linux_dsm_epyc7002/block/blk-zoned.c
Johannes Thumshirn 1a1206dc4c 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 
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: 6c6b354914 ("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>
2020-08-03 09:24:04 -06:00

538 lines
14 KiB
C

// 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>
#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);
static inline sector_t blk_zone_start(struct request_queue *q,
sector_t sector)
{
sector_t zone_mask = blk_queue_zone_sectors(q) - 1;
return sector & ~zone_mask;
}
/*
* 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->seq_zones_wlock)
return false;
if (blk_rq_is_passthrough(rq))
return false;
switch (req_op(rq)) {
case REQ_OP_WRITE_ZEROES:
case REQ_OP_WRITE_SAME:
case REQ_OP_WRITE:
return blk_rq_zone_is_seq(rq);
default:
return false;
}
}
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->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);
void __blk_req_zone_write_lock(struct request *rq)
{
if (WARN_ON_ONCE(test_and_set_bit(blk_rq_zone_no(rq),
rq->q->seq_zones_wlock)))
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->seq_zones_wlock)
WARN_ON_ONCE(!test_and_clear_bit(blk_rq_zone_no(rq),
rq->q->seq_zones_wlock));
}
EXPORT_SYMBOL_GPL(__blk_req_zone_write_unlock);
/**
* blkdev_nr_zones - Get number of zones
* @disk: Target gendisk
*
* 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 blkdev_nr_zones(struct gendisk *disk)
{
sector_t zone_sectors = blk_queue_zone_sectors(disk->queue);
if (!blk_queue_is_zoned(disk->queue))
return 0;
return (get_capacity(disk) + zone_sectors - 1) >> ilog2(zone_sectors);
}
EXPORT_SYMBOL_GPL(blkdev_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 (!blk_queue_is_zoned(bdev_get_queue(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);
static inline bool blkdev_allow_reset_all_zones(struct block_device *bdev,
sector_t sector,
sector_t nr_sectors)
{
if (!blk_queue_zone_resetall(bdev_get_queue(bdev)))
return false;
/*
* REQ_OP_ZONE_RESET_ALL can be executed only if the number of sectors
* of the applicable zone range is the entire disk.
*/
return !sector && nr_sectors == get_capacity(bdev->bd_disk);
}
/**
* blkdev_zone_mgmt - Execute a zone management operation on a range of zones
* @bdev: Target block device
* @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:
* 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.
* 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_opf op,
sector_t sector, sector_t nr_sectors,
gfp_t gfp_mask)
{
struct request_queue *q = bdev_get_queue(bdev);
sector_t zone_sectors = blk_queue_zone_sectors(q);
sector_t capacity = get_capacity(bdev->bd_disk);
sector_t end_sector = sector + nr_sectors;
struct bio *bio = NULL;
int ret;
if (!blk_queue_is_zoned(q))
return -EOPNOTSUPP;
if (bdev_read_only(bdev))
return -EPERM;
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 (sector & (zone_sectors - 1))
return -EINVAL;
if ((nr_sectors & (zone_sectors - 1)) && end_sector != capacity)
return -EINVAL;
while (sector < end_sector) {
bio = blk_next_bio(bio, 0, gfp_mask);
bio_set_dev(bio, bdev);
/*
* Special case for the zone reset operation that reset all
* zones, this is useful for applications like mkfs.
*/
if (op == REQ_OP_ZONE_RESET &&
blkdev_allow_reset_all_zones(bdev, sector, nr_sectors)) {
bio->bi_opf = REQ_OP_ZONE_RESET_ALL;
break;
}
bio->bi_opf = op | REQ_SYNC;
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;
}
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, fmode_t mode,
unsigned int cmd, unsigned long arg)
{
void __user *argp = (void __user *)arg;
struct zone_report_args args;
struct request_queue *q;
struct blk_zone_report rep;
int ret;
if (!argp)
return -EINVAL;
q = bdev_get_queue(bdev);
if (!q)
return -ENXIO;
if (!blk_queue_is_zoned(q))
return -ENOTTY;
if (!capable(CAP_SYS_ADMIN))
return -EACCES;
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;
}
/*
* BLKRESETZONE, BLKOPENZONE, BLKCLOSEZONE and BLKFINISHZONE ioctl processing.
* Called from blkdev_ioctl.
*/
int blkdev_zone_mgmt_ioctl(struct block_device *bdev, fmode_t mode,
unsigned int cmd, unsigned long arg)
{
void __user *argp = (void __user *)arg;
struct request_queue *q;
struct blk_zone_range zrange;
enum req_opf op;
if (!argp)
return -EINVAL;
q = bdev_get_queue(bdev);
if (!q)
return -ENXIO;
if (!blk_queue_is_zoned(q))
return -ENOTTY;
if (!capable(CAP_SYS_ADMIN))
return -EACCES;
if (!(mode & FMODE_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;
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;
}
return blkdev_zone_mgmt(bdev, op, zrange.sector, zrange.nr_sectors,
GFP_KERNEL);
}
static inline unsigned long *blk_alloc_zone_bitmap(int node,
unsigned int nr_zones)
{
return kcalloc_node(BITS_TO_LONGS(nr_zones), sizeof(unsigned long),
GFP_NOIO, node);
}
void blk_queue_free_zone_bitmaps(struct request_queue *q)
{
kfree(q->conv_zones_bitmap);
q->conv_zones_bitmap = NULL;
kfree(q->seq_zones_wlock);
q->seq_zones_wlock = NULL;
}
struct blk_revalidate_zone_args {
struct gendisk *disk;
unsigned long *conv_zones_bitmap;
unsigned long *seq_zones_wlock;
unsigned int nr_zones;
sector_t zone_sectors;
sector_t sector;
};
/*
* 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)
{
struct blk_revalidate_zone_args *args = data;
struct gendisk *disk = args->disk;
struct request_queue *q = disk->queue;
sector_t capacity = get_capacity(disk);
/*
* All zones must have the same size, with the exception on an eventual
* smaller last zone.
*/
if (zone->start == 0) {
if (zone->len == 0 || !is_power_of_2(zone->len)) {
pr_warn("%s: Invalid zoned device with non power of two zone size (%llu)\n",
disk->disk_name, zone->len);
return -ENODEV;
}
args->zone_sectors = zone->len;
args->nr_zones = (capacity + zone->len - 1) >> ilog2(zone->len);
} else if (zone->start + args->zone_sectors < capacity) {
if (zone->len != args->zone_sectors) {
pr_warn("%s: Invalid zoned device with non constant zone size\n",
disk->disk_name);
return -ENODEV;
}
} else {
if (zone->len > args->zone_sectors) {
pr_warn("%s: Invalid zoned device with larger last zone size\n",
disk->disk_name);
return -ENODEV;
}
}
/* Check for 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;
}
/* 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;
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;
}
break;
default:
pr_warn("%s: Invalid zone type 0x%x at sectors %llu\n",
disk->disk_name, (int)zone->type, zone->start);
return -ENODEV;
}
args->sector += zone->len;
return 0;
}
/**
* 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
*
* Helper function for low-level device drivers to (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. For BIO based
* drivers only q->nr_zones needs to be updated 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.
*/
int blk_revalidate_disk_zones(struct gendisk *disk,
void (*update_driver_data)(struct gendisk *disk))
{
struct request_queue *q = disk->queue;
struct blk_revalidate_zone_args args = {
.disk = disk,
};
unsigned int noio_flag;
int ret;
if (WARN_ON_ONCE(!blk_queue_is_zoned(q)))
return -EIO;
if (WARN_ON_ONCE(!queue_is_mq(q)))
return -EIO;
if (!get_capacity(disk))
return -EIO;
/*
* Ensure that all memory allocations in this context are done as if
* GFP_NOIO was specified.
*/
noio_flag = memalloc_noio_save();
ret = disk->fops->report_zones(disk, 0, UINT_MAX,
blk_revalidate_zone_cb, &args);
memalloc_noio_restore(noio_flag);
/*
* 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).
*/
blk_mq_freeze_queue(q);
if (ret >= 0) {
blk_queue_chunk_sectors(q, args.zone_sectors);
q->nr_zones = args.nr_zones;
swap(q->seq_zones_wlock, args.seq_zones_wlock);
swap(q->conv_zones_bitmap, args.conv_zones_bitmap);
if (update_driver_data)
update_driver_data(disk);
ret = 0;
} else {
pr_warn("%s: failed to revalidate zones\n", disk->disk_name);
blk_queue_free_zone_bitmaps(q);
}
blk_mq_unfreeze_queue(q);
kfree(args.seq_zones_wlock);
kfree(args.conv_zones_bitmap);
return ret;
}
EXPORT_SYMBOL_GPL(blk_revalidate_disk_zones);