From 0c19f846d582af919db66a5914a0189f9f92c936 Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Tue, 21 Nov 2017 10:22:25 -0500 Subject: 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/ Fixes: fb652fdfe837 ("macvlan/macvtap: Remove NETIF_F_UFO advertisement.") Reported-by: Michal Kubecek Signed-off-by: Willem de Bruijn Acked-by: Jason Wang Signed-off-by: David S. Miller --- include/linux/netdev_features.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux/netdev_features.h') diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index dc8b4896b77b..b1b0ca7ccb2b 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -54,8 +54,9 @@ enum { NETIF_F_GSO_TUNNEL_REMCSUM_BIT, /* ... TUNNEL with TSO & REMCSUM */ NETIF_F_GSO_SCTP_BIT, /* ... SCTP fragmentation */ NETIF_F_GSO_ESP_BIT, /* ... ESP with TSO */ + NETIF_F_GSO_UDP_BIT, /* ... UFO, deprecated except tuntap */ /**/NETIF_F_GSO_LAST = /* last bit, see GSO_MASK */ - NETIF_F_GSO_ESP_BIT, + NETIF_F_GSO_UDP_BIT, NETIF_F_FCOE_CRC_BIT, /* FCoE CRC32 */ NETIF_F_SCTP_CRC_BIT, /* SCTP checksum offload */ @@ -132,6 +133,7 @@ enum { #define NETIF_F_GSO_TUNNEL_REMCSUM __NETIF_F(GSO_TUNNEL_REMCSUM) #define NETIF_F_GSO_SCTP __NETIF_F(GSO_SCTP) #define NETIF_F_GSO_ESP __NETIF_F(GSO_ESP) +#define NETIF_F_GSO_UDP __NETIF_F(GSO_UDP) #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) -- cgit v1.2.3 From fb1f5f79ae96331a0201b4080d34f3bc3b5c0b1d Mon Sep 17 00:00:00 2001 From: Michael Chan Date: Sat, 16 Dec 2017 03:09:40 -0500 Subject: net: Introduce NETIF_F_GRO_HW. Introduce NETIF_F_GRO_HW feature flag for NICs that support hardware GRO. With this flag, we can now independently turn on or off hardware GRO when GRO is on. Previously, drivers were using NETIF_F_GRO to control hardware GRO and so it cannot be independently turned on or off without affecting GRO. Hardware GRO (just like GRO) guarantees that packets can be re-segmented by TSO/GSO to reconstruct the original packet stream. Logically, GRO_HW should depend on GRO since it a subset, but we will let individual drivers enforce this dependency as they see fit. Since NETIF_F_GRO is not propagated between upper and lower devices, NETIF_F_GRO_HW should follow suit since it is a subset of GRO. In other words, a lower device can independent have GRO/GRO_HW enabled or disabled and no feature propagation is required. This will preserve the current GRO behavior. This can be changed later if we decide to propagate GRO/ GRO_HW/RXCSUM from upper to lower devices. Cc: Ariel Elior Cc: everest-linux-l2@cavium.com Signed-off-by: Michael Chan Acked-by: Alexander Duyck Signed-off-by: David S. Miller --- Documentation/networking/netdev-features.txt | 9 +++++++++ include/linux/netdev_features.h | 3 +++ net/core/dev.c | 12 ++++++++++++ net/core/ethtool.c | 1 + 4 files changed, 25 insertions(+) (limited to 'include/linux/netdev_features.h') diff --git a/Documentation/networking/netdev-features.txt b/Documentation/networking/netdev-features.txt index 7413eb05223b..c77f9d57eb91 100644 --- a/Documentation/networking/netdev-features.txt +++ b/Documentation/networking/netdev-features.txt @@ -163,3 +163,12 @@ This requests that the NIC receive all possible frames, including errored frames (such as bad FCS, etc). This can be helpful when sniffing a link with bad packets on it. Some NICs may receive more packets if also put into normal PROMISC mode. + +* rx-gro-hw + +This requests that the NIC enables Hardware GRO (generic receive offload). +Hardware GRO is basically the exact reverse of TSO, and is generally +stricter than Hardware LRO. A packet stream merged by Hardware GRO must +be re-segmentable by GSO or TSO back to the exact original packet stream. +Hardware GRO is dependent on RXCSUM since every packet successfully merged +by hardware must also have the checksum verified by hardware. diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index b1b0ca7ccb2b..db84c516bcfb 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -78,6 +78,8 @@ enum { NETIF_F_HW_ESP_TX_CSUM_BIT, /* ESP with TX checksum offload */ NETIF_F_RX_UDP_TUNNEL_PORT_BIT, /* Offload of RX port for UDP tunnels */ + NETIF_F_GRO_HW_BIT, /* Hardware Generic receive offload */ + /* * Add your fresh new feature above and remember to update * netdev_features_strings[] in net/core/ethtool.c and maybe @@ -97,6 +99,7 @@ enum { #define NETIF_F_FRAGLIST __NETIF_F(FRAGLIST) #define NETIF_F_FSO __NETIF_F(FSO) #define NETIF_F_GRO __NETIF_F(GRO) +#define NETIF_F_GRO_HW __NETIF_F(GRO_HW) #define NETIF_F_GSO __NETIF_F(GSO) #define NETIF_F_GSO_ROBUST __NETIF_F(GSO_ROBUST) #define NETIF_F_HIGHDMA __NETIF_F(HIGHDMA) diff --git a/net/core/dev.c b/net/core/dev.c index b0eee49a2489..4b43f5dcabcd 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -7424,6 +7424,18 @@ static netdev_features_t netdev_fix_features(struct net_device *dev, features &= ~dev->gso_partial_features; } + if (!(features & NETIF_F_RXCSUM)) { + /* NETIF_F_GRO_HW implies doing RXCSUM since every packet + * successfully merged by hardware must also have the + * checksum verified by hardware. If the user does not + * want to enable RXCSUM, logically, we should disable GRO_HW. + */ + if (features & NETIF_F_GRO_HW) { + netdev_dbg(dev, "Dropping NETIF_F_GRO_HW since no RXCSUM feature.\n"); + features &= ~NETIF_F_GRO_HW; + } + } + return features; } diff --git a/net/core/ethtool.c b/net/core/ethtool.c index f8fcf450a36e..50a79203043b 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -73,6 +73,7 @@ static const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN] [NETIF_F_LLTX_BIT] = "tx-lockless", [NETIF_F_NETNS_LOCAL_BIT] = "netns-local", [NETIF_F_GRO_BIT] = "rx-gro", + [NETIF_F_GRO_HW_BIT] = "rx-gro-hw", [NETIF_F_LRO_BIT] = "rx-lro", [NETIF_F_TSO_BIT] = "tx-tcp-segmentation", -- cgit v1.2.3