Hi Bing, > -----Original Message----- > From: Bing Zhao <bi...@mellanox.com> > Sent: Monday, April 13, 2020 5:56 PM > To: john.mcnam...@intel.com; marko.kovace...@intel.com; Slava Ovsiienko > <viachesl...@mellanox.com>; Matan Azrad <ma...@mellanox.com> > Cc: Shahaf Shuler <shah...@mellanox.com>; Raslan Darawsheh > <rasl...@mellanox.com>; Ori Kam <or...@mellanox.com>; dev@dpdk.org; > Thomas Monjalon <tho...@monjalon.net> > Subject: [PATCH v2] doc: update flow non-cached mode notes > > This patch updates the MLX5 PMD and release notes documentations. > Adding the notes of the behavior change that rte flows organization > is switched into non-cached mode for applications. > > Signed-off-by: Bing Zhao <bi...@mellanox.com> > --- > v2: update the description in release notes. > --- > doc/guides/nics/mlx5.rst | 10 ++++++++++ > doc/guides/rel_notes/release_20_05.rst | 1 + > 2 files changed, 11 insertions(+) > > diff --git a/doc/guides/nics/mlx5.rst b/doc/guides/nics/mlx5.rst > index e13c07d..63138c4 100644 > --- a/doc/guides/nics/mlx5.rst > +++ b/doc/guides/nics/mlx5.rst > @@ -1287,6 +1287,16 @@ set, and we should allow to specify zero values as > rte_flow parameters for the > META and MARK items and actions. In the same time zero mask has no > meaning and > should be rejected on validation stage. > > +Notes for rte_flow > +------------------ > +Implementation of flows organization is in non-cached mode. When stopping a > +device, all the flows inserted from application will be considered invalid > and > +flushed automatically in the background. After restarting of the device, no > +application's flow exists in the system. > +
I think that it should be stated that all flows are destroyed, and the reference to those flows are not valid any more. It is important to tell that the pointers that the application is holding is not valid anymore, and should be discarded by the application. > +The application should re-insert the flows as required after device > restarting, > +and must not try to destroy or flush the invalid flows before stopping. > + Here I think it should say: The application should recreate the flows. Again it to make sure that the application flow pointers are not valid anymore. Also I don't understand the last line, The application should destroy all flows before stopping the device. > Notes for testpmd > ----------------- > > diff --git a/doc/guides/rel_notes/release_20_05.rst > b/doc/guides/rel_notes/release_20_05.rst > index 4b81893..b951745 100644 > --- a/doc/guides/rel_notes/release_20_05.rst > +++ b/doc/guides/rel_notes/release_20_05.rst > @@ -62,6 +62,7 @@ New Features > > * Added support for matching on IPv4 Time To Live and IPv6 Hop Limit. > * Added support for creating Relaxed Ordering Memory Regions. > + * Flow rules caching removed from the driver for memory saving. > And correctness according to RTE flow. Thanks, Ori > * **Updated the Intel ice driver.** > > -- > 1.8.3.1
