)]}' { "log": [ { "commit": "4e77ae3e105d28aa9410585715d83818f0abe871", "tree": "4ba47b6741a1d941908b4d73394ffbbd4a37ac73", "parents": [ "b8ce33590687888ebb900d09557b8807c4539022" ], "author": { "name": "Thomas Gleixner", "email": "tglx@linutronix.de", "time": "Fri Oct 12 23:04:07 2007 +0200" }, "committer": { "name": "Thomas Gleixner", "email": "tglx@inhelltoy.tec.linutronix.de", "time": "Fri Oct 12 23:04:07 2007 +0200" }, "message": "x86: Fix irq0 / local apic timer accounting\n\nThe clock events merge introduced a change to the nmi watchdog code to\nhandle the not longer increasing local apic timer count in the\nbroadcast mode. This is fine for UP, but on SMP it pampers over a\nstuck CPU which is not handling the broadcast interrupt due to the\nunconditional sum up of local apic timer count and irq0 count.\n\nTo cover all cases we need to keep track on which CPU irq0 is\nhandled. In theory this is CPU#0 due to the explicit disabling of irq\nbalancing for irq0, but there are systems which ignore this on the\nhardware level. The per cpu irq0 accounting allows us to remove the\nirq0 to CPU0 binding as well.\n\nAdd a per cpu counter for irq0 and evaluate this instead of the global\nirq0 count in the nmi watchdog code.\n\nSigned-off-by: Thomas Gleixner \u003ctglx@linutronix.de\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Arjan van de Ven \u003carjan@linux.intel.com\u003e\n\n" }, { "commit": "96a388de5dc53a8b234b3fd41f3ae2cedc9ffd42", "tree": "d947a467aa2da3140279617bc4b9b101640d7bf4", "parents": [ "27bd0c955648646abf2a353a8371d28c37bcd982" ], "author": { "name": "Thomas Gleixner", "email": "tglx@linutronix.de", "time": "Thu Oct 11 11:20:03 2007 +0200" }, "committer": { "name": "Thomas Gleixner", "email": "tglx@linutronix.de", "time": "Thu Oct 11 11:20:03 2007 +0200" }, "message": "i386/x86_64: move headers to include/asm-x86\n\nMove the headers to include/asm-x86 and fixup the\nheader install make rules\n\nSigned-off-by: Thomas Gleixner \u003ctglx@linutronix.de\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "9446868b5383eb87f76b2d4389dea4bb968a6657", "tree": "d253d9a0ae99c77f43ca271019fcbdbfd349b665", "parents": [ "8c131af1db510793f87dc43edbc8950a35370df3" ], "author": { "name": "Andi Kleen", "email": "ak@suse.de", "time": "Tue Nov 14 16:57:46 2006 +0100" }, "committer": { "name": "Andi Kleen", "email": "andi@basil.nowhere.org", "time": "Tue Nov 14 16:57:46 2006 +0100" }, "message": "[PATCH] x86-64: Fix race in exit_idle\n\nWhen another interrupt happens in exit_idle the exit idle notifier\ncould be called an incorrect number of times.\n\nAdd a test_and_clear_bit_pda and use it handle the bit\natomically against interrupts to avoid this.\n\nPointed out by Stephane Eranian\n\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\n" }, { "commit": "a15da49debaf7f09460a886b0ecd08588410715e", "tree": "685ed022695ff03cec167c6690815e08191a803c", "parents": [ "1c9c0a6ca35e9325cea811d734d6ab7352be086b" ], "author": { "name": "Andi Kleen", "email": "ak@suse.de", "time": "Tue Sep 26 10:52:40 2006 +0200" }, "committer": { "name": "Andi Kleen", "email": "andi@basil.nowhere.org", "time": "Tue Sep 26 10:52:40 2006 +0200" }, "message": "[PATCH] Fix idle notifiers\n\nPreviously exit_idle would be called more often than enter_idle\n\nNow instead of using complicated tests just keep track of it\nusing the per CPU variable as a flip flop. I moved the idle state into the\nPDA to make the access more efficient.\n\nOriginal bug report and an initial patch from Stephane Eranian,\nbut redone by AK.\n\nCc: Stephane Eranian \u003ceranian@hpl.hp.com\u003e\n\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\n" }, { "commit": "fd167e42b237e0688005b3dec380eb5a6e5f3585", "tree": "628687df15662dd47781eebd6b227fa823e9924d", "parents": [ "c1a9d41f4f103bfef2ed0bea1e95b3190e39e448" ], "author": { "name": "Andi Kleen", "email": "ak@suse.de", "time": "Tue Sep 26 10:52:40 2006 +0200" }, "committer": { "name": "Andi Kleen", "email": "andi@basil.nowhere.org", "time": "Tue Sep 26 10:52:40 2006 +0200" }, "message": "[PATCH] Define __bad_pda_field as noreturn\n\nThis quietens so warnings about uninitialized use of the return\nvalue of the pda read operations.\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\n" }, { "commit": "c1a9d41f4f103bfef2ed0bea1e95b3190e39e448", "tree": "1b11b8fa27c5b4308a5014453b944ec15c22b1a8", "parents": [ "383d079bfdfcfccd6a720405a510fe325b3e6576" ], "author": { "name": "Andi Kleen", "email": "ak@suse.de", "time": "Tue Sep 26 10:52:40 2006 +0200" }, "committer": { "name": "Andi Kleen", "email": "andi@basil.nowhere.org", "time": "Tue Sep 26 10:52:40 2006 +0200" }, "message": "[PATCH] Reindent macros in pda.h\n\nReindent the macros in x86-64 pda.h, making them much more readable.\nFollows Jeremy\u0027s i386 version of this.\n\nNo functional changes\n\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\n" }, { "commit": "85691f135db78f3548107a0abe383dfab3bc38fa", "tree": "5bde2c801824b4c3d7e7d3def97b6a89ab178a1e", "parents": [ "baf5695dd1a49bb48a3daf08726d7f243f42e97e" ], "author": { "name": "Jeremy Fitzhardinge", "email": "jeremy@goop.org", "time": "Tue Sep 26 10:52:39 2006 +0200" }, "committer": { "name": "Andi Kleen", "email": "andi@basil.nowhere.org", "time": "Tue Sep 26 10:52:39 2006 +0200" }, "message": "[PATCH] Type checking for write_pda()\n\nI just added type checking for assignments the PDA in the i386 PDA code.\nHere\u0027s the x86-64 equivalent. (Obviously this doesn\u0027t contain the latest\nx86-64 PDA change.)\n\nSigned-off-by: Jeremy Fitzhardinge \u003cjeremy@goop.org\u003e\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\n" }, { "commit": "baf5695dd1a49bb48a3daf08726d7f243f42e97e", "tree": "7479fb8562395e168654d931db0ad89ba8ccd39c", "parents": [ "96e540492ab54423f3693958329e095878f1f12b" ], "author": { "name": "Andi Kleen", "email": "ak@suse.de", "time": "Tue Sep 26 10:52:39 2006 +0200" }, "committer": { "name": "Andi Kleen", "email": "andi@basil.nowhere.org", "time": "Tue Sep 26 10:52:39 2006 +0200" }, "message": "[PATCH] Use %c instead of %P modifier in pda access\n\nApparently that is the more official way to get numbers without $ in inline\nassembly\n\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\n" }, { "commit": "0a4254058037eb172758961d0a5b94f4320a1425", "tree": "e9e64daf007952322c7ab0671b2f2f841085c04d", "parents": [ "b62a5c740df1e3d49a97349fce0c6a23f633d7fe" ], "author": { "name": "Arjan van de Ven", "email": "arjan@linux.intel.com", "time": "Tue Sep 26 10:52:38 2006 +0200" }, "committer": { "name": "Andi Kleen", "email": "andi@basil.nowhere.org", "time": "Tue Sep 26 10:52:38 2006 +0200" }, "message": "[PATCH] Add the canary field to the PDA area and the task struct\n\nThis patch adds the per thread cookie field to the task struct and the PDA.\nAlso it makes sure that the PDA value gets the new cookie value at context\nswitch, and that a new task gets a new cookie at task creation time.\n\nSigned-off-by: Arjan van Ven \u003carjan@linux.intel.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nCC: Andi Kleen \u003cak@suse.de\u003e\n" }, { "commit": "29a9af60e2120f874d0c600bf9e27617254a0488", "tree": "90b4309599fa1081d58d0312c94e899eaf18f115", "parents": [ "027a51cef330433ba5924fc92fb25ef48bcfc1a3" ], "author": { "name": "Arjan van de Ven", "email": "arjan@linux.intel.com", "time": "Tue Sep 26 10:52:38 2006 +0200" }, "committer": { "name": "Andi Kleen", "email": "andi@basil.nowhere.org", "time": "Tue Sep 26 10:52:38 2006 +0200" }, "message": "[PATCH] Add comments to the PDA structure to annotate offsets\n\nChange the comments in the pda structure to make the first fields to have\ntheir offset documented and to have the comments aligned.\nThe stack protector series needs a field at offset 40 (gcc ABI); annotate\nupto 40 for that reason.\n\nSigned-off-by: Arjan van de Ven \u003carjan@linux.intel.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nCC: Andi Kleen \u003cak@suse.de\u003e\n" }, { "commit": "f574164491d00d28b727d713685fb5edc9138200", "tree": "7ab1a5a2257e27824cf3762fcf276840259deceb", "parents": [ "575400d1b483fbe9e03c68758059bfaf4e4768d1" ], "author": { "name": "Keith Owens", "email": "kaos@ocs.com.au", "time": "Tue Sep 26 10:52:38 2006 +0200" }, "committer": { "name": "Andi Kleen", "email": "andi@basil.nowhere.org", "time": "Tue Sep 26 10:52:38 2006 +0200" }, "message": "[PATCH] Remove most of the special cases for the debug IST stack\n\nRemove most of the special cases for the debug IST stack. This is a\nfollow on clean up patch, it requires the bug fix patch that adds\norig_ist.\n\nSigned-off-by: Keith Owens \u003ckaos@ocs.com.au\u003e\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\n" }, { "commit": "53ee11ae0d73f28029a5f0d991bc4dcd7c817e7a", "tree": "c0a025cc592d516674bb1d8a0046bf281b6d1724", "parents": [ "80d2679cbc8e170011c9649fb8fb684ffd7e5c8f" ], "author": { "name": "Andi Kleen", "email": "ak@suse.de", "time": "Tue Sep 26 10:52:38 2006 +0200" }, "committer": { "name": "Andi Kleen", "email": "andi@basil.nowhere.org", "time": "Tue Sep 26 10:52:38 2006 +0200" }, "message": "[PATCH] Optimize PDA accesses slightly\n\nBased on a idea by Jeremy Fitzhardinge:\n\nReplace the volatiles and memory clobbers in the PDA access with\ntelling gcc about access to a proxy PDA structure that doesn\u0027t\nactually exist. But the dummy accesses give a defined ordering for\nread/write accesses.\n\nAlso add some memory barriers to the early GS initialization to\nmake sure no PDA access is moved before it.\n\nAdvantage is some .text savings (probably most from better\ncode for accessing \"current\"):\n\n text data bss dec hex filename\n4845647 1223688 615864 6685199 66020f vmlinux\n4837780 1223688 615864 6677332 65e354 vmlinux-pda\n\n1.2% smaller code\n\nCc: Jeremy Fitzhardinge \u003cjeremy@goop.org\u003e\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\n" }, { "commit": "df92004ce60a0bb60c8315903c0765873c34a702", "tree": "420782e1621f8d5d44dd8b4ecc640cbcfc0c4131", "parents": [ "01d4bed417b5943577e9290fbf672ea9a449dc46" ], "author": { "name": "Arjan van de Ven", "email": "arjan@linux.intel.com", "time": "Sat Mar 25 16:31:01 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Sat Mar 25 09:10:56 2006 -0800" }, "message": "[PATCH] x86_64: Reorder one field of the PDA to reduce padding\n\nThis reorders the mmu_state int in the pda, such that there is no more\npadding (there currently is 4 bytes of padding). Boot tested.\n\nSigned-off-by: Arjan van de Ven \u003carjan@linux.intel.com\u003e\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "365ba9179f84244d2ffa98e46ae3cddfeb2ef6ff", "tree": "b84be7f9f929d8084fa76af2618877439baee841", "parents": [ "df79efde82952edc653fa6eb1338a82b87aa0585" ], "author": { "name": "Ravikiran G Thirumalai", "email": "kiran@scalex86.org", "time": "Wed Jan 11 22:45:42 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:04:59 2006 -0800" }, "message": "[PATCH] x86_64: Allocate PDAs in the local node\n\nPatch uses a static PDA array early at boot and reallocates processor PDA\nwith node local memory when kmalloc is ready, just before pda_init.\nThe boot_cpu_pda is needed since the cpu_pda is used even before pda_init for\nthat cpu is called (to set the static per-cpu areas offset table etc)\n\nSigned-off-by: Ravikiran Thirumalai \u003ckiran@scalex86.org\u003e\nSigned-off-by: Shai Fultheim \u003cshai@scalex86.org\u003e\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "df79efde82952edc653fa6eb1338a82b87aa0585", "tree": "67abb221cf834c3a7766c406aae1e55aa31b6bcf", "parents": [ "05b3cbd8bb98736387df8a2e1efe311b1fb4d2ad" ], "author": { "name": "Ravikiran G Thirumalai", "email": "kiran@scalex86.org", "time": "Wed Jan 11 22:45:39 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:04:59 2006 -0800" }, "message": "[PATCH] x86_64: Node local pda take 2 -- cpu_pda preparation\n\nHelper patch to change cpu_pda users to use macros to access cpu_pda\ninstead of the cpu_pda[] array.\n\nSigned-off-by: Ravikiran Thirumalai \u003ckiran@scalex86.org\u003e\nSigned-off-by: Shai Fultheim \u003cshai@scalex86.org\u003e\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "b556b35e98ad2b9174a7a623d152cdf412d1a999", "tree": "10f99d70e719fba811dee85d2f3a82b26d7a4ce8", "parents": [ "ed8388a5d9db0445322f86ee8381b0f04a2057ee" ], "author": { "name": "Jan Beulich", "email": "jbeulich@novell.com", "time": "Wed Jan 11 22:43:00 2006 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Jan 11 19:01:13 2006 -0800" }, "message": "[PATCH] x86_64: Move int 3 handler to debug stack and allow to increase it.\n\nThis\n- switches the INT3 handler to run on an IST stack (to cope with\n breakpoints set by a kernel debugger on places where the kernel\u0027s\n %gs base hasn\u0027t been set up, yet); the IST stack used is shared with\n the INT1 handler\u0027s\n[AK: this also allows setting a kprobe on the interrupt/exception entry\npoints]\n- allows nesting of INT1/INT3 handlers so that one can, with a kernel\n debugger, debug (at least) the user-mode portions of the INT1/INT3\n handling; the nesting isn\u0027t actively enabled here since a kernel-\n debugger-free kernel doesn\u0027t need it\n\nSigned-Off-By: Jan Beulich \u003cjbeulich@novell.com\u003e\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "69d81fcde7797342417591ba7affb372b9c86eae", "tree": "97fbc73fd20f8ebc313b2bc41367a8efe36c2c3d", "parents": [ "50895c5d76e15d8af480eff1aaab5770cabbc2c2" ], "author": { "name": "Andi Kleen", "email": "ak@suse.de", "time": "Sat Nov 05 17:25:53 2005 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Mon Nov 14 19:55:14 2005 -0800" }, "message": "[PATCH] x86_64: Speed up numa_node_id by putting it directly into the PDA\n\nNot go from the CPU number to an mapping array.\nMode number is often used now in fast paths.\n\nThis also adds a generic numa_node_id to all the topology includes\n\nSuggested by Eric Dumazet\n\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "3f74478b5fd7263e9311cdb320923d599c73a792", "tree": "d61962b55cc7bae06cf872f35d8ab3ae753c70c1", "parents": [ "459192c92cde49d1a2f721c90adf45d774c2dcf5" ], "author": { "name": "Andi Kleen", "email": "ak@suse.de", "time": "Mon Sep 12 18:49:24 2005 +0200" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Mon Sep 12 10:49:58 2005 -0700" }, "message": "[PATCH] x86-64: Some cleanup and optimization to the processor data area.\n\n- Remove unused irqrsp field\n- Remove pda-\u003eme\n- Optimize set_softirq_pending slightly\n\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "b91691164be174b780f5c1bb145a7ab5d33fce2f", "tree": "be33a63344b027ce0e68c75c536895184afab7a0", "parents": [ "8675b1a454016c7c50215552ea5c5c4a2413fda0" ], "author": { "name": "Andi Kleen", "email": "ak@suse.de", "time": "Mon Sep 12 18:49:24 2005 +0200" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Mon Sep 12 10:49:56 2005 -0700" }, "message": "[PATCH] x86-64: Don\u0027t cache align PDA on UP builds\n\nSuggested by someone I forgot who sorry.\n\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "1da177e4c3f41524e886b7f1b8a0c1fc7321cac2", "tree": "0bba044c4ce775e45a88a51686b5d9f90697ea9d", "parents": [], "author": { "name": "Linus Torvalds", "email": "torvalds@ppc970.osdl.org", "time": "Sat Apr 16 15:20:36 2005 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@ppc970.osdl.org", "time": "Sat Apr 16 15:20:36 2005 -0700" }, "message": "Linux-2.6.12-rc2\n\nInitial git repository build. I\u0027m not bothering with the full history,\neven though we have it. We can create a separate \"historical\" git\narchive of that later if we want to, and in the meantime it\u0027s about\n3.2GB when imported into git - space that would just make the early\ngit days unnecessarily complicated, when we don\u0027t have a lot of good\ninfrastructure for it.\n\nLet it rip!\n" } ] }