Commit 734e1a86 authored by Damien Le Moal's avatar Damien Le Moal Committed by Jens Axboe
Browse files

block: Prevent deadlocks when switching elevators 



Commit af281414 ("block: freeze the queue in queue_attr_store")
changed queue_attr_store() to always freeze a sysfs attribute queue
before calling the attribute store() method, to ensure that no IOs are
in-flight when an attribute value is being updated.

However, this change created a potential deadlock situation for the
scheduler queue attribute as changing the queue elevator with
elv_iosched_store() can result in a call to request_module() if the user
requested module is not already registered. If the file of the requested
module is stored on the block device of the frozen queue, a deadlock
will happen as the read operations triggered by request_module() will
wait for the queue freeze to end.

Solve this issue by introducing the load_module method in struct
queue_sysfs_entry, and to calling this method function in
queue_attr_store() before freezing the attribute queue.
The macro definition QUEUE_RW_LOAD_MODULE_ENTRY() is added to define a
queue sysfs attribute that needs loading a module.

The definition of the scheduler atrribute is changed to using
QUEUE_RW_LOAD_MODULE_ENTRY(), with the function
elv_iosched_load_module() defined as the load_module method.
elv_iosched_store() can then be simplified to remove the call to
request_module().

Reported-by: default avatarRichard W.M. Jones <rjones@redhat.com>
Reported-by: default avatarJiri Jaburek <jjaburek@redhat.com>
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=219166


Fixes: af281414 ("block: freeze the queue in queue_attr_store")
Cc: stable@vger.kernel.org
Signed-off-by: default avatarDamien Le Moal <dlemoal@kernel.org>
Tested-by: default avatarRichard W.M. Jones <rjones@redhat.com>
Link: https://lore.kernel.org/r/20240908000704.414538-1-dlemoal@kernel.org


Signed-off-by: default avatarJens Axboe <axboe@kernel.dk>
parent 4ba032bc

block/blk-sysfs.c

+21 −1
Original line number Diff line number Diff line
@@ -23,6 +23,7 @@ 
struct queue_sysfs_entry {

	struct attribute attr;

	ssize_t (*show)(struct gendisk *disk, char *page);

	int (*load_module)(struct gendisk *disk, const char *page, size_t count);

	ssize_t (*store)(struct gendisk *disk, const char *page, size_t count);

};
@@ -413,6 +414,14 @@ static struct queue_sysfs_entry _prefix##_entry = { \ 
	.store	= _prefix##_store,			\

};



#define QUEUE_RW_LOAD_MODULE_ENTRY(_prefix, _name)		\

static struct queue_sysfs_entry _prefix##_entry = {		\

	.attr		= { .name = _name, .mode = 0644 },	\

	.show		= _prefix##_show,			\

	.load_module	= _prefix##_load_module,		\

	.store		= _prefix##_store,			\

}



QUEUE_RW_ENTRY(queue_requests, "nr_requests");

QUEUE_RW_ENTRY(queue_ra, "read_ahead_kb");

QUEUE_RW_ENTRY(queue_max_sectors, "max_sectors_kb");
@@ -420,7 +429,7 @@ QUEUE_RO_ENTRY(queue_max_hw_sectors, "max_hw_sectors_kb"); 
QUEUE_RO_ENTRY(queue_max_segments, "max_segments");

QUEUE_RO_ENTRY(queue_max_integrity_segments, "max_integrity_segments");

QUEUE_RO_ENTRY(queue_max_segment_size, "max_segment_size");

QUEUE_RW_ENTRY(elv_iosched, "scheduler");

QUEUE_RW_LOAD_MODULE_ENTRY(elv_iosched, "scheduler");



QUEUE_RO_ENTRY(queue_logical_block_size, "logical_block_size");

QUEUE_RO_ENTRY(queue_physical_block_size, "physical_block_size");
@@ -670,6 +679,17 @@ queue_attr_store(struct kobject *kobj, struct attribute *attr, 
	if (!entry->store)

		return -EIO;



	/*

	 * If the attribute needs to load a module, do it before freezing the

	 * queue to ensure that the module file can be read when the request

	 * queue is the one for the device storing the module file.

	 */

	if (entry->load_module) {

		res = entry->load_module(disk, page, length);

		if (res)

			return res;

	}



	blk_mq_freeze_queue(q);

	mutex_lock(&q->sysfs_lock);

	res = entry->store(disk, page, length);

block/elevator.c

+15 −6
Original line number Diff line number Diff line
@@ -697,18 +697,27 @@ static int elevator_change(struct request_queue *q, const char *elevator_name) 
	if (q->elevator && elevator_match(q->elevator->type, elevator_name))

		return 0;



	e = elevator_find_get(q, elevator_name);

	if (!e) {

		request_module("%s-iosched", elevator_name);

	e = elevator_find_get(q, elevator_name);

	if (!e)

		return -EINVAL;

	}

	ret = elevator_switch(q, e);

	elevator_put(e);

	return ret;

}



int elv_iosched_load_module(struct gendisk *disk, const char *buf,

			    size_t count)

{

	char elevator_name[ELV_NAME_MAX];



	if (!elv_support_iosched(disk->queue))

		return -EOPNOTSUPP;



	strscpy(elevator_name, buf, sizeof(elevator_name));



	return request_module("%s-iosched", strstrip(elevator_name));

}



ssize_t elv_iosched_store(struct gendisk *disk, const char *buf,

			  size_t count)

{

block/elevator.h

+2 −0
Original line number Diff line number Diff line
@@ -148,6 +148,8 @@ extern void elv_unregister(struct elevator_type *); 
 * io scheduler sysfs switching

 */

ssize_t elv_iosched_show(struct gendisk *disk, char *page);

int elv_iosched_load_module(struct gendisk *disk, const char *page,

			    size_t count);

ssize_t elv_iosched_store(struct gendisk *disk, const char *page, size_t count);



extern bool elv_bio_merge_ok(struct request *, struct bio *);