On Sun, Mar 29, 2026 at 03:20:16PM -0700, Jakub Kicinski wrote:

On Thu, 26 Mar 2026 16:52:27 -0700 Joe Damato wrote:

quoted

+	/* Upper bound on the number of descriptors needed.
+	 *
+	 * Each segment uses 1 long BD + 1 ext BD + payload BDs, which is
+	 * at most num_segs + nr_frags (each frag boundary crossing adds at
+	 * most 1 extra BD).
+	 */
+	bds_needed = 3 * num_segs + skb_shinfo(skb)->nr_frags + 1;
+
+	if (unlikely(bnxt_tx_avail(bp, txr) < bds_needed)) {
+		netif_txq_try_stop(txq, bnxt_tx_avail(bp, txr),
+				   bp->tx_wake_thresh);
+		return NETDEV_TX_BUSY;
+	}
+
+	slots = BNXT_SW_USO_MAX_SEGS - (txr->tx_inline_prod - txr->tx_inline_cons);
+
+	if (unlikely(slots < num_segs)) {
+		netif_txq_try_stop(txq, bnxt_tx_avail(bp, txr),

This looks sus, try_stop() will evaluate the bnxt_tx_avail(bp, txr)
and leave the ring running.

Yea, I think the slot check can actually be removed entirely. Each segment
consumes 1 inline slot and at least 3 BDs. BNXT_SW_USO_MAX_SEGS is 64 and the
ring's minimum size is 2 * BNXT_SW_USO_MAX_DESCS (420).

Using 64 slots would consume at least 192 BDs, so the check above would fire
first.

I think as long as the ring size is constrained by the code in fix_features
and set_ringparam then this if block can be removed.

quoted

+				   bp->tx_wake_thresh);

Is tx_wake_thresh larger than the max USO even for smallest ring size?

Yes, it is.

Maybe its worth adding a comment in the code somewhere to make
this more clear? Not sure where would be an appropriate place, but maybe
bnxt_init_tx_rings?