net/netvsc: allow setting Rx and Tx copy break

The values for Rx and Tx copy break should be tunable rather
than hard coded constants.

The rx_copybreak sets the threshold where the driver uses an
external mbuf to avoid having to copy data. Setting 0 for copybreak
will cause driver to always create an external mbuf. Setting
a value greater than the MTU would prevent it from ever making
an external mbuf and always copy. The default value is 256 (bytes).

Likewise the tx_copybreak sets the threshold where the driver
aggregates multiple small packets into one request. If tx_copybreak
is 0 then each packet goes as a VMBus request (no copying).
If tx_copybreak is set larger than the MTU, then all packets smaller
than the chunk size of the VMBus send buffer will be copied; larger
packets always have to go as a single direct request. The default
value is 512 (bytes).

Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: Long Li <longli@microsoft.com>

doc/guides/nics/netvsc.rst

@@ -116,3 +116,20 @@ The user can specify below argument in devargs.
     values save CPU cycles. This parameter is in microseconds.
     If the value is too large or too small it will be
     ignored by the host. (Default: 50)
+
+#.  ``rx_copybreak``:
+
+    The rx_copybreak sets the threshold where the driver uses an external
+    mbuf to avoid having to copy data. Setting 0 for copybreak will cause
+    driver to always create an external mbuf. Setting a value greater than
+    the MTU would prevent it from ever making an external mbuf and always
+    copy. The default value is 256 (bytes).
+
+#.  ``tx_copybreak``:
+
+    The tx_copybreak sets the threshold where the driver aggregates
+    multiple small packets into one request. If tx_copybreak is 0 then
+    each packet goes as a VMBus request (no copying). If tx_copybreak is
+    set larger than the MTU, then all packets smaller than the chunk size
+    of the VMBus send buffer will be copied; larger packets always have to
+    go as a single direct request. The default value is 512 (bytes).

drivers/net/netvsc/hn_ethdev.c

@@ -45,6 +45,10 @@
 			    DEV_RX_OFFLOAD_VLAN_STRIP | \
 			    DEV_RX_OFFLOAD_RSS_HASH)
 
+#define NETVSC_ARG_LATENCY "latency"
+#define NETVSC_ARG_RXBREAK "rx_copybreak"
+#define NETVSC_ARG_TXBREAK "tx_copybreak"
+
 struct hn_xstats_name_off {
 	char name[RTE_ETH_XSTATS_NAME_SIZE];
 	unsigned int offset;
@@ -136,24 +140,32 @@ eth_dev_vmbus_release(struct rte_eth_dev *eth_dev)
 	eth_dev->intr_handle = NULL;
 }
 
-/* handle "latency=X" from devargs */
+static int hn_set_parameter(const char *key, const char *value, void *opaque)
-static int hn_set_latency(const char *key, const char *value, void *opaque)
 {
 	struct hn_data *hv = opaque;
 	char *endp = NULL;
-	unsigned long lat;
+	unsigned long v;
-
-	errno = 0;
-	lat = strtoul(value, &endp, 0);
 
+	v = strtoul(value, &endp, 0);
 	if (*value == '\0' || *endp != '\0') {
 		PMD_DRV_LOG(ERR, "invalid parameter %s=%s", key, value);
 		return -EINVAL;
 	}
 
-	PMD_DRV_LOG(DEBUG, "set latency %lu usec", lat);
+	if (!strcmp(key, NETVSC_ARG_LATENCY)) {
+		/* usec to nsec */
+		hv->latency = v * 1000;
+		PMD_DRV_LOG(DEBUG, "set latency %u usec", hv->latency);
+	} else if (!strcmp(key, NETVSC_ARG_RXBREAK)) {
+		hv->rx_copybreak = v;
+		PMD_DRV_LOG(DEBUG, "rx copy break set to %u",
+			    hv->rx_copybreak);
+	} else if (!strcmp(key, NETVSC_ARG_TXBREAK)) {
+		hv->tx_copybreak = v;
+		PMD_DRV_LOG(DEBUG, "tx copy break set to %u",
+			    hv->tx_copybreak);
+	}
 
-	hv->latency = lat * 1000;	/* usec to nsec */
 	return 0;
 }
 
@@ -163,7 +175,9 @@ static int hn_parse_args(const struct rte_eth_dev *dev)
 	struct hn_data *hv = dev->data->dev_private;
 	struct rte_devargs *devargs = dev->device->devargs;
 	static const char * const valid_keys[] = {
-		"latency",
+		NETVSC_ARG_LATENCY,
+		NETVSC_ARG_RXBREAK,
+		NETVSC_ARG_TXBREAK,
 		NULL
 	};
 	struct rte_kvargs *kvlist;
@@ -177,15 +191,13 @@ static int hn_parse_args(const struct rte_eth_dev *dev)
 
 	kvlist = rte_kvargs_parse(devargs->args, valid_keys);
 	if (!kvlist) {
-		PMD_DRV_LOG(NOTICE, "invalid parameters");
+		PMD_DRV_LOG(ERR, "invalid parameters");
 		return -EINVAL;
 	}
 
-	ret = rte_kvargs_process(kvlist, "latency", hn_set_latency, hv);
+	ret = rte_kvargs_process(kvlist, NULL, hn_set_parameter, hv);
-	if (ret)
-		PMD_DRV_LOG(ERR, "Unable to process latency arg\n");
-
 	rte_kvargs_free(kvlist);
+
 	return ret;
 }
 
@@ -966,7 +978,10 @@ eth_hn_dev_init(struct rte_eth_dev *eth_dev)
 	hv->chim_res  = &vmbus->resource[HV_SEND_BUF_MAP];
 	hv->port_id = eth_dev->data->port_id;
 	hv->latency = HN_CHAN_LATENCY_NS;
+	hv->rx_copybreak = HN_RXCOPY_THRESHOLD;
+	hv->tx_copybreak = HN_TXCOPY_THRESHOLD;
 	hv->max_queues = 1;
+
 	rte_rwlock_init(&hv->vf_lock);
 	hv->vf_port = HN_INVALID_PORT;
 
@@ -1122,3 +1137,7 @@ RTE_PMD_REGISTER_VMBUS(net_netvsc, rte_netvsc_pmd);
 RTE_PMD_REGISTER_KMOD_DEP(net_netvsc, "* uio_hv_generic");
 RTE_LOG_REGISTER(hn_logtype_init, pmd.net.netvsc.init, NOTICE);
 RTE_LOG_REGISTER(hn_logtype_driver, pmd.net.netvsc.driver, NOTICE);
+RTE_PMD_REGISTER_PARAM_STRING(net_netvsc,
+			      NETVSC_ARG_LATENCY "=<uint32> "
+			      NETVSC_ARG_RXBREAK "=<uint32> "
+			      NETVSC_ARG_TXBREAK "=<uint32>");

drivers/net/netvsc/hn_rxtx.c

@@ -40,9 +40,6 @@
 	(sizeof(struct vmbus_chanpkt_hdr) + sizeof(struct hn_nvs_rndis))
 
 #define HN_TXD_CACHE_SIZE	32 /* per cpu tx_descriptor pool cache */
-#define HN_TXCOPY_THRESHOLD	512
-
-#define HN_RXCOPY_THRESHOLD	256
 #define HN_RXQ_EVENT_DEFAULT	2048
 
 struct hn_rxinfo {
@@ -573,7 +570,7 @@ static void hn_rxpkt(struct hn_rx_queue *rxq, struct hn_rx_bufinfo *rxb,
 	 * For large packets, avoid copy if possible but need to keep
 	 * some space available in receive area for later packets.
 	 */
-	if (dlen >= HN_RXCOPY_THRESHOLD &&
+	if (dlen > hv->rx_copybreak &&
 	    (uint32_t)rte_atomic32_read(&rxq->rxbuf_outstanding) <
 			hv->rxbuf_section_cnt / 2) {
 		struct rte_mbuf_ext_shared_info *shinfo;
@@ -1517,7 +1514,8 @@ hn_xmit_pkts(void *ptxq, struct rte_mbuf **tx_pkts, uint16_t nb_pkts)
 			break;
 
 		/* For small packets aggregate them in chimney buffer */
-		if (m->pkt_len < HN_TXCOPY_THRESHOLD && pkt_size <= txq->agg_szmax) {
+		if (m->pkt_len <= hv->tx_copybreak &&
+		    pkt_size <= txq->agg_szmax) {
 			/* If this packet will not fit, then flush  */
 			if (txq->agg_pktleft == 0 ||
 			    RTE_ALIGN(pkt_size, txq->agg_align) > txq->agg_szleft) {

drivers/net/netvsc/hn_var.h

@@ -23,6 +23,9 @@
 /* Host monitor interval */
 #define HN_CHAN_LATENCY_NS	50000
 
+#define HN_TXCOPY_THRESHOLD	512
+#define HN_RXCOPY_THRESHOLD	256
+
 /* Buffers need to be aligned */
 #ifndef PAGE_SIZE
 #define PAGE_SIZE 4096
@@ -116,6 +119,7 @@ struct hn_data {
 
 	struct rte_mem_resource *rxbuf_res;	/* UIO resource for Rx */
 	uint32_t	rxbuf_section_cnt;	/* # of Rx sections */
+	uint32_t	rx_copybreak;
 	uint16_t	max_queues;		/* Max available queues */
 	uint16_t	num_queues;
 	uint64_t	rss_offloads;
@@ -124,6 +128,7 @@ struct hn_data {
 	struct rte_mem_resource *chim_res;	/* UIO resource for Tx */
 	struct rte_bitmap *chim_bmap;		/* Send buffer map */
 	void		*chim_bmem;
+	uint32_t	tx_copybreak;
 	uint32_t	chim_szmax;		/* Max size per buffer */
 	uint32_t	chim_cnt;		/* Max packets per buffer */