net: mana: add ethtool private flag for full-page RX buffers

index 9e31e2595ae3..482cd16009ab 100644
@@ -138,53 +138,70 @@ static int mana_get_sset_count(struct net_device *ndev, int stringset)
 	struct mana_port_context *apc = netdev_priv(ndev);
 	unsigned int num_queues = apc->num_queues;
 
-	if (stringset != ETH_SS_STATS)
+	switch (stringset) {
+	case ETH_SS_STATS:
+		return ARRAY_SIZE(mana_eth_stats) +
+		       ARRAY_SIZE(mana_phy_stats) +
+		       ARRAY_SIZE(mana_hc_stats)  +
+		       num_queues * (MANA_STATS_RX_COUNT + MANA_STATS_TX_COUNT);
+	default:
 		return -EINVAL;
-
-	return ARRAY_SIZE(mana_eth_stats) + ARRAY_SIZE(mana_phy_stats) + ARRAY_SIZE(mana_hc_stats) +
-			num_queues * (MANA_STATS_RX_COUNT + MANA_STATS_TX_COUNT);
+	}
 }
 
-static void mana_get_strings(struct net_device *ndev, u32 stringset, u8 *data)
+static void mana_get_strings_stats(struct mana_port_context *apc, u8 **data)
 {
-	struct mana_port_context *apc = netdev_priv(ndev);
 	unsigned int num_queues = apc->num_queues;
 	int i, j;
 
-	if (stringset != ETH_SS_STATS)
-		return;
 	for (i = 0; i < ARRAY_SIZE(mana_eth_stats); i++)
-		ethtool_puts(&data, mana_eth_stats[i].name);
+		ethtool_puts(data, mana_eth_stats[i].name);
 
 	for (i = 0; i < ARRAY_SIZE(mana_hc_stats); i++)
-		ethtool_puts(&data, mana_hc_stats[i].name);
+		ethtool_puts(data, mana_hc_stats[i].name);
 
 	for (i = 0; i < ARRAY_SIZE(mana_phy_stats); i++)
-		ethtool_puts(&data, mana_phy_stats[i].name);
+		ethtool_puts(data, mana_phy_stats[i].name);
 
 	for (i = 0; i < num_queues; i++) {
-		ethtool_sprintf(&data, "rx_%d_packets", i);
-		ethtool_sprintf(&data, "rx_%d_bytes", i);
-		ethtool_sprintf(&data, "rx_%d_xdp_drop", i);
-		ethtool_sprintf(&data, "rx_%d_xdp_tx", i);
-		ethtool_sprintf(&data, "rx_%d_xdp_redirect", i);
-		ethtool_sprintf(&data, "rx_%d_pkt_len0_err", i);
+		ethtool_sprintf(data, "rx_%d_packets", i);
+		ethtool_sprintf(data, "rx_%d_bytes", i);
+		ethtool_sprintf(data, "rx_%d_xdp_drop", i);
+		ethtool_sprintf(data, "rx_%d_xdp_tx", i);
+		ethtool_sprintf(data, "rx_%d_xdp_redirect", i);
+		ethtool_sprintf(data, "rx_%d_pkt_len0_err", i);
 		for (j = 0; j < MANA_RXCOMP_OOB_NUM_PPI - 1; j++)
-			ethtool_sprintf(&data, "rx_%d_coalesced_cqe_%d", i, j + 2);
+			ethtool_sprintf(data,
+					"rx_%d_coalesced_cqe_%d",
+					i,
+					j + 2);
 	}
 
 	for (i = 0; i < num_queues; i++) {
-		ethtool_sprintf(&data, "tx_%d_packets", i);
-		ethtool_sprintf(&data, "tx_%d_bytes", i);
-		ethtool_sprintf(&data, "tx_%d_xdp_xmit", i);
-		ethtool_sprintf(&data, "tx_%d_tso_packets", i);
-		ethtool_sprintf(&data, "tx_%d_tso_bytes", i);
-		ethtool_sprintf(&data, "tx_%d_tso_inner_packets", i);
-		ethtool_sprintf(&data, "tx_%d_tso_inner_bytes", i);
-		ethtool_sprintf(&data, "tx_%d_long_pkt_fmt", i);
-		ethtool_sprintf(&data, "tx_%d_short_pkt_fmt", i);
-		ethtool_sprintf(&data, "tx_%d_csum_partial", i);
-		ethtool_sprintf(&data, "tx_%d_mana_map_err", i);
+		ethtool_sprintf(data, "tx_%d_packets", i);
+		ethtool_sprintf(data, "tx_%d_bytes", i);
+		ethtool_sprintf(data, "tx_%d_xdp_xmit", i);
+		ethtool_sprintf(data, "tx_%d_tso_packets", i);
+		ethtool_sprintf(data, "tx_%d_tso_bytes", i);
+		ethtool_sprintf(data, "tx_%d_tso_inner_packets", i);
+		ethtool_sprintf(data, "tx_%d_tso_inner_bytes", i);
+		ethtool_sprintf(data, "tx_%d_long_pkt_fmt", i);
+		ethtool_sprintf(data, "tx_%d_short_pkt_fmt", i);
+		ethtool_sprintf(data, "tx_%d_csum_partial", i);
+		ethtool_sprintf(data, "tx_%d_mana_map_err", i);
+	}
+}
+
+static void mana_get_strings(struct net_device *ndev, u32 stringset, u8 *data)
+{
+	struct mana_port_context *apc = netdev_priv(ndev);
+
+	switch (stringset) {
+	case ETH_SS_STATS:
+		mana_get_strings_stats(apc, &data);
+		break;
+	default:
+		break;
 	}
 }
 

index 89e7f59f635d..d859c2eae0a5 100644
@@ -755,6 +755,25 @@ static void *mana_get_rxbuf_pre(struct mana_rxq *rxq, dma_addr_t *da)
 	return va;
 }
 
+static bool
+mana_use_single_rxbuf_per_page(struct mana_port_context *apc, u32 mtu)
+{
+	/* On some platforms with 4K PAGE_SIZE, page_pool fragment allocation
+	 * in the RX refill path (~2kB buffer) can cause significant throughput
+	 * regression under high connection counts. Allow user to force one RX
+	 * buffer per page via ethtool private flag to bypass the fragment
+	 * path.
+	 */
+	if (apc->priv_flags & BIT(MANA_PRIV_FLAG_USE_FULL_PAGE_RXBUF))
+		return true;
+
+	/* For xdp and jumbo frames make sure only one packet fits per page. */
+	if (mtu + MANA_RXBUF_PAD > PAGE_SIZE / 2 || mana_xdp_get(apc))
+		return true;
+
+	return false;
+}
+
 /* Get RX buffer's data size, alloc size, XDP headroom based on MTU */
 static void mana_get_rxbuf_cfg(struct mana_port_context *apc,
 			       int mtu, u32 *datasize, u32 *alloc_size,

@@ -765,8 +784,7 @@ static void mana_get_rxbuf_cfg(struct mana_port_context *apc,
 	/* Calculate datasize first (consistent across all cases) */
 	*datasize = mtu + ETH_HLEN;
 
-	/* For xdp and jumbo frames make sure only one packet fits per page */
-	if (mtu + MANA_RXBUF_PAD > PAGE_SIZE / 2 || mana_xdp_get(apc)) {
+	if (mana_use_single_rxbuf_per_page(apc, mtu)) {
 		if (mana_xdp_get(apc)) {
 			*headroom = XDP_PACKET_HEADROOM;
 			*alloc_size = PAGE_SIZE;

134 lines not on this page · raw message

index 226b61504596..768d9f9bf167 100644
@@ -31,6 +31,12 @@ enum TRI_STATE {
 	TRI_STATE_TRUE = 1
 };
 
+/* MANA ethtool private flag bit positions */
+enum mana_priv_flag_bits {
+	MANA_PRIV_FLAG_USE_FULL_PAGE_RXBUF = 0,
+	MANA_PRIV_FLAG_MAX,
+};
+
 /* Number of entries for hardware indirection table must be in power of 2 */
 #define MANA_INDIRECT_TABLE_MAX_SIZE 512
 #define MANA_INDIRECT_TABLE_DEF_SIZE 64

@@ -565,6 +571,8 @@ struct mana_port_context {
 	u32 rxbpre_headroom;
 	u32 rxbpre_frag_count;
 
+	u32 priv_flags;
+
 	struct bpf_prog *bpf_prog;
 
 	/* Create num_queues EQs, SQs, SQ-CQs, RQs and RQ-CQs, respectively. */