On 2026-02-05 10:37:05 [+0000], Loktionov, Aleksandr wrote: > > > > How or where can it sleep? > > > > Sebastian > > igb_ptp_tx_hwtstamp() -> > https://elixir.bootlin.com/linux/v6.19-rc5/C/ident/skb_tstamp_tx -> > https://elixir.bootlin.com/linux/v6.19-rc5/C/ident/__skb_complete_tx_timestamp > -> https://elixir.bootlin.com/linux/v6.19-rc5/C/ident/sock_queue_err_skb -> > https://elixir.bootlin.com/linux/v6.19-rc5/C/ident/skb_queue_tail -> > https://elixir.bootlin.com/linux/v6.19-rc5/source/net/core/skbuff.c#L4075
Would you please quote an actual call chain that can be looked up and not this where a line crosses 300 characters? > spin_lock_irqsave(&wq_head->lock, flags); <- RT mutex can sleep Okay. So you are concerned about this spinlock_t, I see. igb_tsync_interrupt() also invokes ptp_clock_event() which acquires pps_event_time::tsevqs_lock. Why is this not a problem? Sebastian
