)]}' { "log": [ { "commit": "e1e72965ec2c02db99b415cd06c17ea90767e3a4", "tree": "94e43aac35bdc33220e64f285b72b3b2b787fd57", "parents": [ "568a17ffce2eeceae0cd9fc37e97cbad12f70278" ], "author": { "name": "Rusty Russell", "email": "rusty@rustcorp.com.au", "time": "Thu Oct 25 15:02:50 2007 +1000" }, "committer": { "name": "Rusty Russell", "email": "rusty@rustcorp.com.au", "time": "Thu Oct 25 15:02:50 2007 +1000" }, "message": "lguest: documentation update\n\nWent through the documentation doing typo and content fixes. This\npatch contains only comment and whitespace changes.\n\nSigned-off-by: Rusty Russell \u003crusty@rustcorp.com.au\u003e\n\n" }, { "commit": "47436aa4ad054c1c7c8231618e86ebd9305308dc", "tree": "a9ba6e0521f9116442144a86e781a3164ec86094", "parents": [ "c18acd73ffc209def08003a1927473096f66c5ad" ], "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": "Boot with virtual \u003d\u003d physical to get closer to native Linux.\n\n1) This allows us to get alot closer to booting bzImages.\n\n2) It means we don\u0027t have to know page_offset.\n\n3) The Guest needs to modify the boot pagetables to create the\n PAGE_OFFSET mapping before jumping to C code.\n\n4) guest_pa() walks the page tables rather than using page_offset.\n\n5) We don\u0027t use page_offset to figure out whether to emulate: it was\n always kinda quesationable, and won\u0027t work for instructions done\n before remapping (bzImage unpacking in particular).\n\n6) We still want the kernel address for tlb flushing: have the initial\n hypercall give us that, too.\n\nSigned-off-by: Rusty Russell \u003crusty@rustcorp.com.au\u003e\n" }, { "commit": "c18acd73ffc209def08003a1927473096f66c5ad", "tree": "dd8e292ac8ca90b061b7e37ad6947231ced566e3", "parents": [ "ee3db0f2b6053b65f3b70253f5f810d9a3d67b28" ], "author": { "name": "Rusty Russell", "email": "rusty@rustcorp.com.au", "time": "Mon Oct 22 11:03:35 2007 +1000" }, "committer": { "name": "Rusty Russell", "email": "rusty@rustcorp.com.au", "time": "Tue Oct 23 15:49:53 2007 +1000" }, "message": "Allow guest to specify syscall vector to use.\n\n(Based on Ron Minnich\u0027s LGUEST_PLAN9_SYSCALL patch).\n\nThis patch allows Guests to specify what system call vector they want,\nand we try to reserve it. We only allow one non-Linux system call\nvector, to try to avoid DoS on the Host.\n\nSigned-off-by: Rusty Russell \u003crusty@rustcorp.com.au\u003e\n" }, { "commit": "47aee45ae3c708ab678e09abfba0efaf6ca0e87a", "tree": "068d85a5bad5436268abbd5b090d67b2ce22dc21", "parents": [ "d612cde060a005c1effb13d0f665448a04ce5f67" ], "author": { "name": "Jes Sorensen", "email": "jes@sgi.com", "time": "Mon Oct 22 11:03:33 2007 +1000" }, "committer": { "name": "Rusty Russell", "email": "rusty@rustcorp.com.au", "time": "Tue Oct 23 15:49:52 2007 +1000" }, "message": "lguest.h declares a struct timespec, make it include linux/time.h\n\nSigned-off-by: Jes Sorensen \u003cjes@sgi.com\u003e\nSigned-off-by: Rusty Russell \u003crusty@rustcorp.com.au\u003e\n" }, { "commit": "b410e7b1499c49513cab18275db8a8ab549d9e09", "tree": "8a71fa34660f5ccc9d71677137c5ae211a38bbf2", "parents": [ "cc6d4fbcef328acdc9fa7023e69f39f753f72fe1" ], "author": { "name": "Jes Sorensen", "email": "jes@sgi.com", "time": "Mon Oct 22 11:03:31 2007 +1000" }, "committer": { "name": "Rusty Russell", "email": "rusty@rustcorp.com.au", "time": "Tue Oct 23 15:49:52 2007 +1000" }, "message": "Make hypercalls arch-independent.\n\nClean up the hypercall code to make the code in hypercalls.c\narchitecture independent. First process the common hypercalls and\nthen call lguest_arch_do_hcall() if the call hasn\u0027t been handled.\nRename struct hcall_ring to hcall_args.\n\nThis patch requires the previous patch which reorganize the layout of\nstruct lguest_regs on i386 so they match the layout of struct\nhcall_args.\n\nSigned-off-by: Jes Sorensen \u003cjes@sgi.com\u003e\nSigned-off-by: Rusty Russell \u003crusty@rustcorp.com.au\u003e\n" }, { "commit": "48245cc0708d49d1d0566b9fa617ad6c5f4c6934", "tree": "b396fd2d1ab185aab20894570e7e84bd4f656355", "parents": [ "3c6b5bfa3cf3b4057788e08482a468cc3bc00780" ], "author": { "name": "Rusty Russell", "email": "rusty@rustcorp.com.au", "time": "Mon Oct 22 11:03:27 2007 +1000" }, "committer": { "name": "Rusty Russell", "email": "rusty@rustcorp.com.au", "time": "Tue Oct 23 15:49:51 2007 +1000" }, "message": "Remove fixed limit on number of guests, and lguests array.\n\nBack when we had all the Guest state in the switcher, we had a fixed\narray of them. This is no longer necessary.\n\nIf we switch the network code to using random_ether_addr (46 bits is\nenough to avoid clashes), we can get rid of the concept of \"guest id\"\naltogether.\n\nSigned-off-by: Rusty Russell \u003crusty@rustcorp.com.au\u003e\n" }, { "commit": "c37ae93d597fc63bae979db76b527dcc7740dc9d", "tree": "2ac25ff96a42593b536d4cdb10f5cbfdb96ef347", "parents": [ "05aa026a62d0fe0b4664a01d1537984b12567e7c" ], "author": { "name": "Jes Sorensen", "email": "jes@sgi.com", "time": "Mon Oct 22 10:56:26 2007 +1000" }, "committer": { "name": "Rusty Russell", "email": "rusty@rustcorp.com.au", "time": "Tue Oct 23 15:49:49 2007 +1000" }, "message": "Move lguest hcalls to arch-specific header\n\nMove architecture specific portion of lg_hcall code to asm-i386/lg_hcall.h\nand have it included from linux/lguest.h.\n\n[Changed to asm-i386/lguest_hcall.h so documentation finds it -RR]\n\nSigned-off-by: Jes Sorensen \u003cjes@sgi.com\u003e\nSigned-off-by: Rusty Russell \u003crusty@rustcorp.com.au\u003e\nCc: Jes Sorensen \u003cjes@sgi.com\u003e\n" }, { "commit": "6c8dca5d53f95009d4fff00195bf38f277dc4366", "tree": "60cc83cf949d6e598e6dc80dc668aebd42c65540", "parents": [ "a8a11f06973fa63ad692a8f97694cb5eeb70b3f3" ], "author": { "name": "Rusty Russell", "email": "rusty@rustcorp.com.au", "time": "Fri Jul 27 13:42:52 2007 +1000" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Sat Jul 28 19:54:33 2007 -0700" }, "message": "Provide timespec to guests rather than jiffies clock.\n\nA non-periodic clock_event_device and the \"jiffies\" clock don\u0027t mix well:\ntick_handle_periodic() can go into an infinite loop.\n\nCurrently lguest guests use the jiffies clock when the TSC is\nunusable. Instead, make the Host write the current time into the lguest\npage on every interrupt. This doesn\u0027t cost much but is more precise\nand at least as accurate as the jiffies clock. It also gets rid of\nthe GET_WALLCLOCK hypercall.\n\nAlso, delay setting sched_clock until our clock is set up, otherwise\nthe early printk timestamps can go backwards (not harmful, just ugly).\n\nSigned-off-by: Rusty Russell \u003crusty@rustcorp.com.au\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "b2b47c214f4e85ce3968120d42e8b18eccb4f4e3", "tree": "f77d6898a769b8e0fcb552207e87f273bdc19f09", "parents": [ "f938d2c892db0d80d144253d4a7b7083efdbedeb" ], "author": { "name": "Rusty Russell", "email": "rusty@rustcorp.com.au", "time": "Thu Jul 26 10:41:02 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Thu Jul 26 11:35:17 2007 -0700" }, "message": "lguest: documentation II: Guest\n\nDocumentation: The Guest\n\nSigned-off-by: 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": "d7e28ffe6c74416b54345d6004fd0964c115b12c", "tree": "844beb4f400d5400098538e0c1e5f12d20a9504a", "parents": [ "07ad157f6e5d228be78acd5cea0291e5d0360398" ], "author": { "name": "Rusty Russell", "email": "rusty@rustcorp.com.au", "time": "Thu Jul 19 01:49:23 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Thu Jul 19 10:04:52 2007 -0700" }, "message": "lguest: the host code\n\nThis is the code for the \"lg.ko\" module, which allows lguest guests to\nbe launched.\n\n[akpm@linux-foundation.org: update for futex-new-private-futexes]\n[akpm@linux-foundation.org: build fix]\n[jmorris@namei.org: lguest: use hrtimers]\n[akpm@linux-foundation.org: x86_64 build fix]\nSigned-off-by: Rusty Russell \u003crusty@rustcorp.com.au\u003e\nCc: Andi Kleen \u003cak@suse.de\u003e\nCc: Eric Dumazet \u003cdada1@cosmosbay.com\u003e\nCc: Thomas Gleixner \u003ctglx@linutronix.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "07ad157f6e5d228be78acd5cea0291e5d0360398", "tree": "87180c2d1aa53857f46d1dc293e08c0fbea0608a", "parents": [ "5992b6dac0d23a2b51a1ccbaf8f1a2e62097b12b" ], "author": { "name": "Rusty Russell", "email": "rusty@rustcorp.com.au", "time": "Thu Jul 19 01:49:22 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Thu Jul 19 10:04:52 2007 -0700" }, "message": "lguest: the guest code\n\nlguest is a simple hypervisor for Linux on Linux. Unlike kvm it doesn\u0027t need\nVT/SVM hardware. Unlike Xen it\u0027s simply \"modprobe and go\". Unlike both, it\u0027s\n5000 lines and self-contained.\n\nPerformance is ok, but not great (-30% on kernel compile). But given its\nhackability, I expect this to improve, along with the paravirt_ops code which\nit supplies a complete example for. There\u0027s also a 64-bit version being\nworked on and other craziness.\n\nBut most of all, lguest is awesome fun! Too much of the kernel is a big ball\nof hair. lguest is simple enough to dive into and hack, plus has some warts\nwhich scream \"fork me!\".\n\nThis patch:\n\nThis is the code and headers required to make an i386 kernel an lguest guest.\n\nSigned-off-by: Rusty Russell \u003crusty@rustcorp.com.au\u003e\nCc: Andi Kleen \u003cak@suse.de\u003e\nCc: Jeremy Fitzhardinge \u003cjeremy@goop.org\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" } ] }