)]}' { "log": [ { "commit": "6659a0f0bb7481d0f94ca3f203a4e1e406a9694d", "tree": "6803f9ad7ceb8556e8a07a8ba2e2d1a61e7283f1", "parents": [ "bd1939de9061dbc5cac44ffb4425aaf4c9b894f1" ], "author": { "name": "Johann Felix Soden", "email": "johfel@users.sourceforge.net", "time": "Wed Feb 06 01:40:22 2008 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Wed Feb 06 10:41:21 2008 -0800" }, "message": "virtio: add missing #include \u003clinux/delay.h\u003e\n\nInclude linux/delay.h to fix compiler error:\n\ndrivers/virtio/virtio_balloon.c: In function \u0027fill_balloon\u0027:\ndrivers/virtio/virtio_balloon.c:98: error: implicit declaration of function \u0027msleep\u0027\n\nSigned-off-by: Johann Felix Soden \u003cjohfel@users.sourceforge.net\u003e\nCc: Rusty Russell \u003crusty@rustcorp.com.au\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "6b35e40767c6c1ac783330109ae8e0c09ea6bc82", "tree": "e820d770894cb945c3070fa6739b0149b1bfa2f9", "parents": [ "55a7c066041e7850948d29ed813f62821a9ec046" ], "author": { "name": "Rusty Russell", "email": "rusty@rustcorp.com.au", "time": "Mon Feb 04 23:50:12 2008 -0500" }, "committer": { "name": "Rusty Russell", "email": "rusty@rustcorp.com.au", "time": "Mon Feb 04 23:50:13 2008 +1100" }, "message": "virtio: balloon driver\n\nAfter discussions with Anthony Liguori, it seems that the virtio\nballoon can be made even simpler. Here\u0027s my attempt.\n\nThe device configuration tells the driver how much memory it should\ntake from the guest (ie. balloon size). The guest feeds the page\nnumbers it has taken via one virtqueue.\n\nA second virtqueue feeds the page numbers the driver wants back: if\nthe device has the VIRTIO_BALLOON_F_MUST_TELL_HOST bit, then this\nqueue is compulsory, otherwise it\u0027s advisory (and the guest can simply\nfault the pages back in).\n\nThis driver can be enhanced later to deflate the balloon via a\nshrinker, oom callback or we could even go for a complete set of\nin-guest regulators.\n\nSigned-off-by: Rusty Russell \u003crusty@rustcorp.com.au\u003e\n" }, { "commit": "55a7c066041e7850948d29ed813f62821a9ec046", "tree": "ea4ef20c8014d5222957cef83d4fc62b75c58fd6", "parents": [ "3343660d8c62c6b00b2f15324ef3fcb6be207bfa" ], "author": { "name": "Anthony Liguori", "email": "aliguori@us.ibm.com", "time": "Mon Jan 28 09:59:59 2008 -0600" }, "committer": { "name": "Rusty Russell", "email": "rusty@rustcorp.com.au", "time": "Mon Feb 04 23:50:12 2008 +1100" }, "message": "virtio: Use PCI revision field to indicate virtio PCI ABI version\n\nAs Avi pointed out, as we continue to massage the virtio PCI ABI, we can make\nthings a little more friendly to users by utilizing the PCI revision field to\nindicate which version of the ABI we\u0027re using. This is a hard ABI version\nand incrementing it will cause the guest driver to break.\n\nThis is the necessary changes to virtio_pci to support this.\n\nSigned-off-by: Anthony Liguori \u003caliguori@us.ibm.com\u003e\nSigned-off-by: Rusty Russell \u003crusty@rustcorp.com.au\u003e\n" }, { "commit": "3343660d8c62c6b00b2f15324ef3fcb6be207bfa", "tree": "06d86446da65fc1814edad944e43aeb62f092422", "parents": [ "d50ed907dc3db5bf2dd0a05b4e199a65793a3788" ], "author": { "name": "Anthony Liguori", "email": "aliguori@us.ibm.com", "time": "Mon Nov 12 21:30:26 2007 -0600" }, "committer": { "name": "Rusty Russell", "email": "rusty@rustcorp.com.au", "time": "Mon Feb 04 23:50:11 2008 +1100" }, "message": "virtio: PCI device\n\nThis is a PCI device that implements a transport for virtio. It allows virtio\ndevices to be used by QEMU based VMMs like KVM or Xen.\n\nSigned-off-by: Anthony Liguori \u003caliguori@us.ibm.com\u003e\nSigned-off-by: Rusty Russell \u003crusty@rustcorp.com.au\u003e\n" }, { "commit": "c6fd47011b4bdebad3f1513bac75fe4895e332ee", "tree": "12224cdb2594be26e02291b142ba6e1e2c1c8122", "parents": [ "15f9c8903cbdb02aee0f1bcf86a97c2e238b9a3d" ], "author": { "name": "Rusty Russell", "email": "rusty@rustcorp.com.au", "time": "Mon Feb 04 23:50:05 2008 -0500" }, "committer": { "name": "Rusty Russell", "email": "rusty@rustcorp.com.au", "time": "Mon Feb 04 23:50:06 2008 +1100" }, "message": "virtio: Allow virtio to be modular and used by modules\n\nThis is needed for the virtio PCI device to be compiled as a module.\n\nSigned-off-by: Anthony Liguori \u003caliguori@us.ibm.com\u003e\nSigned-off-by: Rusty Russell \u003crusty@rustcorp.com.au\u003e\n" }, { "commit": "15f9c8903cbdb02aee0f1bcf86a97c2e238b9a3d", "tree": "a215ccf3f745e52ae67aed1ac822baa57326b9b6", "parents": [ "0ad07ec1fd2f3e90dfb086b04c07a83db40e9172" ], "author": { "name": "Rusty Russell", "email": "rusty@rustcorp.com.au", "time": "Mon Feb 04 23:50:05 2008 -0500" }, "committer": { "name": "Rusty Russell", "email": "rusty@rustcorp.com.au", "time": "Mon Feb 04 23:50:05 2008 +1100" }, "message": "virtio: Use the sg_phys convenience function.\n\nSimple cleanup.\n\nSigned-off-by: Rusty Russell \u003crusty@rustcorp.com.au\u003e\n" }, { "commit": "81a8deab1ce3816c6a89e3429e234e7d3686da94", "tree": "d62e7dcc09dddd0edc6d507e7b219c16e66d3b02", "parents": [ "6e5aa7efb27aec7e55b6463fa2c8db594c4226fa" ], "author": { "name": "Rusty Russell", "email": "rusty@rustcorp.com.au", "time": "Mon Feb 04 23:50:04 2008 -0500" }, "committer": { "name": "Rusty Russell", "email": "rusty@rustcorp.com.au", "time": "Mon Feb 04 23:50:04 2008 +1100" }, "message": "virtio: handle interrupts after callbacks turned off\n\nAnthony Liguori found double interrupt suppression in the virtio_net\ndriver, triggered by two skb_recv_done\u0027s in a row. This is because\nvirtio_ring\u0027s interrupt suppression is a best-effort optimization: it\ncontains no synchronization so the host can miss it and still send\ninterrupts.\n\nBut it\u0027s certainly nicer for virtio users if calling disable_cb\nactually disables callbacks, so we check for the race in the interrupt\nroutine.\n\nNote: SMP guests might require syncronization here, but since\ndisable_cb is actually called from interrupt context, there has to be\nsome form of synchronization before the next same interrupt handler is\ncalled (Linux guarantees that the same device\u0027s irq handler will never\nrun simultanously on multiple CPUs).\n\nSigned-off-by: Rusty Russell \u003crusty@rustcorp.com.au\u003e\n" }, { "commit": "6e5aa7efb27aec7e55b6463fa2c8db594c4226fa", "tree": "060a955e711ac224136157a5410e88dcdab965af", "parents": [ "b3369c1fb410fddeb38a404316c861395f6d6ae8" ], "author": { "name": "Rusty Russell", "email": "rusty@rustcorp.com.au", "time": "Mon Feb 04 23:50:03 2008 -0500" }, "committer": { "name": "Rusty Russell", "email": "rusty@rustcorp.com.au", "time": "Mon Feb 04 23:50:03 2008 +1100" }, "message": "virtio: reset function\n\nA reset function solves three problems:\n\n1) It allows us to renegotiate features, eg. if we want to upgrade a\n guest driver without rebooting the guest.\n\n2) It gives us a clean way of shutting down virtqueues: after a reset,\n we know that the buffers won\u0027t be used by the host, and\n\n3) It helps the guest recover from messed-up drivers.\n\nSo we remove the -\u003eshutdown hook, and the only way we now remove\nfeature bits is via reset.\n\nWe leave it to the driver to do the reset before it deletes queues:\nthe balloon driver, for example, needs to chat to the host in its\nremove function.\n\nSigned-off-by: Rusty Russell \u003crusty@rustcorp.com.au\u003e\n" }, { "commit": "426e3e0af5d2473e67d4256fc1340b7faebd1cc7", "tree": "29912e63889e45307f41ef08116ecd895b17e21c", "parents": [ "3309daaad724dd08eb598bf9c12b7bb9daddd706" ], "author": { "name": "Rusty Russell", "email": "rusty@rustcorp.com.au", "time": "Mon Feb 04 23:49:59 2008 -0500" }, "committer": { "name": "Rusty Russell", "email": "rusty@rustcorp.com.au", "time": "Mon Feb 04 23:50:00 2008 +1100" }, "message": "virtio: clarify NO_NOTIFY flag usage\n\nThe other side (host) can set the NO_NOTIFY flag as an optimization,\nto say \"no need to kick me when you add things\". Make it clear that\nthis is advisory only; especially that we should always notify when\nthe ring is full.\n\nSigned-off-by: Rusty Russell \u003crusty@rustcorp.com.au\u003e\n" }, { "commit": "18445c4d501b9ab4336f66ef46b092661ddaf336", "tree": "9d23185f207d912942890cf047d1d3200806b401", "parents": [ "a586d4f6016f7139d8c26df0e6927131168d3b5b" ], "author": { "name": "Rusty Russell", "email": "rusty@rustcorp.com.au", "time": "Mon Feb 04 23:49:57 2008 -0500" }, "committer": { "name": "Rusty Russell", "email": "rusty@rustcorp.com.au", "time": "Mon Feb 04 23:49:58 2008 +1100" }, "message": "virtio: explicit enable_cb/disable_cb rather than callback return.\n\nIt seems that virtio_net wants to disable callbacks (interrupts) before\ncalling netif_rx_schedule(), so we can\u0027t use the return value to do so.\n\nRename \"restart\" to \"cb_enable\" and introduce \"cb_disable\" hook: callback\nnow returns void, rather than a boolean.\n\nSigned-off-by: Rusty Russell \u003crusty@rustcorp.com.au\u003e\n" }, { "commit": "a586d4f6016f7139d8c26df0e6927131168d3b5b", "tree": "1c47e1a6b6b8fb18baa42f32980f29c4ae9cbbdc", "parents": [ "f35d9d8aae08940b7fdd1bb8110619da2ece6b28" ], "author": { "name": "Rusty Russell", "email": "rusty@rustcorp.com.au", "time": "Mon Feb 04 23:49:56 2008 -0500" }, "committer": { "name": "Rusty Russell", "email": "rusty@rustcorp.com.au", "time": "Mon Feb 04 23:49:57 2008 +1100" }, "message": "virtio: simplify config mechanism.\n\nPreviously we used a type/len pair within the config space, but this\nseems overkill. We now simply define a structure which represents the\nlayout in the config space: the config space can now only be extended\nat the end.\n\nThe main driver-visible changes:\n1) We indicate what fields are present with an explicit feature bit.\n2) Virtqueues are explicitly numbered, and not in the config space.\n\nSigned-off-by: Rusty Russell \u003crusty@rustcorp.com.au\u003e\n" }, { "commit": "74b2553f1d13e60fb27063204bd5b6908a6f8494", "tree": "cd35e82d16cf190ccd95362478a598314de639ce", "parents": [ "d1c856e0f1a4c946c6329cff126548ef4288735f" ], "author": { "name": "Rusty Russell", "email": "rusty@rustcorp.com.au", "time": "Mon Nov 19 11:20:42 2007 -0500" }, "committer": { "name": "Rusty Russell", "email": "rusty@rustcorp.com.au", "time": "Mon Nov 19 11:20:42 2007 +1100" }, "message": "virtio: fix module/device unloading\n\nThe virtio code never hooked through the -\u003eremove callback. Although\nnoone supports device removal at the moment, this code is already\nneeded for module unloading.\n\nThis of course also revealed bugs in virtio_blk, virtio_net and lguest\nunloading paths.\n\nSigned-off-by: Rusty Russell \u003crusty@rustcorp.com.au\u003e\n" }, { "commit": "42b36cc0ce717deeb10030141a43dede763a3ebe", "tree": "b2dc48b4f16c5dc59461ad24b027d631edda1da4", "parents": [ "1200e646ae238afc536be70257290eb33fb6e364" ], "author": { "name": "Rusty Russell", "email": "rusty@rustcorp.com.au", "time": "Mon Nov 12 13:39:18 2007 +1100" }, "committer": { "name": "Rusty Russell", "email": "rusty@rustcorp.com.au", "time": "Mon Nov 12 13:59:40 2007 +1100" }, "message": "virtio: Force use of power-of-two for descriptor ring sizes\n\nThe virtio descriptor rings of size N-1 were nicely set up to be\naligned to an N-byte boundary. But as Anthony Liguori points out, the\nfree-running indices used by virtio require that the sizes be a power\nof 2, otherwise we get problems on wrap (demonstrated with lguest).\n\nSo we replace the clever \"2^n-1\" scheme with a simple \"align to page\nboundary\" scheme: this means that all virtio rings take at least two\npages, but it\u0027s safer than guessing cache alignment.\n\nSigned-off-by: Rusty Russell \u003crusty@rustcorp.com.au\u003e\n" }, { "commit": "1bc4953ed44454c7f53d0b609445d1534981ee75", "tree": "05f67206d6978261ad2569d3a0030f0299331191", "parents": [ "4d125de3a5d130054df2285e542c1491d214d3e8" ], "author": { "name": "Anthony Liguori", "email": "aliguori@us.ibm.com", "time": "Wed Nov 07 15:49:24 2007 -0600" }, "committer": { "name": "Rusty Russell", "email": "rusty@rustcorp.com.au", "time": "Mon Nov 12 13:59:09 2007 +1100" }, "message": "virtio: Fix used_idx wrap-around\n\nThe more_used() function compares the vq-\u003evring.used-\u003eidx with last_used_idx.\nSince vq-\u003evring.used-\u003eidx is a 16-bit integer, and last_used_idx is an\nunsigned int, this results in unpredictable behavior when vq-\u003evring.used-\u003eidx\nwraps around.\n\nThis patch corrects this by changing last_used_idx to the correct type.\n\nSigned-off-by: Anthony Liguori \u003caliguori@us.ibm.com\u003e\nSigned-off-by: Rusty Russell \u003crusty@rustcorp.com.au\u003e\n" }, { "commit": "0a8a69dd77ddbd4513b21363021ecde7e1025502", "tree": "ed6d8f0756835390b4c0d9a172422f2e42a65523", "parents": [ "b01d9f2863349b0e041b90c3c86a998ee0fed2b0" ], "author": { "name": "Rusty Russell", "email": "rusty@rustcorp.com.au", "time": "Mon Oct 22 11:03:40 2007 +1000" }, "committer": { "name": "Rusty Russell", "email": "rusty@rustcorp.com.au", "time": "Tue Oct 23 15:49:55 2007 +1000" }, "message": "Virtio helper routines for a descriptor ringbuffer implementation\n\nThese helper routines supply most of the virtqueue_ops for hypervisors\nwhich want to use a ring for virtio. Unlike the previous lguest\nimplementation:\n\n1) The rings are variable sized (2^n-1 elements).\n2) They have an unfortunate limit of 65535 bytes per sg element.\n3) The page numbers are always 64 bit (PAE anyone?)\n4) They no longer place used[] on a separate page, just a separate\n cacheline.\n5) We do a modulo on a variable. We could be tricky if we cared.\n6) Interrupts and notifies are suppressed using flags within the rings.\n\nUsers need only get the ring pages and provide a notify hook (KVM\nwants the guest to allocate the rings, lguest does it sanely).\n\nSigned-off-by: Rusty Russell \u003crusty@rustcorp.com.au\u003e\nCc: Dor Laor \u003cdor.laor@qumranet.com\u003e\n" }, { "commit": "b01d9f2863349b0e041b90c3c86a998ee0fed2b0", "tree": "8789a06631a0ee502c58388d12c230eb4a2059b2", "parents": [ "31610434bc3523c0b01a10917a1185096a03c4c8" ], "author": { "name": "Rusty Russell", "email": "rusty@rustcorp.com.au", "time": "Mon Oct 22 11:03:39 2007 +1000" }, "committer": { "name": "Rusty Russell", "email": "rusty@rustcorp.com.au", "time": "Tue Oct 23 15:49:55 2007 +1000" }, "message": "Module autoprobing support for virtio drivers.\n\nThis adds the logic to convert the virtio ids into module aliases, and\nincludes a modalias entry in sysfs and the env var to make probing work.\n\nSigned-off-by: Rusty Russell \u003crusty@rustcorp.com.au\u003e\n" }, { "commit": "ec3d41c4db4c21164332826ea8d812f94f2f6886", "tree": "9b947e900745cfcc4df7409c6ba5583428964215", "parents": [ "47436aa4ad054c1c7c8231618e86ebd9305308dc" ], "author": { "name": "Rusty Russell", "email": "rusty@rustcorp.com.au", "time": "Mon Oct 22 11:03:36 2007 +1000" }, "committer": { "name": "Rusty Russell", "email": "rusty@rustcorp.com.au", "time": "Tue Oct 23 15:49:54 2007 +1000" }, "message": "Virtio interface\n\nThis attempts to implement a \"virtual I/O\" layer which should allow\ncommon drivers to be efficiently used across most virtual I/O\nmechanisms. It will no-doubt need further enhancement.\n\nThe virtio drivers add buffers to virtio queues; as the buffers are consumed\nthe driver \"interrupt\" callbacks are invoked.\n\nThere is also a generic implementation of config space which drivers can query\nto get setup information from the host.\n\nSigned-off-by: Rusty Russell \u003crusty@rustcorp.com.au\u003e\nCc: Dor Laor \u003cdor.laor@qumranet.com\u003e\nCc: Arnd Bergmann \u003carnd@arndb.de\u003e\n" } ] }