2011-11-15 23:29:55 +08:00
|
|
|
/*
|
|
|
|
|
* Network device features.
|
|
|
|
|
*
|
|
|
|
|
*
|
|
|
|
|
* This program is free software; you can redistribute it and/or
|
|
|
|
|
* modify it under the terms of the GNU General Public License
|
|
|
|
|
* as published by the Free Software Foundation; either version
|
|
|
|
|
* 2 of the License, or (at your option) any later version.
|
|
|
|
|
*/
|
|
|
|
|
#ifndef _LINUX_NETDEV_FEATURES_H
|
|
|
|
|
#define _LINUX_NETDEV_FEATURES_H
|
|
|
|
|
|
2011-11-15 23:29:55 +08:00
|
|
|
#include <linux/types.h>
|
|
|
|
|
|
2011-11-15 23:29:55 +08:00
|
|
|
typedef u64 netdev_features_t;
|
2011-11-15 23:29:55 +08:00
|
|
|
|
2011-11-15 23:29:55 +08:00
|
|
|
enum {
|
|
|
|
|
NETIF_F_SG_BIT, /* Scatter/gather IO. */
|
|
|
|
|
NETIF_F_IP_CSUM_BIT, /* Can checksum TCP/UDP over IPv4. */
|
2011-11-15 23:29:55 +08:00
|
|
|
__UNUSED_NETIF_F_1,
|
2011-11-15 23:29:55 +08:00
|
|
|
NETIF_F_HW_CSUM_BIT, /* Can checksum all the packets. */
|
|
|
|
|
NETIF_F_IPV6_CSUM_BIT, /* Can checksum TCP/UDP over IPV6 */
|
|
|
|
|
NETIF_F_HIGHDMA_BIT, /* Can DMA to high memory. */
|
|
|
|
|
NETIF_F_FRAGLIST_BIT, /* Scatter/gather IO. */
|
2013-04-19 10:04:27 +08:00
|
|
|
NETIF_F_HW_VLAN_CTAG_TX_BIT, /* Transmit VLAN CTAG HW acceleration */
|
|
|
|
|
NETIF_F_HW_VLAN_CTAG_RX_BIT, /* Receive VLAN CTAG HW acceleration */
|
|
|
|
|
NETIF_F_HW_VLAN_CTAG_FILTER_BIT,/* Receive filtering on VLAN CTAGs */
|
2011-11-15 23:29:55 +08:00
|
|
|
NETIF_F_VLAN_CHALLENGED_BIT, /* Device cannot handle VLAN packets */
|
|
|
|
|
NETIF_F_GSO_BIT, /* Enable software GSO. */
|
|
|
|
|
NETIF_F_LLTX_BIT, /* LockLess TX - deprecated. Please */
|
2011-11-15 23:29:55 +08:00
|
|
|
/* do not use LLTX in new drivers */
|
2011-11-15 23:29:55 +08:00
|
|
|
NETIF_F_NETNS_LOCAL_BIT, /* Does not change network namespaces */
|
|
|
|
|
NETIF_F_GRO_BIT, /* Generic receive offload */
|
|
|
|
|
NETIF_F_LRO_BIT, /* large receive offload */
|
|
|
|
|
|
|
|
|
|
/**/NETIF_F_GSO_SHIFT, /* keep the order of SKB_GSO_* bits */
|
|
|
|
|
NETIF_F_TSO_BIT /* ... TCPv4 segmentation */
|
|
|
|
|
= NETIF_F_GSO_SHIFT,
|
|
|
|
|
NETIF_F_GSO_ROBUST_BIT, /* ... ->SKB_GSO_DODGY */
|
|
|
|
|
NETIF_F_TSO_ECN_BIT, /* ... TCP ECN support */
|
2016-04-11 09:44:51 +08:00
|
|
|
NETIF_F_TSO_MANGLEID_BIT, /* ... IPV4 ID mangling allowed */
|
2011-11-15 23:29:55 +08:00
|
|
|
NETIF_F_TSO6_BIT, /* ... TCPv6 segmentation */
|
|
|
|
|
NETIF_F_FSO_BIT, /* ... FCoE segmentation */
|
2013-02-14 22:02:41 +08:00
|
|
|
NETIF_F_GSO_GRE_BIT, /* ... GRE with TSO */
|
2014-06-05 08:20:23 +08:00
|
|
|
NETIF_F_GSO_GRE_CSUM_BIT, /* ... GRE with csum with TSO */
|
2016-05-19 00:06:10 +08:00
|
|
|
NETIF_F_GSO_IPXIP4_BIT, /* ... IP4 or IP6 over IP4 with TSO */
|
|
|
|
|
NETIF_F_GSO_IPXIP6_BIT, /* ... IP4 or IP6 over IP6 with TSO */
|
2013-03-07 21:21:51 +08:00
|
|
|
NETIF_F_GSO_UDP_TUNNEL_BIT, /* ... UDP TUNNEL with TSO */
|
2014-06-05 08:20:16 +08:00
|
|
|
NETIF_F_GSO_UDP_TUNNEL_CSUM_BIT,/* ... UDP TUNNEL with TSO & CSUM */
|
2016-04-11 09:45:03 +08:00
|
|
|
NETIF_F_GSO_PARTIAL_BIT, /* ... Only segment inner-most L4
|
|
|
|
|
* in hardware and all other
|
|
|
|
|
* headers in software.
|
|
|
|
|
*/
|
2014-11-05 01:06:54 +08:00
|
|
|
NETIF_F_GSO_TUNNEL_REMCSUM_BIT, /* ... TUNNEL with TSO & REMCSUM */
|
2016-06-03 02:05:43 +08:00
|
|
|
NETIF_F_GSO_SCTP_BIT, /* ... SCTP fragmentation */
|
2017-04-14 16:05:36 +08:00
|
|
|
NETIF_F_GSO_ESP_BIT, /* ... ESP with TSO */
|
net: accept UFO datagrams from tuntap and packet
Tuntap and similar devices can inject GSO packets. Accept type
VIRTIO_NET_HDR_GSO_UDP, even though not generating UFO natively.
Processes are expected to use feature negotiation such as TUNSETOFFLOAD
to detect supported offload types and refrain from injecting other
packets. This process breaks down with live migration: guest kernels
do not renegotiate flags, so destination hosts need to expose all
features that the source host does.
Partially revert the UFO removal from 182e0b6b5846~1..d9d30adf5677.
This patch introduces nearly(*) no new code to simplify verification.
It brings back verbatim tuntap UFO negotiation, VIRTIO_NET_HDR_GSO_UDP
insertion and software UFO segmentation.
It does not reinstate protocol stack support, hardware offload
(NETIF_F_UFO), SKB_GSO_UDP tunneling in SKB_GSO_SOFTWARE or reception
of VIRTIO_NET_HDR_GSO_UDP packets in tuntap.
To support SKB_GSO_UDP reappearing in the stack, also reinstate
logic in act_csum and openvswitch. Achieve equivalence with v4.13 HEAD
by squashing in commit 939912216fa8 ("net: skb_needs_check() removes
CHECKSUM_UNNECESSARY check for tx.") and reverting commit 8d63bee643f1
("net: avoid skb_warn_bad_offload false positives on UFO").
(*) To avoid having to bring back skb_shinfo(skb)->ip6_frag_id,
ipv6_proxy_select_ident is changed to return a __be32 and this is
assigned directly to the frag_hdr. Also, SKB_GSO_UDP is inserted
at the end of the enum to minimize code churn.
Tested
Booted a v4.13 guest kernel with QEMU. On a host kernel before this
patch `ethtool -k eth0` shows UFO disabled. After the patch, it is
enabled, same as on a v4.13 host kernel.
A UFO packet sent from the guest appears on the tap device:
host:
nc -l -p -u 8000 &
tcpdump -n -i tap0
guest:
dd if=/dev/zero of=payload.txt bs=1 count=2000
nc -u 192.16.1.1 8000 < payload.txt
Direct tap to tap transmission of VIRTIO_NET_HDR_GSO_UDP succeeds,
packets arriving fragmented:
./with_tap_pair.sh ./tap_send_ufo tap0 tap1
(from https://github.com/wdebruij/kerneltools/tree/master/tests)
Changes
v1 -> v2
- simplified set_offload change (review comment)
- documented test procedure
Link: http://lkml.kernel.org/r/<CAF=yD-LuUeDuL9YWPJD9ykOZ0QCjNeznPDr6whqZ9NGMNF12Mw@mail.gmail.com>
Fixes: fb652fdfe837 ("macvlan/macvtap: Remove NETIF_F_UFO advertisement.")
Reported-by: Michal Kubecek <mkubecek@suse.cz>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2017-11-21 23:22:25 +08:00
|
|
|
NETIF_F_GSO_UDP_BIT, /* ... UFO, deprecated except tuntap */
|
2018-04-27 01:42:21 +08:00
|
|
|
NETIF_F_GSO_UDP_L4_BIT, /* ... UDP payload GSO (not UFO) */
|
2013-03-07 21:21:51 +08:00
|
|
|
/**/NETIF_F_GSO_LAST = /* last bit, see GSO_MASK */
|
2018-04-27 01:42:21 +08:00
|
|
|
NETIF_F_GSO_UDP_L4_BIT,
|
2011-11-15 23:29:55 +08:00
|
|
|
|
|
|
|
|
NETIF_F_FCOE_CRC_BIT, /* FCoE CRC32 */
|
2015-12-15 03:19:41 +08:00
|
|
|
NETIF_F_SCTP_CRC_BIT, /* SCTP checksum offload */
|
2011-11-15 23:29:55 +08:00
|
|
|
NETIF_F_FCOE_MTU_BIT, /* Supports max FCoE MTU, 2158 bytes*/
|
|
|
|
|
NETIF_F_NTUPLE_BIT, /* N-tuple filters supported */
|
|
|
|
|
NETIF_F_RXHASH_BIT, /* Receive hashing offload */
|
|
|
|
|
NETIF_F_RXCSUM_BIT, /* Receive checksumming offload */
|
|
|
|
|
NETIF_F_NOCACHE_COPY_BIT, /* Use no-cache copyfromuser */
|
|
|
|
|
NETIF_F_LOOPBACK_BIT, /* Enable loopback */
|
2012-02-11 23:39:14 +08:00
|
|
|
NETIF_F_RXFCS_BIT, /* Append FCS to skb pkt data */
|
2012-02-11 23:39:45 +08:00
|
|
|
NETIF_F_RXALL_BIT, /* Receive errored frames too */
|
2013-05-02 16:31:32 +08:00
|
|
|
NETIF_F_HW_VLAN_STAG_TX_BIT, /* Transmit VLAN STAG HW acceleration */
|
|
|
|
|
NETIF_F_HW_VLAN_STAG_RX_BIT, /* Receive VLAN STAG HW acceleration */
|
|
|
|
|
NETIF_F_HW_VLAN_STAG_FILTER_BIT,/* Receive filtering on VLAN STAGs */
|
2013-11-07 01:54:46 +08:00
|
|
|
NETIF_F_HW_L2FW_DOFFLOAD_BIT, /* Allow L2 Forwarding in Hardware */
|
2011-11-15 23:29:55 +08:00
|
|
|
|
2016-02-17 13:17:37 +08:00
|
|
|
NETIF_F_HW_TC_BIT, /* Offload TC infrastructure */
|
2017-04-14 16:05:36 +08:00
|
|
|
NETIF_F_HW_ESP_BIT, /* Hardware ESP transformation offload */
|
|
|
|
|
NETIF_F_HW_ESP_TX_CSUM_BIT, /* ESP with TX checksum offload */
|
2017-07-21 18:49:28 +08:00
|
|
|
NETIF_F_RX_UDP_TUNNEL_PORT_BIT, /* Offload of RX port for UDP tunnels */
|
2018-04-30 15:16:14 +08:00
|
|
|
NETIF_F_HW_TLS_TX_BIT, /* Hardware TLS TX offload */
|
2018-07-13 19:33:36 +08:00
|
|
|
NETIF_F_HW_TLS_RX_BIT, /* Hardware TLS RX offload */
|
2016-02-17 13:17:37 +08:00
|
|
|
|
2017-12-16 16:09:40 +08:00
|
|
|
NETIF_F_GRO_HW_BIT, /* Hardware Generic receive offload */
|
2018-04-01 00:11:53 +08:00
|
|
|
NETIF_F_HW_TLS_RECORD_BIT, /* Offload TLS record */
|
2017-12-16 16:09:40 +08:00
|
|
|
|
2011-11-15 23:29:55 +08:00
|
|
|
/*
|
|
|
|
|
* Add your fresh new feature above and remember to update
|
|
|
|
|
* netdev_features_strings[] in net/core/ethtool.c and maybe
|
|
|
|
|
* some feature mask #defines below. Please also describe it
|
|
|
|
|
* in Documentation/networking/netdev-features.txt.
|
|
|
|
|
*/
|
2011-11-15 23:29:55 +08:00
|
|
|
|
2011-11-15 23:29:55 +08:00
|
|
|
/**/NETDEV_FEATURE_COUNT
|
|
|
|
|
};
|
2011-11-15 23:29:55 +08:00
|
|
|
|
2011-11-15 23:29:55 +08:00
|
|
|
/* copy'n'paste compression ;) */
|
|
|
|
|
#define __NETIF_F_BIT(bit) ((netdev_features_t)1 << (bit))
|
|
|
|
|
#define __NETIF_F(name) __NETIF_F_BIT(NETIF_F_##name##_BIT)
|
|
|
|
|
|
|
|
|
|
#define NETIF_F_FCOE_CRC __NETIF_F(FCOE_CRC)
|
|
|
|
|
#define NETIF_F_FCOE_MTU __NETIF_F(FCOE_MTU)
|
|
|
|
|
#define NETIF_F_FRAGLIST __NETIF_F(FRAGLIST)
|
|
|
|
|
#define NETIF_F_FSO __NETIF_F(FSO)
|
|
|
|
|
#define NETIF_F_GRO __NETIF_F(GRO)
|
2017-12-16 16:09:40 +08:00
|
|
|
#define NETIF_F_GRO_HW __NETIF_F(GRO_HW)
|
2011-11-15 23:29:55 +08:00
|
|
|
#define NETIF_F_GSO __NETIF_F(GSO)
|
|
|
|
|
#define NETIF_F_GSO_ROBUST __NETIF_F(GSO_ROBUST)
|
|
|
|
|
#define NETIF_F_HIGHDMA __NETIF_F(HIGHDMA)
|
|
|
|
|
#define NETIF_F_HW_CSUM __NETIF_F(HW_CSUM)
|
2013-04-19 10:04:27 +08:00
|
|
|
#define NETIF_F_HW_VLAN_CTAG_FILTER __NETIF_F(HW_VLAN_CTAG_FILTER)
|
|
|
|
|
#define NETIF_F_HW_VLAN_CTAG_RX __NETIF_F(HW_VLAN_CTAG_RX)
|
|
|
|
|
#define NETIF_F_HW_VLAN_CTAG_TX __NETIF_F(HW_VLAN_CTAG_TX)
|
2011-11-15 23:29:55 +08:00
|
|
|
#define NETIF_F_IP_CSUM __NETIF_F(IP_CSUM)
|
|
|
|
|
#define NETIF_F_IPV6_CSUM __NETIF_F(IPV6_CSUM)
|
|
|
|
|
#define NETIF_F_LLTX __NETIF_F(LLTX)
|
|
|
|
|
#define NETIF_F_LOOPBACK __NETIF_F(LOOPBACK)
|
|
|
|
|
#define NETIF_F_LRO __NETIF_F(LRO)
|
|
|
|
|
#define NETIF_F_NETNS_LOCAL __NETIF_F(NETNS_LOCAL)
|
|
|
|
|
#define NETIF_F_NOCACHE_COPY __NETIF_F(NOCACHE_COPY)
|
|
|
|
|
#define NETIF_F_NTUPLE __NETIF_F(NTUPLE)
|
|
|
|
|
#define NETIF_F_RXCSUM __NETIF_F(RXCSUM)
|
|
|
|
|
#define NETIF_F_RXHASH __NETIF_F(RXHASH)
|
2015-12-15 03:19:41 +08:00
|
|
|
#define NETIF_F_SCTP_CRC __NETIF_F(SCTP_CRC)
|
2011-11-15 23:29:55 +08:00
|
|
|
#define NETIF_F_SG __NETIF_F(SG)
|
|
|
|
|
#define NETIF_F_TSO6 __NETIF_F(TSO6)
|
|
|
|
|
#define NETIF_F_TSO_ECN __NETIF_F(TSO_ECN)
|
|
|
|
|
#define NETIF_F_TSO __NETIF_F(TSO)
|
|
|
|
|
#define NETIF_F_VLAN_CHALLENGED __NETIF_F(VLAN_CHALLENGED)
|
2012-02-11 23:39:14 +08:00
|
|
|
#define NETIF_F_RXFCS __NETIF_F(RXFCS)
|
2012-02-11 23:39:45 +08:00
|
|
|
#define NETIF_F_RXALL __NETIF_F(RXALL)
|
2013-03-16 12:47:55 +08:00
|
|
|
#define NETIF_F_GSO_GRE __NETIF_F(GSO_GRE)
|
2014-06-05 08:20:23 +08:00
|
|
|
#define NETIF_F_GSO_GRE_CSUM __NETIF_F(GSO_GRE_CSUM)
|
2016-05-19 00:06:10 +08:00
|
|
|
#define NETIF_F_GSO_IPXIP4 __NETIF_F(GSO_IPXIP4)
|
|
|
|
|
#define NETIF_F_GSO_IPXIP6 __NETIF_F(GSO_IPXIP6)
|
2013-03-16 12:47:55 +08:00
|
|
|
#define NETIF_F_GSO_UDP_TUNNEL __NETIF_F(GSO_UDP_TUNNEL)
|
2014-06-15 14:23:52 +08:00
|
|
|
#define NETIF_F_GSO_UDP_TUNNEL_CSUM __NETIF_F(GSO_UDP_TUNNEL_CSUM)
|
2016-04-11 09:44:51 +08:00
|
|
|
#define NETIF_F_TSO_MANGLEID __NETIF_F(TSO_MANGLEID)
|
2016-04-11 09:45:03 +08:00
|
|
|
#define NETIF_F_GSO_PARTIAL __NETIF_F(GSO_PARTIAL)
|
2014-11-05 01:06:54 +08:00
|
|
|
#define NETIF_F_GSO_TUNNEL_REMCSUM __NETIF_F(GSO_TUNNEL_REMCSUM)
|
2016-06-03 02:05:43 +08:00
|
|
|
#define NETIF_F_GSO_SCTP __NETIF_F(GSO_SCTP)
|
2017-04-14 16:05:36 +08:00
|
|
|
#define NETIF_F_GSO_ESP __NETIF_F(GSO_ESP)
|
net: accept UFO datagrams from tuntap and packet
Tuntap and similar devices can inject GSO packets. Accept type
VIRTIO_NET_HDR_GSO_UDP, even though not generating UFO natively.
Processes are expected to use feature negotiation such as TUNSETOFFLOAD
to detect supported offload types and refrain from injecting other
packets. This process breaks down with live migration: guest kernels
do not renegotiate flags, so destination hosts need to expose all
features that the source host does.
Partially revert the UFO removal from 182e0b6b5846~1..d9d30adf5677.
This patch introduces nearly(*) no new code to simplify verification.
It brings back verbatim tuntap UFO negotiation, VIRTIO_NET_HDR_GSO_UDP
insertion and software UFO segmentation.
It does not reinstate protocol stack support, hardware offload
(NETIF_F_UFO), SKB_GSO_UDP tunneling in SKB_GSO_SOFTWARE or reception
of VIRTIO_NET_HDR_GSO_UDP packets in tuntap.
To support SKB_GSO_UDP reappearing in the stack, also reinstate
logic in act_csum and openvswitch. Achieve equivalence with v4.13 HEAD
by squashing in commit 939912216fa8 ("net: skb_needs_check() removes
CHECKSUM_UNNECESSARY check for tx.") and reverting commit 8d63bee643f1
("net: avoid skb_warn_bad_offload false positives on UFO").
(*) To avoid having to bring back skb_shinfo(skb)->ip6_frag_id,
ipv6_proxy_select_ident is changed to return a __be32 and this is
assigned directly to the frag_hdr. Also, SKB_GSO_UDP is inserted
at the end of the enum to minimize code churn.
Tested
Booted a v4.13 guest kernel with QEMU. On a host kernel before this
patch `ethtool -k eth0` shows UFO disabled. After the patch, it is
enabled, same as on a v4.13 host kernel.
A UFO packet sent from the guest appears on the tap device:
host:
nc -l -p -u 8000 &
tcpdump -n -i tap0
guest:
dd if=/dev/zero of=payload.txt bs=1 count=2000
nc -u 192.16.1.1 8000 < payload.txt
Direct tap to tap transmission of VIRTIO_NET_HDR_GSO_UDP succeeds,
packets arriving fragmented:
./with_tap_pair.sh ./tap_send_ufo tap0 tap1
(from https://github.com/wdebruij/kerneltools/tree/master/tests)
Changes
v1 -> v2
- simplified set_offload change (review comment)
- documented test procedure
Link: http://lkml.kernel.org/r/<CAF=yD-LuUeDuL9YWPJD9ykOZ0QCjNeznPDr6whqZ9NGMNF12Mw@mail.gmail.com>
Fixes: fb652fdfe837 ("macvlan/macvtap: Remove NETIF_F_UFO advertisement.")
Reported-by: Michal Kubecek <mkubecek@suse.cz>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2017-11-21 23:22:25 +08:00
|
|
|
#define NETIF_F_GSO_UDP __NETIF_F(GSO_UDP)
|
2013-05-02 16:31:32 +08:00
|
|
|
#define NETIF_F_HW_VLAN_STAG_FILTER __NETIF_F(HW_VLAN_STAG_FILTER)
|
|
|
|
|
#define NETIF_F_HW_VLAN_STAG_RX __NETIF_F(HW_VLAN_STAG_RX)
|
|
|
|
|
#define NETIF_F_HW_VLAN_STAG_TX __NETIF_F(HW_VLAN_STAG_TX)
|
2013-11-07 01:54:46 +08:00
|
|
|
#define NETIF_F_HW_L2FW_DOFFLOAD __NETIF_F(HW_L2FW_DOFFLOAD)
|
2016-02-17 13:17:37 +08:00
|
|
|
#define NETIF_F_HW_TC __NETIF_F(HW_TC)
|
2017-04-14 16:05:36 +08:00
|
|
|
#define NETIF_F_HW_ESP __NETIF_F(HW_ESP)
|
|
|
|
|
#define NETIF_F_HW_ESP_TX_CSUM __NETIF_F(HW_ESP_TX_CSUM)
|
2017-07-21 18:49:28 +08:00
|
|
|
#define NETIF_F_RX_UDP_TUNNEL_PORT __NETIF_F(RX_UDP_TUNNEL_PORT)
|
2018-04-01 00:11:53 +08:00
|
|
|
#define NETIF_F_HW_TLS_RECORD __NETIF_F(HW_TLS_RECORD)
|
2018-04-27 01:42:21 +08:00
|
|
|
#define NETIF_F_GSO_UDP_L4 __NETIF_F(GSO_UDP_L4)
|
2018-04-30 15:16:14 +08:00
|
|
|
#define NETIF_F_HW_TLS_TX __NETIF_F(HW_TLS_TX)
|
2018-07-13 19:33:36 +08:00
|
|
|
#define NETIF_F_HW_TLS_RX __NETIF_F(HW_TLS_RX)
|
2011-11-15 23:29:55 +08:00
|
|
|
|
2015-11-03 23:15:59 +08:00
|
|
|
#define for_each_netdev_feature(mask_addr, bit) \
|
|
|
|
|
for_each_set_bit(bit, (unsigned long *)mask_addr, NETDEV_FEATURE_COUNT)
|
net/core: generic support for disabling netdev features down stack
There are some netdev features, which when disabled on an upper device,
such as a bonding master or a bridge, must be disabled and cannot be
re-enabled on underlying devices.
This is a rework of an earlier more heavy-handed appraoch, which simply
disables and prevents re-enabling of netdev features listed in a new
define in include/net/netdev_features.h, NETIF_F_UPPER_DISABLES. Any upper
device that disables a flag in that feature mask, the disabling will
propagate down the stack, and any lower device that has any upper device
with one of those flags disabled should not be able to enable said flag.
Initially, only LRO is included for proof of concept, and because this
code effectively does the same thing as dev_disable_lro(), though it will
also activate from the ethtool path, which was one of the goals here.
[root@dell-per730-01 ~]# ethtool -k bond0 |grep large
large-receive-offload: on
[root@dell-per730-01 ~]# ethtool -k p5p1 |grep large
large-receive-offload: on
[root@dell-per730-01 ~]# ethtool -K bond0 lro off
[root@dell-per730-01 ~]# ethtool -k bond0 |grep large
large-receive-offload: off
[root@dell-per730-01 ~]# ethtool -k p5p1 |grep large
large-receive-offload: off
dmesg dump:
[ 1033.277986] bond0: Disabling feature 0x0000000000008000 on lower dev p5p2.
[ 1034.067949] bnx2x 0000:06:00.1 p5p2: using MSI-X IRQs: sp 74 fp[0] 76 ... fp[7] 83
[ 1034.753612] bond0: Disabling feature 0x0000000000008000 on lower dev p5p1.
[ 1035.591019] bnx2x 0000:06:00.0 p5p1: using MSI-X IRQs: sp 62 fp[0] 64 ... fp[7] 71
This has been successfully tested with bnx2x, qlcnic and netxen network
cards as slaves in a bond interface. Turning LRO on or off on the master
also turns it on or off on each of the slaves, new slaves are added with
LRO in the same state as the master, and LRO can't be toggled on the
slaves.
Also, this should largely remove the need for dev_disable_lro(), and most,
if not all, of its call sites can be replaced by simply making sure
NETIF_F_LRO isn't included in the relevant device's feature flags.
Note that this patch is driven by bug reports from users saying it was
confusing that bonds and slaves had different settings for the same
features, and while it won't be 100% in sync if a lower device doesn't
support a feature like LRO, I think this is a good step in the right
direction.
CC: "David S. Miller" <davem@davemloft.net>
CC: Eric Dumazet <edumazet@google.com>
CC: Jay Vosburgh <j.vosburgh@gmail.com>
CC: Veaceslav Falico <vfalico@gmail.com>
CC: Andy Gospodarek <gospo@cumulusnetworks.com>
CC: Jiri Pirko <jiri@resnulli.us>
CC: Nikolay Aleksandrov <razor@blackwall.org>
CC: Michal Kubecek <mkubecek@suse.cz>
CC: Alexander Duyck <alexander.duyck@gmail.com>
CC: netdev@vger.kernel.org
Signed-off-by: Jarod Wilson <jarod@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2015-11-03 10:55:59 +08:00
|
|
|
|
2011-11-15 23:29:55 +08:00
|
|
|
/* Features valid for ethtool to change */
|
|
|
|
|
/* = all defined minus driver/device-class-related */
|
|
|
|
|
#define NETIF_F_NEVER_CHANGE (NETIF_F_VLAN_CHALLENGED | \
|
|
|
|
|
NETIF_F_LLTX | NETIF_F_NETNS_LOCAL)
|
2011-11-15 23:29:55 +08:00
|
|
|
|
|
|
|
|
/* remember that ((t)1 << t_BITS) is undefined in C99 */
|
|
|
|
|
#define NETIF_F_ETHTOOL_BITS ((__NETIF_F_BIT(NETDEV_FEATURE_COUNT - 1) | \
|
|
|
|
|
(__NETIF_F_BIT(NETDEV_FEATURE_COUNT - 1) - 1)) & \
|
|
|
|
|
~NETIF_F_NEVER_CHANGE)
|
|
|
|
|
|
|
|
|
|
/* Segmentation offload feature mask */
|
|
|
|
|
#define NETIF_F_GSO_MASK (__NETIF_F_BIT(NETIF_F_GSO_LAST + 1) - \
|
|
|
|
|
__NETIF_F_BIT(NETIF_F_GSO_SHIFT))
|
2011-11-15 23:29:55 +08:00
|
|
|
|
2015-12-15 03:19:44 +08:00
|
|
|
/* List of IP checksum features. Note that NETIF_F_ HW_CSUM should not be
|
2015-12-15 03:19:43 +08:00
|
|
|
* set in features when NETIF_F_IP_CSUM or NETIF_F_IPV6_CSUM are set--
|
|
|
|
|
* this would be contradictory
|
|
|
|
|
*/
|
2015-12-15 03:19:44 +08:00
|
|
|
#define NETIF_F_CSUM_MASK (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | \
|
|
|
|
|
NETIF_F_HW_CSUM)
|
2011-11-15 23:29:55 +08:00
|
|
|
|
2016-04-15 05:04:34 +08:00
|
|
|
#define NETIF_F_ALL_TSO (NETIF_F_TSO | NETIF_F_TSO6 | \
|
|
|
|
|
NETIF_F_TSO_ECN | NETIF_F_TSO_MANGLEID)
|
2011-11-15 23:29:55 +08:00
|
|
|
|
|
|
|
|
#define NETIF_F_ALL_FCOE (NETIF_F_FCOE_CRC | NETIF_F_FCOE_MTU | \
|
|
|
|
|
NETIF_F_FSO)
|
|
|
|
|
|
2016-04-20 02:02:19 +08:00
|
|
|
/* List of features with software fallbacks. */
|
2017-07-03 22:31:57 +08:00
|
|
|
#define NETIF_F_GSO_SOFTWARE (NETIF_F_ALL_TSO | \
|
2016-06-03 02:05:43 +08:00
|
|
|
NETIF_F_GSO_SCTP)
|
2016-04-20 02:02:19 +08:00
|
|
|
|
2011-11-15 23:29:55 +08:00
|
|
|
/*
|
|
|
|
|
* If one device supports one of these features, then enable them
|
|
|
|
|
* for all in netdev_increment_features.
|
|
|
|
|
*/
|
|
|
|
|
#define NETIF_F_ONE_FOR_ALL (NETIF_F_GSO_SOFTWARE | NETIF_F_GSO_ROBUST | \
|
|
|
|
|
NETIF_F_SG | NETIF_F_HIGHDMA | \
|
2015-05-11 00:48:07 +08:00
|
|
|
NETIF_F_FRAGLIST | NETIF_F_VLAN_CHALLENGED)
|
2015-01-30 14:40:11 +08:00
|
|
|
|
2011-11-15 23:29:55 +08:00
|
|
|
/*
|
|
|
|
|
* If one device doesn't support one of these features, then disable it
|
|
|
|
|
* for all in netdev_increment_features.
|
|
|
|
|
*/
|
|
|
|
|
#define NETIF_F_ALL_FOR_ALL (NETIF_F_NOCACHE_COPY | NETIF_F_FSO)
|
|
|
|
|
|
net/core: generic support for disabling netdev features down stack
There are some netdev features, which when disabled on an upper device,
such as a bonding master or a bridge, must be disabled and cannot be
re-enabled on underlying devices.
This is a rework of an earlier more heavy-handed appraoch, which simply
disables and prevents re-enabling of netdev features listed in a new
define in include/net/netdev_features.h, NETIF_F_UPPER_DISABLES. Any upper
device that disables a flag in that feature mask, the disabling will
propagate down the stack, and any lower device that has any upper device
with one of those flags disabled should not be able to enable said flag.
Initially, only LRO is included for proof of concept, and because this
code effectively does the same thing as dev_disable_lro(), though it will
also activate from the ethtool path, which was one of the goals here.
[root@dell-per730-01 ~]# ethtool -k bond0 |grep large
large-receive-offload: on
[root@dell-per730-01 ~]# ethtool -k p5p1 |grep large
large-receive-offload: on
[root@dell-per730-01 ~]# ethtool -K bond0 lro off
[root@dell-per730-01 ~]# ethtool -k bond0 |grep large
large-receive-offload: off
[root@dell-per730-01 ~]# ethtool -k p5p1 |grep large
large-receive-offload: off
dmesg dump:
[ 1033.277986] bond0: Disabling feature 0x0000000000008000 on lower dev p5p2.
[ 1034.067949] bnx2x 0000:06:00.1 p5p2: using MSI-X IRQs: sp 74 fp[0] 76 ... fp[7] 83
[ 1034.753612] bond0: Disabling feature 0x0000000000008000 on lower dev p5p1.
[ 1035.591019] bnx2x 0000:06:00.0 p5p1: using MSI-X IRQs: sp 62 fp[0] 64 ... fp[7] 71
This has been successfully tested with bnx2x, qlcnic and netxen network
cards as slaves in a bond interface. Turning LRO on or off on the master
also turns it on or off on each of the slaves, new slaves are added with
LRO in the same state as the master, and LRO can't be toggled on the
slaves.
Also, this should largely remove the need for dev_disable_lro(), and most,
if not all, of its call sites can be replaced by simply making sure
NETIF_F_LRO isn't included in the relevant device's feature flags.
Note that this patch is driven by bug reports from users saying it was
confusing that bonds and slaves had different settings for the same
features, and while it won't be 100% in sync if a lower device doesn't
support a feature like LRO, I think this is a good step in the right
direction.
CC: "David S. Miller" <davem@davemloft.net>
CC: Eric Dumazet <edumazet@google.com>
CC: Jay Vosburgh <j.vosburgh@gmail.com>
CC: Veaceslav Falico <vfalico@gmail.com>
CC: Andy Gospodarek <gospo@cumulusnetworks.com>
CC: Jiri Pirko <jiri@resnulli.us>
CC: Nikolay Aleksandrov <razor@blackwall.org>
CC: Michal Kubecek <mkubecek@suse.cz>
CC: Alexander Duyck <alexander.duyck@gmail.com>
CC: netdev@vger.kernel.org
Signed-off-by: Jarod Wilson <jarod@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2015-11-03 10:55:59 +08:00
|
|
|
/*
|
|
|
|
|
* If upper/master device has these features disabled, they must be disabled
|
|
|
|
|
* on all lower/slave devices as well.
|
|
|
|
|
*/
|
|
|
|
|
#define NETIF_F_UPPER_DISABLES NETIF_F_LRO
|
|
|
|
|
|
2011-11-15 23:29:55 +08:00
|
|
|
/* changeable features with no special hardware requirements */
|
|
|
|
|
#define NETIF_F_SOFT_FEATURES (NETIF_F_GSO | NETIF_F_GRO)
|
|
|
|
|
|
2014-03-28 10:14:49 +08:00
|
|
|
#define NETIF_F_VLAN_FEATURES (NETIF_F_HW_VLAN_CTAG_FILTER | \
|
|
|
|
|
NETIF_F_HW_VLAN_CTAG_RX | \
|
|
|
|
|
NETIF_F_HW_VLAN_CTAG_TX | \
|
|
|
|
|
NETIF_F_HW_VLAN_STAG_FILTER | \
|
|
|
|
|
NETIF_F_HW_VLAN_STAG_RX | \
|
|
|
|
|
NETIF_F_HW_VLAN_STAG_TX)
|
|
|
|
|
|
2014-07-18 06:14:15 +08:00
|
|
|
#define NETIF_F_GSO_ENCAP_ALL (NETIF_F_GSO_GRE | \
|
|
|
|
|
NETIF_F_GSO_GRE_CSUM | \
|
2016-05-19 00:06:10 +08:00
|
|
|
NETIF_F_GSO_IPXIP4 | \
|
|
|
|
|
NETIF_F_GSO_IPXIP6 | \
|
2014-07-18 06:14:15 +08:00
|
|
|
NETIF_F_GSO_UDP_TUNNEL | \
|
2014-11-06 07:27:48 +08:00
|
|
|
NETIF_F_GSO_UDP_TUNNEL_CSUM)
|
2014-07-18 06:14:15 +08:00
|
|
|
|
2011-11-15 23:29:55 +08:00
|
|
|
#endif /* _LINUX_NETDEV_FEATURES_H */
|