ionic: use per-queue xdp_prog

We originally were using a per-interface xdp_prog variable to track
a loaded XDP program since we knew there would never be support for a
per-queue XDP program.  With that, we only built the per queue rxq_info
struct when an XDP program was loaded and removed it on XDP program unload,
and used the pointer as an indicator in the Rx hotpath to know to how build
the buffers.  However, that's really not the model generally used, and
makes a conversion to page_pool Rx buffer cacheing a little problematic.

This patch converts the driver to use the more common approach of using
a per-queue xdp_prog pointer to work out buffer allocations and need
for bpf_prog_run_xdp().  We jostle a couple of fields in the queue struct
in order to keep the new xdp_prog pointer in a warm cacheline.
Signed-off-by: Shannon Nelson <shannon.nelson@amd.com>
Signed-off-by: Brett Creeley <brett.creeley@amd.com>
Link: https://patch.msgid.link/20240906232623.39651-4-brett.creeley@amd.comSigned-off-by: Jakub Kicinski <kuba@kernel.org>

drivers/net/ethernet/pensando/ionic/ionic_dev.h

@@ -238,9 +238,8 @@ struct ionic_queue {
 	unsigned int index;
 	unsigned int num_descs;
 	unsigned int max_sg_elems;
+
 	u64 features;
-	unsigned int type;
-	unsigned int hw_index;
 	unsigned int hw_type;
 	bool xdp_flush;
 	union {
@@ -261,7 +260,11 @@ struct ionic_queue {
 		struct ionic_rxq_sg_desc *rxq_sgl;
 	};
 	struct xdp_rxq_info *xdp_rxq_info;
+	struct bpf_prog *xdp_prog;
 	struct ionic_queue *partner;
+
+	unsigned int type;
+	unsigned int hw_index;
 	dma_addr_t base_pa;
 	dma_addr_t cmb_base_pa;
 	dma_addr_t sg_base_pa;

drivers/net/ethernet/pensando/ionic/ionic_lif.c

@@ -46,7 +46,7 @@ static int ionic_start_queues(struct ionic_lif *lif);
 static void ionic_stop_queues(struct ionic_lif *lif);
 static void ionic_lif_queue_identify(struct ionic_lif *lif);
 
-static int ionic_xdp_queues_config(struct ionic_lif *lif);
+static int ionic_xdp_rxqs_update(struct ionic_lif *lif);
 static void ionic_xdp_unregister_rxq_info(struct ionic_queue *q);
 
 static void ionic_dim_work(struct work_struct *work)
@@ -2143,7 +2143,7 @@ static int ionic_txrx_enable(struct ionic_lif *lif)
 	int derr = 0;
 	int i, err;
 
-	err = ionic_xdp_queues_config(lif);
+	err = ionic_xdp_rxqs_update(lif);
 	if (err)
 		return err;
 
@@ -2192,7 +2192,7 @@ static int ionic_txrx_enable(struct ionic_lif *lif)
 		derr = ionic_qcq_disable(lif, lif->rxqcqs[i], derr);
 	}
 
-	ionic_xdp_queues_config(lif);
+	ionic_xdp_rxqs_update(lif);
 
 	return err;
 }
@@ -2698,35 +2698,35 @@ static int ionic_xdp_register_rxq_info(struct ionic_queue *q, unsigned int napi_
 	return err;
 }
 
-static int ionic_xdp_queues_config(struct ionic_lif *lif)
+static int ionic_xdp_rxqs_update(struct ionic_lif *lif)
 {
+	struct bpf_prog *xdp_prog;
 	unsigned int i;
 	int err;
 
 	if (!lif->rxqcqs)
 		return 0;
 
-	/* There's no need to rework memory if not going to/from NULL program.
-	 * If there is no lif->xdp_prog, there should also be no q.xdp_rxq_info
-	 * This way we don't need to keep an *xdp_prog in every queue struct.
-	 */
-	if (!lif->xdp_prog == !lif->rxqcqs[0]->q.xdp_rxq_info)
-		return 0;
-
+	xdp_prog = READ_ONCE(lif->xdp_prog);
 	for (i = 0; i < lif->ionic->nrxqs_per_lif && lif->rxqcqs[i]; i++) {
 		struct ionic_queue *q = &lif->rxqcqs[i]->q;
 
-		if (q->xdp_rxq_info) {
+		if (q->xdp_prog) {
 			ionic_xdp_unregister_rxq_info(q);
-			continue;
+			q->xdp_prog = NULL;
 		}
 
-		err = ionic_xdp_register_rxq_info(q, lif->rxqcqs[i]->napi.napi_id);
-		if (err) {
-			dev_err(lif->ionic->dev, "failed to register RX queue %d info for XDP, err %d\n",
-				i, err);
-			goto err_out;
+		if (xdp_prog) {
+			unsigned int napi_id = lif->rxqcqs[i]->napi.napi_id;
+
+			err = ionic_xdp_register_rxq_info(q, napi_id);
+			if (err) {
+				dev_err(lif->ionic->dev, "failed to register RX queue %d info for XDP, err %d\n",
+					i, err);
+				goto err_out;
+			}
 		}
+		q->xdp_prog = xdp_prog;
 	}
 
 	return 0;
@@ -2878,6 +2878,7 @@ static void ionic_swap_queues(struct ionic_qcq *a, struct ionic_qcq *b)
 	swap(a->q.base,       b->q.base);
 	swap(a->q.base_pa,    b->q.base_pa);
 	swap(a->q.info,       b->q.info);
+	swap(a->q.xdp_prog,   b->q.xdp_prog);
 	swap(a->q.xdp_rxq_info, b->q.xdp_rxq_info);
 	swap(a->q.partner,    b->q.partner);
 	swap(a->q_base,       b->q_base);

drivers/net/ethernet/pensando/ionic/ionic_txrx.c

@@ -190,7 +190,7 @@ static bool ionic_rx_buf_recycle(struct ionic_queue *q,
 	if (page_to_nid(buf_info->page) != numa_mem_id())
 		return false;
 
-	size = ALIGN(len, q->xdp_rxq_info ? IONIC_PAGE_SIZE : IONIC_PAGE_SPLIT_SZ);
+	size = ALIGN(len, q->xdp_prog ? IONIC_PAGE_SIZE : IONIC_PAGE_SPLIT_SZ);
 	buf_info->page_offset += size;
 	if (buf_info->page_offset >= IONIC_PAGE_SIZE)
 		return false;
@@ -639,8 +639,7 @@ static void ionic_rx_clean(struct ionic_queue *q,
 	struct net_device *netdev = q->lif->netdev;
 	struct ionic_qcq *qcq = q_to_qcq(q);
 	struct ionic_rx_stats *stats;
-	struct bpf_prog *xdp_prog;
-	unsigned int headroom;
+	unsigned int headroom = 0;
 	struct sk_buff *skb;
 	bool synced = false;
 	bool use_copybreak;
@@ -664,14 +663,13 @@ static void ionic_rx_clean(struct ionic_queue *q,
 	stats->pkts++;
 	stats->bytes += len;
 
-	xdp_prog = READ_ONCE(q->lif->xdp_prog);
-	if (xdp_prog) {
-		if (ionic_run_xdp(stats, netdev, xdp_prog, q, desc_info->bufs, len))
+	if (q->xdp_prog) {
+		if (ionic_run_xdp(stats, netdev, q->xdp_prog, q, desc_info->bufs, len))
 			return;
 		synced = true;
+		headroom = XDP_PACKET_HEADROOM;
 	}
 
-	headroom = q->xdp_rxq_info ? XDP_PACKET_HEADROOM : 0;
 	use_copybreak = len <= q->lif->rx_copybreak;
 	if (use_copybreak)
 		skb = ionic_rx_copybreak(netdev, q, desc_info,
@@ -814,7 +812,7 @@ void ionic_rx_fill(struct ionic_queue *q)
 	len = netdev->mtu + VLAN_ETH_HLEN;
 
 	for (i = n_fill; i; i--) {
-		unsigned int headroom;
+		unsigned int headroom = 0;
 		unsigned int buf_len;
 
 		nfrags = 0;
@@ -835,11 +833,12 @@ void ionic_rx_fill(struct ionic_queue *q)
 		 * XDP uses space in the first buffer, so account for
 		 * head room, tail room, and ip header in the first frag size.
 		 */
-		headroom = q->xdp_rxq_info ? XDP_PACKET_HEADROOM : 0;
-		if (q->xdp_rxq_info)
+		if (q->xdp_prog) {
 			buf_len = IONIC_XDP_MAX_LINEAR_MTU + VLAN_ETH_HLEN;
-		else
+			headroom = XDP_PACKET_HEADROOM;
+		} else {
 			buf_len = ionic_rx_buf_size(buf_info);
+		}
 		frag_len = min_t(u16, len, buf_len);
 
 		desc->addr = cpu_to_le64(ionic_rx_buf_pa(buf_info) + headroom);