On Fri, Mar 06, 2026 at 12:01:27AM -0500, Brad Smith wrote:
> >> @@ -5183,7 +5183,7 @@ ixl_dmamem_alloc(struct ixl_softc *sc, s
> >>   		return (1);
> >>   	if (bus_dmamem_alloc(sc->sc_dmat, ixm->ixm_size,
> >>   	    align, 0, &ixm->ixm_seg, 1, &ixm->ixm_nsegs,
> >> -	    BUS_DMA_WAITOK | BUS_DMA_ZERO) != 0)
> >> +	    BUS_DMA_WAITOK | BUS_DMA_ZERO | BUS_DMA_64BIT) != 0)
> >>   		goto destroy;
> >>   	if (bus_dmamem_map(sc->sc_dmat, &ixm->ixm_seg, ixm->ixm_nsegs,
> >>   	    ixm->ixm_size, &ixm->ixm_kva, BUS_DMA_WAITOK) != 0)

> > Same with aq(4), iavf(4) and myx(4).
> 
> ping.

I don't have the hardware and there is no diff flying around on
tech@ for these devices.

Brad: If you need these, please provide a diff and test it.  Testing
is most effort, especially setting up virtual environment for
iavf(4).

In my setup I have ice, ixl, ix, igc, em, bnxt, bge, vio in multiple
variants.  Testing a diff for them with a bunch of network
configurations is easy.  It is just starting a script.  Everything
else requires work.  Maybe I will get a permanent setup for ixv and
iavf in the future.

bluhm