github-mirror/linux
1
0
Fork 0
mirror of https://github.com/torvalds/linux.git synced 2026-05-12 16:18:45 +02:00
Code Issues Actions Packages Projects Releases Wiki Activity

ublk: allow buffer registration before device is started

Browse Source 
Before START_DEV, there is no disk, no queue, no I/O dispatch, so
the maple tree can be safely modified under ub->mutex alone without
freezing the queue.

Add ublk_lock_buf_tree()/ublk_unlock_buf_tree() helpers that take
ub->mutex first, then freeze the queue if device is started. This
ordering (mutex -> freeze) is safe because ublk_stop_dev_unlocked()
already holds ub->mutex when calling del_gendisk() which freezes
the queue.

Suggested-by: Caleb Sander Mateos <csander@purestorage.com>
Signed-off-by: Ming Lei <tom.leiming@gmail.com>
Link: https://patch.msgid.link/20260409133020.3780098-6-tom.leiming@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
This commit is contained in:
Ming Lei 2026-04-09 21:30:17 +08:00 committed by Jens Axboe
parent 5e864438e2
commit 365ea7cc62
1 changed files with 28 additions and 51 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

79
drivers/block/ublk_drv.c
View File

@ -5238,23 +5238,29 @@ static int ublk_char_dev_permission(struct ublk_device *ub,
}
/*
* Drain inflight I/O and quiesce the queue. Freeze drains all inflight
* requests, quiesce_nowait marks the queue so no new requests dispatch,
* then unfreeze allows new submissions (which won't dispatch due to
* quiesce). This keeps freeze and ub->mutex non-nested.
*/
static void ublk_quiesce_and_release(struct gendisk *disk)
* Lock for maple tree modification: acquire ub->mutex, then freeze queue
* if device is started. If device is not yet started, only mutex is
* needed since no I/O path can access the tree.
*
* This ordering (mutex -> freeze) is safe because ublk_stop_dev_unlocked()
* already holds ub->mutex when calling del_gendisk() which freezes the queue.
*/
static unsigned int ublk_lock_buf_tree(struct ublk_device *ub)
{
unsigned int memflags;
unsigned int memflags = 0;
memflags = blk_mq_freeze_queue(disk->queue);
blk_mq_quiesce_queue_nowait(disk->queue);
blk_mq_unfreeze_queue(disk->queue, memflags);
mutex_lock(&ub->mutex);
if (ub->ub_disk)
memflags = blk_mq_freeze_queue(ub->ub_disk->queue);
return memflags;
}
static void ublk_unquiesce_and_resume(struct gendisk *disk)
static void ublk_unlock_buf_tree(struct ublk_device *ub, unsigned int memflags)
{
blk_mq_unquiesce_queue(disk->queue);
if (ub->ub_disk)
blk_mq_unfreeze_queue(ub->ub_disk->queue, memflags);
mutex_unlock(&ub->mutex);
}
/* Erase coalesced PFN ranges from the maple tree matching buf_index */
@ -5327,7 +5333,7 @@ static int ublk_ctrl_reg_buf(struct ublk_device *ub,
unsigned long addr, size, nr_pages;
struct page **pages = NULL;
unsigned int gup_flags;
struct gendisk *disk;
unsigned int memflags;
long pinned;
int index;
int ret;
@ -5354,16 +5360,10 @@ static int ublk_ctrl_reg_buf(struct ublk_device *ub,
!PAGE_ALIGNED(size) || !PAGE_ALIGNED(addr))
return -EINVAL;
disk = ublk_get_disk(ub);
if (!disk)
return -ENODEV;
/* Pin pages before quiescing (may sleep) */
/* Pin pages before any locks (may sleep) */
pages = kvmalloc_array(nr_pages, sizeof(*pages), GFP_KERNEL);
if (!pages) {
ret = -ENOMEM;
goto put_disk;
}
if (!pages)
return -ENOMEM;
gup_flags = FOLL_LONGTERM;
if (!(buf_reg.flags & UBLK_SHMEM_BUF_READ_ONLY))
@ -5379,14 +5379,7 @@ static int ublk_ctrl_reg_buf(struct ublk_device *ub,
goto err_unpin;
}
/*
* Drain inflight I/O and quiesce the queue so no new requests
* are dispatched while we modify the maple tree. Keep freeze
* and mutex non-nested to avoid lock dependency.
*/
ublk_quiesce_and_release(disk);
mutex_lock(&ub->mutex);
memflags = ublk_lock_buf_tree(ub);
index = ida_alloc_max(&ub->buf_ida, USHRT_MAX, GFP_KERNEL);
if (index < 0) {
@ -5400,22 +5393,16 @@ static int ublk_ctrl_reg_buf(struct ublk_device *ub,
goto err_unlock;
}
mutex_unlock(&ub->mutex);
ublk_unlock_buf_tree(ub, memflags);
kvfree(pages);
ublk_unquiesce_and_resume(disk);
ublk_put_disk(disk);
return index;
err_unlock:
mutex_unlock(&ub->mutex);
ublk_unquiesce_and_resume(disk);
ublk_unlock_buf_tree(ub, memflags);
err_unpin:
unpin_user_pages(pages, pinned);
err_free_pages:
kvfree(pages);
put_disk:
ublk_put_disk(disk);
return ret;
}
@ -5459,7 +5446,7 @@ static int ublk_ctrl_unreg_buf(struct ublk_device *ub,
struct ublksrv_ctrl_cmd *header)
{
int index = (int)header->data[0];
struct gendisk *disk;
unsigned int memflags;
int ret;
if (!ublk_dev_support_shmem_zc(ub))
@ -5468,23 +5455,13 @@ static int ublk_ctrl_unreg_buf(struct ublk_device *ub,
if (index < 0 || index > USHRT_MAX)
return -EINVAL;
disk = ublk_get_disk(ub);
if (!disk)
return -ENODEV;
/* Drain inflight I/O before modifying the maple tree */
ublk_quiesce_and_release(disk);
mutex_lock(&ub->mutex);
memflags = ublk_lock_buf_tree(ub);
ret = __ublk_ctrl_unreg_buf(ub, index);
if (!ret)
ida_free(&ub->buf_ida, index);
mutex_unlock(&ub->mutex);
ublk_unquiesce_and_resume(disk);
ublk_put_disk(disk);
ublk_unlock_buf_tree(ub, memflags);
return ret;
}