diff options
| author | Shailend Chand <shailend@google.com> | 2024-05-02 02:25:44 +0300 |
|---|---|---|
| committer | David S. Miller <davem@davemloft.net> | 2024-05-05 16:35:34 +0300 |
| commit | 864616d97a4505a719d5f67c29d31776038d39ef (patch) | |
| tree | 46edda4c0c5b33f89f0d3d6ddba8963f41a3cd33 /drivers/net/ethernet/google | |
| parent | 5abc37bdcbc5a32f7c5cb21f5c0334cbf0e81752 (diff) | |
| download | linux-864616d97a4505a719d5f67c29d31776038d39ef.tar.xz | |
gve: Make gve_turnup work for nonempty queues
gVNIC has a requirement that all queues have to be quiesced before any
queue is operated on (created or destroyed). To enable the
implementation of future ndo hooks that work on a single queue, we need
to evolve gve_turnup to account for queues already having some
unprocessed descriptors in the ring.
Say rxq 4 is being stopped and started via the queue api. Due to gve's
requirement of quiescence, queues 0 through 3 are not processing their
rings while queue 4 is being toggled. Once they are made live, these
queues need to be poked to cause them to check their rings for
descriptors that were written during their brief period of quiescence.
Tested-by: Mina Almasry <almasrymina@google.com>
Reviewed-by: Praveen Kaligineedi <pkaligineedi@google.com>
Reviewed-by: Harshitha Ramamurthy <hramamurthy@google.com>
Signed-off-by: Shailend Chand <shailend@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'drivers/net/ethernet/google')
| -rw-r--r-- | drivers/net/ethernet/google/gve/gve_main.c | 14 |
1 files changed, 14 insertions, 0 deletions
diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c index 469a914c71d6..ef902b72b9a9 100644 --- a/drivers/net/ethernet/google/gve/gve_main.c +++ b/drivers/net/ethernet/google/gve/gve_main.c @@ -1979,6 +1979,13 @@ static void gve_turnup(struct gve_priv *priv) gve_set_itr_coalesce_usecs_dqo(priv, block, priv->tx_coalesce_usecs); } + + /* Any descs written by the NIC before this barrier will be + * handled by the one-off napi schedule below. Whereas any + * descs after the barrier will generate interrupts. + */ + mb(); + napi_schedule(&block->napi); } for (idx = 0; idx < priv->rx_cfg.num_queues; idx++) { int ntfy_idx = gve_rx_idx_to_ntfy(priv, idx); @@ -1994,6 +2001,13 @@ static void gve_turnup(struct gve_priv *priv) gve_set_itr_coalesce_usecs_dqo(priv, block, priv->rx_coalesce_usecs); } + + /* Any descs written by the NIC before this barrier will be + * handled by the one-off napi schedule below. Whereas any + * descs after the barrier will generate interrupts. + */ + mb(); + napi_schedule(&block->napi); } gve_set_napi_enabled(priv); |