)]}' { "log": [ { "commit": "2a85a37f168d2b4d74d493b578af4dc9032be92e", "tree": "26ed7136e9092e61ae693e117a540045ec5d54a0", "parents": [ "d2d45c7a03a2b1a14159cbb665e9dd60991a7d4f" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Mon Dec 19 21:57:44 2011 -0500" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Wed Dec 21 07:26:35 2011 -0500" }, "message": "ftrace: Allow access to the boot time function enabling\n\nChange set_ftrace_early_filter() to ftrace_set_early_filter()\nand make it a global function. This will allow other subsystems\nin the kernel to be able to enable function tracing at start\nup and reuse the ftrace function parsing code.\n\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "69a3083c4a7df0322d97bb2b43a33cb12af8131a", "tree": "96b0c48178e812819a2f8d8ccf4600997be41fbb", "parents": [ "fc13cb0ce45296f331263a6034aa1814203e1ac3" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Mon Dec 19 15:21:16 2011 -0500" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Wed Dec 21 07:25:24 2011 -0500" }, "message": "ftrace: Decouple hash items from showing filtered functions\n\nThe set_ftrace_filter shows \"hashed\" functions, which are functions\nthat are added with operations to them (like traceon and traceoff).\n\nAs other subsystems may be able to show what functions they are\nusing for function tracing, the hash items should no longer\nbe shown just because the FILTER flag is set. As they have nothing\nto do with other subsystems filters.\n\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "fc13cb0ce45296f331263a6034aa1814203e1ac3", "tree": "2c66d6296ee01bcbd27cb9df4b72885339300ba6", "parents": [ "06a51d9307380c78bb5c92e68fc80ad2c7d7f890" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Mon Dec 19 14:41:25 2011 -0500" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Wed Dec 21 07:25:06 2011 -0500" }, "message": "ftrace: Allow other users of function tracing to use the output listing\n\nThe function tracer is set up to allow any other subsystem (like perf)\nto use it. Ftrace already has a way to list what functions are enabled\nby the global_ops. It would be very helpful to let other users of\nthe function tracer to be able to use the same code.\n\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "06a51d9307380c78bb5c92e68fc80ad2c7d7f890", "tree": "e0f38e8780f92937e8f19f17b8bf9eff6bcc3137", "parents": [ "c842e975520f8ab09e293cc92f51a1f396251fd5" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Mon Dec 19 19:07:36 2011 -0500" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Wed Dec 21 07:23:11 2011 -0500" }, "message": "ftrace: Create ftrace_hash_empty() helper routine\n\nThere are two types of hashes in the ftrace_ops; one type\nis the filter_hash and the other is the notrace_hash. Either\none may be null, meaning it has no elements. But when elements\nare added, the hash is allocated.\n\nThroughout the code, a check needs to be made to see if a hash\nexists or the hash has elements, but the check if the hash exists\nis usually missing causing the possible \"NULL pointer dereference bug\".\n\nAdd a helper routine called \"ftrace_hash_empty()\" that returns\ntrue if the hash doesn\u0027t exist or its count is zero. As they mean\nthe same thing.\n\nLast-bug-reported-by: Jiri Olsa \u003cjolsa@redhat.com\u003e\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "c842e975520f8ab09e293cc92f51a1f396251fd5", "tree": "87102ee6a89cb30415927f43b7694e3ec5b127aa", "parents": [ "5855fead9cc358adebd6bdeec202d040c623ae38" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Mon Dec 19 18:44:44 2011 -0500" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Wed Dec 21 07:21:43 2011 -0500" }, "message": "ftrace: Fix ftrace hash record update with notrace\n\nWhen disabling the \"notrace\" records, that means we want to trace them.\nIf the notrace_hash is zero, it means that we want to trace all\nrecords. But to disable a zero notrace_hash means nothing.\n\nThe check for the notrace_hash count was incorrect with:\n\n\tif (hash \u0026\u0026 !hash-\u003ecount)\n\t\treturn\n\nWith the correct comment above it that states that we do nothing\nif the notrace_hash has zero count. But !hash also means that\nthe notrace hash has zero count. I think this was done to\nprotect against dereferencing NULL. But if !hash is true, then\nwe go through the following loop without doing a single thing.\n\nFix it to:\n\n\tif (!hash || !hash-\u003ecount)\n\t\treturn;\n\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "5855fead9cc358adebd6bdeec202d040c623ae38", "tree": "c95d272ff41b7873cc33feef3686ede3f020d4cd", "parents": [ "68950619f8c82e468d8976130462617abea605a8" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Fri Dec 16 19:27:42 2011 -0500" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Wed Dec 21 07:20:50 2011 -0500" }, "message": "ftrace: Use bsearch to find record ip\n\nNow that each set of pages in the function list are sorted by\nip, we can use bsearch to find a record within each set of pages.\nThis speeds up the ftrace_location() function by magnitudes.\n\nFor archs (like x86) that need to add a breakpoint at every function\nthat will be converted from a nop to a callback and vice versa,\nthe breakpoint callback needs to know if the breakpoint was for\nftrace or not. It requires finding the breakpoint ip within the\nrecords. Doing a linear search is extremely inefficient. It is\na must to be able to do a fast binary search to find these locations.\n\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "68950619f8c82e468d8976130462617abea605a8", "tree": "88a2a4ae266b0bad4335c9bb803b7feb76d71c90", "parents": [ "85ae32ae019bc1c2cc22e5f51fe0c9f2812ef68c" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Fri Dec 16 17:06:45 2011 -0500" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Wed Dec 21 07:19:58 2011 -0500" }, "message": "ftrace: Sort the mcount records on each page\n\nSort records by ip locations of the ftrace mcount calls on each of the\nset of pages in the function list. This helps in localizing cache\nusuage when updating the function locations, as well as gives us\nthe ability to quickly find an ip location in the list.\n\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "85ae32ae019bc1c2cc22e5f51fe0c9f2812ef68c", "tree": "38ce2528dd0af0190e61cbf1dcc9f6d0c4ac3cf6", "parents": [ "a79008755497daff157f5294c02e3b940641cc11" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Fri Dec 16 16:30:31 2011 -0500" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Wed Dec 21 07:19:03 2011 -0500" }, "message": "ftrace: Replace record newlist with record page list\n\nAs new functions come in to be initalized from mcount to nop,\nthey are done by groups of pages. Whether it is the core kernel\nor a module. There\u0027s no need to keep track of these on a per record\nbasis.\n\nAt startup, and as any module is loaded, the functions to be\ntraced are stored in a group of pages and added to the function\nlist at the end. We just need to keep a pointer to the first\npage of the list that was added, and use that to know where to\nstart on the list for initializing functions.\n\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "a79008755497daff157f5294c02e3b940641cc11", "tree": "941e16ae559cbe82f371d07c09b03642bb6e83dd", "parents": [ "3208230983a0ee3d95be22d463257e530c684956" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Fri Dec 16 16:23:44 2011 -0500" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Wed Dec 21 07:18:30 2011 -0500" }, "message": "ftrace: Allocate the mcount record pages as groups\n\nAllocate the mcount record pages as a group of pages as big\nas can be allocated and waste no more than a single page.\n\nGrouping the mcount pages as much as possible helps with cache\nlocality, as we do not need to redirect with descriptors as we\ncross from page to page. It also allows us to do more with the\nrecords later on (sort them with bigger benefits).\n\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "3208230983a0ee3d95be22d463257e530c684956", "tree": "fdba765e348c53a4fd65094ac17e66061f0b8932", "parents": [ "c88fd8634ea68e74c7d19fd2621b4078fd22864c" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Fri Dec 16 14:42:37 2011 -0500" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Wed Dec 21 07:17:57 2011 -0500" }, "message": "ftrace: Remove usage of \"freed\" records\n\nRecords that are added to the function trace table are\npermanently there, except for modules. By separating out the\nmodules to their own pages that can be freed in one shot\nwe can remove the \"freed\" flag and simplify some of the record\nmanagement.\n\nAnother benefit of doing this is that we can also move the\nrecords around; sort them.\n\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "c88fd8634ea68e74c7d19fd2621b4078fd22864c", "tree": "9d8bbc57d20eec9869a9655ff79cc1c4d6359b88", "parents": [ "45959ee7aa645815a5ce303a0ea1e48a21e67c6a" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Tue Aug 16 09:53:39 2011 -0400" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Wed Dec 21 07:16:58 2011 -0500" }, "message": "ftrace: Allow archs to modify code without stop machine\n\nThe stop machine method to modify all functions in the kernel\n(some 20,000 of them) is the safest way to do so across all archs.\nBut some archs may not need this big hammer approach to modify code\non SMP machines, and can simply just update the code it needs.\n\nAdding a weak function arch_ftrace_update_code() that now does the\nstop machine, will also let any arch override this method.\n\nIf the arch needs to check the system and then decide if it can\navoid stop machine, it can still call ftrace_run_stop_machine() to\nuse the old method.\n\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "30fb6aa74011dcf595f306ca2727254d708b786e", "tree": "cda3efc265f74c8d6496b2d976f528fcdc1cb81d", "parents": [ "74eec26facadbe6dbc0621bc862892c915c4534f" ], "author": { "name": "Jiri Olsa", "email": "jolsa@redhat.com", "time": "Mon Dec 05 18:22:48 2011 +0100" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Wed Dec 21 07:09:14 2011 -0500" }, "message": "ftrace: Fix unregister ftrace_ops accounting\n\nMultiple users of the function tracer can register their functions\nwith the ftrace_ops structure. The accounting within ftrace will\nupdate the counter on each function record that is being traced.\nWhen the ftrace_ops filtering adds or removes functions, the\nfunction records will be updated accordingly if the ftrace_ops is\nstill registered.\n\nWhen a ftrace_ops is removed, the counter of the function records,\nthat the ftrace_ops traces, are decremented. When they reach zero\nthe functions that they represent are modified to stop calling the\nmcount code.\n\nWhen changes are made, the code is updated via stop_machine() with\na command passed to the function to tell it what to do. There is an\nENABLE and DISABLE command that tells the called function to enable\nor disable the functions. But the ENABLE is really a misnomer as it\nshould just update the records, as records that have been enabled\nand now have a count of zero should be disabled.\n\nThe DISABLE command is used to disable all functions regardless of\ntheir counter values. This is the big off switch and is not the\ncomplement of the ENABLE command.\n\nTo make matters worse, when a ftrace_ops is unregistered and there\nis another ftrace_ops registered, neither the DISABLE nor the\nENABLE command are set when calling into the stop_machine() function\nand the records will not be updated to match their counter. A command\nis passed to that function that will update the mcount code to call\nthe registered callback directly if it is the only one left. This\nmeans that the ftrace_ops that is still registered will have its callback\ncalled by all functions that have been set for it as well as the ftrace_ops\nthat was just unregistered.\n\nHere\u0027s a way to trigger this bug. Compile the kernel with\nCONFIG_FUNCTION_PROFILER set and with CONFIG_FUNCTION_GRAPH not set:\n\n CONFIG_FUNCTION_PROFILER\u003dy\n # CONFIG_FUNCTION_GRAPH is not set\n\nThis will force the function profiler to use the function tracer instead\nof the function graph tracer.\n\n # cd /sys/kernel/debug/tracing\n # echo schedule \u003e set_ftrace_filter\n # echo function \u003e current_tracer\n # cat set_ftrace_filter\n schedule\n # cat trace\n # tracer: nop\n #\n # entries-in-buffer/entries-written: 692/68108025 #P:4\n #\n # _-----\u003d\u003e irqs-off\n # / _----\u003d\u003e need-resched\n # | / _---\u003d\u003e hardirq/softirq\n # || / _--\u003d\u003e preempt-depth\n # ||| / delay\n # TASK-PID CPU# |||| TIMESTAMP FUNCTION\n # | | | |||| | |\n kworker/0:2-909 [000] .... 531.235574: schedule \u003c-worker_thread\n \u003cidle\u003e-0 [001] .N.. 531.235575: schedule \u003c-cpu_idle\n kworker/0:2-909 [000] .... 531.235597: schedule \u003c-worker_thread\n sshd-2563 [001] .... 531.235647: schedule \u003c-schedule_hrtimeout_range_clock\n\n # echo 1 \u003e function_profile_enabled\n # echo 0 \u003e function_porfile_enabled\n # cat set_ftrace_filter\n schedule\n # cat trace\n # tracer: function\n #\n # entries-in-buffer/entries-written: 159701/118821262 #P:4\n #\n # _-----\u003d\u003e irqs-off\n # / _----\u003d\u003e need-resched\n # | / _---\u003d\u003e hardirq/softirq\n # || / _--\u003d\u003e preempt-depth\n # ||| / delay\n # TASK-PID CPU# |||| TIMESTAMP FUNCTION\n # | | | |||| | |\n \u003cidle\u003e-0 [002] ...1 604.870655: local_touch_nmi \u003c-cpu_idle\n \u003cidle\u003e-0 [002] d..1 604.870655: enter_idle \u003c-cpu_idle\n \u003cidle\u003e-0 [002] d..1 604.870656: atomic_notifier_call_chain \u003c-enter_idle\n \u003cidle\u003e-0 [002] d..1 604.870656: __atomic_notifier_call_chain \u003c-atomic_notifier_call_chain\n\nThe same problem could have happened with the trace_probe_ops,\nbut they are modified with the set_frace_filter file which does the\nupdate at closure of the file.\n\nThe simple solution is to change ENABLE to UPDATE and call it every\ntime an ftrace_ops is unregistered.\n\nLink: http://lkml.kernel.org/r/1323105776-26961-3-git-send-email-jolsa@redhat.com\n\nCc: stable@vger.kernel.org # 3.0+\nSigned-off-by: Jiri Olsa \u003cjolsa@redhat.com\u003e\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "efc96737bd82b508794d2b28061a12af4a3f7766", "tree": "e9fe4982967b74c0d25a35a2d7f7c62d8be98a47", "parents": [ "1ec454baf1245df4fdb5dae728da3363630ce6de", "7e9a49ef542610609144d1afcd516dc3fafac4d6" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Fri Nov 11 08:19:37 2011 +0100" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Fri Nov 11 08:19:37 2011 +0100" }, "message": "Merge branch \u0027tip/perf/core\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace into perf/core\n" }, { "commit": "d4d34b981a5327eec956c6cb4cce397ce6f57279", "tree": "a5ee3ca4103b2a987f369a15cd9f28798d0d91cf", "parents": [ "49908a1b25d448d68fd26faca260e1850201575f" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Fri Nov 04 20:32:39 2011 -0400" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Mon Nov 07 13:48:05 2011 -0500" }, "message": "ftrace: Fix hash record accounting bug\n\nIf the set_ftrace_filter is cleared by writing just whitespace to\nit, then the filter hash refcounts will be decremented but not\nupdated. This causes two bugs:\n\n1) No functions will be enabled for tracing when they all should be\n\n2) If the users clears the set_ftrace_filter twice, it will crash ftrace:\n\n------------[ cut here ]------------\nWARNING: at /home/rostedt/work/git/linux-trace.git/kernel/trace/ftrace.c:1384 __ftrace_hash_rec_update.part.27+0x157/0x1a7()\nModules linked in:\nPid: 2330, comm: bash Not tainted 3.1.0-test+ #32\nCall Trace:\n [\u003cffffffff81051828\u003e] warn_slowpath_common+0x83/0x9b\n [\u003cffffffff8105185a\u003e] warn_slowpath_null+0x1a/0x1c\n [\u003cffffffff810ba362\u003e] __ftrace_hash_rec_update.part.27+0x157/0x1a7\n [\u003cffffffff810ba6e8\u003e] ? ftrace_regex_release+0xa7/0x10f\n [\u003cffffffff8111bdfe\u003e] ? kfree+0xe5/0x115\n [\u003cffffffff810ba51e\u003e] ftrace_hash_move+0x2e/0x151\n [\u003cffffffff810ba6fb\u003e] ftrace_regex_release+0xba/0x10f\n [\u003cffffffff8112e49a\u003e] fput+0xfd/0x1c2\n [\u003cffffffff8112b54c\u003e] filp_close+0x6d/0x78\n [\u003cffffffff8113a92d\u003e] sys_dup3+0x197/0x1c1\n [\u003cffffffff8113a9a6\u003e] sys_dup2+0x4f/0x54\n [\u003cffffffff8150cac2\u003e] system_call_fastpath+0x16/0x1b\n---[ end trace 77a3a7ee73794a02 ]---\n\nLink: http://lkml.kernel.org/r/20111101141420.GA4918@debian\n\nReported-by: Rabin Vincent \u003crabin@rab.in\u003e\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "8ee3c92b7f2751c392be2d8fc360a410480b8757", "tree": "60ebbd1d3dc66eda28f73cc08d19c0ccbd082cbf", "parents": [ "e5e78d08f3ab3094783b8df08a5b6d1d1a56a58f" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Fri Nov 04 10:45:23 2011 -0400" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Mon Nov 07 11:02:33 2011 -0500" }, "message": "ftrace: Remove force undef config value left for testing\n\nA forced undef of a config value was used for testing and was\naccidently left in during the final commit. This causes x86 to\nrun slower than needed while running function tracing as well\nas causes the function graph selftest to fail when DYNMAIC_FTRACE\nis not set. This is because the code in MCOUNT expects the ftrace\ncode to be processed with the config value set that happened to\nbe forced not set.\n\nThe forced config option was left in by:\n commit 6331c28c962561aee59e5a493b7556a4bb585957\n ftrace: Fix dynamic selftest failure on some archs\n\nLink: http://lkml.kernel.org/r/20111102150255.GA6973@debian\n\nCc: stable@vger.kernel.org\nReported-by: Rabin Vincent \u003crabin@rab.in\u003e\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "56d82e000cdfb51aa92241d4682302f78c35cd92", "tree": "db011bf38930f2d0d0fa8a8f43e223fd03e25fad", "parents": [ "9984de1a5a8a96275fcab818f7419af5a3c86e71" ], "author": { "name": "Paul Gortmaker", "email": "paul.gortmaker@windriver.com", "time": "Thu May 26 17:53:52 2011 -0400" }, "committer": { "name": "Paul Gortmaker", "email": "paul.gortmaker@windriver.com", "time": "Mon Oct 31 09:20:12 2011 -0400" }, "message": "kernel: Add \u003clinux/module.h\u003e to files using it implicitly\n\nThese files are doing things like module_put and try_module_get\nso they need to call out the module.h for explicit inclusion,\nrather than getting it via \u003clinux/device.h\u003e which we ideally want\nto remove the module.h inclusion from.\n\nSigned-off-by: Paul Gortmaker \u003cpaul.gortmaker@windriver.com\u003e\n" }, { "commit": "e0a413f619ef8bc366dafc6f8221674993b8d85f", "tree": "a6696b0e7ef5422490bdbcc28d385c031d3e4eb8", "parents": [ "e36de1de4a5f95b7cb3e5c37d10e6bbb91833ef0" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Thu Sep 29 21:26:16 2011 -0400" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Tue Oct 11 09:13:25 2011 -0400" }, "message": "tracing: Warn on output if the function tracer was found corrupted\n\nAs the function tracer is very intrusive, lots of self checks are\nperformed on the tracer and if something is found to be strange\nit will shut itself down keeping it from corrupting the rest of the\nkernel. This shutdown may still allow functions to be traced, as the\ntracing only stops new modifications from happening. Trying to stop\nthe function tracer itself can cause more harm as it requires code\nmodification.\n\nAlthough a WARN_ON() is executed, a user may not notice it. To help\nthe user see that something isn\u0027t right with the tracing of the system\na big warning is added to the output of the tracer that lets the user\nknow that their data may be incomplete.\n\nReported-by: Thomas Gleixner \u003ctglx@linutronix.de\u003e\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "40bcea7bbe8fe452a2d272e2ffd3dea281eec9ff", "tree": "aedb6d02e53e3cf84cc32fd81db84032cee205e1", "parents": [ "492f73a303b488ffd67097b2351d54aa6e6c7c73", "14a8fd7ceea6915c613746203d6e9a2bf273f16c" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Thu Jul 21 09:32:40 2011 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Thu Jul 21 09:32:40 2011 +0200" }, "message": "Merge branch \u0027tip/perf/core\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-2.6-trace into perf/core\n" }, { "commit": "492f73a303b488ffd67097b2351d54aa6e6c7c73", "tree": "6e6c16fbd628bb5eb577cfc70a488ca286563e58", "parents": [ "e08fbb78f03fe2c4f88824faf6f51ce6af185e11", "f7bc8b61f65726ff98f52e286b28e294499d7a08" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Thu Jul 21 09:29:14 2011 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Thu Jul 21 09:29:21 2011 +0200" }, "message": "Merge branch \u0027perf/urgent\u0027 into perf/core\n\nMerge reason: pick up the latest fixes - they won\u0027t make v3.0.\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "f7bc8b61f65726ff98f52e286b28e294499d7a08", "tree": "88ef0c943d27aa9f69824d87faa990731cc2ebfe", "parents": [ "04da85b86188f224cc9b391b5bdd92a3ba20ffcf" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Thu Jul 14 23:02:27 2011 -0400" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Thu Jul 14 23:02:27 2011 -0400" }, "message": "ftrace: Fix regression where ftrace breaks when modules are loaded\n\nEnabling function tracer to trace all functions, then load a module and\nthen disable function tracing will cause ftrace to fail.\n\nThis can also happen by enabling function tracing on the command line:\n\n ftrace\u003dfunction\n\nand during boot up, modules are loaded, then you disable function tracing\nwith \u0027echo nop \u003e current_tracer\u0027 you will trigger a bug in ftrace that\nwill shut itself down.\n\nThe reason is, the new ftrace code keeps ref counts of all ftrace_ops that\nare registered for tracing. When one or more ftrace_ops are registered,\nall the records that represent the functions that the ftrace_ops will\ntrace have a ref count incremented. If this ref count is not zero,\nwhen the code modification runs, that function will be enabled for tracing.\nIf the ref count is zero, that function will be disabled from tracing.\n\nTo make sure the accounting was working, FTRACE_WARN_ON()s were added\nto updating of the ref counts.\n\nIf the ref count hits its max (\u003e 2^30 ftrace_ops added), or if\nthe ref count goes below zero, a FTRACE_WARN_ON() is triggered which\ndisables all modification of code.\n\nSince it is common for ftrace_ops to trace all functions in the kernel,\ninstead of creating \u003e 20,000 hash items for the ftrace_ops, the hash\ncount is just set to zero, and it represents that the ftrace_ops is\nto trace all functions. This is where the issues arrise.\n\nIf you enable function tracing to trace all functions, and then add\na module, the modules function records do not get the ref count updated.\nWhen the function tracer is disabled, all function records ref counts\nare subtracted. Since the modules never had their ref counts incremented,\nthey go below zero and the FTRACE_WARN_ON() is triggered.\n\nThe solution to this is rather simple. When modules are loaded, and\ntheir functions are added to the the ftrace pool, look to see if any\nftrace_ops are registered that trace all functions. And for those,\nupdate the ref count for the module function records.\n\nReported-by: Thomas Gleixner \u003ctglx@linutronix.de\u003e\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "6331c28c962561aee59e5a493b7556a4bb585957", "tree": "33292a3127aa831ee8ec2394e790bc2a8817beee", "parents": [ "072126f4529196f71a97960248bca54fd4554c2d" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Wed Jul 13 15:11:02 2011 -0400" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Wed Jul 13 22:25:09 2011 -0400" }, "message": "ftrace: Fix dynamic selftest failure on some archs\n\nArchs that do not implement CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST, will\nfail the dynamic ftrace selftest.\n\nThe function tracer has a quick \u0027off\u0027 variable that will prevent\nthe call back functions from being called. This variable is called\nfunction_trace_stop. In x86, this is implemented directly in the mcount\nassembly, but for other archs, an intermediate function is used called\nftrace_test_stop_func().\n\nIn dynamic ftrace, the function pointer variable ftrace_trace_function is\nused to update the caller code in the mcount caller. But for archs that\ndo not have CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST set, it only calls\nftrace_test_stop_func() instead, which in turn calls __ftrace_trace_function.\n\nWhen more than one ftrace_ops is registered, the function it calls is\nftrace_ops_list_func(), which will iterate over all registered ftrace_ops\nand call the callbacks that have their hash matching.\n\nThe issue happens when two ftrace_ops are registered for different functions\nand one is then unregistered. The __ftrace_trace_function is then pointed\nto the remaining ftrace_ops callback function directly. This mean it will\nbe called for all functions that were registered to trace by both ftrace_ops\nthat were registered.\n\nThis is not an issue for archs with CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST,\nbecause the update of ftrace_trace_function doesn\u0027t happen until after all\nfunctions have been updated, and then the mcount caller is updated. But\nfor those archs that do use the ftrace_test_stop_func(), the update is\nimmediate.\n\nThe dynamic selftest fails because it hits this situation, and the\nftrace_ops that it registers fails to only trace what it was suppose to\nand instead traces all other functions.\n\nThe solution is to delay the setting of __ftrace_trace_function until\nafter all the functions have been updated according to the registered\nftrace_ops. Also, function_trace_stop is set during the update to prevent\nfunction tracing from calling code that is caused by the function tracer\nitself.\n\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "072126f4529196f71a97960248bca54fd4554c2d", "tree": "cb1275288f49b59e4643abb85855ad6889aba94f", "parents": [ "41fb61c2d08107ce96a5dcb3a6289b2afd3e135c" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Wed Jul 13 15:08:31 2011 -0400" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Wed Jul 13 22:10:05 2011 -0400" }, "message": "ftrace: Update filter when tracing enabled in set_ftrace_filter()\n\nCurrently, if set_ftrace_filter() is called when the ftrace_ops is\nactive, the function filters will not be updated. They will only be updated\nwhen tracing is disabled and re-enabled.\n\nUpdate the functions immediately during set_ftrace_filter().\n\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "41fb61c2d08107ce96a5dcb3a6289b2afd3e135c", "tree": "ca3ae1796ca1d3f01f2bb62eba1fbc93db1affae", "parents": [ "4376cac66778b25e599be3f5d54f33f58ba8ead7" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Wed Jul 13 15:03:44 2011 -0400" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Wed Jul 13 22:00:50 2011 -0400" }, "message": "ftrace: Balance records when updating the hash\n\nWhenever the hash of the ftrace_ops is updated, the record counts\nmust be balance. This requires disabling the records that are set\nin the original hash, and then enabling the records that are set\nin the updated hash.\n\nMoving the update into ftrace_hash_move() removes the bug where the\nhash was updated but the records were not, which results in ftrace\ntriggering a warning and disabling itself because the ftrace_ops filter\nis updated while the ftrace_ops was registered, and then the failure\nhappens when the ftrace_ops is unregistered.\n\nThe current code will not trigger this bug, but new code will.\n\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "4376cac66778b25e599be3f5d54f33f58ba8ead7", "tree": "9cf05820586f140bafcde67cd2cd80a4391ef7eb", "parents": [ "e4a3f541f0b67fdad98b326c851dfe7f4b6b6dad" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Fri Jun 24 23:28:13 2011 -0400" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Thu Jul 07 22:39:38 2011 -0400" }, "message": "ftrace: Do not disable interrupts for modules in mcount update\n\nWhen I mounted an NFS directory, it caused several modules to be loaded. At the\ntime I was running the preemptirqsoff tracer, and it showed the following\noutput:\n\n# tracer: preemptirqsoff\n#\n# preemptirqsoff latency trace v1.1.5 on 2.6.33.9-rt30-mrg-test\n# --------------------------------------------------------------------\n# latency: 1177 us, #4/4, CPU#3 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:4)\n# -----------------\n# | task: modprobe-19370 (uid:0 nice:0 policy:0 rt_prio:0)\n# -----------------\n# \u003d\u003e started at: ftrace_module_notify\n# \u003d\u003e ended at: ftrace_module_notify\n#\n#\n# _------\u003d\u003e CPU#\n# / _-----\u003d\u003e irqs-off\n# | / _----\u003d\u003e need-resched\n# || / _---\u003d\u003e hardirq/softirq\n# ||| / _--\u003d\u003e preempt-depth\n# |||| /_--\u003d\u003e lock-depth\n# |||||/ delay\n# cmd pid |||||| time | caller\n# \\ / |||||| \\ | /\nmodprobe-19370 3d.... 0us!: ftrace_process_locs \u003c-ftrace_module_notify\nmodprobe-19370 3d.... 1176us : ftrace_process_locs \u003c-ftrace_module_notify\nmodprobe-19370 3d.... 1178us : trace_hardirqs_on \u003c-ftrace_module_notify\nmodprobe-19370 3d.... 1178us : \u003cstack trace\u003e\n \u003d\u003e ftrace_process_locs\n \u003d\u003e ftrace_module_notify\n \u003d\u003e notifier_call_chain\n \u003d\u003e __blocking_notifier_call_chain\n \u003d\u003e blocking_notifier_call_chain\n \u003d\u003e sys_init_module\n \u003d\u003e system_call_fastpath\n\nThat\u0027s over 1ms that interrupts are disabled on a Real-Time kernel!\n\nLooking at the cause (being the ftrace author helped), I found that the\ninterrupts are disabled before the code modification of mcounts into nops. The\ninterrupts only need to be disabled on start up around this code, not when\nmodules are being loaded.\n\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "43dd61c9a09bd413e837df829e6bfb42159be52a", "tree": "613b8ceaf798c87a4fac4ff66dc2ac0e13c3e46b", "parents": [ "40ee4dffff061399eb9358e0c8fcfbaf8de4c8fe" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Thu Jul 07 11:09:22 2011 -0400" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Thu Jul 07 11:30:08 2011 -0400" }, "message": "ftrace: Fix regression of :mod:module function enabling\n\nThe new code that allows different utilities to pick and choose\nwhat functions they trace broke the :mod: hook that allows users\nto trace only functions of a particular module.\n\nThe reason is that the :mod: hook bypasses the hash that is setup\nto allow individual users to trace their own functions and uses\nthe global hash directly. But if the global hash has not been\nset up, it will cause a bug:\n\necho \u0027*:mod:radeon\u0027 \u003e /sys/kernel/debug/set_ftrace_filter\n\nproduces:\n\n [drm:drm_mode_getfb] *ERROR* invalid framebuffer id\n [drm:radeon_crtc_page_flip] *ERROR* failed to reserve new rbo buffer before flip\n BUG: unable to handle kernel paging request at ffffffff8160ec90\n IP: [\u003cffffffff810d9136\u003e] add_hash_entry+0x66/0xd0\n PGD 1a05067 PUD 1a09063 PMD 80000000016001e1\n Oops: 0003 [#1] SMP Jul 7 04:02:28 phyllis kernel: [55303.858604] CPU 1\n Modules linked in: cryptd aes_x86_64 aes_generic binfmt_misc rfcomm bnep ip6table_filter hid radeon r8169 ahci libahci mii ttm drm_kms_helper drm video i2c_algo_bit intel_agp intel_gtt\n\n Pid: 10344, comm: bash Tainted: G WC 3.0.0-rc5 #1 Dell Inc. Inspiron N5010/0YXXJJ\n RIP: 0010:[\u003cffffffff810d9136\u003e] [\u003cffffffff810d9136\u003e] add_hash_entry+0x66/0xd0\n RSP: 0018:ffff88003a96bda8 EFLAGS: 00010246\n RAX: ffff8801301735c0 RBX: ffffffff8160ec80 RCX: 0000000000306ee0\n RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffff880137c92940\n RBP: ffff88003a96bdb8 R08: ffff880137c95680 R09: 0000000000000000\n R10: 0000000000000001 R11: 0000000000000000 R12: ffffffff81c9df78\n R13: ffff8801153d1000 R14: 0000000000000000 R15: 0000000000000000\n FS: 00007f329c18a700(0000) GS:ffff880137c80000(0000) knlGS:0000000000000000\n CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033\n CR2: ffffffff8160ec90 CR3: 000000003002b000 CR4: 00000000000006e0\n DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000\n DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400\n Process bash (pid: 10344, threadinfo ffff88003a96a000, task ffff88012fcfc470)\n Stack:\n 0000000000000fd0 00000000000000fc ffff88003a96be38 ffffffff810d92f5\n ffff88011c4c4e00 ffff880000000000 000000000b69f4d0 ffffffff8160ec80\n ffff8800300e6f06 0000000081130295 0000000000000282 ffff8800300e6f00\n Call Trace:\n [\u003cffffffff810d92f5\u003e] match_records+0x155/0x1b0\n [\u003cffffffff810d940c\u003e] ftrace_mod_callback+0xbc/0x100\n [\u003cffffffff810dafdf\u003e] ftrace_regex_write+0x16f/0x210\n [\u003cffffffff810db09f\u003e] ftrace_filter_write+0xf/0x20\n [\u003cffffffff81166e48\u003e] vfs_write+0xc8/0x190\n [\u003cffffffff81167001\u003e] sys_write+0x51/0x90\n [\u003cffffffff815c7e02\u003e] system_call_fastpath+0x16/0x1b\n Code: 48 8b 33 31 d2 48 85 f6 75 33 49 89 d4 4c 03 63 08 49 8b 14 24 48 85 d2 48 89 10 74 04 48 89 42 08 49 89 04 24 4c 89 60 08 31 d2\n RIP [\u003cffffffff810d9136\u003e] add_hash_entry+0x66/0xd0\n RSP \u003cffff88003a96bda8\u003e\n CR2: ffffffff8160ec90\n ---[ end trace a5d031828efdd88e ]---\n\nReported-by: Brian Marete \u003cmarete@toshnix.com\u003e\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "931da6137e8e8c622f59251e8b645467aea293f1", "tree": "2169cbd29d5d9a4cbc7104b2a744a95ba746c50d", "parents": [ "5d67be97f8903d05ce53597fb5f3bc25a45e8026", "1fd8df2c3970c9e7e4e262354154ee39e58bdd7c" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Tue Jul 05 11:55:43 2011 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Tue Jul 05 11:55:43 2011 +0200" }, "message": "Merge branch \u0027tip/perf/core-2\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-2.6-trace into perf/core\n" }, { "commit": "22fe9b54d859e53bfbbbdc1a0a77a82bc453927c", "tree": "4aec2d069decbe0786ad5474908f5bbe49732ad4", "parents": [ "749230b06a753a22f6ed96e5dd60815d6ab12865" ], "author": { "name": "Peter Huewe", "email": "peterhuewe@gmx.de", "time": "Tue Jun 07 21:58:27 2011 +0200" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Tue Jun 14 22:48:50 2011 -0400" }, "message": "tracing: Convert to kstrtoul_from_user\n\nThis patch replaces the code for getting an unsigned long from a\nuserspace buffer by a simple call to kstroul_from_user.\nThis makes it easier to read and less error prone.\n\nSigned-off-by: Peter Huewe \u003cpeterhuewe@gmx.de\u003e\nLink: http://lkml.kernel.org/r/1307476707-14762-1-git-send-email-peterhuewe@gmx.de\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "bd38c0e6f98326132a691d73b2056b426423c638", "tree": "4e7f9a0efcfdb23e564db51da275fd9234ffa84f", "parents": [ "cf30cf67d6c7592c670ec946d89fc15ee0deb0eb" ], "author": { "name": "Paul McQuade", "email": "tungstentide@gmail.com", "time": "Tue May 31 20:51:55 2011 +0100" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Tue Jun 14 22:48:45 2011 -0400" }, "message": "ftrace: Fixed an include coding style issue\n\nRemoved \u003casm/ftrace.h\u003e because \u003clinux/ftrace.h\u003e was already declared.\nBraces of struct\u0027s coding style fixed.\n\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nSigned-off-by: Paul McQuade \u003ctungstentide@gmail.com\u003e\nLink: http://lkml.kernel.org/r/4DE59711.3090900@gmail.com\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "a4f18ed11a4ddf327dd91cd19e237278600ad327", "tree": "bbe96241c6db2be16e881920a3312ec937ed7cd1", "parents": [ "265a5b7ee3eb21a4d0e53e17d59ba6eada91af39" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Tue Jun 07 09:26:46 2011 -0400" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Tue Jun 07 14:49:19 2011 -0400" }, "message": "ftrace: Revert 8ab2b7efd ftrace: Remove unnecessary disabling of irqs\n\nRevert the commit that removed the disabling of interrupts around\nthe initial modifying of mcount callers to nops, and update the comment.\n\nThe original comment was outdated and stated that the interrupts were\nbeing disabled to prevent kstop machine, which was required with the\nold ftrace daemon, but was no longer the case.\n\nWhat the comment failed to mention was that interrupts needed to be\ndisabled to keep interrupts from preempting the modifying of the code\nand then executing the code that was partially modified.\n\nRevert the commit and update the comment.\n\nReported-by: Richard W.M. Jones \u003crjones@redhat.com\u003e\nTested-by: Richard W.M. Jones \u003crjones@redhat.com\u003e\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "0aff1c0cef13b34c17e81a502336fad738151c37", "tree": "3bf383429c3d948bd34ff71ae78d82bb2439fab5", "parents": [ "d7ebe75b065a7c2d58ffc12f9d2e00d5ea4e71eb" ], "author": { "name": "GuoWen Li", "email": "guowen.li.linux@gmail.com", "time": "Wed Jun 01 19:18:47 2011 +0800" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Mon Jun 06 22:34:25 2011 -0400" }, "message": "ftrace: Fix possible undefined return code\n\nkernel/trace/ftrace.c: In function \u0027ftrace_regex_write.clone.15\u0027:\nkernel/trace/ftrace.c:2743:6: warning: \u0027ret\u0027 may be used uninitialized in this\nfunction\n\nSigned-off-by: GuoWen Li \u003cguowen.li.linux@gmail.com\u003e\nLink: http://lkml.kernel.org/r/201106011918.47939.guowen.li.linux@gmail.com\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "b1cff0ad1062621ae63cb6c5dc4165191fe2e9f1", "tree": "81c35a8fe57b1a139416aac637b0fc198f67199d", "parents": [ "7f34b746f79c1e1f8fd6d09799d133263ae7a504" ], "author": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Wed May 25 14:27:43 2011 -0400" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Wed May 25 22:13:49 2011 -0400" }, "message": "ftrace: Add internal recursive checks\n\nWitold reported a reboot caused by the selftests of the dynamic function\ntracer. He sent me a config and I used ktest to do a config_bisect on it\n(as my config did not cause the crash). It pointed out that the problem\nconfig was CONFIG_PROVE_RCU.\n\nWhat happened was that if multiple callbacks are attached to the\nfunction tracer, we iterate a list of callbacks. Because the list is\nmanaged by synchronize_sched() and preempt_disable, the access to the\npointers uses rcu_dereference_raw().\n\nWhen PROVE_RCU is enabled, the rcu_dereference_raw() calls some\ndebugging functions, which happen to be traced. The tracing of the debug\nfunction would then call rcu_dereference_raw() which would then call the\ndebug function and then... well you get the idea.\n\nI first wrote two different patches to solve this bug.\n\n1) add a __rcu_dereference_raw() that would not do any checks.\n2) add notrace to the offending debug functions.\n\nBoth of these patches worked.\n\nTalking with Paul McKenney on IRC, he suggested to add recursion\ndetection instead. This seemed to be a better solution, so I decided to\nimplement it. As the task_struct already has a trace_recursion to detect\nrecursion in the ring buffer, and that has a very small number it\nallows, I decided to use that same variable to add flags that can detect\nthe recursion inside the infrastructure of the function tracer.\n\nI plan to change it so that the task struct bit can be checked in\nmcount, but as that requires changes to all archs, I will hold that off\nto the next merge window.\n\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nCc: Thomas Gleixner \u003ctglx@linutronix.de\u003e\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Paul E. McKenney \u003cpaulmck@linux.vnet.ibm.com\u003e\nLink: http://lkml.kernel.org/r/1306348063.1465.116.camel@gandalf.stny.rr.com\nReported-by: Witold Baryluk \u003cbaryluk@smp.if.uj.edu.pl\u003e\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "3b6cfdb1714a33ae4d2ca9fbc818a42cf7adee69", "tree": "1fc1ca6ff17da6c7ab30d2dffa99d3cb6d4cfca4", "parents": [ "17bb615ad4f8d2d2c0f02794d27d7f83e0009ef4" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Mon May 23 15:33:49 2011 -0400" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Wed May 25 22:13:42 2011 -0400" }, "message": "ftrace: Set ops-\u003eflag to enabled even on static function tracing\n\nWhen dynamic ftrace is not configured, the ops-\u003eflags still needs\nto have its FTRACE_OPS_FL_ENABLED bit set in ftrace_startup().\n\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "a1cd6173596c6f7d1f0b41ac7d33ecf03c581edc", "tree": "413ed775a2c48d8ad003740fa6ef0d912f784842", "parents": [ "7cbc5b8d4a775a43875a09e29c49a2a8195b5b2d" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Mon May 23 15:24:25 2011 -0400" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Wed May 25 22:13:37 2011 -0400" }, "message": "ftrace: Have ftrace_startup() return failure code\n\nThe register_ftrace_function() returns an error code on failure\nexcept if the call to ftrace_startup() fails. Add a error return to\nftrace_startup() if it fails to start, allowing register_ftrace_funtion()\nto return a proper error value.\n\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "936e074b286ae779f134312178dbab139ee7ea52", "tree": "6b0497be4d5e6258ad9b1ec99b2a9feb25b2dd22", "parents": [ "cdbe61bfe70440939e457fb4a8d0995eaaed17de" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Thu May 05 22:54:01 2011 -0400" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Wed May 18 19:22:52 2011 -0400" }, "message": "ftrace: Modify ftrace_set_filter/notrace to take ops\n\nSince users of the function tracer can now pick and choose which\nfunctions they want to trace agnostically from other users of the\nfunction tracer, we need to pass the ops struct to the ftrace_set_filter()\nfunctions.\n\nThe functions ftrace_set_global_filter() and ftrace_set_global_notrace()\nis added to keep the old filter functions which are used to modify\nthe generic function tracers.\n\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "cdbe61bfe70440939e457fb4a8d0995eaaed17de", "tree": "6e82066db25ab6fa42455a42bb77783dac5260b8", "parents": [ "b848914ce39589d89ee0078a6d1ef452b464729e" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Thu May 05 21:14:55 2011 -0400" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Wed May 18 15:29:51 2011 -0400" }, "message": "ftrace: Allow dynamically allocated function tracers\n\nNow that functions may be selected individually, it only makes sense\nthat we should allow dynamically allocated trace structures to\nbe traced. This will allow perf to allocate a ftrace_ops structure\nat runtime and use it to pick and choose which functions that\nstructure will trace.\n\nNote, a dynamically allocated ftrace_ops will always be called\nindirectly instead of being called directly from the mcount in\nentry.S. This is because there\u0027s no safe way to prevent mcount\nfrom being preempted before calling the function, unless we\nmodify every entry.S to do so (not likely). Thus, dynamically allocated\nfunctions will now be called by the ftrace_ops_list_func() that\nloops through the ops that are allocated if there are more than\none op allocated at a time. This loop is protected with a\npreempt_disable.\n\nTo determine if an ftrace_ops structure is allocated or not, a new\nutil function was added to the kernel/extable.c called\ncore_kernel_data(), which returns 1 if the address is between\n_sdata and _edata.\n\nCc: Paul E. McKenney \u003cpaulmck@linux.vnet.ibm.com\u003e\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "b848914ce39589d89ee0078a6d1ef452b464729e", "tree": "542bf09ae3c2d9118833132621585fb458e2a003", "parents": [ "07fd5515f3b5c20704707f63e7f4485b534508a8" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Wed May 04 09:27:52 2011 -0400" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Wed May 18 15:29:50 2011 -0400" }, "message": "ftrace: Implement separate user function filtering\n\nftrace_ops that are registered to trace functions can now be\nagnostic to each other in respect to what functions they trace.\nEach ops has their own hash of the functions they want to trace\nand a hash to what they do not want to trace. A empty hash for\nthe functions they want to trace denotes all functions should\nbe traced that are not in the notrace hash.\n\nCc: Paul E. McKenney \u003cpaulmck@linux.vnet.ibm.com\u003e\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "07fd5515f3b5c20704707f63e7f4485b534508a8", "tree": "f018ec497f8c6b49a0fcfcd7a92a600e670f90f2", "parents": [ "2b499381bc50ede01b3d8eab164ca2fad00655f0" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Thu May 05 18:03:47 2011 -0400" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Wed May 18 15:29:50 2011 -0400" }, "message": "ftrace: Free hash with call_rcu_sched()\n\nWhen a hash is modified and might be in use, we need to perform\na schedule RCU operation on it, as the hashes will soon be used\ndirectly in the function tracer callback.\n\nCc: Paul E. McKenney \u003cpaulmck@linux.vnet.ibm.com\u003e\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "2b499381bc50ede01b3d8eab164ca2fad00655f0", "tree": "3140c277582b03b1645fffcb829763d62e2f01fa", "parents": [ "bd69c30b1d08032d97ab0dabd7a1eb7fb73ca2b2" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Tue May 03 22:49:52 2011 -0400" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Wed May 18 15:29:49 2011 -0400" }, "message": "ftrace: Have global_ops store the functions that are to be traced\n\nThis is a step towards each ops structure defining its own set\nof functions to trace. As the current code with pid\u0027s and such\nare specific to the global_ops, it is restructured to be used\nwith the global ops.\n\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "bd69c30b1d08032d97ab0dabd7a1eb7fb73ca2b2", "tree": "e8bd00dc87de4f10f049e0c41fd09f630b96585d", "parents": [ "647bcd03d5b2fb44fd9c9ef1a4f50c2eee8f779a" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Tue May 03 21:55:54 2011 -0400" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Wed May 18 15:29:48 2011 -0400" }, "message": "ftrace: Add ops parameter to ftrace_startup/shutdown functions\n\nIn order to allow different ops to enable different functions,\nthe ftrace_startup() and ftrace_shutdown() functions need the\nops parameter passed to them.\n\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "647bcd03d5b2fb44fd9c9ef1a4f50c2eee8f779a", "tree": "32946158175458f16ae95c383ca7985162eefe09", "parents": [ "ed926f9b35cda0988234c356e16a7cb30f4e5338" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Tue May 03 14:39:21 2011 -0400" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Wed May 18 15:29:47 2011 -0400" }, "message": "ftrace: Add enabled_functions file\n\nAdd the enabled_functions file that is used to show all the\nfunctions that have been enabled for tracing as well as their\nref counts. This helps seeing if any function has been registered\nand what functions are being traced.\n\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "ed926f9b35cda0988234c356e16a7cb30f4e5338", "tree": "32169b7aaf6b0ef7815b095a544cce93e884bb73", "parents": [ "33dc9b1267d59cef46ff0bd6bc043190845dc919" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Tue May 03 13:25:24 2011 -0400" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Wed May 18 15:29:47 2011 -0400" }, "message": "ftrace: Use counters to enable functions to trace\n\nEvery function has its own record that stores the instruction\npointer and flags for the function to be traced. There are only\ntwo flags: enabled and free. The enabled flag states that tracing\nfor the function has been enabled (actively traced), and the free\nflag states that the record no longer points to a function and can\nbe used by new functions (loaded modules).\n\nThese flags are now moved to the MSB of the flags (actually just\nthe top 32bits). The rest of the bits (30 bits) are now used as\na ref counter. Everytime a tracer register functions to trace,\nthose functions will have its counter incremented.\n\nWhen tracing is enabled, to determine if a function should be traced,\nthe counter is examined, and if it is non-zero it is set to trace.\n\nWhen a ftrace_ops is registered to trace functions, its hashes\nare examined. If the ftrace_ops filter_hash count is zero, then\nall functions are set to be traced, otherwise only the functions\nin the hash are to be traced. The exception to this is if a function\nis also in the ftrace_ops notrace_hash. Then that function\u0027s counter\nis not incremented for this ftrace_ops.\n\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "33dc9b1267d59cef46ff0bd6bc043190845dc919", "tree": "d5a3f78a6aabcd33b9848d3bf86b9b53ff6ea2e0", "parents": [ "f45948e898e7bc76a73a468796d2ce80dd040058" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Mon May 02 17:34:47 2011 -0400" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Wed May 18 15:29:46 2011 -0400" }, "message": "ftrace: Separate hash allocation and assignment\n\nWhen filtering, allocate a hash to insert the function records.\nAfter the filtering is complete, assign it to the ftrace_ops structure.\n\nThis allows the ftrace_ops structure to have a much smaller array of\nhash buckets instead of wasting a lot of memory.\n\nA read only empty_hash is created to be the minimum size that any ftrace_ops\ncan point to.\n\nWhen a new hash is created, it has the following steps:\n\no Allocate a default hash.\no Walk the function records assigning the filtered records to the hash\no Allocate a new hash with the appropriate size buckets\no Move the entries from the default hash to the new hash.\n\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "f45948e898e7bc76a73a468796d2ce80dd040058", "tree": "483979d8030cc2cf156ed65218c03a2d6825d9f5", "parents": [ "1cf41dd79993389b012e4542ab502ce36ae7343f" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Mon May 02 12:29:25 2011 -0400" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Wed May 18 15:29:45 2011 -0400" }, "message": "ftrace: Create a global_ops to hold the filter and notrace hashes\n\nCombine the filter and notrace hashes to be accessed by a single entity,\nthe global_ops. The global_ops is a ftrace_ops structure that is passed\nto different functions that can read or modify the filtering of the\nfunction tracer.\n\nThe ftrace_ops structure was modified to hold a filter and notrace\nhashes so that later patches may allow each ftrace_ops to have its own\nset of rules to what functions may be filtered.\n\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "1cf41dd79993389b012e4542ab502ce36ae7343f", "tree": "e1d0b58b2256d5936cff0c9d29ca8f68a80cedd8", "parents": [ "b448c4e3ae6d20108dba1d7833f2c0d3dbad87ce" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Fri Apr 29 20:59:51 2011 -0400" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Wed May 18 15:29:44 2011 -0400" }, "message": "ftrace: Use hash instead for FTRACE_FL_FILTER\n\nWhen multiple users are allowed to have their own set of functions\nto trace, having the FTRACE_FL_FILTER flag will not be enough to\nhandle the accounting of those users. Each user will need their own\nset of functions.\n\nReplace the FTRACE_FL_FILTER with a filter_hash instead. This is\ntemporary until the rest of the function filtering accounting\ngets in.\n\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "b448c4e3ae6d20108dba1d7833f2c0d3dbad87ce", "tree": "504e5a3640328458e652e41cfd2ed74e4652e5b3", "parents": [ "94692349c4fc1bc74c19a28f9379509361a06a3b" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Fri Apr 29 15:12:32 2011 -0400" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Wed May 18 15:29:44 2011 -0400" }, "message": "ftrace: Replace FTRACE_FL_NOTRACE flag with a hash of ignored functions\n\nTo prepare for the accounting system that will allow multiple users of\nthe function tracer, having the FTRACE_FL_NOTRACE as a flag in the\ndyn_trace record does not make sense.\n\nAll ftrace_ops will soon have a hash of functions they should trace\nand not trace. By making a global hash of functions not to trace makes\nthis easier for the transition.\n\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "ac0a3260f37b8616da8d33488ec94b94e6ae5b31", "tree": "0db61f7492d45f1d548b0bcef06a0df9c904442c", "parents": [ "809435ff4f43a5c0cb0201b3b89176253d5ade18", "b9df92d2a94eef8811061aecb1396290df440e2e" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Sun May 01 19:11:42 2011 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Sun May 01 19:11:42 2011 +0200" }, "message": "Merge branch \u0027tip/perf/core\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-2.6-trace into perf/core\n" }, { "commit": "b9df92d2a94eef8811061aecb1396290df440e2e", "tree": "313ad90dd3cd726af8da4d7768c912f96b3daa9a", "parents": [ "491d0dcfb9707e1f83eff93ca503eb7573162ef2" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Thu Apr 28 20:32:08 2011 -0400" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Fri Apr 29 22:53:14 2011 -0400" }, "message": "ftrace: Consolidate the function match routines for normal and mods\n\nThe code used for matching functions is almost identical between normal\nselecting of functions and using the :mod: feature of set_ftrace_notrace.\n\nConsolidate the two users into one function.\n\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "491d0dcfb9707e1f83eff93ca503eb7573162ef2", "tree": "ab156f8c4bc8ebfcc7429533a34726226a11bbba", "parents": [ "996e87be7f537fb34638875dd37083166c733425" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Wed Apr 27 21:43:36 2011 -0400" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Fri Apr 29 22:53:11 2011 -0400" }, "message": "ftrace: Consolidate updating of ftrace_trace_function\n\nThere are three locations that perform almost identical functions in order\nto update the ftrace_trace_function (the ftrace function variable that gets\ncalled by mcount).\n\nConsolidate these into a single function called update_ftrace_function().\n\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "996e87be7f537fb34638875dd37083166c733425", "tree": "0d961a4870b39450470b117cde45c3c2c1931959", "parents": [ "d2c8c3eafbf715306ec891e7ca52d3d999acbe31" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Tue Apr 26 16:11:03 2011 -0400" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Fri Apr 29 22:53:08 2011 -0400" }, "message": "ftrace: Move record update for normal and modules into a separate function\n\nThe updating of a function record is moved to a single function. This will allow\nus to add specific changes in one location for both modules and kernel\nfunctions.\n\nLater patches will determine if the function record itself needs to be updated\n(which enables the mcount caller), or just the ftrace_ops needs the update.\n\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "d2c8c3eafbf715306ec891e7ca52d3d999acbe31", "tree": "1dd5b7ae74f1dd951b542df3eb455af445a349c1", "parents": [ "45a4a2372b364107cabea79f255b333236626416" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Mon Apr 25 14:32:42 2011 -0400" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Fri Apr 29 22:53:04 2011 -0400" }, "message": "ftrace: Remove FTRACE_FL_CONVERTED flag\n\nSince we disable all function tracer processing if we detect\nthat a modification of a instruction had failed, we do not need\nto track that the record has failed. No more ftrace processing\nis allowed, and the FTRACE_FL_CONVERTED flag is pointless.\n\nThe FTRACE_FL_CONVERTED flag was used to denote records that were\nsuccessfully converted from mcount calls into nops. But if a single\nrecord fails, all of ftrace is disabled.\n\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "45a4a2372b364107cabea79f255b333236626416", "tree": "dfe3e1c3b55451fedc8896aaa8359677d583a0e5", "parents": [ "3499e461147636bf55c41128d83b679ac6ab2d86" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Thu Apr 21 23:16:46 2011 -0400" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Fri Apr 29 22:53:01 2011 -0400" }, "message": "ftrace: Remove FTRACE_FL_FAILED flag\n\nSince we disable all function tracer processing if we detect\nthat a modification of a instruction had failed, we do not need\nto track that the record has failed. No more ftrace processing\nis allowed, and the FTRACE_FL_FAILED flag is pointless.\n\nRemoving this flag simplifies some of the code, but some ftrace_disabled\nchecks needed to be added or move around a little.\n\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "3499e461147636bf55c41128d83b679ac6ab2d86", "tree": "2e79e9becedf3ac971b02160502c2384f9c3018a", "parents": [ "8ab2b7efd3e2ccf2c2dda3206b8171ecdbd0af40" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Thu Apr 21 22:59:12 2011 -0400" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Fri Apr 29 22:52:58 2011 -0400" }, "message": "ftrace: Remove failures file\n\nThe failures file in the debugfs tracing directory would list the\nfunctions that failed to convert when the old dead ftrace daemon\ntried to update code but failed. Since this code is now dead along\nwith the daemon the failures file is useless. Remove it.\n\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "8ab2b7efd3e2ccf2c2dda3206b8171ecdbd0af40", "tree": "69b3bbcdbbe7deecf3910ee28ee62e07c004a2ea", "parents": [ "0778d9ad33898faab7bf6316108b471790376e35" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Thu Apr 21 22:41:35 2011 -0400" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Fri Apr 29 22:52:55 2011 -0400" }, "message": "ftrace: Remove unnecessary disabling of irqs\n\nThe disabling of interrupts around ftrace_update_code() was used\nto protect against the evil ftrace daemon from years past. But that\ndaemon has long been killed. It is safe to keep interrupts enabled\nwhile updating the initial mcount into nops.\n\nThe ftrace_mutex is also held which keeps other users at bay.\n\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "0778d9ad33898faab7bf6316108b471790376e35", "tree": "c096fedf744e114a01acac52930f2bc8a741e863", "parents": [ "32673822e440eb92eb334631eb0a199d0c532d13" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Fri Apr 29 10:36:31 2011 -0400" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Fri Apr 29 22:52:52 2011 -0400" }, "message": "ftrace: Make FTRACE_WARN_ON() work in if condition\n\nLet FTRACE_WARN_ON() be used as a stand alone statement or\ninside a conditional: if (FTRACE_WARN_ON(x))\n\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "058e297d34a404caaa5ed277de15698d8dc43000", "tree": "0a4cfa547a4cf466f8c746978ff5fe464cbe88ab", "parents": [ "2bce5daca28346f19c190dbdb5542c9fe3e8c6e6" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Fri Apr 29 22:35:33 2011 -0400" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Fri Apr 29 22:42:59 2011 -0400" }, "message": "ftrace: Only update the function code on write to filter files\n\nIf function tracing is enabled, a read of the filter files will\ncause the call to stop_machine to update the function trace sites.\nIt should only call stop_machine on write.\n\nCc: stable@kernel.org\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "25985edcedea6396277003854657b5f3cb31a628", "tree": "f026e810210a2ee7290caeb737c23cb6472b7c38", "parents": [ "6aba74f2791287ec407e0f92487a725a25908067" ], "author": { "name": "Lucas De Marchi", "email": "lucas.demarchi@profusion.mobi", "time": "Wed Mar 30 22:57:33 2011 -0300" }, "committer": { "name": "Lucas De Marchi", "email": "lucas.demarchi@profusion.mobi", "time": "Thu Mar 31 11:26:23 2011 -0300" }, "message": "Fix common misspellings\n\nFixes generated by \u0027codespell\u0027 and manually reviewed.\n\nSigned-off-by: Lucas De Marchi \u003clucas.demarchi@profusion.mobi\u003e\n" }, { "commit": "1106b6997df7d0c0487e21fd9c9dd2ce3d4a52db", "tree": "638a067a0d407948fb5362b794d8de397c6aa421", "parents": [ "8df341cf251f3b77eaaef66f806570e74ab44452" ], "author": { "name": "Jiri Olsa", "email": "jolsa@redhat.com", "time": "Wed Feb 16 17:35:34 2011 +0100" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Tue Mar 22 12:52:03 2011 -0400" }, "message": "tracing: Fix set_ftrace_filter probe function display\n\nIf one or more function probes (like traceon) are enabled,\nand there\u0027s no other function filter, the first probe\nfunc is skipped (which one depends on the position in the hash).\n\n$ echo sys_open:traceon sys_close:traceon \u003e ./set_ftrace_filter\n$ cat set_ftrace_filter\n#### all functions enabled ####\nsys_close:traceon:unlimited\n$\n\nThe reason was, that in the case of no other function filter,\nthe func_pos was not properly updated before calling t_hash_start.\n\nSigned-off-by: Jiri Olsa \u003cjolsa@redhat.com\u003e\nLKML-Reference: \u003c1297874134-7008-1-git-send-email-jolsa@redhat.com\u003e\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "868baf07b1a259f5f3803c1dc2777b6c358f83cf", "tree": "a97caf3db1095ceb806ba53ba7d88d47a153e1b8", "parents": [ "862b6f62bf0cd768910b087f6d051f420206c4d6" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Thu Feb 10 21:26:13 2011 -0500" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Fri Feb 11 16:23:33 2011 -0500" }, "message": "ftrace: Fix memory leak with function graph and cpu hotplug\n\nWhen the fuction graph tracer starts, it needs to make a special\nstack for each task to save the real return values of the tasks.\nAll running tasks have this stack created, as well as any new\ntasks.\n\nOn CPU hot plug, the new idle task will allocate a stack as well\nwhen init_idle() is called. The problem is that cpu hotplug does\nnot create a new idle_task. Instead it uses the idle task that\nexisted when the cpu went down.\n\nftrace_graph_init_task() will add a new ret_stack to the task\nthat is given to it. Because a clone will make the task\nhave a stack of its parent it does not check if the task\u0027s\nret_stack is already NULL or not. When the CPU hotplug code\nstarts a CPU up again, it will allocate a new stack even\nthough one already existed for it.\n\nThe solution is to treat the idle_task specially. In fact, the\nfunction_graph code already does, just not at init_idle().\nInstead of using the ftrace_graph_init_task() for the idle task,\nwhich that function expects the task to be a clone, have a\nseparate ftrace_graph_init_idle_task(). Also, we will create a\nper_cpu ret_stack that is used by the idle task. When we call\nftrace_graph_init_idle_task() it will check if the idle task\u0027s\nret_stack is NULL, if it is, then it will assign it the per_cpu\nret_stack.\n\nReported-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\nSuggested-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: Stable Tree \u003cstable@kernel.org\u003e\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "092e0e7e520a1fca03e13c9f2d157432a8657ff2", "tree": "451897252c4c08c4b5a8ef535da156f1e817e80b", "parents": [ "79f14b7c56d3b3ba58f8b43d1f70b9b71477a800", "776c163b1b93c8dfa5edba885bc2bfbc2d228a5f" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Fri Oct 22 10:52:56 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Fri Oct 22 10:52:56 2010 -0700" }, "message": "Merge branch \u0027llseek\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/arnd/bkl\n\n* \u0027llseek\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/arnd/bkl:\n vfs: make no_llseek the default\n vfs: don\u0027t use BKL in default_llseek\n llseek: automatically add .llseek fop\n libfs: use generic_file_llseek for simple_attr\n mac80211: disallow seeks in minstrel debug code\n lirc: make chardev nonseekable\n viotape: use noop_llseek\n raw: use explicit llseek file operations\n ibmasmfs: use generic_file_llseek\n spufs: use llseek in all file operations\n arm/omap: use generic_file_llseek in iommu_debug\n lkdtm: use generic_file_llseek in debugfs\n net/wireless: use generic_file_llseek in debugfs\n drm: use noop_llseek\n" }, { "commit": "907f27840985fe6a0c62e43cd4702c6e04b4bcc7", "tree": "1023e32295a25e0602aef4bab14f41b97975f6bd", "parents": [ "f92f6e6ee35d2779aa62e70f78ad8e1cd417eb52" ], "author": { "name": "matt mooney", "email": "mfm@muteddisk.com", "time": "Mon Sep 27 19:04:53 2010 -0700" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Mon Oct 18 10:53:22 2010 -0400" }, "message": "tracing/trivial: Remove cast from void*\n\nUnnecessary cast from void* in assignment.\n\nSigned-off-by: matt mooney \u003cmfm@muteddisk.com\u003e\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "6038f373a3dc1f1c26496e60b6c40b164716f07e", "tree": "a0d3bbd026eea41b9fc36b8c722cbaf56cd9f825", "parents": [ "1ec5584e3edf9c4bf2c88c846534d19cf986ba11" ], "author": { "name": "Arnd Bergmann", "email": "arnd@arndb.de", "time": "Sun Aug 15 18:52:59 2010 +0200" }, "committer": { "name": "Arnd Bergmann", "email": "arnd@arndb.de", "time": "Fri Oct 15 15:53:27 2010 +0200" }, "message": "llseek: automatically add .llseek fop\n\nAll file_operations should get a .llseek operation so we can make\nnonseekable_open the default for future file operations without a\n.llseek pointer.\n\nThe three cases that we can automatically detect are no_llseek, seq_lseek\nand default_llseek. For cases where we can we can automatically prove that\nthe file offset is always ignored, we use noop_llseek, which maintains\nthe current behavior of not returning an error from a seek.\n\nNew drivers should normally not use noop_llseek but instead use no_llseek\nand call nonseekable_open at open time. Existing drivers can be converted\nto do the same when the maintainer knows for certain that no user code\nrelies on calling seek on the device file.\n\nThe generated code is often incorrectly indented and right now contains\ncomments that clarify for each added line why a specific variant was\nchosen. In the version that gets submitted upstream, the comments will\nbe gone and I will manually fix the indentation, because there does not\nseem to be a way to do that using coccinelle.\n\nSome amount of new code is currently sitting in linux-next that should get\nthe same modifications, which I will do at the end of the merge window.\n\nMany thanks to Julia Lawall for helping me learn to write a semantic\npatch that does all this.\n\n\u003d\u003d\u003d\u003d\u003d begin semantic patch \u003d\u003d\u003d\u003d\u003d\n// This adds an llseek\u003d method to all file operations,\n// as a preparation for making no_llseek the default.\n//\n// The rules are\n// - use no_llseek explicitly if we do nonseekable_open\n// - use seq_lseek for sequential files\n// - use default_llseek if we know we access f_pos\n// - use noop_llseek if we know we don\u0027t access f_pos,\n// but we still want to allow users to call lseek\n//\n@ open1 exists @\nidentifier nested_open;\n@@\nnested_open(...)\n{\n\u003c+...\nnonseekable_open(...)\n...+\u003e\n}\n\n@ open exists@\nidentifier open_f;\nidentifier i, f;\nidentifier open1.nested_open;\n@@\nint open_f(struct inode *i, struct file *f)\n{\n\u003c+...\n(\nnonseekable_open(...)\n|\nnested_open(...)\n)\n...+\u003e\n}\n\n@ read disable optional_qualifier exists @\nidentifier read_f;\nidentifier f, p, s, off;\ntype ssize_t, size_t, loff_t;\nexpression E;\nidentifier func;\n@@\nssize_t read_f(struct file *f, char *p, size_t s, loff_t *off)\n{\n\u003c+...\n(\n *off \u003d E\n|\n *off +\u003d E\n|\n func(..., off, ...)\n|\n E \u003d *off\n)\n...+\u003e\n}\n\n@ read_no_fpos disable optional_qualifier exists @\nidentifier read_f;\nidentifier f, p, s, off;\ntype ssize_t, size_t, loff_t;\n@@\nssize_t read_f(struct file *f, char *p, size_t s, loff_t *off)\n{\n... when !\u003d off\n}\n\n@ write @\nidentifier write_f;\nidentifier f, p, s, off;\ntype ssize_t, size_t, loff_t;\nexpression E;\nidentifier func;\n@@\nssize_t write_f(struct file *f, const char *p, size_t s, loff_t *off)\n{\n\u003c+...\n(\n *off \u003d E\n|\n *off +\u003d E\n|\n func(..., off, ...)\n|\n E \u003d *off\n)\n...+\u003e\n}\n\n@ write_no_fpos @\nidentifier write_f;\nidentifier f, p, s, off;\ntype ssize_t, size_t, loff_t;\n@@\nssize_t write_f(struct file *f, const char *p, size_t s, loff_t *off)\n{\n... when !\u003d off\n}\n\n@ fops0 @\nidentifier fops;\n@@\nstruct file_operations fops \u003d {\n ...\n};\n\n@ has_llseek depends on fops0 @\nidentifier fops0.fops;\nidentifier llseek_f;\n@@\nstruct file_operations fops \u003d {\n...\n .llseek \u003d llseek_f,\n...\n};\n\n@ has_read depends on fops0 @\nidentifier fops0.fops;\nidentifier read_f;\n@@\nstruct file_operations fops \u003d {\n...\n .read \u003d read_f,\n...\n};\n\n@ has_write depends on fops0 @\nidentifier fops0.fops;\nidentifier write_f;\n@@\nstruct file_operations fops \u003d {\n...\n .write \u003d write_f,\n...\n};\n\n@ has_open depends on fops0 @\nidentifier fops0.fops;\nidentifier open_f;\n@@\nstruct file_operations fops \u003d {\n...\n .open \u003d open_f,\n...\n};\n\n// use no_llseek if we call nonseekable_open\n////////////////////////////////////////////\n@ nonseekable1 depends on !has_llseek \u0026\u0026 has_open @\nidentifier fops0.fops;\nidentifier nso ~\u003d \"nonseekable_open\";\n@@\nstruct file_operations fops \u003d {\n... .open \u003d nso, ...\n+.llseek \u003d no_llseek, /* nonseekable */\n};\n\n@ nonseekable2 depends on !has_llseek @\nidentifier fops0.fops;\nidentifier open.open_f;\n@@\nstruct file_operations fops \u003d {\n... .open \u003d open_f, ...\n+.llseek \u003d no_llseek, /* open uses nonseekable */\n};\n\n// use seq_lseek for sequential files\n/////////////////////////////////////\n@ seq depends on !has_llseek @\nidentifier fops0.fops;\nidentifier sr ~\u003d \"seq_read\";\n@@\nstruct file_operations fops \u003d {\n... .read \u003d sr, ...\n+.llseek \u003d seq_lseek, /* we have seq_read */\n};\n\n// use default_llseek if there is a readdir\n///////////////////////////////////////////\n@ fops1 depends on !has_llseek \u0026\u0026 !nonseekable1 \u0026\u0026 !nonseekable2 \u0026\u0026 !seq @\nidentifier fops0.fops;\nidentifier readdir_e;\n@@\n// any other fop is used that changes pos\nstruct file_operations fops \u003d {\n... .readdir \u003d readdir_e, ...\n+.llseek \u003d default_llseek, /* readdir is present */\n};\n\n// use default_llseek if at least one of read/write touches f_pos\n/////////////////////////////////////////////////////////////////\n@ fops2 depends on !fops1 \u0026\u0026 !has_llseek \u0026\u0026 !nonseekable1 \u0026\u0026 !nonseekable2 \u0026\u0026 !seq @\nidentifier fops0.fops;\nidentifier read.read_f;\n@@\n// read fops use offset\nstruct file_operations fops \u003d {\n... .read \u003d read_f, ...\n+.llseek \u003d default_llseek, /* read accesses f_pos */\n};\n\n@ fops3 depends on !fops1 \u0026\u0026 !fops2 \u0026\u0026 !has_llseek \u0026\u0026 !nonseekable1 \u0026\u0026 !nonseekable2 \u0026\u0026 !seq @\nidentifier fops0.fops;\nidentifier write.write_f;\n@@\n// write fops use offset\nstruct file_operations fops \u003d {\n... .write \u003d write_f, ...\n+\t.llseek \u003d default_llseek, /* write accesses f_pos */\n};\n\n// Use noop_llseek if neither read nor write accesses f_pos\n///////////////////////////////////////////////////////////\n\n@ fops4 depends on !fops1 \u0026\u0026 !fops2 \u0026\u0026 !fops3 \u0026\u0026 !has_llseek \u0026\u0026 !nonseekable1 \u0026\u0026 !nonseekable2 \u0026\u0026 !seq @\nidentifier fops0.fops;\nidentifier read_no_fpos.read_f;\nidentifier write_no_fpos.write_f;\n@@\n// write fops use offset\nstruct file_operations fops \u003d {\n...\n .write \u003d write_f,\n .read \u003d read_f,\n...\n+.llseek \u003d noop_llseek, /* read and write both use no f_pos */\n};\n\n@ depends on has_write \u0026\u0026 !has_read \u0026\u0026 !fops1 \u0026\u0026 !fops2 \u0026\u0026 !has_llseek \u0026\u0026 !nonseekable1 \u0026\u0026 !nonseekable2 \u0026\u0026 !seq @\nidentifier fops0.fops;\nidentifier write_no_fpos.write_f;\n@@\nstruct file_operations fops \u003d {\n... .write \u003d write_f, ...\n+.llseek \u003d noop_llseek, /* write uses no f_pos */\n};\n\n@ depends on has_read \u0026\u0026 !has_write \u0026\u0026 !fops1 \u0026\u0026 !fops2 \u0026\u0026 !has_llseek \u0026\u0026 !nonseekable1 \u0026\u0026 !nonseekable2 \u0026\u0026 !seq @\nidentifier fops0.fops;\nidentifier read_no_fpos.read_f;\n@@\nstruct file_operations fops \u003d {\n... .read \u003d read_f, ...\n+.llseek \u003d noop_llseek, /* read uses no f_pos */\n};\n\n@ depends on !has_read \u0026\u0026 !has_write \u0026\u0026 !fops1 \u0026\u0026 !fops2 \u0026\u0026 !has_llseek \u0026\u0026 !nonseekable1 \u0026\u0026 !nonseekable2 \u0026\u0026 !seq @\nidentifier fops0.fops;\n@@\nstruct file_operations fops \u003d {\n...\n+.llseek \u003d noop_llseek, /* no read or write fn */\n};\n\u003d\u003d\u003d\u003d\u003d End semantic patch \u003d\u003d\u003d\u003d\u003d\n\nSigned-off-by: Arnd Bergmann \u003carnd@arndb.de\u003e\nCc: Julia Lawall \u003cjulia@diku.dk\u003e\nCc: Christoph Hellwig \u003chch@infradead.org\u003e\n" }, { "commit": "3aabae7d9dfaed60effe93662f02c19bafc18537", "tree": "af94cdd69add07601d9f3f5988dfc1dc255e3886", "parents": [ "79e406d7b00ab2b261ae32a59f266fd3b7af6f29", "57c072c7113f54f9512624d6c665db6184448782" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Wed Sep 15 10:27:31 2010 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Wed Sep 15 10:27:31 2010 +0200" }, "message": "Merge branch \u0027tip/perf/core\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-2.6-trace into perf/core\n" }, { "commit": "79e406d7b00ab2b261ae32a59f266fd3b7af6f29", "tree": "e1f635e807691cb634fd63478861938592f226fa", "parents": [ "b304d0441a4118fadd4c3f16e4dc600c271030b5" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Tue Sep 14 22:19:46 2010 -0400" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Tue Sep 14 22:19:46 2010 -0400" }, "message": "tracing: Remove leftover FTRACE_ENABLE/DISABLE_MCOUNT enums\n\nThe enums for FTRACE_ENABLE_MCOUNT and FTRACE_DISABLE_MCOUNT were\nused as commands to ftrace_run_update_code(). But these commands\nwere used by the old nasty ftrace daemon that has long been slain.\n\nThis is a clean up patch to remove the references to these enums\nand simplify the code a little.\n\nReported-by: Wu Zhangjin \u003cwuzhangjin@gmail.com\u003e\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "57c072c7113f54f9512624d6c665db6184448782", "tree": "c005a9325d308763bd1763853395c7b13010b5e3", "parents": [ "98c4fd046f07156ca6055677e8f03d4280be16c1" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Tue Sep 14 11:21:11 2010 -0400" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Tue Sep 14 15:14:20 2010 -0400" }, "message": "tracing: Fix reading of set_ftrace_filter across lists\n\nIf we do:\n\n # cd /sys/kernel/debug\n # echo \u0027do_IRQ:traceon schedule:traceon sys_write:traceon\u0027 \u003e \\\n set_ftrace_filter\n # cat set_ftrace_filter\n\nWe get the following output:\n\n #### all functions enabled ####\n sys_write:traceon:unlimited\n schedule:traceon:unlimited\n do_IRQ:traceon:unlimited\n\nThis outputs two lists. One is the fact that all functions are\ncurrently enabled for function tracing, the other has three probed\nfunctions, which happen to have \u0027traceon\u0027 as their commands.\n\nCurrently, when reading the first list (functions enabled) the\nseq_file code will receive a \"NULL\" from the t_next() function\ncausing it to exit early. This makes \"read()\" from userspace stop\nreading the code at this boarder. Although read is allowed to do this,\nsome (broken) applications might consider this an end of file and\nstop early.\n\nThis patch adds the start of the second list to t_next() when it\nfinishes the first list. It is a simple change and gives the\nset_ftrace_filter file nicer reading ability.\n\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "98c4fd046f07156ca6055677e8f03d4280be16c1", "tree": "bf461479713dbbaf79b0bf1a50a3ba0f30a2f17c", "parents": [ "4aeb69672d011fac5c8df671f3ca89f7987c104e" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Fri Sep 10 11:47:43 2010 -0400" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Tue Sep 14 14:46:01 2010 -0400" }, "message": "tracing: Keep track of set_ftrace_filter position and allow lseek again\n\nThis patch keeps track of the index within the elements of\nset_ftrace_filter and if the position goes backwards, it nicely\nresets and starts from the beginning again.\n\nThis allows for lseek and pread to work properly now.\n\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "4aeb69672d011fac5c8df671f3ca89f7987c104e", "tree": "d2a96af23b9d6ac742725bb17aafe3d4b377cb6a", "parents": [ "2bccfffd1538f3523847583213567e2f7ce00926" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Thu Sep 09 10:00:28 2010 -0400" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Tue Sep 14 11:42:30 2010 -0400" }, "message": "tracing: Replace typecasted void pointer in set_ftrace_filter code\n\nThe set_ftrace_filter uses seq_file and reads from two lists. The\npointer returned by t_next() can either be of type struct dyn_ftrace\nor struct ftrace_func_probe. If there is a bug (there was one)\nthe wrong pointer may be used and the reference can cause an oops.\n\nThis patch makes t_next() and friends only return the iterator structure\nwhich now has a pointer of type struct dyn_ftrace and struct\nftrace_func_probe. The t_show() can now test if the pointer is NULL or\nnot and if the pointer exists, it is guaranteed to be of the correct type.\n\nNow if there\u0027s a bug, only wrong data will be shown but not an oops.\n\nCc: Chris Wright \u003cchrisw@sous-sol.org\u003e\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "2bccfffd1538f3523847583213567e2f7ce00926", "tree": "7062e0bfc46f66efa2ec3231a6c718a901a0a80c", "parents": [ "bfa88ea7ee9e6b4fd673e45a8cc0a8e0b7ef4761" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Thu Sep 09 08:43:22 2010 -0400" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Tue Sep 14 11:42:29 2010 -0400" }, "message": "tracing: Do not reset *pos in set_ftrace_filter\n\nAfter the filtered functions are read, the probed functions are read\nfrom the hash in set_ftrace_filter. When the hashed probed functions\nare read, the *pos passed in is reset. Instead of modifying the pos\ngiven to the read function, just record the pos where the filtered\nfunctions ended and subtract from that.\n\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "df09162550fbb53354f0c88e85b5d0e6129ee9cc", "tree": "e8ba6014c442cf72d587948733f8c29e0d330925", "parents": [ "5e11637e2c929e34dcc0fbbfb48bdb638937701a" ], "author": { "name": "Chris Wright", "email": "chrisw@sous-sol.org", "time": "Thu Sep 09 16:34:59 2010 -0700" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Thu Sep 09 22:43:49 2010 -0400" }, "message": "tracing: t_start: reset FTRACE_ITER_HASH in case of seek/pread\n\nBe sure to avoid entering t_show() with FTRACE_ITER_HASH set without\nhaving properly started the iterator to iterate the hash. This case is\ndegenerate and, as discovered by Robert Swiecki, can cause t_hash_show()\nto misuse a pointer. This causes a NULL ptr deref with possible security\nimplications. Tracked as CVE-2010-3079.\n\nCc: Robert Swiecki \u003cswiecki@google.com\u003e\nCc: Eugene Teo \u003ceugene@redhat.com\u003e\nCc: \u003cstable@kernel.org\u003e\nSigned-off-by: Chris Wright \u003cchrisw@sous-sol.org\u003e\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "9c55cb12c1c172e2d51e85fbb5a4796ca86b77e7", "tree": "0f86d1e27fbfc31cba108e71643d686315468db9", "parents": [ "4177c42a6301a34c20038ec2771a33dcc30bb338" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Wed Sep 08 11:20:37 2010 -0400" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Wed Sep 08 12:08:01 2010 -0400" }, "message": "tracing: Do not allow llseek to set_ftrace_filter\n\nReading the file set_ftrace_filter does three things.\n\n1) shows whether or not filters are set for the function tracer\n2) shows what functions are set for the function tracer\n3) shows what triggers are set on any functions\n\n3 is independent from 1 and 2.\n\nThe way this file currently works is that it is a state machine,\nand as you read it, it may change state. But this assumption breaks\nwhen you use lseek() on the file. The state machine gets out of sync\nand the t_show() may use the wrong pointer and cause a kernel oops.\n\nLuckily, this will only kill the app that does the lseek, but the app\ndies while holding a mutex. This prevents anyone else from using the\nset_ftrace_filter file (or any other function tracing file for that matter).\n\nA real fix for this is to rewrite the code, but that is too much for\na -rc release or stable. This patch simply disables llseek on the\nset_ftrace_filter() file for now, and we can do the proper fix for the\nnext major release.\n\nReported-by: Robert Swiecki \u003cswiecki@google.com\u003e\nCc: Chris Wright \u003cchrisw@sous-sol.org\u003e\nCc: Tavis Ormandy \u003ctaviso@google.com\u003e\nCc: Eugene Teo \u003ceugene@redhat.com\u003e\nCc: vendor-sec@lst.de\nCc: \u003cstable@kernel.org\u003e\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "3aaba20f26f58843e8f20611e5c0b1c06954310f", "tree": "ad15d7aa21af465ddf6091eb490d84312089f245", "parents": [ "fa66f07aa1f0950e1dc78b7ab39728b3f8aa77a1" ], "author": { "name": "Li Zefan", "email": "lizf@cn.fujitsu.com", "time": "Mon Aug 23 16:50:12 2010 +0800" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Tue Aug 31 16:46:23 2010 -0400" }, "message": "tracing: Fix a race in function profile\n\nWhile we are reading trace_stat/functionX and someone just\ndisabled function_profile at that time, we can trigger this:\n\n\tdivide error: 0000 [#1] PREEMPT SMP\n\t...\n\tEIP is at function_stat_show+0x90/0x230\n\t...\n\nThis fix just takes the ftrace_profile_lock and checks if\nrec-\u003ecounter is 0. If it\u0027s 0, we know the profile buffer\nhas been reset.\n\nSigned-off-by: Li Zefan \u003clizf@cn.fujitsu.com\u003e\nCc: stable@kernel.org\nLKML-Reference: \u003c4C723644.4040708@cn.fujitsu.com\u003e\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "5168ae50a66e3ff7184c2b16d661bd6d70367e50", "tree": "2fb21fc3bd346e4f589605d940dfb1bacac30bf5", "parents": [ "d1f74e20b5b064a130cd0743a256c2d3cfe84010" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Thu Jun 03 09:36:50 2010 -0400" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Thu Jun 03 19:32:38 2010 -0400" }, "message": "tracing: Remove ftrace_preempt_disable/enable\n\nThe ftrace_preempt_disable/enable functions were to address a\nrecursive race caused by the function tracer. The function tracer\ntraces all functions which makes it easily susceptible to recursion.\nOne area was preempt_enable(). This would call the scheduler and\nthe schedulre would call the function tracer and loop.\n(So was it thought).\n\nThe ftrace_preempt_disable/enable was made to protect against recursion\ninside the scheduler by storing the NEED_RESCHED flag. If it was\nset before the ftrace_preempt_disable() it would not call schedule\non ftrace_preempt_enable(), thinking that if it was set before then\nit would have already scheduled unless it was already in the scheduler.\n\nThis worked fine except in the case of SMP, where another task would set\nthe NEED_RESCHED flag for a task on another CPU, and then kick off an\nIPI to trigger it. This could cause the NEED_RESCHED to be saved at\nftrace_preempt_disable() but the IPI to arrive in the the preempt\ndisabled section. The ftrace_preempt_enable() would not call the scheduler\nbecause the flag was already set before entring the section.\n\nThis bug would cause a missed preemption check and cause lower latencies.\n\nInvestigating further, I found that the recusion caused by the function\ntracer was not due to schedule(), but due to preempt_schedule(). Now\nthat preempt_schedule is completely annotated with notrace, the recusion\nno longer is an issue.\n\nReported-by: Thomas Gleixner \u003ctglx@linutronix.de\u003e\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "38516ab59fbc5b3bb278cf5e1fe2867c70cff32e", "tree": "904476d7780a27001281b9cb93c7959128f9a1d7", "parents": [ "53da59aa6dd881fd0bbdd058a8a299d90ce9dd1d" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Tue Apr 20 17:04:50 2010 -0400" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Fri May 14 09:50:34 2010 -0400" }, "message": "tracing: Let tracepoints have data passed to tracepoint callbacks\n\nThis patch adds data to be passed to tracepoint callbacks.\n\nThe created functions from DECLARE_TRACE() now need a mandatory data\nparameter. For example:\n\nDECLARE_TRACE(mytracepoint, int value, value)\n\nWill create the register function:\n\nint register_trace_mytracepoint((void(*)(void *data, int value))probe,\n void *data);\n\nAs the first argument, all callbacks (probes) must take a (void *data)\nparameter. So a callback for the above tracepoint will look like:\n\nvoid myprobe(void *data, int value)\n{\n}\n\nThe callback may choose to ignore the data parameter.\n\nThis change allows callbacks to register a private data pointer along\nwith the function probe.\n\n\tvoid mycallback(void *data, int value);\n\n\tregister_trace_mytracepoint(mycallback, mydata);\n\nThen the mycallback() will receive the \"mydata\" as the first parameter\nbefore the args.\n\nA more detailed example:\n\n DECLARE_TRACE(mytracepoint, TP_PROTO(int status), TP_ARGS(status));\n\n /* In the C file */\n\n DEFINE_TRACE(mytracepoint, TP_PROTO(int status), TP_ARGS(status));\n\n [...]\n\n trace_mytracepoint(status);\n\n /* In a file registering this tracepoint */\n\n int my_callback(void *data, int status)\n {\n\tstruct my_struct my_data \u003d data;\n\t[...]\n }\n\n [...]\n\tmy_data \u003d kmalloc(sizeof(*my_data), GFP_KERNEL);\n\tinit_my_data(my_data);\n\tregister_trace_mytracepoint(my_callback, my_data);\n\nThe same callback can also be registered to the same tracepoint as long\nas the data registered is different. Note, the data must also be used\nto unregister the callback:\n\n\tunregister_trace_mytracepoint(my_callback, my_data);\n\nBecause of the data parameter, tracepoints declared this way can not have\nno args. That is:\n\n DECLARE_TRACE(mytracepoint, TP_PROTO(void), TP_ARGS());\n\nwill cause an error.\n\nIf no arguments are needed, a new macro can be used instead:\n\n DECLARE_TRACE_NOARGS(mytracepoint);\n\nSince there are no arguments, the proto and args fields are left out.\n\nThis is part of a series to make the tracepoint footprint smaller:\n\n text\t data\t bss\t dec\t hex\tfilename\n4913961\t1088356\t 861512\t6863829\t 68bbd5\tvmlinux.orig\n4914025\t1088868\t 861512\t6864405\t 68be15\tvmlinux.class\n4918492\t1084612\t 861512\t6864616\t 68bee8\tvmlinux.tracepoint\n\nAgain, this patch also increases the size of the kernel, but\nlays the ground work for decreasing it.\n\n v5: Fixed net/core/drop_monitor.c to handle these updates.\n\n v4: Moved the DECLARE_TRACE() DECLARE_TRACE_NOARGS out of the\n #ifdef CONFIG_TRACE_POINTS, since the two are the same in both\n cases. The __DECLARE_TRACE() is what changes.\n Thanks to Frederic Weisbecker for pointing this out.\n\n v3: Made all register_* functions require data to be passed and\n all callbacks to take a void * parameter as its first argument.\n This makes the calling functions comply with C standards.\n\n Also added more comments to the modifications of DECLARE_TRACE().\n\n v2: Made the DECLARE_TRACE() have the ability to pass arguments\n and added a new DECLARE_TRACE_NOARGS() for tracepoints that\n do not need any arguments.\n\nAcked-by: Mathieu Desnoyers \u003cmathieu.desnoyers@efficios.com\u003e\nAcked-by: Masami Hiramatsu \u003cmhiramat@redhat.com\u003e\nAcked-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Neil Horman \u003cnhorman@tuxdriver.com\u003e\nCc: David S. Miller \u003cdavem@davemloft.net\u003e\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "23e117fa44429cc054cb27d5621d64e4ced91e52", "tree": "a4b9d0902b9c6f009b2c297515221c1b9bed3af8", "parents": [ "668eb65f092902eb7dd526af73d4a7f025a94612", "a93d2f1744206827ccf416e2cdc5018aa503314e" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Fri May 14 09:29:52 2010 -0400" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Fri May 14 09:29:52 2010 -0400" }, "message": "Merge branch \u0027sched/core\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip into trace/tip/tracing/core-4\n" }, { "commit": "27a9da6538ee18046d7bff8e36a9f783542c54c3", "tree": "9f9944ca8742ec52f7e4a674f7475fc0378abdb8", "parents": [ "48652ced1533c3372f996a0d83b6e73b1f1c9381" ], "author": { "name": "Peter Zijlstra", "email": "a.p.zijlstra@chello.nl", "time": "Tue May 04 20:36:56 2010 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Fri May 07 11:28:17 2010 +0200" }, "message": "sched: Remove rq argument to the tracepoints\n\nstruct rq isn\u0027t visible outside of sched.o so its near useless to\nexpose the pointer, also there are no users of it, so remove it.\n\nAcked-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nLKML-Reference: \u003c1272997616.1642.207.camel@laptop\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "37e44bc50d91df1fe7edcf6f02fe168c6d802e64", "tree": "40058a2b27e94400dc4345ba13b334fb732ae532", "parents": [ "e330b3bcd83199dd63a819d8d12e40f9edae6c77" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Tue Apr 27 21:04:24 2010 -0400" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Tue Apr 27 21:04:24 2010 -0400" }, "message": "tracing: Fix sleep time function profiling\n\nWhen sleep_time is off the function profiler ignores the time that a task\nis scheduled out. When the task is scheduled out a timestamp is taken.\nWhen the task is scheduled back in, the timestamp is compared to the\ncurrent time and the saved calltimes are adjusted accordingly.\n\nBut when stopping the function profiler, the sched switch hook that\ndoes this adjustment was stopped before shutting down the tracer.\nThis allowed some tasks to not get their timestamps set when they\nscheduled out. When the function profiler started again, this would\nskew the times of the scheduler functions.\n\nThis patch moves the stopping of the sched switch to after the function\nprofiler is stopped. It also ignores zero set calltimes, which may\nhappen on start up.\n\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "e330b3bcd83199dd63a819d8d12e40f9edae6c77", "tree": "45d488ed1f112db14ca180af5f4d2d09515a1f09", "parents": [ "07271aa42d13378e67ebd79ea9ca1c4a5e2ad46f" ], "author": { "name": "Chase Douglas", "email": "chase.douglas@canonical.com", "time": "Mon Apr 26 14:02:05 2010 -0400" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Tue Apr 27 18:23:15 2010 -0400" }, "message": "tracing: Show sample std dev in function profiling\n\nWhen combined with function graph tracing the ftrace function profiler\nalso prints the average run time of functions. While this gives us some\ngood information, it doesn\u0027t tell us anything about the variance of the\nrun times of the function. This change prints out the s^2 sample\nstandard deviation alongside the average.\n\nThis change adds one entry to the profile record structure. This\nincreases the memory footprint of the function profiler by 1/3 on a\n32-bit system, and by 1/5 on a 64-bit system when function graphing is\nenabled, though the memory is only allocated when the profiler is turned\non. During the profiling, one extra line of code adds the squared\ncalltime to the new record entry, so this should not adversly affect\nperformance.\n\nNote that the square of the sample standard deviation is printed because\nthere is no sqrt implementation for unsigned long long in the kernel.\n\nSigned-off-by: Chase Douglas \u003cchase.douglas@canonical.com\u003e\nLKML-Reference: \u003c1272304925-2436-1-git-send-email-chase.douglas@canonical.com\u003e\n\n[ fixed comment about ns^2 -\u003e us^2 conversion ]\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "5a0e3ad6af8660be21ca98a971cd00f331318c05", "tree": "5bfb7be11a03176a87296a43ac6647975c00a1d1", "parents": [ "ed391f4ebf8f701d3566423ce8f17e614cde9806" ], "author": { "name": "Tejun Heo", "email": "tj@kernel.org", "time": "Wed Mar 24 17:04:11 2010 +0900" }, "committer": { "name": "Tejun Heo", "email": "tj@kernel.org", "time": "Tue Mar 30 22:02:32 2010 +0900" }, "message": "include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h\n\npercpu.h is included by sched.h and module.h and thus ends up being\nincluded when building most .c files. percpu.h includes slab.h which\nin turn includes gfp.h making everything defined by the two files\nuniversally available and complicating inclusion dependencies.\n\npercpu.h -\u003e slab.h dependency is about to be removed. Prepare for\nthis change by updating users of gfp and slab facilities include those\nheaders directly instead of assuming availability. As this conversion\nneeds to touch large number of source files, the following script is\nused as the basis of conversion.\n\n http://userweb.kernel.org/~tj/misc/slabh-sweep.py\n\nThe script does the followings.\n\n* Scan files for gfp and slab usages and update includes such that\n only the necessary includes are there. ie. if only gfp is used,\n gfp.h, if slab is used, slab.h.\n\n* When the script inserts a new include, it looks at the include\n blocks and try to put the new include such that its order conforms\n to its surrounding. It\u0027s put in the include block which contains\n core kernel includes, in the same order that the rest are ordered -\n alphabetical, Christmas tree, rev-Xmas-tree or at the end if there\n doesn\u0027t seem to be any matching order.\n\n* If the script can\u0027t find a place to put a new include (mostly\n because the file doesn\u0027t have fitting include block), it prints out\n an error message indicating which .h file needs to be added to the\n file.\n\nThe conversion was done in the following steps.\n\n1. The initial automatic conversion of all .c files updated slightly\n over 4000 files, deleting around 700 includes and adding ~480 gfp.h\n and ~3000 slab.h inclusions. The script emitted errors for ~400\n files.\n\n2. Each error was manually checked. Some didn\u0027t need the inclusion,\n some needed manual addition while adding it to implementation .h or\n embedding .c file was more appropriate for others. This step added\n inclusions to around 150 files.\n\n3. The script was run again and the output was compared to the edits\n from #2 to make sure no file was left behind.\n\n4. Several build tests were done and a couple of problems were fixed.\n e.g. lib/decompress_*.c used malloc/free() wrappers around slab\n APIs requiring slab.h to be added manually.\n\n5. The script was run on all .h files but without automatically\n editing them as sprinkling gfp.h and slab.h inclusions around .h\n files could easily lead to inclusion dependency hell. Most gfp.h\n inclusion directives were ignored as stuff from gfp.h was usually\n wildly available and often used in preprocessor macros. Each\n slab.h inclusion directive was examined and added manually as\n necessary.\n\n6. percpu.h was updated not to include slab.h.\n\n7. Build test were done on the following configurations and failures\n were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my\n distributed build env didn\u0027t work with gcov compiles) and a few\n more options had to be turned off depending on archs to make things\n build (like ipr on powerpc/64 which failed due to missing writeq).\n\n * x86 and x86_64 UP and SMP allmodconfig and a custom test config.\n * powerpc and powerpc64 SMP allmodconfig\n * sparc and sparc64 SMP allmodconfig\n * ia64 SMP allmodconfig\n * s390 SMP allmodconfig\n * alpha SMP allmodconfig\n * um on x86_64 SMP allmodconfig\n\n8. percpu.h modifications were reverted so that it could be applied as\n a separate patch and serve as bisection point.\n\nGiven the fact that I had only a couple of failures from tests on step\n6, I\u0027m fairly confident about the coverage of this conversion patch.\nIf there is a breakage, it\u0027s likely to be something in one of the arch\nheaders which should be easily discoverable easily on most builds of\nthe specific arch.\n\nSigned-off-by: Tejun Heo \u003ctj@kernel.org\u003e\nGuess-its-ok-by: Christoph Lameter \u003ccl@linux-foundation.org\u003e\nCc: Ingo Molnar \u003cmingo@redhat.com\u003e\nCc: Lee Schermerhorn \u003cLee.Schermerhorn@hp.com\u003e\n" }, { "commit": "4e3eaddd142e2142c048c5052a0a9d2604fccfc6", "tree": "5bc45a286502e54e790c54948f22364c5afd9d89", "parents": [ "8655e7e3ddec60603c4f6c14cdf642e2ba198df8", "b97c4bc16734a2e597dac7f91ee9eb78f4aeef9a" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Sat Mar 13 14:43:01 2010 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Sat Mar 13 14:43:01 2010 -0800" }, "message": "Merge branch \u0027core-fixes-for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip\n\n* \u0027core-fixes-for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:\n locking: Make sparse work with inline spinlocks and rwlocks\n x86/mce: Fix RCU lockdep splats\n rcu: Increase RCU CPU stall timeouts if PROVE_RCU\n ftrace: Replace read_barrier_depends() with rcu_dereference_raw()\n rcu: Suppress RCU lockdep warnings during early boot\n rcu, ftrace: Fix RCU lockdep splat in ftrace_perf_buf_prepare()\n rcu: Suppress __mpol_dup() false positive from RCU lockdep\n rcu: Make rcu_read_lock_sched_held() handle !PREEMPT\n rcu: Add control variables to lockdep_rcu_dereference() diagnostics\n rcu, cgroup: Relax the check in task_subsys_state() as early boot is now handled by lockdep-RCU\n rcu: Use wrapper function instead of exporting tasklist_lock\n sched, rcu: Fix rcu_dereference() for RCU-lockdep\n rcu: Make task_subsys_state() RCU-lockdep checks handle boot-time use\n rcu: Fix holdoff for accelerated GPs for last non-dynticked CPU\n x86/gart: Unexport gart_iommu_aperture\n\nFix trivial conflicts in kernel/trace/ftrace.c\n" }, { "commit": "ea14eb714041d40fcc5180b5a586034503650149", "tree": "a7cb72753c85cf79ac6fa31863d65d2f081e0823", "parents": [ "52fbe9cde7fdb5c6fac196d7ebd2d92d05ef3cd4" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Fri Mar 12 19:41:23 2010 -0500" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Fri Mar 12 20:28:02 2010 -0500" }, "message": "function-graph: Init curr_ret_stack with ret_stack\n\nIf the graph tracer is active, and a task is forked but the allocating of\nthe processes graph stack fails, it can cause crash later on.\n\nThis is due to the temporary stack being NULL, but the curr_ret_stack\nvariable is copied from the parent. If it is not -1, then in\nftrace_graph_probe_sched_switch() the following:\n\n\tfor (index \u003d next-\u003ecurr_ret_stack; index \u003e\u003d 0; index--)\n\t\tnext-\u003eret_stack[index].calltime +\u003d timestamp;\n\nWill cause a kernel OOPS.\n\nFound with Li Zefan\u0027s ftrace_stress_test.\n\nCc: stable@kernel.org\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "915a0b575fdb2376135ed9334b3ccb1eb51db622", "tree": "12070fc07897e0cd9170aeb351a96923d44d7813", "parents": [ "e02c4fd3142dfb9412531bbfabd510a2a7c6ea46", "0e95017355dcf43031da6d0e360a748717e56df1" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Thu Mar 11 13:39:33 2010 +0100" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Thu Mar 11 13:39:33 2010 +0100" }, "message": "Merge branch \u0027tip/tracing/core\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-2.6-trace into tracing/urgent\n" }, { "commit": "3f379b03fbfddd20536389a85c6456f8233d1f8d", "tree": "2847590a23aa0d72e799bd6d65a8a794abb565ac", "parents": [ "54dbf96c921513bf98484a20ef366d51944a4c4d" ], "author": { "name": "Paul E. McKenney", "email": "paulmck@linux.vnet.ibm.com", "time": "Fri Mar 05 15:03:25 2010 -0800" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Thu Mar 11 13:38:01 2010 +0100" }, "message": "ftrace: Replace read_barrier_depends() with rcu_dereference_raw()\n\nReplace the calls to read_barrier_depends() in\nftrace_list_func() with rcu_dereference_raw() to improve\nreadability. The reason that we use rcu_dereference_raw() here\nis that removed entries are never freed, instead they are simply\nleaked. This is one of a very few cases where use of\nrcu_dereference_raw() is the long-term right answer. And I\ndon\u0027t yet know of any others. ;-)\n\nSigned-off-by: Paul E. McKenney \u003cpaulmck@linux.vnet.ibm.com\u003e\nAcked-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: laijs@cn.fujitsu.com\nCc: dipankar@in.ibm.com\nCc: mathieu.desnoyers@polymtl.ca\nCc: josh@joshtriplett.org\nCc: dvhltc@us.ibm.com\nCc: niv@us.ibm.com\nCc: peterz@infradead.org\nCc: Valdis.Kletnieks@vt.edu\nCc: dhowells@redhat.com\nLKML-Reference: \u003c1267830207-9474-1-git-send-email-paulmck@linux.vnet.ibm.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "801c29fd1fdeb84f60241beb445ff5db154450ae", "tree": "ce6d2cf95d86c7863393914b5ba37c90b56b44e9", "parents": [ "ae1f30384baef4056438d81b305a6a5199b0d16c" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Fri Mar 05 20:02:19 2010 -0500" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Fri Mar 05 21:00:30 2010 -0500" }, "message": "function-graph: Fix unused reference to ftrace_set_func()\n\nThe declaration of ftrace_set_func() is at the start of the ftrace.c file\nand wrapped with a #ifdef CONFIG_FUNCTION_GRAPH condition. If function\ngraph tracing is enabled but CONFIG_DYNAMIC_FTRACE is not, a warning\nabout that function being declared static and unused is given.\n\nThis really should have been placed within the CONFIG_FUNCTION_GRAPH\ncondition that uses ftrace_set_func().\n\nMoving the declaration down fixes the warning and makes the code cleaner.\n\nReported-by: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "6556a6743549defc32e5f90ee2cb1ecd833a44c3", "tree": "622306583d4a3c13235a8bfc012854c125c597f1", "parents": [ "e0d272429a34ff143bfa04ee8e29dd4eed2964c7", "1dd2980d990068e20045b90c424518cc7f3657ff" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Sun Feb 28 10:20:25 2010 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Sun Feb 28 10:20:25 2010 -0800" }, "message": "Merge branch \u0027perf-core-for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip\n\n* \u0027perf-core-for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (172 commits)\n perf_event, amd: Fix spinlock initialization\n perf_event: Fix preempt warning in perf_clock()\n perf tools: Flush maps on COMM events\n perf_events, x86: Split PMU definitions into separate files\n perf annotate: Handle samples not at objdump output addr boundaries\n perf_events, x86: Remove superflous MSR writes\n perf_events: Simplify code by removing cpu argument to hw_perf_group_sched_in()\n perf_events, x86: AMD event scheduling\n perf_events: Add new start/stop PMU callbacks\n perf_events: Report the MMAP pgoff value in bytes\n perf annotate: Defer allocating sym_priv-\u003ehist array\n perf symbols: Improve debugging information about symtab origins\n perf top: Use a macro instead of a constant variable\n perf symbols: Check the right return variable\n perf/scripts: Tag syscall_name helper as not yet available\n perf/scripts: Add perf-trace-python Documentation\n perf/scripts: Remove unnecessary PyTuple resizes\n perf/scripts: Add syscall tracing scripts\n perf/scripts: Add Python scripting engine\n perf/scripts: Remove check-perf-trace from listed scripts\n ...\n\nFix trivial conflict in tools/perf/util/probe-event.c\n" }, { "commit": "64b9fb5704a479d98a59f2a1d45d3331a8f847f8", "tree": "2b1052b05fa7615c817894bc9802bc5bb2af7ac1", "parents": [ "83f0d53993b2967e54186468b0fc4321447f68f1", "60b341b778cc2929df16c0a504c91621b3c6a4ad" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Fri Feb 26 09:18:32 2010 +0100" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Fri Feb 26 09:18:32 2010 +0100" }, "message": "Merge commit \u0027v2.6.33\u0027 into tracing/core\n\nConflicts:\n\tscripts/recordmcount.pl\n\nMerge reason: Merge up to v2.6.33.\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "c7c6b1fe9f942c1a30585ec2210a09dfff238506", "tree": "de7780b1b6cff9c8f33c9de1240a0b19bea9aa94", "parents": [ "ede55c9d78101fef0d8e620940a5163f14b02f29" ], "author": { "name": "Li Zefan", "email": "lizf@cn.fujitsu.com", "time": "Wed Feb 10 15:43:04 2010 +0800" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Thu Feb 11 14:32:38 2010 -0500" }, "message": "ftrace: Allow to remove a single function from function graph filter\n\nI don\u0027t see why we can only clear all functions from the filter.\n\nAfter patching:\n\n # echo sys_open \u003e set_graph_function\n # echo sys_close \u003e\u003e set_graph_function\n # cat set_graph_function\n sys_open\n sys_close\n # echo \u0027!sys_close\u0027 \u003e\u003e set_graph_function\n # cat set_graph_function\n sys_open\n\nSigned-off-by: Li Zefan \u003clizf@cn.fujitsu.com\u003e\nLKML-Reference: \u003c4B726388.2000408@cn.fujitsu.com\u003e\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "f24bb999d2b9f2950e5cac5b69bffedf73c24ea4", "tree": "2c595d1c4c34f06eda309fd3770e3a7fb9ffba8a", "parents": [ "4554dbcb85a4ed2abaa2b6fa15649b796699ec89" ], "author": { "name": "Masami Hiramatsu", "email": "mhiramat@redhat.com", "time": "Tue Feb 02 16:49:25 2010 -0500" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Thu Feb 04 09:36:19 2010 +0100" }, "message": "ftrace: Remove record freezing\n\nRemove record freezing. Because kprobes never puts probe on\nftrace\u0027s mcount call anymore, it doesn\u0027t need ftrace to check\nwhether kprobes on it.\n\nSigned-off-by: Masami Hiramatsu \u003cmhiramat@redhat.com\u003e\nCc: systemtap \u003csystemtap@sources.redhat.com\u003e\nCc: DLE \u003cdle-develop@lists.sourceforge.net\u003e\nCc: Steven Rostedt \u003crostedt@goodmis.org\u003e\nCc: przemyslaw@pawelczyk.it\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nLKML-Reference: \u003c20100202214925.4694.73469.stgit@dhcp-100-2-132.bos.redhat.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "2cfa19780d61740f65790c5bae363b759d7c96fa", "tree": "cc7a8277a9f04c1bd613efe03c7d6d16cd18dc96", "parents": [ "615d0ebbc782b67296e3226c293f520f93f93515" ], "author": { "name": "Masami Hiramatsu", "email": "mhiramat@redhat.com", "time": "Tue Feb 02 16:49:11 2010 -0500" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Thu Feb 04 09:36:19 2010 +0100" }, "message": "ftrace/alternatives: Introducing *_text_reserved functions\n\nIntroducing *_text_reserved functions for checking the text\naddress range is partially reserved or not. This patch provides\nchecking routines for x86 smp alternatives and dynamic ftrace.\nSince both functions modify fixed pieces of kernel text, they\nshould reserve and protect those from other dynamic text\nmodifier, like kprobes.\n\nThis will also be extended when introducing other subsystems\nwhich modify fixed pieces of kernel text. Dynamic text modifiers\nshould avoid those.\n\nSigned-off-by: Masami Hiramatsu \u003cmhiramat@redhat.com\u003e\nCc: systemtap \u003csystemtap@sources.redhat.com\u003e\nCc: DLE \u003cdle-develop@lists.sourceforge.net\u003e\nCc: Steven Rostedt \u003crostedt@goodmis.org\u003e\nCc: przemyslaw@pawelczyk.it\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Ananth N Mavinakayanahalli \u003cananth@in.ibm.com\u003e\nCc: Jim Keniston \u003cjkenisto@us.ibm.com\u003e\nCc: Mathieu Desnoyers \u003ccompudj@krystal.dyndns.org\u003e\nCc: Jason Baron \u003cjbaron@redhat.com\u003e\nLKML-Reference: \u003c20100202214911.4694.16587.stgit@dhcp-100-2-132.bos.redhat.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "751e9983ee276cb150e8812b1d995f6035a63878", "tree": "7f9abfa2ea11bcc2ccfa9922af17811d5020fa69", "parents": [ "b82a4045f7962483a78a874343dc6e31b79c96c1" ], "author": { "name": "Li Zefan", "email": "lizf@cn.fujitsu.com", "time": "Thu Jan 14 10:53:02 2010 +0800" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Thu Jan 14 22:38:03 2010 -0500" }, "message": "ftrace: Fix MATCH_END_ONLY function filter\n\nFor \u0027*foo\u0027 pattern, we should allow any string ending with\n\u0027foo\u0027, but ftrace filter incorrectly disallows strings\nlike bar_foo_foo:\n\n # echo \u0027*io\u0027 \u003e set_ftrace_filter\n # cat set_ftrace_filter | grep \u0027req_bio_endio\u0027\n # cat available_filter_functions | grep \u0027req_bio_endio\u0027\n req_bio_endio\n\nSigned-off-by: Li Zefan \u003clizf@cn.fujitsu.com\u003e\nLKML-Reference: \u003c4B4E870E.6060607@cn.fujitsu.com\u003e\nAcked-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "91baf6285be7282cfa487de92f836c50749dffb9", "tree": "766544ebcc24fecf177eba5bd8be475cf3516eef", "parents": [ "313254a9400d388b46150c0f355e216418a2f598" ], "author": { "name": "Li Zefan", "email": "lizf@cn.fujitsu.com", "time": "Tue Dec 08 11:15:45 2009 +0800" }, "committer": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Sun Dec 13 18:37:26 2009 +0100" }, "message": "function-graph: Allow writing the same val to set_graph_function\n\n# echo \u0027do_open\u0027 \u003e set_graph_function\n # echo \u0027do_open\u0027 \u003e\u003e set_graph_function\n bash: echo: write error: Invalid argument\n\nMake it valid to write the same value to set_graph_function,\nwhich is consistent with set_ftrace_filter interface.\n\nSigned-off-by: Li Zefan \u003clizf@cn.fujitsu.com\u003e\nAcked-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\nLKML-reference: \u003c4B1DC4E1.1060303@cn.fujitsu.com\u003e\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\n" }, { "commit": "313254a9400d388b46150c0f355e216418a2f598", "tree": "190c360ad60b27763e2f95dc5cf8fa9068d3d71e", "parents": [ "311d16da575f53c3367099579736c1d233efe0dc" ], "author": { "name": "Li Zefan", "email": "lizf@cn.fujitsu.com", "time": "Tue Dec 08 11:15:30 2009 +0800" }, "committer": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Sun Dec 13 18:37:26 2009 +0100" }, "message": "ftrace: Call trace_parser_clear() properly\n\nI found a weird behavior:\n\n # echo \u0027fuse:*\u0027 \u003e set_ftrace_filter\n bash: echo: write error: Invalid argument\n # cat set_ftrace_filter\n fuse_dev_fasync\n fuse_dev_poll\n fuse_copy_do\n\nWe should call trace_parser_clear() no matter ftrace_process_regex()\nreturns 0 or -errno, otherwise we will actually take the unaccepted\nrecords from ftrace_regex_release().\n\nSigned-off-by: Li Zefan \u003clizf@cn.fujitsu.com\u003e\nAcked-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\nLKML-Reference: \u003c4B1DC4D2.3000406@cn.fujitsu.com\u003e\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\n" }, { "commit": "311d16da575f53c3367099579736c1d233efe0dc", "tree": "6fea069fc00f50afac428021989d037f0bb0162f", "parents": [ "3b8e4273814a7f9e9a74ece517d9206fea919aaa" ], "author": { "name": "Li Zefan", "email": "lizf@cn.fujitsu.com", "time": "Tue Dec 08 11:15:11 2009 +0800" }, "committer": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Sun Dec 13 18:37:25 2009 +0100" }, "message": "ftrace: Return EINVAL when writing invalid val to set_ftrace_filter\n\nCurrently it doesn\u0027t warn user on invald value:\n\n # echo nonexist_symbol \u003e set_ftrace_filter\nor:\n # echo \u0027nonexist_symbol:mod:fuse\u0027 \u003e set_ftrace_filter\n\nBetter make it return failure.\n\nSigned-off-by: Li Zefan \u003clizf@cn.fujitsu.com\u003e\nAcked-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\nLKML-Reference: \u003c4B1DC4BF.2070003@cn.fujitsu.com\u003e\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\n" }, { "commit": "96fa2b508d2d3fe040cf4ef2fffb955f0a537ea1", "tree": "3cec6d72a450735fe6b8ed996c7399f57c05a5cb", "parents": [ "7a797cdcca2b3c0031e580203f18d6c9483aaec5", "b8007ef7422270864eae523cb38d7522a53a94d3" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Sat Dec 05 09:53:36 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Sat Dec 05 09:53:36 2009 -0800" }, "message": "Merge branch \u0027tracing-core-for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip\n\n* \u0027tracing-core-for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (40 commits)\n tracing: Separate raw syscall from syscall tracer\n ring-buffer-benchmark: Add parameters to set produce/consumer priorities\n tracing, function tracer: Clean up strstrip() usage\n ring-buffer benchmark: Run producer/consumer threads at nice +19\n tracing: Remove the stale include/trace/power.h\n tracing: Only print objcopy version warning once from recordmcount\n tracing: Prevent build warning: \u0027ftrace_graph_buf\u0027 defined but not used\n ring-buffer: Move access to commit_page up into function used\n tracing: do not disable interrupts for trace_clock_local\n ring-buffer: Add multiple iterations between benchmark timestamps\n kprobes: Sanitize struct kretprobe_instance allocations\n tracing: Fix to use __always_unused attribute\n compiler: Introduce __always_unused\n tracing: Exit with error if a weak function is used in recordmcount.pl\n tracing: Move conditional into update_funcs() in recordmcount.pl\n tracing: Add regex for weak functions in recordmcount.pl\n tracing: Move mcount section search to front of loop in recordmcount.pl\n tracing: Fix objcopy revision check in recordmcount.pl\n tracing: Check absolute path of input file in recordmcount.pl\n tracing: Correct the check for number of arguments in recordmcount.pl\n ...\n" }, { "commit": "457dc928f586f3f4b930206965e6db270034e97e", "tree": "db1ff1d43058451cc42f6499f495e68d1a37e335", "parents": [ "98e4833ba3c314c99dc364012fba6ac894230ad0" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Nov 23 11:03:28 2009 +0100" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Nov 23 11:04:07 2009 +0100" }, "message": "tracing, function tracer: Clean up strstrip() usage\n\nClean up strstrip() usage - which also addresses this build warning:\n\n kernel/trace/ftrace.c: In function \u0027ftrace_pid_write\u0027:\n kernel/trace/ftrace.c:3004: warning: ignoring return value of \u0027strstrip\u0027, declared with attribute warn_unused_result\n\nCc: Steven Rostedt \u003crostedt@goodmis.org\u003e\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: Mike Galbraith \u003cefault@gmx.de\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\nLKML-Reference: \u003cnew-submission\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "f6060f46819f313d34a8c8151390cda509c23389", "tree": "96ec1c80695498d73172b3c2ef7df585b9d28e4f", "parents": [ "5a50e33cc916f6a81cb96f0f24f6a88c9ab78b79" ], "author": { "name": "Lai Jiangshan", "email": "laijs@cn.fujitsu.com", "time": "Thu Nov 05 11:16:17 2009 +0800" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Tue Nov 17 11:05:49 2009 -0500" }, "message": "tracing: Prevent build warning: \u0027ftrace_graph_buf\u0027 defined but not used\n\nPrevent build warning when CONFIG_FUNCTION_GRAPH_TRACER is not set.\n\nSigned-off-by: Lai Jiangshan \u003claijs@cn.fujitsu.com\u003e\nLKML-Reference: \u003c4AF24381.5060307@cn.fujitsu.com\u003e\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "ed146b25942b428f8e8056587b7638ce76573c2f", "tree": "36b3355b5d53057accb92000ee5b3986d5a05a8b", "parents": [ "f7112949f6a4cd6883d66c882d568c2197321de6" ], "author": { "name": "Li Zefan", "email": "lizf@cn.fujitsu.com", "time": "Tue Nov 03 08:55:38 2009 +0800" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Wed Nov 04 01:42:10 2009 -0500" }, "message": "ftrace: Fix unmatched locking in ftrace_regex_write()\n\nWhen a command is passed to the set_ftrace_filter, then\nthe ftrace_regex_lock is still held going back to user space.\n\n # echo \u0027do_open : foo\u0027 \u003e set_ftrace_filter\n (still holding ftrace_regex_lock when returning to user space!)\n\nSigned-off-by: Li Zefan \u003clizf@cn.fujitsu.com\u003e\nLKML-Reference: \u003c4AEF7F8A.3080300@cn.fujitsu.com\u003e\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "9de09ace8d518141a4375e1d216ab64db4377799", "tree": "da8e7a77f4ea91eb3bb73fc6da72ecf8c99e1c16", "parents": [ "1beee96bae0daf7f491356777c3080cc436950f5", "6d3f1e12f46a2f9a1bb7e7aa433df8dd31ce5647" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Thu Oct 29 09:02:15 2009 +0100" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Thu Oct 29 09:02:20 2009 +0100" }, "message": "Merge branch \u0027tracing/urgent\u0027 into tracing/core\n\nMerge reason: Pick up fixes and move base from -rc1 to -rc5.\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "cf8517cf905b5cd31d5790250b9ac39f7cb8aa53", "tree": "22796f676ce955ec204ece1485dac6e93d1aeb3e", "parents": [ "964fe080d94db82a3268443e9b9ece4c60246414" ], "author": { "name": "Jiri Olsa", "email": "jolsa@redhat.com", "time": "Fri Oct 23 19:36:16 2009 -0400" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Sat Oct 24 11:07:49 2009 +0200" }, "message": "tracing: Update *ppos instead of filp-\u003ef_pos\n\nInstead of directly updating filp-\u003ef_pos we should update the *ppos\nargument. The filp-\u003ef_pos gets updated within the file_pos_write()\nfunction called from sys_write().\n\nSigned-off-by: Jiri Olsa \u003cjolsa@redhat.com\u003e\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nLKML-Reference: \u003c20091023233646.399670810@goodmis.org\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "06f43d66ec36388056f5c697bf1e67c0e0a1645c", "tree": "04b8735f670570d146c0c12bb403effc94e14346", "parents": [ "459c6d15a0c52bae43842ff2cd0dd41aa7de9b7f" ], "author": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Wed Oct 14 20:43:39 2009 +0200" }, "committer": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Wed Oct 14 20:43:39 2009 +0200" }, "message": "ftrace: Copy ftrace_graph_filter boot param using strlcpy\n\nWe are using strncpy in the wrong way to copy the ftrace_graph_filter\nboot param because we pass the buffer size instead of the max string\nsize it can contain (buffer size - 1). The end result might not be\nNULL terminated as we are abusing the max string size.\n\nLets use strlcpy() instead.\n\nReported-by: Li Zefan \u003clizf@cn.fujitsu.com\u003e\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "5cb084bb1f3fd4dcdaf7e4cf564994346ec8f783", "tree": "0faf55a8a91ff69ae7cd0dff349dc5fbe27a53da", "parents": [ "756d17ee7ee4fbc8238bdf97100af63e6ac441ef" ], "author": { "name": "Jiri Olsa", "email": "jolsa@redhat.com", "time": "Tue Oct 13 16:33:53 2009 -0400" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Wed Oct 14 08:13:54 2009 +0200" }, "message": "tracing: Enable records during the module load\n\nI was debuging some module using \"function\" and \"function_graph\"\ntracers and noticed, that if you load module after you enabled\ntracing, the module\u0027s hooks will convert only to NOP instructions.\n\nThe attached patch enables modules\u0027 hooks if there\u0027s function trace\nallready on, thus allowing to trace module functions.\n\nSigned-off-by: Jiri Olsa \u003cjolsa@redhat.com\u003e\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\nLKML-Reference: \u003c20091013203425.896285120@goodmis.org\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "756d17ee7ee4fbc8238bdf97100af63e6ac441ef", "tree": "d0b794f4964be5689fc1bd64302969405000e18b", "parents": [ "194ec34184869f0de1cf255c924fc5299e1b3d27" ], "author": { "name": "jolsa@redhat.com", "email": "jolsa@redhat.com", "time": "Tue Oct 13 16:33:52 2009 -0400" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Wed Oct 14 08:13:53 2009 +0200" }, "message": "tracing: Support multiple pids in set_pid_ftrace file\n\nAdding the possibility to set more than 1 pid in the set_pid_ftrace\nfile, thus allowing to trace more than 1 independent processes.\n\nUsage:\n\n sh-4.0# echo 284 \u003e ./set_ftrace_pid\n sh-4.0# cat ./set_ftrace_pid\n 284\n sh-4.0# echo 1 \u003e\u003e ./set_ftrace_pid\n sh-4.0# echo 0 \u003e\u003e ./set_ftrace_pid\n sh-4.0# cat ./set_ftrace_pid\n swapper tasks\n 1\n 284\n sh-4.0# echo 4 \u003e ./set_ftrace_pid\n sh-4.0# cat ./set_ftrace_pid\n 4\n sh-4.0# echo \u003e ./set_ftrace_pid\n sh-4.0# cat ./set_ftrace_pid\n no pid\n sh-4.0#\n\nSigned-off-by: Jiri Olsa \u003cjolsa@redhat.com\u003e\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nLKML-Reference: \u003c20091013203425.565454612@goodmis.org\u003e\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" } ], "next": "1bac0497ef9af8d933860672223e38bd6ac4934a" }