RE: [PATCH v6 2/4] net/i40e: implement mbufs recycle mode

[Konstantin Ananyev <konstantin.ananyev@huawei.com>]

> > > Define specific function implementation for i40e driver.
> > > Currently, mbufs recycle 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
> > > <mailto:honnappa.nagarahalli@arm.com>
> > > Signed-off-by: Feifei Wang <mailto:feifei.wang2@arm.com>
> > > Reviewed-by: Ruifeng Wang <mailto:ruifeng.wang@arm.com>
> > > Reviewed-by: Honnappa Nagarahalli
> > > <mailto:honnappa.nagarahalli@arm.com>
> > > ---
> > >  drivers/net/i40e/i40e_ethdev.c | 1 +
> > >  drivers/net/i40e/i40e_ethdev.h | 2 +
> > >  .../net/i40e/i40e_recycle_mbufs_vec_common.c | 140
> > ++++++++++++++++++
> > > drivers/net/i40e/i40e_rxtx.c | 32 ++++  drivers/net/i40e/i40e_rxtx.h |
> > > 4 +  drivers/net/i40e/meson.build | 2 +
> > >  6 files changed, 181 insertions(+)
> > >  create mode 100644 drivers/net/i40e/i40e_recycle_mbufs_vec_common.c
> > >
> > > diff --git a/drivers/net/i40e/i40e_ethdev.c
> > > b/drivers/net/i40e/i40e_ethdev.c index f9d8f9791f..d4eecd16cf 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,
> > > + .recycle_rxq_info_get = i40e_recycle_rxq_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..b5b2d6cf2b 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_recycle_rxq_info_get(struct rte_eth_dev *dev, uint16_t
> > > +queue_id,  struct rte_eth_recycle_rxq_info *recycle_rxq_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_recycle_mbufs_vec_common.c
> > > b/drivers/net/i40e/i40e_recycle_mbufs_vec_common.c
> > > new file mode 100644
> > > index 0000000000..08d708fd7d
> > > --- /dev/null
> > > +++ b/drivers/net/i40e/i40e_recycle_mbufs_vec_common.c
> > > @@ -0,0 +1,140 @@
> > > +/* SPDX-License-Identifier: BSD-3-Clause
> > > + * Copyright (c) 2023 Arm Limited.
> > > + */
> > > +
> > > +#include <stdint.h>
> > > +#include <ethdev_driver.h>
> > > +
> > > +#include "base/i40e_prototype.h"
> > > +#include "base/i40e_type.h"
> > > +#include "i40e_ethdev.h"
> > > +#include "i40e_rxtx.h"
> > > +
> > > +#pragma GCC diagnostic ignored "-Wcast-qual"
> > > +
> > > +void
> > > +i40e_recycle_rx_descriptors_refill_vec(void *rx_queue, uint16_t
> > > +nb_mbufs) {  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_mbufs; 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_mbufs;
> > > + rx_id = rxq->rxrearm_start - 1;
> > > +
> > > + if (unlikely(rxq->rxrearm_start >= rxq->nb_rx_desc)) {
> > > + rxq->rxrearm_start = 0;
> > > + rx_id = rxq->nb_rx_desc - 1;
> > > + }
> > > +
> > > + rxq->rxrearm_nb -= nb_mbufs;
> > > +
> > > + rte_io_wmb();
> > > + /* Update the tail pointer on the NIC */
> > > +I40E_PCI_REG_WRITE_RELAXED(rxq->qrx_tail, rx_id); }
> > > +
> > > +uint16_t
> > > +i40e_recycle_tx_mbufs_reuse_vec(void *tx_queue,  struct
> > > +rte_eth_recycle_rxq_info *recycle_rxq_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 mbuf_ring_size =
> > > +recycle_rxq_info->mbuf_ring_size;
> > > + uint16_t mask = recycle_rxq_info->mbuf_ring_size - 1;  uint16_t
> > > +refill_requirement = recycle_rxq_info->refill_requirement;
> > > + uint16_t refill_head = *recycle_rxq_info->refill_head;  uint16_t
> > > +receive_tail = *recycle_rxq_info->receive_tail;
> > > +
> > > + /* Get available recycling Rx buffers. */ avail = (mbuf_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;
> > > +
> > > + /* Mbufs recycle mode can only support no ring buffer wrapping around.
> > > + * Two case for this:
> > > + *
> > > + * case 1: The refill head of Rx buffer ring needs to be aligned with
> > > + * mbuf ring size. In this case, the number of Tx freeing buffers
> > > + * should be equal to refill_requirement.
> > > + *
> > > + * case 2: The refill head of Rx ring buffer does not need to be
> > > + aligned
> > > + * with mbuf ring size. In this case, the update of refill head can
> > > + not
> > > + * exceed the Rx mbuf ring size.
> > > + */
> > > + if (refill_requirement != n ||
> > > + (!refill_requirement && (refill_head + n > mbuf_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 =
> > > + recycle_rxq_info->mbuf_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 mempool. */ if
> > > + (unlikely(recycle_rxq_info->mp != txep[i].mbuf->pool)) return 0;
> > > I don't think that it is possible to simply return 0 here:
> > > we might already have some mbufs inside rxep[], so we probably need to
> > > return that number (j).
> > >
> > > No, here is just pre-free, not actually put mbufs into rxeq.
> >
> > I understand that.
> > What I am saying: after you call pktmbuf_prefree_seg(mbuf), you can’t keep it
> > in the txq anymore.
> > You have either to put it into rxep[], or back into mempool.
> > Also txq state (nb_tx_free, etc.) need to be updated.
> >
> > > After run out of the loop, we call rte_memcpy to actually copy mbufs
> > > into rxep.
> > > +
> > > + 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_requirement)) return 0;
> > >
> > > same here, we can't simply return 0, it will introduce mbuf leakage.
> > > + /* In case 2, the number of valid Tx free
> > > + * buffers should be recorded.
> > > + */
> > > + j++;
> > > + }
> > > + rte_memcpy(rxep, m, sizeof(void *) * j);
> > > Wonder why do you need intermediate buffer for released mbufs?
> > > Why can't just:
> > > ...
> > > m = rte_pktmbuf_prefree_seg(txep[i].mbuf);
> > > ...
> > > rxep[j++] = m;
> > > ?
> > > Might save you few extra cycles.
> > > Sometimes ‘rte_pktmbuf_prefree_seg’ can return NULL due to
> > > mbuf->refcnt > 1. So we should firstly ensure all ‘m’ are valid and
> > > then copy them into rxep.
> >
> > I understand that, but you can check is it NULL or not.
> For i40e rxq, it must rearm ' RTE_I40E_RXQ_REARM_THRESH ' pkts once a time
> based on its ring wrapping mechanism.
> 
> For i40e txq, it must free ' txq->tx_rs_thresh' pkts once a time.
> 
> So we need firstly ensure all tx free mbufs are valid, and then copy these into rxq.
> If not enough valid mbufs, it will break rxq's ring wrapping mechanism.
 
I think you can still copy mbufs into rxep[], if there are not enough mbufs,
you can still return 0 (or whatever is a proper value here), and that would mean
all these new rxep[] entries will be considered as invalid.
Anyway that's just a suggestion to avoid extra copy.

> 
> >
> > > + }
> > > +
> > > + /* 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;
> > > +}