Merge tag 'block-7.4-20261112' of git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux

Pull block fixes from Jens Axboe:

 - ublk fixes: don't publish a new device in the idr until it's fully
   set up, and don't hold ublk_ctl_mutex across device removal, as a
   stuck filesystem on one device otherwise blocked ADD_DEV and DEL_DEV
   for every other ublk device.

 - s390/dasd fixes: re-initialize the RCD buffer magic before every
   request start, fix a wrong free and refcount leak in the check_tcw
   error path, don't trust the userspace-supplied result field in the
   format check, and a typo fix.

* tag 'block-7.4-20261112' of git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux:
  s390/dasd: Don't trust userspace-supplied result field in format check
  s390/dasd: Fix wrong free and refcount leak in build_check_tcw error path
  s390/dasd: Re-initialize RCD buffer with "V1.0" before every start
  s390/dasd: Fix typo 'immediatly' -> 'immediately'
  ublk: don't take ublk_ctl_mutex in DEL_DEV
  ublk: publish a new device by its id only once it is set up
This commit is contained in:
Linus Torvalds
2026-11-13 10:31:05 -08:00
6 changed files with 90 additions and 73 deletions
+40 -26
View File
@@ -881,7 +881,8 @@ static ssize_t ublk_batch_copy_io_tags(struct ublk_batch_fetch_cmd *fcmd,
* by cgroup.
*/
static unsigned int unprivileged_ublks_max = 64;
static unsigned int unprivileged_ublks_added; /* protected by ublk_ctl_mutex */
/* checked and incremented under ublk_ctl_mutex, decremented without it */
static atomic_t unprivileged_ublks_added = ATOMIC_INIT(0);
static struct miscdevice ublk_misc;
@@ -4405,14 +4406,18 @@ static int ublk_alloc_dev_number(struct ublk_device *ub, int idx)
int i = idx;
int err;
/*
* Only reserve the id: the device is published by
* ublk_publish_dev_number() once it is fully set up.
*/
spin_lock(&ublk_idr_lock);
/* allocate id, if @id >= 0, we're requesting that specific id */
if (i >= 0) {
err = idr_alloc(&ublk_index_idr, ub, i, i + 1, GFP_NOWAIT);
err = idr_alloc(&ublk_index_idr, NULL, i, i + 1, GFP_NOWAIT);
if (err == -ENOSPC)
err = -EEXIST;
} else {
err = idr_alloc(&ublk_index_idr, ub, 0, UBLK_MAX_UBLKS,
err = idr_alloc(&ublk_index_idr, NULL, 0, UBLK_MAX_UBLKS,
GFP_NOWAIT);
}
spin_unlock(&ublk_idr_lock);
@@ -4423,6 +4428,19 @@ static int ublk_alloc_dev_number(struct ublk_device *ub, int idx)
return err;
}
/*
* Make the device visible to control commands by its id. Before its char
* device is added, DEL_DEV could find it and remove a char device that was
* never added, and drop the reference that ublk_add_chdev() drops on
* failure.
*/
static void ublk_publish_dev_number(struct ublk_device *ub)
{
spin_lock(&ublk_idr_lock);
WARN_ON_ONCE(idr_replace(&ublk_index_idr, ub, ub->ub_number) != NULL);
spin_unlock(&ublk_idr_lock);
}
static void ublk_free_dev_number(struct ublk_device *ub)
{
spin_lock(&ublk_idr_lock);
@@ -4469,7 +4487,7 @@ static int ublk_add_chdev(struct ublk_device *ub)
goto fail;
if (ub->dev_info.flags & UBLK_F_UNPRIVILEGED_DEV)
unprivileged_ublks_added++;
atomic_inc(&unprivileged_ublks_added);
return 0;
fail:
put_device(dev);
@@ -4501,15 +4519,9 @@ static int ublk_add_tag_set(struct ublk_device *ub)
static void ublk_remove(struct ublk_device *ub)
{
bool unprivileged;
ublk_stop_dev(ub);
cdev_device_del(&ub->cdev, &ub->cdev_dev);
unprivileged = ub->dev_info.flags & UBLK_F_UNPRIVILEGED_DEV;
ublk_put_device(ub);
if (unprivileged)
unprivileged_ublks_added--;
}
static struct ublk_device *ublk_get_device_from_id(int idx)
@@ -4899,7 +4911,7 @@ static int ublk_ctrl_add_dev(const struct ublksrv_ctrl_cmd *header)
ret = -EACCES;
if ((info.flags & UBLK_F_UNPRIVILEGED_DEV) &&
unprivileged_ublks_added >= unprivileged_ublks_max)
atomic_read(&unprivileged_ublks_added) >= unprivileged_ublks_max)
goto out_unlock;
ret = -ENOMEM;
@@ -4991,6 +5003,8 @@ static int ublk_ctrl_add_dev(const struct ublksrv_ctrl_cmd *header)
* ublk_add_chdev() will cleanup everything if it fails.
*/
ret = ublk_add_chdev(ub);
if (!ret)
ublk_publish_dev_number(ub);
goto out_unlock;
out_deinit_queues:
@@ -5023,23 +5037,23 @@ static int ublk_ctrl_del_dev(struct ublk_device **p_ub, bool wait)
{
struct ublk_device *ub = *p_ub;
int idx = ub->ub_number;
int ret;
ret = mutex_lock_killable(&ublk_ctl_mutex);
if (ret)
return ret;
if (!test_bit(UB_STATE_DELETED, &ub->state)) {
ublk_remove(ub);
set_bit(UB_STATE_DELETED, &ub->state);
}
mutex_unlock(&ublk_ctl_mutex);
bool unprivileged = ub->dev_info.flags & UBLK_F_UNPRIVILEGED_DEV;
/*
* Drop the reference outside ublk_ctl_mutex: if it is the last one,
* the release frees the tag set, which waits for an SRCU grace period,
* and holding the mutex would serialize concurrent deletions on it.
* Don't take ublk_ctl_mutex: stopping the device may wait for the
* filesystem on its disk indefinitely, and ADD_DEV and DEL_DEV of all
* other ublk devices would wait for that too. ADD_DEV is done with the
* device, it is found by its id only then.
*/
if (!test_and_set_bit(UB_STATE_DELETED, &ub->state)) {
ublk_remove(ub);
if (unprivileged)
atomic_dec(&unprivileged_ublks_added);
}
/*
* If this is the last reference, the release frees the tag set, which
* waits for an SRCU grace period.
*/
*p_ub = NULL;
ublk_put_device(ub);
+3 -2
View File
@@ -1396,6 +1396,7 @@ int dasd_start_IO(struct dasd_ccw_req *cqr)
cqr->status = DASD_CQR_ERROR;
return -EIO;
}
dasd_start_IO_prepare(cqr);
cqr->startclk = get_tod_clock();
cqr->starttime = jiffies;
cqr->retries--;
@@ -2576,7 +2577,7 @@ static inline int _dasd_term_running_cqr(struct dasd_device *device)
return rc;
}
int dasd_sleep_on_immediatly(struct dasd_ccw_req *cqr)
int dasd_sleep_on_immediately(struct dasd_ccw_req *cqr)
{
struct dasd_device *device;
int rc;
@@ -2628,7 +2629,7 @@ int dasd_sleep_on_immediatly(struct dasd_ccw_req *cqr)
return rc;
}
EXPORT_SYMBOL(dasd_sleep_on_immediatly);
EXPORT_SYMBOL(dasd_sleep_on_immediately);
/*
* Cancels a request that was started with dasd_sleep_on_req.
+1 -1
View File
@@ -750,7 +750,7 @@ static int reset_summary_unit_check(struct alias_lcu *lcu,
cqr->buildclk = get_tod_clock();
cqr->status = DASD_CQR_FILLED;
rc = dasd_sleep_on_immediatly(cqr);
rc = dasd_sleep_on_immediately(cqr);
return rc;
}
+27 -42
View File
@@ -845,20 +845,29 @@ static int dasd_eckd_compare_path_uid(struct dasd_device *device,
return memcmp(&device_uid, &path_uid, sizeof(struct dasd_uid));
}
/*
* The RCD buffer has to start with EBCDIC "V1.0" to show support for
* virtual device SNEQ. The RCD data is written into the same buffer, so
* a failed attempt may already have overwritten the magic. Re-initialize
* it before every start, including restarts by ERP requests.
*/
static void dasd_eckd_rcd_prepare_io(struct dasd_ccw_req *cqr)
{
struct ccw1 *ccw = cqr->cpaddr;
__u8 *rcd_buffer = dma32_to_virt(ccw->cda);
rcd_buffer[0] = 0xE5;
rcd_buffer[1] = 0xF1;
rcd_buffer[2] = 0x4B;
rcd_buffer[3] = 0xF0;
}
static void dasd_eckd_fill_rcd_cqr(struct dasd_device *device,
struct dasd_ccw_req *cqr,
__u8 *rcd_buffer,
__u8 lpm)
{
struct ccw1 *ccw;
/*
* buffer has to start with EBCDIC "V1.0" to show
* support for virtual device SNEQ
*/
rcd_buffer[0] = 0xE5;
rcd_buffer[1] = 0xF1;
rcd_buffer[2] = 0x4B;
rcd_buffer[3] = 0xF0;
ccw = cqr->cpaddr;
ccw->cmd_code = DASD_ECKD_CCW_RCD;
@@ -875,33 +884,10 @@ static void dasd_eckd_fill_rcd_cqr(struct dasd_device *device,
cqr->retries = 256;
cqr->buildclk = get_tod_clock();
cqr->status = DASD_CQR_FILLED;
cqr->prepare_io = dasd_eckd_rcd_prepare_io;
set_bit(DASD_CQR_VERIFY_PATH, &cqr->flags);
}
/*
* Wakeup helper for read_conf
* if the cqr is not done and needs some error recovery
* the buffer has to be re-initialized with the EBCDIC "V1.0"
* to show support for virtual device SNEQ
*/
static void read_conf_cb(struct dasd_ccw_req *cqr, void *data)
{
struct ccw1 *ccw;
__u8 *rcd_buffer;
if (cqr->status != DASD_CQR_DONE) {
ccw = cqr->cpaddr;
rcd_buffer = dma32_to_virt(ccw->cda);
memset(rcd_buffer, 0, sizeof(*rcd_buffer));
rcd_buffer[0] = 0xE5;
rcd_buffer[1] = 0xF1;
rcd_buffer[2] = 0x4B;
rcd_buffer[3] = 0xF0;
}
dasd_wakeup_cb(cqr, data);
}
static int dasd_eckd_read_conf_immediately(struct dasd_device *device,
struct dasd_ccw_req *cqr,
__u8 *rcd_buffer,
@@ -921,8 +907,7 @@ static int dasd_eckd_read_conf_immediately(struct dasd_device *device,
clear_bit(DASD_CQR_FLAGS_USE_ERP, &cqr->flags);
set_bit(DASD_CQR_ALLOW_SLOCK, &cqr->flags);
cqr->retries = 5;
cqr->callback = read_conf_cb;
rc = dasd_sleep_on_immediatly(cqr);
rc = dasd_sleep_on_immediately(cqr);
return rc;
}
@@ -959,7 +944,6 @@ static int dasd_eckd_read_conf_lpm(struct dasd_device *device,
goto out_error;
}
dasd_eckd_fill_rcd_cqr(device, cqr, rcd_buf, lpm);
cqr->callback = read_conf_cb;
ret = dasd_sleep_on(cqr);
/*
* on success we update the user input parms
@@ -2780,7 +2764,8 @@ dasd_eckd_build_check_tcw(struct dasd_device *base, struct format_data_t *fdata,
return cqr;
out_err:
dasd_sfree_request(cqr, startdev);
start_priv->count--;
dasd_ffree_request(cqr, startdev);
return ERR_PTR(rc);
}
@@ -6008,7 +5993,7 @@ __context_unsafe(/* Conditional locking */)
cqr->buildclk = get_tod_clock();
cqr->status = DASD_CQR_FILLED;
rc = dasd_sleep_on_immediatly(cqr);
rc = dasd_sleep_on_immediately(cqr);
if (!rc)
clear_bit(DASD_FLAG_IS_RESERVED, &device->flags);
@@ -6064,7 +6049,7 @@ __context_unsafe(/* Conditional locking */)
cqr->buildclk = get_tod_clock();
cqr->status = DASD_CQR_FILLED;
rc = dasd_sleep_on_immediatly(cqr);
rc = dasd_sleep_on_immediately(cqr);
if (!rc)
set_bit(DASD_FLAG_IS_RESERVED, &device->flags);
@@ -6119,7 +6104,7 @@ __context_unsafe(/* Conditional locking */)
cqr->buildclk = get_tod_clock();
cqr->status = DASD_CQR_FILLED;
rc = dasd_sleep_on_immediatly(cqr);
rc = dasd_sleep_on_immediately(cqr);
if (!rc)
set_bit(DASD_FLAG_IS_RESERVED, &device->flags);
@@ -6183,7 +6168,7 @@ __context_unsafe(/* Conditional locking */)
cqr->status = DASD_CQR_FILLED;
cqr->lpm = usrparm.path_mask;
rc = dasd_sleep_on_immediatly(cqr);
rc = dasd_sleep_on_immediately(cqr);
/* verify that I/O processing didn't modify the path mask */
if (!rc && usrparm.path_mask && (cqr->lpm != usrparm.path_mask))
rc = -EIO;
@@ -6815,7 +6800,7 @@ retry:
cqr->block = NULL;
cqr->expires = 10 * HZ;
set_bit(DASD_CQR_VERIFY_PATH, &cqr->flags);
/* dasd_sleep_on_immediatly does not do complex error
/* dasd_sleep_on_immediately does not do complex error
* recovery so clear erp flag and set retry counter to
* do basic erp */
clear_bit(DASD_CQR_FLAGS_USE_ERP, &cqr->flags);
@@ -6847,7 +6832,7 @@ retry:
cqr->buildclk = get_tod_clock();
cqr->status = DASD_CQR_FILLED;
rc = dasd_sleep_on_immediatly(cqr);
rc = dasd_sleep_on_immediately(cqr);
if (rc == 0) {
prssdp = (struct dasd_psf_prssd_data *) cqr->data;
message_buf = (struct dasd_rssd_messages *)
+16 -1
View File
@@ -147,6 +147,8 @@ struct dasd_ccw_req {
void *data; /* pointer to data area */
struct irb irb; /* device status in case of an error */
struct dasd_ccw_req *refers; /* ERP-chain queueing. */
/* optional prepare function called before every start_io, must not sleep */
void (*prepare_io)(struct dasd_ccw_req *cqr);
void *function; /* originating ERP action */
void *mem_chunk;
@@ -892,6 +894,19 @@ static inline void *dasd_get_callback_data(struct dasd_ccw_req *cqr)
return cqr->callback_data;
}
/*
* Walk down the ERP chain to the original CQR and call its
* prepare_io function if set.
*/
static inline void dasd_start_IO_prepare(struct dasd_ccw_req *cqr)
{
/* ERP requests use the prepare function of the original request */
while (cqr->refers)
cqr = cqr->refers;
if (cqr->prepare_io)
cqr->prepare_io(cqr);
}
static inline bool dasd_req_conflict(struct dasd_ccw_req *cqr1,
struct dasd_ccw_req *cqr2)
{
@@ -998,7 +1013,7 @@ void dasd_schedule_device_bh(struct dasd_device *);
void dasd_schedule_block_bh(struct dasd_block *);
int dasd_sleep_on(struct dasd_ccw_req *);
int dasd_sleep_on_queue(struct list_head *);
int dasd_sleep_on_immediatly(struct dasd_ccw_req *);
int dasd_sleep_on_immediately(struct dasd_ccw_req *);
int dasd_sleep_on_queue_interruptible(struct list_head *);
int dasd_sleep_on_interruptible(struct dasd_ccw_req *);
void dasd_device_set_timer(struct dasd_device *, int);
+3 -1
View File
@@ -303,7 +303,9 @@ static int dasd_ioctl_check_format(struct block_device *bdev, void __user *argp)
goto out_err;
}
if (copy_from_user(&cdata, argp, sizeof(cdata))) {
/* copy only input fields, clear the rest */
memset(&cdata, 0, sizeof(cdata));
if (copy_from_user(&cdata.expect, argp, sizeof(cdata.expect))) {
rc = -EFAULT;
goto out_err;
}