[PATCH v3 6/9] app/testpmd: factorize core cycles record

[David Marchand <david.marchand@redhat.com>]

Rather than have each forward engines deal with core cycles recording,
move this to testpmd common code.
fwd engines just need to report that they did some busy work.

By doing this, get_*_cycles() helpers are unneeded and removed.

Signed-off-by: David Marchand <david.marchand@redhat.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@amd.com>
---
Changes since v2:
- fixed fwd_streams[] access,

Changes since v1:
- removed (now unneeded) get_*_cycles() helpers,
- removed unrelated changes on noisy_vnf change,

---
 app/test-pmd/5tswap.c         | 11 ++++-------
 app/test-pmd/csumonly.c       | 10 +++-------
 app/test-pmd/flowgen.c        |  7 ++-----
 app/test-pmd/icmpecho.c       |  9 +++------
 app/test-pmd/ieee1588fwd.c    | 17 +++++++++--------
 app/test-pmd/iofwd.c          |  9 +++------
 app/test-pmd/macfwd.c         |  9 +++------
 app/test-pmd/macswap.c        | 10 ++++------
 app/test-pmd/noisy_vnf.c      |  8 ++------
 app/test-pmd/rxonly.c         |  9 +++------
 app/test-pmd/shared_rxq_fwd.c |  9 ++++-----
 app/test-pmd/testpmd.c        | 16 +++++++++++++---
 app/test-pmd/testpmd.h        | 16 +---------------
 app/test-pmd/txonly.c         |  9 +++------
 14 files changed, 57 insertions(+), 92 deletions(-)

diff --git a/app/test-pmd/5tswap.c b/app/test-pmd/5tswap.c
index c45a811f59..0a3a897e7b 100644
--- a/app/test-pmd/5tswap.c
+++ b/app/test-pmd/5tswap.c
@@ -81,7 +81,7 @@ swap_udp(struct rte_udp_hdr *udp_hdr)
  * 2,3,4. Swaps source and destination for MAC, IPv4/IPv6, UDP/TCP.
  * Parses each layer and swaps it. When the next layer doesn't match it stops.
  */
-static void
+static bool
 pkt_burst_5tuple_swap(struct fwd_stream *fs)
 {
 	struct rte_mbuf  *pkts_burst[MAX_PKT_BURST];
@@ -105,10 +105,6 @@ pkt_burst_5tuple_swap(struct fwd_stream *fs)
 		uint8_t *byte;
 	} h;
 
-	uint64_t start_tsc = 0;
-
-	get_start_cycles(&start_tsc);
-
 	/*
 	 * Receive a burst of packets and forward them.
 	 */
@@ -116,7 +112,7 @@ pkt_burst_5tuple_swap(struct fwd_stream *fs)
 				 nb_pkt_per_burst);
 	inc_rx_burst_stats(fs, nb_rx);
 	if (unlikely(nb_rx == 0))
-		return;
+		return false;
 
 	fs->rx_packets += nb_rx;
 	txp = &ports[fs->tx_port];
@@ -180,7 +176,8 @@ pkt_burst_5tuple_swap(struct fwd_stream *fs)
 		fs->fwd_dropped += (nb_rx - nb_tx);
 		rte_pktmbuf_free_bulk(&pkts_burst[nb_tx], nb_rx - nb_tx);
 	}
-	get_end_cycles(fs, start_tsc);
+
+	return true;
 }
 
 static void
diff --git a/app/test-pmd/csumonly.c b/app/test-pmd/csumonly.c
index 0b2d4c0593..07850501f4 100644
--- a/app/test-pmd/csumonly.c
+++ b/app/test-pmd/csumonly.c
@@ -828,7 +828,7 @@ pkts_ip_csum_recalc(struct rte_mbuf **pkts_burst, const uint16_t nb_pkts, uint64
  * IP, UDP, TCP and SCTP flags always concern the inner layer. The
  * OUTER_IP is only useful for tunnel packets.
  */
-static void
+static bool
 pkt_burst_checksum_forward(struct fwd_stream *fs)
 {
 	struct rte_mbuf *pkts_burst[MAX_PKT_BURST];
@@ -859,16 +859,12 @@ pkt_burst_checksum_forward(struct fwd_stream *fs)
 	uint32_t rx_bad_outer_ip_csum;
 	struct testpmd_offload_info info;
 
-	uint64_t start_tsc = 0;
-
-	get_start_cycles(&start_tsc);
-
 	/* receive a burst of packet */
 	nb_rx = rte_eth_rx_burst(fs->rx_port, fs->rx_queue, pkts_burst,
 				 nb_pkt_per_burst);
 	inc_rx_burst_stats(fs, nb_rx);
 	if (unlikely(nb_rx == 0))
-		return;
+		return false;
 
 	fs->rx_packets += nb_rx;
 	rx_bad_ip_csum = 0;
@@ -1202,7 +1198,7 @@ pkt_burst_checksum_forward(struct fwd_stream *fs)
 		rte_pktmbuf_free_bulk(&tx_pkts_burst[nb_tx], nb_prep - nb_tx);
 	}
 
-	get_end_cycles(fs, start_tsc);
+	return true;
 }
 
 static void
diff --git a/app/test-pmd/flowgen.c b/app/test-pmd/flowgen.c
index bc3d684496..b3bd4f7c65 100644
--- a/app/test-pmd/flowgen.c
+++ b/app/test-pmd/flowgen.c
@@ -58,7 +58,7 @@ RTE_DEFINE_PER_LCORE(int, _next_flow);
  * terminate receive traffic.  Received traffic is simply discarded, but we
  * still do so in order to maintain traffic statistics.
  */
-static void
+static bool
 pkt_burst_flow_gen(struct fwd_stream *fs)
 {
 	unsigned pkt_size = tx_pkt_length - 4;	/* Adjust FCS */
@@ -77,11 +77,8 @@ pkt_burst_flow_gen(struct fwd_stream *fs)
 	uint16_t nb_clones = nb_pkt_flowgen_clones;
 	uint32_t retry;
 	uint64_t tx_offloads;
-	uint64_t start_tsc = 0;
 	int next_flow = RTE_PER_LCORE(_next_flow);
 
-	get_start_cycles(&start_tsc);
-
 	/* Receive a burst of packets and discard them. */
 	nb_rx = rte_eth_rx_burst(fs->rx_port, fs->rx_queue, pkts_burst,
 				 nb_pkt_per_burst);
@@ -192,7 +189,7 @@ pkt_burst_flow_gen(struct fwd_stream *fs)
 
 	RTE_PER_LCORE(_next_flow) = next_flow;
 
-	get_end_cycles(fs, start_tsc);
+	return true;
 }
 
 static int
diff --git a/app/test-pmd/icmpecho.c b/app/test-pmd/icmpecho.c
index 5a779fca3c..5ef1116141 100644
--- a/app/test-pmd/icmpecho.c
+++ b/app/test-pmd/icmpecho.c
@@ -269,7 +269,7 @@ ipv4_hdr_cksum(struct rte_ipv4_hdr *ip_h)
  * Receive a burst of packets, lookup for ICMP echo requests, and, if any,
  * send back ICMP echo replies.
  */
-static void
+static bool
 reply_to_icmp_echo_rqsts(struct fwd_stream *fs)
 {
 	struct rte_mbuf *pkts_burst[MAX_PKT_BURST];
@@ -292,9 +292,6 @@ reply_to_icmp_echo_rqsts(struct fwd_stream *fs)
 	uint32_t cksum;
 	uint8_t  i;
 	int l2_len;
-	uint64_t start_tsc = 0;
-
-	get_start_cycles(&start_tsc);
 
 	/*
 	 * First, receive a burst of packets.
@@ -303,7 +300,7 @@ reply_to_icmp_echo_rqsts(struct fwd_stream *fs)
 				 nb_pkt_per_burst);
 	inc_rx_burst_stats(fs, nb_rx);
 	if (unlikely(nb_rx == 0))
-		return;
+		return false;
 
 	fs->rx_packets += nb_rx;
 	nb_replies = 0;
@@ -507,7 +504,7 @@ reply_to_icmp_echo_rqsts(struct fwd_stream *fs)
 		}
 	}
 
-	get_end_cycles(fs, start_tsc);
+	return true;
 }
 
 static void
diff --git a/app/test-pmd/ieee1588fwd.c b/app/test-pmd/ieee1588fwd.c
index 242d272948..103c01fcb7 100644
--- a/app/test-pmd/ieee1588fwd.c
+++ b/app/test-pmd/ieee1588fwd.c
@@ -89,7 +89,7 @@ port_ieee1588_tx_timestamp_check(portid_t pi)
 	       (wait_us == 1) ? "" : "s");
 }
 
-static void
+static bool
 ieee1588_packet_fwd(struct fwd_stream *fs)
 {
 	struct rte_mbuf  *mb;
@@ -103,7 +103,7 @@ ieee1588_packet_fwd(struct fwd_stream *fs)
 	 * Receive 1 packet at a time.
 	 */
 	if (rte_eth_rx_burst(fs->rx_port, fs->rx_queue, &mb, 1) == 0)
-		return;
+		return false;
 
 	fs->rx_packets += 1;
 
@@ -126,14 +126,14 @@ ieee1588_packet_fwd(struct fwd_stream *fs)
 			       (unsigned) mb->pkt_len);
 		}
 		rte_pktmbuf_free(mb);
-		return;
+		return false;
 	}
 	if (eth_type != RTE_ETHER_TYPE_1588) {
 		printf("Port %u Received NON PTP packet incorrectly"
 		       " detected by hardware\n",
 		       fs->rx_port);
 		rte_pktmbuf_free(mb);
-		return;
+		return false;
 	}
 
 	/*
@@ -147,14 +147,14 @@ ieee1588_packet_fwd(struct fwd_stream *fs)
 		       " protocol version 0x%x (should be 0x02)\n",
 		       fs->rx_port, ptp_hdr->version);
 		rte_pktmbuf_free(mb);
-		return;
+		return false;
 	}
 	if (ptp_hdr->msg_id != PTP_SYNC_MESSAGE) {
 		printf("Port %u Received PTP V2 Ethernet frame with unexpected"
 		       " message ID 0x%x (expected 0x0 - PTP_SYNC_MESSAGE)\n",
 		       fs->rx_port, ptp_hdr->msg_id);
 		rte_pktmbuf_free(mb);
-		return;
+		return false;
 	}
 	printf("Port %u IEEE1588 PTP V2 SYNC Message filtered by hardware\n",
 	       fs->rx_port);
@@ -168,7 +168,7 @@ ieee1588_packet_fwd(struct fwd_stream *fs)
 		       " by hardware\n",
 		       fs->rx_port);
 		rte_pktmbuf_free(mb);
-		return;
+		return false;
 	}
 
 	/* For i40e we need the timesync register index. It is ignored for the
@@ -188,7 +188,7 @@ ieee1588_packet_fwd(struct fwd_stream *fs)
 		printf("Port %u sent PTP packet dropped\n", fs->tx_port);
 		fs->fwd_dropped += 1;
 		rte_pktmbuf_free(mb);
-		return;
+		return false;
 	}
 	fs->tx_packets += 1;
 
@@ -196,6 +196,7 @@ ieee1588_packet_fwd(struct fwd_stream *fs)
 	 * Check the TX timestamp.
 	 */
 	port_ieee1588_tx_timestamp_check(fs->tx_port);
+	return true;
 }
 
 static int
diff --git a/app/test-pmd/iofwd.c b/app/test-pmd/iofwd.c
index 2bcdf15728..9d0af5f667 100644
--- a/app/test-pmd/iofwd.c
+++ b/app/test-pmd/iofwd.c
@@ -41,16 +41,13 @@
  * This is the fastest possible forwarding operation, as it does not access
  * to packets data.
  */
-static void
+static bool
 pkt_burst_io_forward(struct fwd_stream *fs)
 {
 	struct rte_mbuf *pkts_burst[MAX_PKT_BURST];
 	uint16_t nb_rx;
 	uint16_t nb_tx;
 	uint32_t retry;
-	uint64_t start_tsc = 0;
-
-	get_start_cycles(&start_tsc);
 
 	/*
 	 * Receive a burst of packets and forward them.
@@ -59,7 +56,7 @@ pkt_burst_io_forward(struct fwd_stream *fs)
 			pkts_burst, nb_pkt_per_burst);
 	inc_rx_burst_stats(fs, nb_rx);
 	if (unlikely(nb_rx == 0))
-		return;
+		return false;
 	fs->rx_packets += nb_rx;
 
 	nb_tx = rte_eth_tx_burst(fs->tx_port, fs->tx_queue,
@@ -82,7 +79,7 @@ pkt_burst_io_forward(struct fwd_stream *fs)
 		rte_pktmbuf_free_bulk(&pkts_burst[nb_tx], nb_rx - nb_tx);
 	}
 
-	get_end_cycles(fs, start_tsc);
+	return true;
 }
 
 static void
diff --git a/app/test-pmd/macfwd.c b/app/test-pmd/macfwd.c
index ba08b8f323..3a840247c7 100644
--- a/app/test-pmd/macfwd.c
+++ b/app/test-pmd/macfwd.c
@@ -41,7 +41,7 @@
  * Change the source and the destination Ethernet addressed of packets
  * before forwarding them.
  */
-static void
+static bool
 pkt_burst_mac_forward(struct fwd_stream *fs)
 {
 	struct rte_mbuf  *pkts_burst[MAX_PKT_BURST];
@@ -54,9 +54,6 @@ pkt_burst_mac_forward(struct fwd_stream *fs)
 	uint16_t i;
 	uint64_t ol_flags = 0;
 	uint64_t tx_offloads;
-	uint64_t start_tsc = 0;
-
-	get_start_cycles(&start_tsc);
 
 	/*
 	 * Receive a burst of packets and forward them.
@@ -65,7 +62,7 @@ pkt_burst_mac_forward(struct fwd_stream *fs)
 				 nb_pkt_per_burst);
 	inc_rx_burst_stats(fs, nb_rx);
 	if (unlikely(nb_rx == 0))
-		return;
+		return false;
 
 	fs->rx_packets += nb_rx;
 	txp = &ports[fs->tx_port];
@@ -113,7 +110,7 @@ pkt_burst_mac_forward(struct fwd_stream *fs)
 		rte_pktmbuf_free_bulk(&pkts_burst[nb_tx], nb_rx - nb_tx);
 	}
 
-	get_end_cycles(fs, start_tsc);
+	return true;
 }
 
 static void
diff --git a/app/test-pmd/macswap.c b/app/test-pmd/macswap.c
index 9f0933bbff..14b3eefffd 100644
--- a/app/test-pmd/macswap.c
+++ b/app/test-pmd/macswap.c
@@ -47,7 +47,7 @@
  * MAC swap forwarding mode: Swap the source and the destination Ethernet
  * addresses of packets before forwarding them.
  */
-static void
+static bool
 pkt_burst_mac_swap(struct fwd_stream *fs)
 {
 	struct rte_mbuf  *pkts_burst[MAX_PKT_BURST];
@@ -55,9 +55,6 @@ pkt_burst_mac_swap(struct fwd_stream *fs)
 	uint16_t nb_rx;
 	uint16_t nb_tx;
 	uint32_t retry;
-	uint64_t start_tsc = 0;
-
-	get_start_cycles(&start_tsc);
 
 	/*
 	 * Receive a burst of packets and forward them.
@@ -66,7 +63,7 @@ pkt_burst_mac_swap(struct fwd_stream *fs)
 				 nb_pkt_per_burst);
 	inc_rx_burst_stats(fs, nb_rx);
 	if (unlikely(nb_rx == 0))
-		return;
+		return false;
 
 	fs->rx_packets += nb_rx;
 	txp = &ports[fs->tx_port];
@@ -91,7 +88,8 @@ pkt_burst_mac_swap(struct fwd_stream *fs)
 		fs->fwd_dropped += (nb_rx - nb_tx);
 		rte_pktmbuf_free_bulk(&pkts_burst[nb_tx], nb_rx - nb_tx);
 	}
-	get_end_cycles(fs, start_tsc);
+
+	return true;
 }
 
 static void
diff --git a/app/test-pmd/noisy_vnf.c b/app/test-pmd/noisy_vnf.c
index 055a80a62c..396fdd7814 100644
--- a/app/test-pmd/noisy_vnf.c
+++ b/app/test-pmd/noisy_vnf.c
@@ -134,14 +134,13 @@ drop_pkts(struct rte_mbuf **pkts, uint16_t nb_rx, uint16_t nb_tx)
  *    out of the FIFO
  * 4. Cases 2 and 3 combined
  */
-static void
+static bool
 pkt_burst_noisy_vnf(struct fwd_stream *fs)
 {
 	const uint64_t freq_khz = rte_get_timer_hz() / 1000;
 	struct noisy_config *ncf = noisy_cfg[fs->rx_port];
 	struct rte_mbuf *pkts_burst[MAX_PKT_BURST];
 	struct rte_mbuf *tmp_pkts[MAX_PKT_BURST];
-	uint64_t start_tsc = 0;
 	uint16_t nb_deqd = 0;
 	uint16_t nb_rx = 0;
 	uint16_t nb_tx = 0;
@@ -151,8 +150,6 @@ pkt_burst_noisy_vnf(struct fwd_stream *fs)
 	bool needs_flush = false;
 	uint64_t now;
 
-	get_start_cycles(&start_tsc);
-
 	nb_rx = rte_eth_rx_burst(fs->rx_port, fs->rx_queue,
 			pkts_burst, nb_pkt_per_burst);
 	inc_rx_burst_stats(fs, nb_rx);
@@ -221,8 +218,7 @@ pkt_burst_noisy_vnf(struct fwd_stream *fs)
 		ncf->prev_time = rte_get_timer_cycles();
 	}
 end:
-	if (nb_rx > 0 || nb_tx > 0)
-		get_end_cycles(fs, start_tsc);
+	return nb_rx > 0 || nb_tx > 0;
 }
 
 #define NOISY_STRSIZE 256
diff --git a/app/test-pmd/rxonly.c b/app/test-pmd/rxonly.c
index 8fa5e95ad4..ad4597cf9a 100644
--- a/app/test-pmd/rxonly.c
+++ b/app/test-pmd/rxonly.c
@@ -41,14 +41,11 @@
 /*
  * Received a burst of packets.
  */
-static void
+static bool
 pkt_burst_receive(struct fwd_stream *fs)
 {
 	struct rte_mbuf  *pkts_burst[MAX_PKT_BURST];
 	uint16_t nb_rx;
-	uint64_t start_tsc = 0;
-
-	get_start_cycles(&start_tsc);
 
 	/*
 	 * Receive a burst of packets.
@@ -57,12 +54,12 @@ pkt_burst_receive(struct fwd_stream *fs)
 				 nb_pkt_per_burst);
 	inc_rx_burst_stats(fs, nb_rx);
 	if (unlikely(nb_rx == 0))
-		return;
+		return false;
 
 	fs->rx_packets += nb_rx;
 	rte_pktmbuf_free_bulk(pkts_burst, nb_rx);
 
-	get_end_cycles(fs, start_tsc);
+	return true;
 }
 
 static void
diff --git a/app/test-pmd/shared_rxq_fwd.c b/app/test-pmd/shared_rxq_fwd.c
index 05f90185df..4902ec407e 100644
--- a/app/test-pmd/shared_rxq_fwd.c
+++ b/app/test-pmd/shared_rxq_fwd.c
@@ -89,21 +89,20 @@ forward_shared_rxq(struct fwd_stream *fs, uint16_t nb_rx,
 			  &pkts_burst[nb_rx - nb_sub_burst]);
 }
 
-static void
+static bool
 shared_rxq_fwd(struct fwd_stream *fs)
 {
 	struct rte_mbuf *pkts_burst[nb_pkt_per_burst];
 	uint16_t nb_rx;
-	uint64_t start_tsc = 0;
 
-	get_start_cycles(&start_tsc);
 	nb_rx = rte_eth_rx_burst(fs->rx_port, fs->rx_queue, pkts_burst,
 				 nb_pkt_per_burst);
 	inc_rx_burst_stats(fs, nb_rx);
 	if (unlikely(nb_rx == 0))
-		return;
+		return false;
 	forward_shared_rxq(fs, nb_rx, pkts_burst);
-	get_end_cycles(fs, start_tsc);
+
+	return true;
 }
 
 static void
diff --git a/app/test-pmd/testpmd.c b/app/test-pmd/testpmd.c
index 964cd0ce2b..f80b1c1ca7 100644
--- a/app/test-pmd/testpmd.c
+++ b/app/test-pmd/testpmd.c
@@ -2271,9 +2271,19 @@ run_pkt_fwd_on_lcore(struct fwd_lcore *fc, packet_fwd_t pkt_fwd)
 	nb_fs = fc->stream_nb;
 	prev_tsc = rte_rdtsc();
 	do {
-		for (sm_id = 0; sm_id < nb_fs; sm_id++)
-			if (!fsm[sm_id]->disabled)
-				(*pkt_fwd)(fsm[sm_id]);
+		for (sm_id = 0; sm_id < nb_fs; sm_id++) {
+			struct fwd_stream *fs = fsm[sm_id];
+			uint64_t start_fs_tsc = 0;
+			bool busy;
+
+			if (fs->disabled)
+				continue;
+			if (record_core_cycles)
+				start_fs_tsc = rte_rdtsc();
+			busy = (*pkt_fwd)(fs);
+			if (record_core_cycles && busy)
+				fs->busy_cycles += rte_rdtsc() - start_fs_tsc;
+		}
 #ifdef RTE_LIB_BITRATESTATS
 		if (bitrate_enabled != 0 &&
 				bitrate_lcore_id == rte_lcore_id()) {
diff --git a/app/test-pmd/testpmd.h b/app/test-pmd/testpmd.h
index 329a6378a1..ce47d1ed92 100644
--- a/app/test-pmd/testpmd.h
+++ b/app/test-pmd/testpmd.h
@@ -382,7 +382,7 @@ struct fwd_lcore {
 typedef int (*port_fwd_begin_t)(portid_t pi);
 typedef void (*port_fwd_end_t)(portid_t pi);
 typedef void (*stream_init_t)(struct fwd_stream *fs);
-typedef void (*packet_fwd_t)(struct fwd_stream *fs);
+typedef bool (*packet_fwd_t)(struct fwd_stream *fs);
 
 struct fwd_engine {
 	const char       *fwd_mode_name; /**< Forwarding mode name. */
@@ -837,20 +837,6 @@ mbuf_pool_find(unsigned int sock_id, uint16_t idx)
 	return rte_mempool_lookup((const char *)pool_name);
 }
 
-static inline void
-get_start_cycles(uint64_t *start_tsc)
-{
-	if (record_core_cycles)
-		*start_tsc = rte_rdtsc();
-}
-
-static inline void
-get_end_cycles(struct fwd_stream *fs, uint64_t start_tsc)
-{
-	if (record_core_cycles)
-		fs->busy_cycles += rte_rdtsc() - start_tsc;
-}
-
 static inline void
 inc_rx_burst_stats(struct fwd_stream *fs, uint16_t nb_rx)
 {
diff --git a/app/test-pmd/txonly.c b/app/test-pmd/txonly.c
index 076cdb86d5..63ad5e69bf 100644
--- a/app/test-pmd/txonly.c
+++ b/app/test-pmd/txonly.c
@@ -323,7 +323,7 @@ pkt_burst_prepare(struct rte_mbuf *pkt, struct rte_mempool *mbp,
 /*
  * Transmit a burst of multi-segments packets.
  */
-static void
+static bool
 pkt_burst_transmit(struct fwd_stream *fs)
 {
 	struct rte_mbuf *pkts_burst[MAX_PKT_BURST];
@@ -337,9 +337,6 @@ pkt_burst_transmit(struct fwd_stream *fs)
 	uint32_t retry;
 	uint64_t ol_flags = 0;
 	uint64_t tx_offloads;
-	uint64_t start_tsc = 0;
-
-	get_start_cycles(&start_tsc);
 
 	mbp = current_fwd_lcore()->mbp;
 	txp = &ports[fs->tx_port];
@@ -392,7 +389,7 @@ pkt_burst_transmit(struct fwd_stream *fs)
 	}
 
 	if (nb_pkt == 0)
-		return;
+		return false;
 
 	nb_tx = rte_eth_tx_burst(fs->tx_port, fs->tx_queue, pkts_burst, nb_pkt);
 
@@ -424,7 +421,7 @@ pkt_burst_transmit(struct fwd_stream *fs)
 		rte_pktmbuf_free_bulk(&pkts_burst[nb_tx], nb_pkt - nb_tx);
 	}
 
-	get_end_cycles(fs, start_tsc);
+	return true;
 }
 
 static int
-- 
2.39.2