On 2025-05-28 3:55 a.m., Simon Horman wrote:
On Fri, May 23, 2025 at 02:55:37PM -0600, Ahmed Zaki wrote:
With VIRTCHNL2_CAP_MACFILTER enabled, the following warning is generated
on module load:

[  324.701677] BUG: sleeping function called from invalid context at 
kernel/locking/mutex.c:578
[  324.701684] in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 1582, 
name: NetworkManager
[  324.701689] preempt_count: 201, expected: 0
[  324.701693] RCU nest depth: 0, expected: 0
[  324.701697] 2 locks held by NetworkManager/1582:
[  324.701702]  #0: ffffffff9f7be770 (rtnl_mutex){....}-{3:3}, at: 
rtnl_newlink+0x791/0x21e0
[  324.701730]  #1: ff1100216c380368 (_xmit_ETHER){....}-{2:2}, at: 
__dev_open+0x3f0/0x870
[  324.701749] Preemption disabled at:
[  324.701752] [<ffffffff9cd23b9d>] __dev_open+0x3dd/0x870
[  324.701765] CPU: 30 UID: 0 PID: 1582 Comm: NetworkManager Not tainted 
6.15.0-rc5+ #2 PREEMPT(voluntary)
[  324.701771] Hardware name: Intel Corporation M50FCP2SBSTD/M50FCP2SBSTD, BIOS 
SE5C741.86B.01.01.0001.2211140926 11/14/2022
[  324.701774] Call Trace:
[  324.701777]  <TASK>
[  324.701779]  dump_stack_lvl+0x5d/0x80
[  324.701788]  ? __dev_open+0x3dd/0x870
[  324.701793]  __might_resched.cold+0x1ef/0x23d
<..>
[  324.701818]  __mutex_lock+0x113/0x1b80
<..>
[  324.701917]  idpf_ctlq_clean_sq+0xad/0x4b0 [idpf]
[  324.701935]  ? kasan_save_track+0x14/0x30
[  324.701941]  idpf_mb_clean+0x143/0x380 [idpf]
<..>
[  324.701991]  idpf_send_mb_msg+0x111/0x720 [idpf]
[  324.702009]  idpf_vc_xn_exec+0x4cc/0x990 [idpf]
[  324.702021]  ? rcu_is_watching+0x12/0xc0
[  324.702035]  idpf_add_del_mac_filters+0x3ed/0xb50 [idpf]
<..>
[  324.702122]  __hw_addr_sync_dev+0x1cf/0x300
[  324.702126]  ? find_held_lock+0x32/0x90
[  324.702134]  idpf_set_rx_mode+0x317/0x390 [idpf]
[  324.702152]  __dev_open+0x3f8/0x870
[  324.702159]  ? __pfx___dev_open+0x10/0x10
[  324.702174]  __dev_change_flags+0x443/0x650
<..>
[  324.702208]  netif_change_flags+0x80/0x160
[  324.702218]  do_setlink.isra.0+0x16a0/0x3960
<..>
[  324.702349]  rtnl_newlink+0x12fd/0x21e0

The sequence is as follows:
        rtnl_newlink()->
        __dev_change_flags()->
        __dev_open()->
        dev_set_rx_mode() - >  # disables BH and grabs "dev->addr_list_lock"
        idpf_set_rx_mode() ->  # proceed only if VIRTCHNL2_CAP_MACFILTER is ON
        __dev_uc_sync() ->
        idpf_add_mac_filter ->
        idpf_add_del_mac_filters ->
        idpf_send_mb_msg() ->
        idpf_mb_clean() ->
        idpf_ctlq_clean_sq()   # mutex_lock(cq_lock)

Fix by converting cq_lock to a spinlock. All operations under the new
lock are safe except freeing the DMA memory, which may use vunmap(). Fix
by requesting a contiguous physical memory for the DMA mapping.

Hi Ahmed,

Hi Simon, Sorry for the late reply, I was off last week.


If I understand things correctly, then by safe you mean won't sleep.  But

correct, that is what I meant.

if so my question is if the path that frees DMA memory which is updated by
this patch is run in a context where sleeping is not allowed.

I am not sure I understand the question, but the current freeing path runs in process context and sleeping is allowed (hence the previous use of mutex).

With the new spinlock, we need to make sure all code in-between the new spin lock/unlock cannot sleep. All was safe except DMA buffer freeing which called vunmap(). That is avoided in this patch by requesting contiguous DMA memory via DMA_ATTR_FORCE_CONTIGUOUS.




Reply via email to