On 2025年9月10日 02:03:06 +0200, Michal Pecio wrote: > On 2025年9月10日 01:57:39 +0300, Mathias Nyman wrote: > > On 9.9.2025 20.38, Michal Pecio wrote: > > > On Tue, 9 Sep 2025 16:04:33 +0300, Mathias Nyman wrote: > > >> Adding the zero-length TRB to the original TD when we need to send a > > >> zero-length packet would simplify things, and I would otherwise fully > > >> support this, but the xHCI spec is pretty clear that it requires a > > >> dedicated TD for zero-length transactions. > > > > > > You are right of course, an empty TRB in a TD would simply send no > > > data, or maybe it's a TRB Error, I'm not sure. > > > > > > But this is not what this patch is about - the trick is to use an > > > *unchained* TRB, which is a separate TD from HW's perspective, and > > > to count it as part of the same TD from the driver's perspective. > > > > Ok, I see. > > The whole TD without completion flag does worry me a bit. > > > > We need to make sure stop/stald mid TD cases work, and urb length is > > set correctly. > > It looks odd, but I can't find anything wrong. > > 4.10.4 discusses what happens when IOC is clear on the last TRB of > a TD so it looks like this is allowed. > > If the first TD halts or stops before completion then it doesn't > matter that we cleared its IOC. Everything works as before, except > that Set TR Deq will skip both TDs and the URB will be given back. Well, there is one difference, but so far I found no ill effects. All those (ep_trb == td->end_trb) comparisons will be false in case of an event on the last TRB of the first TD, currently they are true. But it should be harmless: * COMP_SUCCESS case in process_bulk_intr_td() is impossible (no IOC) * on errors, we may use sum_trb_lengths() unnecessarily, should be OK. These are the only such checks I see. Nothing in handle_tx_event() and finish_td(), and from there we go to handle_halted_endpoint(). Generally, I tried running this with wMaxPacket=64, TRB length reduced to 64B (patched xhci_hcd) to force multiple TRBs in the first TD and with transfer lengths of 32, 64, 96, 128, 192, 256. It worked. I can run it again tomorrow and send event-ring/trbs and epXX/trbs.