dpaa2-eth: Don't account Tx confirmation frames on NAPI poll

Until now, both Rx and Tx confirmation frames handled during
NAPI poll were counted toward the NAPI budget. However, Tx
confirmations are lighter to process than Rx frames, which can
skew the amount of work actually done inside one NAPI cycle.

Update the code to only count Rx frames toward the NAPI budget
and set a separate threshold on how many Tx conf frames can be
processed in one poll cycle.

The NAPI poll routine stops when either the budget is consumed
by Rx frames or when Tx confirmation frames reach this threshold.
Signed-off-by: Ioana Radulescu <ruxandra.radulescu@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c

@@ -289,10 +289,11 @@ static void dpaa2_eth_rx(struct dpaa2_eth_priv *priv,
  *
  * Observance of NAPI budget is not our concern, leaving that to the caller.
  */
-static int consume_frames(struct dpaa2_eth_channel *ch)
+static int consume_frames(struct dpaa2_eth_channel *ch,
+			  enum dpaa2_eth_fq_type *type)
 {
 	struct dpaa2_eth_priv *priv = ch->priv;
-	struct dpaa2_eth_fq *fq;
+	struct dpaa2_eth_fq *fq = NULL;
 	struct dpaa2_dq *dq;
 	const struct dpaa2_fd *fd;
 	int cleaned = 0;
@@ -311,12 +312,23 @@ static int consume_frames(struct dpaa2_eth_channel *ch)
 
 		fd = dpaa2_dq_fd(dq);
 		fq = (struct dpaa2_eth_fq *)(uintptr_t)dpaa2_dq_fqd_ctx(dq);
-		fq->stats.frames++;
 
 		fq->consume(priv, ch, fd, &ch->napi, fq->flowid);
 		cleaned++;
 	} while (!is_last);
 
+	if (!cleaned)
+		return 0;
+
+	fq->stats.frames += cleaned;
+	ch->stats.frames += cleaned;
+
+	/* A dequeue operation only pulls frames from a single queue
+	 * into the store. Return the frame queue type as an out param.
+	 */
+	if (type)
+		*type = fq->type;
+
 	return cleaned;
 }
 
@@ -921,14 +933,16 @@ static int pull_channel(struct dpaa2_eth_channel *ch)
 static int dpaa2_eth_poll(struct napi_struct *napi, int budget)
 {
 	struct dpaa2_eth_channel *ch;
-	int cleaned = 0, store_cleaned;
 	struct dpaa2_eth_priv *priv;
+	int rx_cleaned = 0, txconf_cleaned = 0;
+	enum dpaa2_eth_fq_type type;
+	int store_cleaned;
 	int err;
 
 	ch = container_of(napi, struct dpaa2_eth_channel, napi);
 	priv = ch->priv;
 
-	while (cleaned < budget) {
+	do {
 		err = pull_channel(ch);
 		if (unlikely(err))
 			break;
@@ -936,30 +950,32 @@ static int dpaa2_eth_poll(struct napi_struct *napi, int budget)
 		/* Refill pool if appropriate */
 		refill_pool(priv, ch, priv->bpid);
 
-		store_cleaned = consume_frames(ch);
-		cleaned += store_cleaned;
+		store_cleaned = consume_frames(ch, &type);
+		if (type == DPAA2_RX_FQ)
+			rx_cleaned += store_cleaned;
+		else
+			txconf_cleaned += store_cleaned;
 
-		/* If we have enough budget left for a full store,
-		 * try a new pull dequeue, otherwise we're done here
+		/* If we either consumed the whole NAPI budget with Rx frames
+		 * or we reached the Tx confirmations threshold, we're done.
 		 */
-		if (store_cleaned == 0 ||
-		    cleaned > budget - DPAA2_ETH_STORE_SIZE)
-			break;
-	}
-
-	if (cleaned < budget && napi_complete_done(napi, cleaned)) {
-		/* Re-enable data available notifications */
-		do {
-			err = dpaa2_io_service_rearm(ch->dpio, &ch->nctx);
-			cpu_relax();
-		} while (err == -EBUSY);
-		WARN_ONCE(err, "CDAN notifications rearm failed on core %d",
-			  ch->nctx.desired_cpu);
-	}
+		if (rx_cleaned >= budget ||
+		    txconf_cleaned >= DPAA2_ETH_TXCONF_PER_NAPI)
+			return budget;
+	} while (store_cleaned);
 
-	ch->stats.frames += cleaned;
+	/* We didn't consume the entire budget, so finish napi and
+	 * re-enable data availability notifications
+	 */
+	napi_complete_done(napi, rx_cleaned);
+	do {
+		err = dpaa2_io_service_rearm(ch->dpio, &ch->nctx);
+		cpu_relax();
+	} while (err == -EBUSY);
+	WARN_ONCE(err, "CDAN notifications rearm failed on core %d",
+		  ch->nctx.desired_cpu);
 
-	return cleaned;
+	return max(rx_cleaned, 1);
 }
 
 static void enable_ch_napi(struct dpaa2_eth_priv *priv)
@@ -1076,7 +1092,7 @@ static u32 drain_channel(struct dpaa2_eth_priv *priv,
 
 	do {
 		pull_channel(ch);
-		drained = consume_frames(ch);
+		drained = consume_frames(ch, NULL);
 		total += drained;
 	} while (drained);
 

drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h

@@ -40,6 +40,11 @@
  */
 #define DPAA2_ETH_TAILDROP_THRESH	(64 * 1024)
 
+/* Maximum number of Tx confirmation frames to be processed
+ * in a single NAPI call
+ */
+#define DPAA2_ETH_TXCONF_PER_NAPI	256
+
 /* Buffer quota per queue. Must be large enough such that for minimum sized
  * frames taildrop kicks in before the bpool gets depleted, so we compute
  * how many 64B frames fit inside the taildrop threshold and add a margin