On 1/28/17 3:20 AM, Saeed Mahameed wrote:
On Sat, Jan 28, 2017 at 1:23 AM, Alexei Starovoitov <a...@fb.com> wrote:
On 1/27/17 1:15 PM, Saeed Mahameed wrote:
It is only mandatory for configurations that needs eswitch, where the
driver has no way to know about them, for a good old bare metal box,
eswitch is not needed.
we can do some work to strip the l2 table logic - needed for PFs to
work on multi-host - out of eswitch but again that would further
complicate the driver code since eswitch will still need to update l2
tables for VFs.
Saeed,
for multi-host setups every host in that multi-host doesn't
actually see the eswitch, no? Otherwise broken driver on one machine
can affect the other hosts in the same bundle? Please double check,
each host (PF) has its own eswitch, and each eswitch lives in its own
"steering-space"
and it can't affect others.
since this is absolutely critical HW requirement.
The only shared HW resources between hosts (PFs) is the simple l2 table,
and the only thing a host can ask from the l2 talbe (FW) is: "forward
UC MAC to me", and it is the responsibility of the the driver eswitch
to do so.
the l2 table is created and managed by FW, SW eswitch can only request
from FW, and the FW is trusted.
ok. clear. thanks for explaining.
Could you describe the sequence of function calls within mlx5
that does the assignment of uc mac for PF ?
since I'm missing where eswitch is involved.
I can see:
mlx5e_nic_enable | mlx5e_set_mac
queue_work(priv->wq, &priv->set_rx_mode_work);
mlx5e_set_rx_mode_work
mlx5e_apply_netdev_addr
mlx5e_add_l2_flow_rule
