Re: [PATCH v5 3/8] nbd: reset write cache on disconnect

在 2026/8/2 20:02, yu kuai 写道:
> Hi,
> 
> 在 2026/8/2 19:51, yu kuai 写道:
>> Hi,
>>
>> 在 2026/7/30 16:20, Yang Erkun 写道:
>>> An inactive nbd device may refuse any I/O operations. The nbd_config_put
>>> function calls invalidate_disk, which sets the device capacity to zero
>>> to reject all read and write I/O. For zero-sector flush I/O requests
>>> from blkdev_issue_flush, if the write cache is disabled, the zero-sector
>>> flush I/O immediately returns 0 in submit_bio_noacct. However, since
>>> nbd_config_put does not clear the write cache state, an inactive nbd
>>> device might still have the write cache enabled. In this situation,
>>> zero-sector flush I/O will return -EIO because there is no active socket.
>>> Although this does not cause any bugs, resetting the write cache state
>>> would make the behavior consistent.
>> I don't think this make sense, at this point nbd->config_refs is 0, which means
>> there is no opener for the device, so how can there still be outstanding read/write
>> or flush IO?
> 
> I see what you want to do after checking the next patch. However, since a disconnected
> nbd device can be reused later, the stale BLK_FEAT flags from the last connection looks
> like a real problem. So, I think it's better to reset queue_limits to default, the same
> as add_disk().

Yeah, I prefer this way! Thanks for your advise.

> 
>>
>>> Signed-off-by: Yang Erkun <[email protected]>
>>> ---
>>>     drivers/block/nbd.c | 5 +++++
>>>     1 file changed, 5 insertions(+)
>>>
>>> diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
>>> index 7ec85f94f742..da4b48ef3c79 100644
>>> --- a/drivers/block/nbd.c
>>> +++ b/drivers/block/nbd.c
>>> @@ -1469,8 +1469,13 @@ static void nbd_config_put(struct nbd_device *nbd)
>>>     	if (refcount_dec_and_mutex_lock(&nbd->config_refs,
>>>     					&nbd->config_lock)) {
>>>     		struct nbd_config *config = nbd->config;
>>> +		struct queue_limits lim;
>>>     		nbd_dev_dbg_close(nbd);
>>>     		invalidate_disk(nbd->disk);
>>> +		/* reset write cache */
>>> +		lim = queue_limits_start_update(nbd->disk->queue);
>>> +		lim.features &= ~(BLK_FEAT_WRITE_CACHE | BLK_FEAT_FUA);
>>> +		queue_limits_commit_update(nbd->disk->queue, &lim);
>>>     		if (nbd->config->bytesize)
>>>     			kobject_uevent(&nbd_to_dev(nbd)->kobj, KOBJ_CHANGE);
>>>     		if (test_and_clear_bit(NBD_RT_HAS_PID_FILE,
>