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 5/7] zloop: add degrade_element control command
Date: Mon, 5 Oct 2026 18:46:30 +0900 [thread overview]
Message-ID: <20261005094632.580753-6-dlemoal@kernel.org> (raw)
In-Reply-To: <20261005094632.580753-1-dlemoal@kernel.org>
Allow users to mark storage elements of a zloop device as degraded using
the new "degrade_element" control command. The element to degrade is
indicated using the element_id option. Example:
echo "degrade_element id=0,element_id=2" > /dev/zloop-control
If the element ID identifies an all access storage element, read and write
operations targeting a zone served by the degraded lement are failed.
For a partial access storage element, read or write operations are failed
depending on the storage element type.
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
---
drivers/block/zloop.c | 112 ++++++++++++++++++++++++++++++++++++++++--
1 file changed, 107 insertions(+), 5 deletions(-)
diff --git a/drivers/block/zloop.c b/drivers/block/zloop.c
index 7e6b5cc8017d..1d51060b832b 100644
--- a/drivers/block/zloop.c
+++ b/drivers/block/zloop.c
@@ -38,6 +38,7 @@ enum {
ZLOOP_OPT_DISCARD_WRITE_CACHE = (1 << 11),
ZLOOP_OPT_MAX_OPEN_ZONES = (1 << 12),
ZLOOP_OPT_STOR_ELEMENTS = (1 << 13),
+ ZLOOP_OPT_ELEMENT_ID = (1 << 14),
};
static const match_table_t zloop_opt_tokens = {
@@ -55,6 +56,7 @@ static const match_table_t zloop_opt_tokens = {
{ ZLOOP_OPT_DISCARD_WRITE_CACHE, "discard_write_cache" },
{ ZLOOP_OPT_MAX_OPEN_ZONES, "max_open_zones=%u" },
{ ZLOOP_OPT_STOR_ELEMENTS, "stor_elements=%u" },
+ { ZLOOP_OPT_ELEMENT_ID, "element_id=%u" },
{ ZLOOP_OPT_ERR, NULL }
};
@@ -81,6 +83,7 @@ enum zloop_stor_elements {
#define ZLOOP_DEF_ZONE_APPEND true
#define ZLOOP_DEF_ORDERED_ZONE_APPEND false
#define ZLOOP_DEF_STOR_ELEMENTS ZLOOP_STOR_ELEMENTS_NONE
+#define ZLOOP_DEF_ELEMENT_ID 0
/* Arbitrary limit on the zone size (16GB). */
#define ZLOOP_MAX_ZONE_SIZE_MB 16384
@@ -101,6 +104,7 @@ struct zloop_options {
bool ordered_zone_append;
bool discard_write_cache;
enum zloop_stor_elements stor_elements;
+ unsigned int element_id;
};
/*
@@ -201,6 +205,29 @@ static unsigned int rq_zone_no(struct request *rq)
return blk_rq_pos(rq) >> zlo->zone_shift;
}
+static bool zloop_zone_healthy(struct zloop_device *zlo,
+ struct zloop_zone *zone, bool write)
+{
+ struct blk_storage_element *se;
+
+ if (!zlo->nr_elements)
+ return true;
+
+ /* Check the zone condition first. */
+ if (zone->cond == BLK_ZONE_COND_OFFLINE)
+ return false;
+ if (zone->cond == BLK_ZONE_COND_READONLY && write)
+ return false;
+
+ /* Check the health state of the storage element serving the zone. */
+ if (write)
+ se = &zlo->elements[zone->wr_se_id - 1];
+ else
+ se = &zlo->elements[zone->rd_se_id - 1];
+
+ return se->status == BLK_SE_STS_DEGRADED;
+}
+
/*
* Open an already open zone. This is mostly a no-op, except for the imp open ->
* exp open condition change that may happen. We also move a zone at the tail of
@@ -733,9 +760,7 @@ static void zloop_rw(struct zloop_cmd *cmd)
zone->start + zlo->zone_size))
goto out;
- if (zone->cond == BLK_ZONE_COND_OFFLINE)
- goto out;
- if (zone->cond == BLK_ZONE_COND_READONLY && is_write)
+ if (!zloop_zone_healthy(zlo, zone, is_write))
goto out;
if (test_and_clear_bit(ZLOOP_ZONE_SEQ_ERROR, &zone->flags)) {
@@ -1095,6 +1120,31 @@ static int zloop_report_elements(struct gendisk *disk,
return 0;
}
+static int zloop_degrade_element(struct zloop_device *zlo,
+ unsigned int element_id)
+{
+ struct blk_storage_element *se;
+ int ret = 0;
+
+ if (zlo->stor_elements == ZLOOP_STOR_ELEMENTS_NONE)
+ return -EOPNOTSUPP;
+
+ if (!element_id || element_id > zlo->nr_elements)
+ return -EINVAL;
+
+ mutex_lock(&zlo->stor_elements_lock);
+
+ se = &zlo->elements[element_id - 1];
+ if (se->status == BLK_SE_STS_OK)
+ se->status = BLK_SE_STS_DEGRADED;
+ else
+ ret = -EINVAL;
+
+ mutex_unlock(&zlo->stor_elements_lock);
+
+ return ret;
+}
+
static void zloop_remove_element_work(struct work_struct *work)
{
struct zloop_device *zlo = container_of(work, struct zloop_device,
@@ -1904,6 +1954,39 @@ static int zloop_ctl_remove(struct zloop_options *opts)
return 0;
}
+static int zloop_ctl_degrade_element(struct zloop_options *opts)
+{
+ struct zloop_device *zlo;
+ int ret = 0;
+
+ if (!(opts->mask & ZLOOP_OPT_ID)) {
+ pr_err("No ID specified for degrade_element\n");
+ return -EINVAL;
+ }
+
+ if (opts->mask & ~(ZLOOP_OPT_ID | ZLOOP_OPT_ELEMENT_ID)) {
+ pr_err("Invalid option specified for degrade_element\n");
+ return -EINVAL;
+ }
+
+ mutex_lock(&zloop_ctl_mutex);
+ zlo = idr_find(&zloop_index_idr, opts->id);
+ if (!zlo || zlo->state == Zlo_creating)
+ ret = -ENODEV;
+ else if (zlo->state == Zlo_deleting)
+ ret = -EINVAL;
+ mutex_unlock(&zloop_ctl_mutex);
+ if (ret)
+ return ret;
+
+ ret = zloop_degrade_element(zlo, opts->element_id);
+ if (!ret)
+ pr_info("Degraded element %u of device %u\n",
+ opts->id, opts->element_id);
+
+ return ret;
+}
+
static int zloop_parse_options(struct zloop_options *opts, const char *buf)
{
substring_t args[MAX_OPT_ARGS];
@@ -1924,6 +2007,7 @@ static int zloop_parse_options(struct zloop_options *opts, const char *buf)
opts->zone_append = ZLOOP_DEF_ZONE_APPEND;
opts->ordered_zone_append = ZLOOP_DEF_ORDERED_ZONE_APPEND;
opts->stor_elements = ZLOOP_DEF_STOR_ELEMENTS;
+ opts->element_id = ZLOOP_DEF_ELEMENT_ID;
if (!buf)
return 0;
@@ -2075,6 +2159,13 @@ static int zloop_parse_options(struct zloop_options *opts, const char *buf)
}
opts->stor_elements = token;
break;
+ case ZLOOP_OPT_ELEMENT_ID:
+ if (match_uint(args, &token)) {
+ ret = -EINVAL;
+ goto out;
+ }
+ opts->element_id = token;
+ break;
case ZLOOP_OPT_ERR:
default:
pr_warn("unknown parameter or missing value '%s'\n", p);
@@ -2103,14 +2194,16 @@ static int zloop_parse_options(struct zloop_options *opts, const char *buf)
enum {
ZLOOP_CTL_ADD,
ZLOOP_CTL_REMOVE,
+ ZLOOP_CTL_DEGRADE_ELEMENT,
};
static struct zloop_ctl_op {
int code;
const char *name;
} zloop_ctl_ops[] = {
- { ZLOOP_CTL_ADD, "add" },
- { ZLOOP_CTL_REMOVE, "remove" },
+ { ZLOOP_CTL_ADD, "add" },
+ { ZLOOP_CTL_REMOVE, "remove" },
+ { ZLOOP_CTL_DEGRADE_ELEMENT, "degrade_element" },
{ -1, NULL },
};
@@ -2158,6 +2251,9 @@ static ssize_t zloop_ctl_write(struct file *file, const char __user *ubuf,
case ZLOOP_CTL_REMOVE:
ret = zloop_ctl_remove(&opts);
break;
+ case ZLOOP_CTL_DEGRADE_ELEMENT:
+ ret = zloop_ctl_degrade_element(&opts);
+ break;
default:
pr_err("Invalid operation\n");
ret = -EINVAL;
@@ -2181,6 +2277,8 @@ static int zloop_ctl_show(struct seq_file *seq_file, void *private)
tok = &zloop_opt_tokens[i];
if (!tok->pattern)
break;
+ if (tok->token == ZLOOP_OPT_ELEMENT_ID)
+ continue;
if (i)
seq_putc(seq_file, ',');
seq_puts(seq_file, tok->pattern);
@@ -2191,6 +2289,10 @@ static int zloop_ctl_show(struct seq_file *seq_file, void *private)
seq_puts(seq_file, zloop_ctl_ops[1].name);
seq_puts(seq_file, " id=%d\n");
+ /* Degrade element operation */
+ seq_puts(seq_file, zloop_ctl_ops[2].name);
+ seq_puts(seq_file, " id=%d,element_id=%d\n");
+
return 0;
}
--
2.55.0
next prev parent reply other threads:[~2026-10-05 9:46 UTC|newest]
Thread overview: 20+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-10-05 9:46 [PATCH 0/7] Add support for storage element depopulation Damien Le Moal
2026-10-05 9:46 ` [PATCH 1/7] block: fail reads to offline zones early Damien Le Moal
2026-10-05 10:45 ` Hannes Reinecke
2026-10-05 9:46 ` [PATCH 2/7] block: introduce storage element management Damien Le Moal
2026-10-05 10:52 ` Hannes Reinecke
2026-10-05 22:15 ` kernel test robot
2026-10-05 9:46 ` [PATCH 3/7] block: add storage element management ioctls Damien Le Moal
2026-10-05 11:09 ` Hannes Reinecke
2026-10-05 9:46 ` [PATCH 4/7] zloop: add storage element emulation Damien Le Moal
2026-10-05 11:14 ` Hannes Reinecke
2026-10-05 9:46 ` Damien Le Moal [this message]
2026-10-05 11:17 ` [PATCH 5/7] zloop: add degrade_element control command Hannes Reinecke
2026-10-05 9:46 ` [PATCH 6/7] scsi: sd_zbc: always revalidate zones for disks supporting head depopulation Damien Le Moal
2026-10-05 11:19 ` Hannes Reinecke
2026-10-05 9:46 ` [PATCH 7/7] scsi: sd_zbc: define storage element management operations Damien Le Moal
2026-10-05 11:48 ` Hannes Reinecke
2026-10-05 20:48 ` kernel test robot
2026-10-05 21:41 ` kernel test robot
2026-10-05 11:13 ` [PATCH 0/7] Add support for storage element depopulation Hannes Reinecke
2026-10-07 7:14 ` 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=20261005094632.580753-6-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