On Tue, Jun 29, 2021 at 01:11:43AM +0530, pbhagavat...@marvell.com wrote:
> From: Pavan Nikhilesh <pbhagavat...@marvell.com>
>
> Add multi segment Tx vector routine.
>
> Signed-off-by: Pavan Nikhilesh <pbhagavat...@marvell.com>
> ---
> drivers/net/cnxk/cn10k_tx.c | 20 +-
> drivers/net/cnxk/cn10k_tx.h | 388 +++++++++++++++++++++++++--
> drivers/net/cnxk/cn10k_tx_vec_mseg.c | 24 ++
> drivers/net/cnxk/cn9k_tx.c | 20 +-
> drivers/net/cnxk/cn9k_tx.h | 272 ++++++++++++++++++-
> drivers/net/cnxk/cn9k_tx_vec_mseg.c | 24 ++
> drivers/net/cnxk/meson.build | 6 +-
> 7 files changed, 709 insertions(+), 45 deletions(-)
> create mode 100644 drivers/net/cnxk/cn10k_tx_vec_mseg.c
> create mode 100644 drivers/net/cnxk/cn9k_tx_vec_mseg.c
>
> diff --git a/drivers/net/cnxk/cn10k_tx.c b/drivers/net/cnxk/cn10k_tx.c
> index d06879163..1f30bab59 100644
> --- a/drivers/net/cnxk/cn10k_tx.c
> +++ b/drivers/net/cnxk/cn10k_tx.c
> @@ -67,13 +67,23 @@ cn10k_eth_set_tx_function(struct rte_eth_dev *eth_dev)
> #undef T
> };
>
> - if (dev->scalar_ena)
> + const eth_tx_burst_t nix_eth_tx_vec_burst_mseg[2][2][2][2][2][2] = {
> +#define T(name, f5, f4, f3, f2, f1, f0, sz, flags)
> \
> + [f5][f4][f3][f2][f1][f0] = cn10k_nix_xmit_pkts_vec_mseg_##name,
> +
> + NIX_TX_FASTPATH_MODES
> +#undef T
> + };
> +
> + if (dev->scalar_ena) {
> pick_tx_func(eth_dev, nix_eth_tx_burst);
> - else
> + if (dev->tx_offloads & DEV_TX_OFFLOAD_MULTI_SEGS)
> + pick_tx_func(eth_dev, nix_eth_tx_burst_mseg);
> + } else {
> pick_tx_func(eth_dev, nix_eth_tx_vec_burst);
> -
> - if (dev->tx_offloads & DEV_TX_OFFLOAD_MULTI_SEGS)
> - pick_tx_func(eth_dev, nix_eth_tx_burst_mseg);
> + if (dev->tx_offloads & DEV_TX_OFFLOAD_MULTI_SEGS)
> + pick_tx_func(eth_dev, nix_eth_tx_vec_burst_mseg);
> + }
>
> rte_mb();
> }
> diff --git a/drivers/net/cnxk/cn10k_tx.h b/drivers/net/cnxk/cn10k_tx.h
> index 26797581e..532b53b31 100644
> --- a/drivers/net/cnxk/cn10k_tx.h
> +++ b/drivers/net/cnxk/cn10k_tx.h
> @@ -42,6 +42,13 @@
> } \
> } while (0)
>
> +/* Encoded number of segments to number of dwords macro, each value of
> nb_segs
> + * is encoded as 4bits.
> + */
> +#define NIX_SEGDW_MAGIC 0x76654432210ULL
> +
> +#define NIX_NB_SEGS_TO_SEGDW(x) ((NIX_SEGDW_MAGIC >> ((x) << 2)) & 0xF)
> +
> #define LMT_OFF(lmt_addr, lmt_num, offset)
> \
> (void *)((lmt_addr) + ((lmt_num) << ROC_LMT_LINE_SIZE_LOG2) + (offset))
>
> @@ -102,6 +109,14 @@ cn10k_nix_tx_steor_data(const uint16_t flags)
> return data;
> }
>
> +static __rte_always_inline uint8_t
> +cn10k_nix_tx_dwords_per_line_seg(const uint16_t flags)
> +{
> + return ((flags & NIX_TX_NEED_EXT_HDR) ?
> + (flags & NIX_TX_OFFLOAD_TSTAMP_F) ? 8 : 6 :
> + 4);
> +}
> +
> static __rte_always_inline uint64_t
> cn10k_nix_tx_steor_vec_data(const uint16_t flags)
> {
> @@ -729,7 +744,244 @@ cn10k_nix_prepare_tso(struct rte_mbuf *m, union
> nix_send_hdr_w1_u *w1,
> }
> }
>
> +static __rte_always_inline void
> +cn10k_nix_prepare_mseg_vec_list(struct rte_mbuf *m, uint64_t *cmd,
> + union nix_send_hdr_w0_u *sh,
> + union nix_send_sg_s *sg, const uint32_t flags)
> +{
> + struct rte_mbuf *m_next;
> + uint64_t *slist, sg_u;
> + uint16_t nb_segs;
> + int i = 1;
> +
> + sh->total = m->pkt_len;
> + /* Clear sg->u header before use */
> + sg->u &= 0xFC00000000000000;
> + sg_u = sg->u;
> + slist = &cmd[0];
> +
> + sg_u = sg_u | ((uint64_t)m->data_len);
> +
> + nb_segs = m->nb_segs - 1;
> + m_next = m->next;
> +
> + /* Set invert df if buffer is not to be freed by H/W */
> + if (flags & NIX_TX_OFFLOAD_MBUF_NOFF_F)
> + sg_u |= (cnxk_nix_prefree_seg(m) << 55);
> + /* Mark mempool object as "put" since it is freed by NIX */
> +#ifdef RTE_LIBRTE_MEMPOOL_DEBUG
> + if (!(sg_u & (1ULL << 55)))
> + __mempool_check_cookies(m->pool, (void **)&m, 1, 0);
> + rte_io_wmb();
> +#endif
> +
> + m = m_next;
> + /* Fill mbuf segments */
> + do {
> + m_next = m->next;
> + sg_u = sg_u | ((uint64_t)m->data_len << (i << 4));
> + *slist = rte_mbuf_data_iova(m);
> + /* Set invert df if buffer is not to be freed by H/W */
> + if (flags & NIX_TX_OFFLOAD_MBUF_NOFF_F)
> + sg_u |= (cnxk_nix_prefree_seg(m) << (i + 55));
> + /* Mark mempool object as "put" since it is freed by NIX
> + */
> +#ifdef RTE_LIBRTE_MEMPOOL_DEBUG
> + if (!(sg_u & (1ULL << (i + 55))))
> + __mempool_check_cookies(m->pool, (void **)&m, 1, 0);
> + rte_io_wmb();
> +#endif
> + slist++;
> + i++;
> + nb_segs--;
> + if (i > 2 && nb_segs) {
> + i = 0;
> + /* Next SG subdesc */
> + *(uint64_t *)slist = sg_u & 0xFC00000000000000;
> + sg->u = sg_u;
> + sg->segs = 3;
> + sg = (union nix_send_sg_s *)slist;
> + sg_u = sg->u;
> + slist++;
> + }
> + m = m_next;
> + } while (nb_segs);
> +
> + sg->u = sg_u;
> + sg->segs = i;
> +}
> +
> +static __rte_always_inline void
> +cn10k_nix_prepare_mseg_vec(struct rte_mbuf *m, uint64_t *cmd, uint64x2_t
> *cmd0,
> + uint64x2_t *cmd1, const uint8_t segdw,
> + const uint32_t flags)
> +{
> + union nix_send_hdr_w0_u sh;
> + union nix_send_sg_s sg;
> +
> + if (m->nb_segs == 1) {
> + if (flags & NIX_TX_OFFLOAD_MBUF_NOFF_F) {
> + sg.u = vgetq_lane_u64(cmd1[0], 0);
> + sg.u |= (cnxk_nix_prefree_seg(m) << 55);
> + cmd1[0] = vsetq_lane_u64(sg.u, cmd1[0], 0);
> + }
> +
> +#ifdef RTE_LIBRTE_MEMPOOL_DEBUG
> + sg.u = vgetq_lane_u64(cmd1[0], 0);
> + if (!(sg.u & (1ULL << 55)))
> + __mempool_check_cookies(m->pool, (void **)&m, 1, 0);
> + rte_io_wmb();
> +#endif
> + return;
> + }
> +
> + sh.u = vgetq_lane_u64(cmd0[0], 0);
> + sg.u = vgetq_lane_u64(cmd1[0], 0);
> +
> + cn10k_nix_prepare_mseg_vec_list(m, cmd, &sh, &sg, flags);
> +
> + sh.sizem1 = segdw - 1;
> + cmd0[0] = vsetq_lane_u64(sh.u, cmd0[0], 0);
> + cmd1[0] = vsetq_lane_u64(sg.u, cmd1[0], 0);
> +}
> +
> #define NIX_DESCS_PER_LOOP 4
> +
> +static __rte_always_inline uint8_t
> +cn10k_nix_prep_lmt_mseg_vector(struct rte_mbuf **mbufs, uint64x2_t *cmd0,
> + uint64x2_t *cmd1, uint64x2_t *cmd2,
> + uint64x2_t *cmd3, uint8_t *segdw,
> + uint64_t *lmt_addr, __uint128_t *data128,
> + uint8_t *shift, const uint16_t flags)
> +{
> + uint8_t j, off, lmt_used;
> +
> + if (!(flags & NIX_TX_NEED_EXT_HDR) &&
> + !(flags & NIX_TX_OFFLOAD_TSTAMP_F)) {
> + /* No segments in 4 consecutive packets. */
> + if ((segdw[0] + segdw[1] + segdw[2] + segdw[3]) <= 8) {
> + for (j = 0; j < NIX_DESCS_PER_LOOP; j++)
> + cn10k_nix_prepare_mseg_vec(mbufs[j], NULL,
> + &cmd0[j], &cmd1[j],
> + segdw[j], flags);
> + vst1q_u64(lmt_addr, cmd0[0]);
> + vst1q_u64(lmt_addr + 2, cmd1[0]);
> + vst1q_u64(lmt_addr + 4, cmd0[1]);
> + vst1q_u64(lmt_addr + 6, cmd1[1]);
> + vst1q_u64(lmt_addr + 8, cmd0[2]);
> + vst1q_u64(lmt_addr + 10, cmd1[2]);
> + vst1q_u64(lmt_addr + 12, cmd0[3]);
> + vst1q_u64(lmt_addr + 14, cmd1[3]);
> +
> + *data128 |= ((__uint128_t)7) << *shift;
> + shift += 3;
> +
> + return 1;
> + }
> + }
> +
> + lmt_used = 0;
> + for (j = 0; j < NIX_DESCS_PER_LOOP;) {
> + /* Fit consecutive packets in same LMTLINE. */
> + if ((segdw[j] + segdw[j + 1]) <= 8) {
> + if (flags & NIX_TX_OFFLOAD_TSTAMP_F) {
> + cn10k_nix_prepare_mseg_vec(mbufs[j], NULL,
> + &cmd0[j], &cmd1[j],
> + segdw[j], flags);
> + cn10k_nix_prepare_mseg_vec(mbufs[j + 1], NULL,
> + &cmd0[j + 1],
> + &cmd1[j + 1],
> + segdw[j + 1], flags);
> + /* TSTAMP takes 4 each, no segs. */
> + vst1q_u64(lmt_addr, cmd0[j]);
> + vst1q_u64(lmt_addr + 2, cmd2[j]);
> + vst1q_u64(lmt_addr + 4, cmd1[j]);
> + vst1q_u64(lmt_addr + 6, cmd3[j]);
> +
> + vst1q_u64(lmt_addr + 8, cmd0[j + 1]);
> + vst1q_u64(lmt_addr + 10, cmd2[j + 1]);
> + vst1q_u64(lmt_addr + 12, cmd1[j + 1]);
> + vst1q_u64(lmt_addr + 14, cmd3[j + 1]);
> + } else if (flags & NIX_TX_NEED_EXT_HDR) {
> + /* EXT header take 3 each, space for 2 segs.*/
> + cn10k_nix_prepare_mseg_vec(mbufs[j],
> + lmt_addr + 6,
> + &cmd0[j], &cmd1[j],
> + segdw[j], flags);
> + vst1q_u64(lmt_addr, cmd0[j]);
> + vst1q_u64(lmt_addr + 2, cmd2[j]);
> + vst1q_u64(lmt_addr + 4, cmd1[j]);
> + off = segdw[j] - 3;
> + off <<= 1;
> + cn10k_nix_prepare_mseg_vec(mbufs[j + 1],
> + lmt_addr + 12 + off,
> + &cmd0[j + 1],
> + &cmd1[j + 1],
> + segdw[j + 1], flags);
> + vst1q_u64(lmt_addr + 6 + off, cmd0[j + 1]);
> + vst1q_u64(lmt_addr + 8 + off, cmd2[j + 1]);
> + vst1q_u64(lmt_addr + 10 + off, cmd1[j + 1]);
> + } else {
> + cn10k_nix_prepare_mseg_vec(mbufs[j],
> + lmt_addr + 4,
> + &cmd0[j], &cmd1[j],
> + segdw[j], flags);
> + vst1q_u64(lmt_addr, cmd0[j]);
> + vst1q_u64(lmt_addr + 2, cmd1[j]);
> + off = segdw[j] - 2;
> + off <<= 1;
> + cn10k_nix_prepare_mseg_vec(mbufs[j + 1],
> + lmt_addr + 8 + off,
> + &cmd0[j + 1],
> + &cmd1[j + 1],
> + segdw[j + 1], flags);
> + vst1q_u64(lmt_addr + 4 + off, cmd0[j + 1]);
> + vst1q_u64(lmt_addr + 6 + off, cmd1[j + 1]);
> + }
> + *data128 |= ((__uint128_t)(segdw[j] + segdw[j + 1]) - 1)
> + << *shift;
> + *shift += 3;
> + j += 2;
> + } else {
> + if ((flags & NIX_TX_NEED_EXT_HDR) &&
> + (flags & NIX_TX_OFFLOAD_TSTAMP_F)) {
> + cn10k_nix_prepare_mseg_vec(mbufs[j],
> + lmt_addr + 6,
> + &cmd0[j], &cmd1[j],
> + segdw[j], flags);
> + vst1q_u64(lmt_addr, cmd0[j]);
> + vst1q_u64(lmt_addr + 2, cmd2[j]);
> + vst1q_u64(lmt_addr + 4, cmd1[j]);
> + off = segdw[j] - 4;
> + off <<= 1;
> + vst1q_u64(lmt_addr + 6 + off, cmd3[j]);
> + } else if (flags & NIX_TX_NEED_EXT_HDR) {
> + cn10k_nix_prepare_mseg_vec(mbufs[j],
> + lmt_addr + 6,
> + &cmd0[j], &cmd1[j],
> + segdw[j], flags);
> + vst1q_u64(lmt_addr, cmd0[j]);
> + vst1q_u64(lmt_addr + 2, cmd2[j]);
> + vst1q_u64(lmt_addr + 4, cmd1[j]);
> + } else {
> + cn10k_nix_prepare_mseg_vec(mbufs[j],
> + lmt_addr + 4,
> + &cmd0[j], &cmd1[j],
> + segdw[j], flags);
> + vst1q_u64(lmt_addr, cmd0[j]);
> + vst1q_u64(lmt_addr + 2, cmd1[j]);
> + }
> + *data128 |= ((__uint128_t)(segdw[j]) - 1) << *shift;
> + *shift += 3;
> + j++;
> + }
> + lmt_used++;
> + lmt_addr += 16;
> + }
> +
> + return lmt_used;
> +}
> +
> static __rte_always_inline uint16_t
> cn10k_nix_xmit_pkts_vector(void *tx_queue, struct rte_mbuf **tx_pkts,
> uint16_t pkts, uint64_t *cmd, const uint16_t flags)
> @@ -738,7 +990,7 @@ cn10k_nix_xmit_pkts_vector(void *tx_queue, struct
> rte_mbuf **tx_pkts,
> uint64x2_t len_olflags0, len_olflags1, len_olflags2, len_olflags3;
> uint64x2_t cmd0[NIX_DESCS_PER_LOOP], cmd1[NIX_DESCS_PER_LOOP],
> cmd2[NIX_DESCS_PER_LOOP], cmd3[NIX_DESCS_PER_LOOP];
> - uint64_t *mbuf0, *mbuf1, *mbuf2, *mbuf3, data, pa;
> + uint64_t *mbuf0, *mbuf1, *mbuf2, *mbuf3, pa;
> uint64x2_t senddesc01_w0, senddesc23_w0;
> uint64x2_t senddesc01_w1, senddesc23_w1;
> uint16_t left, scalar, burst, i, lmt_id;
> @@ -746,6 +998,7 @@ cn10k_nix_xmit_pkts_vector(void *tx_queue, struct
> rte_mbuf **tx_pkts,
> uint64x2_t sendext01_w1, sendext23_w1;
> uint64x2_t sendmem01_w0, sendmem23_w0;
> uint64x2_t sendmem01_w1, sendmem23_w1;
> + uint8_t segdw[NIX_DESCS_PER_LOOP + 1];
> uint64x2_t sgdesc01_w0, sgdesc23_w0;
> uint64x2_t sgdesc01_w1, sgdesc23_w1;
> struct cn10k_eth_txq *txq = tx_queue;
> @@ -754,7 +1007,11 @@ cn10k_nix_xmit_pkts_vector(void *tx_queue, struct
> rte_mbuf **tx_pkts,
> uint64x2_t ltypes01, ltypes23;
> uint64x2_t xtmp128, ytmp128;
> uint64x2_t xmask01, xmask23;
> - uint8_t lnum;
> + uint8_t lnum, shift;
> + union wdata {
> + __uint128_t data128;
> + uint64_t data[2];
> + } wd;
>
> NIX_XMIT_FC_OR_RETURN(txq, pkts);
>
> @@ -798,8 +1055,43 @@ cn10k_nix_xmit_pkts_vector(void *tx_queue, struct
> rte_mbuf **tx_pkts,
> burst = left > cn10k_nix_pkts_per_vec_brst(flags) ?
> cn10k_nix_pkts_per_vec_brst(flags) :
> left;
> + if (flags & NIX_TX_MULTI_SEG_F) {
> + wd.data128 = 0;
> + shift = 16;
> + }
> lnum = 0;
> +
> for (i = 0; i < burst; i += NIX_DESCS_PER_LOOP) {
> + if (flags & NIX_TX_MULTI_SEG_F) {
> + struct rte_mbuf *m = tx_pkts[j];
> + uint8_t j;
[Nithin] I guess it moved out of below loop while rebasing.
With this fixed,
Series-acked-by: Nithin Dabilpuram <ndabilpu...@marvell.com>
> +
> + for (j = 0; j < NIX_DESCS_PER_LOOP; j++) {
> + /* Get dwords based on nb_segs. */
> + segdw[j] = NIX_NB_SEGS_TO_SEGDW(m->nb_segs);
> + /* Add dwords based on offloads. */
> + segdw[j] += 1 + /* SEND HDR */
> + !!(flags & NIX_TX_NEED_EXT_HDR) +
> + !!(flags & NIX_TX_OFFLOAD_TSTAMP_F);
> + }
> +
> + /* Check if there are enough LMTLINES for this loop */
> + if (lnum + 4 > 32) {
> + uint8_t ldwords_con = 0, lneeded = 0;
> + for (j = 0; j < NIX_DESCS_PER_LOOP; j++) {
> + ldwords_con += segdw[j];
> + if (ldwords_con > 8) {
> + lneeded += 1;
> + ldwords_con = segdw[j];
> + }
> + }
> + lneeded += 1;
> + if (lnum + lneeded > 32) {
> + burst = i;
> + break;
> + }
> + }
> + }
> /* Clear lower 32bit of SEND_HDR_W0 and SEND_SG_W0 */
> senddesc01_w0 =
> vbicq_u64(senddesc01_w0, vdupq_n_u64(0xFFFFFFFF));
> @@ -1527,7 +1819,8 @@ cn10k_nix_xmit_pkts_vector(void *tx_queue, struct
> rte_mbuf **tx_pkts,
> sendext23_w0 = vld1q_u64(sx_w0 + 2);
> }
>
> - if (flags & NIX_TX_OFFLOAD_MBUF_NOFF_F) {
> + if ((flags & NIX_TX_OFFLOAD_MBUF_NOFF_F) &&
> + !(flags & NIX_TX_MULTI_SEG_F)) {
> /* Set don't free bit if reference count > 1 */
> xmask01 = vdupq_n_u64(0);
> xmask23 = xmask01;
> @@ -1567,7 +1860,7 @@ cn10k_nix_xmit_pkts_vector(void *tx_queue, struct
> rte_mbuf **tx_pkts,
> (void **)&mbuf3, 1, 0);
> senddesc01_w0 = vorrq_u64(senddesc01_w0, xmask01);
> senddesc23_w0 = vorrq_u64(senddesc23_w0, xmask23);
> - } else {
> + } else if (!(flags & NIX_TX_MULTI_SEG_F)) {
> /* Move mbufs to iova */
> mbuf0 = (uint64_t *)tx_pkts[0];
> mbuf1 = (uint64_t *)tx_pkts[1];
> @@ -1612,7 +1905,19 @@ cn10k_nix_xmit_pkts_vector(void *tx_queue, struct
> rte_mbuf **tx_pkts,
> cmd2[3] = vzip2q_u64(sendext23_w0, sendext23_w1);
> }
>
> - if (flags & NIX_TX_NEED_EXT_HDR) {
> + if (flags & NIX_TX_MULTI_SEG_F) {
> + uint8_t j;
> +
> + segdw[4] = 8;
> + j = cn10k_nix_prep_lmt_mseg_vector(tx_pkts, cmd0, cmd1,
> + cmd2, cmd3, segdw,
> + (uint64_t *)
> + LMT_OFF(laddr, lnum,
> + 0),
> + &wd.data128, &shift,
> + flags);
> + lnum += j;
> + } else if (flags & NIX_TX_NEED_EXT_HDR) {
> /* Store the prepared send desc to LMT lines */
> if (flags & NIX_TX_OFFLOAD_TSTAMP_F) {
> vst1q_u64(LMT_OFF(laddr, lnum, 0), cmd0[0]);
> @@ -1664,34 +1969,55 @@ cn10k_nix_xmit_pkts_vector(void *tx_queue, struct
> rte_mbuf **tx_pkts,
> tx_pkts = tx_pkts + NIX_DESCS_PER_LOOP;
> }
>
> + if (flags & NIX_TX_MULTI_SEG_F)
> + wd.data[0] >>= 16;
> +
> /* Trigger LMTST */
> if (lnum > 16) {
> - data = cn10k_nix_tx_steor_vec_data(flags);
> - pa = io_addr | (data & 0x7) << 4;
> - data &= ~0x7ULL;
> - data |= (15ULL << 12);
> - data |= (uint64_t)lmt_id;
> + if (!(flags & NIX_TX_MULTI_SEG_F))
> + wd.data[0] = cn10k_nix_tx_steor_vec_data(flags);
> +
> + pa = io_addr | (wd.data[0] & 0x7) << 4;
> + wd.data[0] &= ~0x7ULL;
> +
> + if (flags & NIX_TX_MULTI_SEG_F)
> + wd.data[0] <<= 16;
> +
> + wd.data[0] |= (15ULL << 12);
> + wd.data[0] |= (uint64_t)lmt_id;
>
> /* STEOR0 */
> - roc_lmt_submit_steorl(data, pa);
> + roc_lmt_submit_steorl(wd.data[0], pa);
>
> - data = cn10k_nix_tx_steor_vec_data(flags);
> - pa = io_addr | (data & 0x7) << 4;
> - data &= ~0x7ULL;
> - data |= ((uint64_t)(lnum - 17)) << 12;
> - data |= (uint64_t)(lmt_id + 16);
> + if (!(flags & NIX_TX_MULTI_SEG_F))
> + wd.data[1] = cn10k_nix_tx_steor_vec_data(flags);
> +
> + pa = io_addr | (wd.data[1] & 0x7) << 4;
> + wd.data[1] &= ~0x7ULL;
> +
> + if (flags & NIX_TX_MULTI_SEG_F)
> + wd.data[1] <<= 16;
> +
> + wd.data[1] |= ((uint64_t)(lnum - 17)) << 12;
> + wd.data[1] |= (uint64_t)(lmt_id + 16);
>
> /* STEOR1 */
> - roc_lmt_submit_steorl(data, pa);
> + roc_lmt_submit_steorl(wd.data[1], pa);
> } else if (lnum) {
> - data = cn10k_nix_tx_steor_vec_data(flags);
> - pa = io_addr | (data & 0x7) << 4;
> - data &= ~0x7ULL;
> - data |= ((uint64_t)(lnum - 1)) << 12;
> - data |= lmt_id;
> + if (!(flags & NIX_TX_MULTI_SEG_F))
> + wd.data[0] = cn10k_nix_tx_steor_vec_data(flags);
> +
> + pa = io_addr | (wd.data[0] & 0x7) << 4;
> + wd.data[0] &= ~0x7ULL;
> +
> + if (flags & NIX_TX_MULTI_SEG_F)
> + wd.data[0] <<= 16;
> +
> + wd.data[0] |= ((uint64_t)(lnum - 1)) << 12;
> + wd.data[0] |= lmt_id;
>
> /* STEOR0 */
> - roc_lmt_submit_steorl(data, pa);
> + roc_lmt_submit_steorl(wd.data[0], pa);
> }
>
> left -= burst;
> @@ -1699,9 +2025,14 @@ cn10k_nix_xmit_pkts_vector(void *tx_queue, struct
> rte_mbuf **tx_pkts,
> if (left)
> goto again;
>
> - if (unlikely(scalar))
> - pkts += cn10k_nix_xmit_pkts(tx_queue, tx_pkts, scalar, cmd,
> - flags);
> + if (unlikely(scalar)) {
> + if (flags & NIX_TX_MULTI_SEG_F)
> + pkts += cn10k_nix_xmit_pkts_mseg(tx_queue, tx_pkts,
> + scalar, cmd, flags);
> + else
> + pkts += cn10k_nix_xmit_pkts(tx_queue, tx_pkts, scalar,
> + cmd, flags);
> + }
>
> return pkts;
> }
> @@ -1866,7 +2197,10 @@ T(ts_tso_noff_vlan_ol3ol4csum_l3l4csum, 1, 1,
> 1, 1, 1, 1, 8, \
> void *tx_queue, struct rte_mbuf **tx_pkts, uint16_t pkts); \
> \
> uint16_t __rte_noinline __rte_hot cn10k_nix_xmit_pkts_vec_##name( \
> - void *tx_queue, struct rte_mbuf **tx_pkts, uint16_t pkts);
> + void *tx_queue, struct rte_mbuf **tx_pkts, uint16_t pkts); \
> + \
> + uint16_t __rte_noinline __rte_hot cn10k_nix_xmit_pkts_vec_mseg_##name( \
> + void *tx_queue, struct rte_mbuf **tx_pkts, uint16_t pkts); \
>
> NIX_TX_FASTPATH_MODES
> #undef T
> diff --git a/drivers/net/cnxk/cn10k_tx_vec_mseg.c
> b/drivers/net/cnxk/cn10k_tx_vec_mseg.c
> new file mode 100644
> index 000000000..1fad81dba
> --- /dev/null
> +++ b/drivers/net/cnxk/cn10k_tx_vec_mseg.c
> @@ -0,0 +1,24 @@
> +/* SPDX-License-Identifier: BSD-3-Clause
> + * Copyright(C) 2021 Marvell.
> + */
> +
> +#include "cn10k_ethdev.h"
> +#include "cn10k_tx.h"
> +
> +#define T(name, f5, f4, f3, f2, f1, f0, sz, flags)
> \
> + uint16_t __rte_noinline __rte_hot cn10k_nix_xmit_pkts_vec_mseg_##name( \
> + void *tx_queue, struct rte_mbuf **tx_pkts, uint16_t pkts) \
> + { \
> + uint64_t cmd[sz]; \
> + \
> + /* For TSO inner checksum is a must */ \
> + if (((flags) & NIX_TX_OFFLOAD_TSO_F) && \
> + !((flags) & NIX_TX_OFFLOAD_L3_L4_CSUM_F)) \
> + return 0; \
> + return cn10k_nix_xmit_pkts_vector( \
> + tx_queue, tx_pkts, pkts, cmd, \
> + (flags) | NIX_TX_MULTI_SEG_F); \
> + }
> +
> +NIX_TX_FASTPATH_MODES
> +#undef T
> diff --git a/drivers/net/cnxk/cn9k_tx.c b/drivers/net/cnxk/cn9k_tx.c
> index 735e21cc6..763f9a14f 100644
> --- a/drivers/net/cnxk/cn9k_tx.c
> +++ b/drivers/net/cnxk/cn9k_tx.c
> @@ -66,13 +66,23 @@ cn9k_eth_set_tx_function(struct rte_eth_dev *eth_dev)
> #undef T
> };
>
> - if (dev->scalar_ena)
> + const eth_tx_burst_t nix_eth_tx_vec_burst_mseg[2][2][2][2][2][2] = {
> +#define T(name, f5, f4, f3, f2, f1, f0, sz, flags) \
> + [f5][f4][f3][f2][f1][f0] = cn9k_nix_xmit_pkts_vec_mseg_##name,
> +
> + NIX_TX_FASTPATH_MODES
> +#undef T
> + };
> +
> + if (dev->scalar_ena) {
> pick_tx_func(eth_dev, nix_eth_tx_burst);
> - else
> + if (dev->tx_offloads & DEV_TX_OFFLOAD_MULTI_SEGS)
> + pick_tx_func(eth_dev, nix_eth_tx_burst_mseg);
> + } else {
> pick_tx_func(eth_dev, nix_eth_tx_vec_burst);
> -
> - if (dev->tx_offloads & DEV_TX_OFFLOAD_MULTI_SEGS)
> - pick_tx_func(eth_dev, nix_eth_tx_burst_mseg);
> + if (dev->tx_offloads & DEV_TX_OFFLOAD_MULTI_SEGS)
> + pick_tx_func(eth_dev, nix_eth_tx_vec_burst_mseg);
> + }
>
> rte_mb();
> }
> diff --git a/drivers/net/cnxk/cn9k_tx.h b/drivers/net/cnxk/cn9k_tx.h
> index dca732a9f..ed65cd351 100644
> --- a/drivers/net/cnxk/cn9k_tx.h
> +++ b/drivers/net/cnxk/cn9k_tx.h
> @@ -582,7 +582,238 @@ cn9k_nix_prepare_tso(struct rte_mbuf *m, union
> nix_send_hdr_w1_u *w1,
> }
> }
>
> +static __rte_always_inline uint8_t
> +cn9k_nix_prepare_mseg_vec_list(struct rte_mbuf *m, uint64_t *cmd,
> + union nix_send_hdr_w0_u *sh,
> + union nix_send_sg_s *sg, const uint32_t flags)
> +{
> + struct rte_mbuf *m_next;
> + uint64_t *slist, sg_u;
> + uint16_t nb_segs;
> + uint64_t segdw;
> + int i = 1;
> +
> + sh->total = m->pkt_len;
> + /* Clear sg->u header before use */
> + sg->u &= 0xFC00000000000000;
> + sg_u = sg->u;
> + slist = &cmd[0];
> +
> + sg_u = sg_u | ((uint64_t)m->data_len);
> +
> + nb_segs = m->nb_segs - 1;
> + m_next = m->next;
> +
> + /* Set invert df if buffer is not to be freed by H/W */
> + if (flags & NIX_TX_OFFLOAD_MBUF_NOFF_F)
> + sg_u |= (cnxk_nix_prefree_seg(m) << 55);
> + /* Mark mempool object as "put" since it is freed by NIX */
> +#ifdef RTE_LIBRTE_MEMPOOL_DEBUG
> + if (!(sg_u & (1ULL << 55)))
> + __mempool_check_cookies(m->pool, (void **)&m, 1, 0);
> + rte_io_wmb();
> +#endif
> +
> + m = m_next;
> + /* Fill mbuf segments */
> + do {
> + m_next = m->next;
> + sg_u = sg_u | ((uint64_t)m->data_len << (i << 4));
> + *slist = rte_mbuf_data_iova(m);
> + /* Set invert df if buffer is not to be freed by H/W */
> + if (flags & NIX_TX_OFFLOAD_MBUF_NOFF_F)
> + sg_u |= (cnxk_nix_prefree_seg(m) << (i + 55));
> + /* Mark mempool object as "put" since it is freed by NIX
> + */
> +#ifdef RTE_LIBRTE_MEMPOOL_DEBUG
> + if (!(sg_u & (1ULL << (i + 55))))
> + __mempool_check_cookies(m->pool, (void **)&m, 1, 0);
> + rte_io_wmb();
> +#endif
> + slist++;
> + i++;
> + nb_segs--;
> + if (i > 2 && nb_segs) {
> + i = 0;
> + /* Next SG subdesc */
> + *(uint64_t *)slist = sg_u & 0xFC00000000000000;
> + sg->u = sg_u;
> + sg->segs = 3;
> + sg = (union nix_send_sg_s *)slist;
> + sg_u = sg->u;
> + slist++;
> + }
> + m = m_next;
> + } while (nb_segs);
> +
> + sg->u = sg_u;
> + sg->segs = i;
> + segdw = (uint64_t *)slist - (uint64_t *)&cmd[0];
> +
> + segdw += 2;
> + /* Roundup extra dwords to multiple of 2 */
> + segdw = (segdw >> 1) + (segdw & 0x1);
> + /* Default dwords */
> + segdw += 1 + !!(flags & NIX_TX_NEED_EXT_HDR) +
> + !!(flags & NIX_TX_OFFLOAD_TSTAMP_F);
> + sh->sizem1 = segdw - 1;
> +
> + return segdw;
> +}
> +
> +static __rte_always_inline uint8_t
> +cn9k_nix_prepare_mseg_vec(struct rte_mbuf *m, uint64_t *cmd, uint64x2_t
> *cmd0,
> + uint64x2_t *cmd1, const uint32_t flags)
> +{
> + union nix_send_hdr_w0_u sh;
> + union nix_send_sg_s sg;
> + uint8_t ret;
> +
> + if (m->nb_segs == 1) {
> + if (flags & NIX_TX_OFFLOAD_MBUF_NOFF_F) {
> + sg.u = vgetq_lane_u64(cmd1[0], 0);
> + sg.u |= (cnxk_nix_prefree_seg(m) << 55);
> + cmd1[0] = vsetq_lane_u64(sg.u, cmd1[0], 0);
> + }
> +
> +#ifdef RTE_LIBRTE_MEMPOOL_DEBUG
> + sg.u = vgetq_lane_u64(cmd1[0], 0);
> + if (!(sg.u & (1ULL << 55)))
> + __mempool_check_cookies(m->pool, (void **)&m, 1, 0);
> + rte_io_wmb();
> +#endif
> + return 2 + !!(flags & NIX_TX_NEED_EXT_HDR) +
> + !!(flags & NIX_TX_OFFLOAD_TSTAMP_F);
> + }
> +
> + sh.u = vgetq_lane_u64(cmd0[0], 0);
> + sg.u = vgetq_lane_u64(cmd1[0], 0);
> +
> + ret = cn9k_nix_prepare_mseg_vec_list(m, cmd, &sh, &sg, flags);
> +
> + cmd0[0] = vsetq_lane_u64(sh.u, cmd0[0], 0);
> + cmd1[0] = vsetq_lane_u64(sg.u, cmd1[0], 0);
> + return ret;
> +}
> +
> #define NIX_DESCS_PER_LOOP 4
> +
> +static __rte_always_inline void
> +cn9k_nix_xmit_pkts_mseg_vector(uint64x2_t *cmd0, uint64x2_t *cmd1,
> + uint64x2_t *cmd2, uint64x2_t *cmd3,
> + uint8_t *segdw,
> + uint64_t slist[][CNXK_NIX_TX_MSEG_SG_DWORDS - 2],
> + uint64_t *lmt_addr, rte_iova_t io_addr,
> + const uint32_t flags)
> +{
> + uint64_t lmt_status;
> + uint8_t j, off;
> +
> + if (!(flags & NIX_TX_NEED_EXT_HDR) &&
> + !(flags & NIX_TX_OFFLOAD_TSTAMP_F)) {
> + /* No segments in 4 consecutive packets. */
> + if ((segdw[0] + segdw[1] + segdw[2] + segdw[3]) <= 8) {
> + do {
> + vst1q_u64(lmt_addr, cmd0[0]);
> + vst1q_u64(lmt_addr + 2, cmd1[0]);
> + vst1q_u64(lmt_addr + 4, cmd0[1]);
> + vst1q_u64(lmt_addr + 6, cmd1[1]);
> + vst1q_u64(lmt_addr + 8, cmd0[2]);
> + vst1q_u64(lmt_addr + 10, cmd1[2]);
> + vst1q_u64(lmt_addr + 12, cmd0[3]);
> + vst1q_u64(lmt_addr + 14, cmd1[3]);
> + lmt_status = roc_lmt_submit_ldeor(io_addr);
> + } while (lmt_status == 0);
> +
> + return;
> + }
> + }
> +
> + for (j = 0; j < NIX_DESCS_PER_LOOP;) {
> + /* Fit consecutive packets in same LMTLINE. */
> + if ((segdw[j] + segdw[j + 1]) <= 8) {
> +again0:
> + if ((flags & NIX_TX_NEED_EXT_HDR) &&
> + (flags & NIX_TX_OFFLOAD_TSTAMP_F)) {
> + vst1q_u64(lmt_addr, cmd0[j]);
> + vst1q_u64(lmt_addr + 2, cmd2[j]);
> + vst1q_u64(lmt_addr + 4, cmd1[j]);
> + /* Copy segs */
> + off = segdw[j] - 4;
> + roc_lmt_mov_seg(lmt_addr + 6, slist[j], off);
> + off <<= 1;
> + vst1q_u64(lmt_addr + 6 + off, cmd3[j]);
> +
> + vst1q_u64(lmt_addr + 8 + off, cmd0[j + 1]);
> + vst1q_u64(lmt_addr + 10 + off, cmd2[j + 1]);
> + vst1q_u64(lmt_addr + 12 + off, cmd1[j + 1]);
> + roc_lmt_mov_seg(lmt_addr + 14 + off,
> + slist[j + 1], segdw[j + 1] - 4);
> + off += ((segdw[j + 1] - 4) << 1);
> + vst1q_u64(lmt_addr + 14 + off, cmd3[j + 1]);
> + } else if (flags & NIX_TX_NEED_EXT_HDR) {
> + vst1q_u64(lmt_addr, cmd0[j]);
> + vst1q_u64(lmt_addr + 2, cmd2[j]);
> + vst1q_u64(lmt_addr + 4, cmd1[j]);
> + /* Copy segs */
> + off = segdw[j] - 3;
> + roc_lmt_mov_seg(lmt_addr + 6, slist[j], off);
> + off <<= 1;
> + vst1q_u64(lmt_addr + 6 + off, cmd0[j + 1]);
> + vst1q_u64(lmt_addr + 8 + off, cmd2[j + 1]);
> + vst1q_u64(lmt_addr + 10 + off, cmd1[j + 1]);
> + roc_lmt_mov_seg(lmt_addr + 12 + off,
> + slist[j + 1], segdw[j + 1] - 3);
> + } else {
> + vst1q_u64(lmt_addr, cmd0[j]);
> + vst1q_u64(lmt_addr + 2, cmd1[j]);
> + /* Copy segs */
> + off = segdw[j] - 2;
> + roc_lmt_mov_seg(lmt_addr + 4, slist[j], off);
> + off <<= 1;
> + vst1q_u64(lmt_addr + 4 + off, cmd0[j + 1]);
> + vst1q_u64(lmt_addr + 6 + off, cmd1[j + 1]);
> + roc_lmt_mov_seg(lmt_addr + 8 + off,
> + slist[j + 1], segdw[j + 1] - 2);
> + }
> + lmt_status = roc_lmt_submit_ldeor(io_addr);
> + if (lmt_status == 0)
> + goto again0;
> + j += 2;
> + } else {
> +again1:
> + if ((flags & NIX_TX_NEED_EXT_HDR) &&
> + (flags & NIX_TX_OFFLOAD_TSTAMP_F)) {
> + vst1q_u64(lmt_addr, cmd0[j]);
> + vst1q_u64(lmt_addr + 2, cmd2[j]);
> + vst1q_u64(lmt_addr + 4, cmd1[j]);
> + /* Copy segs */
> + off = segdw[j] - 4;
> + roc_lmt_mov_seg(lmt_addr + 6, slist[j], off);
> + off <<= 1;
> + vst1q_u64(lmt_addr + 6 + off, cmd3[j]);
> + } else if (flags & NIX_TX_NEED_EXT_HDR) {
> + vst1q_u64(lmt_addr, cmd0[j]);
> + vst1q_u64(lmt_addr + 2, cmd2[j]);
> + vst1q_u64(lmt_addr + 4, cmd1[j]);
> + /* Copy segs */
> + off = segdw[j] - 3;
> + roc_lmt_mov_seg(lmt_addr + 6, slist[j], off);
> + } else {
> + vst1q_u64(lmt_addr, cmd0[j]);
> + vst1q_u64(lmt_addr + 2, cmd1[j]);
> + /* Copy segs */
> + off = segdw[j] - 2;
> + roc_lmt_mov_seg(lmt_addr + 4, slist[j], off);
> + }
> + lmt_status = roc_lmt_submit_ldeor(io_addr);
> + if (lmt_status == 0)
> + goto again1;
> + j += 1;
> + }
> + }
> +}
> +
> static __rte_always_inline uint16_t
> cn9k_nix_xmit_pkts_vector(void *tx_queue, struct rte_mbuf **tx_pkts,
> uint16_t pkts, uint64_t *cmd, const uint16_t flags)
> @@ -1380,7 +1611,8 @@ cn9k_nix_xmit_pkts_vector(void *tx_queue, struct
> rte_mbuf **tx_pkts,
> sendext23_w0 = vld1q_u64(sx_w0 + 2);
> }
>
> - if (flags & NIX_TX_OFFLOAD_MBUF_NOFF_F) {
> + if ((flags & NIX_TX_OFFLOAD_MBUF_NOFF_F) &&
> + !(flags & NIX_TX_MULTI_SEG_F)) {
> /* Set don't free bit if reference count > 1 */
> xmask01 = vdupq_n_u64(0);
> xmask23 = xmask01;
> @@ -1424,7 +1656,7 @@ cn9k_nix_xmit_pkts_vector(void *tx_queue, struct
> rte_mbuf **tx_pkts,
> * cnxk_nix_prefree_seg are written before LMTST.
> */
> rte_io_wmb();
> - } else {
> + } else if (!(flags & NIX_TX_MULTI_SEG_F)) {
> /* Move mbufs to iova */
> mbuf0 = (uint64_t *)tx_pkts[0];
> mbuf1 = (uint64_t *)tx_pkts[1];
> @@ -1472,7 +1704,27 @@ cn9k_nix_xmit_pkts_vector(void *tx_queue, struct
> rte_mbuf **tx_pkts,
> cmd2[3] = vzip2q_u64(sendext23_w0, sendext23_w1);
> }
>
> - if (flags & NIX_TX_NEED_EXT_HDR) {
> + if (flags & NIX_TX_MULTI_SEG_F) {
> + uint64_t seg_list[NIX_DESCS_PER_LOOP]
> + [CNXK_NIX_TX_MSEG_SG_DWORDS - 2];
> + uint8_t j, segdw[NIX_DESCS_PER_LOOP + 1];
> +
> + /* Build mseg list for each packet individually. */
> + for (j = 0; j < NIX_DESCS_PER_LOOP; j++)
> + segdw[j] = cn9k_nix_prepare_mseg_vec(tx_pkts[j],
> + seg_list[j], &cmd0[j],
> + &cmd1[j], flags);
> + segdw[4] = 8;
> +
> + /* Commit all changes to mbuf before LMTST. */
> + if (flags & NIX_TX_OFFLOAD_MBUF_NOFF_F)
> + rte_io_wmb();
> +
> + cn9k_nix_xmit_pkts_mseg_vector(cmd0, cmd1, cmd2, cmd3,
> + segdw, seg_list,
> + lmt_addr, io_addr,
> + flags);
> + } else if (flags & NIX_TX_NEED_EXT_HDR) {
> /* With ext header in the command we can no longer send
> * all 4 packets together since LMTLINE is 128bytes.
> * Split and Tx twice.
> @@ -1534,9 +1786,14 @@ cn9k_nix_xmit_pkts_vector(void *tx_queue, struct
> rte_mbuf **tx_pkts,
> tx_pkts = tx_pkts + NIX_DESCS_PER_LOOP;
> }
>
> - if (unlikely(pkts_left))
> - pkts += cn9k_nix_xmit_pkts(tx_queue, tx_pkts, pkts_left, cmd,
> - flags);
> + if (unlikely(pkts_left)) {
> + if (flags & NIX_TX_MULTI_SEG_F)
> + pkts += cn9k_nix_xmit_pkts_mseg(tx_queue, tx_pkts,
> + pkts_left, cmd, flags);
> + else
> + pkts += cn9k_nix_xmit_pkts(tx_queue, tx_pkts, pkts_left,
> + cmd, flags);
> + }
>
> return pkts;
> }
> @@ -1701,6 +1958,9 @@ T(ts_tso_noff_vlan_ol3ol4csum_l3l4csum, 1, 1, 1, 1, 1,
> 1, 8, \
> void *tx_queue, struct rte_mbuf **tx_pkts, uint16_t pkts); \
> \
> uint16_t __rte_noinline __rte_hot cn9k_nix_xmit_pkts_vec_##name( \
> + void *tx_queue, struct rte_mbuf **tx_pkts, uint16_t pkts); \
> + \
> + uint16_t __rte_noinline __rte_hot cn9k_nix_xmit_pkts_vec_mseg_##name( \
> void *tx_queue, struct rte_mbuf **tx_pkts, uint16_t pkts);
>
> NIX_TX_FASTPATH_MODES
> diff --git a/drivers/net/cnxk/cn9k_tx_vec_mseg.c
> b/drivers/net/cnxk/cn9k_tx_vec_mseg.c
> new file mode 100644
> index 000000000..0256efd45
> --- /dev/null
> +++ b/drivers/net/cnxk/cn9k_tx_vec_mseg.c
> @@ -0,0 +1,24 @@
> +/* SPDX-License-Identifier: BSD-3-Clause
> + * Copyright(C) 2021 Marvell.
> + */
> +
> +#include "cn9k_ethdev.h"
> +#include "cn9k_tx.h"
> +
> +#define T(name, f5, f4, f3, f2, f1, f0, sz, flags)
> \
> + uint16_t __rte_noinline __rte_hot cn9k_nix_xmit_pkts_vec_mseg_##name( \
> + void *tx_queue, struct rte_mbuf **tx_pkts, uint16_t pkts) \
> + { \
> + uint64_t cmd[sz]; \
> + \
> + /* For TSO inner checksum is a must */ \
> + if (((flags) & NIX_TX_OFFLOAD_TSO_F) && \
> + !((flags) & NIX_TX_OFFLOAD_L3_L4_CSUM_F)) \
> + return 0; \
> + return cn9k_nix_xmit_pkts_vector(tx_queue, tx_pkts, pkts, cmd, \
> + (flags) | \
> + NIX_TX_MULTI_SEG_F); \
> + }
> +
> +NIX_TX_FASTPATH_MODES
> +#undef T
> diff --git a/drivers/net/cnxk/meson.build b/drivers/net/cnxk/meson.build
> index aa8c7253f..361f7ce84 100644
> --- a/drivers/net/cnxk/meson.build
> +++ b/drivers/net/cnxk/meson.build
> @@ -26,7 +26,8 @@ sources += files('cn9k_ethdev.c',
> 'cn9k_rx_vec_mseg.c',
> 'cn9k_tx.c',
> 'cn9k_tx_mseg.c',
> - 'cn9k_tx_vec.c')
> + 'cn9k_tx_vec.c',
> + 'cn9k_tx_vec_mseg.c')
> # CN10K
> sources += files('cn10k_ethdev.c',
> 'cn10k_rte_flow.c',
> @@ -36,7 +37,8 @@ sources += files('cn10k_ethdev.c',
> 'cn10k_rx_vec_mseg.c',
> 'cn10k_tx.c',
> 'cn10k_tx_mseg.c',
> - 'cn10k_tx_vec.c')
> + 'cn10k_tx_vec.c',
> + 'cn10k_tx_vec_mseg.c')
>
> deps += ['bus_pci', 'cryptodev', 'eventdev', 'security']
> deps += ['common_cnxk', 'mempool_cnxk']
> --
> 2.17.1
>
