)]}' { "log": [ { "commit": "c93f216b5b985a12a18323e5ca2eb01db3d2f000", "tree": "45fa35b290005f8b241dd76b6342875b81432fc3", "parents": [ "c61b79b6ef266890954213a701d8f6021d8c1289", "ab3c9c686e22ab264269337ce7b75d9760211198" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Apr 07 14:10:10 2009 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Apr 07 14:10:10 2009 -0700" }, "message": "Merge branch \u0027tracing-fixes-for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip\n\n* \u0027tracing-fixes-for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:\n branch tracer, intel-iommu: fix build with CONFIG_BRANCH_TRACER\u003dy\n branch tracer: Fix for enabling branch profiling makes sparse unusable\n ftrace: Correct a text align for event format output\n Update /debug/tracing/README\n tracing/ftrace: alloc the started cpumask for the trace file\n tracing, x86: remove duplicated #include\n ftrace: Add check of sched_stopped for probe_sched_wakeup\n function-graph: add proper initialization for init task\n tracing/ftrace: fix missing include string.h\n tracing: fix incorrect return type of ns2usecs()\n tracing: remove CALLER_ADDR2 from wakeup tracer\n blktrace: fix pdu_len when tracing packet command requests\n blktrace: small cleanup in blk_msg_write()\n blktrace: NUL-terminate user space messages\n tracing: move scripts/trace/power.pl to scripts/tracing/power.pl\n" }, { "commit": "cf8e3474654f20433aab9aa35826d43b5f245008", "tree": "bbb3e87ca324ae4192fd524c0777047ee075c5d9", "parents": [ "301fd748e2c81e78e74edbc694a64caa7b95dda2" ], "author": { "name": "Lai Jiangshan", "email": "laijs@cn.fujitsu.com", "time": "Mon Mar 30 13:48:00 2009 +0800" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Tue Apr 07 13:59:23 2009 +0200" }, "message": "tracing: fix incorrect return type of ns2usecs()\n\nImpact: fix time output bug in 32bits system\n\nns2usecs() returns \u0027long\u0027, it\u0027s incorrect.\n\n(In i386)\n...\n \u003cidle\u003e-0 [000] 521.442100: _spin_lock \u003c-tick_do_update_jiffies64\n \u003cidle\u003e-0 [000] 521.442101: do_timer \u003c-tick_do_update_jiffies64\n \u003cidle\u003e-0 [000] 521.442102: update_wall_time \u003c-do_timer\n \u003cidle\u003e-0 [000] 521.442102: update_xtime_cache \u003c-update_wall_time\n....\n(It always print the time less than 2200 seconds besides ...)\nBecause \u0027long\u0027 is 32bits in i386. ( (1\u003c\u003c31) useconds is about 2200 seconds)\n\n...\n \u003cidle\u003e-0 [001] 4154502640.134759: rcu_bh_qsctr_inc \u003c-__do_softirq\n \u003cidle\u003e-0 [001] 4154502640.134760: _local_bh_enable \u003c-__do_softirq\n \u003cidle\u003e-0 [001] 4154502640.134761: idle_cpu \u003c-irq_exit\n...\n(very large value)\nBecause \u0027long\u0027 is a signed type and it is 32bits in i386.\n\nChanges in v2:\nreturn \u0027unsigned long long\u0027 instead of \u0027cycle_t\u0027\n\nSigned-off-by: Lai Jiangshan \u003claijs@cn.fujitsu.com\u003e\nLKML-Reference: \u003c49D05D10.4030009@cn.fujitsu.com\u003e\nReported-by: Li Zefan \u003clizf@cn.fujitsu.com\u003e\nAcked-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "ca2b84cb3c4a0d4d2143b46ec072cdff5d1b3b87", "tree": "7163bac040f11c444b24cab53c4a784df73fa4f3", "parents": [ "ac44021fccd8f1f2b267b004f23a2e8d7ef05f7b" ], "author": { "name": "Eduard - Gabriel Munteanu", "email": "eduard.munteanu@linux360.ro", "time": "Mon Mar 23 15:12:24 2009 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Fri Apr 03 12:23:06 2009 +0200" }, "message": "kmemtrace: use tracepoints\n\nkmemtrace now uses tracepoints instead of markers. We no longer need to\nuse format specifiers to pass arguments.\n\nSigned-off-by: Eduard - Gabriel Munteanu \u003ceduard.munteanu@linux360.ro\u003e\n[ folded: Use the new TP_PROTO and TP_ARGS to fix the build. ]\n[ folded: fix build when CONFIG_KMEMTRACE is disabled. ]\n[ folded: define tracepoints when CONFIG_TRACEPOINTS is enabled. ]\nSigned-off-by: Pekka Enberg \u003cpenberg@cs.helsinki.fi\u003e\nLKML-Reference: \u003cae61c0f37156db8ec8dc0d5778018edde60a92e3.1237813499.git.eduard.munteanu@linux360.ro\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "8b54e45b0005875f59cb8b1c44d429a161d5f245", "tree": "0e7c98418384f3f773d2046eea50f529e89f1cba", "parents": [ "0a5d649018b151cb9331c213a843ac4a3e7e44ab", "9a8118baaeb0eaa148913bed77bf9c6335f6ca63", "b14b70a6a4e394c9630bcde17e07d3bcdcbca27e", "fee039a1d05c6e0f71b0fe270d847742a02d56c4", "18cea4591a98817697017bcb056a848bae1205df", "548c316137901cc81dea35e26362a9d5ba0b89b6" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Tue Mar 31 17:46:40 2009 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Tue Mar 31 17:46:40 2009 +0200" }, "message": "Merge branches \u0027tracing/docs\u0027, \u0027tracing/filters\u0027, \u0027tracing/ftrace\u0027, \u0027tracing/kprobes\u0027, \u0027tracing/blktrace-v2\u0027 and \u0027tracing/textedit\u0027 into tracing/core-v2\n" }, { "commit": "be6f164a02f394675e2ac2077dd354cebef5b4c0", "tree": "9805294731c00ddb61857a4e1e42019058eb1542", "parents": [ "8aef2d2856158a36c295a8d1288281e4839bff13" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Tue Mar 24 11:06:24 2009 -0400" }, "committer": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Tue Mar 24 11:06:24 2009 -0400" }, "message": "function-graph: add option for include sleep times\n\nImpact: give user a choice to show times spent while sleeping\n\nThe user may want to see the time a function spent sleeping.\nThis patch adds the trace option \"sleep-time\" to allow that.\nThe \"sleep-time\" option is default on.\n\n echo sleep-time \u003e /debug/tracing/trace_options\n\nproduces:\n\n ------------------------------------------\n 2) avahi-d-3428 \u003d\u003e \u003cidle\u003e-0\n ------------------------------------------\n\n 2) | finish_task_switch() {\n 2) 0.621 us | _spin_unlock_irq();\n 2) 2.202 us | }\n 2) ! 1002.197 us | }\n 2) ! 1003.521 us | }\n\nwhere as,\n\n echo nosleep-time \u003e /debug/tracing/trace_options\n\nproduces:\n\n 0) \u003cidle\u003e-0 \u003d\u003e yum-upd-3416\n ------------------------------------------\n\n 0) | finish_task_switch() {\n 0) 0.643 us | _spin_unlock_irq();\n 0) 2.342 us | }\n 0) + 41.302 us | }\n 0) + 42.453 us | }\n\nSigned-off-by: Steven Rostedt \u003csrostedt@redhat.com\u003e\n" }, { "commit": "4bda2d517bfa3ce3d7044e06988cdddae7adffe2", "tree": "62d99deb281a0395942b462f7cff2d2b42f2d905", "parents": [ "09f1f245c79585383de63e3ca54d0f91824bff3a" ], "author": { "name": "Tom Zanussi", "email": "tzanussi@gmail.com", "time": "Tue Mar 24 02:14:31 2009 -0500" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Tue Mar 24 08:26:52 2009 +0100" }, "message": "tracing/filters: use trace_seq_printf() to print filters\n\nImpact: cleanup\n\nInstead of just using the trace_seq buffer to print the filters, use\ntrace_seq_printf() as it was intended to be used.\n\nReported-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\nSigned-off-by: Tom Zanussi \u003ctzanussi@gmail.com\u003e\nCc: \u003d?ISO-8859-1?Q?Fr\u003dE9d\u003dE9ric?\u003d Weisbecker \u003cfweisbec@gmail.com\u003e\nLKML-Reference: \u003c1237878871.8339.59.camel@charm-linux\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "07edf7121374609709ef1b0889f6e7b8d6a62ec1", "tree": "ad1649c9546dc3ce23bb2f8609a7459a7ca2006e", "parents": [ "9bd7d099ab3f10dd666da399c064999bae427cd9" ], "author": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Sun Mar 22 23:10:46 2009 +0100" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Mar 23 09:22:14 2009 +0100" }, "message": "tracing/events: don\u0027t use wake up for events\n\nImpact: fix hard-lockup with sched switch events\n\nSome ftrace events, such as sched wakeup, can be traced\nwhile the runqueue lock is hold. Since they are using\ntrace_current_buffer_unlock_commit(), they call wake_up()\nwhich can try to grab the runqueue lock too, resulting in\na deadlock.\n\nNow for all event, we call a new helper:\ntrace_nowake_buffer_unlock_commit() which do pretty the same than\ntrace_current_buffer_unlock_commit() except than it doesn\u0027t call\ntrace_wake_up().\n\nReported-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Steven Rostedt \u003crostedt@goodmis.org\u003e\nLKML-Reference: \u003c1237759847-21025-4-git-send-email-fweisbec@gmail.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "cfb180f3e71b2a280a254c8646a9ab1beab63f84", "tree": "93fb1a319b40851ebb7a3cc0d9ea4cc9a88e919a", "parents": [ "7ce7e4249921d5073e764f7ff7ad83cfa9894bd7" ], "author": { "name": "Tom Zanussi", "email": "tzanussi@gmail.com", "time": "Sun Mar 22 03:31:17 2009 -0500" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Sun Mar 22 18:38:47 2009 +0100" }, "message": "tracing: add per-subsystem filtering\n\nThis patch adds per-subsystem filtering to the event tracing subsystem.\n\nIt adds a \u0027filter\u0027 debugfs file to each subsystem directory. This file\ncan be written to to set filters; reading from it will display the\ncurrent set of filters set for that subsystem.\n\nBasically what it does is propagate the filter down to each event\ncontained in the subsystem. If a particular event doesn\u0027t have a field\nwith the name specified in the filter, it simply doesn\u0027t get set for\nthat event. You can verify whether or not the filter was set for a\nparticular event by looking at the filter file for that event.\n\nAs with per-event filters, compound expressions are supported, echoing\n\u00270\u0027 to the subsystem\u0027s filter file clears all filters in the subsystem,\netc.\n\nSigned-off-by: Tom Zanussi \u003ctzanussi@gmail.com\u003e\nAcked-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nLKML-Reference: \u003c1237710677.7703.49.camel@charm-linux\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "7ce7e4249921d5073e764f7ff7ad83cfa9894bd7", "tree": "d8a3026e85d3230ce39ca99f446abe76a710c337", "parents": [ "2d622719f1572ef31e0616444a515eba3094d050" ], "author": { "name": "Tom Zanussi", "email": "tzanussi@gmail.com", "time": "Sun Mar 22 03:31:04 2009 -0500" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Sun Mar 22 18:38:46 2009 +0100" }, "message": "tracing: add per-event filtering\n\nThis patch adds per-event filtering to the event tracing subsystem.\n\nIt adds a \u0027filter\u0027 debugfs file to each event directory. This file can\nbe written to to set filters; reading from it will display the current\nset of filters set for that event.\n\nBasically, any field listed in the \u0027format\u0027 file for an event can be\nfiltered on (including strings, but not yet other array types) using\neither matching (\u0027\u003d\u003d\u0027) or non-matching (\u0027!\u003d\u0027) \u0027predicates\u0027. A\n\u0027predicate\u0027 can be either a single expression:\n\n # echo pid !\u003d 0 \u003e filter\n\n # cat filter\n pid !\u003d 0\n\nor a compound expression of up to 8 sub-expressions combined using \u0027\u0026\u0026\u0027\nor \u0027||\u0027:\n\n # echo comm \u003d\u003d Xorg \u003e filter\n # echo \"\u0026\u0026 sig !\u003d 29\" \u003e filter\n\n # cat filter\n comm \u003d\u003d Xorg\n \u0026\u0026 sig !\u003d 29\n\nOnly events having field values matching an expression will be available\nin the trace output; non-matching events are discarded.\n\nNote that a compound expression is built up by echoing each\nsub-expression separately - it\u0027s not the most efficient way to do\nthings, but it keeps the parser simple and assumes that compound\nexpressions will be relatively uncommon. In any case, a subsequent\npatch introducing a way to set filters for entire subsystems should\nmitigate any need to do this for lots of events.\n\nSetting a filter without an \u0027\u0026\u0026\u0027 or \u0027||\u0027 clears the previous filter\ncompletely and sets the filter to the new expression:\n\n # cat filter\n comm \u003d\u003d Xorg\n \u0026\u0026 sig !\u003d 29\n\n # echo comm !\u003d Xorg\n\n # cat filter\n comm !\u003d Xorg\n\nTo clear a filter, echo 0 to the filter file:\n\n # echo 0 \u003e filter\n # cat filter\n none\n\nThe limit of 8 predicates for a compound expression is arbitrary - for\nefficiency, it\u0027s implemented as an array of pointers to predicates, and\n8 seemed more than enough for any filter...\n\nSigned-off-by: Tom Zanussi \u003ctzanussi@gmail.com\u003e\nAcked-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nLKML-Reference: \u003c1237710665.7703.48.camel@charm-linux\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "cf027f645e6aee4f0ca6197a6b6a57f327fdb13f", "tree": "f8a20e8707967db5d9140f9069426f410a30dd32", "parents": [ "0cf53ff62b3e9e491ff5e5f05b193fb6ce643047" ], "author": { "name": "Tom Zanussi", "email": "tzanussi@gmail.com", "time": "Sun Mar 22 03:30:39 2009 -0500" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Sun Mar 22 18:11:22 2009 +0100" }, "message": "tracing: add run-time field descriptions for event filtering\n\nThis patch makes the field descriptions defined for event tracing\navailable at run-time, for the event-filtering mechanism introduced\nin a subsequent patch.\n\nThe common event fields are prepended with \u0027common_\u0027 in the format\ndisplay, allowing them to be distinguished from the other fields\nthat might internally have same name and can therefore be\nunambiguously used in filters.\n\nSigned-off-by: Tom Zanussi \u003ctzanussi@gmail.com\u003e\nAcked-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nLKML-Reference: \u003c1237710639.7703.46.camel@charm-linux\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "ac199db0189c091f2863312061c0575937f68810", "tree": "0068aaa77ca00102ca60754eb32329f06821bba0", "parents": [ "28bea271e58e429eccfad3d7ee2ad12d6ee015bf" ], "author": { "name": "Peter Zijlstra", "email": "a.p.zijlstra@chello.nl", "time": "Thu Mar 19 20:26:15 2009 +0100" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Fri Mar 20 10:17:07 2009 +0100" }, "message": "ftrace: event profile hooks\n\nImpact: new tracing infrastructure feature\n\nProvide infrastructure to generate software perf counter events\nfrom tracepoints.\n\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Steven Rostedt \u003crostedt@goodmis.org\u003e\nLKML-Reference: \u003c20090319194233.557364871@chello.nl\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "40ce74f19c28077550646c76d96a075bf312e461", "tree": "bd58d38b6ac806be6f59276f16d1e0758376fa1d", "parents": [ "2fbcdb35aca614f9529a0e7d340146cf0b71684f" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Thu Mar 19 14:03:53 2009 -0400" }, "committer": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Thu Mar 19 15:58:47 2009 -0400" }, "message": "tracing: remove recording function depth from trace_printk\n\nThe function depth in trace_printk was to facilitate the function\ngraph output. Now that the function graph calculates the depth within\nthe trace output, we no longer need to record the depth when the\ntrace_printk is called.\n\nSigned-off-by: Steven Rostedt \u003csrostedt@redhat.com\u003e\n" }, { "commit": "327019b01e068d66dada6a8b2571180ab3674d20", "tree": "c81354a509d6962f6878145fcf3cdbe50a000a89", "parents": [ "03418c7efaa429dc7647ac93e3862e3fe1816873", "62524d55e5b9ffe36e3bf3dd7a594114f150b449" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Wed Mar 18 06:59:56 2009 +0100" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Wed Mar 18 06:59:56 2009 +0100" }, "message": "Merge branch \u0027tip/tracing/ftrace\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-2.6-trace into tracing/ftrace\n" }, { "commit": "af4617bdba34aa556272b34c3986b0a4d588f568", "tree": "c46a6b695724ee27c0113f6affcebeffcefbcf23", "parents": [ "37886f6a9f62d22530ffee8d3f9215c8345b6969" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Tue Mar 17 18:09:55 2009 -0400" }, "committer": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Tue Mar 17 23:10:35 2009 -0400" }, "message": "tracing: add global-clock option to provide cross CPU clock to traces\n\nImpact: feature to allow better serialized clock\n\nThis patch adds an option called \"global-clock\" that will allow\nthe tracer to switch to a slower but more accurate (across CPUs)\nclock.\n\nSigned-off-by: Steven Rostedt \u003csrostedt@redhat.com\u003e\n" }, { "commit": "4176935b58eeb636917e65a2c388e4607e36cce6", "tree": "dac4e0005cda5a3a5a313dde35bbac2877d9bd93", "parents": [ "c269fc8c537d761f36cb98e637ae934d9331a9d5", "6adaad14d7d4d3ef31b4e2dc992b18b5da7c4eb3" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Tue Mar 17 10:37:37 2009 +0100" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Tue Mar 17 10:37:37 2009 +0100" }, "message": "Merge branch \u0027tip/tracing/ftrace\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-2.6-trace into tracing/ftrace\n" }, { "commit": "4ca530852346be239b7c19e7bec5d2b78855bebe", "tree": "96e5252faaf362115a96ed6df7c4e4f698a027dc", "parents": [ "03303549b1695dc024d4a653cc16bd79f78f9750" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Mon Mar 16 19:20:15 2009 -0400" }, "committer": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Mon Mar 16 23:27:06 2009 -0400" }, "message": "tracing: protect reader of cmdline output\n\nImpact: fix to one cause of incorrect comm outputs in trace\n\nThe spinlock only protected the creation of a comm \u003c\u003d\u003e pid pair.\nBut it was possible that a reader could look up a pid, and get the\nwrong comm because it had no locking.\n\nThis also required changing trace_find_cmdline to copy the comm cache\nand not just send back a pointer to it.\n\nSigned-off-by: Steven Rostedt \u003csrostedt@redhat.com\u003e\n" }, { "commit": "7243f2145a9b06e5cf9a49fc9b8b9a4fff6fb42e", "tree": "50b73e168e0e8b711d5e1ca8878389464d6c905c", "parents": [ "b478b782e110fdb4135caa3062b6d687e989d994", "62395efdb0ef42e664ca81677901268c403a6286", "5bee17f18b595937e6beafeee5197868a3f74a06" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Mar 16 09:12:42 2009 +0100" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Mar 16 09:12:42 2009 +0100" }, "message": "Merge branches \u0027tracing/ftrace\u0027, \u0027tracing/syscalls\u0027 and \u0027linus\u0027 into tracing/core\n\nConflicts:\n\tarch/parisc/kernel/irq.c\n" }, { "commit": "bed1ffca022cc876fb83161d26670e9b5d3cf36b", "tree": "a896c79e9ea1af11f992826f1de7e2ece52fbe33", "parents": [ "f58ba100678f421bdcb000a3c71793f432dfab93" ], "author": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Fri Mar 13 15:42:11 2009 +0100" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Fri Mar 13 16:57:42 2009 +0100" }, "message": "tracing/syscalls: core infrastructure for syscalls tracing, enhancements\n\nImpact: new feature\n\nThis adds the generic support for syscalls tracing. This is\ncurrently exploited through a devoted tracer but other tracing\nengines can use it. (They just have to play with\n{start,stop}_ftrace_syscalls() and use the display callbacks\nunless they want to override them.)\n\nThe syscalls prototypes definitions are abused here to steal\nsome metadata informations:\n\n- syscall name, param types, param names, number of params\n\nThe syscall addr is not directly saved during this definition\nbecause we don\u0027t know if its prototype is available in the\nnamespace. But we don\u0027t really need it. The arch has just to\nbuild a function able to resolve the syscall number to its\nmetadata struct.\n\nThe current tracer prints the syscall names, parameters names\nand values (and their types optionally). Currently the value is\na raw hex but higher level values diplaying is on my TODO list.\n\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nLKML-Reference: \u003c1236955332-10133-2-git-send-email-fweisbec@gmail.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "62a394eb77a1ddea73273f53ed8c3ccf6e04f2fb", "tree": "ee72d87524b29eb9457b45e02a4587d8fbd9191d", "parents": [ "d2e82546ae98eee353fae57e389f487586fe380d", "1b3fa2ce64363c289b3b14723cca7290bf91cfce" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Fri Mar 13 10:23:39 2009 +0100" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Fri Mar 13 10:23:39 2009 +0100" }, "message": "Merge branches \u0027tracing/ftrace\u0027 and \u0027tracing/syscalls\u0027; commit \u0027v2.6.29-rc8\u0027 into tracing/core\n" }, { "commit": "ee08c6eccb7d1295516f7cf420fddf7b14e9146f", "tree": "ec6d209e47bb1a8910d16c1c8b4ea65959850689", "parents": [ "4c6ed8f496fe89ff81b3d6e617a531bedfb613e4" ], "author": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Sat Mar 07 05:52:59 2009 +0100" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Fri Mar 13 06:25:43 2009 +0100" }, "message": "tracing/ftrace: syscall tracing infrastructure, basics\n\nProvide basic callbacks to do syscall tracing.\n\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nAcked-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\nCc: Lai Jiangshan \u003claijs@cn.fujitsu.com\u003e\nLKML-Reference: \u003c1236401580-5758-2-git-send-email-fweisbec@gmail.com\u003e\n[ simplified it to a trace_printk() for now. ]\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "bdc067582b8b71c7771bab076bbc51569c594fb4", "tree": "a202353e4e365ae29c5bf95ca33eacd8eb4dfb54", "parents": [ "eb1871f34358024acfa3523ef375ef14b7527173" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Fri Mar 13 00:12:52 2009 -0400" }, "committer": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Fri Mar 13 00:15:46 2009 -0400" }, "message": "tracing: add comment for use of double __builtin_consant_p\n\nImpact: documentation\n\nThe use of the double __builtin_contant_p checks in the event_trace_printk\ncan be confusing to developers and reviewers. This patch adds a comment\nto explain why it is there.\n\nRequested-by: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nLKML-Reference: \u003c20090313122235.43EB.A69D9226@jp.fujitsu.com\u003e\nSigned-off-by: Steven Rostedt \u003csrostedt@redhat.com\u003e\n" }, { "commit": "e9fb2b6d5845e24f104713591286b6f39761c027", "tree": "13239f3046b28b9b8b6166e438a4c509e57972c9", "parents": [ "828275574e0161bdddb5817d4bd76a0265ef0470" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Thu Mar 12 14:19:25 2009 -0400" }, "committer": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Thu Mar 12 21:15:00 2009 -0400" }, "message": "tracing: have event_trace_printk use static tracer\n\nImpact: speed up on event tracing\n\nThe event_trace_printk is currently a wrapper function that calls\ntrace_vprintk. Because it uses a variable for the fmt it misses out\non the optimization of using the binary printk.\n\nThis patch makes event_trace_printk into a macro wrapper to use the\nfmt as the same as the trace_printks.\n\nSigned-off-by: Steven Rostedt \u003csrostedt@redhat.com\u003e\n" }, { "commit": "48ead02030f849d011259244bb4ea9b985479006", "tree": "4500f27dc7eb6567ca79dd03fa94fe9e56fbc316", "parents": [ "db526ca329f855510e8ce672332eba3304aed590" ], "author": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Thu Mar 12 18:24:49 2009 +0100" }, "committer": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Thu Mar 12 21:15:00 2009 -0400" }, "message": "tracing/core: bring back raw trace_printk for dynamic formats strings\n\nImpact: fix callsites with dynamic format strings\n\nSince its new binary implementation, trace_printk() internally uses static\ncontainers for the format strings on each callsites. But the value is\nassigned once at build time, which means that it can\u0027t take dynamic\nformats.\n\nSo this patch unearthes the raw trace_printk implementation for the callers\nthat will need trace_printk to be able to carry these dynamic format\nstrings. The trace_printk() macro will use the appropriate implementation\nfor each callsite. Most of the time however, the binary implementation will\nstill be used.\n\nThe other impact of this patch is that mmiotrace_printk() will use the old\nimplementation because it calls the low level trace_vprintk and we can\u0027t\nguess here whether the format passed in it is dynamic or not.\n\nSome parts of this patch have been written by Steven Rostedt (most notably\nthe part that chooses the appropriate implementation for each callsites).\n\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nSigned-off-by: Steven Rostedt \u003csrostedt@redhat.com\u003e\n" }, { "commit": "1852fcce181faa237c010a3dbedb473cf9d4555f", "tree": "863cd12b573fd36436e7fb042f9bd96a73a9f725", "parents": [ "73c5162aa362a543793f4a957c6c536dcbaa89ce" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Wed Mar 11 14:33:00 2009 -0400" }, "committer": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Wed Mar 11 22:15:24 2009 -0400" }, "message": "tracing: expand the ring buffers when an event is activated\n\nTo save memory, the tracer ring buffers are set to a minimum.\nThe activating of a trace expands the ring buffer size. This patch\nadds this expanding, when an event is activated.\n\nSigned-off-by: Steven Rostedt \u003csrostedt@redhat.com\u003e\n" }, { "commit": "da4d03020c2af32f73e8bfbab0a66620d85bb9bb", "tree": "3ee6d7d69754df7910454315a6011c14d8664d01", "parents": [ "9cc26a261d43e5898287a1f5808132f8f05ceb1c" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Mon Mar 09 17:14:30 2009 -0400" }, "committer": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Tue Mar 10 00:35:07 2009 -0400" }, "message": "tracing: new format for specialized trace points\n\nImpact: clean up and enhancement\n\nThe TRACE_EVENT_FORMAT macro looks quite ugly and is limited in its\nability to save data as well as to print the record out. Working with\nIngo Molnar, we came up with a new format that is much more pleasing to\nthe eye of C developers. This new macro is more C style than the old\nmacro, and is more obvious to what it does.\n\nHere\u0027s the example. The only updated macro in this patch is the\nsched_switch trace point.\n\nThe old method looked like this:\n\n TRACE_EVENT_FORMAT(sched_switch,\n TP_PROTO(struct rq *rq, struct task_struct *prev,\n struct task_struct *next),\n TP_ARGS(rq, prev, next),\n TP_FMT(\"task %s:%d \u003d\u003d\u003e %s:%d\",\n prev-\u003ecomm, prev-\u003epid, next-\u003ecomm, next-\u003epid),\n TRACE_STRUCT(\n TRACE_FIELD(pid_t, prev_pid, prev-\u003epid)\n TRACE_FIELD(int, prev_prio, prev-\u003eprio)\n TRACE_FIELD_SPECIAL(char next_comm[TASK_COMM_LEN],\n next_comm,\n TP_CMD(memcpy(TRACE_ENTRY-\u003enext_comm,\n next-\u003ecomm,\n TASK_COMM_LEN)))\n TRACE_FIELD(pid_t, next_pid, next-\u003epid)\n TRACE_FIELD(int, next_prio, next-\u003eprio)\n ),\n TP_RAW_FMT(\"prev %d:%d \u003d\u003d\u003e next %s:%d:%d\")\n );\n\nThe above method is hard to read and requires two format fields.\n\nThe new method:\n\n /*\n * Tracepoint for task switches, performed by the scheduler:\n *\n * (NOTE: the \u0027rq\u0027 argument is not used by generic trace events,\n * but used by the latency tracer plugin. )\n */\n TRACE_EVENT(sched_switch,\n\n\tTP_PROTO(struct rq *rq, struct task_struct *prev,\n\t\t struct task_struct *next),\n\n\tTP_ARGS(rq, prev, next),\n\n\tTP_STRUCT__entry(\n\t\t__array(\tchar,\tprev_comm,\tTASK_COMM_LEN\t)\n\t\t__field(\tpid_t,\tprev_pid\t\t\t)\n\t\t__field(\tint,\tprev_prio\t\t\t)\n\t\t__array(\tchar,\tnext_comm,\tTASK_COMM_LEN\t)\n\t\t__field(\tpid_t,\tnext_pid\t\t\t)\n\t\t__field(\tint,\tnext_prio\t\t\t)\n\t),\n\n\tTP_printk(\"task %s:%d [%d] \u003d\u003d\u003e %s:%d [%d]\",\n\t\t__entry-\u003eprev_comm, __entry-\u003eprev_pid, __entry-\u003eprev_prio,\n\t\t__entry-\u003enext_comm, __entry-\u003enext_pid, __entry-\u003enext_prio),\n\n\tTP_fast_assign(\n\t\tmemcpy(__entry-\u003enext_comm, next-\u003ecomm, TASK_COMM_LEN);\n\t\t__entry-\u003eprev_pid\t\u003d prev-\u003epid;\n\t\t__entry-\u003eprev_prio\t\u003d prev-\u003eprio;\n\t\tmemcpy(__entry-\u003eprev_comm, prev-\u003ecomm, TASK_COMM_LEN);\n\t\t__entry-\u003enext_pid\t\u003d next-\u003epid;\n\t\t__entry-\u003enext_prio\t\u003d next-\u003eprio;\n\t)\n );\n\nThis macro is called TRACE_EVENT, it is broken up into 5 parts:\n\n TP_PROTO: the proto type of the trace point\n TP_ARGS: the arguments of the trace point\n TP_STRUCT_entry: the structure layout of the entry in the ring buffer\n TP_printk: the printk format\n TP_fast_assign: the method used to write the entry into the ring buffer\n\nThe structure is the definition of how the event will be saved in the\nring buffer. The printk is used by the internal tracing in case of\nan oops, and the kernel needs to print out the format of the record\nto the console. This the TP_printk gives a means to show the records\nin a human readable format. It is also used to print out the data\nfrom the trace file.\n\nThe TP_fast_assign is executed directly. It is basically like a C function,\nwhere the __entry is the handle to the record.\n\nSigned-off-by: Steven Rostedt \u003csrostedt@redhat.com\u003e\n" }, { "commit": "9de36825b321fe9fe9cf73260554251af579f4ca", "tree": "0bde90baa93cb7a1ac09c6ae73d6ec1d67ac2f44", "parents": [ "769b0441f438c4bb4872cb8560eb6fe51bcc09ee" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Fri Mar 06 17:52:03 2009 +0100" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Fri Mar 06 17:59:12 2009 +0100" }, "message": "tracing: trace_bprintk() cleanups\n\nImpact: cleanup\n\nRemove a few leftovers and clean up the code a bit.\n\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Steven Rostedt \u003crostedt@goodmis.org\u003e\nLKML-Reference: \u003c1236356510-8381-5-git-send-email-fweisbec@gmail.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "769b0441f438c4bb4872cb8560eb6fe51bcc09ee", "tree": "9908682dfd89e97c3097a7c3adcae35d821e1895", "parents": [ "1ba28e02a18cbdbea123836f6c98efb09cbf59ec" ], "author": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Fri Mar 06 17:21:49 2009 +0100" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Fri Mar 06 17:59:12 2009 +0100" }, "message": "tracing/core: drop the old trace_printk() implementation in favour of trace_bprintk()\n\nImpact: faster and lighter tracing\n\nNow that we have trace_bprintk() which is faster and consume lesser\nmemory than trace_printk() and has the same purpose, we can now drop\nthe old implementation in favour of the binary one from trace_bprintk(),\nwhich means we move all the implementation of trace_bprintk() to\ntrace_printk(), so the Api doesn\u0027t change except that we must now use\ntrace_seq_bprintk() to print the TRACE_PRINT entries.\n\nSome changes result of this:\n\n- Previously, trace_bprintk depended of a single tracer and couldn\u0027t\n work without. This tracer has been dropped and the whole implementation\n of trace_printk() (like the module formats management) is now integrated\n in the tracing core (comes with CONFIG_TRACING), though we keep the file\n trace_printk (previously trace_bprintk.c) where we can find the module\n management. Thus we don\u0027t overflow trace.c\n\n- changes some parts to use trace_seq_bprintk() to print TRACE_PRINT entries.\n\n- change a bit trace_printk/trace_vprintk macros to support non-builtin formats\n constants, and fix \u0027const\u0027 qualifiers warnings. But this is all transparent for\n developers.\n\n- etc...\n\nV2:\n\n- Rebase against last changes\n- Fix mispell on the changelog\n\nV3:\n\n- Rebase against last changes (moving trace_printk() to kernel.h)\n\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nAcked-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\nLKML-Reference: \u003c1236356510-8381-5-git-send-email-fweisbec@gmail.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "1427cdf0592368bdec57276edaf714040ee8744f", "tree": "4b214ee49643db383328cf53a31959eb0627a167", "parents": [ "546e5354a6e4ec760ac03ef1148e9a4762abb5f5" ], "author": { "name": "Lai Jiangshan", "email": "laijs@cn.fujitsu.com", "time": "Fri Mar 06 17:21:47 2009 +0100" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Fri Mar 06 17:59:11 2009 +0100" }, "message": "tracing: infrastructure for supporting binary record\n\nImpact: save on memory for tracing\n\nCurrent tracers are typically using a struct(like struct ftrace_entry,\nstruct ctx_switch_entry, struct special_entr etc...)to record a binary\nevent. These structs can only record a their own kind of events.\nA new kind of tracer need a new struct and a lot of code too handle it.\n\nSo we need a generic binary record for events. This infrastructure\nis for this purpose.\n\n[fweisbec@gmail.com: rebase against latest -tip, make it safe while sched\ntracing as reported by Steven Rostedt]\n\nSigned-off-by: Lai Jiangshan \u003claijs@cn.fujitsu.com\u003e\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nAcked-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\nLKML-Reference: \u003c1236356510-8381-3-git-send-email-fweisbec@gmail.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "5e1607a00bd082972629d3d68c95c8bcf902b55a", "tree": "2751baf5ee286cdec8f4b1afcb7332f4c1f5f454", "parents": [ "53664738c122bfe8b0e489fddaf2ab265c9133c8" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Thu Mar 05 10:24:48 2009 +0100" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Thu Mar 05 10:24:48 2009 +0100" }, "message": "tracing: rename ftrace_printk() \u003d\u003e trace_printk()\n\nImpact: cleanup\n\nUse a more generic name - this also allows the prototype to move\nto kernel.h and be generally available to kernel developers who\nwant to do some quick tracing.\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "c032ef64d680717e4e8ce3da65da6419a35f8a2c", "tree": "f6d77c0033e9a33f22adac66d939338c55f06525", "parents": [ "e74da5235cec6cb71eb338c987f876ecc793138b" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Wed Mar 04 20:34:24 2009 -0500" }, "committer": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Wed Mar 04 20:34:24 2009 -0500" }, "message": "tracing: add latency output format option\n\nWith the removal of the latency_trace file, we lost the ability\nto see some of the finer details in a trace. Like the state of\ninterrupts enabled, the preempt count, need resched, and if we\nare in an interrupt handler, softirq handler or not.\n\nThis patch simply creates an option to bring back the old format.\nThis also removes the warning about an unused variable that held\nthe latency_trace file operations.\n\nSigned-off-by: Steven Rostedt \u003csrostedt@redhat.com\u003e\n" }, { "commit": "2cadf9135eb3b6d84b6427314be827ddd443c308", "tree": "919e201f615b8de6d0263ded5693bad326196671", "parents": [ "474d32b68d6d842f3e710e9ae9fe2568c53339f8" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Mon Dec 01 22:20:19 2008 -0500" }, "committer": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Tue Mar 03 21:01:55 2009 -0500" }, "message": "tracing: add binary buffer files for use with splice\n\nImpact: new feature\n\nThis patch creates a directory of files that correspond to the\nper CPU ring buffers. These are binary files and are made to\nbe used with splice. This is the fastest way to extract data from\nthe ftrace ring buffers.\n\nThanks to Jiaying Zhang for pushing me to get this code fixed,\n and to Eduard - Gabriel Munteanu for his splice code that helped\n me debug my code.\n\nSigned-off-by: Steven Rostedt \u003csrostedt@redhat.com\u003e\n" }, { "commit": "981d081ec8b958b7d962ee40d433581a55d40fc5", "tree": "366aa5da7dc98cc2354002946e6f19ec60c02301", "parents": [ "f9520750c4c9924c14325cd951efae5fae58104c" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Mon Mar 02 13:53:59 2009 -0500" }, "committer": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Mon Mar 02 14:27:27 2009 -0500" }, "message": "tracing: add format file to describe event struct fields\n\nThis patch adds the \"format\" file to the trace point event directory.\nThis is based off of work by Tom Zanussi, in which a file is exported\nto be tread from user land such that a user space app may read the\nbinary record stored in the ring buffer.\n\n # cat /debug/tracing/events/sched/sched_switch/format\n field:pid_t prev_pid; offset:12; size:4;\n field:int prev_prio; offset:16; size:4;\n field special:char next_comm[TASK_COMM_LEN]; offset:20; size:16;\n field:pid_t next_pid; offset:36; size:4;\n field:int next_prio; offset:40; size:4;\n\nIdea-from: Tom Zanussi \u003ctzanussi@gmail.com\u003e\nSigned-off-by: Steven Rostedt \u003csrostedt@redhat.com\u003e\n" }, { "commit": "f9520750c4c9924c14325cd951efae5fae58104c", "tree": "b6958c13894816db9388f856f101e9f67b3bf1a4", "parents": [ "11a241a3302277db05561e01477528629d806c4e" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Mon Mar 02 14:04:40 2009 -0500" }, "committer": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Mon Mar 02 14:08:51 2009 -0500" }, "message": "tracing: make trace_seq_reset global and rename to trace_seq_init\n\nImpact: clean up\n\nThe trace_seq functions may be used separately outside of the ftrace\niterator. The trace_seq_reset is needed for these operations.\n\nThis patch also renames trace_seq_reset to the more appropriate\ntrace_seq_init.\n\nSigned-off-by: Steven Rostedt \u003csrostedt@redhat.com\u003e\n" }, { "commit": "fd99498989f3b3feeab89dcadf537138ba136d24", "tree": "9470e9b4e886466511d47a70281e77e5a8c674ff", "parents": [ "c32e827b25054cb17b79cf97fb5e63ae4ce2223c" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Sat Feb 28 02:41:25 2009 -0500" }, "committer": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Sat Feb 28 04:04:03 2009 -0500" }, "message": "tracing: add raw fast tracing interface for trace events\n\nThis patch adds the interface to enable the C style trace points.\nIn the directory /debugfs/tracing/events/subsystem/event\nWe now have three files:\n\n enable : values 0 or 1 to enable or disable the trace event.\n\n available_types: values \u0027raw\u0027 and \u0027printf\u0027 which indicate the tracing\n types available for the trace point. If a developer does not\n use the TRACE_EVENT_FORMAT macro and just uses the TRACE_FORMAT\n macro, then only \u0027printf\u0027 will be available. This file is\n read only.\n\n type: values \u0027raw\u0027 or \u0027printf\u0027. This indicates which type of tracing\n is active for that trace point. \u0027printf\u0027 is the default and\n if \u0027raw\u0027 is not available, this file is read only.\n\n # echo raw \u003e /debug/tracing/events/sched/sched_wakeup/type\n # echo 1 \u003e /debug/tracing/events/sched/sched_wakeup/enable\n\n Will enable the C style tracing for the sched_wakeup trace point.\n\nSigned-off-by: Steven Rostedt \u003csrostedt@redhat.com\u003e\n" }, { "commit": "c32e827b25054cb17b79cf97fb5e63ae4ce2223c", "tree": "9a79a8662d88557303a671d147f80038b5fd87dc", "parents": [ "ef5580d0fffce6e0a01043bac0625128b5d409a7" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Fri Feb 27 19:12:30 2009 -0500" }, "committer": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Sat Feb 28 03:09:32 2009 -0500" }, "message": "tracing: add raw trace point recording infrastructure\n\nImpact: lower overhead tracing\n\nThe current event tracer can automatically pick up trace points\nthat are registered with the TRACE_FORMAT macro. But it required\na printf format string and parsing. Although, this adds the ability\nto get guaranteed information like task names and such, it took\na hit in overhead processing. This processing can add about 500-1000\nnanoseconds overhead, but in some cases that too is considered\ntoo much and we want to shave off as much from this overhead as\npossible.\n\nTom Zanussi recently posted tracing patches to lkml that are based\non a nice idea about capturing the data via C structs using\nSTRUCT_ENTER, STRUCT_EXIT type of macros.\n\nI liked that method very much, but did not like the implementation\nthat required a developer to add data/code in several disjoint\nlocations.\n\nThis patch extends the event_tracer macros to do a similar \"raw C\"\napproach that Tom Zanussi did. But instead of having the developers\nneeding to tweak a bunch of code all over the place, they can do it\nall in one macro - preferably placed near the code that it is\ntracing. That makes it much more likely that tracepoints will be\nmaintained on an ongoing basis by the code they modify.\n\nThe new macro TRACE_EVENT_FORMAT is created for this approach. (Note,\na developer may still utilize the more low level DECLARE_TRACE macros\nif they don\u0027t care about getting their traces automatically in the event\ntracer.)\n\nThey can also use the existing TRACE_FORMAT if they don\u0027t need to code\nthe tracepoint in C, but just want to use the convenience of printf.\n\nSo if the developer wants to \"hardwire\" a tracepoint in the fastest\npossible way, and wants to acquire their data via a user space utility\nin a raw binary format, or wants to see it in the trace output but not\nsacrifice any performance, then they can implement the faster but\nmore complex TRACE_EVENT_FORMAT macro.\n\nHere\u0027s what usage looks like:\n\n TRACE_EVENT_FORMAT(name,\n\tTPPROTO(proto),\n\tTPARGS(args),\n\tTPFMT(fmt, fmt_args),\n\tTRACE_STUCT(\n\t\tTRACE_FIELD(type1, item1, assign1)\n\t\tTRACE_FIELD(type2, item2, assign2)\n\t\t\t[...]\n\t),\n\tTPRAWFMT(raw_fmt)\n\t);\n\nNote name, proto, args, and fmt, are all identical to what TRACE_FORMAT\nuses.\n\n name: is the unique identifier of the trace point\n proto: The proto type that the trace point uses\n args: the args in the proto type\n fmt: printf format to use with the event printf tracer\n fmt_args: the printf argments to match fmt\n\n TRACE_STRUCT starts the ability to create a structure.\n Each item in the structure is defined with a TRACE_FIELD\n\n TRACE_FIELD(type, item, assign)\n\n type: the C type of item.\n item: the name of the item in the stucture\n assign: what to assign the item in the trace point callback\n\n raw_fmt is a way to pretty print the struct. It must match\n the order of the items are added in TRACE_STUCT\n\n An example of this would be:\n\n TRACE_EVENT_FORMAT(sched_wakeup,\n\tTPPROTO(struct rq *rq, struct task_struct *p, int success),\n\tTPARGS(rq, p, success),\n\tTPFMT(\"task %s:%d %s\",\n\t p-\u003ecomm, p-\u003epid, success?\"succeeded\":\"failed\"),\n\tTRACE_STRUCT(\n\t\tTRACE_FIELD(pid_t, pid, p-\u003epid)\n\t\tTRACE_FIELD(int, success, success)\n\t),\n\tTPRAWFMT(\"task %d success\u003d%d\")\n\t);\n\n This creates us a unique struct of:\n\n struct {\n\tpid_t\t\tpid;\n\tint\t\tsuccess;\n };\n\n And the way the call back would assign these values would be:\n\n\tentry-\u003epid \u003d p-\u003epid;\n\tentry-\u003esuccess \u003d success;\n\nThe nice part about this is that the creation of the assignent is done\nvia macro magic in the event tracer. Once the TRACE_EVENT_FORMAT is\ncreated, the developer will then have a faster method to record\ninto the ring buffer. They do not need to worry about the tracer itself.\n\nThe developer would only need to touch the files in include/trace/*.h\n\nAgain, I would like to give special thanks to Tom Zanussi for this\nnice idea.\n\nIdea-from: Tom Zanussi \u003ctzanussi@gmail.com\u003e\nSigned-off-by: Steven Rostedt \u003csrostedt@redhat.com\u003e\n" }, { "commit": "ef5580d0fffce6e0a01043bac0625128b5d409a7", "tree": "bc6ca68064d6b5c9853227ef876b391cc8b0c939", "parents": [ "3d7ba938da8481b4f7f9ed3d943dbae49389b284" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Fri Feb 27 19:38:04 2009 -0500" }, "committer": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Sat Feb 28 03:06:44 2009 -0500" }, "message": "tracing: add interface to write into current tracer buffer\n\nRight now all tracers must manage their own trace buffers. This was\nto enforce tracers to be independent in case we finally decide to\nallow each tracer to have their own trace buffer.\n\nBut now we are adding event tracing that writes to the current tracer\u0027s\nbuffer. This adds an interface to allow events to write to the current\ntracer buffer without having to manage its own. Since event tracing\nhas no \"tracer\", and is just a way to hook into any other tracer.\n\nSigned-off-by: Steven Rostedt \u003csrostedt@redhat.com\u003e\n" }, { "commit": "d7350c3f45694104e820041969c8185c5f99e57c", "tree": "7aaed9e59f6d33c82e0b62c21f9d1bda9f094b4e", "parents": [ "b04cc6b1f6398b0e0b60d37e27ce51b4899672ec" ], "author": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Wed Feb 25 06:13:16 2009 +0100" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Wed Feb 25 13:40:58 2009 +0100" }, "message": "tracing/core: make the read callbacks reentrants\n\nNow that several per-cpu files can be read or spliced at the\nsame, we want the read/splice callbacks for tracing files to be\nreentrants.\n\nUntil now, a single global mutex (trace_types_lock) serialized\nthe access to tracing_read_pipe(), tracing_splice_read_pipe(),\nand the seq helpers.\n\nIe: it means that if a user tries to read trace_pipe0 and\ntrace_pipe1 at the same time, the access to the function\ntracing_read_pipe() is contended and one reader must wait for\nthe other to finish its read call.\n\nThe trace_type_lock mutex is mostly here to serialize the access\nto the global current tracer (current_trace), which can be\nchanged concurrently. Although the iter struct keeps a private\npointer to this tracer, its callbacks can be changed by another\nfunction.\n\nThe method used here is to not keep anymore private reference to\nthe tracer inside the iterator but to make a copy of it inside\nthe iterator. Then it checks on subsequents read calls if the\ntracer has changed. This is not costly because the current\ntracer is not expected to be changed often, so we use a branch\nprediction for that.\n\nMoreover, we add a private mutex to the iterator (there is one\niterator per file descriptor) to serialize the accesses in case\nof multiple consumers per file descriptor (which would be a\nsilly idea from the user). Note that this is not to protect the\nring buffer, since the ring buffer already serializes the\nreaders accesses. This is to prevent from traces weirdness in\ncase of concurrent consumers. But these mutexes can be dropped\nanyway, that would not result in any crash. Just tell me what\nyou think about it.\n\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\nCc: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nCc: Steven Rostedt \u003crostedt@goodmis.org\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "b04cc6b1f6398b0e0b60d37e27ce51b4899672ec", "tree": "61d5bd59b364913f5a124d25925b908c5deaf871", "parents": [ "2b1b858f690d6369a59ad241335eeedec6eb0c8c" ], "author": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Wed Feb 25 03:22:28 2009 +0100" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Wed Feb 25 13:40:58 2009 +0100" }, "message": "tracing/core: introduce per cpu tracing files\n\nImpact: split up tracing output per cpu\n\nCurrently, on the tracing debugfs directory, three files are\navailable to the user to let him extracting the trace output:\n\n- trace is an iterator through the ring-buffer. It\u0027s a reader\n but not a consumer It doesn\u0027t block when no more traces are\n available.\n\n- trace pretty similar to the former, except that it adds more\n informations such as prempt count, irq flag, ...\n\n- trace_pipe is a reader and a consumer, it will also block\n waiting for traces if necessary (heh, yes it\u0027s a pipe).\n\nThe traces coming from different cpus are curretly mixed up\ninside these files. Sometimes it messes up the informations,\nsometimes it\u0027s useful, depending on what does the tracer\ncapture.\n\nThe tracing_cpumask file is useful to filter the output and\nselect only the traces captured a custom defined set of cpus.\nBut still it is not enough powerful to extract at the same time\none trace buffer per cpu.\n\nSo this patch creates a new directory: /debug/tracing/per_cpu/.\n\nInside this directory, you will now find one trace_pipe file and\none trace file per cpu.\n\nWhich means if you have two cpus, you will have:\n\n trace0\n trace1\n trace_pipe0\n trace_pipe1\n\nAnd of course, reading these files will have the same effect\nthan with the usual tracing files, except that you will only see\nthe traces from the given cpu.\n\nThe original all-in-one cpu trace file are still available on\ntheir original place.\n\nUntil now, only one consumer was allowed on trace_pipe to avoid\nracy consuming on the ring-buffer. Now the approach changed a\nbit, you can have only one consumer per cpu.\n\nWhich means you are allowed to read concurrently trace_pipe0 and\ntrace_pipe1 But you can\u0027t have two readers on trace_pipe0 or\ntrace_pipe1.\n\nFollowing the same logic, if there is one reader on the common\ntrace_pipe, you can not have at the same time another reader on\ntrace_pipe0 or in trace_pipe1. Because in trace_pipe is already\na consumer in all cpu buffers in essence.\n\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\nCc: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nCc: Steven Rostedt \u003crostedt@goodmis.org\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "6eaaa5d57e76c454479833fc8594cd7c3b75c789", "tree": "c8f3c130004199bbbc8d141bbfb0f216539c0724", "parents": [ "ac07bcaa8259841905ead3f8cd60b1923ca6c0e5" ], "author": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Wed Feb 11 02:25:00 2009 +0100" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Wed Feb 18 01:40:20 2009 +0100" }, "message": "tracing/core: use appropriate waiting on trace_pipe\n\nImpact: api and pipe waiting change\n\nCurrently, the waiting used in tracing_read_pipe() is done through a\n100 msecs schedule_timeout() loop which periodically check if there\nare traces on the buffer.\n\nThis can cause small latencies for programs which are reading the incoming\nevents.\n\nThis patch makes the reader waiting for the trace_wait waitqueue except\nfor few tracers such as the sched and functions tracers which might be\nalready hold the runqueue lock while waking up the reader.\n\nThis is performed through a new callback wait_pipe() on struct tracer.\nIf none is implemented on a specific tracer, the default waiting for\ntrace_wait queue is attached.\n\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "3c56819b14b00dd449bd776303e61f8532fad09f", "tree": "5a0617aa39fa441673382cf69d873b1906146e7e", "parents": [ "b91facc367366b3f71375f337eb5997ec9ab4e69" ], "author": { "name": "Eduard - Gabriel Munteanu", "email": "eduard.munteanu@linux360.ro", "time": "Mon Feb 09 08:15:56 2009 +0200" }, "committer": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Mon Feb 09 12:24:34 2009 -0500" }, "message": "tracing: splice support for tracing_pipe\n\nAdded and implemented tracing_pipe_fops-\u003esplice_read(). This allows\nuserspace programs to get tracing data more efficiently.\n\nSigned-off-by: Eduard - Gabriel Munteanu \u003ceduard.munteanu@linux360.ro\u003e\nSigned-off-by: Steven Rostedt \u003csrostedt@redhat.com\u003e\n" }, { "commit": "b91facc367366b3f71375f337eb5997ec9ab4e69", "tree": "1f7c8914f493080cadcfdec23b33d9a5936fe98b", "parents": [ "1dfba05d0f1a9b4245bb242a7c17fe448811a520" ], "author": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Fri Feb 06 18:30:44 2009 +0100" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Feb 09 12:37:27 2009 +0100" }, "message": "tracing/function-graph-tracer: handle the leaf functions from trace_pipe\n\nWhen one cats the trace file, the leaf functions are printed without brackets:\n\n function();\n\nwhereas in the trace_pipe file we\u0027ll see the following:\n\n function() {\n }\n\nThis is because the ring_buffer handling is not the same between those two files.\nOn the trace file, when an entry is printed, the iterator advanced and then we can\ncheck the next entry.\n\nThere is no iterator with trace_pipe, the current entry to print has been peeked\nand not consumed. So checking the next entry will still return the current one while\nwe don\u0027t consume it.\n\nThis patch introduces a new value for the output callbacks to ask the tracing\ncore to not consume the current entry after printing it.\n\nWe need it because we will have to consume the current entry ourself to check\nthe next one.\n\nNow the trace_pipe is able to handle well the leaf functions.\n\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nAcked-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "1292211058aaf872eeb2a0e2677d237916b4501f", "tree": "7127ffe80e42faed85bf45b4182c97a39f299642", "parents": [ "7447dce96f2233d250bc39a4a10a42f7c3dd46fc" ], "author": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Sat Feb 07 22:16:12 2009 +0100" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Feb 09 10:51:38 2009 +0100" }, "message": "tracing/power: move the power trace headers to a dedicated file\n\nImpact: cleanup\n\nMove the power tracer headers to trace/power.h to keep ftrace.h and power bits\nmore easy to maintain as separated topics.\n\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Arjan van de Ven \u003carjan@infradead.org\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "7447dce96f2233d250bc39a4a10a42f7c3dd46fc", "tree": "c02c991cca658e69a0c83c1a93b068df1d5caa53", "parents": [ "2db270a80b8f2238e536876cfb3987af02684df8" ], "author": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Sat Feb 07 21:33:57 2009 +0100" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Feb 09 10:51:37 2009 +0100" }, "message": "tracing/function-graph-tracer: provide a selftest for the function graph tracer\n\nMaking it more easy to do a basic regression test for this tracer.\n\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "44b0635481437140b0e29d6023f05e805d5e7620", "tree": "ff31986115075410d0479df307a6b9841976026c", "parents": [ "4ad476e11f94fd3724c6e272d8220e99cd222b27", "57794a9d48b63e34acbe63282628c9f029603308" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Feb 09 10:35:12 2009 +0100" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Feb 09 10:35:12 2009 +0100" }, "message": "Merge branch \u0027tip/tracing/core/devel\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-2.6-trace into tracing/ftrace\n\nConflicts:\n\tkernel/trace/trace_hw_branches.c\n" }, { "commit": "57794a9d48b63e34acbe63282628c9f029603308", "tree": "ed42d073f82cd91b8d8a331c60814aa699c3293d", "parents": [ "a81bd80a0b0a405dc0483e2c428332d69da2c79f" ], "author": { "name": "Wenji Huang", "email": "wenji.huang@oracle.com", "time": "Fri Feb 06 17:33:27 2009 +0800" }, "committer": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Sat Feb 07 20:03:36 2009 -0500" }, "message": "trace: trivial fixes in comment typos.\n\nImpact: clean up\n\nFixed several typos in the comments.\n\nSigned-off-by: Wenji Huang \u003cwenji.huang@oracle.com\u003e\nSigned-off-by: Steven Rostedt \u003csrostedt@redhat.com\u003e\n" }, { "commit": "1830b52d0de8c60c4f5dfbac134aa8f69d815801", "tree": "2aa803853ac145fedd0d65324d77f64d25e7b3a2", "parents": [ "43769f10b4826376cbf4ce17af74a5b4e8dc4fcd" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Sat Feb 07 19:38:43 2009 -0500" }, "committer": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Sat Feb 07 19:38:43 2009 -0500" }, "message": "trace: remove deprecated entry-\u003ecpu\n\nImpact: fix to prevent developers from using entry-\u003ecpu\n\nWith the new ring buffer infrastructure, the cpu for the entry is\nimplicit with which CPU buffer it is on.\n\nThe original code use to record the current cpu into the generic\nentry header, which can be retrieved by entry-\u003ecpu. When the\nring buffer was introduced, the users were convert to use the\nthe cpu number of which cpu ring buffer was in use (this was passed\nto the tracers by the iterator: iter-\u003ecpu).\n\nUnfortunately, the cpu item in the entry structure was never removed.\nThis allowed for developers to use it instead of the proper iter-\u003ecpu,\nunknowingly, using an uninitialized variable. This was not the fault\nof the developers, since it would seem like the logical place to\nretrieve the cpu identifier.\n\nThis patch removes the cpu item from the entry structure and fixes\nall the users that should have been using iter-\u003ecpu.\n\nSigned-off-by: Steven Rostedt \u003csrostedt@redhat.com\u003e\n" }, { "commit": "b6f11df26fdc28324cf9c9e3b77f2dc985c1bb13", "tree": "e03b4b8b9dad8a2d3f81574c10aab8fb7a779cbb", "parents": [ "51a763dd84253bab1d0a1e68e11a7753d1b702ca" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Thu Feb 05 18:02:00 2009 -0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Fri Feb 06 01:01:41 2009 +0100" }, "message": "trace: Call tracing_reset_online_cpus before tracer-\u003einit()\n\nImpact: cleanup\n\nTo make it easy for ftrace plugin writers, as this was open coded in\nthe existing plugins\n\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\nAcked-by: Frédéric Weisbecker \u003cfweisbec@gmail.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "51a763dd84253bab1d0a1e68e11a7753d1b702ca", "tree": "2cc2cf0509db480391c585786285267e360c1338", "parents": [ "0a9877514c4fed10a70720293b37213dd172ee3e" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Thu Feb 05 16:14:13 2009 -0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Fri Feb 06 01:01:41 2009 +0100" }, "message": "tracing: Introduce trace_buffer_{lock_reserve,unlock_commit}\n\nImpact: new API\n\nThese new functions do what previously was being open coded, reducing\nthe number of details ftrace plugin writers have to worry about.\n\nIt also standardizes the handling of stacktrace, userstacktrace and\nother trace options we may introduce in the future.\n\nWith this patch, for instance, the blk tracer (and some others already\nin the tree) can use the \"userstacktrace\" /d/tracing/trace_options\nfacility.\n\n$ codiff /tmp/vmlinux.before /tmp/vmlinux.after\nlinux-2.6-tip/kernel/trace/trace.c:\n trace_vprintk | -5\n trace_graph_return | -22\n trace_graph_entry | -26\n trace_function | -45\n __ftrace_trace_stack | -27\n ftrace_trace_userstack | -29\n tracing_sched_switch_trace | -66\n tracing_stop | +1\n trace_seq_to_user | -1\n ftrace_trace_special | -63\n ftrace_special | +1\n tracing_sched_wakeup_trace | -70\n tracing_reset_online_cpus | -1\n 13 functions changed, 2 bytes added, 355 bytes removed, diff: -353\n\nlinux-2.6-tip/block/blktrace.c:\n __blk_add_trace | -58\n 1 function changed, 58 bytes removed, diff: -58\n\nlinux-2.6-tip/kernel/trace/trace.c:\n trace_buffer_lock_reserve | +88\n trace_buffer_unlock_commit | +86\n 2 functions changed, 174 bytes added, diff: +174\n\n/tmp/vmlinux.after:\n 16 functions changed, 176 bytes added, 413 bytes removed, diff: -237\n\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\nAcked-by: Frédéric Weisbecker \u003cfweisbec@gmail.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "7be421510b91491d5aa5a29fa1005712039b95af", "tree": "43c85cd688ea4e33b32816bb3f363215d572f052", "parents": [ "97e5b191ae7dc0f4f5b82b9db29782928b103b4d" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Thu Feb 05 01:13:37 2009 -0500" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Thu Feb 05 14:35:47 2009 +0100" }, "message": "trace: Remove unused trace_array_cpu parameter\n\nImpact: cleanup\n\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\nSigned-off-by: Steven Rostedt \u003csrostedt@redhat.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "c4a8e8be2d43cc22b371e8e9c05c253409759d94", "tree": "274962a78a082a11550d07c6cc088817d6558db5", "parents": [ "dc573f9b20c8710105ac35c08ed0fe1da5160ecd" ], "author": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Mon Feb 02 20:29:21 2009 -0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Tue Feb 03 14:03:52 2009 +0100" }, "message": "trace: better manage the context info for events\n\nImpact: make trace_event more convenient for tracers\n\nAll tracers (for the moment) that use the struct trace_event want to\nhave the context info printed before their own output: the pid/cmdline,\ncpu, and timestamp.\n\nBut some other tracers that want to implement their trace_event\ncallbacks will not necessary need these information or they may want to\nformat them as they want.\n\nThis patch adds a new default-enabled trace option:\nTRACE_ITER_CONTEXT_INFO When disabled through:\n\necho nocontext-info \u003e /debugfs/tracing/trace_options\n\nThe pid, cpu and timestamps headers will not be printed.\n\nIE with the sched_switch tracer with context-info (default):\n\n bash-2935 [001] 100.356561: 2935:120:S \u003d\u003d\u003e [001] 0:140:R \u003cidle\u003e\n \u003cidle\u003e-0 [000] 100.412804: 0:140:R + [000] 11:115:S events/0\n \u003cidle\u003e-0 [000] 100.412816: 0:140:R \u003d\u003d\u003e [000] 11:115:R events/0\n events/0-11 [000] 100.412829: 11:115:S \u003d\u003d\u003e [000] 0:140:R \u003cidle\u003e\n\nWithout context-info:\n\n 2935:120:S \u003d\u003d\u003e [001] 0:140:R \u003cidle\u003e\n 0:140:R + [000] 11:115:S events/0\n 0:140:R \u003d\u003d\u003e [000] 11:115:R events/0\n 11:115:S \u003d\u003d\u003e [000] 0:140:R \u003cidle\u003e\n\nA tracer can disable it at runtime by clearing the bit\nTRACE_ITER_CONTEXT_INFO in trace_flags.\n\nThe print routines were renamed to trace_print_context and\ntrace_print_lat_context, so that they can be used by tracers if they\nwant to use them for one of the trace_event callbacks.\n\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "c71a896154119f4ca9e89d6078f5f63ad60ef199", "tree": "0018ea80af12d6385fd0aa5295dddefdb284eebe", "parents": [ "9011262a37cb438f0fa9394b5e83840db8f9680a" ], "author": { "name": "Arnaldo Carvalho de Melo", "email": "acme@redhat.com", "time": "Fri Jan 23 12:06:27 2009 -0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Jan 26 14:40:53 2009 +0100" }, "message": "blktrace: add ftrace plugin\n\nImpact: New way of using the blktrace infrastructure\n\nThis drops the requirement of userspace utilities to use the blktrace\nfacility.\n\nConfiguration is done thru sysfs, adding a \"trace\" directory to the\npartition directory where blktrace can be enabled for the associated\nrequest_queue.\n\nThe same filters present in the IOCTL interface are present as sysfs\ndevice attributes.\n\nThe /sys/block/sdX/sdXN/trace/enable file allows tracing without any\nfilters.\n\nThe other files in this directory: pid, act_mask, start_lba and end_lba\ncan be used with the same meaning as with the IOCTL interface.\n\nUsing the sysfs interface will only setup the request_queue-\u003eblk_trace\nfields, tracing will only take place when the \"blk\" tracer is selected\nvia the ftrace interface, as in the following example:\n\nTo see the trace, one can use the /d/tracing/trace file or the\n/d/tracign/trace_pipe file, with semantics defined in the ftrace\ndocumentation in Documentation/ftrace.txt.\n\n[root@f10-1 ~]# cat /t/trace\n kjournald-305 [000] 3046.491224: 8,1 A WBS 6367 + 8 \u003c- (8,1) 6304\n kjournald-305 [000] 3046.491227: 8,1 Q R 6367 + 8 [kjournald]\n kjournald-305 [000] 3046.491236: 8,1 G RB 6367 + 8 [kjournald]\n kjournald-305 [000] 3046.491239: 8,1 P NS [kjournald]\n kjournald-305 [000] 3046.491242: 8,1 I RBS 6367 + 8 [kjournald]\n kjournald-305 [000] 3046.491251: 8,1 D WB 6367 + 8 [kjournald]\n kjournald-305 [000] 3046.491610: 8,1 U WS [kjournald] 1\n \u003cidle\u003e-0 [000] 3046.511914: 8,1 C RS 6367 + 8 [6367]\n[root@f10-1 ~]#\n\nThe default line context (prefix) format is the one described in the ftrace\ndocumentation, with the blktrace specific bits using its existing format,\ndescribed in blkparse(8).\n\nIf one wants to have the classic blktrace formatting, this is possible by\nusing:\n\n[root@f10-1 ~]# echo blk_classic \u003e /t/trace_options\n[root@f10-1 ~]# cat /t/trace\n 8,1 0 3046.491224 305 A WBS 6367 + 8 \u003c- (8,1) 6304\n 8,1 0 3046.491227 305 Q R 6367 + 8 [kjournald]\n 8,1 0 3046.491236 305 G RB 6367 + 8 [kjournald]\n 8,1 0 3046.491239 305 P NS [kjournald]\n 8,1 0 3046.491242 305 I RBS 6367 + 8 [kjournald]\n 8,1 0 3046.491251 305 D WB 6367 + 8 [kjournald]\n 8,1 0 3046.491610 305 U WS [kjournald] 1\n 8,1 0 3046.511914 0 C RS 6367 + 8 [6367]\n[root@f10-1 ~]#\n\nUsing the ftrace standard format allows more flexibility, such\nas the ability of asking for backtraces via trace_options:\n\n[root@f10-1 ~]# echo noblk_classic \u003e /t/trace_options\n[root@f10-1 ~]# echo stacktrace \u003e /t/trace_options\n\n[root@f10-1 ~]# cat /t/trace\n kjournald-305 [000] 3318.826779: 8,1 A WBS 6375 + 8 \u003c- (8,1) 6312\n kjournald-305 [000] 3318.826782:\n \u003c\u003d submit_bio\n \u003c\u003d submit_bh\n \u003c\u003d sync_dirty_buffer\n \u003c\u003d journal_commit_transaction\n \u003c\u003d kjournald\n \u003c\u003d kthread\n \u003c\u003d child_rip\n kjournald-305 [000] 3318.826836: 8,1 Q R 6375 + 8 [kjournald]\n kjournald-305 [000] 3318.826837:\n \u003c\u003d generic_make_request\n \u003c\u003d submit_bio\n \u003c\u003d submit_bh\n \u003c\u003d sync_dirty_buffer\n \u003c\u003d journal_commit_transaction\n \u003c\u003d kjournald\n \u003c\u003d kthread\n\nPlease read the ftrace documentation to use aditional, standardized\ntracing filters such as /d/tracing/trace_cpumask, etc.\n\nSee also /d/tracing/trace_mark to add comments in the trace stream,\nthat is equivalent to the /d/block/sdaN/msg interface.\n\nSigned-off-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "b1818748b0cf9427e48acf9713295e829a0d715f", "tree": "49e8f8dc4328799fa69eae635f4b69ee97228445", "parents": [ "5c5317de147e9b38ea9c4cbdc2d15bed7648d036" ], "author": { "name": "Markus Metzger", "email": "markus.t.metzger@intel.com", "time": "Mon Jan 19 10:31:01 2009 +0100" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Tue Jan 20 13:03:48 2009 +0100" }, "message": "x86, ftrace, hw-branch-tracer: dump trace on oops\n\nDump the branch trace on an oops (based on ftrace_dump_on_oops).\n\nSigned-off-by: Markus Metzger \u003cmarkus.t.metzger@intel.com\u003e\nSigned-off-by: Steven Rostedt \u003csrostedt@redhat.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "a225cdd263f340c864febb1992802fb5b08bc328", "tree": "a457f609c0071216c37f255cbaba00217bf1a7ed", "parents": [ "3eb36aa05329a47cbe201c151fd0024a4a3649cd" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Thu Jan 15 23:06:03 2009 -0500" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Fri Jan 16 12:17:58 2009 +0100" }, "message": "ftrace: remove static from function tracer functions\n\nImpact: clean up\n\nAfter reorganizing the functions in trace.c and trace_function.c,\nthey no longer need to be in global context. This patch makes the\nfunctions and one variable into static.\n\nSigned-off-by: Steven Rostedt \u003csrostedt@redhat.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "5361499101306cfb776c3cfa0f69d0479bc63868", "tree": "1acf51a942abe6582e08ed86b4bbb98f9c095c89", "parents": [ "6c1a99afbda99cd8d8c69d756387041567a13d87" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Thu Jan 15 19:12:40 2009 -0500" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Fri Jan 16 12:15:32 2009 +0100" }, "message": "ftrace: add stack trace to function tracer\n\nImpact: new feature to stack trace any function\n\nChris Mason asked about being able to pick and choose a function\nand get a stack trace from it. This feature enables his request.\n\n # echo io_schedule \u003e /debug/tracing/set_ftrace_filter\n # echo function \u003e /debug/tracing/current_tracer\n # echo func_stack_trace \u003e /debug/tracing/trace_options\n\nProduces the following in /debug/tracing/trace:\n\n kjournald-702 [001] 135.673060: io_schedule \u003c-sync_buffer\n kjournald-702 [002] 135.673671:\n \u003c\u003d sync_buffer\n \u003c\u003d __wait_on_bit\n \u003c\u003d out_of_line_wait_on_bit\n \u003c\u003d __wait_on_buffer\n \u003c\u003d sync_dirty_buffer\n \u003c\u003d journal_commit_transaction\n \u003c\u003d kjournald\n\nNote, be careful about turning this on without filtering the functions.\nYou may find that you have a 10 second lag between typing and seeing\nwhat you typed. This is why the stack trace for the function tracer\ndoes not use the same stack_trace flag as the other tracers use.\n\nSigned-off-by: Steven Rostedt \u003csrostedt@redhat.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "002bb86d8d42f18937aef396c3ecd65c7e02e21a", "tree": "ce8e81f6dc2515f6442198bbd4b527d900982f8e", "parents": [ "a14a07b8018b714e03a39ff2180c66e307ef4238" ], "author": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Sat Jan 10 11:34:13 2009 -0800" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Wed Jan 14 12:11:37 2009 +0100" }, "message": "tracing/ftrace: separate events tracing and stats tracing engine\n\nImpact: tracing\u0027s Api change\n\nCurrently, the stat tracing depends on the events tracing.\nWhen you switch to a new tracer, the stats files of the previous tracer\nwill disappear. But it\u0027s more scalable to separate those two engines.\nThis way, we can keep the stat files of one or several tracers when we\nwant, without bothering of multiple tracer stat files or tracer switching.\n\nTo build/destroys its stats files, a tracer just have to call\nregister_stat_tracer/unregister_stat_tracer everytimes it wants to.\n\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nSigned-off-by: Steven Rostedt \u003csrostedt@redhat.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "034939b65ad5ff64b9709210b3469a95153c51a3", "tree": "14fc36bdcabc9c76ac179e4b39b7af11fcbdfb35", "parents": [ "67d347245f76a149c45bffb1a10145d31d61d1da" ], "author": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Thu Jan 08 10:03:56 2009 -0800" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Sun Jan 11 04:00:44 2009 +0100" }, "message": "tracing/ftrace: handle more than one stat file per tracer\n\nImpact: new API for tracers\n\nMake the stat tracing API reentrant. And also provide the new directory\n/debugfs/tracing/trace_stat which will contain all the stat files for the\ncurrent active tracer.\n\nNow a tracer will, if desired, want to provide a zero terminated array of\ntracer_stat structures.\nEach one contains the callbacks necessary for one stat file.\nIt have to provide at least a name for its stat file, an iterator with\nstat_start/start_next callback and an output callback for one stat entry.\n\nAlso adapt the branch tracer to this new API.\nWe create two files \"all\" and \"annotated\" inside the /debugfs/tracing/trace_stat\ndirectory, making the both stats simultaneously available instead of needing\nto change an option to switch from one stat file to another.\n\nThe output of these stats haven\u0027t changed.\n\nChanges in v2:\n\n_ Apply the previous memory leak fix (rebase against tip/master)\n\nChanges in v3:\n\n_ Merge the patch that adapted the branch tracer to this Api in this patch to\n not break the kernel build.\n\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nSigned-off-by: Steven Rostedt \u003csrostedt@redhat.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "99793e3dbe39a50d871eedc361659a894601e2bf", "tree": "a676d42a42f4c884e38121e5a5a4d6630929a9f7", "parents": [ "3e80680208ba6ce9635ca7c21ad0019442ea166a", "a103e2ab7377dbbef2506be59c49a3f2ae10b60b" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Tue Jan 06 10:18:43 2009 +0100" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Tue Jan 06 10:18:43 2009 +0100" }, "message": "Merge branches \u0027tracing/kmemtrace2\u0027 and \u0027tracing/ftrace\u0027 into tracing/urgent\n" }, { "commit": "3d7a96f5a485b7d06c2379f343d7312af89ec9e2", "tree": "5f097f68eb0f9fd3fa4a10f38672e300e9127b10", "parents": [ "723cbe0775514853c22dc45005af59c360916af1", "238c6d54830c624f34ac9cf123ac04aebfca5013" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Tue Jan 06 09:53:05 2009 +0100" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Tue Jan 06 09:53:05 2009 +0100" }, "message": "Merge branch \u0027linus\u0027 into tracing/kmemtrace2\n" }, { "commit": "4462344ee9ea9224d026801b877887f2f39774a3", "tree": "deb703d6858f2fb7f7db69c65e90560ce4a0654e", "parents": [ "9e01c1b74c9531e301c900edaa92a99fcb7738f2" ], "author": { "name": "Rusty Russell", "email": "rusty@rustcorp.com.au", "time": "Thu Jan 01 10:12:23 2009 +1030" }, "committer": { "name": "Rusty Russell", "email": "rusty@rustcorp.com.au", "time": "Thu Jan 01 10:12:23 2009 +1030" }, "message": "cpumask: convert kernel trace functions further\n\nImpact: Reduce future memory usage, use new cpumask API.\n\nSince the last patch was created and acked, more old cpumask users\nslipped into kernel/trace.\n\nMostly trivial conversions, except struct trace_iterator\u0027s \"started\"\nmember becomes a cpumask_var_t.\n\nSigned-off-by: Rusty Russell \u003crusty@rustcorp.com.au\u003e\n" }, { "commit": "36994e58a48fb8f9651c7dc845a6de298aba5bfc", "tree": "fac4b8a1c30560e91460651487f3a57ef7f2b5cc", "parents": [ "7a51cffbd10886c0557677dd916c090097c691ef" ], "author": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Mon Dec 29 13:42:23 2008 -0800" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Tue Dec 30 09:36:13 2008 +0100" }, "message": "tracing/kmemtrace: normalize the raw tracer event to the unified tracing API\n\nImpact: new tracer plugin\n\nThis patch adapts kmemtrace raw events tracing to the unified tracing API.\n\nTo enable and use this tracer, just do the following:\n\n echo kmemtrace \u003e /debugfs/tracing/current_tracer\n cat /debugfs/tracing/trace\n\nYou will have the following output:\n\n # tracer: kmemtrace\n #\n #\n # ALLOC TYPE REQ GIVEN FLAGS POINTER NODE CALLER\n # FREE | | | | | | | |\n # |\n\ntype_id 1 call_site 18446744071565527833 ptr 18446612134395152256\ntype_id 0 call_site 18446744071565585597 ptr 18446612134405955584 bytes_req 4096 bytes_alloc 4096 gfp_flags 208 node -1\ntype_id 1 call_site 18446744071565585534 ptr 18446612134405955584\ntype_id 0 call_site 18446744071565585597 ptr 18446612134405955584 bytes_req 4096 bytes_alloc 4096 gfp_flags 208 node -1\ntype_id 0 call_site 18446744071565636711 ptr 18446612134345164672 bytes_req 240 bytes_alloc 240 gfp_flags 208 node -1\ntype_id 1 call_site 18446744071565585534 ptr 18446612134405955584\ntype_id 0 call_site 18446744071565585597 ptr 18446612134405955584 bytes_req 4096 bytes_alloc 4096 gfp_flags 208 node -1\ntype_id 0 call_site 18446744071565636711 ptr 18446612134345164912 bytes_req 240 bytes_alloc 240 gfp_flags 208 node -1\ntype_id 1 call_site 18446744071565585534 ptr 18446612134405955584\ntype_id 0 call_site 18446744071565585597 ptr 18446612134405955584 bytes_req 4096 bytes_alloc 4096 gfp_flags 208 node -1\ntype_id 0 call_site 18446744071565636711 ptr 18446612134345165152 bytes_req 240 bytes_alloc 240 gfp_flags 208 node -1\ntype_id 0 call_site 18446744071566144042 ptr 18446612134346191680 bytes_req 1304 bytes_alloc 1312 gfp_flags 208 node -1\ntype_id 1 call_site 18446744071565585534 ptr 18446612134405955584\ntype_id 0 call_site 18446744071565585597 ptr 18446612134405955584 bytes_req 4096 bytes_alloc 4096 gfp_flags 208 node -1\ntype_id 1 call_site 18446744071565585534 ptr 18446612134405955584\n\nThat was to stay backward compatible with the format output produced in\ninux/tracepoint.h.\n\nThis is the default ouput, but note that I tried something else.\n\nIf you change an option:\n\necho kmem_minimalistic \u003e /debugfs/trace_options\n\nand then cat /debugfs/trace, you will have the following output:\n\n # tracer: kmemtrace\n #\n #\n # ALLOC TYPE REQ GIVEN FLAGS POINTER NODE CALLER\n # FREE | | | | | | | |\n # |\n\n - C 0xffff88007c088780 file_free_rcu\n + K 4096 4096 000000d0 0xffff88007cad6000 -1 getname\n - C 0xffff88007cad6000 putname\n + K 4096 4096 000000d0 0xffff88007cad6000 -1 getname\n + K 240 240 000000d0 0xffff8800790dc780 -1 d_alloc\n - C 0xffff88007cad6000 putname\n + K 4096 4096 000000d0 0xffff88007cad6000 -1 getname\n + K 240 240 000000d0 0xffff8800790dc870 -1 d_alloc\n - C 0xffff88007cad6000 putname\n + K 4096 4096 000000d0 0xffff88007cad6000 -1 getname\n + K 240 240 000000d0 0xffff8800790dc960 -1 d_alloc\n + K 1304 1312 000000d0 0xffff8800791d7340 -1 reiserfs_alloc_inode\n - C 0xffff88007cad6000 putname\n + K 4096 4096 000000d0 0xffff88007cad6000 -1 getname\n - C 0xffff88007cad6000 putname\n + K 992 1000 000000d0 0xffff880079045b58 -1 alloc_inode\n + K 768 1024 000080d0 0xffff88007c096400 -1 alloc_pipe_info\n + K 240 240 000000d0 0xffff8800790dca50 -1 d_alloc\n + K 272 320 000080d0 0xffff88007c088780 -1 get_empty_filp\n + K 272 320 000080d0 0xffff88007c088000 -1 get_empty_filp\n\nYeah I shall confess kmem_minimalistic should be: kmem_alternative.\n\nWhatever, I find it more readable but this a personal opinion of course.\nWe can drop it if you want.\n\nOn the ALLOC/FREE column, + means an allocation and - a free.\n\nOn the type column, you have K \u003d kmalloc, C \u003d cache, P \u003d page\n\nI would like the flags to be GFP_* strings but that would not be easy to not\nbreak the column with strings....\n\nAbout the node...it seems to always be -1. I don\u0027t know why but that shouldn\u0027t\nbe difficult to find.\n\nI moved linux/tracepoint.h to trace/tracepoint.h as well. I think that would\nbe more easy to find the tracer headers if they are all in their common\ndirectory.\n\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "f7d48cbde5c0710008caeaf7dbf14f4a9b064940", "tree": "f7b6bed9338b26bcdb4d95da434eab92463d8a5a", "parents": [ "e302cf3f961ceb54c1dd0aff7ba8531df83be07a" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Dec 29 13:02:17 2008 +0100" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Dec 29 13:06:24 2008 +0100" }, "message": "tracing/ftrace: make trace_find_cmdline() generally available\n\nImpact: build fix\n\nOn !CONFIG_CONTEXT_SWITCH_TRACER trace_find_cmdline() is not defined:\n\n kernel/trace/trace_output.c: In function \u0027trace_ctxwake_print\u0027:\n kernel/trace/trace_output.c:499: error: implicit declaration of function \u0027trace_find_cmdline\u0027\n kernel/trace/trace_output.c:499: warning: assignment makes pointer from integer without a cast\n\nMove it to the generic section in trace.h.\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "dbd0b4b33074aa6b7832a9d9a5bd985eca5c1aa2", "tree": "b2f498a25c176cdba29cb1f9d1e854d38204192e", "parents": [ "f633cef0200bbaec539e2dbb0bc4bed7f022f98b" ], "author": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Sun Dec 28 20:44:51 2008 -0800" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Dec 29 12:55:45 2008 +0100" }, "message": "tracing/ftrace: provide the base infrastructure for histogram tracing\n\nImpact: extend the tracing API\n\nThe goal of this patch is to normalize and make more easy the\nimplementation of statistical (histogram) tracing.\n\nIt implements a trace_stat file into the /debugfs/tracing directory where\none can print a one-shot output of statistics/histogram entries.\n\nA tracer has to provide two basic iterator callbacks:\n\n stat_start() \u003d\u003e the first entry\n stat_next(prev, idx) \u003d\u003e the next one.\n\nNote that it is adapted for arrays or hash tables or lists.... since it\nprovides a pointer to the previous entry and the current index of the\niterator.\n\nThese two callbacks are called to get a snapshot of the statistics at each\nopening of the trace_stat file because. The values are so updated between\ntwo \"cat trace_stat\". And the tracer is free to lock its datas during the\niteration to keep consistent values.\n\nSince it is almost always interesting to sort statisticals values to\naddress the problems by priority, this infrastructure provides a \"sorting\"\nof the stat entries too if desired. A tracer has just to provide a\nstat_cmp callback to compare two entries and the stat tracing\ninfrastructure will build a sorted list of the given entries.\n\nA last callback, called stat_headers, can be implemented by a tracer to\noutput headers on its trace.\n\nIf one of these callbacks is changed on runtime, it just have to signal it\nto the stat tracing API by calling the init_tracer_stat() helper.\n\nChanges in V2:\n\n- Fix a memory leak if the user opens multiple times the trace_stat file\n without closing it. Now we always free our list before rebuilding it.\n\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "f0868d1e23a8efec33beb3aa688aab7fdb1ae093", "tree": "73593e14d0d127fe3fe055a85b6e16b50a43578a", "parents": [ "c47956d9ae3341d2d1998bff26620fa3338c01e4" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Tue Dec 23 23:24:12 2008 -0500" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Dec 29 12:46:11 2008 +0100" }, "message": "ftrace: set up trace event hash infrastructure\n\nImpact: simplify/generalize/refactor trace.c\n\nThe trace.c file is becoming more difficult to maintain due to the\ngrowing number of events. There is several formats that an event may\nbe printed. This patch sets up the infrastructure of an event hash to\nallow for events to register how they should be printed.\n\nSigned-off-by: Steven Rostedt \u003csrostedt@redhat.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "c47956d9ae3341d2d1998bff26620fa3338c01e4", "tree": "f6b3569f070ec8fe1a999985b2e8909cd9792785", "parents": [ "0f01f07fad4ee11d98fe6faa442afbeb0328a378" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Tue Dec 23 23:24:11 2008 -0500" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Dec 29 12:46:10 2008 +0100" }, "message": "ftrace: remove obsolete print continue functionality\n\nImpact: cleanup, remove obsolete code\n\nNow that the ring buffer used by ftrace allows for variable length\nentries, we do not need the \u0027cont\u0027 feature of the buffer. This code\nmakes other parts of ftrace more complex and by removing this it\nsimplifies the ftrace code.\n\nSigned-off-by: Steven Rostedt \u003csrostedt@redhat.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "213cc060797378059a28ebc5c539f3e9a80160bd", "tree": "e159f9fae35ca59fe2c02e905c2b4b91881d865c", "parents": [ "30cd324e9787ccc9a5ede59742d5409857550692" ], "author": { "name": "Pekka J Enberg", "email": "penberg@cs.helsinki.fi", "time": "Fri Dec 19 12:08:39 2008 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Fri Dec 19 16:29:34 2008 +0100" }, "message": "ftrace: introduce tracing_reset_online_cpus() helper\n\nImpact: cleanup\n\nThis patch factors out common code from multiple tracers into a\ntracing_reset_online_cpus() function and converts the tracers to use it.\n\nSigned-off-by: Pekka Enberg \u003cpenberg@cs.helsinki.fi\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "66896a85cf2890b6bbbc4c9ccdcd296600ffbf89", "tree": "ad6b0a4df65a59280163f5b8ab0b92b2fe54c283", "parents": [ "2c2d7329d8afa9efa3ec24e19a53e7be9d14f242" ], "author": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Sat Dec 13 20:18:13 2008 +0100" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Wed Dec 17 00:26:36 2008 +0100" }, "message": "tracing/ftrace: add the printk-msg-only option\n\nImpact: display ftrace_printk messages \"as is\"\n\nBy default, ftrace_printk() messages find their output with some other\ninformations like pid, caller, ...\nSometimes a developer just want to have the ftrace_printk left \"as is\", without\nother information.\n\nThis is done by providing a default-off option called printk-msg-only.\nTo enable it, just do `echo printk-msg-only \u003e /debugfs/tracing/trace_options`\n\nBefore the patch:\n\n \u003c...\u003e-2739 [000] 145.692153: __might_sleep: I\u0027m an ftrace_printk msg in __might_sleep\n \u003c...\u003e-2739 [000] 145.692155: __might_sleep: I\u0027m another ftrace_printk msg in __might_sleep\n\nAfter the patch and the printk-msg-only option enabled:\n\nI\u0027m an ftrace_printk msg in __might_sleep\nI\u0027m another ftrace_printk msg in __might_sleep\n\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Steven Rostedt \u003crostedt@goodmis.org\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "a93751cab71d63126687551823ed3e70cd85854a", "tree": "665e9bf274c457edd672ad44320fad962e6c16f5", "parents": [ "c2724775ce57c98b8af9694857b941dc61056516" ], "author": { "name": "Markus Metzger", "email": "markut.t.metzger@intel.com", "time": "Thu Dec 11 13:53:26 2008 +0100" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Fri Dec 12 08:08:14 2008 +0100" }, "message": "x86, bts, ftrace: adapt the hw-branch-tracer to the ds.c interface\n\nImpact: restructure code, cleanup\n\nRemove BTS bits from the hw-branch-tracer (renamed from bts-tracer) and\nuse the ds interface.\n\nSigned-off-by: Markus Metzger \u003cmarkut.t.metzger@intel.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "77d683f3e0258d522c5506e7b5fd05c9411184d9", "tree": "defa7451b5218e7cfdd3a92117fca96368791425", "parents": [ "ff32504fdc56407654584ef187b20022c94a3486" ], "author": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Thu Dec 04 23:49:47 2008 +0100" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Fri Dec 05 14:47:43 2008 +0100" }, "message": "tracing/ftrace: fix the check of ftrace_trace_task\n\nImpact: fix default empty traces on function-graph-tracer\n\nThe actual ftrace_trace_task() checks if ftrace_pid_trace is allocated\nand return 1 if it is true.\nIf it is NULL, it will check the bit of pid tracing flag for the current\ntask (which are not set by default).\nSo by default, a task is not traced.\nActually all tasks should be traced by default and filter_by_pid when\nftrace_pid_trace is allocated.\n\nThe appropriate condition should be to return 1 if filter_by_pid is\nset.\n\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nAcke-dby: Steven Rostedt \u003crostedt@goodmis.org\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "970987beb9c99ca806edc464518d411cc399fb4d", "tree": "51e2298b6eb7e6412009428b380a51e1f17b531b", "parents": [ "faec2ec505d397e9426754722b6e80d519c4938f", "1fd8f2a3f9a91b287a876cef830b21baafc8a799", "feaf3848a813a106f163013af6fcf6c4bfec92d9" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Fri Dec 05 14:45:22 2008 +0100" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Fri Dec 05 14:45:22 2008 +0100" }, "message": "Merge branches \u0027tracing/ftrace\u0027, \u0027tracing/function-graph-tracer\u0027 and \u0027tracing/urgent\u0027 into tracing/core\n" }, { "commit": "1fd8f2a3f9a91b287a876cef830b21baafc8a799", "tree": "2baf0dfb14e3765efa370edafa2ab7f78d654308", "parents": [ "b29144c317fb748dae6d72c0f88eda9d43165b8d" ], "author": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Wed Dec 03 23:45:11 2008 +0100" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Thu Dec 04 10:18:39 2008 +0100" }, "message": "tracing/function-graph-tracer: handle ftrace_printk entries\n\nHandle the TRACE_PRINT entries from the function grapg tracer\nand output them as a C comment just below the function that called\nit, as if it was a comment inside this function.\n\nExample with an ftrace_printk inside might_sleep() function:\n\nvoid __might_sleep(char *file, int line)\n{\n\tstatic unsigned long prev_jiffy;\t/* ratelimiting */\n\n\tftrace_printk(\"Hi I\u0027m a comment in might_sleep() :-)\");\n\nA chunk of a resulting trace:\n\n 0) | _reiserfs_free_block() {\n 0) | reiserfs_read_bitmap_block() {\n 0) | __bread() {\n 0) | __getblk() {\n 0) | __find_get_block() {\n 0) 0.698 us | mark_page_accessed();\n 0) 2.267 us | }\n 0) | __might_sleep() {\n 0) | /* Hi I\u0027m a comment in might_sleep() :-) */\n 0) 1.321 us | }\n 0) 5.872 us | }\n 0) 7.313 us | }\n 0) 8.718 us | }\n\nAnd this patch brings two minor fixes:\n\n- The newline after a switch-out task has disappeared\n- The \"|\" sign just before the cpu number on task-switch has been deleted.\n\n 0) 0.616 us | pick_next_task_rt();\n 0) 1.457 us | _spin_trylock();\n 0) 0.653 us | _spin_unlock();\n 0) 0.728 us | _spin_trylock();\n 0) 0.631 us | _spin_unlock();\n 0) 0.729 us | native_load_sp0();\n 0) 0.593 us | native_load_tls();\n ------------------------------------------\n 0) cat-2834 \u003d\u003e migrati-3\n ------------------------------------------\n\n 0) | finish_task_switch() {\n 0) 0.841 us | _spin_unlock_irq();\n 0) 0.616 us | post_schedule_rt();\n 0) 3.882 us | }\n\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nAcked-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "6b2539302bee8e88c99e3c7d80c16a04dbe5e2ad", "tree": "d4ae4b2af29f2e75546d3a496b6f077c5ef01555", "parents": [ "e32d89569128e76bdf84867be0928902ca9f7555" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Thu Dec 04 09:18:28 2008 +0100" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Thu Dec 04 09:33:01 2008 +0100" }, "message": "tracing: fix typo and missing inline function\n\nImpact: fix build bugs\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "978f3a45d9499c7a447ca7615455cefb63d44165", "tree": "13a59046c8fe7ae3a095444515cd50c0a57727b3", "parents": [ "5ef6476190d24419a9a537baa0b5641845136989" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Thu Dec 04 00:26:40 2008 -0500" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Thu Dec 04 09:09:37 2008 +0100" }, "message": "ftrace: use struct pid\n\nImpact: clean up, extend PID filtering to PID namespaces\n\nEric Biederman suggested using the struct pid for filtering on\npids in the kernel. This patch is based off of a demonstration\nof an implementation that Eric sent me in an email.\n\nSigned-off-by: Steven Rostedt \u003csrostedt@redhat.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "804a685162a7080386714166776f57255a75238e", "tree": "f7b79000146532c0ad6571440652368e2521119a", "parents": [ "0ef8cde56ab92ab3f65221246dc1622c6b5068b3" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Wed Dec 03 15:36:59 2008 -0500" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Thu Dec 04 09:09:36 2008 +0100" }, "message": "ftrace: trace single pid for function graph tracer\n\nImpact: New feature\n\nThis patch makes the changes to set_ftrace_pid apply to the function\ngraph tracer.\n\n # echo $$ \u003e /debugfs/tracing/set_ftrace_pid\n # echo function_graph \u003e /debugfs/tracing/current_tracer\n\nWill cause only the current task to be traced. Note, the trace flags are\nalso inherited by child processes, so the children of the shell\nwill also be traced.\n\nSigned-off-by: Steven Rostedt \u003csrostedt@redhat.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "ea4e2bc4d9f7370e57a343ccb5e7c0ad3222ec3c", "tree": "64a4a1d9d7d3de0695cb2e8c7161886ab660e311", "parents": [ "b29144c317fb748dae6d72c0f88eda9d43165b8d" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Wed Dec 03 15:36:57 2008 -0500" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Thu Dec 04 09:09:34 2008 +0100" }, "message": "ftrace: graph of a single function\n\nThis patch adds the file:\n\n /debugfs/tracing/set_graph_function\n\nwhich can be used along with the function graph tracer.\n\nWhen this file is empty, the function graph tracer will act as\nusual. When the file has a function in it, the function graph\ntracer will only trace that function.\n\nFor example:\n\n # echo blk_unplug \u003e /debugfs/tracing/set_graph_function\n # cat /debugfs/tracing/trace\n [...]\n ------------------------------------------\n | 2) make-19003 \u003d\u003e kjournald-2219\n ------------------------------------------\n\n 2) | blk_unplug() {\n 2) | dm_unplug_all() {\n 2) | dm_get_table() {\n 2) 1.381 us | _read_lock();\n 2) 0.911 us | dm_table_get();\n 2) 1. 76 us | _read_unlock();\n 2) + 12.912 us | }\n 2) | dm_table_unplug_all() {\n 2) | blk_unplug() {\n 2) 0.778 us | generic_unplug_device();\n 2) 2.409 us | }\n 2) 5.992 us | }\n 2) 0.813 us | dm_table_put();\n 2) + 29. 90 us | }\n 2) + 34.532 us | }\n\nYou can add up to 32 functions into this file. Currently we limit it\nto 32, but this may change with later improvements.\n\nTo add another function, use the append \u0027\u003e\u003e\u0027:\n\n # echo sys_read \u003e\u003e /debugfs/tracing/set_graph_function\n # cat /debugfs/tracing/set_graph_function\n blk_unplug\n sys_read\n\nUsing the \u0027\u003e\u0027 will clear out the function and write anew:\n\n # echo sys_write \u003e /debug/tracing/set_graph_function\n # cat /debug/tracing/set_graph_function\n sys_write\n\nNote, if you have function graph running while doing this, the small\ntime between clearing it and updating it will cause the graph to\nrecord all functions. This should not be an issue because after\nit sets the filter, only those functions will be recorded from then on.\nIf you need to only record a particular function then set this\nfile first before starting the function graph tracer. In the future\nthis side effect may be corrected.\n\nThe set_graph_function file is similar to the set_ftrace_filter but\nit does not take wild cards nor does it allow for more than one\nfunction to be set with a single write. There is no technical reason why\nthis is the case, I just do not have the time yet to implement that.\n\nNote, dynamic ftrace must be enabled for this to appear because it\nuses the dynamic ftrace records to match the name to the mcount\ncall sites.\n\nSigned-off-by: Steven Rostedt \u003csrostedt@redhat.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "e49dc19c6a19ea112fcb94b7c62ec62cdd5c08aa", "tree": "851dcdfe321e16a327d656ecd7040ef6e8590bec", "parents": [ "7ee991fbc6f947e9b04f29c9c6c1d057d0671a16" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Tue Dec 02 23:50:05 2008 -0500" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Wed Dec 03 08:56:26 2008 +0100" }, "message": "ftrace: function graph return for function entry\n\nImpact: feature, let entry function decide to trace or not\n\nThis patch lets the graph tracer entry function decide if the tracing\nshould be done at the end as well. This requires all function graph\nentry functions return 1 if it should trace, or 0 if the return should\nnot be traced.\n\nSigned-off-by: Steven Rostedt \u003csrostedt@redhat.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "c7cc77307669336a08928ab8668bdb3f3bcc021b", "tree": "c9f2997a7266cc5d8c5b61e964d8e014f274f5d3", "parents": [ "0bfc24559d7945506184d86739fe365a181f06b7", "d144d5ee6a265823d39f75ecfed351a516295183", "437f24fb897d409a9978eb71ecfaf279dcd94acd", "f3f47a6768a29448866da4422b6f6bee485c947f" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Thu Nov 27 10:56:13 2008 +0100" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Thu Nov 27 10:56:13 2008 +0100" }, "message": "Merge branches \u0027tracing/blktrace\u0027, \u0027tracing/ftrace\u0027, \u0027tracing/function-graph-tracer\u0027 and \u0027tracing/power-tracer\u0027 into tracing/core\n" }, { "commit": "f3f47a6768a29448866da4422b6f6bee485c947f", "tree": "ba4bf1b79cbd13412871eec50250294d7140fd09", "parents": [ "509dceef6470442d8c7b8a43ec34125205840b3c" ], "author": { "name": "Arjan van de Ven", "email": "arjan@infradead.org", "time": "Sun Nov 23 16:49:58 2008 -0800" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Wed Nov 26 08:29:32 2008 +0100" }, "message": "tracing: add \"power-tracer\": C/P state tracer to help power optimization\n\nImpact: new \"power-tracer\" ftrace plugin\n\nThis patch adds a C/P-state ftrace plugin that will generate\ndetailed statistics about the C/P-states that are being used,\nso that we can look at detailed decisions that the C/P-state\ncode is making, rather than the too high level \"average\"\nthat we have today.\n\nAn example way of using this is:\n\n mount -t debugfs none /sys/kernel/debug\n echo cstate \u003e /sys/kernel/debug/tracing/current_tracer\n echo 1 \u003e /sys/kernel/debug/tracing/tracing_enabled\n sleep 1\n echo 0 \u003e /sys/kernel/debug/tracing/tracing_enabled\n cat /sys/kernel/debug/tracing/trace | perl scripts/trace/cstate.pl \u003e out.svg\n\nSigned-off-by: Arjan van de Ven \u003carjan@linux.intel.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "660c7f9be96321fc80026d76411bd15e6f418a72", "tree": "5ae61fa51c9e9ce7b42f64cfaa168cd09439ac3d", "parents": [ "e53a6319cca69111c1643dc9f18f4465d7f1cbf0" ], "author": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Wed Nov 26 00:16:26 2008 -0500" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Wed Nov 26 06:52:56 2008 +0100" }, "message": "ftrace: add thread comm to function graph tracer\n\nImpact: enhancement to function graph tracer\n\nExport the trace_find_cmdline so the function graph tracer can\nuse it to print the comms of the threads.\n\nSigned-off-by: Steven Rostedt \u003csrostedt@redhat.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "287b6e68ca7209caec40b2f44f837c580a413bae", "tree": "b0867d75868f6049dc5747bd39fdae2d477dde66", "parents": [ "fb52607afcd0629776f1dc9e657647ceae81dd50" ], "author": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Wed Nov 26 00:57:25 2008 +0100" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Wed Nov 26 01:59:45 2008 +0100" }, "message": "tracing/function-return-tracer: set a more human readable output\n\nImpact: feature\n\nThis patch sets a C-like output for the function graph tracing.\nFor this aim, we now call two handler for each function: one on the entry\nand one other on return. This way we can draw a well-ordered call stack.\n\nThe pid of the previous trace is loosely stored to be compared against\nthe one of the current trace to see if there were a context switch.\n\nWithout this little feature, the call tree would seem broken at\nsome locations.\nWe could use the sched_tracer to capture these sched_events but this\nway of processing is much more simpler.\n\n2 spaces have been chosen for indentation to fit the screen while deep\ncalls. The time of execution in nanosecs is printed just after closed\nbraces, it seems more easy this way to find the corresponding function.\nIf the time was printed as a first column, it would be not so easy to\nfind the corresponding function if it is called on a deep depth.\n\nI plan to output the return value but on 32 bits CPU, the return value\ncan be 32 or 64, and its difficult to guess on which case we are.\nI don\u0027t know what would be the better solution on X86-32: only print\neax (low-part) or even edx (high-part).\n\nActually it\u0027s thee same problem when a function return a 8 bits value, the\nhigh part of eax could contain junk values...\n\nHere is an example of trace:\n\nsys_read() {\n fget_light() {\n } 526\n vfs_read() {\n rw_verify_area() {\n security_file_permission() {\n cap_file_permission() {\n } 519\n } 1564\n } 2640\n do_sync_read() {\n pipe_read() {\n __might_sleep() {\n } 511\n pipe_wait() {\n prepare_to_wait() {\n } 760\n deactivate_task() {\n dequeue_task() {\n dequeue_task_fair() {\n dequeue_entity() {\n update_curr() {\n update_min_vruntime() {\n } 504\n } 1587\n clear_buddies() {\n } 512\n add_cfs_task_weight() {\n } 519\n update_min_vruntime() {\n } 511\n } 5602\n dequeue_entity() {\n update_curr() {\n update_min_vruntime() {\n } 496\n } 1631\n clear_buddies() {\n } 496\n update_min_vruntime() {\n } 527\n } 4580\n hrtick_update() {\n hrtick_start_fair() {\n } 488\n } 1489\n } 13700\n } 14949\n } 16016\n msecs_to_jiffies() {\n } 496\n put_prev_task_fair() {\n } 504\n pick_next_task_fair() {\n } 489\n pick_next_task_rt() {\n } 496\n pick_next_task_fair() {\n } 489\n pick_next_task_idle() {\n } 489\n\n------------8\u003c---------- thread 4 ------------8\u003c----------\n\nfinish_task_switch() {\n} 1203\ndo_softirq() {\n __do_softirq() {\n __local_bh_disable() {\n } 669\n rcu_process_callbacks() {\n __rcu_process_callbacks() {\n cpu_quiet() {\n rcu_start_batch() {\n } 503\n } 1647\n } 3128\n __rcu_process_callbacks() {\n } 542\n } 5362\n _local_bh_enable() {\n } 587\n } 8880\n} 9986\nkthread_should_stop() {\n} 669\ndeactivate_task() {\n dequeue_task() {\n dequeue_task_fair() {\n dequeue_entity() {\n update_curr() {\n calc_delta_mine() {\n } 511\n update_min_vruntime() {\n } 511\n } 2813\n\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nAcked-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "fb52607afcd0629776f1dc9e657647ceae81dd50", "tree": "7bf43b41ff8510d3098c089913cce56a9049f0fd", "parents": [ "509dceef6470442d8c7b8a43ec34125205840b3c" ], "author": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Tue Nov 25 21:07:04 2008 +0100" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Wed Nov 26 01:59:45 2008 +0100" }, "message": "tracing/function-return-tracer: change the name into function-graph-tracer\n\nImpact: cleanup\n\nThis patch changes the name of the \"return function tracer\" into\nfunction-graph-tracer which is a more suitable name for a tracing\nwhich makes one able to retrieve the ordered call stack during\nthe code flow.\n\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nAcked-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "1e9b51c28312f7334394aa30be56ff52c2b65b7e", "tree": "c0a231d83541263ee938e3452475409323e4e9a9", "parents": [ "8bba1bf5e2434c83f2fe8b1422604ace9bbe4cb8" ], "author": { "name": "Markus Metzger", "email": "markus.t.metzger@intel.com", "time": "Tue Nov 25 09:24:15 2008 +0100" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Tue Nov 25 17:31:13 2008 +0100" }, "message": "x86, bts, ftrace: a BTS ftrace plug-in prototype\n\nImpact: add new ftrace plugin\n\nA prototype for a BTS ftrace plug-in.\n\nThe tracer collects branch trace in a cyclic buffer for each cpu.\n\nThe tracer is not configurable and the trace for each snapshot is\nappended when doing cat /debug/tracing/trace.\n\nThis is a proof of concept that will be extended with future patches\nto become a (hopefully) useful tool.\n\nSigned-off-by: Markus Metzger \u003cmarkus.t.metzger@intel.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "8bba1bf5e2434c83f2fe8b1422604ace9bbe4cb8", "tree": "3df07de04de7e3a838dbf544e6a98eadac37b027", "parents": [ "6abb11aecd888d1da6276399380b7355f127c006" ], "author": { "name": "Markus Metzger", "email": "markus.t.metzger@intel.com", "time": "Tue Nov 25 09:12:31 2008 +0100" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Tue Nov 25 17:31:13 2008 +0100" }, "message": "x86, ftrace: call trace-\u003eopen() before stopping tracing; add trace-\u003eprint_header()\n\nAdd a callback to allow an ftrace plug-in to write its own header.\n\nMove the call to trace-\u003eopen() up a few lines.\n\nThe changes are required by the BTS ftrace plug-in.\n\nSigned-off-by: Markus Metzger \u003cmarkus.t.metzger@intel.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "b54d3de9f3b8956653b06f1a32e9f9321c6d9027", "tree": "fef98e07a9327371304811191cafebdd65311502", "parents": [ "74e2f334f4440cbcb63e9ebbcdcea430d41bdfa3" ], "author": { "name": "Török Edwin", "email": "edwintorok@gmail.com", "time": "Sat Nov 22 13:28:48 2008 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Sun Nov 23 09:45:42 2008 +0100" }, "message": "tracing: identify which executable object the userspace address belongs to\n\nImpact: modify+improve the userstacktrace tracing visualization feature\n\nStore thread group leader id, and use it to lookup the address in the\nprocess\u0027s map. We could have looked up the address on thread\u0027s map,\nbut the thread might not exist by the time we are called. The process\nmight not exist either, but if you are reading trace_pipe, that is\nunlikely.\n\nExample usage:\n\n mount -t debugfs nodev /sys/kernel/debug\n cd /sys/kernel/debug/tracing\n echo userstacktrace \u003eiter_ctrl\n echo sym-userobj \u003eiter_ctrl\n echo sched_switch \u003ecurrent_tracer\n echo 1 \u003etracing_enabled\n cat trace_pipe \u003e/tmp/trace\u0026\n .... run application ...\n echo 0 \u003etracing_enabled\n cat /tmp/trace\n\nYou\u0027ll see stack entries like:\n\n /lib/libpthread-2.7.so[+0xd370]\n\nYou can convert them to function/line using:\n\n addr2line -fie /lib/libpthread-2.7.so 0xd370\n\nOr:\n\n addr2line -fie /usr/lib/debug/libpthread-2.7.so 0xd370\n\nFor non-PIC/PIE executables this won\u0027t work:\n\n a.out[+0x73b]\n\nYou need to run the following: addr2line -fie a.out 0x40073b\n(where 0x400000 is the default load address of a.out)\n\nSigned-off-by: Török Edwin \u003cedwintorok@gmail.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "02b67518e2b1c490787dac7f35e1204e74fe21ba", "tree": "a3d92846e1a09a829f300ab15726ee9c288cb49e", "parents": [ "a0a70c735ef714fe1b6777b571630c3d50c7b008" ], "author": { "name": "Török Edwin", "email": "edwintorok@gmail.com", "time": "Sat Nov 22 13:28:47 2008 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Sun Nov 23 09:25:15 2008 +0100" }, "message": "tracing: add support for userspace stacktraces in tracing/iter_ctrl\n\nImpact: add new (default-off) tracing visualization feature\n\nUsage example:\n\n mount -t debugfs nodev /sys/kernel/debug\n cd /sys/kernel/debug/tracing\n echo userstacktrace \u003eiter_ctrl\n echo sched_switch \u003ecurrent_tracer\n echo 1 \u003etracing_enabled\n .... run application ...\n echo 0 \u003etracing_enabled\n\nThen read one of \u0027trace\u0027,\u0027latency_trace\u0027,\u0027trace_pipe\u0027.\n\nTo get the best output you can compile your userspace programs with\nframe pointers (at least glibc + the app you are tracing).\n\nSigned-off-by: Török Edwin \u003cedwintorok@gmail.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "0231022cc32d5f2e7f3c06b75691dda0ad6aec33", "tree": "b45429e95fc7d52bae32e62ef514f3d7ccf62ce6", "parents": [ "0619faf657806b943e6acf51f60f1cd023a96c78" ], "author": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Mon Nov 17 03:22:41 2008 +0100" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Tue Nov 18 11:11:00 2008 +0100" }, "message": "tracing/function-return-tracer: add the overrun field\n\nImpact: help to find the better depth of trace\n\nWe decided to arbitrary define the depth of function return trace as\n\"20\". Perhaps this is not enough. To help finding an optimal depth, we\nmeasure now the overrun: the number of functions that have been missed\nfor the current thread. By default this is not displayed, we have to\ndo set a particular flag on the return tracer: echo overrun \u003e\n/debug/tracing/trace_options And the overrun will be printed on the\nright.\n\nAs the trace shows below, the current 20 depth is not enough.\n\nupdate_wall_time+0x37f/0x8c0 -\u003e update_xtime_cache (345 ns) (Overruns: 2838)\nupdate_wall_time+0x384/0x8c0 -\u003e clocksource_get_next (1141 ns) (Overruns: 2838)\ndo_timer+0x23/0x100 -\u003e update_wall_time (3882 ns) (Overruns: 2838)\ntick_do_update_jiffies64+0xbf/0x160 -\u003e do_timer (5339 ns) (Overruns: 2838)\ntick_sched_timer+0x6a/0xf0 -\u003e tick_do_update_jiffies64 (7209 ns) (Overruns: 2838)\nvgacon_set_cursor_size+0x98/0x120 -\u003e native_io_delay (2613 ns) (Overruns: 274)\nvgacon_cursor+0x16e/0x1d0 -\u003e vgacon_set_cursor_size (33151 ns) (Overruns: 274)\nset_cursor+0x5f/0x80 -\u003e vgacon_cursor (36432 ns) (Overruns: 274)\ncon_flush_chars+0x34/0x40 -\u003e set_cursor (38790 ns) (Overruns: 274)\nrelease_console_sem+0x1ec/0x230 -\u003e up (721 ns) (Overruns: 274)\nrelease_console_sem+0x225/0x230 -\u003e wake_up_klogd (316 ns) (Overruns: 274)\ncon_flush_chars+0x39/0x40 -\u003e release_console_sem (2996 ns) (Overruns: 274)\ncon_write+0x22/0x30 -\u003e con_flush_chars (46067 ns) (Overruns: 274)\nn_tty_write+0x1cc/0x360 -\u003e con_write (292670 ns) (Overruns: 274)\nsmp_apic_timer_interrupt+0x2a/0x90 -\u003e native_apic_mem_write (330 ns) (Overruns: 274)\nirq_enter+0x17/0x70 -\u003e idle_cpu (413 ns) (Overruns: 274)\nsmp_apic_timer_interrupt+0x2f/0x90 -\u003e irq_enter (1525 ns) (Overruns: 274)\nktime_get_ts+0x40/0x70 -\u003e getnstimeofday (465 ns) (Overruns: 274)\nktime_get_ts+0x60/0x70 -\u003e set_normalized_timespec (436 ns) (Overruns: 274)\nktime_get+0x16/0x30 -\u003e ktime_get_ts (2501 ns) (Overruns: 274)\nhrtimer_interrupt+0x77/0x1a0 -\u003e ktime_get (3439 ns) (Overruns: 274)\n\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nAcked-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "adf9f19574334c9a29a2bc956009fcac7edf1a6b", "tree": "644415fb8e460290a6747c5933a1c62be9a9d50f", "parents": [ "5a209c2d58e70f9bc415b9cdf0e3b9aaefb70371" ], "author": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Mon Nov 17 19:23:42 2008 +0100" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Tue Nov 18 11:10:58 2008 +0100" }, "message": "tracing/ftrace: implement a set_flag callback for tracers\n\nImpact: give a way to send specific messages to tracers\n\nThe current implementation of tracing uses some flags to control the\noutput of general tracers. But we have no way to implement custom\nflags handling for a specific tracer. This patch proposes a new\ncallback for the struct tracer which called set_flag and a structure\nthat represents a 32 bits variable flag.\n\nA tracer can implement a struct tracer_flags on which it puts the\ninitial value of the flag integer. Than it can place a range of flags\nwith their name and their flag mask on the flag integer. The structure\nthat implement a single flag is called struct tracer_opt.\n\nThese custom flags will be available through the trace_options file\nlike the general tracing flags. Changing their value is done like the\nother general flags. For example if you have a flag that calls \"foo\",\nyou can activate it by writing \"foo\" or \"nofoo\" on trace_options.\n\nNote that the set_flag callback is optional and is only needed if you\nwant the flags changing to be signaled to your tracer and let it to\naccept or refuse their assignment.\n\nV2: Some arrangements in coding style....\n\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nAcked-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "5a209c2d58e70f9bc415b9cdf0e3b9aaefb70371", "tree": "02e63e90cc26792eaea21dced12bd7c10f996d30", "parents": [ "3f8e402f34ecc7d1d00b54703d3baa401b8bdd78", "0c726da983de0704254250ef6495ca152e7abcca", "e270219f4372b58bd3eeac12bd9f7edc592b8f6b" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Tue Nov 18 08:52:13 2008 +0100" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Tue Nov 18 08:52:13 2008 +0100" }, "message": "Merge branches \u0027tracing/branch-tracer\u0027 and \u0027tracing/urgent\u0027 into tracing/core\n" }, { "commit": "0c726da983de0704254250ef6495ca152e7abcca", "tree": "fe57e18784cef716c65a1f4daa39da20acd15b4f", "parents": [ "072b40a15616fe6bea68466e6bffcfcbf5c8f26f" ], "author": { "name": "Aneesh Kumar K.V", "email": "aneesh.kumar@linux.vnet.ibm.com", "time": "Sun Nov 16 16:07:58 2008 +0530" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Nov 17 12:07:27 2008 +0100" }, "message": "tracing: branch tracer, fix writing to trace/trace_options\n\nImpact: fix trace_options behavior\n\nwriting to trace/trace_options use the index of the array\nto find the value of the flag. With branch tracer flag\ndefined conditionally, this breaks writing to trace_options\nwith branch tracer disabled.\n\nSigned-off-by: Aneesh Kumar K.V \u003caneesh.kumar@linux.vnet.ibm.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "1c80025a49855b12fa09bb6db71820e3367b1369", "tree": "063fe72ed9bb3410c3293c83a7882cecc46e7410", "parents": [ "e6e7a65aabdb696cf05a56cfd495c49a11fd4cde" ], "author": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Sun Nov 16 05:57:26 2008 +0100" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Sun Nov 16 07:55:23 2008 +0100" }, "message": "tracing/ftrace: change the type of the init() callback\n\nImpact: extend the -\u003einit() method with the ability to fail\n\nThis bring a way to know if the initialization of a tracer successed.\nA tracer must return 0 on success and a traditional error (ie:\n-ENOMEM) if it fails.\n\nIf a tracer fails to init, it is free to print a detailed warn. The\ntracing api will not and switch to a new tracer will just return the\nerror from the init callback.\n\nNote: this will be used for the return tracer.\n\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "12ef7d448613ead2babd41c3ebfa1fe03c20edef", "tree": "252b12211d2bbf96e4a90625f0c6116c9a4bd7de", "parents": [ "ee6bce52276c0717ed3e63296e5d9465d339e923" ], "author": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Wed Nov 12 17:52:38 2008 -0500" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Thu Nov 13 09:49:24 2008 +0100" }, "message": "ftrace: CPU buffer start annotation clean ups\n\nImpact: better handling of CPU buffer start annotation\n\nBecause of the confusion with the per CPU buffers wrapping where\none CPU might be more active at the end of the trace than the other\nCPUs causing that one CPU to have a shorter history. Kernel\ndevelopers were confused by the \"missing\" data of that one CPU\nat the beginning of the trace output. An annotation was added to\nthe trace output to show that the buffer had started:\n\n # tracer: function\n #\n # TASK-PID CPU# TIMESTAMP FUNCTION\n # | | | | |\n ##### CPU 3 buffer started ####\n \u003cidle\u003e-0 [003] 158.192959: smp_apic_timer_interrupt\n [...]\n \u003cidle\u003e-0 [003] 161.556520: default_idle\n ##### CPU 1 buffer started ####\n \u003cidle\u003e-0 [001] 161.592494: hrtimer_force_reprogram\n [etc]\n\nBut this annotation gets a bit messy when tracers do not fill the\nbuffers. This patch does a couple of things:\n\n One) it adds a flag to trace_options to disable these annotations\n\n Two) it does not annotate if the tracer did not overflow its buffer.\n\nThis makes the output much cleaner.\n\nSigned-off-by: Steven Rostedt \u003csrostedt@redhat.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "80e5ea4506791af206266c5921c97f11d3b17866", "tree": "847eb231f1c98377bdd600a801657a338cd1baa1", "parents": [ "9f029e83e968e5661d7be045bbcb620dbb909938" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Wed Nov 12 15:24:24 2008 -0500" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Wed Nov 12 22:28:25 2008 +0100" }, "message": "ftrace: add tracer called branch\n\nImpact: added new branch tracer\n\nCurrently the tracing of branch profiling (unlikelys and likelys hit)\nis only activated by the iter_ctrl. This patch adds a tracer called\n\"branch\" that will just trace the branch profiling. The advantage\nof adding this tracer is that it can be added to the ftrace selftests\non startup.\n\nSigned-off-by: Steven Rostedt \u003csrostedt@redhat.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "9f029e83e968e5661d7be045bbcb620dbb909938", "tree": "13beecf2626162dc8a3912c79d58fc91e2193de5", "parents": [ "2ed84eeb8808cf3c9f039213ca137ffd7d753f0e" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Wed Nov 12 15:24:24 2008 -0500" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Wed Nov 12 22:28:09 2008 +0100" }, "message": "ftrace: rename unlikely iter_ctrl to branch\n\nImpact: rename of iter_ctrl unlikely to branch\n\nThe unlikely name is ugly. This patch converts the iter_ctrl command\n\"unlikely\" and \"nounlikely\" to \"branch\" and \"nobranch\" respectively.\n\nIt also renames a lot of internal functions to use \"branch\" instead\nof \"unlikely\".\n\nSigned-off-by: Steven Rostedt \u003csrostedt@redhat.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "2ed84eeb8808cf3c9f039213ca137ffd7d753f0e", "tree": "3aa22269a1fd5ed0b66826120ca9b572400962b5", "parents": [ "68d119f0a66f7e3663304343b072e56a2693446b" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Wed Nov 12 15:24:24 2008 -0500" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Wed Nov 12 22:27:58 2008 +0100" }, "message": "trace: rename unlikely profiler to branch profiler\n\nImpact: name change of unlikely tracer and profiler\n\nIngo Molnar suggested changing the config from UNLIKELY_PROFILE\nto BRANCH_PROFILING. I never did like the \"unlikely\" name so I\nwent one step farther, and renamed all the unlikely configurations\nto a \"BRANCH\" variant.\n\nSigned-off-by: Steven Rostedt \u003csrostedt@redhat.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "52f232cb720a7babb752849cbc2cab2d24021209", "tree": "47c7e800549457bd5ab9b54f47729acac6e10780", "parents": [ "1f0d69a9fc815db82f15722bf05227190b1d714d" ], "author": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Wed Nov 12 00:14:40 2008 -0500" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Wed Nov 12 11:52:02 2008 +0100" }, "message": "tracing: likely/unlikely branch annotation tracer\n\nImpact: new likely/unlikely branch tracer\n\nThis patch adds a way to record the instances of the likely() and unlikely()\nbranch condition annotations.\n\nWhen \"unlikely\" is set in /debugfs/tracing/iter_ctrl the unlikely conditions\nwill be added to any of the ftrace tracers. The change takes effect when\na new tracer is passed into the current_tracer file.\n\nFor example:\n\n bash-3471 [003] 357.014755: [INCORRECT] sched_info_dequeued:sched_stats.h:177\n bash-3471 [003] 357.014756: [correct] update_curr:sched_fair.c:489\n bash-3471 [003] 357.014758: [correct] calc_delta_fair:sched_fair.c:411\n bash-3471 [003] 357.014759: [correct] account_group_exec_runtime:sched_stats.h:356\n bash-3471 [003] 357.014761: [correct] update_curr:sched_fair.c:489\n bash-3471 [003] 357.014763: [INCORRECT] calc_delta_fair:sched_fair.c:411\n bash-3471 [003] 357.014765: [correct] calc_delta_mine:sched.c:1279\n\nWhich shows the normal tracer heading, as well as whether the condition was\ncorrect \"[correct]\" or was mistaken \"[INCORRECT]\", followed by the function,\nfile name and line number.\n\nSigned-off-by: Steven Rostedt \u003csrostedt@redhat.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "74239072830ef3f1398edeb1bc1076fc330fd4a2", "tree": "60a244c6c88d9943760ded98a1a29ce018292107", "parents": [ "3f5ec13696fd4a33bde42f385406cbb1d3cc96fd" ], "author": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Tue Nov 11 23:24:42 2008 +0100" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Wed Nov 12 10:17:19 2008 +0100" }, "message": "tracing/fastboot: Use the ring-buffer timestamp for initcall entries\n\nImpact: Split the boot tracer entries in two parts: call and return\n\nNow that we are using the sched tracer from the boot tracer, we want\nto use the same timestamp than the ring-buffer to have consistent time\ncaptures between sched events and initcall events.\n\nSo we get rid of the old time capture by the boot tracer and split the\ninitcall events in two parts: call and return. This way we have the\nring buffer timestamp of both.\n\nAn example trace:\n\n[ 27.904149584] calling net_ns_init+0x0/0x1c0 @ 1\n[ 27.904429624] initcall net_ns_init+0x0/0x1c0 returned 0 after 0 msecs\n[ 27.904575926] calling reboot_init+0x0/0x20 @ 1\n[ 27.904655399] initcall reboot_init+0x0/0x20 returned 0 after 0 msecs\n[ 27.904800228] calling sysctl_init+0x0/0x30 @ 1\n[ 27.905142914] initcall sysctl_init+0x0/0x30 returned 0 after 0 msecs\n[ 27.905287211] calling ksysfs_init+0x0/0xb0 @ 1\n ##### CPU 0 buffer started ####\n init-1 [000] 27.905395: 1:120:R + [001] 11:115:S\n ##### CPU 1 buffer started ####\n \u003cidle\u003e-0 [001] 27.905425: 0:140:R \u003d\u003d\u003e [001] 11:115:R\n init-1 [000] 27.905426: 1:120:D \u003d\u003d\u003e [000] 0:140:R\n \u003cidle\u003e-0 [000] 27.905431: 0:140:R + [000] 4:115:S\n \u003cidle\u003e-0 [000] 27.905451: 0:140:R \u003d\u003d\u003e [000] 4:115:R\n ksoftirqd/0-4 [000] 27.905456: 4:115:S \u003d\u003d\u003e [000] 0:140:R\n udevd-11 [001] 27.905458: 11:115:R + [001] 14:115:R\n \u003cidle\u003e-0 [000] 27.905459: 0:140:R + [000] 4:115:S\n \u003cidle\u003e-0 [000] 27.905462: 0:140:R \u003d\u003d\u003e [000] 4:115:R\n udevd-11 [001] 27.905462: 11:115:R \u003d\u003d\u003e [001] 14:115:R\n ksoftirqd/0-4 [000] 27.905467: 4:115:S \u003d\u003d\u003e [000] 0:140:R\n \u003cidle\u003e-0 [000] 27.905470: 0:140:R + [000] 4:115:S\n \u003cidle\u003e-0 [000] 27.905473: 0:140:R \u003d\u003d\u003e [000] 4:115:R\n ksoftirqd/0-4 [000] 27.905476: 4:115:S \u003d\u003d\u003e [000] 0:140:R\n \u003cidle\u003e-0 [000] 27.905479: 0:140:R + [000] 4:115:S\n \u003cidle\u003e-0 [000] 27.905482: 0:140:R \u003d\u003d\u003e [000] 4:115:R\n ksoftirqd/0-4 [000] 27.905486: 4:115:S \u003d\u003d\u003e [000] 0:140:R\n udevd-14 [001] 27.905499: 14:120:X \u003d\u003d\u003e [001] 11:115:R\n udevd-11 [001] 27.905506: 11:115:R + [000] 1:120:D\n \u003cidle\u003e-0 [000] 27.905515: 0:140:R \u003d\u003d\u003e [000] 1:120:R\n udevd-11 [001] 27.905517: 11:115:S \u003d\u003d\u003e [001] 0:140:R\n[ 27.905557107] initcall ksysfs_init+0x0/0xb0 returned 0 after 3906 msecs\n[ 27.905705736] calling init_jiffies_clocksource+0x0/0x10 @ 1\n[ 27.905779239] initcall init_jiffies_clocksource+0x0/0x10 returned 0 after 0 msecs\n[ 27.906769814] calling pm_init+0x0/0x30 @ 1\n[ 27.906853627] initcall pm_init+0x0/0x30 returned 0 after 0 msecs\n[ 27.906997803] calling pm_disk_init+0x0/0x20 @ 1\n[ 27.907076946] initcall pm_disk_init+0x0/0x20 returned 0 after 0 msecs\n[ 27.907222556] calling swsusp_header_init+0x0/0x30 @ 1\n[ 27.907294325] initcall swsusp_header_init+0x0/0x30 returned 0 after 0 msecs\n[ 27.907439620] calling stop_machine_init+0x0/0x50 @ 1\n init-1 [000] 27.907485: 1:120:R + [000] 2:115:S\n init-1 [000] 27.907490: 1:120:D \u003d\u003d\u003e [000] 2:115:R\n kthreadd-2 [000] 27.907507: 2:115:R + [001] 15:115:R\n \u003cidle\u003e-0 [001] 27.907517: 0:140:R \u003d\u003d\u003e [001] 15:115:R\n kthreadd-2 [000] 27.907517: 2:115:D \u003d\u003d\u003e [000] 0:140:R\n \u003cidle\u003e-0 [000] 27.907521: 0:140:R + [000] 4:115:S\n \u003cidle\u003e-0 [000] 27.907524: 0:140:R \u003d\u003d\u003e [000] 4:115:R\n udevd-15 [001] 27.907527: 15:115:D + [000] 2:115:D\n ksoftirqd/0-4 [000] 27.907537: 4:115:S \u003d\u003d\u003e [000] 2:115:R\n udevd-15 [001] 27.907537: 15:115:D \u003d\u003d\u003e [001] 0:140:R\n kthreadd-2 [000] 27.907546: 2:115:R + [000] 1:120:D\n kthreadd-2 [000] 27.907550: 2:115:S \u003d\u003d\u003e [000] 1:120:R\n init-1 [000] 27.907584: 1:120:R + [000] 15: 0:D\n init-1 [000] 27.907589: 1:120:R + [000] 2:115:S\n init-1 [000] 27.907593: 1:120:D \u003d\u003d\u003e [000] 15: 0:R\n udevd-15 [000] 27.907601: 15: 0:S \u003d\u003d\u003e [000] 2:115:R\n ##### CPU 0 buffer started ####\n kthreadd-2 [000] 27.907616: 2:115:R + [001] 16:115:R\n ##### CPU 1 buffer started ####\n \u003cidle\u003e-0 [001] 27.907620: 0:140:R \u003d\u003d\u003e [001] 16:115:R\n kthreadd-2 [000] 27.907621: 2:115:D \u003d\u003d\u003e [000] 0:140:R\n udevd-16 [001] 27.907625: 16:115:D + [000] 2:115:D\n \u003cidle\u003e-0 [000] 27.907628: 0:140:R + [000] 4:115:S\n udevd-16 [001] 27.907629: 16:115:D \u003d\u003d\u003e [001] 0:140:R\n \u003cidle\u003e-0 [000] 27.907631: 0:140:R \u003d\u003d\u003e [000] 4:115:R\n ksoftirqd/0-4 [000] 27.907636: 4:115:S \u003d\u003d\u003e [000] 2:115:R\n kthreadd-2 [000] 27.907644: 2:115:R + [000] 1:120:D\n kthreadd-2 [000] 27.907647: 2:115:S \u003d\u003d\u003e [000] 1:120:R\n init-1 [000] 27.907657: 1:120:R + [001] 16: 0:D\n \u003cidle\u003e-0 [001] 27.907666: 0:140:R \u003d\u003d\u003e [001] 16: 0:R\n[ 27.907703862] initcall stop_machine_init+0x0/0x50 returned 0 after 0 msecs\n[ 27.907850704] calling filelock_init+0x0/0x30 @ 1\n[ 27.907926573] initcall filelock_init+0x0/0x30 returned 0 after 0 msecs\n[ 27.908071327] calling init_script_binfmt+0x0/0x10 @ 1\n[ 27.908165195] initcall init_script_binfmt+0x0/0x10 returned 0 after 0 msecs\n[ 27.908309461] calling init_elf_binfmt+0x0/0x10 @ 1\n\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nAcked-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "3f5ec13696fd4a33bde42f385406cbb1d3cc96fd", "tree": "3c705c5991fcf0f4968ff790bb2e2ce65c8cbf18", "parents": [ "60a011c736e7dd09a0b01ca6a051a416f3f52ffb" ], "author": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Tue Nov 11 23:21:31 2008 +0100" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Wed Nov 12 10:17:18 2008 +0100" }, "message": "tracing/fastboot: move boot tracer structs and funcs into their own header.\n\nImpact: Cleanups on the boot tracer and ftrace\n\nThis patch bring some cleanups about the boot tracer headers. The\nfunctions and structures of this tracer have nothing related to ftrace\nand should have so their own header file.\n\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nAcked-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "15e6cb3673ea6277999642802406a764b49391b0", "tree": "d0a46a918caa64d5fb1ed37be3e026b30e94fe77", "parents": [ "caf4b323b02a16c92fba449952ac6515ddc76d7a" ], "author": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Tue Nov 11 07:14:25 2008 +0100" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Tue Nov 11 10:29:12 2008 +0100" }, "message": "tracing: add a tracer to catch execution time of kernel functions\n\nImpact: add new tracing plugin which can trace full (entry+exit) function calls\n\nThis tracer uses the low level function return ftrace plugin to\nmeasure the execution time of the kernel functions.\n\nThe first field is the caller of the function, the second is the\nmeasured function, and the last one is the execution time in\nnanoseconds.\n\n- v3:\n\n- HAVE_FUNCTION_RET_TRACER have been added. Each arch that support ftrace return\n should enable it.\n- ftrace_return_stub becomes ftrace_stub.\n- CONFIG_FUNCTION_RET_TRACER depends now on CONFIG_FUNCTION_TRACER\n- Return traces printing can be used for other tracers on trace.c\n- Adapt to the new tracing API (no more ctrl_update callback)\n- Correct the check of \"disabled\" during insertion.\n- Minor changes...\n\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Steven Rostedt \u003crostedt@goodmis.org\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "a309720c876d7ad2e224bfd1982c92ae4364c82e", "tree": "a161d06f29e3739b95d8b96c3cfb67198de9af22", "parents": [ "769c48eb2530c5c1a393e2c82063f4f050571d24" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Fri Nov 07 22:36:02 2008 -0500" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Sat Nov 08 09:51:54 2008 +0100" }, "message": "ftrace: display start of CPU buffer in trace output\n\nImpact: change in trace output\n\nBecause the trace buffers are per cpu ring buffers, the start of\nthe trace can be confusing. If one CPU is very active at the\nend of the trace, its history will not go as far back as the\nother CPU traces. This means that output for a particular CPU\nmay not appear for the first part of a trace.\n\nTo help annotate what is happening, and to prevent any more\nconfusion, this patch adds a line that annotates the start of\na CPU buffer output.\n\nFor example:\n\n automount-3495 [001] 184.596443: dnotify_parent \u003c-vfs_write\n[...]\n automount-3495 [001] 184.596449: dput \u003c-path_put\n automount-3496 [002] 184.596450: down_read_trylock \u003c-do_page_fault\n[...]\n sshd-3497 [001] 184.597069: up_read \u003c-do_page_fault\n \u003cidle\u003e-0 [000] 184.597074: __exit_idle \u003c-exit_idle\n[...]\n automount-3496 [002] 184.597257: filemap_fault \u003c-__do_fault\n \u003cidle\u003e-0 [003] 184.597261: exit_idle \u003c-smp_apic_timer_interrupt\n\nNote, parsers of a trace output should always ignore any lines that\nstart with a \u0027#\u0027.\n\nSigned-off-by: Steven Rostedt \u003csrostedt@redhat.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "c76f06945be50564f925799ddfb6235ee4c26aa0", "tree": "941aaf84dd36096d7fb013f1e4be28bb8f2ac598", "parents": [ "bbf5b1a0cecb56de6236db8b01c5bfb7ab8ba8b2" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Fri Nov 07 22:36:02 2008 -0500" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Sat Nov 08 09:51:39 2008 +0100" }, "message": "ftrace: remove trace array ctrl\n\nImpact: remove obsolete variable in trace_array structure\n\nWith the new start / stop method of ftrace, the ctrl variable\nin the trace_array structure is now obsolete. Remove it.\n\nSigned-off-by: Steven Rostedt \u003csrostedt@redhat.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "bbf5b1a0cecb56de6236db8b01c5bfb7ab8ba8b2", "tree": "ca72072808748d3ebfcf9a58a1255cd6ce63fee8", "parents": [ "49833fc232bd6a5076496994d855f601354501d7" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Fri Nov 07 22:36:02 2008 -0500" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Sat Nov 08 09:51:34 2008 +0100" }, "message": "ftrace: remove ctrl_update method\n\nImpact: Remove the ctrl_update tracer method\n\nWith the new quick start/stop method of tracing, the ctrl_update\nmethod is out of date.\n\nSigned-off-by: Steven Rostedt \u003csrostedt@redhat.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" } ], "next": "e168e0516e476070faa9e8e7b23dfcba79b76d82" }