1. 11 Nov, 2017 22 commits
    • Lawrence Brakmo's avatar
      bpf: Fix tcp_bufs_kern.c sample program · a4174f05
      Lawrence Brakmo authored
      The program was returning -1 in some cases which is not allowed
      by the verifier any longer.
      
      Fixes: 390ee7e2 ("bpf: enforce return code for cgroup-bpf programs")
      Signed-off-by: default avatarLawrence Brakmo <brakmo@fb.com>
      Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      a4174f05
    • Lawrence Brakmo's avatar
      bpf: Fix tcp_rwnd_kern.c sample program · 016e661b
      Lawrence Brakmo authored
      The program was returning -1 in some cases which is not allowed
      by the verifier any longer.
      
      Fixes: 390ee7e2 ("bpf: enforce return code for cgroup-bpf programs")
      Signed-off-by: default avatarLawrence Brakmo <brakmo@fb.com>
      Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      016e661b
    • Lawrence Brakmo's avatar
      bpf: Fix tcp_synrto_kern.c sample program · 7863f46b
      Lawrence Brakmo authored
      The program was returning -1 in some cases which is not allowed
      by the verifier any longer.
      
      Fixes: 390ee7e2 ("bpf: enforce return code for cgroup-bpf programs")
      Signed-off-by: default avatarLawrence Brakmo <brakmo@fb.com>
      Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      7863f46b
    • Jon Maloy's avatar
      tipc: improve link resiliency when rps is activated · 8d6e79d3
      Jon Maloy authored
      Currently, the TIPC RPS dissector is based only on the incoming packets'
      source node address, hence steering all traffic from a node to the same
      core. We have seen that this makes the links vulnerable to starvation
      and unnecessary resets when we turn down the link tolerance to very low
      values.
      
      To reduce the risk of this happening, we exempt probe and probe replies
      packets from the convergence to one core per source node. Instead, we do
      the opposite, - we try to diverge those packets across as many cores as
      possible, by randomizing the flow selector key.
      
      To make such packets identifiable to the dissector, we add a new
      'is_keepalive' bit to word 0 of the LINK_PROTOCOL header. This bit is
      set both for PROBE and PROBE_REPLY messages, and only for those.
      
      It should be noted that these packets are not part of any flow anyway,
      and only constitute a minuscule fraction of all packets sent across a
      link. Hence, there is no risk that this will affect overall performance.
      Acked-by: default avatarYing Xue <ying.xue@windriver.com>
      Signed-off-by: default avatarJon Maloy <jon.maloy@ericsson.com>
      Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      8d6e79d3
    • David S. Miller's avatar
      Merge branch 'macb-next' · 141f575f
      David S. Miller authored
      Michael Grzeschik says:
      
      ====================
      net: macb: add error handling on probe and
      
      This series adds more error handling to the macb driver.
      ====================
      Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      141f575f
    • Michael Grzeschik's avatar
      net: macb: add of_node_put to error paths · 66ee6a06
      Michael Grzeschik authored
      We add the call of_node_put(bp->phy_node) to all associated error
      paths for memory clean up.
      Signed-off-by: default avatarMichael Grzeschik <m.grzeschik@pengutronix.de>
      Acked-by: default avatarNicolas Ferre <nicolas.ferre@microchip.com>
      Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      66ee6a06
    • Michael Grzeschik's avatar
      net: macb: add of_phy_deregister_fixed_link to error paths · 9ce98140
      Michael Grzeschik authored
      We add the call of_phy_deregister_fixed_link to all associated
      error paths for memory clean up.
      Signed-off-by: default avatarMichael Grzeschik <m.grzeschik@pengutronix.de>
      Acked-by: default avatarNicolas Ferre <nicolas.ferre@microchip.com>
      Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      9ce98140
    • Miquel Raynal's avatar
      net: mvpp2: fix GOP statistics loop start and stop conditions · e5c500eb
      Miquel Raynal authored
      GOP statistics from all ports of one instance of the driver are gathered
      with one work recalled in loop in a workqueue. The loop is started when
      a port is up, and stopped when a port is down. This last condition is
      obviously wrong.
      
      Fix this by having a work per port. This way, starting and stoping it
      when the port is up or down will be fine, while minimizing unnecessary
      CPU usage.
      
      Fixes: 118d6298 ("net: mvpp2: add ethtool GOP statistics")
      Reported-by: default avatarStefan Chulski <stefanc@marvell.com>
      Signed-off-by: default avatarMiquel Raynal <miquel.raynal@free-electrons.com>
      Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      e5c500eb
    • David S. Miller's avatar
      Merge branch 'hns3-bug-fixes' · fc981359
      David S. Miller authored
      Lipeng says:
      
      ====================
      net: hns3: Bug fixes & Code improvements in HNS3 driver
      
      This patch-set introduces some bug fixes and code improvements.
      As [patch 1/2] depends on the patch {5392902d net: hns3: Consistently using
      GENMASK in hns3 driver}, which exists in net-next, not exists in net, so
      push this serise to nex-next.
      ====================
      Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      fc981359
    • Fuyun Liang's avatar
      net: hns3: cleanup mac auto-negotiation state query in hclge_update_speed_duplex · c040366b
      Fuyun Liang authored
      When checking whether auto-negotiation is on, driver only needs to
      check the value of mac.autoneg(SW) directly, and does not need to
      query it from hardware. Because this value is always synchronized
      with the auto-negotiation state of hardware.
      
      This patch removes mac auto-negotiation state query in
      hclge_update_speed_duplex().
      
      Fixes: 46a3df9f (net: hns3: Add HNS3 Acceleration Engine & Compatibility Layer Support)
      Signed-off-by: default avatarFuyun Liang <liangfuyun1@huawei.com>
      Signed-off-by: default avatarLipeng <lipeng321@huawei.com>
      Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      c040366b
    • Fuyun Liang's avatar
      net: hns3: fix a bug when getting phy address from NCL_config file · 39e2151f
      Fuyun Liang authored
      Driver gets phy address from NCL_config file and uses the phy address
      to initialize phydev. There are 5 bits for phy address. And C22 phy
      address has 5 bits. So 0-31 are all valid address for phy. If there
      is no phy, it will crash. Because driver always get a valid phy address.
      
      This patch fixes the phy address to 8 bits, and use 0xff to indicate
      invalid phy address.
      
      Fixes: 46a3df9f (net: hns3: Add HNS3 Acceleration Engine & Compatibility Layer Support)
      Signed-off-by: default avatarFuyun Liang <liangfuyun1@huawei.com>
      Signed-off-by: default avatarLipeng <lipeng321@huawei.com>
      Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      39e2151f
    • David Ahern's avatar
      net: netlink: Update attr validation to require exact length for some types · 28033ae4
      David Ahern authored
      Attributes using NLA_U* and NLA_S* (where * is 8, 16,32 and 64) are
      expected to be an exact length. Split these data types from
      nla_attr_minlen into nla_attr_len and update validate_nla to require
      the attribute to have exact length for them.
      Signed-off-by: default avatarDavid Ahern <dsahern@gmail.com>
      Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      28033ae4
    • Maciej Żenczykowski's avatar
      net: ipv6: sysctl to specify IPv6 ND traffic class · 2210d6b2
      Maciej Żenczykowski authored
      Add a per-device sysctl to specify the default traffic class to use for
      kernel originated IPv6 Neighbour Discovery packets.
      
      Currently this includes:
      
        - Router Solicitation (ICMPv6 type 133)
          ndisc_send_rs() -> ndisc_send_skb() -> ip6_nd_hdr()
      
        - Neighbour Solicitation (ICMPv6 type 135)
          ndisc_send_ns() -> ndisc_send_skb() -> ip6_nd_hdr()
      
        - Neighbour Advertisement (ICMPv6 type 136)
          ndisc_send_na() -> ndisc_send_skb() -> ip6_nd_hdr()
      
        - Redirect (ICMPv6 type 137)
          ndisc_send_redirect() -> ndisc_send_skb() -> ip6_nd_hdr()
      
      and if the kernel ever gets around to generating RA's,
      it would presumably also include:
      
        - Router Advertisement (ICMPv6 type 134)
          (radvd daemon could pick up on the kernel setting and use it)
      
      Interface drivers may examine the Traffic Class value and translate
      the DiffServ Code Point into a link-layer appropriate traffic
      prioritization scheme.  An example of mapping IETF DSCP values to
      IEEE 802.11 User Priority values can be found here:
      
          https://tools.ietf.org/html/draft-ietf-tsvwg-ieee-802-11
      
      The expected primary use case is to properly prioritize ND over wifi.
      
      Testing:
        jzem22:~# cat /proc/sys/net/ipv6/conf/eth0/ndisc_tclass
        0
        jzem22:~# echo -1 > /proc/sys/net/ipv6/conf/eth0/ndisc_tclass
        -bash: echo: write error: Invalid argument
        jzem22:~# echo 256 > /proc/sys/net/ipv6/conf/eth0/ndisc_tclass
        -bash: echo: write error: Invalid argument
        jzem22:~# echo 0 > /proc/sys/net/ipv6/conf/eth0/ndisc_tclass
        jzem22:~# echo 255 > /proc/sys/net/ipv6/conf/eth0/ndisc_tclass
        jzem22:~# cat /proc/sys/net/ipv6/conf/eth0/ndisc_tclass
        255
        jzem22:~# echo 34 > /proc/sys/net/ipv6/conf/eth0/ndisc_tclass
        jzem22:~# cat /proc/sys/net/ipv6/conf/eth0/ndisc_tclass
        34
      
        jzem22:~# echo $[0xDC] > /proc/sys/net/ipv6/conf/eth0/ndisc_tclass
        jzem22:~# tcpdump -v -i eth0 icmp6 and src host jzem22.pgc and dst host fe80::1
        tcpdump: listening on eth0, link-type EN10MB (Ethernet), capture size 262144 bytes
        IP6 (class 0xdc, hlim 255, next-header ICMPv6 (58) payload length: 24)
        jzem22.pgc > fe80::1: [icmp6 sum ok] ICMP6, neighbor advertisement,
        length 24, tgt is jzem22.pgc, Flags [solicited]
      
      (based on original change written by Erik Kline, with minor changes)
      
      v2: fix 'suspicious rcu_dereference_check() usage'
          by explicitly grabbing the rcu_read_lock.
      
      Cc: Lorenzo Colitti <lorenzo@google.com>
      Signed-off-by: default avatarErik Kline <ek@google.com>
      Signed-off-by: default avatarMaciej Żenczykowski <maze@google.com>
      Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      2210d6b2
    • Samuel Mendoza-Jonas's avatar
      net/ncsi: Don't return error on normal response · 04bad8bd
      Samuel Mendoza-Jonas authored
      Several response handlers return EBUSY if the data corresponding to the
      command/response pair is already set. There is no reason to return an
      error here; the channel is advertising something as enabled because we
      told it to enable it, and it's possible that the feature has been
      enabled previously.
      Signed-off-by: default avatarSamuel Mendoza-Jonas <sam@mendozajonas.com>
      Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      04bad8bd
    • Samuel Mendoza-Jonas's avatar
      net/ncsi: Improve general state logging · 9ef8690b
      Samuel Mendoza-Jonas authored
      The NCSI driver is mostly silent which becomes a headache when trying to
      determine what has occurred on the NCSI connection. This adds additional
      logging in a few key areas such as state transitions and calling out
      certain errors more visibly.
      Signed-off-by: default avatarSamuel Mendoza-Jonas <sam@mendozajonas.com>
      Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      9ef8690b
    • David S. Miller's avatar
      Merge branch 'bpftool-show-filenames-of-pinned-objects' · a8a6f1e4
      David S. Miller authored
      Prashant Bhole says:
      
      ====================
      tools: bpftool: show filenames of pinned objects
      
      This patchset adds support to show pinned objects in object details.
      
      Patch1 adds a funtionality to open a path in bpf-fs regardless of its object
      type.
      
      Patch2 adds actual functionality by scanning the bpf-fs once and adding
      object information in hash table, with object id as a key. One object may be
      associated with multiple paths because an object can be pinned multiple times
      
      Patch3 adds command line option to enable this functionality. Making it optional
      because scanning bpf-fs can be costly.
      ====================
      Acked-by: default avatarJakub Kicinski <jakub.kicinski@netronome.com>
      a8a6f1e4
    • Prashant Bhole's avatar
      tools: bpftool: optionally show filenames of pinned objects · c541b734
      Prashant Bhole authored
      Making it optional to show file names of pinned objects because
      it scans complete bpf-fs filesystem which is costly.
      Added option -f|--bpffs. Documentation updated.
      Signed-off-by: default avatarPrashant Bhole <bhole_prashant_q7@lab.ntt.co.jp>
      Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      c541b734
    • Prashant Bhole's avatar
      tools: bpftool: show filenames of pinned objects · 4990f1f4
      Prashant Bhole authored
      Added support to show filenames of pinned objects.
      
      For example:
      
      root@test# ./bpftool prog
      3: tracepoint  name tracepoint__irq  tag f677a7dd722299a3
          loaded_at Oct 26/11:39  uid 0
          xlated 160B  not jited  memlock 4096B  map_ids 4
          pinned /sys/fs/bpf/softirq_prog
      
      4: tracepoint  name tracepoint__irq  tag ea5dc530d00b92b6
          loaded_at Oct 26/11:39  uid 0
          xlated 392B  not jited  memlock 4096B  map_ids 4,6
      
      root@test# ./bpftool --json --pretty prog
      [{
              "id": 3,
              "type": "tracepoint",
              "name": "tracepoint__irq",
              "tag": "f677a7dd722299a3",
              "loaded_at": "Oct 26/11:39",
              "uid": 0,
              "bytes_xlated": 160,
              "jited": false,
              "bytes_memlock": 4096,
              "map_ids": [4
              ],
              "pinned": ["/sys/fs/bpf/softirq_prog"
              ]
          },{
              "id": 4,
              "type": "tracepoint",
              "name": "tracepoint__irq",
              "tag": "ea5dc530d00b92b6",
              "loaded_at": "Oct 26/11:39",
              "uid": 0,
              "bytes_xlated": 392,
              "jited": false,
              "bytes_memlock": 4096,
              "map_ids": [4,6
              ],
              "pinned": []
          }
      ]
      
      root@test# ./bpftool map
      4: hash  name start  flags 0x0
          key 4B  value 16B  max_entries 10240  memlock 1003520B
          pinned /sys/fs/bpf/softirq_map1
      5: hash  name iptr  flags 0x0
          key 4B  value 8B  max_entries 10240  memlock 921600B
      
      root@test# ./bpftool --json --pretty map
      [{
              "id": 4,
              "type": "hash",
              "name": "start",
              "flags": 0,
              "bytes_key": 4,
              "bytes_value": 16,
              "max_entries": 10240,
              "bytes_memlock": 1003520,
              "pinned": ["/sys/fs/bpf/softirq_map1"
              ]
          },{
              "id": 5,
              "type": "hash",
              "name": "iptr",
              "flags": 0,
              "bytes_key": 4,
              "bytes_value": 8,
              "max_entries": 10240,
              "bytes_memlock": 921600,
              "pinned": []
          }
      ]
      Signed-off-by: default avatarPrashant Bhole <bhole_prashant_q7@lab.ntt.co.jp>
      Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      4990f1f4
    • Prashant Bhole's avatar
      tools: bpftool: open pinned object without type check · 18527196
      Prashant Bhole authored
      This was needed for opening any file in bpf-fs without knowing
      its object type
      Signed-off-by: default avatarPrashant Bhole <bhole_prashant_q7@lab.ntt.co.jp>
      Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      18527196
    • David S. Miller's avatar
      Merge branch 'BPF-directed-error-injection' · 329fca60
      David S. Miller authored
      Josef Bacik says:
      
      ====================
      Add the ability to do BPF directed error injection
      
      I'm sending this through Dave since it'll conflict with other BPF changes in his
      tree, but since it touches tracing as well Dave would like a review from
      somebody on the tracing side.
      
      v4->v5:
      - disallow kprobe_override programs from being put in the prog map array so we
        don't tail call into something we didn't check.  This allows us to make the
        normal path still fast without a bunch of percpu operations.
      
      v3->v4:
      - fix a build error found by kbuild test bot (I didn't wait long enough
        apparently.)
      - Added a warning message as per Daniels suggestion.
      
      v2->v3:
      - added a ->kprobe_override flag to bpf_prog.
      - added some sanity checks to disallow attaching bpf progs that have
        ->kprobe_override set that aren't for ftrace kprobes.
      - added the trace_kprobe_ftrace helper to check if the trace_event_call is a
        ftrace kprobe.
      - renamed bpf_kprobe_state to bpf_kprobe_override, fixed it so we only read this
        value in the kprobe path, and thus only write to it if we're overriding or
        clearing the override.
      
      v1->v2:
      - moved things around to make sure that bpf_override_return could really only be
        used for an ftrace kprobe.
      - killed the special return values from trace_call_bpf.
      - renamed pc_modified to bpf_kprobe_state so bpf_override_return could tell if
        it was being called from an ftrace kprobe context.
      - reworked the logic in kprobe_perf_func to take advantage of bpf_kprobe_state.
      - updated the test as per Alexei's review.
      
      - Original message -
      
      A lot of our error paths are not well tested because we have no good way of
      injecting errors generically.  Some subystems (block, memory) have ways to
      inject errors, but they are random so it's hard to get reproduceable results.
      
      With BPF we can add determinism to our error injection.  We can use kprobes and
      other things to verify we are injecting errors at the exact case we are trying
      to test.  This patch gives us the tool to actual do the error injection part.
      It is very simple, we just set the return value of the pt_regs we're given to
      whatever we provide, and then override the PC with a dummy function that simply
      returns.
      
      Right now this only works on x86, but it would be simple enough to expand to
      other architectures.  Thanks,
      ====================
      Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      329fca60
    • Josef Bacik's avatar
      samples/bpf: add a test for bpf_override_return · eafb3401
      Josef Bacik authored
      This adds a basic test for bpf_override_return to verify it works.  We
      override the main function for mounting a btrfs fs so it'll return
      -ENOMEM and then make sure that trying to mount a btrfs fs will fail.
      Acked-by: default avatarAlexei Starovoitov <ast@kernel.org>
      Signed-off-by: default avatarJosef Bacik <jbacik@fb.com>
      Acked-by: default avatarDaniel Borkmann <daniel@iogearbox.net>
      Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      eafb3401
    • Josef Bacik's avatar
      bpf: add a bpf_override_function helper · dd0bb688
      Josef Bacik authored
      Error injection is sloppy and very ad-hoc.  BPF could fill this niche
      perfectly with it's kprobe functionality.  We could make sure errors are
      only triggered in specific call chains that we care about with very
      specific situations.  Accomplish this with the bpf_override_funciton
      helper.  This will modify the probe'd callers return value to the
      specified value and set the PC to an override function that simply
      returns, bypassing the originally probed function.  This gives us a nice
      clean way to implement systematic error injection for all of our code
      paths.
      Acked-by: default avatarAlexei Starovoitov <ast@kernel.org>
      Signed-off-by: default avatarJosef Bacik <jbacik@fb.com>
      Acked-by: default avatarDaniel Borkmann <daniel@iogearbox.net>
      Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      dd0bb688
  2. 10 Nov, 2017 18 commits
    • Girish Moodalbail's avatar
      net: fix incorrect comment with regard to VLAN packet handling · 54985120
      Girish Moodalbail authored
      The commit bcc6d479 ("net: vlan: make non-hw-accel rx path similar
      to hw-accel") unified accel and non-accel path for VLAN RX. With that
      fix we do not register any packet_type handler for VLANs anymore, so fix
      the incorrect comment.
      Signed-off-by: default avatarGirish Moodalbail <girish.moodalbail@oracle.com>
      Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      54985120
    • David S. Miller's avatar
      Merge branch 'act_vlan-rcu' · b79c069a
      David S. Miller authored
      Manish Kurup says:
      
      ====================
      net_sched actions: act_vlan now uses RCU
      
      This commit consists of 3 patches:
      
      patch1 (1/3):
      The VLAN action maintains one set of stats across all cores, and uses a
      spinlock to synchronize updates to it from the same. Changed this to use a
      per-CPU stats context instead.
      This change will result in better performance.
      
      patch2 (2/3):
      Modified netronome nfp flower action to use VLAN helper functions instead
      of accessing/referencing TC act_vlan private structures directly.
      
      patch3 (3/3):
      Using a spinlock in the VLAN action causes performance issues when the VLAN
      action is used on multiple cores. Rewrote the VLAN action to use RCU read
      locking for reads and updates instead.
      All functions now use an RCU dereferenced pointer to access the VLAN action
      context. Modified helper functions used by other modules, to use the RCU as
      opposed to directly accessing the structure.
      
      As part of this review, there were some changes suggested by reviewers.
      I have incorporated all the changes that were requested.
      
      Here're the changes:
      v2: Fixed all helper functions to use RCU (rtnl_dereference) - Eric, Jamal
      v2: Fixed indentation, extra line nits - Jamal, Jiri
      v2: Moved rcu_head to the end of the struct - Jiri
      v2: Re-formatted locals to reverse-christmas-tree - Jiri
      v2: Removed mismatched spin_lock() - Cong
      v2: Removed spin_lock_bh() in tcf_vlan_init, rtnl_dereference() should
          suffice - Cong, Jiri
      v4: Modified the nfp flower action code to use the VLAN helper functions
          instead of referencing the structure directly. Isolated this into a
          separate patch - Pieter Jansen
      v5: Got rid of the unlikely() for the allocation case - Simon Horman
      v6: Had forgotten cleanup functions for RCU alloc, added them - Dave Miller
      v7: Re-formatted more locals to reverse-christmas-tree - Pieter V
      v8: Reverted reverse-christmas-tree(v7), not required when dependencies
          make it difficult to implement - Alexander D
      v9: Cover letter subject change - Jamal
      ====================
      Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      b79c069a
    • Manish Kurup's avatar
      act_vlan: VLAN action rewrite to use RCU lock/unlock and update · 4c5b9d96
      Manish Kurup authored
      Using a spinlock in the VLAN action causes performance issues when the VLAN
      action is used on multiple cores. Rewrote the VLAN action to use RCU read
      locking for reads and updates instead.
      All functions now use an RCU dereferenced pointer to access the VLAN action
      context. Modified helper functions used by other modules, to use the RCU as
      opposed to directly accessing the structure.
      Acked-by: default avatarJamal Hadi Salim <jhs@mojatatu.com>
      Acked-by: default avatarJiri Pirko <jiri@mellanox.com>
      Signed-off-by: default avatarManish Kurup <manish.kurup@verizon.com>
      Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      4c5b9d96
    • Manish Kurup's avatar
      nfp flower action: Modified to use VLAN helper functions · bf068bdd
      Manish Kurup authored
      Modified netronome nfp flower action to use VLAN helper functions instead
      of accessing/referencing TC act_vlan private structures directly.
      Reviewed-by: default avatarPieter Jansen van Vuuren <pieter.jansenvanvuuren@netronome.com>
      Signed-off-by: default avatarManish Kurup <manish.kurup@verizon.com>
      Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      bf068bdd
    • Manish Kurup's avatar
      act_vlan: Change stats update to use per-core stats · e0496cbb
      Manish Kurup authored
      The VLAN action maintains one set of stats across all cores, and uses a
      spinlock to synchronize updates to it from the same. Changed this to use a
      per-CPU stats context instead.
      This change will result in better performance.
      Acked-by: default avatarJamal Hadi Salim <jhs@mojatatu.com>
      Acked-by: default avatarJiri Pirko <jiri@mellanox.com>
      Signed-off-by: default avatarManish Kurup <manish.kurup@verizon.com>
      Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      e0496cbb
    • Robert Stonehouse's avatar
      sfc: don't warn on successful change of MAC · cbad52e9
      Robert Stonehouse authored
      Fixes: 535a6177 ("sfc: suppress handled MCDI failures when changing the MAC address")
      Signed-off-by: default avatarBert Kenward <bkenward@solarflare.com>
      Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      cbad52e9
    • Colin Ian King's avatar
      net: vxge: remove redundant assignments and pointers · e4effc09
      Colin Ian King authored
      There are several pointers that are being assigned but never read
      so remove these as they are redundant.  Also remove an assignment
      to function_mode that is never read. Cleans up several clang
      warnings:
      
      vxge-main.c:1139:2: warning: Value stored to 'hldev' is never read
      vxge-main.c:1294:2: warning: Value stored to 'hldev' is never read
      vxge-main.c:2188:2: warning: Value stored to 'dev' is never read
      vxge-main.c:2188:2: warning: Value stored to 'dev' is never read
      vxge-main.c:2723:2: warning: Value stored to 'function_mode' is
      never read
      Signed-off-by: default avatarColin Ian King <colin.king@canonical.com>
      Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      e4effc09
    • David S. Miller's avatar
      Merge branch 'ip_gre-flags-update' · be61a484
      David S. Miller authored
      Xin Long says:
      
      ====================
      ip_gre: add support for i/o_flags update
      
      ip_gre is using as many ip_tunnel apis as possible, newlink works
      fine as gre would do it's own part in .ndo_init. But when changing
      link, ip_tunnel_changelink doesn't even update i/o_flags, and also
      the update of these flags would cause some other gre's properties
      need to be updated or recalculated.
      
      These two patch are to add i/o_flags update and then do adjustment
      on some gre's properties according to the new i/o_flags.
      ====================
      Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      be61a484
    • Xin Long's avatar
      ip_gre: add the support for i/o_flags update via ioctl · a0efab67
      Xin Long authored
      As patch 'ip_gre: add the support for i/o_flags update via netlink'
      did for netlink, we also need to do the same job for these update
      via ioctl.
      
      This patch is to update i/o_flags and call ipgre_link_update to
      recalculate these gre properties after ip_tunnel_ioctl does the
      common update.
      Signed-off-by: default avatarXin Long <lucien.xin@gmail.com>
      Acked-by: default avatarWilliam Tu <u9012063@gmail.com>
      Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      a0efab67
    • Xin Long's avatar
      ip_gre: add the support for i/o_flags update via netlink · dd9d598c
      Xin Long authored
      Now ip_gre is using ip_tunnel_changelink to update it's properties, but
      ip_tunnel_changelink in ip_tunnel doesn't update i/o_flags as a common
      function.
      
      o_flags updates would cause that tunnel->tun_hlen / hlen and dev->mtu /
      needed_headroom need to be recalculated, and dev->(hw_)features need to
      be updated as well.
      
      Therefore, we can't just add the update into ip_tunnel_update called
      in ip_tunnel_changelink, and it's also better not to touch ip_tunnel
      codes.
      
      This patch updates i/o_flags and calls ipgre_link_update to recalculate
      these gre properties after ip_tunnel_changelink does the common update.
      
      Note that since ipgre_link_update doesn't know the lower dev, it will
      update gre->hlen, dev->mtu and dev->needed_headroom with the value of
      'new tun_hlen - old tun_hlen'. In this way, we can avoid many redundant
      codes, unlike ip6_gre.
      Reported-by: default avatarJianlin Shi <jishi@redhat.com>
      Signed-off-by: default avatarXin Long <lucien.xin@gmail.com>
      Acked-by: default avatarWilliam Tu <u9012063@gmail.com>
      Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      dd9d598c
    • David S. Miller's avatar
      Merge branch 'tcp-ns-rmem-wmem' · c7947e43
      David S. Miller authored
      Eric Dumazet says:
      
      ====================
      net: Namespace-ify sysctl_tcp_rmem and sysctl_tcp_wmem
      
      We need to get per netns sysctl for sysctl_[proto]_rmem and sysctl_[proto]_wmem
      
      This patch series adds the basic infrastructure allowing per proto
      conversion, and takes care of TCP.
      ====================
      Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      c7947e43
    • Eric Dumazet's avatar
      tcp: Namespace-ify sysctl_tcp_rmem and sysctl_tcp_wmem · 356d1833
      Eric Dumazet authored
      Note that when a new netns is created, it inherits its
      sysctl_tcp_rmem and sysctl_tcp_wmem from initial netns.
      
      This change is needed so that we can refine TCP rcvbuf autotuning,
      to take RTT into consideration.
      Signed-off-by: default avatarEric Dumazet <edumazet@google.com>
      Cc: Wei Wang <weiwan@google.com>
      Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      356d1833
    • Eric Dumazet's avatar
      net: allow per netns sysctl_rmem and sysctl_wmem for protos · a3dcaf17
      Eric Dumazet authored
      As we want to gradually implement per netns sysctl_rmem and sysctl_wmem
      on per protocol basis, add two new fields in struct proto,
      and two new helpers : sk_get_wmem0() and sk_get_rmem0()
      
      First user will be TCP. Then UDP and SCTP can be easily converted,
      while DECNET probably wont get this support.
      Signed-off-by: default avatarEric Dumazet <edumazet@google.com>
      Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      a3dcaf17
    • Andrew Lunn's avatar
      net: dsa: Don't add vlans when vlan filtering is disabled · 2ea7a679
      Andrew Lunn authored
      The software bridge can be build with vlan filtering support
      included. However, by default it is turned off. In its turned off
      state, it still passes VLANs via switchev, even though they are not to
      be used. Don't pass these VLANs to the hardware. Only do so when vlan
      filtering is enabled.
      
      This fixes at least one corner case. There are still issues in other
      corners, such as when vlan_filtering is later enabled.
      Signed-off-by: default avatarAndrew Lunn <andrew@lunn.ch>
      Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      2ea7a679
    • David S. Miller's avatar
      Merge tag 'mlx5-updates-2017-11-09' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux · 4fdc3023
      David S. Miller authored
      Saeed Mahameed says:
      
      ====================
      mlx5-updates-2017-11-09
      
      This series introduces vlan offloads related improvements for mlx5
      ethernet netdev driver, from Gal Pressman.
      
       - Add support for 802.1ad vlan filter
       - Add support for 802.1ad vlan insertion
       - Add vlan offloads statistics to ethtool (inserted/stripped vlans)
       - CHECKSUM_COMPLETE support for vlan traffic when vlan stripping is off! (Finally)
      ====================
      Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      4fdc3023
    • David S. Miller's avatar
      Merge branch 'IGMP-snooping-for-local-traffic' · 5d37636a
      David S. Miller authored
      Andrew Lunn says:
      
      ====================
      IGMP snooping for local traffic
      
      The linux bridge supports IGMP snooping. It will listen to IGMP
      reports on bridge ports and keep track of which groups have been
      joined on an interface. It will then forward multicast based on this
      group membership.
      
      When the bridge adds or removed groups from an interface, it uses
      switchdev to request the hardware add an mdb to a port, so the
      hardware can perform the selective forwarding between ports.
      
      What is not covered by the current bridge code, is IGMP joins/leaves
      from the host on the brX interface. These are not reported via
      switchdev so that hardware knows the local host is interested in the
      multicast frames.
      
      Luckily, the bridge does track joins/leaves on the brX interface. The
      code is obfusticated, which is why i missed it with my first attempt.
      So the first patch tries to remove this obfustication. Currently,
      there is no notifications sent when the bridge interface joins a
      group. The second patch adds them. bridge monitor then shows
      joins/leaves in the same way as for other ports of the bridge.
      
      Then starts the work passing down to the hardware that the host has
      joined/left a group. The existing switchdev mdb object cannot be used,
      since the semantics are different. The existing
      SWITCHDEV_OBJ_ID_PORT_MDB is used to indicate a specific multicast
      group should be forwarded out that port of the switch. However here we
      require the exact opposite. We want multicast frames for the group
      received on the port to the forwarded to the host. Hence add a new
      object SWITCHDEV_OBJ_ID_HOST_MDB, a multicast database entry to
      forward to the host. This new object is then propagated through the
      DSA layers. No DSA driver changes should be needed, this should just
      work...
      
      This version fixes up the nitpick from Nikolay, removes an unrelated
      white space change, and adds in a patch adding a few const attributes
      to a couple of functions taking a port parameter, in order to stop the
      following patch produces warnings.
      ====================
      Acked-by: default avatarStephen Hemminger <stephen@networkplumber.org>
      Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      5d37636a
    • Andrew Lunn's avatar
      net: dsa: switch: Don't add CPU port to an mdb by default · ae45102c
      Andrew Lunn authored
      Now that the host indicates when a multicast group should be forwarded
      from the switch to the host, don't do it by default.
      Signed-off-by: default avatarAndrew Lunn <andrew@lunn.ch>
      Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      ae45102c
    • Andrew Lunn's avatar
      net: dsa: add more const attributes · bb9f6031
      Andrew Lunn authored
      The notify mechanism does not need to modify the port it is notifying.
      So make the parameter const.
      Signed-off-by: default avatarAndrew Lunn <andrew@lunn.ch>
      Reviewed-by: default avatarVivien Didelot <vivien.didelot@savoirfairelinux.com>
      Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      bb9f6031