)]}' { "log": [ { "commit": "955154fa33df2b74f0fea8e7c84df6dfd954dab2", "tree": "c53021a647f2587d29f451b9e8b4b24d645a70d8", "parents": [ "23537b732f5dd9c917767419272aeb65cc4b8cfd" ], "author": { "name": "Matan Barak", "email": "matanb@mellanox.com", "time": "Wed Jan 30 23:07:10 2013 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Thu Jan 31 12:48:47 2013 -0500" }, "message": "net/mlx4_en: Don\u0027t reassign port mac address on firmware that supports it\n\nMac reassignments should only be done when not supported by the firmware. To\naccomplish that, checking firmware capability bit to know whether we should\nreassign macs in the driver.\n\nSigned-off-by: Matan Barak \u003cmatanb@mellanox.com\u003e\nSigned-off-by: Amir Vadai \u003camirv@mellanox.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "23537b732f5dd9c917767419272aeb65cc4b8cfd", "tree": "db8b3f67a283122a364d1f6176be6eb58969a12f", "parents": [ "0d256c0e93916f416f46d2ec235ea05fca202ede" ], "author": { "name": "Hadar Hen Zion", "email": "hadarh@mellanox.com", "time": "Wed Jan 30 23:07:09 2013 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Thu Jan 31 12:48:47 2013 -0500" }, "message": "net/mlx4_core: Use firmware driven flow steering hash mode\n\nThe Firmware dynamically changes flow steering hash configuration from covering\nL2 only to \"full\" L2/L3/L4 mode needed. The dynamic change allows the driver\nto set hard coded hash configuration which is changed by the firmware from L2\nto L2/L3/L4 when attaching the first L3/L4 flow steering rule and back to L2\nwhen there are no more such rules.\n\nSigned-off-by: Hadar Hen Zion \u003chadarh@mellanox.com\u003e\nSigned-off-by: Amir Vadai \u003camirv@mellanox.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "0d256c0e93916f416f46d2ec235ea05fca202ede", "tree": "64c3883ddcdce138d7371e5af98d081c3a7197e6", "parents": [ "280fce1e3ef85ff7f90a9d7e8c8a0d71bbf5a9a4" ], "author": { "name": "Hadar Hen Zion", "email": "hadarh@mellanox.com", "time": "Wed Jan 30 23:07:08 2013 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Thu Jan 31 12:48:47 2013 -0500" }, "message": "net/mlx4_en: Fix ethtool rules leftovers after module unloaded\n\nAs part of the driver unload flow, all steering rules must be deleted,\nmake sure to remove the rules that were set through ethtool.\n\nSigned-off-by: Hadar Hen Zion \u003chadarh@mellanox.com\u003e\nSigned-off-by: Amir Vadai \u003camirv@mellanox.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "280fce1e3ef85ff7f90a9d7e8c8a0d71bbf5a9a4", "tree": "f90e8fc37a4100effa770b5b302e641d4af6f95d", "parents": [ "8258bd2713c3e42bc0e5664cbede0e07587c125f" ], "author": { "name": "Hadar Hen Zion", "email": "hadarh@mellanox.com", "time": "Wed Jan 30 23:07:07 2013 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Thu Jan 31 12:48:47 2013 -0500" }, "message": "net/mlx4_en: Block insertion of ethtool steering rules while the interface is down\n\nAttaching steering rules while the interface is down is an invalid operation, block it.\n\nSigned-off-by: Hadar Hen Zion \u003chadarh@mellanox.com\u003e\nSigned-off-by: Amir Vadai \u003camirv@mellanox.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "8258bd2713c3e42bc0e5664cbede0e07587c125f", "tree": "de8f4d4f4a18003df648592283194ceb264bc145", "parents": [ "69d7126b7fef09beaa4b7c103ec2a5bd8c8b2666" ], "author": { "name": "Hadar Hen Zion", "email": "hadarh@mellanox.com", "time": "Wed Jan 30 23:07:06 2013 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Thu Jan 31 12:48:47 2013 -0500" }, "message": "net/mlx4_en: Fix vlan mask for ethtool steering rules\n\nThe vlan mask field should be validated and assigned according to the field\nsize which is 12 bits. Also replace the numeric 0xfff mask with existing kernel\nmacro.\n\nSigned-off-by: Hadar Hen Zion \u003chadarh@mellanox.com\u003e\nSigned-off-by: Amir Vadai \u003camirv@mellanox.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "69d7126b7fef09beaa4b7c103ec2a5bd8c8b2666", "tree": "15f525f1d31bb6cadc47ed766d6552de2ddef1ef", "parents": [ "f90a36734a6a0d843baa37b7caa1ef020f799d47" ], "author": { "name": "Hadar Hen Zion", "email": "hadarh@mellanox.com", "time": "Wed Jan 30 23:07:05 2013 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Thu Jan 31 12:48:46 2013 -0500" }, "message": "net/mlx4_en: Validate VLAN IDs provided in ethtool flow steering rules\n\nWhen attaching flow steering rules via Ethtool accept only valid vlans IDs e.g\nin the range: [0,4095].\n\nSigned-off-by: Hadar Hen Zion \u003chadarh@mellanox.com\u003e\nSigned-off-by: Amir Vadai \u003camirv@mellanox.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "f90a36734a6a0d843baa37b7caa1ef020f799d47", "tree": "9bf21e86f331a6719cfa7b324a6b2702c82a5030", "parents": [ "248c62aa12a318fe53bf4f530b69b150c34416e7" ], "author": { "name": "Hadar Hen Zion", "email": "hadarh@mellanox.com", "time": "Wed Jan 30 23:07:04 2013 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Thu Jan 31 12:48:46 2013 -0500" }, "message": "net/mlx4_en: Fix ip/udp steering rules multicast mac when attached via ethtool\n\nDestination mac is a mandatory specification for ip/udp steering rules.\nWhen attaching multicast steering rules via ethtool the unicast mac of the\ninterface was added to the rule specification instead of the multicast mac.\nThe following commit sets the corresponding multicast mac for the rule multicast ip.\n\nSigned-off-by: Hadar Hen Zion \u003chadarh@mellanox.com\u003e\nSigned-off-by: Amir Vadai \u003camirv@mellanox.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "248c62aa12a318fe53bf4f530b69b150c34416e7", "tree": "e5867de8102b81cecf9cb1b6b6d71a725ee4c2bf", "parents": [ "015465f85193fdc3a0debb1c9176433ba19140b2" ], "author": { "name": "Hadar Hen Zion", "email": "hadarh@mellanox.com", "time": "Wed Jan 30 23:07:03 2013 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Thu Jan 31 12:48:46 2013 -0500" }, "message": "net/mlx4_core: Set correctly allow_loopback flag\n\nThe allow_loopback flag was wrongly set using arithmetic bit operation, change\nthe code to use logical bit operation.\n\nSigned-off-by: Hadar Hen Zion \u003chadarh@mellanox.com\u003e\nSigned-off-by: Amir Vadai \u003camirv@mellanox.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "015465f85193fdc3a0debb1c9176433ba19140b2", "tree": "daf121f5fd3e2859321c7047c75905c2c341f88c", "parents": [ "1b13c97fae9c61dc20db8e0d0a72a29df29ac377" ], "author": { "name": "Hadar Hen Zion", "email": "hadarh@mellanox.com", "time": "Wed Jan 30 23:07:02 2013 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Thu Jan 31 12:48:46 2013 -0500" }, "message": "net/mlx4_core: Directly expose fields of HW flow steering rule control segment\n\nSome of the fields for struct mlx4_net_trans_rule_hw_ctrl were packed into u32\nand accessed through bit field operations. Expose and access them directly as\nu8.\n\nSigned-off-by: Hadar Hen Zion \u003chadarh@mellanox.com\u003e\nSigned-off-by: Amir Vadai \u003camirv@mellanox.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "1b13c97fae9c61dc20db8e0d0a72a29df29ac377", "tree": "a0c13a66ebb5da43f79bef2b9a83b1d1eb7b3c18", "parents": [ "c33e7b05f1411b97cd0260ae682fc1cdb27bfaa4" ], "author": { "name": "Yan Burman", "email": "yanb@mellanox.com", "time": "Tue Jan 29 23:43:07 2013 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Wed Jan 30 22:47:22 2013 -0500" }, "message": "net/vxlan: Add ethtool drvinfo\n\nImplement ethtool get_drvinfo.\n\nSigned-off-by: Yan Burman \u003cyanb@mellanox.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "c33e7b05f1411b97cd0260ae682fc1cdb27bfaa4", "tree": "d00958e4600cbef4a45b4622df6b3a9c4e205fa4", "parents": [ "18367681a10bd29c3f2305e6b7b984de5b33d548" ], "author": { "name": "YOSHIFUJI Hideaki / 吉藤英明", "email": "yoshfuji@linux-ipv6.org", "time": "Wed Jan 30 09:27:58 2013 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Wed Jan 30 22:41:13 2013 -0500" }, "message": "ipv6 anycast: Convert ipv6_sk_ac_lock to spinlock.\n\nSince all users are write-lock, it does not make sense to use\nrwlock here. Use simple spinlock.\n\nSigned-off-by: YOSHIFUJI Hideaki \u003cyoshfuji@linux-ipv6.org\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "18367681a10bd29c3f2305e6b7b984de5b33d548", "tree": "9c651ed8531fef6c7985548330cbe69576e0eb41", "parents": [ "d3aedd5ebd4b0b925b0bcda548066803e1318499" ], "author": { "name": "YOSHIFUJI Hideaki / 吉藤英明", "email": "yoshfuji@linux-ipv6.org", "time": "Wed Jan 30 09:27:52 2013 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Wed Jan 30 22:41:13 2013 -0500" }, "message": "ipv6 flowlabel: Convert np-\u003eipv6_fl_list to RCU.\n\nSigned-off-by: YOSHIFUJI Hideaki \u003cyoshfuji@linux-ipv6.org\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "d3aedd5ebd4b0b925b0bcda548066803e1318499", "tree": "d145189ad0a3192326d8df5b73188ec77ca942b7", "parents": [ "f256dc59d0729cf7d371b93062375d9bc79c1e44" ], "author": { "name": "YOSHIFUJI Hideaki / 吉藤英明", "email": "yoshfuji@linux-ipv6.org", "time": "Wed Jan 30 09:27:47 2013 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Wed Jan 30 22:41:13 2013 -0500" }, "message": "ipv6 flowlabel: Convert hash list to RCU.\n\nSigned-off-by: YOSHIFUJI Hideaki \u003cyoshfuji@linux-ipv6.org\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "f256dc59d0729cf7d371b93062375d9bc79c1e44", "tree": "59625bb29b227292b4fe2265f07147af35f9c560", "parents": [ "3b58908a92e00840bcd9050808f3dc86fd547029" ], "author": { "name": "YOSHIFUJI Hideaki / 吉藤英明", "email": "yoshfuji@linux-ipv6.org", "time": "Wed Jan 30 09:26:42 2013 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Wed Jan 30 22:41:12 2013 -0500" }, "message": "ipv6 flowlabel: Ensure to take lock when modifying np-\u003eip6_sk_fl_list.\n\nSigned-off-by: YOSHIFUJI Hideaki \u003cyoshfuji@linux-ipv6.org\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "3b58908a92e00840bcd9050808f3dc86fd547029", "tree": "3d3a2f97da69a5681a83cebf46e816e40670e34b", "parents": [ "45acd3a0a18c5692b34ee9091858c6f6c7b5d4a8" ], "author": { "name": "Eric Dumazet", "email": "edumazet@google.com", "time": "Wed Jan 30 17:51:44 2013 -0800" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Wed Jan 30 22:38:34 2013 -0500" }, "message": "x86: bpf_jit_comp: add pkt_type support\n\nSupporting access to skb-\u003epkt_type is a bit tricky if we want\nto have a generic code, allowing pkt_type to be moved in struct sk_buff\n\npkt_type is a bit field, so compiler cannot really help us to find\nits offset. Let\u0027s use a helper for this : It will throw a one time\nmessage if pkt_type no longer starts at a byte boundary or is\nno longer a 3bit field.\n\nReported-by: Willem de Bruijn \u003cwillemb@google.com\u003e\nSigned-off-by: Eric Dumazet \u003cedumazet@google.com\u003e\nCc: Maciej Żenczykowski \u003cmaze@google.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "45acd3a0a18c5692b34ee9091858c6f6c7b5d4a8", "tree": "bc25cc88dc3985f49bf5eb96bbc636d3274de78c", "parents": [ "fec9dd15d5bbea28297a53b138ed990e1bd48559" ], "author": { "name": "Jitendra Kalsaria", "email": "jitendra.kalsaria@qlogic.com", "time": "Wed Jan 30 12:47:19 2013 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Wed Jan 30 20:34:50 2013 -0500" }, "message": "qlcnic: Bump up the version to 5.1.33\n\nSigned-off-by: Jitendra Kalsaria \u003cjitendra.kalsaria@qlogic.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "fec9dd15d5bbea28297a53b138ed990e1bd48559", "tree": "2087c65296d1823f903c3a2a77e2fd654c291285", "parents": [ "22fd5ab4623883ea895e48b1288f97856294d17d" ], "author": { "name": "Stephen Hemminger", "email": "shemminger@vyatta.com", "time": "Wed Jan 30 12:47:18 2013 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Wed Jan 30 20:34:50 2013 -0500" }, "message": "qlcnic: make pci_error_handlers const\n\nSigned-off-by: Stephen Hemminger \u003cshemminger@vyatta.com\u003e\nSigned-off-by: Bjorn Helgaas \u003cbhelgaas@google.com\u003e\nSigned-off-by: Jitendra Kalsaria \u003cjitendra.kalsaria@qlogic.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "22fd5ab4623883ea895e48b1288f97856294d17d", "tree": "20d872f6c5cc9c5e47b40c102f569213b0804867", "parents": [ "4d53f40f541ab29c15982774abddbad4c361cc8c" ], "author": { "name": "Manish chopra", "email": "manish.chopra@qlogic.com", "time": "Wed Jan 30 12:47:17 2013 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Wed Jan 30 20:34:50 2013 -0500" }, "message": "qlcnic: Fix RX/TX checksum setting for some adapter types\n\nSigned-off-by: Manish chopra \u003cmanish.chopra@qlogic.com\u003e\nSigned-off-by: Jitendra Kalsaria \u003cjitendra.kalsaria@qlogic.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "4d53f40f541ab29c15982774abddbad4c361cc8c", "tree": "ca4509c790878d4b7638950c03f2735606be960e", "parents": [ "283c1c687051241e644af57bef7b6532cd65118a" ], "author": { "name": "Shahed Shaikh", "email": "shahed.shaikh@qlogic.com", "time": "Wed Jan 30 12:47:16 2013 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Wed Jan 30 20:34:50 2013 -0500" }, "message": "qlcnic: Fix minidump in NPAR mode\n\nSigned-off-by: Shahed Shaikh \u003cshahed.shaikh@qlogic.com\u003e\nSigned-off-by: Jitendra Kalsaria \u003cjitendra.kalsaria@qlogic.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "283c1c687051241e644af57bef7b6532cd65118a", "tree": "3f58307dc3dcc3dc32083746fa748a968b48fc14", "parents": [ "cdc84dda1e0214960df14aaee6708993b40e28f0" ], "author": { "name": "Manish chopra", "email": "manish.chopra@qlogic.com", "time": "Wed Jan 30 12:47:15 2013 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Wed Jan 30 20:34:50 2013 -0500" }, "message": "qlcnic: driver LRO bug fix\n\no ipv4 address was not getting programmed properly because of\n improper byte order conversion\n\nSigned-off-by: Manish chopra \u003cmanish.chopra@qlogic.com\u003e\nSigned-off-by: Jitendra Kalsaria \u003cjitendra.kalsaria@qlogic.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "cdc84dda1e0214960df14aaee6708993b40e28f0", "tree": "656230b8013c2365e618b13243ad1eee24cf213e", "parents": [ "1403f43a8fc8b1e1880b08a4c8a4ddac985171eb" ], "author": { "name": "Manish chopra", "email": "manish.chopra@qlogic.com", "time": "Wed Jan 30 12:47:14 2013 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Wed Jan 30 20:34:49 2013 -0500" }, "message": "qlcnic: Free irq for mailbox interrupts\n\nSigned-off-by: Manish chopra \u003cmanish.chopra@qlogic.com\u003e\nSigned-off-by: Jitendra Kalsaria \u003cjitendra.kalsaria@qlogic.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "1403f43a8fc8b1e1880b08a4c8a4ddac985171eb", "tree": "53377dd0fc01f66828fa4fbba9580a7f5658e97d", "parents": [ "069048f18bc51fbfd08d2e08a9003c2681ce44dd" ], "author": { "name": "Manish chopra", "email": "manish.chopra@qlogic.com", "time": "Wed Jan 30 12:47:13 2013 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Wed Jan 30 20:34:49 2013 -0500" }, "message": "qlcnic: Fix bug in reading HW reset template\n\nSigned-off-by: Manish chopra \u003cmanish.chopra@qlogic.com\u003e\nSigned-off-by: Jitendra Kalsaria \u003cjitendra.kalsaria@qlogic.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "069048f18bc51fbfd08d2e08a9003c2681ce44dd", "tree": "e9f02a2ffc56d80b7c011e8d6e7c1992f5c119a9", "parents": [ "409cc1f8a4149c26bbb8e5d3bacb36541ad371e2" ], "author": { "name": "Shahed Shaikh", "email": "shahed.shaikh@qlogic.com", "time": "Wed Jan 30 12:47:12 2013 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Wed Jan 30 20:34:49 2013 -0500" }, "message": "qlcnic: Fix sparse check endian warnings\n\nSigned-off-by: Shahed Shaikh \u003cshahed.shaikh@qlogic.com\u003e\nSigned-off-by: Jitendra Kalsaria \u003cjitendra.kalsaria@qlogic.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "409cc1f8a4149c26bbb8e5d3bacb36541ad371e2", "tree": "89049778a0b6126fd19dc806fafa192b3ef800fa", "parents": [ "d2ed273d30c5ffd14f6b5ec7ecc751d960f832fc" ], "author": { "name": "Jiri Pirko", "email": "jiri@resnulli.us", "time": "Wed Jan 30 11:08:11 2013 +0100" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Wed Jan 30 15:34:00 2013 -0500" }, "message": "bond: have random dev address by default instead of zeroes\n\nMakes more sense to have randomly generated address by default than to\nhave all zeroes. It also allows user to for example put the bond into\nbridge without need to have any slaves in it.\n\nAlso note that this changes only behaviour of bonds with no slaves. Once\nthe first slave device is enslaved, its address will be used (no change\nhere).\n\nAlso, fix dev_assign_type values on the way.\n\nReported-by: Pavel Šimerda \u003cpsimerda@redhat.com\u003e\nSigned-off-by: Jiri Pirko \u003cjiri@resnulli.us\u003e\nSigned-off-by: Jay Vosburgh \u003cfubar@us.ibm.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "d2ed273d30c5ffd14f6b5ec7ecc751d960f832fc", "tree": "3a127f68981cd7536303fb111ee2668af44003e9", "parents": [ "29e3b1608c8dca3ae4224a26862d18ea003ccee6" ], "author": { "name": "Michał Mirosław", "email": "mirq-linux@rere.qmqm.pl", "time": "Tue Jan 29 15:14:16 2013 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Tue Jan 29 22:58:40 2013 -0500" }, "message": "net: disallow drivers with buggy VLAN accel to register_netdevice()\n\nInstead of jumping aroung bugs that are easily fixed just don\u0027t let them in:\naffected drivers should be either fixed or have NETIF_F_HW_VLAN_FILTER\nremoved from advertised features.\n\nQuick grep in drivers/net shows two drivers that have NETIF_F_HW_VLAN_FILTER\nbut not ndo_vlan_rx_add/kill_vid(), but those are false-positives (features\nare commented out).\n\nOTOH two drivers have ndo_vlan_rx_add/kill_vid() implemented but don\u0027t\nadvertise NETIF_F_HW_VLAN_FILTER. Those are:\n\n+ethernet/cisco/enic/enic_main.c\n+ethernet/qlogic/qlcnic/qlcnic_main.c\n\nSigned-off-by: Michał Mirosław \u003cmirq-linux@rere.qmqm.pl\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "29e3b1608c8dca3ae4224a26862d18ea003ccee6", "tree": "f830a52bbf2eae7f6bbe9976ff8220d63df04a48", "parents": [ "d9e85655b5c9fcebf81aedc69182efbfdf4fe740" ], "author": { "name": "YOSHIFUJI Hideaki / 吉藤英明", "email": "yoshfuji@linux-ipv6.org", "time": "Tue Jan 29 12:49:03 2013 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Tue Jan 29 22:58:40 2013 -0500" }, "message": "netfilter ipset: Use ipv6_addr_equal() where appropriate.\n\nSigned-off-by: YOSHIFUJI Hideaki \u003cyoshfuji@linux-ipv6.org\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "d9e85655b5c9fcebf81aedc69182efbfdf4fe740", "tree": "5ac2f186fb1a6f44a161639f8950d0409a4ab008", "parents": [ "70e94e66aec255aff276397f5ed3f3626c548f1c" ], "author": { "name": "YOSHIFUJI Hideaki / 吉藤英明", "email": "yoshfuji@linux-ipv6.org", "time": "Tue Jan 29 12:48:58 2013 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Tue Jan 29 22:58:40 2013 -0500" }, "message": "netfilter ip6table_mangle: Use ipv6_addr_equal() where appropriate.\n\nSigned-off-by: YOSHIFUJI Hideaki \u003cyoshfuji@linux-ipv6.org\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "70e94e66aec255aff276397f5ed3f3626c548f1c", "tree": "f8a266b768f73394271a58a90b7d8375705079df", "parents": [ "ff88b30c717f21dffba6784cae4d3287da16f6ef" ], "author": { "name": "YOSHIFUJI Hideaki / 吉藤英明", "email": "yoshfuji@linux-ipv6.org", "time": "Tue Jan 29 12:48:50 2013 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Tue Jan 29 22:58:40 2013 -0500" }, "message": "xfrm: Convert xfrm_addr_cmp() to boolean xfrm_addr_equal().\n\nAll users of xfrm_addr_cmp() use its result as boolean.\nIntroduce xfrm_addr_equal() (which is equal to !xfrm_addr_cmp())\nand convert all users.\n\nSigned-off-by: YOSHIFUJI Hideaki \u003cyoshfuji@linux-ipv6.org\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "ff88b30c717f21dffba6784cae4d3287da16f6ef", "tree": "e7247eef942addb4210e3969b5655a6d43d753f6", "parents": [ "07c2fecc363c8f94a0bd2fdf9b7209ec6f5a0ab5" ], "author": { "name": "YOSHIFUJI Hideaki / 吉藤英明", "email": "yoshfuji@linux-ipv6.org", "time": "Tue Jan 29 12:48:31 2013 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Tue Jan 29 22:58:40 2013 -0500" }, "message": "xfrm: Use ipv6_addr_equal() where appropriate.\n\nSigned-off-by: YOSHIFUJI Hideaki \u003cyoshfuji@linux-ipv6.org\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "07c2fecc363c8f94a0bd2fdf9b7209ec6f5a0ab5", "tree": "13a4adfe52746981b88270d99634f2a3946d992e", "parents": [ "b53c47dd4fdb3f062c07b1ba8a7f9f80237be182" ], "author": { "name": "YOSHIFUJI Hideaki / 吉藤英明", "email": "yoshfuji@linux-ipv6.org", "time": "Tue Jan 29 12:48:23 2013 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Tue Jan 29 22:58:40 2013 -0500" }, "message": "ipv6 mcast: Use ipv6_addr_equal() in ip6_mc_source().\n\nSigned-off-by: YOSHIFUJI Hideaki \u003cyoshfuji@linux-ipv6.org\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "b53c47dd4fdb3f062c07b1ba8a7f9f80237be182", "tree": "f34f3c260c2f089f0ed89faeddba43771fd21694", "parents": [ "f1e7b73acc26e8908af783bcd3a9900fd80688f5", "a7966d908ae8472e8183496916b7baec5f65b3a6" ], "author": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Tue Jan 29 15:59:45 2013 -0500" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Tue Jan 29 15:59:45 2013 -0500" }, "message": "Merge tag \u0027batman-adv-for-davem\u0027 of git://git.open-mesh.org/linux-merge\n\nIncluded changes:\n- fix recently introduced output behaviour\n\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "f1e7b73acc26e8908af783bcd3a9900fd80688f5", "tree": "9a9382fb7f12f1889020efb4bffa3f4a88589fc5", "parents": [ "218774dc341f219bfcf940304a081b121a0e8099", "fc16e884a2320198b8cb7bc2fdcf6b4485e79709" ], "author": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Tue Jan 29 15:32:13 2013 -0500" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Tue Jan 29 15:32:13 2013 -0500" }, "message": "Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net\n\nBring in the \u0027net\u0027 tree so that we can get some ipv4/ipv6 bug\nfixes that some net-next work will build upon.\n\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "218774dc341f219bfcf940304a081b121a0e8099", "tree": "3dda133e7c1d25847198fc85108535f0b912a2ed", "parents": [ "ee873fda3bec7c668407b837fc5519eb961fcd37" ], "author": { "name": "Hannes Frederic Sowa", "email": "hannes@stressinduktion.org", "time": "Tue Jan 29 08:24:25 2013 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Tue Jan 29 15:22:03 2013 -0500" }, "message": "ipv6: add anti-spoofing checks for 6to4 and 6rd\n\nThis patch adds anti-spoofing checks in sit.c as specified in RFC3964\nsection 5.2 for 6to4 and RFC5969 section 12 for 6rd. I left out the\nchecks which could easily be implemented with netfilter.\n\nSpecifically this patch adds following logic (based loosely on the\npseudocode in RFC3964 section 5.2):\n\nif prefix (inner_src_v6) \u003d\u003d rd6_prefix (2002::/16 is the default)\n and outer_src_v4 !\u003d embedded_ipv4 (inner_src_v6)\n drop\nif prefix (inner_dst_v6) \u003d\u003d rd6_prefix (or 2002::/16 is the default)\n and outer_dst_v4 !\u003d embedded_ipv4 (inner_dst_v6)\n drop\naccept\n\nTo accomplish the specified security checks proposed by above RFCs,\nit is still necessary to employ uRPF filters with netfilter. These new\nchecks only kick in if the employed addresses are within the 2002::/16 or\nanother range specified by the 6rd-prefix (which defaults to 2002::/16).\n\nCc: YOSHIFUJI Hideaki \u003cyoshfuji@linux-ipv6.org\u003e\nCc: David Miller \u003cdavem@davemloft.net\u003e\nSigned-off-by: Hannes Frederic Sowa \u003channes@stressinduktion.org\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "ee873fda3bec7c668407b837fc5519eb961fcd37", "tree": "3743136009cf51fe350fdf984bc64ae8517ccc7c", "parents": [ "5fedcc14d40e355f966d46e6b19c209e2b36fd5b" ], "author": { "name": "Claudiu Manoil", "email": "claudiu.manoil@freescale.com", "time": "Tue Jan 29 03:55:12 2013 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Tue Jan 29 15:22:02 2013 -0500" }, "message": "gianfar: Pack struct gfar_priv_grp into three cachelines\n\n* remove unused members(!): imask, ievent\n* move space consuming interrupt name strings (int_name_* members) to\nexternal structures, unessential for the driver\u0027s hot path\n* keep high priority hot path data within the first 2 cache lines\n\nThis reduces struct gfar_priv_grp from 6 to 3 cache lines.\n(Also fixed checkpatch warnings for the old code, in the process.)\n\nSigned-off-by: Claudiu Manoil \u003cclaudiu.manoil@freescale.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "5fedcc14d40e355f966d46e6b19c209e2b36fd5b", "tree": "3b14f578829db22ad9c111222e07e1c54518a0f2", "parents": [ "0cd3fdea07d8e0f0f5bac7534892b785af37e387" ], "author": { "name": "Claudiu Manoil", "email": "claudiu.manoil@freescale.com", "time": "Tue Jan 29 03:55:11 2013 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Tue Jan 29 15:22:02 2013 -0500" }, "message": "gianfar: Cleanup gfar_parse_group() code\n\nFactor out redundant code (improve readability, source code size).\n\nSigned-off-by: Claudiu Manoil \u003cclaudiu.manoil@freescale.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "0cd3fdea07d8e0f0f5bac7534892b785af37e387", "tree": "0592b37e4c30e05db534d1ee4b87551fb131b1d3", "parents": [ "243bb4c6d731f886ac7a99b986e46625f0d5ba07" ], "author": { "name": "Claudiu Manoil", "email": "claudiu.manoil@freescale.com", "time": "Tue Jan 29 03:55:10 2013 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Tue Jan 29 15:22:02 2013 -0500" }, "message": "gianfar: Optimize struct gfar_priv_tx_q for two cache lines\n\nResize and regroup structure members to eliminate memory holes and\nto pack the structure into 2 cache lines (from 3).\ntx_ring_size was resized from 4 to 2 bytes and few members were re-grouped\nin order to eliminate byte holes and achieve compactness.\nWhere possible, few members were grouped according to their usage and access\norder (i.e. start_xmit vs. clean_tx_ring members), less important members\nwere pushed at the end.\n\nSigned-off-by: Claudiu Manoil \u003cclaudiu.manoil@freescale.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "243bb4c6d731f886ac7a99b986e46625f0d5ba07", "tree": "e633552080b9dadb1afcfb0cb5ace372655fff39", "parents": [ "4e58a0275015e5c8988bda9cd0635e2ef405c985" ], "author": { "name": "Eric W. Biederman", "email": "ebiederm@xmission.com", "time": "Tue Jan 29 02:16:18 2013 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Tue Jan 29 15:20:12 2013 -0500" }, "message": "ipv6: Fix inet6_csk_bind_conflict so it builds with user namespaces enabled\n\nWhen attempting to build linux-next with user namespaces enabled I ran\ninto this fun build error.\n\n CC net/ipv6/inet6_connection_sock.o\n.../net/ipv6/inet6_connection_sock.c: In function ‘inet6_csk_bind_conflict’:\n.../net/ipv6/inet6_connection_sock.c:37:12: error: incompatible types when initializing type ‘int’ using\n type ‘kuid_t’\n.../net/ipv6/inet6_connection_sock.c:54:30: error: incompatible type for argument 1 of ‘uid_eq’\n.../include/linux/uidgid.h:48:20: note: expected ‘kuid_t’ but argument is of type ‘int’\nmake[3]: *** [net/ipv6/inet6_connection_sock.o] Error 1\nmake[2]: *** [net/ipv6] Error 2\nmake[2]: *** Waiting for unfinished jobs....\n\nUsing kuid_t instead of int to hold the uid fixes this.\n\nCc: Tom Herbert \u003ctherbert@google.com\u003e\nSigned-off-by: \"Eric W. Biederman\" \u003cebiederm@xmission.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "4e58a0275015e5c8988bda9cd0635e2ef405c985", "tree": "743245c3e8b10fb83577b590579c3e593aa693c7", "parents": [ "dc975382d2ef36be7e78fac3717927de1a5abcd8" ], "author": { "name": "Cong Wang", "email": "amwang@redhat.com", "time": "Mon Jan 28 19:55:53 2013 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Tue Jan 29 15:17:46 2013 -0500" }, "message": "pktgen: support net namespace\n\nv3: make pktgen_threads list per-namespace\nv2: remove a useless check\n\nThis patch add net namespace to pktgen, so that\nwe can use pktgen in different namespaces.\n\nCc: Eric W. Biederman \u003cebiederm@xmission.com\u003e\nCc: David S. Miller \u003cdavem@davemloft.net\u003e\nSigned-off-by: Cong Wang \u003camwang@redhat.com\u003e\nAcked-by: \"Eric W. Biederman\" \u003cebiederm@xmission.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "dc975382d2ef36be7e78fac3717927de1a5abcd8", "tree": "e2910709c00adb07b4772351979bcd6213853403", "parents": [ "72aa8e1b29ecaed52a2a9ce1cb838563f9374007" ], "author": { "name": "Frank Li", "email": "Frank.Li@freescale.com", "time": "Mon Jan 28 18:31:42 2013 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Tue Jan 29 14:16:17 2013 -0500" }, "message": "net: fec: add napi support to improve proformance\n\nAdd napi support\n\nBefore this patch\n\n iperf -s -i 1\n ------------------------------------------------------------\n Server listening on TCP port 5001\n TCP window size: 85.3 KByte (default)\n ------------------------------------------------------------\n [ 4] local 10.192.242.153 port 5001 connected with 10.192.242.138 port 50004\n [ ID] Interval Transfer Bandwidth\n [ 4] 0.0- 1.0 sec 41.2 MBytes 345 Mbits/sec\n [ 4] 1.0- 2.0 sec 43.7 MBytes 367 Mbits/sec\n [ 4] 2.0- 3.0 sec 42.8 MBytes 359 Mbits/sec\n [ 4] 3.0- 4.0 sec 43.7 MBytes 367 Mbits/sec\n [ 4] 4.0- 5.0 sec 42.7 MBytes 359 Mbits/sec\n [ 4] 5.0- 6.0 sec 43.8 MBytes 367 Mbits/sec\n [ 4] 6.0- 7.0 sec 43.0 MBytes 361 Mbits/sec\n\nAfter this patch\n [ 4] 2.0- 3.0 sec 51.6 MBytes 433 Mbits/sec\n [ 4] 3.0- 4.0 sec 51.8 MBytes 435 Mbits/sec\n [ 4] 4.0- 5.0 sec 52.2 MBytes 438 Mbits/sec\n [ 4] 5.0- 6.0 sec 52.1 MBytes 437 Mbits/sec\n [ 4] 6.0- 7.0 sec 52.1 MBytes 437 Mbits/sec\n [ 4] 7.0- 8.0 sec 52.3 MBytes 439 Mbits/sec\n\nSigned-off-by: Frank Li \u003cFrank.Li@freescale.com\u003e\nSigned-off-by: Fugang Duan \u003cB38611@freescale.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "72aa8e1b29ecaed52a2a9ce1cb838563f9374007", "tree": "9a4fd32699cb18c3e6a11b0c2b169ccf79de8d92", "parents": [ "040468a0a7b3f9c7966126d98151bc64f1423657" ], "author": { "name": "Barry Grussling", "email": "barry@grussling.com", "time": "Sun Jan 27 18:44:36 2013 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Tue Jan 29 14:07:05 2013 -0500" }, "message": "ethoc: Cleanup driver format\n\nCleanup the format of ethoc.c to meet network driver style as\nper checkpatch.pl.\n\nSigned-off-by: Barry Grussling \u003cbarry@grussling.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "040468a0a7b3f9c7966126d98151bc64f1423657", "tree": "454a47cf1a533492017579efe7658fc3b8496922", "parents": [ "5c766d642bcaffd0c2a5b354db2068515b3846cf" ], "author": { "name": "David Ward", "email": "david.ward@ll.mit.edu", "time": "Sun Jan 27 13:04:58 2013 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Tue Jan 29 14:05:28 2013 -0500" }, "message": "ip_gre: When TOS is inherited, use configured TOS value for non-IP packets\n\nA GRE tunnel can be configured so that outgoing tunnel packets inherit\nthe value of the TOS field from the inner IP header. In doing so, when\na non-IP packet is transmitted through the tunnel, the TOS field will\nalways be set to 0.\n\nInstead, the user should be able to configure a different TOS value as\nthe fallback to use for non-IP packets. This is helpful when the non-IP\npackets are all control packets and should be handled by routers outside\nthe tunnel as having Internet Control precedence. One example of this is\nthe NHRP packets that control a DMVPN-compatible mGRE tunnel; they are\nencapsulated directly by GRE and do not contain an inner IP header.\n\nUnder the existing behavior, the IFLA_GRE_TOS parameter must be set to\n\u00271\u0027 for the TOS value to be inherited. Now, only the least significant\nbit of this parameter must be set to \u00271\u0027, and when a non-IP packet is\nsent through the tunnel, the upper 6 bits of this same parameter will be\ncopied into the TOS field. (The ECN bits get masked off as before.)\n\nThis behavior is backwards-compatible with existing configurations and\niproute2 versions.\n\nSigned-off-by: David Ward \u003cdavid.ward@ll.mit.edu\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "5c766d642bcaffd0c2a5b354db2068515b3846cf", "tree": "f5bb2ed37d70c79304c17911de77779ea92c1041", "parents": [ "5a1dc31708701e54db1b2bb80215c67d61505d3e" ], "author": { "name": "Jiri Pirko", "email": "jiri@resnulli.us", "time": "Thu Jan 24 09:41:41 2013 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Tue Jan 29 13:59:57 2013 -0500" }, "message": "ipv4: introduce address lifetime\n\nThere are some usecase when lifetime of ipv4 addresses might be helpful.\nFor example:\n1) initramfs networkmanager uses a DHCP daemon to learn network\nconfiguration parameters\n2) initramfs networkmanager addresses, routes and DNS configuration\n3) initramfs networkmanager is requested to stop\n4) initramfs networkmanager stops all daemons including dhclient\n5) there are addresses and routes configured but no daemon running. If\nthe system doesn\u0027t start networkmanager for some reason, addresses and\nroutes will be used forever, which violates RFC 2131.\n\nThis patch is essentially a backport of ivp6 address lifetime mechanism\nfor ipv4 addresses.\n\nCurrent \"ip\" tool supports this without any patch (since it does not\ndistinguish between ipv4 and ipv6 addresses in this perspective.\n\nAlso, this should be back-compatible with all current netlink users.\n\nReported-by: Pavel Šimerda \u003cpsimerda@redhat.com\u003e\nSigned-off-by: Jiri Pirko \u003cjiri@resnulli.us\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "5a1dc31708701e54db1b2bb80215c67d61505d3e", "tree": "3f0d424f598a82eb17a5199d27fec9964513e16e", "parents": [ "656a05c899b4026ee828ccddd550202ded7a26c6", "3ef0eb0db4bf92c6d2510fe5c4dc51852746f206" ], "author": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Tue Jan 29 13:37:29 2013 -0500" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Tue Jan 29 13:37:29 2013 -0500" }, "message": "Merge branch \u0027ipfrags\u0027\n\nJesper Dangaard Brouer says:\n\n\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\nThis patchset is V2, with some trivial code fixes, which were noticed\nby DaveM. It is still a partly respin of my fragmentation optimization\npatches: http://thread.gmane.org/gmane.linux.network/250914\n\nThis is not the complete patchset, from the gmane link above. In this\npatchset, I primarily focus on adjusting cacheline for better SMP/NUMA\nperformance.\n\nOnce this patchset have been agreed upon, I will continue and respin\nthe rest of my patches.\n\nThis time around, I have created a frag DoS generator, via the tool\ntrafgen (http://netsniff-ng.org/). To create a stable DoS scenario\n(no longer relying on frame dropping due to disabled flow-control).\n\nTwo 10G interfaces are under-test, and uses Ethernet flow-control. A\nthird interface is used for generating the DoS attack (this interface\nis also 10G, but it does not need to be, as 500Kpps DoS is enough).\n\nTest types summary (netperf):\n Test-20G64K \u003d\u003d 2x10G with 65K fragments\n Test-20G3F \u003d\u003d 2x10G with 3x fragments (3*1472 bytes)\n Test-20G64K+DoS \u003d\u003d Same as 20G64K with frag DoS\n Test-20G3F+DoS \u003d\u003d Same as 20G3F with frag DoS\n\nPatch list:\n Patch-01 - net: cacheline adjust struct netns_frags for better frag performance\n Patch-02 - net: cacheline adjust struct inet_frags for better frag performance\n Patch-03 - net: cacheline adjust struct inet_frag_queue\n Patch-04 - net: frag helper functions for mem limit tracking\n Patch-05 - net: use lib/percpu_counter API for fragmentation mem accounting\n Patch-06 - net: frag, move LRU list maintenance outside of rwlock\n\nPerformance table summary:\n\n Test-type: Test-20G64K Test-20G3F 20G64K+DoS 20G3F+DoS\n ---------- ----------- ---------- ---------- ---------\n net-next: 15114.5 Mbit/s 8954.21 2444.28 3918.01 Mbit/s\n Patch-01: 16075.8 Mbit/s 8976.18 2621.49 4072.79 Mbit/s\n Patch-02: 17806.9 Mbit/s 9280.32 2478.62 4274.59 Mbit/s\n Patch-03: 17317.4 Mbit/s 9308.62 2546.05 4336.59 Mbit/s\n Patch-04: 17635.9 Mbit/s 9256.16 2535.25 4327.63 Mbit/s\n Patch-05: 18027.0 Mbit/s 9918.99 2492.62 3621.68 Mbit/s\n Patch-06: 18486.7 Mbit/s 10723.20 3657.85 4560.64 Mbit/s\n\n I cannot explain the under-DoS regression that patch-05/percpu_counter\n introduces. But patch-06/LRU-lock corrects the situation again.\n\nBelow is a testlab setup description, with links to the trafgen DoS\npacket config used.\n\nTestlab\n\u003d\u003d\u003d\u003d\u003d\u003d\u003d\n\nServer setup\n------------\nThe machine acting as a server:\n - 2x CPU (E5-2630)\n - Thus a NUMA arch/machine\n - 4x 10Gbit/s ports\n - NICs 2x Intel Dual port 82599 based (driver ixgbe)\n\nSetup:\n - Interfaces uses Ethernet flow control\n - Flush all iptables\n - Remove all iptables related module.\n - Kill irqbalance\n - Pin each 10G NIC port to a *single* CPU each\n\nPinning can easily be done by command hacks::\n\n for x in /proc/irq/*/eth8*/../smp_affinity_list ; do echo 1 \u003e $x; done\n for x in /proc/irq/*/eth9*/../smp_affinity_list ; do echo 3 \u003e $x; done\n for x in /proc/irq/*/eth31*/../smp_affinity_list; do echo 6 \u003e $x; done\n for x in /proc/irq/*/eth32*/../smp_affinity_list; do echo 8 \u003e $x; done\n\nNotice NUMA setting: The CPU to NIC tying is carefully choosen\naccording to the NUMA node setup. Thus, NICs connected to a PCI-e\nslot that is connected to a physical CPU socket are tied together.\n\nChoosing only a single CPU per NIC (port) is just to ease provoking\nand debugging this performance issue. (In real setups, you can choose\nmore CPU, just remember the NUMA node in the equation).\n\nTools\n-----\n\nNetperf is used, with option -T to ensure CPU binding.\nThe netserver processes, are NAPI pinned::\n\n numactl -m0 -c0 netserver\n numactl -m1 -c 1 netserver -p 1337\n\nI now have a frag DoS generator, created via the tool:\n trafgen (see: http://netsniff-ng.org/)\n\nTrafgen packet config file:\n http://people.netfilter.org/hawk/frag_work/trafgen/frag_packet03_small_frag.txf\n\nNotice, I\u0027m using features of trafgen, recently developed by Daniel\nBorkmann, thus you need the latest git tree to use my trafgen packet\nconfig.\n\n git://github.com/borkmann/netsniff-ng.git\n\nCommand line:\n trafgen --dev eth51 --conf frag_packet03_small_frag.txf -V -k 100 --cpus 2\n\nTests types\n-----------\n\nTest(20G64K) UDP-64K 2x 10Gbit/s with no DoS traffic:\n~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n\n export SIZE\u003d$((65507)); export TIME\u003d$((20)); export LOG\u003d/tmp/netperf.log ;\\\n netperf -p 1337 -H 192.168.31.2 -T7,7 -t UDP_STREAM -l $TIME -- -m $SIZE \u003e\u003e ${LOG}.31 \u0026\\\n netperf -H 192.168.81.2 -T2,2 -t UDP_STREAM -l $TIME -- -m $SIZE \u003e\u003e ${LOG}.81 \u0026\u0026 \\\n wait $! \u0026\u0026 tail -n3 ${LOG}.* \u0026\u0026 \\\n tail -n3 ${LOG}.{31,81} | awk \u0027BEGIN{sum\u003d0;} /212992 / {sum+\u003d$4; print \" +\"$4} /\u003d\u003d/ {print \" file:\"$2} END{print \"sum:\"sum\" Mbit/s\"}\u0027\n\nTest(20G3F) UDP-3xfrags 2x 10Gbit/s with no DoS traffic:\n~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n\n export SIZE\u003d$((3*1472)); export TIME\u003d$((20)); export LOG\u003d/tmp/netperf.log ;\\\n netperf -p 1337 -H 192.168.31.2 -T7,7 -t UDP_STREAM -l $TIME -- -m $SIZE \u003e\u003e ${LOG}.31 \u0026\\\n netperf -H 192.168.81.2 -T2,2 -t UDP_STREAM -l $TIME -- -m $SIZE \u003e\u003e ${LOG}.81 \u0026\u0026 \\\n wait $! \u0026\u0026 tail -n3 ${LOG}.* \u0026\u0026 \\\ntail -n3 ${LOG}.{31,81} | awk \u0027BEGIN{sum\u003d0;} /212992 / {sum+\u003d$4; print \" +\"$4} /\u003d\u003d/ {print \" file:\"$2} END{print \"sum:\"sum\" Mbit/s\"}\u0027\n\nAwk script for summming results:\n~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n\ntail -n3 ${LOG}.{31,81} | awk \u0027BEGIN{sum\u003d0;} /212992 / {sum+\u003d$4; print \" +\"$4} /\u003d\u003d/ {print \" file:\"$2} END{print \"sum:\"sum\" Mbit/s\"}\u0027\n\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\n\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "3ef0eb0db4bf92c6d2510fe5c4dc51852746f206", "tree": "3f0d424f598a82eb17a5199d27fec9964513e16e", "parents": [ "6d7b857d541ecd1d9bd997c97242d4ef94b19de2" ], "author": { "name": "Jesper Dangaard Brouer", "email": "brouer@redhat.com", "time": "Mon Jan 28 23:45:51 2013 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Tue Jan 29 13:36:24 2013 -0500" }, "message": "net: frag, move LRU list maintenance outside of rwlock\n\nUpdating the fragmentation queues LRU (Least-Recently-Used) list,\nrequired taking the hash writer lock. However, the LRU list isn\u0027t\ntied to the hash at all, so we can use a separate lock for it.\n\nOriginal-idea-by: Florian Westphal \u003cfw@strlen.de\u003e\nSigned-off-by: Jesper Dangaard Brouer \u003cbrouer@redhat.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "6d7b857d541ecd1d9bd997c97242d4ef94b19de2", "tree": "df7813da4f92cad8413f71c325969b89416d8a24", "parents": [ "d433673e5f9180e05a770c4b2ab18c08ad51cc21" ], "author": { "name": "Jesper Dangaard Brouer", "email": "brouer@redhat.com", "time": "Mon Jan 28 23:45:33 2013 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Tue Jan 29 13:36:24 2013 -0500" }, "message": "net: use lib/percpu_counter API for fragmentation mem accounting\n\nReplace the per network namespace shared atomic \"mem\" accounting\nvariable, in the fragmentation code, with a lib/percpu_counter.\n\nGetting percpu_counter to scale to the fragmentation code usage\nrequires some tweaks.\n\nAt first view, percpu_counter looks superfast, but it does not\nscale on multi-CPU/NUMA machines, because the default batch size\nis too small, for frag code usage. Thus, I have adjusted the\nbatch size by using __percpu_counter_add() directly, instead of\npercpu_counter_sub() and percpu_counter_add().\n\nThe batch size is increased to 130.000, based on the largest 64K\nfragment memory usage. This does introduce some imprecise\nmemory accounting, but its does not need to be strict for this\nuse-case.\n\nIt is also essential, that the percpu_counter, does not\nshare cacheline with other writers, to make this scale.\n\nSigned-off-by: Jesper Dangaard Brouer \u003cbrouer@redhat.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "d433673e5f9180e05a770c4b2ab18c08ad51cc21", "tree": "7d71bb8483724418e6a4f48cc4099a8722c704c8", "parents": [ "6e34a8b37aca63f109bf990d46131ee07206f5f1" ], "author": { "name": "Jesper Dangaard Brouer", "email": "brouer@redhat.com", "time": "Mon Jan 28 23:45:12 2013 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Tue Jan 29 13:36:24 2013 -0500" }, "message": "net: frag helper functions for mem limit tracking\n\nThis change is primarily a preparation to ease the extension of memory\nlimit tracking.\n\nThe change does reduce the number atomic operation, during freeing of\na frag queue. This does introduce a some performance improvement, as\nthese atomic operations are at the core of the performance problems\nseen on NUMA systems.\n\nSigned-off-by: Jesper Dangaard Brouer \u003cbrouer@redhat.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "6e34a8b37aca63f109bf990d46131ee07206f5f1", "tree": "2daf8bc157035e3493636eea48db3805a2a92f3f", "parents": [ "5f8e1e8b767bdb8e471d4f49612b88c606f8811e" ], "author": { "name": "Jesper Dangaard Brouer", "email": "brouer@redhat.com", "time": "Mon Jan 28 23:44:49 2013 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Tue Jan 29 13:36:23 2013 -0500" }, "message": "net: cacheline adjust struct inet_frag_queue\n\nFragmentation code cacheline adjusting of struct inet_frag_queue.\n\nTake advantage of the size of struct timer_list, and move all but\nspinlock_t lock, below the timer struct. On 64-bit \u0027lru_list\u0027,\n\u0027list\u0027 and \u0027refcnt\u0027, fits exactly into the next cacheline, and a\nnew cacheline starts at \u0027fragments\u0027.\n\nThe netns_frags *net pointer is moved to the end of the struct,\nbecause its used in a compare, with \"next/close-by\" elements of\nwhich this struct is embedded into.\n\nSigned-off-by: Jesper Dangaard Brouer \u003cbrouer@redhat.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "5f8e1e8b767bdb8e471d4f49612b88c606f8811e", "tree": "ce54f4695fd3bc8b400dd28ed965de9cfa202cd6", "parents": [ "cd39a7890aed7433beb3188c7ad8591e260ebf10" ], "author": { "name": "Jesper Dangaard Brouer", "email": "brouer@redhat.com", "time": "Mon Jan 28 23:44:37 2013 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Tue Jan 29 13:36:23 2013 -0500" }, "message": "net: cacheline adjust struct inet_frags for better frag performance\n\nThe globally shared rwlock, of struct inet_frags, shares\ncacheline with the \u0027rnd\u0027 number, which is used by the hash\ncalculations. Fix this, as this obviously is a bad idea, as\nunnecessary cache-misses will occur when accessing the \u0027rnd\u0027\nnumber.\n\nAlso small note that, moving function ptr (*match) up in struct,\nis to avoid it lands on the next cacheline (on 64-bit).\n\nSigned-off-by: Jesper Dangaard Brouer \u003cbrouer@redhat.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "cd39a7890aed7433beb3188c7ad8591e260ebf10", "tree": "1a5de7566bbc4e1cb5f00495c664c27abc1085d4", "parents": [ "656a05c899b4026ee828ccddd550202ded7a26c6" ], "author": { "name": "Jesper Dangaard Brouer", "email": "brouer@redhat.com", "time": "Mon Jan 28 23:44:14 2013 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Tue Jan 29 13:36:23 2013 -0500" }, "message": "net: cacheline adjust struct netns_frags for better frag performance\n\nThis small cacheline adjustment of struct netns_frags improves\nperformance significantly for the fragmentation code.\n\nStruct members \u0027lru_list\u0027 and \u0027mem\u0027 are both hot elements, and it\nhurts performance, due to cacheline bouncing at every call point,\nwhen they share a cacheline. Also notice, how mem is placed\ntogether with \u0027high_thresh\u0027 and \u0027low_thresh\u0027, as they are used in\nthe compare operations together.\n\nSigned-off-by: Jesper Dangaard Brouer \u003cbrouer@redhat.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "656a05c899b4026ee828ccddd550202ded7a26c6", "tree": "8a336e017c76026044a0d121a18fa5c070e0e05a", "parents": [ "08433eff2d041b263c68306f6a6ccb4e1f75e196" ], "author": { "name": "Felipe Balbi", "email": "balbi@ti.com", "time": "Tue Jan 29 09:16:30 2013 +0200" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Tue Jan 29 13:32:00 2013 -0500" }, "message": "net: ks8851: convert to threaded IRQ\n\njust as it should have been. It also helps\nremoving the, now unnecessary, workqueue.\n\nSigned-off-by: Felipe Balbi \u003cbalbi@ti.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "08433eff2d041b263c68306f6a6ccb4e1f75e196", "tree": "a983dd9edfdb434076751c50f3952c744f64e17f", "parents": [ "cdda88912d62f9603d27433338a18be83ef23ac1" ], "author": { "name": "YOSHIFUJI Hideaki / 吉藤英明", "email": "yoshfuji@linux-ipv6.org", "time": "Thu Jan 24 00:44:23 2013 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Jan 28 23:17:51 2013 -0500" }, "message": "net neigh: Optimize neighbor entry size calculation.\n\nWhen allocating memory for neighbour cache entry, if\ntbl-\u003eentry_size is not set, we always calculate\nsizeof(struct neighbour) + tbl-\u003ekey_len, which is common\nin the same table.\n\nWith this change, set tbl-\u003eentry_size during the table\ninitialization phase, if it was not set, and use it in\nneigh_alloc() and neighbour_priv().\n\nThis change also allow us to have both of protocol private\ndata and device priate data at tha same time.\n\nNote that the only user of prototcol private is DECnet\nand the only user of device private is ATM CLIP.\nSince those are exclusive, we have not been facing issues\nhere.\n\nSigned-off-by: YOSHIFUJI Hideaki \u003cyoshfuji@linux-ipv6.org\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "cdda88912d62f9603d27433338a18be83ef23ac1", "tree": "5798502c9546bd3e8d20e2ac2d1ef01a8032b115", "parents": [ "f7b5d1b9bd16e3ec71696abb204a8cfddd93aa62" ], "author": { "name": "bingtian.ly@taobao.com", "email": "bingtian.ly@taobao.com", "time": "Wed Jan 23 20:35:28 2013 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Jan 28 23:15:27 2013 -0500" }, "message": "net: avoid to hang up on sending due to sysctl configuration overflow.\n\n I found if we write a larger than 4GB value to some sysctl\nvariables, the sending syscall will hang up forever, because these\nvariables are 32 bits, such large values make them overflow to 0 or\nnegative.\n\n This patch try to fix overflow or prevent from zero value setup\nof below sysctl variables:\n\nnet.core.wmem_default\nnet.core.rmem_default\n\nnet.core.rmem_max\nnet.core.wmem_max\n\nnet.ipv4.udp_rmem_min\nnet.ipv4.udp_wmem_min\n\nnet.ipv4.tcp_wmem\nnet.ipv4.tcp_rmem\n\nSigned-off-by: Eric Dumazet \u003ceric.dumazet@gmail.com\u003e\nSigned-off-by: Li Yu \u003craise.sail@gmail.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "fc16e884a2320198b8cb7bc2fdcf6b4485e79709", "tree": "d98d1938ab0fb7bcc02193772936f8dec6c22661", "parents": [ "f94d4fe0b5bbe8385245a1d9ef11d785c05df0da", "689dfa894c57842a05bf6dc9f97e6bb71ec5f386" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Jan 28 16:23:07 2013 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Jan 28 16:23:07 2013 -0800" }, "message": "Merge branch \u0027merge\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc\n\nPull powerpc fixes from Benjamin Herrenschmidt:\n \"Whenever you have a chance between two dives, you might want to\n consider pulling my merge branch to pickup a few fixes for 3.8 that\n have been accumulating for the last couple of weeks (I was myself\n travelling then on vacation).\n\n Nothing major, just a handful of powerpc bug fixes that I consider\n worth getting in before 3.8 goes final.\"\n\nAnd I\u0027ll have everybody know that I\u0027m not diving for several days yet.\nSnif.\n\n* \u0027merge\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc:\n powerpc: Max next_tb to prevent from replaying timer interrupt\n powerpc: kernel/kgdb.c: Fix memory leakage\n powerpc/book3e: Disable interrupt after preempt_schedule_irq\n powerpc/oprofile: Fix error in oprofile power7_marked_instr_event() function\n powerpc/pasemi: Fix crash on reboot\n powerpc: Fix MAX_STACK_TRACE_ENTRIES too low warning for ppc32\n" }, { "commit": "f7b5d1b9bd16e3ec71696abb204a8cfddd93aa62", "tree": "8a5789abdd06fbaf45c1b63f025b0fe510dcecc7", "parents": [ "7ab59dc15e2f42a4321ed016bcd6044a4d8de6d1" ], "author": { "name": "Jamie Gloudon", "email": "jamie.gloudon@gmail.com", "time": "Wed Jan 23 18:05:04 2013 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Jan 28 18:43:02 2013 -0500" }, "message": "via-rhine: add 64bit statistics.\n\nSwitch to use ndo_get_stats64 to get 64bit statistics.\n\nSigned-off-by: Jamie Gloudon \u003cjamie.gloudon@gmail.com\u003e\nTested-by: Jamie Gloudon \u003cjamie.gloudon@gmail.com\u003e\nAcked-by: Eric Dumazet \u003cedumazet@google.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "7ab59dc15e2f42a4321ed016bcd6044a4d8de6d1", "tree": "7a6927acae99140a8f897471bcd892a783d3ed65", "parents": [ "ef3d90491a15f0d5cf1ec39a38a45dac6968fb2a" ], "author": { "name": "David J. Choi", "email": "david.choi@micrel.com", "time": "Wed Jan 23 14:05:15 2013 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Jan 28 18:42:10 2013 -0500" }, "message": "drivers/net/phy/micrel_phy: Add support for new PHYs\n\nSummary of changes:\n.Newly added phys\n\t-KSZ8081/KSZ8091, which has some phy ids.\n\t-KSZ8061\n\t-KSZ9031, which is Gigabit phy.\n\t-KSZ886X, which has a switch function.\n\t-KSZ8031, which has a same phy ids with KSZ8021.\n\nSigned-off-by: David J. Choi \u003cdavid.choi@micrel.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "ef3d90491a15f0d5cf1ec39a38a45dac6968fb2a", "tree": "d0c2e75577e410b2e282d3d5acd474f13e03c559", "parents": [ "556e6256c813063b95a9f4e55109f77c1a7d3fdd" ], "author": { "name": "Giuseppe CAVALLARO", "email": "peppe.cavallaro@st.com", "time": "Wed Jan 23 00:30:03 2013 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Jan 28 18:34:53 2013 -0500" }, "message": "net: phy: realtek: add rtl8211e driver\n\nThis patch adds the minimal driver to manage the\nRealtek RTL8211E 10/100/1000 Transceivers.\n\nSigned-off-by: Giuseppe Cavallaro \u003cpeppe.cavallaro@st.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "556e6256c813063b95a9f4e55109f77c1a7d3fdd", "tree": "e607bbf12fedcaba7c48f1ea8e12ce8afbf012d2", "parents": [ "faeed828f9607923e9dc22182e819908e95c8852" ], "author": { "name": "Cong Wang", "email": "amwang@redhat.com", "time": "Sun Jan 27 15:55:21 2013 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Jan 28 18:32:55 2013 -0500" }, "message": "netpoll: use the net namespace of current process instead of init_net\n\nThis will allow us to setup netconsole in a different namespace\nrather than where init_net is.\n\nCc: Eric W. Biederman \u003cebiederm@xmission.com\u003e\nCc: David S. Miller \u003cdavem@davemloft.net\u003e\nSigned-off-by: Cong Wang \u003camwang@redhat.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "faeed828f9607923e9dc22182e819908e95c8852", "tree": "3fe106b1bf0ea25f6d2b1a73193bfeef18f67d87", "parents": [ "5fbee843c32e5de2d8af68ba0bdd113bb0af9d86" ], "author": { "name": "Cong Wang", "email": "amwang@redhat.com", "time": "Sun Jan 27 15:55:20 2013 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Jan 28 18:32:55 2013 -0500" }, "message": "netpoll: use ipv6_addr_equal() to compare ipv6 addr\n\nipv6_addr_equal() is faster.\n\nCc: David S. Miller \u003cdavem@davemloft.net\u003e\nSigned-off-by: Cong Wang \u003camwang@redhat.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "5fbee843c32e5de2d8af68ba0bdd113bb0af9d86", "tree": "1b5af9ab4177611b00412abe3ee3217030740307", "parents": [ "ce4a600e477a4da600c8056897e71e2f4a8c5ac0" ], "author": { "name": "Cong Wang", "email": "amwang@redhat.com", "time": "Tue Jan 22 21:29:39 2013 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Jan 28 18:32:54 2013 -0500" }, "message": "netpoll: add RCU annotation to npinfo field\n\ndev-\u003enpinfo is protected by RCU.\n\nThis fixes the following sparse warnings:\n\nnet/core/netpoll.c:177:48: error: incompatible types in comparison expression (different address spaces)\nnet/core/netpoll.c:200:35: error: incompatible types in comparison expression (different address spaces)\nnet/core/netpoll.c:221:35: error: incompatible types in comparison expression (different address spaces)\nnet/core/netpoll.c:327:18: error: incompatible types in comparison expression (different address spaces)\n\nCc: Eric Dumazet \u003ceric.dumazet@gmail.com\u003e\nCc: David S. Miller \u003cdavem@davemloft.net\u003e\nSigned-off-by: Cong Wang \u003camwang@redhat.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "ce4a600e477a4da600c8056897e71e2f4a8c5ac0", "tree": "9b610dde96127321d986d42301cc243ee75a2fc4", "parents": [ "8a67b05db93688600ca330692b87668cad37e507", "4205e6ef4ee747aa81930537b6035086ba5f1e28" ], "author": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Jan 28 18:21:38 2013 -0500" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Jan 28 18:21:38 2013 -0500" }, "message": "Merge branch \u0027for-davem\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/linville/wireless-next\n\nJohn W. Linville says:\n\n\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\nIncluded is an NFC pull. Samuel says:\n\n\"It brings the following goodies:\n\n- LLCP socket timestamping (To be used e.g with the recently released nfctool\n application for a more efficient skb timestamping when sniffing).\n- A pretty big pn533 rework from Waldemar, preparing the driver to support\n more flavours of pn533 based devices.\n- HCI changes from Eric in preparation for the microread driver support.\n- Some LLCP memory leak fixes, cleanups and slight improvements.\n- pn544 and nfcwilink move to the devm_kzalloc API.\n- An initial Secure Element (SE) API.\n- An nfc.h license change from the original author, allowing non GPL\n application code to safely include it.\"\n\nAlso included are a pair of mac80211 pulls. Johannes says:\n\n\"We found two bugs in the previous code, so I\u0027m sending you a pull\nrequest again this soon.\n\nThis contains two regulatory bug fixes, some of Thomas\u0027s hwsim beacon\ntimer work and a documentation fix from Bob.\"\n\n\"Another pull request for mac80211-next. This time, I have a number of\nthings, the patches are mostly self-explanatory. There are a few fixes\nfrom Felix and myself, and random cleanups \u0026 improvements. The biggest\nthing is the partial patchset from Marco preparing for mesh powersave.\"\n\nAdditionally, there are a pair of iwlwifi pulls. Johannes says:\n\n\"For iwlwifi-next, I have a few cleanups/improvements as well as a few\nnot very important fixes and more preparations for new devices.\"\n\n\"Please pull a few updates for iwlwifi. These are just some cleanups and\na debug improvement.\"\n\nOn top of that, there is a slew of driver updates. This includes\nbrcmfmac, mwifiex, ath9k, carl9170, and mwl8k as well as a handful\nof others. The bcma and ssb busses get some attention as well.\nStill, I don\u0027t see any big headliners here.\n\nAlso included is a pull of the wireless tree, in order to resolve\nsome merge conflicts.\n\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\n\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "8a67b05db93688600ca330692b87668cad37e507", "tree": "fdc45501bbcb351723c11f7cd74195ecc0c47075", "parents": [ "2bf3440d7b8755f2627232e6a4c37efbbe053685", "8d56b6d507e0c4f6e24680fd202cbaad445935c5" ], "author": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Jan 28 18:18:17 2013 -0500" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Jan 28 18:18:17 2013 -0500" }, "message": "Merge branch \u0027master\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/net-next\n\nJeff Kirsher says:\n\n\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\nThis series contains updates to e1000e, ixgbevf, igb and igbvf.\nMajority of the patches are code cleanups of e1000e where code\nis removed (Yeah!). The other two e1000e patches are fixes. The\nfirst is to fix the maximum frame size for 82579 devices. The second\nfix is to resolve an issue with devices other than 82579 that suffer\nfrom dropped transactions on platforms with deep C-states when\njumbo frames are enabled.\n\nThe ixgbevf patch is to ensure that the driver fetches the correct,\nrefreshed value for link status and speed when the values have changed.\n\nThe igb and igbvf patches are a solution to an issue Stefan Assmann\nreported, where when the PF is up and igbvf is loaded, the MAC address\nis not generated using eth_hw_addr_random().\n\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\n\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "689dfa894c57842a05bf6dc9f97e6bb71ec5f386", "tree": "36b1b888f77c68447b57d6db37cafe3032874f31", "parents": [ "fefd9e6f8860249b2c284d89cb2e51fa71a9503a" ], "author": { "name": "Tiejun Chen", "email": "tiejun.chen@windriver.com", "time": "Tue Jan 15 17:01:19 2013 +0000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Tue Jan 29 10:18:16 2013 +1100" }, "message": "powerpc: Max next_tb to prevent from replaying timer interrupt\n\nWith lazy interrupt, we always call __check_irq_replaysome with\ndecrementers_next_tb to check if we need to replay timer interrupt.\nSo in hotplug case we also need to set decrementers_next_tb as MAX\nto make sure __check_irq_replay don\u0027t replay timer interrupt\nwhen return as we expect, otherwise we\u0027ll trap here infinitely.\n\nSigned-off-by: Tiejun Chen \u003ctiejun.chen@windriver.com\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "fefd9e6f8860249b2c284d89cb2e51fa71a9503a", "tree": "4219d4cd14d7756fda204852171bc8ca1deb8eab", "parents": [ "572177d7c77db1981ba2563e01478126482c43bc" ], "author": { "name": "Cong Ding", "email": "dinggnu@gmail.com", "time": "Mon Jan 14 07:26:32 2013 +0000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Tue Jan 29 10:18:15 2013 +1100" }, "message": "powerpc: kernel/kgdb.c: Fix memory leakage\n\nthe variable backup_current_thread_info isn\u0027t freed before existing the\nfunction.\n\nSigned-off-by: Cong Ding \u003cdinggnu@gmail.com\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "572177d7c77db1981ba2563e01478126482c43bc", "tree": "89a68e8ee9014606031f98f0222f037eb7510aa1", "parents": [ "46ed7a76ae7770cb8ba733ee2b06273397ad8b5b" ], "author": { "name": "Tiejun Chen", "email": "tiejun.chen@windriver.com", "time": "Sun Jan 06 00:49:34 2013 +0000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Tue Jan 29 10:18:15 2013 +1100" }, "message": "powerpc/book3e: Disable interrupt after preempt_schedule_irq\n\nIn preempt case current arch_local_irq_restore() from\npreempt_schedule_irq() may enable hard interrupt but we really\nshould disable interrupts when we return from the interrupt,\nand so that we don\u0027t get interrupted after loading SRR0/1.\n\nSigned-off-by: Tiejun Chen \u003ctiejun.chen@windriver.com\u003e\nCC: \u003cstable@vger.kernel.org\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "46ed7a76ae7770cb8ba733ee2b06273397ad8b5b", "tree": "f0b0f73d2bb546d82f15d8ae98115932f70fc8f9", "parents": [ "72640d880350165c3a7b8f2e4fb4bf852ea7b606" ], "author": { "name": "Carl E. Love", "email": "cel@linux.vnet.ibm.com", "time": "Thu Nov 29 06:42:03 2012 +0000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Tue Jan 29 10:18:14 2013 +1100" }, "message": "powerpc/oprofile: Fix error in oprofile power7_marked_instr_event() function\n\nThe calculation for the left shift of the mask OPROFILE_PM_PMCSEL_MSK has an\nerror. The calculation is should be to shift left by (max_cntrs - cntr) times\nthe width of the pmsel field width. However, the #define OPROFILE_MAX_PMC_NUM\nwas used instead of OPROFILE_PMSEL_FIELD_WIDTH. This patch fixes the\ncalculation.\n\nSigned-off-by: Carl Love \u003ccel@us.ibm.com\u003e\nAcked-by: Paul Mackerras \u003cpaulus@samba.org\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "72640d880350165c3a7b8f2e4fb4bf852ea7b606", "tree": "38c8cb3b7b779a4d291dcb6ba2bc6183a3c26975", "parents": [ "41d82bdb40af74a88cff4589ea7a60091b11070e" ], "author": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Mon Jan 21 17:23:26 2013 +0000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Tue Jan 29 10:18:14 2013 +1100" }, "message": "powerpc/pasemi: Fix crash on reboot\n\ncommit f96972f2dc \"kernel/sys.c: call disable_nonboot_cpus() in\nkernel_restart()\"\n\nadded a call to disable_nonboot_cpus() on kernel_restart(), which tries\nto shutdown all the CPUs except the first one. The issue with the PA\nSemi, is that it does not support CPU hotplug.\n\nWhen the call is made to __cpu_down(), it calls the notifiers\nCPU_DOWN_PREPARE, and then tries to take the CPU down.\n\nOne of the notifiers to the CPU hotplug code, is the cpufreq. The\nDOWN_PREPARE will call __cpufreq_remove_dev() which calls\ncpufreq_driver-\u003eexit. The PA Semi exit handler unmaps regions of I/O\nthat is used by an interrupt that goes off constantly\n(system_reset_common, but it goes off during normal system operations\ntoo). I\u0027m not sure exactly what this interrupt does.\n\nRunning a simple function trace, you can see it goes off quite a bit:\n\n# tracer: function\n#\n# TASK-PID CPU# TIMESTAMP FUNCTION\n# | | | | |\n \u003cidle\u003e-0 [001] 1558.859363: .pasemi_system_reset_exception \u003c-.system_reset_exception\n \u003cidle\u003e-0 [000] 1558.860112: .pasemi_system_reset_exception \u003c-.system_reset_exception\n \u003cidle\u003e-0 [000] 1558.861109: .pasemi_system_reset_exception \u003c-.system_reset_exception\n \u003cidle\u003e-0 [001] 1558.861361: .pasemi_system_reset_exception \u003c-.system_reset_exception\n \u003cidle\u003e-0 [000] 1558.861437: .pasemi_system_reset_exception \u003c-.system_reset_exception\n\nWhen the region is unmapped, the system crashes with:\n\nDisabling non-boot CPUs ...\nError taking CPU1 down: -38\nUnable to handle kernel paging request for data at address 0xd0000800903a0100\nFaulting instruction address: 0xc000000000055fcc\nOops: Kernel access of bad area, sig: 11 [#1]\nPREEMPT SMP NR_CPUS\u003d64 NUMA PA Semi PWRficient\nModules linked in: shpchp\nNIP: c000000000055fcc LR: c000000000055fb4 CTR: c0000000000df1fc\nREGS: c0000000012175d0 TRAP: 0300 Not tainted (3.8.0-rc4-test-dirty)\nMSR: 9000000000009032 \u003cSF,HV,EE,ME,IR,DR,RI\u003e CR: 24000088 XER: 00000000\nSOFTE: 0\nDAR: d0000800903a0100, DSISR: 42000000\nTASK \u003d c0000000010e9008[0] \u0027swapper/0\u0027 THREAD: c000000001214000 CPU: 0\nGPR00: d0000800903a0000 c000000001217850 c0000000012167e0 0000000000000000\nGPR04: 0000000000000000 0000000000000724 0000000000000724 0000000000000000\nGPR08: 0000000000000000 0000000000000000 0000000000000001 0000000000a70000\nGPR12: 0000000024000080 c00000000fff0000 ffffffffffffffff 000000003ffffae0\nGPR16: ffffffffffffffff 0000000000a21198 0000000000000060 0000000000000000\nGPR20: 00000000008fdd35 0000000000a21258 000000003ffffaf0 0000000000000417\nGPR24: 0000000000a226d0 c000000000000000 0000000000000000 0000000000000000\nGPR28: c00000000138b358 0000000000000000 c000000001144818 d0000800903a0100\nNIP [c000000000055fcc] .set_astate+0x5c/0xa4\nLR [c000000000055fb4] .set_astate+0x44/0xa4\nCall Trace:\n[c000000001217850] [c000000000055fb4] .set_astate+0x44/0xa4 (unreliable)\n[c0000000012178f0] [c00000000005647c] .restore_astate+0x2c/0x34\n[c000000001217980] [c000000000054668] .pasemi_system_reset_exception+0x6c/0x88\n[c000000001217a00] [c000000000019ef0] .system_reset_exception+0x48/0x84\n[c000000001217a80] [c000000000001e40] system_reset_common+0x140/0x180\n\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "2bf3440d7b8755f2627232e6a4c37efbbe053685", "tree": "07e31649ec6a5d58649f6b3c9f8cd1a76e76b24f", "parents": [ "cef401de7be8c4e155c6746bfccf721a4fa5fab9" ], "author": { "name": "Oliver Hartkopp", "email": "socketcan@hartkopp.net", "time": "Mon Jan 28 08:33:33 2013 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Jan 28 18:17:25 2013 -0500" }, "message": "can: rework skb reserved data handling\n\nAdded accessor and skb_reserve helpers for struct can_skb_priv.\nRemoved pointless skb_headroom() check.\n\nSigned-off-by: Oliver Hartkopp \u003csocketcan@hartkopp.net\u003e\nCC: Marc Kleine-Budde \u003cmkl@pengutronix.de\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "f94d4fe0b5bbe8385245a1d9ef11d785c05df0da", "tree": "64e20ce42b24bb5f47bdbde3eff4ab55f6e9f89d", "parents": [ "45e72af09faa7dad5d8539ebac0fe317ae88318b", "55ebbb59c1c6eb1b040f62b8c4ae0b724de6e55a" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Jan 28 15:15:34 2013 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Jan 28 15:15:34 2013 -0800" }, "message": "Merge tag \u0027md-3.8-fixes\u0027 of git://neil.brown.name/md\n\nPull dmraid fix from NeilBrown:\n \"Just one fix for md in 3.8\n\n dmraid assess redundancy and replacements slightly inaccurately which\n could lead to some degraded arrays failing to assemble.\"\n\n* tag \u0027md-3.8-fixes\u0027 of git://neil.brown.name/md:\n DM-RAID: Fix RAID10\u0027s check for sufficient redundancy\n" }, { "commit": "41d82bdb40af74a88cff4589ea7a60091b11070e", "tree": "cf65bdbda41cba99692d7d01d31a702d683a7f99", "parents": [ "45e72af09faa7dad5d8539ebac0fe317ae88318b" ], "author": { "name": "Li Zhong", "email": "zhong@linux.vnet.ibm.com", "time": "Sun Dec 02 20:19:22 2012 +0000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Tue Jan 29 10:10:22 2013 +1100" }, "message": "powerpc: Fix MAX_STACK_TRACE_ENTRIES too low warning for ppc32\n\nThis patch fixes MAX_STACK_TRACE_ENTRIES too low warning for ppc32,\nwhich is similar to commit 12660b17.\n\nReported-by: Christian Kujau \u003clists@nerdbynature.de\u003e\nSigned-off-by: Li Zhong \u003czhong@linux.vnet.ibm.com\u003e\nTested-by: Christian Kujau \u003clists@nerdbynature.de\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "45e72af09faa7dad5d8539ebac0fe317ae88318b", "tree": "30699550096e312bceeb584bfda1325d4430db86", "parents": [ "ae2c3d95faa4f75005f52051734464d4e8991612", "d4e0bfec9b6fbb9b58640b44e01bb74ae0d29b22" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Jan 28 11:53:49 2013 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Jan 28 11:53:49 2013 -0800" }, "message": "Merge git://git.kernel.org/pub/scm/linux/kernel/git/steve/gfs2-3.0-fixes\n\nPull GFS2 fix from Steven Whitehouse.\n\n* git://git.kernel.org/pub/scm/linux/kernel/git/steve/gfs2-3.0-fixes:\n GFS2: fix skip unlock condition\n" }, { "commit": "ae2c3d95faa4f75005f52051734464d4e8991612", "tree": "bdfaaf82527a23753db2ab5ce43c1b20aa5e568f", "parents": [ "325a86b65c01408dc77690fac1a7a45c844a613b", "318fe782539c4150d1b8e4e6c9dc3a896512cb8a" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Jan 28 11:52:56 2013 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Jan 28 11:52:56 2013 -0800" }, "message": "Merge tag \u0027iommu-fixes-v3.8-rc5\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu\n\nPull IOMMU fix from Joerg Roedel:\n \"One fix for the AMD IOMMU driver to work around broken BIOSes found in\n the field. Some BIOSes forget to enable a workaround for a hardware\n problem which might cause the IOMMU to stop working under high load\n conditions. The fix makes sure this workaround is enabled.\"\n\n* tag \u0027iommu-fixes-v3.8-rc5\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu:\n IOMMU, AMD Family15h Model10-1Fh erratum 746 Workaround\n" }, { "commit": "325a86b65c01408dc77690fac1a7a45c844a613b", "tree": "bd8f15f6ac34f51b6bc3d3e9b549cbfae0a6244a", "parents": [ "22f837981514e157f8f9737b25ac6d7d90a14006", "2d1484f5990c094e2c706672a8d286576dd096b4" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Jan 28 11:51:57 2013 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Jan 28 11:51:57 2013 -0800" }, "message": "Merge tag \u0027mfd-for-linus-3.8-1\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/sameo/mfd-2.6\n\nPull MFD fixes from Samuel Ortiz:\n \"This is the first pull request for MFD fixes for 3.8\n\n We have some build failure fixes (twl4030, vexpress, abx500 and\n tps65910), some actual runtime oops and lockup fixes (rtsx, da9052),\n and some more hypothetical NULL pointers dereferences fixes for\n pcf50633 and max776xx.\n\n Then we also have additional rtsx fixes for a correct switch output\n voltage and clock divider correctness for rtl8411 (rtsx driver), and\n irqdomain fix for db8550-prcmu, and some more cosmetic fixes for\n arizona and wm5102.\"\n\n* tag \u0027mfd-for-linus-3.8-1\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/sameo/mfd-2.6:\n mfd: rtsx: Fix oops when rtsx_pci_sdmmc is not probed\n mfd: wm5102: Fix definition of WM5102_MAX_REGISTER\n mfd: twl4030: Don\u0027t warn about uninitialized return code\n mfd: da9052/53 lockup fix\n mfd: rtsx: Add clock divider hook\n mmc: rtsx: Call MFD hook to switch output voltage\n mfd: rtsx: Add output voltage switch hook\n mfd: Fix compile errors and warnings when !CONFIG_AB8500_BM\n mfd: vexpress: Export global functions to fix build error\n mfd: arizona: Check errors from regcache_sync()\n mfd: tc3589x: Use simple irqdomain\n mfd: pcf50633: Init pcf-\u003edev before using it\n mfd: max77693: Init max77693-\u003edev before using it\n mfd: max77686: Init max77686-\u003edev before using it\n mfd: db8500-prcmu: Fix irqdomain usage\n mfd: tps65910: Select REGMAP_IRQ in Kconfig to fix build error\n mfd: arizona: Disable control interface reporting for WM5102 and WM5110\n" }, { "commit": "a7966d908ae8472e8183496916b7baec5f65b3a6", "tree": "bcc97922e010adf61c6ee189f30cc5fe5e472589", "parents": [ "cef401de7be8c4e155c6746bfccf721a4fa5fab9" ], "author": { "name": "Antonio Quartulli", "email": "ordex@autistici.org", "time": "Thu Jan 24 11:41:39 2013 +0100" }, "committer": { "name": "Antonio Quartulli", "email": "ordex@autistici.org", "time": "Mon Jan 28 20:46:03 2013 +0100" }, "message": "batman-adv: fix local translation table output\n\nThe last-seen field has to be printed for all the local\nentries but the one marked with the no-purge flag\n\nIntroduced by 15727323d9f8864b2d41930940acc38de987045a\n(\"batman-adv: don\u0027t print the last_seen time for bat0 TT local entry\")\n\nSigned-off-by: Antonio Quartulli \u003cordex@autistici.org\u003e\nSigned-off-by: Marek Lindner \u003clindner_marek@yahoo.de\u003e\n" }, { "commit": "4205e6ef4ee747aa81930537b6035086ba5f1e28", "tree": "b2ebe2b4621f5f531f283cb9bf0005cd3c04ca7b", "parents": [ "cef401de7be8c4e155c6746bfccf721a4fa5fab9", "9ebea3829fac7505e0cd2642fbd13cfa9c038831" ], "author": { "name": "John W. Linville", "email": "linville@tuxdriver.com", "time": "Mon Jan 28 14:43:00 2013 -0500" }, "committer": { "name": "John W. Linville", "email": "linville@tuxdriver.com", "time": "Mon Jan 28 14:43:00 2013 -0500" }, "message": "Merge branch \u0027master\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/linville/wireless-next into for-davem\n" }, { "commit": "22f837981514e157f8f9737b25ac6d7d90a14006", "tree": "5537a70dcd9225023335b1bd1cd0e9a9c0e95cb9", "parents": [ "949db153b6466c6f7cad5a427ecea94985927311", "6642f91c92da07369cf1e582503ea3ccb4a7f1a9" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Jan 28 11:41:37 2013 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Jan 28 11:41:37 2013 -0800" }, "message": "Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net\n\nPull networking updates from David Miller:\n \"Much more accumulated than I would have liked due to an unexpected\n bout with a nasty flu:\n\n 1) AH and ESP input don\u0027t set ECN field correctly because the\n transport head of the SKB isn\u0027t set correctly, fix from Li\n RongQing.\n\n 2) If netfilter conntrack zones are disabled, we can return an\n uninitialized variable instead of the proper error code. Fix from\n Borislav Petkov.\n\n 3) Fix double SKB free in ath9k driver beacon handling, from Felix\n Feitkau.\n\n 4) Remove bogus assumption about netns cleanup ordering in\n nf_conntrack, from Pablo Neira Ayuso.\n\n 5) Remove a bogus BUG_ON in the new TCP fastopen code, from Eric\n Dumazet. It uses spin_is_locked() in it\u0027s test and is therefore\n unsuitable for UP.\n\n 6) Fix SELINUX labelling regressions added by the tuntap multiqueue\n changes, from Paul Moore.\n\n 7) Fix CRC errors with jumbo frame receive in tg3 driver, from Nithin\n Nayak Sujir.\n\n 8) CXGB4 driver sets interrupt coalescing parameters only on first\n queue, rather than all of them. Fix from Thadeu Lima de Souza\n Cascardo.\n\n 9) Fix regression in the dispatch of read/write registers in dm9601\n driver, from Tushar Behera.\n\n 10) ipv6_append_data miscalculates header length, from Romain KUNTZ.\n\n 11) Fix PMTU handling regressions on ipv4 routes, from Steffen\n Klassert, Timo Teräs, and Julian Anastasov.\n\n 12) In 3c574_cs driver, add necessary parenthesis to \"x \u003c\u003c y \u0026 z\"\n expression. From Nickolai Zeldovich.\n\n 13) macvlan_get_size() causes underallocation netlink message space,\n fix from Eric Dumazet.\n\n 14) Avoid division by zero in xfrm_replay_advance_bmp(), from Nickolai\n Zeldovich. Amusingly the zero check was already there, we were\n just performing it after the modulus :-)\n\n 15) Some more splice bug fixes from Eric Dumazet, which fix things\n mostly eminating from how we now more aggressively use high-order\n pages in SKBs.\n\n 16) Fix size calculation bug when freeing hash tables in the IPSEC\n xfrm code, from Michal Kubecek.\n\n 17) Fix PMTU event propagation into socket cached routes, from Steffen\n Klassert.\n\n 18) Fix off by one in TX buffer release in netxen driver, from Eric\n Dumazet.\n\n 19) Fix rediculous memory allocation requirements introduced by the\n tuntap multiqueue changes, from Jason Wang.\n\n 20) Remove bogus AMD platform workaround in r8169 driver that causes\n major problems in normal operation, from Timo Teräs.\n\n 21) virtio-net set affinity and select queue don\u0027t handle\n discontiguous cpu numbers properly, fix from Wanlong Gao.\n\n 22) Fix a route refcounting issue in loopback driver, from Eric\n Dumazet. There\u0027s a similar fix coming that we might add to the\n macvlan driver as well.\n\n 23) Fix SKB leaks in batman-adv\u0027s distributed arp table code, from\n Matthias Schiffer.\n\n 24) r8169 driver gives descriptor ownership back the hardware before\n we\u0027re done reading the VLAN tag out of it, fix from Francois\n Romieu.\n\n 25) Checksums not calculated properly in GRE tunnel driver fix from\n Pravin B Shelar.\n\n26) Fix SCTP memory leak on namespace exit.\"\n\n* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (101 commits)\n dm9601: support dm9620 variant\n SCTP: Free the per-net sysctl table on net exit. v2\n net: phy: icplus: fix broken INTR pin settings\n net: phy: icplus: Use the RGMII interface mode to configure clock delays\n IP_GRE: Fix kernel panic in IP_GRE with GRE csum.\n sctp: set association state to established in dupcook_a handler\n ip6mr: limit IPv6 MRT_TABLE identifiers\n r8169: fix vlan tag read ordering.\n net: cdc_ncm: use IAD provided by the USB core\n batman-adv: filter ARP packets with invalid MAC addresses in DAT\n batman-adv: check for more types of invalid IP addresses in DAT\n batman-adv: fix skb leak in batadv_dat_snoop_incoming_arp_reply()\n net: loopback: fix a dst refcounting issue\n virtio-net: reset virtqueue affinity when doing cpu hotplug\n virtio-net: split out clean affinity function\n virtio-net: fix the set affinity bug when CPU IDs are not consecutive\n can: pch_can: fix invalid error codes\n can: ti_hecc: fix invalid error codes\n can: c_can: fix invalid error codes\n r8169: remove the obsolete and incorrect AMD workaround\n ...\n" }, { "commit": "9ebea3829fac7505e0cd2642fbd13cfa9c038831", "tree": "ed690568a27b7231b8a507e8ba07c1ae34868e5c", "parents": [ "c5e818ef081c4144177fdbdeed154332cd7e4d7a", "83f0c6d1f502bd75bb4a9e31e8d64e59c6894ad1" ], "author": { "name": "John W. Linville", "email": "linville@tuxdriver.com", "time": "Mon Jan 28 13:54:03 2013 -0500" }, "committer": { "name": "John W. Linville", "email": "linville@tuxdriver.com", "time": "Mon Jan 28 13:54:03 2013 -0500" }, "message": "Merge branch \u0027master\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/linville/wireless\n\nConflicts:\n\tdrivers/net/wireless/ath/ath9k/main.c\n\tdrivers/net/wireless/iwlwifi/dvm/tx.c\n" }, { "commit": "318fe782539c4150d1b8e4e6c9dc3a896512cb8a", "tree": "781f37f1e4f8f4e7523b363d6e58194f831e381c", "parents": [ "949db153b6466c6f7cad5a427ecea94985927311" ], "author": { "name": "Suravee Suthikulpanit", "email": "suravee.suthikulpanit@amd.com", "time": "Thu Jan 24 13:17:53 2013 -0600" }, "committer": { "name": "Joerg Roedel", "email": "joro@8bytes.org", "time": "Mon Jan 28 15:26:54 2013 +0100" }, "message": "IOMMU, AMD Family15h Model10-1Fh erratum 746 Workaround\n\nThe IOMMU may stop processing page translations due to a perceived lack\nof credits for writing upstream peripheral page service request (PPR)\nor event logs. If the L2B miscellaneous clock gating feature is enabled\nthe IOMMU does not properly register credits after the log request has\ncompleted, leading to a potential system hang.\n\nBIOSes are supposed to disable L2B micellaneous clock gating by setting\nL2_L2B_CK_GATE_CONTROL[CKGateL2BMiscDisable](D0F2xF4_x90[2]) \u003d 1b. This\npatch corrects that for those which do not enable this workaround.\n\nSigned-off-by: Suravee Suthikulpanit \u003csuravee.suthikulpanit@amd.com\u003e\nAcked-by: Borislav Petkov \u003cbp@suse.de\u003e\nCc: stable@vger.kernel.org\nSigned-off-by: Joerg Roedel \u003cjoro@8bytes.org\u003e\n" }, { "commit": "8d56b6d507e0c4f6e24680fd202cbaad445935c5", "tree": "15d1593e41ee1ab11ad162eb0fe1f89fbd641c8a", "parents": [ "5ac6f91d39e0884813dc010e14552143cd1d0d8b" ], "author": { "name": "Mitch A Williams", "email": "mitch.a.williams@intel.com", "time": "Fri Jan 18 08:57:20 2013 +0000" }, "committer": { "name": "Jeff Kirsher", "email": "jeffrey.t.kirsher@intel.com", "time": "Mon Jan 28 03:18:13 2013 -0800" }, "message": "igbvf: be sane about random MAC addresses\n\nTighten up some of the code surrounding MAC addresses. Since the PF is\nnow giving all zeros instead of a random address, check for this case\nand generate a random address. This ensures that we always know when we\nhave a random address and udev won\u0027t get upset about it.\n\nAdditionally, tighten up some of the log messages and clean up the\nformatting.\n\nSigned-off-by: Mitch Williams \u003cmitch.a.williams@intel.com\u003e\nCC: Andy Gospodarek \u003candy@greyhouse.net\u003e\nCC: Stefan Assmann \u003csassmann@kpanic.de\u003e\nTested-by: Aaron Brown \u003caaron.f.brown@intel.com\u003e\nTested-by: Stefan Assmann \u003csassmann@redhat.com\u003e\nSigned-off-by: Jeff Kirsher \u003cjeffrey.t.kirsher@intel.com\u003e\n" }, { "commit": "5ac6f91d39e0884813dc010e14552143cd1d0d8b", "tree": "97035a2ebe4779f2eca9799859b32b469b0873e8", "parents": [ "aa19c2957b425f724efe93f2d5a5858b8aa613d7" ], "author": { "name": "Mitch A Williams", "email": "mitch.a.williams@intel.com", "time": "Fri Jan 18 08:57:20 2013 +0000" }, "committer": { "name": "Jeff Kirsher", "email": "jeffrey.t.kirsher@intel.com", "time": "Mon Jan 28 03:17:57 2013 -0800" }, "message": "igb: Don\u0027t give VFs random MAC addresses\n\nIf the user has not assigned a MAC address to a VM, then don\u0027t give it a\nrandom one. Instead, just give it zeros and let it figure out what to do\nwith them.\n\nSigned-off-by: Mitch Williams \u003cmitch.a.williams@intel.com\u003e\nCC: Andy Gospodarek \u003candy@greyhouse.net\u003e\nCC: Stefan Assmann \u003csassmann@kpanic.de\u003e\nTested-by: Aaron Brown \u003caaron.f.brown@intel.com\u003e\nTested-by: Stefan Assmann \u003csassmann@redhat.com\u003e\nSigned-off-by: Jeff Kirsher \u003cjeffrey.t.kirsher@intel.com\u003e\n" }, { "commit": "d4e0bfec9b6fbb9b58640b44e01bb74ae0d29b22", "tree": "255f31601ba4745162979ae0cfe80530d60900ac", "parents": [ "949db153b6466c6f7cad5a427ecea94985927311" ], "author": { "name": "David Teigland", "email": "teigland@redhat.com", "time": "Thu Jan 03 17:52:07 2013 -0500" }, "committer": { "name": "Steven Whitehouse", "email": "swhiteho@redhat.com", "time": "Mon Jan 28 09:49:15 2013 +0000" }, "message": "GFS2: fix skip unlock condition\n\nThe recent commit fb6791d100d1bba20b5cdbc4912e1f7086ec60f8\nincluded the wrong logic. The lvbptr check was incorrectly\nadded after the patch was tested.\n\nSigned-off-by: David Teigland \u003cteigland@redhat.com\u003e\nSigned-off-by: Steven Whitehouse \u003cswhiteho@redhat.com\u003e\n" }, { "commit": "aa19c2957b425f724efe93f2d5a5858b8aa613d7", "tree": "d24845e537648220ca90a9d405cfa5106ab20a36", "parents": [ "39149d4da6d50de92f9e7f70c743a8b8c20eeac1" ], "author": { "name": "Greg Rose", "email": "gregory.v.rose@intel.com", "time": "Thu Jan 24 04:54:48 2013 +0000" }, "committer": { "name": "Jeff Kirsher", "email": "jeffrey.t.kirsher@intel.com", "time": "Mon Jan 28 00:19:52 2013 -0800" }, "message": "ixgbevf: Make sure link status and speed are fetched\n\nA recent change makes it necessary to set get_link_status to ensure that\nthe driver fetches the correct, refreshed value for link status and speed\nwhen it has changed in the physical function device.\n\nSigned-off-by: Greg Rose \u003cgregory.v.rose@intel.com\u003e\nTested-by: Sibai Li \u003csibai.li@intel.com\u003e\nSigned-off-by: Jeff Kirsher \u003cjeffrey.t.kirsher@intel.com\u003e\n" }, { "commit": "39149d4da6d50de92f9e7f70c743a8b8c20eeac1", "tree": "ee6697659236fa4c071f29940d0fcfc8e0261bd6", "parents": [ "a9bb6290392fd9edb7293bb335d0fff1d0b5b376" ], "author": { "name": "Bruce Allan", "email": "bruce.w.allan@intel.com", "time": "Sat Jan 12 07:26:53 2013 +0000" }, "committer": { "name": "Jeff Kirsher", "email": "jeffrey.t.kirsher@intel.com", "time": "Mon Jan 28 00:12:03 2013 -0800" }, "message": "e1000e: cleanup: remove comments which are no longer applicable\n\nCode was removed but the applicable comments were not.\n\nSigned-off-by: Bruce Allan \u003cbruce.w.allan@intel.com\u003e\nTested-by: Aaron Brown \u003caaron.f.brown@intel.com\u003e\nSigned-off-by: Jeff Kirsher \u003cjeffrey.t.kirsher@intel.com\u003e\n" }, { "commit": "a9bb6290392fd9edb7293bb335d0fff1d0b5b376", "tree": "d3e7187d4331a08b830127bd6cb267ca23bcd488", "parents": [ "41c7d9c96342989cd4a7efe27f768df4528294f7" ], "author": { "name": "Bruce Allan", "email": "bruce.w.allan@intel.com", "time": "Sat Jan 12 07:26:22 2013 +0000" }, "committer": { "name": "Jeff Kirsher", "email": "jeffrey.t.kirsher@intel.com", "time": "Sun Jan 27 23:50:50 2013 -0800" }, "message": "e1000e: cleanup hw.h\n\nRemove unnecessary #include, forward prototype of struct e1000_adapter and\nan empty comment; fix a comment which mentions \"static data for the MAC\"\nwhich is not applicable to the following struct; and cleanup some\nwhitespace issues.\n\nSigned-off-by: Bruce Allan \u003cbruce.w.allan@intel.com\u003e\nTested-by: Aaron Brown \u003caaron.f.brown@intel.com\u003e\nSigned-off-by: Jeff Kirsher \u003cjeffrey.t.kirsher@intel.com\u003e\n" }, { "commit": "41c7d9c96342989cd4a7efe27f768df4528294f7", "tree": "a019eb05e9b5941125d804df61608cb4ae07ad70", "parents": [ "3e35d9918cbbc224f88da4dd19cd90b2cd4f765e" ], "author": { "name": "Bruce Allan", "email": "bruce.w.allan@intel.com", "time": "Sat Jan 12 07:25:52 2013 +0000" }, "committer": { "name": "Jeff Kirsher", "email": "jeffrey.t.kirsher@intel.com", "time": "Sun Jan 27 23:28:29 2013 -0800" }, "message": "e1000e: cleanup: remove unused #define\n\nAll references to E1000_ERT_2048 have been removed.\n\nSigned-off-by: Bruce Allan \u003cbruce.w.allan@intel.com\u003e\nTested-by: Aaron Brown \u003caaron.f.brown@intel.com\u003e\nSigned-off-by: Jeff Kirsher \u003cjeffrey.t.kirsher@intel.com\u003e\n" }, { "commit": "3e35d9918cbbc224f88da4dd19cd90b2cd4f765e", "tree": "81baa95ae359030814558a35ffd3c359ebe4ece1", "parents": [ "c3d2dbf403367eb5c17f044aa74b772508d745c1" ], "author": { "name": "Bruce Allan", "email": "bruce.w.allan@intel.com", "time": "Sat Jan 12 07:25:22 2013 +0000" }, "committer": { "name": "Jeff Kirsher", "email": "jeffrey.t.kirsher@intel.com", "time": "Sun Jan 27 23:27:41 2013 -0800" }, "message": "e1000e: adjust PM QoS request\n\nIt has been found that devices other than 82579 (a.k.a. e1000_pch2lan)\nsuffer from dropped transactions on platforms with deep C-states when\njumbo frames are enabled. For example, LOMs on ICH9- and ICH10-based\nplatforms which recently had early-receive de-featured (for stability\nreasons) suffer from this. To resolve this for all devices, when jumbo\nframes are enabled set the PM QoS DMA latency request based on the size\nof the receive packet buffer less one full frame.\n\nSigned-off-by: Bruce Allan \u003cbruce.w.allan@intel.com\u003e\nTested-by: Aaron Brown \u003caaron.f.brown@intel.com\u003e\nSigned-off-by: Jeff Kirsher \u003cjeffrey.t.kirsher@intel.com\u003e\n" }, { "commit": "c3d2dbf403367eb5c17f044aa74b772508d745c1", "tree": "9c1dd535c4384e1b7134d14933cd62da00b14f0b", "parents": [ "6b598e1eac68b07ebb831258e0667f5ba2834822" ], "author": { "name": "Bruce Allan", "email": "bruce.w.allan@intel.com", "time": "Wed Jan 09 01:20:46 2013 +0000" }, "committer": { "name": "Jeff Kirsher", "email": "jeffrey.t.kirsher@intel.com", "time": "Sun Jan 27 22:42:58 2013 -0800" }, "message": "e1000e: correct maximum frame size on 82579\n\nThe largest jumbo frame supported by the 82579 hardware is 9018.\n\nSigned-off-by: Bruce Allan \u003cbruce.w.allan@intel.com\u003e\nTested-by: Jeff Pieper \u003cjeffrey.e.pieper@intel.com\u003e\nSigned-off-by: Jeff Kirsher \u003cjeffrey.t.kirsher@intel.com\u003e\n" }, { "commit": "6b598e1eac68b07ebb831258e0667f5ba2834822", "tree": "333965677d54f113bcc2ccc144e903e8302e4885", "parents": [ "dde3a5745cd27167653feb2e7e9fa0e3631e91ce" ], "author": { "name": "Bruce Allan", "email": "bruce.w.allan@intel.com", "time": "Wed Jan 23 06:50:05 2013 +0000" }, "committer": { "name": "Jeff Kirsher", "email": "jeffrey.t.kirsher@intel.com", "time": "Sun Jan 27 22:35:46 2013 -0800" }, "message": "e1000e: cleanup: remove e1000e_commit_phy()\n\nRemove the function e1000e_commit_phy() and replace the few calls to it\nwith the same function pointer that it would call. The function pointer is\nalmost always set for the devices that access these code paths so there is\nno risk of a NULL pointer dereference; for the few instances where the\nfunction pointer might not be set (i.e. can be called for the few devices\nwhich do not have this function pointer set), check for a valid function\npointer.\n\nSigned-off-by: Bruce Allan \u003cbruce.w.allan@intel.com\u003e\nTested-by: Jeff Pieper \u003cjeffrey.e.pieper@intel.com\u003e\nSigned-off-by: Jeff Kirsher \u003cjeffrey.t.kirsher@intel.com\u003e\n" }, { "commit": "dde3a5745cd27167653feb2e7e9fa0e3631e91ce", "tree": "db60143e7143056c5a163cce12330d6a7f5c0133", "parents": [ "84c1befe341d71ed1b878afa28bb637a0b459161" ], "author": { "name": "Bruce Allan", "email": "bruce.w.allan@intel.com", "time": "Sat Jan 05 08:06:24 2013 +0000" }, "committer": { "name": "Jeff Kirsher", "email": "jeffrey.t.kirsher@intel.com", "time": "Sun Jan 27 22:28:55 2013 -0800" }, "message": "e1000e: cleanup: remove e1000_get_cable_length()\n\nRemove the function e1000_get_cable_length() and replace the two calls\nto it with the same function pointer that it would call.\n\nSigned-off-by: Bruce Allan \u003cbruce.w.allan@intel.com\u003e\nTested-by: Aaron Brown \u003caaron.f.brown@intel.com\u003e\nSigned-off-by: Jeff Kirsher \u003cjeffrey.t.kirsher@intel.com\u003e\n" }, { "commit": "84c1befe341d71ed1b878afa28bb637a0b459161", "tree": "20f0cd65729ddb6ef9e2305cba6054285f38bd2c", "parents": [ "fe90849f76de7cd584e8c6c38b076cd366415994" ], "author": { "name": "Bruce Allan", "email": "bruce.w.allan@intel.com", "time": "Sat Jan 05 08:06:19 2013 +0000" }, "committer": { "name": "Jeff Kirsher", "email": "jeffrey.t.kirsher@intel.com", "time": "Sun Jan 27 22:22:11 2013 -0800" }, "message": "e1000e: cleanup: remove e1000_get_phy_cfg_done()\n\nRemove the function e1000_get_phy_cfg_done() and replace the single call\nto it with the same function pointer that it would call. The function\npointer is always set so there is no risk of a NULL pointer dereference.\n\nSigned-off-by: Bruce Allan \u003cbruce.w.allan@intel.com\u003e\nTested-by: Aaron Brown \u003caaron.f.brown@intel.com\u003e\nSigned-off-by: Jeff Kirsher \u003cjeffrey.t.kirsher@intel.com\u003e\n" }, { "commit": "fe90849f76de7cd584e8c6c38b076cd366415994", "tree": "d322c23e43f01ae318d4a19b29202ad4c46c5f95", "parents": [ "c2c6629ba3f57d19b1385554b7fadb671bc7ab30" ], "author": { "name": "Bruce Allan", "email": "bruce.w.allan@intel.com", "time": "Sat Jan 05 08:06:14 2013 +0000" }, "committer": { "name": "Jeff Kirsher", "email": "jeffrey.t.kirsher@intel.com", "time": "Sun Jan 27 21:48:28 2013 -0800" }, "message": "e1000e: cleanup: rename e1000_get_cfg_done()\n\nIn keeping with the e1000e driver function naming convention, the subject\nfunction is renamed to indicate it is generic, i.e. it is applicable to\nmore than just a single MAC family (e.g. 80003es2lan, 82571, ich8lan).\n\nSigned-off-by: Bruce Allan \u003cbruce.w.allan@intel.com\u003e\nTested-by: Aaron Brown \u003caaron.f.brown@intel.com\u003e\nSigned-off-by: Jeff Kirsher \u003cjeffrey.t.kirsher@intel.com\u003e\n" }, { "commit": "c2c6629ba3f57d19b1385554b7fadb671bc7ab30", "tree": "e6ad9fdd26e9b3668d111085d05e858c77d95cfa", "parents": [ "7de89f058ec2c58ef16582e4efadeb33d711c9e1" ], "author": { "name": "Bruce Allan", "email": "bruce.w.allan@intel.com", "time": "Sat Jan 05 08:06:08 2013 +0000" }, "committer": { "name": "Jeff Kirsher", "email": "jeffrey.t.kirsher@intel.com", "time": "Sun Jan 27 21:41:41 2013 -0800" }, "message": "e1000e: cleanup: remove e1000_force_speed_duplex()\n\nRemove the function e1000_force_speed_duplex() and replace the single call\nto it with the same function pointer that it would call. The function\npointer is always set so there is no risk of a NULL pointer dereference.\n\nSigned-off-by: Bruce Allan \u003cbruce.w.allan@intel.com\u003e\nTested-by: Aaron Brown \u003caaron.f.brown@intel.com\u003e\nSigned-off-by: Jeff Kirsher \u003cjeffrey.t.kirsher@intel.com\u003e\n" }, { "commit": "7de89f058ec2c58ef16582e4efadeb33d711c9e1", "tree": "889377999de86c27ebe1afccf52a1f74e0c913ad", "parents": [ "a1b1add07fa794974573d93483d68e373edfe7bd" ], "author": { "name": "Bruce Allan", "email": "bruce.w.allan@intel.com", "time": "Sat Jan 05 08:06:03 2013 +0000" }, "committer": { "name": "Jeff Kirsher", "email": "jeffrey.t.kirsher@intel.com", "time": "Sun Jan 27 21:32:01 2013 -0800" }, "message": "e1000e: cleanup: remove e1000_set_d0_lplu_state()\n\nReplace the function e1000_set_d0_lplu_state() with the contents of it\ncoded in place of the single call to the function.\n\nSigned-off-by: Bruce Allan \u003cbruce.w.allan@intel.com\u003e\nTested-by: Aaron Brown \u003caaron.f.brown@intel.com\u003e\nSigned-off-by: Jeff Kirsher \u003cjeffrey.t.kirsher@intel.com\u003e\n" }, { "commit": "cef401de7be8c4e155c6746bfccf721a4fa5fab9", "tree": "af082329bf0613ed9de5b9575e3f94f3f03b77ec", "parents": [ "61550022b9586972082904b80de26a464c558437" ], "author": { "name": "Eric Dumazet", "email": "edumazet@google.com", "time": "Fri Jan 25 20:34:37 2013 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Jan 28 00:27:15 2013 -0500" }, "message": "net: fix possible wrong checksum generation\n\nPravin Shelar mentioned that GSO could potentially generate\nwrong TX checksum if skb has fragments that are overwritten\nby the user between the checksum computation and transmit.\n\nHe suggested to linearize skbs but this extra copy can be\navoided for normal tcp skbs cooked by tcp_sendmsg().\n\nThis patch introduces a new SKB_GSO_SHARED_FRAG flag, set\nin skb_shinfo(skb)-\u003egso_type if at least one frag can be\nmodified by the user.\n\nTypical sources of such possible overwrites are {vm}splice(),\nsendfile(), and macvtap/tun/virtio_net drivers.\n\nTested:\n\n$ netperf -H 7.7.8.84\nMIGRATED TCP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to\n7.7.8.84 () port 0 AF_INET\nRecv Send Send\nSocket Socket Message Elapsed\nSize Size Size Time Throughput\nbytes bytes bytes secs. 10^6bits/sec\n\n 87380 16384 16384 10.00 3959.52\n\n$ netperf -H 7.7.8.84 -t TCP_SENDFILE\nTCP SENDFILE TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 7.7.8.84 ()\nport 0 AF_INET\nRecv Send Send\nSocket Socket Message Elapsed\nSize Size Size Time Throughput\nbytes bytes bytes secs. 10^6bits/sec\n\n 87380 16384 16384 10.00 3216.80\n\nPerformance of the SENDFILE is impacted by the extra allocation and\ncopy, and because we use order-0 pages, while the TCP_STREAM uses\nbigger pages.\n\nReported-by: Pravin Shelar \u003cpshelar@nicira.com\u003e\nSigned-off-by: Eric Dumazet \u003cedumazet@google.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "61550022b9586972082904b80de26a464c558437", "tree": "590c21eed5f723162d3821a398b6d3831f75a488", "parents": [ "0e36cbb344575e481167e090f0926701f83207d6", "e6afa00a1409bc3bceed9ccb33111519463dfe7b" ], "author": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Jan 28 00:19:34 2013 -0500" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Jan 28 00:19:34 2013 -0500" }, "message": "Merge branch \u0027for-davem\u0027 of git://gitorious.org/linux-can/linux-can-next\n\nMarc Kleine-Budde says:\n\n\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\nthis is a pull-request for net-next/master. There is are 9 patches by\nFabio Baltieri and Kurt Van Dijck which add LED infrastructure and\nsupport for CAN devices. Bernd Krumboeck adds a driver for the USB CAN\nadapter from 8 devices. Oliver Hartkopp improves the CAN gateway\nfunctionality. There are 4 patches by me, which clean up the CAN\u0027s\nKconfig.\n\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\n\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "6642f91c92da07369cf1e582503ea3ccb4a7f1a9", "tree": "e9c2518e78f98808ff97c4b2fb4af2fab70fe43a", "parents": [ "5f19d1219a5b96c7b00ad5c3f889030093a8d1a3" ], "author": { "name": "Peter Korsgaard", "email": "jacmet@sunsite.dk", "time": "Sun Jan 27 12:34:22 2013 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Jan 28 00:18:04 2013 -0500" }, "message": "dm9601: support dm9620 variant\n\ndm9620 is a newer variant of dm9601 with more features (usb 2.0, checksum\noffload, ..), but it can also be put in a dm9601 compatible mode, allowing\nus to reuse the existing driver.\n\nThis does mean that the extended features like checksum offload cannot be\nused, but that\u0027s hardly critical on a 100mbps interface.\n\nThanks to Sławek Wernikowski \u003cslawek@wernikowski.net\u003e for providing me\nwith a dm9620 based device to test.\n\nSigned-off-by: Peter Korsgaard \u003cjacmet@sunsite.dk\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "0e36cbb344575e481167e090f0926701f83207d6", "tree": "c451ec51b9197d5ad9fe64718e9fb1ae1f12049f", "parents": [ "cec771d646d6c9a6f123b50e132ab142342dcb97" ], "author": { "name": "Cong Wang", "email": "amwang@redhat.com", "time": "Tue Jan 22 21:09:51 2013 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Jan 28 00:15:28 2013 -0500" }, "message": "net: add RCU annotation to sk_dst_cache field\n\nsock-\u003esk_dst_cache is protected by RCU.\n\nReported-by: Fengguang Wu \u003cfengguang.wu@intel.com\u003e\nCc: Eric Dumazet \u003ceric.dumazet@gmail.com\u003e\nCc: David S. Miller \u003cdavem@davemloft.net\u003e\nSigned-off-by: Cong Wang \u003camwang@redhat.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "cec771d646d6c9a6f123b50e132ab142342dcb97", "tree": "d0591d47af01fb210a16635ff316e77161c5ec3a", "parents": [ "78fb2de711ec28997bf38bcf3e48e108e907be77" ], "author": { "name": "Cong Wang", "email": "amwang@redhat.com", "time": "Tue Jan 22 21:09:50 2013 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Jan 28 00:15:27 2013 -0500" }, "message": "decnet: use correct RCU API to deref sk_dst_cache field\n\nsock-\u003esk_dst_cache is protected by RCU, therefore we should\nuse __sk_dst_get() to deref it once we lock the sock.\n\nThis fixes several sparse warnings.\n\nCc: linux-decnet-user@lists.sourceforge.net\nCc: Eric Dumazet \u003ceric.dumazet@gmail.com\u003e\nCc: David S. Miller \u003cdavem@davemloft.net\u003e\nSigned-off-by: Cong Wang \u003camwang@redhat.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "78fb2de711ec28997bf38bcf3e48e108e907be77", "tree": "85c8bb674392d99000bbf2e04014d2f021054324", "parents": [ "7225922558f04f25a22683ce08454dae8dd4b9f4" ], "author": { "name": "Amir Vadai", "email": "amirv@mellanox.com", "time": "Thu Jan 24 01:54:19 2013 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Jan 28 00:14:28 2013 -0500" }, "message": "net/mlx4_en: Initialize RFS filters lock and list in init_netdev\n\nfilters_lock might have been used while it was re-initialized.\nMoved filters_lock and filters_list initialization to init_netdev instead of\nalloc_resources which is called every time the device is configured.\n\nSigned-off-by: Amir Vadai \u003camirv@mellanox.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "7225922558f04f25a22683ce08454dae8dd4b9f4", "tree": "2a3871ca8287e5f197c39d170375df8fe3c93b03", "parents": [ "f356fcbe12c1174713e83651b630330f8f0f8415" ], "author": { "name": "Amir Vadai", "email": "amirv@mellanox.com", "time": "Thu Jan 24 01:54:18 2013 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Jan 28 00:14:24 2013 -0500" }, "message": "net/mlx4_en: Fix a race when closing TX queue\n\nThere is a possible race where the TX completion handler can clean the\nentire TX queue between the decision that the queue is full and actually\nclosing it. To avoid this situation, check again if the queue is really\nfull, if not, reopen the transmit and continue with sending the packet.\n\nCC: Eric Dumazet \u003cedumazet@google.com\u003e\n\nSigned-off-by: Yevgeny Petrilin \u003cyevgenyp@mellanox.com\u003e\nSigned-off-by: Eugenia Emantayev \u003ceugenia@mellanox.com\u003e\nSigned-off-by: Amir Vadai \u003camirv@mellanox.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "f356fcbe12c1174713e83651b630330f8f0f8415", "tree": "8e5582ef389f5567b764806f175477162415f50c", "parents": [ "dbd501a80671180a8f3cdf93ca465959031fef18" ], "author": { "name": "Jack Morgenstein", "email": "jackm@dev.mellanox.co.il", "time": "Thu Jan 24 01:54:17 2013 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Jan 28 00:13:57 2013 -0500" }, "message": "net/mlx4_core: Return proper error code when __mlx4_add_one fails\n\nReturning 0 (success) when in fact we are aborting the load, leads to kernel\npanic when unloading the module. Fix that by returning the actual error code.\n\nSigned-off-by: Jack Morgenstein \u003cjackm@dev.mellanox.co.il\u003e\nSigned-off-by: Eugenia Emantayev \u003ceugenia@mellanox.com\u003e\nSigned-off-by: Amir Vadai \u003camirv@mellanox.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" } ], "next": "dbd501a80671180a8f3cdf93ca465959031fef18" }