)]}' { "log": [ { "commit": "b98eba52784fbd4a96241c5395c2c8d99fdb9433", "tree": "219ee5004554753984442b98043a45b03c831632", "parents": [ "a7fc948f4d11d80ac2bd08335dc1e0fb77ddf468" ], "author": { "name": "Eddie Wai", "email": "waie@broadcom.com", "time": "Mon May 17 17:32:56 2010 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon May 17 17:32:56 2010 -0700" }, "message": "bnx2: Fix register printouts during NETEV_WATCHDOG.\n\nDump the correct MCP registers and add EMAC_RX_STATUS register during\nNETDEV_WATCHDOG for debugging.\n\nSigned-off-by: Eddie Wai \u003cwaie@broadcom.com\u003e\nSigned-off-by: Benjamin Li \u003cbenli@broadcom.com\u003e\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "a33fa66bcf365ffe5b79d1ae1d3582cc261ae56e", "tree": "cf714757a5c3644bd8154a4da0cea4eb53a80032", "parents": [ "c67938a9e071fa51c91ed17a14382e128368d115" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Thu May 06 08:58:13 2010 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Thu May 06 22:17:24 2010 -0700" }, "message": "bnx2: Add prefetches to rx path.\n\nAdd prefetches of the skb and the next rx descriptor to speed up rx path.\n\nUse prefetchw() for the skb [suggested by Eric Dumazet].\n\nThe rx descriptor is in skb-\u003edata which is mapped for streaming mode DMA.\nEric Dumazet pointed out that we should not prefetch the data before\ndma_sync. So we prefetch only if dma_sync is no_op on the system.\n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "1a4ccc2d460f252853dfa2fb38b4ea881916713d", "tree": "a08c297a00cac40459a79ce23bab077bf48f5595", "parents": [ "5e01d2f91df62be4d6f282149bc2a8858992ceca" ], "author": { "name": "FUJITA Tomonori", "email": "fujita.tomonori@lab.ntt.co.jp", "time": "Thu Apr 01 16:56:57 2010 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Wed Apr 07 21:05:35 2010 -0700" }, "message": "bnx2: use the dma state API instead of the pci equivalents\n\nThe DMA API is preferred.\n\nSigned-off-by: FUJITA Tomonori \u003cfujita.tomonori@lab.ntt.co.jp\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "5726026bfffa13e9b1098d7bc177618cbbaa9388", "tree": "ecb18de894b79ef7d6c1dff118ae98196e37ba9e", "parents": [ "e9f26c49ce790de0064474f97d6402ce1fefac2a" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Mon Feb 15 19:42:09 2010 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Tue Feb 16 15:19:03 2010 -0800" }, "message": "bnx2: Adjust flow control water marks.\n\nThe current water marks are too high and can cause unnecessary flow\ncontrol frames.\n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: Benjamin Li \u003cbenli@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "354fcd7774a00809ebefdba75e747364cb22a940", "tree": "5608a763f03b1af9ba8650c9a1e99f5546eb0797", "parents": [ "a47430583dab67b23161b0e75226781deed50138" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Sun Jan 17 07:30:44 2010 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Sun Jan 17 19:16:03 2010 -0800" }, "message": "bnx2: Save statistics during reset.\n\nMTU changes, ring size changes, etc cause the chip to be reset and the\nstatisctics flushed. To keep track of the accumulated statistics, we\nadd code to save the whole statistics block before reset. We also\nmodify the macros and statistics functions to return the sum of the\nsaved and current counters.\n\nBased on original patch by Breno Leitao \u003cleitao@linux.vnet.ibm.com\u003e\n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "20175c57f23cde2049c509eb00a2f9d373478107", "tree": "fb70e0bd2c5d7ac0ef657cbb0cee6acf0f6f064d", "parents": [ "51bf6bb424c14bfd3590a0de03fbd07fc800435e" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Thu Dec 03 09:46:32 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Thu Dec 03 13:18:11 2009 -0800" }, "message": "bnx2: Dump some state during tx timeout.\n\nTo help debug the problem.\n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: Benjamin Li \u003cbenli@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "e95524a726904a1d2b91552f0577838f67d53c6c", "tree": "ae04c29ad8125fb43bbf34f30d9a90e120737233", "parents": [ "a7d5ca40ff56e2cd4e30bbe91f2d0deab6bfc006" ], "author": { "name": "Alexander Duyck", "email": "alexander.h.duyck@intel.com", "time": "Wed Dec 02 16:47:57 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Wed Dec 02 19:57:13 2009 -0800" }, "message": "bnx2: remove skb_dma_map/unmap calls from driver\n\nDue to the fact that skb_dma_map/unmap do not work correctly when a HW\nIOMMU is enabled it has been recommended to go about removing the calls\nfrom the network device drivers.\n\n[ Fix bnx2_free_tx_skbs() ring indexing and use NETDEV_TX_OK return\n code in bnx2_start_xmit() after cleaning up DMA mapping errors. -Mchan ]\n\nSigned-off-by: Alexander Duyck \u003calexander.h.duyck@intel.com\u003e\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: Jeff Kirsher \u003cjeffrey.t.kirsher@intel.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "d0549382da9997834ce65e489d9dbdc4b4693a2b", "tree": "e6b145c7ca382a47e4adb3fe79ff00a976338f5a", "parents": [ "f568a926a353d6816b3704d7367f34371df44ce7" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Wed Oct 28 03:41:59 2009 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Wed Oct 28 03:41:59 2009 -0700" }, "message": "cnic: Fix L2CTX_STATUSB_NUM offset in context memory.\n\nThe BNX2_L2CTX_STATUSB_NUM definition needs to be changed to match\nthe recent firmware update:\n\ncommit 078b0735881c7969aaf21469f3577831cddd9f8c\nbnx2: Update firmware to 5.0.0.j3.\n\nWithout the fix, bnx2 can crash intermittently in bnx2_rx_int() when\niSCSI is enabled.\n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: Benjamin Li \u003cbenli@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "6cdee2f96a97f6da26bd3759c3f8823332fbb438", "tree": "ec79086f05ffc3bdf1aecc37e108ccfc3a95450d", "parents": [ "0625491493d9000e4556bf566d205c28c8e7dc4e", "2fbd3da3877ad8d923b055e5996f80b4d4a6daf4" ], "author": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Wed Sep 02 00:32:56 2009 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Wed Sep 02 00:32:56 2009 -0700" }, "message": "Merge branch \u0027master\u0027 of master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6\n\nConflicts:\n\tdrivers/net/yellowfin.c\n" }, { "commit": "0ced9d01d19795f913b95cebedd7d03986671379", "tree": "712f614dbfdcc8d8641da18d925b1e757fff342e", "parents": [ "cf7474a6f4eda22603591b7d6253dffc224e4784" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Fri Aug 21 16:20:49 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Sat Aug 22 17:48:54 2009 -0700" }, "message": "bnx2: Use const on flash_table structure.\n\nThe structure, once initialized, never changes.\n\nSigned-off-by: Benjamin Li \u003cbenli@broadcom.com\u003e\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "61d9e3fa7eacabfb7879e3da91709f1a5420c507", "tree": "c1a14dc4fa43429961e1b53651870f4b749d66af", "parents": [ "6fefb65e78f098c09d0ab877b2c70421e4c84116" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Fri Aug 21 16:20:46 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Sat Aug 22 17:48:48 2009 -0700" }, "message": "bnx2: Apply BROKEN_STATS workaround to 5706 and 5708.\n\nAdd flag to expand the workaround to both chips.\n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "c5a889508203446c1abc1d670599b3a816841813", "tree": "9e03c5f9a1dd88bcf8e277cdabbde49f1a6ab3e3", "parents": [ "a3059b12adae868c42629ecf058a94195ef1e958" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Fri Aug 14 15:49:45 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Sat Aug 15 18:50:44 2009 -0700" }, "message": "bnx2: Use mutex on slow path cnic calls.\n\nThe slow path calls to the cnic driver are sleepable calls so we\ncannot use rcu_read_lock(). Use mutex for these slow path calls\ninstead.\n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nReviewed-by: Benjamin Li \u003cbenli@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "9cbc1cb8cd46ce1f7645b9de249b2ce8460129bb", "tree": "8d104ec2a459346b99413b0b77421ca7b9936c1a", "parents": [ "ca44d6e60f9de26281fda203f58b570e1748c015", "45e3e1935e2857c54783291107d33323b3ef33c8" ], "author": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Jun 15 03:02:23 2009 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Jun 15 03:02:23 2009 -0700" }, "message": "Merge branch \u0027master\u0027 of master.kernel.org:/pub/scm/linux/kernel/git/torvalds/linux-2.6\n\nConflicts:\n\tDocumentation/feature-removal-schedule.txt\n\tdrivers/scsi/fcoe/fcoe.c\n\tnet/core/drop_monitor.c\n\tnet/core/net-traces.c\n" }, { "commit": "4edd473f208cff77ce1f7ef26d5a41f31fa198e0", "tree": "3ae81d17069288b068d91ba9f2e329c1e5872fea", "parents": [ "43514774ff40c4fbe0cbbd3d8293a359f1a9fe71" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Mon Jun 08 18:14:42 2009 -0700" }, "committer": { "name": "James Bottomley", "email": "James.Bottomley@HansenPartnership.com", "time": "Tue Jun 09 10:22:38 2009 -0500" }, "message": "[SCSI] bnx2: Add support for CNIC driver.\n\nAdd interface and functions to support a new CNIC driver to drive\nthe Broadcom bnx2 hardware for iSCSI offload.\n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nAcked-by: David S. Miller \u003cdavem@davemloft.net\u003e\nSigned-off-by: James Bottomley \u003cJames.Bottomley@HansenPartnership.com\u003e\n" }, { "commit": "d62fda082c48b417b47a553860abf75d9cf8b591", "tree": "1b2679e4fcce72eb6ac584ecf9cc039fe9ea2c4a", "parents": [ "9dc20c5f78c53bf57fb7874b6e942842e1db20d3" ], "author": { "name": "Eric Dumazet", "email": "dada1@cosmosbay.com", "time": "Tue May 12 20:48:02 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Sun May 17 20:47:44 2009 -0700" }, "message": "bnx2: bnx2_tx_int() optimizations\n\nWhen using bnx2 in a high transmit load, bnx2_tx_int() cost is pretty high.\n\nThere are two reasons.\n\nOne is an expensive call to bnx2_get_hw_tx_cons(bnapi) for each freed skb\n\nOne is cpu stalls when accessing skb_is_gso(skb) / skb_shinfo(skb)-\u003enr_frags\nbecause of two cache line misses.\n(One to get skb-\u003eend/head to compute skb_shinfo(skb),\n one to get is_gso/nr_frags)\n\nThis patch :\n\n1) avoids calling bnx2_get_hw_tx_cons(bnapi) too many times.\n\n2) makes bnx2_start_xmit() cache is_gso \u0026 nr_frags into sw_tx_bd descriptor.\n This uses a litle bit more ram (256 longs per device on x86), but helps a lot.\n\n3) uses a prefetch(\u0026skb-\u003eend) to speedup dev_kfree_skb(), bringing\n cache line that will be needed in skb_release_data()\n\nresult is 5 % bandwidth increase in benchmarks, involving UDP or TCP receive\n \u0026 transmits, when a cpu is dedicated to ksoftirqd for bnx2.\n\nbnx2_tx_int going from 3.33 % cpu to 0.5 % cpu in oprofile\n\nNote : skb_dma_unmap() still very expensive but this is for another patch,\nnot related to bnx2 (2.9 % of cpu, while it does nothing on x86_32)\n\nSigned-off-by: Eric Dumazet \u003cdada1@cosmosbay.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "57579f7629a3d46c307405fbd2ea6bdb650d692f", "tree": "c407da542bfa50989bfc4f41daf7c1a181207d93", "parents": [ "5d4d9e8ad6c646c4811bf0049df761dee6affc3d" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Sat Apr 04 16:51:14 2009 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Sat Apr 04 16:51:14 2009 -0700" }, "message": "bnx2: Use request_firmware()\n\nBased on original patch by Ben Hutchings \u003cben@decadent.org.uk\u003e and\nBastian Blank \u003cwaldi@debian.org\u003e, with the following main changes:\n\nSeparated the mips firmware and rv2p firmware into different files\nto make it easier to update them separately.\n\nAdded some code to fixup the rv2p code with run-time information\nsuch as PAGE_SIZE.\n\nUpdate version to 2.0.0.\n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "a6952b5299ab506051f05395f7c26ff1352759ad", "tree": "92e21b85d2c2e424b6bcc4a69597cc2a28cd089c", "parents": [ "990ec3804bb9fd37fcce3e165c95e8b79a783aa3" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Thu Feb 12 16:54:48 2009 -0800" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Thu Feb 12 16:54:48 2009 -0800" }, "message": "bnx2: Update version to 1.9.2 and copyright.\n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "f6d52432a4bc6da5de2a0bbb350f735db3206aa5", "tree": "c04b76071b57bd461d826cc1ec0384911f66d429", "parents": [ "1f2435e532bd64742c3f766b7d5c17cc9d0b8558" ], "author": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Tue Dec 16 23:45:02 2008 -0800" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Tue Dec 16 23:54:23 2008 -0800" }, "message": "bnx2: Don\u0027t redefine FLOW_CTRL_{RX,TX}.\n\nThey are provided generically by linux/mii.h now.\n\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "4e1d0de95c55383f598516ebf82969260c18e4bd", "tree": "cf990d6d5f86cffc323e2d82883204b729296dbe", "parents": [ "f40e0638237a2d3e2ce8bedf3af4b3c02cf6fff7" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Tue Dec 16 20:27:45 2008 -0800" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Tue Dec 16 20:27:45 2008 -0800" }, "message": "bnx2: Rename MSI-X vectors.\n\nChange MSI-X vector names to \"ethx-%d\".\n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: Benjamin Li \u003cbenli@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "730c30ec646bd252a9448a66ecd51d794853513f", "tree": "c0d413860f9d8bf37374f17cfabb4911143465d7", "parents": [ "726e07a8a38168266ac95d87736f9501a2d9e7b2", "0a0755c9fe47dc9f8271935909c66096e43efbfe" ], "author": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Fri Dec 05 22:54:40 2008 -0800" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Fri Dec 05 22:54:40 2008 -0800" }, "message": "Merge branch \u0027master\u0027 of master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6\n\nConflicts:\n\n\tdrivers/net/wireless/iwlwifi/iwl-core.c\n\tdrivers/net/wireless/iwlwifi/iwl-sta.c\n" }, { "commit": "efba01803c8570bab11d0d6188a630231d0ddccf", "tree": "ef7971d2aade5064c6049d21db871244194611a9", "parents": [ "d5654efd3ff1cd0baa935a0c9a5d89862f07d009" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Wed Dec 03 00:36:15 2008 -0800" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Wed Dec 03 00:36:15 2008 -0800" }, "message": "bnx2: Add workaround to handle missed MSI.\n\nThe bnx2 chips do not support per MSI vector masking. On 5706/5708, new MSI\naddress/data are stored only when the MSI enable bit is toggled. As a result,\nSMP affinity no longer works in the latest kernel. A more serious problem is\nthat the driver will no longer receive interrupts when the MSI receiving CPU\ngoes offline.\n\nThe workaround in this patch only addresses the problem of CPU going offline.\nWhen that happens, the driver\u0027s timer function will detect that it is making\nno forward progress on pending interrupt events and will recover from it.\n\nEric Dumazet reported the problem.\n\nWe also found that if an interrupt is internally asserted while MSI and INTA\nare disabled, the chip will end up in the same state after MSI is re-enabled.\nThe same workaround is needed for this problem. \n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nTested-by: Eric Dumazet \u003cdada1@cosmosbay.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "d8e8034dcdef8c8fa94a14c3b555c09e065e742f", "tree": "ffa5e2dfb8ea234a5555de8339f4f32d9357619c", "parents": [ "9fd428761adbd5fbd7e23c312955eec1db8ace7a" ], "author": { "name": "Ilpo Järvinen", "email": "ilpo.jarvinen@helsinki.fi", "time": "Fri Nov 28 15:52:43 2008 -0800" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Fri Nov 28 15:52:43 2008 -0800" }, "message": "bnx2: use net_device_stats nowadays available in net_device\n\nSigned-off-by: Ilpo Järvinen \u003cilpo.jarvinen@helsinki.fi\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "40105c0b0753515711318db87d36c8338dc74490", "tree": "fba1e682769648d1856ce1d09f1481c7d2eae170", "parents": [ "d8026d939495c105cf747c0196a8fa738cf2ad20" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Wed Nov 12 16:02:45 2008 -0800" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Wed Nov 12 16:02:45 2008 -0800" }, "message": "bnx2: Reorganize timeout constants.\n\nMove all related timeout constants to the same location. BNX2\nprefix is also added to make them more consistent.\n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nSigned-off-by: Benjamin Li \u003cbenli@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "d8026d939495c105cf747c0196a8fa738cf2ad20", "tree": "9240f3af1002c84bfdedbc4c952234684eef3a92", "parents": [ "5ec6d7bf195c2e70003ff30e4f51390ef7e85a31" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Wed Nov 12 16:02:20 2008 -0800" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Wed Nov 12 16:02:20 2008 -0800" }, "message": "bnx2: Set rx buffer water marks based on MTU.\n\nThe default rx buffer water marks for XOFF/XON are for 1500 MTU. At\nlarger MTUs, these water marks need to be adjusted for effective\nflow control.\n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nSigned-off-by: Benjamin Li \u003cbenli@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "3d16af8665504c89f9ef3aae56f54fb93e48da61", "tree": "465889b9ddae41530e7203d0eb97e7661fb2db93", "parents": [ "a1efb4b686babf38e5e63add8b990f18e38becc4" ], "author": { "name": "Benjamin Li", "email": "benli@broadcom.com", "time": "Thu Oct 09 12:26:41 2008 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Thu Oct 09 12:26:41 2008 -0700" }, "message": "bnx2: Handle DMA mapping errors.\n\nBefore, the driver would not care about the return codes from pci_map_*\nfunctions. This could be potentially dangerous if a mapping failed.\nNow, we will check all pci_map_* calls. On the transmit side, we switch\nto use the new function skb_dma_map(). On the receive side, we add\npci_dma_mapping_error().\n\nSigned-off-by: Benjamin Li \u003cbenli@broadcom.com\u003e\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "b262e60309e1b0eb25d300c7e739427d5316abb1", "tree": "bf319d78c79bb5cb617ff0c8340c73aa349bba15", "parents": [ "93c8b90f01f0dc73891da4e84b26524b61d29d66", "0523820482dcb42784572ffd2296c2f08c275a2b" ], "author": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Wed Oct 01 06:12:56 2008 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Wed Oct 01 06:12:56 2008 -0700" }, "message": "Merge branch \u0027master\u0027 of master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6\n\nConflicts:\n\n\tdrivers/net/wireless/ath9k/core.c\n\tdrivers/net/wireless/ath9k/main.c\n\tnet/core/dev.c\n" }, { "commit": "27ed9ddfde8d2967076c51815e4ce297c4a18139", "tree": "98fff4be1e8c4192d902c402bfb85e282bac53e3", "parents": [ "add52379dde2e5300e2d574b172e62c6cf43b3d3" ], "author": { "name": "Benjamin Li", "email": "benli@broadcom.com", "time": "Thu Sep 18 16:46:11 2008 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Thu Sep 18 16:46:11 2008 -0700" }, "message": "bnx2: Promote vector field in bnx2_irq structure from u16 to unsigned int\n\nThe bnx2 driver stores/uses the irq value from the pci_dev internally.\nBut when it stores the irq value, it has been performing an\ninteger demotion. Because of the recent changes made to\narch/x86/kernel/io_apic.c, the new method in creating the irq value\n(using build_irq_for_pci_dev()) has exposed this bug on x86 systems.\n\nBecause of this demotion when calling request_irq() from\nbnx2_request_irq(), the driver would get a return code of -EINVAL.\nThis is because the kernel could not find the requested irq descriptor.\nBy storing the irq value properly, the kernel can find the correct\nirq descriptor and the bnx2 driver can operate normally.\n\nSigned-off-by: Benjamin Li \u003cbenli@broadcom.com\u003e\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "ac392abce936d78f7b731d90bfbc1001ddb446ea", "tree": "a5ed2bc8da59aa34748b418365496baf442d9521", "parents": [ "fbbf68b7f88953a9c56b7a7b4019fa5212987b34" ], "author": { "name": "Benjamin Li", "email": "benli@broadcom.com", "time": "Thu Sep 18 16:40:49 2008 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Thu Sep 18 16:40:49 2008 -0700" }, "message": "bnx2: Remove timer_interval field from the bnx2 structure\n\nThe timer_interval field is only assigned once, and never reassigned.\nWe can safely replace all instances of the timer_interval with a\nconstant value.\n\nSigned-off-by: Benjamin Li \u003cbenli@broadcom.com\u003e\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nAcked-by: Jeff Garzik \u003cjeff@garzik.org\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "fbbf68b7f88953a9c56b7a7b4019fa5212987b34", "tree": "0baee873b2eb091946b537595d27ce2688df9c56", "parents": [ "453a9c6e995149c4a43e50b5482a48ed0298b0dc" ], "author": { "name": "Benjamin Li", "email": "benli@broadcom.com", "time": "Thu Sep 18 16:40:03 2008 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Thu Sep 18 16:40:03 2008 -0700" }, "message": "bnx2: Remove name field from bnx2 structure\n\nThe name of the board is only used during the initialization of\nthe adapter. We can save the space of a pointer by not storing\nthis information.\n\nSigned-off-by: Benjamin Li \u003cbenli@broadcom.com\u003e\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nAcked-by: Jeff Garzik \u003cjeff@garzik.org\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "706bf24038ba88ec77503b4829b16da712a32f04", "tree": "522c78dad8ebe426ce9c1244b260a102d50a8c7c", "parents": [ "4f83ec19bbd0c78a2158c7a5d28f70d8b4417803" ], "author": { "name": "Benjamin Li", "email": "benli@broadcom.com", "time": "Fri Jul 18 17:55:11 2008 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Fri Jul 18 17:55:11 2008 -0700" }, "message": "bnx2: Add TX multiqueue support.\n\nSigned-off-by: Benjamin Li \u003cbenli@broadcom.com\u003e\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "5fcaed0124cde73124227542bfce4ed57fccbb50", "tree": "408431b6e281b4c7db2fabced90493ee3bc80b56", "parents": [ "7c62e83beb1446d690ed921beddb0dcf34c9baa9" ], "author": { "name": "Benjamin Li", "email": "benli@broadcom.com", "time": "Mon Jul 14 22:39:52 2008 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Jul 14 22:39:52 2008 -0700" }, "message": "bnx2: Support secondary MAC addresses.\n\nAdd support for configuring secondary unicast addresses. There\nare 4 additional perfect match filters which can be used for\nsecondary unicast address support.\n\n * Modified bnx2_set_mac_addr() to be more generic in handling\n the setting of the perfect match filters\n * Changed bnx2_set_rx_mode() to handle the unicast dev_addr_list\n\nSigned-off-by: Benjamin Li \u003cbenli@broadcom.com\u003e\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "7c62e83beb1446d690ed921beddb0dcf34c9baa9", "tree": "1961273dd946f6b82bb7831dbcd56a422d83c97f", "parents": [ "a2f138900d5c342742c369293edaf92d2173c92e" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Mon Jul 14 22:39:03 2008 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Jul 14 22:39:03 2008 -0700" }, "message": "bnx2: Allow flexible VLAN tag settings.\n\nNegotiate with boot code and ASF firmware to see if it can\nsupport keeping VLAN tags in the RX packets. If supported\nby firmware, the VLAN tag will be kept in the RX packet\nunless VLAN acceleration is registered.\n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "5e9ad9e108883503fedfac3279ac101dce00bb56", "tree": "240d424599a9c384d382b56633b3bba4100aa97e", "parents": [ "2dffcc3dcd659b10ff97c6eda427d9d83a94a399" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Thu Jun 19 16:43:17 2008 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Thu Jun 19 16:43:17 2008 -0700" }, "message": "bnx2: Turn on multi rx rings.\n\nEnable multiple rx rings if MSI-X vectors are available. We enable\nup to 7 rx rings.\n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: Benjamin Li \u003cbenli@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "43e80b89b65cbc62b5e0fde09b47c9fc572a8b11", "tree": "894984eda36c720a44e00a6bd1c1c2567b45102b", "parents": [ "bb4f98abf590cf9899017f14f1a54984f02a0009" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Thu Jun 19 16:41:08 2008 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Thu Jun 19 16:41:08 2008 -0700" }, "message": "bnx2: Optimize fast-path tx and rx work.\n\nAdd hw_tx_cons_ptr and hw_rx_cons_ptr to speed up the retreival of\nthe tx and rx consumer index, since the MSI-X and default status\nblocks have different structures.\n\nCombine status_blk and status_blk_msix into a union. We\u0027ll only use\none type of status block for each vector.\n\nSeparate the code to detect more rx and tx work from the code to\ndetect link related work.\n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: Benjamin Li \u003cbenli@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "bb4f98abf590cf9899017f14f1a54984f02a0009", "tree": "602da9b7cab22a16f2f1fd77f5db51a3de44b085", "parents": [ "35e9010b22503f42cbf88144ffe1feff90ea3835" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Thu Jun 19 16:38:19 2008 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Thu Jun 19 16:38:19 2008 -0700" }, "message": "bnx2: Put rx ring variables in a separate struct.\n\nIn preparation for multi-ring support, rx ring variables are now put\nin a separate bnx2_rx_ring_info struct. With MSI-X, we can support\nmultiple rx rings.\n\nThe functions to allocate/free rx memory and to initialize rx rings\nare now modified to handle multiple rings.\n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: Benjamin Li \u003cbenli@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "35e9010b22503f42cbf88144ffe1feff90ea3835", "tree": "ee2c0e5ae61ee6a7508cce38ed2a79ce52049d38", "parents": [ "4497b0763cb1afae463f5e144c28b5d806e28b60" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Thu Jun 19 16:37:42 2008 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Thu Jun 19 16:37:42 2008 -0700" }, "message": "bnx2: Put tx ring variables in a separate struct.\n\nIn preparation for multi-ring support, tx ring variables are now put\nin a separate bnx2_tx_ring_info struct. Multi tx ring will not be\nenabled until it is fully supported by the stack. Only 1 tx ring\nwill be used at the moment.\n\nThe functions to allocate/free tx memory and to initialize tx rings\nare now modified to handle multiple rings.\n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: Benjamin Li \u003cbenli@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "4ae127d1b6c71f9240dd4245f240e6dd8fc98014", "tree": "b7aa27b3e0c655f4613fe2146cb57d7f69e421f6", "parents": [ "875ec4333b99144e2589e900a0bcd2c25c757b27", "7775c9753b94fe429dc4323360d6502c95e0dd6e" ], "author": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Fri Jun 13 20:52:39 2008 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Fri Jun 13 20:52:39 2008 -0700" }, "message": "Merge branch \u0027master\u0027 of master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6\n\nConflicts:\n\n\tdrivers/net/smc911x.c\n" }, { "commit": "4bb073c0e32a0862bdb5215d11af19f6c0180c98", "tree": "009d95592e3813346c75129bb19d140d393ca913", "parents": [ "7afb380db43ed137b7f67e0e3c3e5afd1ecde730" ], "author": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Thu Jun 12 02:22:02 2008 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Thu Jun 12 02:22:02 2008 -0700" }, "message": "net: Eliminate flush_scheduled_work() calls while RTNL is held.\n\nIf the RTNL is held when we invoke flush_scheduled_work() we could\ndeadlock. One such case is linkwatch, it is a work struct which tries\nto grab the RTNL semaphore.\n\nThe most common case are net driver -\u003estop() methods. The\nsimplest conversion is to instead use cancel_{delayed_}work_sync()\nexplicitly on the various work struct the driver uses.\n\nThis is an OK transformation because these work structs are doing\nthings like resetting the chip, restarting link negotiation, and so\nforth. And if we\u0027re bringing down the device, we\u0027re about to turn the\nchip off and reset it anways. So if we cancel a pending work event,\nthat\u0027s fine here.\n\nSome drivers were working around this deadlock by using a msleep()\npolling loop of some sort, and those cases are converted to instead\nuse cancel_{delayed_}work_sync() as well.\n\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "601d3d18b2c1e4c197aa3cd902fb77bd99c41f10", "tree": "5151028aa528f0d8bcbe166bacfb0ea235339043", "parents": [ "d89cb6af41559a601e9cfe081d34de07945b0d8b" ], "author": { "name": "Benjamin Li", "email": "benli@broadcom.com", "time": "Fri May 16 22:19:35 2008 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Fri May 16 22:19:35 2008 -0700" }, "message": "bnx2: Rename RX_COPY_THRESH to BNX2_RX_COPY_THRESH.\n\nTo make the bnx2 code more consistent, all instances of\nRX_COPY_THRESH have been changed to BNX2_RX_COPY_THRESH.\n\nSigned-off-by: Benjamin Li \u003cbenli@broadcom.com\u003e\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "d89cb6af41559a601e9cfe081d34de07945b0d8b", "tree": "cf6aa02b5b014eb8d6bda336ec001472792fdca8", "parents": [ "6ff2da49c8a68320c2564006c94a492db58de5cd" ], "author": { "name": "Benjamin Li", "email": "benli@broadcom.com", "time": "Fri May 16 22:18:57 2008 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Fri May 16 22:18:57 2008 -0700" }, "message": "bnx2: Remove the rx_offset field from the bnx2 structure.\n\nThe rx_offset field is set to a constant value and initialized\nonly once. By replacing all references to the rx_offset field,\nwe can eliminate rx_offset from the bnx2 structure. This will\nsave 4 bytes for every bnx2 instance.\n\n[Added parentheses to the definition of BNX2_RX_OFFSET, as noted\nby Ben Hutchings.]\n\nSigned-off-by: Benjamin Li \u003cbenli@broadcom.com\u003e\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "38ea3686f6d1110a3787dfd7c5cf7bad1926818b", "tree": "9fcbc871ef493c4f718959ffe7a268a82eacc925", "parents": [ "a2724e2559a3c41ac6182da6e2446d3abf0720a5" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Sat Feb 23 19:48:57 2008 -0800" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Sat Feb 23 19:48:57 2008 -0800" }, "message": "[BNX2]: Disable parallel detect on an HP blade.\n\nBecause of some board issues, we need to disable parallel detect on\nan HP blade. Without this patch, the link state can become stuck\nwhen it goes into parallel detect mode.\n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "83e3fc89bb2b7bb27b3a6da5a541c43ce7706f42", "tree": "1216f5b1f02e30362d5cd153d29ac4e1182b0f1f", "parents": [ "62a8313cddbea04f2a28d1d76acf317c2a56cfae" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Tue Jan 29 21:37:17 2008 -0800" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Thu Jan 31 19:27:16 2008 -0800" }, "message": "[BNX2]: Fine-tune flow control on 5709.\n\nMake use of the programmable high/low water marks in 5709 for\n802.3 flow control.\n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "62a8313cddbea04f2a28d1d76acf317c2a56cfae", "tree": "fc4f14124044b98b417df64b607386e24e0789c4", "parents": [ "2726d6e126c0c16efeba30356d4ae105f1854d1e" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Tue Jan 29 21:35:40 2008 -0800" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Thu Jan 31 19:27:15 2008 -0800" }, "message": "[BNX2]: Remove CTX_WR macro.\n\nThe CTX_WR macro is unnecessary and obfuscates the code.\n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "2726d6e126c0c16efeba30356d4ae105f1854d1e", "tree": "e952b9ab7aebe5822d1ec9379f247708422221bf", "parents": [ "6f743ca052575a26439d796249d9e7740b8192d7" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Tue Jan 29 21:35:05 2008 -0800" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Thu Jan 31 19:27:14 2008 -0800" }, "message": "[BNX2]: Remove REG_WR_IND/REG_RD_IND macros.\n\nThe REG_WR_IND/REG_RD_IND macros are unnecessary and obfuscate the\ncode. Many callers to these macros read and write shared memory from\nthe bp-\u003eshmem_base, so we add 2 similar functions that automatically\nadd the shared memory base.\n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "6f743ca052575a26439d796249d9e7740b8192d7", "tree": "1fb81426131ff21d4201b565e9d007c4fbc2686c", "parents": [ "f3014c0cb60ec15a0a2542cbfae7e8d888aa5cf8" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Tue Jan 29 21:34:08 2008 -0800" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Thu Jan 31 19:27:13 2008 -0800" }, "message": "[BNX2]: Refine tx coalescing setup.\n\nMake the tx coalescing setup code independent of the MSIX vector.\n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "f3014c0cb60ec15a0a2542cbfae7e8d888aa5cf8", "tree": "9b57e7a8c0efdbdaccd9ee1800d3e924ebebbd70", "parents": [ "b6c0632105f7d7548f1d642ba830088478d4f2b0" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Tue Jan 29 21:33:03 2008 -0800" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Thu Jan 31 19:27:12 2008 -0800" }, "message": "[BNX2]: Fix 5706 serdes link down bug.\n\n1. Correct the MII expansion serdes control register definition.\n2. Check an additional RUDI_INVALID bit when determining 5706S link.\n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "b491edd5817f1618f4e06d67638739591a714bdb", "tree": "2e0aae92f7190b7b3f0de336229eb726b30a3264", "parents": [ "f305f789bb96ee6e35e71f58324b72abb7bd0b13" ], "author": { "name": "Al Viro", "email": "viro@ftp.linux.org.uk", "time": "Sat Dec 22 19:44:51 2007 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Jan 28 15:10:32 2008 -0800" }, "message": "bnx2 annotations\n\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\nSigned-off-by: Jeff Garzik \u003cjeff@garzik.org\u003e\n" }, { "commit": "583c28e5645c464b57b4f5d3d53113c06bb0ac5f", "tree": "636d9220936d4e62b703913581fc669956e74824", "parents": [ "ecfdc8c5424079393a9b05e8a5aaf5c6873029f6" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Mon Jan 21 19:51:35 2008 -0800" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Jan 28 15:10:23 2008 -0800" }, "message": "[BNX2]: Fix driver phy_flags name space.\n\nPrefix \"bp-\u003ephy_flags\" names with BNX2_PHY_FLAG_* for consistency.\n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "f86e82fb547efe05457391df069cce7ab530b181", "tree": "31365a448cbf0327c329f9ea3393875f6f54f9e4", "parents": [ "feebb33183cee0fdf8e8a9c4f0da3231f0cfa2bb" ], "author": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Jan 21 17:15:40 2008 -0800" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Jan 28 15:10:16 2008 -0800" }, "message": "[BNX2]: Fix driver software flag namespace.\n\nPrefix \"bnx2-\u003eflags\" names with BNX2_* for consistency.\n\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "b2fadeae1334008c1bb4d87bc507141cb7aaf0e8", "tree": "26fbaeefce8860a40e54852783280446c4c95847", "parents": [ "1097f5e92107ca3950fabf5e1d724faa80c91e7f" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Mon Jan 21 17:07:06 2008 -0800" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Jan 28 15:10:15 2008 -0800" }, "message": "[BNX2]: Add link-down workaround on 5706 serdes.\n\nIn some blade systems using the 5706 serdes, the hardware sometimes\ndoes not properly generate link down interrupts. We add a workaround\nin the driver\u0027s timer to force a link-down when some PHY registers\nreport loss of SYNC.\n\nThe parallel detect logic is cleaned up slightly to better integrate\nthe workaround.\n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "2dd201d7b735f252df1a915a3f2e6a71910a3d87", "tree": "09a3fa5be7947c52a30cf640c40b230eb6cc72d6", "parents": [ "819d772b0ceddebb5b4907d5aa5505c99aec985b" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Mon Jan 21 17:06:09 2008 -0800" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Jan 28 15:10:13 2008 -0800" }, "message": "[BNX2]: Disable jumbo rx paging on 5709 Ax.\n\nThe chip has problem running in this mode and needs to be disabled.\n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "57851d84533655db6948e25c54df19ecb673bf2f", "tree": "631cf8e8cf72e5766294fb9658035d442131ceff", "parents": [ "c76c04758b8fd24a1c38b19742e3437e954e945b" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Thu Dec 20 20:01:44 2007 -0800" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Jan 28 14:57:39 2008 -0800" }, "message": "[BNX2]: Enable new tx ring.\n\nEnable new tx ring and add new MSIX handler and NAPI poll function\nfor the new tx ring. Enable MSIX when the hardware supports it.\n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "c76c04758b8fd24a1c38b19742e3437e954e945b", "tree": "248d6953e058d7513c5bb9442f24a0ae92ea4305", "parents": [ "b4b360420dcbbffb15f5749fc78225f4113cc7e2" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Thu Dec 20 20:01:19 2007 -0800" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Jan 28 14:57:38 2008 -0800" }, "message": "[BNX2]: Add support for a new tx ring.\n\nTo separate TX IRQs into a different MSIX vector, we need to\nsupport a new tx ring. The original tx ring will still be used\nwhen not using MSIX.\n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "b4b360420dcbbffb15f5749fc78225f4113cc7e2", "tree": "a7378249d52fd80ac2599c66f624abf5918318ed", "parents": [ "a1f6019090f2c075b41624c32a825775f6865577" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Thu Dec 20 19:59:30 2007 -0800" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Jan 28 14:57:37 2008 -0800" }, "message": "[BNX2]: Support multiple MSIX IRQs.\n\nChange bnx2_napi struct into an array and add code to manage multiple\nIRQs. MSIX hardware structures and new registers are also added.\n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "a1f6019090f2c075b41624c32a825775f6865577", "tree": "62fabe6555766ee35328e0c280bcf8c324a2ab6c", "parents": [ "a550c99bc39caf292ed214c0c9c2c4d0b9c95161" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Thu Dec 20 19:57:19 2007 -0800" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Jan 28 14:57:37 2008 -0800" }, "message": "[BNX2]: Move rx indexes into bnx2_napi struct.\n\nRx related fields used in NAPI polling are moved from the main\nbnx2 struct to the bnx2_napi struct.\n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "a550c99bc39caf292ed214c0c9c2c4d0b9c95161", "tree": "061b23ae2c3478f8863a1978117ac394b9b7a6b0", "parents": [ "35efa7c1f4aa868d4a948a9069f20ccef1b3b28d" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Thu Dec 20 19:56:59 2007 -0800" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Jan 28 14:57:36 2008 -0800" }, "message": "[BNX2]: Move tx indexes into bnx2_napi struct.\n\nTx related fields used in NAPI polling are moved from the main\nbnx2 struct to the bnx2_napi struct.\n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "35efa7c1f4aa868d4a948a9069f20ccef1b3b28d", "tree": "9369da5bfcd93139ce0ac961059d29b57c66626c", "parents": [ "6d866ffc69b0c3e584782f212a3f783708d31e9a" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Thu Dec 20 19:56:37 2007 -0800" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Jan 28 14:57:35 2008 -0800" }, "message": "[BNX2]: Introduce new bnx2_napi structure.\n\nIntroduce a bnx2_napi structure that will hold a napi_struct and\nother fields to handle NAPI polling for the napi_struct. Various tx\nand rx indexes and status block pointers will be moved from the main\nbnx2 structure to this bnx2_napi structure.\n\nMost NAPI path functions are modified to be passed this bnx2_napi\nstruct pointer.\n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "6d866ffc69b0c3e584782f212a3f783708d31e9a", "tree": "b8a25c8fe7b53344b82c3c07eda5109c832a2b31", "parents": [ "ead7270b993bed77cb45a5bc786a879679e2b16a" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Thu Dec 20 19:56:09 2007 -0800" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Jan 28 14:57:34 2008 -0800" }, "message": "[BNX2]: Restructure IRQ datastructures.\n\nAdd a table to keep track of multiple IRQs and restructure the IRQ\nrequest and free functions so that they can be easily expanded to\nhandle multiple IRQs.\n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "1db82f2aec0766edd4a4f8d86283e91559350de7", "tree": "7f356cec78c596ca2c6143c5c2fdbfeed13fe802", "parents": [ "47bf4246a357d36762c9e7c282d7307152eb92e1" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Wed Dec 12 11:19:35 2007 -0800" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Jan 28 14:57:31 2008 -0800" }, "message": "[BNX2]: Add fast path code to handle RX pages.\n\nAdd function to reuse a page in case of allocation or other errors.\nAdd code to construct the completed SKB with the additional data in\nthe pages.\n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "47bf4246a357d36762c9e7c282d7307152eb92e1", "tree": "91f28518be9daf3a2e26efd9efa9bdbb4b664454", "parents": [ "110d0ef9907b519fed1607c73b3ae883f270561e" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Wed Dec 12 11:19:12 2007 -0800" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Jan 28 14:57:30 2008 -0800" }, "message": "[BNX2]: Add init. code to handle RX pages.\n\nAdd new fields to keep track of the pages and the page rings.\nAdd functions to allocate and free pages.\n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "5d5d001504b4a415a008f7ac1adb9fbec1637811", "tree": "c73dd0b4231e29c8586dd75a807901716f7df7e1", "parents": [ "85833c6269016d009ada17b04ac288e2ab9c37ea" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Wed Dec 12 11:17:43 2007 -0800" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Jan 28 14:57:29 2008 -0800" }, "message": "[BNX2]: Restructure RX ring init. code.\n\nFactor out the common functions that will be used to initialize the\nnormal RX rings and the page rings.\n\nChange the copybreak constant RX_COPY_THRESH to 128. This same\nconstant will be used for the max. size of the linear SKB when pages\nare used. Copybreak will be turned off when pages are used.\n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "e343d55c0a624c5bb88cd6821a17586474f20271", "tree": "af9efb9725694bd9d7b8d0b5e88ddf6a7c74e5ad", "parents": [ "f5f97b57b5208a7ca270ac86887a2838ab7862f5" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Wed Dec 12 11:16:19 2007 -0800" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Jan 28 14:57:27 2008 -0800" }, "message": "[BNX2]: Add ring constants.\n\nDefine the various ring constants to make the code cleaner.\n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "c09c262783dcac62352293912d82b794063cefc3", "tree": "14941c7d5c49bbfa3e2b2a3d61cba274baea6b05", "parents": [ "fb0c18bd1f61086fcfac90017b59891a356cc288" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Mon Dec 10 17:18:37 2007 -0800" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Dec 11 02:45:30 2007 -0800" }, "message": "[BNX2]: Fix RX packet rot.\n\nPackets can be left in the RX ring if the NAPI budget is reached.\nThis is caused by storing the latest rx index at the beginning of\nbnx2_rx_int(). We may not process all the work up to this index\nif the budget is reached and so some packets in the RX ring may rot\nwhen we later check for more work using this stored rx index.\n\nThe fix is to not store this latest hw index and only store the\nprocessed rx index. We use a new function bnx2_get_hw_rx_cons()\nto fetch the latest hw rx index.\n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "846f5c622fe033520c775cc2c40c06f3e2adea85", "tree": "384203c173be7827d96e1a722fdd754a3b8ca886", "parents": [ "489310a440e606512b1fd79d8562d1da6b715448" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Wed Oct 10 16:16:51 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Wed Oct 10 16:55:57 2007 -0700" }, "message": "[BNX2]: Fix default WoL setting.\n\nChange the default WoL setting to match the NVRAM\u0027s setting. It\nalways defaulted to WoL disabled before and caused a lot of confusion\nfor users.\n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "ea1f8d5c3a593a791463c2efc07e5dfebd056500", "tree": "e25bb6cffff8637b19c73f6ca68eeb901a2473a3", "parents": [ "dad8c737962669240470923f951570ed716da1a1" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Tue Oct 02 16:27:35 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Wed Oct 10 16:54:07 2007 -0700" }, "message": "[BNX2]: Optimize firmware loading.\n\nThis is a follow up to the patches from Denys Vlasenkos\n\u003cvda.linux@googlemail.com\u003e to further optimize firmware loading.\n\n1. In bnx2_init_cpus(), we allocate memory for decompression once\nand use it repeatedly instead of doing this for every firmware image.\n\n2. We eliminate the BSS and SBSS firmware sections in bnx2_fw*.h since\nthese are always zeros.\n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "b3448b0bde5f1a858397fe791f76632e978a1dc8", "tree": "930bd73182f12eb37c2f14121556b1c6ff67d6bd", "parents": [ "89e536a190f90d038bae7905a0c582cb7089b739" ], "author": { "name": "Denys Vlasenko", "email": "vda.linux@googlemail.com", "time": "Sun Sep 30 17:55:51 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Wed Oct 10 16:53:57 2007 -0700" }, "message": "[BNX2]: factor out gzip unpacker\n\nThis patch modifies gzip unpacking code in bnx2 driver so that\nit does not depend on bnx2 internals. I will move this code\nout of the driver and into zlib in follow-on patch.\n\nIt can be useful in other drivers which need to store firmwares\nor any other relatively big binary blobs - fonts, cursor bitmaps,\nwhatever.\n\nPatch is run tested by Michael Chan (driver author).\n\nSigned-off-by: Denys Vlasenko \u003cvda.linux@googlemail.com\u003e\nAcked-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "bea3348eef27e6044b6161fd04c3152215f96411", "tree": "f0990b263e5ce42505d290a4c346fe990bcd4c33", "parents": [ "dde4e47e8fe333a5649a3fa0e7db1fa7c08d6158" ], "author": { "name": "Stephen Hemminger", "email": "shemminger@linux-foundation.org", "time": "Wed Oct 03 16:41:36 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Wed Oct 10 16:47:45 2007 -0700" }, "message": "[NET]: Make NAPI polling independent of struct net_device objects.\n\nSeveral devices have multiple independant RX queues per net\ndevice, and some have a single interrupt doorbell for several\nqueues.\n\nIn either case, it\u0027s easier to support layouts like that if the\nstructure representing the poll is independant from the net\ndevice itself.\n\nThe signature of the -\u003epoll() call back goes from:\n\n\tint foo_poll(struct net_device *dev, int *budget)\n\nto\n\n\tint foo_poll(struct napi_struct *napi, int budget)\n\nThe caller is returned the number of RX packets processed (or\nthe number of \"NAPI credits\" consumed if you want to get\nabstract). The callee no longer messes around bumping\ndev-\u003equota, *budget, etc. because that is all handled in the\ncaller upon return.\n\nThe napi_struct is to be embedded in the device driver private data\nstructures.\n\nFurthermore, it is the driver\u0027s responsibility to disable all NAPI\ninstances in it\u0027s -\u003estop() device close handler. Since the\nnapi_struct is privatized into the driver\u0027s private data structures,\nonly the driver knows how to get at all of the napi_struct instances\nit may have per-device.\n\nWith lots of help and suggestions from Rusty Russell, Roland Dreier,\nMichael Chan, Jeff Garzik, and Jamal Hadi Salim.\n\nBug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra,\nJoseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan.\n\n[ Ported to current tree and all drivers converted. Integrated\n Stephen\u0027s follow-on kerneldoc additions, and restored poll_list\n handling to the old style to fix mutual exclusion issues. -DaveM ]\n\nSigned-off-by: Stephen Hemminger \u003cshemminger@linux-foundation.org\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "e30372c91273bb5777597362c74e63f96d9cd434", "tree": "c81534ad188650d51219c59e920701a43b5c3075", "parents": [ "cb32da0416b823b7f4b65e7e85d6cba16ca4d1e1" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Mon Jul 16 18:26:23 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Wed Jul 18 01:46:46 2007 -0700" }, "message": "[BNX2]: Support NVRAM on 5709.\n\nThe NVRAM interface is slightly modified on the 5709. To properly\nsupport it, we need to change the buffered flag in the flash data\nstructure into multiple flags to indicate buffered operation, address\ntranslation, and the use of write enable (WREN). The 5709 flash\nonly requires the buffered operation bit to be set.\n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "58fc2ea4057511f84deaa182b1a3612327ecbf2d", "tree": "e618b9cb73831595a7bac9418497f8479ae2a790", "parents": [ "df149d70e1f34ec4995c8a703dbde38071ff4a05" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Sat Jul 07 22:52:02 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:18:38 2007 -0700" }, "message": "[BNX2]: Print management firmware version.\n\nAdd management firmware version for ethtool -i.\n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "df149d70e1f34ec4995c8a703dbde38071ff4a05", "tree": "09103d4b997158202370619f5a1492a69f85e7af", "parents": [ "b8a7ce7bedb2134acb731e08e588ad92087a40ff" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Sat Jul 07 22:51:36 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:18:36 2007 -0700" }, "message": "[BNX2]: Enhance the heartbeat.\n\nIn addition to the periodic heartbeat, we\u0027re adding a heartbeat\nrequest interrupt when the heartbeat is late. This is needed during\nnetpoll where the timer is not available. -rt kernels will also\nbenefit since the timer is not as accurate.\n\n[ We discussed this patch last time and we decided that the -rt\n kernel problem alone did not justify this patch. I think the\n netpoll problem makes this patch necessary. ]\n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "9700e6befea505b03b6e625536a9a106811e9a14", "tree": "a3cb01457f6c060d16eab10752c074310ff46bae", "parents": [ "deaf391b4cc9d9f8e2b2793ebd56da776b54197a" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Sat Jul 07 22:48:31 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Tue Jul 10 22:18:31 2007 -0700" }, "message": "[BNX2]: Add remote PHY bit definitions.\n\nAdd new fields in struct bnx2 and other bit definitions in shared\nmemory to support remote PHY.\n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "0aa38df7cd5b6c5b89f5146f4a2286434bc4a8f3", "tree": "428a62a17347f87980cdace06fef7b890288d6fa", "parents": [ "641bdcd56c8bb2110a31da846b2752b11a644050" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Mon Jun 04 21:23:06 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Thu Jun 07 13:38:38 2007 -0700" }, "message": "[BNX2]: Enable DMA on 5709.\n\nAdd missing code to enable DMA on 5709 A1. The bit is a no-op on A0\nand therefore can be set on all 5709 chips.\n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nAcked-by: Jeff Garzik \u003cjeff@garzik.org\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "72fbaeb623971c321112de7fe3fa4e24e12ca59e", "tree": "0dc8989fdeb1de0bdbd05730679a56b4c958d316", "parents": [ "883e51511815930154c64a2645f4df112aa066fb" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Thu May 03 13:25:32 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Thu May 03 13:25:32 2007 -0700" }, "message": "[BNX2]: Update version and reldate.\n\nUpdate version to 1.5.10.\n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "883e51511815930154c64a2645f4df112aa066fb", "tree": "262c504287ef72456211bd33a76ec270e2c2a10a", "parents": [ "8e6a72c435bf8bdd738ad08a746d697abedacfc0" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Thu May 03 13:25:11 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Thu May 03 13:25:11 2007 -0700" }, "message": "[BNX2]: Print bus information for PCIE devices.\n\nFix the code to print PCI or PCIE bus information for all devices.\n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "8e6a72c435bf8bdd738ad08a746d697abedacfc0", "tree": "c80eede41a92196004a2ce9ee03ba4f200eb803f", "parents": [ "da3e4fbed21a5d7edab10ffb77a8c04a725f9eff" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Thu May 03 13:24:48 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Thu May 03 13:24:48 2007 -0700" }, "message": "[BNX2]: Add 1-shot MSI handler for 5709.\n\nThe 5709 supports the one-shot MSI handler similar to some of the tg3\nchips. In this mode, the MSI disables itself automatically until it\nis re-enabled at the end of NAPI poll.\n\nPut the request_irq/free_irq logic in common procedures.\n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "1b8227c48e164655f02aa0eff55862af2d05da51", "tree": "ee1598123fba3ee397a463ff706ec8f235464523", "parents": [ "27a005b883984ef3a3cf24e7ddd78eb78902f494" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Thu May 03 13:24:05 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Thu May 03 13:24:05 2007 -0700" }, "message": "[BNX2]: Add indirect spinlock.\n\nThe indirect register access method will be used by more than one\ncaller in BH context (NAPI poll and timer), so a spinlock is required.\n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "27a005b883984ef3a3cf24e7ddd78eb78902f494", "tree": "c2fbdb130239e7f7ad718cea0cd8cb1a78528da4", "parents": [ "605a9e20aaea23f31a5403e969bd4ab4d0405dab" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Thu May 03 13:23:41 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Thu May 03 13:23:41 2007 -0700" }, "message": "[BNX2]: Add support for 5709 Serdes.\n\nAdd PCI ID and code to support the 5709 Serdes PHY.\n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "ca58c3af99b15f729e56dffe9b74b8b2ce157e8d", "tree": "7c368d0f68cfa0513b25ab32f3a61d7080d82f1c", "parents": [ "4666f87a82cf74b63737a7f55a8b3b057a7b83df" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Thu May 03 13:22:52 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Thu May 03 13:22:52 2007 -0700" }, "message": "[BNX2]: Put MII register offsets in the bnx2 struct.\n\nThe 5709 Serdes device uses non-standard MII register offsets. This\nre-structuring will make it easier to support 5709 Serdes.\n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "4666f87a82cf74b63737a7f55a8b3b057a7b83df", "tree": "67cc362f70fa70bb8218e91e46e82d3bd5f7b57e", "parents": [ "874bb672fdd939aec37ad3a06b50be4ff8b4feac" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Thu May 03 13:22:28 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Thu May 03 13:22:28 2007 -0700" }, "message": "[BNX2]: Add ipv6 TSO and checksum for 5709.\n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "40453c839fdbf86738256cae1c9c1ebe55645d4a", "tree": "8bd941c3ff4b4ef6df0c43cf1060ddbb5abfa7aa", "parents": [ "5bae30c96a3bd09563e484b4ac7211b4b4664679" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Thu May 03 13:19:18 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Thu May 03 13:19:18 2007 -0700" }, "message": "[BNX2]: Add 40-bit DMA workaround for 5708.\n\nThe internal PCIE-to-PCIX bridge of the 5708 has the same 40-bit DMA\nlimitation as some of the tg3 chips. Set dma_mask and persistent DMA\nmask to 40-bit to workaround.\n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "68c9f75a0539db583db074059d54deb607d1a475", "tree": "7c55bcd720a3189c61d40dad97638e232843fd0e", "parents": [ "0bcbc92629044b5403719f77fb015e9005b1f504" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Tue Apr 24 15:35:53 2007 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Tue Apr 24 15:35:53 2007 -0700" }, "message": "[BNX2]: Fix occasional NETDEV WATCHDOG on 5709.\n\nTweak a register setting to prevent the tx mailbox from halting.\n\nUpdate version to 1.5.8.\n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "b659f44e4e144bae02c5beaba78a37db60783ba2", "tree": "e83c812da31b54953615eefb535060bd814e0406", "parents": [ "e34efe3b100d0fbdf053128956c3dd0bc68754d6" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Fri Feb 02 00:46:35 2007 -0800" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Fri Feb 02 00:46:35 2007 -0800" }, "message": "[BNX2]: PHY workaround for 5709 A0.\n\n5709 A0 copper devices will not link up with some link partners\nwithout this workaround.\n\nUpdate driver to 1.5.5.\n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "9052a840fffa2f565ed13e6ecd53fbe2532d51b9", "tree": "2afcae9d212bd5657c610824f65a1e0d41a526cf", "parents": [ "19cdeb794b7ef9e1f0e408777445bd76fe90e694" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Sun Nov 19 14:10:12 2006 -0800" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Sat Dec 02 21:24:25 2006 -0800" }, "message": "[BNX2]: Add new 5709 registers (part 2).\n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "19cdeb794b7ef9e1f0e408777445bd76fe90e694", "tree": "01d8afdb4328220ce26371ffe79a99207c39d6a9", "parents": [ "af3ee519c5d6bebbda9bf0ca3b81bc50b4dd2163" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Sun Nov 19 14:09:48 2006 -0800" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Sat Dec 02 21:24:23 2006 -0800" }, "message": "[BNX2]: Add new 5709 registers (part 1).\n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "af3ee519c5d6bebbda9bf0ca3b81bc50b4dd2163", "tree": "03c4e5e6c10210239109d8456801d1902fb06a49", "parents": [ "a16dda0e67cea666fb7eb708ab1199892c4a1a13" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Sun Nov 19 14:09:25 2006 -0800" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Sat Dec 02 21:24:22 2006 -0800" }, "message": "[BNX2]: Re-organize firmware structures.\n\nRe-organize the firmware handling code and declarations a bit to make\nthe code more compact.\n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "f8dd064ee1bd62ef2cdb398cb9cdc8a8f112cb28", "tree": "0b112a7f0025033647b1ab70784f3e7501b1661f", "parents": [ "48b01e2d7c83d37321722f1cdd46193d4ca73b41" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Sun Nov 19 14:08:29 2006 -0800" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Sat Dec 02 21:24:20 2006 -0800" }, "message": "[BNX2]: Add 5708S parallel detection.\n\nAdd code to parallel detect 1Gbps and 2.5Gbps link speeds.\n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "80be44348e30b68d2d8c5b6d1b7e53f2c5659134", "tree": "6bf7e3c6f9dd11f8ee90ec90a1e7df98f741dd02", "parents": [ "7510873d8659f4192cb5b3327f748e401d216399" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Sun Nov 19 14:07:28 2006 -0800" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Sat Dec 02 21:24:18 2006 -0800" }, "message": "[BNX2]: Improve SerDes handling.\n\n1. Add support for 2.5Gbps forced speed setting.\n2. Remove a long udelay() loop and change to msleep().\n3. Other misc. SerDes fixes.\n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "6aa20a2235535605db6d6d2bd850298b2fe7f31e", "tree": "df0b855043407b831d57f2f2c271f8aab48444f4", "parents": [ "7a291083225af6e22ffaa46b3d91cfc1a1ccaab4" ], "author": { "name": "Jeff Garzik", "email": "jeff@garzik.org", "time": "Wed Sep 13 13:24:59 2006 -0400" }, "committer": { "name": "Jeff Garzik", "email": "jeff@garzik.org", "time": "Wed Sep 13 13:24:59 2006 -0400" }, "message": "drivers/net: Trim trailing whitespace\n\nSigned-off-by: Jeff Garzik \u003cjeff@garzik.org\u003e\n" }, { "commit": "2f8af120a159a843948749ea88bcacda9779b132", "tree": "e633037a72db856b8078e814e3451dd8f44c14de", "parents": [ "fb33f82568d32016b3b3c00819574f9526e52be3" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Tue Aug 15 01:39:10 2006 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Thu Aug 17 16:29:51 2006 -0700" }, "message": "[BNX2]: Fix tx race condition.\n\nFix a subtle race condition between bnx2_start_xmit() and bnx2_tx_int()\nsimilar to the one in tg3 discovered by Herbert Xu:\n\nCPU0\t\t\t\t\tCPU1\nbnx2_start_xmit()\n\tif (tx_ring_full) {\n\t\ttx_lock\n\t\t\t\t\tbnx2_tx()\n\t\t\t\t\t\tif (!netif_queue_stopped)\n\t\tnetif_stop_queue()\n\t\tif (!tx_ring_full)\n\t\t\t\t\t\tupdate_tx_ring\n\t\t\tnetif_wake_queue()\n\t\ttx_unlock\n\t}\n\nEven though tx_ring is updated before the if statement in bnx2_tx_int() in\nprogram order, it can be re-ordered by the CPU as shown above. This\nscenario can cause the tx queue to be stopped forever if bnx2_tx_int() has\njust freed up the entire tx_ring. The possibility of this happening\nshould be very rare though.\n\nThe following changes are made, very much identical to the tg3 fix:\n\n1. Add memory barrier to fix the above race condition.\n\n2. Eliminate the private tx_lock altogether and rely solely on\nnetif_tx_lock. This eliminates one spinlock in bnx2_start_xmit()\nwhen the ring is full.\n\n3. Because of 2, use netif_tx_lock in bnx2_tx_int() before calling\nnetif_wake_queue().\n\n4. Add memory barrier to bnx2_tx_avail().\n\n5. Add bp-\u003etx_wake_thresh which is set to half the tx ring size.\n\n6. Check for the full wake queue condition before getting\nnetif_tx_lock in tg3_tx(). This reduces the number of unnecessary\nspinlocks when the tx ring is full in a steady-state condition.\n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "6c4f095eae35e83eb6148dec7f72874eeadf0c9b", "tree": "1be263c4968b5268e0a3ebb1650a79f0833e3215", "parents": [ "745720e58303f940e12944bf7fab52bc9ce48bda" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Thu Jun 29 12:38:15 2006 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Thu Jun 29 16:58:24 2006 -0700" }, "message": "[BNX2]: Turn off link during shutdown\n\nMinor change in shutdown logic to effect a link down.\n\nUpdate version to 1.4.43.\n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "c86a31f452f7dd132a1765d6d7160b0947f37b14", "tree": "b531650af625d24958bb59b511a1e4157525dc1e", "parents": [ "7a6400cd3dbcfc3bbffcdb6dac4ffc957fb50e19" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Tue Jun 13 15:03:47 2006 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Sat Jun 17 21:30:49 2006 -0700" }, "message": "[BNX2]: Use CPU native page size\n\nUse CPU native page size to determine various ring sizes. This allows\norder-0 memory allocations on all systems.\n\nAdded check to limit the page size to 16K since that\u0027s the maximum rx\nring size that will be used. This will prevent using unnecessarily\nlarge page sizes on some architectures with large page sizes.\n[Suggested by David Miller]\n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "fba9fe911bb4213c3de1d142fe0ee127cd361a78", "tree": "2fc7a68e612644cc8ce3ff8e44f210e20f6964b4", "parents": [ "160882722cb21cbe5cead55cf38a5e70fc3af63e" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Mon Jun 12 22:21:25 2006 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Sat Jun 17 21:30:44 2006 -0700" }, "message": "[BNX2]: Add firmware decompression\n\nAdd functions to decompress firmware before loading to the internal\nCPUs. Compressing the firmware reduces the driver size significantly.\n\nAdded file name length sanity check in the gzip header to prevent\ngoing past the end of buffer [suggested by DaveM].\n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "cea94db9b496d7fe25bbd3ebd0f24afaac2069d5", "tree": "e425453a1f5fcc28c4db9c750f825161a58d03ac", "parents": [ "bc726a71d2799f0f8b68a17f49d86aa030f64abc" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Mon Jun 12 22:16:13 2006 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@sunset.davemloft.net", "time": "Sat Jun 17 21:30:40 2006 -0700" }, "message": "[BNX2]: Add an rx drop counter\n\nAdd a counter for packets dropped by firmware.\n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "29b12174ac14f110225d6d9ebb66c30df5023baf", "tree": "2c90b0bb6d3e6e4e7528cd381688b4413c77507b", "parents": [ "f2a4f05216e95f3b8c06b858abc0fe9a77500816" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Thu Mar 23 01:13:43 2006 -0800" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Thu Mar 23 01:13:43 2006 -0800" }, "message": "[BNX2]: Separate tx producer and consumer fields\n\nPut the tx producer and consumer fields in separate cache lines in\nthe device structure, similar to the VJ net channel queue structure.\n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "f2a4f05216e95f3b8c06b858abc0fe9a77500816", "tree": "1939a86f6370f089246c174bd6dab86c8031ebbc", "parents": [ "0f31f99446270e66c6f18c7d87aadd7db1dad214" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Thu Mar 23 01:13:12 2006 -0800" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Thu Mar 23 01:13:12 2006 -0800" }, "message": "[BNX2]: Move .h files to bnx2.c\n\nMove all #include \u003c\u003e from bnx2.h to bnx2.c.\n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "0f31f99446270e66c6f18c7d87aadd7db1dad214", "tree": "7cac41b473b1e85d97df34a4fe4f6e329a534b6f", "parents": [ "bf5295bba804a6aead9bc1c0d5970173a9d4e08e" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Thu Mar 23 01:12:38 2006 -0800" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Thu Mar 23 01:12:38 2006 -0800" }, "message": "[BNX2]: Combine small mem allocations\n\nCombine two small (56 byte and 320 byte) pci consistent memory\nallocations into one allocation. Jeff Garzik suggested to store\nthe combined size in the bp structure for later use when freeing\nthe memory.\n\nUse kzalloc() instead of kmalloc() + memset().\n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "bf5295bba804a6aead9bc1c0d5970173a9d4e08e", "tree": "561708042eb3348d0693f4d2a4035bf4b58fd8e9", "parents": [ "ca6549af77f0f28ac5d23b662fb8f72713eb16d3" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Thu Mar 23 01:11:56 2006 -0800" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Thu Mar 23 01:11:56 2006 -0800" }, "message": "[BNX2]: Fix link change handling\n\nFix some link-related problems by doing a coalesce_now after link\nchange interrupt to flush out the transient link status.\n\nTo facilitate this, the host coalesce cmd register value is cached in\nthe device structure.\n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "0d36f37bb1e1cbadca6dc90a840bb2bc9ab51c44", "tree": "27856915643532cfa4346a4f4d95a92f11d5e009", "parents": [ "5d424d5a674f782d0659a3b66d951f412901faee" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Mon Mar 20 17:55:25 2006 -0800" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Mar 20 17:55:25 2006 -0800" }, "message": "[BNX2]: include \u003clinux/vmalloc.h\u003e\n\nInclude \u003clinux/vmalloc.h\u003e so that it compiles properly on all archs.\n\nUpdate version to 1.4.38.\n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "13daffa2f2ba65674e7816a0e95e7b93246cb686", "tree": "3170a19dfba530398d4f12e54a21400254fa98b1", "parents": [ "236b6394bb49ea58465c6f935a286d2342576f8d" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Mon Mar 20 17:49:20 2006 -0800" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Mar 20 17:49:20 2006 -0800" }, "message": "[BNX2]: Support larger rx ring sizes (part 1)\n\nIncrease maximum receive ring size from 255 to 1020 by supporting\nup to 4 linked pages of receive descriptors. To accomodate the\nhigher memory usage, each physical descriptor page is allocated\nseparately and the software ring that keeps track of the SKBs and the\nDMA addresses is allocated using vmalloc.\n\nSome of the receive-related fields in the bp structure are re-\norganized a bit for better locality of reference.\n\nThe max. was reduced to 1020 from 4080 after discussion with David\nMiller.\n\nThis patch contains ring init code changes only. This next patch\ncontains rx data path code changes.\n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "206cc83ccdc29e4a73786e9093f9eeec25868441", "tree": "e479b7925b9d80b8b69ddb653f2f0e7726841206", "parents": [ "bc5a0690e917206b423c7b565c997b06675fb572" ], "author": { "name": "Michael Chan", "email": "mchan@broadcom.com", "time": "Mon Jan 23 16:14:05 2006 -0800" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Jan 23 16:14:05 2006 -0800" }, "message": "[BNX2]: Update version and copyright year\n\nUpdate version to 1.4.31 and add 2006 copyright.\n\nSkip the last digit when reporting the firmware version.\n\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" } ], "next": "1122db717ab5443ca9043fc0d23c1e862cfb3a61" }