On May 29 14:36, Daniel Gomez wrote: > From: Daniel Gomez <[email protected]> > > dma_blk_cb() now chunks at IOV_MAX, so the per-mapping cap on sg->qsg > in nvme_map_addr() is redundant. Drop it. > > Suggested-by: Klaus Jensen <[email protected]> > Signed-off-by: Daniel Gomez <[email protected]> > --- > hw/nvme/ctrl.c | 4 ---- > 1 file changed, 4 deletions(-) > > diff --git a/hw/nvme/ctrl.c b/hw/nvme/ctrl.c > index be6c7028cb5..00995d9808f 100644 > --- a/hw/nvme/ctrl.c > +++ b/hw/nvme/ctrl.c > @@ -866,10 +866,6 @@ static uint16_t nvme_map_addr(NvmeCtrl *n, NvmeSg *sg, > hwaddr addr, size_t len) > return NVME_INVALID_USE_OF_CMB | NVME_DNR; > } > > - if (sg->qsg.nsg + 1 > IOV_MAX) { > - goto max_mappings_exceeded; > - } > - > qemu_sglist_add(&sg->qsg, addr, len); > > return NVME_SUCCESS; > > -- > 2.53.0 > >
I posted something similar a while back where I also removed the restriction for CMB/PMR. However, I think that was wrong - for CMB/PMR we take the blk_ path directly, which will not split on its own. However, that means MDTS can't go that high if we have CMB/PMR enabled, right? Thanks, Klaus
signature.asc
Description: PGP signature
