From: Edward Cree
Test creates an ntuple filter with 'action 2' and an RSS context whose
indirection table has entries 0 and 1. Resulting traffic should go to
queues 2 and 3; verify that it never hits queues 0 and 1.
Signed-off-by: Edward Cree
---
.../selftests/drivers/net/hw/rss_ctx.py
From: Edward Cree
sfc hardware does not support filters with only ipproto + dst-port;
adding dst-ip to the flow spec allows the rss_ctx test to be run on
these devices.
Signed-off-by: Edward Cree
---
I'm not sure if this change will break the test for other drivers that
perhaps support the ol
From: Edward Cree
The original semantics of ntuple filters with FLOW_RSS were not
fully understood by all drivers, some ignoring the ring_cookie from
the flow rule. Require this support to be explicitly declared by
the driver for filters relying on it to be inserted, and add self-
test cover
From: Edward Cree
The combination of ntuple action (ring_cookie) and RSS context can
cause an ntuple rule to target a higher queue than appears in any
RSS indirection table or directly in the ntuple rule, since the two
numbers are added together. Verify the logic that prevents reducing
the q
Jakub Kicinski writes:
> On Mon, 11 Nov 2024 18:09:01 +0100 Petr Machata wrote:
>> Check that only one notification is produced for various FDB edit
>> operations.
>>
>> Regarding the ip_link_add() and ip_link_master() helpers. This pattern of
>> action plus corresponding defer is bound to com
From: Edward Cree
In ethtool_check_max_channel(), the new RX count must not only cover the
max queue indices in RSS indirection tables and RXNFC destinations
separately, but must also, for RXNFC rules with FLOW_RSS, cover the sum
of the destination queue and the maximum index in the associated
From: Edward Cree
Ethtool ntuple filters with FLOW_RSS were originally defined as adding
the base queue ID (ring_cookie) to the value from the indirection table,
so that the same table could distribute over more than one set of queues
when used by different filters.
However, some drivers / har
