From: Damien Le Moal <dlemoal@kernel.org>
To: Jens Axboe <axboe@kernel.dk>,
linux-block@vger.kernel.org, Christoph Hellwig <hch@lst.de>,
linux-scsi@vger.kernel.org,
"Martin K . Petersen" <martin.petersen@oracle.com>
Subject: [PATCH v6 05/10] zloop: avoid potential wp_lock deadlocks
Date: Tue, 13 Oct 2026 21:27:45 +0900 [thread overview]
Message-ID: <20261013122750.2237843-6-dlemoal@kernel.org> (raw)
In-Reply-To: <20261013122750.2237843-1-dlemoal@kernel.org>
zloop_queue_rq() maybe called from softirq context with interrupts
disabled. However, zloop_queue_rq() may call
zloop_set_zone_append_sector() which takes a zone wp_lock using a simple
spin_lock(). This can cause deadlocks with competing contexts that have
already taken that lock. Avoid this by using the irq disabling/enabling
variants of spin_lock/unlock. While at it, zloop_report_zones() is also
modified to take the wp_lock around both the write pointer and the zone
condition reporting to ensure that both values are consistent for a
report.
Fixes: fcc6eaa3a03a ("zloop: introduce the ordered_zone_append configuration parameter")
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
---
drivers/block/zloop.c | 37 ++++++++++++++++++++++---------------
1 file changed, 22 insertions(+), 15 deletions(-)
diff --git a/drivers/block/zloop.c b/drivers/block/zloop.c
index 8f485ef51557..cbe199c135b0 100644
--- a/drivers/block/zloop.c
+++ b/drivers/block/zloop.c
@@ -312,6 +312,7 @@ static int zloop_update_seq_zone(struct zloop_device *zlo, unsigned int zone_no)
struct zloop_zone *zone = &zlo->zones[zone_no];
struct kstat stat;
sector_t file_sectors;
+ unsigned long flags;
int ret;
lockdep_assert_held(&zone->lock);
@@ -337,7 +338,7 @@ static int zloop_update_seq_zone(struct zloop_device *zlo, unsigned int zone_no)
return -EINVAL;
}
- spin_lock(&zone->wp_lock);
+ spin_lock_irqsave(&zone->wp_lock, flags);
if (!file_sectors) {
zloop_mark_empty(zlo, zone);
} else if (file_sectors == zlo->zone_capacity) {
@@ -348,7 +349,7 @@ static int zloop_update_seq_zone(struct zloop_device *zlo, unsigned int zone_no)
zone->cond = BLK_ZONE_COND_CLOSED;
zone->wp = zone->start + file_sectors;
}
- spin_unlock(&zone->wp_lock);
+ spin_unlock_irqrestore(&zone->wp_lock, flags);
return 0;
}
@@ -381,6 +382,7 @@ static int zloop_open_zone(struct zloop_device *zlo, unsigned int zone_no)
static int zloop_close_zone(struct zloop_device *zlo, unsigned int zone_no)
{
struct zloop_zone *zone = &zlo->zones[zone_no];
+ unsigned long flags;
int ret = 0;
if (test_bit(ZLOOP_ZONE_CONV, &zone->flags))
@@ -399,13 +401,13 @@ static int zloop_close_zone(struct zloop_device *zlo, unsigned int zone_no)
break;
case BLK_ZONE_COND_IMP_OPEN:
case BLK_ZONE_COND_EXP_OPEN:
- spin_lock(&zone->wp_lock);
+ spin_lock_irqsave(&zone->wp_lock, flags);
zloop_lru_remove_open_zone(zlo, zone);
if (zone->wp == zone->start)
zone->cond = BLK_ZONE_COND_EMPTY;
else
zone->cond = BLK_ZONE_COND_CLOSED;
- spin_unlock(&zone->wp_lock);
+ spin_unlock_irqrestore(&zone->wp_lock, flags);
break;
case BLK_ZONE_COND_EMPTY:
case BLK_ZONE_COND_FULL:
@@ -423,6 +425,7 @@ static int zloop_close_zone(struct zloop_device *zlo, unsigned int zone_no)
static int zloop_reset_zone(struct zloop_device *zlo, unsigned int zone_no)
{
struct zloop_zone *zone = &zlo->zones[zone_no];
+ unsigned long flags;
int ret = 0;
if (test_bit(ZLOOP_ZONE_CONV, &zone->flags))
@@ -440,10 +443,10 @@ static int zloop_reset_zone(struct zloop_device *zlo, unsigned int zone_no)
goto unlock;
}
- spin_lock(&zone->wp_lock);
+ spin_lock_irqsave(&zone->wp_lock, flags);
zloop_mark_empty(zlo, zone);
clear_bit(ZLOOP_ZONE_SEQ_ERROR, &zone->flags);
- spin_unlock(&zone->wp_lock);
+ spin_unlock_irqrestore(&zone->wp_lock, flags);
unlock:
mutex_unlock(&zone->lock);
@@ -468,6 +471,7 @@ static int zloop_reset_all_zones(struct zloop_device *zlo)
static int zloop_finish_zone(struct zloop_device *zlo, unsigned int zone_no)
{
struct zloop_zone *zone = &zlo->zones[zone_no];
+ unsigned long flags;
int ret = 0;
if (test_bit(ZLOOP_ZONE_CONV, &zone->flags))
@@ -486,10 +490,10 @@ static int zloop_finish_zone(struct zloop_device *zlo, unsigned int zone_no)
goto unlock;
}
- spin_lock(&zone->wp_lock);
+ spin_lock_irqsave(&zone->wp_lock, flags);
zloop_mark_full(zlo, zone);
clear_bit(ZLOOP_ZONE_SEQ_ERROR, &zone->flags);
- spin_unlock(&zone->wp_lock);
+ spin_unlock_irqrestore(&zone->wp_lock, flags);
unlock:
mutex_unlock(&zone->lock);
@@ -579,9 +583,10 @@ static int zloop_seq_write_prep(struct zloop_cmd *cmd)
bool is_append = req_op(rq) == REQ_OP_ZONE_APPEND;
struct zloop_zone *zone = &zlo->zones[zone_no];
sector_t zone_end = zone->start + zlo->zone_capacity;
+ unsigned long flags;
int ret = 0;
- spin_lock(&zone->wp_lock);
+ spin_lock_irqsave(&zone->wp_lock, flags);
/*
* Zone append operations always go at the current write pointer, but
@@ -632,7 +637,7 @@ static int zloop_seq_write_prep(struct zloop_cmd *cmd)
zloop_mark_full(zlo, zone);
}
out_unlock:
- spin_unlock(&zone->wp_lock);
+ spin_unlock_irqrestore(&zone->wp_lock, flags);
return ret;
}
@@ -887,12 +892,13 @@ static bool zloop_set_zone_append_sector(struct request *rq)
struct zloop_zone *zone = &zlo->zones[zone_no];
sector_t zone_end = zone->start + zlo->zone_capacity;
sector_t nr_sectors = blk_rq_sectors(rq);
+ unsigned long flags;
- spin_lock(&zone->wp_lock);
+ spin_lock_irqsave(&zone->wp_lock, flags);
if (zone->cond == BLK_ZONE_COND_FULL ||
zone->wp + nr_sectors > zone_end) {
- spin_unlock(&zone->wp_lock);
+ spin_unlock_irqrestore(&zone->wp_lock, flags);
return false;
}
@@ -901,7 +907,7 @@ static bool zloop_set_zone_append_sector(struct request *rq)
if (zone->wp >= zone_end)
zloop_mark_full(zlo, zone);
- spin_unlock(&zone->wp_lock);
+ spin_unlock_irqrestore(&zone->wp_lock, flags);
return true;
}
@@ -962,6 +968,7 @@ static int zloop_report_zones(struct gendisk *disk, sector_t sector,
struct zloop_device *zlo = disk->private_data;
struct blk_zone blkz = {};
unsigned int first, i;
+ unsigned long flags;
int ret;
first = disk_zone_no(disk, sector);
@@ -985,10 +992,10 @@ static int zloop_report_zones(struct gendisk *disk, sector_t sector,
blkz.start = zone->start;
blkz.len = zlo->zone_size;
- spin_lock(&zone->wp_lock);
+ spin_lock_irqsave(&zone->wp_lock, flags);
blkz.wp = zone->wp;
- spin_unlock(&zone->wp_lock);
blkz.cond = zone->cond;
+ spin_unlock_irqrestore(&zone->wp_lock, flags);
if (test_bit(ZLOOP_ZONE_CONV, &zone->flags)) {
blkz.type = BLK_ZONE_TYPE_CONVENTIONAL;
blkz.capacity = zlo->zone_size;
--
2.55.0
next prev parent reply other threads:[~2026-10-13 12:27 UTC|newest]
Thread overview: 11+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-10-13 12:27 [PATCH v6 00/10] Add support for storage element depopulation Damien Le Moal
2026-10-13 12:27 ` [PATCH v6 01/10] block: introduce disk_zone_is_offline() Damien Le Moal
2026-10-13 12:27 ` [PATCH v6 02/10] block: refactor blk_revalidate_disk_zones() Damien Le Moal
2026-10-13 12:27 ` [PATCH v6 03/10] block: introduce storage element management Damien Le Moal
2026-10-13 12:27 ` [PATCH v6 04/10] block: add storage element management ioctls Damien Le Moal
2026-10-13 12:27 ` Damien Le Moal [this message]
2026-10-13 12:27 ` [PATCH v6 06/10] zloop: add storage element emulation Damien Le Moal
2026-10-13 12:27 ` [PATCH v6 07/10] zloop: add degrade_element control command Damien Le Moal
2026-10-13 12:27 ` [PATCH v6 08/10] scsi: sd: fail read commands to offline zones early Damien Le Moal
2026-10-13 12:27 ` [PATCH v6 09/10] scsi: sd_zbc: always revalidate zones for disks supporting head depopulation Damien Le Moal
2026-10-13 12:27 ` [PATCH v6 10/10] scsi: sd_zbc: define storage element management operations Damien Le Moal
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20261013122750.2237843-6-dlemoal@kernel.org \
--to=dlemoal@kernel.org \
--cc=axboe@kernel.dk \
--cc=hch@lst.de \
--cc=linux-block@vger.kernel.org \
--cc=linux-scsi@vger.kernel.org \
--cc=martin.petersen@oracle.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox