OpenCloudOS-Kernel/block/blk-zoned.c

637 lines
17 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0
/*
* Zoned block device handling
*
* Copyright (c) 2015, Hannes Reinecke
* Copyright (c) 2015, SUSE Linux GmbH
*
* Copyright (c) 2016, Damien Le Moal
* Copyright (c) 2016, Western Digital
*/
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/rbtree.h>
#include <linux/blkdev.h>
block: Introduce blk_revalidate_disk_zones() Drivers exposing zoned block devices have to initialize and maintain correctness (i.e. revalidate) of the device zone bitmaps attached to the device request queue (seq_zones_bitmap and seq_zones_wlock). To simplify coding this, introduce a generic helper function blk_revalidate_disk_zones() suitable for most (and likely all) cases. This new function always update the seq_zones_bitmap and seq_zones_wlock bitmaps as well as the queue nr_zones field when called for a disk using a request based queue. For a disk using a BIO based queue, only the number of zones is updated since these queues do not have schedulers and so do not need the zone bitmaps. With this change, the zone bitmap initialization code in sd_zbc.c can be replaced with a call to this function in sd_zbc_read_zones(), which is called from the disk revalidate block operation method. A call to blk_revalidate_disk_zones() is also added to the null_blk driver for devices created with the zoned mode enabled. Finally, to ensure that zoned devices created with dm-linear or dm-flakey expose the correct number of zones through sysfs, a call to blk_revalidate_disk_zones() is added to dm_table_set_restrictions(). The zone bitmaps allocated and initialized with blk_revalidate_disk_zones() are freed automatically from __blk_release_queue() using the block internal function blk_queue_free_zone_bitmaps(). Reviewed-by: Hannes Reinecke <hare@suse.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Reviewed-by: Mike Snitzer <snitzer@redhat.com> Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2018-10-12 18:08:50 +08:00
#include <linux/blk-mq.h>
#include <linux/mm.h>
#include <linux/vmalloc.h>
#include <linux/sched/mm.h>
#include "blk.h"
#define ZONE_COND_NAME(name) [BLK_ZONE_COND_##name] = #name
static const char *const zone_cond_name[] = {
ZONE_COND_NAME(NOT_WP),
ZONE_COND_NAME(EMPTY),
ZONE_COND_NAME(IMP_OPEN),
ZONE_COND_NAME(EXP_OPEN),
ZONE_COND_NAME(CLOSED),
ZONE_COND_NAME(READONLY),
ZONE_COND_NAME(FULL),
ZONE_COND_NAME(OFFLINE),
};
#undef ZONE_COND_NAME
/**
* blk_zone_cond_str - Return string XXX in BLK_ZONE_COND_XXX.
* @zone_cond: BLK_ZONE_COND_XXX.
*
* Description: Centralize block layer function to convert BLK_ZONE_COND_XXX
* into string format. Useful in the debugging and tracing zone conditions. For
* invalid BLK_ZONE_COND_XXX it returns string "UNKNOWN".
*/
const char *blk_zone_cond_str(enum blk_zone_cond zone_cond)
{
static const char *zone_cond_str = "UNKNOWN";
if (zone_cond < ARRAY_SIZE(zone_cond_name) && zone_cond_name[zone_cond])
zone_cond_str = zone_cond_name[zone_cond];
return zone_cond_str;
}
EXPORT_SYMBOL_GPL(blk_zone_cond_str);
block: introduce zoned block devices zone write locking Components relying only on the request_queue structure for accessing block devices (e.g. I/O schedulers) have a limited knowledged of the device characteristics. In particular, the device capacity cannot be easily discovered, which for a zoned block device also result in the inability to easily know the number of zones of the device (the zone size is indicated by the chunk_sectors field of the queue limits). Introduce the nr_zones field to the request_queue structure to simplify access to this information. Also, add the bitmap seq_zone_bitmap which indicates which zones of the device are sequential zones (write preferred or write required) and the bitmap seq_zones_wlock which indicates if a zone is write locked, that is, if a write request targeting a zone was dispatched to the device. These fields are initialized by the low level block device driver (sd.c for ZBC/ZAC disks). They are not initialized by stacking drivers (device mappers) handling zoned block devices (e.g. dm-linear). Using this, I/O schedulers can introduce zone write locking to control request dispatching to a zoned block device and avoid write request reordering by limiting to at most a single write request per zone outside of the scheduler at any time. Based on previous patches from Damien Le Moal. Signed-off-by: Christoph Hellwig <hch@lst.de> [Damien] * Fixed comments and identation in blkdev.h * Changed helper functions * Fixed this commit message Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2017-12-21 14:43:38 +08:00
/*
* Return true if a request is a write requests that needs zone write locking.
*/
bool blk_req_needs_zone_write_lock(struct request *rq)
{
if (!rq->q->disk->seq_zones_wlock)
block: introduce zoned block devices zone write locking Components relying only on the request_queue structure for accessing block devices (e.g. I/O schedulers) have a limited knowledged of the device characteristics. In particular, the device capacity cannot be easily discovered, which for a zoned block device also result in the inability to easily know the number of zones of the device (the zone size is indicated by the chunk_sectors field of the queue limits). Introduce the nr_zones field to the request_queue structure to simplify access to this information. Also, add the bitmap seq_zone_bitmap which indicates which zones of the device are sequential zones (write preferred or write required) and the bitmap seq_zones_wlock which indicates if a zone is write locked, that is, if a write request targeting a zone was dispatched to the device. These fields are initialized by the low level block device driver (sd.c for ZBC/ZAC disks). They are not initialized by stacking drivers (device mappers) handling zoned block devices (e.g. dm-linear). Using this, I/O schedulers can introduce zone write locking to control request dispatching to a zoned block device and avoid write request reordering by limiting to at most a single write request per zone outside of the scheduler at any time. Based on previous patches from Damien Le Moal. Signed-off-by: Christoph Hellwig <hch@lst.de> [Damien] * Fixed comments and identation in blkdev.h * Changed helper functions * Fixed this commit message Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2017-12-21 14:43:38 +08:00
return false;
return blk_rq_is_seq_zoned_write(rq);
block: introduce zoned block devices zone write locking Components relying only on the request_queue structure for accessing block devices (e.g. I/O schedulers) have a limited knowledged of the device characteristics. In particular, the device capacity cannot be easily discovered, which for a zoned block device also result in the inability to easily know the number of zones of the device (the zone size is indicated by the chunk_sectors field of the queue limits). Introduce the nr_zones field to the request_queue structure to simplify access to this information. Also, add the bitmap seq_zone_bitmap which indicates which zones of the device are sequential zones (write preferred or write required) and the bitmap seq_zones_wlock which indicates if a zone is write locked, that is, if a write request targeting a zone was dispatched to the device. These fields are initialized by the low level block device driver (sd.c for ZBC/ZAC disks). They are not initialized by stacking drivers (device mappers) handling zoned block devices (e.g. dm-linear). Using this, I/O schedulers can introduce zone write locking to control request dispatching to a zoned block device and avoid write request reordering by limiting to at most a single write request per zone outside of the scheduler at any time. Based on previous patches from Damien Le Moal. Signed-off-by: Christoph Hellwig <hch@lst.de> [Damien] * Fixed comments and identation in blkdev.h * Changed helper functions * Fixed this commit message Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2017-12-21 14:43:38 +08:00
}
EXPORT_SYMBOL_GPL(blk_req_needs_zone_write_lock);
bool blk_req_zone_write_trylock(struct request *rq)
{
unsigned int zno = blk_rq_zone_no(rq);
if (test_and_set_bit(zno, rq->q->disk->seq_zones_wlock))
return false;
WARN_ON_ONCE(rq->rq_flags & RQF_ZONE_WRITE_LOCKED);
rq->rq_flags |= RQF_ZONE_WRITE_LOCKED;
return true;
}
EXPORT_SYMBOL_GPL(blk_req_zone_write_trylock);
block: introduce zoned block devices zone write locking Components relying only on the request_queue structure for accessing block devices (e.g. I/O schedulers) have a limited knowledged of the device characteristics. In particular, the device capacity cannot be easily discovered, which for a zoned block device also result in the inability to easily know the number of zones of the device (the zone size is indicated by the chunk_sectors field of the queue limits). Introduce the nr_zones field to the request_queue structure to simplify access to this information. Also, add the bitmap seq_zone_bitmap which indicates which zones of the device are sequential zones (write preferred or write required) and the bitmap seq_zones_wlock which indicates if a zone is write locked, that is, if a write request targeting a zone was dispatched to the device. These fields are initialized by the low level block device driver (sd.c for ZBC/ZAC disks). They are not initialized by stacking drivers (device mappers) handling zoned block devices (e.g. dm-linear). Using this, I/O schedulers can introduce zone write locking to control request dispatching to a zoned block device and avoid write request reordering by limiting to at most a single write request per zone outside of the scheduler at any time. Based on previous patches from Damien Le Moal. Signed-off-by: Christoph Hellwig <hch@lst.de> [Damien] * Fixed comments and identation in blkdev.h * Changed helper functions * Fixed this commit message Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2017-12-21 14:43:38 +08:00
void __blk_req_zone_write_lock(struct request *rq)
{
if (WARN_ON_ONCE(test_and_set_bit(blk_rq_zone_no(rq),
rq->q->disk->seq_zones_wlock)))
block: introduce zoned block devices zone write locking Components relying only on the request_queue structure for accessing block devices (e.g. I/O schedulers) have a limited knowledged of the device characteristics. In particular, the device capacity cannot be easily discovered, which for a zoned block device also result in the inability to easily know the number of zones of the device (the zone size is indicated by the chunk_sectors field of the queue limits). Introduce the nr_zones field to the request_queue structure to simplify access to this information. Also, add the bitmap seq_zone_bitmap which indicates which zones of the device are sequential zones (write preferred or write required) and the bitmap seq_zones_wlock which indicates if a zone is write locked, that is, if a write request targeting a zone was dispatched to the device. These fields are initialized by the low level block device driver (sd.c for ZBC/ZAC disks). They are not initialized by stacking drivers (device mappers) handling zoned block devices (e.g. dm-linear). Using this, I/O schedulers can introduce zone write locking to control request dispatching to a zoned block device and avoid write request reordering by limiting to at most a single write request per zone outside of the scheduler at any time. Based on previous patches from Damien Le Moal. Signed-off-by: Christoph Hellwig <hch@lst.de> [Damien] * Fixed comments and identation in blkdev.h * Changed helper functions * Fixed this commit message Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2017-12-21 14:43:38 +08:00
return;
WARN_ON_ONCE(rq->rq_flags & RQF_ZONE_WRITE_LOCKED);
rq->rq_flags |= RQF_ZONE_WRITE_LOCKED;
}
EXPORT_SYMBOL_GPL(__blk_req_zone_write_lock);
void __blk_req_zone_write_unlock(struct request *rq)
{
rq->rq_flags &= ~RQF_ZONE_WRITE_LOCKED;
if (rq->q->disk->seq_zones_wlock)
block: introduce zoned block devices zone write locking Components relying only on the request_queue structure for accessing block devices (e.g. I/O schedulers) have a limited knowledged of the device characteristics. In particular, the device capacity cannot be easily discovered, which for a zoned block device also result in the inability to easily know the number of zones of the device (the zone size is indicated by the chunk_sectors field of the queue limits). Introduce the nr_zones field to the request_queue structure to simplify access to this information. Also, add the bitmap seq_zone_bitmap which indicates which zones of the device are sequential zones (write preferred or write required) and the bitmap seq_zones_wlock which indicates if a zone is write locked, that is, if a write request targeting a zone was dispatched to the device. These fields are initialized by the low level block device driver (sd.c for ZBC/ZAC disks). They are not initialized by stacking drivers (device mappers) handling zoned block devices (e.g. dm-linear). Using this, I/O schedulers can introduce zone write locking to control request dispatching to a zoned block device and avoid write request reordering by limiting to at most a single write request per zone outside of the scheduler at any time. Based on previous patches from Damien Le Moal. Signed-off-by: Christoph Hellwig <hch@lst.de> [Damien] * Fixed comments and identation in blkdev.h * Changed helper functions * Fixed this commit message Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2017-12-21 14:43:38 +08:00
WARN_ON_ONCE(!test_and_clear_bit(blk_rq_zone_no(rq),
rq->q->disk->seq_zones_wlock));
block: introduce zoned block devices zone write locking Components relying only on the request_queue structure for accessing block devices (e.g. I/O schedulers) have a limited knowledged of the device characteristics. In particular, the device capacity cannot be easily discovered, which for a zoned block device also result in the inability to easily know the number of zones of the device (the zone size is indicated by the chunk_sectors field of the queue limits). Introduce the nr_zones field to the request_queue structure to simplify access to this information. Also, add the bitmap seq_zone_bitmap which indicates which zones of the device are sequential zones (write preferred or write required) and the bitmap seq_zones_wlock which indicates if a zone is write locked, that is, if a write request targeting a zone was dispatched to the device. These fields are initialized by the low level block device driver (sd.c for ZBC/ZAC disks). They are not initialized by stacking drivers (device mappers) handling zoned block devices (e.g. dm-linear). Using this, I/O schedulers can introduce zone write locking to control request dispatching to a zoned block device and avoid write request reordering by limiting to at most a single write request per zone outside of the scheduler at any time. Based on previous patches from Damien Le Moal. Signed-off-by: Christoph Hellwig <hch@lst.de> [Damien] * Fixed comments and identation in blkdev.h * Changed helper functions * Fixed this commit message Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2017-12-21 14:43:38 +08:00
}
EXPORT_SYMBOL_GPL(__blk_req_zone_write_unlock);
/**
* bdev_nr_zones - Get number of zones
* @bdev: Target device
*
* Return the total number of zones of a zoned block device. For a block
* device without zone capabilities, the number of zones is always 0.
*/
unsigned int bdev_nr_zones(struct block_device *bdev)
{
sector_t zone_sectors = bdev_zone_sectors(bdev);
if (!bdev_is_zoned(bdev))
return 0;
return (bdev_nr_sectors(bdev) + zone_sectors - 1) >>
ilog2(zone_sectors);
}
EXPORT_SYMBOL_GPL(bdev_nr_zones);
/**
* blkdev_report_zones - Get zones information
* @bdev: Target block device
* @sector: Sector from which to report zones
* @nr_zones: Maximum number of zones to report
* @cb: Callback function called for each reported zone
* @data: Private data for the callback
*
* Description:
* Get zone information starting from the zone containing @sector for at most
* @nr_zones, and call @cb for each zone reported by the device.
* To report all zones in a device starting from @sector, the BLK_ALL_ZONES
* constant can be passed to @nr_zones.
* Returns the number of zones reported by the device, or a negative errno
* value in case of failure.
*
* Note: The caller must use memalloc_noXX_save/restore() calls to control
* memory allocations done within this function.
*/
int blkdev_report_zones(struct block_device *bdev, sector_t sector,
unsigned int nr_zones, report_zones_cb cb, void *data)
{
struct gendisk *disk = bdev->bd_disk;
sector_t capacity = get_capacity(disk);
if (!bdev_is_zoned(bdev) || WARN_ON_ONCE(!disk->fops->report_zones))
return -EOPNOTSUPP;
if (!nr_zones || sector >= capacity)
return 0;
return disk->fops->report_zones(disk, sector, nr_zones, cb, data);
}
EXPORT_SYMBOL_GPL(blkdev_report_zones);
block: improve handling of all zones reset operation SCSI, ZNS and null_blk zoned devices support resetting all zones using a single command (REQ_OP_ZONE_RESET_ALL), as indicated using the device request queue flag QUEUE_FLAG_ZONE_RESETALL. This flag is not set for device mapper targets creating zoned devices. In this case, a user request for resetting all zones of a device is processed in blkdev_zone_mgmt() by issuing a REQ_OP_ZONE_RESET operation for each zone of the device. This leads to different behaviors of the BLKRESETZONE ioctl() depending on the target device support for the reset all operation. E.g. blkzone reset /dev/sdX will reset all zones of a SCSI device using a single command that will ignore conventional, read-only or offline zones. But a dm-linear device including conventional, read-only or offline zones cannot be reset in the same manner as some of the single zone reset operations issued by blkdev_zone_mgmt() will fail. E.g.: blkzone reset /dev/dm-Y blkzone: /dev/dm-0: BLKRESETZONE ioctl failed: Remote I/O error To simplify applications and tools development, unify the behavior of the all-zone reset operation by modifying blkdev_zone_mgmt() to not issue a zone reset operation for conventional, read-only and offline zones, thus mimicking what an actual reset-all device command does on a device supporting REQ_OP_ZONE_RESET_ALL. This emulation is done using the new function blkdev_zone_reset_all_emulated(). The zones needing a reset are identified using a bitmap that is initialized using a zone report. Since empty zones do not need a reset, also ignore these zones. The function blkdev_zone_reset_all() is introduced for block devices natively supporting reset all operations. blkdev_zone_mgmt() is modified to call either function to execute an all zone reset request. Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com> [hch: split into multiple functions] Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com> Reviewed-by: Hannes Reinecke <hare@suse.de> Acked-by: Jens Axboe <axboe@kernel.dk> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
2021-05-26 05:24:51 +08:00
static inline unsigned long *blk_alloc_zone_bitmap(int node,
unsigned int nr_zones)
{
block: improve handling of all zones reset operation SCSI, ZNS and null_blk zoned devices support resetting all zones using a single command (REQ_OP_ZONE_RESET_ALL), as indicated using the device request queue flag QUEUE_FLAG_ZONE_RESETALL. This flag is not set for device mapper targets creating zoned devices. In this case, a user request for resetting all zones of a device is processed in blkdev_zone_mgmt() by issuing a REQ_OP_ZONE_RESET operation for each zone of the device. This leads to different behaviors of the BLKRESETZONE ioctl() depending on the target device support for the reset all operation. E.g. blkzone reset /dev/sdX will reset all zones of a SCSI device using a single command that will ignore conventional, read-only or offline zones. But a dm-linear device including conventional, read-only or offline zones cannot be reset in the same manner as some of the single zone reset operations issued by blkdev_zone_mgmt() will fail. E.g.: blkzone reset /dev/dm-Y blkzone: /dev/dm-0: BLKRESETZONE ioctl failed: Remote I/O error To simplify applications and tools development, unify the behavior of the all-zone reset operation by modifying blkdev_zone_mgmt() to not issue a zone reset operation for conventional, read-only and offline zones, thus mimicking what an actual reset-all device command does on a device supporting REQ_OP_ZONE_RESET_ALL. This emulation is done using the new function blkdev_zone_reset_all_emulated(). The zones needing a reset are identified using a bitmap that is initialized using a zone report. Since empty zones do not need a reset, also ignore these zones. The function blkdev_zone_reset_all() is introduced for block devices natively supporting reset all operations. blkdev_zone_mgmt() is modified to call either function to execute an all zone reset request. Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com> [hch: split into multiple functions] Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com> Reviewed-by: Hannes Reinecke <hare@suse.de> Acked-by: Jens Axboe <axboe@kernel.dk> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
2021-05-26 05:24:51 +08:00
return kcalloc_node(BITS_TO_LONGS(nr_zones), sizeof(unsigned long),
GFP_NOIO, node);
}
block: improve handling of all zones reset operation SCSI, ZNS and null_blk zoned devices support resetting all zones using a single command (REQ_OP_ZONE_RESET_ALL), as indicated using the device request queue flag QUEUE_FLAG_ZONE_RESETALL. This flag is not set for device mapper targets creating zoned devices. In this case, a user request for resetting all zones of a device is processed in blkdev_zone_mgmt() by issuing a REQ_OP_ZONE_RESET operation for each zone of the device. This leads to different behaviors of the BLKRESETZONE ioctl() depending on the target device support for the reset all operation. E.g. blkzone reset /dev/sdX will reset all zones of a SCSI device using a single command that will ignore conventional, read-only or offline zones. But a dm-linear device including conventional, read-only or offline zones cannot be reset in the same manner as some of the single zone reset operations issued by blkdev_zone_mgmt() will fail. E.g.: blkzone reset /dev/dm-Y blkzone: /dev/dm-0: BLKRESETZONE ioctl failed: Remote I/O error To simplify applications and tools development, unify the behavior of the all-zone reset operation by modifying blkdev_zone_mgmt() to not issue a zone reset operation for conventional, read-only and offline zones, thus mimicking what an actual reset-all device command does on a device supporting REQ_OP_ZONE_RESET_ALL. This emulation is done using the new function blkdev_zone_reset_all_emulated(). The zones needing a reset are identified using a bitmap that is initialized using a zone report. Since empty zones do not need a reset, also ignore these zones. The function blkdev_zone_reset_all() is introduced for block devices natively supporting reset all operations. blkdev_zone_mgmt() is modified to call either function to execute an all zone reset request. Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com> [hch: split into multiple functions] Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com> Reviewed-by: Hannes Reinecke <hare@suse.de> Acked-by: Jens Axboe <axboe@kernel.dk> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
2021-05-26 05:24:51 +08:00
static int blk_zone_need_reset_cb(struct blk_zone *zone, unsigned int idx,
void *data)
{
/*
block: improve handling of all zones reset operation SCSI, ZNS and null_blk zoned devices support resetting all zones using a single command (REQ_OP_ZONE_RESET_ALL), as indicated using the device request queue flag QUEUE_FLAG_ZONE_RESETALL. This flag is not set for device mapper targets creating zoned devices. In this case, a user request for resetting all zones of a device is processed in blkdev_zone_mgmt() by issuing a REQ_OP_ZONE_RESET operation for each zone of the device. This leads to different behaviors of the BLKRESETZONE ioctl() depending on the target device support for the reset all operation. E.g. blkzone reset /dev/sdX will reset all zones of a SCSI device using a single command that will ignore conventional, read-only or offline zones. But a dm-linear device including conventional, read-only or offline zones cannot be reset in the same manner as some of the single zone reset operations issued by blkdev_zone_mgmt() will fail. E.g.: blkzone reset /dev/dm-Y blkzone: /dev/dm-0: BLKRESETZONE ioctl failed: Remote I/O error To simplify applications and tools development, unify the behavior of the all-zone reset operation by modifying blkdev_zone_mgmt() to not issue a zone reset operation for conventional, read-only and offline zones, thus mimicking what an actual reset-all device command does on a device supporting REQ_OP_ZONE_RESET_ALL. This emulation is done using the new function blkdev_zone_reset_all_emulated(). The zones needing a reset are identified using a bitmap that is initialized using a zone report. Since empty zones do not need a reset, also ignore these zones. The function blkdev_zone_reset_all() is introduced for block devices natively supporting reset all operations. blkdev_zone_mgmt() is modified to call either function to execute an all zone reset request. Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com> [hch: split into multiple functions] Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com> Reviewed-by: Hannes Reinecke <hare@suse.de> Acked-by: Jens Axboe <axboe@kernel.dk> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
2021-05-26 05:24:51 +08:00
* For an all-zones reset, ignore conventional, empty, read-only
* and offline zones.
*/
block: improve handling of all zones reset operation SCSI, ZNS and null_blk zoned devices support resetting all zones using a single command (REQ_OP_ZONE_RESET_ALL), as indicated using the device request queue flag QUEUE_FLAG_ZONE_RESETALL. This flag is not set for device mapper targets creating zoned devices. In this case, a user request for resetting all zones of a device is processed in blkdev_zone_mgmt() by issuing a REQ_OP_ZONE_RESET operation for each zone of the device. This leads to different behaviors of the BLKRESETZONE ioctl() depending on the target device support for the reset all operation. E.g. blkzone reset /dev/sdX will reset all zones of a SCSI device using a single command that will ignore conventional, read-only or offline zones. But a dm-linear device including conventional, read-only or offline zones cannot be reset in the same manner as some of the single zone reset operations issued by blkdev_zone_mgmt() will fail. E.g.: blkzone reset /dev/dm-Y blkzone: /dev/dm-0: BLKRESETZONE ioctl failed: Remote I/O error To simplify applications and tools development, unify the behavior of the all-zone reset operation by modifying blkdev_zone_mgmt() to not issue a zone reset operation for conventional, read-only and offline zones, thus mimicking what an actual reset-all device command does on a device supporting REQ_OP_ZONE_RESET_ALL. This emulation is done using the new function blkdev_zone_reset_all_emulated(). The zones needing a reset are identified using a bitmap that is initialized using a zone report. Since empty zones do not need a reset, also ignore these zones. The function blkdev_zone_reset_all() is introduced for block devices natively supporting reset all operations. blkdev_zone_mgmt() is modified to call either function to execute an all zone reset request. Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com> [hch: split into multiple functions] Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com> Reviewed-by: Hannes Reinecke <hare@suse.de> Acked-by: Jens Axboe <axboe@kernel.dk> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
2021-05-26 05:24:51 +08:00
switch (zone->cond) {
case BLK_ZONE_COND_NOT_WP:
case BLK_ZONE_COND_EMPTY:
case BLK_ZONE_COND_READONLY:
case BLK_ZONE_COND_OFFLINE:
return 0;
default:
set_bit(idx, (unsigned long *)data);
return 0;
}
}
static int blkdev_zone_reset_all_emulated(struct block_device *bdev,
gfp_t gfp_mask)
{
struct gendisk *disk = bdev->bd_disk;
sector_t capacity = bdev_nr_sectors(bdev);
sector_t zone_sectors = bdev_zone_sectors(bdev);
block: improve handling of all zones reset operation SCSI, ZNS and null_blk zoned devices support resetting all zones using a single command (REQ_OP_ZONE_RESET_ALL), as indicated using the device request queue flag QUEUE_FLAG_ZONE_RESETALL. This flag is not set for device mapper targets creating zoned devices. In this case, a user request for resetting all zones of a device is processed in blkdev_zone_mgmt() by issuing a REQ_OP_ZONE_RESET operation for each zone of the device. This leads to different behaviors of the BLKRESETZONE ioctl() depending on the target device support for the reset all operation. E.g. blkzone reset /dev/sdX will reset all zones of a SCSI device using a single command that will ignore conventional, read-only or offline zones. But a dm-linear device including conventional, read-only or offline zones cannot be reset in the same manner as some of the single zone reset operations issued by blkdev_zone_mgmt() will fail. E.g.: blkzone reset /dev/dm-Y blkzone: /dev/dm-0: BLKRESETZONE ioctl failed: Remote I/O error To simplify applications and tools development, unify the behavior of the all-zone reset operation by modifying blkdev_zone_mgmt() to not issue a zone reset operation for conventional, read-only and offline zones, thus mimicking what an actual reset-all device command does on a device supporting REQ_OP_ZONE_RESET_ALL. This emulation is done using the new function blkdev_zone_reset_all_emulated(). The zones needing a reset are identified using a bitmap that is initialized using a zone report. Since empty zones do not need a reset, also ignore these zones. The function blkdev_zone_reset_all() is introduced for block devices natively supporting reset all operations. blkdev_zone_mgmt() is modified to call either function to execute an all zone reset request. Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com> [hch: split into multiple functions] Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com> Reviewed-by: Hannes Reinecke <hare@suse.de> Acked-by: Jens Axboe <axboe@kernel.dk> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
2021-05-26 05:24:51 +08:00
unsigned long *need_reset;
struct bio *bio = NULL;
sector_t sector = 0;
int ret;
need_reset = blk_alloc_zone_bitmap(disk->queue->node, disk->nr_zones);
block: improve handling of all zones reset operation SCSI, ZNS and null_blk zoned devices support resetting all zones using a single command (REQ_OP_ZONE_RESET_ALL), as indicated using the device request queue flag QUEUE_FLAG_ZONE_RESETALL. This flag is not set for device mapper targets creating zoned devices. In this case, a user request for resetting all zones of a device is processed in blkdev_zone_mgmt() by issuing a REQ_OP_ZONE_RESET operation for each zone of the device. This leads to different behaviors of the BLKRESETZONE ioctl() depending on the target device support for the reset all operation. E.g. blkzone reset /dev/sdX will reset all zones of a SCSI device using a single command that will ignore conventional, read-only or offline zones. But a dm-linear device including conventional, read-only or offline zones cannot be reset in the same manner as some of the single zone reset operations issued by blkdev_zone_mgmt() will fail. E.g.: blkzone reset /dev/dm-Y blkzone: /dev/dm-0: BLKRESETZONE ioctl failed: Remote I/O error To simplify applications and tools development, unify the behavior of the all-zone reset operation by modifying blkdev_zone_mgmt() to not issue a zone reset operation for conventional, read-only and offline zones, thus mimicking what an actual reset-all device command does on a device supporting REQ_OP_ZONE_RESET_ALL. This emulation is done using the new function blkdev_zone_reset_all_emulated(). The zones needing a reset are identified using a bitmap that is initialized using a zone report. Since empty zones do not need a reset, also ignore these zones. The function blkdev_zone_reset_all() is introduced for block devices natively supporting reset all operations. blkdev_zone_mgmt() is modified to call either function to execute an all zone reset request. Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com> [hch: split into multiple functions] Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com> Reviewed-by: Hannes Reinecke <hare@suse.de> Acked-by: Jens Axboe <axboe@kernel.dk> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
2021-05-26 05:24:51 +08:00
if (!need_reset)
return -ENOMEM;
ret = disk->fops->report_zones(disk, 0, disk->nr_zones,
blk_zone_need_reset_cb, need_reset);
block: improve handling of all zones reset operation SCSI, ZNS and null_blk zoned devices support resetting all zones using a single command (REQ_OP_ZONE_RESET_ALL), as indicated using the device request queue flag QUEUE_FLAG_ZONE_RESETALL. This flag is not set for device mapper targets creating zoned devices. In this case, a user request for resetting all zones of a device is processed in blkdev_zone_mgmt() by issuing a REQ_OP_ZONE_RESET operation for each zone of the device. This leads to different behaviors of the BLKRESETZONE ioctl() depending on the target device support for the reset all operation. E.g. blkzone reset /dev/sdX will reset all zones of a SCSI device using a single command that will ignore conventional, read-only or offline zones. But a dm-linear device including conventional, read-only or offline zones cannot be reset in the same manner as some of the single zone reset operations issued by blkdev_zone_mgmt() will fail. E.g.: blkzone reset /dev/dm-Y blkzone: /dev/dm-0: BLKRESETZONE ioctl failed: Remote I/O error To simplify applications and tools development, unify the behavior of the all-zone reset operation by modifying blkdev_zone_mgmt() to not issue a zone reset operation for conventional, read-only and offline zones, thus mimicking what an actual reset-all device command does on a device supporting REQ_OP_ZONE_RESET_ALL. This emulation is done using the new function blkdev_zone_reset_all_emulated(). The zones needing a reset are identified using a bitmap that is initialized using a zone report. Since empty zones do not need a reset, also ignore these zones. The function blkdev_zone_reset_all() is introduced for block devices natively supporting reset all operations. blkdev_zone_mgmt() is modified to call either function to execute an all zone reset request. Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com> [hch: split into multiple functions] Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com> Reviewed-by: Hannes Reinecke <hare@suse.de> Acked-by: Jens Axboe <axboe@kernel.dk> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
2021-05-26 05:24:51 +08:00
if (ret < 0)
goto out_free_need_reset;
ret = 0;
while (sector < capacity) {
if (!test_bit(disk_zone_no(disk, sector), need_reset)) {
block: improve handling of all zones reset operation SCSI, ZNS and null_blk zoned devices support resetting all zones using a single command (REQ_OP_ZONE_RESET_ALL), as indicated using the device request queue flag QUEUE_FLAG_ZONE_RESETALL. This flag is not set for device mapper targets creating zoned devices. In this case, a user request for resetting all zones of a device is processed in blkdev_zone_mgmt() by issuing a REQ_OP_ZONE_RESET operation for each zone of the device. This leads to different behaviors of the BLKRESETZONE ioctl() depending on the target device support for the reset all operation. E.g. blkzone reset /dev/sdX will reset all zones of a SCSI device using a single command that will ignore conventional, read-only or offline zones. But a dm-linear device including conventional, read-only or offline zones cannot be reset in the same manner as some of the single zone reset operations issued by blkdev_zone_mgmt() will fail. E.g.: blkzone reset /dev/dm-Y blkzone: /dev/dm-0: BLKRESETZONE ioctl failed: Remote I/O error To simplify applications and tools development, unify the behavior of the all-zone reset operation by modifying blkdev_zone_mgmt() to not issue a zone reset operation for conventional, read-only and offline zones, thus mimicking what an actual reset-all device command does on a device supporting REQ_OP_ZONE_RESET_ALL. This emulation is done using the new function blkdev_zone_reset_all_emulated(). The zones needing a reset are identified using a bitmap that is initialized using a zone report. Since empty zones do not need a reset, also ignore these zones. The function blkdev_zone_reset_all() is introduced for block devices natively supporting reset all operations. blkdev_zone_mgmt() is modified to call either function to execute an all zone reset request. Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com> [hch: split into multiple functions] Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com> Reviewed-by: Hannes Reinecke <hare@suse.de> Acked-by: Jens Axboe <axboe@kernel.dk> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
2021-05-26 05:24:51 +08:00
sector += zone_sectors;
continue;
}
bio = blk_next_bio(bio, bdev, 0, REQ_OP_ZONE_RESET | REQ_SYNC,
gfp_mask);
block: improve handling of all zones reset operation SCSI, ZNS and null_blk zoned devices support resetting all zones using a single command (REQ_OP_ZONE_RESET_ALL), as indicated using the device request queue flag QUEUE_FLAG_ZONE_RESETALL. This flag is not set for device mapper targets creating zoned devices. In this case, a user request for resetting all zones of a device is processed in blkdev_zone_mgmt() by issuing a REQ_OP_ZONE_RESET operation for each zone of the device. This leads to different behaviors of the BLKRESETZONE ioctl() depending on the target device support for the reset all operation. E.g. blkzone reset /dev/sdX will reset all zones of a SCSI device using a single command that will ignore conventional, read-only or offline zones. But a dm-linear device including conventional, read-only or offline zones cannot be reset in the same manner as some of the single zone reset operations issued by blkdev_zone_mgmt() will fail. E.g.: blkzone reset /dev/dm-Y blkzone: /dev/dm-0: BLKRESETZONE ioctl failed: Remote I/O error To simplify applications and tools development, unify the behavior of the all-zone reset operation by modifying blkdev_zone_mgmt() to not issue a zone reset operation for conventional, read-only and offline zones, thus mimicking what an actual reset-all device command does on a device supporting REQ_OP_ZONE_RESET_ALL. This emulation is done using the new function blkdev_zone_reset_all_emulated(). The zones needing a reset are identified using a bitmap that is initialized using a zone report. Since empty zones do not need a reset, also ignore these zones. The function blkdev_zone_reset_all() is introduced for block devices natively supporting reset all operations. blkdev_zone_mgmt() is modified to call either function to execute an all zone reset request. Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com> [hch: split into multiple functions] Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com> Reviewed-by: Hannes Reinecke <hare@suse.de> Acked-by: Jens Axboe <axboe@kernel.dk> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
2021-05-26 05:24:51 +08:00
bio->bi_iter.bi_sector = sector;
sector += zone_sectors;
/* This may take a while, so be nice to others */
cond_resched();
}
if (bio) {
ret = submit_bio_wait(bio);
bio_put(bio);
}
out_free_need_reset:
kfree(need_reset);
return ret;
}
static int blkdev_zone_reset_all(struct block_device *bdev, gfp_t gfp_mask)
{
struct bio bio;
bio_init(&bio, bdev, NULL, 0, REQ_OP_ZONE_RESET_ALL | REQ_SYNC);
block: improve handling of all zones reset operation SCSI, ZNS and null_blk zoned devices support resetting all zones using a single command (REQ_OP_ZONE_RESET_ALL), as indicated using the device request queue flag QUEUE_FLAG_ZONE_RESETALL. This flag is not set for device mapper targets creating zoned devices. In this case, a user request for resetting all zones of a device is processed in blkdev_zone_mgmt() by issuing a REQ_OP_ZONE_RESET operation for each zone of the device. This leads to different behaviors of the BLKRESETZONE ioctl() depending on the target device support for the reset all operation. E.g. blkzone reset /dev/sdX will reset all zones of a SCSI device using a single command that will ignore conventional, read-only or offline zones. But a dm-linear device including conventional, read-only or offline zones cannot be reset in the same manner as some of the single zone reset operations issued by blkdev_zone_mgmt() will fail. E.g.: blkzone reset /dev/dm-Y blkzone: /dev/dm-0: BLKRESETZONE ioctl failed: Remote I/O error To simplify applications and tools development, unify the behavior of the all-zone reset operation by modifying blkdev_zone_mgmt() to not issue a zone reset operation for conventional, read-only and offline zones, thus mimicking what an actual reset-all device command does on a device supporting REQ_OP_ZONE_RESET_ALL. This emulation is done using the new function blkdev_zone_reset_all_emulated(). The zones needing a reset are identified using a bitmap that is initialized using a zone report. Since empty zones do not need a reset, also ignore these zones. The function blkdev_zone_reset_all() is introduced for block devices natively supporting reset all operations. blkdev_zone_mgmt() is modified to call either function to execute an all zone reset request. Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com> [hch: split into multiple functions] Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com> Reviewed-by: Hannes Reinecke <hare@suse.de> Acked-by: Jens Axboe <axboe@kernel.dk> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
2021-05-26 05:24:51 +08:00
return submit_bio_wait(&bio);
}
/**
2019-10-27 22:05:45 +08:00
* blkdev_zone_mgmt - Execute a zone management operation on a range of zones
* @bdev: Target block device
2019-10-27 22:05:45 +08:00
* @op: Operation to be performed on the zones
* @sector: Start sector of the first zone to operate on
* @nr_sectors: Number of sectors, should be at least the length of one zone and
* must be zone size aligned.
* @gfp_mask: Memory allocation flags (for bio_alloc)
*
* Description:
2019-10-27 22:05:45 +08:00
* Perform the specified operation on the range of zones specified by
* @sector..@sector+@nr_sectors. Specifying the entire disk sector range
* is valid, but the specified range should not contain conventional zones.
2019-10-27 22:05:45 +08:00
* The operation to execute on each zone can be a zone reset, open, close
* or finish request.
*/
int blkdev_zone_mgmt(struct block_device *bdev, enum req_op op,
sector_t sector, sector_t nr_sectors, gfp_t gfp_mask)
{
struct request_queue *q = bdev_get_queue(bdev);
sector_t zone_sectors = bdev_zone_sectors(bdev);
sector_t capacity = bdev_nr_sectors(bdev);
sector_t end_sector = sector + nr_sectors;
struct bio *bio = NULL;
block: improve handling of all zones reset operation SCSI, ZNS and null_blk zoned devices support resetting all zones using a single command (REQ_OP_ZONE_RESET_ALL), as indicated using the device request queue flag QUEUE_FLAG_ZONE_RESETALL. This flag is not set for device mapper targets creating zoned devices. In this case, a user request for resetting all zones of a device is processed in blkdev_zone_mgmt() by issuing a REQ_OP_ZONE_RESET operation for each zone of the device. This leads to different behaviors of the BLKRESETZONE ioctl() depending on the target device support for the reset all operation. E.g. blkzone reset /dev/sdX will reset all zones of a SCSI device using a single command that will ignore conventional, read-only or offline zones. But a dm-linear device including conventional, read-only or offline zones cannot be reset in the same manner as some of the single zone reset operations issued by blkdev_zone_mgmt() will fail. E.g.: blkzone reset /dev/dm-Y blkzone: /dev/dm-0: BLKRESETZONE ioctl failed: Remote I/O error To simplify applications and tools development, unify the behavior of the all-zone reset operation by modifying blkdev_zone_mgmt() to not issue a zone reset operation for conventional, read-only and offline zones, thus mimicking what an actual reset-all device command does on a device supporting REQ_OP_ZONE_RESET_ALL. This emulation is done using the new function blkdev_zone_reset_all_emulated(). The zones needing a reset are identified using a bitmap that is initialized using a zone report. Since empty zones do not need a reset, also ignore these zones. The function blkdev_zone_reset_all() is introduced for block devices natively supporting reset all operations. blkdev_zone_mgmt() is modified to call either function to execute an all zone reset request. Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com> [hch: split into multiple functions] Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com> Reviewed-by: Hannes Reinecke <hare@suse.de> Acked-by: Jens Axboe <axboe@kernel.dk> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
2021-05-26 05:24:51 +08:00
int ret = 0;
if (!bdev_is_zoned(bdev))
return -EOPNOTSUPP;
if (bdev_read_only(bdev))
return -EPERM;
2019-10-27 22:05:45 +08:00
if (!op_is_zone_mgmt(op))
return -EOPNOTSUPP;
if (end_sector <= sector || end_sector > capacity)
/* Out of range */
return -EINVAL;
/* Check alignment (handle eventual smaller last zone) */
if (!bdev_is_zone_start(bdev, sector))
return -EINVAL;
if (!bdev_is_zone_start(bdev, nr_sectors) && end_sector != capacity)
return -EINVAL;
block: improve handling of all zones reset operation SCSI, ZNS and null_blk zoned devices support resetting all zones using a single command (REQ_OP_ZONE_RESET_ALL), as indicated using the device request queue flag QUEUE_FLAG_ZONE_RESETALL. This flag is not set for device mapper targets creating zoned devices. In this case, a user request for resetting all zones of a device is processed in blkdev_zone_mgmt() by issuing a REQ_OP_ZONE_RESET operation for each zone of the device. This leads to different behaviors of the BLKRESETZONE ioctl() depending on the target device support for the reset all operation. E.g. blkzone reset /dev/sdX will reset all zones of a SCSI device using a single command that will ignore conventional, read-only or offline zones. But a dm-linear device including conventional, read-only or offline zones cannot be reset in the same manner as some of the single zone reset operations issued by blkdev_zone_mgmt() will fail. E.g.: blkzone reset /dev/dm-Y blkzone: /dev/dm-0: BLKRESETZONE ioctl failed: Remote I/O error To simplify applications and tools development, unify the behavior of the all-zone reset operation by modifying blkdev_zone_mgmt() to not issue a zone reset operation for conventional, read-only and offline zones, thus mimicking what an actual reset-all device command does on a device supporting REQ_OP_ZONE_RESET_ALL. This emulation is done using the new function blkdev_zone_reset_all_emulated(). The zones needing a reset are identified using a bitmap that is initialized using a zone report. Since empty zones do not need a reset, also ignore these zones. The function blkdev_zone_reset_all() is introduced for block devices natively supporting reset all operations. blkdev_zone_mgmt() is modified to call either function to execute an all zone reset request. Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com> [hch: split into multiple functions] Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com> Reviewed-by: Hannes Reinecke <hare@suse.de> Acked-by: Jens Axboe <axboe@kernel.dk> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
2021-05-26 05:24:51 +08:00
/*
* In the case of a zone reset operation over all zones,
* REQ_OP_ZONE_RESET_ALL can be used with devices supporting this
* command. For other devices, we emulate this command behavior by
* identifying the zones needing a reset.
*/
if (op == REQ_OP_ZONE_RESET && sector == 0 && nr_sectors == capacity) {
if (!blk_queue_zone_resetall(q))
return blkdev_zone_reset_all_emulated(bdev, gfp_mask);
return blkdev_zone_reset_all(bdev, gfp_mask);
}
while (sector < end_sector) {
bio = blk_next_bio(bio, bdev, 0, op | REQ_SYNC, gfp_mask);
bio->bi_iter.bi_sector = sector;
sector += zone_sectors;
/* This may take a while, so be nice to others */
cond_resched();
}
ret = submit_bio_wait(bio);
bio_put(bio);
return ret;
}
2019-10-27 22:05:45 +08:00
EXPORT_SYMBOL_GPL(blkdev_zone_mgmt);
struct zone_report_args {
struct blk_zone __user *zones;
};
static int blkdev_copy_zone_to_user(struct blk_zone *zone, unsigned int idx,
void *data)
{
struct zone_report_args *args = data;
if (copy_to_user(&args->zones[idx], zone, sizeof(struct blk_zone)))
return -EFAULT;
return 0;
}
/*
* BLKREPORTZONE ioctl processing.
* Called from blkdev_ioctl.
*/
int blkdev_report_zones_ioctl(struct block_device *bdev, unsigned int cmd,
unsigned long arg)
{
void __user *argp = (void __user *)arg;
struct zone_report_args args;
struct blk_zone_report rep;
int ret;
if (!argp)
return -EINVAL;
if (!bdev_is_zoned(bdev))
return -ENOTTY;
if (copy_from_user(&rep, argp, sizeof(struct blk_zone_report)))
return -EFAULT;
if (!rep.nr_zones)
return -EINVAL;
args.zones = argp + sizeof(struct blk_zone_report);
ret = blkdev_report_zones(bdev, rep.sector, rep.nr_zones,
blkdev_copy_zone_to_user, &args);
if (ret < 0)
return ret;
rep.nr_zones = ret;
rep.flags = BLK_ZONE_REP_CAPACITY;
if (copy_to_user(argp, &rep, sizeof(struct blk_zone_report)))
return -EFAULT;
return 0;
}
static int blkdev_truncate_zone_range(struct block_device *bdev,
blk_mode_t mode, const struct blk_zone_range *zrange)
{
loff_t start, end;
if (zrange->sector + zrange->nr_sectors <= zrange->sector ||
zrange->sector + zrange->nr_sectors > get_capacity(bdev->bd_disk))
/* Out of range */
return -EINVAL;
start = zrange->sector << SECTOR_SHIFT;
end = ((zrange->sector + zrange->nr_sectors) << SECTOR_SHIFT) - 1;
return truncate_bdev_range(bdev, mode, start, end);
}
/*
* BLKRESETZONE, BLKOPENZONE, BLKCLOSEZONE and BLKFINISHZONE ioctl processing.
* Called from blkdev_ioctl.
*/
int blkdev_zone_mgmt_ioctl(struct block_device *bdev, blk_mode_t mode,
unsigned int cmd, unsigned long arg)
{
void __user *argp = (void __user *)arg;
struct blk_zone_range zrange;
enum req_op op;
int ret;
if (!argp)
return -EINVAL;
if (!bdev_is_zoned(bdev))
return -ENOTTY;
if (!(mode & BLK_OPEN_WRITE))
return -EBADF;
if (copy_from_user(&zrange, argp, sizeof(struct blk_zone_range)))
return -EFAULT;
switch (cmd) {
case BLKRESETZONE:
op = REQ_OP_ZONE_RESET;
/* Invalidate the page cache, including dirty pages. */
filemap_invalidate_lock(bdev->bd_inode->i_mapping);
ret = blkdev_truncate_zone_range(bdev, mode, &zrange);
if (ret)
goto fail;
break;
case BLKOPENZONE:
op = REQ_OP_ZONE_OPEN;
break;
case BLKCLOSEZONE:
op = REQ_OP_ZONE_CLOSE;
break;
case BLKFINISHZONE:
op = REQ_OP_ZONE_FINISH;
break;
default:
return -ENOTTY;
}
ret = blkdev_zone_mgmt(bdev, op, zrange.sector, zrange.nr_sectors,
GFP_KERNEL);
fail:
if (cmd == BLKRESETZONE)
filemap_invalidate_unlock(bdev->bd_inode->i_mapping);
return ret;
}
block: Introduce blk_revalidate_disk_zones() Drivers exposing zoned block devices have to initialize and maintain correctness (i.e. revalidate) of the device zone bitmaps attached to the device request queue (seq_zones_bitmap and seq_zones_wlock). To simplify coding this, introduce a generic helper function blk_revalidate_disk_zones() suitable for most (and likely all) cases. This new function always update the seq_zones_bitmap and seq_zones_wlock bitmaps as well as the queue nr_zones field when called for a disk using a request based queue. For a disk using a BIO based queue, only the number of zones is updated since these queues do not have schedulers and so do not need the zone bitmaps. With this change, the zone bitmap initialization code in sd_zbc.c can be replaced with a call to this function in sd_zbc_read_zones(), which is called from the disk revalidate block operation method. A call to blk_revalidate_disk_zones() is also added to the null_blk driver for devices created with the zoned mode enabled. Finally, to ensure that zoned devices created with dm-linear or dm-flakey expose the correct number of zones through sysfs, a call to blk_revalidate_disk_zones() is added to dm_table_set_restrictions(). The zone bitmaps allocated and initialized with blk_revalidate_disk_zones() are freed automatically from __blk_release_queue() using the block internal function blk_queue_free_zone_bitmaps(). Reviewed-by: Hannes Reinecke <hare@suse.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Reviewed-by: Mike Snitzer <snitzer@redhat.com> Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2018-10-12 18:08:50 +08:00
void disk_free_zone_bitmaps(struct gendisk *disk)
block: Introduce blk_revalidate_disk_zones() Drivers exposing zoned block devices have to initialize and maintain correctness (i.e. revalidate) of the device zone bitmaps attached to the device request queue (seq_zones_bitmap and seq_zones_wlock). To simplify coding this, introduce a generic helper function blk_revalidate_disk_zones() suitable for most (and likely all) cases. This new function always update the seq_zones_bitmap and seq_zones_wlock bitmaps as well as the queue nr_zones field when called for a disk using a request based queue. For a disk using a BIO based queue, only the number of zones is updated since these queues do not have schedulers and so do not need the zone bitmaps. With this change, the zone bitmap initialization code in sd_zbc.c can be replaced with a call to this function in sd_zbc_read_zones(), which is called from the disk revalidate block operation method. A call to blk_revalidate_disk_zones() is also added to the null_blk driver for devices created with the zoned mode enabled. Finally, to ensure that zoned devices created with dm-linear or dm-flakey expose the correct number of zones through sysfs, a call to blk_revalidate_disk_zones() is added to dm_table_set_restrictions(). The zone bitmaps allocated and initialized with blk_revalidate_disk_zones() are freed automatically from __blk_release_queue() using the block internal function blk_queue_free_zone_bitmaps(). Reviewed-by: Hannes Reinecke <hare@suse.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Reviewed-by: Mike Snitzer <snitzer@redhat.com> Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2018-10-12 18:08:50 +08:00
{
kfree(disk->conv_zones_bitmap);
disk->conv_zones_bitmap = NULL;
kfree(disk->seq_zones_wlock);
disk->seq_zones_wlock = NULL;
block: Introduce blk_revalidate_disk_zones() Drivers exposing zoned block devices have to initialize and maintain correctness (i.e. revalidate) of the device zone bitmaps attached to the device request queue (seq_zones_bitmap and seq_zones_wlock). To simplify coding this, introduce a generic helper function blk_revalidate_disk_zones() suitable for most (and likely all) cases. This new function always update the seq_zones_bitmap and seq_zones_wlock bitmaps as well as the queue nr_zones field when called for a disk using a request based queue. For a disk using a BIO based queue, only the number of zones is updated since these queues do not have schedulers and so do not need the zone bitmaps. With this change, the zone bitmap initialization code in sd_zbc.c can be replaced with a call to this function in sd_zbc_read_zones(), which is called from the disk revalidate block operation method. A call to blk_revalidate_disk_zones() is also added to the null_blk driver for devices created with the zoned mode enabled. Finally, to ensure that zoned devices created with dm-linear or dm-flakey expose the correct number of zones through sysfs, a call to blk_revalidate_disk_zones() is added to dm_table_set_restrictions(). The zone bitmaps allocated and initialized with blk_revalidate_disk_zones() are freed automatically from __blk_release_queue() using the block internal function blk_queue_free_zone_bitmaps(). Reviewed-by: Hannes Reinecke <hare@suse.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Reviewed-by: Mike Snitzer <snitzer@redhat.com> Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2018-10-12 18:08:50 +08:00
}
struct blk_revalidate_zone_args {
struct gendisk *disk;
unsigned long *conv_zones_bitmap;
unsigned long *seq_zones_wlock;
unsigned int nr_zones;
sector_t sector;
};
block: Enhance blk_revalidate_disk_zones() For ZBC and ZAC zoned devices, the scsi driver revalidation processing implemented by sd_revalidate_disk() includes a call to sd_zbc_read_zones() which executes a full disk zone report used to check that all zones of the disk are the same size. This processing is followed by a call to blk_revalidate_disk_zones(), used to initialize the device request queue zone bitmaps (zone type and zone write lock bitmaps). To do so, blk_revalidate_disk_zones() also executes a full device zone report to obtain zone types. As a result, the entire zoned block device revalidation process includes two full device zone report. By moving the zone size checks into blk_revalidate_disk_zones(), this process can be optimized to a single full device zone report, leading to shorter device scan and revalidation times. This patch implements this optimization, reducing the original full device zone report implemented in sd_zbc_check_zones() to a single, small, report zones command execution to obtain the size of the first zone of the device. Checks whether all zones of the device are the same size as the first zone size are moved to the generic blk_check_zone() function called from blk_revalidate_disk_zones(). This optimization also has the following benefits: 1) fewer memory allocations in the scsi layer during disk revalidation as the potentailly large buffer for zone report execution is not needed. 2) Implement zone checks in a generic manner, reducing the burden on device driver which only need to obtain the zone size and check that this size is a power of 2 number of LBAs. Any new type of zoned block device will benefit from this. Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Hannes Reinecke <hare@suse.de> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2019-11-11 10:39:22 +08:00
/*
* Helper function to check the validity of zones of a zoned block device.
*/
static int blk_revalidate_zone_cb(struct blk_zone *zone, unsigned int idx,
void *data)
block: Enhance blk_revalidate_disk_zones() For ZBC and ZAC zoned devices, the scsi driver revalidation processing implemented by sd_revalidate_disk() includes a call to sd_zbc_read_zones() which executes a full disk zone report used to check that all zones of the disk are the same size. This processing is followed by a call to blk_revalidate_disk_zones(), used to initialize the device request queue zone bitmaps (zone type and zone write lock bitmaps). To do so, blk_revalidate_disk_zones() also executes a full device zone report to obtain zone types. As a result, the entire zoned block device revalidation process includes two full device zone report. By moving the zone size checks into blk_revalidate_disk_zones(), this process can be optimized to a single full device zone report, leading to shorter device scan and revalidation times. This patch implements this optimization, reducing the original full device zone report implemented in sd_zbc_check_zones() to a single, small, report zones command execution to obtain the size of the first zone of the device. Checks whether all zones of the device are the same size as the first zone size are moved to the generic blk_check_zone() function called from blk_revalidate_disk_zones(). This optimization also has the following benefits: 1) fewer memory allocations in the scsi layer during disk revalidation as the potentailly large buffer for zone report execution is not needed. 2) Implement zone checks in a generic manner, reducing the burden on device driver which only need to obtain the zone size and check that this size is a power of 2 number of LBAs. Any new type of zoned block device will benefit from this. Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Hannes Reinecke <hare@suse.de> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2019-11-11 10:39:22 +08:00
{
struct blk_revalidate_zone_args *args = data;
struct gendisk *disk = args->disk;
block: Enhance blk_revalidate_disk_zones() For ZBC and ZAC zoned devices, the scsi driver revalidation processing implemented by sd_revalidate_disk() includes a call to sd_zbc_read_zones() which executes a full disk zone report used to check that all zones of the disk are the same size. This processing is followed by a call to blk_revalidate_disk_zones(), used to initialize the device request queue zone bitmaps (zone type and zone write lock bitmaps). To do so, blk_revalidate_disk_zones() also executes a full device zone report to obtain zone types. As a result, the entire zoned block device revalidation process includes two full device zone report. By moving the zone size checks into blk_revalidate_disk_zones(), this process can be optimized to a single full device zone report, leading to shorter device scan and revalidation times. This patch implements this optimization, reducing the original full device zone report implemented in sd_zbc_check_zones() to a single, small, report zones command execution to obtain the size of the first zone of the device. Checks whether all zones of the device are the same size as the first zone size are moved to the generic blk_check_zone() function called from blk_revalidate_disk_zones(). This optimization also has the following benefits: 1) fewer memory allocations in the scsi layer during disk revalidation as the potentailly large buffer for zone report execution is not needed. 2) Implement zone checks in a generic manner, reducing the burden on device driver which only need to obtain the zone size and check that this size is a power of 2 number of LBAs. Any new type of zoned block device will benefit from this. Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Hannes Reinecke <hare@suse.de> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2019-11-11 10:39:22 +08:00
struct request_queue *q = disk->queue;
sector_t capacity = get_capacity(disk);
scsi: block: Improve checks in blk_revalidate_disk_zones() blk_revalidate_disk_zones() implements checks of the zones of a zoned block device, verifying that the zone size is a power of 2 number of sectors, that all zones (except possibly the last one) have the same size and that zones cover the entire addressing space of the device. While these checks are appropriate to verify that well tested hardware devices have an adequate zone configurations, they lack in certain areas which may result in issues with emulated devices implemented with user drivers such as ublk or tcmu. Specifically, this function does not check if the device driver indicated support for the mandatory zone append writes, that is, if the device max_zone_append_sectors queue limit is set to a non-zero value. Additionally, invalid zones such as a zero length zone with a start sector equal to the device capacity will not be detected and result in out of bounds use of the zone bitmaps prepared with the callback function blk_revalidate_zone_cb(). Improve blk_revalidate_disk_zones() to address these inadequate checks, relying on the fact that all device drivers supporting zoned block devices must set the device zone size (chunk_sectors queue limit) and the max_zone_append_sectors queue limit before executing this function. The check for a non-zero max_zone_append_sectors value is done in blk_revalidate_disk_zones() before executing the zone report. The zone report callback function blk_revalidate_zone_cb() is also modified to add a check that a zone start is below the device capacity. The check that the zone size is a power of 2 number of sectors is moved to blk_revalidate_disk_zones() as the zone size is already known. Similarly, the number of zones of the device can be calculated in blk_revalidate_disk_zones() before executing the zone report. The kdoc comment for blk_revalidate_disk_zones() is also updated to mention that device drivers must set the device zone size and the max_zone_append_sectors queue limit before calling this function. Signed-off-by: Damien Le Moal <dlemoal@kernel.org> Link: https://lore.kernel.org/r/20230703024812.76778-6-dlemoal@kernel.org Reviewed-by: Bart Van Assche <bvanassche@acm.org> Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2023-07-03 10:48:12 +08:00
sector_t zone_sectors = q->limits.chunk_sectors;
/* Check for bad zones and holes in the zone report */
if (zone->start != args->sector) {
pr_warn("%s: Zone gap at sectors %llu..%llu\n",
disk->disk_name, args->sector, zone->start);
return -ENODEV;
}
if (zone->start >= capacity || !zone->len) {
pr_warn("%s: Invalid zone start %llu, length %llu\n",
disk->disk_name, zone->start, zone->len);
return -ENODEV;
}
block: Enhance blk_revalidate_disk_zones() For ZBC and ZAC zoned devices, the scsi driver revalidation processing implemented by sd_revalidate_disk() includes a call to sd_zbc_read_zones() which executes a full disk zone report used to check that all zones of the disk are the same size. This processing is followed by a call to blk_revalidate_disk_zones(), used to initialize the device request queue zone bitmaps (zone type and zone write lock bitmaps). To do so, blk_revalidate_disk_zones() also executes a full device zone report to obtain zone types. As a result, the entire zoned block device revalidation process includes two full device zone report. By moving the zone size checks into blk_revalidate_disk_zones(), this process can be optimized to a single full device zone report, leading to shorter device scan and revalidation times. This patch implements this optimization, reducing the original full device zone report implemented in sd_zbc_check_zones() to a single, small, report zones command execution to obtain the size of the first zone of the device. Checks whether all zones of the device are the same size as the first zone size are moved to the generic blk_check_zone() function called from blk_revalidate_disk_zones(). This optimization also has the following benefits: 1) fewer memory allocations in the scsi layer during disk revalidation as the potentailly large buffer for zone report execution is not needed. 2) Implement zone checks in a generic manner, reducing the burden on device driver which only need to obtain the zone size and check that this size is a power of 2 number of LBAs. Any new type of zoned block device will benefit from this. Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Hannes Reinecke <hare@suse.de> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2019-11-11 10:39:22 +08:00
/*
* All zones must have the same size, with the exception on an eventual
* smaller last zone.
*/
scsi: block: Improve checks in blk_revalidate_disk_zones() blk_revalidate_disk_zones() implements checks of the zones of a zoned block device, verifying that the zone size is a power of 2 number of sectors, that all zones (except possibly the last one) have the same size and that zones cover the entire addressing space of the device. While these checks are appropriate to verify that well tested hardware devices have an adequate zone configurations, they lack in certain areas which may result in issues with emulated devices implemented with user drivers such as ublk or tcmu. Specifically, this function does not check if the device driver indicated support for the mandatory zone append writes, that is, if the device max_zone_append_sectors queue limit is set to a non-zero value. Additionally, invalid zones such as a zero length zone with a start sector equal to the device capacity will not be detected and result in out of bounds use of the zone bitmaps prepared with the callback function blk_revalidate_zone_cb(). Improve blk_revalidate_disk_zones() to address these inadequate checks, relying on the fact that all device drivers supporting zoned block devices must set the device zone size (chunk_sectors queue limit) and the max_zone_append_sectors queue limit before executing this function. The check for a non-zero max_zone_append_sectors value is done in blk_revalidate_disk_zones() before executing the zone report. The zone report callback function blk_revalidate_zone_cb() is also modified to add a check that a zone start is below the device capacity. The check that the zone size is a power of 2 number of sectors is moved to blk_revalidate_disk_zones() as the zone size is already known. Similarly, the number of zones of the device can be calculated in blk_revalidate_disk_zones() before executing the zone report. The kdoc comment for blk_revalidate_disk_zones() is also updated to mention that device drivers must set the device zone size and the max_zone_append_sectors queue limit before calling this function. Signed-off-by: Damien Le Moal <dlemoal@kernel.org> Link: https://lore.kernel.org/r/20230703024812.76778-6-dlemoal@kernel.org Reviewed-by: Bart Van Assche <bvanassche@acm.org> Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2023-07-03 10:48:12 +08:00
if (zone->start + zone->len < capacity) {
if (zone->len != zone_sectors) {
pr_warn("%s: Invalid zoned device with non constant zone size\n",
disk->disk_name);
return -ENODEV;
}
scsi: block: Improve checks in blk_revalidate_disk_zones() blk_revalidate_disk_zones() implements checks of the zones of a zoned block device, verifying that the zone size is a power of 2 number of sectors, that all zones (except possibly the last one) have the same size and that zones cover the entire addressing space of the device. While these checks are appropriate to verify that well tested hardware devices have an adequate zone configurations, they lack in certain areas which may result in issues with emulated devices implemented with user drivers such as ublk or tcmu. Specifically, this function does not check if the device driver indicated support for the mandatory zone append writes, that is, if the device max_zone_append_sectors queue limit is set to a non-zero value. Additionally, invalid zones such as a zero length zone with a start sector equal to the device capacity will not be detected and result in out of bounds use of the zone bitmaps prepared with the callback function blk_revalidate_zone_cb(). Improve blk_revalidate_disk_zones() to address these inadequate checks, relying on the fact that all device drivers supporting zoned block devices must set the device zone size (chunk_sectors queue limit) and the max_zone_append_sectors queue limit before executing this function. The check for a non-zero max_zone_append_sectors value is done in blk_revalidate_disk_zones() before executing the zone report. The zone report callback function blk_revalidate_zone_cb() is also modified to add a check that a zone start is below the device capacity. The check that the zone size is a power of 2 number of sectors is moved to blk_revalidate_disk_zones() as the zone size is already known. Similarly, the number of zones of the device can be calculated in blk_revalidate_disk_zones() before executing the zone report. The kdoc comment for blk_revalidate_disk_zones() is also updated to mention that device drivers must set the device zone size and the max_zone_append_sectors queue limit before calling this function. Signed-off-by: Damien Le Moal <dlemoal@kernel.org> Link: https://lore.kernel.org/r/20230703024812.76778-6-dlemoal@kernel.org Reviewed-by: Bart Van Assche <bvanassche@acm.org> Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2023-07-03 10:48:12 +08:00
} else if (zone->len > zone_sectors) {
pr_warn("%s: Invalid zoned device with larger last zone size\n",
disk->disk_name);
return -ENODEV;
block: Enhance blk_revalidate_disk_zones() For ZBC and ZAC zoned devices, the scsi driver revalidation processing implemented by sd_revalidate_disk() includes a call to sd_zbc_read_zones() which executes a full disk zone report used to check that all zones of the disk are the same size. This processing is followed by a call to blk_revalidate_disk_zones(), used to initialize the device request queue zone bitmaps (zone type and zone write lock bitmaps). To do so, blk_revalidate_disk_zones() also executes a full device zone report to obtain zone types. As a result, the entire zoned block device revalidation process includes two full device zone report. By moving the zone size checks into blk_revalidate_disk_zones(), this process can be optimized to a single full device zone report, leading to shorter device scan and revalidation times. This patch implements this optimization, reducing the original full device zone report implemented in sd_zbc_check_zones() to a single, small, report zones command execution to obtain the size of the first zone of the device. Checks whether all zones of the device are the same size as the first zone size are moved to the generic blk_check_zone() function called from blk_revalidate_disk_zones(). This optimization also has the following benefits: 1) fewer memory allocations in the scsi layer during disk revalidation as the potentailly large buffer for zone report execution is not needed. 2) Implement zone checks in a generic manner, reducing the burden on device driver which only need to obtain the zone size and check that this size is a power of 2 number of LBAs. Any new type of zoned block device will benefit from this. Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Hannes Reinecke <hare@suse.de> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2019-11-11 10:39:22 +08:00
}
/* Check zone type */
switch (zone->type) {
case BLK_ZONE_TYPE_CONVENTIONAL:
if (!args->conv_zones_bitmap) {
args->conv_zones_bitmap =
blk_alloc_zone_bitmap(q->node, args->nr_zones);
if (!args->conv_zones_bitmap)
return -ENOMEM;
}
set_bit(idx, args->conv_zones_bitmap);
break;
block: Enhance blk_revalidate_disk_zones() For ZBC and ZAC zoned devices, the scsi driver revalidation processing implemented by sd_revalidate_disk() includes a call to sd_zbc_read_zones() which executes a full disk zone report used to check that all zones of the disk are the same size. This processing is followed by a call to blk_revalidate_disk_zones(), used to initialize the device request queue zone bitmaps (zone type and zone write lock bitmaps). To do so, blk_revalidate_disk_zones() also executes a full device zone report to obtain zone types. As a result, the entire zoned block device revalidation process includes two full device zone report. By moving the zone size checks into blk_revalidate_disk_zones(), this process can be optimized to a single full device zone report, leading to shorter device scan and revalidation times. This patch implements this optimization, reducing the original full device zone report implemented in sd_zbc_check_zones() to a single, small, report zones command execution to obtain the size of the first zone of the device. Checks whether all zones of the device are the same size as the first zone size are moved to the generic blk_check_zone() function called from blk_revalidate_disk_zones(). This optimization also has the following benefits: 1) fewer memory allocations in the scsi layer during disk revalidation as the potentailly large buffer for zone report execution is not needed. 2) Implement zone checks in a generic manner, reducing the burden on device driver which only need to obtain the zone size and check that this size is a power of 2 number of LBAs. Any new type of zoned block device will benefit from this. Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Hannes Reinecke <hare@suse.de> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2019-11-11 10:39:22 +08:00
case BLK_ZONE_TYPE_SEQWRITE_REQ:
case BLK_ZONE_TYPE_SEQWRITE_PREF:
if (!args->seq_zones_wlock) {
args->seq_zones_wlock =
blk_alloc_zone_bitmap(q->node, args->nr_zones);
if (!args->seq_zones_wlock)
return -ENOMEM;
}
block: Enhance blk_revalidate_disk_zones() For ZBC and ZAC zoned devices, the scsi driver revalidation processing implemented by sd_revalidate_disk() includes a call to sd_zbc_read_zones() which executes a full disk zone report used to check that all zones of the disk are the same size. This processing is followed by a call to blk_revalidate_disk_zones(), used to initialize the device request queue zone bitmaps (zone type and zone write lock bitmaps). To do so, blk_revalidate_disk_zones() also executes a full device zone report to obtain zone types. As a result, the entire zoned block device revalidation process includes two full device zone report. By moving the zone size checks into blk_revalidate_disk_zones(), this process can be optimized to a single full device zone report, leading to shorter device scan and revalidation times. This patch implements this optimization, reducing the original full device zone report implemented in sd_zbc_check_zones() to a single, small, report zones command execution to obtain the size of the first zone of the device. Checks whether all zones of the device are the same size as the first zone size are moved to the generic blk_check_zone() function called from blk_revalidate_disk_zones(). This optimization also has the following benefits: 1) fewer memory allocations in the scsi layer during disk revalidation as the potentailly large buffer for zone report execution is not needed. 2) Implement zone checks in a generic manner, reducing the burden on device driver which only need to obtain the zone size and check that this size is a power of 2 number of LBAs. Any new type of zoned block device will benefit from this. Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Hannes Reinecke <hare@suse.de> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2019-11-11 10:39:22 +08:00
break;
default:
pr_warn("%s: Invalid zone type 0x%x at sectors %llu\n",
disk->disk_name, (int)zone->type, zone->start);
return -ENODEV;
block: Enhance blk_revalidate_disk_zones() For ZBC and ZAC zoned devices, the scsi driver revalidation processing implemented by sd_revalidate_disk() includes a call to sd_zbc_read_zones() which executes a full disk zone report used to check that all zones of the disk are the same size. This processing is followed by a call to blk_revalidate_disk_zones(), used to initialize the device request queue zone bitmaps (zone type and zone write lock bitmaps). To do so, blk_revalidate_disk_zones() also executes a full device zone report to obtain zone types. As a result, the entire zoned block device revalidation process includes two full device zone report. By moving the zone size checks into blk_revalidate_disk_zones(), this process can be optimized to a single full device zone report, leading to shorter device scan and revalidation times. This patch implements this optimization, reducing the original full device zone report implemented in sd_zbc_check_zones() to a single, small, report zones command execution to obtain the size of the first zone of the device. Checks whether all zones of the device are the same size as the first zone size are moved to the generic blk_check_zone() function called from blk_revalidate_disk_zones(). This optimization also has the following benefits: 1) fewer memory allocations in the scsi layer during disk revalidation as the potentailly large buffer for zone report execution is not needed. 2) Implement zone checks in a generic manner, reducing the burden on device driver which only need to obtain the zone size and check that this size is a power of 2 number of LBAs. Any new type of zoned block device will benefit from this. Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Hannes Reinecke <hare@suse.de> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2019-11-11 10:39:22 +08:00
}
args->sector += zone->len;
return 0;
}
block: Introduce blk_revalidate_disk_zones() Drivers exposing zoned block devices have to initialize and maintain correctness (i.e. revalidate) of the device zone bitmaps attached to the device request queue (seq_zones_bitmap and seq_zones_wlock). To simplify coding this, introduce a generic helper function blk_revalidate_disk_zones() suitable for most (and likely all) cases. This new function always update the seq_zones_bitmap and seq_zones_wlock bitmaps as well as the queue nr_zones field when called for a disk using a request based queue. For a disk using a BIO based queue, only the number of zones is updated since these queues do not have schedulers and so do not need the zone bitmaps. With this change, the zone bitmap initialization code in sd_zbc.c can be replaced with a call to this function in sd_zbc_read_zones(), which is called from the disk revalidate block operation method. A call to blk_revalidate_disk_zones() is also added to the null_blk driver for devices created with the zoned mode enabled. Finally, to ensure that zoned devices created with dm-linear or dm-flakey expose the correct number of zones through sysfs, a call to blk_revalidate_disk_zones() is added to dm_table_set_restrictions(). The zone bitmaps allocated and initialized with blk_revalidate_disk_zones() are freed automatically from __blk_release_queue() using the block internal function blk_queue_free_zone_bitmaps(). Reviewed-by: Hannes Reinecke <hare@suse.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Reviewed-by: Mike Snitzer <snitzer@redhat.com> Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2018-10-12 18:08:50 +08:00
/**
* blk_revalidate_disk_zones - (re)allocate and initialize zone bitmaps
* @disk: Target disk
* @update_driver_data: Callback to update driver data on the frozen disk
block: Introduce blk_revalidate_disk_zones() Drivers exposing zoned block devices have to initialize and maintain correctness (i.e. revalidate) of the device zone bitmaps attached to the device request queue (seq_zones_bitmap and seq_zones_wlock). To simplify coding this, introduce a generic helper function blk_revalidate_disk_zones() suitable for most (and likely all) cases. This new function always update the seq_zones_bitmap and seq_zones_wlock bitmaps as well as the queue nr_zones field when called for a disk using a request based queue. For a disk using a BIO based queue, only the number of zones is updated since these queues do not have schedulers and so do not need the zone bitmaps. With this change, the zone bitmap initialization code in sd_zbc.c can be replaced with a call to this function in sd_zbc_read_zones(), which is called from the disk revalidate block operation method. A call to blk_revalidate_disk_zones() is also added to the null_blk driver for devices created with the zoned mode enabled. Finally, to ensure that zoned devices created with dm-linear or dm-flakey expose the correct number of zones through sysfs, a call to blk_revalidate_disk_zones() is added to dm_table_set_restrictions(). The zone bitmaps allocated and initialized with blk_revalidate_disk_zones() are freed automatically from __blk_release_queue() using the block internal function blk_queue_free_zone_bitmaps(). Reviewed-by: Hannes Reinecke <hare@suse.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Reviewed-by: Mike Snitzer <snitzer@redhat.com> Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2018-10-12 18:08:50 +08:00
*
scsi: block: Improve checks in blk_revalidate_disk_zones() blk_revalidate_disk_zones() implements checks of the zones of a zoned block device, verifying that the zone size is a power of 2 number of sectors, that all zones (except possibly the last one) have the same size and that zones cover the entire addressing space of the device. While these checks are appropriate to verify that well tested hardware devices have an adequate zone configurations, they lack in certain areas which may result in issues with emulated devices implemented with user drivers such as ublk or tcmu. Specifically, this function does not check if the device driver indicated support for the mandatory zone append writes, that is, if the device max_zone_append_sectors queue limit is set to a non-zero value. Additionally, invalid zones such as a zero length zone with a start sector equal to the device capacity will not be detected and result in out of bounds use of the zone bitmaps prepared with the callback function blk_revalidate_zone_cb(). Improve blk_revalidate_disk_zones() to address these inadequate checks, relying on the fact that all device drivers supporting zoned block devices must set the device zone size (chunk_sectors queue limit) and the max_zone_append_sectors queue limit before executing this function. The check for a non-zero max_zone_append_sectors value is done in blk_revalidate_disk_zones() before executing the zone report. The zone report callback function blk_revalidate_zone_cb() is also modified to add a check that a zone start is below the device capacity. The check that the zone size is a power of 2 number of sectors is moved to blk_revalidate_disk_zones() as the zone size is already known. Similarly, the number of zones of the device can be calculated in blk_revalidate_disk_zones() before executing the zone report. The kdoc comment for blk_revalidate_disk_zones() is also updated to mention that device drivers must set the device zone size and the max_zone_append_sectors queue limit before calling this function. Signed-off-by: Damien Le Moal <dlemoal@kernel.org> Link: https://lore.kernel.org/r/20230703024812.76778-6-dlemoal@kernel.org Reviewed-by: Bart Van Assche <bvanassche@acm.org> Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2023-07-03 10:48:12 +08:00
* Helper function for low-level device drivers to check and (re) allocate and
* initialize a disk request queue zone bitmaps. This functions should normally
* be called within the disk ->revalidate method for blk-mq based drivers.
* Before calling this function, the device driver must already have set the
* device zone size (chunk_sector limit) and the max zone append limit.
* For BIO based drivers, this function cannot be used. BIO based device drivers
* only need to set disk->nr_zones so that the sysfs exposed value is correct.
* If the @update_driver_data callback function is not NULL, the callback is
* executed with the device request queue frozen after all zones have been
* checked.
block: Introduce blk_revalidate_disk_zones() Drivers exposing zoned block devices have to initialize and maintain correctness (i.e. revalidate) of the device zone bitmaps attached to the device request queue (seq_zones_bitmap and seq_zones_wlock). To simplify coding this, introduce a generic helper function blk_revalidate_disk_zones() suitable for most (and likely all) cases. This new function always update the seq_zones_bitmap and seq_zones_wlock bitmaps as well as the queue nr_zones field when called for a disk using a request based queue. For a disk using a BIO based queue, only the number of zones is updated since these queues do not have schedulers and so do not need the zone bitmaps. With this change, the zone bitmap initialization code in sd_zbc.c can be replaced with a call to this function in sd_zbc_read_zones(), which is called from the disk revalidate block operation method. A call to blk_revalidate_disk_zones() is also added to the null_blk driver for devices created with the zoned mode enabled. Finally, to ensure that zoned devices created with dm-linear or dm-flakey expose the correct number of zones through sysfs, a call to blk_revalidate_disk_zones() is added to dm_table_set_restrictions(). The zone bitmaps allocated and initialized with blk_revalidate_disk_zones() are freed automatically from __blk_release_queue() using the block internal function blk_queue_free_zone_bitmaps(). Reviewed-by: Hannes Reinecke <hare@suse.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Reviewed-by: Mike Snitzer <snitzer@redhat.com> Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2018-10-12 18:08:50 +08:00
*/
int blk_revalidate_disk_zones(struct gendisk *disk,
void (*update_driver_data)(struct gendisk *disk))
block: Introduce blk_revalidate_disk_zones() Drivers exposing zoned block devices have to initialize and maintain correctness (i.e. revalidate) of the device zone bitmaps attached to the device request queue (seq_zones_bitmap and seq_zones_wlock). To simplify coding this, introduce a generic helper function blk_revalidate_disk_zones() suitable for most (and likely all) cases. This new function always update the seq_zones_bitmap and seq_zones_wlock bitmaps as well as the queue nr_zones field when called for a disk using a request based queue. For a disk using a BIO based queue, only the number of zones is updated since these queues do not have schedulers and so do not need the zone bitmaps. With this change, the zone bitmap initialization code in sd_zbc.c can be replaced with a call to this function in sd_zbc_read_zones(), which is called from the disk revalidate block operation method. A call to blk_revalidate_disk_zones() is also added to the null_blk driver for devices created with the zoned mode enabled. Finally, to ensure that zoned devices created with dm-linear or dm-flakey expose the correct number of zones through sysfs, a call to blk_revalidate_disk_zones() is added to dm_table_set_restrictions(). The zone bitmaps allocated and initialized with blk_revalidate_disk_zones() are freed automatically from __blk_release_queue() using the block internal function blk_queue_free_zone_bitmaps(). Reviewed-by: Hannes Reinecke <hare@suse.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Reviewed-by: Mike Snitzer <snitzer@redhat.com> Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2018-10-12 18:08:50 +08:00
{
struct request_queue *q = disk->queue;
scsi: block: Improve checks in blk_revalidate_disk_zones() blk_revalidate_disk_zones() implements checks of the zones of a zoned block device, verifying that the zone size is a power of 2 number of sectors, that all zones (except possibly the last one) have the same size and that zones cover the entire addressing space of the device. While these checks are appropriate to verify that well tested hardware devices have an adequate zone configurations, they lack in certain areas which may result in issues with emulated devices implemented with user drivers such as ublk or tcmu. Specifically, this function does not check if the device driver indicated support for the mandatory zone append writes, that is, if the device max_zone_append_sectors queue limit is set to a non-zero value. Additionally, invalid zones such as a zero length zone with a start sector equal to the device capacity will not be detected and result in out of bounds use of the zone bitmaps prepared with the callback function blk_revalidate_zone_cb(). Improve blk_revalidate_disk_zones() to address these inadequate checks, relying on the fact that all device drivers supporting zoned block devices must set the device zone size (chunk_sectors queue limit) and the max_zone_append_sectors queue limit before executing this function. The check for a non-zero max_zone_append_sectors value is done in blk_revalidate_disk_zones() before executing the zone report. The zone report callback function blk_revalidate_zone_cb() is also modified to add a check that a zone start is below the device capacity. The check that the zone size is a power of 2 number of sectors is moved to blk_revalidate_disk_zones() as the zone size is already known. Similarly, the number of zones of the device can be calculated in blk_revalidate_disk_zones() before executing the zone report. The kdoc comment for blk_revalidate_disk_zones() is also updated to mention that device drivers must set the device zone size and the max_zone_append_sectors queue limit before calling this function. Signed-off-by: Damien Le Moal <dlemoal@kernel.org> Link: https://lore.kernel.org/r/20230703024812.76778-6-dlemoal@kernel.org Reviewed-by: Bart Van Assche <bvanassche@acm.org> Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2023-07-03 10:48:12 +08:00
sector_t zone_sectors = q->limits.chunk_sectors;
sector_t capacity = get_capacity(disk);
struct blk_revalidate_zone_args args = { };
unsigned int noio_flag;
int ret;
block: Introduce blk_revalidate_disk_zones() Drivers exposing zoned block devices have to initialize and maintain correctness (i.e. revalidate) of the device zone bitmaps attached to the device request queue (seq_zones_bitmap and seq_zones_wlock). To simplify coding this, introduce a generic helper function blk_revalidate_disk_zones() suitable for most (and likely all) cases. This new function always update the seq_zones_bitmap and seq_zones_wlock bitmaps as well as the queue nr_zones field when called for a disk using a request based queue. For a disk using a BIO based queue, only the number of zones is updated since these queues do not have schedulers and so do not need the zone bitmaps. With this change, the zone bitmap initialization code in sd_zbc.c can be replaced with a call to this function in sd_zbc_read_zones(), which is called from the disk revalidate block operation method. A call to blk_revalidate_disk_zones() is also added to the null_blk driver for devices created with the zoned mode enabled. Finally, to ensure that zoned devices created with dm-linear or dm-flakey expose the correct number of zones through sysfs, a call to blk_revalidate_disk_zones() is added to dm_table_set_restrictions(). The zone bitmaps allocated and initialized with blk_revalidate_disk_zones() are freed automatically from __blk_release_queue() using the block internal function blk_queue_free_zone_bitmaps(). Reviewed-by: Hannes Reinecke <hare@suse.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Reviewed-by: Mike Snitzer <snitzer@redhat.com> Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2018-10-12 18:08:50 +08:00
if (WARN_ON_ONCE(!blk_queue_is_zoned(q)))
return -EIO;
if (WARN_ON_ONCE(!queue_is_mq(q)))
return -EIO;
block: Introduce blk_revalidate_disk_zones() Drivers exposing zoned block devices have to initialize and maintain correctness (i.e. revalidate) of the device zone bitmaps attached to the device request queue (seq_zones_bitmap and seq_zones_wlock). To simplify coding this, introduce a generic helper function blk_revalidate_disk_zones() suitable for most (and likely all) cases. This new function always update the seq_zones_bitmap and seq_zones_wlock bitmaps as well as the queue nr_zones field when called for a disk using a request based queue. For a disk using a BIO based queue, only the number of zones is updated since these queues do not have schedulers and so do not need the zone bitmaps. With this change, the zone bitmap initialization code in sd_zbc.c can be replaced with a call to this function in sd_zbc_read_zones(), which is called from the disk revalidate block operation method. A call to blk_revalidate_disk_zones() is also added to the null_blk driver for devices created with the zoned mode enabled. Finally, to ensure that zoned devices created with dm-linear or dm-flakey expose the correct number of zones through sysfs, a call to blk_revalidate_disk_zones() is added to dm_table_set_restrictions(). The zone bitmaps allocated and initialized with blk_revalidate_disk_zones() are freed automatically from __blk_release_queue() using the block internal function blk_queue_free_zone_bitmaps(). Reviewed-by: Hannes Reinecke <hare@suse.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Reviewed-by: Mike Snitzer <snitzer@redhat.com> Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2018-10-12 18:08:50 +08:00
scsi: block: Improve checks in blk_revalidate_disk_zones() blk_revalidate_disk_zones() implements checks of the zones of a zoned block device, verifying that the zone size is a power of 2 number of sectors, that all zones (except possibly the last one) have the same size and that zones cover the entire addressing space of the device. While these checks are appropriate to verify that well tested hardware devices have an adequate zone configurations, they lack in certain areas which may result in issues with emulated devices implemented with user drivers such as ublk or tcmu. Specifically, this function does not check if the device driver indicated support for the mandatory zone append writes, that is, if the device max_zone_append_sectors queue limit is set to a non-zero value. Additionally, invalid zones such as a zero length zone with a start sector equal to the device capacity will not be detected and result in out of bounds use of the zone bitmaps prepared with the callback function blk_revalidate_zone_cb(). Improve blk_revalidate_disk_zones() to address these inadequate checks, relying on the fact that all device drivers supporting zoned block devices must set the device zone size (chunk_sectors queue limit) and the max_zone_append_sectors queue limit before executing this function. The check for a non-zero max_zone_append_sectors value is done in blk_revalidate_disk_zones() before executing the zone report. The zone report callback function blk_revalidate_zone_cb() is also modified to add a check that a zone start is below the device capacity. The check that the zone size is a power of 2 number of sectors is moved to blk_revalidate_disk_zones() as the zone size is already known. Similarly, the number of zones of the device can be calculated in blk_revalidate_disk_zones() before executing the zone report. The kdoc comment for blk_revalidate_disk_zones() is also updated to mention that device drivers must set the device zone size and the max_zone_append_sectors queue limit before calling this function. Signed-off-by: Damien Le Moal <dlemoal@kernel.org> Link: https://lore.kernel.org/r/20230703024812.76778-6-dlemoal@kernel.org Reviewed-by: Bart Van Assche <bvanassche@acm.org> Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2023-07-03 10:48:12 +08:00
if (!capacity)
return -ENODEV;
/*
* Checks that the device driver indicated a valid zone size and that
* the max zone append limit is set.
*/
if (!zone_sectors || !is_power_of_2(zone_sectors)) {
pr_warn("%s: Invalid non power of two zone size (%llu)\n",
disk->disk_name, zone_sectors);
return -ENODEV;
}
if (!q->limits.max_zone_append_sectors) {
pr_warn("%s: Invalid 0 maximum zone append limit\n",
disk->disk_name);
return -ENODEV;
}
block: don't do revalidate zones on invalid devices When we loose a device for whatever reason while (re)scanning zones, we trip over a NULL pointer in blk_revalidate_zone_cb, like in the following log: sd 0:0:0:0: [sda] 3418095616 4096-byte logical blocks: (14.0 TB/12.7 TiB) sd 0:0:0:0: [sda] 52156 zones of 65536 logical blocks sd 0:0:0:0: [sda] Write Protect is off sd 0:0:0:0: [sda] Mode Sense: 37 00 00 08 sd 0:0:0:0: [sda] Write cache: enabled, read cache: enabled, doesn't support DPO or FUA sd 0:0:0:0: [sda] REPORT ZONES start lba 1065287680 failed sd 0:0:0:0: [sda] REPORT ZONES: Result: hostbyte=0x00 driverbyte=0x08 sd 0:0:0:0: [sda] Sense Key : 0xb [current] sd 0:0:0:0: [sda] ASC=0x0 ASCQ=0x6 sda: failed to revalidate zones sd 0:0:0:0: [sda] 0 4096-byte logical blocks: (0 B/0 B) sda: detected capacity change from 14000519643136 to 0 ================================================================== BUG: KASAN: null-ptr-deref in blk_revalidate_zone_cb+0x1b7/0x550 Write of size 8 at addr 0000000000000010 by task kworker/u4:1/58 CPU: 1 PID: 58 Comm: kworker/u4:1 Not tainted 5.8.0-rc1 #692 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.13.0-0-gf21b5a4-rebuilt.opensuse.org 04/01/2014 Workqueue: events_unbound async_run_entry_fn Call Trace: dump_stack+0x7d/0xb0 ? blk_revalidate_zone_cb+0x1b7/0x550 kasan_report.cold+0x5/0x37 ? blk_revalidate_zone_cb+0x1b7/0x550 check_memory_region+0x145/0x1a0 blk_revalidate_zone_cb+0x1b7/0x550 sd_zbc_parse_report+0x1f1/0x370 ? blk_req_zone_write_trylock+0x200/0x200 ? sectors_to_logical+0x60/0x60 ? blk_req_zone_write_trylock+0x200/0x200 ? blk_req_zone_write_trylock+0x200/0x200 sd_zbc_report_zones+0x3c4/0x5e0 ? sd_dif_config_host+0x500/0x500 blk_revalidate_disk_zones+0x231/0x44d ? _raw_write_lock_irqsave+0xb0/0xb0 ? blk_queue_free_zone_bitmaps+0xd0/0xd0 sd_zbc_read_zones+0x8cf/0x11a0 sd_revalidate_disk+0x305c/0x64e0 ? __device_add_disk+0x776/0xf20 ? read_capacity_16.part.0+0x1080/0x1080 ? blk_alloc_devt+0x250/0x250 ? create_object.isra.0+0x595/0xa20 ? kasan_unpoison_shadow+0x33/0x40 sd_probe+0x8dc/0xcd2 really_probe+0x20e/0xaf0 __driver_attach_async_helper+0x249/0x2d0 async_run_entry_fn+0xbe/0x560 process_one_work+0x764/0x1290 ? _raw_read_unlock_irqrestore+0x30/0x30 worker_thread+0x598/0x12f0 ? __kthread_parkme+0xc6/0x1b0 ? schedule+0xed/0x2c0 ? process_one_work+0x1290/0x1290 kthread+0x36b/0x440 ? kthread_create_worker_on_cpu+0xa0/0xa0 ret_from_fork+0x22/0x30 ================================================================== When the device is already gone we end up with the following scenario: The device's capacity is 0 and thus the number of zones will be 0 as well. When allocating the bitmap for the conventional zones, we then trip over a NULL pointer. So if we encounter a zoned block device with a 0 capacity, don't dare to revalidate the zones sizes. Fixes: 6c6b35491422 ("block: set the zone size in blk_revalidate_disk_zones atomically") Signed-off-by: Johannes Thumshirn <johannes.thumshirn@wdc.com> Reviewed-by: Damien Le Moal <damien.lemoal@wdc.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2020-07-30 19:25:17 +08:00
/*
* Ensure that all memory allocations in this context are done as if
* GFP_NOIO was specified.
*/
scsi: block: Improve checks in blk_revalidate_disk_zones() blk_revalidate_disk_zones() implements checks of the zones of a zoned block device, verifying that the zone size is a power of 2 number of sectors, that all zones (except possibly the last one) have the same size and that zones cover the entire addressing space of the device. While these checks are appropriate to verify that well tested hardware devices have an adequate zone configurations, they lack in certain areas which may result in issues with emulated devices implemented with user drivers such as ublk or tcmu. Specifically, this function does not check if the device driver indicated support for the mandatory zone append writes, that is, if the device max_zone_append_sectors queue limit is set to a non-zero value. Additionally, invalid zones such as a zero length zone with a start sector equal to the device capacity will not be detected and result in out of bounds use of the zone bitmaps prepared with the callback function blk_revalidate_zone_cb(). Improve blk_revalidate_disk_zones() to address these inadequate checks, relying on the fact that all device drivers supporting zoned block devices must set the device zone size (chunk_sectors queue limit) and the max_zone_append_sectors queue limit before executing this function. The check for a non-zero max_zone_append_sectors value is done in blk_revalidate_disk_zones() before executing the zone report. The zone report callback function blk_revalidate_zone_cb() is also modified to add a check that a zone start is below the device capacity. The check that the zone size is a power of 2 number of sectors is moved to blk_revalidate_disk_zones() as the zone size is already known. Similarly, the number of zones of the device can be calculated in blk_revalidate_disk_zones() before executing the zone report. The kdoc comment for blk_revalidate_disk_zones() is also updated to mention that device drivers must set the device zone size and the max_zone_append_sectors queue limit before calling this function. Signed-off-by: Damien Le Moal <dlemoal@kernel.org> Link: https://lore.kernel.org/r/20230703024812.76778-6-dlemoal@kernel.org Reviewed-by: Bart Van Assche <bvanassche@acm.org> Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2023-07-03 10:48:12 +08:00
args.disk = disk;
args.nr_zones = (capacity + zone_sectors - 1) >> ilog2(zone_sectors);
noio_flag = memalloc_noio_save();
ret = disk->fops->report_zones(disk, 0, UINT_MAX,
blk_revalidate_zone_cb, &args);
if (!ret) {
pr_warn("%s: No zones reported\n", disk->disk_name);
ret = -ENODEV;
}
memalloc_noio_restore(noio_flag);
block: Introduce blk_revalidate_disk_zones() Drivers exposing zoned block devices have to initialize and maintain correctness (i.e. revalidate) of the device zone bitmaps attached to the device request queue (seq_zones_bitmap and seq_zones_wlock). To simplify coding this, introduce a generic helper function blk_revalidate_disk_zones() suitable for most (and likely all) cases. This new function always update the seq_zones_bitmap and seq_zones_wlock bitmaps as well as the queue nr_zones field when called for a disk using a request based queue. For a disk using a BIO based queue, only the number of zones is updated since these queues do not have schedulers and so do not need the zone bitmaps. With this change, the zone bitmap initialization code in sd_zbc.c can be replaced with a call to this function in sd_zbc_read_zones(), which is called from the disk revalidate block operation method. A call to blk_revalidate_disk_zones() is also added to the null_blk driver for devices created with the zoned mode enabled. Finally, to ensure that zoned devices created with dm-linear or dm-flakey expose the correct number of zones through sysfs, a call to blk_revalidate_disk_zones() is added to dm_table_set_restrictions(). The zone bitmaps allocated and initialized with blk_revalidate_disk_zones() are freed automatically from __blk_release_queue() using the block internal function blk_queue_free_zone_bitmaps(). Reviewed-by: Hannes Reinecke <hare@suse.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Reviewed-by: Mike Snitzer <snitzer@redhat.com> Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2018-10-12 18:08:50 +08:00
/*
* If zones where reported, make sure that the entire disk capacity
* has been checked.
*/
scsi: block: Improve checks in blk_revalidate_disk_zones() blk_revalidate_disk_zones() implements checks of the zones of a zoned block device, verifying that the zone size is a power of 2 number of sectors, that all zones (except possibly the last one) have the same size and that zones cover the entire addressing space of the device. While these checks are appropriate to verify that well tested hardware devices have an adequate zone configurations, they lack in certain areas which may result in issues with emulated devices implemented with user drivers such as ublk or tcmu. Specifically, this function does not check if the device driver indicated support for the mandatory zone append writes, that is, if the device max_zone_append_sectors queue limit is set to a non-zero value. Additionally, invalid zones such as a zero length zone with a start sector equal to the device capacity will not be detected and result in out of bounds use of the zone bitmaps prepared with the callback function blk_revalidate_zone_cb(). Improve blk_revalidate_disk_zones() to address these inadequate checks, relying on the fact that all device drivers supporting zoned block devices must set the device zone size (chunk_sectors queue limit) and the max_zone_append_sectors queue limit before executing this function. The check for a non-zero max_zone_append_sectors value is done in blk_revalidate_disk_zones() before executing the zone report. The zone report callback function blk_revalidate_zone_cb() is also modified to add a check that a zone start is below the device capacity. The check that the zone size is a power of 2 number of sectors is moved to blk_revalidate_disk_zones() as the zone size is already known. Similarly, the number of zones of the device can be calculated in blk_revalidate_disk_zones() before executing the zone report. The kdoc comment for blk_revalidate_disk_zones() is also updated to mention that device drivers must set the device zone size and the max_zone_append_sectors queue limit before calling this function. Signed-off-by: Damien Le Moal <dlemoal@kernel.org> Link: https://lore.kernel.org/r/20230703024812.76778-6-dlemoal@kernel.org Reviewed-by: Bart Van Assche <bvanassche@acm.org> Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2023-07-03 10:48:12 +08:00
if (ret > 0 && args.sector != capacity) {
pr_warn("%s: Missing zones from sector %llu\n",
disk->disk_name, args.sector);
ret = -ENODEV;
}
block: Introduce blk_revalidate_disk_zones() Drivers exposing zoned block devices have to initialize and maintain correctness (i.e. revalidate) of the device zone bitmaps attached to the device request queue (seq_zones_bitmap and seq_zones_wlock). To simplify coding this, introduce a generic helper function blk_revalidate_disk_zones() suitable for most (and likely all) cases. This new function always update the seq_zones_bitmap and seq_zones_wlock bitmaps as well as the queue nr_zones field when called for a disk using a request based queue. For a disk using a BIO based queue, only the number of zones is updated since these queues do not have schedulers and so do not need the zone bitmaps. With this change, the zone bitmap initialization code in sd_zbc.c can be replaced with a call to this function in sd_zbc_read_zones(), which is called from the disk revalidate block operation method. A call to blk_revalidate_disk_zones() is also added to the null_blk driver for devices created with the zoned mode enabled. Finally, to ensure that zoned devices created with dm-linear or dm-flakey expose the correct number of zones through sysfs, a call to blk_revalidate_disk_zones() is added to dm_table_set_restrictions(). The zone bitmaps allocated and initialized with blk_revalidate_disk_zones() are freed automatically from __blk_release_queue() using the block internal function blk_queue_free_zone_bitmaps(). Reviewed-by: Hannes Reinecke <hare@suse.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Reviewed-by: Mike Snitzer <snitzer@redhat.com> Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2018-10-12 18:08:50 +08:00
/*
* Install the new bitmaps and update nr_zones only once the queue is
* stopped and all I/Os are completed (i.e. a scheduler is not
* referencing the bitmaps).
block: Introduce blk_revalidate_disk_zones() Drivers exposing zoned block devices have to initialize and maintain correctness (i.e. revalidate) of the device zone bitmaps attached to the device request queue (seq_zones_bitmap and seq_zones_wlock). To simplify coding this, introduce a generic helper function blk_revalidate_disk_zones() suitable for most (and likely all) cases. This new function always update the seq_zones_bitmap and seq_zones_wlock bitmaps as well as the queue nr_zones field when called for a disk using a request based queue. For a disk using a BIO based queue, only the number of zones is updated since these queues do not have schedulers and so do not need the zone bitmaps. With this change, the zone bitmap initialization code in sd_zbc.c can be replaced with a call to this function in sd_zbc_read_zones(), which is called from the disk revalidate block operation method. A call to blk_revalidate_disk_zones() is also added to the null_blk driver for devices created with the zoned mode enabled. Finally, to ensure that zoned devices created with dm-linear or dm-flakey expose the correct number of zones through sysfs, a call to blk_revalidate_disk_zones() is added to dm_table_set_restrictions(). The zone bitmaps allocated and initialized with blk_revalidate_disk_zones() are freed automatically from __blk_release_queue() using the block internal function blk_queue_free_zone_bitmaps(). Reviewed-by: Hannes Reinecke <hare@suse.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Reviewed-by: Mike Snitzer <snitzer@redhat.com> Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2018-10-12 18:08:50 +08:00
*/
blk_mq_freeze_queue(q);
if (ret > 0) {
disk->nr_zones = args.nr_zones;
swap(disk->seq_zones_wlock, args.seq_zones_wlock);
swap(disk->conv_zones_bitmap, args.conv_zones_bitmap);
if (update_driver_data)
update_driver_data(disk);
ret = 0;
} else {
block: Introduce blk_revalidate_disk_zones() Drivers exposing zoned block devices have to initialize and maintain correctness (i.e. revalidate) of the device zone bitmaps attached to the device request queue (seq_zones_bitmap and seq_zones_wlock). To simplify coding this, introduce a generic helper function blk_revalidate_disk_zones() suitable for most (and likely all) cases. This new function always update the seq_zones_bitmap and seq_zones_wlock bitmaps as well as the queue nr_zones field when called for a disk using a request based queue. For a disk using a BIO based queue, only the number of zones is updated since these queues do not have schedulers and so do not need the zone bitmaps. With this change, the zone bitmap initialization code in sd_zbc.c can be replaced with a call to this function in sd_zbc_read_zones(), which is called from the disk revalidate block operation method. A call to blk_revalidate_disk_zones() is also added to the null_blk driver for devices created with the zoned mode enabled. Finally, to ensure that zoned devices created with dm-linear or dm-flakey expose the correct number of zones through sysfs, a call to blk_revalidate_disk_zones() is added to dm_table_set_restrictions(). The zone bitmaps allocated and initialized with blk_revalidate_disk_zones() are freed automatically from __blk_release_queue() using the block internal function blk_queue_free_zone_bitmaps(). Reviewed-by: Hannes Reinecke <hare@suse.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Reviewed-by: Mike Snitzer <snitzer@redhat.com> Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2018-10-12 18:08:50 +08:00
pr_warn("%s: failed to revalidate zones\n", disk->disk_name);
disk_free_zone_bitmaps(disk);
block: Introduce blk_revalidate_disk_zones() Drivers exposing zoned block devices have to initialize and maintain correctness (i.e. revalidate) of the device zone bitmaps attached to the device request queue (seq_zones_bitmap and seq_zones_wlock). To simplify coding this, introduce a generic helper function blk_revalidate_disk_zones() suitable for most (and likely all) cases. This new function always update the seq_zones_bitmap and seq_zones_wlock bitmaps as well as the queue nr_zones field when called for a disk using a request based queue. For a disk using a BIO based queue, only the number of zones is updated since these queues do not have schedulers and so do not need the zone bitmaps. With this change, the zone bitmap initialization code in sd_zbc.c can be replaced with a call to this function in sd_zbc_read_zones(), which is called from the disk revalidate block operation method. A call to blk_revalidate_disk_zones() is also added to the null_blk driver for devices created with the zoned mode enabled. Finally, to ensure that zoned devices created with dm-linear or dm-flakey expose the correct number of zones through sysfs, a call to blk_revalidate_disk_zones() is added to dm_table_set_restrictions(). The zone bitmaps allocated and initialized with blk_revalidate_disk_zones() are freed automatically from __blk_release_queue() using the block internal function blk_queue_free_zone_bitmaps(). Reviewed-by: Hannes Reinecke <hare@suse.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Reviewed-by: Mike Snitzer <snitzer@redhat.com> Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2018-10-12 18:08:50 +08:00
}
blk_mq_unfreeze_queue(q);
block: Introduce blk_revalidate_disk_zones() Drivers exposing zoned block devices have to initialize and maintain correctness (i.e. revalidate) of the device zone bitmaps attached to the device request queue (seq_zones_bitmap and seq_zones_wlock). To simplify coding this, introduce a generic helper function blk_revalidate_disk_zones() suitable for most (and likely all) cases. This new function always update the seq_zones_bitmap and seq_zones_wlock bitmaps as well as the queue nr_zones field when called for a disk using a request based queue. For a disk using a BIO based queue, only the number of zones is updated since these queues do not have schedulers and so do not need the zone bitmaps. With this change, the zone bitmap initialization code in sd_zbc.c can be replaced with a call to this function in sd_zbc_read_zones(), which is called from the disk revalidate block operation method. A call to blk_revalidate_disk_zones() is also added to the null_blk driver for devices created with the zoned mode enabled. Finally, to ensure that zoned devices created with dm-linear or dm-flakey expose the correct number of zones through sysfs, a call to blk_revalidate_disk_zones() is added to dm_table_set_restrictions(). The zone bitmaps allocated and initialized with blk_revalidate_disk_zones() are freed automatically from __blk_release_queue() using the block internal function blk_queue_free_zone_bitmaps(). Reviewed-by: Hannes Reinecke <hare@suse.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Reviewed-by: Mike Snitzer <snitzer@redhat.com> Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2018-10-12 18:08:50 +08:00
kfree(args.seq_zones_wlock);
kfree(args.conv_zones_bitmap);
block: Introduce blk_revalidate_disk_zones() Drivers exposing zoned block devices have to initialize and maintain correctness (i.e. revalidate) of the device zone bitmaps attached to the device request queue (seq_zones_bitmap and seq_zones_wlock). To simplify coding this, introduce a generic helper function blk_revalidate_disk_zones() suitable for most (and likely all) cases. This new function always update the seq_zones_bitmap and seq_zones_wlock bitmaps as well as the queue nr_zones field when called for a disk using a request based queue. For a disk using a BIO based queue, only the number of zones is updated since these queues do not have schedulers and so do not need the zone bitmaps. With this change, the zone bitmap initialization code in sd_zbc.c can be replaced with a call to this function in sd_zbc_read_zones(), which is called from the disk revalidate block operation method. A call to blk_revalidate_disk_zones() is also added to the null_blk driver for devices created with the zoned mode enabled. Finally, to ensure that zoned devices created with dm-linear or dm-flakey expose the correct number of zones through sysfs, a call to blk_revalidate_disk_zones() is added to dm_table_set_restrictions(). The zone bitmaps allocated and initialized with blk_revalidate_disk_zones() are freed automatically from __blk_release_queue() using the block internal function blk_queue_free_zone_bitmaps(). Reviewed-by: Hannes Reinecke <hare@suse.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Reviewed-by: Mike Snitzer <snitzer@redhat.com> Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2018-10-12 18:08:50 +08:00
return ret;
}
EXPORT_SYMBOL_GPL(blk_revalidate_disk_zones);
void disk_clear_zone_settings(struct gendisk *disk)
{
struct request_queue *q = disk->queue;
blk_mq_freeze_queue(q);
disk_free_zone_bitmaps(disk);
blk_queue_flag_clear(QUEUE_FLAG_ZONE_RESETALL, q);
q->required_elevator_features &= ~ELEVATOR_F_ZBD_SEQ_WRITE;
disk->nr_zones = 0;
disk->max_open_zones = 0;
disk->max_active_zones = 0;
q->limits.chunk_sectors = 0;
q->limits.zone_write_granularity = 0;
q->limits.max_zone_append_sectors = 0;
blk_mq_unfreeze_queue(q);
}