Hi Jerin,

> -----Original Message-----
> From: Jerin Jacob <jerinjac...@gmail.com>
> Sent: 28 September 2021 19:55
> To: Kundapura, Ganapati <ganapati.kundap...@intel.com>
> Cc: Jayatheerthan, Jay <jay.jayatheert...@intel.com>; dpdk-dev
> <dev@dpdk.org>; Yigit, Ferruh <ferruh.yi...@intel.com>
> Subject: Re: [PATCH v2] eventdev: update rx timestamp in mbuf using mbuf
> dynamic field
> 
> On Thu, Sep 16, 2021 at 2:45 PM Ganapati Kundapura
> <ganapati.kundap...@intel.com> wrote:
> >
> > Add support to register timestamp dynamic field in mbuf.
> >
> > Update the timestamp in mbuf for each packet before enqueuing to event
> > device if the timestamp is not already set.
> >
> > Adding the timestamp in Rx adapter avoids additional latency due to
> > the event device.
> >
> > Signed-off-by: Ganapati Kundapura <ganapati.kundap...@intel.com>
> >
> > ---
> > Depends-on: patch-97549(make Rx-adapter enqueue buffer as circular
> > buffer)
> >
> > v2:
> > * Removed rte_ prefix from the internal function
> >
> > v1:
> > * Add support to register timestamp dynamic field in mbuf
> > ---
> > ---
> >  lib/eventdev/rte_event_eth_rx_adapter.c | 33
> > +++++++++++++++++++++++++++++++++
> >  1 file changed, 33 insertions(+)
> >
> > diff --git a/lib/eventdev/rte_event_eth_rx_adapter.c
> > b/lib/eventdev/rte_event_eth_rx_adapter.c
> > index f2dc695..fd79b28 100644
> > --- a/lib/eventdev/rte_event_eth_rx_adapter.c
> > +++ b/lib/eventdev/rte_event_eth_rx_adapter.c
> > @@ -17,6 +17,7 @@
> >  #include <rte_service_component.h>
> >  #include <rte_thash.h>
> >  #include <rte_interrupts.h>
> > +#include <rte_mbuf_dyn.h>
> >
> >  #include "rte_eventdev.h"
> >  #include "eventdev_pmd.h"
> > @@ -240,6 +241,17 @@ struct eth_rx_queue_info {
> >
> >  static struct rte_event_eth_rx_adapter **event_eth_rx_adapter;
> >
> > +/* Enable dynamic timestamp field in mbuf */ uint64_t
> > +event_eth_rx_timestamp_dynflag; int
> > +event_eth_rx_timestamp_dynfield_offset = -1;
> 
> # If the scope is only this file. Please make both as "static"
> # Please fix the following check path and git log issue.
> 
Updated timestamp variables to static

> 
> Wrong headline case:
>                         "eventdev: update rx timestamp in mbuf using mbuf 
> dynamic
> field": rx --> Rx Headline too long:
>         eventdev: update rx timestamp in mbuf using mbuf dynamic field
> 
/workspace/sw/gkundap/LINUX/linux/scripts $ ./checkpatch.pl --version
Usage: ./checkpatch.pl [OPTION]... [FILE]...
Version: 0.32

/workspace/sw/gkundap/dpdk-upstream/dpdk-next-eventdev $ 
./devtools/checkpatches.sh 
v3-0001-eventdev-update-Rx-timestamp-in-mbuf-using-mbuf-d.patch

1/1 valid patch
/workspace/sw/gkundap/dpdk-upstream/dpdk-next-eventdev $

/workspace/sw/gkundap/dpdk-upstream/dpdk-next-eventdev $ 
./devtools/check-git-log.sh 
v3-0001-eventdev-update-Rx-timestamp-in-mbuf-using-mbuf-d.patch

1/1 valid patch
/workspace/sw/gkundap/dpdk-upstream/dpdk-next-eventdev $

> 
> Feel free to add my Acked-By in the next version.
Added in v3
> 
> > +
> > +static inline rte_mbuf_timestamp_t *
> > +rxa_timestamp_dynfield(struct rte_mbuf *mbuf) {
> > +       return RTE_MBUF_DYNFIELD(mbuf,
> > +               event_eth_rx_timestamp_dynfield_offset,
> > +rte_mbuf_timestamp_t *); }
> > +
> >  static inline int
> >  rxa_validate_id(uint8_t id)
> >  {
> > @@ -890,8 +902,18 @@ rxa_buffer_mbufs(struct
> rte_event_eth_rx_adapter *rx_adapter,
> >         int do_rss;
> >         uint16_t nb_cb;
> >         uint16_t dropped;
> > +       uint64_t ts, ts_mask;
> >
> >         if (!eth_rx_queue_info->ena_vector) {
> > +               ts = m->ol_flags & event_eth_rx_timestamp_dynflag ?
> > +                                               0 :
> > + rte_get_tsc_cycles();
> > +
> > +               /* 0xffff ffff ffff ffff if PKT_RX_TIMESTAMP is set,
> > +                * otherwise 0
> > +                */
> > +               ts_mask = (uint64_t)(!(m->ol_flags &
> > +
> > + event_eth_rx_timestamp_dynflag)) - 1ULL;
> > +
> >                 /* 0xffff ffff if PKT_RX_RSS_HASH is set, otherwise 0 */
> >                 rss_mask = ~(((m->ol_flags & PKT_RX_RSS_HASH) != 0) - 1);
> >                 do_rss = !rss_mask &&
> > !eth_rx_queue_info->flow_id_mask; @@ -899,6 +921,9 @@
> rxa_buffer_mbufs(struct rte_event_eth_rx_adapter *rx_adapter,
> >                         struct rte_event *ev;
> >
> >                         m = mbufs[i];
> > +                       *rxa_timestamp_dynfield(m) = ts |
> > +                                       (*rxa_timestamp_dynfield(m) &
> > + ts_mask);
> > +
> >                         ev = &buf->events[new_tail];
> >
> >                         rss = do_rss ? rxa_do_softrss(m,
> > rx_adapter->rss_key_be) @@ -2238,6 +2263,14 @@
> rte_event_eth_rx_adapter_create_ext(uint8_t id, uint8_t dev_id,
> >         event_eth_rx_adapter[id] = rx_adapter;
> >         if (conf_cb == rxa_default_conf_cb)
> >                 rx_adapter->default_cb_arg = 1;
> > +
> > +       if (rte_mbuf_dyn_rx_timestamp_register(
> > +                       &event_eth_rx_timestamp_dynfield_offset,
> > +                       &event_eth_rx_timestamp_dynflag) != 0) {
> > +               RTE_EDEV_LOG_ERR("Error registering timestamp field in
> mbuf\n");
> > +               return -rte_errno;
> > +       }
> > +
> >         rte_eventdev_trace_eth_rx_adapter_create(id, dev_id, conf_cb,
> >                 conf_arg);
> >         return 0;
> > --
> > 2.6.4
> >

Reply via email to