DPDK patches and discussions
 help / color / mirror / Atom feed
From: Feifei Wang <feifei.wang2@arm.com>
To: Yuying Zhang <Yuying.Zhang@intel.com>,
	Beilei Xing <beilei.xing@intel.com>
Cc: dev@dpdk.org, konstantin.v.ananyev@yandex.ru,
	mb@smartsharesystems.com, nd@arm.com,
	Feifei Wang <feifei.wang2@arm.com>,
	Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>,
	Ruifeng Wang <ruifeng.wang@arm.com>
Subject: [PATCH v5 2/3] net/i40e: implement recycle buffer mode
Date: Thu, 30 Mar 2023 14:29:38 +0800	[thread overview]
Message-ID: <20230330062939.1206267-3-feifei.wang2@arm.com> (raw)
In-Reply-To: <20230330062939.1206267-1-feifei.wang2@arm.com>

Define specific function implementation for i40e driver.
Currently, recycle buffer mode can support 128bit
vector path and avx2 path. And can be enabled both in
fast free and no fast free mode.

Suggested-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
Signed-off-by: Feifei Wang <feifei.wang2@arm.com>
Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
Reviewed-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
---
 drivers/net/i40e/i40e_ethdev.c |   1 +
 drivers/net/i40e/i40e_ethdev.h |   2 +
 drivers/net/i40e/i40e_rxtx.c   | 159 +++++++++++++++++++++++++++++++++
 drivers/net/i40e/i40e_rxtx.h   |   4 +
 4 files changed, 166 insertions(+)

diff --git a/drivers/net/i40e/i40e_ethdev.c b/drivers/net/i40e/i40e_ethdev.c
index cb0070f94b..456fb256f5 100644
--- a/drivers/net/i40e/i40e_ethdev.c
+++ b/drivers/net/i40e/i40e_ethdev.c
@@ -496,6 +496,7 @@ static const struct eth_dev_ops i40e_eth_dev_ops = {
 	.flow_ops_get                 = i40e_dev_flow_ops_get,
 	.rxq_info_get                 = i40e_rxq_info_get,
 	.txq_info_get                 = i40e_txq_info_get,
+	.rxq_buf_recycle_info_get     = i40e_rxq_buf_recycle_info_get,
 	.rx_burst_mode_get            = i40e_rx_burst_mode_get,
 	.tx_burst_mode_get            = i40e_tx_burst_mode_get,
 	.timesync_enable              = i40e_timesync_enable,
diff --git a/drivers/net/i40e/i40e_ethdev.h b/drivers/net/i40e/i40e_ethdev.h
index 9b806d130e..83c5ff5859 100644
--- a/drivers/net/i40e/i40e_ethdev.h
+++ b/drivers/net/i40e/i40e_ethdev.h
@@ -1355,6 +1355,8 @@ void i40e_rxq_info_get(struct rte_eth_dev *dev, uint16_t queue_id,
 	struct rte_eth_rxq_info *qinfo);
 void i40e_txq_info_get(struct rte_eth_dev *dev, uint16_t queue_id,
 	struct rte_eth_txq_info *qinfo);
+void i40e_rxq_buf_recycle_info_get(struct rte_eth_dev *dev, uint16_t queue_id,
+	struct rte_eth_rxq_buf_recycle_info *rxq_buf_recycle_info);
 int i40e_rx_burst_mode_get(struct rte_eth_dev *dev, uint16_t queue_id,
 			   struct rte_eth_burst_mode *mode);
 int i40e_tx_burst_mode_get(struct rte_eth_dev *dev, uint16_t queue_id,
diff --git a/drivers/net/i40e/i40e_rxtx.c b/drivers/net/i40e/i40e_rxtx.c
index 788ffb51c2..55c788317f 100644
--- a/drivers/net/i40e/i40e_rxtx.c
+++ b/drivers/net/i40e/i40e_rxtx.c
@@ -1536,6 +1536,134 @@ i40e_xmit_pkts_vec(void *tx_queue, struct rte_mbuf **tx_pkts,
 	return nb_tx;
 }
 
+uint16_t
+i40e_tx_buf_stash_vec(void *tx_queue,
+	struct rte_eth_rxq_buf_recycle_info *rxq_buf_recycle_info)
+{
+	struct i40e_tx_queue *txq = tx_queue;
+	struct i40e_tx_entry *txep;
+	struct rte_mbuf **rxep;
+	struct rte_mbuf *m[RTE_I40E_TX_MAX_FREE_BUF_SZ];
+	int i, j, n;
+	uint16_t avail = 0;
+	uint16_t buf_ring_size = rxq_buf_recycle_info->buf_ring_size;
+	uint16_t mask = rxq_buf_recycle_info->buf_ring_size - 1;
+	uint16_t refill_request = rxq_buf_recycle_info->refill_request;
+	uint16_t refill_head = *rxq_buf_recycle_info->refill_head;
+	uint16_t receive_tail = *rxq_buf_recycle_info->receive_tail;
+
+	/* Get available recycling Rx buffers. */
+	avail = (buf_ring_size - (refill_head - receive_tail)) & mask;
+
+	/* Check Tx free thresh and Rx available space. */
+	if (txq->nb_tx_free > txq->tx_free_thresh || avail <= txq->tx_rs_thresh)
+		return 0;
+
+	/* check DD bits on threshold descriptor */
+	if ((txq->tx_ring[txq->tx_next_dd].cmd_type_offset_bsz &
+				rte_cpu_to_le_64(I40E_TXD_QW1_DTYPE_MASK)) !=
+			rte_cpu_to_le_64(I40E_TX_DESC_DTYPE_DESC_DONE))
+		return 0;
+
+	n = txq->tx_rs_thresh;
+
+	/* Buffer recycle can only support no ring buffer wraparound.
+	 * Two case for this:
+	 *
+	 * case 1: The refill head of Rx buffer ring needs to be aligned with
+	 * buffer ring size. In this case, the number of Tx freeing buffers
+	 * should be equal to refill_request.
+	 *
+	 * case 2: The refill head of Rx ring buffer does not need to be aligned
+	 * with buffer ring size. In this case, the update of refill head can not
+	 * exceed the Rx buffer ring size.
+	 */
+	if (refill_request != n ||
+		(!refill_request && (refill_head + n > buf_ring_size)))
+		return 0;
+
+	/* First buffer to free from S/W ring is at index
+	 * tx_next_dd - (tx_rs_thresh-1).
+	 */
+	txep = &txq->sw_ring[txq->tx_next_dd - (n - 1)];
+	rxep = rxq_buf_recycle_info->buf_ring;
+	rxep += refill_head;
+
+	if (txq->offloads & RTE_ETH_TX_OFFLOAD_MBUF_FAST_FREE) {
+		/* Directly put mbufs from Tx to Rx. */
+		for (i = 0; i < n; i++, rxep++, txep++)
+			*rxep = txep[0].mbuf;
+	} else {
+		for (i = 0, j = 0; i < n; i++) {
+			/* Avoid txq contains buffers from expected mempoo. */
+			if (unlikely(rxq_buf_recycle_info->mp
+						!= txep[i].mbuf->pool))
+				return 0;
+
+			m[j] = rte_pktmbuf_prefree_seg(txep[i].mbuf);
+
+			/* In case 1, each of Tx buffers should be the
+			 * last reference.
+			 */
+			if (unlikely(m[j] == NULL && refill_request))
+				return 0;
+			/* In case 2, the number of valid Tx free
+			 * buffers should be recorded.
+			 */
+			j++;
+		}
+		rte_memcpy(rxep, m, sizeof(void *) * j);
+	}
+
+	/* Update counters for Tx. */
+	txq->nb_tx_free = (uint16_t)(txq->nb_tx_free + txq->tx_rs_thresh);
+	txq->tx_next_dd = (uint16_t)(txq->tx_next_dd + txq->tx_rs_thresh);
+	if (txq->tx_next_dd >= txq->nb_tx_desc)
+		txq->tx_next_dd = (uint16_t)(txq->tx_rs_thresh - 1);
+
+	return n;
+}
+
+uint16_t
+i40e_rx_descriptors_refill_vec(void *rx_queue, uint16_t nb)
+{
+	struct i40e_rx_queue *rxq = rx_queue;
+	struct i40e_rx_entry *rxep;
+	volatile union i40e_rx_desc *rxdp;
+	uint16_t rx_id;
+	uint64_t paddr;
+	uint64_t dma_addr;
+	uint16_t i;
+
+	rxdp = rxq->rx_ring + rxq->rxrearm_start;
+	rxep = &rxq->sw_ring[rxq->rxrearm_start];
+
+	for (i = 0; i < nb; i++) {
+		/* Initialize rxdp descs. */
+		paddr = (rxep[i].mbuf)->buf_iova + RTE_PKTMBUF_HEADROOM;
+		dma_addr = rte_cpu_to_le_64(paddr);
+		/* flush desc with pa dma_addr */
+		rxdp[i].read.hdr_addr = 0;
+		rxdp[i].read.pkt_addr = dma_addr;
+	}
+
+	/* Update the descriptor initializer index */
+	rxq->rxrearm_start += nb;
+	if (rxq->rxrearm_start >= rxq->nb_rx_desc)
+		rxq->rxrearm_start = 0;
+
+	rxq->rxrearm_nb -= nb;
+
+	rx_id = (uint16_t)((rxq->rxrearm_start == 0) ?
+			(rxq->nb_rx_desc - 1) : (rxq->rxrearm_start - 1));
+
+	rte_io_wmb();
+	/* Update the tail pointer on the NIC */
+	I40E_PCI_REG_WRITE_RELAXED(rxq->qrx_tail, rx_id);
+
+	return nb;
+}
+
 /*********************************************************************
  *
  *  TX simple prep functions
@@ -3197,6 +3325,30 @@ i40e_txq_info_get(struct rte_eth_dev *dev, uint16_t queue_id,
 	qinfo->conf.offloads = txq->offloads;
 }
 
+void
+i40e_rxq_buf_recycle_info_get(struct rte_eth_dev *dev, uint16_t queue_id,
+	struct rte_eth_rxq_buf_recycle_info *rxq_buf_recycle_info)
+{
+	struct i40e_rx_queue *rxq;
+	struct i40e_adapter *ad =
+		I40E_DEV_PRIVATE_TO_ADAPTER(dev->data->dev_private);
+
+	rxq = dev->data->rx_queues[queue_id];
+
+	rxq_buf_recycle_info->buf_ring = (void *)rxq->sw_ring;
+	rxq_buf_recycle_info->mp = rxq->mp;
+	rxq_buf_recycle_info->buf_ring_size = rxq->nb_rx_desc;
+	rxq_buf_recycle_info->receive_tail = &rxq->rx_tail;
+
+	if (ad->rx_vec_allowed) {
+		rxq_buf_recycle_info->refill_request = RTE_I40E_RXQ_REARM_THRESH;
+		rxq_buf_recycle_info->refill_head = &rxq->rxrearm_start;
+	} else {
+		rxq_buf_recycle_info->refill_request = rxq->rx_free_thresh;
+		rxq_buf_recycle_info->refill_head = &rxq->rx_free_trigger;
+	}
+}
+
 #ifdef RTE_ARCH_X86
 static inline bool
 get_avx_supported(bool request_avx512)
@@ -3291,6 +3443,8 @@ i40e_set_rx_function(struct rte_eth_dev *dev)
 				dev->rx_pkt_burst = ad->rx_use_avx2 ?
 					i40e_recv_scattered_pkts_vec_avx2 :
 					i40e_recv_scattered_pkts_vec;
+				dev->rx_descriptors_refill =
+					i40e_rx_descriptors_refill_vec;
 			}
 		} else {
 			if (ad->rx_use_avx512) {
@@ -3309,9 +3463,12 @@ i40e_set_rx_function(struct rte_eth_dev *dev)
 				dev->rx_pkt_burst = ad->rx_use_avx2 ?
 					i40e_recv_pkts_vec_avx2 :
 					i40e_recv_pkts_vec;
+				dev->rx_descriptors_refill =
+					i40e_rx_descriptors_refill_vec;
 			}
 		}
 #else /* RTE_ARCH_X86 */
+		dev->rx_descriptors_refill = i40e_rx_descriptors_refill_vec;
 		if (dev->data->scattered_rx) {
 			PMD_INIT_LOG(DEBUG,
 				     "Using Vector Scattered Rx (port %d).",
@@ -3479,6 +3636,7 @@ i40e_set_tx_function(struct rte_eth_dev *dev)
 				dev->tx_pkt_burst = ad->tx_use_avx2 ?
 						    i40e_xmit_pkts_vec_avx2 :
 						    i40e_xmit_pkts_vec;
+				dev->tx_buf_stash = i40e_tx_buf_stash_vec;
 			}
 #else /* RTE_ARCH_X86 */
 			PMD_INIT_LOG(DEBUG, "Using Vector Tx (port %d).",
@@ -3488,6 +3646,7 @@ i40e_set_tx_function(struct rte_eth_dev *dev)
 		} else {
 			PMD_INIT_LOG(DEBUG, "Simple tx finally be used.");
 			dev->tx_pkt_burst = i40e_xmit_pkts_simple;
+			dev->tx_buf_stash = i40e_tx_buf_stash_vec;
 		}
 		dev->tx_pkt_prepare = i40e_simple_prep_pkts;
 	} else {
diff --git a/drivers/net/i40e/i40e_rxtx.h b/drivers/net/i40e/i40e_rxtx.h
index 5e6eecc501..0ad8f530f9 100644
--- a/drivers/net/i40e/i40e_rxtx.h
+++ b/drivers/net/i40e/i40e_rxtx.h
@@ -233,6 +233,10 @@ uint32_t i40e_dev_rx_queue_count(void *rx_queue);
 int i40e_dev_rx_descriptor_status(void *rx_queue, uint16_t offset);
 int i40e_dev_tx_descriptor_status(void *tx_queue, uint16_t offset);
 
+uint16_t i40e_tx_buf_stash_vec(void *tx_queue,
+		struct rte_eth_rxq_buf_recycle_info *rxq_buf_recycle_info);
+uint16_t i40e_rx_descriptors_refill_vec(void *rx_queue, uint16_t nb);
+
 uint16_t i40e_recv_pkts_vec(void *rx_queue, struct rte_mbuf **rx_pkts,
 			    uint16_t nb_pkts);
 uint16_t i40e_recv_scattered_pkts_vec(void *rx_queue,
-- 
2.25.1


  parent reply	other threads:[~2023-03-30  6:30 UTC|newest]

Thread overview: 67+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-12-24 16:46 [RFC PATCH v1 0/4] Direct re-arming of buffers on receive side Feifei Wang
2021-12-24 16:46 ` [RFC PATCH v1 1/4] net/i40e: enable direct re-arm mode Feifei Wang
2021-12-24 16:46 ` [RFC PATCH v1 2/4] ethdev: add API for " Feifei Wang
2021-12-24 19:38   ` Stephen Hemminger
2021-12-26  9:49     ` 回复: " Feifei Wang
2021-12-26 10:31       ` Morten Brørup
2021-12-24 16:46 ` [RFC PATCH v1 3/4] net/i40e: add direct re-arm mode internal API Feifei Wang
2021-12-24 16:46 ` [RFC PATCH v1 4/4] examples/l3fwd: give an example for direct rearm mode Feifei Wang
2021-12-26 10:25 ` [RFC PATCH v1 0/4] Direct re-arming of buffers on receive side Morten Brørup
2021-12-28  6:55   ` 回复: " Feifei Wang
2022-01-18 15:51     ` Ferruh Yigit
2022-01-18 16:53       ` Thomas Monjalon
2022-01-18 17:27         ` Morten Brørup
2022-01-27  5:24           ` Honnappa Nagarahalli
2022-01-27 16:45             ` Ananyev, Konstantin
2022-02-02 19:46               ` Honnappa Nagarahalli
2022-01-27  5:16         ` Honnappa Nagarahalli
2023-02-28  6:43       ` 回复: " Feifei Wang
2023-02-28  6:52         ` Feifei Wang
2022-01-27  4:06   ` Honnappa Nagarahalli
2022-01-27 17:13     ` Morten Brørup
2022-01-28 11:29     ` Morten Brørup
2023-03-23 10:43 ` [PATCH v4 0/3] Recycle buffers from Tx to Rx Feifei Wang
2023-03-23 10:43   ` [PATCH v4 1/3] ethdev: add API for buffer recycle mode Feifei Wang
2023-03-23 11:41     ` Morten Brørup
2023-03-29  2:16       ` Feifei Wang
2023-03-23 10:43   ` [PATCH v4 2/3] net/i40e: implement recycle buffer mode Feifei Wang
2023-03-23 10:43   ` [PATCH v4 3/3] net/ixgbe: " Feifei Wang
2023-03-30  6:29 ` [PATCH v5 0/3] Recycle buffers from Tx to Rx Feifei Wang
2023-03-30  6:29   ` [PATCH v5 1/3] ethdev: add API for buffer recycle mode Feifei Wang
2023-03-30  7:19     ` Morten Brørup
2023-03-30  9:31       ` Feifei Wang
2023-03-30 15:15         ` Morten Brørup
2023-03-30 15:58         ` Morten Brørup
2023-04-26  6:59           ` Feifei Wang
2023-04-19 14:46     ` Ferruh Yigit
2023-04-26  7:29       ` Feifei Wang
2023-03-30  6:29   ` Feifei Wang [this message]
2023-03-30  6:29   ` [PATCH v5 3/3] net/ixgbe: implement recycle buffer mode Feifei Wang
2023-04-19 14:46     ` Ferruh Yigit
2023-04-26  7:36       ` Feifei Wang
2023-03-30 15:04   ` [PATCH v5 0/3] Recycle buffers from Tx to Rx Stephen Hemminger
2023-04-03  2:48     ` Feifei Wang
2023-04-19 14:56   ` Ferruh Yigit
2023-04-25  7:57     ` Feifei Wang
2023-05-25  9:45 ` [PATCH v6 0/4] Recycle mbufs from Tx queue to Rx queue Feifei Wang
2023-05-25  9:45   ` [PATCH v6 1/4] ethdev: add API for mbufs recycle mode Feifei Wang
2023-05-25 15:08     ` Morten Brørup
2023-05-31  6:10       ` Feifei Wang
2023-06-05 12:53     ` Константин Ананьев
2023-06-06  2:55       ` Feifei Wang
2023-06-06  7:10         ` Konstantin Ananyev
2023-06-06  7:31           ` Feifei Wang
2023-06-06  8:34             ` Konstantin Ananyev
2023-06-07  0:00               ` Ferruh Yigit
2023-06-12  3:25                 ` Feifei Wang
2023-05-25  9:45   ` [PATCH v6 2/4] net/i40e: implement " Feifei Wang
2023-06-05 13:02     ` Константин Ананьев
2023-06-06  3:16       ` Feifei Wang
2023-06-06  7:18         ` Konstantin Ananyev
2023-06-06  7:58           ` Feifei Wang
2023-06-06  8:27             ` Konstantin Ananyev
2023-06-12  3:05               ` Feifei Wang
2023-05-25  9:45   ` [PATCH v6 3/4] net/ixgbe: " Feifei Wang
2023-05-25  9:45   ` [PATCH v6 4/4] app/testpmd: add recycle mbufs engine Feifei Wang
2023-06-05 13:08     ` Константин Ананьев
2023-06-06  6:32       ` Feifei Wang

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20230330062939.1206267-3-feifei.wang2@arm.com \
    --to=feifei.wang2@arm.com \
    --cc=Yuying.Zhang@intel.com \
    --cc=beilei.xing@intel.com \
    --cc=dev@dpdk.org \
    --cc=honnappa.nagarahalli@arm.com \
    --cc=konstantin.v.ananyev@yandex.ru \
    --cc=mb@smartsharesystems.com \
    --cc=nd@arm.com \
    --cc=ruifeng.wang@arm.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).