)]}'
{
  "log": [
    {
      "commit": "9b93ab981e3bf62ff95a8cbb6faf652cd400decd",
      "tree": "34e27bb7871cc59e32d92c0d721d5d386c02db74",
      "parents": [
        "4484e2994887cf57815c8e55ac1f9eaf0036928e"
      ],
      "author": {
        "name": "Gal Pressman",
        "email": "galp@mellanox.com",
        "time": "Tue Nov 28 11:58:51 2017 +0200"
      },
      "committer": {
        "name": "Saeed Mahameed",
        "email": "saeedm@mellanox.com",
        "time": "Fri Dec 29 00:43:52 2017 +0200"
      },
      "message": "net/mlx5: Separate ingress/egress namespaces for each vport\n\nEach vport has its own root flow table for the ACL flow tables and root\nflow table is per namespace, therefore we should create a namespace for\neach vport.\n\nFixes: efdc810ba39d (\"net/mlx5: Flow steering, Add vport ACL support\")\nSigned-off-by: Gal Pressman \u003cgalp@mellanox.com\u003e\nSigned-off-by: Saeed Mahameed \u003csaeedm@mellanox.com\u003e\n"
    },
    {
      "commit": "508541146af18e43072e41a31aa62fac2b01aac1",
      "tree": "b5fd1b410d40c8ef481bf7c2428789f25e0d51b9",
      "parents": [
        "5360fd473c23f18b42722cdb13a1c6ec7acd96ff"
      ],
      "author": {
        "name": "Yishai Hadas",
        "email": "yishaih@mellanox.com",
        "time": "Tue Apr 25 10:39:57 2017 +0300"
      },
      "committer": {
        "name": "Saeed Mahameed",
        "email": "saeedm@mellanox.com",
        "time": "Sun May 14 13:33:45 2017 +0300"
      },
      "message": "net/mlx5: Use underlay QPN from the root name space\n\nRoot flow table is dynamically changed by the underlying flow steering\nlayer, and IPoIB/ULPs have no idea what will be the root flow table in\nthe future, hence we need a dynamic infrastructure to move Underlay QPs\nwith the root flow table.\n\nFixes: b3ba51498bdd (\"net/mlx5: Refactor create flow table method to accept underlay QP\")\nSigned-off-by: Erez Shitrit \u003cerezsh@mellanox.com\u003e\nSigned-off-by: Maor Gottlieb \u003cmaorg@mellanox.com\u003e\nSigned-off-by: Yishai Hadas \u003cyishaih@mellanox.com\u003e\nSigned-off-by: Saeed Mahameed \u003csaeedm@mellanox.com\u003e\n"
    },
    {
      "commit": "b3ba51498bddd72a526d9067b8b0ecf4932ce57e",
      "tree": "1695700d639997c8d2b6ac84d9616a9deec0cb4f",
      "parents": [
        "500a3d0ded5ee41072d0f084bff938747ee0c125"
      ],
      "author": {
        "name": "Erez Shitrit",
        "email": "erezsh@mellanox.com",
        "time": "Thu Apr 13 06:36:52 2017 +0300"
      },
      "committer": {
        "name": "David S. Miller",
        "email": "davem@davemloft.net",
        "time": "Mon Apr 17 11:08:29 2017 -0400"
      },
      "message": "net/mlx5: Refactor create flow table method to accept underlay QP\n\nIB flow tables need the underlay qp to perform flow steering.\nHere we change the API of the flow tables creation to accept the\nunderlay QP number as a parameter in order to support IB (IPoIB) flow\nsteering.\n\nSigned-off-by: Erez Shitrit \u003cerezsh@mellanox.com\u003e\nSigned-off-by: Saeed Mahameed \u003csaeedm@mellanox.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n"
    },
    {
      "commit": "2a69cb9ff7caac00f3bf7c865964228dd2a0c415",
      "tree": "4bce548234a8528d93558c5f7fb67818d708c765",
      "parents": [
        "a750276f81918294a5cb0ffa37686cf25314cf53"
      ],
      "author": {
        "name": "Or Gerlitz",
        "email": "ogerlitz@mellanox.com",
        "time": "Thu Jan 19 19:31:25 2017 +0200"
      },
      "committer": {
        "name": "Saeed Mahameed",
        "email": "saeedm@mellanox.com",
        "time": "Tue Mar 28 15:34:04 2017 +0300"
      },
      "message": "net/mlx5: Introduce modify header structures, commands and steering action definitions\n\nAdd the definitions related to creation/deletion of a modify header\ncontext and the modify header steering action which are used for HW\npacket header modify (re-write) as part of steering. Add as well the\nmodify header id into two intermediate structs and set it to the FTE.\n\nNote that as the push/pop vlan steering actions are emulated by the\newitch management code, we\u0027re not breaking any compatibility while\nchanging their values to make room for the modify header action which\nis not emulated and whose value is part of the FW API. The new bit\nvalues for the emulated actions are at the end of the possible range.\n\nSigned-off-by: Or Gerlitz \u003cogerlitz@mellanox.com\u003e\nReviewed-by: Hadar Hen Zion \u003chadarh@mellanox.com\u003e\nSigned-off-by: Saeed Mahameed \u003csaeedm@mellanox.com\u003e\n"
    },
    {
      "commit": "e753b2b50dc3c6582e9d5971555693db41a6d821",
      "tree": "d0e3eb99fca8fd2b5ed684c07e5f4849e1ee78af",
      "parents": [
        "aa0cbbae5d360ea23a15038d24f6f7c9573eecaf"
      ],
      "author": {
        "name": "Or Gerlitz",
        "email": "ogerlitz@mellanox.com",
        "time": "Wed Feb 01 19:01:18 2017 +0200"
      },
      "committer": {
        "name": "Saeed Mahameed",
        "email": "saeedm@mellanox.com",
        "time": "Tue Mar 28 15:34:01 2017 +0300"
      },
      "message": "net/mlx5: Add helper to initialize a flow steering actions struct instance\n\nThere are bunch of places in the code where the intermediate struct\nthat keeps the elements related to flow actions is initialized with\nthe same default values. Put that into a small DECLARE type helper.\n\nThis patch doesn\u0027t change any functionality.\n\nSigned-off-by: Or Gerlitz \u003cogerlitz@mellanox.com\u003e\nReviewed-by: Hadar Hen Zion \u003chadarh@mellanox.com\u003e\nSigned-off-by: Saeed Mahameed \u003csaeedm@mellanox.com\u003e\n"
    },
    {
      "commit": "66958ed906b87816314c0517f05fe0b5766ec7fe",
      "tree": "510ff1d5fada4353baebb2acc584666bc39f5c56",
      "parents": [
        "c9f1b073d0d750ccf8b30b272d1d76479f4cccbc"
      ],
      "author": {
        "name": "Hadar Hen Zion",
        "email": "hadarh@mellanox.com",
        "time": "Mon Nov 07 15:14:45 2016 +0200"
      },
      "committer": {
        "name": "David S. Miller",
        "email": "davem@davemloft.net",
        "time": "Wed Nov 09 13:41:56 2016 -0500"
      },
      "message": "net/mlx5: Support encap id when setting new steering entry\n\nIn order to support steering rules which add encapsulation headers,\nencap_id parameter is needed.\n\nAdd new mlx5_flow_act struct which holds action related parameter:\naction, flow_tag and encap_id. Use mlx5_flow_act struct when adding a new\nsteering rule.\nThis patch doesn\u0027t change any functionality.\n\nSigned-off-by: Hadar Hen Zion \u003chadarh@mellanox.com\u003e\nSigned-off-by: Saeed Mahameed \u003csaeedm@mellanox.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n"
    },
    {
      "commit": "c9f1b073d0d750ccf8b30b272d1d76479f4cccbc",
      "tree": "459a294de042444ac8103e9ea6ed8efaea1ac4a2",
      "parents": [
        "43f93839e359c8044200ec3f6fa455b47ba3aa2c"
      ],
      "author": {
        "name": "Hadar Hen Zion",
        "email": "hadarh@mellanox.com",
        "time": "Mon Nov 07 15:14:44 2016 +0200"
      },
      "committer": {
        "name": "David S. Miller",
        "email": "davem@davemloft.net",
        "time": "Wed Nov 09 13:41:56 2016 -0500"
      },
      "message": "net/mlx5: Add creation flags when adding new flow table\n\nWhen creating flow tables, allow the caller to specify creation flags.\nCurrently no flags are used and as such this patch doesn\u0027t add any new\nfunctionality.\n\nSigned-off-by: Hadar Hen Zion \u003chadarh@mellanox.com\u003e\nSigned-off-by: Saeed Mahameed \u003csaeedm@mellanox.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n"
    },
    {
      "commit": "74491de937125d0c98c9b9c9208b4105717a3caa",
      "tree": "6e65856d0f70d4b93dd6e3e51429b54bd4e52702",
      "parents": [
        "a62249857779733dc7cb5d43d6ecdc35fa81b88f"
      ],
      "author": {
        "name": "Mark Bloch",
        "email": "markb@mellanox.com",
        "time": "Wed Aug 31 11:24:25 2016 +0000"
      },
      "committer": {
        "name": "Leon Romanovsky",
        "email": "leon@kernel.org",
        "time": "Sun Oct 30 15:43:17 2016 +0200"
      },
      "message": "net/mlx5: Add multi dest support\n\nCurrently when calling mlx5_add_flow_rule we accept\nonly one flow destination, this commit allows to pass\nmultiple destinations.\n\nThis change forces us to change the return structure to a more\nflexible one. We introduce a flow handle (struct mlx5_flow_handle),\nit holds internally the number for rules created and holds an array\nwhere each cell points the to a flow rule.\n\nFrom the consumers (of mlx5_add_flow_rule) point of view this\nchange is only cosmetic and requires only to change the type\nof the returned value they store.\n\nFrom the core point of view, we now need to use a loop when\nallocating and deleting rules (e.g given to us a flow handler).\n\nSigned-off-by: Mark Bloch \u003cmarkb@mellanox.com\u003e\nSigned-off-by: Saeed Mahameed \u003csaeedm@mellanox.com\u003e\nSigned-off-by: Leon Romanovsky \u003cleon@kernel.org\u003e\n"
    },
    {
      "commit": "87d22483ce68e609818d61e3a65361f5634c6cd6",
      "tree": "b842f7bc6c6f10b54bb6f20a920f5bb5203a9a0b",
      "parents": [
        "cea824d416522ce63d83b45fc0dc53c0f5b68cee"
      ],
      "author": {
        "name": "Maor Gottlieb",
        "email": "maorg@mellanox.com",
        "time": "Mon Jun 06 18:09:35 2016 +0300"
      },
      "committer": {
        "name": "Leon Romanovsky",
        "email": "leon@kernel.org",
        "time": "Thu Aug 18 18:49:59 2016 +0300"
      },
      "message": "net/mlx5: Add sniffer namespaces\n\nAdd sniffer TX and RX namespaces to receive ingoing and outgoing\ntraffic.\n\nEach outgoing/incoming packet is duplicated and steered to the sniffer\nTX/RX namespace in addition to the regular flow.\n\nSigned-off-by: Maor Gottlieb \u003cmaorg@mellanox.com\u003e\nSigned-off-by: Saeed Mahameed \u003csaeedm@mellanox.com\u003e\nSigned-off-by: Leon Romanovsky \u003cleon@kernel.org\u003e\n"
    },
    {
      "commit": "3e75d4ebaae7aac5ba82fc7a6e0e6fb56dac1916",
      "tree": "40d519a9323d06e8004bf1f7a4f0ccf74bbfc134",
      "parents": [
        "aaff1bea16bb7f259a263c3ae4633d092e2da799"
      ],
      "author": {
        "name": "Aviv Heller",
        "email": "avivh@mellanox.com",
        "time": "Mon May 09 10:02:29 2016 +0000"
      },
      "committer": {
        "name": "Leon Romanovsky",
        "email": "leon@kernel.org",
        "time": "Thu Aug 18 18:49:57 2016 +0300"
      },
      "message": "net/mlx5: Add LAG flow steering namespace\n\nThis namespace is used for LAG demux flowtable.\n\nThe idea is to position the LAG demux ft between\nbypass and kernel flowtables, allowing raw-eth\ntraffic from both ports to be received by the PF0\nIB device.\n\nSigned-off-by: Aviv Heller \u003cavivh@mellanox.com\u003e\nReviewed-by: Maor Gottlieb \u003cmaorg@mellanox.com\u003e\nSigned-off-by: Saeed Mahameed \u003csaeedm@mellanox.com\u003e\nSigned-off-by: Leon Romanovsky \u003cleon@kernel.org\u003e\n"
    },
    {
      "commit": "aaff1bea16bb7f259a263c3ae4633d092e2da799",
      "tree": "6c4f82ed6a6abac3f8c95eaf020dbca0ebee5b66",
      "parents": [
        "edb31b1686751f605eb02a6dcf5ef29c5d485a8e"
      ],
      "author": {
        "name": "Aviv Heller",
        "email": "avivh@mellanox.com",
        "time": "Mon May 09 09:57:05 2016 +0000"
      },
      "committer": {
        "name": "Leon Romanovsky",
        "email": "leon@kernel.org",
        "time": "Thu Aug 18 18:49:56 2016 +0300"
      },
      "message": "net/mlx5: LAG demux flow table support\n\nAdd interfaces to allow the creation and destruction of a\nLAG demux flow table.\n\nIt is a special flow table used during LAG for redirecting\nnon user-mode packets from PF0 to PF1 root ft, if a packet was\nreceived on phys port two.\n\nSigned-off-by: Aviv Heller \u003cavivh@mellanox.com\u003e\nReviewed-by: Maor Gottlieb \u003cmaorg@mellanox.com\u003e\nSigned-off-by: Saeed Mahameed \u003csaeedm@mellanox.com\u003e\nSigned-off-by: Leon Romanovsky \u003cleon@kernel.org\u003e\n"
    },
    {
      "commit": "6dc6071cfcde6cf687f8d288c9cef9ee6ee24dc7",
      "tree": "e9a4b2d401edb2d4f857f7f85825002965087bee",
      "parents": [
        "0da2d66666d32769fa0aebb5f1d2d0a86be6c5d2"
      ],
      "author": {
        "name": "Maor Gottlieb",
        "email": "maorg@mellanox.com",
        "time": "Mon Jul 04 17:23:08 2016 +0300"
      },
      "committer": {
        "name": "David S. Miller",
        "email": "davem@davemloft.net",
        "time": "Tue Jul 05 00:06:02 2016 -0700"
      },
      "message": "net/mlx5e: Add ethtool flow steering support\n\nImplement etrhtool set_rxnfc callback to support ethtool flow spec\ndirect steering. This patch adds only the support of ether flow type\nspec. L3/L4 flow specs support will be added in downstream patches.\n\nSigned-off-by: Maor Gottlieb \u003cmaorg@mellanox.com\u003e\nSigned-off-by: Saeed Mahameed \u003csaeedm@mellanox.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n"
    },
    {
      "commit": "c5bb17302e734967822be559cf661704b707b4ed",
      "tree": "5fe959504ac3236a3c7bafb9bd9401f5fec0c26e",
      "parents": [
        "019d0c99364a818eb08f52d7ee4b75ea6df07d09"
      ],
      "author": {
        "name": "Maor Gottlieb",
        "email": "maorg@mellanox.com",
        "time": "Mon Jul 04 17:23:05 2016 +0300"
      },
      "committer": {
        "name": "David S. Miller",
        "email": "davem@davemloft.net",
        "time": "Tue Jul 05 00:06:02 2016 -0700"
      },
      "message": "net/mlx5: Refactor mlx5_add_flow_rule\n\nReduce the set of arguments passed to mlx5_add_flow_rule\nby introducing flow_spec structure.\n\nSigned-off-by: Maor Gottlieb \u003cmaorg@mellanox.com\u003e\nSigned-off-by: Saeed Mahameed \u003csaeedm@mellanox.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n"
    },
    {
      "commit": "acbc2004d7129a1ecf02414c1da8808bdc06d5a2",
      "tree": "95890f06922fb5eea82e92a0bb378d915ffac1d8",
      "parents": [
        "ab22be9ba30a08482b2c2effb36ac3f0ed3df465"
      ],
      "author": {
        "name": "Or Gerlitz",
        "email": "ogerlitz@mellanox.com",
        "time": "Fri Jul 01 14:50:58 2016 +0300"
      },
      "committer": {
        "name": "David S. Miller",
        "email": "davem@davemloft.net",
        "time": "Sat Jul 02 14:40:39 2016 -0400"
      },
      "message": "net/mlx5: Introduce offloads steering namespace\n\nAdd a new namespace (MLX5_FLOW_NAMESPACE_OFFLOADS) to be populated\nwith flow steering rules that deal with rules that have have to\nbe executed before the EN NIC steering rules are matched.\n\nThe namespace is located after the bypass name-space and before the\nkernel name-space. Therefore, it precedes the HW processing done for\nrules set for the kernel NIC name-space.\n\nUnder SRIOV, it would allow us to match on e-switch missed packet\nand forward them to the relevant VF representor TIR.\n\nSigned-off-by: Or Gerlitz \u003cogerlitz@mellanox.com\u003e\nSigned-off-by: Amir Vadai \u003camir@vadai.me\u003e\nSigned-off-by: Saeed Mahameed \u003csaeedm@mellanox.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n"
    },
    {
      "commit": "43a335e055bb7ebdc8a68ce7362ef26ef5bda92b",
      "tree": "0441f14934b5e341f12df45bc86bbca9c3dc3d03",
      "parents": [
        "bd5251dbf156b6bc0661a9409d46e47160df61dd"
      ],
      "author": {
        "name": "Amir Vadai",
        "email": "amirva@mellanox.com",
        "time": "Fri May 13 12:55:41 2016 +0000"
      },
      "committer": {
        "name": "David S. Miller",
        "email": "davem@davemloft.net",
        "time": "Mon May 16 13:43:51 2016 -0400"
      },
      "message": "net/mlx5_core: Flow counters infrastructure\n\nIf a counter has the aging flag set when created, it is added to a list\nof counters that will be queried periodically from a workqueue.  query\nresult and last use timestamp are cached.\nadd/del counter must be very efficient since thousands of such\noperations might be issued in a second.\nThere is only a single reference to counters without aging, therefore\nno need for locks.\nBut, counters with aging enabled are stored in a list. In order to make\ncode as lockless as possible, all the list manipulation and access to\nhardware is done from a single context - the periodic counters query\nthread.\n\nThe hardware supports multiple counters per FTE, however currently we\nare using one counter for each FTE.\n\nSigned-off-by: Amir Vadai \u003camirva@mellanox.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n"
    },
    {
      "commit": "bd5251dbf156b6bc0661a9409d46e47160df61dd",
      "tree": "4d2fa3780ab1a0c30c6b1814245e84fe1b69e22c",
      "parents": [
        "9dc0b289c4c09bc1a92bdcc055cb37af9b72eb28"
      ],
      "author": {
        "name": "Amir Vadai",
        "email": "amirva@mellanox.com",
        "time": "Fri May 13 12:55:40 2016 +0000"
      },
      "committer": {
        "name": "David S. Miller",
        "email": "davem@davemloft.net",
        "time": "Mon May 16 13:43:51 2016 -0400"
      },
      "message": "net/mlx5_core: Introduce flow steering destination of type counter\n\nWhen adding a flow steering rule with a counter, need to supply a\ndestination of type MLX5_FLOW_DESTINATION_TYPE_COUNTER, with a pointer\nto a struct mlx5_fc.\nAlso, MLX5_FLOW_CONTEXT_ACTION_COUNT bit should be set in the action.\n\nSigned-off-by: Amir Vadai \u003camirva@mellanox.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n"
    },
    {
      "commit": "efdc810ba39dae0ccce9cb9c1c84ff9b0157ca43",
      "tree": "0f52fbc9ee304e8b367249f5e3752341fbe7916f",
      "parents": [
        "fbc4a69b562e38d6946bc8bd7e97d30fe0acd5d0"
      ],
      "author": {
        "name": "Mohamad Haj Yahia",
        "email": "mohamad@mellanox.com",
        "time": "Tue May 03 17:13:54 2016 +0300"
      },
      "committer": {
        "name": "David S. Miller",
        "email": "davem@davemloft.net",
        "time": "Wed May 04 14:04:46 2016 -0400"
      },
      "message": "net/mlx5: Flow steering, Add vport ACL support\n\nUpdate the relevant flow steering device structs and commands to\nsupport vport.\nUpdate the flow steering core API to receive vport number.\nAdd ingress and egress ACL flow table name spaces.\nAdd ACL flow table support:\n* ACL (Access Control List) flow table is a table that contains\nonly allow/drop steering rules.\n\n* We have two types of ACL flow tables - ingress and egress.\n\n* ACLs handle traffic sent from/to E-Switch FDB table, Ingress refers to\ntraffic sent from Vport to E-Switch and Egress refers to traffic sent\nfrom E-Switch to vport.\n\n* Ingress ACL flow table allow/drop rules is checked against traffic\nsent from VF.\n\n* Egress ACL flow table allow/drop rules is checked against traffic sent\nto VF.\n\nSigned-off-by: Mohamad Haj Yahia \u003cmohamad@mellanox.com\u003e\nSigned-off-by: Saeed Mahameed \u003csaeedm@mellanox.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n"
    },
    {
      "commit": "d63cd28608bb563d52e62990fa01c016e8dbdb75",
      "tree": "d3b42d39a1a4129c127e09f928f27f04f06ba96b",
      "parents": [
        "a257b94a18f7eb60bbe9b5fd415d208ac71d49ea"
      ],
      "author": {
        "name": "Maor Gottlieb",
        "email": "maorg@mellanox.com",
        "time": "Fri Apr 29 01:36:35 2016 +0300"
      },
      "committer": {
        "name": "David S. Miller",
        "email": "davem@davemloft.net",
        "time": "Fri Apr 29 16:29:09 2016 -0400"
      },
      "message": "net/mlx5: Add user chosen levels when allocating flow tables\n\nCurrently, consumers of the flow steering infrastructure can\u0027t\nchoose their own flow table levels and are limited to one\nflow table per level. This just waste levels.\nInstead, we introduce here the possibility to use multiple\nflow tables in a level. The user is free to connect these\nflow tables, while following the rule (FTEs in FT of level x\ncould only point to FTs of level y where y \u003e x).\n\nIn addition this patch switch the order of the create/destroy\nflow tables of the NIC(vlan and main).\n\nSigned-off-by: Maor Gottlieb \u003cmaorg@mellanox.com\u003e\nSigned-off-by: Saeed Mahameed \u003csaeedm@mellanox.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n"
    },
    {
      "commit": "d745098cedb3f5c6a554796d4a3a505abd4ebaa6",
      "tree": "c3ce6883c3163e39f5664f255ce1a6a36feaf7ed",
      "parents": [
        "1da366964ec907fccdea0339d81c2e9ef3d803f8"
      ],
      "author": {
        "name": "Maor Gottlieb",
        "email": "maorg@mellanox.com",
        "time": "Fri Apr 29 01:36:33 2016 +0300"
      },
      "committer": {
        "name": "David S. Miller",
        "email": "davem@davemloft.net",
        "time": "Fri Apr 29 16:29:08 2016 -0400"
      },
      "message": "net/mlx5: Introduce modify flow rule destination\n\nThis API is used for modifying the flow rule destination.\nThis is needed for modifying the pointed flow table by the\ntraffic type classifier rules to point on the aRFS tables.\n\nSigned-off-by: Maor Gottlieb \u003cmaorg@mellanox.com\u003e\nSigned-off-by: Saeed Mahameed \u003csaeedm@mellanox.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n"
    },
    {
      "commit": "b3638e1a76648dbd482cc5a8f27eb6948cc3bc86",
      "tree": "2e4ee030ec36f1bf2492564968b3d33a1c809f00",
      "parents": [
        "153fefbf34e5079c2dd69490f5f23373758d2e9c"
      ],
      "author": {
        "name": "Maor Gottlieb",
        "email": "maorg@mellanox.com",
        "time": "Mon Mar 07 18:51:46 2016 +0200"
      },
      "committer": {
        "name": "Doug Ledford",
        "email": "dledford@redhat.com",
        "time": "Thu Mar 10 09:22:06 2016 -0500"
      },
      "message": "net/mlx5_core: Introduce forward to next priority action\n\nAdd support to create flow rule that forward packets\nto the first flow table in the next priority (next priority\ncould be the first priority in the next namespace or the\nnext priority in the same namespace).\nThis feature could be used for DONT_TRAP rules or rules\nthat only want to mark the packet with flow tag.\n\nIn order to do it optimally, each flow table has list\nof all rules that point to this flow table,\nwhen a flow table is destroyed/created, we update the list\nhead correspondingly.\n\nThis kind of rule is created when destination is NULL and\naction is MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO.\n\nSigned-off-by: Maor Gottlieb \u003cmaorg@mellanox.com\u003e\nReviewed-by: Matan Barak \u003cmatanb@mellanox.com\u003e\nSigned-off-by: Doug Ledford \u003cdledford@redhat.com\u003e\n"
    },
    {
      "commit": "153fefbf34e5079c2dd69490f5f23373758d2e9c",
      "tree": "ec529dd63611b40a6c54a39ff835e794eb0a9867",
      "parents": [
        "0e451e883bd13ce616f439e2414b8c17fa28318a"
      ],
      "author": {
        "name": "Maor Gottlieb",
        "email": "maorg@mellanox.com",
        "time": "Mon Mar 07 18:51:45 2016 +0200"
      },
      "committer": {
        "name": "Doug Ledford",
        "email": "dledford@redhat.com",
        "time": "Thu Mar 10 09:22:06 2016 -0500"
      },
      "message": "net/mlx5_core: Create anchor of last flow table\n\nCreate an empty flow table in the end of NIC rx namesapce.\nAdding this flow table simplify the implementation of \"forward\nto next prio\" rules.\n\nSigned-off-by: Maor Gottlieb \u003cmaorg@mellanox.com\u003e\nReviewed-by: Matan Barak \u003cmatanb@mellanox.com\u003e\nSigned-off-by: Doug Ledford \u003cdledford@redhat.com\u003e\n"
    },
    {
      "commit": "038d2ef87572757861a177b19f9d489def2c48b8",
      "tree": "04ab4306825571d353669cd2f92dfe1dd9257ec2",
      "parents": [
        "b217ea25afd8910e7ec0abb556bcb312d397c8a6"
      ],
      "author": {
        "name": "Maor Gottlieb",
        "email": "maorg@mellanox.com",
        "time": "Mon Jan 11 10:26:07 2016 +0200"
      },
      "committer": {
        "name": "David S. Miller",
        "email": "davem@davemloft.net",
        "time": "Mon Jan 11 17:48:53 2016 -0500"
      },
      "message": "IB/mlx5: Add flow steering support\n\nAdding flow steering support by creating a flow-table per\npriority (if rules exist in the priority). mlx5_ib uses\nautogrouping and thus only creates the required destinations.\n\nAlso includes adding of these flow steering utilities\n\n1. Parsing verbs flow attributes hardware steering specs.\n\n2. Check if flow is multicast - this is required in order to decide\nto which flow table will we add the steering rule.\n\n3. Set outer headers in flow match criteria to zeros.\n\nSigned-off-by: Maor Gottlieb \u003cmaorg@mellanox.com\u003e\nSigned-off-by: Moni Shoua \u003cmonis@mellanox.com\u003e\nSigned-off-by: Matan Barak \u003cmatanb@mellanox.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n"
    },
    {
      "commit": "4cbdd30ed5c8bc5cf40813b025b4fb57b376a592",
      "tree": "361753a5341684d8ce0480b8df210b58dce55e3b",
      "parents": [
        "8d40d162c014dc3be316c5950b382d608aa2c8de"
      ],
      "author": {
        "name": "Maor Gottlieb",
        "email": "maorg@mellanox.com",
        "time": "Mon Jan 11 10:26:04 2016 +0200"
      },
      "committer": {
        "name": "David S. Miller",
        "email": "davem@davemloft.net",
        "time": "Mon Jan 11 17:48:53 2016 -0500"
      },
      "message": "net/mlx5_core: Enable flow steering support for the IB driver\n\nWhen the driver is loaded, we create flow steering namespace\nfor kernel bypass with nine priorities and another namespace\nfor leftovers(in order to catch packets that weren\u0027t matched).\nVerbs applications will use these priorities.\nwe found nine as a number that balances the requirements from the\nuser and retains performance.\n\nThe bypass namespace is used by verbs applications that want to bypass\nthe kernel networking stack. The leftovers namespace is used by verbs\napplications and the sniffer in order to catch packets that weren\u0027t\nhandled by any preceding rules.\n\nSigned-off-by: Maor Gottlieb \u003cmaorg@mellanox.com\u003e\nSigned-off-by: Moni Shoua \u003cmonis@mellanox.com\u003e\nSigned-off-by: Matan Barak \u003cmatanb@mellanox.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n"
    },
    {
      "commit": "f0d22d1874730530a2ac304fd0888cb8a6864527",
      "tree": "eb6cbc01671d019638ac125a2bfb4953131b1877",
      "parents": [
        "23c09c2640c1cb9cba919cf4f181ae99a46d53bc"
      ],
      "author": {
        "name": "Maor Gottlieb",
        "email": "maorg@mellanox.com",
        "time": "Mon Jan 11 10:25:57 2016 +0200"
      },
      "committer": {
        "name": "David S. Miller",
        "email": "davem@davemloft.net",
        "time": "Mon Jan 11 17:48:52 2016 -0500"
      },
      "message": "net/mlx5_core: Introduce flow steering autogrouped flow table\n\nWhen user add rule to autogrouped flow table, we search\nfor flow group with the same match criteria, if we don\u0027t\nfind such group then we create new flow group with the\nrequired match criteria and insert the rule to this group.\n\nWe divide the flow table into required_groups + 1,\nin order to reserve a part of the flow table for rules\nwhich don\u0027t match any existing group.\n\nSigned-off-by: Maor Gottlieb \u003cmaorg@mellanox.com\u003e\nSigned-off-by: Moni Shoua \u003cmonis@mellanox.com\u003e\nSigned-off-by: Matan Barak \u003cmatanb@mellanox.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n"
    },
    {
      "commit": "86d722ad2c3bd2f0536b196b7fd67ae2a7e2a492",
      "tree": "47690b3e2490ac45a9c15abc7a73f36124611f6e",
      "parents": [
        "2530236303d9e705db6a28eb9a10c8d79b288b37"
      ],
      "author": {
        "name": "Maor Gottlieb",
        "email": "maorg@mellanox.com",
        "time": "Thu Dec 10 17:12:44 2015 +0200"
      },
      "committer": {
        "name": "David S. Miller",
        "email": "davem@davemloft.net",
        "time": "Sat Dec 12 00:15:24 2015 -0500"
      },
      "message": "net/mlx5: Use flow steering infrastructure for mlx5_en\n\nExpose the new flow steering API and remove the old\none.\n\nFew changes are required:\n\n1. The Ethernet flow steering follows the existing implementation, but uses\nthe new steering API. The old flow steering implementation is removed.\n\n2. Move the E-switch FDB management to use the new API.\n\n3. When driver is loaded call to mlx5_init_fs which initialize\nthe flow steering tree structure, open namespaces for NIC receive\nand for E-switch FDB.\n\n4. Call to mlx5_cleanup_fs when the driver is unloaded.\n\nSigned-off-by: Maor Gottlieb \u003cmaorg@mellanox.com\u003e\nSigned-off-by: Moni Shoua \u003cmonis@mellanox.com\u003e\nSigned-off-by: Matan Barak \u003cmatanb@mellanox.com\u003e\nSigned-off-by: Saeed Mahameed \u003csaeedm@mellanox.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n"
    },
    {
      "commit": "2530236303d9e705db6a28eb9a10c8d79b288b37",
      "tree": "aa1da81cbec8394d7b2dfe52b059c61f43d6d208",
      "parents": [
        "0c56b97503fdf027488897db5709e2557aa1592a"
      ],
      "author": {
        "name": "Maor Gottlieb",
        "email": "maorg@mellanox.com",
        "time": "Thu Dec 10 17:12:43 2015 +0200"
      },
      "committer": {
        "name": "David S. Miller",
        "email": "davem@davemloft.net",
        "time": "Sat Dec 12 00:15:24 2015 -0500"
      },
      "message": "net/mlx5_core: Flow steering tree initialization\n\nFlow steering initialization is based on static tree which\nillustrates the flow steering tree when the driver is loaded. The\ninitialization considers the max supported flow table level of the device,\na minimum of 2 kernel flow tables(vlan and mac) are required to have\nkernel flow table functionality.\n\nThe tree structures when the driver is loaded:\n\n\t\troot_namespace(receive nic)\n\t\t\t  |\n\t\tpriority-0 (kernel priority)\n\t\t\t  |\n\t\tnamespace(kernel namespace)\n\t\t\t  |\n\t\tpriority-0 (flow tables priority)\n\nIn the following patches, When the EN driver will use the flow steering\nAPI, it create two flow tables and their flow groups under\npriority-0(flow tables priority).\n\nSigned-off-by: Maor Gottlieb \u003cmaorg@mellanox.com\u003e\nSigned-off-by: Moni Shoua \u003cmonis@mellanox.com\u003e\nSigned-off-by: Matan Barak \u003cmatanb@mellanox.com\u003e\nSigned-off-by: Saeed Mahameed \u003csaeedm@mellanox.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n"
    },
    {
      "commit": "26a8145390b36cbe97a5bd0b9e97249f21af6aea",
      "tree": "79c633614e4d561294002d7806f2662e9bddfc66",
      "parents": [
        "108805fc196e001053e9e7c76f259977804dc0d6"
      ],
      "author": {
        "name": "Maor Gottlieb",
        "email": "maorg@mellanox.com",
        "time": "Thu Dec 10 17:12:39 2015 +0200"
      },
      "committer": {
        "name": "David S. Miller",
        "email": "davem@davemloft.net",
        "time": "Sat Dec 12 00:15:23 2015 -0500"
      },
      "message": "net/mlx5_core: Introduce flow steering firmware commands\n\nIntroduce new Flow Steering (FS) firmware commands,\nin-order to support the new flow steering infrastructure.\n\nSigned-off-by: Maor Gottlieb \u003cmaorg@mellanox.com\u003e\nSigned-off-by: Moni Shoua \u003cmonis@mellanox.com\u003e\nSigned-off-by: Matan Barak \u003cmatanb@mellanox.com\u003e\nSigned-off-by: Saeed Mahameed \u003csaeedm@mellanox.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n"
    }
  ]
}