6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Gal Pressman gal@nvidia.com
commit 94071909477677fc2a1abf3fb281f203f66cf3ca upstream.
The check for non-zero ring with RSS is only relevant for ETHTOOL_SRXCLSRLINS command, in other cases the check tries to access memory which was not initialized by the userspace tool. Only perform the check in case of ETHTOOL_SRXCLSRLINS.
Without this patch, filter deletion (for example) could statistically result in a false error: # ethtool --config-ntuple eth3 delete 484 rmgr: Cannot delete RX class rule: Invalid argument Cannot delete classification rule
Fixes: 9e43ad7a1ede ("net: ethtool: only allow set_rxnfc with rss + ring_cookie if driver opts in") Link: https://lore.kernel.org/netdev/871a9ecf-1e14-40dd-bbd7-e90c92f89d47@nvidia.c... Reviewed-by: Dragos Tatulea dtatulea@nvidia.com Reviewed-by: Tariq Toukan tariqt@nvidia.com Signed-off-by: Gal Pressman gal@nvidia.com Reviewed-by: Edward Cree ecree.xilinx@gmail.com Link: https://patch.msgid.link/20241202164805.1637093-1-gal@nvidia.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/ethtool/ioctl.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)
--- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -993,7 +993,8 @@ static noinline_for_stack int ethtool_se return rc;
/* Nonzero ring with RSS only makes sense if NIC adds them together */ - if (info.flow_type & FLOW_RSS && !ops->cap_rss_rxnfc_adds && + if (cmd == ETHTOOL_SRXCLSRLINS && info.flow_type & FLOW_RSS && + !ops->cap_rss_rxnfc_adds && ethtool_get_flow_spec_ring(info.fs.ring_cookie)) return -EINVAL;