On Mon, Dec 01, 2025 at 03:02:40PM -0500, Frank Li wrote:
> On Sun, Nov 30, 2025 at 01:03:52AM +0900, Koichiro Den wrote:
> > Historically both TX and RX have assumed the same per-QP MW slice
> > (tx_max_entry == remote rx_max_entry), while those are calculated
> > separately in different places (pre and post the link-up negotiation
> > point). This has been safe because nt->link_is_up is never set to true
> > unless the pre-determined qp_count are the same among them, and qp_count
> > is typically limited to nt->mw_count, which should be carefully
> > configured by admin.
> >
> > However, setup_qp_mw can actually split mw and handle multi-qps in one
> > MW properly, so qp_count needs not to be limited by nt->mw_count. Once
> > we relaxing the limitation, pre-determined qp_count can differ among
> > host side and endpoint, and link-up negotiation can easily fail.
> >
> > Move the TX MW configuration (per-QP offset and size) into
> > ntb_transport_setup_qp_mw() so that both RX and TX layout decisions are
> > centralized in a single helper. ntb_transport_init_queue() now deals
> > only with per-QP software state, not with MW layout.
> >
> > This keeps the previous behaviour, while preparing for relaxing the
> > qp_count limitation and improving readibility.
> >
> > No functional change is intended.
> >
> > Signed-off-by: Koichiro Den <den@valinux.co.jp>
> > ---
> > drivers/ntb/ntb_transport.c | 67 ++++++++++++++-----------------------
> > 1 file changed, 26 insertions(+), 41 deletions(-)
> >
> > diff --git a/drivers/ntb/ntb_transport.c b/drivers/ntb/ntb_transport.c
> > index 57b4c0511927..79063e2f911b 100644
> > --- a/drivers/ntb/ntb_transport.c
> > +++ b/drivers/ntb/ntb_transport.c
> > @@ -569,7 +569,8 @@ static int ntb_transport_setup_qp_mw(struct ntb_transport_ctx *nt,
> > struct ntb_transport_mw *mw;
> > struct ntb_dev *ndev = nt->ndev;
> > struct ntb_queue_entry *entry;
> > - unsigned int rx_size, num_qps_mw;
> > + unsigned int num_qps_mw;
> > + unsigned int mw_size, mw_size_per_qp, qp_offset, rx_info_offset;
> > unsigned int mw_num, mw_count, qp_count;
> > unsigned int i;
> > int node;
> > @@ -588,15 +589,33 @@ static int ntb_transport_setup_qp_mw(struct ntb_transport_ctx *nt,
> > else
> > num_qps_mw = qp_count / mw_count;
> >
> > - rx_size = (unsigned int)mw->xlat_size / num_qps_mw;
> > - qp->rx_buff = mw->virt_addr + rx_size * (qp_num / mw_count);
> > - rx_size -= sizeof(struct ntb_rx_info);
> > + mw_size = min(nt->mw_vec[mw_num].phys_size, mw->xlat_size);
> > + if (max_mw_size && mw_size > max_mw_size)
> > + mw_size = max_mw_size;
> >
> > - qp->remote_rx_info = qp->rx_buff + rx_size;
> > + /* Split this MW evenly among the queue pairs mapped to it. */
> > + mw_size_per_qp = (unsigned int)mw_size / num_qps_mw;
>
> Can you use the same variable firstly to make review easily?
>
> tx_size = (unsigned int)mw_size / num_qps_mw;
>
> It is hard to make sure code logic is the same as old one.
I'll do so. Thank you!
Koichiro
>
> Frank
>
> > + qp_offset = mw_size_per_qp * (qp_num / mw_count);
> > +
> > + /* Place remote_rx_info at the end of the per-QP region. */
> > + rx_info_offset = mw_size_per_qp - sizeof(struct ntb_rx_info);
> > +
> > + qp->tx_mw_size = mw_size_per_qp;
> > + qp->tx_mw = nt->mw_vec[mw_num].vbase + qp_offset;
> > + if (!qp->tx_mw)
> > + return -EINVAL;
> > + qp->tx_mw_phys = nt->mw_vec[mw_num].phys_addr + qp_offset;
> > + if (!qp->tx_mw_phys)
> > + return -EINVAL;
> > + qp->rx_info = qp->tx_mw + rx_info_offset;
> > + qp->rx_buff = mw->virt_addr + qp_offset;
> > + qp->remote_rx_info = qp->rx_buff + rx_info_offset;
> >
> > /* Due to housekeeping, there must be atleast 2 buffs */
> > - qp->rx_max_frame = min(transport_mtu, rx_size / 2);
> > - qp->rx_max_entry = rx_size / qp->rx_max_frame;
> > + qp->tx_max_frame = min(transport_mtu, mw_size_per_qp / 2);
> > + qp->tx_max_entry = mw_size_per_qp / qp->tx_max_frame;
> > + qp->rx_max_frame = min(transport_mtu, mw_size_per_qp / 2);
> > + qp->rx_max_entry = mw_size_per_qp / qp->rx_max_frame;
> > qp->rx_index = 0;
> >
> > /*
> > @@ -1133,11 +1152,7 @@ static int ntb_transport_init_queue(struct ntb_transport_ctx *nt,
> > unsigned int qp_num)
> > {
> > struct ntb_transport_qp *qp;
> > - phys_addr_t mw_base;
> > - resource_size_t mw_size;
> > - unsigned int num_qps_mw, tx_size;
> > unsigned int mw_num, mw_count, qp_count;
> > - u64 qp_offset;
> >
> > mw_count = nt->mw_count;
> > qp_count = nt->qp_count;
> > @@ -1152,36 +1167,6 @@ static int ntb_transport_init_queue(struct ntb_transport_ctx *nt,
> > qp->event_handler = NULL;
> > ntb_qp_link_context_reset(qp);
> >
> > - if (mw_num < qp_count % mw_count)
> > - num_qps_mw = qp_count / mw_count + 1;
> > - else
> > - num_qps_mw = qp_count / mw_count;
> > -
> > - mw_base = nt->mw_vec[mw_num].phys_addr;
> > - mw_size = nt->mw_vec[mw_num].phys_size;
> > -
> > - if (max_mw_size && mw_size > max_mw_size)
> > - mw_size = max_mw_size;
> > -
> > - tx_size = (unsigned int)mw_size / num_qps_mw;
> > - qp_offset = tx_size * (qp_num / mw_count);
> > -
> > - qp->tx_mw_size = tx_size;
> > - qp->tx_mw = nt->mw_vec[mw_num].vbase + qp_offset;
> > - if (!qp->tx_mw)
> > - return -EINVAL;
> > -
> > - qp->tx_mw_phys = mw_base + qp_offset;
> > - if (!qp->tx_mw_phys)
> > - return -EINVAL;
> > -
> > - tx_size -= sizeof(struct ntb_rx_info);
> > - qp->rx_info = qp->tx_mw + tx_size;
> > -
> > - /* Due to housekeeping, there must be atleast 2 buffs */
> > - qp->tx_max_frame = min(transport_mtu, tx_size / 2);
> > - qp->tx_max_entry = tx_size / qp->tx_max_frame;
> > -
> > if (nt->debugfs_node_dir) {
> > char debugfs_name[8];
> >
> > --
> > 2.48.1
> >