)]}' { "log": [ { "commit": "d28daf923ac5e4a0d7cecebae56f3e339189366b", "tree": "8c8dff978e186bcd91ad60caa484480d3ed4ac11", "parents": [ "ed011b22ce567eabefa9ea571d3721c10ecd0553", "4a88d44ab17da5f8a238050d1b43dfd2e204bc2f" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Sun Sep 06 06:27:40 2009 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Sun Sep 06 06:27:40 2009 +0200" }, "message": "Merge branch \u0027tracing/core\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/frederic/random-tracing into tracing/core\n" }, { "commit": "ed011b22ce567eabefa9ea571d3721c10ecd0553", "tree": "c7aee6684613075c772388a99a9137014549434e", "parents": [ "85bac32c4a52c592b857f2c360cc5ec93a097d70", "e07cccf4046978df10f2e13fe2b99b2f9b3a65db" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Sun Sep 06 06:11:38 2009 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Sun Sep 06 06:11:42 2009 +0200" }, "message": "Merge commit \u0027v2.6.31-rc9\u0027 into tracing/core\n\nMerge reason: move from -rc5 to -rc9.\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "85bac32c4a52c592b857f2c360cc5ec93a097d70", "tree": "510e516dd5fa388cb9582a2f6b055f3725fbf2c1", "parents": [ "62f0b3eb5cb58931a02ee4e599e19c80a171e351" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Fri Sep 04 14:24:40 2009 -0400" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Fri Sep 04 19:42:22 2009 -0400" }, "message": "ring-buffer: only enable ring_buffer_swap_cpu when needed\n\nSince the ability to swap the cpu buffers adds a small overhead to\nthe recording of a trace, we only want to add it when needed.\n\nOnly the irqsoff and preemptoff tracers use this feature, and both are\nnot recommended for production kernels. This patch disables its use\nwhen neither irqsoff nor preemptoff is configured.\n\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "62f0b3eb5cb58931a02ee4e599e19c80a171e351", "tree": "344b3b8f55e6162f7fa08316aa6fde333b304c04", "parents": [ "e8165dbb03ed04d798163ee512074b9a9466a9c8" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Fri Sep 04 14:11:34 2009 -0400" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Fri Sep 04 19:38:42 2009 -0400" }, "message": "ring-buffer: check for swapped buffers in start of committing\n\nBecause the irqsoff tracer can swap an internal CPU buffer, it is possible\nthat a swap happens between the start of the write and before the committing\nbit is set (the committing bit will disable swapping).\n\nThis patch adds a check for this and will fail the write if it detects it.\n\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "e8165dbb03ed04d798163ee512074b9a9466a9c8", "tree": "a9e640253a8ce14bada6a83fe1d85ecd74968695", "parents": [ "659372d3e42a3e17a2e042d38a8bcdb94bfbe797" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Thu Sep 03 19:13:05 2009 -0400" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Fri Sep 04 19:22:41 2009 -0400" }, "message": "tracing: report error in trace if we fail to swap latency buffer\n\nThe irqsoff tracer will fail to swap the cpu buffer with the max\nbuffer if it preempts a commit. Instead of ignoring this, this patch\nmakes the tracer report it if the last max latency failed due to preempting\na current commit.\n\nThe output of the latency tracer will look like this:\n\n # tracer: irqsoff\n #\n # irqsoff latency trace v1.1.5 on 2.6.31-rc5\n # --------------------------------------------------------------------\n # latency: 112 us, #1/1, CPU#1 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:4)\n # -----------------\n # | task: -4281 (uid:0 nice:0 policy:0 rt_prio:0)\n # -----------------\n # \u003d\u003e started at: save_args\n # \u003d\u003e ended at: __do_softirq\n #\n #\n # _------\u003d\u003e CPU#\n # / _-----\u003d\u003e irqs-off\n # | / _----\u003d\u003e need-resched\n # || / _---\u003d\u003e hardirq/softirq\n # ||| / _--\u003d\u003e preempt-depth\n # |||| /\n # ||||| delay\n # cmd pid ||||| time | caller\n # \\ / ||||| \\ | /\n bash-4281 1d.s6 265us : update_max_tr_single: Failed to swap buffers due to commit in progress\n\nNote the latency time and the functions that disabled the irqs or preemption\nwill still be listed.\n\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "659372d3e42a3e17a2e042d38a8bcdb94bfbe797", "tree": "4c6195eb5e96569f902695f33babbea37e00bd41", "parents": [ "e77405ad80f53966524b5c31244e13fbbbecbd84" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Thu Sep 03 19:11:07 2009 -0400" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Fri Sep 04 19:13:53 2009 -0400" }, "message": "tracing: add trace_array_printk for internal tracers to use\n\nThis patch adds a trace_array_printk to allow a tracer to use the\ntrace_printk on its own trace array.\n\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "e77405ad80f53966524b5c31244e13fbbbecbd84", "tree": "65c05f9e1573e9958e52bb72655e00c8592aacd2", "parents": [ "f633903af2ceb0cec07d45e499a072b6593d0ed1" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Wed Sep 02 14:17:06 2009 -0400" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Fri Sep 04 18:59:39 2009 -0400" }, "message": "tracing: pass around ring buffer instead of tracer\n\nThe latency tracers (irqsoff and wakeup) can swap trace buffers\non the fly. If an event is happening and has reserved data on one of\nthe buffers, and the latency tracer swaps the global buffer with the\nmax buffer, the result is that the event may commit the data to the\nwrong buffer.\n\nThis patch changes the API to the trace recording to be recieve the\nbuffer that was used to reserve a commit. Then this buffer can be passed\nin to the commit.\n\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "f633903af2ceb0cec07d45e499a072b6593d0ed1", "tree": "9a484fa299142a00d0dbb5a97e1108031db96e70", "parents": [ "2f26ebd549b9ab55ac756b836ec759c11fe93f81" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Fri Sep 04 12:35:16 2009 -0400" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Fri Sep 04 18:46:51 2009 -0400" }, "message": "tracing: make tracing_reset safe for external use\n\nReseting the trace buffer without first disabling the buffer and\nwaiting for any writers to complete, can corrupt the ring buffer.\n\nThis patch makes the external version of tracing_reset safe from\ncorruption by disabling the ring buffer and calling synchronize_sched.\n\nThis version can no longer be called from interrupt context. But all those\ncallers have been removed.\n\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "2f26ebd549b9ab55ac756b836ec759c11fe93f81", "tree": "0f6fb154e2b5e9233a683b3267e5efe862a846f4", "parents": [ "76f0d07376388f32698ba51b6090a26b90c1342f" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Tue Sep 01 11:06:29 2009 -0400" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Fri Sep 04 18:44:22 2009 -0400" }, "message": "tracing: use timestamp to determine start of latency traces\n\nCurrently the latency tracers reset the ring buffer. Unfortunately\nif a commit is in process (due to a trace event), this can corrupt\nthe ring buffer. When this happens, the ring buffer will detect\nthe corruption and then permanently disable the ring buffer.\n\nThe bug does not crash the system, but it does prevent further tracing\nafter the bug is hit.\n\nInstead of reseting the trace buffers, the timestamp of the start of\nthe trace is used instead. The buffers will still contain the previous\ndata, but the output will not count any data that is before the\ntimestamp of the trace.\n\nNote, this only affects the static trace output (trace) and not the\nruntime trace output (trace_pipe). The runtime trace output does not\nmake sense for the latency tracers anyway.\n\nReported-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "c58b43218c1a04a0bcf338ea47406c759ac28e11", "tree": "e13e33f195a13b4c959494ee7d059b87c2167be3", "parents": [ "8e254c1d183f0225ad21f9049641529e56cce4da" ], "author": { "name": "Li Zefan", "email": "lizf@cn.fujitsu.com", "time": "Tue Sep 01 13:31:38 2009 +0800" }, "committer": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Fri Sep 04 23:22:33 2009 +0200" }, "message": "tracing/filters: Defer pred allocation, fix memory leak\n\nThe predicates of an event and their filter structure are allocated\nwhen we create an event filter for the first time.\n\nThese objects must be created once but each time we come with a new\nfilter, we overwrite such pre-existing allocation, if any.\n\nThus, this patch checks if the filter has already been allocated\nbefore going ahead.\n\nSpotted-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nSigned-off-by: Li Zefan \u003clizf@cn.fujitsu.com\u003e\nCc: Steven Rostedt \u003crostedt@goodmis.org\u003e\nCc: Tom Zanussi \u003ctzanussi@gmail.com\u003e\nCc: Masami Hiramatsu \u003cmhiramat@redhat.com\u003e\nLKML-Reference: \u003c4A9CB1BA.3060402@cn.fujitsu.com\u003e\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\n" }, { "commit": "76f0d07376388f32698ba51b6090a26b90c1342f", "tree": "ea3a2576e7d2ae85d610aa088cb05986a13f03b1", "parents": [ "621968cdb2563b667d6ecb484ba91ef4c3a797b3" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Fri Sep 04 12:12:39 2009 -0400" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Fri Sep 04 12:12:39 2009 -0400" }, "message": "tracing: remove users of tracing_reset\n\nThe function tracing_reset is deprecated for outside use of trace.c.\n\nThe new function to reset the the buffers is tracing_reset_online_cpus.\n\nThe reason for this is that resetting the buffers while the event\ntrace points are active can corrupt the buffers, because they may\nbe writing at the time of reset. The tracing_reset_online_cpus disables\nwrites and waits for current writers to finish.\n\nThis patch replaces all users of tracing_reset except for the latency\ntracers. Those changes require more work and will be removed in the\nfollowing patches.\n\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "621968cdb2563b667d6ecb484ba91ef4c3a797b3", "tree": "a4b8e3ba1f55d6b725b37a4e42c2f376d6150cdc", "parents": [ "b8de7bd168fa54d059b16d3057b2f8a32cc5bdc3" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Fri Sep 04 12:02:35 2009 -0400" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Fri Sep 04 12:02:35 2009 -0400" }, "message": "tracing: disable buffers and synchronize_sched before resetting\n\nResetting the ring buffers while traces are happening can corrupt\nthe ring buffer and disable it (no kernel crash to worry about).\n\nThe safest thing to do is disable the ring buffers, call synchronize_sched()\nto wait for all current writers to finish and then reset the buffer.\n\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "b8de7bd168fa54d059b16d3057b2f8a32cc5bdc3", "tree": "3455ec59050f7f6d466a8c08275567079914d1b1", "parents": [ "8248ac052dfd1eb41819fbc0ca5c7a1667e7e70c" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Mon Aug 31 22:32:27 2009 -0400" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Fri Sep 04 11:52:24 2009 -0400" }, "message": "tracing: disable update max tracer while reading trace\n\nWhen reading the tracer from the trace file, updating the max latency\nmay corrupt the output. This patch disables the tracing of the max\nlatency while reading the trace file.\n\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "8248ac052dfd1eb41819fbc0ca5c7a1667e7e70c", "tree": "d979964a23112b6266d26da19a572057e5060367", "parents": [ "077c5407cd3231cf13472623995f0dfdda510d62" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Wed Sep 02 12:27:41 2009 -0400" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Fri Sep 04 11:48:12 2009 -0400" }, "message": "tracing: print out start and stop in latency traces\n\nDuring development of the tracer, we would copy information from\nthe live tracer to the max tracer with one memcpy. Since then we\nadded a generic ring buffer and we handle the copies differently now.\nUnfortunately, we never copied the critical section information, and\nwe lost the output:\n\n # \u003d\u003e started at: kmem_cache_alloc\n # \u003d\u003e ended at: kmem_cache_alloc\n\nThis patch adds back the critical start and end copying as well as\nremoves the unused \"trace_idx\" and \"overrun\" fields of the\ntrace_array_cpu structure.\n\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "077c5407cd3231cf13472623995f0dfdda510d62", "tree": "843c729463363495f13333b2b55f3985ea75dfd8", "parents": [ "a1863c212b7517afc2b13e549552ac322fb44cab" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Thu Sep 03 19:53:46 2009 -0400" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Fri Sep 04 11:46:25 2009 -0400" }, "message": "ring-buffer: disable all cpu buffers when one finds a problem\n\nCurrently the way RB_WARN_ON works, is to disable either the current\nCPU buffer or all CPU buffers, depending on whether a ring_buffer or\nring_buffer_per_cpu struct was passed into the macro.\n\nMost users of the RB_WARN_ON pass in the CPU buffer, so only the one\nCPU buffer gets disabled but the rest are still active. This may\nconfuse users even though a warning is sent to the console.\n\nThis patch changes the macro to disable the entire buffer even if\nthe CPU buffer is passed in.\n\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "a1863c212b7517afc2b13e549552ac322fb44cab", "tree": "20ad746370b0d03950f23a349ebb07c913f99fd2", "parents": [ "dc892f7339af2d125478b800edb9081d6149665b" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Thu Sep 03 10:23:58 2009 -0400" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Fri Sep 04 11:43:36 2009 -0400" }, "message": "ring-buffer: do not count discarded events\n\nThe latency tracers report the number of items in the trace buffer.\nThis uses the ring buffer data to calculate this. Because discarded\nevents are also counted, the numbers do not match the number of items\nthat are printed. The ring buffer also adds a \"padding\" item to the\nend of each buffer page which also gets counted as a discarded item.\n\nThis patch decrements the counter to the page entries on a discard.\nThis allows us to ignore discarded entries while reading the buffer.\n\nDecrementing the counter is still safe since it can only happen while\nthe committing flag is still set.\n\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "dc892f7339af2d125478b800edb9081d6149665b", "tree": "3377439556b600c7bd3d53cbc0a893dd75bed634", "parents": [ "7e9391cfedce34eb9786bfa69d7d545dc93ef930" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Thu Sep 03 15:33:41 2009 -0400" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Fri Sep 04 11:36:19 2009 -0400" }, "message": "ring-buffer: remove ring_buffer_event_discard\n\nThe function ring_buffer_event_discard can be used on any item in the\nring buffer, even after the item was committed. This function provides\nno safety nets and is very race prone.\n\nAn item may be safely removed from the ring buffer before it is committed\nwith the ring_buffer_discard_commit.\n\nSince there are currently no users of this function, and because this\nfunction is racey and error prone, this patch removes it altogether.\n\nNote, removing this function also allows the counters to ignore\nall discarded events (patches will follow).\n\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "7e9391cfedce34eb9786bfa69d7d545dc93ef930", "tree": "e3901037e9269cbf10bd2952835ebcc573e5741d", "parents": [ "1b959e18c4d6b4b981f887260b0f8e7939efa411" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Thu Sep 03 10:02:09 2009 -0400" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Fri Sep 04 11:28:39 2009 -0400" }, "message": "ring-buffer: fix ring_buffer_read crossing pages\n\nWhen the ring buffer uses an iterator (static read mode, not on the\nfly reading), when it crosses a page boundery, it will skip the first\nentry on the next page. The reason is that the last entry of a page\nis usually padding if the page is not full. The padding will not be\nreturned to the user.\n\nThe problem arises on ring_buffer_read because it also increments the\niterator. Because both the read and peek use the same rb_iter_peek,\nthe rb_iter_peak will return the padding but also increment to the next\nitem. This is because the ring_buffer_peek will not incerment it\nitself.\n\nThe ring_buffer_read will increment it again and then call rb_iter_peek\nagain to get the next item. But that will be the second item, not the\nfirst one on the page.\n\nThe reason this never showed up before, is because the ftrace utility\nalways calls ring_buffer_peek first and only uses ring_buffer_read\nto increment to the next item. The ring_buffer_peek will always keep\nthe pointer to a valid item and not padding. This just hid the bug.\n\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "1b959e18c4d6b4b981f887260b0f8e7939efa411", "tree": "3f7b9950cfe19742cfe04bc3feb11f7ad0a46e71", "parents": [ "98277991a99734f3a31d638afb47d4484ac73e43" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Thu Sep 03 10:12:13 2009 -0400" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Fri Sep 04 11:25:27 2009 -0400" }, "message": "ring-buffer: remove unnecessary cpu_relax\n\nThe loops in the ring buffer that use cpu_relax are not dependent on\nother CPUs. They simply came across some padding in the ring buffer and\nare skipping over them. It is a normal loop and does not require a\ncpu_relax.\n\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "98277991a99734f3a31d638afb47d4484ac73e43", "tree": "6688cb3c43562d6bd7b67961478ac337297064e5", "parents": [ "41b6a95d693319f804607b559893fbbd27498548" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Wed Sep 02 10:56:15 2009 -0400" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Fri Sep 04 11:22:47 2009 -0400" }, "message": "ring-buffer: do not swap buffers during a commit\n\nIf a commit is taking place on a CPU ring buffer, do not allow it to\nbe swapped. Return -EBUSY when this is detected instead.\n\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "41b6a95d693319f804607b559893fbbd27498548", "tree": "eafa22ab694eda7723cec115592a861867432a66", "parents": [ "8e254c1d183f0225ad21f9049641529e56cce4da" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Wed Sep 02 09:59:48 2009 -0400" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Fri Sep 04 11:15:08 2009 -0400" }, "message": "ring-buffer: do not reset while in a commit\n\nThe callers of reset must ensure that no commit can be taking place\nat the time of the reset. If it does then we may corrupt the ring buffer.\n\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "8e254c1d183f0225ad21f9049641529e56cce4da", "tree": "5b559726a38b60c6bc92b3c8667c676db1038701", "parents": [ "73222acf966792c7fda219724af963339be32e62" ], "author": { "name": "Li Zefan", "email": "lizf@cn.fujitsu.com", "time": "Mon Aug 31 16:49:41 2009 +0800" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Aug 31 10:58:08 2009 +0200" }, "message": "tracing/filters: Defer pred allocation\n\ninit_preds() allocates about 5392 bytes of memory (on x86_32) for\na TRACE_EVENT. With my config, at system boot total memory occupied\nis:\n\n\t5392 * (642 + 15) \u003d\u003d 3459KB\n\n642 \u003d\u003d cat available_events | wc -l\n15 \u003d\u003d number of dirs in events/ftrace\n\nThat\u0027s quite a lot, so we\u0027d better defer memory allocation util\nit\u0027s needed, that\u0027s when filter is used.\n\nSigned-off-by: Li Zefan \u003clizf@cn.fujitsu.com\u003e\nCc: Steven Rostedt \u003crostedt@goodmis.org\u003e\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Tom Zanussi \u003ctzanussi@gmail.com\u003e\nCc: Masami Hiramatsu \u003cmhiramat@redhat.com\u003e\nLKML-Reference: \u003c4A9B8EA5.6020700@cn.fujitsu.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "73222acf966792c7fda219724af963339be32e62", "tree": "83109ded0bcfdc6a0ec5e8ea6becffd7ac41ec6a", "parents": [ "0dd7b74787eaf7858c6c573353a83c3e2766e674", "5d4a9dba2d7fbab69f00dedd430d1788834a055a" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Sat Aug 29 13:06:05 2009 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Sat Aug 29 13:06:05 2009 +0200" }, "message": "Merge branch \u0027tip/tracing/core\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-2.6-trace into tracing/core\n" }, { "commit": "5d4a9dba2d7fbab69f00dedd430d1788834a055a", "tree": "a57ec209fc1ac86d7acbd67164b068ecdadd6317", "parents": [ "c0729be99cb2b9d9749256254f1c40a801835896" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Thu Aug 27 16:52:21 2009 -0400" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Thu Aug 27 16:58:05 2009 -0400" }, "message": "tracing: only show tracing_max_latency when latency tracer configured\n\nThe tracing_max_latency file should only be present when one of the\nlatency tracers ({preempt|irqs}off, wakeup*) are enabled.\n\nThis patch also removes tracing_thresh when latency tracers are not\nenabled, as well as compiles out code that is only used for latency\ntracers.\n\nReported-by: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "c0729be99cb2b9d9749256254f1c40a801835896", "tree": "f7cb3d86ed28f2f42dcaa23035f2ecc30e363137", "parents": [ "6c347d43eea29221a8ebab9ff9cbe7a00cddac98" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Wed Aug 26 22:23:52 2009 -0400" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Thu Aug 27 16:58:03 2009 -0400" }, "message": "tracing: remove legacy select of MARKERS by context switch tracing\n\nThe context switch tracer was made before tracepoints were mature, and\nthe original version used markers. This is no longer true and this\npatch removes the select.\n\nReported-by: Thomas Gleixner \u003ctglx@linutronix.de\u003e\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "57421dbbdc932d65f0e6a41ebb027a2bfe3d0669", "tree": "0dec1f947cc6d3e9d5fe813c31cbaa960c9ed7b6", "parents": [ "a5a2f8e2acb991327952c45a13f5441fc09dffd6" ], "author": { "name": "Jason Baron", "email": "jbaron@redhat.com", "time": "Mon Aug 24 17:40:22 2009 -0400" }, "committer": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Wed Aug 26 21:30:02 2009 +0200" }, "message": "tracing: Convert event tracing code to use NR_syscalls\n\nConvert the syscalls event tracing code to use NR_syscalls, instead of\nFTRACE_SYSCALL_MAX. NR_syscalls is standard accross most arches, and\nreduces code confusion/complexity.\n\nSigned-off-by: Jason Baron \u003cjbaron@redhat.com\u003e\nCc: Paul Mundt \u003clethal@linux-sh.org\u003e\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Lai Jiangshan \u003claijs@cn.fujitsu.com\u003e\nCc: Steven Rostedt \u003crostedt@goodmis.org\u003e\nCc: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nCc: Mathieu Desnoyers \u003cmathieu.desnoyers@polymtl.ca\u003e\nCc: Jiaying Zhang \u003cjiayingz@google.com\u003e\nCc: Martin Bligh \u003cmbligh@google.com\u003e\nCc: Li Zefan \u003clizf@cn.fujitsu.com\u003e\nCc: Josh Stone \u003cjistone@redhat.com\u003e\nCc: Thomas Gleixner \u003ctglx@linutronix.de\u003e\nCc: H. Peter Anwin \u003chpa@zytor.com\u003e\nCc: Hendrik Brueckner \u003cbrueckner@linux.vnet.ibm.com\u003e\nCc: Heiko Carstens \u003cheiko.carstens@de.ibm.com\u003e\nLKML-Reference: \u003c9b4f1a84ecae57cc6599412772efa36f0d2b815b.1251146513.git.jbaron@redhat.com\u003e\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\n" }, { "commit": "cd0980fc8add25e8ab12fcf1051c0f20cbc7c0c0", "tree": "307fe4d60c058c016c650366db2c2761b20cfd6d", "parents": [ "7515bf59f87f19b2a17972b74230d2f91756fe3c" ], "author": { "name": "Hendrik Brueckner", "email": "brueckner@linux.vnet.ibm.com", "time": "Tue Aug 25 14:50:27 2009 +0200" }, "committer": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Wed Aug 26 21:29:48 2009 +0200" }, "message": "tracing: Check invalid syscall nr while tracing syscalls\n\nMost arch syscall_get_nr() implementations returns -1 if the syscall\nnumber is not valid. Accessing the bit field without a check might\nresult in a kernel oops (at least I saw it on s390 for ftrace selftest).\n\nBefore this change, this problem did not occur, because the invalid\nsyscall number (-1) caused syscall_nr_to_meta() to return NULL.\n\nThere are at least two scenarios where syscall_get_nr() can return -1:\n\n1. For example, ptrace stores an invalid syscall number, and thus,\n tracing code resets it.\n (see do_syscall_trace_enter in arch/s390/kernel/ptrace.c)\n\n2. The syscall_regfunc() (kernel/tracepoint.c) sets the\n TIF_SYSCALL_FTRACE (now: TIF_SYSCALL_TRACEPOINT) flag for all threads\n which include kernel threads.\n However, the ftrace selftest triggers a kernel oops when testing\n syscall trace points:\n - The kernel thread is started as ususal (do_fork()),\n - tracing code sets TIF_SYSCALL_FTRACE,\n - the ret_from_fork() function is triggered and starts\n\tftrace_syscall_exit() with an invalid syscall number.\n\nTo avoid these scenarios, I suggest to check the syscall_nr.\n\nFor instance, the ftrace selftest fails for s390 (with config option\nCONFIG_FTRACE_SYSCALLS set) and produces the following kernel oops.\n\nUnable to handle kernel pointer dereference at virtual kernel address 2000000000\n\nOops: 0038 [#1] PREEMPT SMP\nModules linked in:\nCPU: 0 Not tainted 2.6.31-rc6-next-20090819-dirty #18\nProcess kthreadd (pid: 818, task: 000000003ea207e8, ksp: 000000003e813eb8)\nKrnl PSW : 0704100180000000 00000000000ea54c (ftrace_syscall_exit+0x58/0xdc)\n R:0 T:1 IO:1 EX:1 Key:0 M:1 W:0 P:0 AS:0 CC:1 PM:0 EA:3\nKrnl GPRS: 0000000000000000 00000000000e0000 ffffffffffffffff 20000000008c2650\n 0000000000000007 0000000000000000 0000000000000000 0000000000000000\n 0000000000000000 0000000000000000 ffffffffffffffff 000000003e813d78\n 000000003e813f58 0000000000505ba8 000000003e813e18 000000003e813d78\nKrnl Code: 00000000000ea540: e330d0000008 ag %r3,0(%r13)\n 00000000000ea546: a7480007 lhi %r4,7\n 00000000000ea54a: 1442 nr %r4,%r2\n \u003e00000000000ea54c: e31030000090 llgc %r1,0(%r3)\n 00000000000ea552: 5410d008 n %r1,8(%r13)\n 00000000000ea556: 8a104000 sra %r1,0(%r4)\n 00000000000ea55a: 5410d00c n %r1,12(%r13)\n 00000000000ea55e: 1211 ltr %r1,%r1\nCall Trace:\n([\u003c0000000000000000\u003e] 0x0)\n [\u003c000000000001fa22\u003e] do_syscall_trace_exit+0x132/0x18c\n [\u003c000000000002d0c4\u003e] sysc_return+0x0/0x8\n [\u003c000000000001c738\u003e] kernel_thread_starter+0x0/0xc\nLast Breaking-Event-Address:\n [\u003c00000000000ea51e\u003e] ftrace_syscall_exit+0x2a/0xdc\n\nSigned-off-by: Hendrik Brueckner \u003cbrueckner@linux.vnet.ibm.com\u003e\nAcked-by: Heiko Carstens \u003cheiko.carstens@de.ibm.com\u003e\nCc: Jason Baron \u003cjbaron@redhat.com\u003e\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Lai Jiangshan \u003claijs@cn.fujitsu.com\u003e\nCc: Steven Rostedt \u003crostedt@goodmis.org\u003e\nCc: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nCc: Mathieu Desnoyers \u003cmathieu.desnoyers@polymtl.ca\u003e\nCc: Jiaying Zhang \u003cjiayingz@google.com\u003e\nCc: Martin Bligh \u003cmbligh@google.com\u003e\nCc: Li Zefan \u003clizf@cn.fujitsu.com\u003e\nCc: Martin Schwidefsky \u003cschwidefsky@de.ibm.com\u003e\nCc: Paul Mundt \u003clethal@linux-sh.org\u003e\nLKML-Reference: \u003c20090825125027.GE4639@cetus.boeblingen.de.ibm.com\u003e\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\n" }, { "commit": "35dce1a99d010f3d738af4ce1b9b77302fdfe69c", "tree": "e34a37de965a79a2ae301de4d0557f500111dde6", "parents": [ "7cb2e3ee2aeec5b83ecadba929a2dc575dd4008f", "1c569f0264ea629c10bbab471dd0626ce4d3f19f" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Wed Aug 26 08:29:02 2009 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Wed Aug 26 08:29:02 2009 +0200" }, "message": "Merge branch \u0027tracing/core\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/frederic/random-tracing into tracing/core\n\nConflicts:\n\tinclude/linux/tracepoint.h\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "5079f3261ffd7fe4a537679af695f2328943a245", "tree": "1f9ab5128f37c3628979496610bc862b4a321cd6", "parents": [ "87a342f5db69d53ea70493bb1ec69c9047677038" ], "author": { "name": "Zhaolei", "email": "zhaolei@cn.fujitsu.com", "time": "Tue Aug 25 16:12:56 2009 +0800" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Wed Aug 26 00:32:08 2009 -0400" }, "message": "ftrace: Move setting of clock-source out of options\n\nThere are many clock sources for the tracing system but we can only\nenable/disable one at a time with the trace/options file.\nWe can move the setting of clock-source out of options and add a separate\nfile for it:\n # cat trace_clock\n [local] global\n # echo global \u003e trace_clock\n # cat trace_clock\n local [global]\n\nSigned-off-by: Zhao Lei \u003czhaolei@cn.fujitsu.com\u003e\nLKML-Reference: \u003c4A939D08.6050604@cn.fujitsu.com\u003e\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "87a342f5db69d53ea70493bb1ec69c9047677038", "tree": "89ec97b3a32d6508d10f1598201e48a24c08c46e", "parents": [ "43b51ead3f752a3935116e5b1a94254b8573734f" ], "author": { "name": "Li Zefan", "email": "lizf@cn.fujitsu.com", "time": "Fri Aug 07 10:33:43 2009 +0800" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Wed Aug 26 00:32:07 2009 -0400" }, "message": "tracing/filters: Support filtering for char * strings\n\nUsually, char * entries are dangerous in traces because the string\ncan be released whereas a pointer to it can still wait to be read from\nthe ring buffer.\n\nBut sometimes we can assume it\u0027s safe, like in case of RO data\n(eg: __file__ or __line__, used in bkl trace event). If these RO data\nare in a module and so is the call to the trace event, then it\u0027s safe,\nbecause the ring buffer will be flushed once this module get unloaded.\n\nTo allow char * to be treated as a string:\n\n\tTRACE_EVENT(...,\n\n\t\tTP_STRUCT__entry(\n\t\t\t__field_ext(const char *, name, FILTER_PTR_STRING)\n\t\t\t...\n\t\t)\n\n\t\t...\n\t);\n\nThe filtering will not dereference \"char *\" unless the developer\nexplicitly sets FILTER_PTR_STR in __field_ext.\n\nSigned-off-by: Li Zefan \u003clizf@cn.fujitsu.com\u003e\nLKML-Reference: \u003c4A7B9287.90205@cn.fujitsu.com\u003e\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "43b51ead3f752a3935116e5b1a94254b8573734f", "tree": "5d9e88635c85ba7b1d273dea3c4d8d96e5000154", "parents": [ "aa38e9fc3ea804290efd3a39316d7f7e6c945800" ], "author": { "name": "Li Zefan", "email": "lizf@cn.fujitsu.com", "time": "Fri Aug 07 10:33:22 2009 +0800" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Wed Aug 26 00:32:06 2009 -0400" }, "message": "tracing/filters: Add __field_ext() to TRACE_EVENT\n\nAdd __field_ext(), so a field can be assigned to a specific\nfilter_type, which matches a corresponding filter function.\n\nFor example, a later patch will allow this:\n\t__field_ext(const char *, str, FILTER_PTR_STR);\n\nSigned-off-by: Li Zefan \u003clizf@cn.fujitsu.com\u003e\nLKML-Reference: \u003c4A7B9272.6050709@cn.fujitsu.com\u003e\n\n[\n Fixed a -1 to FILTER_OTHER\n Forward ported to latest kernel.\n]\n\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "aa38e9fc3ea804290efd3a39316d7f7e6c945800", "tree": "8f9766b20c9006c1373f11c927fb46441e01df0f", "parents": [ "6591b493871cf9b17de2ba272edb8ab529a8058b" ], "author": { "name": "Li Zefan", "email": "lizf@cn.fujitsu.com", "time": "Fri Aug 07 10:33:02 2009 +0800" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Wed Aug 26 00:32:06 2009 -0400" }, "message": "tracing/filters: Add filter_type to struct ftrace_event_field\n\nThe type of a field is stored as a string in @type, and here\nwe add @filter_type which is an enum value.\n\nThis prepares for later patches, so we can specifically assign\ndifferent @filter_type for the same @type.\n\nFor example normally a \"char *\" field is treated as a ptr,\nbut we may want it to be treated as a string when doing filting.\n\nSigned-off-by: Li Zefan \u003clizf@cn.fujitsu.com\u003e\nLKML-Reference: \u003c4A7B925E.9030605@cn.fujitsu.com\u003e\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "1c569f0264ea629c10bbab471dd0626ce4d3f19f", "tree": "00fcbf85a7318c568f468518c3aa665a200c871e", "parents": [ "97419875865859fd2403e66266c02ce028e2f5ab" ], "author": { "name": "Josh Stone", "email": "jistone@redhat.com", "time": "Mon Aug 24 14:43:14 2009 -0700" }, "committer": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Wed Aug 26 00:41:48 2009 +0200" }, "message": "tracing: Create generic syscall TRACE_EVENTs\n\nThis converts the syscall_enter/exit tracepoints into TRACE_EVENTs, so\nyou can have generic ftrace events that capture all system calls with\narguments and return values. These generic events are also renamed to\nsys_enter/exit, so they\u0027re more closely aligned to the specific\nsys_enter_foo events.\n\nSigned-off-by: Josh Stone \u003cjistone@redhat.com\u003e\nCc: Jason Baron \u003cjbaron@redhat.com\u003e\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Li Zefan \u003clizf@cn.fujitsu.com\u003e\nCc: Steven Rostedt \u003crostedt@goodmis.org\u003e\nCc: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nCc: Mathieu Desnoyers \u003cmathieu.desnoyers@polymtl.ca\u003e\nCc: Jiaying Zhang \u003cjiayingz@google.com\u003e\nCc: Martin Bligh \u003cmbligh@google.com\u003e\nCc: Lai Jiangshan \u003claijs@cn.fujitsu.com\u003e\nCc: Paul Mundt \u003clethal@linux-sh.org\u003e\nCc: Martin Schwidefsky \u003cschwidefsky@de.ibm.com\u003e\nCc: Heiko Carstens \u003cheiko.carstens@de.ibm.com\u003e\nLKML-Reference: \u003c1251150194-1713-5-git-send-email-jistone@redhat.com\u003e\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\n" }, { "commit": "667000011927b4fcc359beac4a2447889db6d349", "tree": "d21f0bce17e08479885818792529d3cadf7b8003", "parents": [ "d88cb582325830698de5071fa8b8c9e933dbbcad" ], "author": { "name": "Josh Stone", "email": "jistone@redhat.com", "time": "Mon Aug 24 14:43:11 2009 -0700" }, "committer": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Wed Aug 26 00:17:35 2009 +0200" }, "message": "tracing: Rename FTRACE_SYSCALLS for tracepoints\n\ns/HAVE_FTRACE_SYSCALLS/HAVE_SYSCALL_TRACEPOINTS/g\ns/TIF_SYSCALL_FTRACE/TIF_SYSCALL_TRACEPOINT/g\n\nThe syscall enter/exit tracing is no longer specific to just ftrace, so\nthey now have names that reflect their tie to tracepoints instead.\n\nSigned-off-by: Josh Stone \u003cjistone@redhat.com\u003e\nCc: Jason Baron \u003cjbaron@redhat.com\u003e\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Li Zefan \u003clizf@cn.fujitsu.com\u003e\nCc: Steven Rostedt \u003crostedt@goodmis.org\u003e\nCc: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nCc: Mathieu Desnoyers \u003cmathieu.desnoyers@polymtl.ca\u003e\nCc: Jiaying Zhang \u003cjiayingz@google.com\u003e\nCc: Martin Bligh \u003cmbligh@google.com\u003e\nCc: Lai Jiangshan \u003claijs@cn.fujitsu.com\u003e\nCc: Paul Mundt \u003clethal@linux-sh.org\u003e\nCc: Martin Schwidefsky \u003cschwidefsky@de.ibm.com\u003e\nCc: Heiko Carstens \u003cheiko.carstens@de.ibm.com\u003e\nLKML-Reference: \u003c1251150194-1713-2-git-send-email-jistone@redhat.com\u003e\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\n" }, { "commit": "4539f07701b3f743580d19dc5d655fb8d21b0a3c", "tree": "15bb4504cda47f4e5281831eccd91b51dcd4b095", "parents": [ "540b7b8d65575c80162f2a0f38e1d313c92a6042" ], "author": { "name": "Li Zefan", "email": "lizf@cn.fujitsu.com", "time": "Thu Aug 20 16:13:35 2009 +0800" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Thu Aug 20 12:12:22 2009 +0200" }, "message": "tracing/syscalls: Fix the output of syscalls with no arguments\n\nBefore:\n\n # echo 1 \u003e events/syscalls/sys_enter_sync/enable\n # cat events/syscalls/sys_enter_sync/format\n ...\n field:int nr; offset:12; size:4;\n\n print fmt: \"# sync\n # cat trace\n ...\n sync-8950 [000] 2366.087670: sys_sync(\n\nAfter:\n\n # echo 1 \u003e events/syscalls/sys_enter_sync/enable\n # cat events/syscalls/sys_enter_sync/format\n ...\n field:int nr; offset:12; size:4;\n\n print fmt: \"\"\n # sync\n # cat trace\n sync-2134 [001] 136.780735: sys_sync()\n\nReported-by: Masami Hiramatsu \u003cmhiramat@redhat.com\u003e\nSigned-off-by: Li Zefan \u003clizf@cn.fujitsu.com\u003e\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Steven Rostedt \u003crostedt@goodmis.org\u003e\nCc: Jason Baron \u003cjbaron@redhat.com\u003e\nCc: Masami Hiramatsu \u003cmhiramat@redhat.com\u003e\nLKML-Reference: \u003c4A8D05AF.20103@cn.fujitsu.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "540b7b8d65575c80162f2a0f38e1d313c92a6042", "tree": "664bdd01ce8fce990e634a304f9b3ab51e50970c", "parents": [ "e647d6b314266adb904d4b84973eda0afa856946" ], "author": { "name": "Li Zefan", "email": "lizf@cn.fujitsu.com", "time": "Wed Aug 19 15:54:51 2009 +0800" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Wed Aug 19 15:02:24 2009 +0200" }, "message": "tracing/syscalls: Add filtering support\n\nAdd filtering support for syscall events:\n\n # echo \u0027mode \u003d\u003d 0666\u0027 \u003e events/syscalls/sys_enter_open\n # echo \u0027ret \u003d\u003d 0\u0027 \u003e events/syscalls/sys_exit_open\n # echo 1 \u003e events/syscalls/sys_enter_open\n # echo 1 \u003e events/syscalls/sys_exit_open\n # cat trace\n ...\n modprobe-3084 [001] 117.463140: sys_open(filename: 917d3e8, flags: 0, mode: 1b6)\n modprobe-3084 [001] 117.463176: sys_open -\u003e 0x0\n less-3086 [001] 117.510455: sys_open(filename: 9c6bdb8, flags: 8000, mode: 1b6)\n sendmail-2574 [001] 122.145840: sys_open(filename: b807a365, flags: 0, mode: 1b6)\n ...\n\nSigned-off-by: Li Zefan \u003clizf@cn.fujitsu.com\u003e\nCc: Jason Baron \u003cjbaron@redhat.com\u003e\nCc: Steven Rostedt \u003crostedt@goodmis.org\u003e\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nLKML-Reference: \u003c4A8BAFCB.1040006@cn.fujitsu.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "e647d6b314266adb904d4b84973eda0afa856946", "tree": "e4f18b57d37a25910b3d19b6c2461f87db0084a3", "parents": [ "14be96c9716cb8c46dca94bd890defd7856e0734" ], "author": { "name": "Li Zefan", "email": "lizf@cn.fujitsu.com", "time": "Wed Aug 19 15:54:32 2009 +0800" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Wed Aug 19 15:02:24 2009 +0200" }, "message": "tracing/events: Add trace_define_common_fields()\n\nExtract duplicate code. Also prepare for the later patch.\n\nSigned-off-by: Li Zefan \u003clizf@cn.fujitsu.com\u003e\nCc: Jason Baron \u003cjbaron@redhat.com\u003e\nCc: Steven Rostedt \u003crostedt@goodmis.org\u003e\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nLKML-Reference: \u003c4A8BAFB8.1010304@cn.fujitsu.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "14be96c9716cb8c46dca94bd890defd7856e0734", "tree": "d9a064f3191182f16ff01176b17c4dda073d8dc8", "parents": [ "10a5b66f625904ad5a2867cf7a28073e1236ff32" ], "author": { "name": "Li Zefan", "email": "lizf@cn.fujitsu.com", "time": "Wed Aug 19 15:53:52 2009 +0800" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Wed Aug 19 15:02:23 2009 +0200" }, "message": "tracing/events: Add ftrace_event_call param to define_fields()\n\nThis parameter is needed by syscall events to add define_fields()\nhandler.\n\nSigned-off-by: Li Zefan \u003clizf@cn.fujitsu.com\u003e\nCc: Jason Baron \u003cjbaron@redhat.com\u003e\nCc: Steven Rostedt \u003crostedt@goodmis.org\u003e\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nLKML-Reference: \u003c4A8BAF90.6060801@cn.fujitsu.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "10a5b66f625904ad5a2867cf7a28073e1236ff32", "tree": "165c3d0f480e2862d3d97f3f3ceecad9c1cdc8b8", "parents": [ "e6971969c331caa5c3c88cbd1be4f465b3355452" ], "author": { "name": "Li Zefan", "email": "lizf@cn.fujitsu.com", "time": "Wed Aug 19 15:53:05 2009 +0800" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Wed Aug 19 15:02:23 2009 +0200" }, "message": "tracing/syscalls: Add fields format for exit events\n\nAdd \"format\" file for syscall exit events:\n\n # cat events/syscalls/sys_exit_open/format\n name: sys_exit_open\n ID: 344\n format:\n field:unsigned short common_type; offset:0; size:2;\n field:unsigned char common_flags; offset:2; size:1;\n field:unsigned char common_preempt_count; offset:3; size:1;\n field:int common_pid; offset:4; size:4;\n field:int common_tgid; offset:8; size:4;\n\n field:int nr; offset:12; size:4;\n field:unsigned long ret; offset:16; size:4;\n\nSigned-off-by: Li Zefan \u003clizf@cn.fujitsu.com\u003e\nCc: Jason Baron \u003cjbaron@redhat.com\u003e\nCc: Steven Rostedt \u003crostedt@goodmis.org\u003e\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nLKML-Reference: \u003c4A8BAF61.3060307@cn.fujitsu.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "e6971969c331caa5c3c88cbd1be4f465b3355452", "tree": "0d66906d1882566257db824b38ab905d8a0dc721", "parents": [ "5e9ad7df9fd056f1071af8aa91034a1c3170257d" ], "author": { "name": "Li Zefan", "email": "lizf@cn.fujitsu.com", "time": "Wed Aug 19 15:52:25 2009 +0800" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Wed Aug 19 15:02:22 2009 +0200" }, "message": "tracing/syscalls: Fix fields format for enter events\n\nThe \"format\" file of a trace event is originally for parsers to\nparse ftrace binary output.\n\nBut the \"format\" file of a syscall event can only be used by\nperfcounter, because it describes the format of struct\nsyscall_enter_record not struct syscall_trace_enter.\n\nTo fix this, we remove struct syscall_enter_record, and then\nstruct syscall_trace_enter will be used by both perf profile\nand ftrace.\n\nSigned-off-by: Li Zefan \u003clizf@cn.fujitsu.com\u003e\nCc: Jason Baron \u003cjbaron@redhat.com\u003e\nCc: Steven Rostedt \u003crostedt@goodmis.org\u003e\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nLKML-Reference: \u003c4A8BAF39.1030404@cn.fujitsu.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "eda1e328556565e211b7450250e40d6de751563a", "tree": "a0d4d6c056f3c4452a9a7d0e4b9af52e7a2d089d", "parents": [ "f2d84b65b9778e8a35dd904f7d3993f0a60c9756" ], "author": { "name": "Jiri Olsa", "email": "jolsa@redhat.com", "time": "Tue Aug 11 17:29:04 2009 +0200" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Tue Aug 18 20:39:48 2009 -0400" }, "message": "tracing: handle broken names in ftrace filter\n\nIf one filter item (for set_ftrace_filter and set_ftrace_notrace) is being\nsetup by more than 1 consecutive writes (FTRACE_ITER_CONT flag), it won\u0027t\nbe handled corretly.\n\nI used following program to test/verify:\n\n[snip]\n#include \u003cstdio.h\u003e\n#include \u003csys/types.h\u003e\n#include \u003csys/stat.h\u003e\n#include \u003cfcntl.h\u003e\n#include \u003cstring.h\u003e\n\nint main(int argc, char **argv)\n{\n int fd, i;\n char *file \u003d argv[1];\n\n if (-1 \u003d\u003d (fd \u003d open(file, O_WRONLY))) {\n perror(\"open failed\");\n return -1;\n }\n\n for(i \u003d 0; i \u003c (argc - 2); i++) {\n int len \u003d strlen(argv[2+i]);\n int cnt, off \u003d 0;\n\n while(len) {\n cnt \u003d write(fd, argv[2+i] + off, len);\n len -\u003d cnt;\n off +\u003d cnt;\n }\n }\n\n close(fd);\n return 0;\n}\n[snip]\n\nbefore change:\nsh-4.0# echo \u003e ./set_ftrace_filter\nsh-4.0# /test ./set_ftrace_filter \"sys\" \"_open \"\nsh-4.0# cat ./set_ftrace_filter\n#### all functions enabled ####\nsh-4.0#\n\nafter change:\nsh-4.0# echo \u003e ./set_ftrace_notrace\nsh-4.0# test ./set_ftrace_notrace \"sys\" \"_open \"\nsh-4.0# cat ./set_ftrace_notrace\nsys_open\nsh-4.0#\n\nSigned-off-by: Jiri Olsa \u003cjolsa@redhat.com\u003e\nLKML-Reference: \u003c20090811152904.GA26065@jolsa.lab.eng.brq.redhat.com\u003e\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "f2d84b65b9778e8a35dd904f7d3993f0a60c9756", "tree": "472a349bcc647cdf99c55f832156492478734f99", "parents": [ "df4ecf1524c7793de3121b2d4e5fc6bcc0da3bfb" ], "author": { "name": "Zhaolei", "email": "zhaolei@cn.fujitsu.com", "time": "Fri Aug 07 18:55:48 2009 +0800" }, "committer": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Tue Aug 18 02:07:04 2009 +0200" }, "message": "ftrace: Unify effect of writing to trace_options and option/*\n\n\"echo noglobal-clock \u003e trace_options\" can be used to change trace\nclock but \"echo 0 \u003e options/global-clock\" can\u0027t. The flag toggling\nwill be silently accepted without actually changing the clock callback.\n\nWe can fix it by using set_tracer_flags() in\ntrace_options_core_write().\n\nChangelog:\nv1-\u003ev2: Simplified switch() after Li Zefan \u003clizf@cn.fujitsu.com\u003e\u0027s\n suggestion\n\nSigned-off-by: Zhao Lei \u003czhaolei@cn.fujitsu.com\u003e\nCc: Steven Rostedt \u003csrostedt@redhat.com\u003e\nCc: Li Zefan \u003clizf@cn.fujitsu.com\u003e\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\n" }, { "commit": "3be04b471b95b870bd129a138463756629e86f3f", "tree": "056a6f2ecf5be83c0441ebe9357f16bc1f91cd0c", "parents": [ "2fc5f0cff4cf1c4cd336d0f61f11bca6eeee1d84" ], "author": { "name": "Li Zefan", "email": "lizf@cn.fujitsu.com", "time": "Mon Aug 17 16:54:03 2009 +0800" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Aug 17 11:25:10 2009 +0200" }, "message": "ftrace: Simplify seqfile code\n\nUse seq_release_private().\n\nSigned-off-by: Li Zefan \u003clizf@cn.fujitsu.com\u003e\nCc: Steven Rostedt \u003crostedt@goodmis.org\u003e\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Li Zefan \u003clizf@cn.fujitsu.com\u003e\nLKML-Reference: \u003c4A891AAB.8090701@cn.fujitsu.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "2fc5f0cff4cf1c4cd336d0f61f11bca6eeee1d84", "tree": "a86845315b93dbdffc2536f8089ee3169cec9113", "parents": [ "97d53202a5670a08b79c8ef2e4fff1c1ee21317c" ], "author": { "name": "Li Zefan", "email": "lizf@cn.fujitsu.com", "time": "Mon Aug 17 16:53:37 2009 +0800" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Aug 17 11:25:09 2009 +0200" }, "message": "trace_stack: Simplify seqfile code\n\nExtract duplicate code in t_start() and t_next().\n\nSigned-off-by: Li Zefan \u003clizf@cn.fujitsu.com\u003e\nCc: Steven Rostedt \u003crostedt@goodmis.org\u003e\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nLKML-Reference: \u003c4A891A91.4030602@cn.fujitsu.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "97d53202a5670a08b79c8ef2e4fff1c1ee21317c", "tree": "5ba925559a3031a833c5803d05a0a43e13ea1866", "parents": [ "ba8b3a40ba7e06d00c27508f090803af90e8dbbf" ], "author": { "name": "Li Zefan", "email": "lizf@cn.fujitsu.com", "time": "Mon Aug 17 16:52:53 2009 +0800" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Aug 17 11:25:09 2009 +0200" }, "message": "trace_stat: Fix missing entry in stat file\n\nOne entry is missing in the output of a stat file.\n\nThe cause is, when stat_seq_start() is called the 2nd time, we\nshould start from the (pos-1)th elem in the rbtree but not pos,\nbecause pos \u003d\u003d 0 is the header.\n\nSigned-off-by: Li Zefan \u003clizf@cn.fujitsu.com\u003e\nCc: Steven Rostedt \u003crostedt@goodmis.org\u003e\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nLKML-Reference: \u003c4A891A65.70009@cn.fujitsu.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "ba8b3a40ba7e06d00c27508f090803af90e8dbbf", "tree": "7805446c5a6a945dddb872a9b84c3ceee30d1583", "parents": [ "7ead8b8313d92b3a69a1a61b0dcbc4cd66c960dc" ], "author": { "name": "Li Zefan", "email": "lizf@cn.fujitsu.com", "time": "Mon Aug 17 16:55:18 2009 +0800" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Aug 17 11:25:09 2009 +0200" }, "message": "tracing/syscalls: Fix to print parameter types\n\nWhen syscall tracing was implemented as a tracer,\n\"syscall_arg_type\" trace option could be set to enable the\ndisplay of syscall parameter types.\n\nNow this option is gone since it\u0027s no longer a tracer, but the\ncode is still there but dead.\n\nSo we remove dead code and re-enable the printing of paramete\ntypes via the verbose option:\n\n # echo verbose \u003e trace_options\n # echo syscalls \u003e set_event\n # cat trace\n\t...\n bash-3331 [000] 95.348937: sys_fcntl64 -\u003e 0x1\n bash-3331 [000] 95.348942: sys_close(unsigned int fd: a)\n\t...\n\nSigned-off-by: Li Zefan \u003clizf@cn.fujitsu.com\u003e\nCc: Steven Rostedt \u003crostedt@goodmis.org\u003e\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Jason Baron \u003cjbaron@redhat.com\u003e\nLKML-Reference: \u003c4A891AF6.5050102@cn.fujitsu.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "39cbb602b543e477df71dca84b5b2e36f8bd29fc", "tree": "70639084b6a04ce428cecbaa5fa30c2d71d5ff33", "parents": [ "7cb7beb31aa3d941833b6a6e553687422c31e4b6" ], "author": { "name": "Alan D. Brunelle", "email": "alan.brunelle@hp.com", "time": "Fri Aug 07 12:01:08 2009 -0400" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Wed Aug 12 18:50:08 2009 +0200" }, "message": "Remove double removal of blktrace directory\n\ncommit fd51d251e4cdb21f68e9dbc4336514d64a105a79\nAuthor: Stefan Raspl \u003craspl@linux.vnet.ibm.com\u003e\nDate: Tue May 19 09:59:08 2009 +0200\n\n blktrace: remove debugfs entries on bad path\n\nadded in an explicit invocation of debugfs_remove for bt-\u003edir, in\nblk_remove_buf_file_callback we are also getting the directory removed. On\noccasion I am seeing memory corruption that I have bisected down to\nthis commit. [The testing involves a (long) series of I/O benchmarks\nwith blktrace invoked around the actual runs.] I believe that this\ncommitted patch is correct, but the problem actually lies in the code\nin blk_remove_buf_file_callback.\n\nWith this patch I am able to consistently get complete runs whereas\npreviously I could not get a single run to complete.\n\nThe first part of the patch simply moves the debugfs_remove below the\nrelay_close: the relay_close call will remove files under bt-\u003edir, and\nso we should not remove the directory until all the files we created\nhave been removed. (Note: This is not sufficient to fix the problem -\nthe file system code has ref counts on the directoy, so our invocation\ndoes not cause the directory to actually be removed. Nonetheless, we\nshould not rely upon that feature.)\n\nSigned-off-by: Alan D. Brunelle \u003calan.brunelle@hp.com\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "19007a67a64f9b3cbbd7024f972654ebf14daade", "tree": "a993570902eb009cf6bdbc5bccfa485ff6ec960a", "parents": [ "dc4ddb4c0b7348f1c9759ae8a9e7d734dc1cda82" ], "author": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Tue Aug 11 20:22:53 2009 +0200" }, "committer": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Tue Aug 11 20:35:30 2009 +0200" }, "message": "tracing: Support for syscall events raw records in perfcounters\n\nThis bring the support for raw syscall events in perfcounters.\nThe arguments or exit value are saved as a raw sample using\nthe PERF_SAMPLE_RAW attribute in a perf counter.\n\nExample (for now you must explicitly set the PERF_SAMPLE_RAW flag\nin perf record):\n\nperf record -e syscalls:sys_enter_open -f -F 1 -a\nperf report -D\n\n\t0x2cbb8 [0x50]: event: 9\n\t.\n\t. ... raw event: size 80 bytes\n\t. 0000: 09 00 00 00 02 00 50 00 20 e9 39 ab 0a 7f 00 00 ......P. .9....\n\t. 0010: bc 14 00 00 bc 14 00 00 01 00 00 00 00 00 00 00 ...............\n\t. 0020: 2c 00 00 00 15 01 01 00 bc 14 00 00 bc 14 00 00 ,..............\n ^ ^ ^ ^ ^ ^ ^ ..........................\n Event Size struct trace_entry\n\n\t. 0030: 00 00 00 00 46 98 43 02 00 00 00 00 80 08 00 00 ....F.C........\n ^ ^ ^ ^ ^ ^ ^ ^ ^ ^ ^ ^ ^ ^ ^ ^\n ptr to file name open flags\n\n\t. 0040: 00 00 00 00 02 00 00 00 00 00 00 00 00 00 00 00 ...............\n ^ ^ ^ ^ ^ ^ ^ ^ ^ ^ ^ ^ ^ ^ ^ ^\n\t. open mode padding\n\n\t0x2cbb8 [0x50]: PERF_EVENT_SAMPLE (IP, 2): 5308: 0x7f0aab39e920 period: 1\n\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Lai Jiangshan \u003claijs@cn.fujitsu.com\u003e\nCc: Steven Rostedt \u003crostedt@goodmis.org\u003e\nCc: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nCc: Mathieu Desnoyers \u003cmathieu.desnoyers@polymtl.ca\u003e\nCc: Jiaying Zhang \u003cjiayingz@google.com\u003e\nCc: Martin Bligh \u003cmbligh@google.com\u003e\nCc: Li Zefan \u003clizf@cn.fujitsu.com\u003e\nCc: Jason Baron \u003cjbaron@redhat.com\u003e\nCc: Masami Hiramatsu \u003cmhiramat@redhat.com\u003e\n" }, { "commit": "dc4ddb4c0b7348f1c9759ae8a9e7d734dc1cda82", "tree": "00c0df5d9b7809a0c0cf89713c55c7e04ce6c248", "parents": [ "e8f9f4d79a677f55c8ec3acbe87b33a87e2df0de" ], "author": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Tue Aug 11 19:03:54 2009 +0200" }, "committer": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Tue Aug 11 20:35:30 2009 +0200" }, "message": "tracing: Add fields format definition for syscall events\n\nDefine the format of the syscall trace fields to parse the binary\nvalues from a raw trace using the syscall events \"format\" file.\n\nThis is defined dynamically using the syscalls metadata.\nIt prepares the export of syscall event raw records to perf\ncounters.\n\nExample:\n\n$ cat /debug/tracing/events/syscalls/sys_enter_sched_getparam/format\nname: sys_enter_sched_getparam\nID: 39\nformat:\n\tfield:unsigned short common_type;\toffset:0;\tsize:2;\n\tfield:unsigned char common_flags;\toffset:2;\tsize:1;\n\tfield:unsigned char common_preempt_count;\toffset:3;\tsize:1;\n\tfield:int common_pid;\toffset:4;\tsize:4;\n\tfield:int common_tgid;\toffset:8;\tsize:4;\n\n\tfield:pid_t pid;\toffset:12;\tsize:8;\n\tfield:struct sched_param * param;\toffset:20;\tsize:8;\n\nprint fmt: \"pid: 0x%08lx, param: 0x%08lx\", ((unsigned long)(REC-\u003epid)), ((unsigned long)(REC-\u003eparam))\n\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Lai Jiangshan \u003claijs@cn.fujitsu.com\u003e\nCc: Steven Rostedt \u003crostedt@goodmis.org\u003e\nCc: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nCc: Mathieu Desnoyers \u003cmathieu.desnoyers@polymtl.ca\u003e\nCc: Jiaying Zhang \u003cjiayingz@google.com\u003e\nCc: Martin Bligh \u003cmbligh@google.com\u003e\nCc: Li Zefan \u003clizf@cn.fujitsu.com\u003e\nCc: Masami Hiramatsu \u003cmhiramat@redhat.com\u003e\nCc: Jason Baron \u003cjbaron@redhat.com\u003e\n" }, { "commit": "e8f9f4d79a677f55c8ec3acbe87b33a87e2df0de", "tree": "3b20dcf2c7b49fe23e0641805ca7aaac921bc46d", "parents": [ "0ac676fb50f5f8a22e5e80afc40bf38e31b77c00" ], "author": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Tue Aug 11 17:42:52 2009 +0200" }, "committer": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Tue Aug 11 20:35:29 2009 +0200" }, "message": "tracing: Add ftrace event call parameter to its field descriptor handler\n\nAdd the struct ftrace_event_call as a parameter of its show_format()\ncallback. This way we can use it from the syscall trace events to\nretrieve the syscall name from the ftrace event call parameter and\ndescribe its fields using the syscalls metadata.\n\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Lai Jiangshan \u003claijs@cn.fujitsu.com\u003e\nCc: Steven Rostedt \u003crostedt@goodmis.org\u003e\nCc: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nCc: Mathieu Desnoyers \u003cmathieu.desnoyers@polymtl.ca\u003e\nCc: Jiaying Zhang \u003cjiayingz@google.com\u003e\nCc: Martin Bligh \u003cmbligh@google.com\u003e\nCc: Li Zefan \u003clizf@cn.fujitsu.com\u003e\nCc: Masami Hiramatsu \u003cmhiramat@redhat.com\u003e\nCc: Jason Baron \u003cjbaron@redhat.com\u003e\n" }, { "commit": "f4b5ffccc83c82947f5d9f15d6f1b6edb1b71cd7", "tree": "06ec4a005b40ba0b6039e6c3425dd186486b8c6f", "parents": [ "64c12e0444fcc6b75eb49144ba46d43dbdc6bc8f" ], "author": { "name": "Jason Baron", "email": "jbaron@redhat.com", "time": "Mon Aug 10 16:53:02 2009 -0400" }, "committer": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Tue Aug 11 20:35:29 2009 +0200" }, "message": "tracing: Add perf counter support for syscalls tracing\n\nThe perf counter support is automated for usual trace events. But we\nhave to define specific callbacks for this to handle syscalls trace\nevents\n\nMake \u0027perf stat -e syscalls:sys_enter_blah\u0027 work with syscall style\ntracepoints.\n\nSigned-off-by: Jason Baron \u003cjbaron@redhat.com\u003e\nCc: Lai Jiangshan \u003claijs@cn.fujitsu.com\u003e\nCc: Steven Rostedt \u003crostedt@goodmis.org\u003e\nCc: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nCc: Mathieu Desnoyers \u003cmathieu.desnoyers@polymtl.ca\u003e\nCc: Jiaying Zhang \u003cjiayingz@google.com\u003e\nCc: Martin Bligh \u003cmbligh@google.com\u003e\nCc: Li Zefan \u003clizf@cn.fujitsu.com\u003e\nCc: Masami Hiramatsu \u003cmhiramat@redhat.com\u003e\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\n" }, { "commit": "64c12e0444fcc6b75eb49144ba46d43dbdc6bc8f", "tree": "8fe7b546fe787061fca8f97ed2051f40f9b16a57", "parents": [ "fb34a08c3469b2be9eae626ccb96476b4687b810" ], "author": { "name": "Jason Baron", "email": "jbaron@redhat.com", "time": "Mon Aug 10 16:52:53 2009 -0400" }, "committer": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Tue Aug 11 20:35:28 2009 +0200" }, "message": "tracing: Add individual syscalls tracepoint id support\n\nThe current state of syscalls tracepoints generates only one event id\nfor every syscall events.\n\nThis patch associates an id with each syscall trace event, so that we\ncan identify each syscall trace event using the \u0027perf\u0027 tool.\n\nSigned-off-by: Jason Baron \u003cjbaron@redhat.com\u003e\nCc: Lai Jiangshan \u003claijs@cn.fujitsu.com\u003e\nCc: Steven Rostedt \u003crostedt@goodmis.org\u003e\nCc: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nCc: Mathieu Desnoyers \u003cmathieu.desnoyers@polymtl.ca\u003e\nCc: Jiaying Zhang \u003cjiayingz@google.com\u003e\nCc: Martin Bligh \u003cmbligh@google.com\u003e\nCc: Li Zefan \u003clizf@cn.fujitsu.com\u003e\nCc: Masami Hiramatsu \u003cmhiramat@redhat.com\u003e\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\n" }, { "commit": "fb34a08c3469b2be9eae626ccb96476b4687b810", "tree": "f308cd109de2c967a1f8bd485eb9c398992a9414", "parents": [ "69fd4f0eb2ececbf8ade55e31a933e174965745e" ], "author": { "name": "Jason Baron", "email": "jbaron@redhat.com", "time": "Mon Aug 10 16:52:47 2009 -0400" }, "committer": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Tue Aug 11 20:35:28 2009 +0200" }, "message": "tracing: Add trace events for each syscall entry/exit\n\nLayer Frederic\u0027s syscall tracer on tracepoints. We create trace events\nvia hooking into the SYSCALL_DEFINE macros. This allows us to\nindividually toggle syscall entry and exit points on/off.\n\nSigned-off-by: Jason Baron \u003cjbaron@redhat.com\u003e\nCc: Lai Jiangshan \u003claijs@cn.fujitsu.com\u003e\nCc: Steven Rostedt \u003crostedt@goodmis.org\u003e\nCc: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nCc: Mathieu Desnoyers \u003cmathieu.desnoyers@polymtl.ca\u003e\nCc: Jiaying Zhang \u003cjiayingz@google.com\u003e\nCc: Martin Bligh \u003cmbligh@google.com\u003e\nCc: Li Zefan \u003clizf@cn.fujitsu.com\u003e\nCc: Masami Hiramatsu \u003cmhiramat@redhat.com\u003e\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\n" }, { "commit": "69fd4f0eb2ececbf8ade55e31a933e174965745e", "tree": "bebe7f5b88b8e2c6c240390e4e546d0c3522e79b", "parents": [ "f744bd576a827c5b02e756b81fc2578edf8179b8" ], "author": { "name": "Jason Baron", "email": "jbaron@redhat.com", "time": "Mon Aug 10 16:52:44 2009 -0400" }, "committer": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Tue Aug 11 20:35:27 2009 +0200" }, "message": "tracing: Add ftrace_event_call void * \u0027data\u0027 field\n\nadd an optional void * pointer to \u0027ftrace_event_call\u0027 that is\npassed in for regfunc and unregfunc.\n\nThis prepares for syscall tracepoints creation by passing the name of\nthe syscall we want to trace and then retrieve its number through our\narch syscall table.\n\nSigned-off-by: Jason Baron \u003cjbaron@redhat.com\u003e\nCc: Lai Jiangshan \u003claijs@cn.fujitsu.com\u003e\nCc: Steven Rostedt \u003crostedt@goodmis.org\u003e\nCc: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nCc: Mathieu Desnoyers \u003cmathieu.desnoyers@polymtl.ca\u003e\nCc: Jiaying Zhang \u003cjiayingz@google.com\u003e\nCc: Martin Bligh \u003cmbligh@google.com\u003e\nCc: Li Zefan \u003clizf@cn.fujitsu.com\u003e\nCc: Masami Hiramatsu \u003cmhiramat@redhat.com\u003e\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\n" }, { "commit": "f744bd576a827c5b02e756b81fc2578edf8179b8", "tree": "d2e1242d87953476ee6cacb7e34e0f791b641c02", "parents": [ "9daa77e2e9a6b8b859660d5e24d0f8cd77c2af39" ], "author": { "name": "Jason Baron", "email": "jbaron@redhat.com", "time": "Mon Aug 10 16:52:39 2009 -0400" }, "committer": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Tue Aug 11 20:35:27 2009 +0200" }, "message": "tracing: Raw_init() bailout in trace event register fail case\n\nAllow the return value of raw_init() trace event callback to bail us out\nof creating a trace event file, in case we fail to register our\nevent.\n\nAlso, we plan to return -ENOSYS for syscall events that don\u0027t match any\nsyscalls listed in our arch tracing syscall table, we don\u0027t want to warn\nin that case, we just want this event to be invisible in debugfs and\nignored.\n\nSigned-off-by: Jason Baron \u003cjbaron@redhat.com\u003e\nCc: Lai Jiangshan \u003claijs@cn.fujitsu.com\u003e\nCc: Steven Rostedt \u003crostedt@goodmis.org\u003e\nCc: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nCc: Mathieu Desnoyers \u003cmathieu.desnoyers@polymtl.ca\u003e\nCc: Jiaying Zhang \u003cjiayingz@google.com\u003e\nCc: Martin Bligh \u003cmbligh@google.com\u003e\nCc: Li Zefan \u003clizf@cn.fujitsu.com\u003e\nCc: Masami Hiramatsu \u003cmhiramat@redhat.com\u003e\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\n" }, { "commit": "066e0378c23f0a3db730893f6a041e4a3922a385", "tree": "be402805c83dfc6547d4eb1e8b4129dcec1d9831", "parents": [ "eeac19a7efa150231e4a6bb110d6f27500bcc8ce" ], "author": { "name": "Jason Baron", "email": "jbaron@redhat.com", "time": "Mon Aug 10 16:52:23 2009 -0400" }, "committer": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Tue Aug 11 20:35:26 2009 +0200" }, "message": "tracing: Call arch_init_ftrace_syscalls at boot\n\nCall arch_init_ftrace_syscalls at boot, so we can determine early the\nset of syscalls for the syscall trace events.\n\nSigned-off-by: Jason Baron \u003cjbaron@redhat.com\u003e\nCc: Lai Jiangshan \u003claijs@cn.fujitsu.com\u003e\nCc: Steven Rostedt \u003crostedt@goodmis.org\u003e\nCc: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nCc: Mathieu Desnoyers \u003cmathieu.desnoyers@polymtl.ca\u003e\nCc: Jiaying Zhang \u003cjiayingz@google.com\u003e\nCc: Martin Bligh \u003cmbligh@google.com\u003e\nCc: Li Zefan \u003clizf@cn.fujitsu.com\u003e\nCc: Masami Hiramatsu \u003cmhiramat@redhat.com\u003e\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\n" }, { "commit": "7770841e63730d62928b0879498064e9614b2ce0", "tree": "6bc12618ec2cdbc6e5294e6b967652eaf7c3c9d6", "parents": [ "89034bc2c7b839702c00a704e79d112737f98be0" ], "author": { "name": "Zhaolei", "email": "zhaolei@cn.fujitsu.com", "time": "Fri Aug 07 18:53:21 2009 +0800" }, "committer": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Tue Aug 11 20:35:25 2009 +0200" }, "message": "tracing: Rename set_tracer_flags()\u0027s local variable trace_flags\n\nset_tracer_flags() have a local variable named trace_flags which has\nthe same name than a global one in the same scope.\nThis leads to confusion, using tracer_flags should be better by its\nmeaning.\n\nChangelog:\nv1-\u003ev2: Simplified another patch in this patchset, no change in this\n patch.\n\nSigned-off-by: Zhao Lei \u003czhaolei@cn.fujitsu.com\u003e\nCc: Steven Rostedt \u003crostedt@goodmis.org\u003e\nCc: Li Zefan \u003clizf@cn.fujitsu.com\u003e\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\n" }, { "commit": "89034bc2c7b839702c00a704e79d112737f98be0", "tree": "e65b1f3d4c751baa840efc81bc4734f089379eb3", "parents": [ "fb82ad719831db58e9baa4c67015aae3fe27e7e3", "85dfd81dc57e8183a277ddd7a56aa65c96f3f487" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Tue Aug 11 14:19:09 2009 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Tue Aug 11 14:19:09 2009 +0200" }, "message": "Merge branch \u0027linus\u0027 into tracing/core\n\nConflicts:\n\tkernel/trace/trace_events_filter.c\n\nWe use the tracing/core version.\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "f413cdb80ce00ec1a4d0ab949b5d96c81cae7f75", "tree": "08a9621cb1318f73a37faeed14c4e728408551ad", "parents": [ "3a6593050fbd8bbcaed3a44d01c31d907315c86c" ], "author": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Fri Aug 07 01:25:54 2009 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Sun Aug 09 12:53:48 2009 +0200" }, "message": "perf_counter: Fix/complete ftrace event records sampling\n\nThis patch implements the kernel side support for ftrace event\nrecord sampling.\n\nA new counter sampling attribute is added:\n\n PERF_SAMPLE_TP_RECORD\n\nwhich requests ftrace events record sampling. In this case\nif a PERF_TYPE_TRACEPOINT counter is active and a tracepoint\nfires, we emit the tracepoint binary record to the\nperfcounter event buffer, as a sample.\n\nResult, after setting PERF_SAMPLE_TP_RECORD attribute from perf\nrecord:\n\n perf record -f -F 1 -a -e workqueue:workqueue_execution\n perf report -D\n\n 0x21e18 [0x48]: event: 9\n .\n . ... raw event: size 72 bytes\n . 0000: 09 00 00 00 01 00 48 00 d0 c7 00 81 ff ff ff ff ......H........\n . 0010: 0a 00 00 00 0a 00 00 00 21 00 00 00 00 00 00 00 ........!......\n . 0020: 2b 00 01 02 0a 00 00 00 0a 00 00 00 65 76 65 6e +...........eve\n . 0030: 74 73 2f 31 00 00 00 00 00 00 00 00 0a 00 00 00 ts/1...........\n . 0040: e0 b1 31 81 ff ff ff ff .......\n.\n0x21e18 [0x48]: PERF_EVENT_SAMPLE (IP, 1): 10: 0xffffffff8100c7d0 period: 33\n\nThe raw ftrace binary record starts at offset 0020.\n\nTranslation:\n\n struct trace_entry {\n\ttype\t\t\u003d 0x2b \u003d 43;\n\tflags\t\t\u003d 1;\n\tpreempt_count\t\u003d 2;\n\tpid\t\t\u003d 0xa \u003d 10;\n\ttgid\t\t\u003d 0xa \u003d 10;\n }\n\n thread_comm \u003d \"events/1\"\n thread_pid \u003d 0xa \u003d 10;\n func\t \u003d 0xffffffff8131b1e0 \u003d flush_to_ldisc()\n\nWhat will come next?\n\n - Userspace support (\u0027perf trace\u0027), \u0027flight data recorder\u0027 mode\n for perf trace, etc.\n\n - The unconditional copy from the profiling callback brings\n some costs however if someone wants no such sampling to\n occur, and needs to be fixed in the future. For that we need\n to have an instant access to the perf counter attribute.\n This is a matter of a flag to add in the struct ftrace_event.\n\n - Take care of the events recursivity! Don\u0027t ever try to record\n a lock event for example, it seems some locking is used in\n the profiling fast path and lead to a tracing recursivity.\n That will be fixed using raw spinlock or recursivity\n protection.\n\n - [...]\n\n - Profit! :-)\n\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Li Zefan \u003clizf@cn.fujitsu.com\u003e\nCc: Tom Zanussi \u003ctzanussi@gmail.com\u003e\nCc: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: Mike Galbraith \u003cefault@gmx.de\u003e\nCc: Steven Rostedt \u003crostedt@goodmis.org\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Pekka Enberg \u003cpenberg@cs.helsinki.fi\u003e\nCc: Gabriel Munteanu \u003ceduard.munteanu@linux360.ro\u003e\nCc: Lai Jiangshan \u003claijs@cn.fujitsu.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "e3560336be655c6791316482fe288b119f34c427", "tree": "43ca9a6b489aaa3918b773f78a7eda37458ef0a8", "parents": [ "26528e773ecc74fb1b61b7275f86f761cbb340ec", "7b2aa037e878c939676675969983284a02958ae3" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Sun Aug 09 12:46:45 2009 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Sun Aug 09 12:46:49 2009 +0200" }, "message": "Merge branch \u0027linus\u0027 into tracing/urgent\n\nMerge reason: Merge up to almost-rc6 to pick up latest perfcounters\n (on which we\u0027ll queue up a dependent fix)\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "fb82ad719831db58e9baa4c67015aae3fe27e7e3", "tree": "61009acdbd934e75c8328d1af6314e10ade6ffaf", "parents": [ "a2ca5e03b6a5a1d401062f0a7f78888cf9e5e3b0" ], "author": { "name": "Tom Zanussi", "email": "tzanussi@gmail.com", "time": "Sat Aug 08 10:49:36 2009 -0500" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Sat Aug 08 17:58:07 2009 +0200" }, "message": "tracing/filters: Don\u0027t use pred on alloc failure\n\nDan Carpenter sent me a fix to prevent pred from being used if\nit couldn\u0027t be allocated. This updates his patch for the same\nproblem in the tracing tree (which has changed this code quite\nsubstantially).\n\nReported-by: Dan Carpenter \u003cerror27@gmail.com\u003e\nSigned-off-by: Tom Zanussi \u003ctzanussi@gmail.com\u003e\nCc: Steven Rostedt \u003crostedt@goodmis.org\u003e\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Li Zefan \u003clizf@cn.fujitsu.com\u003e\nLKML-Reference: \u003c1249746576.6453.30.camel@tropicana\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nThe original report:\n\ncreate_logical_pred() could sometimes return NULL.\n\nIt\u0027s a static checker complaining rather than problems at runtime...\n" }, { "commit": "26528e773ecc74fb1b61b7275f86f761cbb340ec", "tree": "e3892e1c58783cc022517dab31b1e18179cb930b", "parents": [ "96b2de313b1e0e02aea80ee47df6a2b5cbdf8e13" ], "author": { "name": "Tom Zanussi", "email": "tzanussi@gmail.com", "time": "Sat Aug 08 10:49:53 2009 -0500" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Sat Aug 08 17:56:13 2009 +0200" }, "message": "tracing/filters: Always free pred on filter_add_subsystem_pred() failure\n\nIf filter_add_subsystem_pred() fails due to ENOSPC or ENOMEM,\nthe pred doesn\u0027t get freed, while as a side effect it does for\nother errors. Make it so the caller always frees the pred for\nany error.\n\nSigned-off-by: Tom Zanussi \u003ctzanussi@gmail.com\u003e\nCc: Steven Rostedt \u003crostedt@goodmis.org\u003e\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Li Zefan \u003clizf@cn.fujitsu.com\u003e\nLKML-Reference: \u003c1249746593.6453.32.camel@tropicana\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "96b2de313b1e0e02aea80ee47df6a2b5cbdf8e13", "tree": "f6d1a22d6ab587d346f642fe89db9d75401da57b", "parents": [ "bd3f02212d6a457267e0c9c02c426151c436d9d4" ], "author": { "name": "Tom Zanussi", "email": "tzanussi@gmail.com", "time": "Sat Aug 08 10:49:09 2009 -0500" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Sat Aug 08 17:55:34 2009 +0200" }, "message": "tracing/filters: Don\u0027t use pred on alloc failure\n\nDan Carpenter sent me a fix to prevent pred from being used if\nit couldn\u0027t be allocated. I noticed the same problem also\nexisted for the create_pred() case and added a fix for that.\n\nReported-by: Dan Carpenter \u003cerror27@gmail.com\u003e\nSigned-off-by: Tom Zanussi \u003ctzanussi@gmail.com\u003e\nCc: Steven Rostedt \u003crostedt@goodmis.org\u003e\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Li Zefan \u003clizf@cn.fujitsu.com\u003e\nLKML-Reference: \u003c1249746549.6453.29.camel@tropicana\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "bd3f02212d6a457267e0c9c02c426151c436d9d4", "tree": "eb96e54b958c0d8202e2a3c65ada5399c387f9c0", "parents": [ "7dbdee2e9a2ac42ea5135801bcc9d1a8e3f672aa" ], "author": { "name": "Eric Dumazet", "email": "eric.dumazet@gmail.com", "time": "Fri Aug 07 12:49:29 2009 +0200" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Fri Aug 07 12:46:39 2009 -0400" }, "message": "ring-buffer: Fix memleak in ring_buffer_free()\n\nI noticed oprofile memleaked in linux-2.6 current tree,\nand tracked this ring-buffer leak.\n\nSigned-off-by: Eric Dumazet \u003ceric.dumazet@gmail.com\u003e\nLKML-Reference: \u003c4A7C06B9.2090302@gmail.com\u003e\nCc: stable@kernel.org\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "469535a598f28c13a2a42037e1b778f671af1d16", "tree": "907a3434e87bdab3f37f3c965a230af7af9bdb30", "parents": [ "3f6e968ef4e1d8d93d8a8505461b0e50a9e97ad8" ], "author": { "name": "Robert Richter", "email": "robert.richter@amd.com", "time": "Thu Jul 30 19:19:18 2009 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Thu Aug 06 14:20:25 2009 +0200" }, "message": "ring-buffer: Fix advance of reader in rb_buffer_peek()\n\nWhen calling rb_buffer_peek() from ring_buffer_consume() and a\npadding event is returned, the function rb_advance_reader() is\ncalled twice. This may lead to missing samples or under high\nworkloads to the warning below. This patch fixes this. If a padding\nevent is returned by rb_buffer_peek() it will be consumed by the\ncalling function now.\n\nAlso, I simplified some code in ring_buffer_consume().\n\n------------[ cut here ]------------\nWARNING: at /dev/shm/.source/linux/kernel/trace/ring_buffer.c:2289 rb_advance_reader+0x2e/0xc5()\nHardware name: Anaheim\nModules linked in:\nPid: 29, comm: events/2 Tainted: G W 2.6.31-rc3-oprofile-x86_64-standard-00059-g5050dc2 #1\nCall Trace:\n[\u003cffffffff8106776f\u003e] ? rb_advance_reader+0x2e/0xc5\n[\u003cffffffff81039ffe\u003e] warn_slowpath_common+0x77/0x8f\n[\u003cffffffff8103a025\u003e] warn_slowpath_null+0xf/0x11\n[\u003cffffffff8106776f\u003e] rb_advance_reader+0x2e/0xc5\n[\u003cffffffff81068bda\u003e] ring_buffer_consume+0xa0/0xd2\n[\u003cffffffff81326933\u003e] op_cpu_buffer_read_entry+0x21/0x9e\n[\u003cffffffff810be3af\u003e] ? __find_get_block+0x4b/0x165\n[\u003cffffffff8132749b\u003e] sync_buffer+0xa5/0x401\n[\u003cffffffff810be3af\u003e] ? __find_get_block+0x4b/0x165\n[\u003cffffffff81326c1b\u003e] ? wq_sync_buffer+0x0/0x78\n[\u003cffffffff81326c76\u003e] wq_sync_buffer+0x5b/0x78\n[\u003cffffffff8104aa30\u003e] worker_thread+0x113/0x1ac\n[\u003cffffffff8104dd95\u003e] ? autoremove_wake_function+0x0/0x38\n[\u003cffffffff8104a91d\u003e] ? worker_thread+0x0/0x1ac\n[\u003cffffffff8104dc9a\u003e] kthread+0x88/0x92\n[\u003cffffffff8100bdba\u003e] child_rip+0xa/0x20\n[\u003cffffffff8104dc12\u003e] ? kthread+0x0/0x92\n[\u003cffffffff8100bdb0\u003e] ? child_rip+0x0/0x20\n---[ end trace f561c0a58fcc89bd ]---\n\nCc: Steven Rostedt \u003crostedt@goodmis.org\u003e\nCc: \u003cstable@kernel.org\u003e\nSigned-off-by: Robert Richter \u003crobert.richter@amd.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "a2ca5e03b6a5a1d401062f0a7f78888cf9e5e3b0", "tree": "b3c35ebab71bf1d944acfed671d2a02cf5304017", "parents": [ "1a0799a8fef5acc6503f9c5e79b2cd003317826c" ], "author": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Thu Aug 06 07:32:21 2009 +0200" }, "committer": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Thu Aug 06 07:32:21 2009 +0200" }, "message": "tracing/events: Only define remove_subsystem_dir() if CONFIG_MODULES\n\nIf we disable modules, we get the following warning in ftrace events\nfile:\n\nkernel/trace/trace_events.c:912: attention : ‘remove_subsystem_dir’ defined but not used\n\nremove_subystem_dir() is useless if !CONFIG_MODULES, then move it to\nthe appropriate #ifdef section of trace_events.c\n\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "1a0799a8fef5acc6503f9c5e79b2cd003317826c", "tree": "8aec6e623981cd8505de53752234d9f6b5d94843", "parents": [ "82e04af498a85ba425efe77580b7ba08234411df" ], "author": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Wed Jul 29 18:59:58 2009 +0200" }, "committer": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Thu Aug 06 07:28:06 2009 +0200" }, "message": "tracing/function-graph-tracer: Move graph event insertion helpers in the graph tracer file\n\nThe function graph events helpers which insert the function entry and\nreturn events into the ring buffer currently reside in trace.c\nBut this file is quite overloaded and the right place for these helpers\nis in the function graph tracer file.\n\nThen move them to trace_functions_graph.c\n\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "82e04af498a85ba425efe77580b7ba08234411df", "tree": "3683fb5e68cd96b518eb72d76b608205613feb24", "parents": [ "c0a0d0d3f65284c71115a9bb1ed801ee33eeb552" ], "author": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Wed Jul 29 18:00:29 2009 +0200" }, "committer": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Thu Aug 06 07:28:06 2009 +0200" }, "message": "tracing: Move sched event insertion helpers in the sched switch tracer file\n\nThe sched events helpers which insert the sched switch and wakeup\nevents into the ring buffer currently reside in trace.c\nBut this file is quite overloaded and the right place for these helpers\nis in the sched switch tracer file.\n\nThen move them to trace_functions.c\n\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "c0a0d0d3f65284c71115a9bb1ed801ee33eeb552", "tree": "ac4c74e18c73f368abc8721f8f04c9101069fcaf", "parents": [ "5e5bf483986ad86ad25f25eec5299c86eb2d1c57" ], "author": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Wed Jul 29 17:51:13 2009 +0200" }, "committer": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Thu Aug 06 07:28:05 2009 +0200" }, "message": "tracing/core: Make the stack entry helpers global\n\nMake the stacktrace event insertion helpers globals.\nThis has two effects:\n\n- Prepare for moving the sched events insertion helpers to\n the sched switch tracer file.\n- Move some ifdef outside function definitions\n\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "5e5bf483986ad86ad25f25eec5299c86eb2d1c57", "tree": "51ca52240afe82bab1366b1677d9f8a55bbee6fb", "parents": [ "07868b086cca784f4b532fc2ab574ec3a73b468a" ], "author": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Wed Jul 29 17:11:12 2009 +0200" }, "committer": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Thu Aug 06 07:28:05 2009 +0200" }, "message": "tracing/core: Turn ftrace_cpu_disabled into a global var\n\nIn order to prepare the moving of the function graph tracer insertion\nhelpers from trace.c to trace_functions_graph.c, we need to export the\nftrace_cpu_disabled variable.\n\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "0c9e6f639aed490202bbc79214f4495cf4bfde58", "tree": "0df6f05086a033ec49995fe1cd3fde5474446cdb", "parents": [ "1f9963cbb0280e0cd554161e00f1a0eeddbf1ae1" ], "author": { "name": "Lai Jiangshan", "email": "laijs@cn.fujitsu.com", "time": "Tue Jul 28 20:26:06 2009 +0800" }, "committer": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Thu Aug 06 07:28:04 2009 +0200" }, "message": "tracing: Simplify print_graph_cpu()\n\nprint_graph_cpu() is little over-designed.\n\nAnd \"log10_all\" may be wrong when there are holes in cpu_online_mask:\nthe max online cpu id \u003e cpumask_weight(cpu_online_mask)\n\nSo change it by using a static column length for the cpu matching\nnr_cpu_ids number of decimal characters.\n\nSigned-off-by: Lai Jiangshan \u003claijs@cn.fujitsu.com\u003e\nCc: Steven Rostedt \u003crostedt@goodmis.org\u003e\nLKML-Reference: \u003c4A6EEE5E.2000001@cn.fujitsu.com\u003e\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\n" }, { "commit": "af6af30c0fcd77e621638e53ef8b176bca8bd3b4", "tree": "fde3faf7cc117e208dd033eee707dbd9de5f912e", "parents": [ "386c0b702b1ea81c0f54f5c9832a3d4a52270f14" ], "author": { "name": "Peter Zijlstra", "email": "peterz@infradead.org", "time": "Wed Aug 05 20:41:04 2009 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Thu Aug 06 06:26:09 2009 +0200" }, "message": "ftrace: Fix perf-tracepoint OOPS\n\nNot all tracepoints are created equal, in specific the ftrace\ntracepoints are created with TRACE_EVENT_FORMAT() which does\nnot generate the needed bits to tie them into perf counters.\n\nFor those events, don\u0027t create the \u0027id\u0027 file and fail\n-\u003eprofile_enable when their ID is specified through other\nmeans.\n\nReported-by: Chris Mason \u003cchris.mason@oracle.com\u003e\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: Steven Rostedt \u003crostedt@goodmis.org\u003e\nLKML-Reference: \u003c1249497664.5890.4.camel@laptop\u003e\n[ v2: fix build error in the !CONFIG_EVENT_PROFILE case ]\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "464e85eb0e63096bd52e4c3e2a6fb8357fb95828", "tree": "838010839e0b7b3e3a403d381f2b56dd065da3d0", "parents": [ "0f2541d299d233eddddee4345795e0c46264fd56" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Wed Aug 05 15:26:37 2009 -0400" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Wed Aug 05 20:20:00 2009 -0400" }, "message": "ring-buffer: do not disable ring buffer on oops_in_progress\n\nThe commit:\n\n commit e0fdace10e75dac67d906213b780ff1b1a4cc360\n Author: David Miller \u003cdavem@davemloft.net\u003e\n Date: Fri Aug 1 01:11:22 2008 -0700\n\n debug_locks: set oops_in_progress if we will log messages.\n\n Otherwise lock debugging messages on runqueue locks can deadlock the\n system due to the wakeups performed by printk().\n\n Signed-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n Signed-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n\nWill permanently set oops_in_progress on any lockdep failure.\nWhen this triggers it will cause any read from the ring buffer to\npermanently disable the ring buffer (not to mention no locking of\nprintk).\n\nThis patch removes the check. It keeps the print in NMI which makes\nsense. This is probably OK, since the ring buffer should not cause\nsomething to set oops_in_progress anyway.\n\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "0f2541d299d233eddddee4345795e0c46264fd56", "tree": "19a1628703792d1e0ae8abe18c240d60a6e1705d", "parents": [ "e16852cfc5580b88cb327413ab8c89375f380592" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Wed Aug 05 12:02:48 2009 -0400" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Wed Aug 05 20:19:59 2009 -0400" }, "message": "ring-buffer: fix check of try_to_discard result\n\nThe function ring_buffer_discard_commit inversed the code path\nof the result of try_to_discard. It should skip incrementing the\nentry counter if try_to_discard succeeded. But instead, it increments\nthe entry conder if it succeeded to discard, and does not increment\nit if it fails.\n\nThe result of this bug is that filtering will make the stat counters\nincorrect.\n\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "e16852cfc5580b88cb327413ab8c89375f380592", "tree": "67e7d5b84e2602986f2da689625e5a25d7af7bb4", "parents": [ "bdff78707f3ce47e891f3201c9666122a70556ce", "74e7ff8c50b6b022e6ffaa736b16a4dc161d3eaf" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Tue Aug 04 13:58:28 2009 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Tue Aug 04 13:58:28 2009 +0200" }, "message": "Merge branch \u0027tracing/fixes\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/frederic/random-tracing into tracing/urgent\n" }, { "commit": "74e7ff8c50b6b022e6ffaa736b16a4dc161d3eaf", "tree": "5bbe7b9f239f1e7b0a688b521f5dca8b9ea99ef4", "parents": [ "38ceb592fcac9110c6b3c87ea0a27bff68c43486" ], "author": { "name": "Lai Jiangshan", "email": "laijs@cn.fujitsu.com", "time": "Tue Jul 28 20:17:22 2009 +0800" }, "committer": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Tue Jul 28 23:17:23 2009 +0200" }, "message": "tracing: Fix missing function_graph events when we splice_read from trace_pipe\n\nAbout a half events are missing when we splice_read\nfrom trace_pipe. They are unexpectedly consumed because we ignore\nthe TRACE_TYPE_NO_CONSUME return value used by the function graph\ntracer when it needs to consume the events by itself to walk on\nthe ring buffer.\n\nThe same problem appears with ftrace_dump()\n\nExample of an output before this patch:\n\n1) | ktime_get_real() {\n1) 2.846 us | read_hpet();\n1) 4.558 us | }\n1) 6.195 us | }\n\nAfter this patch:\n\n0) | ktime_get_real() {\n0) | getnstimeofday() {\n0) 1.960 us | read_hpet();\n0) 3.597 us | }\n0) 5.196 us | }\n\nThe fix also applies on 2.6.30\n\nSigned-off-by: Lai Jiangshan \u003claijs@cn.fujitsu.com\u003e\nCc: Steven Rostedt \u003crostedt@goodmis.org\u003e\nCc: stable@kernel.org\nLKML-Reference: \u003c4A6EEC52.90704@cn.fujitsu.com\u003e\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\n" }, { "commit": "38ceb592fcac9110c6b3c87ea0a27bff68c43486", "tree": "6051e8914161679905245a77077ab8f61dbbf64b", "parents": [ "4733fd328f14280900435d9dbae1487d110a4d56" ], "author": { "name": "Lai Jiangshan", "email": "laijs@cn.fujitsu.com", "time": "Tue Jul 28 20:11:24 2009 +0800" }, "committer": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Tue Jul 28 23:17:23 2009 +0200" }, "message": "tracing: Fix invalid function_graph entry\n\nWhen print_graph_entry() computes a function call entry event, it needs\nto also check the next entry to guess if it matches the return event of\nthe current function entry.\nIn order to look at this next event, it needs to consume the current\nentry before going ahead in the ring buffer.\n\nHowever, if the current event that gets consumed is the last one in the\nring buffer head page, the ring_buffer may reuse the page for writers.\nThe consumed entry will then become invalid because of possible\nracy overwriting.\n\nMe must then handle this entry by making a copy of it.\n\nThe fix also applies on 2.6.30\n\nSigned-off-by: Lai Jiangshan \u003claijs@cn.fujitsu.com\u003e\nCc: Steven Rostedt \u003crostedt@goodmis.org\u003e\nCc: stable@kernel.org\nLKML-Reference: \u003c4A6EEAEC.3050508@cn.fujitsu.com\u003e\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\n" }, { "commit": "8650ae32ef7045e763825dee6256dde7f331bb85", "tree": "546a07e4c5b6fc731b48604769392a671c1fb18e", "parents": [ "4c739ff043e5787d97c9691d62cabf7a29e75a9d" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Wed Jul 22 23:29:30 2009 -0400" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Thu Jul 23 10:07:18 2009 -0400" }, "message": "tracing: only truncate ftrace files when O_TRUNC is set\n\nThe current code will truncate the ftrace files contents if O_APPEND\nis not set and the file is opened in write mode. This is incorrect.\nIt should only truncate the file if O_TRUNC is set. Otherwise\nif one of these files is opened by a C program with fopen \"r+\",\nit will incorrectly truncate the file.\n\nReported-by: Jiri Olsa \u003cjolsa@redhat.com\u003e\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "4c739ff043e5787d97c9691d62cabf7a29e75a9d", "tree": "d2604b88d526a4ac4b216d5d46d2834ac8171782", "parents": [ "636eacee3b0c76915151db37203cc624becb6d7b" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Wed Jul 22 23:11:03 2009 -0400" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Thu Jul 23 10:07:17 2009 -0400" }, "message": "tracing: show proper address for trace-printk format\n\nSince the trace_printk may use pointers to the format fields\nin the buffer, they are exported via debugfs/tracing/printk_formats.\nThis is used by utilities that read the ring buffer in binary format.\nIt helps the utilities map the address of the format in the binary\nbuffer to what the printf format looks like.\n\nUnfortunately, the way the output code works, it exports the address\nof the pointer to the format address, and not the format address\nitself. This makes the file totally useless in trying to figure\nout what format string a binary address belongs to.\n\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "636eacee3b0c76915151db37203cc624becb6d7b", "tree": "99251e7d38d22b3f5b3808d797757840a597349b", "parents": [ "87827111a5538633b18e5c641ced673c4c2bb6ce" ], "author": { "name": "Li Zefan", "email": "lizf@cn.fujitsu.com", "time": "Thu Jul 23 11:29:47 2009 +0800" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Thu Jul 23 09:53:55 2009 -0400" }, "message": "tracing/stat: Fix seqfile memory leak\n\nEvery time we cat a trace_stat file, we leak memory allocated by\nseq_open().\n\nAlso fix memory leak in a failure path in tracing_stat_open().\n\nSigned-off-by: Li Zefan \u003clizf@cn.fujitsu.com\u003e\nLKML-Reference: \u003c4A67D92B.4060704@cn.fujitsu.com\u003e\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "87827111a5538633b18e5c641ced673c4c2bb6ce", "tree": "46249db51a7f94e31948f48b07efbbbc5de3e7c3", "parents": [ "d8cc1ab793993c886c62abf77c93287df33ffd8b" ], "author": { "name": "Li Zefan", "email": "lizf@cn.fujitsu.com", "time": "Thu Jul 23 11:29:11 2009 +0800" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Thu Jul 23 09:53:23 2009 -0400" }, "message": "function-graph: Fix seqfile memory leak\n\nEvery time we cat set_graph_function, we leak memory allocated\nby seq_open().\n\nSigned-off-by: Li Zefan \u003clizf@cn.fujitsu.com\u003e\nLKML-Reference: \u003c4A67D907.2010500@cn.fujitsu.com\u003e\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "d8cc1ab793993c886c62abf77c93287df33ffd8b", "tree": "1e941a2832791b69ab9870c9ad9e9e844af50e1c", "parents": [ "e5d490b252423605a77c54b2e35b10ea663763df" ], "author": { "name": "Li Zefan", "email": "lizf@cn.fujitsu.com", "time": "Thu Jul 23 11:28:40 2009 +0800" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Thu Jul 23 09:52:09 2009 -0400" }, "message": "trace_stack: Fix seqfile memory leak\n\nEvery time we cat stack_trace, we leak memory allocated by seq_open().\n\nSigned-off-by: Li Zefan \u003clizf@cn.fujitsu.com\u003e\nLKML-Reference: \u003c4A67D8E8.3020500@cn.fujitsu.com\u003e\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "1f9963cbb0280e0cd554161e00f1a0eeddbf1ae1", "tree": "80e27aa2cf5401fc04f7dbb806ad7e0ec04b6e8c", "parents": [ "ff4e9da2330beb8d64498a513d3f9694e941b01a" ], "author": { "name": "Li Zefan", "email": "lizf@cn.fujitsu.com", "time": "Mon Jul 20 10:20:53 2009 +0800" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Mon Jul 20 13:29:19 2009 -0400" }, "message": "tracing/filters: improve subsystem filter\n\nCurrently a subsystem filter should be applicable to all events\nunder the subsystem, and if it failed, all the event filters\nwill be cleared. Those behaviors make subsys filter much less\nuseful:\n\n # echo \u0027vec \u003d\u003d 1\u0027 \u003e irq/softirq_entry/filter\n # echo \u0027irq \u003d\u003d 5\u0027 \u003e irq/filter\n bash: echo: write error: Invalid argument\n # cat irq/softirq_entry/filter\n none\n\nI\u0027d expect it set the filter for irq_handler_entry/exit, and\nnot touch softirq_entry/exit.\n\nThe basic idea is, try to see if the filter can be applied\nto which events, and then just apply to the those events:\n\n # echo \u0027vec \u003d\u003d 1\u0027 \u003e softirq_entry/filter\n # echo \u0027irq \u003d\u003d 5\u0027 \u003e filter\n # cat irq_handler_entry/filter\n irq \u003d\u003d 5\n # cat softirq_entry/filter\n vec \u003d\u003d 1\n\nChangelog for v2:\n- do some cleanups to address Frederic\u0027s comments.\n\nInspired-by: Steven Rostedt \u003csrostedt@redhat.com\u003e\nSigned-off-by: Li Zefan \u003clizf@cn.fujitsu.com\u003e\nAcked-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nLKML-Reference: \u003c4A63D485.7030703@cn.fujitsu.com\u003e\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "ff4e9da2330beb8d64498a513d3f9694e941b01a", "tree": "c45a1d50d1f9a015af9497afe8f17b6025200efd", "parents": [ "7d536cb3fb9993bdcd5a2fbaa6b0670ded4e101c" ], "author": { "name": "Xiao Guangrong", "email": "xiaoguangrong@cn.fujitsu.com", "time": "Mon Jun 22 10:33:07 2009 +0800" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Mon Jul 20 12:02:09 2009 -0400" }, "message": "tracing: cleanup for tracing_trace_options_read()\n\n\u0027\\n\u0027 is already appended, and what we need is just an extra\nspace for the \u0027\\0\u0027.\n\nSigned-off-by: Xiao Guangrong \u003cxiaoguangrong@cn.fujitsu.com\u003e\nLKML-Reference: \u003c4A3EED63.3090908@cn.fujitsu.com\u003e\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "7d536cb3fb9993bdcd5a2fbaa6b0670ded4e101c", "tree": "63c4a6ec6de75d9a2db7d677c768a5f2953fa237", "parents": [ "68fd60a8c8bca6af51805c45f286f0f2572ac977" ], "author": { "name": "Li Zefan", "email": "lizf@cn.fujitsu.com", "time": "Thu Jul 16 10:54:02 2009 +0800" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Mon Jul 20 11:38:44 2009 -0400" }, "message": "tracing/events: record the size of dynamic arrays\n\nWhen a dynamic array is defined, we add __data_loc_foo in\ntrace_entry to record the offset of the array, but the\nsize of the array is not recorded, which causes 2 problems:\n\n- the event filter just compares the first 2 chars of the strings.\n\n- parsers can\u0027t parse dynamic arrays.\n\nSo we encode the size of each dynamic array in the higher 16 bits\nof __data_loc_foo, while the offset is in lower 16 bits.\n\nSigned-off-by: Li Zefan \u003clizf@cn.fujitsu.com\u003e\nLKML-Reference: \u003c4A5E964A.9000403@cn.fujitsu.com\u003e\nAcked-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "566b0aaf798a0dddfc455d1a5b05c424c6686c65", "tree": "ce8e8bfb62986ba4e5ba1b1d7d729c83aeb74387", "parents": [ "45bceffc3013bda7d2ebc7802e9b153b674e2d44" ], "author": { "name": "jolsa@redhat.com", "email": "jolsa@redhat.com", "time": "Thu Jul 16 21:44:26 2009 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Sat Jul 18 12:21:16 2009 +0200" }, "message": "tracing: Remove unused fields/variables\n\nSigned-off-by: Jiri Olsa \u003cjolsa@redhat.com\u003e\nCc: rostedt@goodmis.org\nLKML-Reference: \u003c1247773468-11594-2-git-send-email-jolsa@redhat.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "45bceffc3013bda7d2ebc7802e9b153b674e2d44", "tree": "222d7dd8fd300925cbf12cdc0fba5bee2528997e", "parents": [ "6f2f3cf00ee32f75ba007a46bab88a54d68a5deb", "78af08d90b8f745044b1274430bc4bc6b2b27aca" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Sat Jul 18 12:19:57 2009 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Sat Jul 18 12:20:01 2009 +0200" }, "message": "Merge branch \u0027linus\u0027 into tracing/core\n\nMerge reason: tracing/core was on an older, pre-rc1 base.\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "6f2f3cf00ee32f75ba007a46bab88a54d68a5deb", "tree": "89aaab40d502c84e135b7e9e72b20bb7d498bc8c", "parents": [ "79173bf556417a737e9d2e096e0788452ec30a61" ], "author": { "name": "Xiao Guangrong", "email": "xiaoguangrong@cn.fujitsu.com", "time": "Thu Jul 16 14:21:08 2009 +0800" }, "committer": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Fri Jul 17 01:45:51 2009 -0400" }, "message": "tracing/function: Cleanup for function tracer\n\nWe can directly use %pf input format instead of kallsyms_lookup()\nand %s input format\n\nSigned-off-by: Xiao Guangrong \u003cxiaoguangrong@cn.fujitsu.com\u003e\nReviewed-by: Li Zefan \u003clizf@cn.fujitsu.com\u003e\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\n" }, { "commit": "79173bf556417a737e9d2e096e0788452ec30a61", "tree": "c27a263ce2efae15ad7b045f60cd28a0b2390862", "parents": [ "64fbcd162819bddaf0d99e78b16371b655aa5dee" ], "author": { "name": "Xiao Guangrong", "email": "xiaoguangrong@cn.fujitsu.com", "time": "Thu Jul 16 14:17:11 2009 +0800" }, "committer": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Fri Jul 17 01:44:10 2009 -0400" }, "message": "tracing/trace_stack: Cleanup for trace_lookup_stack()\n\nWe can directly use %pF input format instead of sprint_symbol()\nand %s input format.\n\nSigned-off-by: Xiao Guangrong \u003cxiaoguangrong@cn.fujitsu.com\u003e\nReviewed-by: Li Zefan \u003clizf@cn.fujitsu.com\u003e\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\n" }, { "commit": "64fbcd162819bddaf0d99e78b16371b655aa5dee", "tree": "abc34dd23386f13675502455d99d868b9b63173e", "parents": [ "da706d8bc833e7153622435560422e653bdb2e94" ], "author": { "name": "Xiao Guangrong", "email": "xiaoguangrong@cn.fujitsu.com", "time": "Wed Jul 15 12:32:15 2009 +0800" }, "committer": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Fri Jul 17 00:37:53 2009 -0400" }, "message": "tracing/function: Simplify __ftrace_replace_code()\n\nRewrite the __ftrace_replace_code() function, simplify it, but don\u0027t\nchange the code\u0027s logic.\n\nFirst, we get the state we want to set, if the record has the same\nstate, then do nothing, otherwise enable/disable it.\n\nSigned-off-by: Xiao Guangrong \u003cxiaoguangrong@cn.fujitsu.com\u003e\nReviewed-by: Li Zefan \u003clizf@cn.fujitsu.com\u003e\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\n" }, { "commit": "04aef32d39cc4ef80087c0ce8ed113c6d64f1a6b", "tree": "fb6e1231d7ac8fb38cf514c0c6107291234228d9", "parents": [ "4b0a84043e0c14088958fddb62f416d050368011" ], "author": { "name": "Xiao Guangrong", "email": "xiaoguangrong@cn.fujitsu.com", "time": "Wed Jul 15 12:29:06 2009 +0800" }, "committer": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Thu Jul 16 23:34:32 2009 -0400" }, "message": "tracing/function: Fix the return value of ftrace_trace_onoff_callback()\n\nftrace_trace_onoff_callback() will return an error even if we do the\nright operation, for example:\n\n # echo _spin_*:traceon:10 \u003e set_ftrace_filter\n -bash: echo: write error: Invalid argument\n # cat set_ftrace_filter\n #### all functions enabled ####\n _spin_trylock_bh:traceon:count\u003d10\n _spin_unlock_irq:traceon:count\u003d10\n _spin_unlock_bh:traceon:count\u003d10\n _spin_lock_irq:traceon:count\u003d10\n _spin_unlock:traceon:count\u003d10\n _spin_trylock:traceon:count\u003d10\n _spin_unlock_irqrestore:traceon:count\u003d10\n _spin_lock_irqsave:traceon:count\u003d10\n _spin_lock_bh:traceon:count\u003d10\n _spin_lock:traceon:count\u003d10\n\nWe want to set _spin_*:traceon:10 to set_ftrace_filter, it complains\nwith \"Invalid argument\", but the operation is successful.\n\nThis is because ftrace_process_regex() returns the number of functions that\nmatched the pattern. If the number is not 0, this value is returned\nby ftrace_regex_write() whereas we want to return the number of bytes\nvirtually written.\nAlso the file offset pointer is not updated in this case.\n\nIf the number of matched functions is lower than the number of bytes written\nby the user, this results to a reprocessing of the string given by the user with\na lower size, leading to a malformed ftrace regex and then a -EINVAL returned.\n\nSo, this patch fixes it by returning 0 if no error occured.\nThe fix also applies on 2.6.30\n\nSigned-off-by: Xiao Guangrong \u003cxiaoguangrong@cn.fujitsu.com\u003e\nReviewed-by: Li Zefan \u003clizf@cn.fujitsu.com\u003e\nCc: stable@kernel.org\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\n" }, { "commit": "da706d8bc833e7153622435560422e653bdb2e94", "tree": "0da824f6db67ce361976ef3b4d5a7212ea92619b", "parents": [ "e202687927c132b1e1ff36b526b5e78ac33de840" ], "author": { "name": "Lai Jiangshan", "email": "laijs@cn.fujitsu.com", "time": "Wed Jul 15 16:27:30 2009 +0800" }, "committer": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Thu Jul 16 18:46:47 2009 -0400" }, "message": "ring_buffer: Fix warning while ignoring cmpxchg return value\n\nkernel/trace/ring_buffer.c: In function \u0027rb_tail_page_update\u0027:\nkernel/trace/ring_buffer.c:849: warning: value computed is not used\nkernel/trace/ring_buffer.c:850: warning: value computed is not used\n\nAdd \"(void)\"s to fix this warning, because we don\u0027t need here to handle\nthe fail case of cmpxchg, it\u0027s fine if an interrupt already did the\njob.\n\nChanged from V1:\n Add a comment(which is written by Steven) for it.\n\nSigned-off-by: Lai Jiangshan \u003claijs@cn.fujitsu.com\u003e\nAcked-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\n" }, { "commit": "6ab5d668b131d3c5416f6df1d3ca95b82d4fe8a2", "tree": "dc5cd05361845a431c1388f83f913e4610a2dfca", "parents": [ "d0b6e04a4cd8360e3c9c419f7c30a3081a0c142a" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Thu Jun 04 00:55:45 2009 -0400" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Jul 13 11:01:10 2009 +0200" }, "message": "tracing/function-profiler: do not free per cpu variable stat\n\nThe per cpu variable stat is freeded if we fail to allocate a name\non start up. This was due to stat at first being allocated in the\ninitial design. But since then, it has become a static per cpu variable\nbut the free on error was not removed.\n\nAlso added __init annotation to the function that this is in.\n\n[ Impact: prevent possible memory corruption on low mem at boot up ]\n\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "405f55712dfe464b3240d7816cc4fe4174831be2", "tree": "96c425ea7fa8b31058b8f83a433c5e5265c8ebc7", "parents": [ "f9fabcb58a6d26d6efde842d1703ac7cfa9427b6" ], "author": { "name": "Alexey Dobriyan", "email": "adobriyan@gmail.com", "time": "Sat Jul 11 22:08:37 2009 +0400" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Sun Jul 12 12:22:34 2009 -0700" }, "message": "headers: smp_lock.h redux\n\n* Remove smp_lock.h from files which don\u0027t need it (including some headers!)\n* Add smp_lock.h to files which do need it\n* Make smp_lock.h include conditional in hardirq.h\n It\u0027s needed only for one kernel_locked() usage which is under CONFIG_PREEMPT\n\n This will make hardirq.h inclusion cheaper for every PREEMPT\u003dn config\n (which includes allmodconfig/allyesconfig, BTW)\n\nSigned-off-by: Alexey Dobriyan \u003cadobriyan@gmail.com\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "e202687927c132b1e1ff36b526b5e78ac33de840", "tree": "8c1cadd560913e41237af48fc0058a9ed640dda7", "parents": [ "a35780005eb256eb5ec83ffcc802967295887a45", "8b2c70d1e43074cc06afe99b0de12b686d9c9d02" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Fri Jul 10 13:30:06 2009 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Fri Jul 10 13:30:06 2009 +0200" }, "message": "Merge branch \u0027tip/tracing/ring-buffer-3\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-2.6-trace into tracing/core\n" }, { "commit": "a35780005eb256eb5ec83ffcc802967295887a45", "tree": "187244378069f3dd02b23e706d10a3054837f3ba", "parents": [ "d8ea37d5de58d35a39d0b4e7d209751aaa1b8174" ], "author": { "name": "Lai Jiangshan", "email": "laijs@cn.fujitsu.com", "time": "Mon Jul 06 16:10:23 2009 +0800" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Fri Jul 10 12:14:07 2009 +0200" }, "message": "tracing/workqueues: Add refcnt to struct cpu_workqueue_stats\n\nThe stat entries can be freed when the stat file is being read.\nThe worse is, the ptr can be freed immediately after it\u0027s returned\nfrom workqueue_stat_start/next().\n\nAdd a refcnt to struct cpu_workqueue_stats to avoid use-after-free.\n\nSigned-off-by: Lai Jiangshan \u003claijs@cn.fujitsu.com\u003e\nSigned-off-by: Li Zefan \u003clizf@cn.fujitsu.com\u003e\nAcked-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Steven Rostedt \u003crostedt@goodmis.org\u003e\nLKML-Reference: \u003c4A51B16F.6010608@cn.fujitsu.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "d8ea37d5de58d35a39d0b4e7d209751aaa1b8174", "tree": "a64ffb2c844ad0f0e99616a69e6f548370d31665", "parents": [ "80098c200e2ee3b4c86a9d1e156dbcd05380e08f" ], "author": { "name": "Lai Jiangshan", "email": "laijs@cn.fujitsu.com", "time": "Mon Jul 06 16:10:18 2009 +0800" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Fri Jul 10 12:14:05 2009 +0200" }, "message": "tracing/stat: Add stat_release() callback\n\nAdd stat_release() callback to struct tracer_stat, so a stat tracer\ncan release it\u0027s entries after the stat file has been read out.\n\nSigned-off-by: Lai Jiangshan \u003claijs@cn.fujitsu.com\u003e\nSigned-off-by: Li Zefan \u003clizf@cn.fujitsu.com\u003e\nCc: Lai Jiangshan \u003claijs@cn.fujitsu.com\u003e\nCc: Steven Rostedt \u003crostedt@goodmis.org\u003e\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nLKML-Reference: \u003c4A51B16A.6020708@cn.fujitsu.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "80098c200e2ee3b4c86a9d1e156dbcd05380e08f", "tree": "25a216567c02e94a9f4203ddc452fb24bb200176", "parents": [ "6a167c655858cbec4175532fd00417661c87f149" ], "author": { "name": "Li Zefan", "email": "lizf@cn.fujitsu.com", "time": "Mon Jul 06 16:15:04 2009 +0800" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Fri Jul 10 12:09:04 2009 +0200" }, "message": "kmemtrace: Rename some functions\n\nSo we have:\n\n - kmemtrace_print_alloc/free() for kmemtrace default output\n\n - kmemtrace_print_alloc/free_user() for binary output used\n by kmemtrace-user.\n\nSuggested-by: Eduard - Gabriel Munteanu \u003ceduard.munteanu@linux360.ro\u003e\nSigned-off-by: Li Zefan \u003clizf@cn.fujitsu.com\u003e\nAcked-by: Pekka Enberg \u003cpenberg@cs.helsinki.fi\u003e\nCc: Steven Rostedt \u003crostedt@goodmis.org\u003e\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nLKML-Reference: \u003c4A51B288.70505@cn.fujitsu.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "6a167c655858cbec4175532fd00417661c87f149", "tree": "f177c7a7ea5a6c949bf7f4cc37cebb5665e38ed1", "parents": [ "68baafcfc46074c4bb4e4c3115c2c76a8a85f37d" ], "author": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Thu Jul 09 04:46:30 2009 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Fri Jul 10 12:07:20 2009 +0200" }, "message": "tracing/kmemtrace: Use the %pf format\n\nRemove the obsolete seq_print_ip_sym() usage and replace it\nby the %pf format in order to print function symbols.\n\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nReviewed-by: Li Zefan \u003clizf@cn.fujitsu.com\u003e\nCc: Steven Rostedt \u003crostedt@goodmis.org\u003e\nCc: Lai Jiangshan \u003claijs@cn.fujitsu.com\u003e\nCc: Pekka Enberg \u003cpenberg@cs.helsinki.fi\u003e\nCc: Eduard - Gabriel Munteanu \u003ceduard.munteanu@linux360.ro\u003e\nLKML-Reference: \u003c1247107590-6428-3-git-send-email-fweisbec@gmail.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "68baafcfc46074c4bb4e4c3115c2c76a8a85f37d", "tree": "b3790c3fcd871d981c09932fb8ce6af2d36c070c", "parents": [ "dc82ec98a4727fd51b77e92d05fe7d2db3dcc11c" ], "author": { "name": "Frederic Weisbecker", "email": "fweisbec@gmail.com", "time": "Thu Jul 09 04:46:29 2009 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Fri Jul 10 12:07:19 2009 +0200" }, "message": "tracing/function-graph-tracer: Use the %pf format\n\nRemove the obsolete seq_print_ip_sym() usage and replace it\nby the %pf format in order to print function symbols.\n\nSigned-off-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nReviewed-by: Li Zefan \u003clizf@cn.fujitsu.com\u003e\nCc: Steven Rostedt \u003crostedt@goodmis.org\u003e\nCc: Lai Jiangshan \u003claijs@cn.fujitsu.com\u003e\nLKML-Reference: \u003c1247107590-6428-2-git-send-email-fweisbec@gmail.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" } ], "next": "dc82ec98a4727fd51b77e92d05fe7d2db3dcc11c" }