)]}' { "log": [ { "commit": "ba5b0bfa06b6fbee03c6889046e9adcefa5d2c20", "tree": "b785505656b57774b51f1163af884a5a0316afbb", "parents": [ "55dffe79b34e2af98bd1315f1e00c2fc6a7a7078" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Tue Jan 12 10:11:40 2010 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Wed Jan 13 17:18:54 2010 -0800" }, "message": "tg3: Update copyright and driver version\n\nThis patch updates the copyright notice for 2010 and updates the version\nnumber to 3.106.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nReviewed-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "55dffe79b34e2af98bd1315f1e00c2fc6a7a7078", "tree": "96ecbf679f582be592f8bd68d20b5bb99521f8df", "parents": [ "d1ec96af77df611d1728f3bb70289f83a02df1ea" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Tue Jan 12 10:11:39 2010 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Wed Jan 13 17:18:54 2010 -0800" }, "message": "tg3: Disable 5717 serdes and B0 support\n\nThe B0 revision of the 5717 will not get enough testing by the time\n2.6.33 ships. Since the kernel is already at RC3, serdes support\nwill require too many patches to fix. For these reasons, this patch\ndisables 5717 serdes support and will refuse to attach to all 5717\ndevices that are later than an A0 revision.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nReviewed-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "d1ec96af77df611d1728f3bb70289f83a02df1ea", "tree": "b6268f532c7d40272da4149f27518afa0dd2191b", "parents": [ "86cfe4ff02a51294cb2c974a8bedc7f648491df9" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Tue Jan 12 10:11:38 2010 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Wed Jan 13 17:18:53 2010 -0800" }, "message": "tg3: Add reliable serdes detection for 5717 A0\n\nThe serdes status bit does not work as intended for the 5717 A0.\nThis patch implements an alternative detection scheme that will only be\nvalid for A0 revisions.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nReviewed-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "86cfe4ff02a51294cb2c974a8bedc7f648491df9", "tree": "d2241293b99f32b07ec339ae7c05d96717fea8e4", "parents": [ "13fa95b0398d65885a79c6e95a09976ee9f8c009" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Tue Jan 12 10:11:37 2010 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Wed Jan 13 17:18:53 2010 -0800" }, "message": "tg3: Fix std rx prod ring handling\n\nThere are some tg3 devices that require the driver to post new rx\nbuffers in smaller increments. Commit\n4361935afe3abc3e5a93006b99197fac1fabbd50, \"tg3: Consider\nrx_std_prod_idx a hw mailbox\" changed how the driver tracks the rx\nproducer ring updates, but it does not make any special considerations\nfor the above-mentioned devices. For those devices, it is possible for\nthe driver to hit the special case path, which updates the hardware\nmailbox register but skips updating the shadow software mailbox member.\nIf the special case path represents the final mailbox update for this\nISR iteration, the hardware and software mailbox values will be out of\nsync. Ultimately, this will cause the driver to use a stale mailbox\nvalue on the next iteration, which will appear to the hardware as a\nlarge rx buffer update. Bad things ensue.\n\nThe fix is to update the software shadow mailbox member when the special\ncase path is taken.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nReviewed-by: Michael Chan \u003cmchan@broadcom.com\u003e\nReported-by: Dmitry Torokhov \u003cdmitry.torokhov@gmail.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "13fa95b0398d65885a79c6e95a09976ee9f8c009", "tree": "85296ba31a76727f4fb6fa0040d023a6a5151dd0", "parents": [ "f3766c26a5d00189e5c0965c66f01956d15a92d6" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Tue Jan 12 10:11:36 2010 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Wed Jan 13 17:18:52 2010 -0800" }, "message": "tg3: Fix std prod ring nicaddr for 5787 and 57765\n\nCommit 87668d352aa8d135bd695a050f18bbfc7b50b506, titled \"tg3: Don\u0027t\ntouch RCB nic addresses\", tried to avoid assigning the nic address of\nthe standard producer ring. Unfortunately, the default nic address is\nnot correct for the 5787, the 5755M, or the 57765. This patch\nreenables the old behavior and opts out of the assignment only\nfor the 5717.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nReviewed-by: Michael Chan \u003cmchan@broadcom.com\u003e\nTested-by: Chow Loong Jin \u003chyperair@ubuntu.com\u003e\nTested-by: Dmitry Torokhov \u003cdtor@mail.ru\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "cceea982ef78cf358b70f3412a6799f153211e14", "tree": "6206b33631b6d5c0276b921fd0f74f118ba463a8", "parents": [ "026a6c21646cf77ea838f3c121de29cdf948ca71" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Thu Dec 03 08:36:25 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Thu Dec 03 13:18:08 2009 -0800" }, "message": "tg3: Update version to 3.105\n\nThis patch updates the tg3 version to 3.105.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nReviewed-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "026a6c21646cf77ea838f3c121de29cdf948ca71", "tree": "5c4dd0df2e64086464d2091b4f36f547789e0a24", "parents": [ "94c982bd9f07b801f03cebe32b20f893b4ad6d27" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Thu Dec 03 08:36:24 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Thu Dec 03 13:18:07 2009 -0800" }, "message": "tg3: Clean tg3_init_one()\n\nTg3\u0027s firmware is no longer loaded from tg3_init_one(). Remove the\nerror path that releases the firmware back to the system.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nReviewed-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "94c982bd9f07b801f03cebe32b20f893b4ad6d27", "tree": "2df6b908732f09f8882a8e8a91b0dc083fce2dde", "parents": [ "141518c95870228da4e050fbe31a8f0c9df82c72" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Thu Dec 03 08:36:23 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Thu Dec 03 13:18:06 2009 -0800" }, "message": "tg3: Use pci_read_vpd() instead of private method\n\nIf the driver needs to use PCI configuration space to read the VPD data,\nthe accesses could collide with the pci_read_vpd() function. This patch\nconverts the driver to use pci_read_vpd() to avoid any potential\ncollisions.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nReviewed-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "141518c95870228da4e050fbe31a8f0c9df82c72", "tree": "377e3cb707cf848213f5aeb653dd50cae572135c", "parents": [ "b703df6f628ab63eaa875232551b1f2f0503b9af" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Thu Dec 03 08:36:22 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Thu Dec 03 13:18:04 2009 -0800" }, "message": "tg3: Add some VPD preprocessor constants\n\nThis patch cleans up the VPD code by creating preprocessor definitions\nand using them in the place of hardcoded constants.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nReviewed-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "b703df6f628ab63eaa875232551b1f2f0503b9af", "tree": "cbeb9291af92306fc8b36a9fcac5d2d9b9d4c3df", "parents": [ "19cfaecc094781da273b5cd1411ee46589898d0e" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Thu Dec 03 08:36:21 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Thu Dec 03 13:18:03 2009 -0800" }, "message": "tg3: Add 57765 asic rev\n\nThis patch adds the 57765 asic revision.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "19cfaecc094781da273b5cd1411ee46589898d0e", "tree": "738a9e022d83e573a33abf9ab47aae62eaaa98ee", "parents": [ "8e95a2026f3b43f7c3d676adaccd2de9532e8dcc" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Thu Dec 03 08:36:20 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Thu Dec 03 13:18:02 2009 -0800" }, "message": "tg3: Make TSS enable independent of MSI-X enable\n\nThe 57765 asic rev has MSI-X capability, but does not support TSS. This\npatch changes the tx paths so that TSS is explicitly mentioned, rather\nthan implied through the ENABLE_MSIX flag.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "8e95a2026f3b43f7c3d676adaccd2de9532e8dcc", "tree": "3733318168cd512480b6db58c5c16d1c8847f0b7", "parents": [ "3454f835837609d60b29a266e3bd9d701073b060" ], "author": { "name": "Joe Perches", "email": "joe@perches.com", "time": "Thu Dec 03 07:58:21 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Thu Dec 03 13:18:01 2009 -0800" }, "message": "drivers/net: Move \u0026\u0026 and || to end of previous line\n\nOnly files where David Miller is the primary git-signer.\nwireless, wimax, ixgbe, etc are not modified.\n\nCompile tested x86 allyesconfig only\nNot all files compiled (not x86 compatible)\n\nAdded a few \u003e 80 column lines, which I ignored.\nExisting checkpatch complaints ignored.\n\nSigned-off-by: Joe Perches \u003cjoe@perches.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "f4188d8affc8267a0f0f1b587a4d0a4b9b7f2999", "tree": "cd460b981c0cb3eee56ac91ade3b52279af55ab0", "parents": [ "a73b796ed85483a2b999d74d197f31f887ffa82d" ], "author": { "name": "Alexander Duyck", "email": "alexander.h.duyck@intel.com", "time": "Wed Dec 02 16:48:38 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Wed Dec 02 19:57:15 2009 -0800" }, "message": "tg3: remove use of skb_dma_map/unmap\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\nSigned-off-by: Alexander Duyck \u003calexander.h.duyck@intel.com\u003e\nSigned-off-by: Jeff Kirsher \u003cjeffrey.t.kirsher@intel.com\u003e\nCC: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nCC: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "c5d5d1721763842a516529e553433d13b11c3f31", "tree": "18126fa310bec04524999da433e595316b7d690d", "parents": [ "5001e2f638011859c1351f9fe57ca4e545a15c47" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Fri Nov 13 13:03:52 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Sun Nov 15 22:14:55 2009 -0800" }, "message": "tg3: Update version to 3.104\n\nThis patch updates the tg3 version to 3.104.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nReviewed-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "5001e2f638011859c1351f9fe57ca4e545a15c47", "tree": "7ba357c34b36bfe9f855ac93f78c46c7a87fb081", "parents": [ "b196c7e45f30cbcd38c83386bc8a04a21477f8d3" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Fri Nov 13 13:03:51 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Sun Nov 15 22:14:54 2009 -0800" }, "message": "tg3: Fix DIDs, Enable 5717 support\n\nThis patch fixes the 5717 variant device ID enumerations and adds those\nDIDs to the PCI ID table.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nReviewed-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "b196c7e45f30cbcd38c83386bc8a04a21477f8d3", "tree": "97bdf9375a9a2b7c400204587a85515bd90c8a37", "parents": [ "66711e66639776685aeaad774488be1857abce26" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Fri Nov 13 13:03:50 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Sun Nov 15 22:14:54 2009 -0800" }, "message": "tg3: Add rx prod ring consolidation\n\nThis patch adds code to funnel each MSI-X vector\u0027s rx packet buffers\ninto a single set of producer rings which will then be submitted to the\nhardware.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "66711e66639776685aeaad774488be1857abce26", "tree": "e719edd75292bd3ac6d739f26e29613c0c2c3b03", "parents": [ "2b2cdb65bec42d38268b2ac115876b066afa7f95" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Fri Nov 13 13:03:49 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Sun Nov 15 22:14:53 2009 -0800" }, "message": "tg3: Create aliases for rx producer mailbox regs\n\nThe rx producer mailbox registers are used in several spots in the code.\nThe addition of TG3_64BIT_REG_LOW makes register references\nuncomfortably long. This patch creates an alias for the standard and\njumbo ring producer index registers to make the code cleaner.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "2b2cdb65bec42d38268b2ac115876b066afa7f95", "tree": "239a38242e57bc4d56b79d1bbc4e118a0cbc73d9", "parents": [ "4361935afe3abc3e5a93006b99197fac1fabbd50" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Fri Nov 13 13:03:48 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Sun Nov 15 22:14:51 2009 -0800" }, "message": "tg3: Lay proucer ring handling groundwork\n\nThe patch increases the number of producer rings available and\nimplements the constructor and destructor code that deals with them.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nReviewed-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "4361935afe3abc3e5a93006b99197fac1fabbd50", "tree": "88becadbc88f1f0800b224cd597a940caaccbdde", "parents": [ "411da6407e778bf946911df08bb5afc505422f31" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Fri Nov 13 13:03:47 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Sun Nov 15 22:14:50 2009 -0800" }, "message": "tg3: Consider rx_std_prod_idx a hw mailbox\n\nThis patch changes how the code uses the rx_std_prod_idx member. In the\nfollowing patch, the code will be changed so that it will act just like\na hardware mailbox. This patch prepares the code so that memory barriers\ncan be more easily inserted.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nReviewed-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "411da6407e778bf946911df08bb5afc505422f31", "tree": "24bd8cde28cb13191f029796bbc7fa4806a8fbd2", "parents": [ "86b21e59c9a65c8e46d35ac6c4220f63639828c6" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Fri Nov 13 13:03:46 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Sun Nov 15 22:14:49 2009 -0800" }, "message": "tg3: rename rx_[std|jmb]_ptr\n\nA later patch is going to add consumer indicies for the producer rings.\nTo keep things readable, this patch renames rx_[std|jmb]_ptr to\nrx_[std|jmb]_prod_idx.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nReviewed-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "86b21e59c9a65c8e46d35ac6c4220f63639828c6", "tree": "087a426dfec82cab6efc4c036367e411971d869b", "parents": [ "a3896167160ce9ad1eadeb88fd2f3971888444ae" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Fri Nov 13 13:03:45 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Sun Nov 15 22:14:49 2009 -0800" }, "message": "tg3: tg3_alloc_rx_skb(tnapi \u003d\u003e tp)\n\nThis patch converts the tnapi argument of tg3_alloc_rx_skb() to tp. The\nlevel of indirection is unnecessary.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nReviewed-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "a3896167160ce9ad1eadeb88fd2f3971888444ae", "tree": "504efd6573241c592e75d7139715cece3a15bc46", "parents": [ "afc081f83c59a7cf2c025a3ed89d011b5db556eb" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Fri Nov 13 13:03:44 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Sun Nov 15 22:14:48 2009 -0800" }, "message": "tg3: Add prodring parameter to tg3_alloc_rx_skb()\n\nThis patch changes the tg3_alloc_rx_skb() implementation to accept the\ndestination producer ring set pointer as a parameter rather than\nassuming the source and destination producer rings are the same.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nReviewed-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "afc081f83c59a7cf2c025a3ed89d011b5db556eb", "tree": "509ef4581f8be885a28a7b69a215aab835984765", "parents": [ "78f90dcf184b8225a24217605c4289f1986451a3" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Fri Nov 13 13:03:43 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Sun Nov 15 22:14:46 2009 -0800" }, "message": "tg3: Make tg3_alloc_rx_skb() a dst-only operation\n\nThis patch removes the source index parameter of tg3_alloc_rx_skb(). A\nlater patch will make it possible for the source and destination\nproducer rings to be different. This patch opts to make\ntg3_alloc_rx_skb() a destination-only implementation and move the code\nsensitive to the difference elsewhere.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nReviewed-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "78f90dcf184b8225a24217605c4289f1986451a3", "tree": "ee0559bf41211975701c8f2cc310ef8ec7303fe2", "parents": [ "35f2d7d0d7c222a580da0ed91c8d70c54267620a" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Fri Nov 13 13:03:42 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Sun Nov 15 22:14:45 2009 -0800" }, "message": "tg3: Move napi_add calls below tg3_get_invariants\n\ntg3_get_invariants(), among other things, discovers whether or not\nthe device is MSI-X capable and how many interrupts it supports.\nThis discovery needs to happen before registering NAPI instances with\nnetdev. This patch moves the code block that calls napi_add later in\ntg3_init_one() so that tg3_get_invariants() has a chance to run first.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nReviewed-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "35f2d7d0d7c222a580da0ed91c8d70c54267620a", "tree": "ffd6467756d992aeaf431aa732ba4c3fa553916f", "parents": [ "cbf9ca6cf8304beb640a948709c4672bc1d5a55f" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Fri Nov 13 13:03:41 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Sun Nov 15 22:14:45 2009 -0800" }, "message": "tg3: Create tg3_poll_msix() for non-zero MSIX vecs\n\nThis patch gives all non-zero MSIX vectors their own NAPI handler. This\nwill make NAPI handling for those vectors slightly more efficient.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nReviewed-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "cbf9ca6cf8304beb640a948709c4672bc1d5a55f", "tree": "f1941d408d9db7eb4524fc6423de19f3ef16c342", "parents": [ "615774fe598f8ee971a8dfeb1f2ec4211241c433" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Fri Nov 13 13:03:40 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Sun Nov 15 22:14:43 2009 -0800" }, "message": "tg3: Allow DMAs to cross cacheline boundaries\n\nBy default, the 5717 (and future chips) break up PCIe DMA packets across\ncacheline boundaries. This isn\u0027t necessary on x86. This patch\nselectively loosens the restriction.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nReviewed-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "615774fe598f8ee971a8dfeb1f2ec4211241c433", "tree": "ce0568fe76b0496a4fa8b16d1d9956fdca3137fc", "parents": [ "e849cdc309de4a1e49dc3c23c6c36da91b990c9f" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Fri Nov 13 13:03:39 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Sun Nov 15 22:14:41 2009 -0800" }, "message": "tg3: Use tg3_start_xmit_dma_bug for 5717 A0\n\nThe A0 revision of the 5717 has problems with short packet fragments.\nIt needs to use the tg3_start_xmit_dma_bug() routine.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nReviewed-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "e849cdc309de4a1e49dc3c23c6c36da91b990c9f", "tree": "1809164b142f3b8788e27192f16210c4f677d6d8", "parents": [ "507399f18ea5810de42f0ea228c14305a8f67512" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Fri Nov 13 13:03:38 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Sun Nov 15 22:14:40 2009 -0800" }, "message": "tg3: Add new HW_TSO_3 flag for 5717\n\nThe 5717 sets up TSO slightly differently in the transmit path. It\nlooks like this method will be the new way of doing things. This patch\ndefines a flag to indicate this.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nReviewed-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "507399f18ea5810de42f0ea228c14305a8f67512", "tree": "cbb2d9dad6f78a08d40276137256368c5f416ab9", "parents": [ "f66a29b03a2637ff052f2b8a81a5417fa44e228b" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Fri Nov 13 13:03:37 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Sun Nov 15 22:14:39 2009 -0800" }, "message": "tg3: Refine TSO and MSI discovery\n\nThis patch consolidates the TSO capability discovery code into its own\ncode block. The code that decides whether or not to allow TSO is then\ncleaned up. Finally, the patch consolidates all MSI and MSIX\ncapability code into a single code block.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nReviewed-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "f66a29b03a2637ff052f2b8a81a5417fa44e228b", "tree": "b0cef7e1be9fe0e44c90ad95039ef5d9122ce5fc", "parents": [ "24f4efd4e6c89a4093d0b8653d6669e45de45001" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Fri Nov 13 13:03:36 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Sun Nov 15 22:14:39 2009 -0800" }, "message": "tg3: Move TG3_FLG2_PROTECTED_NVRAM to tg3_flags3\n\nWe need room for another TSO flag and it would be most efficient if it\nresided in tg3_flags2. This patch moves the TG3_FLG2_PROTECTED_NVRAM\nto tg3_flags3 to make room.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nReviewed-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "24f4efd4e6c89a4093d0b8653d6669e45de45001", "tree": "98b671463db5330ae239266844412a1636668377", "parents": [ "87668d352aa8d135bd695a050f18bbfc7b50b506" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Fri Nov 13 13:03:35 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Sun Nov 15 22:14:37 2009 -0800" }, "message": "tg3: Napify tg3_start_xmit_dma_bug()\n\nThis patch converts tg3_start_xmit_dma_bug() to accomodate multiple NAPI\ninstances. This is prep work for a later patch in this series.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nReviewed-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "87668d352aa8d135bd695a050f18bbfc7b50b506", "tree": "106007b89bd67a957420b565d1c3cf599226e8a9", "parents": [ "c2060fe1f36565e60e622662a4519babd3b72f68" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Fri Nov 13 13:03:34 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Sun Nov 15 22:14:36 2009 -0800" }, "message": "tg3: Don\u0027t touch RCB nic addresses\n\nThis patch avoids reprogramming the RCB NIC addresses for all 5755 and\nlater devices. The address is incorrect for 5717 devices and should be\ncorrect by default for all other affected devices.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nReviewed-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "c2060fe1f36565e60e622662a4519babd3b72f68", "tree": "57c9a292656910250349b8af8de17947bc0b54a7", "parents": [ "9a1654ba0b50402a6bd03c7b0fe9b0200a5ea7b1" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Fri Nov 13 13:03:33 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Sun Nov 15 22:14:35 2009 -0800" }, "message": "tg3: Add 5717 phy ID\n\nThis patch adds the 5717 phy ID.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nReviewed-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "123b43e9716115302a0095e14f2c545811712715", "tree": "ee6d0b8df1fb8331e78fd2bffa69cfece2b83d2d", "parents": [ "52fae0837153e86e4dabaf5df517a0b8b7a20bd7" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Mon Nov 02 14:33:03 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Nov 02 23:39:15 2009 -0800" }, "message": "tg3: Update version to 3.103\n\nThis patch updates the tg3 version to 3.103.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nReviewed-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "52fae0837153e86e4dabaf5df517a0b8b7a20bd7", "tree": "72259bf0230f7facdbf6d928f8f1f662a133e10b", "parents": [ "c704dc23cac0e433796bfe0a1fe2f1a64da11ac7" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Mon Nov 02 14:32:38 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Nov 02 23:39:15 2009 -0800" }, "message": "tg3 / broadcom: Optionally disable TXC if no link\n\nThis patch adds code to disable the TXC and RXC reference clocks if link\nis not available.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nReviewed-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "c704dc23cac0e433796bfe0a1fe2f1a64da11ac7", "tree": "8fad42adbda6d2911dcb3907b20d440625d292b7", "parents": [ "32e5a8d651c0dbb02bf82ca954206282e44c4b11" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Mon Nov 02 14:32:12 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Nov 02 23:39:13 2009 -0800" }, "message": "tg3 / broadcom: Add APD support for GPHYs\n\nThis patch adds an RXC auto power-down feature to the code that supports\nthe gphys.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nReviewed-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "32e5a8d651c0dbb02bf82ca954206282e44c4b11", "tree": "7d8508afb30951c46e3e1edab56f9e664e833275", "parents": [ "cdd4e09d692bd4f3457b3789279005e112b7696d" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Mon Nov 02 14:31:39 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Nov 02 23:39:13 2009 -0800" }, "message": "tg3 / broadcom: Add code to disable rxc refclk\n\nThe 5785 does not use the RXC reference clock. Turning it off is\ndesirable as it saves power.\n\nBy default, the 50610 enables the RXC reference clock and the 50610M\ndisables it. Presumably this is one of the reasons why the hardware\narchitect chose one over the other.\n\nAdding a \"rx reference clock disable\" flag is not the ideal way to\ndescribe the option, as it would force the MAC using a 50610M to set\nthe flag. Ideally we want the flags to represent opt-in behavior that\ndeviates from hardware defaults. Furthermore, the lack of a\n\"disable\" flag implies that the requester wants the rx reference clock\nenabled, which doesn\u0027t necessarily follow.\n\nBy presenting the option as a passive statement (rx reference clock\nunused) rather than a command, I hope to convey an opt-in option to\ndisable the rx reference clock that falls back to hardware defaults if\nnot set. A secondary benefit of this is that it keeps the\nintelligence about phy defaults in the broadcom module where it belongs\nand allows the broadcom module more latitude should a bug arise.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nReviewed-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "cdd4e09d692bd4f3457b3789279005e112b7696d", "tree": "25a7619a2cd9dc2ab787fd768bda96c8f507243d", "parents": [ "63a14ce449dd6d647de2725809159eb072b2c44f" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Mon Nov 02 14:31:11 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Nov 02 23:39:12 2009 -0800" }, "message": "tg3 / broadcom: Refine AC131 APD support\n\nAuto power-down (APD) support is a power-saving feature. It should be\nselectively enabled since it might expose MAC bugs. This patch changes\nthe code to enable APD only if the PHY_BRCM_AUTO_PWRDWN_ENABLE flag is\nset. The tg3 driver was changed to set this bit.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nReviewed-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "63a14ce449dd6d647de2725809159eb072b2c44f", "tree": "d4db22459a237188aefc2c5bc3ee35374443fe1e", "parents": [ "8649f13d2d810406da444a6101906041b796fbde" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Mon Nov 02 14:30:40 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Nov 02 23:39:11 2009 -0800" }, "message": "tg3 / broadcom: Add PHY_BRCM_CLEAR_RGMII_MODE flag\n\nBroadcom 50610M parts changed the default definitions of the RGMII mode\nshadow register. The 5785 needs the RGMII mode selection bits [4:3]\ncleared.\n\nThe default value of the remaining bits in this register are zero.\nRather than unnecessarily burn an extra bit in the dev_flags member in\nan attempt to enumerate all possible combinations, this patch take a\nmore course grained approach and labels the option as \"clear all bits\".\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nReviewed-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "c73430d04ec75962e20e186d34c40b6d999f0968", "tree": "5b4e2ad9868925397e34c17eaaa9ee6d4a458116", "parents": [ "219c6efefaa3f5cd05db52cda50402b2e1c9ae21" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Mon Nov 02 14:29:34 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Nov 02 23:39:10 2009 -0800" }, "message": "tg3: Add 50610M phy ID for 5785\n\nThis patch adds the 50610M phy ID for 5785.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nReviewed-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "303fc9218246a748304c005e629d658927cf12d0", "tree": "39be2f9d8e6c6d5c6a89076be9a1ba1a444ac610", "parents": [ "c3df0748ee43101dfc5c94d1f61ddfca0ff5baa4" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Mon Nov 02 14:27:34 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Nov 02 23:39:08 2009 -0800" }, "message": "tg3: Extend loopback test timeout\n\nThis patch extends the loopback test timeout from 250 usec to 350 usec.\nWhen the 5785 is paired against an AC131 phy, the older timeout is\njust a little too close to the expected performance based on timings.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nReviewed-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "c3df0748ee43101dfc5c94d1f61ddfca0ff5baa4", "tree": "4359acf03c51dd18ff512ee4b44674c3ca885ec5", "parents": [ "0e5f784c77197edf29d2770b518dc78777d5a480" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Mon Nov 02 14:27:02 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Nov 02 23:39:07 2009 -0800" }, "message": "tg3: 5785: Set port mode to MII when link down\n\nThis patch sets the port mode to MII when the link is down for the 5785.\nSetting the port mode to MII instead of GMII saves power.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nReviewed-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "0e5f784c77197edf29d2770b518dc78777d5a480", "tree": "92b4e99661a56fe9ea324feb39cccda5c01c3bf6", "parents": [ "788a035e6061a66c6c77059c417fdc6234e140ff" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Mon Nov 02 14:26:38 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Nov 02 23:39:05 2009 -0800" }, "message": "tg3: Add AC131 power down support\n\nThe AC131 does not respect the power down bit (bit 11) of the MII\nControl Register (reg 0x0). Instead, software is required to put the\nphy into standby power down mode through the shadow register set. This\npatch implements support for the AC131 standby power down mode.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nReviewed-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "788a035e6061a66c6c77059c417fdc6234e140ff", "tree": "594df5b1f962b98fb3bc514dc1bf435a9ec58ccf", "parents": [ "a21771dd189b340328c573da9e005068e8a74c53" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Mon Nov 02 14:26:03 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Nov 02 23:39:03 2009 -0800" }, "message": "tg3: Improve 5785 PCIe performance\n\nThis patch improves 5785 performance by allowing the write DMA engine to\nrequest larger DMA burst sizes than it otherwise would.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nReviewed-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "a21771dd189b340328c573da9e005068e8a74c53", "tree": "84181a65a4e13edd6b14898e1747d8c84240c6c8", "parents": [ "52cdf8526fe24f11d300b75458ddee017f3f4c88" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Mon Nov 02 14:25:31 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Nov 02 23:39:02 2009 -0800" }, "message": "tg3: Add more PCI DMA map error checking\n\nThis patch adds code to check the status of pci_map_single() before\nallowing rx buffers to be used. It also converts the pci_map_single()\ncall in tg3_run_loopback() to use skb_dma_map() instead.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\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": "52cdf8526fe24f11d300b75458ddee017f3f4c88", "tree": "bbee325ec108529b37633738a69f7830bac876f8", "parents": [ "3f0e3ad72393db9c2932a2ca86cc1a49294bbc63" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Mon Nov 02 14:25:06 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Nov 02 23:39:02 2009 -0800" }, "message": "tg3: Prevent a PCIe tx glitch\n\nThis patch prevents a PCIe tx glitch by allowing the transmitter to go\nto a low power state.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nReviewed-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "3f0e3ad72393db9c2932a2ca86cc1a49294bbc63", "tree": "abba6a3c1d5cdb6a3fe05d79a78c45c41ae7bc71", "parents": [ "f40386c8452f9eead9c5906bfffaaf59f3dc748f" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Mon Nov 02 14:24:36 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Nov 02 23:39:01 2009 -0800" }, "message": "tg3: Convert PHY_ADDR \u003d\u003e TG3_PHY_MII_ADDR\n\nThis patch renames the PHY_ADDR preprocessor definition. The following\npatch will identify a new member on the MDIO bus, so we want this\npreprocessor definition to be a little more descriptive.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nReviewed-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "f40386c8452f9eead9c5906bfffaaf59f3dc748f", "tree": "9b58866117c15dc257e39a448829f472eaad02ce", "parents": [ "92c6b8d16a36df3f28b2537bed2a56491fb08f11" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Mon Nov 02 14:24:02 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Nov 02 23:39:00 2009 -0800" }, "message": "tg3: Fix disappearing 57780 devices\n\nUnder certain power saving conditions, 57780 asic rev devices might\ndisappear from the system. The fix is to disallow the PCIe PLL from\npowering down.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nReviewed-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "92c6b8d16a36df3f28b2537bed2a56491fb08f11", "tree": "13f89b031c7c82163233963c24bfe20312ba901e", "parents": [ "0e1406dd404ce55dbe8d68b4b5e2aed7e5c75fdb" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Mon Nov 02 14:23:27 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Nov 02 23:39:00 2009 -0800" }, "message": "tg3: Fix 5906 transmit hangs\n\nThe 5906 has trouble with fragments that are less than 8 bytes in size.\nThis patch works around the problem by pivoting the 5906\u0027s transmit\nroutine to tg3_start_xmit_dma_bug() and introducing a new SHORT_DMA_BUG\nflag that enables code to detect and react to the problematic condition.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nSigned-off-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "0e1406dd404ce55dbe8d68b4b5e2aed7e5c75fdb", "tree": "4af423112c4c0c6afdcdc96350a5d23af54c7455", "parents": [ "01e6b953ada927093c4d162f634200a20323c537" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Mon Nov 02 12:33:33 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Nov 02 23:38:58 2009 -0800" }, "message": "tg3: Assign flags to fixes in start_xmit_dma_bug\n\nThis patch adds a flag for each bug workaround in\ntg3_start_xmit_dma_bug(). This is prep work for the following patch.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nReviewed-by: Michael Chan \u003cmchan@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "24bb4fb6dac59f220f42fb375ba0e0f19365a227", "tree": "f3c14601de35332b12260e89526426c220578121", "parents": [ "083925d5432d910025e84d445d1243dd260d4afb" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Mon Oct 05 17:55:29 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Wed Oct 07 03:37:39 2009 -0700" }, "message": "tg3: Fix phylib locking strategy\n\nFelix Radensky noted that chip resets were generating stack trace dumps.\nThis is because the driver is attempting to acquire the mdio bus mutex\nwhile holding the tp-\u003elock spinlock. The fix is to change the code such\nthat every phy access takes the tp-\u003elock spinlock instead.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "5ea1c50662d447de344812054175d7151783ea25", "tree": "0e8808b8d747dd237316ce050fe3fceb7bb32cd3", "parents": [ "9feae56c0de65fdd8b1f64f376bb6578417d2b79" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Fri Sep 11 16:50:16 2009 -0700" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Fri Sep 11 16:50:16 2009 -0700" }, "message": "tg3: Fix return ring size breakage\n\nCommit f6eb9b1fc1411d22c073f5264e5630a541d0f7df, \"tg3: Add 5717 asic\nrev\" changed how the rx return ring size operations are done. It\neffectively inverts the sense of the previous test, but it failed to\nalso invert the resulting sizes. This patch corrects that error.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "7ab0f2736bfe137a82a7084bbfb5f809da95cabd", "tree": "e305ec96eceebb285efee4b6fd307822ab257fe6", "parents": [ "aae5e7c30fc660c50dfecbdd745799b05af90f01" ], "author": { "name": "Ben Hutchings", "email": "bhutchings@solarflare.com", "time": "Thu Sep 03 10:39:43 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Thu Sep 03 20:02:11 2009 -0700" }, "message": "netdev: Remove redundant checks for CAP_NET_ADMIN in MDIO implementations\n\ndev_ioctl() already checks capable(CAP_NET_ADMIN) before calling the\ndriver\u0027s implementation of MDIO ioctls.\n\nSigned-off-by: Ben Hutchings \u003cbhutchings@solarflare.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "daf09de817353f18bb81a23a023d429cfd258e62", "tree": "ef2f6c77bd0d0652ec1a28d389b1040e27d4e9f4", "parents": [ "882e9793faa9425dff581c33b1af45ed10145626" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Tue Sep 01 13:22:42 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Wed Sep 02 00:44:11 2009 -0700" }, "message": "tg3: Update version to 3.102\n\nThis patch updates the tg3 version to 3.102.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nReviewed-by: Benjamin Li \u003cbenli@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "882e9793faa9425dff581c33b1af45ed10145626", "tree": "82ad75d5fb45ebaaf05981baaa306c064f102e0d", "parents": [ "a1b950d56de3c72bea3343f54de24c43fb7dc74e" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Tue Sep 01 13:21:36 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Wed Sep 02 00:44:09 2009 -0700" }, "message": "tg3: Add MDIO bus address assignments\n\nThe 5717 is a dual port chip that has a shared MDIO bus design. While\nit is impossible for one function to interface with the wrong phy, that\nfunction still needs to know which MDIO bus address to use when\ninterfacing with its own phy. This patch adds code to determine which\nMDIO bus address to use.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nReviewed-by: Benjamin Li \u003cbenli@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "a1b950d56de3c72bea3343f54de24c43fb7dc74e", "tree": "f54f22cec072bbc17ec963ddc3e832ccf4db7bc0", "parents": [ "f6eb9b1fc1411d22c073f5264e5630a541d0f7df" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Tue Sep 01 13:20:17 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Wed Sep 02 00:44:06 2009 -0700" }, "message": "tg3: Add 5717 NVRAM detection routines\n\nThis patch adds NVRAM detection routines for the 5717.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nReviewed-by: Benjamin Li \u003cbenli@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "f6eb9b1fc1411d22c073f5264e5630a541d0f7df", "tree": "8966482a7874e3087301fc3b9c0a5a2e9870eed8", "parents": [ "8d9d7cfc0ec2fe37ff9afd74326d03f38f96ad1b" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Tue Sep 01 13:19:53 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Wed Sep 02 00:44:01 2009 -0700" }, "message": "tg3: Add 5717 asic rev\n\nThis patch adds the 5717 asic rev.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nReviewed-by: Benjamin Li \u003cbenli@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "8d9d7cfc0ec2fe37ff9afd74326d03f38f96ad1b", "tree": "3fc4ef598534d0e309a4a980b29e3a601f4581e1", "parents": [ "0c1d0e2b05e92ad847b3ebe1c75b7974086bc8fa" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Tue Sep 01 13:19:05 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Wed Sep 02 00:43:58 2009 -0700" }, "message": "tg3: Assign rx ret producer indexes by vector\n\nWhen RSS is enabled, the status block format changes slightly. The\n\"rx_jumbo_consumer\", \"reserved\", and \"rx_mini_consumer\" members get\nmapped to the other three rx return ring producer indexes. This patch\nintroduces a new per-interrupt member which identifies which location\nin the status block a particular vector should look for return ring\nupdates.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nReviewed-by: Benjamin Li \u003cbenli@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "0c1d0e2b05e92ad847b3ebe1c75b7974086bc8fa", "tree": "fab2d998ab474a4969f1717812fd7f80b047e616", "parents": [ "baf8a94a572928710e9e60967d153a7bf3aebd9c" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Tue Sep 01 13:16:33 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Wed Sep 02 00:43:52 2009 -0700" }, "message": "tg3: Adjust RSS ring allocation strategies\n\nWhen multivector RSS is enabled, the first interrupt vector is only used\nto report link interrupts and error conditions. This patch changes the\ncode so that rx and tx ring resources are not allocated for this vector.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nReviewed-by: Benjamin Li \u003cbenli@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "baf8a94a572928710e9e60967d153a7bf3aebd9c", "tree": "a61c57ab84e29bd536c98b9e43129fc30d86abfa", "parents": [ "b6080e126012047d42e53154189fdca286d0600e" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Tue Sep 01 13:13:00 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Wed Sep 02 00:43:49 2009 -0700" }, "message": "tg3: Add RSS support\n\nThis patch adds code needed to enable RSS.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nReviewed-by: Benjamin Li \u003cbenli@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "b6080e126012047d42e53154189fdca286d0600e", "tree": "254fb744e29dab5fc17baf4e37287a742dda9452", "parents": [ "fed9781081aa9600765346c108ff22751e003715" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Tue Sep 01 13:12:00 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Wed Sep 02 00:43:46 2009 -0700" }, "message": "tg3: Add coalesce parameters for msix vectors\n\nThis patch adds code to tune the coalescing parameters for the other\nmsix vectors.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nReviewed-by: Benjamin Li \u003cbenli@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "fed9781081aa9600765346c108ff22751e003715", "tree": "e6e8e3650cc5c49e8a2a60f01175efc4d6b72b7e", "parents": [ "fe5f5787f0866e9f883bdd90018a354f2f3defd1" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Tue Sep 01 13:10:19 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Wed Sep 02 00:43:45 2009 -0700" }, "message": "tg3: Enable NAPI instances for other int vectors\n\nThis patch adds code to enable and disable the rest of the NAPI\ninstances.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nReviewed-by: Benjamin Li \u003cbenli@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "fe5f5787f0866e9f883bdd90018a354f2f3defd1", "tree": "85412719b0f4742d1a3ebf3b9592a3b1a5fafd94", "parents": [ "89aeb3bceaa1a02651206a76a7b9dcb8f3884702" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Tue Sep 01 13:09:39 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Wed Sep 02 00:43:44 2009 -0700" }, "message": "tg3: Add TSS support\n\nThis patch exposes the additional transmit rings to the kernel and makes\nthe necessary modifications to transmit, open, and close paths.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nReviewed-by: Benjamin Li \u003cbenli@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "89aeb3bceaa1a02651206a76a7b9dcb8f3884702", "tree": "ebdd17083599e5af4fa96f86668b654ace211bf3", "parents": [ "f77a6a8e6cee17b21a43bdf6b853cc2fc0e2c4df" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Tue Sep 01 13:08:58 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Wed Sep 02 00:43:42 2009 -0700" }, "message": "tg3: Update intmbox and coal_now for msix\n\nThis patch fixes up two spots that need attention now that msix support\nhas been added.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nReviewed-by: Benjamin Li \u003cbenli@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "f77a6a8e6cee17b21a43bdf6b853cc2fc0e2c4df", "tree": "e604b171d1579cc6cc61b8124425fd331486bf57", "parents": [ "646c9eddcffd202bb0f3d906cecf94eaf10cad31" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Tue Sep 01 13:04:37 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Wed Sep 02 00:43:39 2009 -0700" }, "message": "tg3: Add tx and rx ring resource tracking\n\nThis patch adds code to assign status block, tx producer ring and rx\nreturn ring resources needed for the other interrupt vectors.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nReviewed-by: Benjamin Li \u003cbenli@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "646c9eddcffd202bb0f3d906cecf94eaf10cad31", "tree": "5f6ad6b05ef0d9f06d43d5db06dec9f842c68291", "parents": [ "679563f47cd2547a0e091b5bd3ddf30027af6b08" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Tue Sep 01 12:58:41 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Wed Sep 02 00:43:36 2009 -0700" }, "message": "tg3: Add mailbox assignments\n\nThe 5717 assigns mailbox locations to interrupt vectors in a rather\nnon-intuitive way. (Much of the complexity stems from legacy\ncompatibility issues.) This patch implements the assignment scheme.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nReviewed-by: Benjamin Li \u003cbenli@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "679563f47cd2547a0e091b5bd3ddf30027af6b08", "tree": "efb6a8a9e6d080447b89014725bfcfad0b33a3e6", "parents": [ "4f125f42dd55390016e21f8b3960f99d02d1001f" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Tue Sep 01 12:55:46 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Wed Sep 02 00:43:33 2009 -0700" }, "message": "tg3: Add MSI-X support\n\nThis patch adds MSI-X support.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nReviewed-by: Benjamin Li \u003cbenli@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "4f125f42dd55390016e21f8b3960f99d02d1001f", "tree": "a976eb6c317db2a93bad2ba339be627deb59b3be", "parents": [ "2d31ecaf10c4ae03d49aed516481b2839b0220f6" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Tue Sep 01 12:55:02 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Wed Sep 02 00:43:30 2009 -0700" }, "message": "tg3: Add support code around kernel interrupt API\n\nThis patch adds code to support multiple interrupt vectors around the\nkernel\u0027s interrupt API.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nReviewed-by: Benjamin Li \u003cbenli@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "2d31ecaf10c4ae03d49aed516481b2839b0220f6", "tree": "c30ad4887a0dcc6f26856b329401169d6221421f", "parents": [ "fd2ce37f8e4a570ce90b141a2e7c476c5b399836" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Tue Sep 01 12:53:31 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Wed Sep 02 00:43:28 2009 -0700" }, "message": "tg3: Create tg3_rings_reset()\n\nThis patch moves most of the chip ring setup logic into a separate\nfunction. This will make it easier to verify the multi ring setup\nchanges.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nReviewed-by: Benjamin Li \u003cbenli@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "fd2ce37f8e4a570ce90b141a2e7c476c5b399836", "tree": "2bb84bb3dfcf9900b47f221073f573e3a6f0941f", "parents": [ "f19af9c2cc015e42dfe4bd5c383e32066ec2801c" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Tue Sep 01 12:51:13 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Wed Sep 02 00:43:25 2009 -0700" }, "message": "tg3: Add per-int coalesce now member\n\nEach interrupt vector has its own bit in the host coalescing register to\nforce that vector\u0027s status block to be updated and generate an\ninterrupt. This patch adds a member to the per-interrupt structure\nthat records which bit belongs to that vector.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nReviewed-by: Benjamin Li \u003cbenli@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "f19af9c2cc015e42dfe4bd5c383e32066ec2801c", "tree": "8b6b51c7f54013433ab14c48ce78754061e9b0a9", "parents": [ "6cdee2f96a97f6da26bd3759c3f8823332fbb438" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Tue Sep 01 12:47:49 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Wed Sep 02 00:43:22 2009 -0700" }, "message": "tg3: inline tg3_cond_int()\n\nThis patch inlines the code of tg3_cond_int() into the function\u0027s only\ncallsite. This prep work makes the following patch cleaner.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nReviewed-by: Benjamin Li \u003cbenli@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "61357325f377889a1daffa14962d705dc814dd0e", "tree": "7b436f1097abbc5681de6d1e5901f62963b42220", "parents": [ "d0cf9c0dadcdc89a755bcb301cfc9c796eb28ccf" ], "author": { "name": "Stephen Hemminger", "email": "shemminger@vyatta.com", "time": "Mon Aug 31 19:50:58 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Tue Sep 01 01:14:07 2009 -0700" }, "message": "netdev: convert bulk of drivers to netdev_tx_t\n\nIn a couple of cases collapse some extra code like:\n int retval \u003d NETDEV_TX_OK;\n ...\n return retval;\ninto\n return NETDEV_TX_OK;\n\nSigned-off-by: Stephen Hemminger \u003cshemminger@vyatta.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "fc57e515a2c02599b00d252545521288dfc0158a", "tree": "aafa7042840553bffdf76ea3b6a7e7240ed29990", "parents": [ "f3f3f27e5b4e27737f824535e6f145a3c88b976c" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Fri Aug 28 14:03:44 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Sat Aug 29 15:43:06 2009 -0700" }, "message": "tg3: Update version to 3.101\n\nThis patch updates the tg3 version to 3.101.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "f3f3f27e5b4e27737f824535e6f145a3c88b976c", "tree": "042a57424aca2fa1ff5736518321740070da767c", "parents": [ "723344820aa405ac2663ab9e36fd27833d06129b" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Fri Aug 28 14:03:21 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Sat Aug 29 15:43:04 2009 -0700" }, "message": "tg3: Move per-int tx members to a per-int struct\n\nThis patch moves the tx_prod, tx_cons, tx_pending, tx_ring, and\ntx_buffers transmit ring device members to a per-interrupt structure.\nIt also adds a new transmit producer mailbox member (prodmbox) and\nconverts the code to use it rather than a preprocessor constant.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "723344820aa405ac2663ab9e36fd27833d06129b", "tree": "dad1b2b19c269ff1ba9dcd3d5bbbc8d4ac38a9ba", "parents": [ "898a56f8d8170c188e47ae3acb90d2ea9a585ebe" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Fri Aug 28 14:03:01 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Sat Aug 29 15:43:03 2009 -0700" }, "message": "tg3: Move per-int rx members to per-int struct\n\nThis patch moves the rx_rcb, rx_rcb_mapping, and rx_rcb_ptr return ring\ndevice members to a per-interrupt structure. It also adds a new return\nring consumer mailbox register member (consmbox) and converts the code\nto use it rather than a preprocessor constant.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "898a56f8d8170c188e47ae3acb90d2ea9a585ebe", "tree": "6880f6bec0090eac6cd56458fc23e383b3f7d078", "parents": [ "17375d25d3dcd3d4caf9456fa94f60e29d6b1146" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Fri Aug 28 14:02:40 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Sat Aug 29 15:43:01 2009 -0700" }, "message": "tg3: Move general int members to a per-int struct\n\nThis patch moves the last_tag, last_tag_irq, and hw_status device\nmembers to a per-interrupt structure. It also adds a new interrupt\nmailbox member (int_mbox) and converts the code to use it rather than a\ndirect preprocessor constant.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "17375d25d3dcd3d4caf9456fa94f60e29d6b1146", "tree": "ab33928dc44e87c37b0067dc6f54c6a38bab73be", "parents": [ "09943a1819a240ff4a72f924d0038818fcdd0a90" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Fri Aug 28 14:02:18 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Sat Aug 29 15:42:59 2009 -0700" }, "message": "tg3: Convert napi handlers to use tnapi\n\nThis patch converts the napi interrupt handler functions to accept and\nuse tg3_napi structures.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "09943a1819a240ff4a72f924d0038818fcdd0a90", "tree": "7cb2e3833a2ec97b71e7b0bd7cb79fb31781cda8", "parents": [ "8ef0442f98850333196bc56415192e52a6267878" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Fri Aug 28 14:01:57 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Sat Aug 29 15:42:58 2009 -0700" }, "message": "tg3: Convert ISR parameter to tnapi\n\nThis patch migrates the ISR parameter from struct net_device to struct\ntg3_napi. Checkpatch complains about the existence of the preexisting\nIRQF_SAMPLE_RANDOM flag. I\u0027ve opted to keep this patch conservative and\nlet it continue to exist until the flag gets officially purged from the\nkernel.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "8ef0442f98850333196bc56415192e52a6267878", "tree": "5ba3ec9ed6ef805ecec9073906017e233063aa2e", "parents": [ "07b0173cb5d6a9d77646cd855066ebe90b9203f2" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Fri Aug 28 14:01:37 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Sat Aug 29 15:42:56 2009 -0700" }, "message": "tg3: Move napi to per-int struct\n\nThis patch creates a per-interrupt data structure, moves the napi\nmember over, and creates a tg3 pointer back to the device structure.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "07b0173cb5d6a9d77646cd855066ebe90b9203f2", "tree": "5a2490f1965e552688f4b3cec4453d0bba99a386", "parents": [ "79ed5ac7ddd5f8d6463f5a17b3575772e9896481" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Fri Aug 28 14:01:15 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Sat Aug 29 15:42:54 2009 -0700" }, "message": "tg3: Cleanup interrupt setup / teardown\n\nLater patches will be adding MSIX support, which will complicate\ninterrupt initialization. This patch prepares for the integration by\nbreaking out the interrupt setup and teardown code into separate\nfunctions and cleaning up the error return paths.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "79ed5ac7ddd5f8d6463f5a17b3575772e9896481", "tree": "46e9a73d5457532e1e50c077a94213505e1d4606", "parents": [ "21f581a5366d48d86b9ae86043fc61d44e992c0c" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Fri Aug 28 14:00:55 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Sat Aug 29 15:42:52 2009 -0700" }, "message": "tg3: Use ext rx bds\n\nThe 5717 only uses extended buffer descriptors for the jumbo producer\nring. Extended buffer descriptors are available on all devices that\nsupport a separate jumbo producer ring so make the change universal.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "21f581a5366d48d86b9ae86043fc61d44e992c0c", "tree": "bfaa5a591d663ad5d61b9cdd219409ec4922f0dd", "parents": [ "cf7a7298c4f47ab7546b933bb54ad3ea03a1daf6" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Fri Aug 28 14:00:25 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Sat Aug 29 15:42:50 2009 -0700" }, "message": "tg3: Create a new prodring_set structure\n\nThis patch migrates most of the rx producer ring variables to a new\ntg3_rx_prodring_set structure and modifies the code accordingly.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "cf7a7298c4f47ab7546b933bb54ad3ea03a1daf6", "tree": "3ad2a934a87fa018cb318002bba26d229dd4d57d", "parents": [ "287be12e1774d842bff21ea0c1809c2387d7b310" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Fri Aug 28 13:59:57 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Sat Aug 29 15:42:47 2009 -0700" }, "message": "tg3: Create rx producer ring setup routines\n\nLater patches are going to complicate the ring initialization routines.\nThis patch breaks out the setup and teardown of the rx producer rings\ninto separate functions to make the code more readable.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "287be12e1774d842bff21ea0c1809c2387d7b310", "tree": "edeb3e887cc9e7e3d0f5197a262a6acf2e86ce9a", "parents": [ "8f666b07ac53eeedd6c035adf6d4299f9ed0df2d" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Fri Aug 28 13:58:46 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Sat Aug 29 15:42:43 2009 -0700" }, "message": "tg3: Clarify rx buffer relationships\n\nThis patch attempts to document the various rx buffer sizes used by the\ndriver and how they relate to each other.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "8f666b07ac53eeedd6c035adf6d4299f9ed0df2d", "tree": "a7c1b24da09573873097c33a25d25af2ea9206bc", "parents": [ "fdb72b38c94c0ead1f78ecc8db64b832feda22c3" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Fri Aug 28 13:58:24 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Sat Aug 29 15:42:41 2009 -0700" }, "message": "tg3: Move the JUMBO_CAPABLE and SUPPORT_MSI flags\n\nThis patch moves where the jumbo capable and msi support flags are\nlocated. This is prep work for the addition of msix support flags.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "fdb72b38c94c0ead1f78ecc8db64b832feda22c3", "tree": "fba8a1f9351b6d2f5abb6b63f4d906627ea3572a", "parents": [ "8590a603e5e20ccf49d6cf0ea71ecf5388d1f9da" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Fri Aug 28 13:57:12 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Sat Aug 29 15:42:36 2009 -0700" }, "message": "tg3: Break out mini producer ring handling\n\nThis patch separates the code that sets up the mini producer ring from\nthe code that sets up the jumbo producer rings. The 5717 asic rev\ndevices do not have a mini ring, but do have a jumbo frame\nimplementation similar to the 5704 and previous devices.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "8590a603e5e20ccf49d6cf0ea71ecf5388d1f9da", "tree": "fe9c1f335c96afa70da75ee64bd33ffe4f210c07", "parents": [ "2befdcea96fcd9a13e94373c66ea1dd7365d2a74" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Fri Aug 28 12:29:16 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Sat Aug 29 15:42:33 2009 -0700" }, "message": "tg3: Reformat NVRAM case statements\n\nThis patch fixes up the NVRAM detection switch statements to conform\nto the kernel coding style.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "2befdcea96fcd9a13e94373c66ea1dd7365d2a74", "tree": "6cebb5d4aa9b6b90fc26402471b9fb0e9e1c8e32", "parents": [ "0a9140cff22e405fce1747a2e02d41851c36c55a" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Fri Aug 28 12:28:45 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Sat Aug 29 15:42:31 2009 -0700" }, "message": "tg3: Add new 5785 10/100 only device ID\n\nThis patch adds a new device ID for those 5785 devices that will only\nuse 10/100 phys.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "0a9140cff22e405fce1747a2e02d41851c36c55a", "tree": "db68a54a136cde1920541e252c0c77f0abeef9e1", "parents": [ "b3df9a514f3c2020952cff34bc5bc6694a31c00c" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Fri Aug 28 12:27:50 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Sat Aug 29 15:42:27 2009 -0700" }, "message": "tg3: Delay mdio bus init until fw finishes\n\nThe device firmware uses the MDIO bus during early setup. If the driver\nmodifies the MDIO bus configuration while it is in use by the firmware,\nany number of bad things can happen. This patch delays MDIO setup until\nafter the firmware posts its magic signature, signifying initialization\nis complete.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "f656f39801b00c3c2aa26cefbdee2775d6706d45", "tree": "6c7bd9aa35eed609a7a7e1edb090dac330d9816d", "parents": [ "d9221e66002a7f24fb71b73132aa46c40079745f" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Tue Aug 25 10:11:55 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Wed Aug 26 15:48:08 2009 -0700" }, "message": "tg3: Update version to 3.100\n\nThis patch updates the tg3 version to 3.100.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nReviewed-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": "7f97a4bd47291e4ec9b9eaf63d7275ddfb498cb3", "tree": "af60b056cbb1c87b042e4db2931bd391dc8d94cd", "parents": [ "535ef6e1124d445efbcc13b7126561dc544b0b64" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Tue Aug 25 10:10:03 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Wed Aug 26 15:48:00 2009 -0700" }, "message": "tg3: Convert code to use PHY_IS_FET\n\nThis patch converts the code to use the PHY_IS_FET flag rather than the\nASIC revision to decide whether or not to use FET paths.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nReviewed-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": "535ef6e1124d445efbcc13b7126561dc544b0b64", "tree": "a961c86394eca3c40f660743ac79585dc2c0613c", "parents": [ "bb85fbb6a98d8edab81599913559c7ff0a963984" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Tue Aug 25 10:09:36 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Wed Aug 26 15:47:58 2009 -0700" }, "message": "tg3: Create MII_TG3_FET namespace\n\nBroadcom\u0027s phys come in two distinctly different register layouts. For\nthe lack of an official term to distinguish between the two formats, we\ncan loosely categorize them by their fast ethernet or gigabit ethernet\ntransceiver description. This patch creates the (driver-internal) Fast\nEthernet Transceiver (FET) namespace and converts the 5906 EPHY\ndefinitions over.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nReviewed-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": "bb85fbb6a98d8edab81599913559c7ff0a963984", "tree": "3509fc3b02a48597f3dac4d5678db547e33f69a6", "parents": [ "5e7ccf2003e6a9c35b5aa24953ba5009a1a8b653" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Tue Aug 25 10:09:07 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Wed Aug 26 15:47:56 2009 -0700" }, "message": "tg3: Tune 5785 clock switching\n\nThis patch tunes the timeouts the CPMU uses to decide when to switch\nfrom the clocks output by the PHY to internal clock sources.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nReviewed-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": "5e7ccf2003e6a9c35b5aa24953ba5009a1a8b653", "tree": "5533444c48b514dd9ebcd1ae8d63c374ecf85ddb", "parents": [ "e7126997342560533317d8467e8516119ebcbd21" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Tue Aug 25 10:08:42 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Wed Aug 26 15:47:53 2009 -0700" }, "message": "tg3: Add 57788, remove 57720\n\nThis patch adds support for the 57788 and removes support for the 57720\nwhich was never released.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nReviewed-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": "e7126997342560533317d8467e8516119ebcbd21", "tree": "cc592fc98d946756caa30dd6dccde7374d3af2e4", "parents": [ "29ea095fb727ac48228ff2d1af484c27bf1dcbd4" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Tue Aug 25 10:08:16 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Wed Aug 26 15:47:53 2009 -0700" }, "message": "tg3: Preserve PCIe MPS setting for new devs\n\nMost older tg3 devices only supported a PCIe maximum payload size of\n128 bytes. More recent devices bump this limit up to 256 bytes\nthough. This patch modifies the code so that the MPS limit is only\nenforced on those devices that only allow the 128 byte setting.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nReviewed-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": "29ea095fb727ac48228ff2d1af484c27bf1dcbd4", "tree": "340b7879e0d2e3b76492265ddef978f242675fb1", "parents": [ "255ca311b650caece3ec4f78b88ef298664d561f" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Tue Aug 25 10:07:54 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Wed Aug 26 15:47:51 2009 -0700" }, "message": "tg3: Fix TSO test against wrong flags var\n\nJulia Lawall discovered that the TG3_FLG2_TSO_CAPABLE flag was being\ncompared against the wrong flags device member. This patch implements\nthe fix.\n\nSigned-off-by: Julia Lawall \u003cjulia@diku.dk\u003e\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nReviewed-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": "255ca311b650caece3ec4f78b88ef298664d561f", "tree": "cf26fdfb0fb9f5fba78bb59a82f37abb132d4b62", "parents": [ "521e6b90dd3f0392062845d7ef13e6e41bb99d8a" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Tue Aug 25 10:07:27 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Wed Aug 26 15:47:47 2009 -0700" }, "message": "tg3: Prevent tx BD corruption\n\nThis patch prevents a tx BD corruption bug by preventing the device from\npowering down the PLL from L1 if the link speed is 10Mbps or 100Mbps.\n\nThe same bits are also used to prevent a system hang during chip reset\nresulting from a complicated set of events that ultimately leads to\nPCIe block register corruption.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nReviewed-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": "521e6b90dd3f0392062845d7ef13e6e41bb99d8a", "tree": "cf7405a1a6a3b3b247c9c3c2c24372779c7faea6", "parents": [ "c46b59b241ec52ffaf92ece8d8ab726621d580fb" ], "author": { "name": "Matt Carlson", "email": "mcarlson@broadcom.com", "time": "Tue Aug 25 10:06:01 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Wed Aug 26 15:47:45 2009 -0700" }, "message": "tg3: Fix 57780 asic rev PCIe link receiver errors\n\nThis patch fixes some PCIe link receiver errors by decreasing the internal\nelectrical idle timeout.\n\nSigned-off-by: Matt Carlson \u003cmcarlson@broadcom.com\u003e\nReviewed-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": "042a53a9e437feaf2230dd2cadcecfae9c7bfe05", "tree": "ae9078f61e390a3014aecb3fe80d3438ab25ee51", "parents": [ "eae3f29cc73f83cc3f1891d3ad40021b5172c630" ], "author": { "name": "Eric Dumazet", "email": "eric.dumazet@gmail.com", "time": "Fri Jun 05 04:04:16 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Mon Jun 08 00:21:48 2009 -0700" }, "message": "net: skb_shared_info optimization\n\nskb_dma_unmap() is quite expensive for small packets,\nbecause we use two different cache lines from skb_shared_info.\n\nOne to access nr_frags, one to access dma_maps[0]\n\nInstead of dma_maps being an array of MAX_SKB_FRAGS + 1 elements,\nlet dma_head alone in a new dma_head field, close to nr_frags,\nto reduce cache lines misses.\n\nTested on my dev machine (bnx2 \u0026 tg3 adapters), nice speedup !\n\nSigned-off-by: Eric Dumazet \u003ceric.dumazet@gmail.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" }, { "commit": "cdd0db058d64f2619b08e7d098ee0014aa0a5bc1", "tree": "a5e31f6687eff581309b095781c7e2f0bc676182", "parents": [ "28679751a924c11f7135641f26e99249385de5b4" ], "author": { "name": "Eric Dumazet", "email": "eric.dumazet@gmail.com", "time": "Thu May 28 00:00:41 2009 +0000" }, "committer": { "name": "David S. Miller", "email": "davem@davemloft.net", "time": "Fri May 29 01:46:27 2009 -0700" }, "message": "net: dont update dev-\u003etrans_start\n\nSecond round of drivers for Gb cards (and NIU one I forgot in the 10GB round)\n\nNow that core network takes care of trans_start updates, dont do it\nin drivers themselves, if possible. Drivers can avoid one cache miss\n(on dev-\u003etrans_start) in their start_xmit() handler.\n\nExceptions are NETIF_F_LLTX drivers\n\nSigned-off-by: Eric Dumazet \u003ceric.dumazet@gmail.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n" } ], "next": "bb9e63e27117b469a151c61fb0045a8ec4cced5d" }