- 21 Jun, 2017 7 commits
-
-
David S. Miller authored
Julien Gomes says: ==================== ipmr/ip6mr: add Netlink notifications on cache reports Currently, all ipmr/ip6mr cache reports are sent through the mroute/mroute6 socket only. This forces the use of a single socket for mroute programming, cache reports and, regarding ipmr, IGMP messages without Router Alert option reception. The present patches are aiming to send Netlink notifications in addition to the existing igmpmsg/mrt6msg to give user programs a way to handle cache reports in parallel with multiple sockets other than the mroute/mroute6 socket. Changes in v2: - Changed attributes naming from {IPMRA,IP6MRA}_CACHEREPORTA_* to {IPMRA,IP6MRA}_CREPORT_* - Improved packet data copy to handle non-linear packets in ipmr/ip6mr cache report Netlink notification creation - Added two rtnetlink groups with restricted-binding - Changed cache report notified groups from RTNL_{IPV4,IPV6}_MROUTE to the new restricted groups in ipmr/ip6mr Changes in v3: - Put message size calculation for {igmp,mrt6}msg_netlink_event in separate functions - Increased vif id attributes size from u8 to u32 ==================== Signed-off-by:David S. Miller <davem@davemloft.net>
-
Julien Gomes authored
Add Netlink notifications on cache reports in ip6mr, in addition to the existing mrt6msg sent to mroute6_sk. Send RTM_NEWCACHEREPORT notifications to RTNLGRP_IPV6_MROUTE_R. MSGTYPE, MIF_ID, SRC_ADDR and DST_ADDR Netlink attributes contain the same data as their equivalent fields in the mrt6msg header. PKT attribute is the packet sent to mroute6_sk, without the added mrt6msg header. Suggested-by:
Ryan Halbrook <halbrook@arista.com> Signed-off-by:
Julien Gomes <julien@arista.com> Reviewed-by:
Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by:
-
Julien Gomes authored
Add Netlink notifications on cache reports in ipmr, in addition to the existing igmpmsg sent to mroute_sk. Send RTM_NEWCACHEREPORT notifications to RTNLGRP_IPV4_MROUTE_R. MSGTYPE, VIF_ID, SRC_ADDR and DST_ADDR Netlink attributes contain the same data as their equivalent fields in the igmpmsg header. PKT attribute is the packet sent to mroute_sk, without the added igmpmsg header. Suggested-by:
-
Julien Gomes authored
Add RTNLGRP_{IPV4,IPV6}_MROUTE_R as two new restricted groups for the NETLINK_ROUTE family. Binding to these groups specifically requires CAP_NET_ADMIN to allow multicast of sensitive messages (e.g. mroute cache reports). Suggested-by: -
Julien Gomes authored
New NEWCACHEREPORT message type to be used for cache reports sent via Netlink, effectively allowing splitting cache report reception from mroute programming. Suggested-by:
-
Arnd Bergmann authored
Changing from a memcpy to per-member comparison left the size variable unused: net/ipv4/tcp_ipv4.c: In function 'tcp_md5_do_lookup': net/ipv4/tcp_ipv4.c:910:15: error: unused variable 'size' [-Werror=unused-variable] This does not show up when CONFIG_IPV6 is enabled, but the variable can be removed either way, along with the now unused assignment. Fixes: 6797318e ("tcp: md5: add an address prefix for key lookup") Signed-off-by:
Arnd Bergmann <arnd@arndb.de> Signed-off-by:
-
yuan linyu authored
in my commit b952f4df, - *(u8 *)skb_put(skb_out, 1) = (u8)(accm >> 24); \ + skb_put(skb_out, (u8)(accm >> 24)); \ it should skb_put_u8() Fixes: b952f4df ("net: manual clean code which call skb_put_[data:zero])") Signed-off-by:
yuan linyu <Linyu.Yuan@alcatel-sbell.com.cn> Signed-off-by:
-
- 20 Jun, 2017 33 commits
-
-
git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linuxDavid S. Miller authored
Saeed Mahameed says: ==================== mlx5-updates-2017-06-20 (mlx5 IPoIB updates) This series includes updates to mlx5 IPoIB netdevice driver (mlx5i), 1. We move ipoib files into separate directory, to allow it to grow separately in its own space 2. Remove HW update carrier logic from IPoIB and VF representors profiles. 3. Add basic ethtool support. (Rings options/statistics and driver info). 4. Change MTU support. 5. Xmit path statistics reporting. 6. add PTP support. For the new ethtool ops, PTP (ioctl) and change_mtu ndos in IPoIB, we didn't add new implementation or new logic, we only reused those callbacks from the already existing mlx5e (ethernet netdevice profile) and exposed them in IPoIB netdevice/ethtool ops. ==================== Signed-off-by: -
David S. Miller authored
Julian Wiedmann says: ==================== s390/net updates, part 2 (v2) thanks for the feedback. Here's an updated patchset that honours the reverse christmas tree and drops the __packed attribute. Please apply. ==================== Signed-off-by: -
Julian Wiedmann authored
When a s390 guest runs on a z/VM host that's part of a SSI cluster, it can be migrated to a different host. In this case, the MAC address it originally obtained on the old host may be re-assigned to a new guest. This would result in address conflicts between the two guests. When running as z/VM guest, use the diag26c MAC Service to obtain a hypervisor-managed MAC address. The MAC Service is SSI-aware, and won't re-assign the address after the guest is migrated to a new host. This patch adds support for the z/VM MAC Service on L2 devices. Signed-off-by:
Julian Wiedmann <jwi@linux.vnet.ibm.com> Acked-by:
Ursula Braun <ubraun@linux.vnet.ibm.com> Signed-off-by:
-
Julian Wiedmann authored
Implement support for the hypervisor diagnose 0x26c ('Access Certain System Information'). It passes a request buffer and a subfunction code, and receives a response buffer and a return code. Also add the scaffolding for the 'MAC Services' subfunction. It may be used by network devices to obtain a hypervisor-managed MAC address. Signed-off-by:Heiko Carstens <heiko.carstens@de.ibm.com> Signed-off-by:
-
Julian Wiedmann authored
There's two spots in qeth_send_packet() where we don't accurately account for transmitted packing buffers in qeth's performance statistics: 1) when flushing the current buffer due to insufficient size, and the next buffer is not EMPTY, we need to account for that flushed buffer. 2) when synchronizing with the TX completion code, we reset flush_count and thus forget to account for any previously flushed buffers. Reported-by:
Nils Hoppmann <niho@de.ibm.com> Signed-off-by:
-
Kittipon Meesompop authored
add ipa return codes for Bridgeport (HiperSockets and OSA) according to system level design. Signed-off-by:
Kittipon Meesompop <kmeesomp@linux.vnet.ibm.com> Reviewed-by:
-
Xin Long authored
It's a bad thing not to handle errors when updating asoc. The memory allocation failure in any of the functions called in sctp_assoc_update() would cause sctp to work unexpectedly. This patch is to fix it by aborting the asoc and reporting the error when any of these functions fails. Signed-off-by:
Xin Long <lucien.xin@gmail.com> Acked-by:
Neil Horman <nhorman@tuxdriver.com> Acked-by:
Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by:
-
Xin Long authored
local_cork is used to decide if it should uncork asoc outq after processing some cmds, and it is set when replying or sending msgs. local_cork should always have the same value with current asoc q->cork in some way. The thing is when changing to a new asoc by cmd SET_ASOC, local_cork may not be consistent with the current asoc any more. The cmd seqs can be: SCTP_CMD_UPDATE_ASSOC (asoc) SCTP_CMD_REPLY (asoc) SCTP_CMD_SET_ASOC (new_asoc) SCTP_CMD_DELETE_TCB (new_asoc) SCTP_CMD_SET_ASOC (asoc) SCTP_CMD_REPLY (asoc) The 1st REPLY makes OLD asoc q->cork and local_cork both are 1, and the cmd DELETE_TCB clears NEW asoc q->cork and local_cork. After asoc goes back to OLD asoc, q->cork is still 1 while local_cork is 0. The 2nd REPLY will not set local_cork because q->cork is already set and it can't be uncorked and sent out because of this. To keep local_cork consistent with the current asoc q->cork, this patch is to uncork the old asoc if local_cork is set before changing to the new one. Note that the above cmd seqs will be used in the next patch when updating asoc and handling errors in it. Suggested-by:
-
Xin Long authored
Patch "call inet_add_protocol after register_pernet_subsys in dccp_v4_init" fixed a null pointer dereference issue for dccp_ipv4 module. The same fix is needed for dccp_ipv6 module. Signed-off-by:
-
Xin Long authored
Now dccp_ipv4 works as a kernel module. During loading this module, if one dccp packet is being recieved after inet_add_protocol but before register_pernet_subsys in which v4_ctl_sk is initialized, a null pointer dereference may be triggered because of init_net.dccp.v4_ctl_sk is 0x0. Jianlin found this issue when the following call trace occurred: [ 171.950177] BUG: unable to handle kernel NULL pointer dereference at 0000000000000110 [ 171.951007] IP: [<ffffffffc0558364>] dccp_v4_ctl_send_reset+0xc4/0x220 [dccp_ipv4] [...] [ 171.984629] Call Trace: [ 171.984859] <IRQ> [ 171.985061] [ 171.985213] [<ffffffffc0559a53>] dccp_v4_rcv+0x383/0x3f9 [dccp_ipv4] [ 171.985711] [<ffffffff815ca054>] ip_local_deliver_finish+0xb4/0x1f0 [ 171.986309] [<ffffffff815ca339>] ip_local_deliver+0x59/0xd0 [ 171.986852] [<ffffffff810cd7a4>] ? update_curr+0x104/0x190 [ 171.986956] [<ffffffff815c9cda>] ip_rcv_finish+0x8a/0x350 [ 171.986956] [<ffffffff815ca666>] ip_rcv+0x2b6/0x410 [ 171.986956] [<ffffffff810c83b4>] ? task_cputime+0x44/0x80 [ 171.986956] [<ffffffff81586f22>] __netif_receive_skb_core+0x572/0x7c0 [ 171.986956] [<ffffffff810d2c51>] ? trigger_load_balance+0x61/0x1e0 [ 171.986956] [<ffffffff81587188>] __netif_receive_skb+0x18/0x60 [ 171.986956] [<ffffffff8158841e>] process_backlog+0xae/0x180 [ 171.986956] [<ffffffff8158799d>] net_rx_action+0x16d/0x380 [ 171.986956] [<ffffffff81090b7f>] __do_softirq+0xef/0x280 [ 171.986956] [<ffffffff816b6a1c>] call_softirq+0x1c/0x30 This patch is to move inet_add_protocol after register_pernet_subsys in dccp_v4_init, so that v4_ctl_sk is initialized before any incoming dccp packets are processed. Reported-by:
Jianlin Shi <jishi@redhat.com> Signed-off-by:
-
Govindarajulu Varadarajan authored
With -Wformat-truncation, gcc throws the following warning. Fix this by increasing the size of devname to accommodate 15 character netdev interface name and description. Remove length format precision for %s. We can fit entire name. Also increment the version. drivers/net/ethernet/cisco/enic/enic_main.c: In function ‘enic_open’: drivers/net/ethernet/cisco/enic/enic_main.c:1740:15: warning: ‘%u’ directive output may be truncated writing between 1 and 2 bytes into a region of size between 1 and 12 [-Wformat-truncation=] "%.11s-rx-%u", netdev->name, i); ^~ drivers/net/ethernet/cisco/enic/enic_main.c:1740:5: note: directive argument in the range [0, 16] "%.11s-rx-%u", netdev->name, i); ^~~~~~~~~~~~~ drivers/net/ethernet/cisco/enic/enic_main.c:1738:4: note: ‘snprintf’ output between 6 and 18 bytes into a destination of size 16 snprintf(enic->msix[intr].devname, ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ sizeof(enic->msix[intr].devname), ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ "%.11s-rx-%u", netdev->name, i); ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Signed-off-by:Govindarajulu Varadarajan <gvaradar@cisco.com> Signed-off-by:
-
Niklas Cassel authored
There is nothing in the IP that prevents us from enabling TSO for IPv6. Before patch: ftp fe80::2aa:bbff:fecc:1336%eth0 ftp> get /dev/zero 882512708 bytes received in 00:14 (56.11 MiB/s) After patch: ftp fe80::2aa:bbff:fecc:1336%eth0 ftp> get /dev/zero 1203326784 bytes received in 00:12 (94.52 MiB/s) Signed-off-by:
Niklas Cassel <niklas.cassel@axis.com> Signed-off-by:
-
John Allen authored
If the ibmvnic driver is not in the VNIC_OPEN state, return from ibmvnic_resume callback. If we are not in the VNIC_OPEN state, interrupts may not be initialized and directly calling the interrupt handler will cause a crash. Signed-off-by:
John Allen <jallen@linux.vnet.ibm.com> Reviewed-by:
Nathan Fontenot <nfont@linux.vnet.ibm.com> Signed-off-by:
-
Thomas Bogendoerfer authored
Provide link partner advertising information. Removed testing for gigabit modes, which is useless for a fast ethernet phy. Signed-off-by:
Thomas Bogendoerfer <tbogendoerfer@suse.de> Reviewed-by:
Andrew Lunn <andrew@lunn.ch> Signed-off-by:
-
David S. Miller authored
John Crispin says: ==================== net-next: mediatek: various performance improvements During development we mainly ran testing using iperf doing 1500 byte tcp frames. It was pointed out recently, that the driver does not perform very well when using 512 byte udp frames. The biggest problem was that RPS was not working as no rx queue was being set. fixing this more than doubled the throughput. Additionally the IRQ mask register is now locked independently for RX and TX. RX IRQ aggregation is also added. With all these patches applied we can almost triple the throughput. While at it we also add PHY status change reporting for GMACs connecting directly to a PHY. ==================== Signed-off-by: -
John Crispin authored
The get_rps_cpu() function will not do any RPS on the data flow when no queue is setup and always use the current cpu where the IRQ was handled to also handle the backlog. As we only have one physical queue we always set this to 0 unconditionally. Signed-off-by:
John Crispin <john@phrozen.org> Signed-off-by:
-
John Crispin authored
Originally the driver only utilised the new QDMA engine. The current code still assumes this is the case when locking the IRQ mask register. Since RX now runs on the old style PDMA engine we can add a second lock. This patch reduces the IRQ latency as the TX and RX path no longer need to wait on each other under heavy load. Signed-off-by:
-
John Crispin authored
The PDMA engine used for RX allows IRQ aggregation. The patch sets up the corresponding registers to aggregate 4 IRQs into one. Using aggregation reduces the load on the core handling to a quarter thus reducing IRQ latency and increasing RX performance by around 10%. Signed-off-by:
-
John Crispin authored
Currently PHY status changes are only printed for DSA ports. This patch adds code to also print status changes for non-fixed links. Signed-off-by:
-
David S. Miller authored
Matthias Schiffer says: ==================== vxlan: cleanup and IPv6 link-local support Running VXLANs over IPv6 link-local addresses allows to use them as a drop-in replacement for VLANs, avoiding to allocate additional outer IP addresses to run the VXLAN over. Since v1, I have added a lot more consistency checks to the address configuration, making sure address families and scopes match. To simplify the implementation, I also did some general refactoring of the configuration handling in the new first patch of the series. The second patch is more cleanup; is slightly touches OVS code, so that list is in CC this time, too. As in v1, the last two patches actually make VXLAN over IPv6 link-local work, and allow multiple VXLANs with the same VNI and port, as long as link-local addresses on different interfaces are used. As suggested, I now store in the flags field if the VXLAN uses link-local addresses or not. v3 removes log messages as suggested by Roopa Prabhu (as it is very unusual for errors in netlink requests to be printed to the kernel log.) The commit message of patch 5 has been extended to add a note about IPv4. ==================== Signed-off-by: -
Matthias Schiffer authored
As link-local addresses are only valid for a single interface, we can allow to use the same VNI for multiple independent VXLANs, as long as the used interfaces are distinct. This way, VXLANs can always be used as a drop-in replacement for VLANs with greater ID space. This also extends VNI lookup to respect the ifindex when link-local IPv6 addresses are used, so using the same VNI on multiple interfaces can actually work. Signed-off-by:
Matthias Schiffer <mschiffer@universe-factory.net> Signed-off-by:
-
Matthias Schiffer authored
If VXLAN is run over link-local IPv6 addresses, it is necessary to store the ifindex in the FDB entries. Otherwise, the used interface is undefined and unicast communication will most likely fail. Support for link-local IPv4 addresses should be possible as well, but as the semantics aren't as well defined as for IPv6, and there doesn't seem to be much interest in having the support, it's not implemented for now. Signed-off-by:
-
Matthias Schiffer authored
* Multicast addresses are never valid as local address * Link-local IPv6 unicast addresses may only be used as remote when the local address is link-local as well * Don't allow link-local IPv6 local/remote addresses without interface We also store in the flags field if link-local addresses are used for the follow-up patches that actually make VXLAN over link-local IPv6 work. Signed-off-by:
-
Matthias Schiffer authored
Address families of source and destination addresses must match, and changelink operations can't change the address family. In addition, always use the VXLAN_F_IPV6 to check if a VXLAN device uses IPv4 or IPv6. Signed-off-by:
-
Matthias Schiffer authored
There is no good reason to keep the flags twice in vxlan_dev and vxlan_config. Signed-off-by:
-
Matthias Schiffer authored
The vxlan_dev_configure function was mixing validation and application of the vxlan configuration; this could easily lead to bugs with the changelink operation, as it was hard to see if the function wcould return an error after parts of the configuration had already been applied. This commit splits validation and application out of vxlan_dev_configure as separate functions to make it clearer where error returns are allowed and where the vxlan_dev or net_device may be configured. Log messages in these functions are removed, as it is generally unexpected to find error output for netlink requests in the kernel log. Userspace should be able to handle errors based on the error codes returned via netlink just fine. In addition, some validation and initialization is moved to vxlan_validate and vxlan_setup respectively to improve grouping of similar settings. Finally, this also fixes two actual bugs: * if set, conf->mtu would overwrite dev->mtu in each changelink operation, reverting other changes of dev->mtu * the "if (!conf->dst_port)" branch would never be run, as conf->dst_port was set in vxlan_setup before. This caused VXLAN-GPE to use the same default port as other VXLAN sockets instead of the intended IANA-assigned 4790. Signed-off-by:
-
David S. Miller authored
yuan linyu says: ==================== net: more skb_put_[data:zero] related work yuan linyu (3): net: introduce __skb_put_[zero, data, u8] net: replace more place to skb_put_[data:zero] net: manual clean code which call skb_put_[data:zero] ==================== Signed-off-by: -
yuan linyu authored
Signed-off-by:
-
yuan linyu authored
spatch file, @@ expression skb, len, data; type t; @@ -memcpy((t *)skb_put(skb, len), data, len); +skb_put_data(skb, data, len); @@ identifier p; expression skb, len, data; type t; @@ -p = (t *)memset(skb_put(skb, len), data, len); +p = skb_put_zero(skb, len); @@ expression skb, len, data; type t; @@ -memcpy((t *)__skb_put(skb, len), data, len); +__skb_put_data(skb, data, len); @@ identifier p; expression skb, len, data; type t; @@ -p = (t *)memset(__skb_put(skb, len), data, len); +p = __skb_put_zero(skb, len); Signed-off-by:
-
yuan linyu authored
follow Johannes Berg, semantic patch file as below, @@ identifier p, p2; expression len; expression skb; type t, t2; @@ ( -p = __skb_put(skb, len); +p = __skb_put_zero(skb, len); | -p = (t)__skb_put(skb, len); +p = __skb_put_zero(skb, len); ) ... when != p ( p2 = (t2)p; -memset(p2, 0, len); | -memset(p, 0, len); ) @@ identifier p; expression len; expression skb; type t; @@ ( -t p = __skb_put(skb, len); +t p = __skb_put_zero(skb, len); ) ... when != p ( -memset(p, 0, len); ) @@ type t, t2; identifier p, p2; expression skb; @@ t *p; ... ( -p = __skb_put(skb, sizeof(t)); +p = __skb_put_zero(skb, sizeof(t)); | -p = (t *)__skb_put(skb, sizeof(t)); +p = __skb_put_zero(skb, sizeof(t)); ) ... when != p ( p2 = (t2)p; -memset(p2, 0, sizeof(*p)); | -memset(p, 0, sizeof(*p)); ) @@ expression skb, len; @@ -memset(__skb_put(skb, len), 0, len); +__skb_put_zero(skb, len); @@ expression skb, len, data; @@ -memcpy(__skb_put(skb, len), data, len); +__skb_put_data(skb, data, len); @@ expression SKB, C, S; typedef u8; identifier fn = {__skb_put}; fresh identifier fn2 = fn ## "_u8"; @@ - *(u8 *)fn(SKB, S) = C; + fn2(SKB, C); Signed-off-by: -
Vivien Didelot authored
Kill the remaining shift macro in favor of calculating at compile time its value from the more descriptive mask, which gives us a better representation of the register layout. Signed-off-by:
Vivien Didelot <vivien.didelot@savoirfairelinux.com> Signed-off-by:
-
David S. Miller authored
Vivien Didelot says: ==================== net: dsa: Global 2 cosmetics Similarly to what has been done for the Port and Global 1 registers, this patch series prefixes and documents the macros of Global 2. It brings no functional changes except for 1/10 which fixes the IRL init for 88E6390 family. Changes in v2: make *_g2_irl_init_all static inline without NET_DSA_MV88E6XXX_GLOBAL2 and compile test with and without the symbol. ==================== Signed-off-by: -
Vivien Didelot authored
Prefix and document the remaining Global 2 registers macros. Signed-off-by:
-
