)]}' { "log": [ { "commit": "e3f2ddeac718c768fdac4b7fe69d465172f788a8", "tree": "5428532dc6c87710c35a71858425f6d726f0e44c", "parents": [ "627371d73cdd04ed23fe098755b4f855138ad9e0" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Sat Jul 29 05:17:57 2006 +0200" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Fri Jul 28 21:02:00 2006 -0700" }, "message": "[PATCH] pi-futex: robust-futex exit\n\nFix robust PI-futexes to be properly unlocked on unexpected exit.\n\nFor this to work the kernel has to know whether a futex is a PI or a\nnon-PI one, because the semantics are different. Since the space in\nrelevant glibc data structures is extremely scarce, the best solution is\nto encode the \u0027PI\u0027 information in bit 0 of the robust list pointer.\nExisting (non-PI) glibc robust futexes have this bit always zero, so the\nABI is kept. New glibc with PI-robust-futexes will set this bit.\n\nFurther fixes from Thomas Gleixner \u003ctglx@linutronix.de\u003e\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Ulrich Drepper \u003cdrepper@redhat.com\u003e\nSigned-off-by: Thomas Gleixner \u003ctglx@linutronix.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "c87e2837be82df479a6bae9f155c43516d2feebc", "tree": "ad6ab35f0b78f71abaa7b05185e9e3f97809c6de", "parents": [ "0cdbee9920fb37eb2dc49b860c2b28862d647adc" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Tue Jun 27 02:54:58 2006 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Tue Jun 27 17:32:47 2006 -0700" }, "message": "[PATCH] pi-futex: futex_lock_pi/futex_unlock_pi support\n\nThis adds the actual pi-futex implementation, based on rt-mutexes.\n\n[dino@in.ibm.com: fix an oops-causing race]\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Thomas Gleixner \u003ctglx@linutronix.de\u003e\nSigned-off-by: Arjan van de Ven \u003carjan@linux.intel.com\u003e\nSigned-off-by: Dinakar Guniguntala \u003cdino@in.ibm.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "e2970f2fb6950183a34e8545faa093eb49d186e1", "tree": "a4035274368d846488a3b0152925502c06b064b0", "parents": [ "66e5393a78b3fcca63e7748e38221dcca61c4aab" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Tue Jun 27 02:54:47 2006 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Tue Jun 27 17:32:46 2006 -0700" }, "message": "[PATCH] pi-futex: futex code cleanups\n\nWe are pleased to announce \"lightweight userspace priority inheritance\" (PI)\nsupport for futexes. The following patchset and glibc patch implements it,\nontop of the robust-futexes patchset which is included in 2.6.16-mm1.\n\nWe are calling it lightweight for 3 reasons:\n\n - in the user-space fastpath a PI-enabled futex involves no kernel work\n (or any other PI complexity) at all. No registration, no extra kernel\n calls - just pure fast atomic ops in userspace.\n\n - in the slowpath (in the lock-contention case), the system call and\n scheduling pattern is in fact better than that of normal futexes, due to\n the \u0027integrated\u0027 nature of FUTEX_LOCK_PI. [more about that further down]\n\n - the in-kernel PI implementation is streamlined around the mutex\n abstraction, with strict rules that keep the implementation relatively\n simple: only a single owner may own a lock (i.e. no read-write lock\n support), only the owner may unlock a lock, no recursive locking, etc.\n\n Priority Inheritance - why, oh why???\n -------------------------------------\n\nMany of you heard the horror stories about the evil PI code circling Linux for\nyears, which makes no real sense at all and is only used by buggy applications\nand which has horrible overhead. Some of you have dreaded this very moment,\nwhen someone actually submits working PI code ;-)\n\nSo why would we like to see PI support for futexes?\n\nWe\u0027d like to see it done purely for technological reasons. We dont think it\u0027s\na buggy concept, we think it\u0027s useful functionality to offer to applications,\nwhich functionality cannot be achieved in other ways. We also think it\u0027s the\nright thing to do, and we think we\u0027ve got the right arguments and the right\nnumbers to prove that. We also believe that we can address all the\ncounter-arguments as well. For these reasons (and the reasons outlined below)\nwe are submitting this patch-set for upstream kernel inclusion.\n\nWhat are the benefits of PI?\n\n The short reply:\n ----------------\n\nUser-space PI helps achieving/improving determinism for user-space\napplications. In the best-case, it can help achieve determinism and\nwell-bound latencies. Even in the worst-case, PI will improve the statistical\ndistribution of locking related application delays.\n\n The longer reply:\n -----------------\n\nFirstly, sharing locks between multiple tasks is a common programming\ntechnique that often cannot be replaced with lockless algorithms. As we can\nsee it in the kernel [which is a quite complex program in itself], lockless\nstructures are rather the exception than the norm - the current ratio of\nlockless vs. locky code for shared data structures is somewhere between 1:10\nand 1:100. Lockless is hard, and the complexity of lockless algorithms often\nendangers to ability to do robust reviews of said code. I.e. critical RT\napps often choose lock structures to protect critical data structures, instead\nof lockless algorithms. Furthermore, there are cases (like shared hardware,\nor other resource limits) where lockless access is mathematically impossible.\n\nMedia players (such as Jack) are an example of reasonable application design\nwith multiple tasks (with multiple priority levels) sharing short-held locks:\nfor example, a highprio audio playback thread is combined with medium-prio\nconstruct-audio-data threads and low-prio display-colory-stuff threads. Add\nvideo and decoding to the mix and we\u0027ve got even more priority levels.\n\nSo once we accept that synchronization objects (locks) are an unavoidable fact\nof life, and once we accept that multi-task userspace apps have a very fair\nexpectation of being able to use locks, we\u0027ve got to think about how to offer\nthe option of a deterministic locking implementation to user-space.\n\nMost of the technical counter-arguments against doing priority inheritance\nonly apply to kernel-space locks. But user-space locks are different, there\nwe cannot disable interrupts or make the task non-preemptible in a critical\nsection, so the \u0027use spinlocks\u0027 argument does not apply (user-space spinlocks\nhave the same priority inversion problems as other user-space locking\nconstructs). Fact is, pretty much the only technique that currently enables\ngood determinism for userspace locks (such as futex-based pthread mutexes) is\npriority inheritance:\n\nCurrently (without PI), if a high-prio and a low-prio task shares a lock [this\nis a quite common scenario for most non-trivial RT applications], even if all\ncritical sections are coded carefully to be deterministic (i.e. all critical\nsections are short in duration and only execute a limited number of\ninstructions), the kernel cannot guarantee any deterministic execution of the\nhigh-prio task: any medium-priority task could preempt the low-prio task while\nit holds the shared lock and executes the critical section, and could delay it\nindefinitely.\n\n Implementation:\n ---------------\n\nAs mentioned before, the userspace fastpath of PI-enabled pthread mutexes\ninvolves no kernel work at all - they behave quite similarly to normal\nfutex-based locks: a 0 value means unlocked, and a value\u003d\u003dTID means locked.\n(This is the same method as used by list-based robust futexes.) Userspace uses\natomic ops to lock/unlock these mutexes without entering the kernel.\n\nTo handle the slowpath, we have added two new futex ops:\n\n FUTEX_LOCK_PI\n FUTEX_UNLOCK_PI\n\nIf the lock-acquire fastpath fails, [i.e. an atomic transition from 0 to TID\nfails], then FUTEX_LOCK_PI is called. The kernel does all the remaining work:\nif there is no futex-queue attached to the futex address yet then the code\nlooks up the task that owns the futex [it has put its own TID into the futex\nvalue], and attaches a \u0027PI state\u0027 structure to the futex-queue. The pi_state\nincludes an rt-mutex, which is a PI-aware, kernel-based synchronization\nobject. The \u0027other\u0027 task is made the owner of the rt-mutex, and the\nFUTEX_WAITERS bit is atomically set in the futex value. Then this task tries\nto lock the rt-mutex, on which it blocks. Once it returns, it has the mutex\nacquired, and it sets the futex value to its own TID and returns. Userspace\nhas no other work to perform - it now owns the lock, and futex value contains\nFUTEX_WAITERS|TID.\n\nIf the unlock side fastpath succeeds, [i.e. userspace manages to do a TID -\u003e\n0 atomic transition of the futex value], then no kernel work is triggered.\n\nIf the unlock fastpath fails (because the FUTEX_WAITERS bit is set), then\nFUTEX_UNLOCK_PI is called, and the kernel unlocks the futex on the behalf of\nuserspace - and it also unlocks the attached pi_state-\u003ert_mutex and thus wakes\nup any potential waiters.\n\nNote that under this approach, contrary to other PI-futex approaches, there is\nno prior \u0027registration\u0027 of a PI-futex. [which is not quite possible anyway,\ndue to existing ABI properties of pthread mutexes.]\n\nAlso, under this scheme, \u0027robustness\u0027 and \u0027PI\u0027 are two orthogonal properties\nof futexes, and all four combinations are possible: futex, robust-futex,\nPI-futex, robust+PI-futex.\n\n glibc support:\n --------------\n\nUlrich Drepper and Jakub Jelinek have written glibc support for PI-futexes\n(and robust futexes), enabling robust and PI (PTHREAD_PRIO_INHERIT) POSIX\nmutexes. (PTHREAD_PRIO_PROTECT support will be added later on too, no\nadditional kernel changes are needed for that). [NOTE: The glibc patch is\nobviously inofficial and unsupported without matching upstream kernel\nfunctionality.]\n\nthe patch-queue and the glibc patch can also be downloaded from:\n\n http://redhat.com/~mingo/PI-futex-patches/\n\nMany thanks go to the people who helped us create this kernel feature: Steven\nRostedt, Esben Nielsen, Benedikt Spranger, Daniel Walker, John Cooper, Arjan\nvan de Ven, Oleg Nesterov and others. Credits for related prior projects goes\nto Dirk Grambow, Inaky Perez-Gonzalez, Bill Huey and many others.\n\nClean up the futex code, before adding more features to it:\n\n - use u32 as the futex field type - that\u0027s the ABI\n - use __user and pointers to u32 instead of unsigned long\n - code style / comment style cleanups\n - rename hash-bucket name from \u0027bh\u0027 to \u0027hb\u0027.\n\nI checked the pre and post futex.o object files to make sure this\npatch has no code effects.\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Thomas Gleixner \u003ctglx@linutronix.de\u003e\nSigned-off-by: Arjan van de Ven \u003carjan@linux.intel.com\u003e\nCc: Ulrich Drepper \u003cdrepper@redhat.com\u003e\nCc: Jakub Jelinek \u003cjakub@redhat.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "76b81e2b0e2241accebcc68e126bc5ab958661b9", "tree": "0d99cdc838cc2e7a5c383a56ec707ac739739d2c", "parents": [ "8f17d3a5049d32392b79925c73a0cf99ce6d5af0" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Mar 27 01:16:28 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Mon Mar 27 08:44:50 2006 -0800" }, "message": "[PATCH] lightweight robust futexes updates 2\n\nfutex.h updates:\n\n- get rid of FUTEX_OWNER_PENDING - it\u0027s not used\n- reduce ROBUST_LIST_LIMIT to a saner value\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "8f17d3a5049d32392b79925c73a0cf99ce6d5af0", "tree": "3c2aa0cbe337684d353dd2cfb0c177b4ae15217c", "parents": [ "8fdd6c6df7889dc89df3d9fe0f5bbe6733e39f48" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Mar 27 01:16:27 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Mon Mar 27 08:44:49 2006 -0800" }, "message": "[PATCH] lightweight robust futexes updates\n\n- fix: initialize the robust list(s) to NULL in copy_process.\n\n- doc update\n\n- cleanup: rename _inuser to _inatomic\n\n- __user cleanups and other small cleanups\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Thomas Gleixner \u003ctglx@linutronix.de\u003e\nCc: Arjan van de Ven \u003carjan@infradead.org\u003e\nCc: Ulrich Drepper \u003cdrepper@redhat.com\u003e\nCc: Andi Kleen \u003cak@muc.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "0771dfefc9e538f077d0b43b6dec19a5a67d0e70", "tree": "696267e69228b7406b337f9651dedc75055a589e", "parents": [ "e9056f13bfcdd054a0c3d730e4e096748d8a363a" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Mar 27 01:16:22 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Mon Mar 27 08:44:49 2006 -0800" }, "message": "[PATCH] lightweight robust futexes: core\n\nAdd the core infrastructure for robust futexes: structure definitions, the new\nsyscalls and the do_exit() based cleanup mechanism.\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Thomas Gleixner \u003ctglx@linutronix.de\u003e\nSigned-off-by: Arjan van de Ven \u003carjan@infradead.org\u003e\nAcked-by: Ulrich Drepper \u003cdrepper@redhat.com\u003e\nCc: Michael Kerrisk \u003cmtk-manpages@gmx.net\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "4732efbeb997189d9f9b04708dc26bf8613ed721", "tree": "885308bb2b521e52e13aaa8a67c78b2ab3c18cd8", "parents": [ "5b039e681b8c5f30aac9cc04385cc94be45d0823" ], "author": { "name": "Jakub Jelinek", "email": "jakub@redhat.com", "time": "Tue Sep 06 15:16:25 2005 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Wed Sep 07 16:57:17 2005 -0700" }, "message": "[PATCH] FUTEX_WAKE_OP: pthread_cond_signal() speedup\n\nATM pthread_cond_signal is unnecessarily slow, because it wakes one waiter\n(which at least on UP usually means an immediate context switch to one of\nthe waiter threads). This waiter wakes up and after a few instructions it\nattempts to acquire the cv internal lock, but that lock is still held by\nthe thread calling pthread_cond_signal. So it goes to sleep and eventually\nthe signalling thread is scheduled in, unlocks the internal lock and wakes\nthe waiter again.\n\nNow, before 2003-09-21 NPTL was using FUTEX_REQUEUE in pthread_cond_signal\nto avoid this performance issue, but it was removed when locks were\nredesigned to the 3 state scheme (unlocked, locked uncontended, locked\ncontended).\n\nFollowing scenario shows why simply using FUTEX_REQUEUE in\npthread_cond_signal together with using lll_mutex_unlock_force in place of\nlll_mutex_unlock is not enough and probably why it has been disabled at\nthat time:\n\nThe number is value in cv-\u003e__data.__lock.\n thr1 thr2 thr3\n0 pthread_cond_wait\n1 lll_mutex_lock (cv-\u003e__data.__lock)\n0 lll_mutex_unlock (cv-\u003e__data.__lock)\n0 lll_futex_wait (\u0026cv-\u003e__data.__futex, futexval)\n0 pthread_cond_signal\n1 lll_mutex_lock (cv-\u003e__data.__lock)\n1 pthread_cond_signal\n2 lll_mutex_lock (cv-\u003e__data.__lock)\n2 lll_futex_wait (\u0026cv-\u003e__data.__lock, 2)\n2 lll_futex_requeue (\u0026cv-\u003e__data.__futex, 0, 1, \u0026cv-\u003e__data.__lock)\n # FUTEX_REQUEUE, not FUTEX_CMP_REQUEUE\n2 lll_mutex_unlock_force (cv-\u003e__data.__lock)\n0 cv-\u003e__data.__lock \u003d 0\n0 lll_futex_wake (\u0026cv-\u003e__data.__lock, 1)\n1 lll_mutex_lock (cv-\u003e__data.__lock)\n0 lll_mutex_unlock (cv-\u003e__data.__lock)\n # Here, lll_mutex_unlock doesn\u0027t know there are threads waiting\n # on the internal cv\u0027s lock\n\nNow, I believe it is possible to use FUTEX_REQUEUE in pthread_cond_signal,\nbut it will cost us not one, but 2 extra syscalls and, what\u0027s worse, one of\nthese extra syscalls will be done for every single waiting loop in\npthread_cond_*wait.\n\nWe would need to use lll_mutex_unlock_force in pthread_cond_signal after\nrequeue and lll_mutex_cond_lock in pthread_cond_*wait after lll_futex_wait.\n\nAnother alternative is to do the unlocking pthread_cond_signal needs to do\n(the lock can\u0027t be unlocked before lll_futex_wake, as that is racy) in the\nkernel.\n\nI have implemented both variants, futex-requeue-glibc.patch is the first\none and futex-wake_op{,-glibc}.patch is the unlocking inside of the kernel.\n The kernel interface allows userland to specify how exactly an unlocking\noperation should look like (some atomic arithmetic operation with optional\nconstant argument and comparison of the previous futex value with another\nconstant).\n\nIt has been implemented just for ppc*, x86_64 and i?86, for other\narchitectures I\u0027m including just a stub header which can be used as a\nstarting point by maintainers to write support for their arches and ATM\nwill just return -ENOSYS for FUTEX_WAKE_OP. The requeue patch has been\n(lightly) tested just on x86_64, the wake_op patch on ppc64 kernel running\n32-bit and 64-bit NPTL and x86_64 kernel running 32-bit and 64-bit NPTL.\n\nWith the following benchmark on UP x86-64 I get:\n\nfor i in nptl-orig nptl-requeue nptl-wake_op; do echo time elf/ld.so --library-path .:$i /tmp/bench; \\\nfor j in 1 2; do echo ( time elf/ld.so --library-path .:$i /tmp/bench ) 2\u003e\u00261; done; done\ntime elf/ld.so --library-path .:nptl-orig /tmp/bench\nreal 0m0.655s user 0m0.253s sys 0m0.403s\nreal 0m0.657s user 0m0.269s sys 0m0.388s\ntime elf/ld.so --library-path .:nptl-requeue /tmp/bench\nreal 0m0.496s user 0m0.225s sys 0m0.271s\nreal 0m0.531s user 0m0.242s sys 0m0.288s\ntime elf/ld.so --library-path .:nptl-wake_op /tmp/bench\nreal 0m0.380s user 0m0.176s sys 0m0.204s\nreal 0m0.382s user 0m0.175s sys 0m0.207s\n\nThe benchmark is at:\nhttp://sourceware.org/ml/libc-alpha/2005-03/txt00001.txt\nOlder futex-requeue-glibc.patch version is at:\nhttp://sourceware.org/ml/libc-alpha/2005-03/txt00002.txt\nOlder futex-wake_op-glibc.patch version is at:\nhttp://sourceware.org/ml/libc-alpha/2005-03/txt00003.txt\nWill post a new version (just x86-64 fixes so that the patch\napplies against pthread_cond_signal.S) to libc-hacker ml soon.\n\nAttached is the kernel FUTEX_WAKE_OP patch as well as a simple-minded\ntestcase that will not test the atomicity of the operation, but at least\ncheck if the threads that should have been woken up are woken up and\nwhether the arithmetic operation in the kernel gave the expected results.\n\nAcked-by: Ingo Molnar \u003cmingo@redhat.com\u003e\nCc: Ulrich Drepper \u003cdrepper@redhat.com\u003e\nCc: Jamie Lokier \u003cjamie@shareable.org\u003e\nCc: Rusty Russell \u003crusty@rustcorp.com.au\u003e\nSigned-off-by: Yoichi Yuasa \u003cyuasa@hh.iij4u.or.jp\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\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" } ] }