| Message ID | 1463355755-3481375-3-git-send-email-tom@herbertland.com |
|---|---|
| State | Changes Requested, archived |
| Delegated to: | David Miller |
| Headers | show |
On Sun, 2016-05-15 at 16:42 -0700, Tom Herbert wrote: > This patch defines two new GSO definitions SKB_GSO_IPXIP4 and > SKB_GSO_IPXIP6 along with corresponding NETIF_F_GSO_IPXIP4 and > NETIF_F_GSO_IPXIP6. These are used to described IP in IP > tunnel and what the outer protocol is. The inner protocol > can be deduced from other GSO types (e.g. SKB_GSO_TCPV4 and > SKB_GSO_TCPV6). The GSO types of SKB_GSO_IPIP and SKB_GSO_SIT > are removed (these are both instances of SKB_GSO_IPXIP4). > SKB_GSO_IPXIP6 will be used when support for GSO with IP > encapsulation over IPv6 is added. > > Signed-off-by: Tom Herbert <tom@herbertland.com> Acked-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com> For the Intel driver changes... > --- > drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c | 5 ++--- > drivers/net/ethernet/broadcom/bnxt/bnxt.c | 4 ++-- > drivers/net/ethernet/intel/i40e/i40e_main.c | 3 +-- > drivers/net/ethernet/intel/i40e/i40e_txrx.c | 3 +-- > drivers/net/ethernet/intel/i40evf/i40e_txrx.c | 3 +-- > drivers/net/ethernet/intel/i40evf/i40evf_main.c | 3 +-- > drivers/net/ethernet/intel/igb/igb_main.c | 3 +-- > drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 3 +-- > drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c | 3 +-- > include/linux/netdev_features.h | 12 ++++++------ > include/linux/netdevice.h | 4 ++-- > include/linux/skbuff.h | 4 ++-- > net/core/ethtool.c | 4 ++-- > net/ipv4/af_inet.c | 2 +- > net/ipv4/ipip.c | 2 +- > net/ipv6/ip6_offload.c | 4 ++-- > net/ipv6/sit.c | 4 ++-- > net/netfilter/ipvs/ip_vs_xmit.c | 17 +++++++---------- > 18 files changed, 36 insertions(+), 47 deletions(-)
On Sun, May 15, 2016 at 4:42 PM, Tom Herbert <tom@herbertland.com> wrote: > This patch defines two new GSO definitions SKB_GSO_IPXIP4 and > SKB_GSO_IPXIP6 along with corresponding NETIF_F_GSO_IPXIP4 and > NETIF_F_GSO_IPXIP6. These are used to described IP in IP > tunnel and what the outer protocol is. The inner protocol > can be deduced from other GSO types (e.g. SKB_GSO_TCPV4 and > SKB_GSO_TCPV6). The GSO types of SKB_GSO_IPIP and SKB_GSO_SIT > are removed (these are both instances of SKB_GSO_IPXIP4). > SKB_GSO_IPXIP6 will be used when support for GSO with IP > encapsulation over IPv6 is added. > > Signed-off-by: Tom Herbert <tom@herbertland.com> > --- > drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c | 5 ++--- > drivers/net/ethernet/broadcom/bnxt/bnxt.c | 4 ++-- > drivers/net/ethernet/intel/i40e/i40e_main.c | 3 +-- > drivers/net/ethernet/intel/i40e/i40e_txrx.c | 3 +-- > drivers/net/ethernet/intel/i40evf/i40e_txrx.c | 3 +-- > drivers/net/ethernet/intel/i40evf/i40evf_main.c | 3 +-- > drivers/net/ethernet/intel/igb/igb_main.c | 3 +-- > drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 3 +-- > drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c | 3 +-- > include/linux/netdev_features.h | 12 ++++++------ > include/linux/netdevice.h | 4 ++-- > include/linux/skbuff.h | 4 ++-- > net/core/ethtool.c | 4 ++-- > net/ipv4/af_inet.c | 2 +- > net/ipv4/ipip.c | 2 +- > net/ipv6/ip6_offload.c | 4 ++-- > net/ipv6/sit.c | 4 ++-- > net/netfilter/ipvs/ip_vs_xmit.c | 17 +++++++---------- > 18 files changed, 36 insertions(+), 47 deletions(-) It looks like you missed drivers/net/ethernet/intel/igb/netdev.c. If you don't get it then it will break the build. Thanks. - Alex
On Sun, May 15, 2016 at 4:42 PM, Tom Herbert <tom@herbertland.com> wrote: > This patch defines two new GSO definitions SKB_GSO_IPXIP4 and > SKB_GSO_IPXIP6 along with corresponding NETIF_F_GSO_IPXIP4 and > NETIF_F_GSO_IPXIP6. These are used to described IP in IP > tunnel and what the outer protocol is. The inner protocol > can be deduced from other GSO types (e.g. SKB_GSO_TCPV4 and > SKB_GSO_TCPV6). The GSO types of SKB_GSO_IPIP and SKB_GSO_SIT > are removed (these are both instances of SKB_GSO_IPXIP4). > SKB_GSO_IPXIP6 will be used when support for GSO with IP > encapsulation over IPv6 is added. > > Signed-off-by: Tom Herbert <tom@herbertland.com> > --- > drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c | 5 ++--- > drivers/net/ethernet/broadcom/bnxt/bnxt.c | 4 ++-- > drivers/net/ethernet/intel/i40e/i40e_main.c | 3 +-- > drivers/net/ethernet/intel/i40e/i40e_txrx.c | 3 +-- > drivers/net/ethernet/intel/i40evf/i40e_txrx.c | 3 +-- > drivers/net/ethernet/intel/i40evf/i40evf_main.c | 3 +-- > drivers/net/ethernet/intel/igb/igb_main.c | 3 +-- > drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 3 +-- > drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c | 3 +-- > include/linux/netdev_features.h | 12 ++++++------ > include/linux/netdevice.h | 4 ++-- > include/linux/skbuff.h | 4 ++-- > net/core/ethtool.c | 4 ++-- > net/ipv4/af_inet.c | 2 +- > net/ipv4/ipip.c | 2 +- > net/ipv6/ip6_offload.c | 4 ++-- > net/ipv6/sit.c | 4 ++-- > net/netfilter/ipvs/ip_vs_xmit.c | 17 +++++++---------- > 18 files changed, 36 insertions(+), 47 deletions(-) > <...> > diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c > index 5a0dca3..bfc1e94 100644 > --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c > +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c > @@ -6311,7 +6311,7 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) > dev->hw_features = NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | NETIF_F_SG | > NETIF_F_TSO | NETIF_F_TSO6 | > NETIF_F_GSO_UDP_TUNNEL | NETIF_F_GSO_GRE | > - NETIF_F_GSO_IPIP | NETIF_F_GSO_SIT | > + NETIF_F_GSO_IPXIP4 | > NETIF_F_GSO_UDP_TUNNEL_CSUM | NETIF_F_GSO_GRE_CSUM | > NETIF_F_GSO_PARTIAL | NETIF_F_RXHASH | > NETIF_F_RXCSUM | NETIF_F_LRO | NETIF_F_GRO; > @@ -6321,7 +6321,7 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) > NETIF_F_TSO | NETIF_F_TSO6 | > NETIF_F_GSO_UDP_TUNNEL | NETIF_F_GSO_GRE | > NETIF_F_GSO_UDP_TUNNEL_CSUM | NETIF_F_GSO_GRE_CSUM | > - NETIF_F_GSO_IPIP | NETIF_F_GSO_SIT | > + NETIF_F_GSO_IPXIP4; > NETIF_F_GSO_PARTIAL; > dev->gso_partial_features = NETIF_F_GSO_UDP_TUNNEL_CSUM | > NETIF_F_GSO_GRE_CSUM; This bit here is breaking the build as well. It should be a '|' following the IPXIP4, not a ';'. As it currently is it is generating the following error: drivers/net/ethernet/broadcom/bnxt/bnxt.c: In function ‘bnxt_init_one’: include/linux/netdev_features.h:88:28: warning: statement with no effect [-Wunused-value] #define __NETIF_F_BIT(bit) ((netdev_features_t)1 << (bit)) ^ include/linux/netdev_features.h:89:26: note: in expansion of macro ‘__NETIF_F_BIT’ #define __NETIF_F(name) __NETIF_F_BIT(NETIF_F_##name##_BIT) ^ include/linux/netdev_features.h:129:30: note: in expansion of macro ‘__NETIF_F’ #define NETIF_F_GSO_PARTIAL __NETIF_F(GSO_PARTIAL) ^ drivers/net/ethernet/broadcom/bnxt/bnxt.c:6325:4: note: in expansion of macro ‘NETIF_F_GSO_PARTIAL’ NETIF_F_GSO_PARTIAL; ^ - Alex
On Sun, May 15, 2016 at 4:42 PM, Tom Herbert <tom@herbertland.com> wrote: > This patch defines two new GSO definitions SKB_GSO_IPXIP4 and > SKB_GSO_IPXIP6 along with corresponding NETIF_F_GSO_IPXIP4 and > NETIF_F_GSO_IPXIP6. These are used to described IP in IP > tunnel and what the outer protocol is. The inner protocol > can be deduced from other GSO types (e.g. SKB_GSO_TCPV4 and > SKB_GSO_TCPV6). The GSO types of SKB_GSO_IPIP and SKB_GSO_SIT > are removed (these are both instances of SKB_GSO_IPXIP4). > SKB_GSO_IPXIP6 will be used when support for GSO with IP > encapsulation over IPv6 is added. > > Signed-off-by: Tom Herbert <tom@herbertland.com> > --- > drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c | 5 ++--- > drivers/net/ethernet/broadcom/bnxt/bnxt.c | 4 ++-- > drivers/net/ethernet/intel/i40e/i40e_main.c | 3 +-- > drivers/net/ethernet/intel/i40e/i40e_txrx.c | 3 +-- > drivers/net/ethernet/intel/i40evf/i40e_txrx.c | 3 +-- > drivers/net/ethernet/intel/i40evf/i40evf_main.c | 3 +-- > drivers/net/ethernet/intel/igb/igb_main.c | 3 +-- > drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 3 +-- > drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c | 3 +-- > include/linux/netdev_features.h | 12 ++++++------ > include/linux/netdevice.h | 4 ++-- > include/linux/skbuff.h | 4 ++-- > net/core/ethtool.c | 4 ++-- > net/ipv4/af_inet.c | 2 +- > net/ipv4/ipip.c | 2 +- > net/ipv6/ip6_offload.c | 4 ++-- > net/ipv6/sit.c | 4 ++-- > net/netfilter/ipvs/ip_vs_xmit.c | 17 +++++++---------- > 18 files changed, 36 insertions(+), 47 deletions(-) > <...> > diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c > index 2172769..808d48f 100644 > --- a/drivers/net/ethernet/intel/igb/igb_main.c > +++ b/drivers/net/ethernet/intel/igb/igb_main.c > @@ -2418,8 +2418,7 @@ static int igb_probe(struct pci_dev *pdev, const struct pci_device_id *ent) > > #define IGB_GSO_PARTIAL_FEATURES (NETIF_F_GSO_GRE | \ > NETIF_F_GSO_GRE_CSUM | \ > - NETIF_F_GSO_IPIP | \ > - NETIF_F_GSO_SIT | \ > + SKB_GSO_IPXIP4 | \ > NETIF_F_GSO_UDP_TUNNEL | \ > NETIF_F_GSO_UDP_TUNNEL_CSUM) > Sorry but this is yet another bug. It should be NETIF_F_GSO_IPXIP4, not SKB_GSO_IPXIP4. So we are up to at least 3 items that need to be addressed in this patch. 1. igbvf/netdev.c also has a reference to NETIF_F_GSO_IPIP/NETIF_F_GSO_SIT. 2. bnxt needs a '|' instead of a ';' to avoid statement with no effect. 3. Use of SKB_GSO_IPXIP4 in igb/igb_main.c which should have been NETIF_F_GSO_IPXIP4. I think that is everything for this patch. I'll be certain once I can do some performance testing to determine if the hardware offloads for the Intel parts are working correctly. Thanks. - Alex
On Mon, May 16, 2016 at 9:32 AM, Alexander Duyck <alexander.duyck@gmail.com> wrote: > On Sun, May 15, 2016 at 4:42 PM, Tom Herbert <tom@herbertland.com> wrote: >> This patch defines two new GSO definitions SKB_GSO_IPXIP4 and >> SKB_GSO_IPXIP6 along with corresponding NETIF_F_GSO_IPXIP4 and >> NETIF_F_GSO_IPXIP6. These are used to described IP in IP >> tunnel and what the outer protocol is. The inner protocol >> can be deduced from other GSO types (e.g. SKB_GSO_TCPV4 and >> SKB_GSO_TCPV6). The GSO types of SKB_GSO_IPIP and SKB_GSO_SIT >> are removed (these are both instances of SKB_GSO_IPXIP4). >> SKB_GSO_IPXIP6 will be used when support for GSO with IP >> encapsulation over IPv6 is added. >> >> Signed-off-by: Tom Herbert <tom@herbertland.com> >> --- >> drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c | 5 ++--- >> drivers/net/ethernet/broadcom/bnxt/bnxt.c | 4 ++-- >> drivers/net/ethernet/intel/i40e/i40e_main.c | 3 +-- >> drivers/net/ethernet/intel/i40e/i40e_txrx.c | 3 +-- >> drivers/net/ethernet/intel/i40evf/i40e_txrx.c | 3 +-- >> drivers/net/ethernet/intel/i40evf/i40evf_main.c | 3 +-- >> drivers/net/ethernet/intel/igb/igb_main.c | 3 +-- >> drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 3 +-- >> drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c | 3 +-- >> include/linux/netdev_features.h | 12 ++++++------ >> include/linux/netdevice.h | 4 ++-- >> include/linux/skbuff.h | 4 ++-- >> net/core/ethtool.c | 4 ++-- >> net/ipv4/af_inet.c | 2 +- >> net/ipv4/ipip.c | 2 +- >> net/ipv6/ip6_offload.c | 4 ++-- >> net/ipv6/sit.c | 4 ++-- >> net/netfilter/ipvs/ip_vs_xmit.c | 17 +++++++---------- >> 18 files changed, 36 insertions(+), 47 deletions(-) > > It looks like you missed drivers/net/ethernet/intel/igb/netdev.c. If > you don't get it then it will break the build. > I don't see file that in betdev branch, maybe it's new? Tom > Thanks. > > - Alex
On Mon, May 16, 2016 at 11:07 AM, Tom Herbert <tom@herbertland.com> wrote: > On Mon, May 16, 2016 at 9:32 AM, Alexander Duyck > <alexander.duyck@gmail.com> wrote: >> On Sun, May 15, 2016 at 4:42 PM, Tom Herbert <tom@herbertland.com> wrote: >>> This patch defines two new GSO definitions SKB_GSO_IPXIP4 and >>> SKB_GSO_IPXIP6 along with corresponding NETIF_F_GSO_IPXIP4 and >>> NETIF_F_GSO_IPXIP6. These are used to described IP in IP >>> tunnel and what the outer protocol is. The inner protocol >>> can be deduced from other GSO types (e.g. SKB_GSO_TCPV4 and >>> SKB_GSO_TCPV6). The GSO types of SKB_GSO_IPIP and SKB_GSO_SIT >>> are removed (these are both instances of SKB_GSO_IPXIP4). >>> SKB_GSO_IPXIP6 will be used when support for GSO with IP >>> encapsulation over IPv6 is added. >>> >>> Signed-off-by: Tom Herbert <tom@herbertland.com> >>> --- >>> drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c | 5 ++--- >>> drivers/net/ethernet/broadcom/bnxt/bnxt.c | 4 ++-- >>> drivers/net/ethernet/intel/i40e/i40e_main.c | 3 +-- >>> drivers/net/ethernet/intel/i40e/i40e_txrx.c | 3 +-- >>> drivers/net/ethernet/intel/i40evf/i40e_txrx.c | 3 +-- >>> drivers/net/ethernet/intel/i40evf/i40evf_main.c | 3 +-- >>> drivers/net/ethernet/intel/igb/igb_main.c | 3 +-- >>> drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 3 +-- >>> drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c | 3 +-- >>> include/linux/netdev_features.h | 12 ++++++------ >>> include/linux/netdevice.h | 4 ++-- >>> include/linux/skbuff.h | 4 ++-- >>> net/core/ethtool.c | 4 ++-- >>> net/ipv4/af_inet.c | 2 +- >>> net/ipv4/ipip.c | 2 +- >>> net/ipv6/ip6_offload.c | 4 ++-- >>> net/ipv6/sit.c | 4 ++-- >>> net/netfilter/ipvs/ip_vs_xmit.c | 17 +++++++---------- >>> 18 files changed, 36 insertions(+), 47 deletions(-) >> >> It looks like you missed drivers/net/ethernet/intel/igb/netdev.c. If >> you don't get it then it will break the build. >> > > I don't see file that in betdev branch, maybe it's new? Nope, it has been there for a while. It got patched to support IPIP and SIT tunnels in the same patch that updated igb/igb_main.c. I am also looking into the other patches now. It looks like something broke hardware offloads again as I am only getting .9 Mb/s for IPv6 based GRE tunnels with your patches applied. I'm trying to bisect it now. - Alex
On Mon, May 16, 2016 at 11:13 AM, Alexander Duyck <alexander.duyck@gmail.com> wrote: > On Mon, May 16, 2016 at 11:07 AM, Tom Herbert <tom@herbertland.com> wrote: >> On Mon, May 16, 2016 at 9:32 AM, Alexander Duyck >> <alexander.duyck@gmail.com> wrote: >>> On Sun, May 15, 2016 at 4:42 PM, Tom Herbert <tom@herbertland.com> wrote: >>>> This patch defines two new GSO definitions SKB_GSO_IPXIP4 and >>>> SKB_GSO_IPXIP6 along with corresponding NETIF_F_GSO_IPXIP4 and >>>> NETIF_F_GSO_IPXIP6. These are used to described IP in IP >>>> tunnel and what the outer protocol is. The inner protocol >>>> can be deduced from other GSO types (e.g. SKB_GSO_TCPV4 and >>>> SKB_GSO_TCPV6). The GSO types of SKB_GSO_IPIP and SKB_GSO_SIT >>>> are removed (these are both instances of SKB_GSO_IPXIP4). >>>> SKB_GSO_IPXIP6 will be used when support for GSO with IP >>>> encapsulation over IPv6 is added. >>>> >>>> Signed-off-by: Tom Herbert <tom@herbertland.com> >>>> --- >>>> drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c | 5 ++--- >>>> drivers/net/ethernet/broadcom/bnxt/bnxt.c | 4 ++-- >>>> drivers/net/ethernet/intel/i40e/i40e_main.c | 3 +-- >>>> drivers/net/ethernet/intel/i40e/i40e_txrx.c | 3 +-- >>>> drivers/net/ethernet/intel/i40evf/i40e_txrx.c | 3 +-- >>>> drivers/net/ethernet/intel/i40evf/i40evf_main.c | 3 +-- >>>> drivers/net/ethernet/intel/igb/igb_main.c | 3 +-- >>>> drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 3 +-- >>>> drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c | 3 +-- >>>> include/linux/netdev_features.h | 12 ++++++------ >>>> include/linux/netdevice.h | 4 ++-- >>>> include/linux/skbuff.h | 4 ++-- >>>> net/core/ethtool.c | 4 ++-- >>>> net/ipv4/af_inet.c | 2 +- >>>> net/ipv4/ipip.c | 2 +- >>>> net/ipv6/ip6_offload.c | 4 ++-- >>>> net/ipv6/sit.c | 4 ++-- >>>> net/netfilter/ipvs/ip_vs_xmit.c | 17 +++++++---------- >>>> 18 files changed, 36 insertions(+), 47 deletions(-) >>> >>> It looks like you missed drivers/net/ethernet/intel/igb/netdev.c. If >>> you don't get it then it will break the build. >>> >> >> I don't see file that in betdev branch, maybe it's new? > > Nope, it has been there for a while. It got patched to support IPIP > and SIT tunnels in the same patch that updated igb/igb_main.c. > Looks like it's drivers/net/ethernet/intel/igbvf/netdev.c > I am also looking into the other patches now. It looks like something > broke hardware offloads again as I am only getting .9 Mb/s for IPv6 > based GRE tunnels with your patches applied. I'm trying to bisect it > now. > What hardware are you using? Tom > - Alex
On Mon, May 16, 2016 at 11:28 AM, Tom Herbert <tom@herbertland.com> wrote: > On Mon, May 16, 2016 at 11:13 AM, Alexander Duyck > <alexander.duyck@gmail.com> wrote: >> On Mon, May 16, 2016 at 11:07 AM, Tom Herbert <tom@herbertland.com> wrote: >>> On Mon, May 16, 2016 at 9:32 AM, Alexander Duyck >>> <alexander.duyck@gmail.com> wrote: >>>> On Sun, May 15, 2016 at 4:42 PM, Tom Herbert <tom@herbertland.com> wrote: >>>>> This patch defines two new GSO definitions SKB_GSO_IPXIP4 and >>>>> SKB_GSO_IPXIP6 along with corresponding NETIF_F_GSO_IPXIP4 and >>>>> NETIF_F_GSO_IPXIP6. These are used to described IP in IP >>>>> tunnel and what the outer protocol is. The inner protocol >>>>> can be deduced from other GSO types (e.g. SKB_GSO_TCPV4 and >>>>> SKB_GSO_TCPV6). The GSO types of SKB_GSO_IPIP and SKB_GSO_SIT >>>>> are removed (these are both instances of SKB_GSO_IPXIP4). >>>>> SKB_GSO_IPXIP6 will be used when support for GSO with IP >>>>> encapsulation over IPv6 is added. >>>>> >>>>> Signed-off-by: Tom Herbert <tom@herbertland.com> >>>>> --- >>>>> drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c | 5 ++--- >>>>> drivers/net/ethernet/broadcom/bnxt/bnxt.c | 4 ++-- >>>>> drivers/net/ethernet/intel/i40e/i40e_main.c | 3 +-- >>>>> drivers/net/ethernet/intel/i40e/i40e_txrx.c | 3 +-- >>>>> drivers/net/ethernet/intel/i40evf/i40e_txrx.c | 3 +-- >>>>> drivers/net/ethernet/intel/i40evf/i40evf_main.c | 3 +-- >>>>> drivers/net/ethernet/intel/igb/igb_main.c | 3 +-- >>>>> drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 3 +-- >>>>> drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c | 3 +-- >>>>> include/linux/netdev_features.h | 12 ++++++------ >>>>> include/linux/netdevice.h | 4 ++-- >>>>> include/linux/skbuff.h | 4 ++-- >>>>> net/core/ethtool.c | 4 ++-- >>>>> net/ipv4/af_inet.c | 2 +- >>>>> net/ipv4/ipip.c | 2 +- >>>>> net/ipv6/ip6_offload.c | 4 ++-- >>>>> net/ipv6/sit.c | 4 ++-- >>>>> net/netfilter/ipvs/ip_vs_xmit.c | 17 +++++++---------- >>>>> 18 files changed, 36 insertions(+), 47 deletions(-) >>>> >>>> It looks like you missed drivers/net/ethernet/intel/igb/netdev.c. If >>>> you don't get it then it will break the build. >>>> >>> >>> I don't see file that in betdev branch, maybe it's new? >> >> Nope, it has been there for a while. It got patched to support IPIP >> and SIT tunnels in the same patch that updated igb/igb_main.c. >> > > Looks like it's > > drivers/net/ethernet/intel/igbvf/netdev.c > >> I am also looking into the other patches now. It looks like something >> broke hardware offloads again as I am only getting .9 Mb/s for IPv6 >> based GRE tunnels with your patches applied. I'm trying to bisect it >> now. >> > What hardware are you using? I'm using an Intel X710, it is an i40e based NIC. - Alex
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index d465bd7..0a5b770 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -13259,12 +13259,11 @@ static int bnx2x_init_dev(struct bnx2x *bp, struct pci_dev *pdev, NETIF_F_RXHASH | NETIF_F_HW_VLAN_CTAG_TX; if (!chip_is_e1x) { dev->hw_features |= NETIF_F_GSO_GRE | NETIF_F_GSO_UDP_TUNNEL | - NETIF_F_GSO_IPIP | NETIF_F_GSO_SIT; + NETIF_F_GSO_IPXIP4; dev->hw_enc_features = NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | NETIF_F_SG | NETIF_F_TSO | NETIF_F_TSO_ECN | NETIF_F_TSO6 | - NETIF_F_GSO_IPIP | - NETIF_F_GSO_SIT | + NETIF_F_GSO_IPXIP4 | NETIF_F_GSO_GRE | NETIF_F_GSO_UDP_TUNNEL; } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 5a0dca3..bfc1e94 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -6311,7 +6311,7 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) dev->hw_features = NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | NETIF_F_SG | NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_GSO_UDP_TUNNEL | NETIF_F_GSO_GRE | - NETIF_F_GSO_IPIP | NETIF_F_GSO_SIT | + NETIF_F_GSO_IPXIP4 | NETIF_F_GSO_UDP_TUNNEL_CSUM | NETIF_F_GSO_GRE_CSUM | NETIF_F_GSO_PARTIAL | NETIF_F_RXHASH | NETIF_F_RXCSUM | NETIF_F_LRO | NETIF_F_GRO; @@ -6321,7 +6321,7 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_GSO_UDP_TUNNEL | NETIF_F_GSO_GRE | NETIF_F_GSO_UDP_TUNNEL_CSUM | NETIF_F_GSO_GRE_CSUM | - NETIF_F_GSO_IPIP | NETIF_F_GSO_SIT | + NETIF_F_GSO_IPXIP4; NETIF_F_GSO_PARTIAL; dev->gso_partial_features = NETIF_F_GSO_UDP_TUNNEL_CSUM | NETIF_F_GSO_GRE_CSUM; diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 1cd0ebf..242a1ff 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -9083,8 +9083,7 @@ static int i40e_config_netdev(struct i40e_vsi *vsi) NETIF_F_TSO6 | NETIF_F_GSO_GRE | NETIF_F_GSO_GRE_CSUM | - NETIF_F_GSO_IPIP | - NETIF_F_GSO_SIT | + NETIF_F_GSO_IPXIP4 | NETIF_F_GSO_UDP_TUNNEL | NETIF_F_GSO_UDP_TUNNEL_CSUM | NETIF_F_GSO_PARTIAL | diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index 99a524d..0a8122c 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -2284,8 +2284,7 @@ static int i40e_tso(struct sk_buff *skb, u8 *hdr_len, u64 *cd_type_cmd_tso_mss) if (skb_shinfo(skb)->gso_type & (SKB_GSO_GRE | SKB_GSO_GRE_CSUM | - SKB_GSO_IPIP | - SKB_GSO_SIT | + SKB_GSO_IPXIP4 | SKB_GSO_UDP_TUNNEL | SKB_GSO_UDP_TUNNEL_CSUM)) { if (!(skb_shinfo(skb)->gso_type & SKB_GSO_PARTIAL) && diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c index fd7dae46..2bbbbd0 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c @@ -1559,8 +1559,7 @@ static int i40e_tso(struct sk_buff *skb, u8 *hdr_len, u64 *cd_type_cmd_tso_mss) if (skb_shinfo(skb)->gso_type & (SKB_GSO_GRE | SKB_GSO_GRE_CSUM | - SKB_GSO_IPIP | - SKB_GSO_SIT | + SKB_GSO_IPXIP4 | SKB_GSO_UDP_TUNNEL | SKB_GSO_UDP_TUNNEL_CSUM)) { if (!(skb_shinfo(skb)->gso_type & SKB_GSO_PARTIAL) && diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/i40evf/i40evf_main.c index 642bb45..02d0a1c 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c +++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c @@ -2230,8 +2230,7 @@ int i40evf_process_config(struct i40evf_adapter *adapter) NETIF_F_TSO6 | NETIF_F_GSO_GRE | NETIF_F_GSO_GRE_CSUM | - NETIF_F_GSO_IPIP | - NETIF_F_GSO_SIT | + NETIF_F_GSO_IPXIP4 | NETIF_F_GSO_UDP_TUNNEL | NETIF_F_GSO_UDP_TUNNEL_CSUM | NETIF_F_GSO_PARTIAL | diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 2172769..808d48f 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -2418,8 +2418,7 @@ static int igb_probe(struct pci_dev *pdev, const struct pci_device_id *ent) #define IGB_GSO_PARTIAL_FEATURES (NETIF_F_GSO_GRE | \ NETIF_F_GSO_GRE_CSUM | \ - NETIF_F_GSO_IPIP | \ - NETIF_F_GSO_SIT | \ + SKB_GSO_IPXIP4 | \ NETIF_F_GSO_UDP_TUNNEL | \ NETIF_F_GSO_UDP_TUNNEL_CSUM) diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index d08fbcf..28e3b5a 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -9482,8 +9482,7 @@ skip_sriov: #define IXGBE_GSO_PARTIAL_FEATURES (NETIF_F_GSO_GRE | \ NETIF_F_GSO_GRE_CSUM | \ - NETIF_F_GSO_IPIP | \ - NETIF_F_GSO_SIT | \ + NETIF_F_GSO_IPXIP4 | \ NETIF_F_GSO_UDP_TUNNEL | \ NETIF_F_GSO_UDP_TUNNEL_CSUM) diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c index 5e348b1..d86e511 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c @@ -4062,8 +4062,7 @@ static int ixgbevf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) #define IXGBEVF_GSO_PARTIAL_FEATURES (NETIF_F_GSO_GRE | \ NETIF_F_GSO_GRE_CSUM | \ - NETIF_F_GSO_IPIP | \ - NETIF_F_GSO_SIT | \ + NETIF_F_GSO_IPXIP4 | \ NETIF_F_GSO_UDP_TUNNEL | \ NETIF_F_GSO_UDP_TUNNEL_CSUM) diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index bc87362..aa7b240 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -44,8 +44,8 @@ enum { NETIF_F_FSO_BIT, /* ... FCoE segmentation */ NETIF_F_GSO_GRE_BIT, /* ... GRE with TSO */ NETIF_F_GSO_GRE_CSUM_BIT, /* ... GRE with csum with TSO */ - NETIF_F_GSO_IPIP_BIT, /* ... IPIP tunnel with TSO */ - NETIF_F_GSO_SIT_BIT, /* ... SIT tunnel with TSO */ + NETIF_F_GSO_IPXIP4_BIT, /* ... IP4 or IP6 over IP4 with TSO */ + NETIF_F_GSO_IPXIP6_BIT, /* ... IP4 or IP6 over IP6 with TSO */ NETIF_F_GSO_UDP_TUNNEL_BIT, /* ... UDP TUNNEL with TSO */ NETIF_F_GSO_UDP_TUNNEL_CSUM_BIT,/* ... UDP TUNNEL with TSO & CSUM */ NETIF_F_GSO_PARTIAL_BIT, /* ... Only segment inner-most L4 @@ -121,8 +121,8 @@ enum { #define NETIF_F_RXALL __NETIF_F(RXALL) #define NETIF_F_GSO_GRE __NETIF_F(GSO_GRE) #define NETIF_F_GSO_GRE_CSUM __NETIF_F(GSO_GRE_CSUM) -#define NETIF_F_GSO_IPIP __NETIF_F(GSO_IPIP) -#define NETIF_F_GSO_SIT __NETIF_F(GSO_SIT) +#define NETIF_F_GSO_IPXIP4 __NETIF_F(GSO_IPXIP4) +#define NETIF_F_GSO_IPXIP6 __NETIF_F(GSO_IPXIP6) #define NETIF_F_GSO_UDP_TUNNEL __NETIF_F(GSO_UDP_TUNNEL) #define NETIF_F_GSO_UDP_TUNNEL_CSUM __NETIF_F(GSO_UDP_TUNNEL_CSUM) #define NETIF_F_TSO_MANGLEID __NETIF_F(TSO_MANGLEID) @@ -200,8 +200,8 @@ enum { #define NETIF_F_GSO_ENCAP_ALL (NETIF_F_GSO_GRE | \ NETIF_F_GSO_GRE_CSUM | \ - NETIF_F_GSO_IPIP | \ - NETIF_F_GSO_SIT | \ + NETIF_F_GSO_IPXIP4 | \ + NETIF_F_GSO_IPXIP6 | \ NETIF_F_GSO_UDP_TUNNEL | \ NETIF_F_GSO_UDP_TUNNEL_CSUM) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index c2f5112..b36c3cc 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4007,8 +4007,8 @@ static inline bool net_gso_ok(netdev_features_t features, int gso_type) BUILD_BUG_ON(SKB_GSO_FCOE != (NETIF_F_FSO >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_GRE != (NETIF_F_GSO_GRE >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_GRE_CSUM != (NETIF_F_GSO_GRE_CSUM >> NETIF_F_GSO_SHIFT)); - BUILD_BUG_ON(SKB_GSO_IPIP != (NETIF_F_GSO_IPIP >> NETIF_F_GSO_SHIFT)); - BUILD_BUG_ON(SKB_GSO_SIT != (NETIF_F_GSO_SIT >> NETIF_F_GSO_SHIFT)); + BUILD_BUG_ON(SKB_GSO_IPXIP4 != (NETIF_F_GSO_IPXIP4 >> NETIF_F_GSO_SHIFT)); + BUILD_BUG_ON(SKB_GSO_IPXIP6 != (NETIF_F_GSO_IPXIP6 >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_UDP_TUNNEL != (NETIF_F_GSO_UDP_TUNNEL >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_UDP_TUNNEL_CSUM != (NETIF_F_GSO_UDP_TUNNEL_CSUM >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_PARTIAL != (NETIF_F_GSO_PARTIAL >> NETIF_F_GSO_SHIFT)); diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index c413c58..65968a9 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -471,9 +471,9 @@ enum { SKB_GSO_GRE_CSUM = 1 << 8, - SKB_GSO_IPIP = 1 << 9, + SKB_GSO_IPXIP4 = 1 << 9, - SKB_GSO_SIT = 1 << 10, + SKB_GSO_IPXIP6 = 1 << 10, SKB_GSO_UDP_TUNNEL = 1 << 11, diff --git a/net/core/ethtool.c b/net/core/ethtool.c index bdb4013..f403481 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -84,8 +84,8 @@ static const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN] [NETIF_F_FSO_BIT] = "tx-fcoe-segmentation", [NETIF_F_GSO_GRE_BIT] = "tx-gre-segmentation", [NETIF_F_GSO_GRE_CSUM_BIT] = "tx-gre-csum-segmentation", - [NETIF_F_GSO_IPIP_BIT] = "tx-ipip-segmentation", - [NETIF_F_GSO_SIT_BIT] = "tx-sit-segmentation", + [NETIF_F_GSO_IPXIP4_BIT] = "tx-ipxip4-segmentation", + [NETIF_F_GSO_IPXIP6_BIT] = "tx-ipxip6-segmentation", [NETIF_F_GSO_UDP_TUNNEL_BIT] = "tx-udp_tnl-segmentation", [NETIF_F_GSO_UDP_TUNNEL_CSUM_BIT] = "tx-udp_tnl-csum-segmentation", [NETIF_F_GSO_PARTIAL_BIT] = "tx-gso-partial", diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 7f08d45..25040b1 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1483,7 +1483,7 @@ out_unlock: static int ipip_gro_complete(struct sk_buff *skb, int nhoff) { skb->encapsulation = 1; - skb_shinfo(skb)->gso_type |= SKB_GSO_IPIP; + skb_shinfo(skb)->gso_type |= SKB_GSO_IPXIP4; return inet_gro_complete(skb, nhoff); } diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 9282748..9783701 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -219,7 +219,7 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) if (unlikely(skb->protocol != htons(ETH_P_IP))) goto tx_error; - if (iptunnel_handle_offloads(skb, SKB_GSO_IPIP)) + if (iptunnel_handle_offloads(skb, SKB_GSO_IPXIP4)) goto tx_error; skb_set_inner_ipproto(skb, IPPROTO_IPIP); diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c index 9ad743b..787e55f 100644 --- a/net/ipv6/ip6_offload.c +++ b/net/ipv6/ip6_offload.c @@ -86,7 +86,7 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, proto = ipv6_gso_pull_exthdrs(skb, ipv6h->nexthdr); if (skb->encapsulation && - skb_shinfo(skb)->gso_type & (SKB_GSO_SIT|SKB_GSO_IPIP)) + skb_shinfo(skb)->gso_type & (SKB_GSO_IPXIP4 | SKB_GSO_IPXIP6)) udpfrag = proto == IPPROTO_UDP && encap; else udpfrag = proto == IPPROTO_UDP && !skb->encapsulation; @@ -294,7 +294,7 @@ out_unlock: static int sit_gro_complete(struct sk_buff *skb, int nhoff) { skb->encapsulation = 1; - skb_shinfo(skb)->gso_type |= SKB_GSO_SIT; + skb_shinfo(skb)->gso_type |= SKB_GSO_IPXIP4; return ipv6_gro_complete(skb, nhoff); } diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index a13d8c1..0a5a255 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -913,7 +913,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, goto tx_error; } - if (iptunnel_handle_offloads(skb, SKB_GSO_SIT)) { + if (iptunnel_handle_offloads(skb, SKB_GSO_IPXIP4)) { ip_rt_put(rt); goto tx_error; } @@ -1000,7 +1000,7 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) struct ip_tunnel *tunnel = netdev_priv(dev); const struct iphdr *tiph = &tunnel->parms.iph; - if (iptunnel_handle_offloads(skb, SKB_GSO_IPIP)) + if (iptunnel_handle_offloads(skb, SKB_GSO_IPXIP4)) goto tx_error; skb_set_inner_ipproto(skb, IPPROTO_IPIP); diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 6d19d2e..01d3d89 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -932,17 +932,14 @@ error: static inline int __tun_gso_type_mask(int encaps_af, int orig_af) { - if (encaps_af == AF_INET) { - if (orig_af == AF_INET) - return SKB_GSO_IPIP; - - return SKB_GSO_SIT; + switch (encaps_af) { + case AF_INET: + return SKB_GSO_IPXIP4; + case AF_INET6: + return SKB_GSO_IPXIP6; + default: + return 0; } - - /* GSO: we need to provide proper SKB_GSO_ value for IPv6: - * SKB_GSO_SIT/IPV6 - */ - return 0; } /*
This patch defines two new GSO definitions SKB_GSO_IPXIP4 and SKB_GSO_IPXIP6 along with corresponding NETIF_F_GSO_IPXIP4 and NETIF_F_GSO_IPXIP6. These are used to described IP in IP tunnel and what the outer protocol is. The inner protocol can be deduced from other GSO types (e.g. SKB_GSO_TCPV4 and SKB_GSO_TCPV6). The GSO types of SKB_GSO_IPIP and SKB_GSO_SIT are removed (these are both instances of SKB_GSO_IPXIP4). SKB_GSO_IPXIP6 will be used when support for GSO with IP encapsulation over IPv6 is added. Signed-off-by: Tom Herbert <tom@herbertland.com> --- drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c | 5 ++--- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 4 ++-- drivers/net/ethernet/intel/i40e/i40e_main.c | 3 +-- drivers/net/ethernet/intel/i40e/i40e_txrx.c | 3 +-- drivers/net/ethernet/intel/i40evf/i40e_txrx.c | 3 +-- drivers/net/ethernet/intel/i40evf/i40evf_main.c | 3 +-- drivers/net/ethernet/intel/igb/igb_main.c | 3 +-- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 3 +-- drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c | 3 +-- include/linux/netdev_features.h | 12 ++++++------ include/linux/netdevice.h | 4 ++-- include/linux/skbuff.h | 4 ++-- net/core/ethtool.c | 4 ++-- net/ipv4/af_inet.c | 2 +- net/ipv4/ipip.c | 2 +- net/ipv6/ip6_offload.c | 4 ++-- net/ipv6/sit.c | 4 ++-- net/netfilter/ipvs/ip_vs_xmit.c | 17 +++++++---------- 18 files changed, 36 insertions(+), 47 deletions(-)