>From: Pavan Nikhilesh <pbhagavat...@marvell.com>
>
>Use em vector path to process event vector.
>
>Signed-off-by: Pavan Nikhilesh <pbhagavat...@marvell.com>
>---
> examples/l3fwd/l3fwd_em.c | 13 +++--
> examples/l3fwd/l3fwd_em.h | 29 +++++------
> examples/l3fwd/l3fwd_em_hlm.h | 72 +++++-----------------------
> examples/l3fwd/l3fwd_em_sequential.h | 25 ++++++----
> examples/l3fwd/l3fwd_event.h | 21 --------
> 5 files changed, 48 insertions(+), 112 deletions(-)
>
>diff --git a/examples/l3fwd/l3fwd_em.c b/examples/l3fwd/l3fwd_em.c
>index a203dc9e46..35de31157e 100644
>--- a/examples/l3fwd/l3fwd_em.c
>+++ b/examples/l3fwd/l3fwd_em.c
>@@ -860,10 +860,15 @@ em_event_loop_vector(struct l3fwd_event_resources
>*evt_rsrc,
> int i, nb_enq = 0, nb_deq = 0;
> struct lcore_conf *lconf;
> unsigned int lcore_id;
>+ uint16_t *dst_ports;
>
> if (event_p_id < 0)
> return;
>
>+ dst_ports = rte_zmalloc("", sizeof(uint16_t) * evt_rsrc->vector_size,
>+ RTE_CACHE_LINE_SIZE);
>+ if (dst_ports == NULL)
>+ return;
> lcore_id = rte_lcore_id();
> lconf = &lcore_conf[lcore_id];
>
>@@ -885,13 +890,12 @@ em_event_loop_vector(struct l3fwd_event_resources
>*evt_rsrc,
> }
>
> #if defined RTE_ARCH_X86 || defined __ARM_NEON
>- l3fwd_em_process_event_vector(events[i].vec, lconf);
>+ l3fwd_em_process_event_vector(events[i].vec, lconf,
>+ dst_ports);
> #else
> l3fwd_em_no_opt_process_event_vector(events[i].vec,
>- lconf);
>+ lconf, dst_ports);
> #endif
>- if (flags & L3FWD_EVENT_TX_DIRECT)
>- event_vector_txq_set(events[i].vec, 0);
> }
>
> if (flags & L3FWD_EVENT_TX_ENQ) {
>@@ -915,6 +919,7 @@ em_event_loop_vector(struct l3fwd_event_resources
>*evt_rsrc,
>
> l3fwd_event_worker_cleanup(event_d_id, event_p_id, events, nb_enq,
> nb_deq, 1);
>+ rte_free(dst_ports);
> }
>
> int __rte_noinline
>diff --git a/examples/l3fwd/l3fwd_em.h b/examples/l3fwd/l3fwd_em.h
>index fe2ee59f6a..7d051fc076 100644
>--- a/examples/l3fwd/l3fwd_em.h
>+++ b/examples/l3fwd/l3fwd_em.h
>@@ -100,7 +100,7 @@ l3fwd_em_simple_forward(struct rte_mbuf *m, uint16_t
>portid,
> }
> }
>
>-static __rte_always_inline void
>+static __rte_always_inline uint16_t
> l3fwd_em_simple_process(struct rte_mbuf *m, struct lcore_conf *qconf)
> {
> struct rte_ether_hdr *eth_hdr;
>@@ -117,6 +117,8 @@ l3fwd_em_simple_process(struct rte_mbuf *m, struct
>lcore_conf *qconf)
> m->port = l3fwd_em_handle_ipv6(m, m->port, eth_hdr, qconf);
> else
> m->port = BAD_PORT;
>+
>+ return m->port;
> }
>
> /*
>@@ -179,7 +181,8 @@ l3fwd_em_no_opt_process_events(int nb_rx, struct
>rte_event **events,
>
> static inline void
> l3fwd_em_no_opt_process_event_vector(struct rte_event_vector *vec,
>- struct lcore_conf *qconf)
>+ struct lcore_conf *qconf,
>+ uint16_t *dst_ports)
> {
> struct rte_mbuf **mbufs = vec->mbufs;
> int32_t i;
>@@ -188,30 +191,20 @@ l3fwd_em_no_opt_process_event_vector(struct
>rte_event_vector *vec,
> for (i = 0; i < PREFETCH_OFFSET && i < vec->nb_elem; i++)
> rte_prefetch0(rte_pktmbuf_mtod(mbufs[i], void *));
>
>- /* Process first packet to init vector attributes */
>- l3fwd_em_simple_process(mbufs[0], qconf);
>- if (vec->attr_valid) {
>- if (mbufs[0]->port != BAD_PORT)
>- vec->port = mbufs[0]->port;
>- else
>- vec->attr_valid = 0;
>- }
>-
> /*
> * Prefetch and forward already prefetched packets.
> */
>- for (i = 1; i < (vec->nb_elem - PREFETCH_OFFSET); i++) {
>+ for (i = 0; i < (vec->nb_elem - PREFETCH_OFFSET); i++) {
> rte_prefetch0(
> rte_pktmbuf_mtod(mbufs[i + PREFETCH_OFFSET], void
>*));
>- l3fwd_em_simple_process(mbufs[i], qconf);
>- event_vector_attr_validate(vec, mbufs[i]);
>+ dst_ports[i] = l3fwd_em_simple_process(mbufs[i], qconf);
> }
>
> /* Forward remaining prefetched packets */
>- for (; i < vec->nb_elem; i++) {
>- l3fwd_em_simple_process(mbufs[i], qconf);
>- event_vector_attr_validate(vec, mbufs[i]);
>- }
>+ for (; i < vec->nb_elem; i++)
>+ dst_ports[i] = l3fwd_em_simple_process(mbufs[i], qconf);
>+
>+ process_event_vector(vec, dst_ports);
> }
>
> #endif /* __L3FWD_EM_H__ */
>diff --git a/examples/l3fwd/l3fwd_em_hlm.h b/examples/l3fwd/l3fwd_em_hlm.h
>index 12b997e477..2e11eefad7 100644
>--- a/examples/l3fwd/l3fwd_em_hlm.h
>+++ b/examples/l3fwd/l3fwd_em_hlm.h
>@@ -332,70 +332,20 @@ l3fwd_em_process_events(int nb_rx, struct rte_event
>**ev,
>
> static inline void
> l3fwd_em_process_event_vector(struct rte_event_vector *vec,
>- struct lcore_conf *qconf)
>+ struct lcore_conf *qconf, uint16_t *dst_port)
> {
>- struct rte_mbuf **mbufs = vec->mbufs;
>- uint16_t dst_port[MAX_PKT_BURST];
>- int32_t i, j, n, pos;
>-
>- for (j = 0; j < EM_HASH_LOOKUP_COUNT && j < vec->nb_elem; j++)
>- rte_prefetch0(
>- rte_pktmbuf_mtod(mbufs[j], struct rte_ether_hdr *) + 1);
>+ uint16_t i;
>
> if (vec->attr_valid)
>- vec->port = em_get_dst_port(qconf, mbufs[0], mbufs[0]->port);
>-
>- n = RTE_ALIGN_FLOOR(vec->nb_elem, EM_HASH_LOOKUP_COUNT);
>- for (j = 0; j < n; j += EM_HASH_LOOKUP_COUNT) {
>- uint32_t pkt_type =
>- RTE_PTYPE_L3_MASK | RTE_PTYPE_L4_TCP |
>RTE_PTYPE_L4_UDP;
>- uint32_t l3_type, tcp_or_udp;
>-
>- for (i = 0; i < EM_HASH_LOOKUP_COUNT; i++)
>- pkt_type &= mbufs[j + i]->packet_type;
>-
>- l3_type = pkt_type & RTE_PTYPE_L3_MASK;
>- tcp_or_udp = pkt_type & (RTE_PTYPE_L4_TCP |
>RTE_PTYPE_L4_UDP);
>-
>- for (i = 0, pos = j + EM_HASH_LOOKUP_COUNT;
>- i < EM_HASH_LOOKUP_COUNT && pos < vec->nb_elem;
>- i++, pos++) {
>- rte_prefetch0(rte_pktmbuf_mtod(mbufs[pos],
>- struct rte_ether_hdr *) +
>- 1);
>- }
>-
>- if (tcp_or_udp && (l3_type == RTE_PTYPE_L3_IPV4)) {
>- em_get_dst_port_ipv4xN_events(qconf, &mbufs[j],
>- &dst_port[j]);
>- } else if (tcp_or_udp && (l3_type == RTE_PTYPE_L3_IPV6)) {
>- em_get_dst_port_ipv6xN_events(qconf, &mbufs[j],
>- &dst_port[j]);
>- } else {
>- for (i = 0; i < EM_HASH_LOOKUP_COUNT; i++) {
>- mbufs[j + i]->port =
>- em_get_dst_port(qconf, mbufs[j + i],
>- mbufs[j + i]->port);
>- process_packet(mbufs[j + i],
>- &mbufs[j + i]->port);
>- event_vector_attr_validate(vec, mbufs[j + i]);
>- }
>- continue;
>- }
>- processx4_step3(&mbufs[j], &dst_port[j]);
>-
>- for (i = 0; i < EM_HASH_LOOKUP_COUNT; i++) {
>- mbufs[j + i]->port = dst_port[j + i];
>- event_vector_attr_validate(vec, mbufs[j + i]);
>- }
>- }
>-
>- for (; j < vec->nb_elem; j++) {
>- mbufs[j]->port =
>- em_get_dst_port(qconf, mbufs[j], mbufs[j]->port);
>- process_packet(mbufs[j], &mbufs[j]->port);
>- event_vector_attr_validate(vec, mbufs[j]);
>- }
>+ l3fwd_em_process_packets(vec->nb_elem, vec->mbufs,
>dst_port,
>+ vec->port, qconf, 1);
>+ else
>+ for (i = 0; i < vec->nb_elem; i++)
>+ l3fwd_em_process_packets(1, &vec->mbufs[i],
>+ &dst_port[i],
>+ vec->mbufs[i]->port, qconf, 1);
>+
>+ process_event_vector(vec, dst_port);
> }
>
> #endif /* __L3FWD_EM_HLM_H__ */
>diff --git a/examples/l3fwd/l3fwd_em_sequential.h
>b/examples/l3fwd/l3fwd_em_sequential.h
>index d2f75edb8a..067f23889a 100644
>--- a/examples/l3fwd/l3fwd_em_sequential.h
>+++ b/examples/l3fwd/l3fwd_em_sequential.h
>@@ -113,39 +113,48 @@ l3fwd_em_process_events(int nb_rx, struct rte_event
>**events,
>
> for (i = 1, j = 0; j < nb_rx; i++, j++) {
> struct rte_mbuf *mbuf = events[j]->mbuf;
>+ uint16_t port;
>
> if (i < nb_rx) {
> rte_prefetch0(rte_pktmbuf_mtod(
> events[i]->mbuf,
> struct rte_ether_hdr *) + 1);
> }
>+ port = mbuf->port;
> mbuf->port = em_get_dst_port(qconf, mbuf, mbuf->port);
> process_packet(mbuf, &mbuf->port);
>+ if (mbuf->port == BAD_PORT)
>+ mbuf->port = port;
> }
> }
>
> static inline void
> l3fwd_em_process_event_vector(struct rte_event_vector *vec,
>- struct lcore_conf *qconf)
>+ struct lcore_conf *qconf, uint16_t *dst_ports)
> {
>+ const uint8_t attr_valid = vec->attr_valid;
> struct rte_mbuf **mbufs = vec->mbufs;
> int32_t i, j;
>
> rte_prefetch0(rte_pktmbuf_mtod(mbufs[0], struct rte_ether_hdr *) + 1);
>
>- if (vec->attr_valid)
>- vec->port = em_get_dst_port(qconf, mbufs[0], mbufs[0]->port);
>-
> for (i = 0, j = 1; i < vec->nb_elem; i++, j++) {
> if (j < vec->nb_elem)
> rte_prefetch0(rte_pktmbuf_mtod(mbufs[j],
> struct rte_ether_hdr *) +
> 1);
>- mbufs[i]->port =
>- em_get_dst_port(qconf, mbufs[i], mbufs[i]->port);
>- process_packet(mbufs[i], &mbufs[i]->port);
>- event_vector_attr_validate(vec, mbufs[i]);
>+ dst_ports[i] = em_get_dst_port(qconf, mbufs[i],
>+ attr_valid ? vec->port :
>+ mbufs[i]->port);
> }
>+ j = RTE_ALIGN_FLOOR(vec->nb_elem, FWDSTEP);
>+
>+ for (i = 0; i != j; i += FWDSTEP)
>+ processx4_step3(&vec->mbufs[i], &dst_ports[i]);
>+ for (; i < vec->nb_elem; i++)
>+ process_packet(vec->mbufs[i], &dst_ports[i]);
>+
>+ process_event_vector(vec, dst_ports);
> }
>
> #endif /* __L3FWD_EM_SEQUENTIAL_H__ */
>diff --git a/examples/l3fwd/l3fwd_event.h b/examples/l3fwd/l3fwd_event.h
>index 3fe38aada0..e21817c36b 100644
>--- a/examples/l3fwd/l3fwd_event.h
>+++ b/examples/l3fwd/l3fwd_event.h
>@@ -103,27 +103,6 @@ process_dst_port(uint16_t *dst_ports, uint16_t
>nb_elem)
> }
> #endif
>
>-static inline void
>-event_vector_attr_validate(struct rte_event_vector *vec, struct rte_mbuf
>*mbuf)
>-{
>- /* l3fwd application only changes mbuf port while processing */
>- if (vec->attr_valid && (vec->port != mbuf->port))
>- vec->attr_valid = 0;
>-}
>-
>-static inline void
>-event_vector_txq_set(struct rte_event_vector *vec, uint16_t txq)
>-{
>- if (vec->attr_valid) {
>- vec->queue = txq;
>- } else {
>- int i;
>-
>- for (i = 0; i < vec->nb_elem; i++)
>- rte_event_eth_tx_adapter_txq_set(vec->mbufs[i], txq);
>- }
>-}
>-
> static inline uint16_t
> filter_bad_packets(struct rte_mbuf **mbufs, uint16_t *dst_port,
> uint16_t nb_pkts)
>--
>2.25.1
For the series:
Acked-by: Shijith Thotton <sthot...@marvell.com>
