From: Edward Cree Date: Wed, 13 Nov 2024 12:13:09 +0000 (+0000) Subject: net: ethtool: only allow set_rxnfc with rss + ring_cookie if driver opts in X-Git-Tag: v6.13-rc1~135^2~38^2~4 X-Git-Url: http://git.ipfire.org/?a=commitdiff_plain;h=9e43ad7a1edef268acac603e1975c8f50a20d02f;p=thirdparty%2Flinux.git net: ethtool: only allow set_rxnfc with rss + ring_cookie if driver opts in 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 / hardware ignore the ring_cookie, and simply use the indirection table entries as queue IDs directly. Thus, for drivers which have not opted in by setting ethtool_ops.cap_rss_rxnfc_adds to declare that they support the original (addition) semantics, reject in ethtool_set_rxnfc any filter which combines FLOW_RSS and a nonzero ring. (For a ring_cookie of zero, both behaviours are equivalent.) Set the cap bit in sfc, as it is known to support this feature. Signed-off-by: Edward Cree Reviewed-by: Martin Habets Link: https://patch.msgid.link/cc3da0844083b0e301a33092a6299e4042b65221.1731499022.git.ecree.xilinx@gmail.com Signed-off-by: Jakub Kicinski --- diff --git a/drivers/net/ethernet/sfc/ef100_ethtool.c b/drivers/net/ethernet/sfc/ef100_ethtool.c index 5c2551369812c..6c3b74000d3b6 100644 --- a/drivers/net/ethernet/sfc/ef100_ethtool.c +++ b/drivers/net/ethernet/sfc/ef100_ethtool.c @@ -59,6 +59,7 @@ const struct ethtool_ops ef100_ethtool_ops = { .get_rxfh_indir_size = efx_ethtool_get_rxfh_indir_size, .get_rxfh_key_size = efx_ethtool_get_rxfh_key_size, .rxfh_per_ctx_key = true, + .cap_rss_rxnfc_adds = true, .rxfh_priv_size = sizeof(struct efx_rss_context_priv), .get_rxfh = efx_ethtool_get_rxfh, .set_rxfh = efx_ethtool_set_rxfh, diff --git a/drivers/net/ethernet/sfc/ethtool.c b/drivers/net/ethernet/sfc/ethtool.c index bb1930818beba..83d715544f7fb 100644 --- a/drivers/net/ethernet/sfc/ethtool.c +++ b/drivers/net/ethernet/sfc/ethtool.c @@ -263,6 +263,7 @@ const struct ethtool_ops efx_ethtool_ops = { .get_rxfh_indir_size = efx_ethtool_get_rxfh_indir_size, .get_rxfh_key_size = efx_ethtool_get_rxfh_key_size, .rxfh_per_ctx_key = true, + .cap_rss_rxnfc_adds = true, .rxfh_priv_size = sizeof(struct efx_rss_context_priv), .get_rxfh = efx_ethtool_get_rxfh, .set_rxfh = efx_ethtool_set_rxfh, diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 1199e308c8ddb..299280c94d070 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -734,6 +734,9 @@ struct kernel_ethtool_ts_info { * @rxfh_per_ctx_key: device supports setting different RSS key for each * additional context. Netlink API should report hfunc, key, and input_xfrm * for every context, not just context 0. + * @cap_rss_rxnfc_adds: device supports nonzero ring_cookie in filters with + * %FLOW_RSS flag; the queue ID from the filter is added to the value from + * the indirection table to determine the delivery queue. * @rxfh_indir_space: max size of RSS indirection tables, if indirection table * size as returned by @get_rxfh_indir_size may change during lifetime * of the device. Leave as 0 if the table size is constant. @@ -956,6 +959,7 @@ struct ethtool_ops { u32 cap_rss_ctx_supported:1; u32 cap_rss_sym_xor_supported:1; u32 rxfh_per_ctx_key:1; + u32 cap_rss_rxnfc_adds:1; u32 rxfh_indir_space; u16 rxfh_key_space; u16 rxfh_priv_size; diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index 7da94e26ced64..d86399bcf223a 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -992,6 +992,11 @@ static noinline_for_stack int ethtool_set_rxnfc(struct net_device *dev, if (rc) 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 && + ethtool_get_flow_spec_ring(info.fs.ring_cookie)) + return -EINVAL; + if (ops->get_rxfh) { struct ethtool_rxfh_param rxfh = {};