_rq(cmd);
-	struct scsi_disk *sdkp = scsi_disk(rq->rq_disk);
+	struct scsi_disk *sdkp = scsi_disk(rq->q->disk);
 	u64 lba = sectors_to_logical(sdp, blk_rq_pos(rq));
 	u32 nr_blocks = sectors_to_logical(sdp, blk_rq_sectors(rq));
 	u32 data_len = sdp->sector_size;
@@ -940,7 +940,7 @@ static blk_status_t sd_setup_write_same10_cmnd(struct scsi_cmnd *cmd,
 {
 	struct scsi_device *sdp = cmd->device;
 	struct request *rq = scsi_cmd_to_rq(cmd);
-	struct scsi_disk *sdkp = scsi_disk(rq->rq_disk);
+	struct scsi_disk *sdkp = scsi_disk(rq->q->disk);
 	u64 lba = sectors_to_logical(sdp, blk_rq_pos(rq));
 	u32 nr_blocks = sectors_to_logical(sdp, blk_rq_sectors(rq));
 	u32 data_len = sdp->sector_size;
@@ -971,7 +971,7 @@ static blk_status_t sd_setup_write_zeroes_cmnd(struct scsi_cmnd *cmd)
 {
 	struct request *rq = scsi_cmd_to_rq(cmd);
 	struct scsi_device *sdp = cmd->device;
-	struct scsi_disk *sdkp = scsi_disk(rq->rq_disk);
+	struct scsi_disk *sdkp = scsi_disk(rq->q->disk);
 	u64 lba = sectors_to_logical(sdp, blk_rq_pos(rq));
 	u32 nr_blocks = sectors_to_logical(sdp, blk_rq_sectors(rq));
 
@@ -1068,7 +1068,7 @@ static blk_status_t sd_setup_write_same_cmnd(struct scsi_cmnd *cmd)
 {
 	struct request *rq = scsi_cmd_to_rq(cmd);
 	struct scsi_device *sdp = cmd->device;
-	struct scsi_disk *sdkp = scsi_disk(rq->rq_disk);
+	struct scsi_disk *sdkp = scsi_disk(rq->q->disk);
 	struct bio *bio = rq->bio;
 	u64 lba = sectors_to_logical(sdp, blk_rq_pos(rq));
 	u32 nr_blocks = sectors_to_logical(sdp, blk_rq_sectors(rq));
@@ -1116,7 +1116,7 @@ static blk_status_t sd_setup_write_same_cmnd(struct scsi_cmnd *cmd)
 static blk_status_t sd_setup_flush_cmnd(struct scsi_cmnd *cmd)
 {
 	struct request *rq = scsi_cmd_to_rq(cmd);
-	struct scsi_disk *sdkp = scsi_disk(rq->rq_disk);
+	struct scsi_disk *sdkp = scsi_disk(rq->q->disk);
 
 	/* flush requests don't perform I/O, zero the S/G table */
 	memset(&cmd->sdb, 0, sizeof(cmd->sdb));
@@ -1215,7 +1215,7 @@ static blk_status_t sd_setup_read_write_cmnd(struct scsi_cmnd *cmd)
 {
 	struct request *rq = scsi_cmd_to_rq(cmd);
 	struct scsi_device *sdp = cmd->device;
-	struct scsi_disk *sdkp = scsi_disk(rq->rq_disk);
+	struct scsi_disk *sdkp = scsi_disk(rq->q->disk);
 	sector_t lba = sectors_to_logical(sdp, blk_rq_pos(rq));
 	sector_t threshold;
 	unsigned int nr_blocks = sectors_to_logical(sdp, blk_rq_sectors(rq));
@@ -1236,7 +1236,7 @@ static blk_status_t sd_setup_read_write_cmnd(struct scsi_cmnd *cmd)
 		goto fail;
 	}
 
-	if (blk_rq_pos(rq) + blk_rq_sectors(rq) > get_capacity(rq->rq_disk)) {
+	if (blk_rq_pos(rq) + blk_rq_sectors(rq) > get_capacity(rq->q->disk)) {
 		scmd_printk(KERN_ERR, cmd, "access beyond end of device\n");
 		goto fail;
 	}
@@ -1331,7 +1331,7 @@ static blk_status_t sd_init_command(struct scsi_cmnd *cmd)
 
 	switch (req_op(rq)) {
 	case REQ_OP_DISCARD:
-		switch (scsi_disk(rq->rq_disk)->provisioning_mode) {
+		switch (scsi_disk(rq->q->disk)->provisioning_mode) {
 		case SD_LBP_UNMAP:
 			return sd_setup_unmap_cmnd(cmd);
 		case SD_LBP_WS16:
@@ -1917,7 +1917,7 @@ static const struct block_device_operations sd_fops = {
  **/
 static void sd_eh_reset(struct scsi_cmnd *scmd)
 {
-	struct scsi_disk *sdkp = scsi_disk(scsi_cmd_to_rq(scmd)->rq_disk);
+	struct scsi_disk *sdkp = scsi_disk(scsi_cmd_to_rq(scmd)->q->disk);
 
 	/* New SCSI EH run, reset gate variable */
 	sdkp->ignore_medium_access_errors = false;
@@ -1937,7 +1937,7 @@ static void sd_eh_reset(struct scsi_cmnd *scmd)
  **/
 static int sd_eh_action(struct scsi_cmnd *scmd, int eh_disp)
 {
-	struct scsi_disk *sdkp = scsi_disk(scsi_cmd_to_rq(scmd)->rq_disk);
+	struct scsi_disk *sdkp = scsi_disk(scsi_cmd_to_rq(scmd)->q->disk);
 	struct scsi_device *sdev = scmd->device;
 
 	if (!scsi_device_online(sdev) ||
@@ -2034,7 +2034,7 @@ static int sd_done(struct scsi_cmnd *SCpnt)
 	unsigned int resid;
 	struct scsi_sense_hdr sshdr;
 	struct request *req = scsi_cmd_to_rq(SCpnt);
-	struct scsi_disk *sdkp = scsi_disk(req->rq_disk);
+	struct scsi_disk *sdkp = scsi_disk(req->q->disk);
 	int sense_valid = 0;
 	int sense_deferred = 0;
 
diff --git a/drivers/scsi/sd_zbc.c b/drivers/scsi/sd_zbc.c
index ed06798983f8..65bfd1e170da 100644
--- a/drivers/scsi/sd_zbc.c
+++ b/drivers/scsi/sd_zbc.c
@@ -244,7 +244,7 @@ out:
 static blk_status_t sd_zbc_cmnd_checks(struct scsi_cmnd *cmd)
 {
 	struct request *rq = scsi_cmd_to_rq(cmd);
-	struct scsi_disk *sdkp = scsi_disk(rq->rq_disk);
+	struct scsi_disk *sdkp = scsi_disk(rq->q->disk);
 	sector_t sector = blk_rq_pos(rq);
 
 	if (!sd_is_zoned(sdkp))
@@ -322,7 +322,7 @@ blk_status_t sd_zbc_prepare_zone_append(struct scsi_cmnd *cmd, sector_t *lba,
 					unsigned int nr_blocks)
 {
 	struct request *rq = scsi_cmd_to_rq(cmd);
-	struct scsi_disk *sdkp = scsi_disk(rq->rq_disk);
+	struct scsi_disk *sdkp = scsi_disk(rq->q->disk);
 	unsigned int wp_offset, zno = blk_rq_zone_no(rq);
 	unsigned long flags;
 	blk_status_t ret;
@@ -388,7 +388,7 @@ blk_status_t sd_zbc_setup_zone_mgmt_cmnd(struct scsi_cmnd *cmd,
 {
 	struct request *rq = scsi_cmd_to_rq(cmd);
 	sector_t sector = blk_rq_pos(rq);
-	struct scsi_disk *sdkp = scsi_disk(rq->rq_disk);
+	struct scsi_disk *sdkp = scsi_disk(rq->q->disk);
 	sector_t block = sectors_to_logical(sdkp->device, sector);
 	blk_status_t ret;
 
@@ -443,7 +443,7 @@ static unsigned int sd_zbc_zone_wp_update(struct scsi_cmnd *cmd,
 {
 	int result = cmd->result;
 	struct request *rq = scsi_cmd_to_rq(cmd);
-	struct scsi_disk *sdkp = scsi_disk(rq->rq_disk);
+	struct scsi_disk *sdkp = scsi_disk(rq->q->disk);
 	unsigned int zno = blk_rq_zone_no(rq);
 	enum req_opf op = req_op(rq);
 	unsigned long flags;
diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c
index 411e2b01966e..7db595c08b20 100644
--- a/drivers/scsi/sr.c
+++ b/drivers/scsi/sr.c
@@ -335,7 +335,7 @@ static int sr_done(struct scsi_cmnd *SCpnt)
 	int block_sectors = 0;
 	long error_sector;
 	struct request *rq = scsi_cmd_to_rq(SCpnt);
-	struct scsi_cd *cd = scsi_cd(rq->rq_disk);
+	struct scsi_cd *cd = scsi_cd(rq->q->disk);
 
 #ifdef DEBUG
 	scmd_printk(KERN_INFO, SCpnt, "done: %x\n", result);
@@ -402,7 +402,7 @@ static blk_status_t sr_init_command(struct scsi_cmnd *SCpnt)
 	ret = scsi_alloc_sgtables(SCpnt);
 	if (ret != BLK_STS_OK)
 		return ret;
-	cd = scsi_cd(rq->rq_disk);
+	cd = scsi_cd(rq->q->disk);
 
 	SCSI_LOG_HLQUEUE(1, scmd_printk(KERN_INFO, SCpnt,
 		"Doing sr request, block = %d\n", block));
diff --git a/drivers/scsi/virtio_scsi.c b/drivers/scsi/virtio_scsi.c
index 28e1d98ae102..65c642b24ecf 100644
--- a/drivers/scsi/virtio_scsi.c
+++ b/drivers/scsi/virtio_scsi.c
@@ -528,7 +528,7 @@ static void virtio_scsi_init_hdr_pi(struct virtio_device *vdev,
 	if (!rq || !scsi_prot_sg_count(sc))
 		return;
 
-	bi = blk_get_integrity(rq->rq_disk);
+	bi = blk_get_integrity(rq->q->disk);
 
 	if (sc->sc_data_direction == DMA_TO_DEVICE)
 		cmd_pi->pi_bytesout = cpu_to_virtio32(vdev,
diff --git a/drivers/usb/storage/transport.c b/drivers/usb/storage/transport.c
index 4c5a0a49035f..1928b3918242 100644
--- a/drivers/usb/storage/transport.c
+++ b/drivers/usb/storage/transport.c
@@ -551,7 +551,7 @@ static void last_sector_hacks(struct us_data *us, struct scsi_cmnd *srb)
 	/* Did this command access the last sector? */
 	sector = (srb->cmnd[2] << 24) | (srb->cmnd[3] << 16) |
 			(srb->cmnd[4] << 8) | (srb->cmnd[5]);
-	disk = scsi_cmd_to_rq(srb)->rq_disk;
+	disk = scsi_cmd_to_rq(srb)->q->disk;
 	if (!disk)
 		goto done;
 	sdkp = scsi_disk(disk);
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index d952c3442261..ede7bef8880a 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -100,7 +100,6 @@ struct request {
 		struct request *rq_next;
 	};
 
-	struct gendisk *rq_disk;
 	struct block_device *part;
 #ifdef CONFIG_BLK_RQ_ALLOC_TIME
 	/* Time that the first bio started allocating this request. */
@@ -890,9 +889,6 @@ static inline void blk_rq_bio_prep(struct request *rq, struct bio *bio,
 	rq->__data_len = bio->bi_iter.bi_size;
 	rq->bio = rq->biotail = bio;
 	rq->ioprio = bio_prio(bio);
-
-	if (bio->bi_bdev)
-		rq->rq_disk = bio->bi_bdev->bd_disk;
 }
 
 void blk_mq_hctx_set_fq_lock_class(struct blk_mq_hw_ctx *hctx,
diff --git a/include/scsi/scsi_cmnd.h b/include/scsi/scsi_cmnd.h
index 477a800a9543..6794d7322cbd 100644
--- a/include/scsi/scsi_cmnd.h
+++ b/include/scsi/scsi_cmnd.h
@@ -164,7 +164,7 @@ static inline struct scsi_driver *scsi_cmd_to_driver(struct scsi_cmnd *cmd)
 {
 	struct request *rq = scsi_cmd_to_rq(cmd);
 
-	return *(struct scsi_driver **)rq->rq_disk->private_data;
+	return *(struct scsi_driver **)rq->q->disk->private_data;
 }
 
 void scsi_done(struct scsi_cmnd *cmd);
diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h
index d1c6fc83b1e3..ab7557d84f75 100644
--- a/include/scsi/scsi_device.h
+++ b/include/scsi/scsi_device.h
@@ -275,9 +275,9 @@ scmd_printk(const char *, const struct scsi_cmnd *, const char *, ...);
 	do {								\
 		struct request *__rq = scsi_cmd_to_rq((scmd));		\
 									\
-		if (__rq->rq_disk)					\
+		if (__rq->q->disk)					\
 			sdev_dbg((scmd)->device, "[%s] " fmt,		\
-				 __rq->rq_disk->disk_name, ##a);	\
+				 __rq->q->disk->disk_name, ##a);	\
 		else							\
 			sdev_dbg((scmd)->device, fmt, ##a);		\
 	} while (0)
diff --git a/include/trace/events/block.h b/include/trace/events/block.h
index a95daa4d4caa..27170e40e8c9 100644
--- a/include/trace/events/block.h
+++ b/include/trace/events/block.h
@@ -85,7 +85,7 @@ TRACE_EVENT(block_rq_requeue,
 	),
 
 	TP_fast_assign(
-		__entry->dev	   = rq->rq_disk ? disk_devt(rq->rq_disk) : 0;
+		__entry->dev	   = rq->q->disk ? disk_devt(rq->q->disk) : 0;
 		__entry->sector    = blk_rq_trace_sector(rq);
 		__entry->nr_sector = blk_rq_trace_nr_sectors(rq);
 
@@ -128,7 +128,7 @@ TRACE_EVENT(block_rq_complete,
 	),
 
 	TP_fast_assign(
-		__entry->dev	   = rq->rq_disk ? disk_devt(rq->rq_disk) : 0;
+		__entry->dev	   = rq->q->disk ? disk_devt(rq->q->disk) : 0;
 		__entry->sector    = blk_rq_pos(rq);
 		__entry->nr_sector = nr_bytes >> 9;
 		__entry->error     = blk_status_to_errno(error);
@@ -161,7 +161,7 @@ DECLARE_EVENT_CLASS(block_rq,
 	),
 
 	TP_fast_assign(
-		__entry->dev	   = rq->rq_disk ? disk_devt(rq->rq_disk) : 0;
+		__entry->dev	   = rq->q->disk ? disk_devt(rq->q->disk) : 0;
 		__entry->sector    = blk_rq_trace_sector(rq);
 		__entry->nr_sector = blk_rq_trace_nr_sectors(rq);
 		__entry->bytes     = blk_rq_bytes(rq);
@@ -512,7 +512,7 @@ TRACE_EVENT(block_rq_remap,
 	),
 
 	TP_fast_assign(
-		__entry->dev		= disk_devt(rq->rq_disk);
+		__entry->dev		= disk_devt(rq->q->disk);
 		__entry->sector		= blk_rq_pos(rq);
 		__entry->nr_sector	= blk_rq_sectors(rq);
 		__entry->old_dev	= dev;
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index 1183c88634aa..431e41bc4c23 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -1045,7 +1045,7 @@ static void blk_add_trace_rq_remap(void *ignore, struct request *rq, dev_t dev,
 	}
 
 	r.device_from = cpu_to_be32(dev);
-	r.device_to   = cpu_to_be32(disk_devt(rq->rq_disk));
+	r.device_to   = cpu_to_be32(disk_devt(rq->q->disk));
 	r.sector_from = cpu_to_be64(from);
 
 	__blk_add_trace(bt, blk_rq_pos(rq), blk_rq_bytes(rq),
-- 
cgit v1.2.3


From b84ba30b6c7a75babdf73b83bc3c7b59b944501a Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 26 Nov 2021 13:18:01 +0100
Subject: block: remove the gendisk argument to blk_execute_rq

Remove the gendisk aregument to blk_execute_rq and blk_execute_rq_nowait
given that it is unused now.  Also convert the boolean at_head parameter
to actually use the bool type while touching the prototype.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Link: https://lore.kernel.org/r/20211126121802.2090656-5-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-mq.c                     | 10 +++-------
 block/bsg-lib.c                    |  2 +-
 drivers/block/mtip32xx/mtip32xx.c  |  2 +-
 drivers/block/paride/pd.c          |  2 +-
 drivers/block/pktcdvd.c            |  2 +-
 drivers/block/sx8.c                |  4 ++--
 drivers/block/virtio_blk.c         |  2 +-
 drivers/mmc/core/block.c           | 10 +++++-----
 drivers/nvme/host/core.c           |  4 ++--
 drivers/nvme/host/pci.c            |  7 +++----
 drivers/nvme/target/passthru.c     |  3 +--
 drivers/scsi/scsi_bsg.c            |  2 +-
 drivers/scsi/scsi_error.c          |  2 +-
 drivers/scsi/scsi_ioctl.c          |  4 ++--
 drivers/scsi/scsi_lib.c            |  2 +-
 drivers/scsi/sg.c                  |  2 +-
 drivers/scsi/sr.c                  |  2 +-
 drivers/scsi/st.c                  |  2 +-
 drivers/scsi/ufs/ufshpb.c          |  4 ++--
 drivers/target/target_core_pscsi.c |  2 +-
 include/linux/blk-mq.h             |  7 +++----
 21 files changed, 35 insertions(+), 42 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-mq.c b/block/blk-mq.c
index f1abfd2e24f7..ecfc47fad236 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1153,7 +1153,6 @@ static void blk_end_sync_rq(struct request *rq, blk_status_t error)
 
 /**
  * blk_execute_rq_nowait - insert a request to I/O scheduler for execution
- * @bd_disk:	matching gendisk
  * @rq:		request to insert
  * @at_head:    insert request at head or tail of queue
  * @done:	I/O completion handler
@@ -1165,8 +1164,7 @@ static void blk_end_sync_rq(struct request *rq, blk_status_t error)
  * Note:
  *    This function will invoke @done directly if the queue is dead.
  */
-void blk_execute_rq_nowait(struct gendisk *bd_disk, struct request *rq,
-			   int at_head, rq_end_io_fn *done)
+void blk_execute_rq_nowait(struct request *rq, bool at_head, rq_end_io_fn *done)
 {
 	WARN_ON(irqs_disabled());
 	WARN_ON(!blk_rq_is_passthrough(rq));
@@ -1204,7 +1202,6 @@ static void blk_rq_poll_completion(struct request *rq, struct completion *wait)
 
 /**
  * blk_execute_rq - insert a request into queue for execution
- * @bd_disk:	matching gendisk
  * @rq:		request to insert
  * @at_head:    insert request at head or tail of queue
  *
@@ -1213,14 +1210,13 @@ static void blk_rq_poll_completion(struct request *rq, struct completion *wait)
  *    for execution and wait for completion.
  * Return: The blk_status_t result provided to blk_mq_end_request().
  */
-blk_status_t blk_execute_rq(struct gendisk *bd_disk, struct request *rq,
-		int at_head)
+blk_status_t blk_execute_rq(struct request *rq, bool at_head)
 {
 	DECLARE_COMPLETION_ONSTACK(wait);
 	unsigned long hang_check;
 
 	rq->end_io_data = &wait;
-	blk_execute_rq_nowait(bd_disk, rq, at_head, blk_end_sync_rq);
+	blk_execute_rq_nowait(rq, at_head, blk_end_sync_rq);
 
 	/* Prevent hang_check timer from firing at us during very long I/O */
 	hang_check = sysctl_hung_task_timeout_secs;
diff --git a/block/bsg-lib.c b/block/bsg-lib.c
index 10aa378702fa..acfe1357bf6c 100644
--- a/block/bsg-lib.c
+++ b/block/bsg-lib.c
@@ -92,7 +92,7 @@ static int bsg_transport_sg_io_fn(struct request_queue *q, struct sg_io_v4 *hdr,
 		goto out_unmap_bidi_rq;
 
 	bio = rq->bio;
-	blk_execute_rq(NULL, rq, !(hdr->flags & BSG_FLAG_Q_AT_TAIL));
+	blk_execute_rq(rq, !(hdr->flags & BSG_FLAG_Q_AT_TAIL));
 
 	/*
 	 * The assignments below don't make much sense, but are kept for
diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c
index c91b9010c1a6..30f471021a40 100644
--- a/drivers/block/mtip32xx/mtip32xx.c
+++ b/drivers/block/mtip32xx/mtip32xx.c
@@ -1015,7 +1015,7 @@ static int mtip_exec_internal_command(struct mtip_port *port,
 	rq->timeout = timeout;
 
 	/* insert request and run queue */
-	blk_execute_rq(NULL, rq, true);
+	blk_execute_rq(rq, true);
 
 	if (int_cmd->status) {
 		dev_err(&dd->pdev->dev, "Internal command [%02X] failed %d\n",
diff --git a/drivers/block/paride/pd.c b/drivers/block/paride/pd.c
index 4f8cce510562..3637c38c72f9 100644
--- a/drivers/block/paride/pd.c
+++ b/drivers/block/paride/pd.c
@@ -781,7 +781,7 @@ static int pd_special_command(struct pd_unit *disk,
 	req = blk_mq_rq_to_pdu(rq);
 
 	req->func = func;
-	blk_execute_rq(disk->gd, rq, 0);
+	blk_execute_rq(rq, false);
 	blk_mq_free_request(rq);
 	return 0;
 }
diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c
index 3af0499857ec..887c98d61684 100644
--- a/drivers/block/pktcdvd.c
+++ b/drivers/block/pktcdvd.c
@@ -722,7 +722,7 @@ static int pkt_generic_packet(struct pktcdvd_device *pd, struct packet_command *
 	if (cgc->quiet)
 		rq->rq_flags |= RQF_QUIET;
 
-	blk_execute_rq(pd->bdev->bd_disk, rq, 0);
+	blk_execute_rq(rq, false);
 	if (scsi_req(rq)->result)
 		ret = -EIO;
 out:
diff --git a/drivers/block/sx8.c b/drivers/block/sx8.c
index d1676fe0da1a..b361583944b9 100644
--- a/drivers/block/sx8.c
+++ b/drivers/block/sx8.c
@@ -540,7 +540,7 @@ static int carm_array_info (struct carm_host *host, unsigned int array_idx)
 	spin_unlock_irq(&host->lock);
 
 	DPRINTK("blk_execute_rq_nowait, tag == %u\n", rq->tag);
-	blk_execute_rq_nowait(NULL, rq, true, NULL);
+	blk_execute_rq_nowait(rq, true, NULL);
 
 	return 0;
 
@@ -579,7 +579,7 @@ static int carm_send_special (struct carm_host *host, carm_sspc_t func)
 	crq->msg_bucket = (u32) rc;
 
 	DPRINTK("blk_execute_rq_nowait, tag == %u\n", rq->tag);
-	blk_execute_rq_nowait(NULL, rq, true, NULL);
+	blk_execute_rq_nowait(rq, true, NULL);
 
 	return 0;
 }
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index cfa303fa7318..c3dc3cd7a779 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -384,7 +384,7 @@ static int virtblk_get_id(struct gendisk *disk, char *id_str)
 	if (err)
 		goto out;
 
-	blk_execute_rq(vblk->disk, req, false);
+	blk_execute_rq(req, false);
 	err = blk_status_to_errno(virtblk_result(blk_mq_rq_to_pdu(req)));
 out:
 	blk_mq_free_request(req);
diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c
index dc094f73d335..ef8f45fa2cee 100644
--- a/drivers/mmc/core/block.c
+++ b/drivers/mmc/core/block.c
@@ -264,7 +264,7 @@ static ssize_t power_ro_lock_store(struct device *dev,
 		goto out_put;
 	}
 	req_to_mmc_queue_req(req)->drv_op = MMC_DRV_OP_BOOT_WP;
-	blk_execute_rq(NULL, req, 0);
+	blk_execute_rq(req, false);
 	ret = req_to_mmc_queue_req(req)->drv_op_result;
 	blk_mq_free_request(req);
 
@@ -657,7 +657,7 @@ static int mmc_blk_ioctl_cmd(struct mmc_blk_data *md,
 		rpmb ? MMC_DRV_OP_IOCTL_RPMB : MMC_DRV_OP_IOCTL;
 	req_to_mmc_queue_req(req)->drv_op_data = idatas;
 	req_to_mmc_queue_req(req)->ioc_count = 1;
-	blk_execute_rq(NULL, req, 0);
+	blk_execute_rq(req, false);
 	ioc_err = req_to_mmc_queue_req(req)->drv_op_result;
 	err = mmc_blk_ioctl_copy_to_user(ic_ptr, idata);
 	blk_mq_free_request(req);
@@ -726,7 +726,7 @@ static int mmc_blk_ioctl_multi_cmd(struct mmc_blk_data *md,
 		rpmb ? MMC_DRV_OP_IOCTL_RPMB : MMC_DRV_OP_IOCTL;
 	req_to_mmc_queue_req(req)->drv_op_data = idata;
 	req_to_mmc_queue_req(req)->ioc_count = num_of_cmds;
-	blk_execute_rq(NULL, req, 0);
+	blk_execute_rq(req, false);
 	ioc_err = req_to_mmc_queue_req(req)->drv_op_result;
 
 	/* copy to user if data and response */
@@ -2743,7 +2743,7 @@ static int mmc_dbg_card_status_get(void *data, u64 *val)
 	if (IS_ERR(req))
 		return PTR_ERR(req);
 	req_to_mmc_queue_req(req)->drv_op = MMC_DRV_OP_GET_CARD_STATUS;
-	blk_execute_rq(NULL, req, 0);
+	blk_execute_rq(req, false);
 	ret = req_to_mmc_queue_req(req)->drv_op_result;
 	if (ret >= 0) {
 		*val = ret;
@@ -2782,7 +2782,7 @@ static int mmc_ext_csd_open(struct inode *inode, struct file *filp)
 	}
 	req_to_mmc_queue_req(req)->drv_op = MMC_DRV_OP_GET_EXT_CSD;
 	req_to_mmc_queue_req(req)->drv_op_data = &ext_csd;
-	blk_execute_rq(NULL, req, 0);
+	blk_execute_rq(req, false);
 	err = req_to_mmc_queue_req(req)->drv_op_result;
 	blk_mq_free_request(req);
 	if (err) {
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 4c63564adeaa..f82c098b1a61 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -1056,7 +1056,7 @@ static int nvme_execute_rq(struct gendisk *disk, struct request *rq,
 {
 	blk_status_t status;
 
-	status = blk_execute_rq(disk, rq, at_head);
+	status = blk_execute_rq(rq, at_head);
 	if (nvme_req(rq)->flags & NVME_REQ_CANCELLED)
 		return -EINTR;
 	if (nvme_req(rq)->status)
@@ -1283,7 +1283,7 @@ static void nvme_keep_alive_work(struct work_struct *work)
 
 	rq->timeout = ctrl->kato * HZ;
 	rq->end_io_data = ctrl;
-	blk_execute_rq_nowait(NULL, rq, 0, nvme_keep_alive_end_io);
+	blk_execute_rq_nowait(rq, false, nvme_keep_alive_end_io);
 }
 
 static void nvme_start_keep_alive(struct nvme_ctrl *ctrl)
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index ca2ee806d74b..8637538f3fd5 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -1371,7 +1371,7 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved)
 	}
 
 	abort_req->end_io_data = NULL;
-	blk_execute_rq_nowait(NULL, abort_req, 0, abort_endio);
+	blk_execute_rq_nowait(abort_req, false, abort_endio);
 
 	/*
 	 * The aborted req will be completed on receiving the abort req.
@@ -2416,9 +2416,8 @@ static int nvme_delete_queue(struct nvme_queue *nvmeq, u8 opcode)
 	req->end_io_data = nvmeq;
 
 	init_completion(&nvmeq->delete_done);
-	blk_execute_rq_nowait(NULL, req, false,
-			opcode == nvme_admin_delete_cq ?
-				nvme_del_cq_end : nvme_del_queue_end);
+	blk_execute_rq_nowait(req, false, opcode == nvme_admin_delete_cq ?
+			nvme_del_cq_end : nvme_del_queue_end);
 	return 0;
 }
 
diff --git a/drivers/nvme/target/passthru.c b/drivers/nvme/target/passthru.c
index f0efb3537989..9e5b89ae29df 100644
--- a/drivers/nvme/target/passthru.c
+++ b/drivers/nvme/target/passthru.c
@@ -284,8 +284,7 @@ static void nvmet_passthru_execute_cmd(struct nvmet_req *req)
 		schedule_work(&req->p.work);
 	} else {
 		rq->end_io_data = req;
-		blk_execute_rq_nowait(ns ? ns->disk : NULL, rq, 0,
-				      nvmet_passthru_req_done);
+		blk_execute_rq_nowait(rq, false, nvmet_passthru_req_done);
 	}
 
 	if (ns)
diff --git a/drivers/scsi/scsi_bsg.c b/drivers/scsi/scsi_bsg.c
index 081b84bb7985..b7a464383cc0 100644
--- a/drivers/scsi/scsi_bsg.c
+++ b/drivers/scsi/scsi_bsg.c
@@ -60,7 +60,7 @@ static int scsi_bsg_sg_io_fn(struct request_queue *q, struct sg_io_v4 *hdr,
 		goto out_free_cmd;
 
 	bio = rq->bio;
-	blk_execute_rq(NULL, rq, !(hdr->flags & BSG_FLAG_Q_AT_TAIL));
+	blk_execute_rq(rq, !(hdr->flags & BSG_FLAG_Q_AT_TAIL));
 
 	/*
 	 * fill in all the output members
diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c
index 2371edbc3af4..3eae2392ef15 100644
--- a/drivers/scsi/scsi_error.c
+++ b/drivers/scsi/scsi_error.c
@@ -2040,7 +2040,7 @@ static void scsi_eh_lock_door(struct scsi_device *sdev)
 	req->timeout = 10 * HZ;
 	rq->retries = 5;
 
-	blk_execute_rq_nowait(NULL, req, 1, eh_lock_door_done);
+	blk_execute_rq_nowait(req, true, eh_lock_door_done);
 }
 
 /**
diff --git a/drivers/scsi/scsi_ioctl.c b/drivers/scsi/scsi_ioctl.c
index 400df3354cd6..340ba0ad6e70 100644
--- a/drivers/scsi/scsi_ioctl.c
+++ b/drivers/scsi/scsi_ioctl.c
@@ -483,7 +483,7 @@ static int sg_io(struct scsi_device *sdev, struct gendisk *disk,
 
 	start_time = jiffies;
 
-	blk_execute_rq(disk, rq, at_head);
+	blk_execute_rq(rq, at_head);
 
 	hdr->duration = jiffies_to_msecs(jiffies - start_time);
 
@@ -620,7 +620,7 @@ static int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk,
 			goto error;
 	}
 
-	blk_execute_rq(disk, rq, 0);
+	blk_execute_rq(rq, false);
 
 	err = req->result & 0xff;	/* only 8 bit SCSI status */
 	if (err) {
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index c23cf8e7b3c3..35e381f6d371 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -241,7 +241,7 @@ int __scsi_execute(struct scsi_device *sdev, const unsigned char *cmd,
 	/*
 	 * head injection *required* here otherwise quiesce won't work
 	 */
-	blk_execute_rq(NULL, req, 1);
+	blk_execute_rq(req, true);
 
 	/*
 	 * Some devices (USB mass-storage in particular) may transfer
diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c
index 141099ab9092..6c8ffad88f9e 100644
--- a/drivers/scsi/sg.c
+++ b/drivers/scsi/sg.c
@@ -833,7 +833,7 @@ sg_common_write(Sg_fd * sfp, Sg_request * srp,
 
 	srp->rq->timeout = timeout;
 	kref_get(&sfp->f_ref); /* sg_rq_end_io() does kref_put(). */
-	blk_execute_rq_nowait(NULL, srp->rq, at_head, sg_rq_end_io);
+	blk_execute_rq_nowait(srp->rq, at_head, sg_rq_end_io);
 	return 0;
 }
 
diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c
index 7db595c08b20..c29589815468 100644
--- a/drivers/scsi/sr.c
+++ b/drivers/scsi/sr.c
@@ -994,7 +994,7 @@ static int sr_read_cdda_bpc(struct cdrom_device_info *cdi, void __user *ubuf,
 	rq->timeout = 60 * HZ;
 	bio = rq->bio;
 
-	blk_execute_rq(disk, rq, 0);
+	blk_execute_rq(rq, false);
 	if (scsi_req(rq)->result) {
 		struct scsi_sense_hdr sshdr;
 
diff --git a/drivers/scsi/st.c b/drivers/scsi/st.c
index c2d5608f6b1a..06acc7db7755 100644
--- a/drivers/scsi/st.c
+++ b/drivers/scsi/st.c
@@ -581,7 +581,7 @@ static int st_scsi_execute(struct st_request *SRpnt, const unsigned char *cmd,
 	rq->retries = retries;
 	req->end_io_data = SRpnt;
 
-	blk_execute_rq_nowait(NULL, req, 1, st_scsi_execute_end);
+	blk_execute_rq_nowait(req, true, st_scsi_execute_end);
 	return 0;
 }
 
diff --git a/drivers/scsi/ufs/ufshpb.c b/drivers/scsi/ufs/ufshpb.c
index ded5ba9b1466..13cd21204bf9 100644
--- a/drivers/scsi/ufs/ufshpb.c
+++ b/drivers/scsi/ufs/ufshpb.c
@@ -677,7 +677,7 @@ static void ufshpb_execute_umap_req(struct ufshpb_lu *hpb,
 	ufshpb_set_unmap_cmd(rq->cmd, rgn);
 	rq->cmd_len = HPB_WRITE_BUFFER_CMD_LENGTH;
 
-	blk_execute_rq_nowait(NULL, req, 1, ufshpb_umap_req_compl_fn);
+	blk_execute_rq_nowait(req, true, ufshpb_umap_req_compl_fn);
 
 	hpb->stats.umap_req_cnt++;
 }
@@ -719,7 +719,7 @@ static int ufshpb_execute_map_req(struct ufshpb_lu *hpb,
 				map_req->rb.srgn_idx, mem_size);
 	rq->cmd_len = HPB_READ_BUFFER_CMD_LENGTH;
 
-	blk_execute_rq_nowait(NULL, req, 1, ufshpb_map_req_compl_fn);
+	blk_execute_rq_nowait(req, true, ufshpb_map_req_compl_fn);
 
 	hpb->stats.map_req_cnt++;
 	return 0;
diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c
index 7fa57fb57bf2..807d06ecadee 100644
--- a/drivers/target/target_core_pscsi.c
+++ b/drivers/target/target_core_pscsi.c
@@ -1005,7 +1005,7 @@ pscsi_execute_cmd(struct se_cmd *cmd)
 		req->timeout = PS_TIMEOUT_OTHER;
 	scsi_req(req)->retries = PS_RETRY;
 
-	blk_execute_rq_nowait(NULL, req, (cmd->sam_task_attr == TCM_HEAD_TAG),
+	blk_execute_rq_nowait(req, cmd->sam_task_attr == TCM_HEAD_TAG,
 			pscsi_req_done);
 
 	return 0;
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index ede7bef8880a..1b87b7c8bbff 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -924,10 +924,9 @@ int blk_rq_unmap_user(struct bio *);
 int blk_rq_map_kern(struct request_queue *, struct request *, void *,
 		unsigned int, gfp_t);
 int blk_rq_append_bio(struct request *rq, struct bio *bio);
-void blk_execute_rq_nowait(struct gendisk *, struct request *, int,
-		rq_end_io_fn *);
-blk_status_t blk_execute_rq(struct gendisk *bd_disk, struct request *rq,
-		int at_head);
+void blk_execute_rq_nowait(struct request *rq, bool at_head,
+		rq_end_io_fn *end_io);
+blk_status_t blk_execute_rq(struct request *rq, bool at_head);
 
 struct req_iterator {
 	struct bvec_iter iter;
-- 
cgit v1.2.3


From 4bdcd1dd4d2f973b1a89fb20ba720d879e9e506b Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Thu, 28 Oct 2021 08:47:05 -0600
Subject: mm: move filemap_range_needs_writeback() into header

No functional changes in this patch, just in preparation for efficiently
calling this light function from the block O_DIRECT handling.

Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/iomap/direct-io.c    |  1 +
 include/linux/fs.h      |  2 --
 include/linux/pagemap.h | 29 +++++++++++++++++++++++++++++
 mm/filemap.c            | 32 +++-----------------------------
 4 files changed, 33 insertions(+), 31 deletions(-)

(limited to 'include/linux')

diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c
index b4dc51063d36..03ea367df19a 100644
--- a/fs/iomap/direct-io.c
+++ b/fs/iomap/direct-io.c
@@ -6,6 +6,7 @@
 #include <linux/module.h>
 #include <linux/compiler.h>
 #include <linux/fs.h>
+#include <linux/pagemap.h>
 #include <linux/iomap.h>
 #include <linux/backing-dev.h>
 #include <linux/uio.h>
diff --git a/include/linux/fs.h b/include/linux/fs.h
index bbf812ce89a8..6b8dc1a78df6 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2847,8 +2847,6 @@ static inline int filemap_fdatawait(struct address_space *mapping)
 
 extern bool filemap_range_has_page(struct address_space *, loff_t lstart,
 				  loff_t lend);
-extern bool filemap_range_needs_writeback(struct address_space *,
-					  loff_t lstart, loff_t lend);
 extern int filemap_write_and_wait_range(struct address_space *mapping,
 				        loff_t lstart, loff_t lend);
 extern int __filemap_fdatawrite_range(struct address_space *mapping,
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 605246452305..274a0710f2c5 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -963,6 +963,35 @@ static inline int add_to_page_cache(struct page *page,
 int __filemap_add_folio(struct address_space *mapping, struct folio *folio,
 		pgoff_t index, gfp_t gfp, void **shadowp);
 
+bool filemap_range_has_writeback(struct address_space *mapping,
+				 loff_t start_byte, loff_t end_byte);
+
+/**
+ * filemap_range_needs_writeback - check if range potentially needs writeback
+ * @mapping:           address space within which to check
+ * @start_byte:        offset in bytes where the range starts
+ * @end_byte:          offset in bytes where the range ends (inclusive)
+ *
+ * Find at least one page in the range supplied, usually used to check if
+ * direct writing in this range will trigger a writeback. Used by O_DIRECT
+ * read/write with IOCB_NOWAIT, to see if the caller needs to do
+ * filemap_write_and_wait_range() before proceeding.
+ *
+ * Return: %true if the caller should do filemap_write_and_wait_range() before
+ * doing O_DIRECT to a page in this range, %false otherwise.
+ */
+static inline bool filemap_range_needs_writeback(struct address_space *mapping,
+						 loff_t start_byte,
+						 loff_t end_byte)
+{
+	if (!mapping->nrpages)
+		return false;
+	if (!mapping_tagged(mapping, PAGECACHE_TAG_DIRTY) &&
+	    !mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK))
+		return false;
+	return filemap_range_has_writeback(mapping, start_byte, end_byte);
+}
+
 /**
  * struct readahead_control - Describes a readahead request.
  *
diff --git a/mm/filemap.c b/mm/filemap.c
index daa0e23a6ee6..655c9eec06b3 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -646,8 +646,8 @@ static bool mapping_needs_writeback(struct address_space *mapping)
 	return mapping->nrpages;
 }
 
-static bool filemap_range_has_writeback(struct address_space *mapping,
-					loff_t start_byte, loff_t end_byte)
+bool filemap_range_has_writeback(struct address_space *mapping,
+				 loff_t start_byte, loff_t end_byte)
 {
 	XA_STATE(xas, &mapping->i_pages, start_byte >> PAGE_SHIFT);
 	pgoff_t max = end_byte >> PAGE_SHIFT;
@@ -667,34 +667,8 @@ static bool filemap_range_has_writeback(struct address_space *mapping,
 	}
 	rcu_read_unlock();
 	return page != NULL;
-
-}
-
-/**
- * filemap_range_needs_writeback - check if range potentially needs writeback
- * @mapping:           address space within which to check
- * @start_byte:        offset in bytes where the range starts
- * @end_byte:          offset in bytes where the range ends (inclusive)
- *
- * Find at least one page in the range supplied, usually used to check if
- * direct writing in this range will trigger a writeback. Used by O_DIRECT
- * read/write with IOCB_NOWAIT, to see if the caller needs to do
- * filemap_write_and_wait_range() before proceeding.
- *
- * Return: %true if the caller should do filemap_write_and_wait_range() before
- * doing O_DIRECT to a page in this range, %false otherwise.
- */
-bool filemap_range_needs_writeback(struct address_space *mapping,
-				   loff_t start_byte, loff_t end_byte)
-{
-	if (!mapping_needs_writeback(mapping))
-		return false;
-	if (!mapping_tagged(mapping, PAGECACHE_TAG_DIRTY) &&
-	    !mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK))
-		return false;
-	return filemap_range_has_writeback(mapping, start_byte, end_byte);
 }
-EXPORT_SYMBOL_GPL(filemap_range_needs_writeback);
+EXPORT_SYMBOL_GPL(filemap_range_has_writeback);
 
 /**
  * filemap_write_and_wait_range - write out & wait on a file range
-- 
cgit v1.2.3


From 0a467d0fdd9594fbb449ebc93852533332c528fd Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Thu, 14 Oct 2021 14:39:59 -0600
Subject: block: switch to atomic_t for request references

refcount_t is not as expensive as it used to be, but it's still more
expensive than the io_uring method of using atomic_t and just checking
for potential over/underflow.

This borrows that same implementation, which in turn is based on the
mm implementation from Linus.

Reviewed-by: Keith Busch <kbusch@kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-flush.c      |  4 ++--
 block/blk-mq-tag.c     |  2 +-
 block/blk-mq.c         | 12 ++++++------
 block/blk.h            | 31 +++++++++++++++++++++++++++++++
 include/linux/blk-mq.h |  2 +-
 5 files changed, 41 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-flush.c b/block/blk-flush.c
index f78bb39e589e..e4df894189ce 100644
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@@ -229,7 +229,7 @@ static void flush_end_io(struct request *flush_rq, blk_status_t error)
 	/* release the tag's ownership to the req cloned from */
 	spin_lock_irqsave(&fq->mq_flush_lock, flags);
 
-	if (!refcount_dec_and_test(&flush_rq->ref)) {
+	if (!req_ref_put_and_test(flush_rq)) {
 		fq->rq_status = error;
 		spin_unlock_irqrestore(&fq->mq_flush_lock, flags);
 		return;
@@ -349,7 +349,7 @@ static void blk_kick_flush(struct request_queue *q, struct blk_flush_queue *fq,
 	 * and READ flush_rq->end_io
 	 */
 	smp_wmb();
-	refcount_set(&flush_rq->ref, 1);
+	req_ref_set(flush_rq, 1);
 
 	blk_flush_queue_rq(flush_rq, false);
 }
diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index 995336abee33..380e2dd31bfc 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -228,7 +228,7 @@ static struct request *blk_mq_find_and_get_req(struct blk_mq_tags *tags,
 
 	spin_lock_irqsave(&tags->lock, flags);
 	rq = tags->rqs[bitnr];
-	if (!rq || rq->tag != bitnr || !refcount_inc_not_zero(&rq->ref))
+	if (!rq || rq->tag != bitnr || !req_ref_inc_not_zero(rq))
 		rq = NULL;
 	spin_unlock_irqrestore(&tags->lock, flags);
 	return rq;
diff --git a/block/blk-mq.c b/block/blk-mq.c
index fc4520e992b1..8c7cab75229e 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -394,7 +394,7 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data,
 	INIT_LIST_HEAD(&rq->queuelist);
 	/* tag was already set */
 	WRITE_ONCE(rq->deadline, 0);
-	refcount_set(&rq->ref, 1);
+	req_ref_set(rq, 1);
 
 	if (rq->rq_flags & RQF_ELV) {
 		struct elevator_queue *e = data->q->elevator;
@@ -642,7 +642,7 @@ void blk_mq_free_request(struct request *rq)
 	rq_qos_done(q, rq);
 
 	WRITE_ONCE(rq->state, MQ_RQ_IDLE);
-	if (refcount_dec_and_test(&rq->ref))
+	if (req_ref_put_and_test(rq))
 		__blk_mq_free_request(rq);
 }
 EXPORT_SYMBOL_GPL(blk_mq_free_request);
@@ -938,7 +938,7 @@ void blk_mq_end_request_batch(struct io_comp_batch *iob)
 		rq_qos_done(rq->q, rq);
 
 		WRITE_ONCE(rq->state, MQ_RQ_IDLE);
-		if (!refcount_dec_and_test(&rq->ref))
+		if (!req_ref_put_and_test(rq))
 			continue;
 
 		blk_crypto_free_request(rq);
@@ -1401,7 +1401,7 @@ void blk_mq_put_rq_ref(struct request *rq)
 {
 	if (is_flush_rq(rq))
 		rq->end_io(rq, 0);
-	else if (refcount_dec_and_test(&rq->ref))
+	else if (req_ref_put_and_test(rq))
 		__blk_mq_free_request(rq);
 }
 
@@ -3049,7 +3049,7 @@ static void blk_mq_clear_rq_mapping(struct blk_mq_tags *drv_tags,
 			unsigned long rq_addr = (unsigned long)rq;
 
 			if (rq_addr >= start && rq_addr < end) {
-				WARN_ON_ONCE(refcount_read(&rq->ref) != 0);
+				WARN_ON_ONCE(req_ref_read(rq) != 0);
 				cmpxchg(&drv_tags->rqs[i], rq, NULL);
 			}
 		}
@@ -3383,7 +3383,7 @@ static void blk_mq_clear_flush_rq_mapping(struct blk_mq_tags *tags,
 	if (!tags)
 		return;
 
-	WARN_ON_ONCE(refcount_read(&flush_rq->ref) != 0);
+	WARN_ON_ONCE(req_ref_read(flush_rq) != 0);
 
 	for (i = 0; i < queue_depth; i++)
 		cmpxchg(&tags->rqs[i], flush_rq, NULL);
diff --git a/block/blk.h b/block/blk.h
index a55d82c3d1c2..24d8b333bb03 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -461,4 +461,35 @@ static inline bool should_fail_request(struct block_device *part,
 }
 #endif /* CONFIG_FAIL_MAKE_REQUEST */
 
+/*
+ * Optimized request reference counting. Ideally we'd make timeouts be more
+ * clever, as that's the only reason we need references at all... But until
+ * this happens, this is faster than using refcount_t. Also see:
+ *
+ * abc54d634334 ("io_uring: switch to atomic_t for io_kiocb reference count")
+ */
+#define req_ref_zero_or_close_to_overflow(req)	\
+	((unsigned int) atomic_read(&(req->ref)) + 127u <= 127u)
+
+static inline bool req_ref_inc_not_zero(struct request *req)
+{
+	return atomic_inc_not_zero(&req->ref);
+}
+
+static inline bool req_ref_put_and_test(struct request *req)
+{
+	WARN_ON_ONCE(req_ref_zero_or_close_to_overflow(req));
+	return atomic_dec_and_test(&req->ref);
+}
+
+static inline void req_ref_set(struct request *req, int value)
+{
+	atomic_set(&req->ref, value);
+}
+
+static inline int req_ref_read(struct request *req)
+{
+	return atomic_read(&req->ref);
+}
+
 #endif /* BLK_INTERNAL_H */
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 1b87b7c8bbff..561beb5be7ec 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -139,7 +139,7 @@ struct request {
 	unsigned short ioprio;
 
 	enum mq_rq_state state;
-	refcount_t ref;
+	atomic_t ref;
 
 	unsigned long deadline;
 
-- 
cgit v1.2.3


From 704b914f15fb7daaf517e3acc4bed472b50ca19e Mon Sep 17 00:00:00 2001
From: Ming Lei <ming.lei@redhat.com>
Date: Fri, 3 Dec 2021 21:15:32 +0800
Subject: blk-mq: move srcu from blk_mq_hw_ctx to request_queue

In case of BLK_MQ_F_BLOCKING, per-hctx srcu is used to protect dispatch
critical area. However, this srcu instance stays at the end of hctx, and
it often takes standalone cacheline, often cold.

Inside srcu_read_lock() and srcu_read_unlock(), WRITE is always done on
the indirect percpu variable which is allocated from heap instead of
being embedded, srcu->srcu_idx is read only in srcu_read_lock(). It
doesn't matter if srcu structure stays in hctx or request queue.

So switch to per-request-queue srcu for protecting dispatch, and this
way simplifies quiesce a lot, not mention quiesce is always done on the
request queue wide.

Signed-off-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20211203131534.3668411-3-ming.lei@redhat.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-core.c       | 27 ++++++++++++++++++++++-----
 block/blk-mq-sysfs.c   |  2 --
 block/blk-mq.c         | 37 ++++++++-----------------------------
 block/blk-mq.h         |  4 ++--
 block/blk-sysfs.c      |  3 ++-
 block/blk.h            | 10 +++++++++-
 block/genhd.c          |  2 +-
 include/linux/blk-mq.h |  8 --------
 include/linux/blkdev.h |  9 +++++++++
 9 files changed, 53 insertions(+), 49 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-core.c b/block/blk-core.c
index b0660c9df852..10619fd83c1b 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -66,6 +66,7 @@ DEFINE_IDA(blk_queue_ida);
  * For queue allocation
  */
 struct kmem_cache *blk_requestq_cachep;
+struct kmem_cache *blk_requestq_srcu_cachep;
 
 /*
  * Controlling structure to kblockd
@@ -437,21 +438,27 @@ static void blk_timeout_work(struct work_struct *work)
 {
 }
 
-struct request_queue *blk_alloc_queue(int node_id)
+struct request_queue *blk_alloc_queue(int node_id, bool alloc_srcu)
 {
 	struct request_queue *q;
 	int ret;
 
-	q = kmem_cache_alloc_node(blk_requestq_cachep,
-				GFP_KERNEL | __GFP_ZERO, node_id);
+	q = kmem_cache_alloc_node(blk_get_queue_kmem_cache(alloc_srcu),
+			GFP_KERNEL | __GFP_ZERO, node_id);
 	if (!q)
 		return NULL;
 
+	if (alloc_srcu) {
+		blk_queue_flag_set(QUEUE_FLAG_HAS_SRCU, q);
+		if (init_srcu_struct(q->srcu) != 0)
+			goto fail_q;
+	}
+
 	q->last_merge = NULL;
 
 	q->id = ida_simple_get(&blk_queue_ida, 0, 0, GFP_KERNEL);
 	if (q->id < 0)
-		goto fail_q;
+		goto fail_srcu;
 
 	ret = bioset_init(&q->bio_split, BIO_POOL_SIZE, 0, 0);
 	if (ret)
@@ -508,8 +515,11 @@ fail_split:
 	bioset_exit(&q->bio_split);
 fail_id:
 	ida_simple_remove(&blk_queue_ida, q->id);
+fail_srcu:
+	if (alloc_srcu)
+		cleanup_srcu_struct(q->srcu);
 fail_q:
-	kmem_cache_free(blk_requestq_cachep, q);
+	kmem_cache_free(blk_get_queue_kmem_cache(alloc_srcu), q);
 	return NULL;
 }
 
@@ -1301,6 +1311,9 @@ int __init blk_dev_init(void)
 			sizeof_field(struct request, cmd_flags));
 	BUILD_BUG_ON(REQ_OP_BITS + REQ_FLAG_BITS > 8 *
 			sizeof_field(struct bio, bi_opf));
+	BUILD_BUG_ON(ALIGN(offsetof(struct request_queue, srcu),
+			   __alignof__(struct request_queue)) !=
+		     sizeof(struct request_queue));
 
 	/* used for unplugging and affects IO latency/throughput - HIGHPRI */
 	kblockd_workqueue = alloc_workqueue("kblockd",
@@ -1311,6 +1324,10 @@ int __init blk_dev_init(void)
 	blk_requestq_cachep = kmem_cache_create("request_queue",
 			sizeof(struct request_queue), 0, SLAB_PANIC, NULL);
 
+	blk_requestq_srcu_cachep = kmem_cache_create("request_queue_srcu",
+			sizeof(struct request_queue) +
+			sizeof(struct srcu_struct), 0, SLAB_PANIC, NULL);
+
 	blk_debugfs_root = debugfs_create_dir("block", NULL);
 
 	return 0;
diff --git a/block/blk-mq-sysfs.c b/block/blk-mq-sysfs.c
index 253c857cba47..674786574075 100644
--- a/block/blk-mq-sysfs.c
+++ b/block/blk-mq-sysfs.c
@@ -36,8 +36,6 @@ static void blk_mq_hw_sysfs_release(struct kobject *kobj)
 	struct blk_mq_hw_ctx *hctx = container_of(kobj, struct blk_mq_hw_ctx,
 						  kobj);
 
-	if (hctx->flags & BLK_MQ_F_BLOCKING)
-		cleanup_srcu_struct(hctx->srcu);
 	blk_free_flush_queue(hctx->fq);
 	sbitmap_free(&hctx->ctx_map);
 	free_cpumask_var(hctx->cpumask);
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 494da31dc1a5..6a2c2704454e 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -260,17 +260,9 @@ EXPORT_SYMBOL_GPL(blk_mq_quiesce_queue_nowait);
  */
 void blk_mq_wait_quiesce_done(struct request_queue *q)
 {
-	struct blk_mq_hw_ctx *hctx;
-	unsigned int i;
-	bool rcu = false;
-
-	queue_for_each_hw_ctx(q, hctx, i) {
-		if (hctx->flags & BLK_MQ_F_BLOCKING)
-			synchronize_srcu(hctx->srcu);
-		else
-			rcu = true;
-	}
-	if (rcu)
+	if (blk_queue_has_srcu(q))
+		synchronize_srcu(q->srcu);
+	else
 		synchronize_rcu();
 }
 EXPORT_SYMBOL_GPL(blk_mq_wait_quiesce_done);
@@ -3400,20 +3392,6 @@ static void blk_mq_exit_hw_queues(struct request_queue *q,
 	}
 }
 
-static int blk_mq_hw_ctx_size(struct blk_mq_tag_set *tag_set)
-{
-	int hw_ctx_size = sizeof(struct blk_mq_hw_ctx);
-
-	BUILD_BUG_ON(ALIGN(offsetof(struct blk_mq_hw_ctx, srcu),
-			   __alignof__(struct blk_mq_hw_ctx)) !=
-		     sizeof(struct blk_mq_hw_ctx));
-
-	if (tag_set->flags & BLK_MQ_F_BLOCKING)
-		hw_ctx_size += sizeof(struct srcu_struct);
-
-	return hw_ctx_size;
-}
-
 static int blk_mq_init_hctx(struct request_queue *q,
 		struct blk_mq_tag_set *set,
 		struct blk_mq_hw_ctx *hctx, unsigned hctx_idx)
@@ -3451,7 +3429,7 @@ blk_mq_alloc_hctx(struct request_queue *q, struct blk_mq_tag_set *set,
 	struct blk_mq_hw_ctx *hctx;
 	gfp_t gfp = GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY;
 
-	hctx = kzalloc_node(blk_mq_hw_ctx_size(set), gfp, node);
+	hctx = kzalloc_node(sizeof(struct blk_mq_hw_ctx), gfp, node);
 	if (!hctx)
 		goto fail_alloc_hctx;
 
@@ -3493,8 +3471,6 @@ blk_mq_alloc_hctx(struct request_queue *q, struct blk_mq_tag_set *set,
 	if (!hctx->fq)
 		goto free_bitmap;
 
-	if (hctx->flags & BLK_MQ_F_BLOCKING)
-		init_srcu_struct(hctx->srcu);
 	blk_mq_hctx_kobj_init(hctx);
 
 	return hctx;
@@ -3830,7 +3806,7 @@ static struct request_queue *blk_mq_init_queue_data(struct blk_mq_tag_set *set,
 	struct request_queue *q;
 	int ret;
 
-	q = blk_alloc_queue(set->numa_node);
+	q = blk_alloc_queue(set->numa_node, set->flags & BLK_MQ_F_BLOCKING);
 	if (!q)
 		return ERR_PTR(-ENOMEM);
 	q->queuedata = queuedata;
@@ -3979,6 +3955,9 @@ static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set,
 int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
 		struct request_queue *q)
 {
+	WARN_ON_ONCE(blk_queue_has_srcu(q) !=
+			!!(set->flags & BLK_MQ_F_BLOCKING));
+
 	/* mark the queue as mq asap */
 	q->mq_ops = set->ops;
 
diff --git a/block/blk-mq.h b/block/blk-mq.h
index e4c396204928..792f0b29c6eb 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -385,9 +385,9 @@ do {								\
 		int srcu_idx;					\
 								\
 		might_sleep();					\
-		srcu_idx = srcu_read_lock((hctx)->srcu);	\
+		srcu_idx = srcu_read_lock((hctx)->queue->srcu);	\
 		(dispatch_ops);					\
-		srcu_read_unlock((hctx)->srcu, srcu_idx);	\
+		srcu_read_unlock((hctx)->queue->srcu, srcu_idx); \
 	}							\
 } while (0)
 
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 4622da4bb992..3e6357321225 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -735,7 +735,8 @@ static void blk_free_queue_rcu(struct rcu_head *rcu_head)
 {
 	struct request_queue *q = container_of(rcu_head, struct request_queue,
 					       rcu_head);
-	kmem_cache_free(blk_requestq_cachep, q);
+
+	kmem_cache_free(blk_get_queue_kmem_cache(blk_queue_has_srcu(q)), q);
 }
 
 /* Unconfigure the I/O scheduler and dissociate from the cgroup controller. */
diff --git a/block/blk.h b/block/blk.h
index 24d8b333bb03..7ccb7c7d86b3 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -27,6 +27,7 @@ struct blk_flush_queue {
 };
 
 extern struct kmem_cache *blk_requestq_cachep;
+extern struct kmem_cache *blk_requestq_srcu_cachep;
 extern struct kobj_type blk_queue_ktype;
 extern struct ida blk_queue_ida;
 
@@ -424,7 +425,14 @@ int bio_add_hw_page(struct request_queue *q, struct bio *bio,
 		struct page *page, unsigned int len, unsigned int offset,
 		unsigned int max_sectors, bool *same_page);
 
-struct request_queue *blk_alloc_queue(int node_id);
+static inline struct kmem_cache *blk_get_queue_kmem_cache(bool srcu)
+{
+	if (srcu)
+		return blk_requestq_srcu_cachep;
+	return blk_requestq_cachep;
+}
+struct request_queue *blk_alloc_queue(int node_id, bool alloc_srcu);
+
 int disk_scan_partitions(struct gendisk *disk, fmode_t mode);
 
 int disk_alloc_events(struct gendisk *disk);
diff --git a/block/genhd.c b/block/genhd.c
index 5179a4f00fba..3c139a1b6f04 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -1338,7 +1338,7 @@ struct gendisk *__blk_alloc_disk(int node, struct lock_class_key *lkclass)
 	struct request_queue *q;
 	struct gendisk *disk;
 
-	q = blk_alloc_queue(node);
+	q = blk_alloc_queue(node, false);
 	if (!q)
 		return NULL;
 
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 561beb5be7ec..ecdc049b52fa 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -4,7 +4,6 @@
 
 #include <linux/blkdev.h>
 #include <linux/sbitmap.h>
-#include <linux/srcu.h>
 #include <linux/lockdep.h>
 #include <linux/scatterlist.h>
 #include <linux/prefetch.h>
@@ -375,13 +374,6 @@ struct blk_mq_hw_ctx {
 	 * q->unused_hctx_list.
 	 */
 	struct list_head	hctx_list;
-
-	/**
-	 * @srcu: Sleepable RCU. Use as lock when type of the hardware queue is
-	 * blocking (BLK_MQ_F_BLOCKING). Must be the last member - see also
-	 * blk_mq_hw_ctx_size().
-	 */
-	struct srcu_struct	srcu[];
 };
 
 /**
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 0a4416ef4fbf..c80cfaefc0a8 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -16,6 +16,7 @@
 #include <linux/percpu-refcount.h>
 #include <linux/blkzoned.h>
 #include <linux/sbitmap.h>
+#include <linux/srcu.h>
 
 struct module;
 struct request_queue;
@@ -373,11 +374,18 @@ struct request_queue {
 	 * devices that do not have multiple independent access ranges.
 	 */
 	struct blk_independent_access_ranges *ia_ranges;
+
+	/**
+	 * @srcu: Sleepable RCU. Use as lock when type of the request queue
+	 * is blocking (BLK_MQ_F_BLOCKING). Must be the last member
+	 */
+	struct srcu_struct	srcu[];
 };
 
 /* Keep blk_queue_flag_name[] in sync with the definitions below */
 #define QUEUE_FLAG_STOPPED	0	/* queue is stopped */
 #define QUEUE_FLAG_DYING	1	/* queue being torn down */
+#define QUEUE_FLAG_HAS_SRCU	2	/* SRCU is allocated */
 #define QUEUE_FLAG_NOMERGES     3	/* disable merge attempts */
 #define QUEUE_FLAG_SAME_COMP	4	/* complete on same CPU-group */
 #define QUEUE_FLAG_FAIL_IO	5	/* fake timeout */
@@ -415,6 +423,7 @@ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q);
 
 #define blk_queue_stopped(q)	test_bit(QUEUE_FLAG_STOPPED, &(q)->queue_flags)
 #define blk_queue_dying(q)	test_bit(QUEUE_FLAG_DYING, &(q)->queue_flags)
+#define blk_queue_has_srcu(q)	test_bit(QUEUE_FLAG_HAS_SRCU, &(q)->queue_flags)
 #define blk_queue_dead(q)	test_bit(QUEUE_FLAG_DEAD, &(q)->queue_flags)
 #define blk_queue_init_done(q)	test_bit(QUEUE_FLAG_INIT_DONE, &(q)->queue_flags)
 #define blk_queue_nomerges(q)	test_bit(QUEUE_FLAG_NOMERGES, &(q)->queue_flags)
-- 
cgit v1.2.3


From 8ab30a331946c34e4ba022c44df8624acea1c74e Mon Sep 17 00:00:00 2001
From: John Garry <john.garry@huawei.com>
Date: Mon, 6 Dec 2021 20:49:48 +0800
Subject: blk-mq: Drop busy_iter_fn blk_mq_hw_ctx argument

The only user of blk_mq_hw_ctx blk_mq_hw_ctx argument is
blk_mq_rq_inflight().

Function blk_mq_rq_inflight() uses the hctx to find the associated request
queue to match against the request. However this same check is already
done in caller bt_iter(), so drop this check.

With that change there are no more users of busy_iter_fn blk_mq_hw_ctx
argument, so drop the argument.

Reviewed-by Hannes Reinecke <hare@suse.de>

Signed-off-by: John Garry <john.garry@huawei.com>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Tested-by: Kashyap Desai <kashyap.desai@broadcom.com>
Link: https://lore.kernel.org/r/1638794990-137490-2-git-send-email-john.garry@huawei.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-mq-tag.c     |  2 +-
 block/blk-mq.c         | 17 ++++++++---------
 include/linux/blk-mq.h |  3 +--
 3 files changed, 10 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index 380e2dd31bfc..d3cf91d764d5 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -254,7 +254,7 @@ static bool bt_iter(struct sbitmap *bitmap, unsigned int bitnr, void *data)
 		return true;
 
 	if (rq->q == hctx->queue && rq->mq_hctx == hctx)
-		ret = iter_data->fn(hctx, rq, iter_data->data, reserved);
+		ret = iter_data->fn(rq, iter_data->data, reserved);
 	blk_mq_put_rq_ref(rq);
 	return ret;
 }
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 0bf3523dd1f5..103c0f58853c 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -127,8 +127,7 @@ struct mq_inflight {
 	unsigned int inflight[2];
 };
 
-static bool blk_mq_check_inflight(struct blk_mq_hw_ctx *hctx,
-				  struct request *rq, void *priv,
+static bool blk_mq_check_inflight(struct request *rq, void *priv,
 				  bool reserved)
 {
 	struct mq_inflight *mi = priv;
@@ -1308,14 +1307,15 @@ void blk_mq_delay_kick_requeue_list(struct request_queue *q,
 }
 EXPORT_SYMBOL(blk_mq_delay_kick_requeue_list);
 
-static bool blk_mq_rq_inflight(struct blk_mq_hw_ctx *hctx, struct request *rq,
-			       void *priv, bool reserved)
+static bool blk_mq_rq_inflight(struct request *rq, void *priv,
+			       bool reserved)
 {
 	/*
-	 * If we find a request that isn't idle and the queue matches,
-	 * we know the queue is busy. Return false to stop the iteration.
+	 * If we find a request that isn't idle we know the queue is busy
+	 * as it's checked in the iter.
+	 * Return false to stop the iteration.
 	 */
-	if (blk_mq_request_started(rq) && rq->q == hctx->queue) {
+	if (blk_mq_request_started(rq)) {
 		bool *busy = priv;
 
 		*busy = true;
@@ -1377,8 +1377,7 @@ void blk_mq_put_rq_ref(struct request *rq)
 		__blk_mq_free_request(rq);
 }
 
-static bool blk_mq_check_expired(struct blk_mq_hw_ctx *hctx,
-		struct request *rq, void *priv, bool reserved)
+static bool blk_mq_check_expired(struct request *rq, void *priv, bool reserved)
 {
 	unsigned long *next = priv;
 
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index ecdc049b52fa..17ebf29e42d8 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -470,8 +470,7 @@ struct blk_mq_queue_data {
 	bool last;
 };
 
-typedef bool (busy_iter_fn)(struct blk_mq_hw_ctx *, struct request *, void *,
-		bool);
+typedef bool (busy_iter_fn)(struct request *, void *, bool);
 typedef bool (busy_tag_iter_fn)(struct request *, void *, bool);
 
 /**
-- 
cgit v1.2.3


From fc39f8d2d1c10ac04976b0a247865bb0cec4dd88 Mon Sep 17 00:00:00 2001
From: John Garry <john.garry@huawei.com>
Date: Mon, 6 Dec 2021 20:49:49 +0800
Subject: blk-mq: Delete busy_iter_fn

Typedefs busy_iter_fn and busy_tag_iter_fn are now identical, so delete
busy_iter_fn to reduce duplication.

It would be nicer to delete busy_tag_iter_fn, as the name busy_iter_fn is
less specific.

However busy_tag_iter_fn is used in many different parts of the tree,
unlike busy_iter_fn which is just use in block/, so just take the
straightforward path now, so that we could rename later treewide.

Signed-off-by: John Garry <john.garry@huawei.com>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Tested-by: Kashyap Desai <kashyap.desai@broadcom.com>
Link: https://lore.kernel.org/r/1638794990-137490-3-git-send-email-john.garry@huawei.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-mq-tag.c     | 6 +++---
 block/blk-mq-tag.h     | 2 +-
 include/linux/blk-mq.h | 1 -
 3 files changed, 4 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index d3cf91d764d5..58b80d4b7a07 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -215,7 +215,7 @@ void blk_mq_put_tags(struct blk_mq_tags *tags, int *tag_array, int nr_tags)
 
 struct bt_iter_data {
 	struct blk_mq_hw_ctx *hctx;
-	busy_iter_fn *fn;
+	busy_tag_iter_fn *fn;
 	void *data;
 	bool reserved;
 };
@@ -274,7 +274,7 @@ static bool bt_iter(struct sbitmap *bitmap, unsigned int bitnr, void *data)
  *		bitmap_tags member of struct blk_mq_tags.
  */
 static void bt_for_each(struct blk_mq_hw_ctx *hctx, struct sbitmap_queue *bt,
-			busy_iter_fn *fn, void *data, bool reserved)
+			busy_tag_iter_fn *fn, void *data, bool reserved)
 {
 	struct bt_iter_data iter_data = {
 		.hctx = hctx,
@@ -457,7 +457,7 @@ EXPORT_SYMBOL(blk_mq_tagset_wait_completed_request);
  * called for all requests on all queues that share that tag set and not only
  * for requests associated with @q.
  */
-void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_iter_fn *fn,
+void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_tag_iter_fn *fn,
 		void *priv)
 {
 	struct blk_mq_hw_ctx *hctx;
diff --git a/block/blk-mq-tag.h b/block/blk-mq-tag.h
index df787b5a23bd..5668e28be0b7 100644
--- a/block/blk-mq-tag.h
+++ b/block/blk-mq-tag.h
@@ -28,7 +28,7 @@ extern void blk_mq_tag_resize_shared_tags(struct blk_mq_tag_set *set,
 extern void blk_mq_tag_update_sched_shared_tags(struct request_queue *q);
 
 extern void blk_mq_tag_wakeup_all(struct blk_mq_tags *tags, bool);
-void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_iter_fn *fn,
+void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_tag_iter_fn *fn,
 		void *priv);
 void blk_mq_all_tag_iter(struct blk_mq_tags *tags, busy_tag_iter_fn *fn,
 		void *priv);
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 17ebf29e42d8..772f8f921526 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -470,7 +470,6 @@ struct blk_mq_queue_data {
 	bool last;
 };
 
-typedef bool (busy_iter_fn)(struct request *, void *, bool);
 typedef bool (busy_tag_iter_fn)(struct request *, void *, bool);
 
 /**
-- 
cgit v1.2.3


From 3c67d44de787dff288d7f2a51c372b22f7356db6 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Fri, 3 Dec 2021 06:48:53 -0700
Subject: block: add mq_ops->queue_rqs hook

If we have a list of requests in our plug list, send it to the driver in
one go, if possible. The driver must set mq_ops->queue_rqs() to support
this, if not the usual one-by-one path is used.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-mq.c         | 26 +++++++++++++++++++++++---
 include/linux/blk-mq.h |  8 ++++++++
 2 files changed, 31 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-mq.c b/block/blk-mq.c
index 75154cc788db..51991232824a 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -2553,6 +2553,7 @@ void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule)
 {
 	struct blk_mq_hw_ctx *this_hctx;
 	struct blk_mq_ctx *this_ctx;
+	struct request *rq;
 	unsigned int depth;
 	LIST_HEAD(list);
 
@@ -2561,7 +2562,28 @@ void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule)
 	plug->rq_count = 0;
 
 	if (!plug->multiple_queues && !plug->has_elevator && !from_schedule) {
-		struct request_queue *q = rq_list_peek(&plug->mq_list)->q;
+		struct request_queue *q;
+
+		rq = rq_list_peek(&plug->mq_list);
+		q = rq->q;
+
+		/*
+		 * Peek first request and see if we have a ->queue_rqs() hook.
+		 * If we do, we can dispatch the whole plug list in one go. We
+		 * already know at this point that all requests belong to the
+		 * same queue, caller must ensure that's the case.
+		 *
+		 * Since we pass off the full list to the driver at this point,
+		 * we do not increment the active request count for the queue.
+		 * Bypass shared tags for now because of that.
+		 */
+		if (q->mq_ops->queue_rqs &&
+		    !(rq->mq_hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED)) {
+			blk_mq_run_dispatch_ops(q,
+				q->mq_ops->queue_rqs(&plug->mq_list));
+			if (rq_list_empty(plug->mq_list))
+				return;
+		}
 
 		blk_mq_run_dispatch_ops(q,
 				blk_mq_plug_issue_direct(plug, false));
@@ -2573,8 +2595,6 @@ void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule)
 	this_ctx = NULL;
 	depth = 0;
 	do {
-		struct request *rq;
-
 		rq = rq_list_pop(&plug->mq_list);
 
 		if (!this_hctx) {
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 772f8f921526..550996cf419c 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -492,6 +492,14 @@ struct blk_mq_ops {
 	 */
 	void (*commit_rqs)(struct blk_mq_hw_ctx *);
 
+	/**
+	 * @queue_rqs: Queue a list of new requests. Driver is guaranteed
+	 * that each request belongs to the same queue. If the driver doesn't
+	 * empty the @rqlist completely, then the rest will be queued
+	 * individually by the block layer upon return.
+	 */
+	void (*queue_rqs)(struct request **rqlist);
+
 	/**
 	 * @get_budget: Reserve budget before queue request, once .queue_rq is
 	 * run, it is driver's responsibility to release the
-- 
cgit v1.2.3


From 8a2ba1785c5803d59a63b6320ff54fd4a37a41ce Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 9 Dec 2021 07:31:21 +0100
Subject: block: remove the nr_task field from struct io_context

Nothing ever looks at ->nr_tasks, so remove it.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jan Kara <jack@suse.cz>
Link: https://lore.kernel.org/r/20211209063131.18537-2-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-ioc.c           | 3 ---
 include/linux/iocontext.h | 1 -
 2 files changed, 4 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-ioc.c b/block/blk-ioc.c
index 536fb496ad76..96336c2134ef 100644
--- a/block/blk-ioc.c
+++ b/block/blk-ioc.c
@@ -207,7 +207,6 @@ void exit_io_context(struct task_struct *task)
 	task->io_context = NULL;
 	task_unlock(task);
 
-	atomic_dec(&ioc->nr_tasks);
 	put_io_context_active(ioc);
 }
 
@@ -259,7 +258,6 @@ static struct io_context *alloc_io_context(gfp_t gfp_flags, int node)
 		return NULL;
 
 	atomic_long_set(&ioc->refcount, 1);
-	atomic_set(&ioc->nr_tasks, 1);
 	atomic_set(&ioc->active_ref, 1);
 	spin_lock_init(&ioc->lock);
 	INIT_RADIX_TREE(&ioc->icq_tree, GFP_ATOMIC);
@@ -339,7 +337,6 @@ int __copy_io(unsigned long clone_flags, struct task_struct *tsk)
 	if (clone_flags & CLONE_IO) {
 		atomic_long_inc(&ioc->refcount);
 		atomic_inc(&ioc->active_ref);
-		atomic_inc(&ioc->nr_tasks);
 		tsk->io_context = ioc;
 	} else if (ioprio_valid(ioc->ioprio)) {
 		tsk->io_context = alloc_io_context(GFP_KERNEL, NUMA_NO_NODE);
diff --git a/include/linux/iocontext.h b/include/linux/iocontext.h
index c1229fbd6691..82c7f4f5f4f5 100644
--- a/include/linux/iocontext.h
+++ b/include/linux/iocontext.h
@@ -99,7 +99,6 @@ struct io_cq {
 struct io_context {
 	atomic_long_t refcount;
 	atomic_t active_ref;
-	atomic_t nr_tasks;
 
 	/* all the fields below are protected by this lock */
 	spinlock_t lock;
-- 
cgit v1.2.3


From a411cd3cfdc5bbd1329d5b33dbf39e2b5213969d Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 9 Dec 2021 07:31:27 +0100
Subject: block: move set_task_ioprio to blk-ioc.c

Keep set_task_ioprio with the other low-level code that accesses the
io_context structure.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jan Kara <jack@suse.cz>
Link: https://lore.kernel.org/r/20211209063131.18537-8-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-ioc.c           | 34 ++++++++++++++++++++++++++++++++--
 block/ioprio.c            | 32 --------------------------------
 include/linux/iocontext.h |  2 --
 3 files changed, 32 insertions(+), 36 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-ioc.c b/block/blk-ioc.c
index f98a29ee8f36..c25ce2f3eb19 100644
--- a/block/blk-ioc.c
+++ b/block/blk-ioc.c
@@ -8,6 +8,7 @@
 #include <linux/bio.h>
 #include <linux/blkdev.h>
 #include <linux/slab.h>
+#include <linux/security.h>
 #include <linux/sched/task.h>
 
 #include "blk.h"
@@ -280,8 +281,8 @@ static struct io_context *create_task_io_context(struct task_struct *task,
  * This function always goes through task_lock() and it's better to use
  * %current->io_context + get_io_context() for %current.
  */
-struct io_context *get_task_io_context(struct task_struct *task,
-				       gfp_t gfp_flags, int node)
+static struct io_context *get_task_io_context(struct task_struct *task,
+		gfp_t gfp_flags, int node)
 {
 	struct io_context *ioc;
 
@@ -298,6 +299,35 @@ struct io_context *get_task_io_context(struct task_struct *task,
 	return ioc;
 }
 
+int set_task_ioprio(struct task_struct *task, int ioprio)
+{
+	int err;
+	struct io_context *ioc;
+	const struct cred *cred = current_cred(), *tcred;
+
+	rcu_read_lock();
+	tcred = __task_cred(task);
+	if (!uid_eq(tcred->uid, cred->euid) &&
+	    !uid_eq(tcred->uid, cred->uid) && !capable(CAP_SYS_NICE)) {
+		rcu_read_unlock();
+		return -EPERM;
+	}
+	rcu_read_unlock();
+
+	err = security_task_setioprio(task, ioprio);
+	if (err)
+		return err;
+
+	ioc = get_task_io_context(task, GFP_ATOMIC, NUMA_NO_NODE);
+	if (ioc) {
+		ioc->ioprio = ioprio;
+		put_io_context(ioc);
+	}
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(set_task_ioprio);
+
 int __copy_io(unsigned long clone_flags, struct task_struct *tsk)
 {
 	struct io_context *ioc = current->io_context;
diff --git a/block/ioprio.c b/block/ioprio.c
index 313c14a70bbd..e118f4bf2dc6 100644
--- a/block/ioprio.c
+++ b/block/ioprio.c
@@ -22,46 +22,14 @@
  */
 #include <linux/gfp.h>
 #include <linux/kernel.h>
-#include <linux/export.h>
 #include <linux/ioprio.h>
 #include <linux/cred.h>
 #include <linux/blkdev.h>
 #include <linux/capability.h>
-#include <linux/sched/user.h>
-#include <linux/sched/task.h>
 #include <linux/syscalls.h>
 #include <linux/security.h>
 #include <linux/pid_namespace.h>
 
-int set_task_ioprio(struct task_struct *task, int ioprio)
-{
-	int err;
-	struct io_context *ioc;
-	const struct cred *cred = current_cred(), *tcred;
-
-	rcu_read_lock();
-	tcred = __task_cred(task);
-	if (!uid_eq(tcred->uid, cred->euid) &&
-	    !uid_eq(tcred->uid, cred->uid) && !capable(CAP_SYS_NICE)) {
-		rcu_read_unlock();
-		return -EPERM;
-	}
-	rcu_read_unlock();
-
-	err = security_task_setioprio(task, ioprio);
-	if (err)
-		return err;
-
-	ioc = get_task_io_context(task, GFP_ATOMIC, NUMA_NO_NODE);
-	if (ioc) {
-		ioc->ioprio = ioprio;
-		put_io_context(ioc);
-	}
-
-	return err;
-}
-EXPORT_SYMBOL_GPL(set_task_ioprio);
-
 int ioprio_check_cap(int ioprio)
 {
 	int class = IOPRIO_PRIO_CLASS(ioprio);
diff --git a/include/linux/iocontext.h b/include/linux/iocontext.h
index 82c7f4f5f4f5..648331f35fc6 100644
--- a/include/linux/iocontext.h
+++ b/include/linux/iocontext.h
@@ -116,8 +116,6 @@ struct task_struct;
 #ifdef CONFIG_BLOCK
 void put_io_context(struct io_context *ioc);
 void exit_io_context(struct task_struct *task);
-struct io_context *get_task_io_context(struct task_struct *task,
-				       gfp_t gfp_flags, int node);
 int __copy_io(unsigned long clone_flags, struct task_struct *tsk);
 static inline int copy_io(unsigned long clone_flags, struct task_struct *tsk)
 {
-- 
cgit v1.2.3


From 5ef1630586317e92c9ebd7b4ce48f393b7ff790f Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 9 Dec 2021 07:31:31 +0100
Subject: block: only build the icq tracking code when needed

Only bfq needs to code to track icq, so make it conditional.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jan Kara <jack@suse.cz>
Link: https://lore.kernel.org/r/20211209063131.18537-12-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/Kconfig             |  3 +++
 block/Kconfig.iosched     |  1 +
 block/blk-ioc.c           | 68 ++++++++++++++++++++++++++++-------------------
 block/blk.h               |  6 +++++
 include/linux/iocontext.h |  6 +++--
 5 files changed, 55 insertions(+), 29 deletions(-)

(limited to 'include/linux')

diff --git a/block/Kconfig b/block/Kconfig
index c6ce41a5e5b2..d5d4197b7ed2 100644
--- a/block/Kconfig
+++ b/block/Kconfig
@@ -35,6 +35,9 @@ config BLK_CGROUP_RWSTAT
 config BLK_DEV_BSG_COMMON
 	tristate
 
+config BLK_ICQ
+	bool
+
 config BLK_DEV_BSGLIB
 	bool "Block layer SG support v4 helper lib"
 	select BLK_DEV_BSG_COMMON
diff --git a/block/Kconfig.iosched b/block/Kconfig.iosched
index 885fee86dfca..615516146086 100644
--- a/block/Kconfig.iosched
+++ b/block/Kconfig.iosched
@@ -18,6 +18,7 @@ config MQ_IOSCHED_KYBER
 
 config IOSCHED_BFQ
 	tristate "BFQ I/O scheduler"
+	select BLK_ICQ
 	help
 	BFQ I/O scheduler for BLK-MQ. BFQ distributes the bandwidth of
 	of the device among all processes according to their weights,
diff --git a/block/blk-ioc.c b/block/blk-ioc.c
index dc7fb064fd5f..87bdc9ca8295 100644
--- a/block/blk-ioc.c
+++ b/block/blk-ioc.c
@@ -19,6 +19,7 @@
  */
 static struct kmem_cache *iocontext_cachep;
 
+#ifdef CONFIG_BLK_ICQ
 /**
  * get_io_context - increment reference count to io_context
  * @ioc: io_context to get
@@ -162,6 +163,42 @@ static bool ioc_delay_free(struct io_context *ioc)
 	return false;
 }
 
+/**
+ * ioc_clear_queue - break any ioc association with the specified queue
+ * @q: request_queue being cleared
+ *
+ * Walk @q->icq_list and exit all io_cq's.
+ */
+void ioc_clear_queue(struct request_queue *q)
+{
+	LIST_HEAD(icq_list);
+
+	spin_lock_irq(&q->queue_lock);
+	list_splice_init(&q->icq_list, &icq_list);
+	spin_unlock_irq(&q->queue_lock);
+
+	rcu_read_lock();
+	while (!list_empty(&icq_list)) {
+		struct io_cq *icq =
+			list_entry(icq_list.next, struct io_cq, q_node);
+
+		spin_lock_irq(&icq->ioc->lock);
+		if (!(icq->flags & ICQ_DESTROYED))
+			ioc_destroy_icq(icq);
+		spin_unlock_irq(&icq->ioc->lock);
+	}
+	rcu_read_unlock();
+}
+#else /* CONFIG_BLK_ICQ */
+static inline void ioc_exit_icqs(struct io_context *ioc)
+{
+}
+static inline bool ioc_delay_free(struct io_context *ioc)
+{
+	return false;
+}
+#endif /* CONFIG_BLK_ICQ */
+
 /**
  * put_io_context - put a reference of io_context
  * @ioc: io_context to put
@@ -193,33 +230,6 @@ void exit_io_context(struct task_struct *task)
 	}
 }
 
-/**
- * ioc_clear_queue - break any ioc association with the specified queue
- * @q: request_queue being cleared
- *
- * Walk @q->icq_list and exit all io_cq's.
- */
-void ioc_clear_queue(struct request_queue *q)
-{
-	LIST_HEAD(icq_list);
-
-	spin_lock_irq(&q->queue_lock);
-	list_splice_init(&q->icq_list, &icq_list);
-	spin_unlock_irq(&q->queue_lock);
-
-	rcu_read_lock();
-	while (!list_empty(&icq_list)) {
-		struct io_cq *icq =
-			list_entry(icq_list.next, struct io_cq, q_node);
-
-		spin_lock_irq(&icq->ioc->lock);
-		if (!(icq->flags & ICQ_DESTROYED))
-			ioc_destroy_icq(icq);
-		spin_unlock_irq(&icq->ioc->lock);
-	}
-	rcu_read_unlock();
-}
-
 static struct io_context *alloc_io_context(gfp_t gfp_flags, int node)
 {
 	struct io_context *ioc;
@@ -231,10 +241,12 @@ static struct io_context *alloc_io_context(gfp_t gfp_flags, int node)
 
 	atomic_long_set(&ioc->refcount, 1);
 	atomic_set(&ioc->active_ref, 1);
+#ifdef CONFIG_BLK_ICQ
 	spin_lock_init(&ioc->lock);
 	INIT_RADIX_TREE(&ioc->icq_tree, GFP_ATOMIC);
 	INIT_HLIST_HEAD(&ioc->icq_list);
 	INIT_WORK(&ioc->release_work, ioc_release_fn);
+#endif
 	return ioc;
 }
 
@@ -300,6 +312,7 @@ int __copy_io(unsigned long clone_flags, struct task_struct *tsk)
 	return 0;
 }
 
+#ifdef CONFIG_BLK_ICQ
 /**
  * ioc_lookup_icq - lookup io_cq from ioc
  * @q: the associated request_queue
@@ -428,6 +441,7 @@ struct io_cq *ioc_find_get_icq(struct request_queue *q)
 	return icq;
 }
 EXPORT_SYMBOL_GPL(ioc_find_get_icq);
+#endif /* CONFIG_BLK_ICQ */
 
 static int __init blk_ioc_init(void)
 {
diff --git a/block/blk.h b/block/blk.h
index 7ccb7c7d86b3..8bd43b3ad33d 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -366,7 +366,13 @@ static inline unsigned int bio_aligned_discard_max_sectors(
  */
 struct io_cq *ioc_find_get_icq(struct request_queue *q);
 struct io_cq *ioc_lookup_icq(struct request_queue *q);
+#ifdef CONFIG_BLK_ICQ
 void ioc_clear_queue(struct request_queue *q);
+#else
+static inline void ioc_clear_queue(struct request_queue *q)
+{
+}
+#endif /* CONFIG_BLK_ICQ */
 
 #ifdef CONFIG_BLK_DEV_THROTTLING_LOW
 extern ssize_t blk_throtl_sample_time_show(struct request_queue *q, char *page);
diff --git a/include/linux/iocontext.h b/include/linux/iocontext.h
index 648331f35fc6..14f7eaf1b443 100644
--- a/include/linux/iocontext.h
+++ b/include/linux/iocontext.h
@@ -100,16 +100,18 @@ struct io_context {
 	atomic_long_t refcount;
 	atomic_t active_ref;
 
+	unsigned short ioprio;
+
+#ifdef CONFIG_BLK_ICQ
 	/* all the fields below are protected by this lock */
 	spinlock_t lock;
 
-	unsigned short ioprio;
-
 	struct radix_tree_root	icq_tree;
 	struct io_cq __rcu	*icq_hint;
 	struct hlist_head	icq_list;
 
 	struct work_struct release_work;
+#endif /* CONFIG_BLK_ICQ */
 };
 
 struct task_struct;
-- 
cgit v1.2.3


From 37ae5a0f5287a52cf51242e76ccf198d02ffe495 Mon Sep 17 00:00:00 2001
From: Tetsuo Handa <penguin-kernel@i-love.sakura.ne.jp>
Date: Sat, 18 Dec 2021 18:41:56 +0900
Subject: block: use "unsigned long" for blk_validate_block_size().

Since lo_simple_ioctl(LOOP_SET_BLOCK_SIZE) and ioctl(NBD_SET_BLKSIZE) pass
user-controlled "unsigned long arg" to blk_validate_block_size(),
"unsigned long" should be used for validation.

Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/9ecbf057-4375-c2db-ab53-e4cc0dff953d@i-love.sakura.ne.jp
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/blkdev.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index c80cfaefc0a8..bb5fb7282e6e 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -45,7 +45,7 @@ struct blk_crypto_profile;
  */
 #define BLKCG_MAX_POLS		6
 
-static inline int blk_validate_block_size(unsigned int bsize)
+static inline int blk_validate_block_size(unsigned long bsize)
 {
 	if (bsize < 512 || bsize > PAGE_SIZE || !is_power_of_2(bsize))
 		return -EINVAL;
-- 
cgit v1.2.3


From 6fd3c510ee4b37f2f9fe3d3cafbfa459e15c5e11 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Wed, 22 Dec 2021 13:15:32 -0800
Subject: bio.h: fix kernel-doc warnings

Fix all kernel-doc warnings in <linux/bio.h>:

include/linux/bio.h:136: warning: Function parameter or member 'nbytes' not described in 'bio_advance'
include/linux/bio.h:136: warning: Excess function parameter 'bytes' description in 'bio_advance'
include/linux/bio.h:391: warning: No description found for return value of 'bio_next_split'

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Kent Overstreet <kent.overstreet@gmail.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: linux-block@vger.kernel.org
Link: https://lore.kernel.org/r/20211222211532.24060-1-rdunlap@infradead.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/bio.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bio.h b/include/linux/bio.h
index fe6bdfbbef66..0a41efe02208 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -124,7 +124,7 @@ void __bio_advance(struct bio *, unsigned bytes);
 /**
  * bio_advance - increment/complete a bio by some number of bytes
  * @bio:	bio to advance
- * @bytes:	number of bytes to complete
+ * @nbytes:	number of bytes to complete
  *
  * This updates bi_sector, bi_size and bi_idx; if the number of bytes to
  * complete doesn't align with a bvec boundary, then bv_len and bv_offset will
@@ -332,7 +332,7 @@ extern struct bio *bio_split(struct bio *bio, int sectors,
  * @gfp:	gfp mask
  * @bs:		bio set to allocate from
  *
- * Returns a bio representing the next @sectors of @bio - if the bio is smaller
+ * Return: a bio representing the next @sectors of @bio - if the bio is smaller
  * than @sectors, returns the original bio unchanged.
  */
 static inline struct bio *bio_next_split(struct bio *bio, int sectors,
-- 
cgit v1.2.3


From a16c7246368db8935652c805bc446928d0e1c0aa Mon Sep 17 00:00:00 2001
From: Keith Busch <kbusch@kernel.org>
Date: Wed, 22 Dec 2021 13:52:39 -0800
Subject: block: remove unnecessary trailing '\'

While harmless, the blank line is certainly not intended to be part of
the rq_list_for_each() macro. Remove it.

Signed-off-by: Keith Busch <kbusch@kernel.org>
Link: https://lore.kernel.org/r/20211222215239.1768164-1-kbusch@kernel.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/blkdev.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index bb5fb7282e6e..22746b2d6825 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1363,7 +1363,7 @@ struct io_comp_batch {
 })
 
 #define rq_list_for_each(listptr, pos)			\
-	for (pos = rq_list_peek((listptr)); pos; pos = rq_list_next(pos)) \
+	for (pos = rq_list_peek((listptr)); pos; pos = rq_list_next(pos))
 
 #define rq_list_next(rq)	(rq)->rq_next
 #define rq_list_empty(list)	((list) == (struct request *) NULL)
-- 
cgit v1.2.3


From edce22e19bfa86efa2522d041d6367f2f099e8ed Mon Sep 17 00:00:00 2001
From: Keith Busch <kbusch@kernel.org>
Date: Wed, 5 Jan 2022 09:05:15 -0800
Subject: block: move rq_list macros to blk-mq.h

Move the request list macros to the header file that defines that struct
they operate on.

Signed-off-by: Keith Busch <kbusch@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20220105170518.3181469-2-kbusch@kernel.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c          |  2 +-
 include/linux/blk-mq.h | 29 +++++++++++++++++++++++++++++
 include/linux/blkdev.h | 29 -----------------------------
 3 files changed, 30 insertions(+), 30 deletions(-)

(limited to 'include/linux')

diff --git a/fs/io_uring.c b/fs/io_uring.c
index c4f217613f56..42bbbd34f45e 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -57,7 +57,7 @@
 #include <linux/mman.h>
 #include <linux/percpu.h>
 #include <linux/slab.h>
-#include <linux/blkdev.h>
+#include <linux/blk-mq.h>
 #include <linux/bvec.h>
 #include <linux/net.h>
 #include <net/sock.h>
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 550996cf419c..bf64b94cd64e 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -216,6 +216,35 @@ static inline unsigned short req_get_ioprio(struct request *req)
 #define rq_dma_dir(rq) \
 	(op_is_write(req_op(rq)) ? DMA_TO_DEVICE : DMA_FROM_DEVICE)
 
+#define rq_list_add(listptr, rq)	do {		\
+	(rq)->rq_next = *(listptr);			\
+	*(listptr) = rq;				\
+} while (0)
+
+#define rq_list_pop(listptr)				\
+({							\
+	struct request *__req = NULL;			\
+	if ((listptr) && *(listptr))	{		\
+		__req = *(listptr);			\
+		*(listptr) = __req->rq_next;		\
+	}						\
+	__req;						\
+})
+
+#define rq_list_peek(listptr)				\
+({							\
+	struct request *__req = NULL;			\
+	if ((listptr) && *(listptr))			\
+		__req = *(listptr);			\
+	__req;						\
+})
+
+#define rq_list_for_each(listptr, pos)			\
+	for (pos = rq_list_peek((listptr)); pos; pos = rq_list_next(pos))
+
+#define rq_list_next(rq)	(rq)->rq_next
+#define rq_list_empty(list)	((list) == (struct request *) NULL)
+
 enum blk_eh_timer_return {
 	BLK_EH_DONE,		/* drivers has completed the command */
 	BLK_EH_RESET_TIMER,	/* reset timer and try again */
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 22746b2d6825..9c95df26fc26 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1339,33 +1339,4 @@ struct io_comp_batch {
 
 #define DEFINE_IO_COMP_BATCH(name)	struct io_comp_batch name = { }
 
-#define rq_list_add(listptr, rq)	do {		\
-	(rq)->rq_next = *(listptr);			\
-	*(listptr) = rq;				\
-} while (0)
-
-#define rq_list_pop(listptr)				\
-({							\
-	struct request *__req = NULL;			\
-	if ((listptr) && *(listptr))	{		\
-		__req = *(listptr);			\
-		*(listptr) = __req->rq_next;		\
-	}						\
-	__req;						\
-})
-
-#define rq_list_peek(listptr)				\
-({							\
-	struct request *__req = NULL;			\
-	if ((listptr) && *(listptr))			\
-		__req = *(listptr);			\
-	__req;						\
-})
-
-#define rq_list_for_each(listptr, pos)			\
-	for (pos = rq_list_peek((listptr)); pos; pos = rq_list_next(pos))
-
-#define rq_list_next(rq)	(rq)->rq_next
-#define rq_list_empty(list)	((list) == (struct request *) NULL)
-
 #endif /* _LINUX_BLKDEV_H */
-- 
cgit v1.2.3


From 3764fd05e1f89530e2ee5cbff0b638f2b1141b90 Mon Sep 17 00:00:00 2001
From: Keith Busch <kbusch@kernel.org>
Date: Wed, 5 Jan 2022 09:05:16 -0800
Subject: block: introduce rq_list_for_each_safe macro

While iterating a list, a particular request may need to be removed for
special handling. Provide an iterator that can safely handle that.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
Link: https://lore.kernel.org/r/20220105170518.3181469-3-kbusch@kernel.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/blk-mq.h | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index bf64b94cd64e..1467f0fa2142 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -242,6 +242,10 @@ static inline unsigned short req_get_ioprio(struct request *req)
 #define rq_list_for_each(listptr, pos)			\
 	for (pos = rq_list_peek((listptr)); pos; pos = rq_list_next(pos))
 
+#define rq_list_for_each_safe(listptr, pos, nxt)			\
+	for (pos = rq_list_peek((listptr)), nxt = rq_list_next(pos);	\
+		pos; pos = nxt, nxt = pos ? rq_list_next(pos) : NULL)
+
 #define rq_list_next(rq)	(rq)->rq_next
 #define rq_list_empty(list)	((list) == (struct request *) NULL)
 
-- 
cgit v1.2.3


From d2528be7a8b09af9796a270debd14101a72bb552 Mon Sep 17 00:00:00 2001
From: Keith Busch <kbusch@kernel.org>
Date: Wed, 5 Jan 2022 09:05:17 -0800
Subject: block: introduce rq_list_move

When iterating a list, a particular request may need to be moved for
special handling. Provide a helper function to achieve that so drivers
don't need to reimplement rqlist manipulation.

Signed-off-by: Keith Busch <kbusch@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20220105170518.3181469-4-kbusch@kernel.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/blk-mq.h | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 1467f0fa2142..f40a05ecca4a 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -249,6 +249,23 @@ static inline unsigned short req_get_ioprio(struct request *req)
 #define rq_list_next(rq)	(rq)->rq_next
 #define rq_list_empty(list)	((list) == (struct request *) NULL)
 
+/**
+ * rq_list_move() - move a struct request from one list to another
+ * @src: The source list @rq is currently in
+ * @dst: The destination list that @rq will be appended to
+ * @rq: The request to move
+ * @prev: The request preceding @rq in @src (NULL if @rq is the head)
+ */
+static void inline rq_list_move(struct request **src, struct request **dst,
+				struct request *rq, struct request *prev)
+{
+	if (prev)
+		prev->rq_next = rq->rq_next;
+	else
+		*src = rq->rq_next;
+	rq_list_add(dst, rq);
+}
+
 enum blk_eh_timer_return {
 	BLK_EH_DONE,		/* drivers has completed the command */
 	BLK_EH_RESET_TIMER,	/* reset timer and try again */
-- 
cgit v1.2.3


From 292c33c95defd0b814fec1fc8cd60d16556cf7b8 Mon Sep 17 00:00:00 2001
From: Yang Li <yang.lee@linux.alibaba.com>
Date: Fri, 7 Jan 2022 08:52:28 +0800
Subject: block: fix old-style declaration
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Move the 'inline' keyword to the front of 'void'.

Remove a warning found by clang(make W=1 LLVM=1)
./include/linux/blk-mq.h:259:1: warning: ‘inline’ is not at beginning of
declaration

Reported-by: Abaci Robot <abaci@linux.alibaba.com>
Signed-off-by: Yang Li <yang.lee@linux.alibaba.com>
Link: https://lore.kernel.org/r/20220107005228.103927-1-yang.lee@linux.alibaba.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/blk-mq.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index f40a05ecca4a..d319ffa59354 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -256,7 +256,7 @@ static inline unsigned short req_get_ioprio(struct request *req)
  * @rq: The request to move
  * @prev: The request preceding @rq in @src (NULL if @rq is the head)
  */
-static void inline rq_list_move(struct request **src, struct request **dst,
+static inline void rq_list_move(struct request **src, struct request **dst,
 				struct request *rq, struct request *prev)
 {
 	if (prev)
-- 
cgit v1.2.3